_ZN8PfxEntryC2EP8AffixMgr: 99| 8| : pmyMgr(pmgr) 100| 8| , next(nullptr) 101| 8| , nexteq(nullptr) 102| 8| , nextne(nullptr) 103| 8| , flgnxt(nullptr) {} _ZN8PfxEntry3addEPKcm: 106| 2|std::string PfxEntry::add(const char* word, size_t len) { 107| 2| std::string result; 108| 2| if ((len > strip.size() || (len == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (108:7): [True: 2, False: 0] | Branch (108:8): [True: 2, False: 0] | Branch (108:31): [True: 0, False: 0] | Branch (108:43): [True: 0, False: 0] ------------------ 109| 2| (len >= numconds) && test_condition(word) && ------------------ | Branch (109:7): [True: 2, False: 0] | Branch (109:28): [True: 2, False: 0] ------------------ 110| 2| (strip.empty() || ------------------ | Branch (110:8): [True: 2, False: 0] ------------------ 111| 2| (len >= strip.size() && strncmp(word, strip.c_str(), strip.size()) == 0))) { ------------------ | Branch (111:8): [True: 0, False: 0] | Branch (111:31): [True: 0, False: 0] ------------------ 112| | /* we have a match so add prefix */ 113| 2| result.assign(appnd); 114| 2| result.append(word + strip.size()); 115| 2| } 116| 2| return result; 117| 2|} _ZN8PfxEntry9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 275| 1.40M| AffixScratch& scratch) { 276| 1.40M| struct hentry* he; // hash entry of root word or NULL 277| | 278| 1.40M| TraceCtx* t = trace_on(scratch.trace); 279| 1.40M| if (t) ------------------ | Branch (279:7): [True: 0, False: 1.40M] ------------------ 280| 0| trace_affix(*t, "pfx", pmyMgr, *this); 281| 1.40M| TraceScope trace_depth(t); 282| | 283| | // on entry prefix is 0 length or already matches the beginning of the word. 284| | // So if the remaining root word has positive length 285| | // and if there are enough chars in root word and added back strip chars 286| | // to meet the number of characters conditions, then test it 287| | 288| 1.40M| int tmpl = len - appnd.size(); // length of tmpword 289| | 290| 1.40M| if (tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) { ------------------ | Branch (290:7): [True: 1.40M, False: 3.43k] | Branch (290:20): [True: 3.43k, False: 0] | Branch (290:33): [True: 0, False: 3.43k] ------------------ 291| | // generate new root word by removing prefix and adding 292| | // back any characters that would have been stripped 293| | 294| 1.40M| std::string& tmpword = scratch.pfx_check_word; 295| 1.40M| tmpword.assign(strip); 296| 1.40M| tmpword.append(word, start + appnd.size(), tmpl); 297| | 298| | // now make sure all of the conditions on characters 299| | // are met. Please see the appendix at the end of 300| | // this file for more info on exactly what is being 301| | // tested 302| | 303| | // if all conditions are met then check if resulting 304| | // root word in the dictionary 305| | 306| 1.40M| if (t) ------------------ | Branch (306:9): [True: 0, False: 1.40M] ------------------ 307| 0| trace(*t, "stem \"%s\"", tmpword.c_str()); 308| | 309| 1.40M| bool passes = test_condition(tmpword); 310| 1.40M| if (t) ------------------ | Branch (310:9): [True: 0, False: 1.40M] ------------------ 311| 0| trace(*t, "test condition cond=\"%s\" on \"%s\" -> %s", 312| 0| get_condition().c_str(), 313| 0| tmpword.c_str(), passes ? "pass" : "fail"); ------------------ | Branch (313:30): [True: 0, False: 0] ------------------ 314| | 315| 1.40M| if (passes) { ------------------ | Branch (315:9): [True: 16.0k, False: 1.38M] ------------------ 316| 16.0k| tmpl += strip.size(); 317| 16.0k| if ((he = pmyMgr->lookup(tmpword.c_str(), tmpword.size())) != nullptr) { ------------------ | Branch (317:11): [True: 0, False: 16.0k] ------------------ 318| 0| if (t) ------------------ | Branch (318:13): [True: 0, False: 0] ------------------ 319| 0| trace(*t, "lookup \"%s\" -> entry \"%s\" flags=%s", tmpword.c_str(), 320| 0| he->word, trace_flags(pmyMgr, he->astr, he->alen).c_str()); 321| 0| do { 322| 0| if (applies_to(he, needflag, t)) { ------------------ | Branch (322:15): [True: 0, False: 0] ------------------ 323| 0| if (t) ------------------ | Branch (323:17): [True: 0, False: 0] ------------------ 324| 0| trace(*t, "accept"); 325| 0| return he; 326| 0| } 327| 0| he = he->next_homonym; // check homonyms 328| 0| if (t) { ------------------ | Branch (328:15): [True: 0, False: 0] ------------------ 329| 0| if (he) ------------------ | Branch (329:17): [True: 0, False: 0] ------------------ 330| 0| trace(*t, "lookup \"%s\" -> entry \"%s\" flags=%s", 331| 0| tmpword.c_str(), he->word, 332| 0| trace_flags(pmyMgr, he->astr, he->alen).c_str()); 333| 0| else 334| 0| trace(*t, "lookup \"%s\" -> no more homonyms", tmpword.c_str()); 335| 0| } 336| 0| } while (he); ------------------ | Branch (336:18): [True: 0, False: 0] ------------------ 337| 16.0k| } else if (t) { ------------------ | Branch (337:18): [True: 0, False: 16.0k] ------------------ 338| 0| trace(*t, "lookup \"%s\" -> miss", tmpword.c_str()); 339| 0| } 340| | 341| | // prefix matched but no root word was found 342| | // if aeXPRODUCT is allowed, try again but now 343| | // ross checked combined with a suffix 344| | 345| | // if ((opts & aeXPRODUCT) && in_compound) { 346| 16.0k| if ((opts & aeXPRODUCT)) { ------------------ | | 65| 16.0k|#define aeXPRODUCT (1 << 0) ------------------ | Branch (346:11): [True: 16.0k, False: 0] ------------------ 347| 16.0k| he = pmyMgr->suffix_check(tmpword, 0, tmpl, aeXPRODUCT, this, ------------------ | | 65| 16.0k|#define aeXPRODUCT (1 << 0) ------------------ 348| 16.0k| scratch, FLAG_NULL, needflag, in_compound); ------------------ | | 99| 16.0k|#define FLAG_NULL 0x00 ------------------ 349| 16.0k| if (he) ------------------ | Branch (349:13): [True: 0, False: 16.0k] ------------------ 350| 0| return he; 351| 16.0k| } 352| 16.0k| } 353| 1.40M| } else if (t) { ------------------ | Branch (353:14): [True: 0, False: 3.43k] ------------------ 354| 0| trace(*t, "test length have=%d -> fail, nothing would be left of the word", 355| 0| tmpl); 356| 0| } 357| 1.40M| return nullptr; 358| 1.40M|} _ZN8PfxEntry12check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 366| 1.40M| AffixScratch& scratch) { 367| | // on entry prefix is 0 length or already matches the beginning of the word. 368| | // So if the remaining root word has positive length 369| | // and if there are enough chars in root word and added back strip chars 370| | // to meet the number of characters conditions, then test it 371| | 372| 1.40M| int tmpl = len - appnd.size(); // length of tmpword 373| | 374| 1.40M| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (374:8): [True: 1.40M, False: 3.33k] | Branch (374:21): [True: 3.33k, False: 0] | Branch (374:34): [True: 0, False: 3.33k] ------------------ 375| 1.40M| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (375:7): [True: 1.35M, False: 46.0k] ------------------ 376| | // generate new root word by removing prefix and adding 377| | // back any characters that would have been stripped 378| | 379| 1.35M| std::string& tmpword = scratch.pfx_check_twosfx; 380| 1.35M| tmpword.assign(strip); 381| 1.35M| tmpword.append(word, start + appnd.size(), tmpl); 382| | 383| | // now make sure all of the conditions on characters 384| | // are met. Please see the appendix at the end of 385| | // this file for more info on exactly what is being 386| | // tested 387| | 388| | // if all conditions are met then check if resulting 389| | // root word in the dictionary 390| | 391| 1.35M| if (test_condition(tmpword)) { ------------------ | Branch (391:9): [True: 12.1k, False: 1.34M] ------------------ 392| 12.1k| tmpl += strip.size(); 393| | 394| | // prefix matched but no root word was found 395| | // if aeXPRODUCT is allowed, try again but now 396| | // cross checked combined with a suffix 397| | 398| 12.1k| if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 65| 12.1k|#define aeXPRODUCT (1 << 0) ------------------ if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 76| 12.1k|#define IN_CPD_BEGIN 1 ------------------ | Branch (398:11): [True: 12.1k, False: 0] | Branch (398:34): [True: 12.1k, False: 0] ------------------ 399| | // hash entry of root word or NULL 400| 12.1k| struct hentry* he = pmyMgr->suffix_check_twosfx(tmpword, 0, tmpl, aeXPRODUCT, this, ------------------ | | 65| 12.1k|#define aeXPRODUCT (1 << 0) ------------------ 401| 12.1k| scratch, needflag); 402| 12.1k| if (he) ------------------ | Branch (402:13): [True: 0, False: 12.1k] ------------------ 403| 0| return he; 404| 12.1k| } 405| 12.1k| } 406| 1.35M| } 407| 1.40M| return nullptr; 408| 1.40M|} _ZN8PfxEntry18check_twosfx_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 416| 702| AffixScratch& scratch) { 417| 702| std::string result; 418| | // on entry prefix is 0 length or already matches the beginning of the word. 419| | // So if the remaining root word has positive length 420| | // and if there are enough chars in root word and added back strip chars 421| | // to meet the number of characters conditions, then test it 422| 702| int tmpl = len - appnd.size(); // length of tmpword 423| | 424| 702| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (424:8): [True: 702, False: 0] | Branch (424:21): [True: 0, False: 0] | Branch (424:34): [True: 0, False: 0] ------------------ 425| 702| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (425:7): [True: 618, False: 84] ------------------ 426| | // generate new root word by removing prefix and adding 427| | // back any characters that would have been stripped 428| | 429| 618| std::string& tmpword = scratch.pfx_check_twosfx; 430| 618| tmpword.assign(strip); 431| 618| tmpword.append(word, start + appnd.size(), tmpl); 432| | 433| | // now make sure all of the conditions on characters 434| | // are met. Please see the appendix at the end of 435| | // this file for more info on exactly what is being 436| | // tested 437| | 438| | // if all conditions are met then check if resulting 439| | // root word in the dictionary 440| | 441| 618| if (test_condition(tmpword)) { ------------------ | Branch (441:9): [True: 0, False: 618] ------------------ 442| 0| tmpl += strip.size(); 443| | 444| | // prefix matched but no root word was found 445| | // if aeXPRODUCT is allowed, try again but now 446| | // ross checked combined with a suffix 447| | 448| 0| if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 76| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (448:11): [True: 0, False: 0] | Branch (448:34): [True: 0, False: 0] ------------------ 449| 0| result = pmyMgr->suffix_check_twosfx_morph(tmpword, 0, tmpl, 450| 0| aeXPRODUCT, ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ 451| 0| this, scratch, needflag); 452| 0| } 453| 0| } 454| 618| } 455| 702| return result; 456| 702|} _ZN8PfxEntry11check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 464| 704| AffixScratch& scratch) { 465| 704| std::string result; 466| | 467| | // on entry prefix is 0 length or already matches the beginning of the word. 468| | // So if the remaining root word has positive length 469| | // and if there are enough chars in root word and added back strip chars 470| | // to meet the number of characters conditions, then test it 471| | 472| 704| int tmpl = len - appnd.size(); // length of tmpword 473| | 474| 704| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (474:8): [True: 704, False: 0] | Branch (474:21): [True: 0, False: 0] | Branch (474:34): [True: 0, False: 0] ------------------ 475| 704| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (475:7): [True: 620, False: 84] ------------------ 476| | // generate new root word by removing prefix and adding 477| | // back any characters that would have been stripped 478| | 479| 620| std::string& tmpword = scratch.pfx_check_word; 480| 620| tmpword.assign(strip); 481| 620| tmpword.append(word, start + appnd.size(), tmpl); 482| | 483| | // now make sure all of the conditions on characters 484| | // are met. Please see the appendix at the end of 485| | // this file for more info on exactly what is being 486| | // tested 487| | 488| | // if all conditions are met then check if resulting 489| | // root word in the dictionary 490| | 491| 620| if (test_condition(tmpword)) { ------------------ | Branch (491:9): [True: 2, False: 618] ------------------ 492| 2| tmpl += strip.size(); 493| 2| struct hentry* he; // hash entry of root word or NULL 494| 2| if ((he = pmyMgr->lookup(tmpword.c_str(), tmpword.size())) != nullptr) { ------------------ | Branch (494:11): [True: 0, False: 2] ------------------ 495| 0| do { 496| 0| if (applies_to(he, needflag, nullptr)) { ------------------ | Branch (496:15): [True: 0, False: 0] ------------------ 497| 0| if (morphcode) { ------------------ | Branch (497:17): [True: 0, False: 0] ------------------ 498| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 499| 0| result.append(morphcode); 500| 0| } else 501| 0| result.append(getKey()); 502| 0| if (!HENTRY_FIND(he, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (502:17): [True: 0, False: 0] ------------------ 503| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 504| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 505| 0| result.append(HENTRY_WORD(he)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 506| 0| } 507| | // store the pointer of the hash entry 508| 0| if (HENTRY_DATA(he)) { ------------------ | Branch (508:17): [True: 0, False: 0] ------------------ 509| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 510| 0| result.append(HENTRY_DATA2(he)); 511| 0| } else { 512| | // return with debug information 513| 0| std::string flag = pmyMgr->encode_flag(getFlag()); 514| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 515| 0| result.append(MORPH_FLAG); ------------------ | | 117| 0|#define MORPH_FLAG "fl:" ------------------ 516| 0| result.append(flag); 517| 0| } 518| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 519| 0| } 520| 0| he = he->next_homonym; 521| 0| } while (he); ------------------ | Branch (521:18): [True: 0, False: 0] ------------------ 522| 0| } 523| | 524| | // prefix matched but no root word was found 525| | // if aeXPRODUCT is allowed, try again but now 526| | // ross checked combined with a suffix 527| | 528| 2| if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 65| 2|#define aeXPRODUCT (1 << 0) ------------------ if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 76| 2|#define IN_CPD_BEGIN 1 ------------------ | Branch (528:11): [True: 2, False: 0] | Branch (528:34): [True: 2, False: 0] ------------------ 529| 2| std::string st = pmyMgr->suffix_check_morph(tmpword, 0, tmpl, aeXPRODUCT, this, ------------------ | | 65| 2|#define aeXPRODUCT (1 << 0) ------------------ 530| 2| scratch, FLAG_NULL, needflag); ------------------ | | 99| 2|#define FLAG_NULL 0x00 ------------------ 531| 2| if (!st.empty()) { ------------------ | Branch (531:13): [True: 0, False: 2] ------------------ 532| 0| result.append(st); 533| 0| } 534| 2| } 535| 2| } 536| 620| } 537| | 538| 704| return result; 539| 704|} _ZN8SfxEntryC2EP8AffixMgr: 542| 34| : pmyMgr(pmgr) // register affix manager 543| 34| , next(nullptr) 544| 34| , nexteq(nullptr) 545| 34| , nextne(nullptr) 546| 34| , flgnxt(nullptr) 547| 34| , l_morph(nullptr) 548| 34| , r_morph(nullptr) 549| 34| , eq_morph(nullptr) {} _ZN8SfxEntry3addEPKcm: 579| 27|std::string SfxEntry::add(const char* word, size_t len) { 580| 27| std::string result; 581| | /* make sure all conditions match */ 582| 27| if ((len > strip.size() || (len == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (582:8): [True: 27, False: 0] | Branch (582:31): [True: 0, False: 0] | Branch (582:43): [True: 0, False: 0] ------------------ 583| 27| (len >= numconds) && test_condition(word + len, word) && ------------------ | Branch (583:7): [True: 27, False: 0] | Branch (583:28): [True: 27, False: 0] ------------------ 584| 27| (strip.empty() || ------------------ | Branch (584:8): [True: 27, False: 0] ------------------ 585| 27| (len >= strip.size() && strcmp(word + len - strip.size(), strip.c_str()) == 0))) { ------------------ | Branch (585:9): [True: 0, False: 0] | Branch (585:32): [True: 0, False: 0] ------------------ 586| 27| result.assign(word, len); 587| | /* we have a match so add suffix */ 588| 27| result.replace(len - strip.size(), std::string::npos, appnd); 589| 27| } 590| 27| return result; 591| 27|} _ZNK8SfxEntry10applies_toEPK6hentryiP8PfxEntrytttPK8TraceCtx: 731| 25| const TraceCtx* t) const { 732| | // the suffix flag is either on the entry itself, or on a prefix that enables 733| | // this suffix 734| 25| bool in_dic = TESTAFF(he->astr, aflag, he->alen); ------------------ | | 102| 25|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ 735| 25| bool in_prefix = ep && ep->getCont() && ------------------ | Branch (735:20): [True: 0, False: 25] | Branch (735:26): [True: 0, False: 0] ------------------ 736| 0| TESTAFF(ep->getCont(), aflag, ep->getContLen()); ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 737| 25| if (t) { ------------------ | Branch (737:7): [True: 0, False: 25] ------------------ 738| 0| if (in_prefix && !in_dic) ------------------ | Branch (738:9): [True: 0, False: 0] | Branch (738:22): [True: 0, False: 0] ------------------ 739| 0| trace_test(*t, "sfx-aflag", pmyMgr, aflag, "pfx-cont", ep->getCont(), 740| 0| ep->getContLen(), "pass, the prefix enables this suffix"); 741| 0| else 742| 0| trace_test(*t, "sfx-aflag", pmyMgr, aflag, "dic", he->astr, he->alen, 743| 0| in_dic ? "pass" : "fail"); ------------------ | Branch (743:18): [True: 0, False: 0] ------------------ 744| 0| } 745| 25| if (!in_dic && !in_prefix) ------------------ | Branch (745:7): [True: 25, False: 0] | Branch (745:18): [True: 25, False: 0] ------------------ 746| 25| return false; 747| | 748| | // the prefix and the suffix have to be allowed to meet 749| 0| if ((optflags & aeXPRODUCT) != 0) { ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ | Branch (749:7): [True: 0, False: 0] ------------------ 750| 0| FLAG pflag = ep ? ep->getFlag() : FLAG_NULL; ------------------ | | 98| 0|#define FLAG unsigned short ------------------ FLAG pflag = ep ? ep->getFlag() : FLAG_NULL; ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ | Branch (750:18): [True: 0, False: 0] ------------------ 751| 0| in_dic = ep && TESTAFF(he->astr, pflag, he->alen); ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (751:14): [True: 0, False: 0] ------------------ 752| 0| bool in_cont = contclass && ep && TESTAFF(contclass, pflag, contclasslen); ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (752:20): [True: 0, False: 0] | Branch (752:33): [True: 0, False: 0] ------------------ 753| 0| if (t) { ------------------ | Branch (753:9): [True: 0, False: 0] ------------------ 754| 0| if (in_cont && !in_dic) ------------------ | Branch (754:11): [True: 0, False: 0] | Branch (754:22): [True: 0, False: 0] ------------------ 755| 0| trace_test(*t, "xprod", pmyMgr, pflag, "sfx-cont", contclass, 756| 0| contclasslen, "pass, this suffix enables the prefix"); 757| 0| else 758| 0| trace_test(*t, "xprod", pmyMgr, pflag, "dic", he->astr, he->alen, 759| 0| in_dic ? "pass" ------------------ | Branch (759:20): [True: 0, False: 0] ------------------ 760| 0| : "fail, the stem does not take the prefix as well"); 761| 0| } 762| 0| if (!in_dic && !in_cont) ------------------ | Branch (762:9): [True: 0, False: 0] | Branch (762:20): [True: 0, False: 0] ------------------ 763| 0| return false; 764| 0| } 765| | 766| | // handle cont. class 767| 0| if (cclass) { ------------------ | Branch (767:7): [True: 0, False: 0] ------------------ 768| 0| bool ok = contclass && TESTAFF(contclass, cclass, contclasslen); ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (768:15): [True: 0, False: 0] ------------------ 769| 0| if (t) ------------------ | Branch (769:9): [True: 0, False: 0] ------------------ 770| 0| trace_test(*t, "cclass", pmyMgr, cclass, "sfx-cont", contclass, 771| 0| contclasslen, 772| 0| ok ? "pass" : "fail, this suffix does not continue the last one"); ------------------ | Branch (772:18): [True: 0, False: 0] ------------------ 773| 0| if (!ok) ------------------ | Branch (773:9): [True: 0, False: 0] ------------------ 774| 0| return false; 775| 0| } 776| | 777| | // check only in compound homonyms (bad flags) 778| 0| if (badflag) { ------------------ | Branch (778:7): [True: 0, False: 0] ------------------ 779| 0| bool ok = !TESTAFF(he->astr, badflag, he->alen); ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ 780| 0| if (t) ------------------ | Branch (780:9): [True: 0, False: 0] ------------------ 781| 0| trace_test(*t, "badflag", pmyMgr, badflag, "dic", he->astr, he->alen, 782| 0| ok ? "pass" : "fail, the stem has a flag this context forbids"); ------------------ | Branch (782:18): [True: 0, False: 0] ------------------ 783| 0| if (!ok) ------------------ | Branch (783:9): [True: 0, False: 0] ------------------ 784| 0| return false; 785| 0| } 786| | 787| | // handle required flag 788| 0| if (needflag) { ------------------ | Branch (788:7): [True: 0, False: 0] ------------------ 789| 0| in_dic = TESTAFF(he->astr, needflag, he->alen); ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ 790| 0| bool in_cont = contclass && TESTAFF(contclass, needflag, contclasslen); ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (790:20): [True: 0, False: 0] ------------------ 791| 0| if (t) { ------------------ | Branch (791:9): [True: 0, False: 0] ------------------ 792| 0| if (in_cont && !in_dic) ------------------ | Branch (792:11): [True: 0, False: 0] | Branch (792:22): [True: 0, False: 0] ------------------ 793| 0| trace_test(*t, "needflag", pmyMgr, needflag, "sfx-cont", contclass, 794| 0| contclasslen, "pass"); 795| 0| else 796| 0| trace_test(*t, "needflag", pmyMgr, needflag, "dic", he->astr, he->alen, 797| 0| in_dic ? "pass" ------------------ | Branch (797:20): [True: 0, False: 0] ------------------ 798| 0| : "fail, the stem lacks the flag the caller asked for"); 799| 0| } 800| 0| if (!in_dic && !in_cont) ------------------ | Branch (800:9): [True: 0, False: 0] | Branch (800:20): [True: 0, False: 0] ------------------ 801| 0| return false; 802| 0| } 803| | 804| 0| return true; 805| 0|} _ZN8SfxEntry9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntrytttR12AffixScratch: 816| 49.1k| AffixScratch& scratch) { 817| 49.1k| struct hentry* he; // hash entry pointer 818| 49.1k| PfxEntry* ep = ppfx; 819| | 820| 49.1k| TraceCtx* t = trace_on(scratch.trace); 821| 49.1k| if (t) ------------------ | Branch (821:7): [True: 0, False: 49.1k] ------------------ 822| 0| trace_affix(*t, "sfx", pmyMgr, *this); 823| 49.1k| TraceScope trace_depth(t); 824| | 825| | // if this suffix is being cross checked with a prefix 826| | // but it does not support cross products skip it 827| | 828| 49.1k| if (((optflags & aeXPRODUCT) != 0) && ((opts & aeXPRODUCT) == 0)) { ------------------ | | 65| 49.1k|#define aeXPRODUCT (1 << 0) ------------------ if (((optflags & aeXPRODUCT) != 0) && ((opts & aeXPRODUCT) == 0)) { ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ | Branch (828:7): [True: 0, False: 49.1k] | Branch (828:41): [True: 0, False: 0] ------------------ 829| 0| if (t) ------------------ | Branch (829:9): [True: 0, False: 0] ------------------ 830| 0| trace(*t, "test xprod -> fail, this suffix class does not cross with a" 831| 0| " prefix"); 832| 0| return nullptr; 833| 0| } 834| | 835| | // upon entry suffix is 0 length or already matches the end of the word. 836| | // So if the remaining root word has positive length 837| | // and if there are enough chars in root word and added back strip chars 838| | // to meet the number of characters conditions, then test it 839| | 840| 49.1k| int tmpl = len - appnd.size(); // length of tmpword 841| | // the second condition is not enough for UTF-8 strings 842| | // it checked in test_condition() 843| | 844| 49.1k| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (844:8): [True: 47.7k, False: 1.40k] | Branch (844:21): [True: 1.40k, False: 0] | Branch (844:34): [True: 0, False: 1.40k] ------------------ 845| 47.7k| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (845:7): [True: 47.7k, False: 0] ------------------ 846| | // generate new root word by removing suffix and adding 847| | // back any characters that would have been stripped or 848| | // or null terminating the shorter string 849| | 850| 47.7k| std::string& tmpword = scratch.sfx_check_word; 851| 47.7k| tmpword.assign(word, start, tmpl); 852| 47.7k| if (!strip.empty()) { ------------------ | Branch (852:9): [True: 0, False: 47.7k] ------------------ 853| 0| tmpword.append(strip); 854| 0| } 855| | 856| 47.7k| const char* beg = tmpword.c_str(); 857| 47.7k| const char* end = beg + tmpword.size(); 858| | 859| | // now make sure all of the conditions on characters 860| | // are met. Please see the appendix at the end of 861| | // this file for more info on exactly what is being 862| | // tested 863| | 864| | // if all conditions are met then check if resulting 865| | // root word in the dictionary 866| | 867| 47.7k| if (t) ------------------ | Branch (867:9): [True: 0, False: 47.7k] ------------------ 868| 0| trace(*t, "stem \"%s\"", tmpword.c_str()); 869| | 870| 47.7k| bool passes = test_condition(end, beg); 871| 47.7k| if (t) ------------------ | Branch (871:9): [True: 0, False: 47.7k] ------------------ 872| 0| trace(*t, "test condition cond=\"%s\" on \"%s\" -> %s", 873| 0| get_condition().c_str(), 874| 0| tmpword.c_str(), passes ? "pass" : "fail"); ------------------ | Branch (874:30): [True: 0, False: 0] ------------------ 875| | 876| 47.7k| if (passes) { ------------------ | Branch (876:9): [True: 47.7k, False: 0] ------------------ 877| |#ifdef SZOSZABLYA_POSSIBLE_ROOTS 878| | fprintf(stdout, "%s %s %c\n", word.c_str() + start, beg, aflag); 879| |#endif 880| 47.7k| if ((he = pmyMgr->lookup(tmpword.c_str(), tmpword.size())) != nullptr) { ------------------ | Branch (880:11): [True: 25, False: 47.7k] ------------------ 881| 25| if (t) ------------------ | Branch (881:13): [True: 0, False: 25] ------------------ 882| 0| trace(*t, "lookup \"%s\" -> entry \"%s\" flags=%s", tmpword.c_str(), 883| 0| he->word, trace_flags(pmyMgr, he->astr, he->alen).c_str()); 884| 25| do { 885| 25| if (applies_to(he, optflags, ep, cclass, needflag, badflag, t)) { ------------------ | Branch (885:15): [True: 0, False: 25] ------------------ 886| 0| if (t) ------------------ | Branch (886:17): [True: 0, False: 0] ------------------ 887| 0| trace(*t, "accept"); 888| 0| return he; 889| 0| } 890| 25| he = he->next_homonym; // check homonyms 891| 25| if (t) { ------------------ | Branch (891:15): [True: 0, False: 25] ------------------ 892| 0| if (he) ------------------ | Branch (892:17): [True: 0, False: 0] ------------------ 893| 0| trace(*t, "lookup \"%s\" -> entry \"%s\" flags=%s", 894| 0| tmpword.c_str(), he->word, 895| 0| trace_flags(pmyMgr, he->astr, he->alen).c_str()); 896| 0| else 897| 0| trace(*t, "lookup \"%s\" -> no more homonyms", tmpword.c_str()); 898| 0| } 899| 25| } while (he); ------------------ | Branch (899:18): [True: 0, False: 25] ------------------ 900| 47.7k| } else if (t) { ------------------ | Branch (900:18): [True: 0, False: 47.7k] ------------------ 901| 0| trace(*t, "lookup \"%s\" -> miss", tmpword.c_str()); 902| 0| } 903| 47.7k| } 904| 47.7k| } else if (t) { ------------------ | Branch (904:14): [True: 0, False: 1.40k] ------------------ 905| 0| trace(*t, "test length have=%d need=%d -> fail, too little is left of the" 906| 0| " word to test", tmpl, (int)numconds); 907| 0| } 908| 49.1k| return nullptr; 909| 49.1k|} _ZN8SfxEntry12check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntrytR12AffixScratch: 918| 26.0k| AffixScratch& scratch) { 919| 26.0k| PfxEntry* ep = ppfx; 920| | 921| | // if this suffix is being cross checked with a prefix 922| | // but it does not support cross products skip it 923| | 924| 26.0k| if ((optflags & aeXPRODUCT) != 0 && (opts & aeXPRODUCT) == 0) ------------------ | | 65| 26.0k|#define aeXPRODUCT (1 << 0) ------------------ if ((optflags & aeXPRODUCT) != 0 && (opts & aeXPRODUCT) == 0) ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ | Branch (924:7): [True: 0, False: 26.0k] | Branch (924:39): [True: 0, False: 0] ------------------ 925| 0| return nullptr; 926| | 927| | // upon entry suffix is 0 length or already matches the end of the word. 928| | // So if the remaining root word has positive length 929| | // and if there are enough chars in root word and added back strip chars 930| | // to meet the number of characters conditions, then test it 931| | 932| 26.0k| int tmpl = len - appnd.size(); // length of tmpword 933| | 934| 26.0k| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (934:8): [True: 25.8k, False: 165] | Branch (934:21): [True: 165, False: 0] | Branch (934:34): [True: 0, False: 165] ------------------ 935| 25.8k| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (935:7): [True: 25.8k, False: 0] ------------------ 936| | // generate new root word by removing suffix and adding 937| | // back any characters that would have been stripped or 938| | // or null terminating the shorter string 939| | 940| 25.8k| std::string& tmpword = scratch.sfx_check_twosfx; 941| 25.8k| tmpword.assign(word, start); 942| 25.8k| tmpword.resize(tmpl); 943| 25.8k| tmpword.append(strip); 944| 25.8k| tmpl += strip.size(); 945| | 946| 25.8k| const char* beg = tmpword.c_str(); 947| 25.8k| const char* end = beg + tmpl; 948| | 949| | // now make sure all of the conditions on characters 950| | // are met. Please see the appendix at the end of 951| | // this file for more info on exactly what is being 952| | // tested 953| | 954| | // if all conditions are met then recall suffix_check 955| | 956| 25.8k| if (test_condition(end, beg)) { ------------------ | Branch (956:9): [True: 25.8k, False: 0] ------------------ 957| 25.8k| struct hentry* he; // hash entry pointer 958| 25.8k| if (ppfx) { ------------------ | Branch (958:11): [True: 0, False: 25.8k] ------------------ 959| | // handle conditional suffix 960| 0| if ((contclass) && TESTAFF(contclass, ep->getFlag(), contclasslen)) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (960:13): [True: 0, False: 0] | Branch (960:13): [True: 0, False: 0] ------------------ 961| 0| he = pmyMgr->suffix_check(tmpword, 0, tmpl, 0, nullptr, scratch, (FLAG)aflag, needflag, IN_CPD_NOT); ------------------ | | 75| 0|#define IN_CPD_NOT 0 ------------------ 962| 0| else 963| 0| he = pmyMgr->suffix_check(tmpword, 0, tmpl, optflags, ppfx, 964| 0| scratch, (FLAG)aflag, needflag, IN_CPD_NOT); ------------------ | | 75| 0|#define IN_CPD_NOT 0 ------------------ 965| 25.8k| } else { 966| 25.8k| he = pmyMgr->suffix_check(tmpword, 0, tmpl, 0, nullptr, scratch, (FLAG)aflag, needflag, IN_CPD_NOT); ------------------ | | 75| 25.8k|#define IN_CPD_NOT 0 ------------------ 967| 25.8k| } 968| 25.8k| if (he) ------------------ | Branch (968:11): [True: 0, False: 25.8k] ------------------ 969| 0| return he; 970| 25.8k| } 971| 25.8k| } 972| 26.0k| return nullptr; 973| 26.0k|} _ZN8SfxEntry15initReverseWordEv: 1083| 34|void SfxEntry::initReverseWord() { 1084| 34| rappnd = appnd; 1085| 34| reverseword(rappnd); 1086| 34|} _ZN8PfxEntry14test_conditionERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 134| 2.76M|inline int PfxEntry::test_condition(const std::string& s) { 135| 2.76M| size_t st = 0; 136| 2.76M| size_t pos = std::string::npos; // group with pos input position 137| 2.76M| bool neg = false; // complementer 138| 2.76M| bool ingroup = false; // character in the group 139| 2.76M| if (numconds == 0) ------------------ | Branch (139:7): [True: 3.87k, False: 2.75M] ------------------ 140| 3.87k| return 1; 141| 2.75M| char* p = c.conds; 142| 2.87M| while (true) { ------------------ | Branch (142:10): [True: 2.87M, Folded] ------------------ 143| 2.87M| switch (*p) { 144| 0| case '\0': ------------------ | Branch (144:7): [True: 0, False: 2.87M] ------------------ 145| 0| return 1; 146| 24.3k| case '[': { ------------------ | Branch (146:7): [True: 24.3k, False: 2.85M] ------------------ 147| 24.3k| neg = false; 148| 24.3k| ingroup = false; 149| 24.3k| p = nextchar(p); 150| 24.3k| pos = st; 151| 24.3k| break; 152| 0| } 153| 24.3k| case '^': { ------------------ | Branch (153:7): [True: 24.3k, False: 2.85M] ------------------ 154| 24.3k| p = nextchar(p); 155| 24.3k| neg = true; 156| 24.3k| break; 157| 0| } 158| 24.3k| case ']': { ------------------ | Branch (158:7): [True: 24.3k, False: 2.85M] ------------------ 159| 24.3k| if (bool(neg) == bool(ingroup)) ------------------ | Branch (159:13): [True: 0, False: 24.3k] ------------------ 160| 0| return 0; 161| 24.3k| pos = std::string::npos; 162| 24.3k| p = nextchar(p); 163| | // skip the next character 164| 24.3k| if (!ingroup && st < s.size()) ------------------ | Branch (164:13): [True: 24.3k, False: 0] | Branch (164:25): [True: 23.0k, False: 1.30k] ------------------ 165| 23.0k| st = (opts & aeUTF8) ? utf8_next(s, st) : st + 1; ------------------ | | 66| 23.0k|#define aeUTF8 (1 << 1) ------------------ | Branch (165:16): [True: 23.0k, False: 0] ------------------ 166| 24.3k| if (st == s.size() && p) ------------------ | Branch (166:13): [True: 3.49k, False: 20.8k] | Branch (166:31): [True: 0, False: 3.49k] ------------------ 167| 0| return 0; // word <= condition 168| 24.3k| break; 169| 24.3k| } 170| 24.3k| case '.': ------------------ | Branch (170:7): [True: 0, False: 2.87M] ------------------ 171| 0| if (pos == std::string::npos) { // dots are not metacharacters in groups: [.] ------------------ | Branch (171:13): [True: 0, False: 0] ------------------ 172| 0| if (st == s.size()) ------------------ | Branch (172:15): [True: 0, False: 0] ------------------ 173| 0| return 0; // dot has no character to match 174| 0| p = nextchar(p); 175| | // skip the next character 176| 0| st = (opts & aeUTF8) ? utf8_next(s, st) : st + 1; ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (176:16): [True: 0, False: 0] ------------------ 177| 0| break; 178| 0| } 179| | /* FALLTHROUGH */ 180| 2.80M| default: { ------------------ | Branch (180:7): [True: 2.80M, False: 72.9k] ------------------ 181| 2.80M| if (st < s.size() && s[st] == *p) { ------------------ | Branch (181:13): [True: 2.80M, False: 2.61k] | Branch (181:30): [True: 24.6k, False: 2.77M] ------------------ 182| 24.6k| ++st; 183| 24.6k| p = nextchar(p); 184| 24.6k| if ((opts & aeUTF8) && (s[st - 1] & 0x80)) { // multibyte ------------------ | | 66| 24.6k|#define aeUTF8 (1 << 1) ------------------ | Branch (184:15): [True: 24.6k, False: 0] | Branch (184:34): [True: 24.6k, False: 0] ------------------ 185| 49.0k| while (p && is_utf8_cont(*p)) { // character ------------------ | Branch (185:20): [True: 49.0k, False: 0] | Branch (185:25): [True: 24.6k, False: 24.3k] ------------------ 186| 24.6k| if (st >= s.size() || *p != s[st]) { ------------------ | Branch (186:19): [True: 0, False: 24.6k] | Branch (186:37): [True: 390, False: 24.3k] ------------------ 187| 390| if (pos == std::string::npos) ------------------ | Branch (187:21): [True: 390, False: 0] ------------------ 188| 390| return 0; 189| 0| st = pos; 190| 0| break; 191| 390| } 192| 24.3k| p = nextchar(p); 193| 24.3k| ++st; 194| 24.3k| } 195| 24.3k| if (pos != std::string::npos && st != pos) { ------------------ | Branch (195:17): [True: 0, False: 24.3k] | Branch (195:45): [True: 0, False: 0] ------------------ 196| 0| ingroup = true; 197| 0| while (p && *p != ']' && ((p = nextchar(p)) != nullptr)) { ------------------ | Branch (197:22): [True: 0, False: 0] | Branch (197:27): [True: 0, False: 0] | Branch (197:40): [True: 0, False: 0] ------------------ 198| 0| } 199| 0| } 200| 24.3k| } else if (pos != std::string::npos) { ------------------ | Branch (200:22): [True: 0, False: 0] ------------------ 201| 0| ingroup = true; 202| 0| while (p && *p != ']' && ((p = nextchar(p)) != nullptr)) { ------------------ | Branch (202:20): [True: 0, False: 0] | Branch (202:25): [True: 0, False: 0] | Branch (202:38): [True: 0, False: 0] ------------------ 203| 0| } 204| 0| } 205| 2.78M| } else if (pos != std::string::npos) { // group ------------------ | Branch (205:20): [True: 48.6k, False: 2.73M] ------------------ 206| 48.6k| p = nextchar(p); 207| 48.6k| } else 208| 2.73M| return 0; 209| 2.80M| } 210| 2.87M| } 211| 145k| if (!p) ------------------ | Branch (211:9): [True: 24.3k, False: 121k] ------------------ 212| 24.3k| return 1; 213| 145k| } 214| 2.75M|} _ZN8PfxEntry8nextcharEPc: 119| 170k|inline char* PfxEntry::nextchar(char* p) { 120| 170k| if (p) { ------------------ | Branch (120:7): [True: 170k, False: 0] ------------------ 121| 170k| p++; 122| 170k| if (opts & aeLONGCOND) { ------------------ | | 69| 170k|#define aeLONGCOND (1 << 4) ------------------ | Branch (122:9): [True: 0, False: 170k] ------------------ 123| | // jump to the 2nd part of the condition 124| 0| if (p == c.conds + MAXCONDLEN_1) ------------------ | | 94| 0|#define MAXCONDLEN_1 (MAXCONDLEN - sizeof(char*)) | | ------------------ | | | | 93| 0|#define MAXCONDLEN 20 | | ------------------ ------------------ | Branch (124:11): [True: 0, False: 0] ------------------ 125| 0| return c.l.conds2; 126| | // end of the MAXCONDLEN length condition 127| 170k| } else if (p == c.conds + MAXCONDLEN) ------------------ | | 93| 170k|#define MAXCONDLEN 20 ------------------ | Branch (127:16): [True: 0, False: 170k] ------------------ 128| 0| return nullptr; 129| 170k| return *p ? p : nullptr; ------------------ | Branch (129:12): [True: 146k, False: 24.3k] ------------------ 130| 170k| } 131| 0| return nullptr; 132| 170k|} _ZN8SfxEntry14test_conditionEPKcS1_: 608| 73.6k|inline int SfxEntry::test_condition(const char* st, const char* beg) { 609| 73.6k| const char* pos = nullptr; // group with pos input position 610| 73.6k| bool neg = false; // complementer 611| 73.6k| bool ingroup = false; // character in the group 612| 73.6k| if (numconds == 0) ------------------ | Branch (612:7): [True: 73.6k, False: 0] ------------------ 613| 73.6k| return 1; 614| 0| char* p = c.conds; 615| 0| st--; 616| 0| int i = 1; 617| 0| while (true) { ------------------ | Branch (617:10): [True: 0, Folded] ------------------ 618| 0| switch (*p) { 619| 0| case '\0': ------------------ | Branch (619:7): [True: 0, False: 0] ------------------ 620| 0| return 1; 621| 0| case '[': ------------------ | Branch (621:7): [True: 0, False: 0] ------------------ 622| 0| p = nextchar(p); 623| 0| pos = st; 624| 0| break; 625| 0| case '^': ------------------ | Branch (625:7): [True: 0, False: 0] ------------------ 626| 0| p = nextchar(p); 627| 0| neg = true; 628| 0| break; 629| 0| case ']': ------------------ | Branch (629:7): [True: 0, False: 0] ------------------ 630| 0| if (!neg && !ingroup) ------------------ | Branch (630:13): [True: 0, False: 0] | Branch (630:21): [True: 0, False: 0] ------------------ 631| 0| return 0; 632| 0| i++; 633| | // skip the next character 634| 0| if (!ingroup) { ------------------ | Branch (634:13): [True: 0, False: 0] ------------------ 635| 0| for (; (opts & aeUTF8) && (st >= beg) && is_utf8_cont(*st); st--) ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (635:18): [True: 0, False: 0] | Branch (635:37): [True: 0, False: 0] | Branch (635:52): [True: 0, False: 0] ------------------ 636| 0| ; 637| 0| st--; 638| 0| } 639| 0| pos = nullptr; 640| 0| neg = false; 641| 0| ingroup = false; 642| 0| p = nextchar(p); 643| 0| if (st < beg && p) ------------------ | Branch (643:13): [True: 0, False: 0] | Branch (643:25): [True: 0, False: 0] ------------------ 644| 0| return 0; // word <= condition 645| 0| break; 646| 0| case '.': ------------------ | Branch (646:7): [True: 0, False: 0] ------------------ 647| 0| if (!pos) { ------------------ | Branch (647:13): [True: 0, False: 0] ------------------ 648| | // dots are not metacharacters in groups: [.] 649| 0| p = nextchar(p); 650| | // skip one character to the left. Walk back over any UTF-8 651| | // continuation bytes of that character to its leading byte first, 652| | // then step past it, so a single-byte match preceded by a 653| | // multibyte character does not consume the multibyte character. 654| 0| for (; (opts & aeUTF8) && (st >= beg) && is_utf8_cont(*st); st--) ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (654:18): [True: 0, False: 0] | Branch (654:37): [True: 0, False: 0] | Branch (654:52): [True: 0, False: 0] ------------------ 655| 0| ; 656| 0| st--; 657| 0| if (st < beg) { // word <= condition ------------------ | Branch (657:15): [True: 0, False: 0] ------------------ 658| 0| if (p) ------------------ | Branch (658:17): [True: 0, False: 0] ------------------ 659| 0| return 0; 660| 0| else 661| 0| return 1; 662| 0| } 663| 0| break; 664| 0| } 665| | /* FALLTHROUGH */ 666| 0| default: { ------------------ | Branch (666:7): [True: 0, False: 0] ------------------ 667| 0| if (*st == *p) { ------------------ | Branch (667:13): [True: 0, False: 0] ------------------ 668| 0| p = nextchar(p); 669| 0| if ((opts & aeUTF8) && (*st & 0x80)) { ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (669:15): [True: 0, False: 0] | Branch (669:34): [True: 0, False: 0] ------------------ 670| 0| st--; 671| 0| while (p && (st >= beg)) { ------------------ | Branch (671:20): [True: 0, False: 0] | Branch (671:25): [True: 0, False: 0] ------------------ 672| 0| if (*p != *st) { ------------------ | Branch (672:19): [True: 0, False: 0] ------------------ 673| 0| if (!pos) ------------------ | Branch (673:21): [True: 0, False: 0] ------------------ 674| 0| return 0; 675| 0| st = pos; 676| 0| break; 677| 0| } 678| | // first byte of the UTF-8 multibyte character 679| 0| if (!is_utf8_cont(*p)) ------------------ | Branch (679:19): [True: 0, False: 0] ------------------ 680| 0| break; 681| 0| p = nextchar(p); 682| 0| st--; 683| 0| } 684| 0| if (pos && st != pos) { ------------------ | Branch (684:17): [True: 0, False: 0] | Branch (684:24): [True: 0, False: 0] ------------------ 685| 0| if (neg) ------------------ | Branch (685:19): [True: 0, False: 0] ------------------ 686| 0| return 0; 687| 0| else if (i == numconds) ------------------ | Branch (687:24): [True: 0, False: 0] ------------------ 688| 0| return 1; 689| 0| ingroup = true; 690| 0| while (p && *p != ']' && ((p = nextchar(p)) != nullptr)) { ------------------ | Branch (690:22): [True: 0, False: 0] | Branch (690:27): [True: 0, False: 0] | Branch (690:40): [True: 0, False: 0] ------------------ 691| 0| } 692| 0| st--; 693| 0| } 694| 0| if (p && *p != ']') ------------------ | Branch (694:17): [True: 0, False: 0] | Branch (694:22): [True: 0, False: 0] ------------------ 695| 0| p = nextchar(p); 696| 0| } else if (pos) { ------------------ | Branch (696:22): [True: 0, False: 0] ------------------ 697| 0| if (neg) ------------------ | Branch (697:17): [True: 0, False: 0] ------------------ 698| 0| return 0; 699| 0| else if (i == numconds) ------------------ | Branch (699:22): [True: 0, False: 0] ------------------ 700| 0| return 1; 701| 0| ingroup = true; 702| 0| while (p && *p != ']' && ((p = nextchar(p)) != nullptr)) { ------------------ | Branch (702:20): [True: 0, False: 0] | Branch (702:25): [True: 0, False: 0] | Branch (702:38): [True: 0, False: 0] ------------------ 703| 0| } 704| | // if (p && *p != ']') p = nextchar(p); 705| 0| st--; 706| 0| } 707| 0| if (!pos) { ------------------ | Branch (707:15): [True: 0, False: 0] ------------------ 708| 0| i++; 709| 0| st--; 710| 0| } 711| 0| if (st < beg && p && *p != ']') ------------------ | Branch (711:15): [True: 0, False: 0] | Branch (711:27): [True: 0, False: 0] | Branch (711:32): [True: 0, False: 0] ------------------ 712| 0| return 0; // word <= condition 713| 0| } else if (pos) { // group ------------------ | Branch (713:20): [True: 0, False: 0] ------------------ 714| 0| p = nextchar(p); 715| 0| } else 716| 0| return 0; 717| 0| } 718| 0| } 719| 0| if (!p) ------------------ | Branch (719:9): [True: 0, False: 0] ------------------ 720| 0| return 1; 721| 0| } 722| 0|} _ZN8PfxEntry7getContEv: 136| 4.21M| inline const unsigned short* getCont() { return contclass; } _ZN8PfxEntry10getContLenEv: 137| 1.40M| inline unsigned short getContLen() { return contclasslen; } _ZN8SfxEntry7getContEv: 226| 367k| inline const unsigned short* getCont() { return contclass; } _ZN8SfxEntry10getContLenEv: 227| 39.1k| inline unsigned short getContLen() { return contclasslen; } _ZN8PfxEntry7getFlagEv: 128| 916| FLAG getFlag() { return aflag; } _ZN8PfxEntry6getKeyEv: 129| 133k| const char* getKey() { return appnd.c_str(); } _ZN8SfxEntry7getFlagEv: 220| 109k| FLAG getFlag() { return aflag; } _ZN8SfxEntry8getAffixEv: 228| 36.6k| inline const char* getAffix() { return appnd.c_str(); } _ZNK8PfxEntry10allowCrossEv: 94| 2| bool allowCross() const { return ((opts & aeXPRODUCT) != 0); } ------------------ | | 65| 2|#define aeXPRODUCT (1 << 0) ------------------ _ZN8PfxEntry9getKeyLenEv: 132| 2.72k| inline int getKeyLen() { return appnd.size(); } _ZN8PfxEntry7getNextEv: 139| 2.73M| inline PfxEntry* getNext() { return next; } _ZN8PfxEntry9getNextNEEv: 140| 57.4k| inline PfxEntry* getNextNE() { return nextne; } _ZN8PfxEntry9getNextEQEv: 141| 75.1k| inline PfxEntry* getNextEQ() { return nexteq; } _ZN8PfxEntry9getFlgNxtEv: 142| 908| inline PfxEntry* getFlgNxt() { return flgnxt; } _ZN8PfxEntry7setNextEPS_: 144| 8| inline void setNext(PfxEntry* ptr) { next = ptr; } _ZN8PfxEntry9setNextNEEPS_: 145| 16| inline void setNextNE(PfxEntry* ptr) { nextne = ptr; } _ZN8PfxEntry9setNextEQEPS_: 146| 14| inline void setNextEQ(PfxEntry* ptr) { nexteq = ptr; } _ZN8PfxEntry9setFlgNxtEPS_: 147| 8| inline void setFlgNxt(PfxEntry* ptr) { flgnxt = ptr; } _ZNK8SfxEntry10allowCrossEv: 176| 27| bool allowCross() const { return ((opts & aeXPRODUCT) != 0); } ------------------ | | 65| 27|#define aeXPRODUCT (1 << 0) ------------------ _ZN8SfxEntry6getKeyEv: 221| 327k| const char* getKey() { return rappnd.c_str(); } _ZN8SfxEntry9getKeyLenEv: 230| 165k| inline int getKeyLen() { return appnd.size(); } _ZN8SfxEntry7getNextEv: 232| 228| inline SfxEntry* getNext() { return next; } _ZN8SfxEntry9getNextNEEv: 233| 40.5k| inline SfxEntry* getNextNE() { return nextne; } _ZN8SfxEntry9getNextEQEv: 234| 287k| inline SfxEntry* getNextEQ() { return nexteq; } _ZN8SfxEntry9getFlgNxtEv: 239| 64.2k| inline SfxEntry* getFlgNxt() { return flgnxt; } _ZN8SfxEntry7setNextEPS_: 241| 34| inline void setNext(SfxEntry* ptr) { next = ptr; } _ZN8SfxEntry9setNextNEEPS_: 242| 80| inline void setNextNE(SfxEntry* ptr) { nextne = ptr; } _ZN8SfxEntry9setNextEQEPS_: 243| 88| inline void setNextEQ(SfxEntry* ptr) { nexteq = ptr; } _ZN8SfxEntry9setFlgNxtEPS_: 244| 34| inline void setFlgNxt(SfxEntry* ptr) { flgnxt = ptr; } _ZN8AffixMgrC2EPKcRKNSt3__16vectorINS2_10unique_ptrI7HashMgrNS2_14default_deleteIS5_EEEENS2_9allocatorIS8_EEEES1_: 137| 38| : alldic(ptr) 138| 38| , pHMgr(ptr[0].get()) { 139| | 140| | // register hash manager and load affix data from aff file 141| 38| csconv = nullptr; 142| 38| utf8 = 0; 143| 38| complexprefixes = 0; 144| 38| parsedmaptable = false; 145| 38| parsedbreaktable = false; 146| 38| iconvtable = nullptr; 147| 38| oconvtable = nullptr; 148| | // allow simplified compound forms (see 3rd field of CHECKCOMPOUNDPATTERN) 149| 38| simplifiedcpd = 0; 150| 38| parsedcheckcpd = false; 151| 38| parseddefcpd = false; 152| 38| phone = nullptr; 153| 38| compoundflag = FLAG_NULL; // permits word in compound forms ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 154| 38| compoundbegin = FLAG_NULL; // may be first word in compound forms ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 155| 38| compoundmiddle = FLAG_NULL; // may be middle word in compound forms ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 156| 38| compoundend = FLAG_NULL; // may be last word in compound forms ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 157| 38| compoundroot = FLAG_NULL; // compound word signing flag ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 158| 38| compoundpermitflag = FLAG_NULL; // compound permitting flag for suffixed word ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 159| 38| compoundforbidflag = FLAG_NULL; // compound fordidden flag for suffixed word ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 160| 38| compoundmoresuffixes = 0; // allow more suffixes within compound words 161| 38| checkcompounddup = 0; // forbid double words in compounds 162| 38| checkcompoundrep = 0; // forbid bad compounds (may be non-compound word with 163| | // a REP substitution) 164| 38| checkcompoundcase = 165| 38| 0; // forbid upper and lowercase combinations at word bounds 166| 38| checkcompoundtriple = 0; // forbid compounds with triple letters 167| 38| simplifiedtriple = 0; // allow simplified triple letters in compounds 168| | // (Schiff+fahrt -> Schiffahrt) 169| 38| forbiddenword = FORBIDDENWORD; // forbidden word signing flag ------------------ | | 127| 38|#define FORBIDDENWORD 65510 ------------------ 170| 38| nosuggest = FLAG_NULL; // don't suggest words signed with NOSUGGEST flag ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 171| 38| nongramsuggest = FLAG_NULL; ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 172| 38| langnum = 0; // language code (see http://l10n.openoffice.org/languages.html) 173| 38| needaffix = FLAG_NULL; // forbidden root, allowed only with suffixes ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 174| 38| cpdwordmax = -1; // default: unlimited wordcount in compound words 175| 38| cpdmin = -1; // undefined 176| 38| cpdmaxsyllable = 0; // default: unlimited syllablecount in compound words 177| 38| pfxappnd = nullptr; // previous prefix for counting syllables of the prefix BUG 178| 38| sfxappnd = nullptr; // previous suffix for counting syllables of the suffix BUG 179| 38| sfxextra = 0; // modifier for syllable count of sfxappnd BUG 180| 38| checknum = 0; // checking numbers, and word with numbers 181| 38| havecontclass = 0; // flags of possible continuing classes (double affix) 182| | // LEMMA_PRESENT: not put root into the morphological output. Lemma presents 183| | // in morhological description in dictionary file. It's often combined with 184| | // PSEUDOROOT. 185| 38| lemma_present = FLAG_NULL; ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 186| 38| circumfix = FLAG_NULL; ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 187| 38| onlyincompound = FLAG_NULL; ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 188| 38| maxngramsugs = -1; // undefined 189| 38| maxdiff = -1; // undefined 190| 38| onlymaxdiff = 0; 191| 38| maxcpdsugs = -1; // undefined 192| 38| nosplitsugs = 0; 193| 38| sugswithdots = 0; 194| 38| keepcase = 0; 195| 38| forceucase = 0; 196| 38| warn = 0; 197| 38| forbidwarn = 0; 198| 38| checksharps = 0; 199| 38| substandard = FLAG_NULL; ------------------ | | 99| 38|#define FLAG_NULL 0x00 ------------------ 200| 38| fullstrip = 0; 201| | 202| 38| sfx = nullptr; 203| 38| pfx = nullptr; 204| | 205| 9.76k| for (int i = 0; i < SETSIZE; i++) { ------------------ | | 61| 9.76k|#define SETSIZE 256 ------------------ | Branch (205:19): [True: 9.72k, False: 38] ------------------ 206| 9.72k| pStart[i] = nullptr; 207| 9.72k| sStart[i] = nullptr; 208| 9.72k| pFlag[i] = nullptr; 209| 9.72k| sFlag[i] = nullptr; 210| 9.72k| } 211| | 212| 38| memset(contclasses, 0, CONTSIZE * sizeof(char)); ------------------ | | 62| 38|#define CONTSIZE 65536 ------------------ 213| | 214| 38| if (parse_file(affpath, key)) { ------------------ | Branch (214:7): [True: 0, False: 38] ------------------ 215| 0| fprintf(stderr, "Failure loading aff file %s\n", affpath); 216| 0| } 217| | 218| | /* get encoding for CHECKCOMPOUNDCASE */ 219| 38| if (!utf8) { ------------------ | Branch (219:7): [True: 20, False: 18] ------------------ 220| 20| csconv = get_current_cs(get_encoding()); 221| 5.14k| for (int i = 0; i <= 255; i++) { ------------------ | Branch (221:21): [True: 5.12k, False: 20] ------------------ 222| 5.12k| if ((csconv[i].cupper != csconv[i].clower) && ------------------ | Branch (222:11): [True: 2.24k, False: 2.88k] ------------------ 223| 2.24k| (wordchars.find((char)i) == std::string::npos)) { ------------------ | Branch (223:11): [True: 2.24k, False: 0] ------------------ 224| 2.24k| wordchars.push_back((char)i); 225| 2.24k| } 226| 5.12k| } 227| 20| } 228| | 229| | // default BREAK definition 230| 38| if (!parsedbreaktable) { ------------------ | Branch (230:7): [True: 34, False: 4] ------------------ 231| 34| breaktable.emplace_back("-"); 232| 34| breaktable.emplace_back("^-"); 233| 34| breaktable.emplace_back("-$"); 234| 34| parsedbreaktable = true; 235| 34| } 236| | 237| 38|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 238| | // not entirely sure this is invalid, so only for fuzzing for now 239| 38| if (iconvtable && !iconvtable->check_against_breaktable(breaktable)) { ------------------ | Branch (239:7): [True: 2, False: 36] | Branch (239:21): [True: 0, False: 2] ------------------ 240| 0| delete iconvtable; 241| 0| iconvtable = nullptr; 242| 0| } 243| 38|#endif 244| | 245| 38| if (cpdmin == -1) ------------------ | Branch (245:7): [True: 34, False: 4] ------------------ 246| 34| cpdmin = MINCPDLEN; ------------------ | | 91| 34|#define MINCPDLEN 3 ------------------ 247| 38|} _ZN8AffixMgr13finishFileMgrEP7FileMgr: 304| 38|void AffixMgr::finishFileMgr(FileMgr* afflst) { 305| 38| delete afflst; 306| | 307| | // convert affix trees to sorted list 308| 38| process_pfx_tree_to_list(); 309| 38| process_sfx_tree_to_list(); 310| 38|} _ZN8AffixMgr10parse_fileEPKcS1_: 313| 38|int AffixMgr::parse_file(const char* affpath, const char* key) { 314| | 315| | // checking flag duplication 316| 38| char dupflags[CONTSIZE]; 317| 38| char dupflags_ini = 1; 318| | 319| | // first line indicator for removing byte order mark 320| 38| int firstline = 1; 321| | 322| | // open the affix file 323| 38| FileMgr* afflst = new FileMgr(affpath, key); 324| | 325| | // step one is to parse the affix file building up the internal 326| | // affix data structures 327| | 328| | // read in each line ignoring any that do not 329| | // start with a known line type indicator 330| 38| std::string line; 331| 646| while (afflst->getline(line)) { ------------------ | Branch (331:10): [True: 608, False: 38] ------------------ 332| 608| mychomp(line); 333| | 334| | /* remove byte order mark */ 335| 608| if (firstline) { ------------------ | Branch (335:9): [True: 38, False: 570] ------------------ 336| 38| firstline = 0; 337| | // Affix file begins with byte order mark: possible incompatibility with 338| | // old Hunspell versions 339| 38| if (line.compare(0, 3, "\xEF\xBB\xBF", 3) == 0) { ------------------ | Branch (339:11): [True: 0, False: 38] ------------------ 340| 0| line.erase(0, 3); 341| 0| } 342| 38| } 343| | 344| | /* parse in the keyboard string */ 345| 608| if (line.compare(0, 3, "KEY", 3) == 0) { ------------------ | Branch (345:9): [True: 0, False: 608] ------------------ 346| 0| if (!parse_string(line, keystring, afflst->getlinenum())) { ------------------ | Branch (346:11): [True: 0, False: 0] ------------------ 347| 0| finishFileMgr(afflst); 348| 0| return 1; 349| 0| } 350| 0| } 351| | 352| | /* parse in the try string */ 353| 608| if (line.compare(0, 3, "TRY", 3) == 0) { ------------------ | Branch (353:9): [True: 2, False: 606] ------------------ 354| 2| if (!parse_string(line, trystring, afflst->getlinenum())) { ------------------ | Branch (354:11): [True: 0, False: 2] ------------------ 355| 0| finishFileMgr(afflst); 356| 0| return 1; 357| 0| } 358| 2| } 359| | 360| | /* parse in the name of the character set used by the .dict and .aff */ 361| 608| if (line.compare(0, 3, "SET", 3) == 0) { ------------------ | Branch (361:9): [True: 18, False: 590] ------------------ 362| 18| if (!parse_string(line, encoding, afflst->getlinenum())) { ------------------ | Branch (362:11): [True: 0, False: 18] ------------------ 363| 0| finishFileMgr(afflst); 364| 0| return 1; 365| 0| } 366| 18| if (encoding == "UTF-8") { ------------------ | Branch (366:11): [True: 18, False: 0] ------------------ 367| 18| utf8 = 1; 368| 18| } 369| 18| } 370| | 371| | /* parse COMPLEXPREFIXES for agglutinative languages with right-to-left 372| | * writing system */ 373| 608| if (line.compare(0, 15, "COMPLEXPREFIXES", 15) == 0) ------------------ | Branch (373:9): [True: 2, False: 606] ------------------ 374| 2| complexprefixes = 1; 375| | 376| | /* parse in the flag used by the controlled compound words */ 377| 608| if (line.compare(0, 12, "COMPOUNDFLAG", 12) == 0) { ------------------ | Branch (377:9): [True: 8, False: 600] ------------------ 378| 8| if (!parse_flag(line, &compoundflag, afflst)) { ------------------ | Branch (378:11): [True: 0, False: 8] ------------------ 379| 0| finishFileMgr(afflst); 380| 0| return 1; 381| 0| } 382| 8| } 383| | 384| | /* parse in the flag used by compound words */ 385| 608| if (line.compare(0, 13, "COMPOUNDBEGIN", 13) == 0) { ------------------ | Branch (385:9): [True: 0, False: 608] ------------------ 386| 0| if (complexprefixes) { ------------------ | Branch (386:11): [True: 0, False: 0] ------------------ 387| 0| if (!parse_flag(line, &compoundend, afflst)) { ------------------ | Branch (387:13): [True: 0, False: 0] ------------------ 388| 0| finishFileMgr(afflst); 389| 0| return 1; 390| 0| } 391| 0| } else { 392| 0| if (!parse_flag(line, &compoundbegin, afflst)) { ------------------ | Branch (392:13): [True: 0, False: 0] ------------------ 393| 0| finishFileMgr(afflst); 394| 0| return 1; 395| 0| } 396| 0| } 397| 0| } 398| | 399| | /* parse in the flag used by compound words */ 400| 608| if (line.compare(0, 14, "COMPOUNDMIDDLE", 14) == 0) { ------------------ | Branch (400:9): [True: 0, False: 608] ------------------ 401| 0| if (!parse_flag(line, &compoundmiddle, afflst)) { ------------------ | Branch (401:11): [True: 0, False: 0] ------------------ 402| 0| finishFileMgr(afflst); 403| 0| return 1; 404| 0| } 405| 0| } 406| | 407| | /* parse in the flag used by compound words */ 408| 608| if (line.compare(0, 11, "COMPOUNDEND", 11) == 0) { ------------------ | Branch (408:9): [True: 0, False: 608] ------------------ 409| 0| if (complexprefixes) { ------------------ | Branch (409:11): [True: 0, False: 0] ------------------ 410| 0| if (!parse_flag(line, &compoundbegin, afflst)) { ------------------ | Branch (410:13): [True: 0, False: 0] ------------------ 411| 0| finishFileMgr(afflst); 412| 0| return 1; 413| 0| } 414| 0| } else { 415| 0| if (!parse_flag(line, &compoundend, afflst)) { ------------------ | Branch (415:13): [True: 0, False: 0] ------------------ 416| 0| finishFileMgr(afflst); 417| 0| return 1; 418| 0| } 419| 0| } 420| 0| } 421| | 422| | /* parse in the data used by compound_check() method */ 423| 608| if (line.compare(0, 15, "COMPOUNDWORDMAX", 15) == 0) { ------------------ | Branch (423:9): [True: 2, False: 606] ------------------ 424| 2| if (!parse_num(line, &cpdwordmax, afflst)) { ------------------ | Branch (424:11): [True: 0, False: 2] ------------------ 425| 0| finishFileMgr(afflst); 426| 0| return 1; 427| 0| } 428| 2| } 429| | 430| | /* parse in the flag sign compounds in dictionary */ 431| 608| if (line.compare(0, 12, "COMPOUNDROOT", 12) == 0) { ------------------ | Branch (431:9): [True: 0, False: 608] ------------------ 432| 0| if (!parse_flag(line, &compoundroot, afflst)) { ------------------ | Branch (432:11): [True: 0, False: 0] ------------------ 433| 0| finishFileMgr(afflst); 434| 0| return 1; 435| 0| } 436| 0| } 437| | 438| | /* parse in the flag used by compound_check() method */ 439| 608| if (line.compare(0, 18, "COMPOUNDPERMITFLAG", 18) == 0) { ------------------ | Branch (439:9): [True: 2, False: 606] ------------------ 440| 2| if (!parse_flag(line, &compoundpermitflag, afflst)) { ------------------ | Branch (440:11): [True: 0, False: 2] ------------------ 441| 0| finishFileMgr(afflst); 442| 0| return 1; 443| 0| } 444| 2| } 445| | 446| | /* parse in the flag used by compound_check() method */ 447| 608| if (line.compare(0, 18, "COMPOUNDFORBIDFLAG", 18) == 0) { ------------------ | Branch (447:9): [True: 2, False: 606] ------------------ 448| 2| if (!parse_flag(line, &compoundforbidflag, afflst)) { ------------------ | Branch (448:11): [True: 0, False: 2] ------------------ 449| 0| finishFileMgr(afflst); 450| 0| return 1; 451| 0| } 452| 2| } 453| | 454| 608| if (line.compare(0, 20, "COMPOUNDMORESUFFIXES", 20) == 0) { ------------------ | Branch (454:9): [True: 0, False: 608] ------------------ 455| 0| compoundmoresuffixes = 1; 456| 0| } 457| | 458| 608| if (line.compare(0, 16, "CHECKCOMPOUNDDUP", 16) == 0) { ------------------ | Branch (458:9): [True: 0, False: 608] ------------------ 459| 0| checkcompounddup = 1; 460| 0| } 461| | 462| 608| if (line.compare(0, 16, "CHECKCOMPOUNDREP", 16) == 0) { ------------------ | Branch (462:9): [True: 2, False: 606] ------------------ 463| 2| checkcompoundrep = 1; 464| 2| } 465| | 466| 608| if (line.compare(0, 19, "CHECKCOMPOUNDTRIPLE", 19) == 0) { ------------------ | Branch (466:9): [True: 0, False: 608] ------------------ 467| 0| checkcompoundtriple = 1; 468| 0| } 469| | 470| 608| if (line.compare(0, 16, "SIMPLIFIEDTRIPLE", 16) == 0) { ------------------ | Branch (470:9): [True: 0, False: 608] ------------------ 471| 0| simplifiedtriple = 1; 472| 0| } 473| | 474| 608| if (line.compare(0, 17, "CHECKCOMPOUNDCASE", 17) == 0) { ------------------ | Branch (474:9): [True: 0, False: 608] ------------------ 475| 0| checkcompoundcase = 1; 476| 0| } 477| | 478| 608| if (line.compare(0, 9, "NOSUGGEST", 9) == 0) { ------------------ | Branch (478:9): [True: 0, False: 608] ------------------ 479| 0| if (!parse_flag(line, &nosuggest, afflst)) { ------------------ | Branch (479:11): [True: 0, False: 0] ------------------ 480| 0| finishFileMgr(afflst); 481| 0| return 1; 482| 0| } 483| 0| } 484| | 485| 608| if (line.compare(0, 14, "NONGRAMSUGGEST", 14) == 0) { ------------------ | Branch (485:9): [True: 0, False: 608] ------------------ 486| 0| if (!parse_flag(line, &nongramsuggest, afflst)) { ------------------ | Branch (486:11): [True: 0, False: 0] ------------------ 487| 0| finishFileMgr(afflst); 488| 0| return 1; 489| 0| } 490| 0| } 491| | 492| | /* parse in the flag used by forbidden words */ 493| 608| if (line.compare(0, 13, "FORBIDDENWORD", 13) == 0) { ------------------ | Branch (493:9): [True: 2, False: 606] ------------------ 494| 2| if (!parse_flag(line, &forbiddenword, afflst)) { ------------------ | Branch (494:11): [True: 0, False: 2] ------------------ 495| 0| finishFileMgr(afflst); 496| 0| return 1; 497| 0| } 498| 2| } 499| | 500| | /* parse in the flag used by forbidden words (is deprecated) */ 501| 608| if (line.compare(0, 13, "LEMMA_PRESENT", 13) == 0) { ------------------ | Branch (501:9): [True: 0, False: 608] ------------------ 502| 0| if (!parse_flag(line, &lemma_present, afflst)) { ------------------ | Branch (502:11): [True: 0, False: 0] ------------------ 503| 0| finishFileMgr(afflst); 504| 0| return 1; 505| 0| } 506| 0| } 507| | 508| | /* parse in the flag used by circumfixes */ 509| 608| if (line.compare(0, 9, "CIRCUMFIX", 9) == 0) { ------------------ | Branch (509:9): [True: 2, False: 606] ------------------ 510| 2| if (!parse_flag(line, &circumfix, afflst)) { ------------------ | Branch (510:11): [True: 0, False: 2] ------------------ 511| 0| finishFileMgr(afflst); 512| 0| return 1; 513| 0| } 514| 2| } 515| | 516| | /* parse in the flag used by fogemorphemes */ 517| 608| if (line.compare(0, 14, "ONLYINCOMPOUND", 14) == 0) { ------------------ | Branch (517:9): [True: 0, False: 608] ------------------ 518| 0| if (!parse_flag(line, &onlyincompound, afflst)) { ------------------ | Branch (518:11): [True: 0, False: 0] ------------------ 519| 0| finishFileMgr(afflst); 520| 0| return 1; 521| 0| } 522| 0| } 523| | 524| | /* parse in the flag used by `needaffixs' (is deprecated) */ 525| 608| if (line.compare(0, 10, "PSEUDOROOT", 10) == 0) { ------------------ | Branch (525:9): [True: 0, False: 608] ------------------ 526| 0| if (!parse_flag(line, &needaffix, afflst)) { ------------------ | Branch (526:11): [True: 0, False: 0] ------------------ 527| 0| finishFileMgr(afflst); 528| 0| return 1; 529| 0| } 530| 0| } 531| | 532| | /* parse in the flag used by `needaffixs' */ 533| 608| if (line.compare(0, 9, "NEEDAFFIX", 9) == 0) { ------------------ | Branch (533:9): [True: 2, False: 606] ------------------ 534| 2| if (!parse_flag(line, &needaffix, afflst)) { ------------------ | Branch (534:11): [True: 0, False: 2] ------------------ 535| 0| finishFileMgr(afflst); 536| 0| return 1; 537| 0| } 538| 2| } 539| | 540| | /* parse in the minimal length for words in compounds */ 541| 608| if (line.compare(0, 11, "COMPOUNDMIN", 11) == 0) { ------------------ | Branch (541:9): [True: 4, False: 604] ------------------ 542| 4| if (!parse_num(line, &cpdmin, afflst)) { ------------------ | Branch (542:11): [True: 0, False: 4] ------------------ 543| 0| finishFileMgr(afflst); 544| 0| return 1; 545| 0| } 546| 4| if (cpdmin < 1) ------------------ | Branch (546:11): [True: 0, False: 4] ------------------ 547| 0| cpdmin = 1; 548| 4| } 549| | 550| | /* parse in the max. words and syllables in compounds */ 551| 608| if (line.compare(0, 16, "COMPOUNDSYLLABLE", 16) == 0) { ------------------ | Branch (551:9): [True: 2, False: 606] ------------------ 552| 2| if (!parse_cpdsyllable(line, afflst)) { ------------------ | Branch (552:11): [True: 0, False: 2] ------------------ 553| 0| finishFileMgr(afflst); 554| 0| return 1; 555| 0| } 556| 2| } 557| | 558| | /* parse in the flag used by compound_check() method */ 559| 608| if (line.compare(0, 11, "SYLLABLENUM", 11) == 0) { ------------------ | Branch (559:9): [True: 0, False: 608] ------------------ 560| 0| if (!parse_string(line, cpdsyllablenum, afflst->getlinenum())) { ------------------ | Branch (560:11): [True: 0, False: 0] ------------------ 561| 0| finishFileMgr(afflst); 562| 0| return 1; 563| 0| } 564| 0| } 565| | 566| | /* parse in the flag used by the controlled compound words */ 567| 608| if (line.compare(0, 8, "CHECKNUM", 8) == 0) { ------------------ | Branch (567:9): [True: 0, False: 608] ------------------ 568| 0| checknum = 1; 569| 0| } 570| | 571| | /* parse in the extra word characters */ 572| 608| if (line.compare(0, 9, "WORDCHARS", 9) == 0) { ------------------ | Branch (572:9): [True: 6, False: 602] ------------------ 573| 6| if (!parse_array(line, wordchars, wordchars_utf16, ------------------ | Branch (573:11): [True: 0, False: 6] ------------------ 574| 6| utf8, afflst->getlinenum())) { 575| 0| finishFileMgr(afflst); 576| 0| return 1; 577| 0| } 578| 6| } 579| | 580| | /* parse in the ignored characters (for example, Arabic optional diacretics 581| | * charachters */ 582| 608| if (line.compare(0, 6, "IGNORE", 6) == 0) { ------------------ | Branch (582:9): [True: 4, False: 604] ------------------ 583| 4| if (!parse_array(line, ignorechars, ignorechars_utf16, ------------------ | Branch (583:11): [True: 0, False: 4] ------------------ 584| 4| utf8, afflst->getlinenum())) { 585| 0| finishFileMgr(afflst); 586| 0| return 1; 587| 0| } 588| 4| } 589| | 590| | /* parse in the input conversion table */ 591| 608| if (line.compare(0, 5, "ICONV", 5) == 0) { ------------------ | Branch (591:9): [True: 2, False: 606] ------------------ 592| 2| if (!parse_convtable(line, afflst, &iconvtable, "ICONV")) { ------------------ | Branch (592:11): [True: 0, False: 2] ------------------ 593| 0| finishFileMgr(afflst); 594| 0| return 1; 595| 0| } 596| 2| } 597| | 598| | /* parse in the output conversion table */ 599| 608| if (line.compare(0, 5, "OCONV", 5) == 0) { ------------------ | Branch (599:9): [True: 2, False: 606] ------------------ 600| 2| if (!parse_convtable(line, afflst, &oconvtable, "OCONV")) { ------------------ | Branch (600:11): [True: 0, False: 2] ------------------ 601| 0| finishFileMgr(afflst); 602| 0| return 1; 603| 0| } 604| 2| } 605| | 606| | /* parse in the phonetic translation table */ 607| 608| if (line.compare(0, 5, "PHONE", 5) == 0) { ------------------ | Branch (607:9): [True: 2, False: 606] ------------------ 608| 2| if (!parse_phonetable(line, afflst)) { ------------------ | Branch (608:11): [True: 0, False: 2] ------------------ 609| 0| finishFileMgr(afflst); 610| 0| return 1; 611| 0| } 612| 2| } 613| | 614| | /* parse in the checkcompoundpattern table */ 615| 608| if (line.compare(0, 20, "CHECKCOMPOUNDPATTERN", 20) == 0) { ------------------ | Branch (615:9): [True: 2, False: 606] ------------------ 616| 2| if (!parse_checkcpdtable(line, afflst)) { ------------------ | Branch (616:11): [True: 0, False: 2] ------------------ 617| 0| finishFileMgr(afflst); 618| 0| return 1; 619| 0| } 620| 2| } 621| | 622| | /* parse in the defcompound table */ 623| 608| if (line.compare(0, 12, "COMPOUNDRULE", 12) == 0) { ------------------ | Branch (623:9): [True: 0, False: 608] ------------------ 624| 0| if (!parse_defcpdtable(line, afflst)) { ------------------ | Branch (624:11): [True: 0, False: 0] ------------------ 625| 0| finishFileMgr(afflst); 626| 0| return 1; 627| 0| } 628| 0| } 629| | 630| | /* parse in the related character map table */ 631| 608| if (line.compare(0, 3, "MAP", 3) == 0) { ------------------ | Branch (631:9): [True: 2, False: 606] ------------------ 632| 2| if (!parse_maptable(line, afflst)) { ------------------ | Branch (632:11): [True: 0, False: 2] ------------------ 633| 0| finishFileMgr(afflst); 634| 0| return 1; 635| 0| } 636| 2| } 637| | 638| | /* parse in the word breakpoints table */ 639| 608| if (line.compare(0, 5, "BREAK", 5) == 0) { ------------------ | Branch (639:9): [True: 4, False: 604] ------------------ 640| 4| if (!parse_breaktable(line, afflst)) { ------------------ | Branch (640:11): [True: 0, False: 4] ------------------ 641| 0| finishFileMgr(afflst); 642| 0| return 1; 643| 0| } 644| 4| } 645| | 646| | /* parse in the language for language specific codes */ 647| 608| if (line.compare(0, 4, "LANG", 4) == 0) { ------------------ | Branch (647:9): [True: 2, False: 606] ------------------ 648| 2| if (!parse_string(line, lang, afflst->getlinenum())) { ------------------ | Branch (648:11): [True: 0, False: 2] ------------------ 649| 0| finishFileMgr(afflst); 650| 0| return 1; 651| 0| } 652| 2| langnum = get_lang_num(lang); 653| 2| } 654| | 655| 608| if (line.compare(0, 7, "VERSION", 7) == 0) { ------------------ | Branch (655:9): [True: 0, False: 608] ------------------ 656| 0| size_t startpos = line.find_first_not_of(" \t", 7); 657| 0| if (startpos != std::string::npos) { ------------------ | Branch (657:11): [True: 0, False: 0] ------------------ 658| 0| version = line.substr(startpos); 659| 0| } 660| 0| } 661| | 662| 608| if (line.compare(0, 12, "MAXNGRAMSUGS", 12) == 0) { ------------------ | Branch (662:9): [True: 4, False: 604] ------------------ 663| 4| if (!parse_num(line, &maxngramsugs, afflst)) { ------------------ | Branch (663:11): [True: 0, False: 4] ------------------ 664| 0| finishFileMgr(afflst); 665| 0| return 1; 666| 0| } 667| 4| } 668| | 669| 608| if (line.compare(0, 11, "ONLYMAXDIFF", 11) == 0) ------------------ | Branch (669:9): [True: 0, False: 608] ------------------ 670| 0| onlymaxdiff = 1; 671| | 672| 608| if (line.compare(0, 7, "MAXDIFF", 7) == 0) { ------------------ | Branch (672:9): [True: 0, False: 608] ------------------ 673| 0| if (!parse_num(line, &maxdiff, afflst)) { ------------------ | Branch (673:11): [True: 0, False: 0] ------------------ 674| 0| finishFileMgr(afflst); 675| 0| return 1; 676| 0| } 677| 0| } 678| | 679| 608| if (line.compare(0, 10, "MAXCPDSUGS", 10) == 0) { ------------------ | Branch (679:9): [True: 0, False: 608] ------------------ 680| 0| if (!parse_num(line, &maxcpdsugs, afflst)) { ------------------ | Branch (680:11): [True: 0, False: 0] ------------------ 681| 0| finishFileMgr(afflst); 682| 0| return 1; 683| 0| } 684| 0| } 685| | 686| 608| if (line.compare(0, 11, "NOSPLITSUGS", 11) == 0) { ------------------ | Branch (686:9): [True: 0, False: 608] ------------------ 687| 0| nosplitsugs = 1; 688| 0| } 689| | 690| 608| if (line.compare(0, 9, "FULLSTRIP", 9) == 0) { ------------------ | Branch (690:9): [True: 0, False: 608] ------------------ 691| 0| fullstrip = 1; 692| 0| } 693| | 694| 608| if (line.compare(0, 12, "SUGSWITHDOTS", 12) == 0) { ------------------ | Branch (694:9): [True: 0, False: 608] ------------------ 695| 0| sugswithdots = 1; 696| 0| } 697| | 698| | /* parse in the flag used by forbidden words */ 699| 608| if (line.compare(0, 8, "KEEPCASE", 8) == 0) { ------------------ | Branch (699:9): [True: 2, False: 606] ------------------ 700| 2| if (!parse_flag(line, &keepcase, afflst)) { ------------------ | Branch (700:11): [True: 0, False: 2] ------------------ 701| 0| finishFileMgr(afflst); 702| 0| return 1; 703| 0| } 704| 2| } 705| | 706| | /* parse in the flag used by `forceucase' */ 707| 608| if (line.compare(0, 10, "FORCEUCASE", 10) == 0) { ------------------ | Branch (707:9): [True: 0, False: 608] ------------------ 708| 0| if (!parse_flag(line, &forceucase, afflst)) { ------------------ | Branch (708:11): [True: 0, False: 0] ------------------ 709| 0| finishFileMgr(afflst); 710| 0| return 1; 711| 0| } 712| 0| } 713| | 714| | /* parse in the flag used by `warn' */ 715| 608| if (line.compare(0, 4, "WARN", 4) == 0) { ------------------ | Branch (715:9): [True: 2, False: 606] ------------------ 716| 2| if (!parse_flag(line, &warn, afflst)) { ------------------ | Branch (716:11): [True: 0, False: 2] ------------------ 717| 0| finishFileMgr(afflst); 718| 0| return 1; 719| 0| } 720| 2| } 721| | 722| 608| if (line.compare(0, 10, "FORBIDWARN", 10) == 0) { ------------------ | Branch (722:9): [True: 0, False: 608] ------------------ 723| 0| forbidwarn = 1; 724| 0| } 725| | 726| | /* parse in the flag used by the affix generator */ 727| 608| if (line.compare(0, 11, "SUBSTANDARD", 11) == 0) { ------------------ | Branch (727:9): [True: 0, False: 608] ------------------ 728| 0| if (!parse_flag(line, &substandard, afflst)) { ------------------ | Branch (728:11): [True: 0, False: 0] ------------------ 729| 0| finishFileMgr(afflst); 730| 0| return 1; 731| 0| } 732| 0| } 733| | 734| 608| if (line.compare(0, 11, "CHECKSHARPS", 11) == 0) { ------------------ | Branch (734:9): [True: 0, False: 608] ------------------ 735| 0| checksharps = 1; 736| 0| } 737| | 738| | /* parse this affix: P - prefix, S - suffix */ 739| | // affix type 740| 608| char ft = ' '; 741| 608| if (line.compare(0, 3, "PFX", 3) == 0) ------------------ | Branch (741:9): [True: 12, False: 596] ------------------ 742| 12| ft = complexprefixes ? 'S' : 'P'; ------------------ | Branch (742:12): [True: 4, False: 8] ------------------ 743| 608| if (line.compare(0, 3, "SFX", 3) == 0) ------------------ | Branch (743:9): [True: 14, False: 594] ------------------ 744| 14| ft = complexprefixes ? 'P' : 'S'; ------------------ | Branch (744:12): [True: 0, False: 14] ------------------ 745| 608| if (ft != ' ') { ------------------ | Branch (745:9): [True: 26, False: 582] ------------------ 746| 26| if (dupflags_ini) { ------------------ | Branch (746:11): [True: 18, False: 8] ------------------ 747| 18| memset(dupflags, 0, sizeof(dupflags)); 748| 18| dupflags_ini = 0; 749| 18| } 750| 26| if (!parse_affix(line, ft, afflst, dupflags)) { ------------------ | Branch (750:11): [True: 0, False: 26] ------------------ 751| 0| finishFileMgr(afflst); 752| 0| return 1; 753| 0| } 754| 26| } 755| 608| } 756| | 757| 38| finishFileMgr(afflst); 758| | // affix trees are sorted now 759| | 760| | // now we can speed up performance greatly taking advantage of the 761| | // relationship between the affixes and the idea of "subsets". 762| | 763| | // View each prefix as a potential leading subset of another and view 764| | // each suffix (reversed) as a potential trailing subset of another. 765| | 766| | // To illustrate this relationship if we know the prefix "ab" is found in the 767| | // word to examine, only prefixes that "ab" is a leading subset of need be 768| | // examined. 769| | // Furthermore is "ab" is not present then none of the prefixes that "ab" is 770| | // is a subset need be examined. 771| | // The same argument goes for suffix string that are reversed. 772| | 773| | // Then to top this off why not examine the first char of the word to quickly 774| | // limit the set of prefixes to examine (i.e. the prefixes to examine must 775| | // be leading supersets of the first character of the word (if they exist) 776| | 777| | // To take advantage of this "subset" relationship, we need to add two links 778| | // from entry. One to take next if the current prefix is found (call it 779| | // nexteq) 780| | // and one to take next if the current prefix is not found (call it nextne). 781| | 782| | // Since we have built ordered lists, all that remains is to properly 783| | // initialize 784| | // the nextne and nexteq pointers that relate them 785| | 786| 38| process_pfx_order(); 787| 38| process_sfx_order(); 788| | 789| 38| return 0; 790| 38|} _ZN8AffixMgr13build_pfxtreeEP8PfxEntry: 796| 8|int AffixMgr::build_pfxtree(PfxEntry* pfxptr) { 797| 8| PfxEntry* ptr; 798| 8| PfxEntry* pptr; 799| 8| PfxEntry* ep = pfxptr; 800| | 801| | // get the right starting points 802| 8| const char* key = ep->getKey(); 803| 8| const auto flg = (unsigned char)(ep->getFlag() & 0x00FF); 804| | 805| | // first index by flag which must exist 806| 8| ptr = pFlag[flg]; 807| 8| ep->setFlgNxt(ptr); 808| 8| pFlag[flg] = ep; 809| | 810| | // handle the special case of null affix string 811| 8| if (*key == '\0') { ------------------ | Branch (811:7): [True: 2, False: 6] ------------------ 812| | // always inset them at head of list at element 0 813| 2| ptr = pStart[0]; 814| 2| ep->setNext(ptr); 815| 2| pStart[0] = ep; 816| 2| return 0; 817| 2| } 818| | 819| | // now handle the normal case 820| 6| ep->setNextEQ(nullptr); 821| 6| ep->setNextNE(nullptr); 822| | 823| 6| unsigned char sp = *((const unsigned char*)key); 824| 6| ptr = pStart[sp]; 825| | 826| | // handle the first insert 827| 6| if (!ptr) { ------------------ | Branch (827:7): [True: 4, False: 2] ------------------ 828| 4| pStart[sp] = ep; 829| 4| return 0; 830| 4| } 831| | 832| | // otherwise use binary tree insertion so that a sorted 833| | // list can easily be generated later 834| 2| pptr = nullptr; 835| 2| for (;;) { 836| 2| pptr = ptr; 837| 2| if (strcmp(ep->getKey(), ptr->getKey()) <= 0) { ------------------ | Branch (837:9): [True: 0, False: 2] ------------------ 838| 0| ptr = ptr->getNextEQ(); 839| 0| if (!ptr) { ------------------ | Branch (839:11): [True: 0, False: 0] ------------------ 840| 0| pptr->setNextEQ(ep); 841| 0| break; 842| 0| } 843| 2| } else { 844| 2| ptr = ptr->getNextNE(); 845| 2| if (!ptr) { ------------------ | Branch (845:11): [True: 2, False: 0] ------------------ 846| 2| pptr->setNextNE(ep); 847| 2| break; 848| 2| } 849| 2| } 850| 2| } 851| 2| return 0; 852| 6|} _ZN8AffixMgr13build_sfxtreeEP8SfxEntry: 857| 34|int AffixMgr::build_sfxtree(SfxEntry* sfxptr) { 858| | 859| 34| sfxptr->initReverseWord(); 860| | 861| 34| SfxEntry* ptr; 862| 34| SfxEntry* pptr; 863| 34| SfxEntry* ep = sfxptr; 864| | 865| | /* get the right starting point */ 866| 34| const char* key = ep->getKey(); 867| 34| const auto flg = (unsigned char)(ep->getFlag() & 0x00FF); 868| | 869| | // first index by flag which must exist 870| 34| ptr = sFlag[flg]; 871| 34| ep->setFlgNxt(ptr); 872| 34| sFlag[flg] = ep; 873| | 874| | // next index by affix string 875| | 876| | // handle the special case of null affix string 877| 34| if (*key == '\0') { ------------------ | Branch (877:7): [True: 0, False: 34] ------------------ 878| | // always inset them at head of list at element 0 879| 0| ptr = sStart[0]; 880| 0| ep->setNext(ptr); 881| 0| sStart[0] = ep; 882| 0| return 0; 883| 0| } 884| | 885| | // now handle the normal case 886| 34| ep->setNextEQ(nullptr); 887| 34| ep->setNextNE(nullptr); 888| | 889| 34| unsigned char sp = *((const unsigned char*)key); 890| 34| ptr = sStart[sp]; 891| | 892| | // handle the first insert 893| 34| if (!ptr) { ------------------ | Branch (893:7): [True: 22, False: 12] ------------------ 894| 22| sStart[sp] = ep; 895| 22| return 0; 896| 22| } 897| | 898| | // otherwise use binary tree insertion so that a sorted 899| | // list can easily be generated later 900| 12| pptr = nullptr; 901| 20| for (;;) { 902| 20| pptr = ptr; 903| 20| if (strcmp(ep->getKey(), ptr->getKey()) <= 0) { ------------------ | Branch (903:9): [True: 18, False: 2] ------------------ 904| 18| ptr = ptr->getNextEQ(); 905| 18| if (!ptr) { ------------------ | Branch (905:11): [True: 10, False: 8] ------------------ 906| 10| pptr->setNextEQ(ep); 907| 10| break; 908| 10| } 909| 18| } else { 910| 2| ptr = ptr->getNextNE(); 911| 2| if (!ptr) { ------------------ | Branch (911:11): [True: 2, False: 0] ------------------ 912| 2| pptr->setNextNE(ep); 913| 2| break; 914| 2| } 915| 2| } 916| 20| } 917| 12| return 0; 918| 34|} _ZN8AffixMgr24process_pfx_tree_to_listEv: 921| 38|int AffixMgr::process_pfx_tree_to_list() { 922| 9.72k| for (int i = 1; i < SETSIZE; i++) { ------------------ | | 61| 9.72k|#define SETSIZE 256 ------------------ | Branch (922:19): [True: 9.69k, False: 38] ------------------ 923| 9.69k| pStart[i] = process_pfx_in_order(pStart[i], nullptr); 924| 9.69k| } 925| 38| return 0; 926| 38|} _ZN8AffixMgr20process_pfx_in_orderEP8PfxEntryS1_: 928| 9.70k|PfxEntry* AffixMgr::process_pfx_in_order(PfxEntry* ptr, PfxEntry* nptr) { 929| 9.70k| if (ptr) { ------------------ | Branch (929:7): [True: 6, False: 9.69k] ------------------ 930| 6| nptr = process_pfx_in_order(ptr->getNextNE(), nptr); 931| 6| ptr->setNext(nptr); 932| 6| nptr = process_pfx_in_order(ptr->getNextEQ(), ptr); 933| 6| } 934| 9.70k| return nptr; 935| 9.70k|} _ZN8AffixMgr24process_sfx_tree_to_listEv: 938| 38|int AffixMgr::process_sfx_tree_to_list() { 939| 9.72k| for (int i = 1; i < SETSIZE; i++) { ------------------ | | 61| 9.72k|#define SETSIZE 256 ------------------ | Branch (939:19): [True: 9.69k, False: 38] ------------------ 940| 9.69k| sStart[i] = process_sfx_in_order(sStart[i], nullptr); 941| 9.69k| } 942| 38| return 0; 943| 38|} _ZN8AffixMgr20process_sfx_in_orderEP8SfxEntryS1_: 945| 9.75k|SfxEntry* AffixMgr::process_sfx_in_order(SfxEntry* ptr, SfxEntry* nptr) { 946| 9.75k| if (ptr) { ------------------ | Branch (946:7): [True: 34, False: 9.72k] ------------------ 947| 34| nptr = process_sfx_in_order(ptr->getNextNE(), nptr); 948| 34| ptr->setNext(nptr); 949| 34| nptr = process_sfx_in_order(ptr->getNextEQ(), ptr); 950| 34| } 951| 9.75k| return nptr; 952| 9.75k|} _ZN8AffixMgr17process_pfx_orderEv: 956| 38|int AffixMgr::process_pfx_order() { 957| 38| PfxEntry* ptr; 958| | 959| | // loop through each prefix list starting point 960| 9.72k| for (int i = 1; i < SETSIZE; i++) { ------------------ | | 61| 9.72k|#define SETSIZE 256 ------------------ | Branch (960:19): [True: 9.69k, False: 38] ------------------ 961| 9.69k| ptr = pStart[i]; 962| | 963| | // look through the remainder of the list 964| | // and find next entry with affix that 965| | // the current one is not a subset of 966| | // mark that as destination for NextNE 967| | // use next in list that you are a subset 968| | // of as NextEQ 969| | 970| 9.69k| for (; ptr != nullptr; ptr = ptr->getNext()) { ------------------ | Branch (970:12): [True: 6, False: 9.69k] ------------------ 971| 6| PfxEntry* nptr = ptr->getNext(); 972| 8| for (; nptr != nullptr; nptr = nptr->getNext()) { ------------------ | Branch (972:14): [True: 2, False: 6] ------------------ 973| 2| if (!isSubset(ptr->getKey(), nptr->getKey())) ------------------ | Branch (973:13): [True: 0, False: 2] ------------------ 974| 0| break; 975| 2| } 976| 6| ptr->setNextNE(nptr); 977| 6| ptr->setNextEQ(nullptr); 978| 6| if ((ptr->getNext()) && ------------------ | Branch (978:11): [True: 2, False: 4] ------------------ 979| 2| isSubset(ptr->getKey(), (ptr->getNext())->getKey())) ------------------ | Branch (979:11): [True: 2, False: 0] ------------------ 980| 2| ptr->setNextEQ(ptr->getNext()); 981| 6| } 982| | 983| | // now clean up by adding smart search termination strings: 984| | // if you are already a superset of the previous prefix 985| | // but not a subset of the next, search can end here 986| | // so set NextNE properly 987| | 988| 9.69k| ptr = pStart[i]; 989| 9.69k| for (; ptr != nullptr; ptr = ptr->getNext()) { ------------------ | Branch (989:12): [True: 6, False: 9.69k] ------------------ 990| 6| PfxEntry* nptr = ptr->getNext(); 991| 6| PfxEntry* mptr = nullptr; 992| 8| for (; nptr != nullptr; nptr = nptr->getNext()) { ------------------ | Branch (992:14): [True: 2, False: 6] ------------------ 993| 2| if (!isSubset(ptr->getKey(), nptr->getKey())) ------------------ | Branch (993:13): [True: 0, False: 2] ------------------ 994| 0| break; 995| 2| mptr = nptr; 996| 2| } 997| 6| if (mptr) ------------------ | Branch (997:11): [True: 2, False: 4] ------------------ 998| 2| mptr->setNextNE(nullptr); 999| 6| } 1000| 9.69k| } 1001| 38| return 0; 1002| 38|} _ZN8AffixMgr17process_sfx_orderEv: 1006| 38|int AffixMgr::process_sfx_order() { 1007| 38| SfxEntry* ptr; 1008| | 1009| | // loop through each prefix list starting point 1010| 9.72k| for (int i = 1; i < SETSIZE; i++) { ------------------ | | 61| 9.72k|#define SETSIZE 256 ------------------ | Branch (1010:19): [True: 9.69k, False: 38] ------------------ 1011| 9.69k| ptr = sStart[i]; 1012| | 1013| | // look through the remainder of the list 1014| | // and find next entry with affix that 1015| | // the current one is not a subset of 1016| | // mark that as destination for NextNE 1017| | // use next in list that you are a subset 1018| | // of as NextEQ 1019| | 1020| 9.72k| for (; ptr != nullptr; ptr = ptr->getNext()) { ------------------ | Branch (1020:12): [True: 34, False: 9.69k] ------------------ 1021| 34| SfxEntry* nptr = ptr->getNext(); 1022| 52| for (; nptr != nullptr; nptr = nptr->getNext()) { ------------------ | Branch (1022:14): [True: 20, False: 32] ------------------ 1023| 20| if (!isSubset(ptr->getKey(), nptr->getKey())) ------------------ | Branch (1023:13): [True: 2, False: 18] ------------------ 1024| 2| break; 1025| 20| } 1026| 34| ptr->setNextNE(nptr); 1027| 34| ptr->setNextEQ(nullptr); 1028| 34| if ((ptr->getNext()) && ------------------ | Branch (1028:11): [True: 12, False: 22] ------------------ 1029| 12| isSubset(ptr->getKey(), (ptr->getNext())->getKey())) ------------------ | Branch (1029:11): [True: 10, False: 2] ------------------ 1030| 10| ptr->setNextEQ(ptr->getNext()); 1031| 34| } 1032| | 1033| | // now clean up by adding smart search termination strings: 1034| | // if you are already a superset of the previous suffix 1035| | // but not a subset of the next, search can end here 1036| | // so set NextNE properly 1037| | 1038| 9.69k| ptr = sStart[i]; 1039| 9.72k| for (; ptr != nullptr; ptr = ptr->getNext()) { ------------------ | Branch (1039:12): [True: 34, False: 9.69k] ------------------ 1040| 34| SfxEntry* nptr = ptr->getNext(); 1041| 34| SfxEntry* mptr = nullptr; 1042| 52| for (; nptr != nullptr; nptr = nptr->getNext()) { ------------------ | Branch (1042:14): [True: 20, False: 32] ------------------ 1043| 20| if (!isSubset(ptr->getKey(), nptr->getKey())) ------------------ | Branch (1043:13): [True: 2, False: 18] ------------------ 1044| 2| break; 1045| 18| mptr = nptr; 1046| 18| } 1047| 34| if (mptr) ------------------ | Branch (1047:11): [True: 10, False: 24] ------------------ 1048| 10| mptr->setNextNE(nullptr); 1049| 34| } 1050| 9.69k| } 1051| 38| return 0; 1052| 38|} _ZN8AffixMgr7condlenERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1065| 8|int AffixMgr::condlen(const std::string& s) { 1066| 8| int l = 0; 1067| 8| bool group = false; 1068| 8| size_t i = 0; 1069| 42| while (i < s.size()) { ------------------ | Branch (1069:10): [True: 34, False: 8] ------------------ 1070| 34| if (s[i] == '[') { ------------------ | Branch (1070:9): [True: 4, False: 30] ------------------ 1071| 4| group = true; 1072| 4| ++l; 1073| 4| ++i; 1074| 30| } else if (s[i] == ']') { ------------------ | Branch (1074:16): [True: 4, False: 26] ------------------ 1075| 4| group = false; 1076| 4| ++i; 1077| 26| } else if (group) { ------------------ | Branch (1077:16): [True: 18, False: 8] ------------------ 1078| 18| ++i; 1079| 18| } else { 1080| 8| ++l; 1081| 8| i = utf8 ? utf8_next(s, i) : i + 1; ------------------ | Branch (1081:11): [True: 8, False: 0] ------------------ 1082| 8| } 1083| 34| } 1084| 8| return l; 1085| 8|} _ZN8AffixMgr8encodeitER8AffEntryRKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEE: 1087| 42|int AffixMgr::encodeit(AffEntry& entry, const std::string& cs) { 1088| 42| if (cs.compare(".") != 0) { ------------------ | Branch (1088:7): [True: 8, False: 34] ------------------ 1089| 8| int n = condlen(cs); 1090| 8| if (n > std::numeric_limits::max()) { ------------------ | Branch (1090:9): [True: 0, False: 8] ------------------ 1091| 0| HUNSPELL_WARNING(stderr, "error: condition length %d is over max limit\n", n); 1092| 0| return 1; 1093| 0| } 1094| 8| entry.numconds = (unsigned char)n; 1095| 8| const size_t cslen = cs.size(); 1096| 8| const size_t short_part = std::min(MAXCONDLEN, cslen); ------------------ | | 93| 8|#define MAXCONDLEN 20 ------------------ 1097| 8| memcpy(entry.c.conds, cs.data(), short_part); 1098| 8| if (short_part < MAXCONDLEN) { ------------------ | | 93| 8|#define MAXCONDLEN 20 ------------------ | Branch (1098:9): [True: 8, False: 0] ------------------ 1099| | //blank out the remaining space 1100| 8| memset(entry.c.conds + short_part, 0, MAXCONDLEN - short_part); ------------------ | | 93| 8|#define MAXCONDLEN 20 ------------------ 1101| 8| } else if (cs[MAXCONDLEN]) { ------------------ | | 93| 0|#define MAXCONDLEN 20 ------------------ | Branch (1101:16): [True: 0, False: 0] ------------------ 1102| | //there is more conditions than fit in fixed space, so its 1103| | //a long condition 1104| 0| entry.opts |= aeLONGCOND; ------------------ | | 69| 0|#define aeLONGCOND (1 << 4) ------------------ 1105| 0| size_t remaining = cs.size() - MAXCONDLEN_1; ------------------ | | 94| 0|#define MAXCONDLEN_1 (MAXCONDLEN - sizeof(char*)) | | ------------------ | | | | 93| 0|#define MAXCONDLEN 20 | | ------------------ ------------------ 1106| 0| entry.c.l.conds2 = new char[1 + remaining]; 1107| 0| memcpy(entry.c.l.conds2, cs.data() + MAXCONDLEN_1, remaining); ------------------ | | 94| 0|#define MAXCONDLEN_1 (MAXCONDLEN - sizeof(char*)) | | ------------------ | | | | 93| 0|#define MAXCONDLEN 20 | | ------------------ ------------------ 1108| 0| entry.c.l.conds2[remaining] = 0; 1109| 0| } 1110| 34| } else { 1111| 34| entry.numconds = 0; 1112| 34| entry.c.conds[0] = '\0'; 1113| 34| } 1114| 42| return 0; 1115| 42|} _ZN8AffixMgr12prefix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratchtt: 1133| 539M| const FLAG avoidflag) { 1134| 539M| struct hentry* rv = nullptr; 1135| | 1136| 539M| pfx = nullptr; 1137| 539M| pfxappnd = nullptr; 1138| 539M| sfxappnd = nullptr; 1139| 539M| sfxextra = 0; 1140| | 1141| 539M| TraceCtx* t = trace_on(scratch.trace); 1142| 539M| int candidates = 0; 1143| | 1144| | // first handle the special case of 0 length prefixes 1145| 539M| PfxEntry* pe = pStart[0]; 1146| 540M| while (pe) { ------------------ | Branch (1146:10): [True: 1.36M, False: 539M] ------------------ 1147| 1.36M| if ( 1148| | // fogemorpheme 1149| 1.36M| ((in_compound != IN_CPD_NOT) || ------------------ | | 75| 1.36M|#define IN_CPD_NOT 0 ------------------ | Branch (1149:10): [True: 0, False: 1.36M] ------------------ 1150| 1.36M| !(pe->getCont() && ------------------ | Branch (1150:12): [True: 1.36M, False: 0] ------------------ 1151| 1.36M| (TESTAFF(pe->getCont(), onlyincompound, pe->getContLen())))) && ------------------ | | 102| 1.36M|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1151:12): [True: 0, False: 1.36M] ------------------ 1152| | // permit prefixes in compounds 1153| 1.36M| ((in_compound != IN_CPD_END) || ------------------ | | 77| 1.36M|#define IN_CPD_END 2 ------------------ | Branch (1153:10): [True: 1.36M, False: 0] ------------------ 1154| 0| (pe->getCont() && ------------------ | Branch (1154:11): [True: 0, False: 0] ------------------ 1155| 1.36M| (TESTAFF(pe->getCont(), compoundpermitflag, pe->getContLen()))))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1155:11): [True: 0, False: 0] ------------------ 1156| | // check prefix 1157| 1.36M| ++candidates; 1158| 1.36M| rv = pe->checkword(word, start, len, in_compound, needflag, scratch); 1159| | // Skip a stem with the avoid flag and keep scanning the other prefixes. 1160| 1.36M| if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) { ------------------ | | 99| 1.36M|#define FLAG_NULL 0x00 ------------------ if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1160:11): [True: 0, False: 1.36M] | Branch (1160:17): [True: 0, False: 0] ------------------ 1161| 0| trace_avoidflag(t, avoidflag, rv); 1162| 0| rv = nullptr; 1163| 0| } 1164| 1.36M| if (rv) { ------------------ | Branch (1164:11): [True: 0, False: 1.36M] ------------------ 1165| 0| pfx = pe; // BUG: pfx not stateless 1166| 0| return rv; 1167| 0| } 1168| 1.36M| } 1169| 1.36M| pe = pe->getNext(); 1170| 1.36M| } 1171| | 1172| | // now handle the general case 1173| 539M| unsigned char sp = word[start]; 1174| 539M| PfxEntry* pptr = pStart[sp]; 1175| | 1176| 539M| while (pptr) { ------------------ | Branch (1176:10): [True: 68.3k, False: 539M] ------------------ 1177| 68.3k| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1177:9): [True: 39.5k, False: 28.7k] ------------------ 1178| 39.5k| if ( 1179| | // fogemorpheme 1180| 39.5k| ((in_compound != IN_CPD_NOT) || ------------------ | | 75| 39.5k|#define IN_CPD_NOT 0 ------------------ | Branch (1180:12): [True: 0, False: 39.5k] ------------------ 1181| 39.5k| !(pptr->getCont() && ------------------ | Branch (1181:14): [True: 35.5k, False: 3.97k] ------------------ 1182| 35.5k| (TESTAFF(pptr->getCont(), onlyincompound, pptr->getContLen())))) && ------------------ | | 102| 35.5k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1182:14): [True: 0, False: 35.5k] ------------------ 1183| | // permit prefixes in compounds 1184| 39.5k| ((in_compound != IN_CPD_END) || ------------------ | | 77| 39.5k|#define IN_CPD_END 2 ------------------ | Branch (1184:12): [True: 39.5k, False: 0] ------------------ 1185| 0| (pptr->getCont() && (TESTAFF(pptr->getCont(), compoundpermitflag, ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1185:13): [True: 0, False: 0] | Branch (1185:32): [True: 0, False: 0] ------------------ 1186| 39.5k| pptr->getContLen()))))) { 1187| | // check prefix 1188| 39.5k| ++candidates; 1189| 39.5k| rv = pptr->checkword(word, start, len, in_compound, needflag, scratch); 1190| 39.5k| if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) { ------------------ | | 99| 39.5k|#define FLAG_NULL 0x00 ------------------ if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1190:13): [True: 0, False: 39.5k] | Branch (1190:19): [True: 0, False: 0] ------------------ 1191| 0| trace_avoidflag(t, avoidflag, rv); 1192| 0| rv = nullptr; 1193| 0| } 1194| 39.5k| if (rv) { ------------------ | Branch (1194:13): [True: 0, False: 39.5k] ------------------ 1195| 0| pfx = pptr; // BUG: pfx not stateless 1196| 0| return rv; 1197| 0| } 1198| 39.5k| } 1199| 39.5k| pptr = pptr->getNextEQ(); 1200| 39.5k| } else { 1201| 28.7k| pptr = pptr->getNextNE(); 1202| 28.7k| } 1203| 68.3k| } 1204| | 1205| | // a pass that had nothing to try says so, which is different from a pass that 1206| | // did not run 1207| 539M| if (t && candidates == 0) ------------------ | Branch (1207:7): [True: 0, False: 539M] | Branch (1207:12): [True: 0, False: 0] ------------------ 1208| 0| trace(*t, "pfx \"%s\" candidates=0", word.substr(start, len).c_str()); 1209| | 1210| 539M| return nullptr; 1211| 539M|} _ZN8AffixMgr19prefix_check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratcht: 1219| 16.6M| const FLAG needflag) { 1220| 16.6M| struct hentry* rv = nullptr; 1221| | 1222| 16.6M| pfx = nullptr; 1223| 16.6M| sfxappnd = nullptr; 1224| 16.6M| sfxextra = 0; 1225| | 1226| | // first handle the special case of 0 length prefixes 1227| 16.6M| PfxEntry* pe = pStart[0]; 1228| | 1229| 17.9M| while (pe) { ------------------ | Branch (1229:10): [True: 1.36M, False: 16.6M] ------------------ 1230| 1.36M| rv = pe->check_twosfx(word, start, len, in_compound, needflag, scratch); 1231| 1.36M| if (rv) ------------------ | Branch (1231:9): [True: 0, False: 1.36M] ------------------ 1232| 0| return rv; 1233| 1.36M| pe = pe->getNext(); 1234| 1.36M| } 1235| | 1236| | // now handle the general case 1237| 16.6M| unsigned char sp = word[start]; 1238| 16.6M| PfxEntry* pptr = pStart[sp]; 1239| | 1240| 16.6M| while (pptr) { ------------------ | Branch (1240:10): [True: 64.3k, False: 16.6M] ------------------ 1241| 64.3k| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1241:9): [True: 35.5k, False: 28.7k] ------------------ 1242| 35.5k| rv = pptr->check_twosfx(word, start, len, in_compound, needflag, scratch); 1243| 35.5k| if (rv) { ------------------ | Branch (1243:11): [True: 0, False: 35.5k] ------------------ 1244| 0| pfx = pptr; 1245| 0| return rv; 1246| 0| } 1247| 35.5k| pptr = pptr->getNextEQ(); 1248| 35.5k| } else { 1249| 28.7k| pptr = pptr->getNextNE(); 1250| 28.7k| } 1251| 64.3k| } 1252| | 1253| 16.6M| return nullptr; 1254| 16.6M|} _ZN8AffixMgr18prefix_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratcht: 1262| 12.7k| const FLAG needflag) { 1263| | 1264| | // many prefixes can analyse a word the same way 1265| 12.7k| DistinctRecords result(MSEP_REC); ------------------ | | 122| 12.7k|#define MSEP_REC '\n' ------------------ 1266| | 1267| 12.7k| pfx = nullptr; 1268| 12.7k| sfxappnd = nullptr; 1269| 12.7k| sfxextra = 0; 1270| | 1271| | // first handle the special case of 0 length prefixes 1272| 12.7k| PfxEntry* pe = pStart[0]; 1273| 13.4k| while (pe) { ------------------ | Branch (1273:10): [True: 702, False: 12.7k] ------------------ 1274| 702| std::string st = pe->check_morph(word, start, len, in_compound, needflag, scratch); 1275| 702| if (!st.empty()) { ------------------ | Branch (1275:9): [True: 0, False: 702] ------------------ 1276| 0| result.append(st); 1277| 0| } 1278| 702| pe = pe->getNext(); 1279| 702| } 1280| | 1281| | // now handle the general case 1282| 12.7k| unsigned char sp = word[start]; 1283| 12.7k| PfxEntry* pptr = pStart[sp]; 1284| | 1285| 12.7k| while (pptr) { ------------------ | Branch (1285:10): [True: 2, False: 12.7k] ------------------ 1286| 2| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1286:9): [True: 2, False: 0] ------------------ 1287| 2| std::string st = pptr->check_morph(word, start, len, in_compound, needflag, scratch); 1288| 2| if (!st.empty()) { ------------------ | Branch (1288:11): [True: 0, False: 2] ------------------ 1289| | // fogemorpheme 1290| 0| if ((in_compound != IN_CPD_NOT) || ------------------ | | 75| 0|#define IN_CPD_NOT 0 ------------------ | Branch (1290:13): [True: 0, False: 0] ------------------ 1291| 0| !((pptr->getCont() && (TESTAFF(pptr->getCont(), onlyincompound, ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1291:16): [True: 0, False: 0] | Branch (1291:35): [True: 0, False: 0] ------------------ 1292| 0| pptr->getContLen()))))) { 1293| 0| result.append(st); 1294| 0| pfx = pptr; 1295| 0| } 1296| 0| } 1297| 2| pptr = pptr->getNextEQ(); 1298| 2| } else { 1299| 0| pptr = pptr->getNextNE(); 1300| 0| } 1301| 2| } 1302| | 1303| 12.7k| return result.join(); 1304| 12.7k|} _ZN8AffixMgr25prefix_check_twosfx_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratcht: 1312| 3.97k| const FLAG needflag) { 1313| | // every prefix crosses with every pair of suffixes 1314| 3.97k| DistinctRecords result(MSEP_REC); ------------------ | | 122| 3.97k|#define MSEP_REC '\n' ------------------ 1315| | 1316| 3.97k| pfx = nullptr; 1317| 3.97k| sfxappnd = nullptr; 1318| 3.97k| sfxextra = 0; 1319| | 1320| | // first handle the special case of 0 length prefixes 1321| 3.97k| PfxEntry* pe = pStart[0]; 1322| 4.67k| while (pe) { ------------------ | Branch (1322:10): [True: 702, False: 3.97k] ------------------ 1323| 702| std::string st = pe->check_twosfx_morph(word, start, len, in_compound, needflag, scratch); 1324| 702| if (!st.empty()) { ------------------ | Branch (1324:9): [True: 0, False: 702] ------------------ 1325| 0| result.append(st); 1326| 0| } 1327| 702| pe = pe->getNext(); 1328| 702| } 1329| | 1330| | // now handle the general case 1331| 3.97k| unsigned char sp = word[start]; 1332| 3.97k| PfxEntry* pptr = pStart[sp]; 1333| | 1334| 3.97k| while (pptr) { ------------------ | Branch (1334:10): [True: 0, False: 3.97k] ------------------ 1335| 0| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1335:9): [True: 0, False: 0] ------------------ 1336| 0| std::string st = pptr->check_twosfx_morph(word, start, len, in_compound, needflag, scratch); 1337| 0| if (!st.empty()) { ------------------ | Branch (1337:11): [True: 0, False: 0] ------------------ 1338| 0| result.append(st); 1339| 0| pfx = pptr; 1340| 0| } 1341| 0| pptr = pptr->getNextEQ(); 1342| 0| } else { 1343| 0| pptr = pptr->getNextNE(); 1344| 0| } 1345| 0| } 1346| | 1347| 3.97k| return result.join(); 1348| 3.97k|} _ZN8AffixMgr12get_syllableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1694| 670|short AffixMgr::get_syllable(const std::string& word) { 1695| 670| if (cpdmaxsyllable == 0) ------------------ | Branch (1695:7): [True: 0, False: 670] ------------------ 1696| 0| return 0; 1697| | 1698| 670| short num = 0; 1699| | 1700| 670| if (!utf8) { ------------------ | Branch (1700:7): [True: 0, False: 670] ------------------ 1701| 0| num = (short)std::count_if(word.begin(), word.end(), 1702| 0| [&](char c) { 1703| 0| return std::binary_search(cpdvowels.begin(), cpdvowels.end(), c); 1704| 0| }); 1705| 670| } else if (!cpdvowels_utf16.empty()) { ------------------ | Branch (1705:14): [True: 670, False: 0] ------------------ 1706| 670| std::vector w; 1707| 670| u8_u16(w, word); 1708| 670| num = (short)std::count_if(w.begin(), w.end(), 1709| 670| [&](w_char wc) { 1710| 670| return std::binary_search(cpdvowels_utf16.begin(), cpdvowels_utf16.end(), wc); 1711| 670| }); 1712| 670| } 1713| | 1714| 670| return num; 1715| 670|} _ZN8AffixMgr10setcminmaxEPmS0_PKcm: 1717| 23.3M|void AffixMgr::setcminmax(size_t* cmin, size_t* cmax, const char* word, size_t len) { 1718| 23.3M| if (utf8) { ------------------ | Branch (1718:7): [True: 1.71M, False: 21.6M] ------------------ 1719| 1.71M| int i; 1720| 5.11M| for (*cmin = 0, i = 0; (i < cpdmin) && *cmin < len; i++) { ------------------ | Branch (1720:28): [True: 3.42M, False: 1.68M] | Branch (1720:44): [True: 3.39M, False: 25.1k] ------------------ 1721| 3.87M| for ((*cmin)++; *cmin < len && is_utf8_cont(word[*cmin]); (*cmin)++) ------------------ | Branch (1721:23): [True: 3.83M, False: 42.4k] | Branch (1721:38): [True: 481k, False: 3.35M] ------------------ 1722| 481k| ; 1723| 3.39M| } 1724| 3.42M| for (*cmax = len, i = 0; (i < (cpdmin - 1)) && *cmax > 0; i++) { ------------------ | Branch (1724:30): [True: 1.71M, False: 1.70M] | Branch (1724:52): [True: 1.70M, False: 3.50k] ------------------ 1725| 2.64M| for ((*cmax)--; *cmax > 0 && is_utf8_cont(word[*cmax]); (*cmax)--) ------------------ | Branch (1725:23): [True: 2.62M, False: 21.6k] | Branch (1725:36): [True: 938k, False: 1.68M] ------------------ 1726| 938k| ; 1727| 1.70M| } 1728| 21.6M| } else { 1729| 21.6M| *cmin = cpdmin; 1730| 21.6M| *cmax = len - cpdmin + 1; 1731| 21.6M| } 1732| 23.3M|} _ZN8AffixMgr14compound_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEssssPP6hentrySB_ccPiR12AffixScratch: 1746| 23.3M| AffixScratch& scratch) { 1747| 23.3M| short oldnumsyllable, oldnumsyllable2, oldwordnum, oldwordnum2; 1748| 23.3M| hentry *rv = nullptr, *rv_first; 1749| 23.3M| std::string st; 1750| 23.3M| char ch = '\0', affixed; 1751| 23.3M| size_t cmin, cmax; 1752| 23.3M| int striple = 0, soldi = 0, oldcmin = 0, oldcmax = 0, oldlen = 0, checkedstriple = 0; 1753| 23.3M| hentry** oldwords = words; 1754| 23.3M| size_t scpd = 0, len = word.size(); 1755| | 1756| 23.3M| TraceCtx* t = trace_on(scratch.trace); 1757| | 1758| | // protect subsequent words[wnum + 1] reads and any recursion 1759| 23.3M| if (wnum + 1 >= maxwordnum) ------------------ | Branch (1759:7): [True: 0, False: 23.3M] ------------------ 1760| 0| return nullptr; 1761| | 1762| 23.3M| int checked_prefix; 1763| | 1764| | // add a time limit to handle possible 1765| | // combinatorical explosion of the overlapping words 1766| | 1767| 23.3M| HUNSPELL_THREAD_LOCAL std::chrono::steady_clock::time_point clock_time_start; ------------------ | | 60| 23.3M|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 1768| 23.3M| HUNSPELL_THREAD_LOCAL bool timelimit_exceeded; ------------------ | | 60| 23.3M|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 1769| | 1770| | // get the current time 1771| 23.3M| std::chrono::steady_clock::time_point clock_now = std::chrono::steady_clock::now(); 1772| | 1773| 23.3M| if (wnum == 0) { ------------------ | Branch (1773:7): [True: 23.3M, False: 289] ------------------ 1774| | // set the start time 1775| 23.3M| clock_time_start = clock_now; 1776| 23.3M| timelimit_exceeded = false; 1777| 23.3M| } 1778| 289| else if (clock_now - clock_time_start > TIMELIMIT_MS) ------------------ | | 109| 289|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (1778:12): [True: 0, False: 289] ------------------ 1779| 0| timelimit_exceeded = true; 1780| | 1781| 23.3M| setcminmax(&cmin, &cmax, word.c_str(), len); 1782| | 1783| | // with SIMPLIFIEDTRIPLE a second part that starts at a doubled letter is one letter longer 1784| | // than the surface shows, so the split can go one letter past cmax 1785| 23.3M| size_t cmaxtriple = simplifiedtriple ? (utf8 ? utf8_next(word, cmax) : cmax + 1) : cmax; ------------------ | Branch (1785:23): [True: 0, False: 23.3M] | Branch (1785:43): [True: 0, False: 0] ------------------ 1786| | 1787| 23.3M| st.assign(word); 1788| | 1789| 514M| for (size_t i = cmin; i < cmaxtriple; ++i) { ------------------ | Branch (1789:25): [True: 491M, False: 22.2M] ------------------ 1790| | // go to end of the UTF-8 character 1791| 491M| if (utf8) { ------------------ | Branch (1791:9): [True: 40.3M, False: 451M] ------------------ 1792| 50.1M| for (; is_utf8_cont(st[i]); i++) ------------------ | Branch (1792:14): [True: 9.75M, False: 40.3M] ------------------ 1793| 9.75M| ; 1794| 40.3M| if (i >= cmaxtriple) ------------------ | Branch (1794:11): [True: 164k, False: 40.2M] ------------------ 1795| 164k| return nullptr; 1796| 40.3M| } 1797| 491M| if (i >= cmax && !(i > 2 && word[i - 1] == word[i - 2])) ------------------ | Branch (1797:9): [True: 0, False: 491M] | Branch (1797:24): [True: 0, False: 0] | Branch (1797:33): [True: 0, False: 0] ------------------ 1798| 0| break; 1799| | 1800| 491M| words = oldwords; 1801| 491M| int onlycpdrule = (words) ? 1 : 0; ------------------ | Branch (1801:23): [True: 0, False: 491M] ------------------ 1802| | 1803| 491M| do { // onlycpdrule loop 1804| | 1805| 491M| oldnumsyllable = numsyllable; 1806| 491M| oldwordnum = wordnum; 1807| 491M| checked_prefix = 0; 1808| | 1809| 491M| do { // simplified checkcompoundpattern loop 1810| | 1811| 491M| if (timelimit_exceeded || ------------------ | Branch (1811:13): [True: 0, False: 491M] | Branch (1811:13): [True: 0, False: 491M] ------------------ 1812| 491M| std::chrono::steady_clock::now() - clock_time_start > TIMELIMIT_MS) { ------------------ | | 109| 491M|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (1812:13): [True: 0, False: 491M] ------------------ 1813| 0| if (t && !timelimit_exceeded) ------------------ | Branch (1813:15): [True: 0, False: 0] | Branch (1813:20): [True: 0, False: 0] ------------------ 1814| 0| trace(*t, "test timelimit -> fail, the compound search stops here and gives up"); 1815| 0| timelimit_exceeded = true; 1816| 0| return nullptr; 1817| 0| } 1818| | 1819| 491M| if (scpd > 0) { ------------------ | Branch (1819:13): [True: 0, False: 491M] ------------------ 1820| 0| for (; scpd <= checkcpdtable.size() && ------------------ | Branch (1820:18): [True: 0, False: 0] ------------------ 1821| 0| (checkcpdtable[scpd - 1].pattern3.empty() || ------------------ | Branch (1821:19): [True: 0, False: 0] ------------------ 1822| 0| i > word.size() || ------------------ | Branch (1822:19): [True: 0, False: 0] ------------------ 1823| 0| word.compare(i, checkcpdtable[scpd - 1].pattern3.size(), checkcpdtable[scpd - 1].pattern3) != 0); ------------------ | Branch (1823:19): [True: 0, False: 0] ------------------ 1824| 0| scpd++) 1825| 0| ; 1826| | 1827| 0| if (scpd > checkcpdtable.size()) ------------------ | Branch (1827:15): [True: 0, False: 0] ------------------ 1828| 0| break; // break simplified checkcompoundpattern loop 1829| 0| st.replace(i, std::string::npos, checkcpdtable[scpd - 1].pattern); 1830| 0| soldi = i; 1831| 0| i += checkcpdtable[scpd - 1].pattern.size(); 1832| 0| st.replace(i, std::string::npos, checkcpdtable[scpd - 1].pattern2); 1833| 0| st.replace(i + checkcpdtable[scpd - 1].pattern2.size(), std::string::npos, 1834| 0| word.substr(soldi + checkcpdtable[scpd - 1].pattern3.size())); 1835| | 1836| 0| oldlen = len; 1837| 0| len += checkcpdtable[scpd - 1].pattern.size() + 1838| 0| checkcpdtable[scpd - 1].pattern2.size() - 1839| 0| checkcpdtable[scpd - 1].pattern3.size(); 1840| 0| oldcmin = cmin; 1841| 0| oldcmax = cmax; 1842| 0| setcminmax(&cmin, &cmax, st.c_str(), len); 1843| | 1844| 0| cmax = len - cpdmin + 1; 1845| 0| } 1846| | 1847| 491M| if (i >= st.size()) ------------------ | Branch (1847:13): [True: 914k, False: 490M] ------------------ 1848| 914k| return nullptr; 1849| | 1850| 490M| ch = st[i]; 1851| 490M| if (t) { ------------------ | Branch (1851:13): [True: 0, False: 490M] ------------------ 1852| | // a non-zero scpd means this split is the retry that one CHECKCOMPOUNDPATTERN entry asks 1853| | // for, with the text at the join replaced by the two sides of that entry 1854| 0| if (scpd != 0) ------------------ | Branch (1854:15): [True: 0, False: 0] ------------------ 1855| 0| trace(*t, "split at=%d left=\"%s\" right=\"%s\" cpdpattern=%d", (int)i, 1856| 0| st.substr(0, i).c_str(), st.substr(i).c_str(), (int)scpd); 1857| 0| else 1858| 0| trace(*t, "split at=%d left=\"%s\" right=\"%s\"", (int)i, 1859| 0| st.substr(0, i).c_str(), st.substr(i).c_str()); 1860| 0| } 1861| | // everything this split point tries belongs to the split 1862| 490M| TraceScope split_depth(t); 1863| 490M| st[i] = '\0'; 1864| | 1865| 490M| sfx = nullptr; 1866| 490M| pfx = nullptr; 1867| | 1868| | // FIRST WORD 1869| | 1870| 490M| affixed = 1; 1871| 490M| rv = lookup(st.c_str(), i); // perhaps without prefix 1872| 490M| if (t) { ------------------ | Branch (1872:13): [True: 0, False: 490M] ------------------ 1873| 0| if (rv) ------------------ | Branch (1873:15): [True: 0, False: 0] ------------------ 1874| 0| trace(*t, "first \"%s\" -> entry \"%s\" flags=%s", st.c_str(), 1875| 0| rv->word, trace_flags(this, rv->astr, rv->alen).c_str()); 1876| 0| else 1877| 0| trace(*t, "first \"%s\" -> miss", st.c_str()); 1878| 0| } 1879| | 1880| | // forbid dictionary stems with COMPOUNDFORBIDFLAG in 1881| | // compound words, overriding the effect of COMPOUNDPERMITFLAG 1882| 490M| if ((rv) && compoundforbidflag && ------------------ | Branch (1882:13): [True: 2.94M, False: 487M] | Branch (1882:21): [True: 49.5k, False: 2.89M] ------------------ 1883| 49.5k| TESTAFF(rv->astr, compoundforbidflag, rv->alen) && !hu_mov_rule) { ------------------ | | 102| 490M|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 49.5k] | | ------------------ ------------------ | Branch (1883:68): [True: 0, False: 0] ------------------ 1884| 0| bool would_continue = !onlycpdrule && simplifiedcpd; ------------------ | Branch (1884:35): [True: 0, False: 0] | Branch (1884:51): [True: 0, False: 0] ------------------ 1885| 0| if (!scpd && would_continue) { ------------------ | Branch (1885:17): [True: 0, False: 0] | Branch (1885:26): [True: 0, False: 0] ------------------ 1886| | // given the while conditions that continue jumps to, this situation 1887| | // never ends 1888| 0| HUNSPELL_WARNING(stderr, "break infinite loop\n"); 1889| 0| break; 1890| 0| } 1891| | 1892| 0| if (scpd > 0 && would_continue) { ------------------ | Branch (1892:17): [True: 0, False: 0] | Branch (1892:29): [True: 0, False: 0] ------------------ 1893| | // under these conditions we loop again, but the assumption above 1894| | // appears to be that cmin and cmax are the original values they 1895| | // had in the outside loop 1896| 0| cmin = oldcmin; 1897| 0| cmax = oldcmax; 1898| 0| } 1899| 0| continue; 1900| 0| } 1901| | 1902| | // search homonym with compound flag 1903| 493M| while ((rv) && !hu_mov_rule && ------------------ | Branch (1903:16): [True: 2.94M, False: 490M] | Branch (1903:24): [True: 2.94M, False: 268] ------------------ 1904| 2.94M| ((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) || ------------------ | | 102| 965k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 965k] | | ------------------ ------------------ | Branch (1904:18): [True: 965k, False: 1.97M] ------------------ 1905| 2.94M| !((compoundflag && !words && !onlycpdrule && ------------------ | Branch (1905:20): [True: 2.94M, False: 0] | Branch (1905:36): [True: 2.94M, False: 0] | Branch (1905:46): [True: 2.94M, False: 0] ------------------ 1906| 2.94M| TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 102| 2.94M|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 472, False: 2.94M] | | ------------------ ------------------ 1907| 2.94M| (compoundbegin && !wordnum && !onlycpdrule && ------------------ | Branch (1907:20): [True: 0, False: 2.94M] | Branch (1907:37): [True: 0, False: 0] | Branch (1907:49): [True: 0, False: 0] ------------------ 1908| 0| TESTAFF(rv->astr, compoundbegin, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1909| 2.94M| (compoundmiddle && wordnum && !words && !onlycpdrule && ------------------ | Branch (1909:20): [True: 0, False: 2.94M] | Branch (1909:38): [True: 0, False: 0] | Branch (1909:49): [True: 0, False: 0] | Branch (1909:59): [True: 0, False: 0] ------------------ 1910| 0| TESTAFF(rv->astr, compoundmiddle, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1911| 2.94M| (!defcpdtable.empty() && onlycpdrule && ------------------ | Branch (1911:20): [True: 0, False: 2.94M] | Branch (1911:44): [True: 0, False: 0] ------------------ 1912| 0| ((!words && !wordnum && ------------------ | Branch (1912:22): [True: 0, False: 0] | Branch (1912:32): [True: 0, False: 0] ------------------ 1913| 0| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0)) || ------------------ | Branch (1913:22): [True: 0, False: 0] ------------------ 1914| 0| (words && ------------------ | Branch (1914:22): [True: 0, False: 0] ------------------ 1915| 0| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0))))) || ------------------ | Branch (1915:22): [True: 0, False: 0] ------------------ 1916| 472| (scpd != 0 && checkcpdtable[scpd - 1].cond != FLAG_NULL && ------------------ | | 99| 472|#define FLAG_NULL 0x00 ------------------ | Branch (1916:18): [True: 0, False: 472] | Branch (1916:31): [True: 0, False: 0] ------------------ 1917| 2.94M| !TESTAFF(rv->astr, checkcpdtable[scpd - 1].cond, rv->alen)))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1917:18): [True: 0, False: 0] ------------------ 1918| 2.94M| rv = rv->next_homonym; 1919| 2.94M| } 1920| | 1921| 490M| if (rv) ------------------ | Branch (1921:13): [True: 740, False: 490M] ------------------ 1922| 740| affixed = 0; 1923| | 1924| 490M| if (!rv) { ------------------ | Branch (1924:13): [True: 490M, False: 740] ------------------ 1925| 490M| if (onlycpdrule) ------------------ | Branch (1925:15): [True: 0, False: 490M] ------------------ 1926| 0| break; 1927| 490M| if (compoundflag && ------------------ | Branch (1927:15): [True: 490M, False: 0] ------------------ 1928| 490M| !(rv = prefix_check(st, 0, i, ------------------ | Branch (1928:15): [True: 490M, False: 0] ------------------ 1929| 490M| hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, ------------------ | | 78| 116k|#define IN_CPD_OTHER 3 ------------------ hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, ------------------ | | 76| 981M|#define IN_CPD_BEGIN 1 ------------------ | Branch (1929:35): [True: 116k, False: 490M] ------------------ 1930| 490M| scratch, compoundflag))) { 1931| 490M| if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 99| 490M|#define FLAG_NULL 0x00 ------------------ if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 78| 116k|#define IN_CPD_OTHER 3 ------------------ if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 76| 981M|#define IN_CPD_BEGIN 1 ------------------ | Branch (1931:18): [True: 0, False: 490M] | Branch (1931:93): [True: 116k, False: 490M] ------------------ 1932| 490M| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, compoundflag)))) && ------------------ | Branch (1932:19): [True: 0, False: 490M] | Branch (1932:43): [True: 0, False: 0] ------------------ 1933| 0| !hu_mov_rule && sfx->getCont() && ------------------ | Branch (1933:17): [True: 0, False: 0] | Branch (1933:33): [True: 0, False: 0] ------------------ 1934| 0| ((compoundforbidflag && TESTAFF(sfx->getCont(), compoundforbidflag, sfx->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1934:19): [True: 0, False: 0] ------------------ 1935| 0| (compoundend && TESTAFF(sfx->getCont(), compoundend, sfx->getContLen())))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1935:19): [True: 0, False: 0] ------------------ 1936| 0| rv = nullptr; 1937| | // the suffix is dropped with the word it built 1938| 0| sfx = nullptr; 1939| 0| } 1940| 490M| } 1941| | 1942| 490M| if (rv || ------------------ | Branch (1942:15): [True: 0, False: 490M] ------------------ 1943| 490M| (((wordnum == 0) && compoundbegin && ------------------ | Branch (1943:17): [True: 490M, False: 117k] | Branch (1943:35): [True: 0, False: 490M] ------------------ 1944| 0| ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundbegin, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundbegin, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 78| 0|#define IN_CPD_OTHER 3 ------------------ ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundbegin, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 76| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (1944:18): [True: 0, False: 0] | Branch (1944:94): [True: 0, False: 0] ------------------ 1945| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (1945:19): [True: 0, False: 0] | Branch (1945:43): [True: 0, False: 0] ------------------ 1946| 0| compoundbegin))) || // twofold suffixes + compound 1947| 0| (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundbegin)))) || ------------------ | | 78| 0|#define IN_CPD_OTHER 3 ------------------ (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundbegin)))) || ------------------ | | 76| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (1947:18): [True: 0, False: 0] | Branch (1947:47): [True: 0, False: 0] ------------------ 1948| 490M| ((wordnum > 0) && compoundmiddle && ------------------ | Branch (1948:17): [True: 960, False: 490M] | Branch (1948:34): [True: 0, False: 960] ------------------ 1949| 0| ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundmiddle, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundmiddle, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 78| 0|#define IN_CPD_OTHER 3 ------------------ ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundmiddle, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 76| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (1949:18): [True: 0, False: 0] | Branch (1949:95): [True: 0, False: 0] ------------------ 1950| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (1950:19): [True: 0, False: 0] | Branch (1950:43): [True: 0, False: 0] ------------------ 1951| 0| compoundmiddle))) || // twofold suffixes + compound 1952| 0| (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundmiddle)))))) ------------------ | | 78| 0|#define IN_CPD_OTHER 3 ------------------ (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundmiddle)))))) ------------------ | | 76| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (1952:18): [True: 0, False: 0] | Branch (1952:47): [True: 0, False: 0] ------------------ 1953| 0| checked_prefix = 1; 1954| | // else check forbiddenwords and needaffix 1955| 490M| } else if (rv->astr && (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 102| 1.05k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 525] | | ------------------ ------------------ | Branch (1955:20): [True: 525, False: 215] | Branch (1955:20): [True: 0, False: 740] ------------------ 1956| 525| TESTAFF(rv->astr, needaffix, rv->alen) || ------------------ | | 102| 1.05k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 525] | | ------------------ ------------------ 1957| 525| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 102| 1.05k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 525] | | ------------------ ------------------ 1958| 525| (is_sug && nosuggest && ------------------ | Branch (1958:34): [True: 6, False: 519] | Branch (1958:44): [True: 0, False: 6] ------------------ 1959| 0| TESTAFF(rv->astr, nosuggest, rv->alen)))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1960| 0| st[i] = ch; 1961| | // continue; 1962| 0| break; 1963| 0| } 1964| | 1965| | // check non_compound flag in suffix and prefix 1966| 490M| if ((rv) && !hu_mov_rule && ------------------ | Branch (1966:13): [True: 740, False: 490M] | Branch (1966:21): [True: 472, False: 268] ------------------ 1967| 472| ((pfx && pfx->getCont() && ------------------ | Branch (1967:15): [True: 0, False: 472] | Branch (1967:22): [True: 0, False: 0] ------------------ 1968| 0| TESTAFF(pfx->getCont(), compoundforbidflag, pfx->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1969| 472| (sfx && sfx->getCont() && ------------------ | Branch (1969:15): [True: 0, False: 472] | Branch (1969:22): [True: 0, False: 0] ------------------ 1970| 0| TESTAFF(sfx->getCont(), compoundforbidflag, ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1971| 472| sfx->getContLen())))) { 1972| 0| rv = nullptr; 1973| 0| } 1974| | 1975| | // check compoundend flag in suffix and prefix 1976| 490M| if ((rv) && !checked_prefix && compoundend && !hu_mov_rule && ------------------ | Branch (1976:13): [True: 740, False: 490M] | Branch (1976:21): [True: 740, False: 0] | Branch (1976:40): [True: 0, False: 740] | Branch (1976:55): [True: 0, False: 0] ------------------ 1977| 0| ((pfx && pfx->getCont() && ------------------ | Branch (1977:15): [True: 0, False: 0] | Branch (1977:22): [True: 0, False: 0] ------------------ 1978| 0| TESTAFF(pfx->getCont(), compoundend, pfx->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1979| 0| (sfx && sfx->getCont() && ------------------ | Branch (1979:15): [True: 0, False: 0] | Branch (1979:22): [True: 0, False: 0] ------------------ 1980| 0| TESTAFF(sfx->getCont(), compoundend, sfx->getContLen())))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1981| 0| rv = nullptr; 1982| 0| } 1983| | 1984| | // check compoundmiddle flag in suffix and prefix 1985| 490M| if ((rv) && !checked_prefix && (wordnum == 0) && compoundmiddle && ------------------ | Branch (1985:13): [True: 740, False: 490M] | Branch (1985:21): [True: 740, False: 0] | Branch (1985:40): [True: 472, False: 268] | Branch (1985:58): [True: 0, False: 472] ------------------ 1986| 0| !hu_mov_rule && ------------------ | Branch (1986:13): [True: 0, False: 0] ------------------ 1987| 0| ((pfx && pfx->getCont() && ------------------ | Branch (1987:15): [True: 0, False: 0] | Branch (1987:22): [True: 0, False: 0] ------------------ 1988| 0| TESTAFF(pfx->getCont(), compoundmiddle, pfx->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1989| 0| (sfx && sfx->getCont() && ------------------ | Branch (1989:15): [True: 0, False: 0] | Branch (1989:22): [True: 0, False: 0] ------------------ 1990| 0| TESTAFF(sfx->getCont(), compoundmiddle, sfx->getContLen())))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1991| 0| rv = nullptr; 1992| 0| } 1993| | 1994| | // check forbiddenwords 1995| 490M| if ((rv) && (rv->astr) && ------------------ | Branch (1995:13): [True: 740, False: 490M] | Branch (1995:13): [True: 0, False: 490M] | Branch (1995:21): [True: 525, False: 215] ------------------ 1996| 525| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 102| 1.05k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 525] | | ------------------ ------------------ 1997| 525| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 102| 1.05k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 525] | | ------------------ ------------------ 1998| 525| (is_sug && nosuggest && TESTAFF(rv->astr, nosuggest, rv->alen)))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1998:15): [True: 6, False: 519] | Branch (1998:25): [True: 0, False: 6] ------------------ 1999| 0| return nullptr; 2000| 0| } 2001| | 2002| | // increment word number, if the second root has a compoundroot flag 2003| 490M| if ((rv) && compoundroot && ------------------ | Branch (2003:13): [True: 740, False: 490M] | Branch (2003:21): [True: 0, False: 740] ------------------ 2004| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2004:13): [True: 0, False: 0] ------------------ 2005| 0| wordnum++; 2006| 0| } 2007| | 2008| | // first word is acceptable in compound words? 2009| 490M| if (((rv) && ------------------ | Branch (2009:13): [True: 525, False: 490M] | Branch (2009:14): [True: 740, False: 490M] ------------------ 2010| 740| (checked_prefix || (words && words[wnum]) || ------------------ | Branch (2010:15): [True: 0, False: 740] | Branch (2010:34): [True: 0, False: 740] | Branch (2010:43): [True: 0, False: 0] ------------------ 2011| 740| (compoundflag && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 102| 740|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 525, False: 215] | | ------------------ ------------------ | Branch (2011:16): [True: 740, False: 0] ------------------ 2012| 215| ((oldwordnum == 0) && compoundbegin && ------------------ | Branch (2012:16): [True: 0, False: 215] | Branch (2012:37): [True: 0, False: 0] ------------------ 2013| 0| TESTAFF(rv->astr, compoundbegin, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2014| 215| ((oldwordnum > 0) && compoundmiddle && ------------------ | Branch (2014:16): [True: 0, False: 215] | Branch (2014:36): [True: 0, False: 0] ------------------ 2015| 0| TESTAFF(rv->astr, compoundmiddle, rv->alen)) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2016| | 2017| | // LANG_hu section: spec. Hungarian rule 2018| 215| || ((langnum == LANG_hu) && hu_mov_rule && ------------------ | Branch (2018:19): [True: 215, False: 0] | Branch (2018:43): [True: 215, False: 0] ------------------ 2019| 215| (TESTAFF( ------------------ | | 102| 430|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 215] | | ------------------ ------------------ 2020| 215| rv->astr, 'F', 2021| 215| rv->alen) || // XXX hardwired Hungarian dictionary codes 2022| 215| TESTAFF(rv->astr, 'G', rv->alen) || ------------------ | | 102| 430|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 215] | | ------------------ ------------------ 2023| 215| TESTAFF(rv->astr, 'H', rv->alen))) ------------------ | | 102| 215|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 215] | | ------------------ ------------------ 2024| | // END of LANG_hu section 2025| 740| ) && 2026| 525| ( 2027| | // test CHECKCOMPOUNDPATTERN conditions 2028| 525| scpd == 0 || checkcpdtable[scpd - 1].cond == FLAG_NULL || ------------------ | | 99| 525|#define FLAG_NULL 0x00 ------------------ | Branch (2028:18): [True: 525, False: 0] | Branch (2028:31): [True: 0, False: 0] ------------------ 2029| 0| join_side_has_flag(rv, checkcpdtable[scpd - 1].cond, pfx, sfx)) && ------------------ | Branch (2029:18): [True: 0, False: 0] ------------------ 2030| 525| !((checkcompoundtriple && scpd == 0 && ------------------ | Branch (2030:17): [True: 0, False: 525] | Branch (2030:40): [True: 0, False: 0] ------------------ 2031| 0| !words && i < word.size() && // test triple letters ------------------ | Branch (2031:17): [True: 0, False: 0] | Branch (2031:27): [True: 0, False: 0] ------------------ 2032| 0| (word[i - 1] == word[i]) && ------------------ | Branch (2032:17): [True: 0, False: 0] ------------------ 2033| 0| (((i > 1) && (word[i - 1] == word[i - 2])) || ------------------ | Branch (2033:19): [True: 0, False: 0] | Branch (2033:30): [True: 0, False: 0] ------------------ 2034| 0| ((word[i - 1] == word[i + 1])) // may be word[i+1] == '\0' ------------------ | Branch (2034:18): [True: 0, False: 0] ------------------ 2035| 0| )) || 2036| 525| (checkcompoundcase && scpd == 0 && !words && i < word.size() && ------------------ | Branch (2036:17): [True: 0, False: 525] | Branch (2036:38): [True: 0, False: 0] | Branch (2036:51): [True: 0, False: 0] | Branch (2036:61): [True: 0, False: 0] ------------------ 2037| 0| cpdcase_check(word, i)))) ------------------ | Branch (2037:17): [True: 0, False: 0] ------------------ 2038| | // LANG_hu section: spec. Hungarian rule 2039| 490M| || ((!rv) && (langnum == LANG_hu) && hu_mov_rule && ------------------ | Branch (2039:17): [True: 490M, False: 215] | Branch (2039:26): [True: 40.2M, False: 450M] | Branch (2039:50): [True: 116k, False: 40.0M] ------------------ 2040| 116k| (rv = affix_check(st, 0, i, scratch)) && ------------------ | Branch (2040:17): [True: 0, False: 116k] ------------------ 2041| 0| (sfx && sfx->getCont() && ------------------ | Branch (2041:18): [True: 0, False: 0] | Branch (2041:25): [True: 0, False: 0] ------------------ 2042| 0| ( // XXX hardwired Hungarian dic. codes 2043| 0| TESTAFF(sfx->getCont(), (unsigned short)'x', ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2044| 0| sfx->getContLen()) || 2045| 0| TESTAFF( ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2046| 0| sfx->getCont(), (unsigned short)'%', 2047| 525| sfx->getContLen()))))) { // first word is ok condition 2048| | 2049| | // LANG_hu section: spec. Hungarian rule 2050| 525| if (langnum == LANG_hu) { ------------------ | Branch (2050:15): [True: 335, False: 190] ------------------ 2051| | // calculate syllable number of the word 2052| 335| numsyllable += get_syllable(st.substr(0, i)); 2053| | // + 1 word, if syllable number of the prefix > 1 (hungarian 2054| | // convention) 2055| 335| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (2055:17): [True: 0, False: 335] | Branch (2055:17): [True: 0, False: 335] | Branch (2055:24): [True: 0, False: 0] ------------------ 2056| 0| wordnum++; 2057| 335| } 2058| | // END of LANG_hu section 2059| | 2060| | // NEXT WORD(S) 2061| 525| rv_first = rv; 2062| | // the affixes that built the first word, so its continuation classes stay reachable once 2063| | // the second word has overwritten pfx and sfx 2064| 525| PfxEntry* rv_first_pfx = pfx; 2065| 525| SfxEntry* rv_first_sfx = sfx; 2066| 525| st[i] = ch; 2067| | 2068| 525| do { // striple loop 2069| | 2070| | // check simplifiedtriple 2071| 525| if (simplifiedtriple) { ------------------ | Branch (2071:17): [True: 0, False: 525] ------------------ 2072| 0| if (striple) { ------------------ | Branch (2072:19): [True: 0, False: 0] ------------------ 2073| 0| checkedstriple = 1; 2074| 0| i--; // check "fahrt" instead of "ahrt" in "Schiffahrt" 2075| 0| } else if (i > 2 && i <= word.size() && word[i - 1] == word[i - 2]) { ------------------ | Branch (2075:26): [True: 0, False: 0] | Branch (2075:35): [True: 0, False: 0] | Branch (2075:55): [True: 0, False: 0] ------------------ 2076| 0| striple = 1; 2077| | // past cmax the surface split is too short, so only the form with the letter 2078| | // put back is tried 2079| 0| if (i >= cmax) { ------------------ | Branch (2079:21): [True: 0, False: 0] ------------------ 2080| 0| checkedstriple = 1; 2081| 0| i--; 2082| 0| } 2083| 0| } 2084| 0| } 2085| | 2086| 525| rv = lookup(st.c_str() + i, st.size() - i); // perhaps without prefix 2087| 525| if (t) { ------------------ | Branch (2087:17): [True: 0, False: 525] ------------------ 2088| 0| if (rv) ------------------ | Branch (2088:19): [True: 0, False: 0] ------------------ 2089| 0| trace(*t, "second \"%s\" -> entry \"%s\" flags=%s", st.c_str() + i, 2090| 0| rv->word, trace_flags(this, rv->astr, rv->alen).c_str()); 2091| 0| else 2092| 0| trace(*t, "second \"%s\" -> miss", st.c_str() + i); 2093| 0| } 2094| | 2095| | // search homonym with compound flag 2096| 525| while ((rv) && ((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2096:20): [True: 0, False: 525] | Branch (2096:30): [True: 0, False: 0] ------------------ 2097| 0| !((compoundflag && !words && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2097:32): [True: 0, False: 0] | Branch (2097:48): [True: 0, False: 0] ------------------ 2098| 0| (compoundend && !words && TESTAFF(rv->astr, compoundend, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2098:32): [True: 0, False: 0] | Branch (2098:47): [True: 0, False: 0] ------------------ 2099| 0| (!defcpdtable.empty() && words && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1))) || ------------------ | Branch (2099:32): [True: 0, False: 0] | Branch (2099:56): [True: 0, False: 0] | Branch (2099:65): [True: 0, False: 0] ------------------ 2100| 0| (scpd != 0 && checkcpdtable[scpd - 1].cond2 != FLAG_NULL && ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ | Branch (2100:30): [True: 0, False: 0] | Branch (2100:43): [True: 0, False: 0] ------------------ 2101| 0| !TESTAFF(rv->astr, checkcpdtable[scpd - 1].cond2, rv->alen)))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2101:30): [True: 0, False: 0] ------------------ 2102| 0| rv = rv->next_homonym; 2103| 0| } 2104| | 2105| | // check FORCEUCASE 2106| 525| if (rv && forceucase && ------------------ | Branch (2106:17): [True: 0, False: 525] | Branch (2106:23): [True: 0, False: 0] ------------------ 2107| 0| (TESTAFF(rv->astr, forceucase, rv->alen)) && ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2107:17): [True: 0, False: 0] ------------------ 2108| 0| !(info && *info & SPELL_ORIGCAP)) ------------------ | | 86| 0|#define SPELL_ORIGCAP (1 << 5) ------------------ | Branch (2108:19): [True: 0, False: 0] | Branch (2108:27): [True: 0, False: 0] ------------------ 2109| 0| rv = nullptr; 2110| | 2111| 525| if (rv && words && words[wnum + 1]) ------------------ | Branch (2111:17): [True: 0, False: 525] | Branch (2111:23): [True: 0, False: 0] | Branch (2111:32): [True: 0, False: 0] ------------------ 2112| 0| return rv_first; 2113| | 2114| 525| oldnumsyllable2 = numsyllable; 2115| 525| oldwordnum2 = wordnum; 2116| | 2117| | // LANG_hu section: spec. Hungarian rule, XXX hardwired dictionary 2118| | // code 2119| 525| if ((rv) && (langnum == LANG_hu) && ------------------ | Branch (2119:17): [True: 0, False: 525] | Branch (2119:17): [True: 0, False: 525] | Branch (2119:25): [True: 0, False: 0] ------------------ 2120| 0| (TESTAFF(rv->astr, 'I', rv->alen)) && ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2120:17): [True: 0, False: 0] ------------------ 2121| 0| !(TESTAFF(rv->astr, 'J', rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2121:17): [True: 0, False: 0] ------------------ 2122| 0| numsyllable--; 2123| 0| } 2124| | // END of LANG_hu section 2125| | 2126| | // increment word number, if the second root has a compoundroot flag 2127| 525| if ((rv) && (compoundroot) && ------------------ | Branch (2127:17): [True: 0, False: 525] | Branch (2127:25): [True: 0, False: 0] ------------------ 2128| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2128:17): [True: 0, False: 0] ------------------ 2129| 0| wordnum++; 2130| 0| } 2131| | 2132| | // check forbiddenwords 2133| 525| if ((rv) && (rv->astr) && ------------------ | Branch (2133:17): [True: 0, False: 525] | Branch (2133:17): [True: 0, False: 525] | Branch (2133:25): [True: 0, False: 0] ------------------ 2134| 0| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2135| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2136| 0| (is_sug && nosuggest && ------------------ | Branch (2136:19): [True: 0, False: 0] | Branch (2136:29): [True: 0, False: 0] ------------------ 2137| 0| TESTAFF(rv->astr, nosuggest, rv->alen)))) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2138| 0| return nullptr; 2139| | 2140| | // second word is acceptable, as a root? 2141| | // hungarian conventions: compounding is acceptable, 2142| | // when compound forms consist of 2 words, or if more, 2143| | // then the syllable number of root words must be 6, or lesser. 2144| | 2145| 525| if ((rv) && ------------------ | Branch (2145:17): [True: 0, False: 525] | Branch (2145:17): [True: 0, False: 525] ------------------ 2146| 0| ((compoundflag && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2146:19): [True: 0, False: 0] ------------------ 2147| 0| (compoundend && TESTAFF(rv->astr, compoundend, rv->alen))) && ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2147:19): [True: 0, False: 0] ------------------ 2148| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (2148:19): [True: 0, False: 0] | Branch (2148:41): [True: 0, False: 0] ------------------ 2149| 0| ((cpdmaxsyllable != 0) && ------------------ | Branch (2149:19): [True: 0, False: 0] ------------------ 2150| 0| (numsyllable + get_syllable(std::string(HENTRY_WORD(rv), rv->blen)) <= ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ | Branch (2150:19): [True: 0, False: 0] ------------------ 2151| 0| cpdmaxsyllable))) && 2152| 0| ( 2153| | // test CHECKCOMPOUNDPATTERN 2154| 0| checkcpdtable.empty() || scpd != 0 || ------------------ | Branch (2154:21): [True: 0, False: 0] | Branch (2154:46): [True: 0, False: 0] ------------------ 2155| 0| (i < word.size() && !cpdpat_check(word, i, rv_first, rv, 0, t, rv_first_pfx, rv_first_sfx, nullptr, nullptr))) && ------------------ | Branch (2155:22): [True: 0, False: 0] | Branch (2155:41): [True: 0, False: 0] ------------------ 2156| 0| ((!checkcompounddup || (rv != rv_first))) ------------------ | Branch (2156:19): [True: 0, False: 0] | Branch (2156:40): [True: 0, False: 0] ------------------ 2157| | // test CHECKCOMPOUNDPATTERN conditions 2158| 0| && 2159| 0| (scpd == 0 || checkcpdtable[scpd - 1].cond2 == FLAG_NULL || ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ | Branch (2159:18): [True: 0, False: 0] | Branch (2159:31): [True: 0, False: 0] ------------------ 2160| 0| TESTAFF(rv->astr, checkcpdtable[scpd - 1].cond2, rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2161| | // forbid compound word, if it is a non-compound word with typical 2162| | // fault 2163| 0| if ((checkcompoundrep && cpdrep_check(word, len, scratch, timelimit_exceeded, clock_time_start)) || ------------------ | Branch (2163:20): [True: 0, False: 0] | Branch (2163:40): [True: 0, False: 0] ------------------ 2164| 0| cpdwordpair_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (2164:19): [True: 0, False: 0] ------------------ 2165| 0| return nullptr; 2166| 0| return rv_first; 2167| 0| } 2168| | 2169| 525| numsyllable = oldnumsyllable2; 2170| 525| wordnum = oldwordnum2; 2171| | 2172| | // perhaps second word has prefix or/and suffix 2173| 525| sfx = nullptr; 2174| 525| sfxflag = FLAG_NULL; ------------------ | | 99| 525|#define FLAG_NULL 0x00 ------------------ 2175| | // the affixes that built the second word, kept because affix_check clears the members 2176| 525| PfxEntry* rv_second_pfx = nullptr; 2177| 525| SfxEntry* rv_second_sfx = nullptr; 2178| 525| rv = (compoundflag && !onlycpdrule && i < word.size()) ? affix_check(word, i, word.size() - i, scratch, compoundflag, IN_CPD_END, FLAG_NULL, &rv_second_pfx, &rv_second_sfx) ------------------ | | 77| 525|#define IN_CPD_END 2 ------------------ rv = (compoundflag && !onlycpdrule && i < word.size()) ? affix_check(word, i, word.size() - i, scratch, compoundflag, IN_CPD_END, FLAG_NULL, &rv_second_pfx, &rv_second_sfx) ------------------ | | 99| 525|#define FLAG_NULL 0x00 ------------------ | Branch (2178:19): [True: 525, False: 0] | Branch (2178:35): [True: 525, False: 0] | Branch (2178:51): [True: 525, False: 0] ------------------ 2179| 525| : nullptr; 2180| 525| if (!rv && compoundend && !onlycpdrule) { ------------------ | Branch (2180:17): [True: 525, False: 0] | Branch (2180:24): [True: 0, False: 525] | Branch (2180:39): [True: 0, False: 0] ------------------ 2181| 0| sfx = nullptr; 2182| 0| pfx = nullptr; 2183| 0| if (i < word.size()) ------------------ | Branch (2183:19): [True: 0, False: 0] ------------------ 2184| 0| rv = affix_check(word, i, word.size() - i, scratch, compoundend, IN_CPD_END, FLAG_NULL, &rv_second_pfx, &rv_second_sfx); ------------------ | | 77| 0|#define IN_CPD_END 2 ------------------ rv = affix_check(word, i, word.size() - i, scratch, compoundend, IN_CPD_END, FLAG_NULL, &rv_second_pfx, &rv_second_sfx); ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ 2185| 0| } 2186| | 2187| 525| if (!rv && !defcpdtable.empty() && words) { ------------------ | Branch (2187:17): [True: 525, False: 0] | Branch (2187:24): [True: 0, False: 525] | Branch (2187:48): [True: 0, False: 0] ------------------ 2188| 0| if (i < word.size()) ------------------ | Branch (2188:19): [True: 0, False: 0] ------------------ 2189| 0| rv = affix_check(word, i, word.size() - i, scratch, 0, IN_CPD_END); ------------------ | | 77| 0|#define IN_CPD_END 2 ------------------ 2190| 0| if (rv && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1)) ------------------ | Branch (2190:19): [True: 0, False: 0] | Branch (2190:25): [True: 0, False: 0] ------------------ 2191| 0| return rv_first; 2192| 0| rv = nullptr; 2193| 0| } 2194| | 2195| | // test CHECKCOMPOUNDPATTERN conditions (allowed forms) 2196| 525| if (rv && ------------------ | Branch (2196:17): [True: 0, False: 525] ------------------ 2197| 0| !(scpd == 0 || checkcpdtable[scpd - 1].cond2 == FLAG_NULL || ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ | Branch (2197:19): [True: 0, False: 0] | Branch (2197:32): [True: 0, False: 0] ------------------ 2198| 0| join_side_has_flag(rv, checkcpdtable[scpd - 1].cond2, rv_second_pfx, ------------------ | Branch (2198:19): [True: 0, False: 0] ------------------ 2199| 0| rv_second_sfx))) 2200| 0| rv = nullptr; 2201| | 2202| | // test CHECKCOMPOUNDPATTERN conditions (forbidden compounds) 2203| 525| if (rv && !checkcpdtable.empty() && scpd == 0 && ------------------ | Branch (2203:17): [True: 0, False: 525] | Branch (2203:23): [True: 0, False: 0] | Branch (2203:49): [True: 0, False: 0] ------------------ 2204| 0| cpdpat_check(word, i, rv_first, rv, affixed, t, rv_first_pfx, rv_first_sfx, rv_second_pfx, rv_second_sfx)) ------------------ | Branch (2204:17): [True: 0, False: 0] ------------------ 2205| 0| rv = nullptr; 2206| | 2207| | // check non_compound flag in suffix and prefix 2208| 525| if ((rv) && ((pfx && pfx->getCont() && ------------------ | Branch (2208:17): [True: 0, False: 525] | Branch (2208:27): [True: 0, False: 0] | Branch (2208:34): [True: 0, False: 0] ------------------ 2209| 0| TESTAFF(pfx->getCont(), compoundforbidflag, ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2210| 0| pfx->getContLen())) || 2211| 0| (sfx && sfx->getCont() && ------------------ | Branch (2211:27): [True: 0, False: 0] | Branch (2211:34): [True: 0, False: 0] ------------------ 2212| 0| TESTAFF(sfx->getCont(), compoundforbidflag, ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2213| 0| sfx->getContLen())))) { 2214| 0| rv = nullptr; 2215| 0| } 2216| | 2217| | // check FORCEUCASE 2218| 525| if (rv && forceucase && ------------------ | Branch (2218:17): [True: 0, False: 525] | Branch (2218:23): [True: 0, False: 0] ------------------ 2219| 0| (TESTAFF(rv->astr, forceucase, rv->alen)) && ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2219:17): [True: 0, False: 0] ------------------ 2220| 0| !(info && *info & SPELL_ORIGCAP)) ------------------ | | 86| 0|#define SPELL_ORIGCAP (1 << 5) ------------------ | Branch (2220:19): [True: 0, False: 0] | Branch (2220:27): [True: 0, False: 0] ------------------ 2221| 0| rv = nullptr; 2222| | 2223| | // check forbiddenwords 2224| 525| if ((rv) && (rv->astr) && ------------------ | Branch (2224:17): [True: 0, False: 525] | Branch (2224:17): [True: 0, False: 525] | Branch (2224:25): [True: 0, False: 0] ------------------ 2225| 0| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2226| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2227| 0| (is_sug && nosuggest && ------------------ | Branch (2227:19): [True: 0, False: 0] | Branch (2227:29): [True: 0, False: 0] ------------------ 2228| 0| TESTAFF(rv->astr, nosuggest, rv->alen)))) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2229| 0| return nullptr; 2230| | 2231| | // pfxappnd = prefix of word+i, or NULL 2232| | // calculate syllable number of prefix. 2233| | // hungarian convention: when syllable number of prefix is more, 2234| | // than 1, the prefix+word counts as two words. 2235| | 2236| 525| if (langnum == LANG_hu) { ------------------ | Branch (2236:17): [True: 335, False: 190] ------------------ 2237| 335| if (i < word.size()) { ------------------ | Branch (2237:19): [True: 335, False: 0] ------------------ 2238| | // calculate syllable number of the word 2239| 335| numsyllable += get_syllable(word.substr(i)); 2240| 335| } 2241| | 2242| | // - affix syllable num. 2243| | // XXX only second suffix (inflections, not derivations) 2244| 335| if (sfxappnd) { ------------------ | Branch (2244:19): [True: 0, False: 335] ------------------ 2245| 0| std::string tmp(sfxappnd); 2246| 0| reverseword(tmp); 2247| 0| numsyllable -= short(get_syllable(tmp) + sfxextra); 2248| 335| } else { 2249| 335| numsyllable -= short(sfxextra); 2250| 335| } 2251| | 2252| | // + 1 word, if syllable number of the prefix > 1 (hungarian 2253| | // convention) 2254| 335| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (2254:19): [True: 0, False: 335] | Branch (2254:19): [True: 0, False: 335] | Branch (2254:26): [True: 0, False: 0] ------------------ 2255| 0| wordnum++; 2256| | 2257| | // increment syllable num, if last word has a SYLLABLENUM flag 2258| | // and the suffix is beginning `s' 2259| | 2260| 335| if (!cpdsyllablenum.empty()) { ------------------ | Branch (2260:19): [True: 0, False: 335] ------------------ 2261| 0| switch (sfxflag) { ------------------ | Branch (2261:25): [True: 0, False: 0] ------------------ 2262| 0| case 'c': { ------------------ | Branch (2262:19): [True: 0, False: 0] ------------------ 2263| 0| numsyllable += 2; 2264| 0| break; 2265| 0| } 2266| 0| case 'J': { ------------------ | Branch (2266:19): [True: 0, False: 0] ------------------ 2267| 0| numsyllable += 1; 2268| 0| break; 2269| 0| } 2270| 0| case 'I': { ------------------ | Branch (2270:19): [True: 0, False: 0] ------------------ 2271| 0| if (rv && TESTAFF(rv->astr, 'J', rv->alen)) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2271:25): [True: 0, False: 0] | Branch (2271:25): [True: 0, False: 0] ------------------ 2272| 0| numsyllable += 1; 2273| 0| break; 2274| 0| } 2275| 0| } 2276| 0| } 2277| 335| } 2278| | 2279| | // increment word number, if the second word has a compoundroot flag 2280| 525| if ((rv) && (compoundroot) && ------------------ | Branch (2280:17): [True: 0, False: 525] | Branch (2280:25): [True: 0, False: 0] ------------------ 2281| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2281:17): [True: 0, False: 0] ------------------ 2282| 0| wordnum++; 2283| 0| } 2284| | // second word is acceptable, as a word with prefix or/and suffix? 2285| | // hungarian conventions: compounding is acceptable, 2286| | // when compound forms consist 2 word, otherwise 2287| | // the syllable number of root words is 6, or lesser. 2288| 525| if ((rv) && ------------------ | Branch (2288:17): [True: 0, False: 525] ------------------ 2289| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (2289:19): [True: 0, False: 0] | Branch (2289:41): [True: 0, False: 0] ------------------ 2290| 0| ((cpdmaxsyllable != 0) && (numsyllable <= cpdmaxsyllable))) && ------------------ | Branch (2290:19): [True: 0, False: 0] | Branch (2290:44): [True: 0, False: 0] ------------------ 2291| 0| ((!checkcompounddup || (rv != rv_first)))) { ------------------ | Branch (2291:19): [True: 0, False: 0] | Branch (2291:40): [True: 0, False: 0] ------------------ 2292| | // forbid compound word, if it is a non-compound word with typical 2293| | // fault 2294| 0| if ((checkcompoundrep && cpdrep_check(word, len, scratch, timelimit_exceeded, clock_time_start)) || ------------------ | Branch (2294:20): [True: 0, False: 0] | Branch (2294:40): [True: 0, False: 0] ------------------ 2295| 0| cpdwordpair_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (2295:19): [True: 0, False: 0] ------------------ 2296| 0| return nullptr; 2297| 0| return rv_first; 2298| 0| } 2299| | 2300| 525| numsyllable = oldnumsyllable2; 2301| 525| wordnum = oldwordnum2; 2302| | 2303| | // perhaps second word is a compound word (recursive call) 2304| | // (only if SPELL_COMPOUND_2 is not set and maxwordnum is not exceeded) 2305| 525| if ((!info || !(*info & SPELL_COMPOUND_2)) && wordnum + 2 < maxwordnum && wnum + 1 < maxwordnum) { ------------------ | | 88| 525|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ | Branch (2305:18): [True: 0, False: 525] | Branch (2305:27): [True: 289, False: 236] | Branch (2305:59): [True: 289, False: 0] | Branch (2305:87): [True: 289, False: 0] ------------------ 2306| 289| rv = compound_check(st.substr(i), wordnum + 1, 2307| 289| numsyllable, maxwordnum, wnum + 1, words, rwords, 0, 2308| 289| is_sug, info, scratch); 2309| | 2310| 289| if (rv && !checkcpdtable.empty() && i < word.size() && ------------------ | Branch (2310:19): [True: 0, False: 289] | Branch (2310:25): [True: 0, False: 0] | Branch (2310:51): [True: 0, False: 0] ------------------ 2311| 0| ((scpd == 0 && ------------------ | Branch (2311:21): [True: 0, False: 0] ------------------ 2312| 0| cpdpat_check(word, i, rv_first, rv, affixed, t, rv_first_pfx, rv_first_sfx, nullptr, nullptr)) || ------------------ | Branch (2312:21): [True: 0, False: 0] ------------------ 2313| 0| (scpd != 0 && ------------------ | Branch (2313:21): [True: 0, False: 0] ------------------ 2314| 0| !cpdpat_check(word, i, rv_first, rv, affixed, t, rv_first_pfx, rv_first_sfx, nullptr, nullptr)))) ------------------ | Branch (2314:21): [True: 0, False: 0] ------------------ 2315| 0| rv = nullptr; 2316| 289| } else { 2317| 236| rv = nullptr; 2318| 236| } 2319| 525| if (rv) { ------------------ | Branch (2319:17): [True: 0, False: 525] ------------------ 2320| | // forbid compound word, if it is a non-compound word with typical 2321| | // fault, or a dictionary word pair 2322| | 2323| 0| if (cpdwordpair_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (2323:19): [True: 0, False: 0] ------------------ 2324| 0| return nullptr; 2325| | 2326| 0| if (checkcompoundrep || forbiddenword) { ------------------ | Branch (2326:19): [True: 0, False: 0] | Branch (2326:39): [True: 0, False: 0] ------------------ 2327| 0| if (checkcompoundrep && cpdrep_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (2327:21): [True: 0, False: 0] | Branch (2327:41): [True: 0, False: 0] ------------------ 2328| 0| return nullptr; 2329| | 2330| | // check first part 2331| 0| if (i < word.size() && word.compare(i, rv->blen, rv->word, rv->blen) == 0) { ------------------ | Branch (2331:21): [True: 0, False: 0] | Branch (2331:40): [True: 0, False: 0] ------------------ 2332| 0| char r = st[i + rv->blen]; 2333| 0| st[i + rv->blen] = '\0'; 2334| | 2335| 0| if ((checkcompoundrep && cpdrep_check(st, i + rv->blen, scratch, timelimit_exceeded, clock_time_start)) || ------------------ | Branch (2335:24): [True: 0, False: 0] | Branch (2335:44): [True: 0, False: 0] ------------------ 2336| 0| cpdwordpair_check(st, i + rv->blen, scratch, timelimit_exceeded, clock_time_start)) { ------------------ | Branch (2336:23): [True: 0, False: 0] ------------------ 2337| 0| st[ + i + rv->blen] = r; 2338| 0| continue; 2339| 0| } 2340| | 2341| 0| if (forbiddenword) { ------------------ | Branch (2341:23): [True: 0, False: 0] ------------------ 2342| 0| struct hentry* rv2 = lookup(word.c_str(), word.size()); 2343| 0| if (!rv2 && len <= word.size()) ------------------ | Branch (2343:25): [True: 0, False: 0] | Branch (2343:33): [True: 0, False: 0] ------------------ 2344| 0| rv2 = affix_check(word, 0, len, scratch); 2345| 0| if (rv2 && rv2->astr && ------------------ | Branch (2345:25): [True: 0, False: 0] | Branch (2345:32): [True: 0, False: 0] ------------------ 2346| 0| TESTAFF(rv2->astr, forbiddenword, rv2->alen) && ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2347| 0| (strncmp(rv2->word, st.c_str(), i + rv->blen) == 0)) { ------------------ | Branch (2347:25): [True: 0, False: 0] ------------------ 2348| 0| return nullptr; 2349| 0| } 2350| 0| } 2351| 0| st[i + rv->blen] = r; 2352| 0| } 2353| 0| } 2354| 0| return rv_first; 2355| 0| } 2356| 525| } while (striple && !checkedstriple); // end of striple loop ------------------ | Branch (2356:20): [True: 0, False: 525] | Branch (2356:31): [True: 0, False: 0] ------------------ 2357| | 2358| 525| if (checkedstriple) { ------------------ | Branch (2358:15): [True: 0, False: 525] ------------------ 2359| 0| i++; 2360| 0| checkedstriple = 0; 2361| 0| striple = 0; 2362| 0| } 2363| | 2364| 525| } // first word is ok condition 2365| | 2366| 490M| if (soldi != 0) { ------------------ | Branch (2366:13): [True: 0, False: 490M] ------------------ 2367| 0| i = soldi; 2368| 0| len = oldlen; 2369| 0| cmin = oldcmin; 2370| 0| cmax = oldcmax; 2371| 0| } 2372| 490M| scpd++; 2373| | 2374| 490M| } while (!onlycpdrule && simplifiedcpd && ------------------ | Branch (2374:16): [True: 490M, False: 0] | Branch (2374:32): [True: 0, False: 490M] ------------------ 2375| 0| scpd <= checkcpdtable.size()); // end of simplifiedcpd loop ------------------ | Branch (2375:16): [True: 0, False: 0] ------------------ 2376| | 2377| 490M| scpd = 0; 2378| 490M| wordnum = oldwordnum; 2379| 490M| numsyllable = oldnumsyllable; 2380| | 2381| 490M| if (soldi != 0) { ------------------ | Branch (2381:11): [True: 0, False: 490M] ------------------ 2382| 0| i = soldi; 2383| 0| st.assign(word); // XXX add more optim. 2384| 0| soldi = 0; 2385| 0| len = oldlen; 2386| 0| cmin = oldcmin; 2387| 0| cmax = oldcmax; 2388| 0| } else 2389| 490M| st[i] = ch; 2390| | 2391| 490M| } while (!defcpdtable.empty() && oldwordnum == 0 && ------------------ | Branch (2391:14): [True: 0, False: 490M] | Branch (2391:38): [True: 0, False: 0] ------------------ 2392| 0| onlycpdrule++ < 1); // end of onlycpd loop ------------------ | Branch (2392:14): [True: 0, False: 0] ------------------ 2393| 491M| } 2394| | 2395| 22.2M| return nullptr; 2396| 23.3M|} _ZN8AffixMgr20compound_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEssssPP6hentrySB_cRS6_PS7_R12AffixScratch: 2410| 2.30k| AffixScratch& scratch) { 2411| 2.30k| short oldnumsyllable, oldnumsyllable2, oldwordnum, oldwordnum2; 2412| 2.30k| hentry *rv = nullptr, *rv_first; 2413| 2.30k| std::string st, presult; 2414| 2.30k| char ch, affixed = 0; 2415| 2.30k| int checked_prefix, ok = 0; 2416| 2.30k| size_t cmin, cmax; 2417| 2.30k| hentry** oldwords = words; 2418| 2.30k| size_t len = word.size(); 2419| | 2420| | // protect subsequent words[wnum + 1] reads and any recursion 2421| 2.30k| if (wnum + 1 >= maxwordnum) ------------------ | Branch (2421:7): [True: 0, False: 2.30k] ------------------ 2422| 0| return 0; 2423| | 2424| | // add a time limit to handle possible 2425| | // combinatorical explosion of the overlapping words 2426| | 2427| 2.30k| HUNSPELL_THREAD_LOCAL std::chrono::steady_clock::time_point clock_time_start; ------------------ | | 60| 2.30k|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 2428| 2.30k| HUNSPELL_THREAD_LOCAL bool timelimit_exceeded; ------------------ | | 60| 2.30k|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 2429| | 2430| | // get the current time 2431| 2.30k| std::chrono::steady_clock::time_point clock_now = std::chrono::steady_clock::now(); 2432| | 2433| 2.30k| if (wnum == 0) { ------------------ | Branch (2433:7): [True: 2.30k, False: 0] ------------------ 2434| | // set the start time 2435| 2.30k| clock_time_start = clock_now; 2436| 2.30k| timelimit_exceeded = false; 2437| 2.30k| } 2438| 0| else if (clock_now - clock_time_start > TIMELIMIT_MS) ------------------ | | 109| 0|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (2438:12): [True: 0, False: 0] ------------------ 2439| 0| timelimit_exceeded = true; 2440| | 2441| 2.30k| setcminmax(&cmin, &cmax, word.c_str(), len); 2442| | 2443| 2.30k| st.assign(word); 2444| | 2445| 32.2k| for (size_t i = cmin; i < cmax; ++i) { ------------------ | Branch (2445:25): [True: 30.2k, False: 2.00k] ------------------ 2446| | // go to end of the UTF-8 character 2447| 30.2k| if (utf8) { ------------------ | Branch (2447:9): [True: 10.2k, False: 19.9k] ------------------ 2448| 12.9k| for (; is_utf8_cont(st[i]); i++) ------------------ | Branch (2448:14): [True: 2.70k, False: 10.2k] ------------------ 2449| 2.70k| ; 2450| 10.2k| if (i >= cmax) ------------------ | Branch (2450:11): [True: 76, False: 10.1k] ------------------ 2451| 76| return 0; 2452| 10.2k| } 2453| | 2454| 30.1k| words = oldwords; 2455| 30.1k| int onlycpdrule = (words) ? 1 : 0; ------------------ | Branch (2455:23): [True: 0, False: 30.1k] ------------------ 2456| | 2457| 30.1k| do { // onlycpdrule loop 2458| | 2459| 30.1k| if (timelimit_exceeded || ------------------ | Branch (2459:11): [True: 0, False: 30.1k] | Branch (2459:11): [True: 0, False: 30.1k] ------------------ 2460| 30.1k| std::chrono::steady_clock::now() - clock_time_start > TIMELIMIT_MS) { ------------------ | | 109| 30.1k|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (2460:11): [True: 0, False: 30.1k] ------------------ 2461| 0| timelimit_exceeded = true; 2462| 0| return 0; 2463| 0| } 2464| | 2465| 30.1k| if (result.size() > MAXMORPHRESULT) ------------------ | | 114| 30.1k|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (2465:11): [True: 0, False: 30.1k] ------------------ 2466| 0| return 0; 2467| | 2468| 30.1k| oldnumsyllable = numsyllable; 2469| 30.1k| oldwordnum = wordnum; 2470| 30.1k| checked_prefix = 0; 2471| | 2472| 30.1k| if (i >= st.size()) ------------------ | Branch (2472:11): [True: 219, False: 29.9k] ------------------ 2473| 219| return 0; 2474| | 2475| 29.9k| ch = st[i]; 2476| 29.9k| st[i] = '\0'; 2477| 29.9k| sfx = nullptr; 2478| | 2479| | // FIRST WORD 2480| | 2481| 29.9k| affixed = 1; 2482| | 2483| 29.9k| presult.clear(); 2484| 29.9k| if (partresult) ------------------ | Branch (2484:11): [True: 0, False: 29.9k] ------------------ 2485| 0| presult.append(*partresult); 2486| | 2487| 29.9k| rv = lookup(st.c_str(), i); // perhaps without prefix 2488| | 2489| | // forbid dictionary stems with COMPOUNDFORBIDFLAG in 2490| | // compound words, overriding the effect of COMPOUNDPERMITFLAG 2491| 29.9k| if ((rv) && compoundforbidflag && ------------------ | Branch (2491:11): [True: 493, False: 29.4k] | Branch (2491:19): [True: 82, False: 411] ------------------ 2492| 82| TESTAFF(rv->astr, compoundforbidflag, rv->alen) && !hu_mov_rule) ------------------ | | 102| 29.9k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 82] | | ------------------ ------------------ | Branch (2492:66): [True: 0, False: 0] ------------------ 2493| 0| continue; 2494| | 2495| | // search homonym with compound flag 2496| 30.4k| while ((rv) && !hu_mov_rule && ------------------ | Branch (2496:14): [True: 493, False: 29.9k] | Branch (2496:22): [True: 493, False: 0] ------------------ 2497| 493| ((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) || ------------------ | | 102| 137|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 137] | | ------------------ ------------------ | Branch (2497:16): [True: 137, False: 356] ------------------ 2498| 493| !((compoundflag && !words && !onlycpdrule && ------------------ | Branch (2498:18): [True: 493, False: 0] | Branch (2498:34): [True: 493, False: 0] | Branch (2498:44): [True: 493, False: 0] ------------------ 2499| 493| TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 102| 493|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 493] | | ------------------ ------------------ 2500| 493| (compoundbegin && !wordnum && !onlycpdrule && ------------------ | Branch (2500:18): [True: 0, False: 493] | Branch (2500:35): [True: 0, False: 0] | Branch (2500:47): [True: 0, False: 0] ------------------ 2501| 0| TESTAFF(rv->astr, compoundbegin, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2502| 493| (compoundmiddle && wordnum && !words && !onlycpdrule && ------------------ | Branch (2502:18): [True: 0, False: 493] | Branch (2502:36): [True: 0, False: 0] | Branch (2502:47): [True: 0, False: 0] | Branch (2502:57): [True: 0, False: 0] ------------------ 2503| 0| TESTAFF(rv->astr, compoundmiddle, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2504| 493| (!defcpdtable.empty() && onlycpdrule && ------------------ | Branch (2504:18): [True: 0, False: 493] | Branch (2504:42): [True: 0, False: 0] ------------------ 2505| 0| ((!words && !wordnum && ------------------ | Branch (2505:20): [True: 0, False: 0] | Branch (2505:30): [True: 0, False: 0] ------------------ 2506| 0| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0)) || ------------------ | Branch (2506:20): [True: 0, False: 0] ------------------ 2507| 0| (words && ------------------ | Branch (2507:20): [True: 0, False: 0] ------------------ 2508| 493| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0))))))) { ------------------ | Branch (2508:20): [True: 0, False: 0] ------------------ 2509| 493| rv = rv->next_homonym; 2510| 493| } 2511| | 2512| | 2513| 29.9k| if (rv) ------------------ | Branch (2513:11): [True: 0, False: 29.9k] ------------------ 2514| 0| affixed = 0; 2515| | 2516| 29.9k| if (rv) { ------------------ | Branch (2516:11): [True: 0, False: 29.9k] ------------------ 2517| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2518| 0| presult.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2519| 0| presult.append(st, 0, i); 2520| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (2520:13): [True: 0, False: 0] ------------------ 2521| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2522| 0| presult.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 2523| 0| presult.append(st, 0, i); 2524| 0| } 2525| 0| if (HENTRY_DATA(rv)) { ------------------ | Branch (2525:13): [True: 0, False: 0] ------------------ 2526| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2527| 0| presult.append(HENTRY_DATA2(rv)); 2528| 0| } 2529| 0| } 2530| | 2531| 29.9k| if (!rv) { ------------------ | Branch (2531:11): [True: 29.9k, False: 0] ------------------ 2532| 29.9k| if (compoundflag && ------------------ | Branch (2532:13): [True: 29.9k, False: 0] ------------------ 2533| 29.9k| !(rv = ------------------ | Branch (2533:13): [True: 29.9k, False: 0] ------------------ 2534| 29.9k| prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, ------------------ | | 78| 0|#define IN_CPD_OTHER 3 ------------------ prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, ------------------ | | 76| 59.8k|#define IN_CPD_BEGIN 1 ------------------ | Branch (2534:42): [True: 0, False: 29.9k] ------------------ 2535| 29.9k| scratch, compoundflag))) { 2536| 29.9k| if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 99| 29.9k|#define FLAG_NULL 0x00 ------------------ if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 78| 0|#define IN_CPD_OTHER 3 ------------------ if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 76| 59.8k|#define IN_CPD_BEGIN 1 ------------------ | Branch (2536:16): [True: 0, False: 29.9k] | Branch (2536:91): [True: 0, False: 29.9k] ------------------ 2537| 29.9k| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, compoundflag)))) && ------------------ | Branch (2537:17): [True: 0, False: 29.9k] | Branch (2537:41): [True: 0, False: 0] ------------------ 2538| 0| !hu_mov_rule && sfx->getCont() && ------------------ | Branch (2538:15): [True: 0, False: 0] | Branch (2538:31): [True: 0, False: 0] ------------------ 2539| 0| ((compoundforbidflag && TESTAFF(sfx->getCont(), compoundforbidflag, sfx->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2539:17): [True: 0, False: 0] ------------------ 2540| 0| (compoundend && TESTAFF(sfx->getCont(), compoundend, sfx->getContLen())))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2540:17): [True: 0, False: 0] ------------------ 2541| 0| rv = nullptr; 2542| 0| } 2543| 29.9k| } 2544| | 2545| 29.9k| if (rv || ------------------ | Branch (2545:13): [True: 0, False: 29.9k] ------------------ 2546| 29.9k| (((wordnum == 0) && compoundbegin && ------------------ | Branch (2546:15): [True: 29.9k, False: 0] | Branch (2546:33): [True: 0, False: 29.9k] ------------------ 2547| 0| ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundbegin, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundbegin, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 78| 0|#define IN_CPD_OTHER 3 ------------------ ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundbegin, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 76| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2547:16): [True: 0, False: 0] | Branch (2547:92): [True: 0, False: 0] ------------------ 2548| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (2548:17): [True: 0, False: 0] | Branch (2548:41): [True: 0, False: 0] ------------------ 2549| 0| compoundbegin))) || // twofold suffix+compound 2550| 0| (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundbegin)))) || ------------------ | | 78| 0|#define IN_CPD_OTHER 3 ------------------ (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundbegin)))) || ------------------ | | 76| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2550:16): [True: 0, False: 0] | Branch (2550:45): [True: 0, False: 0] ------------------ 2551| 29.9k| ((wordnum > 0) && compoundmiddle && ------------------ | Branch (2551:15): [True: 0, False: 29.9k] | Branch (2551:32): [True: 0, False: 0] ------------------ 2552| 0| ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundmiddle, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundmiddle, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 78| 0|#define IN_CPD_OTHER 3 ------------------ ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundmiddle, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 76| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2552:16): [True: 0, False: 0] | Branch (2552:93): [True: 0, False: 0] ------------------ 2553| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (2553:17): [True: 0, False: 0] | Branch (2553:41): [True: 0, False: 0] ------------------ 2554| 0| compoundmiddle))) || // twofold suffix+compound 2555| 0| (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundmiddle)))))) { ------------------ | | 78| 0|#define IN_CPD_OTHER 3 ------------------ (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundmiddle)))))) { ------------------ | | 76| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2555:16): [True: 0, False: 0] | Branch (2555:45): [True: 0, False: 0] ------------------ 2556| 0| std::string p; 2557| 0| if (compoundflag) ------------------ | Branch (2557:15): [True: 0, False: 0] ------------------ 2558| 0| p = affix_check_morph(st, 0, i, scratch, compoundflag); 2559| 0| if (p.empty()) { ------------------ | Branch (2559:15): [True: 0, False: 0] ------------------ 2560| 0| if ((wordnum == 0) && compoundbegin) { ------------------ | Branch (2560:17): [True: 0, False: 0] | Branch (2560:35): [True: 0, False: 0] ------------------ 2561| 0| p = affix_check_morph(st, 0, i, scratch, compoundbegin); 2562| 0| } else if ((wordnum > 0) && compoundmiddle) { ------------------ | Branch (2562:24): [True: 0, False: 0] | Branch (2562:41): [True: 0, False: 0] ------------------ 2563| 0| p = affix_check_morph(st, 0, i, scratch, compoundmiddle); 2564| 0| } 2565| 0| } 2566| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2567| 0| presult.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2568| 0| presult.append(st, 0, i); 2569| 0| if (!p.empty()) { ------------------ | Branch (2569:15): [True: 0, False: 0] ------------------ 2570| 0| line_uniq_app(p, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2571| 0| if (!p.empty() && p[0] != MSEP_FLD) ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ | Branch (2571:17): [True: 0, False: 0] | Branch (2571:31): [True: 0, False: 0] ------------------ 2572| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2573| 0| presult.append(p); 2574| 0| } 2575| 0| checked_prefix = 1; 2576| 0| } 2577| | // else check forbiddenwords 2578| 29.9k| } else if (rv->astr && (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2578:18): [True: 0, False: 0] | Branch (2578:18): [True: 0, False: 0] ------------------ 2579| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2580| 0| TESTAFF(rv->astr, needaffix, rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2581| 0| st[i] = ch; 2582| 0| continue; 2583| 0| } 2584| | 2585| | // check non_compound flag in suffix and prefix 2586| 29.9k| if ((rv) && !hu_mov_rule && ------------------ | Branch (2586:11): [True: 0, False: 29.9k] | Branch (2586:19): [True: 0, False: 0] ------------------ 2587| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2587:13): [True: 0, False: 0] | Branch (2587:20): [True: 0, False: 0] ------------------ 2588| 0| TESTAFF(pfx->getCont(), compoundforbidflag, pfx->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2589| 0| (sfx && sfx->getCont() && ------------------ | Branch (2589:13): [True: 0, False: 0] | Branch (2589:20): [True: 0, False: 0] ------------------ 2590| 0| TESTAFF(sfx->getCont(), compoundforbidflag, sfx->getContLen())))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2591| 0| continue; 2592| 0| } 2593| | 2594| | // check compoundend flag in suffix and prefix 2595| 29.9k| if ((rv) && !checked_prefix && compoundend && !hu_mov_rule && ------------------ | Branch (2595:11): [True: 0, False: 29.9k] | Branch (2595:19): [True: 0, False: 0] | Branch (2595:38): [True: 0, False: 0] | Branch (2595:53): [True: 0, False: 0] ------------------ 2596| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2596:13): [True: 0, False: 0] | Branch (2596:20): [True: 0, False: 0] ------------------ 2597| 0| TESTAFF(pfx->getCont(), compoundend, pfx->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2598| 0| (sfx && sfx->getCont() && ------------------ | Branch (2598:13): [True: 0, False: 0] | Branch (2598:20): [True: 0, False: 0] ------------------ 2599| 0| TESTAFF(sfx->getCont(), compoundend, sfx->getContLen())))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2600| 0| continue; 2601| 0| } 2602| | 2603| | // check compoundmiddle flag in suffix and prefix 2604| 29.9k| if ((rv) && !checked_prefix && (wordnum == 0) && compoundmiddle && ------------------ | Branch (2604:11): [True: 0, False: 29.9k] | Branch (2604:19): [True: 0, False: 0] | Branch (2604:38): [True: 0, False: 0] | Branch (2604:56): [True: 0, False: 0] ------------------ 2605| 0| !hu_mov_rule && ------------------ | Branch (2605:11): [True: 0, False: 0] ------------------ 2606| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2606:13): [True: 0, False: 0] | Branch (2606:20): [True: 0, False: 0] ------------------ 2607| 0| TESTAFF(pfx->getCont(), compoundmiddle, pfx->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2608| 0| (sfx && sfx->getCont() && ------------------ | Branch (2608:13): [True: 0, False: 0] | Branch (2608:20): [True: 0, False: 0] ------------------ 2609| 0| TESTAFF(sfx->getCont(), compoundmiddle, sfx->getContLen())))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2610| 0| rv = nullptr; 2611| 0| } 2612| | 2613| | // check forbiddenwords 2614| 29.9k| if ((rv) && (rv->astr) && (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2614:11): [True: 0, False: 29.9k] | Branch (2614:11): [True: 0, False: 29.9k] | Branch (2614:19): [True: 0, False: 0] ------------------ 2615| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen))) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2616| 0| continue; 2617| | 2618| | // increment word number, if the second root has a compoundroot flag 2619| 29.9k| if ((rv) && (compoundroot) && ------------------ | Branch (2619:11): [True: 0, False: 29.9k] | Branch (2619:19): [True: 0, False: 0] ------------------ 2620| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2620:11): [True: 0, False: 0] ------------------ 2621| 0| wordnum++; 2622| 0| } 2623| | 2624| | // first word is acceptable in compound words? 2625| 29.9k| if (((rv) && ------------------ | Branch (2625:11): [True: 0, False: 29.9k] | Branch (2625:12): [True: 0, False: 29.9k] ------------------ 2626| 0| (checked_prefix || (words && words[wnum]) || (compoundflag && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2626:13): [True: 0, False: 0] | Branch (2626:32): [True: 0, False: 0] | Branch (2626:41): [True: 0, False: 0] | Branch (2626:58): [True: 0, False: 0] ------------------ 2627| 0| ((oldwordnum == 0) && compoundbegin && TESTAFF(rv->astr, compoundbegin, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2627:14): [True: 0, False: 0] | Branch (2627:35): [True: 0, False: 0] ------------------ 2628| 0| ((oldwordnum > 0) && compoundmiddle && TESTAFF(rv->astr, compoundmiddle, rv->alen)) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2628:14): [True: 0, False: 0] | Branch (2628:34): [True: 0, False: 0] ------------------ 2629| | // LANG_hu section: spec. Hungarian rule 2630| 0| || ((langnum == LANG_hu) && // hu_mov_rule ------------------ | Branch (2630:17): [True: 0, False: 0] ------------------ 2631| 0| hu_mov_rule && ------------------ | Branch (2631:17): [True: 0, False: 0] ------------------ 2632| 0| (TESTAFF(rv->astr, 'F', rv->alen) || TESTAFF(rv->astr, 'G', rv->alen) || TESTAFF(rv->astr, 'H', rv->alen))) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ (TESTAFF(rv->astr, 'F', rv->alen) || TESTAFF(rv->astr, 'G', rv->alen) || TESTAFF(rv->astr, 'H', rv->alen))) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ (TESTAFF(rv->astr, 'F', rv->alen) || TESTAFF(rv->astr, 'G', rv->alen) || TESTAFF(rv->astr, 'H', rv->alen))) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2633| | // END of LANG_hu section 2634| 0| ) && 2635| 0| !((checkcompoundtriple && !words && // test triple letters ------------------ | Branch (2635:15): [True: 0, False: 0] | Branch (2635:38): [True: 0, False: 0] ------------------ 2636| 0| (word[i - 1] == word[i]) && ------------------ | Branch (2636:15): [True: 0, False: 0] ------------------ 2637| 0| (((i > 1) && (word[i - 1] == word[i - 2])) || ((word[i - 1] == word[i + 1])) // may be word[i+1] == '\0' ------------------ | Branch (2637:17): [True: 0, False: 0] | Branch (2637:28): [True: 0, False: 0] | Branch (2637:61): [True: 0, False: 0] ------------------ 2638| 0| )) || 2639| 0| ( 2640| | // test CHECKCOMPOUNDPATTERN 2641| 0| !checkcpdtable.empty() && !words && cpdpat_check(word, i, rv, nullptr, affixed, nullptr, nullptr, nullptr, nullptr, nullptr)) || ------------------ | Branch (2641:18): [True: 0, False: 0] | Branch (2641:44): [True: 0, False: 0] | Branch (2641:54): [True: 0, False: 0] ------------------ 2642| 0| (checkcompoundcase && !words && cpdcase_check(word, i)))) ------------------ | Branch (2642:15): [True: 0, False: 0] | Branch (2642:36): [True: 0, False: 0] | Branch (2642:46): [True: 0, False: 0] ------------------ 2643| | // LANG_hu section: spec. Hungarian rule 2644| 29.9k| || ((!rv) && (langnum == LANG_hu) && hu_mov_rule && (rv = affix_check(st, 0, i, scratch)) && ------------------ | Branch (2644:15): [True: 29.9k, False: 0] | Branch (2644:24): [True: 10.1k, False: 19.7k] | Branch (2644:48): [True: 0, False: 10.1k] | Branch (2644:63): [True: 0, False: 0] ------------------ 2645| 0| (sfx && sfx->getCont() && ------------------ | Branch (2645:16): [True: 0, False: 0] | Branch (2645:23): [True: 0, False: 0] ------------------ 2646| 0| (TESTAFF(sfx->getCont(), (unsigned short)'x', sfx->getContLen()) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2647| 0| TESTAFF(sfx->getCont(), (unsigned short)'%', sfx->getContLen())))) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2648| | // END of LANG_hu section 2649| 29.9k| ) { 2650| | // LANG_hu section: spec. Hungarian rule 2651| 0| if (langnum == LANG_hu) { ------------------ | Branch (2651:13): [True: 0, False: 0] ------------------ 2652| | // calculate syllable number of the word 2653| 0| numsyllable += get_syllable(st.substr(0, i)); 2654| | 2655| | // + 1 word, if syllable number of the prefix > 1 (hungarian 2656| | // convention) 2657| 0| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (2657:15): [True: 0, False: 0] | Branch (2657:15): [True: 0, False: 0] | Branch (2657:22): [True: 0, False: 0] ------------------ 2658| 0| wordnum++; 2659| 0| } 2660| | // END of LANG_hu section 2661| | 2662| | // NEXT WORD(S) 2663| 0| rv_first = rv; 2664| 0| rv = lookup(word.c_str() + i, word.size() - i); // perhaps without prefix 2665| | 2666| | // search homonym with compound flag 2667| 0| while ((rv) && ((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2667:16): [True: 0, False: 0] | Branch (2667:26): [True: 0, False: 0] ------------------ 2668| 0| !((compoundflag && !words && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2668:28): [True: 0, False: 0] | Branch (2668:44): [True: 0, False: 0] ------------------ 2669| 0| (compoundend && !words && TESTAFF(rv->astr, compoundend, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2669:28): [True: 0, False: 0] | Branch (2669:43): [True: 0, False: 0] ------------------ 2670| 0| (!defcpdtable.empty() && words && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1))))) { ------------------ | Branch (2670:28): [True: 0, False: 0] | Branch (2670:52): [True: 0, False: 0] | Branch (2670:61): [True: 0, False: 0] ------------------ 2671| 0| rv = rv->next_homonym; 2672| 0| } 2673| | 2674| 0| if (rv && words && words[wnum + 1]) { ------------------ | Branch (2674:13): [True: 0, False: 0] | Branch (2674:19): [True: 0, False: 0] | Branch (2674:28): [True: 0, False: 0] ------------------ 2675| 0| result.append(presult); 2676| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2677| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2678| 0| result.append(word, i, word.size()); 2679| 0| if (complexprefixes && HENTRY_DATA(rv)) ------------------ | Branch (2679:15): [True: 0, False: 0] | Branch (2679:34): [True: 0, False: 0] ------------------ 2680| 0| result.append(HENTRY_DATA2(rv)); 2681| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (2681:15): [True: 0, False: 0] ------------------ 2682| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2683| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 2684| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 2685| 0| } 2686| | // store the pointer of the hash entry 2687| 0| if (!complexprefixes && HENTRY_DATA(rv)) { ------------------ | Branch (2687:15): [True: 0, False: 0] | Branch (2687:35): [True: 0, False: 0] ------------------ 2688| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2689| 0| result.append(HENTRY_DATA2(rv)); 2690| 0| } 2691| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2692| 0| return 0; 2693| 0| } 2694| | 2695| 0| oldnumsyllable2 = numsyllable; 2696| 0| oldwordnum2 = wordnum; 2697| | 2698| | // LANG_hu section: spec. Hungarian rule 2699| 0| if ((rv) && (langnum == LANG_hu) && ------------------ | Branch (2699:13): [True: 0, False: 0] | Branch (2699:13): [True: 0, False: 0] | Branch (2699:21): [True: 0, False: 0] ------------------ 2700| 0| (TESTAFF(rv->astr, 'I', rv->alen)) && ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2700:13): [True: 0, False: 0] ------------------ 2701| 0| !(TESTAFF(rv->astr, 'J', rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2701:13): [True: 0, False: 0] ------------------ 2702| 0| numsyllable--; 2703| 0| } 2704| | // END of LANG_hu section 2705| | // increment word number, if the second root has a compoundroot flag 2706| 0| if ((rv) && (compoundroot) && ------------------ | Branch (2706:13): [True: 0, False: 0] | Branch (2706:21): [True: 0, False: 0] ------------------ 2707| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2707:13): [True: 0, False: 0] ------------------ 2708| 0| wordnum++; 2709| 0| } 2710| | 2711| | // check forbiddenwords 2712| 0| if ((rv) && (rv->astr) && ------------------ | Branch (2712:13): [True: 0, False: 0] | Branch (2712:13): [True: 0, False: 0] | Branch (2712:21): [True: 0, False: 0] ------------------ 2713| 0| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2714| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2715| 0| st[i] = ch; 2716| 0| continue; 2717| 0| } 2718| | 2719| | // second word is acceptable, as a root? 2720| | // hungarian conventions: compounding is acceptable, 2721| | // when compound forms consist of 2 words, or if more, 2722| | // then the syllable number of root words must be 6, or lesser. 2723| 0| if ((rv) && ------------------ | Branch (2723:13): [True: 0, False: 0] | Branch (2723:13): [True: 0, False: 0] ------------------ 2724| 0| ((compoundflag && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2724:15): [True: 0, False: 0] ------------------ 2725| 0| (compoundend && TESTAFF(rv->astr, compoundend, rv->alen))) && ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2725:15): [True: 0, False: 0] ------------------ 2726| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (2726:15): [True: 0, False: 0] | Branch (2726:37): [True: 0, False: 0] ------------------ 2727| 0| ((cpdmaxsyllable != 0) && ------------------ | Branch (2727:15): [True: 0, False: 0] ------------------ 2728| 0| (numsyllable + get_syllable(std::string(HENTRY_WORD(rv), rv->blen)) <= ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ | Branch (2728:15): [True: 0, False: 0] ------------------ 2729| 0| cpdmaxsyllable))) && 2730| 0| ((!checkcompounddup || (rv != rv_first)))) { ------------------ | Branch (2730:15): [True: 0, False: 0] | Branch (2730:36): [True: 0, False: 0] ------------------ 2731| | // bad compound word 2732| 0| result.append(presult); 2733| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2734| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2735| 0| result.append(word, i, word.size()); 2736| | 2737| 0| if (HENTRY_DATA(rv)) { ------------------ | Branch (2737:15): [True: 0, False: 0] ------------------ 2738| 0| if (complexprefixes) ------------------ | Branch (2738:17): [True: 0, False: 0] ------------------ 2739| 0| result.append(HENTRY_DATA2(rv)); 2740| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (2740:17): [True: 0, False: 0] ------------------ 2741| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2742| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 2743| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 2744| 0| } 2745| | // store the pointer of the hash entry 2746| 0| if (!complexprefixes) { ------------------ | Branch (2746:17): [True: 0, False: 0] ------------------ 2747| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2748| 0| result.append(HENTRY_DATA2(rv)); 2749| 0| } 2750| 0| } 2751| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2752| 0| ok = 1; 2753| 0| } 2754| | 2755| 0| numsyllable = oldnumsyllable2; 2756| 0| wordnum = oldwordnum2; 2757| | 2758| | // perhaps second word has prefix or/and suffix 2759| 0| sfx = nullptr; 2760| 0| sfxflag = FLAG_NULL; ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ 2761| | 2762| 0| if (compoundflag && !onlycpdrule) ------------------ | Branch (2762:13): [True: 0, False: 0] | Branch (2762:29): [True: 0, False: 0] ------------------ 2763| 0| rv = affix_check(word, i, word.size() - i, scratch, compoundflag); 2764| 0| else 2765| 0| rv = nullptr; 2766| | 2767| 0| if (!rv && compoundend && !onlycpdrule) { ------------------ | Branch (2767:13): [True: 0, False: 0] | Branch (2767:20): [True: 0, False: 0] | Branch (2767:35): [True: 0, False: 0] ------------------ 2768| 0| sfx = nullptr; 2769| 0| pfx = nullptr; 2770| 0| rv = affix_check(word, i, word.size() - i, scratch, compoundend, IN_CPD_END); ------------------ | | 77| 0|#define IN_CPD_END 2 ------------------ 2771| 0| } 2772| | 2773| 0| if (!rv && !defcpdtable.empty() && words) { ------------------ | Branch (2773:13): [True: 0, False: 0] | Branch (2773:20): [True: 0, False: 0] | Branch (2773:44): [True: 0, False: 0] ------------------ 2774| 0| rv = affix_check(word, i, word.size() - i, scratch, 0, IN_CPD_END); ------------------ | | 77| 0|#define IN_CPD_END 2 ------------------ 2775| 0| if (rv && words && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1)) { ------------------ | Branch (2775:15): [True: 0, False: 0] | Branch (2775:21): [True: 0, False: 0] | Branch (2775:30): [True: 0, False: 0] ------------------ 2776| 0| std::string m; 2777| 0| if (compoundflag) ------------------ | Branch (2777:17): [True: 0, False: 0] ------------------ 2778| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundflag); 2779| 0| if (m.empty() && compoundend) { ------------------ | Branch (2779:17): [True: 0, False: 0] | Branch (2779:30): [True: 0, False: 0] ------------------ 2780| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundend); 2781| 0| } 2782| 0| result.append(presult); 2783| 0| if (!m.empty()) { ------------------ | Branch (2783:17): [True: 0, False: 0] ------------------ 2784| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2785| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2786| 0| result.append(word, i, word.size()); 2787| 0| line_uniq_app(m, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2788| 0| result.append(m); 2789| 0| } 2790| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2791| 0| ok = 1; 2792| 0| } 2793| 0| } 2794| | 2795| | // check non_compound flag in suffix and prefix 2796| 0| if ((rv) && ------------------ | Branch (2796:13): [True: 0, False: 0] ------------------ 2797| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2797:15): [True: 0, False: 0] | Branch (2797:22): [True: 0, False: 0] ------------------ 2798| 0| TESTAFF(pfx->getCont(), compoundforbidflag, pfx->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2799| 0| (sfx && sfx->getCont() && ------------------ | Branch (2799:15): [True: 0, False: 0] | Branch (2799:22): [True: 0, False: 0] ------------------ 2800| 0| TESTAFF(sfx->getCont(), compoundforbidflag, ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2801| 0| sfx->getContLen())))) { 2802| 0| rv = nullptr; 2803| 0| } 2804| | 2805| | // check forbiddenwords 2806| 0| if ((rv) && (rv->astr) && ------------------ | Branch (2806:13): [True: 0, False: 0] | Branch (2806:13): [True: 0, False: 0] | Branch (2806:21): [True: 0, False: 0] ------------------ 2807| 0| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2808| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen)) && ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2809| 0| (!TESTAFF(rv->astr, needaffix, rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2809:13): [True: 0, False: 0] ------------------ 2810| 0| st[i] = ch; 2811| 0| continue; 2812| 0| } 2813| | 2814| 0| if (langnum == LANG_hu) { ------------------ | Branch (2814:13): [True: 0, False: 0] ------------------ 2815| | // calculate syllable number of the word 2816| 0| numsyllable += get_syllable(word.c_str() + i); 2817| | 2818| | // - affix syllable num. 2819| | // XXX only second suffix (inflections, not derivations) 2820| 0| if (sfxappnd) { ------------------ | Branch (2820:15): [True: 0, False: 0] ------------------ 2821| 0| std::string tmp(sfxappnd); 2822| 0| reverseword(tmp); 2823| 0| numsyllable -= short(get_syllable(tmp) + sfxextra); 2824| 0| } else { 2825| 0| numsyllable -= short(sfxextra); 2826| 0| } 2827| | 2828| | // + 1 word, if syllable number of the prefix > 1 (hungarian 2829| | // convention) 2830| 0| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (2830:15): [True: 0, False: 0] | Branch (2830:15): [True: 0, False: 0] | Branch (2830:22): [True: 0, False: 0] ------------------ 2831| 0| wordnum++; 2832| | 2833| | // increment syllable num, if last word has a SYLLABLENUM flag 2834| | // and the suffix is beginning `s' 2835| | 2836| 0| if (!cpdsyllablenum.empty()) { ------------------ | Branch (2836:15): [True: 0, False: 0] ------------------ 2837| 0| switch (sfxflag) { ------------------ | Branch (2837:21): [True: 0, False: 0] ------------------ 2838| 0| case 'c': { ------------------ | Branch (2838:15): [True: 0, False: 0] ------------------ 2839| 0| numsyllable += 2; 2840| 0| break; 2841| 0| } 2842| 0| case 'J': { ------------------ | Branch (2842:15): [True: 0, False: 0] ------------------ 2843| 0| numsyllable += 1; 2844| 0| break; 2845| 0| } 2846| 0| case 'I': { ------------------ | Branch (2846:15): [True: 0, False: 0] ------------------ 2847| 0| if (rv && TESTAFF(rv->astr, 'J', rv->alen)) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2847:21): [True: 0, False: 0] | Branch (2847:21): [True: 0, False: 0] ------------------ 2848| 0| numsyllable += 1; 2849| 0| break; 2850| 0| } 2851| 0| } 2852| 0| } 2853| 0| } 2854| | 2855| | // increment word number, if the second word has a compoundroot flag 2856| 0| if ((rv) && (compoundroot) && ------------------ | Branch (2856:13): [True: 0, False: 0] | Branch (2856:21): [True: 0, False: 0] ------------------ 2857| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2857:13): [True: 0, False: 0] ------------------ 2858| 0| wordnum++; 2859| 0| } 2860| | // second word is acceptable, as a word with prefix or/and suffix? 2861| | // hungarian conventions: compounding is acceptable, 2862| | // when compound forms consist 2 word, otherwise 2863| | // the syllable number of root words is 6, or lesser. 2864| 0| if ((rv) && ------------------ | Branch (2864:13): [True: 0, False: 0] ------------------ 2865| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (2865:15): [True: 0, False: 0] | Branch (2865:37): [True: 0, False: 0] ------------------ 2866| 0| ((cpdmaxsyllable != 0) && (numsyllable <= cpdmaxsyllable))) && ------------------ | Branch (2866:15): [True: 0, False: 0] | Branch (2866:40): [True: 0, False: 0] ------------------ 2867| 0| ((!checkcompounddup || (rv != rv_first)))) { ------------------ | Branch (2867:15): [True: 0, False: 0] | Branch (2867:36): [True: 0, False: 0] ------------------ 2868| 0| std::string m; 2869| 0| if (compoundflag) ------------------ | Branch (2869:15): [True: 0, False: 0] ------------------ 2870| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundflag, IN_CPD_END); ------------------ | | 77| 0|#define IN_CPD_END 2 ------------------ 2871| 0| if (m.empty() && compoundend) { ------------------ | Branch (2871:15): [True: 0, False: 0] | Branch (2871:28): [True: 0, False: 0] ------------------ 2872| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundend, IN_CPD_END); ------------------ | | 77| 0|#define IN_CPD_END 2 ------------------ 2873| 0| } 2874| 0| result.append(presult); 2875| 0| if (!m.empty()) { ------------------ | Branch (2875:15): [True: 0, False: 0] ------------------ 2876| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2877| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2878| 0| result.append(word, i, word.size()); 2879| 0| line_uniq_app(m, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2880| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2881| 0| result.append(m); 2882| 0| } 2883| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2884| 0| ok = 1; 2885| 0| } 2886| | 2887| 0| numsyllable = oldnumsyllable2; 2888| 0| wordnum = oldwordnum2; 2889| | 2890| | // perhaps second word is a compound word (recursive call) 2891| 0| if ((wordnum + 2 < maxwordnum) && (wnum + 1 < maxwordnum) && (ok == 0)) { ------------------ | Branch (2891:13): [True: 0, False: 0] | Branch (2891:43): [True: 0, False: 0] | Branch (2891:70): [True: 0, False: 0] ------------------ 2892| 0| compound_check_morph(word.substr(i), wordnum + 1, 2893| 0| numsyllable, maxwordnum, wnum + 1, words, rwords, 0, 2894| 0| result, &presult, scratch); 2895| 0| } else { 2896| 0| rv = nullptr; 2897| 0| } 2898| 0| } 2899| 29.9k| st[i] = ch; 2900| 29.9k| wordnum = oldwordnum; 2901| 29.9k| numsyllable = oldnumsyllable; 2902| | 2903| 29.9k| } while (!defcpdtable.empty() && oldwordnum == 0 && ------------------ | Branch (2903:14): [True: 0, False: 29.9k] | Branch (2903:38): [True: 0, False: 0] ------------------ 2904| 0| onlycpdrule++ < 1); // end of onlycpd loop ------------------ | Branch (2904:14): [True: 0, False: 0] ------------------ 2905| 30.1k| } 2906| 2.00k| return 0; 2907| 2.30k|} _ZNK8AffixMgr12circumfix_okEP8PfxEntryP8SfxEntryPK8TraceCtx: 2923| 49.1k|bool AffixMgr::circumfix_ok(PfxEntry* pfx, SfxEntry* sfx, const TraceCtx* t) const { 2924| 49.1k| if (!circumfix) ------------------ | Branch (2924:7): [True: 49.1k, False: 0] ------------------ 2925| 49.1k| return true; 2926| 0| bool in_prefix = pfx && pfx->getCont() && ------------------ | Branch (2926:20): [True: 0, False: 0] | Branch (2926:27): [True: 0, False: 0] ------------------ 2927| 0| TESTAFF(pfx->getCont(), circumfix, pfx->getContLen()); ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2928| 0| bool in_suffix = sfx->getCont() && ------------------ | Branch (2928:20): [True: 0, False: 0] ------------------ 2929| 0| TESTAFF(sfx->getCont(), circumfix, sfx->getContLen()); ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2930| 0| if (t) ------------------ | Branch (2930:7): [True: 0, False: 0] ------------------ 2931| 0| trace_circumfix(*t, this, circumfix, pfx, sfx, in_prefix, in_suffix); 2932| 0| return in_prefix == in_suffix; 2933| 49.1k|} _ZNK8AffixMgr17suffix_applicableEP8PfxEntryP8SfxEntrytcPK8TraceCtx: 2953| 241k| const TraceCtx* t) const { 2954| | // suffixes are only allowed at the beginning of a compound when they are signed with the 2955| | // compoundpermitflag flag 2956| 241k| if (in_compound == IN_CPD_BEGIN && ------------------ | | 76| 483k|#define IN_CPD_BEGIN 1 ------------------ | Branch (2956:7): [True: 192k, False: 49.1k] ------------------ 2957| 192k| !(sfx->getCont() && compoundpermitflag && ------------------ | Branch (2957:9): [True: 192k, False: 0] | Branch (2957:27): [True: 0, False: 192k] ------------------ 2958| 192k| TESTAFF(sfx->getCont(), compoundpermitflag, sfx->getContLen()))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2959| 192k| if (t) ------------------ | Branch (2959:9): [True: 0, False: 192k] ------------------ 2960| 0| trace_test(*t, "compoundpermit", this, compoundpermitflag, "sfx-cont", 2961| 0| sfx->getCont(), sfx->getContLen(), 2962| 0| "fail, a suffix at the start of a compound needs this flag"); 2963| 192k| return false; 2964| 192k| } 2965| | 2966| 49.1k| if (!circumfix_ok(pfx, sfx, t)) ------------------ | Branch (2966:7): [True: 0, False: 49.1k] ------------------ 2967| 0| return false; 2968| | 2969| | // a fogemorpheme is only allowed inside a compound 2970| 49.1k| if (!in_compound && sfx->getCont() && ------------------ | Branch (2970:7): [True: 49.1k, False: 6] | Branch (2970:23): [True: 19.5k, False: 29.6k] ------------------ 2971| 19.5k| TESTAFF(sfx->getCont(), onlyincompound, sfx->getContLen())) { ------------------ | | 102| 19.5k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 19.5k] | | ------------------ ------------------ 2972| 0| if (t) ------------------ | Branch (2972:9): [True: 0, False: 0] ------------------ 2973| 0| trace_test(*t, "onlyincompound", this, onlyincompound, "sfx-cont", 2974| 0| sfx->getCont(), sfx->getContLen(), 2975| 0| "fail, this suffix is only allowed inside a compound"); 2976| 0| return false; 2977| 0| } 2978| | 2979| | // a needaffix suffix needs a further affix, so it is allowed either as a second suffix or 2980| | // when a prefix is present that does not itself need one 2981| 49.1k| if (!cclass && sfx->getCont() && ------------------ | Branch (2981:7): [True: 47.9k, False: 1.25k] | Branch (2981:18): [True: 19.5k, False: 28.3k] ------------------ 2982| 19.5k| TESTAFF(sfx->getCont(), needaffix, sfx->getContLen()) && ------------------ | | 102| 68.7k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 19.5k] | | ------------------ ------------------ 2983| 0| !(pfx && !(pfx->getCont() && ------------------ | Branch (2983:9): [True: 0, False: 0] | Branch (2983:18): [True: 0, False: 0] ------------------ 2984| 0| TESTAFF(pfx->getCont(), needaffix, pfx->getContLen())))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 2985| 0| if (t) ------------------ | Branch (2985:9): [True: 0, False: 0] ------------------ 2986| 0| trace_test(*t, "needaffix", this, needaffix, "sfx-cont", sfx->getCont(), 2987| 0| sfx->getContLen(), 2988| 0| "fail, this suffix needs a further affix and has none"); 2989| 0| return false; 2990| 0| } 2991| | 2992| 49.1k| return true; 2993| 49.1k|} _ZN8AffixMgr12suffix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratchttct: 3005| 539M| const FLAG avoidflag) { 3006| 539M| struct hentry* rv = nullptr; 3007| | 3008| 539M| TraceCtx* t = trace_on(scratch.trace); 3009| 539M| int candidates = 0; 3010| | // a pass that had nothing to try says so, which is different from a pass that 3011| | // did not run 3012| 539M| auto report_empty_pass = [t, &word, start, len, sfxopts, &candidates]() { 3013| 539M| if (t && candidates == 0) 3014| 539M| trace(*t, "sfx \"%s\" candidates=0%s", word.substr(start, len).c_str(), 3015| 539M| (sfxopts & aeXPRODUCT) != 0 ? " xprod=Y" : ""); 3016| 539M| }; 3017| | // a rule the suffix conditions turned away never reaches checkword, so name 3018| | // the rule here and run the conditions again to say which of them refused it 3019| 539M| auto report_refused = [this, t, ppfx, cclass, in_compound, 3020| 539M| &candidates](SfxEntry* se) { 3021| 539M| if (!t) 3022| 539M| return; 3023| 539M| ++candidates; 3024| 539M| trace_affix(*t, "sfx", this, *se); 3025| 539M| TraceScope trace_depth(t); 3026| 539M| suffix_applicable(ppfx, se, cclass, in_compound, t); 3027| 539M| }; 3028| | 3029| | // first handle the special case of 0 length suffixes 3030| 539M| SfxEntry* se = sStart[0]; 3031| | 3032| 539M| while (se) { ------------------ | Branch (3032:10): [True: 0, False: 539M] ------------------ 3033| 0| if (!cclass || se->getCont()) { ------------------ | Branch (3033:9): [True: 0, False: 0] | Branch (3033:20): [True: 0, False: 0] ------------------ 3034| 0| if (suffix_applicable(ppfx, se, cclass, in_compound, nullptr)) { ------------------ | Branch (3034:11): [True: 0, False: 0] ------------------ 3035| 0| ++candidates; 3036| 0| rv = se->checkword(word, start, len, sfxopts, ppfx, 3037| 0| (FLAG)cclass, needflag, 3038| 0| (in_compound ? 0 : onlyincompound), ------------------ | Branch (3038:29): [True: 0, False: 0] ------------------ 3039| 0| scratch); 3040| | // Skip a stem with the avoid flag and keep scanning the other suffixes. 3041| 0| if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) { ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (3041:13): [True: 0, False: 0] | Branch (3041:19): [True: 0, False: 0] ------------------ 3042| 0| trace_avoidflag(t, avoidflag, rv); 3043| 0| rv = nullptr; 3044| 0| } 3045| 0| if (rv) { ------------------ | Branch (3045:13): [True: 0, False: 0] ------------------ 3046| 0| sfx = se; // BUG: sfx not stateless 3047| 0| return rv; 3048| 0| } 3049| 0| } else { 3050| 0| report_refused(se); 3051| 0| } 3052| 0| } 3053| 0| se = se->getNext(); 3054| 0| } 3055| | 3056| | // now handle the general case 3057| 539M| if (len == 0) { ------------------ | Branch (3057:7): [True: 44.8k, False: 539M] ------------------ 3058| 44.8k| report_empty_pass(); 3059| 44.8k| return nullptr; // FULLSTRIP 3060| 44.8k| } 3061| 539M| unsigned char sp = word[start + len - 1]; 3062| 539M| SfxEntry* sptr = sStart[sp]; 3063| | 3064| 539M| while (sptr) { ------------------ | Branch (3064:10): [True: 264k, False: 539M] ------------------ 3065| 264k| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (3065:9): [True: 241k, False: 23.0k] ------------------ 3066| 241k| if (!suffix_applicable(ppfx, sptr, cclass, in_compound, nullptr)) ------------------ | Branch (3066:11): [True: 192k, False: 49.1k] ------------------ 3067| 192k| report_refused(sptr); 3068| 49.1k| else if (in_compound != IN_CPD_END || ppfx || ------------------ | | 77| 98.3k|#define IN_CPD_END 2 ------------------ | Branch (3068:16): [True: 49.1k, False: 6] | Branch (3068:45): [True: 0, False: 6] ------------------ 3069| 6| !(sptr->getCont() && ------------------ | Branch (3069:18): [True: 6, False: 0] ------------------ 3070| 49.1k| TESTAFF(sptr->getCont(), onlyincompound, sptr->getContLen()))) { ------------------ | | 102| 6|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 6] | | ------------------ ------------------ 3071| 49.1k| ++candidates; 3072| 49.1k| rv = sptr->checkword(word, start, len, sfxopts, ppfx, 3073| 49.1k| cclass, needflag, 3074| 49.1k| (in_compound ? 0 : onlyincompound), ------------------ | Branch (3074:31): [True: 6, False: 49.1k] ------------------ 3075| 49.1k| scratch); 3076| 49.1k| if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) { ------------------ | | 99| 49.1k|#define FLAG_NULL 0x00 ------------------ if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (3076:13): [True: 0, False: 49.1k] | Branch (3076:19): [True: 0, False: 0] ------------------ 3077| 0| trace_avoidflag(t, avoidflag, rv); 3078| 0| rv = nullptr; 3079| 0| } 3080| 49.1k| if (rv) { ------------------ | Branch (3080:13): [True: 0, False: 49.1k] ------------------ 3081| 0| sfx = sptr; // BUG: sfx not stateless 3082| 0| sfxflag = sptr->getFlag(); // BUG: sfxflag not stateless 3083| 0| if (!sptr->getCont()) ------------------ | Branch (3083:15): [True: 0, False: 0] ------------------ 3084| 0| sfxappnd = sptr->getKey(); // BUG: sfxappnd not stateless 3085| | // LANG_hu section: spec. Hungarian rule 3086| 0| else if (langnum == LANG_hu && sptr->getKeyLen() && ------------------ | Branch (3086:20): [True: 0, False: 0] | Branch (3086:42): [True: 0, False: 0] ------------------ 3087| 0| sptr->getKey()[0] == 'i' && sptr->getKey()[1] != 'y' && ------------------ | Branch (3087:20): [True: 0, False: 0] | Branch (3087:48): [True: 0, False: 0] ------------------ 3088| 0| sptr->getKey()[1] != 't') { ------------------ | Branch (3088:20): [True: 0, False: 0] ------------------ 3089| 0| sfxextra = 1; 3090| 0| } 3091| | // END of LANG_hu section 3092| 0| return rv; 3093| 0| } 3094| 49.1k| } 3095| 241k| sptr = sptr->getNextEQ(); 3096| 241k| } else { 3097| 23.0k| sptr = sptr->getNextNE(); 3098| 23.0k| } 3099| 264k| } 3100| | 3101| 539M| report_empty_pass(); 3102| | 3103| 539M| return nullptr; 3104| 539M|} _ZN8AffixMgr19suffix_check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratcht: 3113| 16.6M| const FLAG needflag) { 3114| 16.6M| struct hentry* rv = nullptr; 3115| | 3116| | // first handle the special case of 0 length suffixes 3117| 16.6M| SfxEntry* se = sStart[0]; 3118| 16.6M| while (se) { ------------------ | Branch (3118:10): [True: 0, False: 16.6M] ------------------ 3119| 0| if (contclasses[se->getFlag()]) { ------------------ | Branch (3119:9): [True: 0, False: 0] ------------------ 3120| 0| rv = se->check_twosfx(word, start, len, sfxopts, ppfx, needflag, scratch); 3121| 0| if (rv) ------------------ | Branch (3121:11): [True: 0, False: 0] ------------------ 3122| 0| return rv; 3123| 0| } 3124| 0| se = se->getNext(); 3125| 0| } 3126| | 3127| | // now handle the general case 3128| 16.6M| if (len == 0) ------------------ | Branch (3128:7): [True: 13.6k, False: 16.6M] ------------------ 3129| 13.6k| return nullptr; // FULLSTRIP 3130| 16.6M| unsigned char sp = word[start + len - 1]; 3131| 16.6M| SfxEntry* sptr = sStart[sp]; 3132| | 3133| 16.6M| while (sptr) { ------------------ | Branch (3133:10): [True: 63.0k, False: 16.6M] ------------------ 3134| 63.0k| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (3134:9): [True: 45.5k, False: 17.4k] ------------------ 3135| 45.5k| if (contclasses[sptr->getFlag()]) { ------------------ | Branch (3135:11): [True: 26.0k, False: 19.5k] ------------------ 3136| 26.0k| rv = sptr->check_twosfx(word, start, len, sfxopts, ppfx, needflag, scratch); 3137| 26.0k| if (rv) { ------------------ | Branch (3137:13): [True: 0, False: 26.0k] ------------------ 3138| 0| sfxflag = sptr->getFlag(); // BUG: sfxflag not stateless 3139| 0| if (!sptr->getCont()) ------------------ | Branch (3139:15): [True: 0, False: 0] ------------------ 3140| 0| sfxappnd = sptr->getKey(); // BUG: sfxappnd not stateless 3141| 0| return rv; 3142| 0| } 3143| 26.0k| } 3144| 45.5k| sptr = sptr->getNextEQ(); 3145| 45.5k| } else { 3146| 17.4k| sptr = sptr->getNextNE(); 3147| 17.4k| } 3148| 63.0k| } 3149| | 3150| 16.6M| return nullptr; 3151| 16.6M|} _ZN8AffixMgr25suffix_check_twosfx_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratcht: 3160| 3.97k| const FLAG needflag) { 3161| 3.97k| std::string result2; 3162| 3.97k| std::string result3; 3163| | // the second suffix runs the whole suffix table again for every first suffix 3164| 3.97k| DistinctRecords result(MSEP_REC); ------------------ | | 122| 3.97k|#define MSEP_REC '\n' ------------------ 3165| | 3166| | // first handle the special case of 0 length suffixes 3167| 3.97k| SfxEntry* se = sStart[0]; 3168| 3.97k| while (se) { ------------------ | Branch (3168:10): [True: 0, False: 3.97k] ------------------ 3169| 0| if (contclasses[se->getFlag()]) { ------------------ | Branch (3169:9): [True: 0, False: 0] ------------------ 3170| 0| std::string st = se->check_twosfx_morph(word, start, len, sfxopts, ppfx, needflag, scratch); 3171| 0| if (!st.empty()) { ------------------ | Branch (3171:11): [True: 0, False: 0] ------------------ 3172| 0| std::string analysis; 3173| 0| if (ppfx) { ------------------ | Branch (3173:13): [True: 0, False: 0] ------------------ 3174| 0| if (ppfx->getMorph()) { ------------------ | Branch (3174:15): [True: 0, False: 0] ------------------ 3175| 0| analysis.append(ppfx->getMorph()); 3176| 0| analysis.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3177| 0| } else 3178| 0| debugflag(analysis, ppfx->getFlag()); 3179| 0| } 3180| 0| analysis.append(st); 3181| 0| if (se->getMorph()) { ------------------ | Branch (3181:13): [True: 0, False: 0] ------------------ 3182| 0| analysis.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3183| 0| analysis.append(se->getMorph()); 3184| 0| } else 3185| 0| debugflag(analysis, se->getFlag()); 3186| 0| result.append(analysis); 3187| 0| } 3188| 0| } 3189| 0| se = se->getNext(); 3190| 0| } 3191| | 3192| | // now handle the general case 3193| 3.97k| if (len == 0) ------------------ | Branch (3193:7): [True: 0, False: 3.97k] ------------------ 3194| 0| return { }; // FULLSTRIP 3195| 3.97k| unsigned char sp = word[start + len - 1]; 3196| 3.97k| SfxEntry* sptr = sStart[sp]; 3197| | 3198| 3.97k| while (sptr) { ------------------ | Branch (3198:10): [True: 0, False: 3.97k] ------------------ 3199| 0| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (3199:9): [True: 0, False: 0] ------------------ 3200| 0| if (contclasses[sptr->getFlag()]) { ------------------ | Branch (3200:11): [True: 0, False: 0] ------------------ 3201| 0| std::string st = sptr->check_twosfx_morph(word, start, len, sfxopts, ppfx, needflag, scratch); 3202| 0| if (!st.empty()) { ------------------ | Branch (3202:13): [True: 0, False: 0] ------------------ 3203| 0| sfxflag = sptr->getFlag(); // BUG: sfxflag not stateless 3204| 0| if (!sptr->getCont()) ------------------ | Branch (3204:15): [True: 0, False: 0] ------------------ 3205| 0| sfxappnd = sptr->getKey(); // BUG: sfxappnd not stateless 3206| 0| result2.assign(st); 3207| | 3208| 0| result3.clear(); 3209| | 3210| 0| if (sptr->getMorph()) { ------------------ | Branch (3210:15): [True: 0, False: 0] ------------------ 3211| 0| result3.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3212| 0| result3.append(sptr->getMorph()); 3213| 0| } else 3214| 0| debugflag(result3, sptr->getFlag()); 3215| 0| strlinecat(result2, result3); 3216| 0| result.append(result2); 3217| 0| } 3218| 0| } 3219| 0| sptr = sptr->getNextEQ(); 3220| 0| } else { 3221| 0| sptr = sptr->getNextNE(); 3222| 0| } 3223| 0| } 3224| | 3225| 3.97k| return result.join(); 3226| 3.97k|} _ZN8AffixMgr18suffix_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratchttc: 3236| 12.7k| char in_compound) { 3237| 12.7k| std::string result; 3238| | 3239| 12.7k| struct hentry* rv = nullptr; 3240| | 3241| | // first handle the special case of 0 length suffixes 3242| 12.7k| SfxEntry* se = sStart[0]; 3243| 12.7k| while (se) { ------------------ | Branch (3243:10): [True: 0, False: 12.7k] ------------------ 3244| 0| if (!cclass || se->getCont()) { ------------------ | Branch (3244:9): [True: 0, False: 0] | Branch (3244:20): [True: 0, False: 0] ------------------ 3245| 0| if (suffix_applicable(ppfx, se, cclass, in_compound, nullptr)) ------------------ | Branch (3245:11): [True: 0, False: 0] ------------------ 3246| 0| rv = se->checkword(word, start, len, sfxopts, ppfx, cclass, 3247| 0| needflag, FLAG_NULL, scratch); ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ 3248| 0| while (rv) { ------------------ | Branch (3248:14): [True: 0, False: 0] ------------------ 3249| 0| if (ppfx) { ------------------ | Branch (3249:13): [True: 0, False: 0] ------------------ 3250| 0| if (ppfx->getMorph()) { ------------------ | Branch (3250:15): [True: 0, False: 0] ------------------ 3251| 0| result.append(ppfx->getMorph()); 3252| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3253| 0| } else 3254| 0| debugflag(result, ppfx->getFlag()); 3255| 0| } 3256| 0| if (complexprefixes && HENTRY_DATA(rv)) ------------------ | Branch (3256:13): [True: 0, False: 0] | Branch (3256:32): [True: 0, False: 0] ------------------ 3257| 0| result.append(HENTRY_DATA2(rv)); 3258| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (3258:13): [True: 0, False: 0] ------------------ 3259| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3260| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 3261| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 3262| 0| } 3263| | 3264| 0| if (!complexprefixes && HENTRY_DATA(rv)) { ------------------ | Branch (3264:13): [True: 0, False: 0] | Branch (3264:33): [True: 0, False: 0] ------------------ 3265| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3266| 0| result.append(HENTRY_DATA2(rv)); 3267| 0| } 3268| 0| if (se->getMorph()) { ------------------ | Branch (3268:13): [True: 0, False: 0] ------------------ 3269| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3270| 0| result.append(se->getMorph()); 3271| 0| } else 3272| 0| debugflag(result, se->getFlag()); 3273| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 3274| 0| rv = se->get_next_homonym(rv, sfxopts, ppfx, cclass, needflag); 3275| 0| } 3276| 0| } 3277| 0| se = se->getNext(); 3278| 0| } 3279| | 3280| | // now handle the general case 3281| 12.7k| if (len == 0) ------------------ | Branch (3281:7): [True: 0, False: 12.7k] ------------------ 3282| 0| return { }; // FULLSTRIP 3283| 12.7k| unsigned char sp = word[start + len - 1]; 3284| 12.7k| SfxEntry* sptr = sStart[sp]; 3285| | 3286| 12.7k| while (sptr) { ------------------ | Branch (3286:10): [True: 0, False: 12.7k] ------------------ 3287| 0| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (3287:9): [True: 0, False: 0] ------------------ 3288| 0| if (suffix_applicable(ppfx, sptr, cclass, in_compound, nullptr)) ------------------ | Branch (3288:11): [True: 0, False: 0] ------------------ 3289| 0| rv = sptr->checkword(word, start, len, sfxopts, ppfx, cclass, 3290| 0| needflag, FLAG_NULL, scratch); ------------------ | | 99| 0|#define FLAG_NULL 0x00 ------------------ 3291| 0| while (rv) { ------------------ | Branch (3291:14): [True: 0, False: 0] ------------------ 3292| 0| if (ppfx) { ------------------ | Branch (3292:13): [True: 0, False: 0] ------------------ 3293| 0| if (ppfx->getMorph()) { ------------------ | Branch (3293:15): [True: 0, False: 0] ------------------ 3294| 0| result.append(ppfx->getMorph()); 3295| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3296| 0| } else 3297| 0| debugflag(result, ppfx->getFlag()); 3298| 0| } 3299| 0| if (complexprefixes && HENTRY_DATA(rv)) ------------------ | Branch (3299:13): [True: 0, False: 0] | Branch (3299:32): [True: 0, False: 0] ------------------ 3300| 0| result.append(HENTRY_DATA2(rv)); 3301| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (3301:13): [True: 0, False: 0] ------------------ 3302| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3303| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 3304| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 3305| 0| } 3306| | 3307| 0| if (!complexprefixes && HENTRY_DATA(rv)) { ------------------ | Branch (3307:13): [True: 0, False: 0] | Branch (3307:33): [True: 0, False: 0] ------------------ 3308| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3309| 0| result.append(HENTRY_DATA2(rv)); 3310| 0| } 3311| | 3312| 0| if (sptr->getMorph()) { ------------------ | Branch (3312:13): [True: 0, False: 0] ------------------ 3313| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3314| 0| result.append(sptr->getMorph()); 3315| 0| } else 3316| 0| debugflag(result, sptr->getFlag()); 3317| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 3318| 0| rv = sptr->get_next_homonym(rv, sfxopts, ppfx, cclass, needflag); 3319| 0| } 3320| 0| sptr = sptr->getNextEQ(); 3321| 0| } else { 3322| 0| sptr = sptr->getNextNE(); 3323| 0| } 3324| 0| } 3325| | 3326| 12.7k| return result; 3327| 12.7k|} _ZN8AffixMgr11affix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiR12AffixScratchtctPP8PfxEntryPP8SfxEntry: 3362| 17.4M| SfxEntry** found_sfx) { 3363| | 3364| 17.4M| TraceCtx* t = trace_on(scratch.trace); 3365| | // the affixes that built the word are reported before the members holding them are cleared 3366| 17.4M| auto report_form = [this, t, &word, start, len, found_pfx, found_sfx](const struct hentry* rv) { 3367| 17.4M| if (!rv) 3368| 17.4M| return; 3369| 17.4M| if (t) 3370| 17.4M| trace_form(*t, this, word.substr(start, len), rv->word, pfx, sfx); 3371| 17.4M| if (found_pfx) 3372| 17.4M| *found_pfx = pfx; 3373| 17.4M| if (found_sfx) 3374| 17.4M| *found_sfx = sfx; 3375| 17.4M| }; 3376| | 3377| | // check all prefixes (also crossed with suffixes if allowed) 3378| 17.4M| struct hentry* rv = prefix_check(word, start, len, in_compound, scratch, needflag, avoidflag); 3379| 17.4M| if (rv) { ------------------ | Branch (3379:7): [True: 0, False: 17.4M] ------------------ 3380| 0| report_form(rv); 3381| 0| return rv; 3382| 0| } 3383| | 3384| | // if still not found check all suffixes 3385| 17.4M| rv = suffix_check(word, start, len, 0, nullptr, scratch, FLAG_NULL, needflag, in_compound, avoidflag); ------------------ | | 99| 17.4M|#define FLAG_NULL 0x00 ------------------ 3386| | 3387| 17.4M| if (havecontclass) { ------------------ | Branch (3387:7): [True: 5.82M, False: 11.6M] ------------------ 3388| 5.82M| if (rv) ------------------ | Branch (3388:9): [True: 0, False: 5.82M] ------------------ 3389| 0| report_form(rv); 3390| | 3391| 5.82M| sfx = nullptr; 3392| 5.82M| pfx = nullptr; 3393| | 3394| 5.82M| if (rv) ------------------ | Branch (3394:9): [True: 0, False: 5.82M] ------------------ 3395| 0| return rv; 3396| | // if still not found check all two-level suffixes 3397| 5.82M| rv = suffix_check_twosfx(word, start, len, 0, nullptr, scratch, needflag); 3398| | 3399| 5.82M| if (rv) { ------------------ | Branch (3399:9): [True: 0, False: 5.82M] ------------------ 3400| 0| report_form(rv); 3401| 0| return rv; 3402| 0| } 3403| | // if still not found check all two-level suffixes 3404| 5.82M| rv = prefix_check_twosfx(word, start, len, IN_CPD_NOT, scratch, needflag); ------------------ | | 75| 5.82M|#define IN_CPD_NOT 0 ------------------ 3405| 5.82M| } 3406| | 3407| 17.4M| report_form(rv); 3408| | 3409| 17.4M| return rv; 3410| 17.4M|} _ZN8AffixMgr17affix_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiR12AffixScratchtc: 3418| 12.7k| char in_compound) { 3419| | // the four checks below overlap 3420| 12.7k| DistinctRecords result(MSEP_REC); ------------------ | | 122| 12.7k|#define MSEP_REC '\n' ------------------ 3421| | 3422| | // check all prefixes (also crossed with suffixes if allowed) 3423| 12.7k| std::string st = prefix_check_morph(word, start, len, in_compound, scratch); 3424| 12.7k| if (!st.empty()) { ------------------ | Branch (3424:7): [True: 0, False: 12.7k] ------------------ 3425| 0| result.append(st); 3426| 0| } 3427| | 3428| | // if still not found check all suffixes 3429| 12.7k| st = suffix_check_morph(word, start, len, 0, nullptr, scratch, '\0', needflag, in_compound); 3430| 12.7k| if (!st.empty()) { ------------------ | Branch (3430:7): [True: 0, False: 12.7k] ------------------ 3431| 0| result.append(st); 3432| 0| } 3433| | 3434| 12.7k| if (havecontclass) { ------------------ | Branch (3434:7): [True: 3.97k, False: 8.74k] ------------------ 3435| 3.97k| sfx = nullptr; 3436| 3.97k| pfx = nullptr; 3437| | // if still not found check all two-level suffixes 3438| 3.97k| st = suffix_check_twosfx_morph(word, start, len, 0, nullptr, scratch, needflag); 3439| 3.97k| if (!st.empty()) { ------------------ | Branch (3439:9): [True: 0, False: 3.97k] ------------------ 3440| 0| result.append(st); 3441| 0| } 3442| | 3443| | // if still not found check all two-level suffixes 3444| 3.97k| st = prefix_check_twosfx_morph(word, start, len, IN_CPD_NOT, scratch, needflag); ------------------ | | 75| 3.97k|#define IN_CPD_NOT 0 ------------------ 3445| 3.97k| if (!st.empty()) { ------------------ | Branch (3445:9): [True: 0, False: 3.97k] ------------------ 3446| 0| result.append(st); 3447| 0| } 3448| 3.97k| } 3449| | 3450| 12.7k| return result.join(); 3451| 12.7k|} _ZN8AffixMgr15expand_rootwordEP9guesswordiPKciPKttS3_iS3_: 3647| 545k| const char* phon) { 3648| 545k| int nh = 0; 3649| | // first add root word to list 3650| 545k| if ((nh < maxn) && ------------------ | Branch (3650:7): [True: 545k, False: 0] ------------------ 3651| 545k| !(al && ((needaffix && TESTAFF(ap, needaffix, al)) || ------------------ | | 102| 4.37k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 2.18k, False: 2.18k] | | ------------------ ------------------ | Branch (3651:9): [True: 96.0k, False: 449k] | Branch (3651:17): [True: 4.37k, False: 91.6k] ------------------ 3652| 543k| (onlyincompound && TESTAFF(ap, onlyincompound, al))))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (3652:17): [True: 0, False: 93.8k] ------------------ 3653| 543k| wlst[nh].word = mystrdup(ts); 3654| 543k| wlst[nh].allow = false; 3655| 543k| wlst[nh].orig = nullptr; 3656| 543k| nh++; 3657| | // add special phonetic version 3658| 543k| if (phon && (nh < maxn)) { ------------------ | Branch (3658:9): [True: 887, False: 542k] | Branch (3658:17): [True: 887, False: 0] ------------------ 3659| 887| wlst[nh].word = mystrdup(phon); 3660| 887| wlst[nh].allow = false; 3661| 887| wlst[nh].orig = mystrdup(ts); 3662| 887| nh++; 3663| 887| } 3664| 543k| } 3665| | 3666| | // handle suffixes 3667| 653k| for (int i = 0; i < al; i++) { ------------------ | Branch (3667:19): [True: 107k, False: 545k] ------------------ 3668| 107k| const auto c = (unsigned char)(ap[i] & 0x00FF); 3669| 107k| SfxEntry* sptr = sFlag[c]; 3670| 172k| while (sptr) { ------------------ | Branch (3670:12): [True: 64.2k, False: 107k] ------------------ 3671| 64.2k| if ((sptr->getFlag() == ap[i]) && ------------------ | Branch (3671:11): [True: 64.2k, False: 0] ------------------ 3672| 64.2k| (!sptr->getKeyLen() || ------------------ | Branch (3672:12): [True: 0, False: 64.2k] ------------------ 3673| 64.2k| ((badl > sptr->getKeyLen()) && ------------------ | Branch (3673:13): [True: 36.6k, False: 27.5k] ------------------ 3674| 36.6k| (strcmp(sptr->getAffix(), bad + badl - sptr->getKeyLen()) == 0))) && ------------------ | Branch (3674:13): [True: 27, False: 36.6k] ------------------ 3675| | // check needaffix flag 3676| 27| !(sptr->getCont() && ------------------ | Branch (3676:13): [True: 14, False: 13] ------------------ 3677| 14| ((needaffix && ------------------ | Branch (3677:15): [True: 7, False: 7] ------------------ 3678| 7| TESTAFF(sptr->getCont(), needaffix, sptr->getContLen())) || ------------------ | | 102| 7|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 7] | | ------------------ ------------------ 3679| 14| (circumfix && ------------------ | Branch (3679:15): [True: 0, False: 14] ------------------ 3680| 0| TESTAFF(sptr->getCont(), circumfix, sptr->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 3681| 14| (onlyincompound && ------------------ | Branch (3681:15): [True: 0, False: 14] ------------------ 3682| 27| TESTAFF(sptr->getCont(), onlyincompound, sptr->getContLen()))))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 3683| 27| std::string newword = sptr->add(ts, wl); 3684| 27| if (!newword.empty()) { ------------------ | Branch (3684:13): [True: 27, False: 0] ------------------ 3685| 27| if (nh < maxn) { ------------------ | Branch (3685:15): [True: 27, False: 0] ------------------ 3686| 27| wlst[nh].word = mystrdup(newword.c_str()); 3687| 27| wlst[nh].allow = sptr->allowCross(); 3688| 27| wlst[nh].orig = nullptr; 3689| 27| nh++; 3690| | // add special phonetic version 3691| 27| if (phon && (nh < maxn)) { ------------------ | Branch (3691:17): [True: 0, False: 27] | Branch (3691:25): [True: 0, False: 0] ------------------ 3692| 0| std::string prefix(phon); 3693| 0| std::string key(sptr->getKey()); 3694| 0| reverseword(key); 3695| 0| prefix.append(key); 3696| 0| wlst[nh].word = mystrdup(prefix.c_str()); 3697| 0| wlst[nh].allow = false; 3698| 0| wlst[nh].orig = mystrdup(newword.c_str()); 3699| 0| nh++; 3700| 0| } 3701| 27| } 3702| 27| } 3703| 27| } 3704| 64.2k| sptr = sptr->getFlgNxt(); 3705| 64.2k| } 3706| 107k| } 3707| | 3708| 545k| int n = nh; 3709| | 3710| | // handle cross products of prefixes and suffixes 3711| 546k| for (int j = 1; j < n; j++) ------------------ | Branch (3711:19): [True: 907, False: 545k] ------------------ 3712| 907| if (wlst[j].allow) { ------------------ | Branch (3712:9): [True: 20, False: 887] ------------------ 3713| 60| for (int k = 0; k < al; k++) { ------------------ | Branch (3713:23): [True: 40, False: 20] ------------------ 3714| 40| const auto c = (unsigned char)(ap[k] & 0x00FF); 3715| 40| PfxEntry* cptr = pFlag[c]; 3716| 40| while (cptr) { ------------------ | Branch (3716:16): [True: 0, False: 40] ------------------ 3717| 0| if ((cptr->getFlag() == ap[k]) && cptr->allowCross() && ------------------ | Branch (3717:15): [True: 0, False: 0] | Branch (3717:45): [True: 0, False: 0] ------------------ 3718| 0| (!cptr->getKeyLen() || ------------------ | Branch (3718:16): [True: 0, False: 0] ------------------ 3719| 0| ((badl > cptr->getKeyLen()) && ------------------ | Branch (3719:17): [True: 0, False: 0] ------------------ 3720| 0| (strncmp(cptr->getKey(), bad, cptr->getKeyLen()) == 0)))) { ------------------ | Branch (3720:17): [True: 0, False: 0] ------------------ 3721| 0| int l1 = strlen(wlst[j].word); 3722| 0| std::string newword = cptr->add(wlst[j].word, l1); 3723| 0| if (!newword.empty()) { ------------------ | Branch (3723:17): [True: 0, False: 0] ------------------ 3724| 0| if (nh < maxn) { ------------------ | Branch (3724:19): [True: 0, False: 0] ------------------ 3725| 0| wlst[nh].word = mystrdup(newword.c_str()); 3726| 0| wlst[nh].allow = cptr->allowCross(); 3727| 0| wlst[nh].orig = nullptr; 3728| 0| nh++; 3729| 0| } 3730| 0| } 3731| 0| } 3732| 0| cptr = cptr->getFlgNxt(); 3733| 0| } 3734| 40| } 3735| 20| } 3736| | 3737| | // now handle pure prefixes 3738| 653k| for (int m = 0; m < al; m++) { ------------------ | Branch (3738:19): [True: 107k, False: 545k] ------------------ 3739| 107k| const auto c = (unsigned char)(ap[m] & 0x00FF); 3740| 107k| PfxEntry* ptr = pFlag[c]; 3741| 108k| while (ptr) { ------------------ | Branch (3741:12): [True: 908, False: 107k] ------------------ 3742| 908| if ((ptr->getFlag() == ap[m]) && ------------------ | Branch (3742:11): [True: 908, False: 0] ------------------ 3743| 908| (!ptr->getKeyLen() || ------------------ | Branch (3743:12): [True: 0, False: 908] ------------------ 3744| 908| ((badl > ptr->getKeyLen()) && ------------------ | Branch (3744:13): [True: 908, False: 0] ------------------ 3745| 908| (strncmp(ptr->getKey(), bad, ptr->getKeyLen()) == 0))) && ------------------ | Branch (3745:13): [True: 2, False: 906] ------------------ 3746| | // check needaffix flag 3747| 2| !(ptr->getCont() && ------------------ | Branch (3747:13): [True: 0, False: 2] ------------------ 3748| 0| ((needaffix && ------------------ | Branch (3748:15): [True: 0, False: 0] ------------------ 3749| 0| TESTAFF(ptr->getCont(), needaffix, ptr->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 3750| 0| (circumfix && ------------------ | Branch (3750:15): [True: 0, False: 0] ------------------ 3751| 0| TESTAFF(ptr->getCont(), circumfix, ptr->getContLen())) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 3752| 0| (onlyincompound && ------------------ | Branch (3752:15): [True: 0, False: 0] ------------------ 3753| 2| TESTAFF(ptr->getCont(), onlyincompound, ptr->getContLen()))))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 3754| 2| std::string newword = ptr->add(ts, wl); 3755| 2| if (!newword.empty()) { ------------------ | Branch (3755:13): [True: 2, False: 0] ------------------ 3756| 2| if (nh < maxn) { ------------------ | Branch (3756:15): [True: 2, False: 0] ------------------ 3757| 2| wlst[nh].word = mystrdup(newword.c_str()); 3758| 2| wlst[nh].allow = ptr->allowCross(); 3759| 2| wlst[nh].orig = nullptr; 3760| 2| nh++; 3761| 2| } 3762| 2| } 3763| 2| } 3764| 908| ptr = ptr->getFlgNxt(); 3765| 908| } 3766| 107k| } 3767| | 3768| 545k| return nh; 3769| 545k|} _ZNK8AffixMgr12get_reptableEv: 3772| 380k|const std::vector& AffixMgr::get_reptable() const { 3773| 380k| return pHMgr->get_reptable(); 3774| 380k|} _ZNK8AffixMgr14get_iconvtableEv: 3777| 14.5M|RepList* AffixMgr::get_iconvtable() const { 3778| 14.5M| if (!iconvtable) ------------------ | Branch (3778:7): [True: 14.1M, False: 355k] ------------------ 3779| 14.1M| return nullptr; 3780| 355k| return iconvtable; 3781| 14.5M|} _ZNK8AffixMgr14get_oconvtableEv: 3784| 101k|RepList* AffixMgr::get_oconvtable() const { 3785| 101k| if (!oconvtable) ------------------ | Branch (3785:7): [True: 95.7k, False: 5.47k] ------------------ 3786| 95.7k| return nullptr; 3787| 5.47k| return oconvtable; 3788| 101k|} _ZNK8AffixMgr14get_phonetableEv: 3791| 61.4k|struct phonetable* AffixMgr::get_phonetable() const { 3792| 61.4k| if (!phone) ------------------ | Branch (3792:7): [True: 57.9k, False: 3.49k] ------------------ 3793| 57.9k| return nullptr; 3794| 3.49k| return phone; 3795| 61.4k|} _ZNK8AffixMgr12get_maptableEv: 3798| 380k|const std::vector& AffixMgr::get_maptable() const { 3799| 380k| return maptable; 3800| 380k|} _ZNK8AffixMgr14get_breaktableEv: 3803| 38|const std::vector& AffixMgr::get_breaktable() const { 3804| 38| return breaktable; 3805| 38|} _ZN8AffixMgr12get_encodingEv: 3808| 78|const std::string& AffixMgr::get_encoding() { 3809| 78| if (encoding.empty()) ------------------ | Branch (3809:7): [True: 20, False: 58] ------------------ 3810| 20| encoding = SPELL_ENCODING; ------------------ | | 99| 20|#define SPELL_ENCODING "ISO8859-1" ------------------ 3811| 78| return encoding; 3812| 78|} _ZNK8AffixMgr11get_langnumEv: 3815| 76|int AffixMgr::get_langnum() const { 3816| 76| return langnum; 3817| 76|} _ZNK8AffixMgr19get_complexprefixesEv: 3820| 76|int AffixMgr::get_complexprefixes() const { 3821| 76| return complexprefixes; 3822| 76|} _ZNK8AffixMgr13get_fullstripEv: 3825| 8.33k|int AffixMgr::get_fullstrip() const { 3826| 8.33k| return fullstrip; 3827| 8.33k|} _ZNK8AffixMgr12get_keepcaseEv: 3829| 102k|FLAG AffixMgr::get_keepcase() const { 3830| 102k| return keepcase; 3831| 102k|} _ZNK8AffixMgr14get_forceucaseEv: 3833| 20.2k|FLAG AffixMgr::get_forceucase() const { 3834| 20.2k| return forceucase; 3835| 20.2k|} _ZNK8AffixMgr8get_warnEv: 3837| 34.0k|FLAG AffixMgr::get_warn() const { 3838| 34.0k| return warn; 3839| 34.0k|} _ZNK8AffixMgr14get_forbidwarnEv: 3841| 4|int AffixMgr::get_forbidwarn() const { 3842| 4| return forbidwarn; 3843| 4|} _ZNK8AffixMgr15get_checksharpsEv: 3845| 655k|int AffixMgr::get_checksharps() const { 3846| 655k| return checksharps; 3847| 655k|} _ZNK8AffixMgr10get_ignoreEv: 3854| 31.8M|const char* AffixMgr::get_ignore() const { 3855| 31.8M| if (ignorechars.empty()) ------------------ | Branch (3855:7): [True: 28.7M, False: 3.12M] ------------------ 3856| 28.7M| return nullptr; 3857| 3.12M| return ignorechars.c_str(); 3858| 31.8M|} _ZNK8AffixMgr16get_ignore_utf16Ev: 3861| 607k|const std::vector& AffixMgr::get_ignore_utf16() const { 3862| 607k| return ignorechars_utf16; 3863| 607k|} _ZN8AffixMgr14get_key_stringEv: 3866| 38|const std::string& AffixMgr::get_key_string() { 3867| 38| if (keystring.empty()) ------------------ | Branch (3867:7): [True: 38, False: 0] ------------------ 3868| 38| keystring = SPELL_KEYSTRING; ------------------ | | 100| 38|#define SPELL_KEYSTRING "qwertyuiop|asdfghjkl|zxcvbnm" ------------------ 3869| 38| return keystring; 3870| 38|} _ZNK8AffixMgr14get_try_stringEv: 3873| 38|const std::string& AffixMgr::get_try_string() const { 3874| 38| return trystring; 3875| 38|} _ZNK8AffixMgr12get_compoundEv: 3887| 76.1M|int AffixMgr::get_compound() const { 3888| 76.1M| return compoundflag || compoundbegin || !defcpdtable.empty(); ------------------ | Branch (3888:10): [True: 18.8M, False: 57.2M] | Branch (3888:26): [True: 0, False: 57.2M] | Branch (3888:43): [True: 0, False: 57.2M] ------------------ 3889| 76.1M|} _ZNK8AffixMgr16get_compoundflagEv: 3892| 56.0k|FLAG AffixMgr::get_compoundflag() const { 3893| 56.0k| return compoundflag; 3894| 56.0k|} _ZNK8AffixMgr17get_forbiddenwordEv: 3897| 165k|FLAG AffixMgr::get_forbiddenword() const { 3898| 165k| return forbiddenword; 3899| 165k|} _ZNK8AffixMgr13get_nosuggestEv: 3902| 61.5k|FLAG AffixMgr::get_nosuggest() const { 3903| 61.5k| return nosuggest; 3904| 61.5k|} _ZNK8AffixMgr18get_nongramsuggestEv: 3907| 61.4k|FLAG AffixMgr::get_nongramsuggest() const { 3908| 61.4k| return nongramsuggest; 3909| 61.4k|} _ZNK8AffixMgr15get_substandardEv: 3912| 143|FLAG AffixMgr::get_substandard() const { 3913| 143| return substandard; 3914| 143|} _ZNK8AffixMgr13get_needaffixEv: 3917| 5.96k|FLAG AffixMgr::get_needaffix() const { 3918| 5.96k| return needaffix; 3919| 5.96k|} _ZNK8AffixMgr18get_onlyincompoundEv: 3927| 66.8k|FLAG AffixMgr::get_onlyincompound() const { 3928| 66.8k| return onlyincompound; 3929| 66.8k|} _ZN8AffixMgr6lookupEPKcm: 3937| 522M|struct hentry* AffixMgr::lookup(const char* word, size_t len) { 3938| 522M| struct hentry* he = nullptr; 3939| 1.04G| for (size_t i = 0; i < alldic.size() && !he; ++i) { ------------------ | Branch (3939:22): [True: 522M, False: 522M] | Branch (3939:43): [True: 522M, False: 0] ------------------ 3940| 522M| he = alldic[i]->lookup(word, len); 3941| 522M| } 3942| 522M| return he; 3943| 522M|} _ZNK8AffixMgr14have_contclassEv: 3946| 31.1M|int AffixMgr::have_contclass() const { 3947| 31.1M| return havecontclass; 3948| 31.1M|} _ZNK8AffixMgr8get_utf8Ev: 3951| 76|int AffixMgr::get_utf8() const { 3952| 76| return utf8; 3953| 76|} _ZNK8AffixMgr16get_maxngramsugsEv: 3955| 69.0k|int AffixMgr::get_maxngramsugs() const { 3956| 69.0k| return maxngramsugs; 3957| 69.0k|} _ZNK8AffixMgr14get_maxcpdsugsEv: 3959| 38|int AffixMgr::get_maxcpdsugs() const { 3960| 38| return maxcpdsugs; 3961| 38|} _ZNK8AffixMgr11get_maxdiffEv: 3963| 47.0k|int AffixMgr::get_maxdiff() const { 3964| 47.0k| return maxdiff; 3965| 47.0k|} _ZNK8AffixMgr15get_onlymaxdiffEv: 3967| 7.44k|int AffixMgr::get_onlymaxdiff() const { 3968| 7.44k| return onlymaxdiff; 3969| 7.44k|} _ZNK8AffixMgr15get_nosplitsugsEv: 3972| 38|int AffixMgr::get_nosplitsugs() const { 3973| 38| return nosplitsugs; 3974| 38|} _ZNK8AffixMgr16get_sugswithdotsEv: 3977| 3.51k|int AffixMgr::get_sugswithdots() const { 3978| 3.51k| return sugswithdots; 3979| 3.51k|} _ZN8AffixMgr10parse_flagERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPtP7FileMgr: 3982| 22|bool AffixMgr::parse_flag(const std::string& line, unsigned short* out, FileMgr* af) { 3983| 22| if (*out != FLAG_NULL && !(*out >= DEFAULTFLAGS)) { ------------------ | | 99| 44|#define FLAG_NULL 0x00 ------------------ if (*out != FLAG_NULL && !(*out >= DEFAULTFLAGS)) { ------------------ | | 126| 2|#define DEFAULTFLAGS 65510 ------------------ | Branch (3983:7): [True: 2, False: 20] | Branch (3983:28): [True: 0, False: 2] ------------------ 3984| 0| HUNSPELL_WARNING( 3985| 0| stderr, 3986| 0| "error: line %d: multiple definitions of an affix file parameter\n", 3987| 0| af->getlinenum()); 3988| 0| return false; 3989| 0| } 3990| 22| std::string s; 3991| 22| if (!parse_string(line, s, af->getlinenum())) ------------------ | Branch (3991:7): [True: 0, False: 22] ------------------ 3992| 0| return false; 3993| 22| *out = pHMgr->decode_flag(s); 3994| 22| return true; 3995| 22|} _ZN8AffixMgr9parse_numERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiP7FileMgr: 3998| 10|bool AffixMgr::parse_num(const std::string& line, int* out, FileMgr* af) { 3999| 10| if (*out != -1) { ------------------ | Branch (3999:7): [True: 0, False: 10] ------------------ 4000| 0| HUNSPELL_WARNING( 4001| 0| stderr, 4002| 0| "error: line %d: multiple definitions of an affix file parameter\n", 4003| 0| af->getlinenum()); 4004| 0| return false; 4005| 0| } 4006| 10| std::string s; 4007| 10| if (!parse_string(line, s, af->getlinenum())) ------------------ | Branch (4007:7): [True: 0, False: 10] ------------------ 4008| 0| return false; 4009| 10| *out = atoi(s.c_str()); 4010| 10| return true; 4011| 10|} _ZN8AffixMgr17parse_cpdsyllableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 4014| 2|bool AffixMgr::parse_cpdsyllable(const std::string& line, FileMgr* af) { 4015| 2| int i = 0; 4016| 2| int np = 0; 4017| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4018| 8| while (start_piece != line.end()) { ------------------ | Branch (4018:10): [True: 6, False: 2] ------------------ 4019| 6| switch (i) { 4020| 2| case 0: { ------------------ | Branch (4020:7): [True: 2, False: 4] ------------------ 4021| 2| np++; 4022| 2| break; 4023| 0| } 4024| 2| case 1: { ------------------ | Branch (4024:7): [True: 2, False: 4] ------------------ 4025| 2| cpdmaxsyllable = atoi(std::string(start_piece, iter).c_str()); 4026| 2| np++; 4027| 2| break; 4028| 0| } 4029| 2| case 2: { ------------------ | Branch (4029:7): [True: 2, False: 4] ------------------ 4030| 2| if (!utf8) { ------------------ | Branch (4030:13): [True: 0, False: 2] ------------------ 4031| 0| cpdvowels.assign(start_piece, iter); 4032| 0| std::sort(cpdvowels.begin(), cpdvowels.end()); 4033| 2| } else { 4034| 2| std::string piece(start_piece, iter); 4035| 2| u8_u16(cpdvowels_utf16, piece); 4036| 2| std::sort(cpdvowels_utf16.begin(), cpdvowels_utf16.end()); 4037| 2| } 4038| 2| np++; 4039| 2| break; 4040| 0| } 4041| 0| default: ------------------ | Branch (4041:7): [True: 0, False: 6] ------------------ 4042| 0| break; 4043| 6| } 4044| 6| ++i; 4045| 6| start_piece = mystrsep(line, iter); 4046| 6| } 4047| 2| if (np < 2) { ------------------ | Branch (4047:7): [True: 0, False: 2] ------------------ 4048| 0| HUNSPELL_WARNING(stderr, 4049| 0| "error: line %d: missing compoundsyllable information\n", 4050| 0| af->getlinenum()); 4051| 0| return false; 4052| 0| } 4053| 2| if (np == 2) ------------------ | Branch (4053:7): [True: 0, False: 2] ------------------ 4054| 0| cpdvowels = "AEIOUaeiou"; 4055| 2| return true; 4056| 2|} _ZN8AffixMgr15parse_convtableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgrPP7RepListS8_: 4061| 4| const std::string& keyword) { 4062| 4| if (*rl) { ------------------ | Branch (4062:7): [True: 0, False: 4] ------------------ 4063| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 4064| 0| af->getlinenum()); 4065| 0| return false; 4066| 0| } 4067| 4| int i = 0; 4068| 4| int np = 0; 4069| 4| int numrl = 0; 4070| 4| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4071| 18| while (start_piece != line.end()) { ------------------ | Branch (4071:10): [True: 14, False: 4] ------------------ 4072| 14| switch (i) { 4073| 4| case 0: { ------------------ | Branch (4073:7): [True: 4, False: 10] ------------------ 4074| 4| np++; 4075| 4| break; 4076| 0| } 4077| 4| case 1: { ------------------ | Branch (4077:7): [True: 4, False: 10] ------------------ 4078| 4| numrl = atoi(std::string(start_piece, iter).c_str()); 4079| 4| if (numrl < 1) { ------------------ | Branch (4079:13): [True: 0, False: 4] ------------------ 4080| 0| HUNSPELL_WARNING(stderr, "error: line %d: incorrect entry number\n", 4081| 0| af->getlinenum()); 4082| 0| return false; 4083| 0| } 4084| 4| *rl = new RepList(numrl); 4085| 4| if (!*rl) ------------------ | Branch (4085:13): [True: 0, False: 4] ------------------ 4086| 0| return false; 4087| 4| np++; 4088| 4| break; 4089| 4| } 4090| 6| default: ------------------ | Branch (4090:7): [True: 6, False: 8] ------------------ 4091| 6| break; 4092| 14| } 4093| 14| ++i; 4094| 14| start_piece = mystrsep(line, iter); 4095| 14| } 4096| 4| if (np != 2) { ------------------ | Branch (4096:7): [True: 0, False: 4] ------------------ 4097| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4098| 0| af->getlinenum()); 4099| 0| return false; 4100| 0| } 4101| | 4102| | /* now parse the num lines to read in the remainder of the table */ 4103| 26| for (int j = 0; j < numrl; j++) { ------------------ | Branch (4103:19): [True: 22, False: 4] ------------------ 4104| 22| std::string nl; 4105| 22| if (!af->getline(nl)) ------------------ | Branch (4105:9): [True: 0, False: 22] ------------------ 4106| 0| return false; 4107| 22| mychomp(nl); 4108| 22| i = 0; 4109| 22| std::string pattern; 4110| 22| std::string pattern2; 4111| 22| iter = nl.begin(); 4112| 22| start_piece = mystrsep(nl, iter); 4113| 130| while (start_piece != nl.end()) { ------------------ | Branch (4113:12): [True: 108, False: 22] ------------------ 4114| 108| { 4115| 108| switch (i) { 4116| 22| case 0: { ------------------ | Branch (4116:11): [True: 22, False: 86] ------------------ 4117| 22| if (nl.compare(start_piece - nl.begin(), keyword.size(), keyword, 0, keyword.size()) != 0) { ------------------ | Branch (4117:17): [True: 0, False: 22] ------------------ 4118| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4119| 0| af->getlinenum()); 4120| 0| delete *rl; 4121| 0| *rl = nullptr; 4122| 0| return false; 4123| 0| } 4124| 22| break; 4125| 22| } 4126| 22| case 1: { ------------------ | Branch (4126:11): [True: 22, False: 86] ------------------ 4127| 22| pattern.assign(start_piece, iter); 4128| 22| break; 4129| 22| } 4130| 22| case 2: { ------------------ | Branch (4130:11): [True: 22, False: 86] ------------------ 4131| 22| pattern2.assign(start_piece, iter); 4132| 22| break; 4133| 22| } 4134| 42| default: ------------------ | Branch (4134:11): [True: 42, False: 66] ------------------ 4135| 42| break; 4136| 108| } 4137| 108| ++i; 4138| 108| } 4139| 0| start_piece = mystrsep(nl, iter); 4140| 108| } 4141| 22| if (pattern.empty() || pattern2.empty()) { ------------------ | Branch (4141:9): [True: 0, False: 22] | Branch (4141:28): [True: 0, False: 22] ------------------ 4142| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4143| 0| af->getlinenum()); 4144| 0| return false; 4145| 0| } 4146| | 4147| 22| (*rl)->add(pattern, pattern2); 4148| 22| } 4149| 4| return true; 4150| 4|} _ZN8AffixMgr16parse_phonetableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 4153| 2|bool AffixMgr::parse_phonetable(const std::string& line, FileMgr* af) { 4154| 2| if (phone) { ------------------ | Branch (4154:7): [True: 0, False: 2] ------------------ 4155| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 4156| 0| af->getlinenum()); 4157| 0| return false; 4158| 0| } 4159| 2| std::unique_ptr new_phone; 4160| 2| int num = -1; 4161| 2| int i = 0; 4162| 2| int np = 0; 4163| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4164| 6| while (start_piece != line.end()) { ------------------ | Branch (4164:10): [True: 4, False: 2] ------------------ 4165| 4| switch (i) { 4166| 2| case 0: { ------------------ | Branch (4166:7): [True: 2, False: 2] ------------------ 4167| 2| np++; 4168| 2| break; 4169| 0| } 4170| 2| case 1: { ------------------ | Branch (4170:7): [True: 2, False: 2] ------------------ 4171| 2| num = atoi(std::string(start_piece, iter).c_str()); 4172| 2| if (num < 1) { ------------------ | Branch (4172:13): [True: 0, False: 2] ------------------ 4173| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 4174| 0| af->getlinenum()); 4175| 0| return false; 4176| 0| } 4177| 2| new_phone = std::make_unique(); 4178| 2| new_phone->utf8 = (char)utf8; 4179| 2| np++; 4180| 2| break; 4181| 2| } 4182| 0| default: ------------------ | Branch (4182:7): [True: 0, False: 4] ------------------ 4183| 0| break; 4184| 4| } 4185| 4| ++i; 4186| 4| start_piece = mystrsep(line, iter); 4187| 4| } 4188| 2| if (np != 2) { ------------------ | Branch (4188:7): [True: 0, False: 2] ------------------ 4189| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4190| 0| af->getlinenum()); 4191| 0| return false; 4192| 0| } 4193| | 4194| | /* now parse the phone->num lines to read in the remainder of the table */ 4195| 212| for (int j = 0; j < num; ++j) { ------------------ | Branch (4195:19): [True: 210, False: 2] ------------------ 4196| 210| std::string nl; 4197| 210| if (!af->getline(nl)) ------------------ | Branch (4197:9): [True: 0, False: 210] ------------------ 4198| 0| return false; 4199| 210| mychomp(nl); 4200| 210| i = 0; 4201| 210| const size_t old_size = new_phone->rules.size(); 4202| 210| iter = nl.begin(); 4203| 210| start_piece = mystrsep(nl, iter); 4204| 840| while (start_piece != nl.end()) { ------------------ | Branch (4204:12): [True: 630, False: 210] ------------------ 4205| 630| { 4206| 630| switch (i) { 4207| 210| case 0: { ------------------ | Branch (4207:11): [True: 210, False: 420] ------------------ 4208| 210| if (nl.compare(start_piece - nl.begin(), 5, "PHONE", 5) != 0) { ------------------ | Branch (4208:17): [True: 0, False: 210] ------------------ 4209| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4210| 0| af->getlinenum()); 4211| 0| return false; 4212| 0| } 4213| 210| break; 4214| 210| } 4215| 210| case 1: { ------------------ | Branch (4215:11): [True: 210, False: 420] ------------------ 4216| 210| new_phone->rules.emplace_back(start_piece, iter); 4217| 210| break; 4218| 210| } 4219| 210| case 2: { ------------------ | Branch (4219:11): [True: 210, False: 420] ------------------ 4220| 210| new_phone->rules.emplace_back(start_piece, iter); 4221| 210| mystrrep(new_phone->rules.back(), "_", ""); 4222| 210| break; 4223| 210| } 4224| 0| default: ------------------ | Branch (4224:11): [True: 0, False: 630] ------------------ 4225| 0| break; 4226| 630| } 4227| 630| ++i; 4228| 630| } 4229| 0| start_piece = mystrsep(nl, iter); 4230| 630| } 4231| 210| if (new_phone->rules.size() != old_size + 2) { ------------------ | Branch (4231:9): [True: 0, False: 210] ------------------ 4232| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4233| 0| af->getlinenum()); 4234| 0| return false; 4235| 0| } 4236| 210| } 4237| 2| new_phone->rules.emplace_back(""); 4238| 2| new_phone->rules.emplace_back(""); 4239| 2| init_phonet_hash(*new_phone); 4240| 2| phone = new_phone.release(); 4241| 2| return true; 4242| 2|} _ZN8AffixMgr19parse_checkcpdtableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 4245| 2|bool AffixMgr::parse_checkcpdtable(const std::string& line, FileMgr* af) { 4246| 2| if (parsedcheckcpd) { ------------------ | Branch (4246:7): [True: 0, False: 2] ------------------ 4247| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 4248| 0| af->getlinenum()); 4249| 0| return false; 4250| 0| } 4251| 2| parsedcheckcpd = true; 4252| 2| int numcheckcpd = -1; 4253| 2| int i = 0; 4254| 2| int np = 0; 4255| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4256| 6| while (start_piece != line.end()) { ------------------ | Branch (4256:10): [True: 4, False: 2] ------------------ 4257| 4| switch (i) { 4258| 2| case 0: { ------------------ | Branch (4258:7): [True: 2, False: 2] ------------------ 4259| 2| np++; 4260| 2| break; 4261| 0| } 4262| 2| case 1: { ------------------ | Branch (4262:7): [True: 2, False: 2] ------------------ 4263| 2| numcheckcpd = atoi(std::string(start_piece, iter).c_str()); 4264| 2| if (numcheckcpd < 1) { ------------------ | Branch (4264:13): [True: 0, False: 2] ------------------ 4265| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 4266| 0| af->getlinenum()); 4267| 0| return false; 4268| 0| } 4269| 2| checkcpdtable.reserve(std::min(numcheckcpd, 16384)); 4270| 2| np++; 4271| 2| break; 4272| 2| } 4273| 0| default: ------------------ | Branch (4273:7): [True: 0, False: 4] ------------------ 4274| 0| break; 4275| 4| } 4276| 4| ++i; 4277| 4| start_piece = mystrsep(line, iter); 4278| 4| } 4279| 2| if (np != 2) { ------------------ | Branch (4279:7): [True: 0, False: 2] ------------------ 4280| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4281| 0| af->getlinenum()); 4282| 0| return false; 4283| 0| } 4284| | 4285| | /* now parse the numcheckcpd lines to read in the remainder of the table */ 4286| 6| for (int j = 0; j < numcheckcpd; ++j) { ------------------ | Branch (4286:19): [True: 4, False: 2] ------------------ 4287| 4| std::string nl; 4288| 4| if (!af->getline(nl)) ------------------ | Branch (4288:9): [True: 0, False: 4] ------------------ 4289| 0| return false; 4290| 4| mychomp(nl); 4291| 4| i = 0; 4292| 4| checkcpdtable.emplace_back(); 4293| 4| iter = nl.begin(); 4294| 4| start_piece = mystrsep(nl, iter); 4295| 16| while (start_piece != nl.end()) { ------------------ | Branch (4295:12): [True: 12, False: 4] ------------------ 4296| 12| switch (i) { 4297| 4| case 0: { ------------------ | Branch (4297:9): [True: 4, False: 8] ------------------ 4298| 4| if (nl.compare(start_piece - nl.begin(), 20, "CHECKCOMPOUNDPATTERN", 20) != 0) { ------------------ | Branch (4298:15): [True: 0, False: 4] ------------------ 4299| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4300| 0| af->getlinenum()); 4301| 0| checkcpdtable.clear(); 4302| 0| return false; 4303| 0| } 4304| 4| break; 4305| 4| } 4306| 4| case 1: { ------------------ | Branch (4306:9): [True: 4, False: 8] ------------------ 4307| 4| checkcpdtable.back().pattern.assign(start_piece, iter); 4308| 4| size_t slash_pos = checkcpdtable.back().pattern.find('/'); 4309| 4| if (slash_pos != std::string::npos) { ------------------ | Branch (4309:15): [True: 0, False: 4] ------------------ 4310| 0| std::string chunk(checkcpdtable.back().pattern, slash_pos + 1); 4311| 0| checkcpdtable.back().pattern.resize(slash_pos); 4312| 0| checkcpdtable.back().cond = pHMgr->decode_flag(chunk); 4313| 0| } 4314| 4| break; 4315| 4| } 4316| 4| case 2: { ------------------ | Branch (4316:9): [True: 4, False: 8] ------------------ 4317| 4| checkcpdtable.back().pattern2.assign(start_piece, iter); 4318| 4| size_t slash_pos = checkcpdtable.back().pattern2.find('/'); 4319| 4| if (slash_pos != std::string::npos) { ------------------ | Branch (4319:15): [True: 0, False: 4] ------------------ 4320| 0| std::string chunk(checkcpdtable.back().pattern2, slash_pos + 1); 4321| 0| checkcpdtable.back().pattern2.resize(slash_pos); 4322| 0| checkcpdtable.back().cond2 = pHMgr->decode_flag(chunk); 4323| 0| } 4324| 4| break; 4325| 4| } 4326| 0| case 3: { ------------------ | Branch (4326:9): [True: 0, False: 12] ------------------ 4327| 0| checkcpdtable.back().pattern3.assign(start_piece, iter); 4328| 0| simplifiedcpd = 1; 4329| 0| break; 4330| 4| } 4331| 0| default: ------------------ | Branch (4331:9): [True: 0, False: 12] ------------------ 4332| 0| break; 4333| 12| } 4334| 12| i++; 4335| 12| start_piece = mystrsep(nl, iter); 4336| 12| } 4337| 4| } 4338| 2| return true; 4339| 2|} _ZN8AffixMgr14parse_maptableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 4443| 2|bool AffixMgr::parse_maptable(const std::string& line, FileMgr* af) { 4444| 2| if (parsedmaptable) { ------------------ | Branch (4444:7): [True: 0, False: 2] ------------------ 4445| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 4446| 0| af->getlinenum()); 4447| 0| return false; 4448| 0| } 4449| 2| parsedmaptable = true; 4450| 2| int nummap = -1; 4451| 2| int i = 0; 4452| 2| int np = 0; 4453| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4454| 6| while (start_piece != line.end()) { ------------------ | Branch (4454:10): [True: 4, False: 2] ------------------ 4455| 4| switch (i) { 4456| 2| case 0: { ------------------ | Branch (4456:7): [True: 2, False: 2] ------------------ 4457| 2| np++; 4458| 2| break; 4459| 0| } 4460| 2| case 1: { ------------------ | Branch (4460:7): [True: 2, False: 2] ------------------ 4461| 2| nummap = atoi(std::string(start_piece, iter).c_str()); 4462| 2| if (nummap < 1) { ------------------ | Branch (4462:13): [True: 0, False: 2] ------------------ 4463| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 4464| 0| af->getlinenum()); 4465| 0| return false; 4466| 0| } 4467| 2| maptable.reserve(std::min(nummap, 16384)); 4468| 2| np++; 4469| 2| break; 4470| 2| } 4471| 0| default: ------------------ | Branch (4471:7): [True: 0, False: 4] ------------------ 4472| 0| break; 4473| 4| } 4474| 4| ++i; 4475| 4| start_piece = mystrsep(line, iter); 4476| 4| } 4477| 2| if (np != 2) { ------------------ | Branch (4477:7): [True: 0, False: 2] ------------------ 4478| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4479| 0| af->getlinenum()); 4480| 0| return false; 4481| 0| } 4482| | 4483| | /* now parse the nummap lines to read in the remainder of the table */ 4484| 8| for (int j = 0; j < nummap; ++j) { ------------------ | Branch (4484:19): [True: 6, False: 2] ------------------ 4485| 6| std::string nl; 4486| 6| if (!af->getline(nl)) ------------------ | Branch (4486:9): [True: 0, False: 6] ------------------ 4487| 0| return false; 4488| 6| mychomp(nl); 4489| 6| i = 0; 4490| 6| maptable.emplace_back(); 4491| 6| iter = nl.begin(); 4492| 6| start_piece = mystrsep(nl, iter); 4493| 18| while (start_piece != nl.end()) { ------------------ | Branch (4493:12): [True: 12, False: 6] ------------------ 4494| 12| switch (i) { 4495| 6| case 0: { ------------------ | Branch (4495:9): [True: 6, False: 6] ------------------ 4496| 6| if (nl.compare(start_piece - nl.begin(), 3, "MAP", 3) != 0) { ------------------ | Branch (4496:15): [True: 0, False: 6] ------------------ 4497| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4498| 0| af->getlinenum()); 4499| 0| nummap = 0; 4500| 0| return false; 4501| 0| } 4502| 6| break; 4503| 6| } 4504| 6| case 1: { ------------------ | Branch (4504:9): [True: 6, False: 6] ------------------ 4505| 22| for (auto k = start_piece; k != iter; ++k) { ------------------ | Branch (4505:38): [True: 16, False: 6] ------------------ 4506| 16| auto chb = k, che = k + 1; 4507| 16| if (*k == '(') { ------------------ | Branch (4507:17): [True: 2, False: 14] ------------------ 4508| 2| auto parpos = std::find(k, iter, ')'); 4509| 2| if (parpos != iter) { ------------------ | Branch (4509:19): [True: 2, False: 0] ------------------ 4510| 2| chb = k + 1; 4511| 2| che = parpos; 4512| 2| k = parpos; 4513| 2| } 4514| 14| } else { 4515| 14| if (utf8 && (*k & 0xc0) == 0xc0) { ------------------ | Branch (4515:19): [True: 14, False: 0] | Branch (4515:27): [True: 10, False: 4] ------------------ 4516| 10| ++k; 4517| 20| while (k != iter && is_utf8_cont(*k)) ------------------ | Branch (4517:24): [True: 18, False: 2] | Branch (4517:37): [True: 10, False: 8] ------------------ 4518| 10| ++k; 4519| 10| che = k; 4520| 10| --k; 4521| 10| } 4522| 14| } 4523| 16| if (chb == che) { ------------------ | Branch (4523:17): [True: 0, False: 16] ------------------ 4524| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4525| 0| af->getlinenum()); 4526| 0| } 4527| | 4528| 16| maptable.back().emplace_back(chb, che); 4529| 16| } 4530| 6| break; 4531| 6| } 4532| 0| default: ------------------ | Branch (4532:9): [True: 0, False: 12] ------------------ 4533| 0| break; 4534| 12| } 4535| 12| ++i; 4536| 12| start_piece = mystrsep(nl, iter); 4537| 12| } 4538| 6| if (maptable.back().empty()) { ------------------ | Branch (4538:9): [True: 0, False: 6] ------------------ 4539| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4540| 0| af->getlinenum()); 4541| 0| return false; 4542| 0| } 4543| 6| } 4544| 2| return true; 4545| 2|} _ZN8AffixMgr16parse_breaktableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 4548| 4|bool AffixMgr::parse_breaktable(const std::string& line, FileMgr* af) { 4549| 4| if (parsedbreaktable) { ------------------ | Branch (4549:7): [True: 0, False: 4] ------------------ 4550| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 4551| 0| af->getlinenum()); 4552| 0| return false; 4553| 0| } 4554| 4| parsedbreaktable = true; 4555| 4| int numbreak = -1; 4556| 4| int i = 0; 4557| 4| int np = 0; 4558| 4| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4559| 12| while (start_piece != line.end()) { ------------------ | Branch (4559:10): [True: 8, False: 4] ------------------ 4560| 8| switch (i) { 4561| 4| case 0: { ------------------ | Branch (4561:7): [True: 4, False: 4] ------------------ 4562| 4| np++; 4563| 4| break; 4564| 0| } 4565| 4| case 1: { ------------------ | Branch (4565:7): [True: 4, False: 4] ------------------ 4566| 4| numbreak = atoi(std::string(start_piece, iter).c_str()); 4567| 4| if (numbreak < 0) { ------------------ | Branch (4567:13): [True: 0, False: 4] ------------------ 4568| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 4569| 0| af->getlinenum()); 4570| 0| return false; 4571| 0| } 4572| 4| if (numbreak == 0) ------------------ | Branch (4572:13): [True: 0, False: 4] ------------------ 4573| 0| return true; 4574| 4| breaktable.reserve(std::min(numbreak, 16384)); 4575| 4| np++; 4576| 4| break; 4577| 4| } 4578| 0| default: ------------------ | Branch (4578:7): [True: 0, False: 8] ------------------ 4579| 0| break; 4580| 8| } 4581| 8| ++i; 4582| 8| start_piece = mystrsep(line, iter); 4583| 8| } 4584| 4| if (np != 2) { ------------------ | Branch (4584:7): [True: 0, False: 4] ------------------ 4585| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4586| 0| af->getlinenum()); 4587| 0| return false; 4588| 0| } 4589| | 4590| | /* now parse the numbreak lines to read in the remainder of the table */ 4591| 10| for (int j = 0; j < numbreak; ++j) { ------------------ | Branch (4591:19): [True: 6, False: 4] ------------------ 4592| 6| std::string nl; 4593| 6| if (!af->getline(nl)) ------------------ | Branch (4593:9): [True: 0, False: 6] ------------------ 4594| 0| return false; 4595| 6| mychomp(nl); 4596| 6| i = 0; 4597| 6| iter = nl.begin(); 4598| 6| start_piece = mystrsep(nl, iter); 4599| 18| while (start_piece != nl.end()) { ------------------ | Branch (4599:12): [True: 12, False: 6] ------------------ 4600| 12| switch (i) { 4601| 6| case 0: { ------------------ | Branch (4601:9): [True: 6, False: 6] ------------------ 4602| 6| if (nl.compare(start_piece - nl.begin(), 5, "BREAK", 5) != 0) { ------------------ | Branch (4602:15): [True: 0, False: 6] ------------------ 4603| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4604| 0| af->getlinenum()); 4605| 0| numbreak = 0; 4606| 0| return false; 4607| 0| } 4608| 6| break; 4609| 6| } 4610| 6| case 1: { ------------------ | Branch (4610:9): [True: 6, False: 6] ------------------ 4611| 6| breaktable.emplace_back(start_piece, iter); 4612| 6| break; 4613| 6| } 4614| 0| default: ------------------ | Branch (4614:9): [True: 0, False: 12] ------------------ 4615| 0| break; 4616| 12| } 4617| 12| ++i; 4618| 12| start_piece = mystrsep(nl, iter); 4619| 12| } 4620| 6| } 4621| | 4622| 4| if (breaktable.size() != static_cast(numbreak)) { ------------------ | Branch (4622:7): [True: 0, False: 4] ------------------ 4623| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4624| 0| af->getlinenum()); 4625| 0| return false; 4626| 0| } 4627| | 4628| 4| return true; 4629| 4|} _ZN8AffixMgr17reverse_conditionERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 4631| 38|void AffixMgr::reverse_condition(std::string& piece) { 4632| 38| if (piece.empty()) ------------------ | Branch (4632:7): [True: 0, False: 38] ------------------ 4633| 0| return; 4634| | 4635| 38| int neg = 0; 4636| | // iterate backwards; k wraps to npos (SIZE_MAX) when decremented past 0 4637| 92| for (size_t k = piece.size() - 1; k != std::string::npos; --k) { ------------------ | Branch (4637:37): [True: 54, False: 38] ------------------ 4638| 54| switch (piece[k]) { 4639| 2| case '[': { ------------------ | Branch (4639:7): [True: 2, False: 52] ------------------ 4640| 2| if (neg) ------------------ | Branch (4640:13): [True: 0, False: 2] ------------------ 4641| 0| piece[k + 1] = '['; 4642| 2| else 4643| 2| piece[k] = ']'; 4644| 2| break; 4645| 0| } 4646| 2| case ']': { ------------------ | Branch (4646:7): [True: 2, False: 52] ------------------ 4647| 2| piece[k] = '['; 4648| 2| if (neg) ------------------ | Branch (4648:13): [True: 0, False: 2] ------------------ 4649| 0| piece[k + 1] = '^'; 4650| 2| neg = 0; 4651| 2| break; 4652| 0| } 4653| 0| case '^': { ------------------ | Branch (4653:7): [True: 0, False: 54] ------------------ 4654| 0| if (piece[k + 1] == ']') ------------------ | Branch (4654:13): [True: 0, False: 0] ------------------ 4655| 0| neg = 1; 4656| 0| else if (neg) ------------------ | Branch (4656:18): [True: 0, False: 0] ------------------ 4657| 0| piece[k + 1] = piece[k]; 4658| 0| break; 4659| 0| } 4660| 50| default: { ------------------ | Branch (4660:7): [True: 50, False: 4] ------------------ 4661| 50| if (neg) ------------------ | Branch (4661:13): [True: 0, False: 50] ------------------ 4662| 0| piece[k + 1] = piece[k]; 4663| 50| } 4664| 54| } 4665| 54| } 4666| 38|} _ZN8AffixMgr11parse_affixERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEcP7FileMgrPc: 4720| 26| char* dupflags) { 4721| 26| int numents = 0; // number of AffEntry structures to parse 4722| | 4723| 26| unsigned short aflag = 0; // affix char identifier 4724| | 4725| 26| char ff = 0; 4726| 26| char xprod = 0; 4727| 26| int headerline = af->getlinenum(); 4728| 26| entries_container affentries(at, this); 4729| | 4730| 26| int i = 0; 4731| | 4732| |// checking lines with bad syntax 4733| |#ifdef DEBUG 4734| | int basefieldnum = 0; 4735| |#endif 4736| | 4737| | // split affix header line into pieces 4738| | 4739| 26| int np = 0; 4740| 26| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4741| 130| while (start_piece != line.end()) { ------------------ | Branch (4741:10): [True: 104, False: 26] ------------------ 4742| 104| switch (i) { 4743| | // piece 1 - is type of affix 4744| 26| case 0: { ------------------ | Branch (4744:7): [True: 26, False: 78] ------------------ 4745| 26| np++; 4746| 26| break; 4747| 0| } 4748| | 4749| | // piece 2 - is affix char 4750| 26| case 1: { ------------------ | Branch (4750:7): [True: 26, False: 78] ------------------ 4751| 26| np++; 4752| 26| aflag = pHMgr->decode_flag(std::string(start_piece, iter)); 4753| 26| if (((at == 'S') && (dupflags[aflag] & dupSFX)) || ------------------ | | 89| 18|#define dupSFX (1 << 0) ------------------ | Branch (4753:14): [True: 18, False: 8] | Branch (4753:29): [True: 0, False: 18] ------------------ 4754| 26| ((at == 'P') && (dupflags[aflag] & dupPFX))) { ------------------ | | 90| 8|#define dupPFX (1 << 1) ------------------ | Branch (4754:14): [True: 8, False: 18] | Branch (4754:29): [True: 0, False: 8] ------------------ 4755| 0| HUNSPELL_WARNING( 4756| 0| stderr, 4757| 0| "error: line %d: multiple definitions of an affix flag\n", 4758| 0| af->getlinenum()); 4759| 0| } 4760| 26| dupflags[aflag] += (char)((at == 'S') ? dupSFX : dupPFX); ------------------ | | 89| 18|#define dupSFX (1 << 0) ------------------ dupflags[aflag] += (char)((at == 'S') ? dupSFX : dupPFX); ------------------ | | 90| 8|#define dupPFX (1 << 1) ------------------ | Branch (4760:35): [True: 18, False: 8] ------------------ 4761| 26| break; 4762| 0| } 4763| | // piece 3 - is cross product indicator 4764| 26| case 2: { ------------------ | Branch (4764:7): [True: 26, False: 78] ------------------ 4765| 26| np++; 4766| 26| xprod = *start_piece; 4767| 26| if (xprod == 'Y') ------------------ | Branch (4767:13): [True: 26, False: 0] ------------------ 4768| 26| ff = aeXPRODUCT; ------------------ | | 65| 26|#define aeXPRODUCT (1 << 0) ------------------ 4769| 26| break; 4770| 0| } 4771| | 4772| | // piece 4 - is number of affentries 4773| 26| case 3: { ------------------ | Branch (4773:7): [True: 26, False: 78] ------------------ 4774| 26| np++; 4775| 26| numents = atoi(std::string(start_piece, iter).c_str()); 4776| 26| if ((numents <= 0) || ((std::numeric_limits::max() / ------------------ | Branch (4776:13): [True: 0, False: 26] | Branch (4776:31): [True: 0, False: 26] ------------------ 4777| 26| sizeof(AffEntry)) < static_cast(numents))) { 4778| 0| std::string err = pHMgr->encode_flag(aflag); 4779| 0| HUNSPELL_WARNING(stderr, "error: line %d: affix %s: bad entry number\n", 4780| 0| af->getlinenum(), err.c_str()); 4781| 0| return false; 4782| 0| } 4783| | 4784| 26| char opts = ff; 4785| 26| if (utf8) ------------------ | Branch (4785:13): [True: 6, False: 20] ------------------ 4786| 6| opts |= aeUTF8; ------------------ | | 66| 6|#define aeUTF8 (1 << 1) ------------------ 4787| 26| if (pHMgr->is_aliasf()) ------------------ | Branch (4787:13): [True: 4, False: 22] ------------------ 4788| 4| opts |= aeALIASF; ------------------ | | 67| 4|#define aeALIASF (1 << 2) ------------------ 4789| 26| if (pHMgr->is_aliasm()) ------------------ | Branch (4789:13): [True: 0, False: 26] ------------------ 4790| 0| opts |= aeALIASM; ------------------ | | 68| 0|#define aeALIASM (1 << 3) ------------------ 4791| 26| affentries.initialize(numents, opts, aflag); 4792| 26| } 4793| | 4794| 26| default: ------------------ | Branch (4794:7): [True: 0, False: 104] ------------------ 4795| 26| break; 4796| 104| } 4797| 104| ++i; 4798| 104| start_piece = mystrsep(line, iter); 4799| 104| } 4800| | // check to make sure we parsed enough pieces 4801| 26| if (np != 4) { ------------------ | Branch (4801:7): [True: 0, False: 26] ------------------ 4802| 0| std::string err = pHMgr->encode_flag(aflag); 4803| 0| HUNSPELL_WARNING(stderr, "error: line %d: affix %s: missing data\n", 4804| 0| af->getlinenum(), err.c_str()); 4805| 0| return false; 4806| 0| } 4807| | 4808| | // now parse numents affentries for this affix 4809| 26| AffEntry* entry = affentries.first_entry(); 4810| 68| for (int ent = 0; ent < numents; ++ent) { ------------------ | Branch (4810:21): [True: 42, False: 26] ------------------ 4811| 42| std::string nl; 4812| 42| if (!af->getline(nl)) ------------------ | Branch (4812:9): [True: 0, False: 42] ------------------ 4813| 0| return false; 4814| 42| mychomp(nl); 4815| 42| int ruleline = af->getlinenum(); 4816| | 4817| 42| iter = nl.begin(); 4818| 42| i = 0; 4819| 42| np = 0; 4820| | 4821| | // split line into pieces 4822| 42| start_piece = mystrsep(nl, iter); 4823| 258| while (start_piece != nl.end()) { ------------------ | Branch (4823:12): [True: 216, False: 42] ------------------ 4824| 216| switch (i) { 4825| | // piece 1 - is type 4826| 42| case 0: { ------------------ | Branch (4826:9): [True: 42, False: 174] ------------------ 4827| 42| np++; 4828| 42| if (ent != 0) ------------------ | Branch (4828:15): [True: 16, False: 26] ------------------ 4829| 16| entry = affentries.add_entry((char)(aeXPRODUCT | aeUTF8 | aeALIASF | aeALIASM)); ------------------ | | 65| 16|#define aeXPRODUCT (1 << 0) ------------------ entry = affentries.add_entry((char)(aeXPRODUCT | aeUTF8 | aeALIASF | aeALIASM)); ------------------ | | 66| 16|#define aeUTF8 (1 << 1) ------------------ entry = affentries.add_entry((char)(aeXPRODUCT | aeUTF8 | aeALIASF | aeALIASM)); ------------------ | | 67| 16|#define aeALIASF (1 << 2) ------------------ entry = affentries.add_entry((char)(aeXPRODUCT | aeUTF8 | aeALIASF | aeALIASM)); ------------------ | | 68| 16|#define aeALIASM (1 << 3) ------------------ 4830| 42| break; 4831| 0| } 4832| | 4833| | // piece 2 - is affix char 4834| 42| case 1: { ------------------ | Branch (4834:9): [True: 42, False: 174] ------------------ 4835| 42| np++; 4836| 42| std::string chunk(start_piece, iter); 4837| 42| if (pHMgr->decode_flag(chunk) != aflag) { ------------------ | Branch (4837:15): [True: 0, False: 42] ------------------ 4838| 0| std::string err = pHMgr->encode_flag(aflag); 4839| 0| HUNSPELL_WARNING(stderr, 4840| 0| "error: line %d: affix %s is corrupt\n", 4841| 0| af->getlinenum(), err.c_str()); 4842| 0| return false; 4843| 0| } 4844| | 4845| 42| if (ent != 0) { ------------------ | Branch (4845:15): [True: 16, False: 26] ------------------ 4846| 16| AffEntry* start_entry = affentries.first_entry(); 4847| 16| entry->aflag = start_entry->aflag; 4848| 16| } 4849| 42| break; 4850| 42| } 4851| | 4852| | // piece 3 - is string to strip or 0 for null 4853| 42| case 2: { ------------------ | Branch (4853:9): [True: 42, False: 174] ------------------ 4854| 42| np++; 4855| 42| entry->strip = std::string(start_piece, iter); 4856| 42| if (complexprefixes) { ------------------ | Branch (4856:15): [True: 4, False: 38] ------------------ 4857| 4| if (utf8) ------------------ | Branch (4857:17): [True: 0, False: 4] ------------------ 4858| 0| reverseword_utf(entry->strip); 4859| 4| else 4860| 4| reverseword(entry->strip); 4861| 4| } 4862| 42| if (entry->strip.compare("0") == 0) { ------------------ | Branch (4862:15): [True: 36, False: 6] ------------------ 4863| 36| entry->strip.clear(); 4864| 36| } 4865| 42| break; 4866| 42| } 4867| | 4868| | // piece 4 - is affix string or 0 for null 4869| 42| case 3: { ------------------ | Branch (4869:9): [True: 42, False: 174] ------------------ 4870| 42| entry->morphcode = nullptr; 4871| 42| entry->contclass = nullptr; 4872| 42| entry->contclasslen = 0; 4873| 42| np++; 4874| 42| std::string::const_iterator dash = std::find(start_piece, iter, '/'); 4875| 42| if (dash != iter) { ------------------ | Branch (4875:15): [True: 18, False: 24] ------------------ 4876| 18| entry->appnd = std::string(start_piece, dash); 4877| 18| std::string dash_str(dash + 1, iter); 4878| | 4879| 18| if (!ignorechars.empty() && !has_no_ignored_chars(entry->appnd, ignorechars)) { ------------------ | Branch (4879:17): [True: 2, False: 16] | Branch (4879:41): [True: 0, False: 2] ------------------ 4880| 0| if (utf8) { ------------------ | Branch (4880:19): [True: 0, False: 0] ------------------ 4881| 0| remove_ignored_chars_utf(entry->appnd, ignorechars_utf16); 4882| 0| } else { 4883| 0| remove_ignored_chars(entry->appnd, ignorechars); 4884| 0| } 4885| 0| } 4886| | 4887| 18| if (complexprefixes) { ------------------ | Branch (4887:17): [True: 2, False: 16] ------------------ 4888| 2| if (utf8) ------------------ | Branch (4888:19): [True: 0, False: 2] ------------------ 4889| 0| reverseword_utf(entry->appnd); 4890| 2| else 4891| 2| reverseword(entry->appnd); 4892| 2| } 4893| | 4894| 18| if (pHMgr->is_aliasf()) { ------------------ | Branch (4894:17): [True: 2, False: 16] ------------------ 4895| 2| int index = atoi(dash_str.c_str()); 4896| 2| entry->contclasslen = (unsigned short)pHMgr->get_aliasf( 4897| 2| index, &(entry->contclass), af); 4898| 2| if (!entry->contclasslen) ------------------ | Branch (4898:19): [True: 0, False: 2] ------------------ 4899| 0| HUNSPELL_WARNING(stderr, 4900| 0| "error: bad affix flag alias: \"%s\"\n", 4901| 0| dash_str.c_str()); 4902| 16| } else { 4903| 16| entry->contclasslen = (unsigned short)pHMgr->decode_flags( 4904| 16| &(entry->contclass), dash_str, af); 4905| 16| std::sort(entry->contclass, entry->contclass + entry->contclasslen); 4906| 16| } 4907| | 4908| 18| havecontclass = 1; 4909| 44| for (unsigned short _i = 0; _i < entry->contclasslen; _i++) { ------------------ | Branch (4909:41): [True: 26, False: 18] ------------------ 4910| 26| contclasses[(entry->contclass)[_i]] = 1; 4911| 26| } 4912| 24| } else { 4913| 24| entry->appnd = std::string(start_piece, iter); 4914| | 4915| 24| if (!ignorechars.empty() && !has_no_ignored_chars(entry->appnd, ignorechars)) { ------------------ | Branch (4915:17): [True: 2, False: 22] | Branch (4915:41): [True: 2, False: 0] ------------------ 4916| 2| if (utf8) { ------------------ | Branch (4916:19): [True: 0, False: 2] ------------------ 4917| 0| remove_ignored_chars_utf(entry->appnd, ignorechars_utf16); 4918| 2| } else { 4919| 2| remove_ignored_chars(entry->appnd, ignorechars); 4920| 2| } 4921| 2| } 4922| | 4923| 24| if (complexprefixes) { ------------------ | Branch (4923:17): [True: 2, False: 22] ------------------ 4924| 2| if (utf8) ------------------ | Branch (4924:19): [True: 0, False: 2] ------------------ 4925| 0| reverseword_utf(entry->appnd); 4926| 2| else 4927| 2| reverseword(entry->appnd); 4928| 2| } 4929| 24| } 4930| | 4931| 42| if (entry->appnd.compare("0") == 0) { ------------------ | Branch (4931:15): [True: 2, False: 40] ------------------ 4932| 2| entry->appnd.clear(); 4933| 2| } 4934| 42| break; 4935| 42| } 4936| | 4937| | // piece 5 - is the conditions descriptions 4938| 42| case 4: { ------------------ | Branch (4938:9): [True: 42, False: 174] ------------------ 4939| 42| std::string chunk(start_piece, iter); 4940| 42| np++; 4941| 42| if (complexprefixes) { ------------------ | Branch (4941:15): [True: 4, False: 38] ------------------ 4942| 4| if (utf8) ------------------ | Branch (4942:17): [True: 0, False: 4] ------------------ 4943| 0| reverseword_utf(chunk); 4944| 4| else 4945| 4| reverseword(chunk); 4946| 4| reverse_condition(chunk); 4947| 4| } 4948| 42| if (!entry->strip.empty() && chunk != "." && ------------------ | Branch (4948:15): [True: 6, False: 36] | Branch (4948:40): [True: 6, False: 0] ------------------ 4949| 6| redundant_condition(at, entry->strip, chunk, ------------------ | Branch (4949:15): [True: 6, False: 0] ------------------ 4950| 6| af->getlinenum())) { 4951| 6| chunk = "."; 4952| 6| entry->opts |= aeREDUNDANTCOND; ------------------ | | 72| 6|#define aeREDUNDANTCOND (1 << 5) ------------------ 4953| 6| } 4954| 42| if (at == 'S') { ------------------ | Branch (4954:15): [True: 34, False: 8] ------------------ 4955| 34| reverseword(chunk); 4956| 34| reverse_condition(chunk); 4957| 34| } 4958| 42| if (encodeit(*entry, chunk)) ------------------ | Branch (4958:15): [True: 0, False: 42] ------------------ 4959| 0| return false; 4960| 42| break; 4961| 42| } 4962| | 4963| 42| case 5: { ------------------ | Branch (4963:9): [True: 6, False: 210] ------------------ 4964| 6| std::string chunk(start_piece, iter); 4965| 6| np++; 4966| 6| if (pHMgr->is_aliasm()) { ------------------ | Branch (4966:15): [True: 0, False: 6] ------------------ 4967| 0| int index = atoi(chunk.c_str()); 4968| 0| entry->morphcode = pHMgr->get_aliasm(index); 4969| 6| } else { 4970| 6| if (complexprefixes) { // XXX - fix me for morph. gen. ------------------ | Branch (4970:17): [True: 0, False: 6] ------------------ 4971| 0| if (utf8) ------------------ | Branch (4971:19): [True: 0, False: 0] ------------------ 4972| 0| reverseword_utf(chunk); 4973| 0| else 4974| 0| reverseword(chunk); 4975| 0| } 4976| | // add the remaining of the line 4977| 6| std::string::const_iterator end = nl.end(); 4978| 6| if (iter != end) { ------------------ | Branch (4978:17): [True: 0, False: 6] ------------------ 4979| 0| chunk.append(iter, end); 4980| 0| } 4981| 6| entry->morphcode = mystrdup(chunk.c_str()); 4982| 6| } 4983| 6| break; 4984| 42| } 4985| 0| default: ------------------ | Branch (4985:9): [True: 0, False: 216] ------------------ 4986| 0| break; 4987| 216| } 4988| 216| i++; 4989| 216| start_piece = mystrsep(nl, iter); 4990| 216| } 4991| | // check to make sure we parsed enough pieces 4992| 42| if (np < 4) { ------------------ | Branch (4992:9): [True: 0, False: 42] ------------------ 4993| 0| std::string err = pHMgr->encode_flag(aflag); 4994| 0| HUNSPELL_WARNING(stderr, "error: line %d: affix %s is corrupt\n", 4995| 0| af->getlinenum(), err.c_str()); 4996| 0| return false; 4997| 0| } 4998| | 4999| 42| entry->line = ruleline; 5000| 42| entry->headerline = headerline; 5001| 42| entry->xprod = xprod; 5002| | 5003| |#ifdef DEBUG 5004| | // detect unnecessary fields, excepting comments 5005| | if (basefieldnum) { 5006| | int fieldnum = 5007| | !(entry->morphcode) ? 5 : ((*(entry->morphcode) == '#') ? 5 : 6); 5008| | if (fieldnum != basefieldnum) 5009| | HUNSPELL_WARNING(stderr, "warning: line %d: bad field number\n", 5010| | af->getlinenum()); 5011| | } else { 5012| | basefieldnum = 5013| | !(entry->morphcode) ? 5 : ((*(entry->morphcode) == '#') ? 5 : 6); 5014| | } 5015| |#endif 5016| 42| } 5017| | 5018| | // now create SfxEntry or PfxEntry objects and use links to 5019| | // build an ordered (sorted by affix string) list 5020| 26| auto start = affentries.begin(), end = affentries.end(); 5021| 68| for (auto affentry = start; affentry != end; ++affentry) { ------------------ | Branch (5021:31): [True: 42, False: 26] ------------------ 5022| 42| if (at == 'P') { ------------------ | Branch (5022:9): [True: 8, False: 34] ------------------ 5023| 8| build_pfxtree(static_cast(*affentry)); 5024| 34| } else { 5025| 34| build_sfxtree(static_cast(*affentry)); 5026| 34| } 5027| 42| } 5028| | 5029| | //contents belong to AffixMgr now 5030| 26| affentries.release(); 5031| | 5032| 26| return true; 5033| 26|} _ZN8AffixMgr19redundant_conditionEcRKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_i: 5038| 6| int linenum) { 5039| 6| int stripl = strip.size(), condl = cond.size(), i, j, neg, in; 5040| 6| if (ft == 'P') { // prefix ------------------ | Branch (5040:7): [True: 0, False: 6] ------------------ 5041| 0| if (strip.compare(0, condl, cond) == 0) ------------------ | Branch (5041:9): [True: 0, False: 0] ------------------ 5042| 0| return 1; 5043| 0| if (utf8) { ------------------ | Branch (5043:9): [True: 0, False: 0] ------------------ 5044| 0| } else { 5045| 0| for (i = 0, j = 0; (i < stripl) && (j < condl); i++, j++) { ------------------ | Branch (5045:26): [True: 0, False: 0] | Branch (5045:42): [True: 0, False: 0] ------------------ 5046| 0| if (cond[j] != '[') { ------------------ | Branch (5046:13): [True: 0, False: 0] ------------------ 5047| 0| if (cond[j] != strip[i]) { ------------------ | Branch (5047:15): [True: 0, False: 0] ------------------ 5048| 0| HUNSPELL_WARNING(stderr, 5049| 0| "warning: line %d: incompatible stripping " 5050| 0| "characters and condition\n", 5051| 0| linenum); 5052| 0| return 0; 5053| 0| } 5054| 0| } else { 5055| 0| neg = (cond[j + 1] == '^') ? 1 : 0; ------------------ | Branch (5055:17): [True: 0, False: 0] ------------------ 5056| 0| in = 0; 5057| 0| do { 5058| 0| j++; 5059| 0| if (strip[i] == cond[j]) ------------------ | Branch (5059:17): [True: 0, False: 0] ------------------ 5060| 0| in = 1; 5061| 0| } while ((j < (condl - 1)) && (cond[j] != ']')); ------------------ | Branch (5061:20): [True: 0, False: 0] | Branch (5061:41): [True: 0, False: 0] ------------------ 5062| 0| if (j == (condl - 1) && (cond[j] != ']')) { ------------------ | Branch (5062:15): [True: 0, False: 0] | Branch (5062:35): [True: 0, False: 0] ------------------ 5063| 0| HUNSPELL_WARNING(stderr, 5064| 0| "error: line %d: missing ] in condition:\n%s\n", 5065| 0| linenum, cond.c_str()); 5066| 0| return 0; 5067| 0| } 5068| 0| if ((!neg && !in) || (neg && in)) { ------------------ | Branch (5068:16): [True: 0, False: 0] | Branch (5068:24): [True: 0, False: 0] | Branch (5068:33): [True: 0, False: 0] | Branch (5068:40): [True: 0, False: 0] ------------------ 5069| 0| HUNSPELL_WARNING(stderr, 5070| 0| "warning: line %d: incompatible stripping " 5071| 0| "characters and condition\n", 5072| 0| linenum); 5073| 0| return 0; 5074| 0| } 5075| 0| } 5076| 0| } 5077| 0| if (j >= condl) ------------------ | Branch (5077:11): [True: 0, False: 0] ------------------ 5078| 0| return 1; 5079| 0| } 5080| 6| } else { // suffix 5081| 6| if ((stripl >= condl) && strip.compare(stripl - condl, std::string::npos, cond) == 0) ------------------ | Branch (5081:9): [True: 6, False: 0] | Branch (5081:30): [True: 6, False: 0] ------------------ 5082| 6| return 1; 5083| 0| if (utf8) { ------------------ | Branch (5083:9): [True: 0, False: 0] ------------------ 5084| 0| } else { 5085| 0| for (i = stripl - 1, j = condl - 1; (i >= 0) && (j >= 0); i--, j--) { ------------------ | Branch (5085:43): [True: 0, False: 0] | Branch (5085:55): [True: 0, False: 0] ------------------ 5086| 0| if (cond[j] != ']') { ------------------ | Branch (5086:13): [True: 0, False: 0] ------------------ 5087| 0| if (cond[j] != strip[i]) { ------------------ | Branch (5087:15): [True: 0, False: 0] ------------------ 5088| 0| HUNSPELL_WARNING(stderr, 5089| 0| "warning: line %d: incompatible stripping " 5090| 0| "characters and condition\n", 5091| 0| linenum); 5092| 0| return 0; 5093| 0| } 5094| 0| } else if (j > 0) { ------------------ | Branch (5094:20): [True: 0, False: 0] ------------------ 5095| 0| in = 0; 5096| 0| do { 5097| 0| j--; 5098| 0| if (strip[i] == cond[j]) ------------------ | Branch (5098:17): [True: 0, False: 0] ------------------ 5099| 0| in = 1; 5100| 0| } while ((j > 0) && (cond[j] != '[')); ------------------ | Branch (5100:20): [True: 0, False: 0] | Branch (5100:31): [True: 0, False: 0] ------------------ 5101| 0| if ((j == 0) && (cond[j] != '[')) { ------------------ | Branch (5101:15): [True: 0, False: 0] | Branch (5101:27): [True: 0, False: 0] ------------------ 5102| 0| HUNSPELL_WARNING(stderr, 5103| 0| "error: line: %d: missing ] in condition:\n%s\n", 5104| 0| linenum, cond.c_str()); 5105| 0| return 0; 5106| 0| } 5107| 0| neg = (cond[j + 1] == '^') ? 1 : 0; ------------------ | Branch (5107:17): [True: 0, False: 0] ------------------ 5108| 0| if ((!neg && !in) || (neg && in)) { ------------------ | Branch (5108:16): [True: 0, False: 0] | Branch (5108:24): [True: 0, False: 0] | Branch (5108:33): [True: 0, False: 0] | Branch (5108:40): [True: 0, False: 0] ------------------ 5109| 0| HUNSPELL_WARNING(stderr, 5110| 0| "warning: line %d: incompatible stripping " 5111| 0| "characters and condition\n", 5112| 0| linenum); 5113| 0| return 0; 5114| 0| } 5115| 0| } 5116| 0| } 5117| 0| if (j < 0) ------------------ | Branch (5117:11): [True: 0, False: 0] ------------------ 5118| 0| return 1; 5119| 0| } 5120| 0| } 5121| 0| return 0; 5122| 6|} _ZN8AffixMgr8isSubsetEPKcS1_: 1118| 132k|inline int AffixMgr::isSubset(const char* s1, const char* s2) { 1119| 194k| while (((*s1 == *s2) || (*s1 == '.')) && (*s1 != '\0') && (*s2 != '\0')) { ------------------ | Branch (1119:11): [True: 132k, False: 61.3k] | Branch (1119:27): [True: 0, False: 61.3k] | Branch (1119:44): [True: 61.5k, False: 71.3k] | Branch (1119:61): [True: 61.5k, False: 0] ------------------ 1120| 61.5k| s1++; 1121| 61.5k| s2++; 1122| 61.5k| } 1123| 132k| return (*s1 == '\0'); 1124| 132k|} affixmgr.cxx:_ZN12_GLOBAL__N_115DistinctRecordsC2Ec: 97| 33.3k| explicit DistinctRecords(char breakchar) : sep(breakchar) {} affixmgr.cxx:_ZNK12_GLOBAL__N_115DistinctRecords4joinEv: 117| 33.3k| std::string join() const { 118| 33.3k| std::string text; 119| 33.3k| for (const std::string& record : records) { ------------------ | Branch (119:38): [True: 0, False: 33.3k] ------------------ 120| 0| text.append(record); 121| 0| text.push_back(sep); 122| 0| } 123| 33.3k| return text; 124| 33.3k| } affixmgr.cxx:_ZZN8AffixMgr12suffix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratchttctENK3$_1clEP8SfxEntry: 3020| 192k| &candidates](SfxEntry* se) { 3021| 192k| if (!t) ------------------ | Branch (3021:9): [True: 192k, False: 0] ------------------ 3022| 192k| return; 3023| 0| ++candidates; 3024| 0| trace_affix(*t, "sfx", this, *se); 3025| 0| TraceScope trace_depth(t); 3026| 0| suffix_applicable(ppfx, se, cclass, in_compound, t); 3027| 0| }; affixmgr.cxx:_ZZN8AffixMgr12suffix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratchttctENK3$_0clEv: 3012| 539M| auto report_empty_pass = [t, &word, start, len, sfxopts, &candidates]() { 3013| 539M| if (t && candidates == 0) ------------------ | Branch (3013:9): [True: 0, False: 539M] | Branch (3013:14): [True: 0, False: 0] ------------------ 3014| 0| trace(*t, "sfx \"%s\" candidates=0%s", word.substr(start, len).c_str(), 3015| 0| (sfxopts & aeXPRODUCT) != 0 ? " xprod=Y" : ""); ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ | Branch (3015:13): [True: 0, False: 0] ------------------ 3016| 539M| }; _ZN8AffixMgr11isRevSubsetEPKcS1_i: 2912| 327k| int len) { 2913| 655k| while ((len > 0) && (*s1 != '\0') && ((*s1 == *end_of_s2) || (*s1 == '.'))) { ------------------ | Branch (2913:10): [True: 651k, False: 3.94k] | Branch (2913:23): [True: 367k, False: 284k] | Branch (2913:41): [True: 327k, False: 39.2k] | Branch (2913:64): [True: 0, False: 39.2k] ------------------ 2914| 327k| s1++; 2915| 327k| end_of_s2--; 2916| 327k| len--; 2917| 327k| } 2918| 327k| return (*s1 == '\0'); 2919| 327k|} affixmgr.cxx:_ZZN8AffixMgr11affix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiR12AffixScratchtctPP8PfxEntryPP8SfxEntryENK3$_0clEPK6hentry: 3366| 17.4M| auto report_form = [this, t, &word, start, len, found_pfx, found_sfx](const struct hentry* rv) { 3367| 17.4M| if (!rv) ------------------ | Branch (3367:9): [True: 17.4M, False: 0] ------------------ 3368| 17.4M| return; 3369| 0| if (t) ------------------ | Branch (3369:9): [True: 0, False: 0] ------------------ 3370| 0| trace_form(*t, this, word.substr(start, len), rv->word, pfx, sfx); 3371| 0| if (found_pfx) ------------------ | Branch (3371:9): [True: 0, False: 0] ------------------ 3372| 0| *found_pfx = pfx; 3373| 0| if (found_sfx) ------------------ | Branch (3373:9): [True: 0, False: 0] ------------------ 3374| 0| *found_sfx = sfx; 3375| 0| }; affixmgr.cxx:_ZN12_GLOBAL__N_18mystrdupEPKc: 3628| 545k| char* mystrdup(const char* s) { 3629| 545k| char* d = nullptr; 3630| 545k| if (s) { ------------------ | Branch (3630:9): [True: 545k, False: 0] ------------------ 3631| 545k| size_t sl = strlen(s) + 1; 3632| 545k| d = new char[sl]; 3633| 545k| memcpy(d, s, sl); 3634| 545k| } 3635| 545k| return d; 3636| 545k| } _ZN17entries_containerC2EcP8AffixMgr: 4674| 26| : m_mgr(mgr) 4675| 26| , m_at(at) { 4676| 26| } _ZN17entries_container10initializeEict: 4681| 26| char opts, unsigned short aflag) { 4682| 26| entries.reserve(std::min(numents, 16384)); 4683| | 4684| 26| if (m_at == 'P') { ------------------ | Branch (4684:9): [True: 8, False: 18] ------------------ 4685| 8| entries.push_back(new PfxEntry(m_mgr)); 4686| 18| } else { 4687| 18| entries.push_back(new SfxEntry(m_mgr)); 4688| 18| } 4689| | 4690| 26| entries.back()->opts = opts; 4691| 26| entries.back()->aflag = aflag; 4692| 26| } _ZN17entries_container11first_entryEv: 4705| 42| AffEntry* first_entry() { return entries.empty() ? nullptr : entries[0]; } ------------------ | Branch (4705:36): [True: 0, False: 42] ------------------ _ZN17entries_container9add_entryEc: 4694| 16| AffEntry* add_entry(char opts) { 4695| 16| if (m_at == 'P') { ------------------ | Branch (4695:9): [True: 0, False: 16] ------------------ 4696| 0| entries.push_back(new PfxEntry(m_mgr)); 4697| 16| } else { 4698| 16| entries.push_back(new SfxEntry(m_mgr)); 4699| 16| } 4700| 16| AffEntry* ret = entries.back(); 4701| 16| ret->opts = entries[0]->opts & opts; 4702| 16| return ret; 4703| 16| } _ZN17entries_container5beginEv: 4713| 26| std::vector::iterator begin() { return entries.begin(); } _ZN17entries_container3endEv: 4714| 26| std::vector::iterator end() { return entries.end(); } _ZN17entries_container7releaseEv: 4677| 26| void release() { 4678| 26| entries.clear(); 4679| 26| } _ZN17entries_containerD2Ev: 4707| 26| ~entries_container() { 4708| 26| for (auto& entry : entries) { ------------------ | Branch (4708:22): [True: 0, False: 26] ------------------ 4709| 0| delete entry; 4710| 0| } 4711| 26| } affixmgr.cxx:_ZZN8AffixMgr12get_syllableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEENK3$_1clE6w_char: 1709| 3.51k| [&](w_char wc) { 1710| 3.51k| return std::binary_search(cpdvowels_utf16.begin(), cpdvowels_utf16.end(), wc); 1711| 3.51k| }); _ZN9guesswordC2Ev: 121| 4.70M| : word(nullptr) 122| 4.70M| , allow(false) 123| 4.70M| , orig(nullptr) 124| 4.70M| { 125| 4.70M| } _ZN8patentryC2Ev: 138| 4| : cond(FLAG_NULL) ------------------ | | 99| 4|#define FLAG_NULL 0x00 ------------------ 139| 4| , cond2(FLAG_NULL) { ------------------ | | 99| 4|#define FLAG_NULL 0x00 ------------------ 140| 4| } csutil.cxx:_ZL16HUNSPELL_WARNINGP8_IO_FILEPKcz: 48| 1.23M|static inline void HUNSPELL_WARNING(FILE*, const char*, ...) {} _ZN8AffEntryC2Ev: 46| 42| : morphcode(nullptr) 47| 42| , contclass(nullptr) 48| 42| , line(0) 49| 42| , headerline(0) 50| 42| , aflag(0) 51| 42| , contclasslen(0) 52| 42| , numconds(0) 53| 42| , opts(0) 54| 42| , xprod(0) {} _Z6myopenRNSt3__114basic_ifstreamIcNS_11char_traitsIcEEEEPKcj: 111| 114|{ 112| |#if defined(_WIN32) && defined(_MSC_VER) 113| |#define WIN32_LONG_PATH_PREFIX "\\\\?\\" 114| | if (strncmp(path, WIN32_LONG_PATH_PREFIX, 4) == 0) { 115| | int len = MultiByteToWideChar(CP_UTF8, 0, path, -1, NULL, 0); 116| | wchar_t* buff = new wchar_t[len]; 117| | wchar_t* buff2 = new wchar_t[len]; 118| | MultiByteToWideChar(CP_UTF8, 0, path, -1, buff, len); 119| | if (_wfullpath(buff2, buff, len) != NULL) { 120| | stream.open(buff2, mode); 121| | } 122| | delete [] buff; 123| | delete [] buff2; 124| | } 125| | else 126| |#endif 127| 114| stream.open(path, mode); 128| 114|} _Z6u16_u8RNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKNS_6vectorI6w_charNS3_IS8_EEEE: 135| 22.5M|std::string& u16_u8(std::string& dest, const std::vector& src) { 136| 22.5M| dest.clear(); 137| 22.5M| dest.reserve(src.size()); 138| 610M| for (const w_char& wc : src) { ------------------ | Branch (138:25): [True: 610M, False: 22.5M] ------------------ 139| 610M| uint16_t cp = (static_cast(wc.h) << 8) | wc.l; 140| 610M| if (cp < 0x80) { ------------------ | Branch (140:9): [True: 532M, False: 77.5M] ------------------ 141| 532M| dest.push_back(static_cast(cp)); 142| 532M| } else if (cp < 0x800) { ------------------ | Branch (142:16): [True: 2.17M, False: 75.3M] ------------------ 143| 2.17M| dest.push_back(static_cast(0xc0 | (cp >> 6))); 144| 2.17M| dest.push_back(static_cast(0x80 | (cp & 0x3f))); 145| 75.3M| } else { 146| 75.3M| dest.push_back(static_cast(0xe0 | (cp >> 12))); 147| 75.3M| dest.push_back(static_cast(0x80 | ((cp >> 6) & 0x3f))); 148| 75.3M| dest.push_back(static_cast(0x80 | (cp & 0x3f))); 149| 75.3M| } 150| 610M| } 151| 22.5M| return dest; 152| 22.5M|} _Z6u8_u16RNSt3__16vectorI6w_charNS_9allocatorIS1_EEEERKNS_12basic_stringIcNS_11char_traitsIcEENS2_IcEEEEb: 170| 3.84M|int u8_u16(std::vector& dest, const std::string& src, bool only_convert_first_letter) { 171| | // faster to oversize initially, assign to elements and resize to what's used 172| | // than to reserve and push_back 173| 3.84M| dest.resize(only_convert_first_letter ? 1 : src.size()); ------------------ | Branch (173:15): [True: 0, False: 3.84M] ------------------ 174| 3.84M| auto out = dest.begin(); 175| 3.84M| auto p = src.begin(), end = src.end(); 176| | 177| 36.2M| while (p < end) { ------------------ | Branch (177:10): [True: 32.6M, False: 3.61M] ------------------ 178| 32.6M| uint8_t b0 = static_cast(*p); 179| 32.6M| uint16_t cp; 180| | 181| 32.6M| if (b0 < 0x80) { ------------------ | Branch (181:9): [True: 29.2M, False: 3.38M] ------------------ 182| | // 1-byte ASCII 183| 29.2M| cp = b0; 184| 29.2M| } else if (b0 < 0xc0) { ------------------ | Branch (184:16): [True: 291k, False: 3.09M] ------------------ 185| | // continuation byte at lead position 186| 291k| HUNSPELL_WARNING(stderr, 187| 291k| "UTF-8 encoding error. Unexpected continuation bytes " 188| 291k| "in %ld. character position\n%s\n", 189| 291k| static_cast(std::distance(src.begin(), p)), 190| 291k| src.c_str()); 191| 291k| cp = 0xfffd; 192| 3.09M| } else if (b0 < 0xe0) { ------------------ | Branch (192:16): [True: 774k, False: 2.31M] ------------------ 193| | // 2-byte sequence: 110xxxxx 10yyyyyy 194| 774k| if (p + 1 < end && is_utf8_cont(p[1])) { ------------------ | Branch (194:11): [True: 682k, False: 91.3k] | Branch (194:11): [True: 158k, False: 615k] | Branch (194:26): [True: 158k, False: 524k] ------------------ 195| 158k| cp = ((b0 & 0x1f) << 6) | (static_cast(p[1]) & 0x3f); 196| 158k| ++p; // step past lead; loop bottom steps past cont 197| 615k| } else { 198| 615k| warn_missing_cont(src, p); 199| 615k| cp = 0xfffd; 200| 615k| } 201| 2.31M| } else if (b0 < 0xf0) { ------------------ | Branch (201:16): [True: 2.09M, False: 223k] ------------------ 202| | // 3-byte sequence: 1110xxxx 10yyyyyy 10zzzzzz 203| 2.09M| if (p + 1 < end && is_utf8_cont(p[1])) { ------------------ | Branch (203:11): [True: 2.06M, False: 26.3k] | Branch (203:11): [True: 1.99M, False: 100k] | Branch (203:26): [True: 1.99M, False: 73.6k] ------------------ 204| 1.99M| uint8_t b1 = static_cast(p[1]); 205| 1.99M| ++p; // step past lead 206| 1.99M| if (p + 1 < end && is_utf8_cont(p[1])) { ------------------ | Branch (206:13): [True: 1.99M, False: 1.02k] | Branch (206:13): [True: 1.98M, False: 5.46k] | Branch (206:28): [True: 1.98M, False: 4.43k] ------------------ 207| 1.98M| cp = ((b0 & 0x0f) << 12) | ((b1 & 0x3f) << 6) | (static_cast(p[1]) & 0x3f); 208| 1.98M| ++p; // step past first cont; loop bottom steps past second cont 209| 1.98M| } else { 210| 5.46k| warn_missing_cont(src, p); 211| 5.46k| cp = 0xfffd; 212| 5.46k| } 213| 1.99M| } else { 214| 100k| warn_missing_cont(src, p); 215| 100k| cp = 0xfffd; 216| 100k| } 217| 2.09M| } else { 218| | // 4+ byte lead: codepoint >= U+10000, can't fit in w_char 219| 223k| HUNSPELL_WARNING(stderr, 220| 223k| "This UTF-8 encoding can't convert to UTF-16:\n%s\n", 221| 223k| src.c_str()); 222| 223k| out->h = 0xff; 223| 223k| out->l = 0xfd; 224| 223k| ++out; 225| 223k| dest.resize(out - dest.begin()); 226| 223k| return -1; 227| 223k| } 228| | 229| 32.4M| out->h = static_cast(cp >> 8); 230| 32.4M| out->l = static_cast(cp); 231| 32.4M| ++out; 232| 32.4M| if (only_convert_first_letter) ------------------ | Branch (232:9): [True: 0, False: 32.4M] ------------------ 233| 0| break; 234| 32.4M| ++p; // consume lead byte 235| 32.4M| } 236| | 237| 3.61M| int size = static_cast(out - dest.begin()); 238| 3.61M| dest.resize(size); 239| 3.61M| return size; 240| 3.84M|} _Z8mystrsepRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERNS_11__wrap_iterIPKcEE: 255| 1.80k| std::string::const_iterator& start) { 256| 1.80k| auto end = str.end(); 257| | 258| 1.80k| is_any_of op(" \t"); 259| | // don't use isspace() here, the string can be in some random charset 260| | // that's way different than the locale's 261| 1.80k| auto sp = start; 262| 5.87k| while (sp != end && op(*sp)) ------------------ | Branch (262:10): [True: 5.43k, False: 442] | Branch (262:23): [True: 4.07k, False: 1.35k] ------------------ 263| 4.07k| ++sp; 264| | 265| 1.80k| auto dp = sp; 266| 6.69k| while (dp != end && !op(*dp)) ------------------ | Branch (266:10): [True: 5.81k, False: 882] | Branch (266:23): [True: 4.89k, False: 918] ------------------ 267| 4.89k| ++dp; 268| | 269| 1.80k| start = dp; 270| 1.80k| return sp; 271| 1.80k|} _Z7mychompRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 274| 1.99k|void mychomp(std::string& s) { 275| 1.99k| size_t k = s.size(); 276| 1.99k| size_t newsize = k; 277| 1.99k| if ((k > 0) && ((s[k - 1] == '\r') || (s[k - 1] == '\n'))) ------------------ | Branch (277:7): [True: 1.80k, False: 190] | Branch (277:19): [True: 0, False: 1.80k] | Branch (277:41): [True: 0, False: 1.80k] ------------------ 278| 0| --newsize; 279| 1.99k| if ((k > 1) && (s[k - 2] == '\r')) ------------------ | Branch (279:7): [True: 1.60k, False: 384] | Branch (279:18): [True: 0, False: 1.60k] ------------------ 280| 0| --newsize; 281| 1.99k| s.resize(newsize); 282| 1.99k|} _Z8line_tokRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEc: 285| 187k|std::vector line_tok(const std::string& text, char breakchar) { 286| 187k| std::vector ret; 287| 187k| if (text.empty()) { ------------------ | Branch (287:7): [True: 11.3k, False: 176k] ------------------ 288| 11.3k| return ret; 289| 11.3k| } 290| | 291| 176k| std::stringstream ss(text); 292| 176k| std::string tok; 293| 352k| while(std::getline(ss, tok, breakchar)) { ------------------ | Branch (293:9): [True: 176k, False: 176k] ------------------ 294| 176k| if (!tok.empty()) { ------------------ | Branch (294:9): [True: 176k, False: 71] ------------------ 295| 176k| ret.push_back(tok); 296| 176k| } 297| 176k| } 298| | 299| 176k| return ret; 300| 187k|} _Z9line_uniqRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEc: 312| 12.7k|{ 313| 12.7k| std::vector lines = line_tok(text, breakchar); 314| 12.7k| text.clear(); 315| 12.7k| if (lines.empty()) { ------------------ | Branch (315:7): [True: 11.3k, False: 1.34k] ------------------ 316| 11.3k| return; 317| 11.3k| } 318| | 319| 1.34k| drop_repeated_lines(lines); 320| | 321| 1.34k| text = lines[0]; 322| 1.35k| for (size_t i = 1; i < lines.size(); ++i) { ------------------ | Branch (322:22): [True: 10, False: 1.34k] ------------------ 323| 10| text.push_back(breakchar); 324| 10| text.append(lines[i]); 325| 10| } 326| 1.34k|} _Z21append_compound_partsRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERS5_: 377| 173k|size_t append_compound_parts(const std::string& desc, std::string& result) { 378| | // find by offset, a search from a bare pointer remeasures the rest of desc on every step 379| 173k| size_t part = desc.find(MORPH_PART); ------------------ | | 116| 173k|#define MORPH_PART "pa:" ------------------ 380| 173k| if (part == std::string::npos) ------------------ | Branch (380:7): [True: 173k, False: 0] ------------------ 381| 173k| return 0; 382| 0| static const char separators[] = {' ', '\t', '\n', '\0'}; 383| 0| size_t nextpart = desc.find(MORPH_PART, part + 1); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 384| 0| while (nextpart != std::string::npos) { ------------------ | Branch (384:10): [True: 0, False: 0] ------------------ 385| 0| const auto field = desc.begin() + part + MORPH_TAG_LEN; ------------------ | | 119| 0|#define MORPH_TAG_LEN strlen(MORPH_STEM) | | ------------------ | | | | 103| 0|#define MORPH_STEM "st:" | | ------------------ ------------------ 386| 0| const auto end = desc.begin() + nextpart; 387| 0| result.append(field, std::find_first_of(field, end, std::begin(separators), 388| 0| std::end(separators))); 389| 0| part = nextpart; 390| 0| nextpart = desc.find(MORPH_PART, part + 1); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 391| 0| } 392| 0| return part; 393| 173k|} _Z10copy_fieldRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKS5_S8_: 397| 160k| const std::string& var) { 398| 160k| if (morph.empty()) ------------------ | Branch (398:7): [True: 0, False: 160k] ------------------ 399| 0| return false; 400| 160k| size_t pos = morph.find(var); 401| 160k| if (pos == std::string::npos) ------------------ | Branch (401:7): [True: 5, False: 160k] ------------------ 402| 5| return false; 403| 160k| pos += MORPH_TAG_LEN; ------------------ | | 119| 160k|#define MORPH_TAG_LEN strlen(MORPH_STEM) | | ------------------ | | | | 103| 160k|#define MORPH_STEM "st:" | | ------------------ ------------------ 404| | // copy the field value up to the next whitespace, without first 405| | // making a throwaway copy of the whole remaining tail of the string 406| 160k| size_t end = morph.find_first_of(" \t\n", pos); 407| 160k| dest.assign(morph, pos, end == std::string::npos ? std::string::npos : end - pos); ------------------ | Branch (407:27): [True: 160k, False: 0] ------------------ 408| | 409| 160k| return true; 410| 160k|} _Z8mystrrepRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKS5_S8_: 414| 1.04M| const std::string& replace) { 415| 1.04M| size_t pos = 0; 416| 1.10M| while ((pos = str.find(search, pos)) != std::string::npos) { ------------------ | Branch (416:10): [True: 62.5k, False: 1.04M] ------------------ 417| 62.5k| str.replace(pos, search.length(), replace); 418| 62.5k| pos += replace.length(); 419| 62.5k| } 420| 1.04M| return str; 421| 1.04M|} _Z11reversewordRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 424| 903k|size_t reverseword(std::string& word) { 425| 903k| std::reverse(word.begin(), word.end()); 426| 903k| return word.size(); 427| 903k|} _Z8uniqlistRNSt3__16vectorINS_12basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS4_IS6_EEEE: 504| 7.13k|void uniqlist(std::vector& list) { 505| 7.13k| if (list.size() < 2) ------------------ | Branch (505:7): [True: 7.13k, False: 0] ------------------ 506| 7.13k| return; 507| | 508| 0| std::vector ret; 509| 0| ret.push_back(list[0]); 510| | 511| 0| for (size_t i = 1; i < list.size(); ++i) { ------------------ | Branch (511:22): [True: 0, False: 0] ------------------ 512| 0| if (std::find(ret.begin(), ret.end(), list[i]) == ret.end()) ------------------ | Branch (512:9): [True: 0, False: 0] ------------------ 513| 0| ret.push_back(list[i]); 514| 0| } 515| | 516| 0| list.swap(ret); 517| 0|} _Z9upper_utf6w_chari: 536| 4.21M|w_char upper_utf(w_char u, int langnum) { 537| | 538| 4.21M|#if defined(_WIN32) || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__==__ORDER_LITTLE_ENDIAN__)) || defined(__LITTLE_ENDIAN__) 539| | 540| |//with these optimizations, msvc can optimize this function to one jmp instruction 541| |//but g++ remains in five instructions 542| |//maybe use inline asm for g++? 543| | 544| |#if (__cplusplus >= 202002L || (defined(_MSVC_LANG) && _MSVC_LANG >= 202002L)) && defined __cpp_lib_bit_cast && __cpp_lib_bit_cast >= 201806L 545| | return std::bit_cast(unicodetoupper((unsigned short)u, langnum)); 546| |#else 547| 4.21M| const auto us = unicodetoupper((unsigned short)u, langnum); 548| 4.21M| memcpy(&u, &us, sizeof(unsigned short)); 549| 4.21M| return u; 550| 4.21M|#endif 551| | 552| |#else 553| | const auto us = unicodetoupper((unsigned short)u, langnum); 554| | u.h = (unsigned char)(us >> 8); 555| | u.l = (unsigned char)(us & 0xff); 556| | return u; 557| |#endif 558| 4.21M|} _Z9lower_utf6w_chari: 560| 6.78M|w_char lower_utf(w_char u, int langnum) { 561| | 562| 6.78M|#if defined(_WIN32) || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__==__ORDER_LITTLE_ENDIAN__)) || defined(__LITTLE_ENDIAN__) 563| | 564| |//with these optimizations, msvc can optimize this function to one jmp instruction 565| |//but g++ remains in five instructions 566| |//maybe use inline asm for g++? 567| | 568| |#if (__cplusplus >= 202002L || (defined(_MSVC_LANG) && _MSVC_LANG >= 202002L)) && defined __cpp_lib_bit_cast && __cpp_lib_bit_cast >= 201806L 569| | return std::bit_cast(unicodetolower((unsigned short)u, langnum)); 570| |#else 571| 6.78M| const auto us = unicodetolower((unsigned short)u, langnum); 572| 6.78M| memcpy(&u, &us, sizeof(unsigned short)); 573| 6.78M| return u; 574| 6.78M|#endif 575| | 576| |#else 577| | const auto us = unicodetolower((unsigned short)u, langnum); 578| | u.h = (unsigned char)(us >> 8); 579| | u.l = (unsigned char)(us & 0xff); 580| | return u; 581| |#endif 582| 6.78M|} _Z8mkallcapRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 585| 265k|std::string& mkallcap(std::string& s, const struct cs_info* csconv) { 586| 5.22M| for (char& aI : s) { ------------------ | Branch (586:17): [True: 5.22M, False: 265k] ------------------ 587| 5.22M| aI = cupper(csconv, static_cast(aI)); 588| 5.22M| } 589| 265k| return s; 590| 265k|} _Z10mkallsmallRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 593| 2.37M|std::string& mkallsmall(std::string& s, const struct cs_info* csconv) { 594| 23.7M| for (char& aI : s) { ------------------ | Branch (594:17): [True: 23.7M, False: 2.37M] ------------------ 595| 23.7M| aI = clower(csconv, static_cast(aI)); 596| 23.7M| } 597| 2.37M| return s; 598| 2.37M|} _Z14mkallsmall_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 600| 942k|std::vector& mkallsmall_utf(std::vector& u, int langnum) { 601| 6.73M| for (auto& i : u) { ------------------ | Branch (601:16): [True: 6.73M, False: 942k] ------------------ 602| 6.73M| i = lower_utf(i, langnum); 603| 6.73M| } 604| 942k| return u; 605| 942k|} _Z12mkallcap_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 607| 160k|std::vector& mkallcap_utf(std::vector& u, int langnum) { 608| 1.93M| for (auto& i : u) { ------------------ | Branch (608:16): [True: 1.93M, False: 160k] ------------------ 609| 1.93M| i = upper_utf(i, langnum); 610| 1.93M| } 611| 160k| return u; 612| 160k|} _Z9mkinitcapRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 614| 1.64M|std::string& mkinitcap(std::string& s, const struct cs_info* csconv) { 615| 1.64M| if (!s.empty()) { ------------------ | Branch (615:7): [True: 1.64M, False: 164] ------------------ 616| 1.64M| s[0] = cupper(csconv, static_cast(s[0])); 617| 1.64M| } 618| 1.64M| return s; 619| 1.64M|} _Z13mkinitcap_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 621| 355k|std::vector& mkinitcap_utf(std::vector& u, int langnum) { 622| 355k| if (!u.empty()) { ------------------ | Branch (622:7): [True: 355k, False: 0] ------------------ 623| 355k| u[0] = upper_utf(u[0], langnum); 624| 355k| } 625| 355k| return u; 626| 355k|} _Z11mkinitsmallRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 628| 200k|std::string& mkinitsmall(std::string& s, const struct cs_info* csconv) { 629| 200k| if (!s.empty()) { ------------------ | Branch (629:7): [True: 200k, False: 0] ------------------ 630| 200k| s[0] = clower(csconv, static_cast(s[0])); 631| 200k| } 632| 200k| return s; 633| 200k|} _Z15mkinitsmall_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 635| 33.1k|std::vector& mkinitsmall_utf(std::vector& u, int langnum) { 636| 33.1k| if (!u.empty()) { ------------------ | Branch (636:7): [True: 33.1k, False: 0] ------------------ 637| 33.1k| u[0] = lower_utf(u[0], langnum); 638| 33.1k| } 639| 33.1k| return u; 640| 33.1k|} _Z14get_current_csRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 2298| 1.80k|const struct cs_info* get_current_cs(const std::string& es) { 2299| 1.80k| char* normalized_encoding = new char[es.size() + 1]; 2300| 1.80k| toAsciiLowerAndRemoveNonAlphanumeric(es.c_str(), normalized_encoding); 2301| | 2302| 1.80k| const struct cs_info* ccs = nullptr; 2303| 1.80k| for (const auto& encd : encds) { ------------------ | Branch (2303:25): [True: 1.80k, False: 0] ------------------ 2304| 1.80k| if (strcmp(normalized_encoding, encd.enc_name) == 0) { ------------------ | Branch (2304:9): [True: 1.80k, False: 0] ------------------ 2305| 1.80k| ccs = encd.cs_table; 2306| 1.80k| break; 2307| 1.80k| } 2308| 1.80k| } 2309| | 2310| 1.80k| delete[] normalized_encoding; 2311| | 2312| 1.80k| if (!ccs) { ------------------ | Branch (2312:7): [True: 0, False: 1.80k] ------------------ 2313| 0| HUNSPELL_WARNING(stderr, 2314| 0| "error: unknown encoding %s: using %s as fallback\n", es.c_str(), 2315| 0| encds[0].enc_name); 2316| 0| ccs = encds[0].cs_table; 2317| 0| } 2318| | 2319| 1.80k| return ccs; 2320| 1.80k|} _Z12get_lang_numRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 2450| 4|int get_lang_num(const std::string& lang) { 2451| 72| for (const auto& i : lang2enc) { ------------------ | Branch (2451:22): [True: 72, False: 0] ------------------ 2452| 72| if (strcmp(lang.c_str(), i.lang) == 0) { ------------------ | Branch (2452:9): [True: 4, False: 68] ------------------ 2453| 4| return i.num; 2454| 4| } 2455| 72| } 2456| 0| return LANG_xx; 2457| 4|} _Z14unicodetoupperti: 2459| 26.3M|unsigned short unicodetoupper(unsigned short c, int langnum) { 2460| | // In Azeri and Turkish, I and i dictinct letters: 2461| | // There are a dotless lower case i pair of upper `I', 2462| | // and an upper I with dot pair of lower `i'. 2463| 26.3M| if (c == 0x0069 && ((langnum == LANG_az) || (langnum == LANG_tr) || (langnum == LANG_crh))) ------------------ | Branch (2463:7): [True: 241k, False: 26.1M] | Branch (2463:23): [True: 0, False: 241k] | Branch (2463:47): [True: 0, False: 241k] | Branch (2463:71): [True: 0, False: 241k] ------------------ 2464| 0| return 0x0130; 2465| |#ifdef OPENOFFICEORG 2466| | return static_cast(u_toupper(c)); 2467| |#else 2468| |#ifdef MOZILLA_CLIENT 2469| | return ToUpperCase((char16_t)c); 2470| |#else 2471| 26.3M| unsigned short up = utf_pages[utf_page_index[c >> 8]][c & 0xFF].cupper; 2472| 26.3M| return up ? up : c; ------------------ | Branch (2472:10): [True: 4.13M, False: 22.2M] ------------------ 2473| 26.3M|#endif 2474| 26.3M|#endif 2475| 26.3M|} _Z14unicodetolowerti: 2477| 29.8M|unsigned short unicodetolower(unsigned short c, int langnum) { 2478| | // In Azeri and Turkish, I and i dictinct letters: 2479| | // There are a dotless lower case i pair of upper `I', 2480| | // and an upper I with dot pair of lower `i'. 2481| 29.8M| if (c == 0x0049 && ((langnum == LANG_az) || (langnum == LANG_tr) || (langnum == LANG_crh))) ------------------ | Branch (2481:7): [True: 73.4k, False: 29.7M] | Branch (2481:23): [True: 0, False: 73.4k] | Branch (2481:47): [True: 0, False: 73.4k] | Branch (2481:71): [True: 0, False: 73.4k] ------------------ 2482| 0| return 0x0131; 2483| |#ifdef OPENOFFICEORG 2484| | return static_cast(u_tolower(c)); 2485| |#else 2486| |#ifdef MOZILLA_CLIENT 2487| | return ToLowerCase((char16_t)c); 2488| |#else 2489| 29.8M| unsigned short lo = utf_pages[utf_page_index[c >> 8]][c & 0xFF].clower; 2490| 29.8M| return lo ? lo : c; ------------------ | Branch (2490:10): [True: 2.33M, False: 27.4M] ------------------ 2491| 29.8M|#endif 2492| 29.8M|#endif 2493| 29.8M|} _Z11get_captypeRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 2504| 11.9M|int get_captype(const std::string& word, const cs_info* csconv) { 2505| | // now determine the capitalization type of the first nl letters 2506| 11.9M| size_t ncap = 0; 2507| 11.9M| size_t nneutral = 0; 2508| 11.9M| size_t firstcap = 0; 2509| 11.9M| if (csconv == nullptr) ------------------ | Branch (2509:7): [True: 0, False: 11.9M] ------------------ 2510| 0| return NOCAP; ------------------ | | 92| 0|#define NOCAP 0 ------------------ 2511| 128M| for (char q : word) { ------------------ | Branch (2511:15): [True: 128M, False: 11.9M] ------------------ 2512| 128M| const auto nIndex = static_cast(q); 2513| 128M| if (ccase(csconv, nIndex)) ------------------ | Branch (2513:9): [True: 4.87M, False: 123M] ------------------ 2514| 4.87M| ncap++; 2515| 128M| if (cupper(csconv, nIndex) == clower(csconv, nIndex)) ------------------ | Branch (2515:9): [True: 99.2M, False: 28.8M] ------------------ 2516| 99.2M| nneutral++; 2517| 128M| } 2518| 11.9M| if (ncap) { ------------------ | Branch (2518:7): [True: 1.97M, False: 9.93M] ------------------ 2519| 1.97M| const auto nIndex = static_cast(word[0]); 2520| 1.97M| firstcap = csconv[nIndex].ccase; 2521| 1.97M| } 2522| | 2523| | // now finally set the captype 2524| 11.9M| if (ncap == 0) { ------------------ | Branch (2524:7): [True: 9.93M, False: 1.97M] ------------------ 2525| 9.93M| return NOCAP; ------------------ | | 92| 9.93M|#define NOCAP 0 ------------------ 2526| 9.93M| } else if ((ncap == 1) && firstcap) { ------------------ | Branch (2526:14): [True: 933k, False: 1.03M] | Branch (2526:29): [True: 312k, False: 621k] ------------------ 2527| 312k| return INITCAP; ------------------ | | 93| 312k|#define INITCAP 1 ------------------ 2528| 1.65M| } else if ((ncap == word.size()) || ((ncap + nneutral) == word.size())) { ------------------ | Branch (2528:14): [True: 6.05k, False: 1.65M] | Branch (2528:39): [True: 549k, False: 1.10M] ------------------ 2529| 555k| return ALLCAP; ------------------ | | 94| 555k|#define ALLCAP 2 ------------------ 2530| 1.10M| } else if ((ncap > 1) && firstcap) { ------------------ | Branch (2530:14): [True: 661k, False: 441k] | Branch (2530:28): [True: 205k, False: 455k] ------------------ 2531| 205k| return HUHINITCAP; ------------------ | | 96| 205k|#define HUHINITCAP 4 ------------------ 2532| 205k| } 2533| 896k| return HUHCAP; ------------------ | | 95| 896k|#define HUHCAP 3 ------------------ 2534| 11.9M|} _Z16get_captype_utf8RKNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 2536| 2.40M|int get_captype_utf8(const std::vector& word, int langnum) { 2537| | // now determine the capitalization type of the first nl letters 2538| 2.40M| size_t ncap = 0; 2539| 2.40M| size_t nneutral = 0; 2540| 2.40M| size_t firstcap = 0; 2541| | 2542| 2.40M| auto it = word.begin(), it_end = word.end(); 2543| 24.3M| while (it != it_end) { ------------------ | Branch (2543:10): [True: 21.9M, False: 2.40M] ------------------ 2544| 21.9M| const auto idx = (unsigned short)*it; 2545| 21.9M| const auto lwridx = unicodetolower(idx, langnum); 2546| 21.9M| if (idx != lwridx) ------------------ | Branch (2546:9): [True: 1.05M, False: 20.9M] ------------------ 2547| 1.05M| ncap++; 2548| 21.9M| if (unicodetoupper(idx, langnum) == lwridx) ------------------ | Branch (2548:9): [True: 17.8M, False: 4.09M] ------------------ 2549| 17.8M| nneutral++; 2550| 21.9M| ++it; 2551| 21.9M| } 2552| 2.40M| if (ncap) { ------------------ | Branch (2552:7): [True: 371k, False: 2.03M] ------------------ 2553| 371k| const auto idx = (unsigned short)word[0]; 2554| 371k| firstcap = (idx != unicodetolower(idx, langnum)); 2555| 371k| } 2556| | 2557| | // now finally set the captype 2558| 2.40M| if (ncap == 0) { ------------------ | Branch (2558:7): [True: 2.03M, False: 371k] ------------------ 2559| 2.03M| return NOCAP; ------------------ | | 92| 2.03M|#define NOCAP 0 ------------------ 2560| 2.03M| } else if ((ncap == 1) && firstcap) { ------------------ | Branch (2560:14): [True: 248k, False: 122k] | Branch (2560:29): [True: 81.7k, False: 166k] ------------------ 2561| 81.7k| return INITCAP; ------------------ | | 93| 81.7k|#define INITCAP 1 ------------------ 2562| 289k| } else if ((ncap == word.size()) || ((ncap + nneutral) == word.size())) { ------------------ | Branch (2562:14): [True: 2.32k, False: 286k] | Branch (2562:39): [True: 108k, False: 178k] ------------------ 2563| 110k| return ALLCAP; ------------------ | | 94| 110k|#define ALLCAP 2 ------------------ 2564| 178k| } else if ((ncap > 1) && firstcap) { ------------------ | Branch (2564:14): [True: 72.6k, False: 106k] | Branch (2564:28): [True: 33.5k, False: 39.0k] ------------------ 2565| 33.5k| return HUHINITCAP; ------------------ | | 96| 33.5k|#define HUHINITCAP 4 ------------------ 2566| 33.5k| } 2567| 145k| return HUHCAP; ------------------ | | 95| 145k|#define HUHCAP 3 ------------------ 2568| 2.40M|} _Z24remove_ignored_chars_utfRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKNS_6vectorI6w_charNS3_IS8_EEEE: 2572| 607k| const std::vector& ignored_chars) { 2573| 607k| std::vector w; 2574| 607k| std::vector w2; 2575| 607k| u8_u16(w, word); 2576| | 2577| 607k| std::copy_if(w.begin(), w.end(), std::back_inserter(w2), 2578| 607k| [&ignored_chars](w_char wc) { 2579| 607k| return !std::binary_search(ignored_chars.begin(), ignored_chars.end(), wc); 2580| 607k| }); 2581| | 2582| 607k| u16_u8(word, w2); 2583| 607k| return w2.size(); 2584| 607k|} _Z20remove_ignored_charsRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKS5_: 2588| 2.51M| const std::string& ignored_chars) { 2589| 2.51M| word.erase( 2590| 2.51M| std::remove_if(word.begin(), word.end(), is_any_of(ignored_chars)), 2591| 2.51M| word.end()); 2592| 2.51M| return word.size(); 2593| 2.51M|} _Z12parse_stringRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERS5_i: 2595| 90|bool parse_string(const std::string& line, std::string& out, int ln) { 2596| 90| if (!out.empty()) { ------------------ | Branch (2596:7): [True: 0, False: 90] ------------------ 2597| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple definitions\n", ln); 2598| 0| return false; 2599| 0| } 2600| 90| int i = 0; 2601| 90| int np = 0; 2602| 90| auto iter = line.begin(), start_piece = mystrsep(line, iter); 2603| 270| while (start_piece != line.end()) { ------------------ | Branch (2603:10): [True: 180, False: 90] ------------------ 2604| 180| switch (i) { 2605| 90| case 0: { ------------------ | Branch (2605:7): [True: 90, False: 90] ------------------ 2606| 90| np++; 2607| 90| break; 2608| 0| } 2609| 90| case 1: { ------------------ | Branch (2609:7): [True: 90, False: 90] ------------------ 2610| 90| out.assign(start_piece, iter); 2611| 90| np++; 2612| 90| break; 2613| 0| } 2614| 0| default: ------------------ | Branch (2614:7): [True: 0, False: 180] ------------------ 2615| 0| break; 2616| 180| } 2617| 180| ++i; 2618| 180| start_piece = mystrsep(line, iter); 2619| 180| } 2620| 90| if (np != 2) { ------------------ | Branch (2620:7): [True: 0, False: 90] ------------------ 2621| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", ln); 2622| 0| return false; 2623| 0| } 2624| 90| return true; 2625| 90|} _Z11parse_arrayRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERS5_RNS_6vectorI6w_charNS3_ISA_EEEEii: 2631| 14| int ln) { 2632| 14| if (!parse_string(line, out, ln)) ------------------ | Branch (2632:7): [True: 0, False: 14] ------------------ 2633| 0| return false; 2634| 14| if (utf8) { ------------------ | Branch (2634:7): [True: 8, False: 6] ------------------ 2635| 8| u8_u16(out_utf16, out); 2636| 8| std::sort(out_utf16.begin(), out_utf16.end()); 2637| 8| } 2638| 14| return true; 2639| 14|} csutil.cxx:_ZL17warn_missing_contRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS_11__wrap_iterIPKcEE: 154| 721k|static void warn_missing_cont(const std::string& src, std::string::const_iterator p) { 155| | HUNSPELL_WARNING(stderr, 156| 721k| "UTF-8 encoding error. Missing continuation byte in " 157| 721k| "%ld. character position:\n%s\n", 158| 721k| static_cast(std::distance(src.begin(), p)), 159| 721k| src.c_str()); 160| 721k|} csutil.cxx:_ZN12_GLOBAL__N_19is_any_ofC2ERKNSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEE: 245| 2.51M| explicit is_any_of(const std::string& in) : chars(in) {} csutil.cxx:_ZNK12_GLOBAL__N_19is_any_ofclEc: 247| 28.5M| bool operator()(char c) const { return chars.find(c) != std::string::npos; } csutil.cxx:_ZL19drop_repeated_linesRNSt3__16vectorINS_12basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS4_IS6_EEEE: 303| 1.34k|static void drop_repeated_lines(std::vector& lines) { 304| 1.34k| std::unordered_set seen; 305| 1.34k| auto firstrepeat = std::remove_if(lines.begin(), lines.end(), 306| 1.34k| [&seen](const std::string& line) { return !seen.insert(line).second; }); 307| 1.34k| lines.erase(firstrepeat, lines.end()); 308| 1.34k|} csutil.cxx:_ZZL19drop_repeated_linesRNSt3__16vectorINS_12basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS4_IS6_EEEEENK3$_0clERKS6_: 306| 1.74k| [&seen](const std::string& line) { return !seen.insert(line).second; }); csutil.cxx:_ZN12_GLOBAL__N_16cupperEPK7cs_infoi: 520| 135M|unsigned char cupper(const struct cs_info* csconv, int nIndex) { 521| 135M| assert(nIndex >= 0 && nIndex <= 255); ------------------ | Branch (521:3): [True: 135M, False: 0] | Branch (521:3): [True: 135M, False: 0] | Branch (521:3): [True: 135M, False: 0] ------------------ 522| 135M| return csconv[nIndex].cupper; 523| 135M|} csutil.cxx:_ZN12_GLOBAL__N_16clowerEPK7cs_infoi: 525| 152M|unsigned char clower(const struct cs_info* csconv, int nIndex) { 526| 152M| assert(nIndex >= 0 && nIndex <= 255); ------------------ | Branch (526:3): [True: 152M, False: 0] | Branch (526:3): [True: 152M, False: 0] | Branch (526:3): [True: 152M, False: 0] ------------------ 527| 152M| return csconv[nIndex].clower; 528| 152M|} csutil.cxx:_ZL36toAsciiLowerAndRemoveNonAlphanumericPKcPc: 2278| 1.80k| char* pBuf) { 2279| 16.3k| while (*pName) { ------------------ | Branch (2279:10): [True: 14.5k, False: 1.80k] ------------------ 2280| | /* A-Z */ 2281| 14.5k| if ((*pName >= 0x41) && (*pName <= 0x5A)) { ------------------ | Branch (2281:9): [True: 5.42k, False: 9.13k] | Branch (2281:29): [True: 294, False: 5.13k] ------------------ 2282| 294| *pBuf = (*pName) + 0x20; /* toAsciiLower */ 2283| 294| pBuf++; 2284| 294| } 2285| | /* a-z, 0-9 */ 2286| 14.2k| else if (((*pName >= 0x61) && (*pName <= 0x7A)) || ------------------ | Branch (2286:15): [True: 5.13k, False: 9.13k] | Branch (2286:35): [True: 5.13k, False: 0] ------------------ 2287| 14.1k| ((*pName >= 0x30) && (*pName <= 0x39))) { ------------------ | Branch (2287:15): [True: 9.04k, False: 98] | Branch (2287:35): [True: 9.04k, False: 0] ------------------ 2288| 14.1k| *pBuf = *pName; 2289| 14.1k| pBuf++; 2290| 14.1k| } 2291| | 2292| 14.5k| pName++; 2293| 14.5k| } 2294| | 2295| 1.80k| *pBuf = '\0'; 2296| 1.80k|} csutil.cxx:_ZN12_GLOBAL__N_15ccaseEPK7cs_infoi: 530| 128M|unsigned char ccase(const struct cs_info* csconv, int nIndex) { 531| 128M| assert(nIndex >= 0 && nIndex <= 255); ------------------ | Branch (531:3): [True: 128M, False: 0] | Branch (531:3): [True: 128M, False: 0] | Branch (531:3): [True: 128M, False: 0] ------------------ 532| 128M| return csconv[nIndex].ccase; 533| 128M|} csutil.cxx:_ZZ24remove_ignored_chars_utfRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKNS_6vectorI6w_charNS3_IS8_EEEEENK3$_0clES8_: 2578| 6.44M| [&ignored_chars](w_char wc) { 2579| 6.44M| return !std::binary_search(ignored_chars.begin(), ignored_chars.end(), wc); 2580| 6.44M| }); _Z12is_utf8_contc: 143| 63.0M|inline bool is_utf8_cont(char c) { 144| 63.0M| return (static_cast(c) & 0xc0) == 0x80; 145| 63.0M|} _Z9utf8_nextRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEm: 148| 23.0k|inline size_t utf8_next(const std::string& s, size_t pos) { 149| 23.0k| if (pos < s.size()) { ------------------ | Branch (149:7): [True: 23.0k, False: 0] ------------------ 150| 23.0k| ++pos; 151| 27.2k| while (pos < s.size() && is_utf8_cont(s[pos])) ------------------ | Branch (151:12): [True: 25.0k, False: 2.19k] | Branch (151:30): [True: 4.23k, False: 20.8k] ------------------ 152| 4.23k| ++pos; 153| 23.0k| } 154| 23.0k| return pos; 155| 23.0k|} _Z20has_no_ignored_charsRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEES7_: 294| 879| const std::string& ignored_chars) { 295| 879| return std::all_of(ignored_chars.begin(), ignored_chars.end(), 296| 879| [&word](char ic) { return word.find(ic) == std::string::npos; }); 297| 879|} _Z11HENTRY_DATAP6hentry: 300| 1.38M|inline char* HENTRY_DATA(struct hentry* h) { 301| 1.38M| char* ret; 302| 1.38M| if (!(h->var & H_OPT)) ------------------ | | 47| 1.38M|#define H_OPT (1 << 0) // is there optional morphological data? ------------------ | Branch (302:7): [True: 1.38M, False: 1.78k] ------------------ 303| 1.38M| ret = nullptr; 304| 1.78k| else if (h->var & H_OPT_ALIASM) ------------------ | | 48| 1.78k|#define H_OPT_ALIASM (1 << 1) // using alias compression? ------------------ | Branch (304:12): [True: 0, False: 1.78k] ------------------ 305| 0| ret = get_stored_pointer(HENTRY_WORD(h) + h->blen + 1); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 306| 1.78k| else 307| 1.78k| ret = HENTRY_WORD(h) + h->blen + 1; ------------------ | | 54| 1.78k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 308| 1.38M| return ret; 309| 1.38M|} _Z11HENTRY_FINDP6hentryPKc: 336| 1.74k|inline char* HENTRY_FIND(struct hentry* h, const char* p) { 337| 1.74k| char* data = HENTRY_DATA(h); 338| 1.74k| return data ? strstr(data, p) : nullptr; ------------------ | Branch (338:10): [True: 4, False: 1.73k] ------------------ 339| 1.74k|} _ZZ20has_no_ignored_charsRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEES7_ENKUlcE_clEc: 296| 6.84k| [&word](char ic) { return word.find(ic) == std::string::npos; }); _ZN7FileMgrC2EPKcS1_: 84| 114| : hin(nullptr) 85| 114| , linenum(0) { 86| 114| in[0] = '\0'; 87| | 88| 114| if (!file || !strlen(file)) ------------------ | Branch (88:7): [True: 0, False: 114] | Branch (88:16): [True: 0, False: 114] ------------------ 89| 0| return; 90| 114| myopen(fin, file, std::ios_base::in); 91| 114| if (!fin.is_open()) { ------------------ | Branch (91:7): [True: 0, False: 114] ------------------ 92| | // check hzipped file 93| 0| std::string st(file); 94| 0| st.append(HZIP_EXTENSION); ------------------ | | 51| 0|#define HZIP_EXTENSION ".hz" ------------------ 95| 0| hin = new Hunzip(st.c_str(), key); 96| 0| } 97| 114| if (!fin.is_open() && !hin->is_open()) ------------------ | Branch (97:7): [True: 0, False: 114] | Branch (97:25): [True: 0, False: 0] ------------------ 98| 0| fail(MSG_OPEN, file); ------------------ | | 53| 0|#define MSG_OPEN "error: %s: cannot open\n" ------------------ 99| 114|} _ZN7FileMgrD2Ev: 101| 114|FileMgr::~FileMgr() { 102| 114| delete hin; 103| 114|} _ZN7FileMgr7getlineERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 105| 2.10k|bool FileMgr::getline(std::string& dest) { 106| 2.10k| bool ret = false; 107| 2.10k| ++linenum; 108| 2.10k| if (fin.is_open()) { ------------------ | Branch (108:7): [True: 2.10k, False: 0] ------------------ 109| | // a line longer than the buffer ends the read the same way the end of the 110| | // file does 111| 2.10k| fin.getline(in, sizeof(in)); 112| 2.10k| ret = !fin.fail(); 113| 2.10k| if (ret) ------------------ | Branch (113:9): [True: 1.99k, False: 112] ------------------ 114| 1.99k| dest.assign(in); 115| 2.10k| } else if (hin && hin->is_open()) { ------------------ | Branch (115:14): [True: 0, False: 0] | Branch (115:21): [True: 0, False: 0] ------------------ 116| 0| ret = hin->getline(dest); 117| 0| } 118| 2.10k| if (!ret) { ------------------ | Branch (118:7): [True: 112, False: 1.99k] ------------------ 119| 112| --linenum; 120| 112| } 121| 2.10k| return ret; 122| 2.10k|} _ZN7FileMgr10getlinenumEv: 124| 164|int FileMgr::getlinenum() { 125| 164| return linenum; 126| 164|} _ZN7HashMgrC2EPKcS1_S1_: 93| 38| : flag_mode(FLAG_CHAR) 94| 38| , complexprefixes(0) 95| 38| , utf8(0) 96| 38| , forbiddenword(FORBIDDENWORD) // forbidden word signing flag ------------------ | | 127| 38|#define FORBIDDENWORD 65510 ------------------ 97| 38| , langnum(0) 98| 38| , csconv(nullptr) { 99| 38| load_config(apath, key); 100| 38| if (!csconv) ------------------ | Branch (100:7): [True: 38, False: 0] ------------------ 101| 38| csconv = get_current_cs(SPELL_ENCODING); ------------------ | | 99| 38|#define SPELL_ENCODING "ISO8859-1" ------------------ 102| 38| int ec = load_tables(tpath, key); 103| 38| if (ec) { ------------------ | Branch (103:7): [True: 0, False: 38] ------------------ 104| | /* error condition - what should we do here */ 105| 0| fprintf(stderr, "Hash Manager Error : %d\n", ec); 106| 0| free_table(); 107| | //keep table size to 1 to fix possible division with zero 108| 0| tableptr.resize(1, nullptr); 109| 0| } 110| 38|} _ZN7HashMgr13release_flagsEPtb: 112| 718|void HashMgr::release_flags(unsigned short* astr, bool owned) { 113| 718| if (owned) ------------------ | Branch (113:7): [True: 447, False: 271] ------------------ 114| 447| delete[] astr; 115| 718|} _ZNK7HashMgr6lookupEPKcm: 154| 539M|struct hentry* HashMgr::lookup(const char* word, size_t len) const { 155| 539M| struct hentry* dp = tableptr[hash(word, len)]; 156| 539M| if (!dp) ------------------ | Branch (156:7): [True: 480M, False: 59.4M] ------------------ 157| 480M| return nullptr; 158| 123M| for (; dp != nullptr; dp = dp->next) { ------------------ | Branch (158:10): [True: 67.0M, False: 56.2M] ------------------ 159| 67.0M| if (strcmp(word, dp->word) == 0) ------------------ | Branch (159:9): [True: 3.18M, False: 63.8M] ------------------ 160| 3.18M| return dp; 161| 67.0M| } 162| 56.2M| return nullptr; 163| 59.4M|} _ZN7HashMgr8add_wordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiPtiPS7_bib: 173| 8.58k| bool own_aff) { 174| | 175| 8.58k| if (al > std::numeric_limits::max()) { ------------------ | Branch (175:7): [True: 0, False: 8.58k] ------------------ 176| 0| HUNSPELL_WARNING(stderr, "error: affix len %d is over max limit\n", al); 177| 0| release_flags(aff, own_aff); 178| 0| return 1; 179| 0| } 180| | 181| 8.58k| const std::string* word = &in_word; 182| 8.58k| const std::string* desc = in_desc; 183| | 184| 8.58k| std::string* word_copy = nullptr; 185| 8.58k| std::string* desc_copy = nullptr; 186| 8.58k| if ((!ignorechars.empty() && !has_no_ignored_chars(in_word, ignorechars)) || complexprefixes) { ------------------ | Branch (186:8): [True: 875, False: 7.71k] | Branch (186:32): [True: 206, False: 669] | Branch (186:80): [True: 523, False: 7.85k] ------------------ 187| 729| word_copy = new std::string(in_word); 188| | 189| 729| if (!ignorechars.empty()) { ------------------ | Branch (189:9): [True: 206, False: 523] ------------------ 190| 206| if (utf8) { ------------------ | Branch (190:11): [True: 52, False: 154] ------------------ 191| 52| wcl = remove_ignored_chars_utf(*word_copy, ignorechars_utf16); 192| 154| } else { 193| 154| remove_ignored_chars(*word_copy, ignorechars); 194| 154| } 195| 206| } 196| | 197| 729| if (complexprefixes) { ------------------ | Branch (197:9): [True: 523, False: 206] ------------------ 198| 523| if (utf8) ------------------ | Branch (198:11): [True: 0, False: 523] ------------------ 199| 0| wcl = reverseword_utf(*word_copy); 200| 523| else 201| 523| reverseword(*word_copy); 202| | 203| 523| if (in_desc && aliasm.empty()) { ------------------ | Branch (203:11): [True: 0, False: 523] | Branch (203:22): [True: 0, False: 0] ------------------ 204| 0| desc_copy = new std::string(*in_desc); 205| | 206| 0| if (complexprefixes) { ------------------ | Branch (206:13): [True: 0, False: 0] ------------------ 207| 0| if (utf8) ------------------ | Branch (207:15): [True: 0, False: 0] ------------------ 208| 0| reverseword_utf(*desc_copy); 209| 0| else 210| 0| reverseword(*desc_copy); 211| 0| } 212| 0| desc = desc_copy; 213| 0| } 214| 523| } 215| | 216| 729| word = word_copy; 217| 729| } 218| | 219| | // limit of hp->blen 220| 8.58k| if (word->size() > std::numeric_limits::max()) { ------------------ | Branch (220:7): [True: 0, False: 8.58k] ------------------ 221| 0| HUNSPELL_WARNING(stderr, "error: word len %ld is over max limit\n", word->size()); 222| 0| delete desc_copy; 223| 0| delete word_copy; 224| 0| release_flags(aff, own_aff); 225| 0| return 1; 226| 0| } 227| | 228| 8.58k| bool upcasehomonym = false; 229| 8.58k| int descl = desc ? (!aliasm.empty() ? sizeof(char*) : desc->size() + 1) : 0; ------------------ | Branch (229:15): [True: 4, False: 8.58k] | Branch (229:23): [True: 0, False: 4] ------------------ 230| | // variable-length hash record with word and optional fields 231| 8.58k| auto hp = 232| 8.58k| (struct hentry*)arena_alloc(sizeof(struct hentry) + word->size() + descl, 233| 8.58k| alignof(struct hentry)); 234| 8.58k| if (!hp) { ------------------ | Branch (234:7): [True: 0, False: 8.58k] ------------------ 235| 0| delete desc_copy; 236| 0| delete word_copy; 237| 0| release_flags(aff, own_aff); 238| 0| return 1; 239| 0| } 240| | 241| 8.58k| char* hpw = hp->word; 242| 8.58k| memcpy(hpw, word->data(), word->size()); 243| 8.58k| hpw[word->size()] = 0; 244| | 245| 8.58k| int i = hash(hpw, word->size()); 246| | 247| 8.58k| hp->blen = (unsigned short)word->size(); 248| 8.58k| hp->clen = (unsigned short)wcl; 249| 8.58k| hp->alen = (short)al; 250| 8.58k| hp->astr = aff; 251| 8.58k| hp->next = nullptr; 252| 8.58k| hp->next_homonym = nullptr; 253| 8.58k| hp->var = (captype == INITCAP) ? H_OPT_INITCAP : 0; ------------------ | | 93| 8.58k|#define INITCAP 1 ------------------ hp->var = (captype == INITCAP) ? H_OPT_INITCAP : 0; ------------------ | | 50| 5.01k|#define H_OPT_INITCAP (1 << 3) // is dictionary word capitalized? ------------------ | Branch (253:13): [True: 5.01k, False: 3.56k] ------------------ 254| 8.58k| if (own_aff) ------------------ | Branch (254:7): [True: 5.84k, False: 2.74k] ------------------ 255| 5.84k| hp->var |= H_OPT_OWNFLAGS; ------------------ | | 51| 5.84k|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 256| | 257| | // store the description string or its pointer 258| 8.58k| if (desc) { ------------------ | Branch (258:7): [True: 4, False: 8.58k] ------------------ 259| 4| hp->var |= H_OPT; ------------------ | | 47| 4|#define H_OPT (1 << 0) // is there optional morphological data? ------------------ 260| 4| if (!aliasm.empty()) { ------------------ | Branch (260:9): [True: 0, False: 4] ------------------ 261| 0| hp->var |= H_OPT_ALIASM; ------------------ | | 48| 0|#define H_OPT_ALIASM (1 << 1) // using alias compression? ------------------ 262| 0| store_pointer(hpw + word->size() + 1, get_aliasm(atoi(desc->c_str()))); 263| 4| } else { 264| 4| strcpy(hpw + word->size() + 1, desc->c_str()); 265| 4| } 266| 4| if (HENTRY_FIND(hp, MORPH_PHON)) { ------------------ | | 114| 4|#define MORPH_PHON "ph:" ------------------ | Branch (266:9): [True: 2, False: 2] ------------------ 267| 2| hp->var |= H_OPT_PHON; ------------------ | | 49| 2|#define H_OPT_PHON (1 << 2) // is there ph: field in the morphological data? ------------------ 268| | // store ph: fields (pronounciation, misspellings, old orthography etc.) 269| | // of a morphological description in reptable to use in REP replacements. 270| 2| size_t predicted = tableptr.size() / MORPH_PHON_RATIO; ------------------ | | 90| 2|#define MORPH_PHON_RATIO 500 ------------------ 271| 2| if (reptable.capacity() < predicted) ------------------ | Branch (271:11): [True: 2, False: 0] ------------------ 272| 2| reptable.reserve(predicted); 273| 2| std::string fields = HENTRY_DATA(hp); 274| 2| std::string::const_iterator iter = fields.begin(), start_piece = mystrsep(fields, iter); 275| 4| while (start_piece != fields.end()) { ------------------ | Branch (275:14): [True: 2, False: 2] ------------------ 276| 2| if (std::string(start_piece, iter).find(MORPH_PHON) == 0) { ------------------ | | 114| 2|#define MORPH_PHON "ph:" ------------------ | Branch (276:13): [True: 2, False: 0] ------------------ 277| 2| std::string ph = std::string(start_piece, iter).substr(sizeof MORPH_PHON - 1); ------------------ | | 114| 2|#define MORPH_PHON "ph:" ------------------ 278| 2| if (!ph.empty()) { ------------------ | Branch (278:15): [True: 2, False: 0] ------------------ 279| 2| std::vector w; 280| 2| size_t strippatt; 281| 2| std::string wordpart; 282| | // dictionary based REP replacement, separated by "->" 283| | // for example "pretty ph:prity ph:priti->pretti" to handle 284| | // both prity -> pretty and pritier -> prettiest suggestions. 285| 2| if (((strippatt = ph.find("->")) != std::string::npos) && ------------------ | Branch (285:17): [True: 0, False: 2] ------------------ 286| 0| (strippatt > 0) && (strippatt < ph.size() - 2)) { ------------------ | Branch (286:21): [True: 0, False: 0] | Branch (286:40): [True: 0, False: 0] ------------------ 287| 0| wordpart = ph.substr(strippatt + 2); 288| 0| ph.erase(ph.begin() + strippatt, ph.end()); 289| 0| } else 290| 2| wordpart = in_word; 291| | // when the ph: field ends with the character *, 292| | // strip last character of the pattern and the replacement 293| | // to match in REP suggestions also at character changes, 294| | // for example, "pretty ph:prity*" results "prit->prett" 295| | // REP replacement instead of "prity->pretty", to get 296| | // prity->pretty and pritiest->prettiest suggestions. 297| 2| if (ph.at(ph.size()-1) == '*') { ------------------ | Branch (297:17): [True: 0, False: 2] ------------------ 298| 0| strippatt = 1; 299| 0| size_t stripword = 0; 300| 0| if (utf8) { ------------------ | Branch (300:19): [True: 0, False: 0] ------------------ 301| 0| while ((strippatt < ph.size()) && ------------------ | Branch (301:24): [True: 0, False: 0] ------------------ 302| 0| is_utf8_cont(ph.at(ph.size()-strippatt-1))) ------------------ | Branch (302:19): [True: 0, False: 0] ------------------ 303| 0| ++strippatt; 304| 0| while ((stripword < wordpart.size()) && ------------------ | Branch (304:24): [True: 0, False: 0] ------------------ 305| 0| is_utf8_cont(wordpart.at(wordpart.size()-stripword-1))) ------------------ | Branch (305:19): [True: 0, False: 0] ------------------ 306| 0| ++stripword; 307| 0| } 308| 0| ++strippatt; 309| 0| ++stripword; 310| 0| if ((ph.size() > strippatt) && (wordpart.size() > stripword)) { ------------------ | Branch (310:19): [True: 0, False: 0] | Branch (310:46): [True: 0, False: 0] ------------------ 311| 0| ph.erase(ph.size()-strippatt, strippatt); 312| 0| wordpart.erase(wordpart.size()-stripword, stripword); 313| 0| } 314| 0| } 315| | // capitalize lowercase pattern for capitalized words to support 316| | // good suggestions also for capitalized misspellings, eg. 317| | // Wednesday ph:wendsay 318| | // results wendsay -> Wednesday and Wendsay -> Wednesday, too. 319| 2| if (captype == INITCAP) { ------------------ | | 93| 2|#define INITCAP 1 ------------------ | Branch (319:17): [True: 0, False: 2] ------------------ 320| 0| std::string ph_capitalized; 321| 0| if (utf8) { ------------------ | Branch (321:19): [True: 0, False: 0] ------------------ 322| 0| u8_u16(w, ph); 323| 0| if (get_captype_utf8(w, langnum) == NOCAP) { ------------------ | | 92| 0|#define NOCAP 0 ------------------ | Branch (323:21): [True: 0, False: 0] ------------------ 324| 0| mkinitcap_utf(w, langnum); 325| 0| u16_u8(ph_capitalized, w); 326| 0| } 327| 0| } else if (get_captype(ph, csconv) == NOCAP) ------------------ | | 92| 0|#define NOCAP 0 ------------------ | Branch (327:26): [True: 0, False: 0] ------------------ 328| 0| mkinitcap(ph_capitalized, csconv); 329| | 330| 0| if (!ph_capitalized.empty()) { ------------------ | Branch (330:19): [True: 0, False: 0] ------------------ 331| | // add also lowercase word in the case of German or 332| | // Hungarian to support lowercase suggestions lowercased by 333| | // compound word generation or derivational suffixes 334| | // (for example by adjectival suffix "-i" of geographical 335| | // names in Hungarian: 336| | // Massachusetts ph:messzecsuzec 337| | // messzecsuzeci -> massachusettsi (adjective) 338| | // For lowercasing by conditional PFX rules, see 339| | // tests/germancompounding test example or the 340| | // Hungarian dictionary.) 341| 0| if (langnum == LANG_de || langnum == LANG_hu) { ------------------ | Branch (341:21): [True: 0, False: 0] | Branch (341:43): [True: 0, False: 0] ------------------ 342| 0| std::string wordpart_lower(wordpart); 343| 0| if (utf8) { ------------------ | Branch (343:23): [True: 0, False: 0] ------------------ 344| 0| u8_u16(w, wordpart_lower); 345| 0| mkallsmall_utf(w, langnum); 346| 0| u16_u8(wordpart_lower, w); 347| 0| } else { 348| 0| mkallsmall(wordpart_lower, csconv); 349| 0| } 350| 0| reptable.emplace_back(); 351| 0| reptable.back().pattern.assign(ph); 352| 0| reptable.back().outstrings[0].assign(wordpart_lower); 353| 0| } 354| 0| reptable.emplace_back(); 355| 0| reptable.back().pattern.assign(ph_capitalized); 356| 0| reptable.back().outstrings[0].assign(wordpart); 357| 0| } 358| 0| } 359| 2| reptable.emplace_back(); 360| 2| reptable.back().pattern.assign(ph); 361| 2| reptable.back().outstrings[0].assign(wordpart); 362| 2| } 363| 2| } 364| 2| start_piece = mystrsep(fields, iter); 365| 2| } 366| 2| } 367| 4| } 368| | 369| 8.58k| struct hentry* dp = tableptr[i]; 370| 8.58k| if (!dp) { ------------------ | Branch (370:7): [True: 6.22k, False: 2.36k] ------------------ 371| 6.22k| tableptr[i] = hp; 372| 6.22k| delete desc_copy; 373| 6.22k| delete word_copy; 374| 6.22k| return 0; 375| 6.22k| } 376| 2.95k| while (dp->next != nullptr) { ------------------ | Branch (376:10): [True: 606, False: 2.34k] ------------------ 377| 606| if ((!dp->next_homonym) && (strcmp(hp->word, dp->word) == 0)) { ------------------ | Branch (377:9): [True: 564, False: 42] | Branch (377:32): [True: 26, False: 538] ------------------ 378| | // remove hidden onlyupcase homonym 379| 26| if (!onlyupcase) { ------------------ | Branch (379:11): [True: 14, False: 12] ------------------ 380| 14| if ((dp->astr) && TESTAFF(dp->astr, ONLYUPCASEFLAG, dp->alen)) { ------------------ | | 102| 8|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 8, False: 0] | | ------------------ ------------------ | Branch (380:13): [True: 8, False: 6] | Branch (380:13): [True: 8, False: 6] ------------------ 381| 8| release_flags(dp->astr, dp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 8|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 382| 8| dp->astr = hp->astr; 383| 8| dp->alen = hp->alen; 384| 8| dp->var &= ~H_OPT_OWNFLAGS; ------------------ | | 51| 8|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 385| 8| dp->var |= (hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 8|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 386| 8| arena_free(hp); 387| 8| delete desc_copy; 388| 8| delete word_copy; 389| 8| return 0; 390| 8| } else if (!dp->astr && dp->alen == 0 && ------------------ | Branch (390:20): [True: 6, False: 0] | Branch (390:33): [True: 6, False: 0] ------------------ 391| 6| !hp->astr && hp->alen == 0) { ------------------ | Branch (391:20): [True: 6, False: 0] | Branch (391:33): [True: 6, False: 0] ------------------ 392| | // word already exists with no flags, skip duplicate 393| 6| release_flags(hp->astr, hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 6|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 394| 6| arena_free(hp); 395| 6| delete desc_copy; 396| 6| delete word_copy; 397| 6| return 0; 398| 6| } else { 399| 0| dp->next_homonym = hp; 400| 0| } 401| 14| } else { 402| 12| upcasehomonym = true; 403| 12| } 404| 26| } 405| 592| dp = dp->next; 406| 592| } 407| 2.34k| if (strcmp(hp->word, dp->word) == 0) { ------------------ | Branch (407:7): [True: 710, False: 1.63k] ------------------ 408| | // remove hidden onlyupcase homonym 409| 710| if (!onlyupcase) { ------------------ | Branch (409:9): [True: 489, False: 221] ------------------ 410| 489| if ((dp->astr) && TESTAFF(dp->astr, ONLYUPCASEFLAG, dp->alen)) { ------------------ | | 102| 48|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 48, False: 0] | | ------------------ ------------------ | Branch (410:11): [True: 48, False: 441] | Branch (410:11): [True: 48, False: 441] ------------------ 411| 48| release_flags(dp->astr, dp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 48|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 412| 48| dp->astr = hp->astr; 413| 48| dp->alen = hp->alen; 414| 48| dp->var &= ~H_OPT_OWNFLAGS; ------------------ | | 51| 48|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 415| 48| dp->var |= (hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 48|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 416| 48| arena_free(hp); 417| 48| delete desc_copy; 418| 48| delete word_copy; 419| 48| return 0; 420| 441| } else if (!dp->astr && dp->alen == 0 && ------------------ | Branch (420:18): [True: 441, False: 0] | Branch (420:31): [True: 441, False: 0] ------------------ 421| 441| !hp->astr && hp->alen == 0) { ------------------ | Branch (421:18): [True: 423, False: 18] | Branch (421:31): [True: 423, False: 0] ------------------ 422| | // word already exists with no flags, skip duplicate 423| 423| release_flags(hp->astr, hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 423|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 424| 423| arena_free(hp); 425| 423| delete desc_copy; 426| 423| delete word_copy; 427| 423| return 0; 428| 423| } else { 429| 18| dp->next_homonym = hp; 430| 18| } 431| 489| } else { 432| 221| upcasehomonym = true; 433| 221| } 434| 710| } 435| 1.87k| if (!upcasehomonym) { ------------------ | Branch (435:7): [True: 1.64k, False: 233] ------------------ 436| 1.64k| dp->next = hp; 437| 1.64k| } else { 438| | // remove hidden onlyupcase homonym 439| 233| release_flags(hp->astr, hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 233|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 440| 233| arena_free(hp); 441| 233| } 442| | 443| 1.87k| delete desc_copy; 444| 1.87k| delete word_copy; 445| 1.87k| return 0; 446| 2.34k|} _ZN7HashMgr27add_hidden_capitalized_wordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiPtiPS7_i: 453| 6.00k| int captype) { 454| 6.00k| if (flags == nullptr) ------------------ | Branch (454:7): [True: 5.88k, False: 118] ------------------ 455| 5.88k| flagslen = 0; 456| | 457| | // add inner capitalized forms to handle the following allcap forms: 458| | // Mixed caps: OpenOffice.org -> OPENOFFICE.ORG 459| | // Allcaps with suffixes: CIA's -> CIA'S 460| 6.00k| if (((captype == HUHCAP) || (captype == HUHINITCAP) || ------------------ | | 95| 6.00k|#define HUHCAP 3 ------------------ if (((captype == HUHCAP) || (captype == HUHINITCAP) || ------------------ | | 96| 5.59k|#define HUHINITCAP 4 ------------------ | Branch (460:8): [True: 411, False: 5.59k] | Branch (460:31): [True: 2.17k, False: 3.42k] ------------------ 461| 3.42k| ((captype == ALLCAP) && (flagslen != 0))) && ------------------ | | 94| 3.42k|#define ALLCAP 2 ------------------ | Branch (461:9): [True: 275, False: 3.14k] | Branch (461:32): [True: 0, False: 275] ------------------ 462| 2.58k| !((flagslen != 0) && TESTAFF(flags, forbiddenword, flagslen))) { ------------------ | | 102| 36|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 36] | | ------------------ ------------------ | Branch (462:9): [True: 36, False: 2.54k] ------------------ 463| 2.58k| auto flags2 = (unsigned short*)arena_alloc((flagslen + 1) * sizeof(unsigned short), 464| 2.58k| alignof(unsigned short)); 465| 2.58k| flags2[flagslen] = ONLYUPCASEFLAG; ------------------ | | 128| 2.58k|#define ONLYUPCASEFLAG 65511 ------------------ 466| 2.58k| if (flagslen) { ------------------ | Branch (466:9): [True: 36, False: 2.54k] ------------------ 467| 36| memcpy(flags2, flags, flagslen * sizeof(unsigned short)); 468| 36| std::sort(flags2, flags2 + flagslen + 1); 469| 36| } 470| 2.58k| if (utf8) { ------------------ | Branch (470:9): [True: 423, False: 2.16k] ------------------ 471| 423| std::string st; 472| 423| std::vector w; 473| 423| u8_u16(w, word); 474| 423| mkallsmall_utf(w, langnum); 475| 423| mkinitcap_utf(w, langnum); 476| 423| u16_u8(st, w); 477| 423| return add_word(st, wcl, flags2, flagslen + 1, dp, true, INITCAP, false); ------------------ | | 93| 423|#define INITCAP 1 ------------------ 478| 2.16k| } else { 479| 2.16k| std::string new_word(word); 480| 2.16k| mkallsmall(new_word, csconv); 481| 2.16k| mkinitcap(new_word, csconv); 482| 2.16k| int ret = add_word(new_word, wcl, flags2, flagslen + 1, dp, true, INITCAP, false); ------------------ | | 93| 2.16k|#define INITCAP 1 ------------------ 483| 2.16k| return ret; 484| 2.16k| } 485| 2.58k| } 486| 3.42k| return 0; 487| 6.00k|} _ZN7HashMgr20get_clen_and_captypeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiRNS0_6vectorI6w_charNS4_ISB_EEEE: 490| 6.00k|int HashMgr::get_clen_and_captype(const std::string& word, int* captype, std::vector &workbuf) { 491| 6.00k| int len; 492| 6.00k| if (utf8) { ------------------ | Branch (492:7): [True: 2.85k, False: 3.15k] ------------------ 493| 2.85k| len = u8_u16(workbuf, word); 494| 2.85k| *captype = get_captype_utf8(workbuf, langnum); 495| 3.15k| } else { 496| 3.15k| len = word.size(); 497| 3.15k| *captype = get_captype(word, csconv); 498| 3.15k| } 499| 6.00k| return len; 500| 6.00k|} _ZN7HashMgr20get_clen_and_captypeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPi: 502| 5.84k|int HashMgr::get_clen_and_captype(const std::string& word, int* captype) { 503| 5.84k| std::vector workbuf; 504| 5.84k| return get_clen_and_captype(word, captype, workbuf); 505| 5.84k|} _ZN7HashMgr21remove_forbidden_flagERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 529| 8.18k|void HashMgr::remove_forbidden_flag(const std::string& word) { 530| 8.18k| struct hentry* dp = lookup(word.c_str(), word.size()); 531| 8.18k| if (!dp) ------------------ | Branch (531:7): [True: 7.60k, False: 574] ------------------ 532| 7.60k| return; 533| 1.18k| while (dp) { ------------------ | Branch (533:10): [True: 610, False: 574] ------------------ 534| 610| if (dp->astr && TESTAFF(dp->astr, forbiddenword, dp->alen)) { ------------------ | | 102| 53|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 53] | | ------------------ ------------------ | Branch (534:9): [True: 53, False: 557] ------------------ 535| 0| if (dp->alen == 1) { ------------------ | Branch (535:11): [True: 0, False: 0] ------------------ 536| 0| release_flags(dp->astr, dp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 537| 0| dp->astr = nullptr; 538| 0| dp->alen = 0; 539| 0| dp->var &= ~H_OPT_OWNFLAGS; ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 540| 0| } else { 541| 0| auto newflags = new unsigned short[dp->alen - 1]; 542| 0| int j = 0; 543| 0| for (int i = 0; i < dp->alen; i++) { ------------------ | Branch (543:25): [True: 0, False: 0] ------------------ 544| 0| if (dp->astr[i] != forbiddenword) ------------------ | Branch (544:15): [True: 0, False: 0] ------------------ 545| 0| newflags[j++] = dp->astr[i]; 546| 0| } 547| 0| release_flags(dp->astr, dp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 548| 0| dp->astr = newflags; 549| 0| dp->alen = (short)j; 550| 0| dp->var |= H_OPT_OWNFLAGS; ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 551| 0| } 552| 0| } 553| 610| dp = dp->next_homonym; 554| 610| } 555| 574|} _ZN7HashMgr3addERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 558| 5.80k|int HashMgr::add(const std::string& word) { 559| 5.80k| remove_forbidden_flag(word); 560| 5.80k| int captype, al = 0; 561| 5.80k| unsigned short* flags = nullptr; 562| 5.80k| int wcl = get_clen_and_captype(word, &captype); 563| 5.80k| if (add_word(word, wcl, flags, al, nullptr, false, captype, true)) ------------------ | Branch (563:7): [True: 0, False: 5.80k] ------------------ 564| 0| return 1; 565| 5.80k| return add_hidden_capitalized_word(word, wcl, flags, al, nullptr, captype); 566| 5.80k|} _ZN7HashMgr14add_with_affixERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 579| 2.37k|int HashMgr::add_with_affix(const std::string& word, const std::string& example) { 580| | // detect captype and modify word length for UTF-8 encoding 581| 2.37k| struct hentry* dp = lookup(example.c_str(), example.size()); 582| 2.37k| remove_forbidden_flag(word); 583| 2.37k| if (dp && dp->astr) { ------------------ | Branch (583:7): [True: 128, False: 2.24k] | Branch (583:13): [True: 36, False: 92] ------------------ 584| 36| int captype; 585| 36| int wcl = get_clen_and_captype(word, &captype); 586| 36| auto flags = new unsigned short[dp->alen]; 587| 36| memcpy(flags, dp->astr, dp->alen * sizeof(unsigned short)); 588| 36| if (add_word(word, wcl, flags, dp->alen, nullptr, false, captype, true)) ------------------ | Branch (588:9): [True: 0, False: 36] ------------------ 589| 0| return 1; 590| 36| return add_hidden_capitalized_word(word, wcl, flags, dp->alen, nullptr, captype); 591| 36| } 592| 2.33k| return 1; 593| 2.37k|} _ZNK7HashMgr14walk_hashtableERiP6hentry: 597| 1.98M|struct hentry* HashMgr::walk_hashtable(int& col, struct hentry* hp) const { 598| 1.98M| if (hp && hp->next != nullptr) ------------------ | Branch (598:7): [True: 1.92M, False: 61.4k] | Branch (598:13): [True: 205k, False: 1.71M] ------------------ 599| 205k| return hp->next; 600| 62.0M| for (col++; col < (int)tableptr.size(); ++col) { ------------------ | Branch (600:15): [True: 62.0M, False: 61.4k] ------------------ 601| 62.0M| if (tableptr[col]) ------------------ | Branch (601:9): [True: 1.71M, False: 60.2M] ------------------ 602| 1.71M| return tableptr[col]; 603| 62.0M| } 604| | // null at end and reset to start 605| 61.4k| col = -1; 606| 61.4k| return nullptr; 607| 1.77M|} _ZN7HashMgr11load_tablesEPKcS1_: 610| 38|int HashMgr::load_tables(const char* tpath, const char* key) { 611| | // open dictionary file 612| 38| FileMgr* dict = new FileMgr(tpath, key); 613| | 614| | // first read the first line of file to get hash table size 615| 38| std::string ts; 616| 38| if (!dict->getline(ts)) { ------------------ | Branch (616:7): [True: 0, False: 38] ------------------ 617| 0| fprintf(stderr, "error: empty dic file %s\n", tpath); 618| 0| delete dict; 619| 0| return 2; 620| 0| } 621| 38| mychomp(ts); 622| | 623| | /* remove byte order mark */ 624| 38| if (ts.compare(0, 3, "\xEF\xBB\xBF", 3) == 0) { ------------------ | Branch (624:7): [True: 0, False: 38] ------------------ 625| 0| ts.erase(0, 3); 626| 0| } 627| | 628| 38| int tablesize = atoi(ts.c_str()); 629| | 630| 38| const int nExtra = 5 + USERWORD; ------------------ | | 57| 38|#define USERWORD 1000 ------------------ 631| |#if !defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 632| | // covers full-form uncompressed dictionaries (~7M for uk_UA expanded) 633| | const int max_allowed = 10000000; 634| |#else 635| 38| const int max_allowed = (10000 - 1 - nExtra) / int(sizeof(struct hentry*)); 636| 38|#endif 637| | 638| 38| if (tablesize <= 0 || tablesize >= max_allowed) { ------------------ | Branch (638:7): [True: 0, False: 38] | Branch (638:25): [True: 0, False: 38] ------------------ 639| 0| fprintf(stderr, 640| 0| "error: %s: line 1: missing or bad word count in the dic file\n", 641| 0| tpath); 642| 0| delete dict; 643| 0| return 4; 644| 0| } 645| 38| tablesize += nExtra; 646| 38| if ((tablesize & 1) == 0) ------------------ | Branch (646:7): [True: 18, False: 20] ------------------ 647| 18| tablesize++; 648| | 649| | // allocate the hash table 650| 38| tableptr.resize(tablesize, nullptr); 651| | 652| | // loop through all words on much list and add to hash 653| | // table and create word and affix strings 654| | 655| 38| std::vector workbuf; 656| | 657| 38| int nLineCount(0); 658| 198| while (dict->getline(ts)) { ------------------ | Branch (658:10): [True: 160, False: 38] ------------------ 659| 160| ++nLineCount; 660| 160|#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION 661| | // limit words loaded to avoid O(n^2) hash chain walk timeout 662| 160| if (nLineCount >= tablesize) ------------------ | Branch (662:9): [True: 0, False: 160] ------------------ 663| 0| break; 664| 160|#endif 665| 160| mychomp(ts); 666| | // split each line into word and morphological description 667| 160| size_t dp_pos = 0; 668| 160| while ((dp_pos = ts.find(':', dp_pos)) != std::string::npos) { ------------------ | Branch (668:12): [True: 4, False: 156] ------------------ 669| 4| if ((dp_pos > 3) && (ts[dp_pos - 3] == ' ' || ts[dp_pos - 3] == '\t')) { ------------------ | Branch (669:11): [True: 4, False: 0] | Branch (669:28): [True: 0, False: 4] | Branch (669:53): [True: 4, False: 0] ------------------ 670| 4| for (dp_pos -= 3; dp_pos > 0 && (ts[dp_pos-1] == ' ' || ts[dp_pos-1] == '\t'); --dp_pos) ------------------ | Branch (670:27): [True: 4, False: 0] | Branch (670:42): [True: 0, False: 4] | Branch (670:65): [True: 0, False: 4] ------------------ 671| 0| ; 672| 4| if (dp_pos == 0) { // missing word ------------------ | Branch (672:13): [True: 0, False: 4] ------------------ 673| 0| dp_pos = std::string::npos; 674| 4| } else { 675| 4| ++dp_pos; 676| 4| } 677| 4| break; 678| 4| } 679| 0| ++dp_pos; 680| 0| } 681| | 682| | // tabulator is the old morphological field separator 683| 160| size_t dp2_pos = ts.find('\t'); 684| 160| if (dp2_pos != std::string::npos && (dp_pos == std::string::npos || dp2_pos < dp_pos)) { ------------------ | Branch (684:9): [True: 4, False: 156] | Branch (684:42): [True: 0, False: 4] | Branch (684:73): [True: 4, False: 0] ------------------ 685| 4| dp_pos = dp2_pos + 1; 686| 4| } 687| | 688| 160| std::string dp; 689| 160| if (dp_pos != std::string::npos) { ------------------ | Branch (689:9): [True: 4, False: 156] ------------------ 690| 4| dp.assign(ts.substr(dp_pos)); 691| 4| ts.resize(dp_pos - 1); 692| 4| } 693| | 694| | // split each line into word and affix char strings 695| | // "\/" signs slash in words (not affix separator) 696| | // "/" at beginning of the line is word character (not affix separator) 697| 160| size_t ap_pos = ts.find('/'); 698| 160| while (ap_pos != std::string::npos) { ------------------ | Branch (698:12): [True: 82, False: 78] ------------------ 699| 82| if (ap_pos == 0) { ------------------ | Branch (699:11): [True: 0, False: 82] ------------------ 700| 0| ++ap_pos; 701| 0| ap_pos = ts.find('/', ap_pos); 702| 0| continue; 703| 82| } else if (ts[ap_pos - 1] != '\\') ------------------ | Branch (703:18): [True: 82, False: 0] ------------------ 704| 82| break; 705| | // replace "\/" with "/" 706| 0| ts.erase(ap_pos - 1, 1); 707| 0| ap_pos = ts.find('/', ap_pos); 708| 0| } 709| | 710| 160| unsigned short* flags; 711| 160| int al; 712| 160| if (ap_pos != std::string::npos && ap_pos != ts.size()) { ------------------ | Branch (712:9): [True: 82, False: 78] | Branch (712:40): [True: 82, False: 0] ------------------ 713| 82| std::string ap(ts.substr(ap_pos + 1)); 714| 82| ts.resize(ap_pos); 715| 82| if (!aliasf.empty()) { ------------------ | Branch (715:11): [True: 2, False: 80] ------------------ 716| 2| int index = atoi(ap.c_str()); 717| 2| al = get_aliasf(index, &flags, dict); 718| 2| if (!al) { ------------------ | Branch (718:13): [True: 0, False: 2] ------------------ 719| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad flag vector alias\n", 720| 0| dict->getlinenum()); 721| 0| } 722| 80| } else { 723| 80| al = decode_flags(&flags, ap, dict, /* arena = */ true); 724| 80| if (al == -1) { ------------------ | Branch (724:13): [True: 0, False: 80] ------------------ 725| 0| HUNSPELL_WARNING(stderr, "Can't allocate memory.\n"); 726| 0| delete dict; 727| 0| return 6; 728| 0| } 729| 80| std::sort(flags, flags + al); 730| 80| } 731| 82| } else { 732| 78| al = 0; 733| 78| flags = nullptr; 734| 78| } 735| | 736| 160| int captype; 737| 160| int wcl = get_clen_and_captype(ts, &captype, workbuf); 738| 160| const std::string* dp_str = dp.empty() ? nullptr : &dp; ------------------ | Branch (738:33): [True: 156, False: 4] ------------------ 739| | // add the word and its index plus its capitalized form optionally 740| | // flags are arena-allocated, so own_aff must be false 741| 160| bool own = false; 742| 160| if (add_word(ts, wcl, flags, al, dp_str, false, captype, own) || ------------------ | Branch (742:9): [True: 0, False: 160] ------------------ 743| 160| add_hidden_capitalized_word(ts, wcl, flags, al, dp_str, captype)) { ------------------ | Branch (743:9): [True: 0, False: 160] ------------------ 744| 0| delete dict; 745| 0| return 5; 746| 0| } 747| 160| } 748| | 749| 38| int ret(0); 750| | 751| | // reject ludicrous tablesizes 752| 38| if (tablesize > 8192 + nExtra && tablesize > nLineCount * 10 + nExtra) { ------------------ | Branch (752:7): [True: 0, False: 38] | Branch (752:36): [True: 0, False: 0] ------------------ 753| 0| HUNSPELL_WARNING(stderr, ".dic initial approximate word count line value of %d is too large for %d lines\n", tablesize, nLineCount); 754| 0| ret = 3; 755| 0| } 756| | 757| 38| delete dict; 758| 38| return ret; 759| 38|} _ZNK7HashMgr4hashEPKcm: 763| 539M|int HashMgr::hash(const char* word, size_t len) const { 764| 539M| unsigned long hv = 0; 765| 539M| size_t i = 0; 766| 2.66G| while (i < 4 && i < len) ------------------ | Branch (766:10): [True: 2.15G, False: 513M] | Branch (766:19): [True: 2.12G, False: 25.5M] ------------------ 767| 2.12G| hv = (hv << 8) | word[i++]; 768| 10.7G| while (i < len) { ------------------ | Branch (768:10): [True: 10.1G, False: 539M] ------------------ 769| 10.1G| ROTATE(hv, ROTATE_LEN); ------------------ | | 44| 10.1G| (v) = ((v) << (q)) | (((v) >> (32 - q)) & ((1 << (q)) - 1)); ------------------ 770| 10.1G| hv ^= word[i++]; 771| 10.1G| } 772| 539M| return (unsigned long)hv % tableptr.size(); 773| 539M|} _ZNK7HashMgr12decode_flagsEPPtRKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEP7FileMgr: 775| 16|int HashMgr::decode_flags(unsigned short** result, const std::string& flags, FileMgr* af) const { 776| 16| return decode_flags(result, flags, af, /* arena = */ false); 777| 16|} _ZNK7HashMgr12decode_flagsEPPtRKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEP7FileMgrb: 779| 100|int HashMgr::decode_flags(unsigned short** result, const std::string& flags, FileMgr* af, bool use_arena) const { 780| 100| auto alloc = [&](int n) -> unsigned short* { 781| 100| return use_arena ? (unsigned short*)this->arena_alloc(n * sizeof(unsigned short), 782| 100| alignof(unsigned short)) 783| 100| : new unsigned short[n]; 784| 100| }; 785| 100| int len; 786| 100| if (flags.empty()) { ------------------ | Branch (786:7): [True: 0, False: 100] ------------------ 787| 0| *result = nullptr; 788| 0| return 0; 789| 0| } 790| 100| switch (flag_mode) { 791| 0| case FLAG_LONG: { // two-character flags (1x2yZz -> 1x 2y Zz) ------------------ | Branch (791:5): [True: 0, False: 100] ------------------ 792| 0| len = flags.size(); 793| 0| if ((len & 1) == 1 && af != nullptr) ------------------ | Branch (793:11): [True: 0, False: 0] | Branch (793:29): [True: 0, False: 0] ------------------ 794| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad flagvector\n", 795| 0| af->getlinenum()); 796| 0| len >>= 1; 797| 0| *result = alloc(len); 798| 0| for (int i = 0; i < len; i++) { ------------------ | Branch (798:23): [True: 0, False: 0] ------------------ 799| 0| unsigned short flag = ((unsigned short)((unsigned char)flags[i << 1]) << 8) | 800| 0| ((unsigned short)((unsigned char)flags[(i << 1) | 1])); 801| | 802| 0| (*result)[i] = flag; 803| 0| } 804| 0| break; 805| 0| } 806| 0| case FLAG_NUM: { // decimal numbers separated by comma (4521,23,233 -> 4521 ------------------ | Branch (806:5): [True: 0, False: 100] ------------------ 807| | // 23 233) 808| 0| len = int(1 + std::count_if(flags.begin(), flags.end(), [](char c) { return c == ','; })); 809| 0| *result = alloc(len); 810| 0| unsigned short* dest = *result; 811| 0| const char* src = flags.c_str(); 812| 0| for (size_t p = 0; p < flags.size(); ++p) { ------------------ | Branch (812:26): [True: 0, False: 0] ------------------ 813| 0| if (flags[p] == ',') { ------------------ | Branch (813:13): [True: 0, False: 0] ------------------ 814| 0| int i = atoi(src); 815| 0| if ((i > std::numeric_limits::max() || i < 0) && af != nullptr) { ------------------ | Branch (815:16): [True: 0, False: 0] | Branch (815:66): [True: 0, False: 0] | Branch (815:76): [True: 0, False: 0] ------------------ 816| 0| HUNSPELL_WARNING( 817| 0| stderr, "error: line %d: flag id %d is out of range\n", 818| 0| af->getlinenum(), i); 819| 0| i = 0; 820| 0| } 821| 0| *dest = (unsigned short)i; 822| 0| if (*dest == 0 && af != nullptr) ------------------ | Branch (822:15): [True: 0, False: 0] | Branch (822:29): [True: 0, False: 0] ------------------ 823| 0| HUNSPELL_WARNING(stderr, "error: line %d: 0 is wrong flag id\n", 824| 0| af->getlinenum()); 825| 0| src = flags.c_str() + p + 1; 826| 0| dest++; 827| 0| } 828| 0| } 829| 0| int i = atoi(src); 830| 0| if ((i > std::numeric_limits::max() || i < 0) && af) { ------------------ | Branch (830:12): [True: 0, False: 0] | Branch (830:62): [True: 0, False: 0] | Branch (830:72): [True: 0, False: 0] ------------------ 831| 0| HUNSPELL_WARNING(stderr, 832| 0| "error: line %d: flag id %d is out of range\n", 833| 0| af->getlinenum(), i); 834| 0| i = 0; 835| 0| } 836| 0| *dest = (unsigned short)i; 837| 0| if (*dest == 0 && af) ------------------ | Branch (837:11): [True: 0, False: 0] | Branch (837:25): [True: 0, False: 0] ------------------ 838| 0| HUNSPELL_WARNING(stderr, "error: line %d: 0 is wrong flag id\n", 839| 0| af->getlinenum()); 840| 0| break; 841| 0| } 842| 0| case FLAG_UNI: { // UTF-8 characters ------------------ | Branch (842:5): [True: 0, False: 100] ------------------ 843| 0| std::vector w; 844| 0| u8_u16(w, flags); 845| 0| len = w.size(); 846| 0| *result = alloc(len); 847| 0|#if defined(_WIN32) || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__==__ORDER_LITTLE_ENDIAN__)) || defined(__LITTLE_ENDIAN__) 848| 0| memcpy(*result, w.data(), len * sizeof(unsigned short)); 849| |#else 850| | unsigned short* dest = *result; 851| | for (const w_char wc : w) { 852| | *dest = (unsigned short)wc; 853| | dest++; 854| | } 855| |#endif 856| 0| break; 857| 0| } 858| 100| default: { // Ispell's one-character flags (erfg -> e r f g) ------------------ | Branch (858:5): [True: 100, False: 0] ------------------ 859| 100| len = flags.size(); 860| 100| *result = alloc(len); 861| 100| unsigned short* dest = *result; 862| 118| for (const char flag : flags) { ------------------ | Branch (862:28): [True: 118, False: 100] ------------------ 863| 118| *dest = (unsigned char)flag; 864| 118| dest++; 865| 118| } 866| 100| } 867| 100| } 868| 100| return len; 869| 100|} _ZNK7HashMgr11decode_flagERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 945| 92|unsigned short HashMgr::decode_flag(const std::string& f) const { 946| 92| unsigned short s = 0; 947| 92| int i; 948| 92| switch (flag_mode) { 949| 0| case FLAG_LONG: ------------------ | Branch (949:5): [True: 0, False: 92] ------------------ 950| 0| if (f.size() >= 2) ------------------ | Branch (950:11): [True: 0, False: 0] ------------------ 951| 0| s = ((unsigned short)((unsigned char)f[0]) << 8) | ((unsigned short)((unsigned char)f[1])); 952| 0| break; 953| 0| case FLAG_NUM: ------------------ | Branch (953:5): [True: 0, False: 92] ------------------ 954| 0| i = atoi(f.c_str()); 955| 0| if (i > std::numeric_limits::max() || i < 0) { ------------------ | Branch (955:11): [True: 0, False: 0] | Branch (955:61): [True: 0, False: 0] ------------------ 956| 0| HUNSPELL_WARNING(stderr, "error: flag id %d is out of range\n", i); 957| 0| i = 0; 958| 0| } 959| 0| s = (unsigned short)i; 960| 0| break; 961| 0| case FLAG_UNI: { ------------------ | Branch (961:5): [True: 0, False: 92] ------------------ 962| 0| std::vector w; 963| 0| u8_u16(w, f); 964| 0| if (!w.empty()) ------------------ | Branch (964:11): [True: 0, False: 0] ------------------ 965| 0| s = (unsigned short)w[0]; 966| 0| break; 967| 0| } 968| 92| default: ------------------ | Branch (968:5): [True: 92, False: 0] ------------------ 969| 92| if (!f.empty()) ------------------ | Branch (969:11): [True: 92, False: 0] ------------------ 970| 92| s = (unsigned char)f[0]; 971| 92| } 972| 92| if (s == 0) ------------------ | Branch (972:7): [True: 0, False: 92] ------------------ 973| 0| HUNSPELL_WARNING(stderr, "error: 0 is wrong flag id\n"); 974| 92| return s; 975| 92|} _ZN7HashMgr11load_configEPKcS1_: 1011| 38|int HashMgr::load_config(const char* affpath, const char* key) { 1012| 38| int firstline = 1; 1013| | 1014| | // open the affix file 1015| 38| FileMgr* afflst = new FileMgr(affpath, key); 1016| | 1017| | // read in each line ignoring any that do not 1018| | // start with a known line type indicator 1019| | 1020| 38| std::string line; 1021| 922| while (afflst->getline(line)) { ------------------ | Branch (1021:10): [True: 886, False: 36] ------------------ 1022| 886| mychomp(line); 1023| | 1024| | /* remove byte order mark */ 1025| 886| if (firstline) { ------------------ | Branch (1025:9): [True: 38, False: 848] ------------------ 1026| 38| firstline = 0; 1027| 38| if (line.compare(0, 3, "\xEF\xBB\xBF", 3) == 0) { ------------------ | Branch (1027:11): [True: 0, False: 38] ------------------ 1028| 0| line.erase(0, 3); 1029| 0| } 1030| 38| } 1031| | 1032| | /* parse in the try string */ 1033| 886| if ((line.compare(0, 4, "FLAG", 4) == 0) && line.size() > 4 && isspace(line[4])) { ------------------ | Branch (1033:9): [True: 0, False: 886] | Branch (1033:49): [True: 0, False: 0] | Branch (1033:68): [True: 0, False: 0] ------------------ 1034| 0| if (flag_mode != FLAG_CHAR) { ------------------ | Branch (1034:11): [True: 0, False: 0] ------------------ 1035| 0| HUNSPELL_WARNING(stderr, 1036| 0| "error: line %d: multiple definitions of the FLAG " 1037| 0| "affix file parameter\n", 1038| 0| afflst->getlinenum()); 1039| 0| } 1040| 0| if (line.find("long") != std::string::npos) ------------------ | Branch (1040:11): [True: 0, False: 0] ------------------ 1041| 0| flag_mode = FLAG_LONG; 1042| 0| if (line.find("num") != std::string::npos) ------------------ | Branch (1042:11): [True: 0, False: 0] ------------------ 1043| 0| flag_mode = FLAG_NUM; 1044| 0| if (line.find("UTF-8") != std::string::npos) ------------------ | Branch (1044:11): [True: 0, False: 0] ------------------ 1045| 0| flag_mode = FLAG_UNI; 1046| 0| if (flag_mode == FLAG_CHAR) { ------------------ | Branch (1046:11): [True: 0, False: 0] ------------------ 1047| 0| HUNSPELL_WARNING( 1048| 0| stderr, 1049| 0| "error: line %d: FLAG needs `num', `long' or `UTF-8' parameter\n", 1050| 0| afflst->getlinenum()); 1051| 0| } 1052| 0| } 1053| | 1054| 886| if (line.compare(0, 13, "FORBIDDENWORD", 13) == 0) { ------------------ | Branch (1054:9): [True: 2, False: 884] ------------------ 1055| 2| std::string st; 1056| 2| if (!parse_string(line, st, afflst->getlinenum())) { ------------------ | Branch (1056:11): [True: 0, False: 2] ------------------ 1057| 0| delete afflst; 1058| 0| return 1; 1059| 0| } 1060| 2| forbiddenword = decode_flag(st); 1061| 2| } 1062| | 1063| 886| if (line.compare(0, 3, "SET", 3) == 0) { ------------------ | Branch (1063:9): [True: 18, False: 868] ------------------ 1064| 18| if (!parse_string(line, enc, afflst->getlinenum())) { ------------------ | Branch (1064:11): [True: 0, False: 18] ------------------ 1065| 0| delete afflst; 1066| 0| return 1; 1067| 0| } 1068| 18| if (enc == "UTF-8") { ------------------ | Branch (1068:11): [True: 18, False: 0] ------------------ 1069| 18| utf8 = 1; 1070| 18| } else 1071| 0| csconv = get_current_cs(enc); 1072| 18| } 1073| | 1074| 886| if (line.compare(0, 4, "LANG", 4) == 0) { ------------------ | Branch (1074:9): [True: 2, False: 884] ------------------ 1075| 2| if (!parse_string(line, lang, afflst->getlinenum())) { ------------------ | Branch (1075:11): [True: 0, False: 2] ------------------ 1076| 0| delete afflst; 1077| 0| return 1; 1078| 0| } 1079| 2| langnum = get_lang_num(lang); 1080| 2| } 1081| | 1082| | /* parse in the ignored characters (for example, Arabic optional diacritics 1083| | * characters */ 1084| 886| if (line.compare(0, 6, "IGNORE", 6) == 0) { ------------------ | Branch (1084:9): [True: 4, False: 882] ------------------ 1085| 4| if (!parse_array(line, ignorechars, ignorechars_utf16, ------------------ | Branch (1085:11): [True: 0, False: 4] ------------------ 1086| 4| utf8, afflst->getlinenum())) { 1087| 0| delete afflst; 1088| 0| return 1; 1089| 0| } 1090| 4| } 1091| | 1092| 886| if ((line.compare(0, 2, "AF", 2) == 0) && line.size() > 2 && isspace(line[2])) { ------------------ | Branch (1092:9): [True: 2, False: 884] | Branch (1092:47): [True: 2, False: 0] | Branch (1092:66): [True: 2, False: 0] ------------------ 1093| 2| if (!parse_aliasf(line, afflst)) { ------------------ | Branch (1093:11): [True: 0, False: 2] ------------------ 1094| 0| delete afflst; 1095| 0| return 1; 1096| 0| } 1097| 2| } 1098| | 1099| 886| if ((line.compare(0, 2, "AM", 2) == 0) && line.size() > 2 && isspace(line[2])) { ------------------ | Branch (1099:9): [True: 0, False: 886] | Branch (1099:47): [True: 0, False: 0] | Branch (1099:66): [True: 0, False: 0] ------------------ 1100| 0| if (!parse_aliasm(line, afflst)) { ------------------ | Branch (1100:11): [True: 0, False: 0] ------------------ 1101| 0| delete afflst; 1102| 0| return 1; 1103| 0| } 1104| 0| } 1105| | 1106| 886| if (line.compare(0, 15, "COMPLEXPREFIXES", 15) == 0) ------------------ | Branch (1106:9): [True: 2, False: 884] ------------------ 1107| 2| complexprefixes = 1; 1108| | 1109| | /* parse in the typical fault correcting table */ 1110| 886| if (line.compare(0, 3, "REP", 3) == 0) { ------------------ | Branch (1110:9): [True: 6, False: 880] ------------------ 1111| 6| if (!parse_reptable(line, afflst)) { ------------------ | Branch (1111:11): [True: 0, False: 6] ------------------ 1112| 0| delete afflst; 1113| 0| return 1; 1114| 0| } 1115| 6| } 1116| | 1117| | // don't check the full affix file, yet 1118| 886| if (((line.compare(0, 3, "SFX", 3) == 0) || ------------------ | Branch (1118:10): [True: 42, False: 844] ------------------ 1119| 844| (line.compare(0, 3, "PFX", 3) == 0)) && ------------------ | Branch (1119:10): [True: 24, False: 820] ------------------ 1120| 66| line.size() > 3 && isspace(line[3]) && ------------------ | Branch (1120:13): [True: 66, False: 0] | Branch (1120:32): [True: 66, False: 0] ------------------ 1121| 66| !reptable.empty()) // (REP table is in the end of Afrikaans aff file) ------------------ | Branch (1121:13): [True: 2, False: 64] ------------------ 1122| 2| break; 1123| 886| } 1124| | 1125| 38| delete afflst; 1126| 38| return 0; 1127| 38|} _ZN7HashMgr12parse_aliasfERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 1130| 2|bool HashMgr::parse_aliasf(const std::string& line, FileMgr* af) { 1131| 2| if (!aliasf.empty()) { ------------------ | Branch (1131:7): [True: 0, False: 2] ------------------ 1132| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 1133| 0| af->getlinenum()); 1134| 0| return false; 1135| 0| } 1136| 2| int i = 0, np = 0, numaliasf = 0; 1137| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 1138| 6| while (start_piece != line.end()) { ------------------ | Branch (1138:10): [True: 4, False: 2] ------------------ 1139| 4| switch (i) { 1140| 2| case 0: { ------------------ | Branch (1140:7): [True: 2, False: 2] ------------------ 1141| 2| np++; 1142| 2| break; 1143| 0| } 1144| 2| case 1: { ------------------ | Branch (1144:7): [True: 2, False: 2] ------------------ 1145| 2| numaliasf = atoi(std::string(start_piece, iter).c_str()); 1146| 2| if (numaliasf < 1) { ------------------ | Branch (1146:13): [True: 0, False: 2] ------------------ 1147| 0| aliasf.clear(); 1148| 0| aliasflen.clear(); 1149| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 1150| 0| af->getlinenum()); 1151| 0| return false; 1152| 0| } 1153| 2| aliasf.reserve(std::min(numaliasf, 16384)); 1154| 2| aliasflen.reserve(std::min(numaliasf, 16384)); 1155| 2| np++; 1156| 2| break; 1157| 2| } 1158| 0| default: ------------------ | Branch (1158:7): [True: 0, False: 4] ------------------ 1159| 0| break; 1160| 4| } 1161| 4| ++i; 1162| 4| start_piece = mystrsep(line, iter); 1163| 4| } 1164| 2| if (np != 2) { ------------------ | Branch (1164:7): [True: 0, False: 2] ------------------ 1165| 0| aliasf.clear(); 1166| 0| aliasflen.clear(); 1167| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 1168| 0| af->getlinenum()); 1169| 0| return false; 1170| 0| } 1171| | 1172| | /* now parse the numaliasf lines to read in the remainder of the table */ 1173| 6| for (int j = 0; j < numaliasf; ++j) { ------------------ | Branch (1173:19): [True: 4, False: 2] ------------------ 1174| 4| std::string nl; 1175| 4| unsigned short* alias = nullptr; 1176| 4| unsigned aliaslen = 0; 1177| 4| i = 0; 1178| 4| if (af->getline(nl)) { ------------------ | Branch (1178:9): [True: 4, False: 0] ------------------ 1179| 4| mychomp(nl); 1180| 4| iter = nl.begin(); 1181| 4| start_piece = mystrsep(nl, iter); 1182| 4| bool errored = false; 1183| 12| while (!errored && start_piece != nl.end()) { ------------------ | Branch (1183:14): [True: 12, False: 0] | Branch (1183:14): [True: 8, False: 4] | Branch (1183:26): [True: 8, False: 4] ------------------ 1184| 8| switch (i) { 1185| 4| case 0: { ------------------ | Branch (1185:11): [True: 4, False: 4] ------------------ 1186| 4| if (nl.compare(start_piece - nl.begin(), 2, "AF", 2) != 0) { ------------------ | Branch (1186:17): [True: 0, False: 4] ------------------ 1187| 0| errored = true; 1188| 0| break; 1189| 0| } 1190| 4| break; 1191| 4| } 1192| 4| case 1: { ------------------ | Branch (1192:11): [True: 4, False: 4] ------------------ 1193| 4| std::string piece(start_piece, iter); 1194| 4| aliaslen = 1195| 4| (unsigned short)decode_flags(&alias, piece, af, /* arena = */ true); 1196| 4| std::sort(alias, alias + aliaslen); 1197| 4| break; 1198| 4| } 1199| 0| default: ------------------ | Branch (1199:11): [True: 0, False: 8] ------------------ 1200| 0| break; 1201| 8| } 1202| 8| ++i; 1203| 8| start_piece = mystrsep(nl, iter); 1204| 8| } 1205| 4| } 1206| 4| if (!alias) { ------------------ | Branch (1206:9): [True: 0, False: 4] ------------------ 1207| 0| for (int k = 0; k < j; ++k) { ------------------ | Branch (1207:23): [True: 0, False: 0] ------------------ 1208| 0| arena_free(aliasf[k]); 1209| 0| } 1210| 0| aliasf.clear(); 1211| 0| aliasflen.clear(); 1212| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 1213| 0| af->getlinenum()); 1214| 0| return false; 1215| 0| } 1216| | 1217| 4| aliasf.push_back(alias); 1218| 4| aliasflen.push_back(aliaslen); 1219| 4| } 1220| 2| return true; 1221| 2|} _ZNK7HashMgr9is_aliasfEv: 1223| 44|int HashMgr::is_aliasf() const { 1224| 44| return !aliasf.empty(); 1225| 44|} _ZNK7HashMgr10get_aliasfEiPPtP7FileMgr: 1227| 4|int HashMgr::get_aliasf(int index, unsigned short** fvec, FileMgr* af) const { 1228| 4| if (index > 0 && static_cast(index) <= aliasflen.size()) { ------------------ | Branch (1228:7): [True: 4, False: 0] | Branch (1228:20): [True: 4, False: 0] ------------------ 1229| 4| *fvec = aliasf[index - 1]; 1230| 4| return aliasflen[index - 1]; 1231| 4| } 1232| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad flag alias index: %d\n", 1233| 0| af->getlinenum(), index); 1234| 0| *fvec = nullptr; 1235| 0| return 0; 1236| 4|} _ZNK7HashMgr9is_aliasmEv: 1334| 32|int HashMgr::is_aliasm() const { 1335| 32| return !aliasm.empty(); 1336| 32|} _ZN7HashMgr14parse_reptableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 1346| 6|bool HashMgr::parse_reptable(const std::string& line, FileMgr* af) { 1347| 6| if (!reptable.empty()) { ------------------ | Branch (1347:7): [True: 0, False: 6] ------------------ 1348| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 1349| 0| af->getlinenum()); 1350| 0| return false; 1351| 0| } 1352| 6| int numrep = -1, i = 0, np = 0; 1353| 6| auto iter = line.begin(), start_piece = mystrsep(line, iter); 1354| 18| while (start_piece != line.end()) { ------------------ | Branch (1354:10): [True: 12, False: 6] ------------------ 1355| 12| switch (i) { 1356| 6| case 0: { ------------------ | Branch (1356:7): [True: 6, False: 6] ------------------ 1357| 6| np++; 1358| 6| break; 1359| 0| } 1360| 6| case 1: { ------------------ | Branch (1360:7): [True: 6, False: 6] ------------------ 1361| 6| numrep = atoi(std::string(start_piece, iter).c_str()); 1362| 6| if (numrep < 1) { ------------------ | Branch (1362:13): [True: 0, False: 6] ------------------ 1363| 0| HUNSPELL_WARNING(stderr, "error: line %d: incorrect entry number\n", 1364| 0| af->getlinenum()); 1365| 0| return false; 1366| 0| } 1367| 6| reptable.reserve(std::min(numrep, 16384)); 1368| 6| np++; 1369| 6| break; 1370| 6| } 1371| 0| default: ------------------ | Branch (1371:7): [True: 0, False: 12] ------------------ 1372| 0| break; 1373| 12| } 1374| 12| ++i; 1375| 12| start_piece = mystrsep(line, iter); 1376| 12| } 1377| 6| if (np != 2) { ------------------ | Branch (1377:7): [True: 0, False: 6] ------------------ 1378| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 1379| 0| af->getlinenum()); 1380| 0| return false; 1381| 0| } 1382| | 1383| | /* now parse the numrep lines to read in the remainder of the table */ 1384| 12| for (int j = 0; j < numrep; ++j) { ------------------ | Branch (1384:19): [True: 6, False: 6] ------------------ 1385| 6| std::string nl; 1386| 6| reptable.emplace_back(); 1387| 6| int type = 0; 1388| 6| if (af->getline(nl)) { ------------------ | Branch (1388:9): [True: 6, False: 0] ------------------ 1389| 6| mychomp(nl); 1390| 6| iter = nl.begin(); 1391| 6| i = 0; 1392| 6| start_piece = mystrsep(nl, iter); 1393| 6| bool errored = false; 1394| 24| while (!errored && start_piece != nl.end()) { ------------------ | Branch (1394:14): [True: 24, False: 0] | Branch (1394:14): [True: 18, False: 6] | Branch (1394:26): [True: 18, False: 6] ------------------ 1395| 18| switch (i) { 1396| 6| case 0: { ------------------ | Branch (1396:11): [True: 6, False: 12] ------------------ 1397| 6| if (nl.compare(start_piece - nl.begin(), 3, "REP", 3) != 0) { ------------------ | Branch (1397:17): [True: 0, False: 6] ------------------ 1398| 0| errored = true; 1399| 0| break; 1400| 0| } 1401| 6| break; 1402| 6| } 1403| 6| case 1: { ------------------ | Branch (1403:11): [True: 6, False: 12] ------------------ 1404| 6| if (*start_piece == '^') ------------------ | Branch (1404:17): [True: 0, False: 6] ------------------ 1405| 0| type = 1; 1406| 6| reptable.back().pattern.assign(start_piece + type, iter); 1407| 6| mystrrep(reptable.back().pattern, "_", " "); 1408| 6| if (!reptable.back().pattern.empty() && reptable.back().pattern[reptable.back().pattern.size() - 1] == '$') { ------------------ | Branch (1408:17): [True: 6, False: 0] | Branch (1408:53): [True: 0, False: 6] ------------------ 1409| 0| type += 2; 1410| 0| reptable.back().pattern.resize(reptable.back().pattern.size() - 1); 1411| 0| } 1412| 6| break; 1413| 6| } 1414| 6| case 2: { ------------------ | Branch (1414:11): [True: 6, False: 12] ------------------ 1415| 6| reptable.back().outstrings[type].assign(start_piece, iter); 1416| 6| mystrrep(reptable.back().outstrings[type], "_", " "); 1417| 6| break; 1418| 6| } 1419| 0| default: ------------------ | Branch (1419:11): [True: 0, False: 18] ------------------ 1420| 0| break; 1421| 18| } 1422| 18| ++i; 1423| 18| start_piece = mystrsep(nl, iter); 1424| 18| } 1425| 6| } 1426| 6| if (reptable.back().pattern.empty() || reptable.back().outstrings[type].empty()) { ------------------ | Branch (1426:9): [True: 0, False: 6] | Branch (1426:44): [True: 0, False: 6] ------------------ 1427| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 1428| 0| af->getlinenum()); 1429| 0| reptable.clear(); 1430| 0| return false; 1431| 0| } 1432| 6| } 1433| 6| return true; 1434| 6|} _ZNK7HashMgr12get_reptableEv: 1437| 380k|const std::vector& HashMgr::get_reptable() const { 1438| 380k| return reptable; 1439| 380k|} _ZNK7HashMgr11arena_allocEmm: 1441| 11.2k|void* HashMgr::arena_alloc(size_t num_bytes, size_t alignment) const { 1442| | // Fixed-size 64KB chunks: small enough to avoid significant waste on small 1443| | // dictionaries, large enough to amortize per-chunk malloc overhead on large 1444| | // ones. make_unique throws std::bad_alloc on OOM. 1445| 11.2k| static const size_t MIN_CHUNK_SIZE = 65536; 1446| 11.2k| static const size_t MAX_ALIGNMENT = alignof(max_align_t); 1447| | // Chunk sizes are rounded up to MAX_ALIGNMENT below; with this invariant, 1448| | // any alignment that divides MAX_ALIGNMENT keeps aligned_offset within bounds. 1449| 11.2k| assert(alignment > 0 && alignment <= MAX_ALIGNMENT); ------------------ | Branch (1449:3): [True: 11.2k, False: 0] | Branch (1449:3): [True: 11.2k, False: 0] | Branch (1449:3): [True: 11.2k, False: 0] ------------------ 1450| | // Pad the offset up to the requested alignment before placing this allocation. 1451| | // make_unique returns memory aligned for any scalar, so chunk-start is fine. 1452| 11.2k| size_t aligned_offset = (current_chunk_offset + alignment - 1) & ~(alignment - 1); 1453| 11.2k| if (arena.empty() || current_chunk_size - aligned_offset < num_bytes) { ------------------ | Branch (1453:7): [True: 38, False: 11.2k] | Branch (1453:24): [True: 57, False: 11.1k] ------------------ 1454| | // Round the new chunk's size up to a multiple of MAX_ALIGNMENT so that an 1455| | // oversized num_bytes (>= MIN_CHUNK_SIZE) cannot leave a non-aligned 1456| | // current_chunk_size that would later cause aligned_offset to overshoot. 1457| | // Allocate before mutating current_chunk_size so a throwing make_unique 1458| | // leaves the HashMgr in a consistent state. 1459| 95| size_t new_size = std::max(MIN_CHUNK_SIZE, num_bytes); 1460| 95| new_size = (new_size + MAX_ALIGNMENT - 1) & ~(MAX_ALIGNMENT - 1); 1461| 95| arena.push_back(std::make_unique(new_size)); 1462| 95| current_chunk_size = new_size; 1463| 95| aligned_offset = 0; 1464| 95| } 1465| | 1466| 11.2k| uint8_t* ptr = &arena.back()[aligned_offset]; 1467| 11.2k| current_chunk_offset = aligned_offset + num_bytes; 1468| 11.2k| ++outstanding_arena_allocations; 1469| 11.2k| return ptr; 1470| 11.2k|} _ZNK7HashMgr10arena_freeEPv: 1472| 718|void HashMgr::arena_free(void*) const { 1473| | // The arena vector owns all allocations and frees them in bulk at HashMgr 1474| | // destruction, so this is a no-op for the memory itself. The counter is a 1475| | // memory-safety check: more arena_free calls than arena_alloc calls would 1476| | // indicate a double-free or use-after-free in Hunspell. Abort hard rather 1477| | // than silently desynchronize tracking, even in release builds. 1478| 718| if (outstanding_arena_allocations == 0) { ------------------ | Branch (1478:7): [True: 0, False: 718] ------------------ 1479| 0| std::abort(); 1480| 0| } 1481| 718| --outstanding_arena_allocations; 1482| 718|} hashmgr.cxx:_ZZNK7HashMgr12decode_flagsEPPtRKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEP7FileMgrbENK3$_0clEi: 780| 100| auto alloc = [&](int n) -> unsigned short* { 781| 100| return use_arena ? (unsigned short*)this->arena_alloc(n * sizeof(unsigned short), ------------------ | Branch (781:12): [True: 84, False: 16] ------------------ 782| 84| alignof(unsigned short)) 783| 100| : new unsigned short[n]; 784| 100| }; _ZN12HunspellImplC2EPKcS1_S1_: 198| 38| : m_trace(std::make_unique(nullptr, nullptr)) 199| 38| , affixpath(affpath) 200| 38| , affixkey(key ? key : "") { ------------------ | Branch (200:14): [True: 0, False: 38] ------------------ 201| 38| csconv = nullptr; 202| 38| utf8 = 0; 203| 38| complexprefixes = 0; 204| | 205| | /* first set up the hash manager */ 206| 38| m_HMgrs.push_back(std::make_unique(dpath, affpath, key)); 207| | 208| | /* next set up the affix manager */ 209| | /* it needs access to the hash manager lookup methods */ 210| 38| pAMgr = std::make_unique(affpath, m_HMgrs, key); 211| | 212| | /* get the preferred try string and the dictionary */ 213| | /* encoding from the Affix Manager for that dictionary */ 214| 38| std::string try_string = pAMgr->get_try_string(); 215| 38| encoding = pAMgr->get_encoding(); 216| 38| langnum = pAMgr->get_langnum(); 217| 38| utf8 = pAMgr->get_utf8(); 218| 38| if (!utf8) ------------------ | Branch (218:7): [True: 20, False: 18] ------------------ 219| 20| csconv = get_current_cs(encoding); 220| 38| complexprefixes = pAMgr->get_complexprefixes(); 221| 38| wordbreak = pAMgr->get_breaktable(); 222| | 223| | /* and finally set up the suggestion manager */ 224| 38| pSMgr = std::make_unique(try_string, MAXSUGGESTION, pAMgr.get()); ------------------ | | 83| 38|#define MAXSUGGESTION 15 ------------------ 225| 38|} _ZN12HunspellImpl12clean_ignoreERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKS6_: 247| 31.8M| const std::string& src) { 248| 31.8M| dest.clear(); 249| 31.8M| dest.assign(src); 250| 31.8M| const char* ignoredchars = pAMgr ? pAMgr->get_ignore() : nullptr; ------------------ | Branch (250:30): [True: 31.8M, False: 0] ------------------ 251| 31.8M| if (ignoredchars != nullptr) { ------------------ | Branch (251:7): [True: 3.12M, False: 28.7M] ------------------ 252| 3.12M| if (utf8) { ------------------ | Branch (252:9): [True: 607k, False: 2.51M] ------------------ 253| 607k| const std::vector& ignoredchars_utf16 = 254| 607k| pAMgr->get_ignore_utf16(); 255| 607k| remove_ignored_chars_utf(dest, ignoredchars_utf16); 256| 2.51M| } else { 257| 2.51M| remove_ignored_chars(dest, ignoredchars); 258| 2.51M| } 259| 3.12M| } 260| 31.8M|} _ZN12HunspellImpl10cleanword2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEERKS6_PiPm: 274| 14.5M| size_t* pabbrev) { 275| 14.5M| dest.clear(); 276| 14.5M| dest_utf.clear(); 277| | 278| | // remove IGNORE characters from the string 279| 14.5M| std::string w2; 280| 14.5M| clean_ignore(w2, src); 281| | 282| 14.5M| const char* q = w2.c_str(); 283| 14.5M| int nl = (int)w2.size(); 284| | 285| | // first skip over any leading blanks 286| 14.6M| while (*q == ' ') { ------------------ | Branch (286:10): [True: 148k, False: 14.5M] ------------------ 287| 148k| ++q; 288| 148k| nl--; 289| 148k| } 290| | 291| | // now strip off any trailing periods (recording their presence) 292| 14.5M| *pabbrev = 0; 293| | 294| 16.3M| while ((nl > 0) && (*(q + nl - 1) == '.')) { ------------------ | Branch (294:10): [True: 16.1M, False: 240k] | Branch (294:22): [True: 1.82M, False: 14.2M] ------------------ 295| 1.82M| nl--; 296| 1.82M| (*pabbrev)++; 297| 1.82M| } 298| | 299| | // if no characters are left it can't be capitalized 300| 14.5M| if (nl <= 0) { ------------------ | Branch (300:7): [True: 240k, False: 14.2M] ------------------ 301| 240k| *pcaptype = NOCAP; ------------------ | | 92| 240k|#define NOCAP 0 ------------------ 302| 240k| return 0; 303| 240k| } 304| | 305| 14.2M| dest.append(q, nl); 306| 14.2M| nl = dest.size(); 307| 14.2M| if (utf8) { ------------------ | Branch (307:7): [True: 2.39M, False: 11.8M] ------------------ 308| 2.39M| u8_u16(dest_utf, dest); 309| 2.39M| *pcaptype = get_captype_utf8(dest_utf, langnum); 310| 11.8M| } else { 311| 11.8M| *pcaptype = get_captype(dest, csconv); 312| 11.8M| } 313| 14.2M| return nl; 314| 14.5M|} _ZN12HunspellImpl9cleanwordERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKS6_PiSA_: 319| 6.44k| int* pabbrev) { 320| 6.44k| dest.clear(); 321| 6.44k| const unsigned char* q = (const unsigned char*)src.c_str(); 322| 6.44k| int firstcap = 0, nl = (int)src.size(); 323| | 324| | // first skip over any leading blanks 325| 12.3k| while (*q == ' ') { ------------------ | Branch (325:10): [True: 5.85k, False: 6.44k] ------------------ 326| 5.85k| ++q; 327| 5.85k| nl--; 328| 5.85k| } 329| | 330| | // now strip off any trailing periods (recording their presence) 331| 6.44k| *pabbrev = 0; 332| | 333| 23.5k| while ((nl > 0) && (*(q + nl - 1) == '.')) { ------------------ | Branch (333:10): [True: 23.2k, False: 285] | Branch (333:22): [True: 17.0k, False: 6.16k] ------------------ 334| 17.0k| nl--; 335| 17.0k| (*pabbrev)++; 336| 17.0k| } 337| | 338| | // if no characters are left it can't be capitalized 339| 6.44k| if (nl <= 0) { ------------------ | Branch (339:7): [True: 285, False: 6.16k] ------------------ 340| 285| *pcaptype = NOCAP; ------------------ | | 92| 285|#define NOCAP 0 ------------------ 341| 285| return; 342| 285| } 343| | 344| | // now determine the capitalization type of the first nl letters 345| 6.16k| int ncap = 0; 346| 6.16k| int nneutral = 0; 347| 6.16k| int nc = 0; 348| | 349| 6.16k| if (!utf8) { ------------------ | Branch (349:7): [True: 3.26k, False: 2.90k] ------------------ 350| 589k| while (nl > 0) { ------------------ | Branch (350:12): [True: 585k, False: 3.26k] ------------------ 351| 585k| nc++; 352| 585k| if (csconv[(*q)].ccase) ------------------ | Branch (352:11): [True: 500k, False: 85.2k] ------------------ 353| 500k| ncap++; 354| 585k| if (csconv[(*q)].cupper == csconv[(*q)].clower) ------------------ | Branch (354:11): [True: 73.0k, False: 512k] ------------------ 355| 73.0k| nneutral++; 356| 585k| dest.push_back(*q++); 357| 585k| nl--; 358| 585k| } 359| | // remember to terminate the destination string 360| 3.26k| firstcap = csconv[static_cast(dest[0])].ccase; 361| 3.26k| } else { 362| 2.90k| std::vector t; 363| 2.90k| u8_u16(t, src); 364| 183k| for (auto& wc : t) { ------------------ | Branch (364:19): [True: 183k, False: 2.90k] ------------------ 365| 183k| const auto idx = (unsigned short)wc; 366| 183k| const auto low = unicodetolower(idx, langnum); 367| 183k| if (idx != low) ------------------ | Branch (367:11): [True: 123k, False: 59.6k] ------------------ 368| 123k| ncap++; 369| 183k| if (unicodetoupper(idx, langnum) == low) ------------------ | Branch (369:11): [True: 57.6k, False: 125k] ------------------ 370| 57.6k| nneutral++; 371| 183k| } 372| 2.90k| u16_u8(dest, t); 373| 2.90k| if (ncap) { ------------------ | Branch (373:9): [True: 1.71k, False: 1.18k] ------------------ 374| 1.71k| const auto idx = (unsigned short)t[0]; 375| 1.71k| firstcap = (idx != unicodetolower(idx, langnum)); 376| 1.71k| } 377| 2.90k| } 378| | 379| | // now finally set the captype 380| 6.16k| if (ncap == 0) { ------------------ | Branch (380:7): [True: 2.11k, False: 4.04k] ------------------ 381| 2.11k| *pcaptype = NOCAP; ------------------ | | 92| 2.11k|#define NOCAP 0 ------------------ 382| 4.04k| } else if ((ncap == 1) && firstcap) { ------------------ | Branch (382:14): [True: 2.17k, False: 1.87k] | Branch (382:29): [True: 1.84k, False: 329] ------------------ 383| 1.84k| *pcaptype = INITCAP; ------------------ | | 93| 1.84k|#define INITCAP 1 ------------------ 384| 2.20k| } else if ((ncap == nc) || ((ncap + nneutral) == nc)) { ------------------ | Branch (384:14): [True: 120, False: 2.08k] | Branch (384:30): [True: 250, False: 1.83k] ------------------ 385| 370| *pcaptype = ALLCAP; ------------------ | | 94| 370|#define ALLCAP 2 ------------------ 386| 1.83k| } else if ((ncap > 1) && firstcap) { ------------------ | Branch (386:14): [True: 1.57k, False: 259] | Branch (386:28): [True: 1.39k, False: 182] ------------------ 387| 1.39k| *pcaptype = HUHINITCAP; ------------------ | | 96| 1.39k|#define HUHINITCAP 4 ------------------ 388| 1.39k| } else { 389| 441| *pcaptype = HUHCAP; ------------------ | | 95| 441|#define HUHCAP 3 ------------------ 390| 441| } 391| 6.16k|} _ZN12HunspellImpl8mkallcapERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 393| 2.80k|void HunspellImpl::mkallcap(std::string& u8) { 394| 2.80k| if (utf8) { ------------------ | Branch (394:7): [True: 1.51k, False: 1.29k] ------------------ 395| 1.51k| std::vector u16; 396| 1.51k| u8_u16(u16, u8); 397| 1.51k| ::mkallcap_utf(u16, langnum); 398| 1.51k| u16_u8(u8, u16); 399| 1.51k| } else { 400| 1.29k| ::mkallcap(u8, csconv); 401| 1.29k| } 402| 2.80k|} _ZN12HunspellImpl11mkallsmall2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEE: 404| 1.92M|int HunspellImpl::mkallsmall2(std::string& u8, std::vector& u16) { 405| 1.92M| if (utf8) { ------------------ | Branch (405:7): [True: 350k, False: 1.57M] ------------------ 406| 350k| ::mkallsmall_utf(u16, langnum); 407| 350k| u16_u8(u8, u16); 408| 1.57M| } else { 409| 1.57M| ::mkallsmall(u8, csconv); 410| 1.57M| } 411| 1.92M| return u8.size(); 412| 1.92M|} _ZN12HunspellImpl11is_keepcaseEPK6hentry: 450| 20.5k|int HunspellImpl::is_keepcase(const hentry* rv) { 451| 20.5k| return pAMgr && rv->astr && pAMgr->get_keepcase() && ------------------ | Branch (451:10): [True: 20.5k, False: 0] | Branch (451:19): [True: 437, False: 20.0k] | Branch (451:31): [True: 41, False: 396] ------------------ 452| 41| TESTAFF(rv->astr, pAMgr->get_keepcase(), rv->alen); ------------------ | | 102| 20.5k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 31, False: 10] | | ------------------ ------------------ 453| 20.5k|} _ZN12HunspellImpl10insert_sugERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_: 456| 17.9k|void HunspellImpl::insert_sug(std::vector& slst, const std::string& word) { 457| 17.9k| slst.insert(slst.begin(), word); 458| 17.9k|} _ZN12HunspellImpl5spellERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEEPiPS6_NS0_6chrono10time_pointINSF_12steady_clockENSF_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 462| 15.1M| std::chrono::steady_clock::time_point suggest_start) { 463| | // something very broken if spell ends up calling itself with the same word 464| 15.1M| if (std::find(candidate_stack.begin(), candidate_stack.end(), word) != candidate_stack.end()) ------------------ | Branch (464:7): [True: 0, False: 15.1M] ------------------ 465| 0| return false; 466| | 467| 15.1M| if (candidate_stack.size() >= MAXBREAKDEPTH) ------------------ | | 87| 15.1M|#define MAXBREAKDEPTH 10 ------------------ | Branch (467:7): [True: 0, False: 15.1M] ------------------ 468| 0| return false; 469| | 470| 15.1M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 15.1M|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (470:7): [True: 0, False: 15.1M] ------------------ 471| 0| return false; 472| | 473| 15.1M| TraceCtx* t = active_trace(); 474| 15.1M| if (t) ------------------ | Branch (474:7): [True: 0, False: 15.1M] ------------------ 475| 0| trace(*t, "word \"%s\"", word.c_str()); 476| | // A word split on a BREAK pattern nests its parts a further level in. 477| 15.1M| TraceScope trace_depth(t); 478| | 479| 15.1M| candidate_stack.push_back(word); 480| 15.1M| bool r = spell_internal(word, candidate_stack, info, root, suggest_start); 481| 15.1M| candidate_stack.pop_back(); 482| | 483| 15.1M| if (t) ------------------ | Branch (483:7): [True: 0, False: 15.1M] ------------------ 484| 0| trace(*t, "result %s", r ? "correct" : "incorrect"); ------------------ | Branch (484:28): [True: 0, False: 0] ------------------ 485| | 486| 15.1M| if (r && root) { ------------------ | Branch (486:7): [True: 2.64M, False: 12.5M] | Branch (486:12): [True: 0, False: 2.64M] ------------------ 487| | // output conversion 488| 0| RepList* rl = (pAMgr) ? pAMgr->get_oconvtable() : nullptr; ------------------ | Branch (488:19): [True: 0, False: 0] ------------------ 489| 0| if (rl) { ------------------ | Branch (489:9): [True: 0, False: 0] ------------------ 490| 0| std::string wspace; 491| 0| if (rl->conv(*root, wspace)) { ------------------ | Branch (491:11): [True: 0, False: 0] ------------------ 492| 0| *root = std::move(wspace); 493| 0| } 494| 0| } 495| 0| } 496| 15.1M| return r; 497| 15.1M|} _ZN12HunspellImpl14spell_internalERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEEPiPS6_NS0_6chrono10time_pointINSF_12steady_clockENSF_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 501| 15.1M| std::chrono::steady_clock::time_point suggest_start) { 502| 15.1M| struct hentry* rv = nullptr; 503| | 504| 15.1M| int info2 = 0; 505| 15.1M| if (!info) ------------------ | Branch (505:7): [True: 15.1M, False: 148] ------------------ 506| 15.1M| info = &info2; 507| 148| else 508| 148| *info = 0; 509| | 510| | // Hunspell supports XML input of the simplified API (see manual) 511| 15.1M| if (word == SPELL_XML) ------------------ | | 80| 15.1M|#define SPELL_XML "" ------------------ | Branch (511:7): [True: 727k, False: 14.4M] ------------------ 512| 727k| return true; 513| 14.4M| if (utf8) { ------------------ | Branch (513:7): [True: 2.42M, False: 12.0M] ------------------ 514| 2.42M| if (word.size() >= MAXWORDUTF8LEN) ------------------ | | 87| 2.42M|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 2.42M|#define MAXWORDLEN 100 | | ------------------ ------------------ | Branch (514:9): [True: 4.00k, False: 2.41M] ------------------ 515| 4.00k| return false; 516| 12.0M| } else { 517| 12.0M| if (word.size() >= MAXWORDLEN) ------------------ | | 90| 12.0M|#define MAXWORDLEN 100 ------------------ | Branch (517:9): [True: 7.01k, False: 12.0M] ------------------ 518| 7.01k| return false; 519| 12.0M| } 520| 14.4M| int captype = NOCAP; ------------------ | | 92| 14.4M|#define NOCAP 0 ------------------ 521| 14.4M| size_t abbv = 0; 522| 14.4M| size_t wl = 0; 523| | 524| 14.4M| std::string scw; 525| 14.4M| std::vector sunicw; 526| | 527| | // input conversion 528| 14.4M| RepList* rl = pAMgr ? pAMgr->get_iconvtable() : nullptr; ------------------ | Branch (528:17): [True: 14.4M, False: 0] ------------------ 529| 14.4M| { 530| 14.4M| std::string wspace; 531| | 532| 14.4M| bool convstatus = rl ? rl->conv(word, wspace) : false; ------------------ | Branch (532:23): [True: 351k, False: 14.1M] ------------------ 533| 14.4M| if (convstatus) { ------------------ | Branch (533:9): [True: 0, False: 14.4M] ------------------ 534| | // the input conversion can grow the word without limit, so hold the 535| | // converted word to the same maximum length as the raw word 536| 0| if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 87| 0|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 0|#define MAXWORDLEN 100 | | ------------------ ------------------ if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 90| 0|#define MAXWORDLEN 100 ------------------ | Branch (536:11): [True: 0, False: 0] | Branch (536:11): [True: 0, False: 0] ------------------ 537| 0| return false; 538| 0| wl = cleanword2(scw, sunicw, wspace, &captype, &abbv); 539| 0| } else 540| 14.4M| wl = cleanword2(scw, sunicw, word, &captype, &abbv); 541| 14.4M| } 542| | 543| 14.4M|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 544| 14.4M| if (wl > 32768) ------------------ | Branch (544:9): [True: 0, False: 14.4M] ------------------ 545| 0| return false; 546| 14.4M|#endif 547| | 548| |#ifdef MOZILLA_CLIENT 549| | // accept the abbreviated words without dots 550| | // workaround for the incomplete tokenization of Mozilla 551| | abbv = 1; 552| |#endif 553| | 554| 14.4M| if (wl == 0 || m_HMgrs.empty()) ------------------ | Branch (554:7): [True: 239k, False: 14.2M] | Branch (554:18): [True: 0, False: 14.2M] ------------------ 555| 239k| return true; 556| 14.2M| if (root) ------------------ | Branch (556:7): [True: 0, False: 14.2M] ------------------ 557| 0| root->clear(); 558| | 559| | // allow numbers with dots, dashes and commas (but forbid double separators: 560| | // "..", "--" etc.). Besides the ASCII digits, accept the Arabic-Indic and 561| | // Extended Arabic-Indic (Persian) digit ranges so those numbers are passed 562| | // over the same way ASCII numbers are. 563| 14.2M| enum { NBEGIN, NNUM, NSEP }; 564| 14.2M| int nstate = NBEGIN; 565| 14.2M| size_t i; 566| 14.2M| size_t n = utf8 ? sunicw.size() : wl; ------------------ | Branch (566:14): [True: 2.36M, False: 11.8M] ------------------ 567| | 568| 28.8M| for (i = 0; (i < n); i++) { ------------------ | Branch (568:15): [True: 27.9M, False: 855k] ------------------ 569| 27.9M| unsigned short c = utf8 ? static_cast(sunicw[i]) : static_cast(scw[i]); ------------------ | Branch (569:24): [True: 4.16M, False: 23.8M] ------------------ 570| 27.9M| if ((c >= '0' && c <= '9') || (c >= 0x0660 && c <= 0x0669) || // Arabic-Indic digits ------------------ | Branch (570:10): [True: 20.2M, False: 7.70M] | Branch (570:22): [True: 14.0M, False: 6.25M] | Branch (570:36): [True: 227k, False: 13.7M] | Branch (570:51): [True: 0, False: 227k] ------------------ 571| 14.0M| (c >= 0x06F0 && c <= 0x06F9)) { // Extended Arabic-Indic (Persian) digits ------------------ | Branch (571:10): [True: 227k, False: 13.7M] | Branch (571:25): [True: 0, False: 227k] ------------------ 572| 14.0M| nstate = NNUM; 573| 14.0M| } else if ((c == ',') || (c == '.') || (c == '-')) { ------------------ | Branch (573:16): [True: 107k, False: 13.8M] | Branch (573:30): [True: 911k, False: 12.9M] | Branch (573:44): [True: 3.07M, False: 9.86M] ------------------ 574| 4.09M| if ((nstate == NSEP) || (i == 0)) ------------------ | Branch (574:11): [True: 102k, False: 3.99M] | Branch (574:31): [True: 3.39M, False: 598k] ------------------ 575| 3.49M| break; 576| 598k| nstate = NSEP; 577| 598k| } else 578| 9.86M| break; 579| 27.9M| } 580| 14.2M| if ((i == n) && (nstate == NNUM)) ------------------ | Branch (580:7): [True: 855k, False: 13.3M] | Branch (580:19): [True: 654k, False: 200k] ------------------ 581| 654k| return true; 582| | 583| 13.5M| switch (captype) { ------------------ | Branch (583:11): [True: 13.5M, False: 0] ------------------ 584| 1.02M| case HUHCAP: ------------------ | | 95| 1.02M|#define HUHCAP 3 ------------------ | Branch (584:5): [True: 1.02M, False: 12.5M] ------------------ 585| | /* FALLTHROUGH */ 586| 1.24M| case HUHINITCAP: ------------------ | | 96| 1.24M|#define HUHINITCAP 4 ------------------ | Branch (586:5): [True: 222k, False: 13.3M] ------------------ 587| 1.24M| *info |= SPELL_ORIGCAP; ------------------ | | 86| 1.24M|#define SPELL_ORIGCAP (1 << 5) ------------------ 588| | /* FALLTHROUGH */ 589| 12.5M| case NOCAP: ------------------ | | 92| 12.5M|#define NOCAP 0 ------------------ | Branch (589:5): [True: 11.2M, False: 2.27M] ------------------ 590| 12.5M| rv = checkword(scw, info, root, suggest_start); 591| 12.5M| if ((abbv) && !(rv)) { ------------------ | Branch (591:11): [True: 1.17M, False: 11.3M] | Branch (591:21): [True: 1.17M, False: 290] ------------------ 592| 1.17M| std::string u8buffer(scw); 593| 1.17M| u8buffer.push_back('.'); 594| 1.17M| rv = checkword(u8buffer, info, root, suggest_start); 595| 1.17M| } 596| | // A stem with an inner capital, capitalised at the start of a sentence 597| | // (uLinda written ULinda), is found by lowering only the first letter. 598| 12.5M| if (!rv && captype == HUHINITCAP) { ------------------ | | 96| 12.5M|#define HUHINITCAP 4 ------------------ | Branch (598:11): [True: 12.5M, False: 13.4k] | Branch (598:18): [True: 219k, False: 12.2M] ------------------ 599| 219k| std::string u8buffer(scw); 600| 219k| std::vector u16buffer(sunicw); 601| 219k| mkinitsmall2(u8buffer, u16buffer); 602| 219k| rv = checkword(u8buffer, info, root, suggest_start); 603| 219k| if (rv && is_keepcase(rv)) ------------------ | Branch (603:13): [True: 12, False: 219k] | Branch (603:19): [True: 0, False: 12] ------------------ 604| 0| rv = nullptr; 605| 219k| } 606| 12.5M| break; 607| 654k| case ALLCAP: { ------------------ | | 94| 654k|#define ALLCAP 2 ------------------ | Branch (607:5): [True: 654k, False: 12.9M] ------------------ 608| 654k| *info |= SPELL_ORIGCAP; ------------------ | | 86| 654k|#define SPELL_ORIGCAP (1 << 5) ------------------ 609| 654k| rv = checkword(scw, info, root, suggest_start); 610| 654k| if (rv) ------------------ | Branch (610:11): [True: 103, False: 654k] ------------------ 611| 103| break; 612| 654k| if (abbv) { ------------------ | Branch (612:11): [True: 97.6k, False: 557k] ------------------ 613| 97.6k| std::string u8buffer(scw); 614| 97.6k| u8buffer.push_back('.'); 615| 97.6k| rv = checkword(u8buffer, info, root, suggest_start); 616| 97.6k| if (rv) ------------------ | Branch (616:13): [True: 0, False: 97.6k] ------------------ 617| 0| break; 618| 97.6k| } 619| | // Spec. prefix handling for Catalan, French, Italian: 620| | // prefixes separated by apostrophe (SANT'ELIA -> Sant'+Elia). 621| 654k| size_t apos = pAMgr ? scw.find('\'') : std::string::npos; ------------------ | Branch (621:21): [True: 654k, False: 0] ------------------ 622| 654k| if (apos != std::string::npos) { ------------------ | Branch (622:11): [True: 151k, False: 503k] ------------------ 623| 151k| mkallsmall2(scw, sunicw); 624| | //conversion may result in string with different len to pre-mkallsmall2 625| | //so re-scan 626| 151k| if (apos != std::string::npos && apos < scw.size() - 1) { ------------------ | Branch (626:13): [True: 151k, False: 0] | Branch (626:42): [True: 137k, False: 14.1k] ------------------ 627| 137k| std::string part1 = scw.substr(0, apos + 1), part2 = scw.substr(apos + 1); 628| 137k| if (utf8) { ------------------ | Branch (628:15): [True: 29.7k, False: 107k] ------------------ 629| 29.7k| std::vector part1u, part2u; 630| 29.7k| u8_u16(part1u, part1); 631| 29.7k| u8_u16(part2u, part2); 632| 29.7k| mkinitcap2(part2, part2u); 633| 29.7k| scw = part1 + part2; 634| 29.7k| sunicw = std::move(part1u); 635| 29.7k| sunicw.insert(sunicw.end(), part2u.begin(), part2u.end()); 636| 29.7k| rv = checkword(scw, info, root, suggest_start); 637| 29.7k| if (rv) ------------------ | Branch (637:17): [True: 0, False: 29.7k] ------------------ 638| 0| break; 639| 107k| } else { 640| 107k| mkinitcap2(part2, sunicw); 641| 107k| scw = part1 + part2; 642| 107k| rv = checkword(scw, info, root, suggest_start); 643| 107k| if (rv) ------------------ | Branch (643:17): [True: 1, False: 107k] ------------------ 644| 1| break; 645| 107k| } 646| 137k| mkinitcap2(scw, sunicw); 647| 137k| rv = checkword(scw, info, root, suggest_start); 648| 137k| if (rv) ------------------ | Branch (648:15): [True: 1, False: 137k] ------------------ 649| 1| break; 650| 137k| } 651| 151k| } 652| 654k| if (pAMgr && pAMgr->get_checksharps() && scw.find("SS") != std::string::npos) { ------------------ | Branch (652:11): [True: 654k, False: 0] | Branch (652:20): [True: 0, False: 654k] | Branch (652:48): [True: 0, False: 0] ------------------ 653| | 654| 0| mkallsmall2(scw, sunicw); 655| 0| std::string u8buffer(scw); 656| 0| rv = spellsharps(u8buffer, 0, 0, 0, info, root, suggest_start); 657| 0| if (!rv) { ------------------ | Branch (657:13): [True: 0, False: 0] ------------------ 658| 0| mkinitcap2(scw, sunicw); 659| 0| rv = spellsharps(scw, 0, 0, 0, info, root, suggest_start); 660| 0| } 661| 0| if ((abbv) && !(rv)) { ------------------ | Branch (661:13): [True: 0, False: 0] | Branch (661:23): [True: 0, False: 0] ------------------ 662| 0| u8buffer.push_back('.'); 663| 0| rv = spellsharps(u8buffer, 0, 0, 0, info, root, suggest_start); 664| 0| if (!rv) { ------------------ | Branch (664:15): [True: 0, False: 0] ------------------ 665| 0| u8buffer = std::string(scw); 666| 0| u8buffer.push_back('.'); 667| 0| rv = spellsharps(u8buffer, 0, 0, 0, info, root, suggest_start); 668| 0| } 669| 0| } 670| 0| if (rv) ------------------ | Branch (670:13): [True: 0, False: 0] ------------------ 671| 0| break; 672| 0| } 673| 654k| } 674| | /* FALLTHROUGH */ 675| 1.02M| case INITCAP: { ------------------ | | 93| 1.02M|#define INITCAP 1 ------------------ | Branch (675:5): [True: 373k, False: 13.1M] ------------------ 676| | // handle special capitalization of dotted I 677| 1.02M| bool Idot = (utf8 && (unsigned char) scw[0] == 0xc4 && (unsigned char) scw[1] == 0xb0); ------------------ | Branch (677:20): [True: 174k, False: 853k] | Branch (677:28): [True: 8, False: 174k] | Branch (677:62): [True: 0, False: 8] ------------------ 678| 1.02M| *info |= SPELL_ORIGCAP; ------------------ | | 86| 1.02M|#define SPELL_ORIGCAP (1 << 5) ------------------ 679| 1.02M| if (captype == ALLCAP) { ------------------ | | 94| 1.02M|#define ALLCAP 2 ------------------ | Branch (679:11): [True: 654k, False: 373k] ------------------ 680| 654k| mkallsmall2(scw, sunicw); 681| 654k| mkinitcap2(scw, sunicw); 682| 654k| if (Idot) ------------------ | Branch (682:15): [True: 0, False: 654k] ------------------ 683| 0| scw.replace(0, 1, "\xc4\xb0"); 684| 654k| } 685| 1.02M| if (captype == INITCAP) ------------------ | | 93| 1.02M|#define INITCAP 1 ------------------ | Branch (685:11): [True: 373k, False: 654k] ------------------ 686| 373k| *info |= SPELL_INITCAP; ------------------ | | 85| 373k|#define SPELL_INITCAP (1 << 4) ------------------ 687| 1.02M| rv = checkword(scw, info, root, suggest_start); 688| 1.02M| if (captype == INITCAP) ------------------ | | 93| 1.02M|#define INITCAP 1 ------------------ | Branch (688:11): [True: 373k, False: 654k] ------------------ 689| 373k| *info &= ~SPELL_INITCAP; ------------------ | | 85| 373k|#define SPELL_INITCAP (1 << 4) ------------------ 690| | // forbid bad capitalization 691| | // (for example, ijs -> Ijs instead of IJs in Dutch) 692| | // use explicit forms in dic: Ijs/F (F = FORBIDDENWORD flag) 693| 1.02M| if (*info & SPELL_FORBIDDEN) { ------------------ | | 82| 1.02M|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (693:11): [True: 0, False: 1.02M] ------------------ 694| 0| rv = nullptr; 695| 0| break; 696| 0| } 697| 1.02M| if (rv && is_keepcase(rv) && (captype == ALLCAP)) ------------------ | | 94| 16|#define ALLCAP 2 ------------------ | Branch (697:11): [True: 19.9k, False: 1.00M] | Branch (697:17): [True: 16, False: 19.8k] | Branch (697:36): [True: 0, False: 16] ------------------ 698| 0| rv = nullptr; 699| 1.02M| if (rv || (Idot && langnum != LANG_az && langnum != LANG_tr && langnum != LANG_crh)) ------------------ | Branch (699:11): [True: 19.9k, False: 1.00M] | Branch (699:18): [True: 0, False: 1.00M] | Branch (699:26): [True: 0, False: 0] | Branch (699:48): [True: 0, False: 0] | Branch (699:70): [True: 0, False: 0] ------------------ 700| 19.9k| break; 701| | 702| 1.00M| mkallsmall2(scw, sunicw); 703| 1.00M| std::string u8buffer(scw); 704| 1.00M| mkinitcap2(scw, sunicw); 705| | 706| 1.00M| rv = checkword(u8buffer, info, root, suggest_start); 707| 1.00M| if (abbv && !rv) { ------------------ | Branch (707:11): [True: 181k, False: 826k] | Branch (707:19): [True: 181k, False: 36] ------------------ 708| 181k| u8buffer.push_back('.'); 709| 181k| rv = checkword(u8buffer, info, root, suggest_start); 710| 181k| if (!rv) { ------------------ | Branch (710:13): [True: 181k, False: 0] ------------------ 711| 181k| u8buffer = scw; 712| 181k| u8buffer.push_back('.'); 713| 181k| if (captype == INITCAP) ------------------ | | 93| 181k|#define INITCAP 1 ------------------ | Branch (713:15): [True: 84.3k, False: 97.6k] ------------------ 714| 84.3k| *info |= SPELL_INITCAP; ------------------ | | 85| 84.3k|#define SPELL_INITCAP (1 << 4) ------------------ 715| 181k| rv = checkword(u8buffer, info, root, suggest_start); 716| 181k| if (captype == INITCAP) ------------------ | | 93| 181k|#define INITCAP 1 ------------------ | Branch (716:15): [True: 84.3k, False: 97.6k] ------------------ 717| 84.3k| *info &= ~SPELL_INITCAP; ------------------ | | 85| 84.3k|#define SPELL_INITCAP (1 << 4) ------------------ 718| 181k| if (rv && is_keepcase(rv) && (captype == ALLCAP)) ------------------ | | 94| 12|#define ALLCAP 2 ------------------ | Branch (718:15): [True: 12, False: 181k] | Branch (718:21): [True: 12, False: 0] | Branch (718:40): [True: 2, False: 10] ------------------ 719| 2| rv = nullptr; 720| 181k| break; 721| 181k| } 722| 181k| } 723| 826k| if (rv && is_keepcase(rv) && ------------------ | Branch (723:11): [True: 595, False: 825k] | Branch (723:17): [True: 3, False: 592] ------------------ 724| 3| ((captype == ALLCAP) || ------------------ | | 94| 3|#define ALLCAP 2 ------------------ | Branch (724:12): [True: 1, False: 2] ------------------ 725| | // if CHECKSHARPS: KEEPCASE words with \xDF are allowed 726| | // in INITCAP form, too. 727| 2| !(pAMgr->get_checksharps() && ------------------ | Branch (727:14): [True: 0, False: 2] ------------------ 728| 0| ((utf8 && u8buffer.find("\xC3\x9F") != std::string::npos) || ------------------ | Branch (728:16): [True: 0, False: 0] | Branch (728:24): [True: 0, False: 0] ------------------ 729| 0| (!utf8 && u8buffer.find('\xDF') != std::string::npos))))) ------------------ | Branch (729:16): [True: 0, False: 0] | Branch (729:25): [True: 0, False: 0] ------------------ 730| 3| rv = nullptr; 731| 826k| break; 732| 1.00M| } 733| 13.5M| } 734| | 735| 13.5M| if (rv) { ------------------ | Branch (735:7): [True: 34.0k, False: 13.5M] ------------------ 736| 34.0k| if (pAMgr && pAMgr->get_warn() && rv->astr && ------------------ | Branch (736:9): [True: 34.0k, False: 0] | Branch (736:9): [True: 4, False: 34.0k] | Branch (736:18): [True: 2.25k, False: 31.7k] | Branch (736:39): [True: 14, False: 2.24k] ------------------ 737| 14| TESTAFF(rv->astr, pAMgr->get_warn(), rv->alen)) { ------------------ | | 102| 14|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 4, False: 10] | | ------------------ ------------------ 738| 4| *info |= SPELL_WARN; ------------------ | | 87| 4|#define SPELL_WARN (1 << 6) ------------------ 739| 4| if (pAMgr->get_forbidwarn()) ------------------ | Branch (739:11): [True: 0, False: 4] ------------------ 740| 0| return false; 741| 4| return true; 742| 4| } 743| 34.0k| return true; 744| 34.0k| } 745| | 746| | // recursive breaking at break points 747| 13.5M| if (!wordbreak.empty() && !(*info & SPELL_FORBIDDEN)) { ------------------ | | 82| 13.5M|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (747:7): [True: 13.5M, False: 0] | Branch (747:29): [True: 13.5M, False: 0] ------------------ 748| | 749| 13.5M| int nbr = 0; 750| 13.5M| wl = scw.size(); 751| | 752| | // calculate break points for recursion limit 753| 40.4M| for (auto& j : wordbreak) { ------------------ | Branch (753:18): [True: 40.4M, False: 13.5M] ------------------ 754| 40.4M| size_t pos = 0; 755| 55.4M| while ((pos = scw.find(j, pos)) != std::string::npos) { ------------------ | Branch (755:14): [True: 14.9M, False: 40.4M] ------------------ 756| 14.9M| ++nbr; 757| 14.9M| pos += j.size(); 758| 14.9M| } 759| 40.4M| } 760| 13.5M| if (nbr >= MAXBREAKDEPTH) ------------------ | | 87| 13.5M|#define MAXBREAKDEPTH 10 ------------------ | Branch (760:9): [True: 6.11k, False: 13.5M] ------------------ 761| 6.11k| return false; 762| | 763| | // check boundary patterns (^begin and end$) 764| 40.4M| for (auto& j : wordbreak) { ------------------ | Branch (764:18): [True: 40.4M, False: 12.5M] ------------------ 765| 40.4M| size_t plen = j.size(); 766| 40.4M| if (plen == 1 || plen > wl) ------------------ | Branch (766:11): [True: 13.5M, False: 26.8M] | Branch (766:24): [True: 3.36M, False: 23.5M] ------------------ 767| 16.8M| continue; 768| | 769| 23.5M| if (j[0] == '^' && scw.compare(0, plen - 1, j, 1, plen - 1) == 0 && ------------------ | Branch (769:11): [True: 11.7M, False: 11.7M] | Branch (769:11): [True: 74.8k, False: 23.4M] | Branch (769:26): [True: 1.26M, False: 10.5M] ------------------ 770| 1.26M| spell(scw.substr(plen - 1), candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (770:11): [True: 74.8k, False: 1.19M] ------------------ 771| 74.8k| *info |= SPELL_COMPOUND; ------------------ | | 81| 74.8k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 772| 74.8k| return true; 773| 74.8k| } 774| | 775| 23.4M| if (j[plen - 1] == '$' && ------------------ | Branch (775:11): [True: 11.7M, False: 11.7M] ------------------ 776| 11.7M| scw.compare(wl - plen + 1, plen - 1, j, 0, plen - 1) == 0) { ------------------ | Branch (776:11): [True: 4.16M, False: 7.54M] ------------------ 777| 4.16M| std::string suffix(scw.substr(wl - plen + 1)); 778| 4.16M| scw.resize(wl - plen + 1); 779| 4.16M| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (779:13): [True: 857k, False: 3.31M] ------------------ 780| 857k| *info |= SPELL_COMPOUND; ------------------ | | 81| 857k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 781| 857k| return true; 782| 857k| } 783| 3.31M| scw.append(suffix); 784| 3.31M| } 785| 23.4M| } 786| | 787| | // other patterns 788| 37.6M| for (auto& j : wordbreak) { ------------------ | Branch (788:18): [True: 37.6M, False: 12.5M] ------------------ 789| 37.6M| size_t plen = j.size(); 790| 37.6M| size_t found = scw.find(j); 791| 37.6M| if ((found > 0) && (found < wl - plen)) { ------------------ | Branch (791:11): [True: 35.1M, False: 2.46M] | Branch (791:26): [True: 3.98M, False: 31.1M] ------------------ 792| 3.98M| size_t found2 = scw.find(j, found + 1); 793| | // try to break at the second occurance 794| | // to recognize dictionary words with wordbreak 795| 3.98M| if (found2 > 0 && (found2 < wl - plen)) ------------------ | Branch (795:13): [True: 3.98M, False: 0] | Branch (795:27): [True: 1.55M, False: 2.42M] ------------------ 796| 1.55M| found = found2; 797| 3.98M| std::string substring(scw.substr(found + plen)); 798| 3.98M| if (!spell(substring, candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (798:13): [True: 3.09M, False: 893k] ------------------ 799| 3.09M| continue; 800| 893k| std::string suffix(scw.substr(found)); 801| 893k| scw.resize(found); 802| | // examine 2 sides of the break point 803| 893k| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (803:13): [True: 53.1k, False: 840k] ------------------ 804| 53.1k| *info |= SPELL_COMPOUND; ------------------ | | 81| 53.1k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 805| 53.1k| return true; 806| 53.1k| } 807| 840k| scw.append(suffix); 808| | 809| | // LANG_hu: spec. dash rule 810| 840k| if (langnum == LANG_hu && j == "-") { ------------------ | Branch (810:13): [True: 165, False: 840k] | Branch (810:35): [True: 165, False: 0] ------------------ 811| 165| suffix = scw.substr(found + 1); 812| 165| scw.resize(found + 1); 813| 165| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (813:15): [True: 0, False: 165] ------------------ 814| 0| *info |= SPELL_COMPOUND; ------------------ | | 81| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 815| 0| return true; // check the first part with dash 816| 0| } 817| 165| scw.append(suffix); 818| 165| } 819| | // end of LANG specific region 820| 840k| } 821| 37.6M| } 822| | 823| | // other patterns (break at first break point) 824| 37.5M| for (auto& j : wordbreak) { ------------------ | Branch (824:18): [True: 37.5M, False: 12.5M] ------------------ 825| 37.5M| size_t plen = j.size(), found = scw.find(j); 826| 37.5M| if ((found > 0) && (found < wl - plen)) { ------------------ | Branch (826:11): [True: 35.0M, False: 2.46M] | Branch (826:26): [True: 3.91M, False: 31.1M] ------------------ 827| 3.91M| if (!spell(scw.substr(found + plen), candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (827:13): [True: 3.21M, False: 698k] ------------------ 828| 3.21M| continue; 829| 698k| std::string suffix(scw.substr(found)); 830| 698k| scw.resize(found); 831| | // examine 2 sides of the break point 832| 698k| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (832:13): [True: 5.18k, False: 693k] ------------------ 833| 5.18k| *info |= SPELL_COMPOUND; ------------------ | | 81| 5.18k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 834| 5.18k| return true; 835| 5.18k| } 836| 693k| scw.append(suffix); 837| | 838| | // LANG_hu: spec. dash rule 839| 693k| if (langnum == LANG_hu && j == "-") { ------------------ | Branch (839:13): [True: 79, False: 693k] | Branch (839:35): [True: 79, False: 0] ------------------ 840| 79| suffix = scw.substr(found + 1); 841| 79| scw.resize(found + 1); 842| 79| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (842:15): [True: 0, False: 79] ------------------ 843| 0| *info |= SPELL_COMPOUND; ------------------ | | 81| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 844| 0| return true; // check the first part with dash 845| 0| } 846| 79| scw.append(suffix); 847| 79| } 848| | // end of LANG specific region 849| 693k| } 850| 37.5M| } 851| 12.5M| } 852| | 853| 12.5M| return false; 854| 13.5M|} _ZN12HunspellImpl9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiPS6_NS0_6chrono10time_pointINSB_12steady_clockENSB_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 857| 17.3M| std::chrono::steady_clock::time_point suggest_start) { 858| | // check overall suggest time limit 859| 17.3M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 17.3M|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (859:7): [True: 0, False: 17.3M] ------------------ 860| 0| return nullptr; 861| | 862| 17.3M| std::string word; 863| | 864| | // remove IGNORE characters from the string 865| 17.3M| clean_ignore(word, w); 866| | 867| 17.3M| if (word.empty()) ------------------ | Branch (867:7): [True: 1.63k, False: 17.3M] ------------------ 868| 1.63k| return nullptr; 869| | 870| | // word reversing wrapper for complex prefixes 871| 17.3M| if (complexprefixes) { ------------------ | Branch (871:7): [True: 887k, False: 16.4M] ------------------ 872| 887k| if (utf8) ------------------ | Branch (872:9): [True: 0, False: 887k] ------------------ 873| 0| reverseword_utf(word); 874| 887k| else 875| 887k| reverseword(word); 876| 887k| } 877| | 878| 17.3M| int len = word.size(); 879| | 880| | // look word in hash table 881| 17.3M| struct hentry* he = nullptr; 882| 17.3M| TraceCtx* t = active_trace(); 883| 34.7M| for (size_t i = 0; (i < m_HMgrs.size()) && !he; ++i) { ------------------ | Branch (883:22): [True: 17.3M, False: 17.3M] | Branch (883:46): [True: 17.3M, False: 0] ------------------ 884| 17.3M| he = m_HMgrs[i]->lookup(word.c_str(), word.size()); 885| | 886| 17.3M| if (t) { ------------------ | Branch (886:9): [True: 0, False: 17.3M] ------------------ 887| 0| std::string dic; 888| 0| if (m_HMgrs.size() > 1) ------------------ | Branch (888:11): [True: 0, False: 0] ------------------ 889| 0| dic = " dic=" + std::to_string(i); 890| 0| if (he) ------------------ | Branch (890:11): [True: 0, False: 0] ------------------ 891| 0| trace(*t, "lookup \"%s\"%s -> entry \"%s\" flags=%s", word.c_str(), 892| 0| dic.c_str(), he->word, 893| 0| trace_flags(pAMgr.get(), he->astr, he->alen).c_str()); 894| 0| else 895| 0| trace(*t, "lookup \"%s\"%s -> miss", word.c_str(), dic.c_str()); 896| 0| } 897| | 898| | // check forbidden and onlyincompound words 899| 17.3M| if ((he) && (he->astr) && (pAMgr) && ------------------ | Branch (899:9): [True: 37.2k, False: 17.3M] | Branch (899:9): [True: 0, False: 17.3M] | Branch (899:17): [True: 4.88k, False: 32.3k] | Branch (899:31): [True: 4.88k, False: 0] ------------------ 900| 4.88k| TESTAFF(he->astr, pAMgr->get_forbiddenword(), he->alen)) { ------------------ | | 102| 4.88k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 4.88k] | | ------------------ ------------------ 901| 0| if (t) ------------------ | Branch (901:11): [True: 0, False: 0] ------------------ 902| 0| trace(*t, "test forbidden flag=%s in=dic have=%s" 903| 0| " -> fail, the word is forbidden", 904| 0| pAMgr->encode_flag(pAMgr->get_forbiddenword()).c_str(), 905| 0| trace_flags(pAMgr.get(), he->astr, he->alen).c_str()); 906| 0| if (info) ------------------ | Branch (906:11): [True: 0, False: 0] ------------------ 907| 0| *info |= SPELL_FORBIDDEN; ------------------ | | 82| 0|#define SPELL_FORBIDDEN (1 << 1) ------------------ 908| | // LANG_hu section: set dash information for suggestions 909| 0| if (langnum == LANG_hu) { ------------------ | Branch (909:11): [True: 0, False: 0] ------------------ 910| 0| if (pAMgr->get_compoundflag() && ------------------ | Branch (910:13): [True: 0, False: 0] | Branch (910:13): [True: 0, False: 0] ------------------ 911| 0| TESTAFF(he->astr, pAMgr->get_compoundflag(), he->alen)) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 912| 0| if (info) ------------------ | Branch (912:15): [True: 0, False: 0] ------------------ 913| 0| *info |= SPELL_COMPOUND; ------------------ | | 81| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 914| 0| } 915| 0| } 916| 0| return nullptr; 917| 0| } 918| | 919| | // he = next not needaffix, onlyincompound homonym or onlyupcase word 920| 17.3M| const struct hentry* first_he = he; 921| 17.3M| while (he && (he->astr) && pAMgr && ------------------ | Branch (921:12): [True: 37.2k, False: 17.3M] | Branch (921:12): [True: 3.18k, False: 17.3M] | Branch (921:18): [True: 4.88k, False: 32.3k] | Branch (921:32): [True: 4.88k, False: 0] ------------------ 922| 4.88k| ((pAMgr->get_needaffix() && ------------------ | Branch (922:14): [True: 380, False: 4.50k] ------------------ 923| 380| TESTAFF(he->astr, pAMgr->get_needaffix(), he->alen)) || ------------------ | | 102| 380|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 380] | | ------------------ ------------------ 924| 4.88k| (pAMgr->get_onlyincompound() && ------------------ | Branch (924:14): [True: 0, False: 4.88k] ------------------ 925| 0| TESTAFF(he->astr, pAMgr->get_onlyincompound(), he->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 926| 4.88k| (info && (*info & SPELL_INITCAP) && ------------------ | | 85| 4.88k|#define SPELL_INITCAP (1 << 4) ------------------ | Branch (926:14): [True: 4.88k, False: 0] | Branch (926:22): [True: 3.21k, False: 1.67k] ------------------ 927| 3.21k| TESTAFF(he->astr, ONLYUPCASEFLAG, he->alen)))) { ------------------ | | 102| 3.21k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 3.18k, False: 26] | | ------------------ ------------------ 928| 3.18k| if (t) { ------------------ | Branch (928:11): [True: 0, False: 3.18k] ------------------ 929| | // Name the branch that fired, in the order the condition tests them. 930| 0| const char* reason = "onlyupcase"; 931| 0| FLAG flag = ONLYUPCASEFLAG; ------------------ | | 98| 0|#define FLAG unsigned short ------------------ FLAG flag = ONLYUPCASEFLAG; ------------------ | | 128| 0|#define ONLYUPCASEFLAG 65511 ------------------ 932| 0| if (pAMgr->get_needaffix() && ------------------ | Branch (932:13): [True: 0, False: 0] | Branch (932:13): [True: 0, False: 0] ------------------ 933| 0| TESTAFF(he->astr, pAMgr->get_needaffix(), he->alen)) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 934| 0| reason = "needaffix"; 935| 0| flag = pAMgr->get_needaffix(); 936| 0| } else if (pAMgr->get_onlyincompound() && ------------------ | Branch (936:20): [True: 0, False: 0] | Branch (936:20): [True: 0, False: 0] ------------------ 937| 0| TESTAFF(he->astr, pAMgr->get_onlyincompound(), he->alen)) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 938| 0| reason = "onlyincompound"; 939| 0| flag = pAMgr->get_onlyincompound(); 940| 0| } 941| 0| trace(*t, "test %s flag=%s in=dic have=%s" 942| 0| " -> fail, on to the next homonym", 943| 0| reason, trace_flag(pAMgr.get(), flag).c_str(), 944| 0| trace_flags(pAMgr.get(), he->astr, he->alen).c_str()); 945| 0| } 946| 3.18k| he = he->next_homonym; 947| 3.18k| } 948| | 949| | // Say which entry the walk left in hand, so the transcript does not end 950| | // on a homonym that was passed over. 951| 17.3M| if (t && he != first_he) { ------------------ | Branch (951:9): [True: 0, False: 17.3M] | Branch (951:14): [True: 0, False: 0] ------------------ 952| 0| if (he) ------------------ | Branch (952:11): [True: 0, False: 0] ------------------ 953| 0| trace(*t, "lookup \"%s\" -> entry \"%s\" flags=%s", word.c_str(), 954| 0| he->word, trace_flags(pAMgr.get(), he->astr, he->alen).c_str()); 955| 0| else 956| 0| trace(*t, "lookup \"%s\" -> no more homonyms", word.c_str()); 957| 0| } 958| 17.3M| } 959| | 960| | // check with affixes 961| 17.3M| if (!he && pAMgr) { ------------------ | Branch (961:7): [True: 17.3M, False: 34.0k] | Branch (961:14): [True: 17.3M, False: 0] ------------------ 962| | // try stripping off affixes 963| 17.3M| AffixScratch scratch; 964| 17.3M| scratch.trace = t; 965| | // For an initial-capital query, make affix_check skip an all-uppercase-only 966| | // stem and keep looking, so a valid mixed-case match behind it is found. 967| 17.3M| FLAG avoidflag = (info && (*info & SPELL_INITCAP)) ? ONLYUPCASEFLAG : FLAG_NULL; ------------------ | | 98| 17.3M|#define FLAG unsigned short ------------------ FLAG avoidflag = (info && (*info & SPELL_INITCAP)) ? ONLYUPCASEFLAG : FLAG_NULL; ------------------ | | 85| 17.3M|#define SPELL_INITCAP (1 << 4) ------------------ FLAG avoidflag = (info && (*info & SPELL_INITCAP)) ? ONLYUPCASEFLAG : FLAG_NULL; ------------------ | | 128| 439k|#define ONLYUPCASEFLAG 65511 ------------------ FLAG avoidflag = (info && (*info & SPELL_INITCAP)) ? ONLYUPCASEFLAG : FLAG_NULL; ------------------ | | 99| 34.2M|#define FLAG_NULL 0x00 ------------------ | Branch (967:23): [True: 17.3M, False: 0] | Branch (967:31): [True: 439k, False: 16.8M] ------------------ 968| 17.3M| he = pAMgr->affix_check(word, 0, len, scratch, 0, IN_CPD_NOT, avoidflag); ------------------ | | 75| 17.3M|#define IN_CPD_NOT 0 ------------------ 969| | 970| | // check compound restriction and onlyupcase 971| 17.3M| if (he && he->astr && ------------------ | Branch (971:9): [True: 0, False: 17.3M] | Branch (971:9): [True: 0, False: 17.3M] | Branch (971:15): [True: 0, False: 0] ------------------ 972| 0| ((pAMgr->get_onlyincompound() && ------------------ | Branch (972:11): [True: 0, False: 0] ------------------ 973| 0| TESTAFF(he->astr, pAMgr->get_onlyincompound(), he->alen)) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 974| 0| (info && (*info & SPELL_INITCAP) && ------------------ | | 85| 0|#define SPELL_INITCAP (1 << 4) ------------------ | Branch (974:11): [True: 0, False: 0] | Branch (974:19): [True: 0, False: 0] ------------------ 975| 0| TESTAFF(he->astr, ONLYUPCASEFLAG, he->alen)))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 976| 0| he = nullptr; 977| 0| } 978| | 979| 17.3M| if (he) { ------------------ | Branch (979:9): [True: 0, False: 17.3M] ------------------ 980| 0| if ((he->astr) && (pAMgr) && ------------------ | Branch (980:11): [True: 0, False: 0] | Branch (980:11): [True: 0, False: 0] | Branch (980:25): [True: 0, False: 0] ------------------ 981| 0| TESTAFF(he->astr, pAMgr->get_forbiddenword(), he->alen)) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 982| 0| if (info) ------------------ | Branch (982:13): [True: 0, False: 0] ------------------ 983| 0| *info |= SPELL_FORBIDDEN; ------------------ | | 82| 0|#define SPELL_FORBIDDEN (1 << 1) ------------------ 984| 0| return nullptr; 985| 0| } 986| 0| if (root) { ------------------ | Branch (986:11): [True: 0, False: 0] ------------------ 987| 0| root->assign(he->word); 988| 0| if (complexprefixes) { ------------------ | Branch (988:13): [True: 0, False: 0] ------------------ 989| 0| if (utf8) ------------------ | Branch (989:15): [True: 0, False: 0] ------------------ 990| 0| reverseword_utf(*root); 991| 0| else 992| 0| reverseword(*root); 993| 0| } 994| 0| } 995| | // try check compound word 996| 17.3M| } else if (pAMgr->get_compound()) { ------------------ | Branch (996:16): [True: 4.49M, False: 12.8M] ------------------ 997| 4.49M| struct hentry* rwords[100] = {}; // buffer for COMPOUND pattern checking 998| | 999| | // first allow only 2 words in the compound 1000| 4.49M| int setinfo = SPELL_COMPOUND_2; ------------------ | | 88| 4.49M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ 1001| 4.49M| if (info) ------------------ | Branch (1001:11): [True: 4.49M, False: 0] ------------------ 1002| 4.49M| setinfo |= *info; 1003| 4.49M| if (TraceCtx* t = trace_on(scratch.trace)) ------------------ | Branch (1003:21): [True: 0, False: 4.49M] ------------------ 1004| 0| trace(*t, "compound words=2"); 1005| 4.49M| { 1006| 4.49M| TraceScope compound_depth(trace_on(scratch.trace)); 1007| 4.49M| he = pAMgr->compound_check(word, 0, 0, 100, 0, nullptr, (hentry**)&rwords, 0, 0, &setinfo, scratch); 1008| 4.49M| } 1009| 4.49M| if (info) ------------------ | Branch (1009:11): [True: 4.49M, False: 0] ------------------ 1010| 4.49M| *info = setinfo & ~SPELL_COMPOUND_2; ------------------ | | 88| 4.49M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ 1011| | // if not 2-word compoud word, try with 3 or more words 1012| | // (only if original info didn't forbid it) 1013| 4.49M| if (!he && info && !(*info & SPELL_COMPOUND_2)) { ------------------ | | 88| 4.49M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ | Branch (1013:11): [True: 4.49M, False: 0] | Branch (1013:18): [True: 4.49M, False: 0] | Branch (1013:26): [True: 4.49M, False: 0] ------------------ 1014| 4.49M| *info &= ~SPELL_COMPOUND_2; ------------------ | | 88| 4.49M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ 1015| 4.49M| if (TraceCtx* t = trace_on(scratch.trace)) ------------------ | Branch (1015:23): [True: 0, False: 4.49M] ------------------ 1016| 0| trace(*t, "compound words=3+"); 1017| 4.49M| { 1018| 4.49M| TraceScope compound_depth(trace_on(scratch.trace)); 1019| 4.49M| he = pAMgr->compound_check(word, 0, 0, 100, 0, nullptr, (hentry**)&rwords, 0, 0, info, scratch); 1020| 4.49M| } 1021| | // accept the compound with 3 or more words only if it is 1022| | // - not a dictionary word with a typo and 1023| | // - not two words written separately, 1024| | // - or if it's an arbitrary number accepted by compound rules (e.g. 999%) 1025| 4.49M| if (he && !isdigit(word[0])) ------------------ | Branch (1025:13): [True: 0, False: 4.49M] | Branch (1025:19): [True: 0, False: 0] ------------------ 1026| 0| { 1027| 0| std::vector slst; 1028| 0| bool simple; 1029| 0| { 1030| | // the suggester runs its whole search here, so report what it 1031| | // decided rather than every candidate it tried 1032| 0| TraceSuppress no_trace(scratch.trace); 1033| 0| simple = pSMgr->suggest(slst, word, nullptr, /*test_simplesug=*/true); 1034| 0| } 1035| 0| if (TraceCtx* t = trace_on(scratch.trace)) ------------------ | Branch (1035:25): [True: 0, False: 0] ------------------ 1036| 0| trace(*t, "test simplesug -> %s", 1037| 0| simple ? "fail, a simpler form of this word exists" ------------------ | Branch (1037:19): [True: 0, False: 0] ------------------ 1038| 0| : "pass, no simpler form of this word exists"); 1039| 0| if (simple) ------------------ | Branch (1039:15): [True: 0, False: 0] ------------------ 1040| 0| he = nullptr; 1041| 0| } 1042| 4.49M| } 1043| | 1044| | // LANG_hu section: `moving rule' with last dash 1045| 4.49M| if ((!he) && (langnum == LANG_hu) && (word[len - 1] == '-')) { ------------------ | Branch (1045:11): [True: 4.49M, False: 0] | Branch (1045:20): [True: 33.8k, False: 4.46M] | Branch (1045:44): [True: 13.8k, False: 20.0k] ------------------ 1046| 13.8k| std::string dup(word, 0, len - 1); 1047| 13.8k| he = pAMgr->compound_check(dup, -5, 0, 100, 0, nullptr, (hentry**)&rwords, 1, 0, info, scratch); 1048| 13.8k| } 1049| | // end of LANG specific region 1050| 4.49M| if (he) { ------------------ | Branch (1050:11): [True: 0, False: 4.49M] ------------------ 1051| 0| if (root) { ------------------ | Branch (1051:13): [True: 0, False: 0] ------------------ 1052| 0| root->assign(he->word); 1053| 0| if (complexprefixes) { ------------------ | Branch (1053:15): [True: 0, False: 0] ------------------ 1054| 0| if (utf8) ------------------ | Branch (1054:17): [True: 0, False: 0] ------------------ 1055| 0| reverseword_utf(*root); 1056| 0| else 1057| 0| reverseword(*root); 1058| 0| } 1059| 0| } 1060| 0| if (info) ------------------ | Branch (1060:13): [True: 0, False: 0] ------------------ 1061| 0| *info |= SPELL_COMPOUND; ------------------ | | 81| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 1062| 0| } 1063| 4.49M| } 1064| 17.3M| } 1065| | 1066| 17.3M| return he; 1067| 17.3M|} _ZN12HunspellImpl7suggestERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEENS0_6chrono10time_pointINSD_12steady_clockENSD_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 1075| 92.9k|std::vector HunspellImpl::suggest(const std::string& word, std::vector& suggest_candidate_stack, std::chrono::steady_clock::time_point suggest_start) { 1076| | 1077| 92.9k| if (suggest_candidate_stack.size() > MAX_CANDIDATE_STACK_DEPTH || // apply a fairly arbitrary depth limit ------------------ | | 1070| 185k|#define MAX_CANDIDATE_STACK_DEPTH 512 ------------------ | Branch (1077:7): [True: 0, False: 92.9k] | Branch (1077:7): [True: 0, False: 92.9k] ------------------ 1078| | // something very broken if suggest ends up calling itself with the same word 1079| 92.9k| std::find(suggest_candidate_stack.begin(), suggest_candidate_stack.end(), word) != suggest_candidate_stack.end()) { ------------------ | Branch (1079:7): [True: 0, False: 92.9k] ------------------ 1080| 0| return { }; 1081| 0| } 1082| | 1083| 92.9k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 92.9k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1083:7): [True: 0, False: 92.9k] ------------------ 1084| 0| return { }; 1085| | 1086| 92.9k| bool capwords; 1087| 92.9k| size_t abbv; 1088| 92.9k| int captype; 1089| 92.9k| std::vector spell_candidate_stack; 1090| 92.9k| suggest_candidate_stack.push_back(word); 1091| 92.9k| std::vector slst = suggest_internal(word, spell_candidate_stack, suggest_candidate_stack, 1092| 92.9k| capwords, abbv, captype, suggest_start); 1093| 92.9k| suggest_candidate_stack.pop_back(); 1094| | // word reversing wrapper for complex prefixes 1095| 92.9k| if (complexprefixes) { ------------------ | Branch (1095:7): [True: 4.76k, False: 88.1k] ------------------ 1096| 4.76k| for (auto& j : slst) { ------------------ | Branch (1096:18): [True: 2.37k, False: 4.76k] ------------------ 1097| 2.37k| if (utf8) ------------------ | Branch (1097:11): [True: 0, False: 2.37k] ------------------ 1098| 0| reverseword_utf(j); 1099| 2.37k| else 1100| 2.37k| reverseword(j); 1101| 2.37k| } 1102| 4.76k| } 1103| | 1104| | // capitalize 1105| 92.9k| if (capwords) { ------------------ | Branch (1105:7): [True: 24.1k, False: 68.7k] ------------------ 1106| 24.1k| for (auto& j : slst) { ------------------ | Branch (1106:18): [True: 16.7k, False: 24.1k] ------------------ 1107| 16.7k| std::string capitalized(j); 1108| 16.7k| mkinitcap(capitalized); 1109| 16.7k| if (capitalized == word) ------------------ | Branch (1109:11): [True: 0, False: 16.7k] ------------------ 1110| 0| continue; // capitalizing would just reproduce the misspelled word 1111| 16.7k| j = std::move(capitalized); 1112| 16.7k| } 1113| 24.1k| } 1114| | 1115| | // expand suggestions with dot(s) 1116| 92.9k| if (abbv && pAMgr && pAMgr->get_sugswithdots() && word.size() >= abbv) { ------------------ | Branch (1116:7): [True: 3.51k, False: 89.4k] | Branch (1116:15): [True: 3.51k, False: 0] | Branch (1116:24): [True: 0, False: 3.51k] | Branch (1116:53): [True: 0, False: 0] ------------------ 1117| 0| for (auto& j : slst) { ------------------ | Branch (1117:18): [True: 0, False: 0] ------------------ 1118| 0| j.append(word.substr(word.size() - abbv)); 1119| 0| } 1120| 0| } 1121| | 1122| | // remove bad capitalized and forbidden forms 1123| 92.9k| if (pAMgr && (pAMgr->get_keepcase() || pAMgr->get_forbiddenword())) { ------------------ | Branch (1123:7): [True: 92.9k, False: 0] | Branch (1123:17): [True: 4.80k, False: 88.1k] | Branch (1123:42): [True: 88.1k, False: 0] ------------------ 1124| 92.9k| switch (captype) { ------------------ | Branch (1124:13): [True: 48.9k, False: 43.9k] ------------------ 1125| 10.1k| case INITCAP: ------------------ | | 93| 10.1k|#define INITCAP 1 ------------------ | Branch (1125:7): [True: 10.1k, False: 82.8k] ------------------ 1126| 19.6k| case ALLCAP: ------------------ | | 94| 19.6k|#define ALLCAP 2 ------------------ | Branch (1126:7): [True: 9.56k, False: 83.3k] ------------------ 1127| 34.9k| case HUHCAP: ------------------ | | 95| 34.9k|#define HUHCAP 3 ------------------ | Branch (1127:7): [True: 15.2k, False: 77.6k] ------------------ 1128| 48.9k| case HUHINITCAP: { ------------------ | | 96| 48.9k|#define HUHINITCAP 4 ------------------ | Branch (1128:7): [True: 14.0k, False: 78.8k] ------------------ 1129| 48.9k| size_t l = 0; 1130| 82.5k| for (size_t j = 0; j < slst.size(); ++j) { ------------------ | Branch (1130:28): [True: 33.5k, False: 48.9k] ------------------ 1131| | // A space-containing suggestion can be an "insert a space" split 1132| | // whose parts each spell on their own, so it is good when every 1133| | // part spells even though the whole string does not. 1134| 33.5k| bool bad = !spell(slst[j], spell_candidate_stack, nullptr, nullptr, suggest_start); 1135| 33.5k| if (bad && slst[j].find(' ') != std::string::npos) { ------------------ | Branch (1135:15): [True: 17.6k, False: 15.8k] | Branch (1135:22): [True: 8.61k, False: 9.04k] ------------------ 1136| 8.61k| bad = false; 1137| 16.9k| for (size_t start = 0; start <= slst[j].size(); ) { ------------------ | Branch (1137:36): [True: 16.9k, False: 0] ------------------ 1138| 16.9k| size_t sp = slst[j].find(' ', start); 1139| 16.9k| size_t end = (sp == std::string::npos) ? slst[j].size() : sp; ------------------ | Branch (1139:28): [True: 2.02k, False: 14.9k] ------------------ 1140| 16.9k| std::string part = slst[j].substr(start, end - start); 1141| 16.9k| if (!part.empty() && ------------------ | Branch (1141:19): [True: 11.4k, False: 5.56k] ------------------ 1142| 11.4k| !spell(part, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1142:19): [True: 7.70k, False: 3.71k] ------------------ 1143| 7.70k| bad = true; 1144| 7.70k| break; 1145| 7.70k| } 1146| 9.28k| if (sp == std::string::npos) ------------------ | Branch (1146:19): [True: 912, False: 8.37k] ------------------ 1147| 912| break; 1148| 8.37k| start = sp + 1; 1149| 8.37k| } 1150| 8.61k| } 1151| 33.5k| if (bad) { ------------------ | Branch (1151:15): [True: 16.7k, False: 16.7k] ------------------ 1152| 16.7k| std::string s; 1153| 16.7k| std::vector w; 1154| 16.7k| if (utf8) { ------------------ | Branch (1154:17): [True: 6.67k, False: 10.0k] ------------------ 1155| 6.67k| u8_u16(w, slst[j]); 1156| 10.0k| } else { 1157| 10.0k| s = slst[j]; 1158| 10.0k| } 1159| 16.7k| mkallsmall2(s, w); 1160| 16.7k| if (spell(s, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1160:17): [True: 54, False: 16.6k] ------------------ 1161| 54| slst[l] = std::move(s); 1162| 54| ++l; 1163| 16.6k| } else { 1164| 16.6k| mkinitcap2(s, w); 1165| 16.6k| if (spell(s, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1165:19): [True: 51, False: 16.6k] ------------------ 1166| 51| slst[l] = std::move(s); 1167| 51| ++l; 1168| 51| } 1169| 16.6k| } 1170| 16.7k| } else { 1171| 16.7k| slst[l] = slst[j]; 1172| 16.7k| ++l; 1173| 16.7k| } 1174| 33.5k| } 1175| 48.9k| slst.resize(l); 1176| 48.9k| } 1177| 92.9k| } 1178| 92.9k| } 1179| | 1180| | // remove duplications 1181| 92.9k| size_t l = 0; 1182| 112k| for (size_t j = 0; j < slst.size(); ++j) { ------------------ | Branch (1182:22): [True: 19.2k, False: 92.9k] ------------------ 1183| 19.2k| slst[l] = slst[j]; 1184| 29.0k| for (size_t k = 0; k < l; ++k) { ------------------ | Branch (1184:24): [True: 10.7k, False: 18.3k] ------------------ 1185| 10.7k| if (slst[k] == slst[j]) { ------------------ | Branch (1185:11): [True: 866, False: 9.87k] ------------------ 1186| 866| --l; 1187| 866| break; 1188| 866| } 1189| 10.7k| } 1190| 19.2k| ++l; 1191| 19.2k| } 1192| 92.9k| slst.resize(l); 1193| | 1194| | // output conversion 1195| 92.9k| RepList* rl = (pAMgr) ? pAMgr->get_oconvtable() : nullptr; ------------------ | Branch (1195:17): [True: 92.9k, False: 0] ------------------ 1196| 92.9k| if (rl) { ------------------ | Branch (1196:7): [True: 5.04k, False: 87.9k] ------------------ 1197| | // hold the converted suggestions to the same ceiling as an analysis 1198| 5.04k| size_t total = 0; 1199| 5.04k| size_t l = 0; 1200| 5.83k| for (size_t i = 0; i < slst.size(); ++i) { ------------------ | Branch (1200:24): [True: 792, False: 5.04k] ------------------ 1201| 792| std::string wspace; 1202| 792| if (rl->conv(slst[i], wspace, MAXMORPHRESULT - total)) { ------------------ | | 114| 792|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (1202:11): [True: 233, False: 559] ------------------ 1203| 233| slst[i] = std::move(wspace); 1204| 233| } 1205| 792| if (slst[i].size() > MAXMORPHRESULT - total) ------------------ | | 114| 792|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (1205:11): [True: 0, False: 792] ------------------ 1206| 0| break; 1207| 792| total += slst[i].size(); 1208| | // gh#1002: OCONV can map a generated form back to the input word 1209| | // (e.g. "románórum" -> "romanórum" when the user typed "romanórum"), 1210| | // leaving the misspelled word as its own suggestion. 1211| 792| if (slst[i] == word) ------------------ | Branch (1211:11): [True: 0, False: 792] ------------------ 1212| 0| continue; 1213| 792| if (l != i) ------------------ | Branch (1213:11): [True: 0, False: 792] ------------------ 1214| 0| slst[l] = std::move(slst[i]); 1215| 792| ++l; 1216| 792| } 1217| 5.04k| slst.resize(l); 1218| 5.04k| } 1219| 92.9k| return slst; 1220| 92.9k|} _ZN12HunspellImpl7suggestERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1222| 64.9k|std::vector HunspellImpl::suggest(const std::string& word) { 1223| 64.9k| std::vector suggest_candidate_stack; 1224| 64.9k| auto suggest_start = std::chrono::steady_clock::now(); 1225| 64.9k| return suggest(word, suggest_candidate_stack, suggest_start); 1226| 64.9k|} _ZN12HunspellImpl16suggest_internalERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEESC_RbRmRiNS0_6chrono10time_pointINSG_12steady_clockENSG_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 1232| 92.9k| std::chrono::steady_clock::time_point suggest_start) { 1233| | // The candidates tried here are the tool's own guesses, not the word the 1234| | // user asked about. 1235| 92.9k| TraceSuppress no_trace(m_trace.get()); 1236| | 1237| 92.9k| captype = NOCAP; ------------------ | | 92| 92.9k|#define NOCAP 0 ------------------ 1238| 92.9k| abbv = 0; 1239| 92.9k| capwords = false; 1240| | 1241| 92.9k| std::vector slst; 1242| | 1243| 92.9k| int onlycmpdsug = 0; 1244| 92.9k| if (!pSMgr || m_HMgrs.empty()) ------------------ | Branch (1244:7): [True: 0, False: 92.9k] | Branch (1244:17): [True: 0, False: 92.9k] ------------------ 1245| 0| return slst; 1246| | 1247| | // process XML input of the simplified API (see manual) 1248| 92.9k| if (word.compare(0, sizeof(SPELL_XML) - 3, SPELL_XML, sizeof(SPELL_XML) - 3) == 0) { ------------------ | | 80| 92.9k|#define SPELL_XML "" ------------------ if (word.compare(0, sizeof(SPELL_XML) - 3, SPELL_XML, sizeof(SPELL_XML) - 3) == 0) { ------------------ | | 80| 92.9k|#define SPELL_XML "" ------------------ if (word.compare(0, sizeof(SPELL_XML) - 3, SPELL_XML, sizeof(SPELL_XML) - 3) == 0) { ------------------ | | 80| 92.9k|#define SPELL_XML "" ------------------ | Branch (1248:7): [True: 23.4k, False: 69.4k] ------------------ 1249| 23.4k| if (word.size() > MAXSPELLMLLEN) ------------------ | | 88| 23.4k|#define MAXSPELLMLLEN 8192 ------------------ | Branch (1249:9): [True: 456, False: 23.0k] ------------------ 1250| 456| return slst; 1251| 23.0k| return spellml(word); 1252| 23.4k| } 1253| 69.4k| if (utf8) { ------------------ | Branch (1253:7): [True: 33.8k, False: 35.5k] ------------------ 1254| 33.8k| if (word.size() >= MAXWORDUTF8LEN) ------------------ | | 87| 33.8k|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 33.8k|#define MAXWORDLEN 100 | | ------------------ ------------------ | Branch (1254:9): [True: 108, False: 33.7k] ------------------ 1255| 108| return slst; 1256| 35.5k| } else { 1257| 35.5k| if (word.size() >= MAXWORDLEN) ------------------ | | 90| 35.5k|#define MAXWORDLEN 100 ------------------ | Branch (1257:9): [True: 140, False: 35.4k] ------------------ 1258| 140| return slst; 1259| 35.5k| } 1260| 69.2k| size_t wl = 0; 1261| | 1262| 69.2k| std::string scw; 1263| 69.2k| std::vector sunicw; 1264| | 1265| | // input conversion 1266| 69.2k| RepList* rl = (pAMgr) ? pAMgr->get_iconvtable() : nullptr; ------------------ | Branch (1266:17): [True: 69.2k, False: 0] ------------------ 1267| 69.2k| { 1268| 69.2k| std::string wspace; 1269| | 1270| 69.2k| bool convstatus = rl ? rl->conv(word, wspace) : false; ------------------ | Branch (1270:23): [True: 3.79k, False: 65.4k] ------------------ 1271| 69.2k| if (convstatus) { ------------------ | Branch (1271:9): [True: 0, False: 69.2k] ------------------ 1272| | // the input conversion can grow the word without limit, so hold the 1273| | // converted word to the same maximum length as the raw word 1274| 0| if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 87| 0|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 0|#define MAXWORDLEN 100 | | ------------------ ------------------ if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 90| 0|#define MAXWORDLEN 100 ------------------ | Branch (1274:11): [True: 0, False: 0] | Branch (1274:11): [True: 0, False: 0] ------------------ 1275| 0| return slst; 1276| 0| wl = cleanword2(scw, sunicw, wspace, &captype, &abbv); 1277| 0| } else 1278| 69.2k| wl = cleanword2(scw, sunicw, word, &captype, &abbv); 1279| | 1280| 69.2k| if (wl == 0) ------------------ | Branch (1280:9): [True: 0, False: 69.2k] ------------------ 1281| 0| return slst; 1282| | 1283| 69.2k|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 1284| 69.2k| if (wl > 32768) ------------------ | Branch (1284:9): [True: 0, False: 69.2k] ------------------ 1285| 0| return slst; 1286| 69.2k|#endif 1287| 69.2k| } 1288| | 1289| 69.2k| bool good = false; 1290| | 1291| | // check capitalized form for FORCEUCASE 1292| 69.2k| if (pAMgr && captype == NOCAP && pAMgr->get_forceucase()) { ------------------ | | 92| 138k|#define NOCAP 0 ------------------ | Branch (1292:7): [True: 69.2k, False: 0] | Branch (1292:16): [True: 20.2k, False: 48.9k] | Branch (1292:36): [True: 0, False: 20.2k] ------------------ 1293| 0| int info = SPELL_ORIGCAP; ------------------ | | 86| 0|#define SPELL_ORIGCAP (1 << 5) ------------------ 1294| 0| if (checkword(scw, &info, nullptr, suggest_start)) { ------------------ | Branch (1294:9): [True: 0, False: 0] ------------------ 1295| 0| std::string form(std::move(scw)); 1296| 0| mkinitcap(form); 1297| 0| slst.push_back(std::move(form)); 1298| 0| return slst; 1299| 0| } 1300| 0| } 1301| | 1302| 69.2k| switch (captype) { ------------------ | Branch (1302:11): [True: 69.2k, False: 0] ------------------ 1303| 20.2k| case NOCAP: { ------------------ | | 92| 20.2k|#define NOCAP 0 ------------------ | Branch (1303:5): [True: 20.2k, False: 48.9k] ------------------ 1304| 20.2k| good |= pSMgr->suggest(slst, scw, &onlycmpdsug); 1305| 20.2k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 20.2k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1305:11): [True: 0, False: 20.2k] ------------------ 1306| 0| return slst; 1307| 20.2k| if (abbv) { ------------------ | Branch (1307:11): [True: 1.66k, False: 18.5k] ------------------ 1308| 1.66k| std::string wspace(scw); 1309| 1.66k| wspace.push_back('.'); 1310| 1.66k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1311| 1.66k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 1.66k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1311:13): [True: 0, False: 1.66k] ------------------ 1312| 0| return slst; 1313| 1.66k| } 1314| 20.2k| break; 1315| 20.2k| } 1316| | 1317| 20.2k| case INITCAP: { ------------------ | | 93| 10.1k|#define INITCAP 1 ------------------ | Branch (1317:5): [True: 10.1k, False: 59.1k] ------------------ 1318| 10.1k| capwords = true; 1319| 10.1k| good |= pSMgr->suggest(slst, scw, &onlycmpdsug); 1320| 10.1k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 10.1k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1320:11): [True: 0, False: 10.1k] ------------------ 1321| 0| return slst; 1322| 10.1k| std::string wspace(scw); 1323| 10.1k| mkallsmall2(wspace, sunicw); 1324| 10.1k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1325| 10.1k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 10.1k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1325:11): [True: 0, False: 10.1k] ------------------ 1326| 0| return slst; 1327| 10.1k| break; 1328| 10.1k| } 1329| 14.0k| case HUHINITCAP: ------------------ | | 96| 14.0k|#define HUHINITCAP 4 ------------------ | Branch (1329:5): [True: 14.0k, False: 55.1k] ------------------ 1330| 14.0k| capwords = true; 1331| | /* FALLTHROUGH */ 1332| 29.3k| case HUHCAP: { ------------------ | | 95| 29.3k|#define HUHCAP 3 ------------------ | Branch (1332:5): [True: 15.2k, False: 53.9k] ------------------ 1333| 29.3k| good |= pSMgr->suggest(slst, scw, &onlycmpdsug); 1334| 29.3k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 29.3k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1334:11): [True: 0, False: 29.3k] ------------------ 1335| 0| return slst; 1336| | // something.The -> something. The 1337| 29.3k| size_t dot_pos = scw.find('.'); 1338| 29.3k| if (dot_pos != std::string::npos) { ------------------ | Branch (1338:11): [True: 10.6k, False: 18.7k] ------------------ 1339| 10.6k| std::string postdot = scw.substr(dot_pos + 1); 1340| 10.6k| int captype_; 1341| 10.6k| if (utf8) { ------------------ | Branch (1341:13): [True: 2.89k, False: 7.72k] ------------------ 1342| 2.89k| std::vector postdotu; 1343| 2.89k| u8_u16(postdotu, postdot); 1344| 2.89k| captype_ = get_captype_utf8(postdotu, langnum); 1345| 7.72k| } else { 1346| 7.72k| captype_ = get_captype(postdot, csconv); 1347| 7.72k| } 1348| 10.6k| if (captype_ == INITCAP) { ------------------ | | 93| 10.6k|#define INITCAP 1 ------------------ | Branch (1348:13): [True: 5.94k, False: 4.68k] ------------------ 1349| 5.94k| std::string str(scw); 1350| 5.94k| str.insert(dot_pos + 1, 1, ' '); 1351| 5.94k| insert_sug(slst, str); 1352| 5.94k| } 1353| 10.6k| } 1354| | 1355| 29.3k| std::string wspace; 1356| | 1357| 29.3k| if (captype == HUHINITCAP) { ------------------ | | 96| 29.3k|#define HUHINITCAP 4 ------------------ | Branch (1357:11): [True: 14.0k, False: 15.2k] ------------------ 1358| | // TheOpenOffice.org -> The OpenOffice.org 1359| 14.0k| wspace = scw; 1360| 14.0k| mkinitsmall2(wspace, sunicw); 1361| 14.0k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1362| 14.0k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 14.0k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1362:13): [True: 0, False: 14.0k] ------------------ 1363| 0| return slst; 1364| 14.0k| } 1365| 29.3k| wspace = scw; 1366| 29.3k| mkallsmall2(wspace, sunicw); 1367| 29.3k| if (spell(wspace, spell_candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (1367:11): [True: 1.28k, False: 28.0k] ------------------ 1368| 1.28k| insert_sug(slst, wspace); 1369| 29.3k| size_t prevns = slst.size(); 1370| 29.3k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1371| 29.3k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 29.3k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1371:11): [True: 1, False: 29.3k] ------------------ 1372| 1| return slst; 1373| 29.3k| if (captype == HUHINITCAP) { ------------------ | | 96| 29.3k|#define HUHINITCAP 4 ------------------ | Branch (1373:11): [True: 14.0k, False: 15.2k] ------------------ 1374| 14.0k| mkinitcap2(wspace, sunicw); 1375| 14.0k| if (spell(wspace, spell_candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (1375:13): [True: 513, False: 13.5k] ------------------ 1376| 513| insert_sug(slst, wspace); 1377| 14.0k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1378| 14.0k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 14.0k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1378:13): [True: 0, False: 14.0k] ------------------ 1379| 0| return slst; 1380| 14.0k| } 1381| | // aNew -> "a New" (instead of "a new") 1382| 30.1k| for (size_t j = prevns; j < slst.size(); ++j) { ------------------ | Branch (1382:31): [True: 774, False: 29.3k] ------------------ 1383| 774| const char* space = strchr(slst[j].c_str(), ' '); 1384| 774| if (space) { ------------------ | Branch (1384:13): [True: 420, False: 354] ------------------ 1385| 420| size_t slen = strlen(space + 1); 1386| | // different case after space (need capitalisation) 1387| 420| if ((slen < wl) && strcmp(scw.c_str() + wl - slen, space + 1) != 0) { ------------------ | Branch (1387:15): [True: 420, False: 0] | Branch (1387:30): [True: 420, False: 0] ------------------ 1388| 420| std::string first(slst[j].c_str(), space + 1); 1389| 420| std::string second(space + 1); 1390| 420| std::vector w; 1391| 420| if (utf8) ------------------ | Branch (1391:17): [True: 133, False: 287] ------------------ 1392| 133| u8_u16(w, second); 1393| 420| mkinitcap2(second, w); 1394| | // set as first suggestion 1395| 420| slst.erase(slst.begin() + j); 1396| 420| slst.insert(slst.begin(), first + second); 1397| 420| } 1398| 420| } 1399| 774| } 1400| 29.3k| break; 1401| 29.3k| } 1402| | 1403| 9.56k| case ALLCAP: { ------------------ | | 94| 9.56k|#define ALLCAP 2 ------------------ | Branch (1403:5): [True: 9.56k, False: 59.6k] ------------------ 1404| 9.56k| std::string wspace(scw); 1405| 9.56k| mkallsmall2(wspace, sunicw); 1406| 9.56k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1407| 9.56k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 9.56k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1407:11): [True: 0, False: 9.56k] ------------------ 1408| 0| return slst; 1409| 9.56k| if (pAMgr && pAMgr->get_keepcase() && spell(wspace, spell_candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (1409:11): [True: 9.56k, False: 0] | Branch (1409:20): [True: 394, False: 9.16k] | Branch (1409:45): [True: 0, False: 394] ------------------ 1410| 0| insert_sug(slst, wspace); 1411| 9.56k| mkinitcap2(wspace, sunicw); 1412| 9.56k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1413| 9.56k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 9.56k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1413:11): [True: 0, False: 9.56k] ------------------ 1414| 0| return slst; 1415| 9.56k| for (auto& j : slst) { ------------------ | Branch (1415:20): [True: 465, False: 9.56k] ------------------ 1416| 465| mkallcap(j); 1417| 465| if (pAMgr && pAMgr->get_checksharps()) { ------------------ | Branch (1417:13): [True: 465, False: 0] | Branch (1417:22): [True: 0, False: 465] ------------------ 1418| 0| if (utf8) { ------------------ | Branch (1418:15): [True: 0, False: 0] ------------------ 1419| 0| mystrrep(j, "\xC3\x9F", "SS"); 1420| 0| } else { 1421| 0| mystrrep(j, "\xDF", "SS"); 1422| 0| } 1423| 0| } 1424| 465| } 1425| 9.56k| break; 1426| 9.56k| } 1427| 69.2k| } 1428| | 1429| | // LANG_hu section: replace '-' with ' ' in Hungarian 1430| 69.2k| if (langnum == LANG_hu) { ------------------ | Branch (1430:7): [True: 3.85k, False: 65.3k] ------------------ 1431| 3.85k| for (auto& j : slst) { ------------------ | Branch (1431:18): [True: 373, False: 3.85k] ------------------ 1432| 373| size_t pos = j.find('-'); 1433| 373| if (pos != std::string::npos) { ------------------ | Branch (1433:11): [True: 148, False: 225] ------------------ 1434| 148| int info = 0; 1435| 148| std::string w(j.substr(0, pos)); 1436| 148| w.append(j.substr(pos + 1)); 1437| 148| (void)spell(w, spell_candidate_stack, &info, nullptr, suggest_start); 1438| 148| if ((info & SPELL_COMPOUND) && (info & SPELL_FORBIDDEN)) { ------------------ | | 81| 148|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ if ((info & SPELL_COMPOUND) && (info & SPELL_FORBIDDEN)) { ------------------ | | 82| 0|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (1438:13): [True: 0, False: 148] | Branch (1438:40): [True: 0, False: 0] ------------------ 1439| 0| j[pos] = ' '; 1440| 0| } else 1441| 148| j[pos] = '-'; 1442| 148| } 1443| 373| } 1444| 3.85k| } 1445| | // END OF LANG_hu section 1446| | // try ngram approach since found nothing good suggestion 1447| 69.2k| if (!good && pAMgr && (slst.empty() || onlycmpdsug) && (pAMgr->get_maxngramsugs() != 0)) { ------------------ | Branch (1447:7): [True: 69.1k, False: 59] | Branch (1447:16): [True: 69.1k, False: 0] | Branch (1447:26): [True: 59.3k, False: 9.83k] | Branch (1447:42): [True: 9.68k, False: 147] | Branch (1447:58): [True: 61.4k, False: 7.58k] ------------------ 1448| 61.4k| switch (captype) { ------------------ | Branch (1448:13): [True: 61.4k, False: 0] ------------------ 1449| 17.2k| case NOCAP: { ------------------ | | 92| 17.2k|#define NOCAP 0 ------------------ | Branch (1449:7): [True: 17.2k, False: 44.1k] ------------------ 1450| 17.2k| pSMgr->ngsuggest(slst, scw.c_str(), m_HMgrs, NOCAP); ------------------ | | 92| 17.2k|#define NOCAP 0 ------------------ 1451| 17.2k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 17.2k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1451:13): [True: 0, False: 17.2k] ------------------ 1452| 0| return slst; 1453| 17.2k| break; 1454| 17.2k| } 1455| | /* FALLTHROUGH */ 1456| 17.2k| case HUHINITCAP: ------------------ | | 96| 13.2k|#define HUHINITCAP 4 ------------------ | Branch (1456:7): [True: 13.2k, False: 48.1k] ------------------ 1457| 13.2k| capwords = true; 1458| | /* FALLTHROUGH */ 1459| 27.2k| case HUHCAP: { ------------------ | | 95| 27.2k|#define HUHCAP 3 ------------------ | Branch (1459:7): [True: 14.0k, False: 47.3k] ------------------ 1460| 27.2k| std::string wspace(scw); 1461| 27.2k| mkallsmall2(wspace, sunicw); 1462| 27.2k| pSMgr->ngsuggest(slst, wspace.c_str(), m_HMgrs, HUHCAP); ------------------ | | 95| 27.2k|#define HUHCAP 3 ------------------ 1463| 27.2k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 27.2k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1463:13): [True: 0, False: 27.2k] ------------------ 1464| 0| return slst; 1465| 27.2k| break; 1466| 27.2k| } 1467| 27.2k| case INITCAP: { ------------------ | | 93| 8.56k|#define INITCAP 1 ------------------ | Branch (1467:7): [True: 8.56k, False: 52.8k] ------------------ 1468| 8.56k| capwords = true; 1469| 8.56k| std::string wspace(scw); 1470| 8.56k| mkallsmall2(wspace, sunicw); 1471| 8.56k| pSMgr->ngsuggest(slst, wspace.c_str(), m_HMgrs, INITCAP); ------------------ | | 93| 8.56k|#define INITCAP 1 ------------------ 1472| 8.56k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 8.56k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1472:13): [True: 0, False: 8.56k] ------------------ 1473| 0| return slst; 1474| 8.56k| break; 1475| 8.56k| } 1476| 8.56k| case ALLCAP: { ------------------ | | 94| 8.30k|#define ALLCAP 2 ------------------ | Branch (1476:7): [True: 8.30k, False: 53.1k] ------------------ 1477| 8.30k| std::string wspace(scw); 1478| 8.30k| mkallsmall2(wspace, sunicw); 1479| 8.30k| size_t oldns = slst.size(); 1480| 8.30k| pSMgr->ngsuggest(slst, wspace.c_str(), m_HMgrs, ALLCAP); ------------------ | | 94| 8.30k|#define ALLCAP 2 ------------------ 1481| 8.30k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 8.30k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1481:13): [True: 0, False: 8.30k] ------------------ 1482| 0| return slst; 1483| 10.6k| for (size_t j = oldns; j < slst.size(); ++j) { ------------------ | Branch (1483:32): [True: 2.33k, False: 8.30k] ------------------ 1484| 2.33k| mkallcap(slst[j]); 1485| 2.33k| } 1486| 8.30k| break; 1487| 8.30k| } 1488| 61.4k| } 1489| 61.4k| } 1490| | 1491| | // try dash suggestion (Afo-American -> Afro-American) 1492| | // Note: LibreOffice was modified to treat dashes as word 1493| | // characters to check "scot-free" etc. word forms, but 1494| | // we need to handle suggestions for "Afo-American", etc., 1495| | // while "Afro-American" is missing from the dictionary. 1496| | // TODO avoid possible overgeneration 1497| 69.2k| size_t dash_pos = scw.find('-'); 1498| 69.2k| if (dash_pos != std::string::npos) { ------------------ | Branch (1498:7): [True: 34.7k, False: 34.4k] ------------------ 1499| 34.7k| int nodashsug = 1; 1500| 45.1k| for (size_t j = 0; j < slst.size() && nodashsug == 1; ++j) { ------------------ | Branch (1500:24): [True: 11.0k, False: 34.1k] | Branch (1500:43): [True: 10.3k, False: 668] ------------------ 1501| 10.3k| if (slst[j].find('-') != std::string::npos) ------------------ | Branch (1501:11): [True: 6.16k, False: 4.17k] ------------------ 1502| 6.16k| nodashsug = 0; 1503| 10.3k| } 1504| | 1505| 34.7k| size_t prev_pos = 0; 1506| 34.7k| bool last = false; 1507| | 1508| 104k| while (!good && nodashsug && !last) { ------------------ | Branch (1508:12): [True: 104k, False: 27] | Branch (1508:21): [True: 69.9k, False: 34.1k] | Branch (1508:34): [True: 69.3k, False: 650] ------------------ 1509| 69.3k| if (dash_pos == scw.size()) ------------------ | Branch (1509:11): [True: 5.09k, False: 64.2k] ------------------ 1510| 5.09k| last = true; 1511| 69.3k| std::string chunk = scw.substr(prev_pos, dash_pos - prev_pos); 1512| 69.3k| if (chunk != word && !spell(chunk, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1512:11): [True: 69.3k, False: 0] | Branch (1512:28): [True: 27.9k, False: 41.3k] ------------------ 1513| 27.9k| std::vector nlst = suggest(chunk, suggest_candidate_stack, suggest_start); 1514| 27.9k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 27.9k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1514:13): [True: 1, False: 27.9k] ------------------ 1515| 1| return slst; 1516| 38.1k| for (auto j = nlst.rbegin(); j != nlst.rend(); ++j) { ------------------ | Branch (1516:38): [True: 10.1k, False: 27.9k] ------------------ 1517| 10.1k| std::string wspace = scw.substr(0, prev_pos); 1518| 10.1k| wspace.append(*j); 1519| 10.1k| if (!last) { ------------------ | Branch (1519:15): [True: 8.64k, False: 1.54k] ------------------ 1520| 8.64k| wspace.append("-"); 1521| 8.64k| wspace.append(scw.substr(dash_pos + 1)); 1522| 8.64k| } 1523| 10.1k| int info = 0; 1524| 10.1k| if (pAMgr && pAMgr->get_forbiddenword()) ------------------ | Branch (1524:15): [True: 10.1k, False: 0] | Branch (1524:24): [True: 10.1k, False: 0] ------------------ 1525| 10.1k| checkword(wspace, &info, nullptr, suggest_start); 1526| 10.1k| if (!(info & SPELL_FORBIDDEN)) ------------------ | | 82| 10.1k|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (1526:15): [True: 10.1k, False: 0] ------------------ 1527| 10.1k| insert_sug(slst, wspace); 1528| 10.1k| } 1529| 27.9k| nodashsug = 0; 1530| 27.9k| } 1531| 69.3k| if (!last) { ------------------ | Branch (1531:11): [True: 64.2k, False: 5.09k] ------------------ 1532| 64.2k| prev_pos = dash_pos + 1; 1533| 64.2k| dash_pos = scw.find('-', prev_pos); 1534| 64.2k| } 1535| 69.3k| if (dash_pos == std::string::npos) ------------------ | Branch (1535:11): [True: 12.7k, False: 56.5k] ------------------ 1536| 12.7k| dash_pos = scw.size(); 1537| 69.3k| } 1538| 34.7k| } 1539| 69.2k| return slst; 1540| 69.2k|} _ZN12HunspellImpl4stemERKNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEE: 1546| 1.00k|std::vector HunspellImpl::stem(const std::vector& desc) { 1547| 1.00k| std::vector slst; 1548| | 1549| 1.00k| std::string result2; 1550| 1.00k| if (desc.empty()) ------------------ | Branch (1550:7): [True: 935, False: 71] ------------------ 1551| 935| return slst; 1552| 71| for (const auto& i : desc) { ------------------ | Branch (1552:22): [True: 71, False: 71] ------------------ 1553| 71| if (result2.size() > MAXMORPHRESULT) ------------------ | | 114| 71|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (1553:9): [True: 0, False: 71] ------------------ 1554| 0| break; 1555| | 1556| 71| std::string result; 1557| | 1558| | // add compound word parts (except the last one) 1559| 71| std::string tok(i, append_compound_parts(i, result)); 1560| 71| size_t alt = 0; 1561| 71| while ((alt = tok.find(" | ", alt)) != std::string::npos) { ------------------ | Branch (1561:12): [True: 0, False: 71] ------------------ 1562| 0| tok[alt + 1] = MSEP_ALT; ------------------ | | 123| 0|#define MSEP_ALT '\v' ------------------ 1563| 0| } 1564| 71| std::vector pl = line_tok(tok, MSEP_ALT); ------------------ | | 123| 71|#define MSEP_ALT '\v' ------------------ 1565| 71| for (auto& k : pl) { ------------------ | Branch (1565:18): [True: 71, False: 71] ------------------ 1566| 71| if (result2.size() > MAXMORPHRESULT) ------------------ | | 114| 71|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (1566:11): [True: 0, False: 71] ------------------ 1567| 0| break; 1568| | 1569| | // add derivational suffixes 1570| 71| if (k.find(MORPH_DERI_SFX) != std::string::npos) { ------------------ | | 109| 71|#define MORPH_DERI_SFX "ds:" ------------------ | Branch (1570:11): [True: 0, False: 71] ------------------ 1571| | // remove inflectional suffixes 1572| 0| const size_t is = k.find(MORPH_INFL_SFX); ------------------ | | 110| 0|#define MORPH_INFL_SFX "is:" ------------------ 1573| 0| if (is != std::string::npos) ------------------ | Branch (1573:13): [True: 0, False: 0] ------------------ 1574| 0| k.resize(is); 1575| 0| std::vector singlepl; 1576| 0| singlepl.push_back(k); 1577| 0| std::string sg = pSMgr->suggest_gen(singlepl, k); 1578| 0| if (!sg.empty()) { ------------------ | Branch (1578:13): [True: 0, False: 0] ------------------ 1579| 0| std::vector gen = line_tok(sg, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1580| 0| for (auto& j : gen) { ------------------ | Branch (1580:24): [True: 0, False: 0] ------------------ 1581| 0| result2.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1582| 0| result2.append(result); 1583| 0| result2.append(j); 1584| 0| } 1585| 0| } 1586| 71| } else { 1587| 71| result2.push_back(MSEP_REC); ------------------ | | 122| 71|#define MSEP_REC '\n' ------------------ 1588| 71| result2.append(result); 1589| 71| if (k.find(MORPH_SURF_PFX) != std::string::npos) { ------------------ | | 112| 71|#define MORPH_SURF_PFX "sp:" ------------------ | Branch (1589:13): [True: 0, False: 71] ------------------ 1590| 0| std::string field; 1591| 0| copy_field(field, k, MORPH_SURF_PFX); ------------------ | | 112| 0|#define MORPH_SURF_PFX "sp:" ------------------ 1592| 0| result2.append(field); 1593| 0| } 1594| 71| std::string field; 1595| 71| copy_field(field, k, MORPH_STEM); ------------------ | | 103| 71|#define MORPH_STEM "st:" ------------------ 1596| 71| result2.append(field); 1597| 71| } 1598| 71| } 1599| 71| } 1600| 71| slst = line_tok(result2, MSEP_REC); ------------------ | | 122| 71|#define MSEP_REC '\n' ------------------ 1601| 71| uniqlist(slst); 1602| 71| return slst; 1603| 1.00k|} _ZN12HunspellImpl4stemERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1605| 1.00k|std::vector HunspellImpl::stem(const std::string& word) { 1606| 1.00k| return stem(analyze(word)); 1607| 1.00k|} _ZN12HunspellImpl9mkinitcapERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1617| 16.7k|void HunspellImpl::mkinitcap(std::string& u8) { 1618| 16.7k| if (utf8) { ------------------ | Branch (1618:7): [True: 4.84k, False: 11.9k] ------------------ 1619| 4.84k| std::vector u16; 1620| 4.84k| u8_u16(u16, u8); 1621| 4.84k| ::mkinitcap_utf(u16, langnum); 1622| 4.84k| u16_u8(u8, u16); 1623| 11.9k| } else { 1624| 11.9k| ::mkinitcap(u8, csconv); 1625| 11.9k| } 1626| 16.7k|} _ZN12HunspellImpl10mkinitcap2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEE: 1628| 1.98M|int HunspellImpl::mkinitcap2(std::string& u8, std::vector& u16) { 1629| 1.98M| if (utf8) { ------------------ | Branch (1629:7): [True: 350k, False: 1.63M] ------------------ 1630| 350k| ::mkinitcap_utf(u16, langnum); 1631| 350k| u16_u8(u8, u16); 1632| 1.63M| } else { 1633| 1.63M| ::mkinitcap(u8, csconv); 1634| 1.63M| } 1635| 1.98M| return u8.size(); 1636| 1.98M|} _ZN12HunspellImpl12mkinitsmall2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEE: 1638| 233k|int HunspellImpl::mkinitsmall2(std::string& u8, std::vector& u16) { 1639| 233k| if (utf8) { ------------------ | Branch (1639:7): [True: 33.1k, False: 200k] ------------------ 1640| 33.1k| ::mkinitsmall_utf(u16, langnum); 1641| 33.1k| u16_u8(u8, u16); 1642| 200k| } else { 1643| 200k| ::mkinitsmall(u8, csconv); 1644| 200k| } 1645| 233k| return u8.size(); 1646| 233k|} _ZN12HunspellImpl3addERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1648| 5.80k|int HunspellImpl::add(const std::string& word) { 1649| 5.80k| if (!m_HMgrs.empty()) ------------------ | Branch (1649:7): [True: 5.80k, False: 0] ------------------ 1650| 5.80k| return m_HMgrs[0]->add(word); 1651| 0| return 0; 1652| 5.80k|} _ZN12HunspellImpl14add_with_affixERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 1660| 2.37k|int HunspellImpl::add_with_affix(const std::string& word, const std::string& example) { 1661| 2.37k| if (!m_HMgrs.empty()) ------------------ | Branch (1661:7): [True: 2.37k, False: 0] ------------------ 1662| 2.37k| return m_HMgrs[0]->add_with_affix(word, example); 1663| 0| return 0; 1664| 2.37k|} _ZN12HunspellImpl10cat_resultERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKS6_: 1683| 429k|void HunspellImpl::cat_result(std::string& result, const std::string& st) { 1684| 429k| if (result.size() > MAXMORPHRESULT) ------------------ | | 114| 429k|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (1684:7): [True: 0, False: 429k] ------------------ 1685| 0| return; 1686| 429k| if (!st.empty()) { ------------------ | Branch (1686:7): [True: 1.34k, False: 428k] ------------------ 1687| 1.34k| if (!result.empty()) ------------------ | Branch (1687:9): [True: 0, False: 1.34k] ------------------ 1688| 0| result.append("\n"); 1689| 1.34k| result.append(st); 1690| 1.34k| } 1691| 429k|} _ZN12HunspellImpl7analyzeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1693| 8.31k|std::vector HunspellImpl::analyze(const std::string& word) { 1694| 8.31k| std::vector slst = analyze_internal(word); 1695| | // output conversion 1696| 8.31k| RepList* rl = (pAMgr) ? pAMgr->get_oconvtable() : nullptr; ------------------ | Branch (1696:17): [True: 8.31k, False: 0] ------------------ 1697| 8.31k| if (rl) { ------------------ | Branch (1697:7): [True: 434, False: 7.87k] ------------------ 1698| | // the output conversion can multiply the length of every line, so hold the 1699| | // converted analysis to the same ceiling as the raw analysis 1700| 434| size_t total = 0; 1701| 434| size_t i = 0; 1702| 459| for (; i < slst.size(); ++i) { ------------------ | Branch (1702:12): [True: 25, False: 434] ------------------ 1703| 25| std::string wspace; 1704| 25| if (rl->conv(slst[i], wspace, MAXMORPHRESULT - total)) { ------------------ | | 114| 25|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (1704:11): [True: 0, False: 25] ------------------ 1705| 0| slst[i] = std::move(wspace); 1706| 0| } 1707| 25| if (slst[i].size() > MAXMORPHRESULT - total) ------------------ | | 114| 25|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (1707:11): [True: 0, False: 25] ------------------ 1708| 0| break; 1709| 25| total += slst[i].size(); 1710| 25| } 1711| 434| slst.resize(i); 1712| 434| } 1713| 8.31k| return slst; 1714| 8.31k|} _ZN12HunspellImpl16analyze_internalERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1716| 8.31k|std::vector HunspellImpl::analyze_internal(const std::string& word) { 1717| 8.31k| std::vector candidate_stack, slst; 1718| 8.31k| if (!pSMgr || m_HMgrs.empty()) ------------------ | Branch (1718:7): [True: 0, False: 8.31k] | Branch (1718:17): [True: 0, False: 8.31k] ------------------ 1719| 0| return slst; 1720| 8.31k| if (utf8) { ------------------ | Branch (1720:7): [True: 3.92k, False: 4.38k] ------------------ 1721| 3.92k| if (word.size() >= MAXWORDUTF8LEN) ------------------ | | 87| 3.92k|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 3.92k|#define MAXWORDLEN 100 | | ------------------ ------------------ | Branch (1721:9): [True: 333, False: 3.58k] ------------------ 1722| 333| return slst; 1723| 4.38k| } else { 1724| 4.38k| if (word.size() >= MAXWORDLEN) ------------------ | | 90| 4.38k|#define MAXWORDLEN 100 ------------------ | Branch (1724:9): [True: 580, False: 3.80k] ------------------ 1725| 580| return slst; 1726| 4.38k| } 1727| 7.39k| int captype = NOCAP; ------------------ | | 92| 7.39k|#define NOCAP 0 ------------------ 1728| 7.39k| size_t abbv = 0; 1729| 7.39k| size_t wl = 0; 1730| | 1731| 7.39k| std::string scw; 1732| 7.39k| std::vector sunicw; 1733| | 1734| | // input conversion 1735| 7.39k| RepList* rl = (pAMgr) ? pAMgr->get_iconvtable() : nullptr; ------------------ | Branch (1735:17): [True: 7.39k, False: 0] ------------------ 1736| 7.39k| { 1737| 7.39k| std::string wspace; 1738| | 1739| 7.39k| bool convstatus = rl ? rl->conv(word, wspace) : false; ------------------ | Branch (1739:23): [True: 397, False: 7.00k] ------------------ 1740| 7.39k| if (convstatus) { ------------------ | Branch (1740:9): [True: 0, False: 7.39k] ------------------ 1741| | // the input conversion can grow the word without limit, so hold the 1742| | // converted word to the same maximum length as the raw word 1743| 0| if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 87| 0|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 0|#define MAXWORDLEN 100 | | ------------------ ------------------ if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 90| 0|#define MAXWORDLEN 100 ------------------ | Branch (1743:11): [True: 0, False: 0] | Branch (1743:11): [True: 0, False: 0] ------------------ 1744| 0| return slst; 1745| 0| wl = cleanword2(scw, sunicw, wspace, &captype, &abbv); 1746| 0| } else 1747| 7.39k| wl = cleanword2(scw, sunicw, word, &captype, &abbv); 1748| | 1749| 7.39k|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 1750| 7.39k| if (wl > 32768) ------------------ | Branch (1750:9): [True: 0, False: 7.39k] ------------------ 1751| 0| return slst; 1752| 7.39k|#endif 1753| 7.39k| } 1754| | 1755| 7.39k| if (wl == 0) { ------------------ | Branch (1755:7): [True: 509, False: 6.88k] ------------------ 1756| 509| if (abbv) { ------------------ | Branch (1756:9): [True: 294, False: 215] ------------------ 1757| 294| scw.clear(); 1758| 7.19k| for (wl = 0; wl < abbv; wl++) ------------------ | Branch (1758:20): [True: 6.90k, False: 294] ------------------ 1759| 6.90k| scw.push_back('.'); 1760| 294| abbv = 0; 1761| 294| } else 1762| 215| return slst; 1763| 509| } 1764| | 1765| 7.18k| std::string result; 1766| | 1767| 7.18k| auto suggest_start = std::chrono::steady_clock::now(); 1768| | 1769| 7.18k| size_t n = 0; 1770| | // test numbers 1771| | // LANG_hu section: set dash information for suggestions 1772| 7.18k| if (langnum == LANG_hu) { ------------------ | Branch (1772:7): [True: 386, False: 6.79k] ------------------ 1773| 386| size_t n2 = 0; 1774| 386| size_t n3 = 0; 1775| | 1776| 525| while ((n < wl) && (((scw[n] <= '9') && (scw[n] >= '0')) || ------------------ | Branch (1776:12): [True: 501, False: 24] | Branch (1776:26): [True: 275, False: 226] | Branch (1776:45): [True: 139, False: 136] ------------------ 1777| 362| (((scw[n] == '.') || (scw[n] == ',')) && (n > 0)))) { ------------------ | Branch (1777:27): [True: 29, False: 333] | Branch (1777:46): [True: 0, False: 333] | Branch (1777:66): [True: 0, False: 29] ------------------ 1778| 139| n++; 1779| 139| if ((scw[n] == '.') || (scw[n] == ',')) { ------------------ | Branch (1779:11): [True: 0, False: 139] | Branch (1779:30): [True: 0, False: 139] ------------------ 1780| 0| if (((n2 == 0) && (n > 3)) || ------------------ | Branch (1780:14): [True: 0, False: 0] | Branch (1780:27): [True: 0, False: 0] ------------------ 1781| 0| ((n2 > 0) && ((scw[n - 1] == '.') || (scw[n - 1] == ',')))) ------------------ | Branch (1781:14): [True: 0, False: 0] | Branch (1781:27): [True: 0, False: 0] | Branch (1781:50): [True: 0, False: 0] ------------------ 1782| 0| break; 1783| 0| n2++; 1784| 0| n3 = n; 1785| 0| } 1786| 139| } 1787| | 1788| 386| if ((n == wl) && (n3 > 0) && (n - n3 > 3)) ------------------ | Branch (1788:9): [True: 24, False: 362] | Branch (1788:22): [True: 0, False: 24] | Branch (1788:34): [True: 0, False: 0] ------------------ 1789| 0| return slst; 1790| 386| if ((n == wl) || ((n > 0) && ((scw[n] == '%') || (scw[n] == '\xB0')) && checkword(scw.substr(n), nullptr, nullptr, suggest_start))) { ------------------ | Branch (1790:9): [True: 24, False: 362] | Branch (1790:9): [True: 24, False: 362] | Branch (1790:23): [True: 11, False: 351] | Branch (1790:35): [True: 0, False: 11] | Branch (1790:54): [True: 0, False: 11] | Branch (1790:77): [True: 0, False: 0] ------------------ 1791| 24| result.append(scw); 1792| 24| result.resize(n - 1); 1793| 24| if (n == wl) ------------------ | Branch (1793:11): [True: 24, False: 0] ------------------ 1794| 24| cat_result(result, pSMgr->suggest_morph(scw.substr(n - 1))); 1795| 0| else { 1796| 0| std::string chunk = scw.substr(n - 1, 1); 1797| 0| cat_result(result, pSMgr->suggest_morph(chunk)); 1798| 0| result.push_back('+'); // XXX SPEC. MORPHCODE 1799| 0| cat_result(result, pSMgr->suggest_morph(scw.substr(n))); 1800| 0| } 1801| 24| return line_tok(result, MSEP_REC); ------------------ | | 122| 24|#define MSEP_REC '\n' ------------------ 1802| 24| } 1803| 386| } 1804| | // END OF LANG_hu section 1805| | 1806| 7.15k| switch (captype) { ------------------ | Branch (1806:11): [True: 7.15k, False: 0] ------------------ 1807| 379| case HUHCAP: ------------------ | | 95| 379|#define HUHCAP 3 ------------------ | Branch (1807:5): [True: 379, False: 6.77k] ------------------ 1808| 1.29k| case HUHINITCAP: ------------------ | | 96| 1.29k|#define HUHINITCAP 4 ------------------ | Branch (1808:5): [True: 913, False: 6.24k] ------------------ 1809| 3.94k| case NOCAP: { ------------------ | | 92| 3.94k|#define NOCAP 0 ------------------ | Branch (1809:5): [True: 2.65k, False: 4.50k] ------------------ 1810| 3.94k| cat_result(result, pSMgr->suggest_morph(scw)); 1811| 3.94k| if (abbv) { ------------------ | Branch (1811:11): [True: 234, False: 3.71k] ------------------ 1812| 234| std::string u8buffer(scw); 1813| 234| u8buffer.push_back('.'); 1814| 234| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1815| 234| } 1816| 3.94k| break; 1817| 1.29k| } 1818| 2.21k| case INITCAP: { ------------------ | | 93| 2.21k|#define INITCAP 1 ------------------ | Branch (1818:5): [True: 2.21k, False: 4.93k] ------------------ 1819| 2.21k| mkallsmall2(scw, sunicw); 1820| 2.21k| std::string u8buffer(scw); 1821| 2.21k| mkinitcap2(scw, sunicw); 1822| 2.21k| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1823| 2.21k| cat_result(result, pSMgr->suggest_morph(scw)); 1824| 2.21k| if (abbv) { ------------------ | Branch (1824:11): [True: 185, False: 2.03k] ------------------ 1825| 185| u8buffer.push_back('.'); 1826| 185| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1827| | 1828| 185| u8buffer = scw; 1829| 185| u8buffer.push_back('.'); 1830| | 1831| 185| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1832| 185| } 1833| 2.21k| break; 1834| 1.29k| } 1835| 990| case ALLCAP: { ------------------ | | 94| 990|#define ALLCAP 2 ------------------ | Branch (1835:5): [True: 990, False: 6.16k] ------------------ 1836| 990| cat_result(result, pSMgr->suggest_morph(scw)); 1837| 990| if (abbv) { ------------------ | Branch (1837:11): [True: 243, False: 747] ------------------ 1838| 243| std::string u8buffer(scw); 1839| 243| u8buffer.push_back('.'); 1840| 243| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1841| 243| } 1842| 990| mkallsmall2(scw, sunicw); 1843| 990| std::string u8buffer(scw); 1844| 990| mkinitcap2(scw, sunicw); 1845| | 1846| 990| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1847| 990| cat_result(result, pSMgr->suggest_morph(scw)); 1848| 990| if (abbv) { ------------------ | Branch (1848:11): [True: 243, False: 747] ------------------ 1849| 243| u8buffer.push_back('.'); 1850| 243| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1851| | 1852| 243| u8buffer = scw; 1853| 243| u8buffer.push_back('.'); 1854| | 1855| 243| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1856| 243| } 1857| 990| break; 1858| 1.29k| } 1859| 7.15k| } 1860| | 1861| 7.15k| if (!result.empty()) { ------------------ | Branch (1861:7): [True: 1.34k, False: 5.81k] ------------------ 1862| | // word reversing wrapper for complex prefixes 1863| 1.34k| if (complexprefixes) { ------------------ | Branch (1863:9): [True: 100, False: 1.24k] ------------------ 1864| 100| if (utf8) ------------------ | Branch (1864:11): [True: 0, False: 100] ------------------ 1865| 0| reverseword_utf(result); 1866| 100| else 1867| 100| reverseword(result); 1868| 100| } 1869| 1.34k| return line_tok(result, MSEP_REC); ------------------ | | 122| 1.34k|#define MSEP_REC '\n' ------------------ 1870| 1.34k| } 1871| | 1872| | // compound word with dash (HU) I18n 1873| | // LANG_hu section: set dash information for suggestions 1874| | 1875| 5.81k| size_t dash_pos = langnum == LANG_hu ? scw.find('-') : std::string::npos; ------------------ | Branch (1875:21): [True: 345, False: 5.47k] ------------------ 1876| 5.81k| if (dash_pos != std::string::npos) { ------------------ | Branch (1876:7): [True: 32, False: 5.78k] ------------------ 1877| 32| int nresult = 0; 1878| | 1879| 32| std::string part1 = scw.substr(0, dash_pos), part2 = scw.substr(dash_pos + 1); 1880| | 1881| | // examine 2 sides of the dash 1882| 32| if (part2.empty()) { // base word ending with dash ------------------ | Branch (1882:9): [True: 6, False: 26] ------------------ 1883| 6| if (spell(part1, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1883:11): [True: 0, False: 6] ------------------ 1884| 0| std::string p = pSMgr->suggest_morph(part1); 1885| 0| if (!p.empty()) { ------------------ | Branch (1885:13): [True: 0, False: 0] ------------------ 1886| 0| slst = line_tok(p, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1887| 0| return slst; 1888| 0| } 1889| 0| } 1890| 26| } else if (part2.size() == 1 && part2[0] == 'e') { // XXX (HU) -e hat. ------------------ | Branch (1890:16): [True: 1, False: 25] | Branch (1890:37): [True: 0, False: 1] ------------------ 1891| 0| if (spell(part1, candidate_stack, nullptr, nullptr, suggest_start) && ------------------ | Branch (1891:11): [True: 0, False: 0] | Branch (1891:11): [True: 0, False: 0] ------------------ 1892| 0| (spell("-e", candidate_stack, nullptr, nullptr, suggest_start))) { ------------------ | Branch (1892:11): [True: 0, False: 0] ------------------ 1893| 0| std::string st = pSMgr->suggest_morph(part1); 1894| 0| if (!st.empty()) { ------------------ | Branch (1894:13): [True: 0, False: 0] ------------------ 1895| 0| result.append(st); 1896| 0| } 1897| 0| result.push_back('+'); // XXX spec. separator in MORPHCODE 1898| 0| st = pSMgr->suggest_morph("-e"); 1899| 0| if (!st.empty()) { ------------------ | Branch (1899:13): [True: 0, False: 0] ------------------ 1900| 0| result.append(st); 1901| 0| } 1902| 0| return line_tok(result, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1903| 0| } 1904| 26| } else { 1905| | // first word ending with dash: word- XXX ??? 1906| 26| part1.push_back(' '); 1907| 26| nresult = spell(part1, candidate_stack, nullptr, nullptr, suggest_start); 1908| 26| part1.erase(part1.size() - 1); 1909| 26| if (nresult && spell(part2, candidate_stack, nullptr, nullptr, suggest_start) && ------------------ | Branch (1909:11): [True: 1, False: 25] | Branch (1909:22): [True: 1, False: 0] ------------------ 1910| 1| ((part2.size() > 1) || ((part2[0] > '0') && (part2[0] < '9')))) { ------------------ | Branch (1910:12): [True: 0, False: 1] | Branch (1910:35): [True: 0, False: 1] | Branch (1910:55): [True: 0, False: 0] ------------------ 1911| 0| std::string st = pSMgr->suggest_morph(part1); 1912| 0| if (!st.empty()) { ------------------ | Branch (1912:13): [True: 0, False: 0] ------------------ 1913| 0| result.append(st); 1914| 0| result.push_back('+'); // XXX spec. separator in MORPHCODE 1915| 0| } 1916| 0| st = pSMgr->suggest_morph(part2); 1917| 0| if (!st.empty()) { ------------------ | Branch (1917:13): [True: 0, False: 0] ------------------ 1918| 0| result.append(st); 1919| 0| } 1920| 0| return line_tok(result, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1921| 0| } 1922| 26| } 1923| | // affixed number in correct word 1924| 32| if (nresult && (dash_pos > 0) && ------------------ | Branch (1924:9): [True: 1, False: 31] | Branch (1924:20): [True: 0, False: 1] ------------------ 1925| 0| (((scw[dash_pos - 1] <= '9') && (scw[dash_pos - 1] >= '0')) || ------------------ | Branch (1925:11): [True: 0, False: 0] | Branch (1925:41): [True: 0, False: 0] ------------------ 1926| 0| (scw[dash_pos - 1] == '.'))) { ------------------ | Branch (1926:10): [True: 0, False: 0] ------------------ 1927| 0| n = 1; 1928| 0| if (scw[dash_pos - n] == '.') ------------------ | Branch (1928:11): [True: 0, False: 0] ------------------ 1929| 0| n++; 1930| | // search first not a number character to left from dash 1931| 0| while ((dash_pos >= n) && ((scw[dash_pos - n] == '0') || (n < 3)) && ------------------ | Branch (1931:14): [True: 0, False: 0] | Branch (1931:34): [True: 0, False: 0] | Branch (1931:64): [True: 0, False: 0] ------------------ 1932| 0| (n < 6)) { ------------------ | Branch (1932:14): [True: 0, False: 0] ------------------ 1933| 0| n++; 1934| 0| } 1935| 0| if (dash_pos < n) ------------------ | Branch (1935:11): [True: 0, False: 0] ------------------ 1936| 0| n--; 1937| | // numbers: valami1000000-hoz 1938| | // examine 100000-hoz, 10000-hoz 1000-hoz, 10-hoz, 1939| | // 56-hoz, 6-hoz 1940| 0| for (; n >= 1; n--) { ------------------ | Branch (1940:14): [True: 0, False: 0] ------------------ 1941| 0| if (scw[dash_pos - n] < '0' || scw[dash_pos - n] > '9') { ------------------ | Branch (1941:13): [True: 0, False: 0] | Branch (1941:40): [True: 0, False: 0] ------------------ 1942| 0| continue; 1943| 0| } 1944| 0| std::string chunk = scw.substr(dash_pos - n); 1945| 0| if (checkword(chunk, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1945:13): [True: 0, False: 0] ------------------ 1946| 0| result.append(chunk); 1947| 0| std::string st = pSMgr->suggest_morph(chunk); 1948| 0| if (!st.empty()) { ------------------ | Branch (1948:15): [True: 0, False: 0] ------------------ 1949| 0| result.append(st); 1950| 0| } 1951| 0| return line_tok(result, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1952| 0| } 1953| 0| } 1954| 0| } 1955| 32| } 1956| 5.81k| return slst; 1957| 5.81k|} _ZN12HunspellImpl8generateERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKNS0_6vectorIS6_NS4_IS6_EEEE: 1959| 7.06k|std::vector HunspellImpl::generate(const std::string& word, const std::vector& pl) { 1960| 7.06k| std::vector slst; 1961| 7.06k| if (!pSMgr || pl.empty()) ------------------ | Branch (1961:7): [True: 0, False: 7.06k] | Branch (1961:17): [True: 619, False: 6.44k] ------------------ 1962| 619| return slst; 1963| 6.44k| std::vector pl2 = analyze(word); 1964| 6.44k| int captype = NOCAP, abbv = 0; ------------------ | | 92| 6.44k|#define NOCAP 0 ------------------ 1965| 6.44k| std::string cw; 1966| 6.44k| cleanword(cw, word, &captype, &abbv); 1967| 6.44k| std::string result; 1968| | 1969| 6.44k| auto suggest_start = std::chrono::steady_clock::now(); 1970| 416k| for (const auto& i : pl) { ------------------ | Branch (1970:22): [True: 416k, False: 6.44k] ------------------ 1971| 416k| cat_result(result, pSMgr->suggest_gen(pl2, i, suggest_start)); 1972| 416k| } 1973| | 1974| 6.44k| if (!result.empty()) { ------------------ | Branch (1974:7): [True: 0, False: 6.44k] ------------------ 1975| | // allcap 1976| 0| if (captype == ALLCAP) ------------------ | | 94| 0|#define ALLCAP 2 ------------------ | Branch (1976:9): [True: 0, False: 0] ------------------ 1977| 0| mkallcap(result); 1978| | 1979| | // line split 1980| 0| slst = line_tok(result, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1981| | 1982| | // capitalize 1983| 0| if (captype == INITCAP || captype == HUHINITCAP) { ------------------ | | 93| 0|#define INITCAP 1 ------------------ if (captype == INITCAP || captype == HUHINITCAP) { ------------------ | | 96| 0|#define HUHINITCAP 4 ------------------ | Branch (1983:9): [True: 0, False: 0] | Branch (1983:31): [True: 0, False: 0] ------------------ 1984| 0| for (auto& str : slst) { ------------------ | Branch (1984:22): [True: 0, False: 0] ------------------ 1985| 0| mkinitcap(str); 1986| 0| } 1987| 0| } 1988| | 1989| | // temporary filtering of prefix related errors (eg. 1990| | // generate("undrinkable", "eats") --> "undrinkables" and "*undrinks") 1991| 0| auto it = slst.begin(); 1992| 0| while (it != slst.end()) { ------------------ | Branch (1992:12): [True: 0, False: 0] ------------------ 1993| 0| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 0|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1993:11): [True: 0, False: 0] ------------------ 1994| 0| break; 1995| 0| std::vector candidate_stack; 1996| 0| if (!spell(*it, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1996:11): [True: 0, False: 0] ------------------ 1997| 0| it = slst.erase(it); 1998| 0| } else { 1999| 0| ++it; 2000| 0| } 2001| 0| } 2002| 0| } 2003| 6.44k| return slst; 2004| 7.06k|} _ZN12HunspellImpl8generateERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 2006| 741|std::vector HunspellImpl::generate(const std::string& word, const std::string& pattern) { 2007| 741| std::vector pl = analyze(pattern); 2008| 741| std::vector slst = generate(word, pl); 2009| 741| uniqlist(slst); 2010| 741| return slst; 2011| 741|} _ZN12HunspellImpl11get_xml_parERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEm: 2014| 515k|std::string HunspellImpl::get_xml_par(const std::string& in_par, std::string::size_type pos) { 2015| 515k| std::string dest; 2016| 515k| if (pos == std::string::npos) ------------------ | Branch (2016:7): [True: 7.06k, False: 508k] ------------------ 2017| 7.06k| return dest; 2018| 508k| const char* par = in_par.c_str() + pos; 2019| 508k| char end = *par; 2020| 508k| if (end == '>') ------------------ | Branch (2020:7): [True: 505k, False: 3.45k] ------------------ 2021| 505k| end = '<'; 2022| 3.45k| else if (end != '\'' && end != '"') ------------------ | Branch (2022:12): [True: 2.79k, False: 665] | Branch (2022:27): [True: 1.21k, False: 1.57k] ------------------ 2023| 1.21k| return dest; // bad XML 2024| 10.5M| for (par++; *par != '\0' && *par != end; ++par) { ------------------ | Branch (2024:15): [True: 10.5M, False: 31.8k] | Branch (2024:31): [True: 10.0M, False: 475k] ------------------ 2025| 10.0M| dest.push_back(*par); 2026| 10.0M| } 2027| 507k| mystrrep(dest, "<", "<"); 2028| 507k| mystrrep(dest, "&", "&"); 2029| 507k| return dest; 2030| 508k|} _ZN12HunspellImpl11get_xml_posERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEmPKc: 2046| 75.2k|std::string::size_type HunspellImpl::get_xml_pos(const std::string& s, std::string::size_type pos, const char* attr) { 2047| 75.2k| if (pos == std::string::npos) ------------------ | Branch (2047:7): [True: 0, False: 75.2k] ------------------ 2048| 0| return std::string::npos; 2049| | 2050| 75.2k| std::string::size_type endpos = s.find('>', pos); 2051| 75.2k| if (attr == nullptr) ------------------ | Branch (2051:7): [True: 0, False: 75.2k] ------------------ 2052| 0| return endpos; 2053| 266k| while (true) { ------------------ | Branch (2053:10): [True: 266k, Folded] ------------------ 2054| 266k| pos = s.find(attr, pos); 2055| 266k| if (pos == std::string::npos || pos >= endpos) ------------------ | Branch (2055:9): [True: 4.18k, False: 262k] | Branch (2055:37): [True: 1.67k, False: 260k] ------------------ 2056| 5.85k| return std::string::npos; 2057| 260k| if (pos == 0 || s[pos - 1] == ' ' || s[pos - 1] == '\n') ------------------ | Branch (2057:9): [True: 0, False: 260k] | Branch (2057:21): [True: 1.44k, False: 259k] | Branch (2057:42): [True: 67.9k, False: 191k] ------------------ 2058| 69.4k| break; 2059| 191k| pos += strlen(attr); 2060| 191k| } 2061| 69.4k| return pos + strlen(attr); 2062| 75.2k|} _ZN12HunspellImpl13check_xml_parERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEmPKcSA_: 2066| 75.2k| const char* value) { 2067| 75.2k| const std::string cw = get_xml_par(q, get_xml_pos(q, pos, attr)); 2068| 75.2k| return cw == value ? 1 : 0; ------------------ | Branch (2068:10): [True: 18.5k, False: 56.6k] ------------------ 2069| 75.2k|} _ZN12HunspellImpl12get_xml_listERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEmPKc: 2071| 7.33k|std::vector HunspellImpl::get_xml_list(const std::string& list, std::string::size_type pos, const char* tag) { 2072| 7.33k| std::vector slst; 2073| 7.33k| if (pos == std::string::npos) ------------------ | Branch (2073:7): [True: 76, False: 7.25k] ------------------ 2074| 76| return slst; 2075| 424k| while (true) { ------------------ | Branch (2075:10): [True: 424k, Folded] ------------------ 2076| 424k| pos = list.find(tag, pos); 2077| 424k| if (pos == std::string::npos) ------------------ | Branch (2077:9): [True: 6.06k, False: 418k] ------------------ 2078| 6.06k| break; 2079| 418k| std::string cw = get_xml_par(list, pos + strlen(tag) - 1); 2080| 418k| if (cw.empty()) { ------------------ | Branch (2080:9): [True: 1.19k, False: 416k] ------------------ 2081| 1.19k| break; 2082| 1.19k| } 2083| 416k| slst.push_back(std::move(cw)); 2084| 416k| ++pos; 2085| 416k| } 2086| 7.25k| return slst; 2087| 7.33k|} _ZN12HunspellImpl7spellmlERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 2089| 23.0k|std::vector HunspellImpl::spellml(const std::string& in_word) { 2090| | // The XML interface spell checks words of its own to answer the query. 2091| 23.0k| TraceSuppress no_trace(m_trace.get()); 2092| | 2093| 23.0k| std::vector slst; 2094| | 2095| 23.0k| std::string::size_type qpos = in_word.find("', qpos); 2100| 22.5k| if (q2pos == std::string::npos) ------------------ | Branch (2100:7): [True: 264, False: 22.2k] ------------------ 2101| 264| return slst; // bad XML input 2102| | 2103| 22.2k| q2pos = in_word.find("', q2pos)); 2109| 399| if (!cw.empty()) ------------------ | Branch (2109:9): [True: 114, False: 285] ------------------ 2110| 114| slst = analyze(cw); 2111| 399| if (slst.empty()) ------------------ | Branch (2111:9): [True: 369, False: 30] ------------------ 2112| 369| return slst; 2113| | // convert the result to ana1ana2 format 2114| 30| std::string r; 2115| 30| r.append(""); 2116| 30| for (auto entry : slst) { ------------------ | Branch (2116:21): [True: 30, False: 30] ------------------ 2117| 30| r.append(""); 2118| | 2119| 30| mystrrep(entry, "\t", " "); 2120| 30| mystrrep(entry, "&", "&"); 2121| 30| mystrrep(entry, "<", "<"); 2122| 30| r.append(entry); 2123| | 2124| 30| r.append(""); 2125| 30| } 2126| 30| r.append(""); 2127| 30| slst.clear(); 2128| 30| slst.push_back(std::move(r)); 2129| 30| return slst; 2130| 21.5k| } else if (check_xml_par(in_word, qpos, "type=", "stem")) { ------------------ | Branch (2130:14): [True: 1.40k, False: 20.1k] ------------------ 2131| 1.40k| std::string cw = get_xml_par(in_word, in_word.find('>', q2pos)); 2132| 1.40k| if (!cw.empty()) ------------------ | Branch (2132:9): [True: 1.00k, False: 399] ------------------ 2133| 1.00k| return stem(cw); 2134| 20.1k| } else if (check_xml_par(in_word, qpos, "type=", "generate")) { ------------------ | Branch (2134:14): [True: 8.53k, False: 11.6k] ------------------ 2135| 8.53k| std::string cw = get_xml_par(in_word, in_word.find('>', q2pos)); 2136| 8.53k| if (cw.empty()) ------------------ | Branch (2136:9): [True: 152, False: 8.37k] ------------------ 2137| 152| return slst; 2138| 8.37k| std::string::size_type q3pos = in_word.find("', q3pos)); 2141| 855| if (!cw2.empty()) { ------------------ | Branch (2141:11): [True: 741, False: 114] ------------------ 2142| 741| return generate(cw, cw2); 2143| 741| } 2144| 7.52k| } else { 2145| 7.52k| q2pos = in_word.find(" slst2 = get_xml_list(in_word, in_word.find('>', q2pos), ""); 2148| 7.33k| if (!slst2.empty()) { ------------------ | Branch (2148:13): [True: 6.32k, False: 1.00k] ------------------ 2149| 6.32k| slst = generate(cw, slst2); 2150| 6.32k| uniqlist(slst); 2151| 6.32k| return slst; 2152| 6.32k| } 2153| 7.33k| } 2154| 7.52k| } 2155| 11.6k| } else if (check_xml_par(in_word, qpos, "type=", "add")) { ------------------ | Branch (2155:14): [True: 8.25k, False: 3.36k] ------------------ 2156| 8.25k| std::string cw = get_xml_par(in_word, in_word.find('>', q2pos)); 2157| 8.25k| if (cw.empty()) ------------------ | Branch (2157:9): [True: 76, False: 8.18k] ------------------ 2158| 76| return slst; 2159| 8.18k| std::string::size_type q3pos = in_word.find("', q3pos)); 2162| 2.75k| if (!cw2.empty()) { ------------------ | Branch (2162:11): [True: 2.37k, False: 380] ------------------ 2163| 2.37k| add_with_affix(cw, cw2); 2164| 2.37k| } else { 2165| 380| add(cw); 2166| 380| } 2167| 5.42k| } else { 2168| 5.42k| add(cw); 2169| 5.42k| } 2170| 8.18k| } 2171| 13.2k| return slst; 2172| 21.9k|} _ZN8HunspellC2EPKcS1_S1_: 2326| 38| : m_Impl(new HunspellImpl(affpath, dpath, key)) { 2327| 38|} _ZN8Hunspell5spellERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiPS6_: 2338| 65.5k|bool Hunspell::spell(const std::string& word, int* info, std::string* root) { 2339| 65.5k| std::vector candidate_stack; 2340| 65.5k| return m_Impl->spell(word, candidate_stack, info, root, 2341| 65.5k| std::chrono::steady_clock::now()); 2342| 65.5k|} _ZN8Hunspell7suggestERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 2344| 64.9k|std::vector Hunspell::suggest(const std::string& word) { 2345| 64.9k| return m_Impl->suggest(word); 2346| 64.9k|} _ZNK12HunspellImpl12active_traceEv: 143| 32.5M| TraceCtx* active_trace() const { 144| 32.5M| return m_trace->on() ? m_trace.get() : nullptr; ------------------ | Branch (144:12): [True: 0, False: 32.5M] ------------------ 145| 32.5M| } _ZNK8TraceCtx2onEv: 110| 32.5M| bool on() const { return m_callback && m_suppressed == 0; } ------------------ | Branch (110:28): [True: 0, False: 32.5M] | Branch (110:42): [True: 0, False: 0] ------------------ _ZN10TraceScopeC2EP8TraceCtx: 129| 516M| explicit TraceScope(TraceCtx* context) : m_context(context) { 130| 516M| if (m_context) ------------------ | Branch (130:9): [True: 0, False: 516M] ------------------ 131| 0| ++m_context->m_depth; 132| 516M| } _ZN10TraceScopeD2Ev: 133| 516M| ~TraceScope() { 134| 516M| if (m_context) ------------------ | Branch (134:9): [True: 0, False: 516M] ------------------ 135| 0| --m_context->m_depth; 136| 516M| } _Z8trace_onP8TraceCtx: 163| 1.13G|inline TraceCtx* trace_on(TraceCtx* context) { 164| 1.13G| return (context && context->on()) ? context : nullptr; ------------------ | Branch (164:11): [True: 0, False: 1.13G] | Branch (164:22): [True: 0, False: 0] ------------------ 165| 1.13G|} _ZN13TraceSuppressC2EP8TraceCtx: 146| 115k| explicit TraceSuppress(TraceCtx* context) : m_context(context) { 147| 115k| if (m_context) ------------------ | Branch (147:9): [True: 115k, False: 0] ------------------ 148| 115k| ++m_context->m_suppressed; 149| 115k| } _ZN13TraceSuppressD2Ev: 150| 115k| ~TraceSuppress() { 151| 115k| if (m_context) ------------------ | Branch (151:9): [True: 115k, False: 0] ------------------ 152| 115k| --m_context->m_suppressed; 153| 115k| } _ZN8TraceCtxC2EPFvPviPKcES0_: 103| 38| : m_callback(callback), m_userdata(userdata) {} _Z16init_phonet_hashR10phonetable: 38| 2|void init_phonet_hash(phonetable& parms) { 39| 2| memset(parms.hash, 0xff, HASHSIZE * sizeof(int)); ------------------ | | 33| 2|#define HASHSIZE 256 ------------------ 40| | 41| 212| for (int i = 0; parms.rules[i][0] != '\0'; i += 2) { ------------------ | Branch (41:19): [True: 210, False: 2] ------------------ 42| | /** set hash value **/ 43| 210| int k = (unsigned char)parms.rules[i][0]; 44| | 45| 210| if (parms.hash[k] < 0) { ------------------ | Branch (45:9): [True: 54, False: 156] ------------------ 46| 54| parms.hash[k] = i; 47| 54| } 48| 210| } 49| 2|} _Z6phonetRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEER10phonetable: 69| 10.1k|std::string phonet(const std::string& inword, phonetable& parms) { 70| | 71| 10.1k| int i, k = 0, p, z, k0, n0, p0 = -333; 72| 10.1k| char c; 73| 10.1k| using uchar = unsigned char; 74| | 75| 10.1k| size_t len = inword.size(); 76| 10.1k| if (len > MAXPHONETUTF8LEN) ------------------ | | 35| 10.1k|#define MAXPHONETUTF8LEN (MAXPHONETLEN * 4) | | ------------------ | | | | 34| 10.1k|#define MAXPHONETLEN 256 | | ------------------ ------------------ | Branch (76:7): [True: 0, False: 10.1k] ------------------ 77| 0| return {}; 78| 10.1k| char word[MAXPHONETUTF8LEN + 1]; 79| 10.1k| strncpy(word, inword.c_str(), MAXPHONETUTF8LEN); ------------------ | | 35| 10.1k|#define MAXPHONETUTF8LEN (MAXPHONETLEN * 4) | | ------------------ | | | | 34| 10.1k|#define MAXPHONETLEN 256 | | ------------------ ------------------ 80| 10.1k| word[MAXPHONETUTF8LEN] = '\0'; ------------------ | | 35| 10.1k|#define MAXPHONETUTF8LEN (MAXPHONETLEN * 4) | | ------------------ | | | | 34| 10.1k|#define MAXPHONETLEN 256 | | ------------------ ------------------ 81| | 82| 10.1k| std::string target; 83| | /** check word **/ 84| 10.1k| i = z = 0; 85| 92.2k| while ((c = word[i]) != '\0') { ------------------ | Branch (85:10): [True: 82.1k, False: 10.1k] ------------------ 86| 82.1k| int n = parms.hash[(uchar)c]; 87| 82.1k| int z0 = 0; 88| | 89| 82.1k| if (n >= 0 && !parms.rules[n].empty()) { ------------------ | Branch (89:9): [True: 25.1k, False: 56.9k] | Branch (89:19): [True: 25.1k, False: 0] ------------------ 90| | /** check all rules for the same letter **/ 91| 65.3k| while (parms.rules[n][0] == c) { ------------------ | Branch (91:14): [True: 63.3k, False: 2.01k] ------------------ 92| | /** check whole string **/ 93| 63.3k| k = 1; /** number of found letters **/ 94| 63.3k| p = 5; /** default priority **/ 95| 63.3k| const char*s = parms.rules[n].c_str(); 96| 63.3k| s++; /** important for (see below) "*(s-1)" **/ 97| | 98| 65.2k| while (*s != '\0' && word[i + k] == *s && !isdigit((unsigned char)*s) && strchr("(-<^$", *s) == nullptr) { ------------------ | Branch (98:16): [True: 44.2k, False: 21.0k] | Branch (98:30): [True: 1.93k, False: 42.2k] | Branch (98:51): [True: 1.93k, False: 0] | Branch (98:82): [True: 1.89k, False: 41] ------------------ 99| 1.89k| k++; 100| 1.89k| s++; 101| 1.89k| } 102| 63.3k| if (*s == '(') { ------------------ | Branch (102:13): [True: 4.52k, False: 58.8k] ------------------ 103| | /** check letters in "(..)" **/ 104| 4.52k| if (myisalpha(word[i + k]) // ...could be implied? ------------------ | Branch (104:15): [True: 3.35k, False: 1.16k] ------------------ 105| 3.35k| && strchr(s + 1, word[i + k]) != nullptr) { ------------------ | Branch (105:18): [True: 353, False: 3.00k] ------------------ 106| 353| k++; 107| 1.95k| while (*s && *s != ')') ------------------ | Branch (107:20): [True: 1.95k, False: 0] | Branch (107:26): [True: 1.60k, False: 353] ------------------ 108| 1.60k| s++; 109| 353| if (*s == ')') ------------------ | Branch (109:17): [True: 353, False: 0] ------------------ 110| 353| s++; 111| 353| } 112| 4.52k| } 113| 63.3k| p0 = (int)*s; 114| 63.3k| k0 = k; 115| 64.7k| while (*s == '-' && k > 1) { ------------------ | Branch (115:16): [True: 1.39k, False: 63.3k] | Branch (115:29): [True: 1.39k, False: 0] ------------------ 116| 1.39k| k--; 117| 1.39k| s++; 118| 1.39k| } 119| 63.3k| if (*s == '<') ------------------ | Branch (119:13): [True: 96, False: 63.2k] ------------------ 120| 96| s++; 121| 63.3k| if (isdigit((unsigned char)*s)) { ------------------ | Branch (121:13): [True: 1, False: 63.3k] ------------------ 122| | /** determine priority **/ 123| 1| p = *s - '0'; 124| 1| s++; 125| 1| } 126| 63.3k| if (*s == '^' && *(s + 1) == '^') ------------------ | Branch (126:13): [True: 2.84k, False: 60.5k] | Branch (126:26): [True: 0, False: 2.84k] ------------------ 127| 0| s++; 128| | 129| 63.3k| if (*s == '\0' || (*s == '^' && (i == 0 || !myisalpha(word[i - 1])) && ------------------ | Branch (129:13): [True: 22.5k, False: 40.8k] | Branch (129:28): [True: 2.84k, False: 37.9k] | Branch (129:42): [True: 148, False: 2.70k] | Branch (129:52): [True: 720, False: 1.98k] ------------------ 130| 868| (*(s + 1) != '$' || (!myisalpha(word[i + k0])))) || ------------------ | Branch (130:29): [True: 868, False: 0] | Branch (130:48): [True: 0, False: 0] ------------------ 131| 39.9k| (*s == '$' && i > 0 && myisalpha(word[i - 1]) && ------------------ | Branch (131:14): [True: 0, False: 39.9k] | Branch (131:27): [True: 0, False: 0] | Branch (131:36): [True: 0, False: 0] ------------------ 132| 23.3k| (!myisalpha(word[i + k0])))) { ------------------ | Branch (132:14): [True: 0, False: 0] ------------------ 133| | /** search for followup rules, if: **/ 134| | /** parms.followup and k > 1 and NO '-' in searchstring **/ 135| 23.3k| char c0 = word[i + k - 1]; 136| 23.3k| n0 = parms.hash[(uchar)c0]; 137| | 138| | // if (parms.followup && k > 1 && n0 >= 0 139| 23.3k| if (k > 1 && n0 >= 0 && p0 != (int)'-' && word[i + k] != '\0' && !parms.rules[n0].empty()) { ------------------ | Branch (139:15): [True: 503, False: 22.8k] | Branch (139:24): [True: 503, False: 0] | Branch (139:35): [True: 452, False: 51] | Branch (139:53): [True: 401, False: 51] | Branch (139:76): [True: 401, False: 0] ------------------ 140| | /** test follow-up rule for "word[i+k]" **/ 141| 1.04k| while (parms.rules[n0][0] == c0) { ------------------ | Branch (141:20): [True: 925, False: 118] ------------------ 142| | /** check whole string **/ 143| 925| k0 = k; 144| 925| p0 = 5; 145| 925| s = parms.rules[n0].c_str(); 146| 925| s++; 147| 1.20k| while (*s != '\0' && word[i + k0] == *s && !isdigit((unsigned char)*s) && strchr("(-<^$", *s) == nullptr) { ------------------ | Branch (147:22): [True: 807, False: 401] | Branch (147:36): [True: 283, False: 524] | Branch (147:58): [True: 283, False: 0] | Branch (147:89): [True: 283, False: 0] ------------------ 148| 283| k0++; 149| 283| s++; 150| 283| } 151| 925| if (*s == '(') { ------------------ | Branch (151:19): [True: 0, False: 925] ------------------ 152| | /** check letters **/ 153| 0| if (myisalpha(word[i + k0]) && strchr(s + 1, word[i + k0]) != nullptr) { ------------------ | Branch (153:21): [True: 0, False: 0] | Branch (153:48): [True: 0, False: 0] ------------------ 154| 0| k0++; 155| 0| while (*s != ')' && *s != '\0') ------------------ | Branch (155:26): [True: 0, False: 0] | Branch (155:39): [True: 0, False: 0] ------------------ 156| 0| s++; 157| 0| if (*s == ')') ------------------ | Branch (157:23): [True: 0, False: 0] ------------------ 158| 0| s++; 159| 0| } 160| 0| } 161| 925| while (*s == '-') { ------------------ | Branch (161:22): [True: 0, False: 925] ------------------ 162| | /** "k0" gets NOT reduced **/ 163| | /** because "if (k0 == k)" **/ 164| 0| s++; 165| 0| } 166| 925| if (*s == '<') ------------------ | Branch (166:19): [True: 0, False: 925] ------------------ 167| 0| s++; 168| 925| if (isdigit((unsigned char)*s)) { ------------------ | Branch (168:19): [True: 0, False: 925] ------------------ 169| 0| p0 = *s - '0'; 170| 0| s++; 171| 0| } 172| | 173| 925| if (*s == '\0' ------------------ | Branch (173:19): [True: 401, False: 524] ------------------ 174| | /** *s == '^' cuts **/ 175| 524| || (*s == '$' && !myisalpha(word[i + k0]))) { ------------------ | Branch (175:23): [True: 0, False: 524] | Branch (175:36): [True: 0, False: 0] ------------------ 176| 401| if (k0 == k) { ------------------ | Branch (176:21): [True: 118, False: 283] ------------------ 177| | /** this is just a piece of the string **/ 178| 118| n0 += 2; 179| 118| continue; 180| 118| } 181| | 182| 283| if (p0 < p) { ------------------ | Branch (182:21): [True: 0, False: 283] ------------------ 183| | /** priority too low **/ 184| 0| n0 += 2; 185| 0| continue; 186| 0| } 187| | /** rule fits; stop search **/ 188| 283| break; 189| 283| } 190| 524| n0 += 2; 191| 524| } /** End of "while (parms.rules[n0][0] == c0)" **/ 192| | 193| 401| if (p0 >= p && parms.rules[n0][0] == c0) { ------------------ | Branch (193:17): [True: 400, False: 1] | Branch (193:28): [True: 283, False: 117] ------------------ 194| 283| n += 2; 195| 283| continue; 196| 283| } 197| 401| } /** end of follow-up stuff **/ 198| | 199| | /** replace string **/ 200| 23.1k| s = parms.rules[n + 1].c_str(); 201| 23.1k| p0 = (!parms.rules[n].empty() && strchr(parms.rules[n].c_str() + 1, '<') != nullptr) ? 1 : 0; ------------------ | Branch (201:17): [True: 23.1k, False: 0] | Branch (201:44): [True: 96, False: 23.0k] ------------------ 202| 23.1k| if (p0 == 1 && z == 0) { ------------------ | Branch (202:15): [True: 96, False: 23.0k] | Branch (202:26): [True: 96, False: 0] ------------------ 203| | /** rule with '<' is used **/ 204| 96| if (!target.empty() && *s != '\0' && ------------------ | Branch (204:17): [True: 80, False: 16] | Branch (204:36): [True: 80, False: 0] ------------------ 205| 80| (target[target.size()-1] == c || target[target.size()-1] == *s)) { ------------------ | Branch (205:18): [True: 0, False: 80] | Branch (205:50): [True: 0, False: 80] ------------------ 206| 0| target.erase(target.size() - 1); 207| 0| } 208| 96| z0 = 1; 209| 96| z = 1; 210| 96| k0 = 0; 211| 192| while (*s != '\0' && word[i + k0] != '\0') { ------------------ | Branch (211:20): [True: 96, False: 96] | Branch (211:34): [True: 96, False: 0] ------------------ 212| 96| word[i + k0] = *s; 213| 96| k0++; 214| 96| s++; 215| 96| } 216| 96| if (k > k0) ------------------ | Branch (216:17): [True: 0, False: 96] ------------------ 217| 0| strmove(&word[0] + i + k0, &word[0] + i + k); 218| | 219| | /** new "actual letter" **/ 220| 96| c = word[i]; 221| 23.0k| } else { /** no '<' rule used **/ 222| 23.0k| i += k - 1; 223| 23.0k| z = 0; 224| 23.1k| while (*s != '\0' && *(s + 1) != '\0' && target.size() < len) { ------------------ | Branch (224:20): [True: 21.9k, False: 1.26k] | Branch (224:34): [True: 227, False: 21.6k] | Branch (224:54): [True: 147, False: 80] ------------------ 225| 147| if (target.empty() || target[target.size()-1] != *s) { ------------------ | Branch (225:19): [True: 8, False: 139] | Branch (225:37): [True: 131, False: 8] ------------------ 226| 139| target.push_back(*s); 227| 139| } 228| 147| s++; 229| 147| } 230| | /** new "actual letter" **/ 231| 23.0k| c = *s; 232| 23.0k| if (!parms.rules[n].empty() && strstr(parms.rules[n].c_str() + 1, "^^") != nullptr) { ------------------ | Branch (232:17): [True: 23.0k, False: 0] | Branch (232:44): [True: 0, False: 23.0k] ------------------ 233| 0| if (c != '\0') { ------------------ | Branch (233:19): [True: 0, False: 0] ------------------ 234| 0| target.push_back(c); 235| 0| } 236| 0| strmove(&word[0], &word[0] + i + 1); 237| 0| i = 0; 238| 0| z0 = 1; 239| 0| } 240| 23.0k| } 241| 23.1k| break; 242| 23.3k| } /** end of follow-up stuff **/ 243| 39.9k| n += 2; 244| 39.9k| } /** end of while (parms.rules[n][0] == c) **/ 245| 25.1k| } /** end of if (n >= 0) **/ 246| 82.1k| if (z0 == 0) { ------------------ | Branch (246:9): [True: 82.0k, False: 96] ------------------ 247| 82.0k| if (k && !p0 && target.size() < len && c != '\0') { ------------------ | Branch (247:11): [True: 25.0k, False: 56.9k] | Branch (247:16): [True: 23.0k, False: 2.01k] | Branch (247:23): [True: 22.9k, False: 100] | Branch (247:46): [True: 21.6k, False: 1.26k] ------------------ 248| | /** condense only double letters **/ 249| 21.6k| target.push_back(c); 250| | /// printf("\n setting \n"); 251| 21.6k| } 252| | 253| 82.0k| i++; 254| 82.0k| z = 0; 255| 82.0k| k = 0; 256| 82.0k| } 257| 82.1k| } /** end of while ((c = word[i]) != '\0') **/ 258| | 259| 10.1k| return target; 260| 10.1k|} /** end of function "phonet" **/ phonet.cxx:_ZL9myisalphac: 59| 7.22k|static int myisalpha(char ch) { 60| 7.22k| if ((unsigned char)ch < 128) ------------------ | Branch (60:7): [True: 6.79k, False: 426] ------------------ 61| 6.79k| return isalpha(ch); 62| 426| return 1; 63| 7.22k|} _ZN7RepListC2Ei: 79| 4|RepList::RepList(int n) { 80| 4| dat.reserve(std::min(n, 16384)); 81| 4| can_use_trie = true; 82| 4|} _ZN7RepList4findEPKcm: 90| 22|int RepList::find(const char* word, size_t max_len) { 91| 22| int p1 = 0; 92| 22| int p2 = dat.size() - 1; 93| 22| int ret = -1; 94| 58| while (p1 <= p2) { ------------------ | Branch (94:10): [True: 36, False: 22] ------------------ 95| 36| int m = ((unsigned)p1 + (unsigned)p2) >> 1; 96| 36| const std::string& pattern = dat[m]->pattern; 97| | // compare only as far as max_len, so a caller can restrict the search to 98| | // patterns no longer than a given length 99| 36| size_t cmplen = pattern.size() < max_len ? pattern.size() : max_len; ------------------ | Branch (99:21): [True: 6, False: 30] ------------------ 100| 36| int c = strncmp(word, pattern.c_str(), cmplen); 101| 36| if (c < 0) ------------------ | Branch (101:9): [True: 12, False: 24] ------------------ 102| 12| p2 = m - 1; 103| 24| else if (c > 0) ------------------ | Branch (103:14): [True: 24, False: 0] ------------------ 104| 24| p1 = m + 1; 105| 0| else if (pattern.size() <= max_len) { // a prefix within the limit ------------------ | Branch (105:14): [True: 0, False: 0] ------------------ 106| 0| ret = m; // scan right for a longer match 107| 0| p1 = m + 1; 108| 0| } else { 109| | // pattern shares the capped prefix but is too long; any shorter 110| | // candidate sorts earlier 111| 0| p2 = m - 1; 112| 0| } 113| 36| } 114| 22| return ret; 115| 22|} _ZN7RepList3addERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 126| 22|int RepList::add(const std::string& in_pat1, const std::string& pat2) { 127| 22| if (in_pat1.empty() || pat2.empty()) { ------------------ | Branch (127:7): [True: 0, False: 22] | Branch (127:26): [True: 0, False: 22] ------------------ 128| 0| return 1; 129| 0| } 130| | 131| | // analyse word context 132| 22| int type = 0; 133| 22| std::string pat1(in_pat1); 134| 22| if (pat1[0] == '_') { ------------------ | Branch (134:7): [True: 0, False: 22] ------------------ 135| 0| pat1.erase(0, 1); 136| 0| type = 1; 137| 0| } 138| 22| if (!pat1.empty() && pat1[pat1.size() - 1] == '_') { ------------------ | Branch (138:7): [True: 22, False: 0] | Branch (138:24): [True: 0, False: 22] ------------------ 139| 0| type = type + 2; 140| 0| pat1.erase(pat1.size() - 1); 141| 0| } 142| 22| mystrrep(pat1, "_", " "); 143| | 144| | // The trie does unanchored whole-string replacement only. Anchored entries 145| | // (a leading or trailing _) depend on the match position within the word, 146| | // which the trie does not model, so fall back to the linear scan once one is 147| | // seen. Feed the trie the same _-to-space normalised strings the linear path 148| | // stores, otherwise the two paths would disagree on output. 149| 22| if (type == 0 && can_use_trie) { ------------------ | Branch (149:7): [True: 22, False: 0] | Branch (149:20): [True: 22, False: 0] ------------------ 150| 22| std::string out(pat2); 151| 22| mystrrep(out, "_", " "); 152| 22| trie.add(pat1, out); 153| 22| } else { 154| 0| can_use_trie = false; 155| 0| } 156| | 157| | // find existing entry 158| 22| int m = find(pat1.c_str(), pat1.size()); 159| 22| if (m >= 0 && dat[m]->pattern == pat1) { ------------------ | Branch (159:7): [True: 0, False: 22] | Branch (159:17): [True: 0, False: 0] ------------------ 160| | // since already used 161| 0| dat[m]->outstrings[type] = pat2; 162| 0| mystrrep(dat[m]->outstrings[type], "_", " "); 163| 0| return 0; 164| 0| } 165| | 166| | // make a new entry if none exists 167| 22| replentry* r = new replentry; 168| 22| r->pattern = std::move(pat1); 169| 22| r->outstrings[type] = pat2; 170| 22| mystrrep(r->outstrings[type], "_", " "); 171| 22| dat.push_back(r); 172| | // sort to the right place in the list 173| 22| size_t i; 174| 36| for (i = dat.size() - 1; i > 0; --i) { ------------------ | Branch (174:28): [True: 30, False: 6] ------------------ 175| 30| if (strcmp(r->pattern.c_str(), dat[i - 1]->pattern.c_str()) < 0) { ------------------ | Branch (175:9): [True: 14, False: 16] ------------------ 176| 14| dat[i] = dat[i - 1]; 177| 14| } else 178| 16| break; 179| 30| } 180| 22| dat[i] = r; 181| 22| return 0; 182| 22|} _ZN7RepList4convERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERS6_m: 184| 356k|bool RepList::conv(const std::string& in_word, std::string& dest, size_t maxlen) { 185| | // get_status guards against a trie that overflowed its index type while 186| | // building, in which case the linear scan below is the correct fallback. 187| 356k| if (can_use_trie && trie.get_status()) ------------------ | Branch (187:7): [True: 356k, False: 0] | Branch (187:23): [True: 356k, False: 0] ------------------ 188| 356k| return trie.transcode(in_word, dest, maxlen) != TranscodeResult::None; 189| | 190| 0| dest.clear(); 191| | 192| 0| const size_t wordlen = in_word.size(); 193| 0| const char* word = in_word.c_str(); 194| | 195| 0| bool change = false; 196| 0| for (size_t i = 0; i < wordlen && dest.size() <= maxlen; ++i) { ------------------ | Branch (196:22): [True: 0, False: 0] | Branch (196:37): [True: 0, False: 0] ------------------ 197| 0| int n = -1; 198| 0| std::string l; 199| | 200| | // Find the longest matching pattern whose replacement actually applies. 201| | // The longest match may be rejected, for example an end-anchored key that 202| | // is not at the end of the word, in which case retry with strictly shorter 203| | // patterns so a shorter match can still apply. 204| 0| for (size_t max_len = wordlen - i; max_len > 0;) { ------------------ | Branch (204:40): [True: 0, False: 0] ------------------ 205| 0| int m = find(word + i, max_len); 206| 0| if (m < 0) ------------------ | Branch (206:11): [True: 0, False: 0] ------------------ 207| 0| break; 208| 0| l = replace(wordlen - i, m, i == 0); 209| 0| if (!l.empty()) { ------------------ | Branch (209:11): [True: 0, False: 0] ------------------ 210| 0| n = m; 211| 0| break; 212| 0| } 213| 0| size_t plen = dat[m]->pattern.size(); 214| 0| if (plen == 0) ------------------ | Branch (214:11): [True: 0, False: 0] ------------------ 215| 0| break; 216| 0| max_len = plen - 1; 217| 0| } 218| | 219| 0| if (n < 0) { ------------------ | Branch (219:9): [True: 0, False: 0] ------------------ 220| 0| dest.push_back(word[i]); 221| 0| continue; 222| 0| } 223| | 224| 0| dest.append(l); 225| 0| if (!dat[n]->pattern.empty()) { ------------------ | Branch (225:9): [True: 0, False: 0] ------------------ 226| 0| i += dat[n]->pattern.size() - 1; 227| 0| } 228| 0| change = true; 229| 0| } 230| | 231| 0| return change; 232| 356k|} _ZNK7RepList24check_against_breaktableERKNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEE: 234| 2|bool RepList::check_against_breaktable(const std::vector& breaktable) const { 235| 8| for (const auto i : dat) { ------------------ | Branch (235:21): [True: 8, False: 2] ------------------ 236| 32| for (auto& outstring : i->outstrings) { ------------------ | Branch (236:26): [True: 32, False: 8] ------------------ 237| 96| for (const auto& str : breaktable) { ------------------ | Branch (237:28): [True: 96, False: 32] ------------------ 238| 96| if (outstring.find(str) != std::string::npos) { ------------------ | Branch (238:13): [True: 0, False: 96] ------------------ 239| 0| return false; 240| 0| } 241| 96| } 242| 32| } 243| 8| } 244| | 245| 2| return true; 246| 2|} _ZN4TrieItLb1EEC2Ev: 161| 4| Trie() : status_ok(true) { 162| | // Initialize the root node (Index 0) 163| 4| nodes.emplace_back(); 164| 4| sub_info_arena.push_back(0xFFFFFFFF); 165| 4| } _ZN4TrieItLb1EE3addERKNSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEES9_: 167| 22| void add(const std::string& key, const std::string& value) { 168| 22| if (!status_ok) return; ------------------ | Branch (168:13): [True: 0, False: 22] ------------------ 169| | 170| | // Size rules diagnostics for our 32-bit (24/8) packing format 171| 22| if (value.size() > 255) { status_ok = false; return; } ------------------ | Branch (171:13): [True: 0, False: 22] ------------------ 172| 22| size_t offset = char_arena.size(); 173| 22| if (offset > 0xFFFFFF) { status_ok = false; return; } ------------------ | Branch (173:13): [True: 0, False: 22] ------------------ 174| | 175| | // Append to the flat char arena 176| 22| char_arena.insert(char_arena.end(), value.begin(), value.end()); 177| 22| uint32_t sub_val = (static_cast(offset) << 8) | static_cast(value.size()); 178| | 179| 22| size_t curr_idx = 0; 180| | 181| | // Traverse the key, adding nodes as necessary 182| 56| for (size_t i = 0; i < key.size(); ++i) { ------------------ | Branch (182:28): [True: 34, False: 22] ------------------ 183| 34| uint8_t byte = static_cast(key[i]); 184| | 185| 34| if (UseNibbles) { ------------------ | Branch (185:17): [True: 34, Folded] ------------------ 186| | // Loop unrolling: Process the High Nibble, then the Low Nibble 187| 34| curr_idx = advance_or_create(curr_idx, (byte >> 4) & 0x0F); 188| 34| if (!status_ok) return; ------------------ | Branch (188:21): [True: 0, False: 34] ------------------ 189| 34| curr_idx = advance_or_create(curr_idx, byte & 0x0F); 190| 34| if (!status_ok) return; ------------------ | Branch (190:21): [True: 0, False: 34] ------------------ 191| 34| } else { 192| | // Process as a single 8-bit lookup 193| 0| curr_idx = advance_or_create(curr_idx, byte); 194| 0| if (!status_ok) return; ------------------ | Branch (194:21): [True: 0, False: 0] ------------------ 195| 0| } 196| 34| } 197| | // Mark the leaf node with the packed substitution metadata 198| 22| sub_info_arena[curr_idx] = sub_val; 199| 22| } _ZN4TrieItLb1EE17advance_or_createEmh: 138| 68| size_t advance_or_create(size_t curr_idx, uint8_t symbol) { 139| 68| IndexType rel_idx = nodes[curr_idx].children[symbol]; 140| 68| if (rel_idx == 0) { ------------------ | Branch (140:13): [True: 38, False: 30] ------------------ 141| 38| size_t new_idx = nodes.size(); 142| 38| size_t diff = new_idx - curr_idx; 143| | 144| | // Diagnostics: Halt execution if the trie outgrows the integer type 145| 38| if (diff > std::numeric_limits::max()) { ------------------ | Branch (145:17): [True: 0, False: 38] ------------------ 146| 0| status_ok = false; 147| 0| return 0; 148| 0| } 149| | 150| 38| nodes[curr_idx].children[symbol] = static_cast(diff); 151| | 152| | // emplace_back constructs the object directly in the vector's memory 153| 38| nodes.emplace_back(); 154| 38| sub_info_arena.push_back(0xFFFFFFFF); // 0xFFFFFFFF = No substitution mapped here 155| 38| return new_idx; 156| 38| } 157| 30| return curr_idx + rel_idx; 158| 68| } _ZNK4TrieItLb1EE10get_statusEv: 275| 356k| bool get_status() const { return status_ok; } _ZNK4TrieItLb1EE9transcodeERKNSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEERS7_m: 205| 356k| TranscodeResult transcode(const std::string& src, std::string& dst, size_t maxlen) const { 206| | // Halt and return None if the trie is in an invalid memory state 207| 356k| if (!status_ok || src.empty()) return TranscodeResult::None; ------------------ | Branch (207:13): [True: 0, False: 356k] | Branch (207:27): [True: 1.89k, False: 354k] ------------------ 208| | 209| 354k| dst.clear(); 210| 354k| dst.reserve(src.size()); 211| | 212| | // State trackers for the 3-way outcome 213| 354k| bool any_substituted = false; 214| 354k| bool any_copied = false; 215| | 216| 354k| size_t i = 0; 217| | 218| 4.47M| while (i < src.size() && dst.size() <= maxlen) { ------------------ | Branch (218:16): [True: 4.12M, False: 354k] | Branch (218:34): [True: 4.12M, False: 0] ------------------ 219| 4.12M| size_t curr_idx = 0; 220| 4.12M| size_t match_len = 0; 221| 4.12M| uint32_t best_sub = 0xFFFFFFFF; 222| | 223| 4.12M| size_t j = i; 224| | 225| | // Greedily traverse the trie to find the longest matching sequence 226| 4.12M| while (j < src.size()) { ------------------ | Branch (226:20): [True: 4.12M, False: 168] ------------------ 227| 4.12M| uint8_t byte = static_cast(src[j]); 228| | 229| 4.12M| if (UseNibbles) { ------------------ | Branch (229:21): [True: 4.12M, Folded] ------------------ 230| 4.12M| IndexType r1 = nodes[curr_idx].children[(byte >> 4) & 0x0F]; 231| 4.12M| if (r1 == 0) break; ------------------ | Branch (231:25): [True: 4.07M, False: 54.1k] ------------------ 232| 54.1k| curr_idx += r1; 233| | 234| 54.1k| IndexType r2 = nodes[curr_idx].children[byte & 0x0F]; 235| 54.1k| if (r2 == 0) break; ------------------ | Branch (235:25): [True: 52.8k, False: 1.27k] ------------------ 236| 1.27k| curr_idx += r2; 237| 1.27k| } else { 238| 0| IndexType r = nodes[curr_idx].children[byte]; 239| 0| if (r == 0) break; ------------------ | Branch (239:25): [True: 0, False: 0] ------------------ 240| 0| curr_idx += r; 241| 0| } 242| | 243| 1.27k| ++j; 244| | 245| | // Track the deepest valid match found during traversal 246| 1.27k| if (sub_info_arena[curr_idx] != 0xFFFFFFFF) { ------------------ | Branch (246:21): [True: 370, False: 900] ------------------ 247| 370| best_sub = sub_info_arena[curr_idx]; 248| 370| match_len = j - i; 249| 370| } 250| 1.27k| } 251| | 252| 4.12M| if (best_sub != 0xFFFFFFFF) { ------------------ | Branch (252:17): [True: 370, False: 4.12M] ------------------ 253| | // Decode the 24-bit offset and 8-bit size, append directly from arena 254| 370| dst.append(&char_arena[best_sub >> 8], best_sub & 0xFF); 255| 370| i += match_len; 256| 370| any_substituted = true; // State update: Substitution occurred 257| 4.12M| } else { 258| | // Fallback: copy unmapped character directly to output 259| 4.12M| dst.push_back(src[i]); 260| 4.12M| ++i; 261| 4.12M| any_copied = true; // State update: Verbatim copy occurred 262| 4.12M| } 263| 4.12M| } 264| | 265| | // ALGORITHM: Outcome Evaluation 266| 354k| if (any_substituted && any_copied) { ------------------ | Branch (266:13): [True: 233, False: 354k] | Branch (266:32): [True: 228, False: 5] ------------------ 267| 228| return TranscodeResult::Partial; 268| 354k| } else if (any_substituted) { ------------------ | Branch (268:20): [True: 5, False: 354k] ------------------ 269| 5| return TranscodeResult::All; 270| 5| } 271| | 272| 354k| return TranscodeResult::None; 273| 354k| } _ZN10SuggestMgrC2ERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEjP8AffixMgr: 87| 38|SuggestMgr::SuggestMgr(const std::string& tryme, unsigned int maxn, AffixMgr* aptr) { 88| | // register affix manager and check in string of chars to 89| | // try when building candidate suggestions 90| 38| pAMgr = aptr; 91| | 92| 38| csconv = nullptr; 93| | 94| 38| ckeyl = 0; 95| | 96| 38| ctryl = 0; 97| | 98| 38| utf8 = 0; 99| 38| langnum = 0; 100| 38| complexprefixes = 0; 101| | 102| 38| maxSug = maxn; 103| 38| nosplitsugs = 0; 104| 38| maxngramsugs = MAXNGRAMSUGS; ------------------ | | 77| 38|#define MAXNGRAMSUGS 4 ------------------ 105| 38| maxcpdsugs = MAXCOMPOUNDSUGS; ------------------ | | 79| 38|#define MAXCOMPOUNDSUGS 3 ------------------ 106| | 107| 38| if (pAMgr) { ------------------ | Branch (107:7): [True: 38, False: 0] ------------------ 108| 38| langnum = pAMgr->get_langnum(); 109| 38| ckey = pAMgr->get_key_string(); 110| 38| nosplitsugs = pAMgr->get_nosplitsugs(); 111| 38| if (pAMgr->get_maxngramsugs() >= 0) ------------------ | Branch (111:9): [True: 4, False: 34] ------------------ 112| 4| maxngramsugs = pAMgr->get_maxngramsugs(); 113| 38| utf8 = pAMgr->get_utf8(); 114| 38| if (pAMgr->get_maxcpdsugs() >= 0) ------------------ | Branch (114:9): [True: 0, False: 38] ------------------ 115| 0| maxcpdsugs = pAMgr->get_maxcpdsugs(); 116| 38| if (!utf8) { ------------------ | Branch (116:9): [True: 20, False: 18] ------------------ 117| 20| csconv = get_current_cs(pAMgr->get_encoding()); 118| 20| } 119| 38| complexprefixes = pAMgr->get_complexprefixes(); 120| 38| } 121| | 122| 38| if (!ckey.empty()) { ------------------ | Branch (122:7): [True: 38, False: 0] ------------------ 123| 38| if (utf8) { ------------------ | Branch (123:9): [True: 18, False: 20] ------------------ 124| 18| int len = u8_u16(ckey_utf, ckey); 125| 18| if (len != -1) { ------------------ | Branch (125:11): [True: 18, False: 0] ------------------ 126| 18| ckeyl = len; 127| 18| } 128| 20| } else { 129| 20| ckeyl = ckey.size(); 130| 20| } 131| 38| } 132| | 133| 38| ctry = tryme; 134| 38| if (!ctry.empty()) { ------------------ | Branch (134:7): [True: 2, False: 36] ------------------ 135| 2| if (utf8) { ------------------ | Branch (135:9): [True: 2, False: 0] ------------------ 136| 2| int len = u8_u16(ctry_utf, ctry); 137| 2| if (len != -1) { ------------------ | Branch (137:11): [True: 2, False: 0] ------------------ 138| 2| ctryl = len; 139| 2| } 140| 2| } else { 141| 0| ctryl = ctry.size(); 142| 0| } 143| 2| } 144| | 145| | // language with possible dash usage 146| | // (latin letters or dash in TRY characters) 147| 38| lang_with_dash_usage = ctry.find('-') != std::string::npos || ------------------ | Branch (147:26): [True: 0, False: 38] ------------------ 148| 38| ctry.find('a') != std::string::npos; ------------------ | Branch (148:26): [True: 0, False: 38] ------------------ 149| 38|} _ZN10SuggestMgr7testsugERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iPiPNS0_6chrono10time_pointINSE_12steady_clockENSE_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEERi: 166| 81.4M| int& info) { 167| 81.4M| if (wlst.size() == maxSug) ------------------ | Branch (167:7): [True: 0, False: 81.4M] ------------------ 168| 0| return; 169| | 170| 81.4M| const int cwrd = std::find(wlst.begin(), wlst.end(), candidate) != wlst.end() ? 0 : 1; ------------------ | Branch (170:20): [True: 31.3k, False: 81.4M] ------------------ 171| | 172| 81.4M| if (cwrd) { ------------------ | Branch (172:7): [True: 81.4M, False: 31.3k] ------------------ 173| 81.4M| if (int result = checkword(candidate, cpdsuggest, timer, timelimit)) { ------------------ | Branch (173:13): [True: 2.08k, False: 81.4M] ------------------ 174| | // compound word in the dictionary 175| 2.08k| if (cpdsuggest == 0 && result >= 2) ------------------ | Branch (175:11): [True: 2.08k, False: 0] | Branch (175:30): [True: 0, False: 2.08k] ------------------ 176| 0| info |= SPELL_COMPOUND; ------------------ | | 81| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 177| 2.08k| wlst.push_back(candidate); 178| 2.08k| } 179| 81.4M| } 180| 81.4M|} _ZN10SuggestMgr7suggestERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_Pib: 190| 147k| int* onlycompoundsug, bool test_simplesug) { 191| 147k| int nocompoundtwowords = 0; // no second or third loops, see below 192| 147k| std::vector word_utf; 193| 147k| size_t nsugorig = slst.size(), oldSug = 0; 194| 147k| std::string w2; 195| 147k| bool good_suggestion = false; 196| | 197| | // word reversing wrapper for complex prefixes 198| 147k| if (complexprefixes) { ------------------ | Branch (198:7): [True: 8.44k, False: 139k] ------------------ 199| 8.44k| w2.assign(w); 200| 8.44k| if (utf8) ------------------ | Branch (200:9): [True: 0, False: 8.44k] ------------------ 201| 0| reverseword_utf(w2); 202| 8.44k| else 203| 8.44k| reverseword(w2); 204| 8.44k| } 205| | 206| 147k| const std::string& word = complexprefixes ? w2 : w; ------------------ | Branch (206:29): [True: 8.44k, False: 139k] ------------------ 207| | 208| 147k| suggest_start = std::chrono::steady_clock::now(); 209| | 210| 147k| if (utf8) { ------------------ | Branch (210:7): [True: 63.0k, False: 84.9k] ------------------ 211| 63.0k| int wl = u8_u16(word_utf, word); 212| 63.0k| if (wl == -1) { ------------------ | Branch (212:9): [True: 9.87k, False: 53.1k] ------------------ 213| 9.87k| return false; 214| 9.87k| } 215| 63.0k| } 216| | 217| | // three loops: 218| | // - the first without compounding, 219| | // - the second one with 2-word compounding, 220| | // - the third one with 3-or-more-word compounding 221| | // Run second and third loops only if: 222| | // - no ~good suggestion in the first loop 223| | // - not for testing compound words with 3 or more words (test_simplesug == false) 224| 138k| int info = 0; 225| 551k| for (int cpdsuggest = 0; cpdsuggest < 3 && nocompoundtwowords == 0; cpdsuggest++) { ------------------ | Branch (225:28): [True: 413k, False: 137k] | Branch (225:46): [True: 413k, False: 147] ------------------ 226| | 227| | // limit compound suggestion 228| 413k| if (cpdsuggest > 0) ------------------ | Branch (228:9): [True: 275k, False: 138k] ------------------ 229| 275k| oldSug = slst.size(); 230| | 231| | // suggestions for an uppercase word (html -> HTML) 232| 413k| if (slst.size() < maxSug) { ------------------ | Branch (232:9): [True: 413k, False: 15] ------------------ 233| 413k| size_t i = slst.size(); 234| 413k| if (utf8) ------------------ | Branch (234:11): [True: 159k, False: 254k] ------------------ 235| 159k| capchars_utf(slst, word_utf, cpdsuggest, info); 236| 254k| else 237| 254k| capchars(slst, word, cpdsuggest, info); 238| 413k| if (slst.size() > i) ------------------ | Branch (238:11): [True: 147, False: 413k] ------------------ 239| 147| good_suggestion = true; 240| 413k| } 241| | 242| | // perhaps we made a typical fault of spelling 243| 413k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (243:9): [True: 413k, False: 15] | Branch (243:36): [True: 138k, False: 275k] | Branch (243:51): [True: 275k, False: 0] ------------------ 244| 413k| size_t i = slst.size(); 245| 413k| replchars(slst, word, cpdsuggest, info); 246| 413k| if (slst.size() > i) { ------------------ | Branch (246:11): [True: 0, False: 413k] ------------------ 247| 0| good_suggestion = true; 248| 0| if (info & SPELL_BEST_SUG) ------------------ | | 89| 0|#define SPELL_BEST_SUG (1 << 8) // limit suggestions for the best ones, i.e. ph: ------------------ | Branch (248:13): [True: 0, False: 0] ------------------ 249| 0| return true; 250| 0| } 251| 413k| } 252| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (252:9): [True: 0, False: 413k] ------------------ 253| 0| return good_suggestion; 254| 413k| if (test_simplesug && slst.size()) ------------------ | Branch (254:9): [True: 0, False: 413k] | Branch (254:27): [True: 0, False: 0] ------------------ 255| 0| return true; 256| | 257| | // perhaps we made chose the wrong char from a related set 258| 413k| if ((slst.size() < maxSug) && ------------------ | Branch (258:9): [True: 413k, False: 15] ------------------ 259| 413k| (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (259:10): [True: 138k, False: 275k] | Branch (259:25): [True: 275k, False: 0] ------------------ 260| 413k| mapchars(slst, word, cpdsuggest, info); 261| 413k| } 262| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (262:9): [True: 11, False: 413k] ------------------ 263| 11| return good_suggestion; 264| 413k| if (test_simplesug && slst.size()) ------------------ | Branch (264:9): [True: 0, False: 413k] | Branch (264:27): [True: 0, False: 0] ------------------ 265| 0| return true; 266| | 267| | // only suggest compound words when no other ~good suggestion 268| 413k| if ((cpdsuggest == 0) && (slst.size() > nsugorig)) ------------------ | Branch (268:9): [True: 138k, False: 275k] | Branch (268:30): [True: 147, False: 137k] ------------------ 269| 147| nocompoundtwowords = 1; 270| | 271| | // did we swap the order of chars by mistake 272| 413k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (272:9): [True: 413k, False: 15] | Branch (272:36): [True: 138k, False: 275k] | Branch (272:51): [True: 275k, False: 0] ------------------ 273| 413k| if (utf8) ------------------ | Branch (273:11): [True: 159k, False: 254k] ------------------ 274| 159k| swapchar_utf(slst, word_utf, cpdsuggest, info); 275| 254k| else 276| 254k| swapchar(slst, word, cpdsuggest, info); 277| 413k| } 278| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (278:9): [True: 0, False: 413k] ------------------ 279| 0| return good_suggestion; 280| 413k| if (test_simplesug && slst.size()) ------------------ | Branch (280:9): [True: 0, False: 413k] | Branch (280:27): [True: 0, False: 0] ------------------ 281| 0| return true; 282| | 283| | // did we swap the order of non adjacent chars by mistake 284| 413k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (284:9): [True: 413k, False: 15] | Branch (284:36): [True: 138k, False: 275k] | Branch (284:51): [True: 275k, False: 0] ------------------ 285| 413k| if (utf8) ------------------ | Branch (285:11): [True: 159k, False: 254k] ------------------ 286| 159k| longswapchar_utf(slst, word_utf, cpdsuggest, info); 287| 254k| else 288| 254k| longswapchar(slst, word, cpdsuggest, info); 289| 413k| } 290| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (290:9): [True: 0, False: 413k] ------------------ 291| 0| return good_suggestion; 292| 413k| if (test_simplesug && slst.size()) ------------------ | Branch (292:9): [True: 0, False: 413k] | Branch (292:27): [True: 0, False: 0] ------------------ 293| 0| return true; 294| | 295| | // did we just hit the wrong key in place of a good char (case and keyboard) 296| 413k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (296:9): [True: 413k, False: 15] | Branch (296:36): [True: 138k, False: 275k] | Branch (296:51): [True: 275k, False: 0] ------------------ 297| 413k| if (utf8) ------------------ | Branch (297:11): [True: 159k, False: 254k] ------------------ 298| 159k| badcharkey_utf(slst, word_utf, cpdsuggest, info); 299| 254k| else 300| 254k| badcharkey(slst, word, cpdsuggest, info); 301| 413k| } 302| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (302:9): [True: 0, False: 413k] ------------------ 303| 0| return good_suggestion; 304| 413k| if (test_simplesug && slst.size()) ------------------ | Branch (304:9): [True: 0, False: 413k] | Branch (304:27): [True: 0, False: 0] ------------------ 305| 0| return true; 306| | 307| | // did we add a char that should not be there 308| 413k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (308:9): [True: 413k, False: 15] | Branch (308:36): [True: 138k, False: 275k] | Branch (308:51): [True: 275k, False: 0] ------------------ 309| 413k| if (utf8) ------------------ | Branch (309:11): [True: 159k, False: 254k] ------------------ 310| 159k| extrachar_utf(slst, word_utf, cpdsuggest, info); 311| 254k| else 312| 254k| extrachar(slst, word, cpdsuggest, info); 313| 413k| } 314| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (314:9): [True: 0, False: 413k] ------------------ 315| 0| return good_suggestion; 316| 413k| if (test_simplesug && slst.size()) ------------------ | Branch (316:9): [True: 0, False: 413k] | Branch (316:27): [True: 0, False: 0] ------------------ 317| 0| return true; 318| | 319| | // did we forgot a char 320| 413k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (320:9): [True: 413k, False: 15] | Branch (320:36): [True: 138k, False: 275k] | Branch (320:51): [True: 275k, False: 0] ------------------ 321| 413k| if (utf8) ------------------ | Branch (321:11): [True: 159k, False: 254k] ------------------ 322| 159k| forgotchar_utf(slst, word_utf, cpdsuggest, info); 323| 254k| else 324| 254k| forgotchar(slst, word, cpdsuggest, info); 325| 413k| } 326| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (326:9): [True: 0, False: 413k] ------------------ 327| 0| return good_suggestion; 328| 413k| if (test_simplesug && slst.size()) ------------------ | Branch (328:9): [True: 0, False: 413k] | Branch (328:27): [True: 0, False: 0] ------------------ 329| 0| return true; 330| | 331| | // did we move a char 332| 413k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (332:9): [True: 413k, False: 15] | Branch (332:36): [True: 138k, False: 275k] | Branch (332:51): [True: 275k, False: 0] ------------------ 333| 413k| if (utf8) ------------------ | Branch (333:11): [True: 159k, False: 254k] ------------------ 334| 159k| movechar_utf(slst, word_utf, cpdsuggest, info); 335| 254k| else 336| 254k| movechar(slst, word, cpdsuggest, info); 337| 413k| } 338| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (338:9): [True: 0, False: 413k] ------------------ 339| 0| return good_suggestion; 340| 413k| if (test_simplesug && slst.size()) ------------------ | Branch (340:9): [True: 0, False: 413k] | Branch (340:27): [True: 0, False: 0] ------------------ 341| 0| return true; 342| | 343| | // did we just hit the wrong key in place of a good char 344| 413k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (344:9): [True: 413k, False: 15] | Branch (344:36): [True: 138k, False: 275k] | Branch (344:51): [True: 275k, False: 0] ------------------ 345| 413k| if (utf8) ------------------ | Branch (345:11): [True: 159k, False: 254k] ------------------ 346| 159k| badchar_utf(slst, word_utf, cpdsuggest, info); 347| 254k| else 348| 254k| badchar(slst, word, cpdsuggest, info); 349| 413k| } 350| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (350:9): [True: 0, False: 413k] ------------------ 351| 0| return good_suggestion; 352| 413k| if (test_simplesug && slst.size()) ------------------ | Branch (352:9): [True: 0, False: 413k] | Branch (352:27): [True: 0, False: 0] ------------------ 353| 0| return true; 354| | 355| | // did we double two characters 356| 413k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (356:9): [True: 413k, False: 15] | Branch (356:36): [True: 138k, False: 275k] | Branch (356:51): [True: 275k, False: 0] ------------------ 357| 413k| if (utf8) ------------------ | Branch (357:11): [True: 159k, False: 254k] ------------------ 358| 159k| doubletwochars_utf(slst, word_utf, cpdsuggest, info); 359| 254k| else 360| 254k| doubletwochars(slst, word, cpdsuggest, info); 361| 413k| } 362| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (362:9): [True: 0, False: 413k] ------------------ 363| 0| return good_suggestion; 364| 413k| if (test_simplesug && slst.size()) ------------------ | Branch (364:9): [True: 0, False: 413k] | Branch (364:27): [True: 0, False: 0] ------------------ 365| 0| return true; 366| | 367| | // perhaps we forgot to hit space and two words ran together 368| | // (dictionary word pairs have top priority here, so 369| | // we always suggest them, in despite of nosplitsugs, and 370| | // drop compound word and other suggestions) 371| 413k| if (!cpdsuggest || (!nosplitsugs && slst.size() < oldSug + maxcpdsugs)) { ------------------ | Branch (371:9): [True: 138k, False: 275k] | Branch (371:25): [True: 275k, False: 0] | Branch (371:41): [True: 275k, False: 0] ------------------ 372| 413k| good_suggestion = twowords(slst, word, cpdsuggest, good_suggestion, info); 373| | 374| 413k| if (info & SPELL_BEST_SUG) ------------------ | | 89| 413k|#define SPELL_BEST_SUG (1 << 8) // limit suggestions for the best ones, i.e. ph: ------------------ | Branch (374:11): [True: 137, False: 413k] ------------------ 375| 137| return true; 376| 413k| } 377| 413k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 413k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (377:9): [True: 0, False: 413k] ------------------ 378| 0| return good_suggestion; 379| | 380| | // testing returns after the first loop 381| 413k| if (test_simplesug) ------------------ | Branch (381:9): [True: 0, False: 413k] ------------------ 382| 0| return slst.size() > 0; 383| | 384| | // don't need third loop, if the second loop was successful or 385| | // the first loop found a dictionary-based compound word 386| | // (we don't need more, likely worse and false 3-or-more-word compound words) 387| 413k| if (cpdsuggest == 1 && (slst.size() > oldSug || (info & SPELL_COMPOUND))) ------------------ | | 81| 137k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ | Branch (387:9): [True: 137k, False: 275k] | Branch (387:29): [True: 0, False: 137k] | Branch (387:53): [True: 0, False: 137k] ------------------ 388| 0| nocompoundtwowords = 1; 389| | 390| 413k| } // repeating ``for'' statement compounding support 391| | 392| 137k| if (!nocompoundtwowords && (!slst.empty()) && onlycompoundsug) ------------------ | Branch (392:7): [True: 137k, False: 147] | Branch (392:30): [True: 17.6k, False: 120k] | Branch (392:49): [True: 17.6k, False: 0] ------------------ 393| 17.6k| *onlycompoundsug = 1; 394| | 395| 137k| return good_suggestion; 396| 138k|} _ZN10SuggestMgr12capchars_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 401| 159k| int cpdsuggest, int& info) { 402| 159k| std::vector candidate_utf(word); 403| 159k| mkallcap_utf(candidate_utf, langnum); 404| 159k| std::string candidate; 405| 159k| u16_u8(candidate, candidate_utf); 406| 159k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 407| 159k|} _ZN10SuggestMgr8capcharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 412| 254k| int cpdsuggest, int& info) { 413| 254k| std::string candidate(word); 414| 254k| mkallcap(candidate, csconv); 415| 254k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 416| 254k|} _ZN10SuggestMgr8mapcharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 421| 413k| int cpdsuggest, int& info) { 422| 413k| std::string candidate; 423| 413k| std::chrono::steady_clock::time_point timelimit; 424| 413k| int timer; 425| | 426| 413k| if (word.size() < 2 || !pAMgr) ------------------ | Branch (426:7): [True: 33.0k, False: 380k] | Branch (426:26): [True: 0, False: 380k] ------------------ 427| 33.0k| return wlst.size(); 428| | 429| 380k| const std::vector& maptable = pAMgr->get_maptable(); 430| 380k| if (maptable.empty()) ------------------ | Branch (430:7): [True: 364k, False: 15.8k] ------------------ 431| 364k| return wlst.size(); 432| | 433| 15.8k| timelimit = std::chrono::steady_clock::now(); 434| 15.8k| timer = MINTIMER; ------------------ | | 110| 15.8k|#define MINTIMER 100 ------------------ 435| 15.8k| return map_related(word, candidate, 0, wlst, cpdsuggest, 436| 15.8k| maptable, &timer, &timelimit, 0, info); 437| 380k|} _ZN10SuggestMgr11map_relatedERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERS6_mRNS0_6vectorIS6_NS4_IS6_EEEEiRKNSA_ISC_NS4_ISC_EEEEPiPNS0_6chrono10time_pointINSJ_12steady_clockENSJ_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEEiRi: 447| 6.42M| int depth, int& info) { 448| 6.42M| if (word.size() == wn) { ------------------ | Branch (448:7): [True: 2.82M, False: 3.60M] ------------------ 449| 2.82M| if (candidate == word) ------------------ | Branch (449:9): [True: 15.8k, False: 2.80M] ------------------ 450| 15.8k| return wlst.size(); 451| 2.80M| const int cwrd = std::find(wlst.begin(), wlst.end(), candidate) != wlst.end() ? 0 : 1; ------------------ | Branch (451:22): [True: 0, False: 2.80M] ------------------ 452| 2.80M| if ((cwrd) && checkword(candidate, cpdsuggest, timer, timelimit)) { ------------------ | Branch (452:9): [True: 2.80M, False: 0] | Branch (452:19): [True: 0, False: 2.80M] ------------------ 453| 0| if (wlst.size() < maxSug) { ------------------ | Branch (453:11): [True: 0, False: 0] ------------------ 454| 0| wlst.push_back(candidate); 455| 0| } 456| 0| } 457| 2.80M| return wlst.size(); 458| 2.82M| } 459| | 460| 3.60M| if (depth > 0x3F00) { ------------------ | Branch (460:7): [True: 0, False: 3.60M] ------------------ 461| 0| *timer = 0; 462| 0| return wlst.size(); 463| 0| } 464| | 465| 3.60M| int in_map = 0; 466| 14.4M| for (size_t j = 0; j < maptable.size(); ++j) { ------------------ | Branch (466:22): [True: 10.8M, False: 3.60M] ------------------ 467| 39.6M| for (size_t k = 0; k < maptable[j].size(); ++k) { ------------------ | Branch (467:24): [True: 28.8M, False: 10.8M] ------------------ 468| 28.8M| size_t len = maptable[j][k].size(); 469| 28.8M| if (len && word.compare(wn, len, maptable[j][k]) == 0) { ------------------ | Branch (469:11): [True: 28.8M, False: 0] | Branch (469:18): [True: 1.40M, False: 27.4M] ------------------ 470| 1.40M| in_map = 1; 471| 1.40M| size_t cn = candidate.size(); 472| 5.61M| for (size_t l = 0; l < maptable[j].size(); ++l) { ------------------ | Branch (472:28): [True: 4.21M, False: 1.40M] ------------------ 473| 4.21M| candidate.resize(cn); 474| 4.21M| candidate.append(maptable[j][l]); 475| 4.21M| map_related(word, candidate, wn + len, wlst, 476| 4.21M| cpdsuggest, maptable, timer, timelimit, depth + 1, info); 477| 4.21M| if (!(*timer)) ------------------ | Branch (477:15): [True: 555, False: 4.21M] ------------------ 478| 555| return wlst.size(); 479| 4.21M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) { ------------------ | | 108| 4.21M|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (479:15): [True: 11, False: 4.21M] ------------------ 480| 11| *timer = 0; 481| 11| return wlst.size(); 482| 11| } 483| 4.21M| } 484| 1.40M| } 485| 28.8M| } 486| 10.8M| } 487| 3.60M| if (!in_map) { ------------------ | Branch (487:7): [True: 2.19M, False: 1.40M] ------------------ 488| 2.19M| candidate.push_back(word[wn]); 489| 2.19M| map_related(word, candidate, wn + 1, wlst, cpdsuggest, 490| 2.19M| maptable, timer, timelimit, depth + 1, info); 491| 2.19M| } 492| 3.60M| return wlst.size(); 493| 3.60M|} _ZN10SuggestMgr9replcharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 499| 413k| int cpdsuggest, int& info) { 500| 413k| std::string candidate; 501| 413k| int wl = word.size(); 502| 413k| if (wl < 2 || !pAMgr) ------------------ | Branch (502:7): [True: 33.0k, False: 380k] | Branch (502:17): [True: 0, False: 380k] ------------------ 503| 33.0k| return wlst.size(); 504| 380k| const std::vector& reptable = pAMgr->get_reptable(); 505| 380k| auto replchars_start = std::chrono::steady_clock::now(); 506| 380k| for (const auto& entry : reptable) { ------------------ | Branch (506:26): [True: 79.0k, False: 380k] ------------------ 507| 79.0k| size_t r = 0; 508| | // search every occurence of the pattern in the word 509| 79.0k| while ((r = word.find(entry.pattern, r)) != std::string::npos) { ------------------ | Branch (509:12): [True: 6, False: 79.0k] ------------------ 510| 6| if (std::chrono::steady_clock::now() - replchars_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 6|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (510:11): [True: 0, False: 6] ------------------ 511| 0| return wlst.size(); 512| 6| int type = (r == 0) ? 1 : 0; ------------------ | Branch (512:18): [True: 0, False: 6] ------------------ 513| 6| if (r + entry.pattern.size() == word.size()) ------------------ | Branch (513:11): [True: 0, False: 6] ------------------ 514| 0| type += 2; 515| 6| while (type && entry.outstrings[type].empty()) ------------------ | Branch (515:14): [True: 0, False: 6] | Branch (515:22): [True: 0, False: 0] ------------------ 516| 0| type = (type == 2 && r != 0) ? 0 : type - 1; ------------------ | Branch (516:17): [True: 0, False: 0] | Branch (516:30): [True: 0, False: 0] ------------------ 517| 6| const std::string&out = entry.outstrings[type]; 518| 6| if (out.empty()) { ------------------ | Branch (518:11): [True: 0, False: 6] ------------------ 519| 0| ++r; 520| 0| continue; 521| 0| } 522| 6| candidate.assign(word, 0, r); 523| 6| candidate.append(entry.outstrings[type]); 524| 6| candidate.append(word, r + entry.pattern.size(), std::string::npos); 525| 6| size_t sp = candidate.find(' '); 526| 6| size_t oldns = wlst.size(); 527| 6| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 528| 6| if (oldns < wlst.size()) { ------------------ | Branch (528:11): [True: 0, False: 6] ------------------ 529| | // REP suggestions are the best, don't search other type of suggestions 530| 0| info |= SPELL_BEST_SUG; ------------------ | | 89| 0|#define SPELL_BEST_SUG (1 << 8) // limit suggestions for the best ones, i.e. ph: ------------------ 531| 0| } 532| | 533| | // check REP suggestions with space 534| 6| if (sp != std::string::npos) { ------------------ | Branch (534:11): [True: 0, False: 6] ------------------ 535| 0| size_t prev = 0; 536| 0| while (sp != std::string::npos) { ------------------ | Branch (536:16): [True: 0, False: 0] ------------------ 537| 0| std::string prev_chunk = candidate.substr(prev, sp - prev); 538| 0| if (checkword(prev_chunk, 0, nullptr, nullptr)) { ------------------ | Branch (538:15): [True: 0, False: 0] ------------------ 539| 0| oldns = wlst.size(); 540| 0| std::string post_chunk = candidate.substr(sp + 1); 541| 0| testsug(wlst, post_chunk, cpdsuggest, nullptr, nullptr, info); 542| 0| if (oldns < wlst.size()) { ------------------ | Branch (542:17): [True: 0, False: 0] ------------------ 543| 0| wlst[wlst.size() - 1] = candidate; 544| 0| } 545| 0| } 546| 0| prev = sp + 1; 547| 0| sp = candidate.find(' ', prev); 548| 0| } 549| 0| } 550| 6| r++; // search for the next letter 551| 6| } 552| 79.0k| } 553| 380k| return wlst.size(); 554| 380k|} _ZN10SuggestMgr14doubletwocharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 563| 254k| int cpdsuggest, int& info) { 564| 254k| size_t wl = word.size(); 565| 254k| if (wl < 5 || !pAMgr) ------------------ | Branch (565:7): [True: 51.1k, False: 203k] | Branch (565:17): [True: 0, False: 203k] ------------------ 566| 51.1k| return wlst.size(); 567| | 568| 203k| int state = 0; 569| 4.81M| for (size_t i = 2; i < wl; ++i) { ------------------ | Branch (569:22): [True: 4.61M, False: 203k] ------------------ 570| 4.61M| if (word[i] == word[i - 2]) { ------------------ | Branch (570:9): [True: 1.18M, False: 3.43M] ------------------ 571| 1.18M| state++; 572| 1.18M| if (state == 3 || (state == 2 && i >= 4)) { ------------------ | Branch (572:11): [True: 6.26k, False: 1.17M] | Branch (572:26): [True: 417k, False: 758k] | Branch (572:40): [True: 408k, False: 8.78k] ------------------ 573| 414k| auto word_iter = word.begin(); 574| 414k| std::string candidate(word_iter, word_iter + i - 1); 575| 414k| candidate.insert(candidate.end(), word_iter + i + 1, word.end()); 576| 414k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 577| 414k| state = 0; 578| 414k| } 579| 3.43M| } else { 580| 3.43M| state = 0; 581| 3.43M| } 582| 4.61M| } 583| 203k| return wlst.size(); 584| 254k|} _ZN10SuggestMgr18doubletwochars_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 593| 159k| int cpdsuggest, int& info) { 594| 159k| size_t wl = word.size(); 595| 159k| int state = 0; 596| 159k| if (wl < 5 || !pAMgr) ------------------ | Branch (596:7): [True: 56.0k, False: 103k] | Branch (596:17): [True: 0, False: 103k] ------------------ 597| 56.0k| return wlst.size(); 598| 1.67M| for (size_t i = 2; i < wl; ++i) { ------------------ | Branch (598:22): [True: 1.57M, False: 103k] ------------------ 599| 1.57M| if (word[i] == word[i - 2]) { ------------------ | Branch (599:9): [True: 473k, False: 1.10M] ------------------ 600| 473k| state++; 601| 473k| if (state == 3 || (state == 2 && i >= 4)) { ------------------ | Branch (601:11): [True: 3.61k, False: 470k] | Branch (601:26): [True: 164k, False: 305k] | Branch (601:40): [True: 159k, False: 5.04k] ------------------ 602| 163k| auto word_iter = word.begin(); 603| 163k| std::vector candidate_utf(word_iter, word_iter + i - 1); 604| 163k| candidate_utf.insert(candidate_utf.end(), word_iter + i + 1, word.end()); 605| 163k| std::string candidate; 606| 163k| u16_u8(candidate, candidate_utf); 607| 163k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 608| 163k| state = 0; 609| 163k| } 610| 1.10M| } else { 611| 1.10M| state = 0; 612| 1.10M| } 613| 1.57M| } 614| 103k| return wlst.size(); 615| 159k|} _ZN10SuggestMgr10badcharkeyERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 621| 254k| int cpdsuggest, int& info) { 622| 254k| std::string candidate(word); 623| | 624| | // swap out each char one by one and try uppercase and neighbor 625| | // keyboard chars in its place to see if that makes a good word 626| 5.39M| for (size_t i = 0, wl = candidate.size(); i < wl; ++i) { ------------------ | Branch (626:45): [True: 5.14M, False: 254k] ------------------ 627| 5.14M| char tmpc = candidate[i]; 628| | // check with uppercase letters 629| 5.14M| candidate[i] = csconv[((unsigned char)tmpc)].cupper; 630| 5.14M| if (tmpc != candidate[i]) { ------------------ | Branch (630:9): [True: 1.35M, False: 3.78M] ------------------ 631| 1.35M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 632| 1.35M| candidate[i] = tmpc; 633| 1.35M| } 634| | // check neighbor characters in keyboard string 635| 5.14M| if (ckey.empty()) ------------------ | Branch (635:9): [True: 0, False: 5.14M] ------------------ 636| 0| continue; 637| 5.14M| size_t loc = 0; 638| 133M| while ((loc < ckeyl) && ckey[loc] != tmpc) ------------------ | Branch (638:12): [True: 129M, False: 4.22M] | Branch (638:29): [True: 128M, False: 915k] ------------------ 639| 128M| ++loc; 640| 6.08M| while (loc < ckeyl) { ------------------ | Branch (640:12): [True: 944k, False: 5.14M] ------------------ 641| | // a long keyboard string can hold many neighbours for this 642| | // character, so give up once the overall time budget is spent 643| 944k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 944k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (643:11): [True: 0, False: 944k] ------------------ 644| 0| return wlst.size(); 645| 944k| if ((loc > 0) && ckey[loc - 1] != '|') { ------------------ | Branch (645:11): [True: 780k, False: 164k] | Branch (645:24): [True: 746k, False: 33.8k] ------------------ 646| 746k| candidate[i] = ckey[loc - 1]; 647| 746k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 648| 746k| } 649| 944k| if (((loc + 1) < ckeyl) && (ckey[loc + 1] != '|')) { ------------------ | Branch (649:11): [True: 867k, False: 77.5k] | Branch (649:34): [True: 785k, False: 81.6k] ------------------ 650| 785k| candidate[i] = ckey[loc + 1]; 651| 785k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 652| 785k| } 653| 15.2M| do { 654| 15.2M| loc++; 655| 15.2M| } while ((loc < ckeyl) && ckey[loc] != tmpc); ------------------ | Branch (655:16): [True: 14.2M, False: 915k] | Branch (655:33): [True: 14.2M, False: 29.4k] ------------------ 656| 944k| } 657| 5.14M| candidate[i] = tmpc; 658| 5.14M| } 659| 254k| return wlst.size(); 660| 254k|} _ZN10SuggestMgr14badcharkey_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 666| 159k| int cpdsuggest, int& info) { 667| 159k| std::string candidate; 668| 159k| std::vector candidate_utf(word); 669| | // swap out each char one by one and try all the tryme 670| | // chars in its place to see if that makes a good word 671| 2.08M| for (size_t i = 0, wl = word.size(); i < wl; ++i) { ------------------ | Branch (671:40): [True: 1.92M, False: 159k] ------------------ 672| 1.92M| w_char tmpc = candidate_utf[i]; 673| | // check with uppercase letters 674| 1.92M| candidate_utf[i] = upper_utf(candidate_utf[i], 1); 675| 1.92M| if (tmpc != candidate_utf[i]) { ------------------ | Branch (675:9): [True: 485k, False: 1.44M] ------------------ 676| 485k| u16_u8(candidate, candidate_utf); 677| 485k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 678| 485k| candidate_utf[i] = tmpc; 679| 485k| } 680| | // check neighbor characters in keyboard string 681| 1.92M| if (ckey_utf.empty()) ------------------ | Branch (681:9): [True: 0, False: 1.92M] ------------------ 682| 0| continue; 683| 1.92M| size_t loc = 0; 684| 47.6M| while ((loc < ckeyl) && ckey_utf[loc] != tmpc) ------------------ | Branch (684:12): [True: 46.2M, False: 1.42M] | Branch (684:29): [True: 45.7M, False: 497k] ------------------ 685| 45.7M| ++loc; 686| 2.44M| while (loc < ckeyl) { ------------------ | Branch (686:12): [True: 513k, False: 1.92M] ------------------ 687| | // a long keyboard string can hold many neighbours for this 688| | // character, so give up once the overall time budget is spent 689| 513k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 513k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (689:11): [True: 0, False: 513k] ------------------ 690| 0| return wlst.size(); 691| 513k| if ((loc > 0) && ckey_utf[loc - 1] != W_VLINE) { ------------------ | Branch (691:11): [True: 410k, False: 103k] | Branch (691:24): [True: 410k, False: 0] ------------------ 692| 410k| candidate_utf[i] = ckey_utf[loc - 1]; 693| 410k| u16_u8(candidate, candidate_utf); 694| 410k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 695| 410k| } 696| 513k| if (((loc + 1) < ckeyl) && (ckey_utf[loc + 1] != W_VLINE)) { ------------------ | Branch (696:11): [True: 462k, False: 51.5k] | Branch (696:34): [True: 462k, False: 0] ------------------ 697| 462k| candidate_utf[i] = ckey_utf[loc + 1]; 698| 462k| u16_u8(candidate, candidate_utf); 699| 462k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 700| 462k| } 701| 8.23M| do { 702| 8.23M| loc++; 703| 8.23M| } while ((loc < ckeyl) && ckey_utf[loc] != tmpc); ------------------ | Branch (703:16): [True: 7.73M, False: 497k] | Branch (703:33): [True: 7.72M, False: 15.9k] ------------------ 704| 513k| } 705| 1.92M| candidate_utf[i] = tmpc; 706| 1.92M| } 707| 159k| return wlst.size(); 708| 159k|} _ZN10SuggestMgr7badcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 713| 254k| int cpdsuggest, int& info) { 714| 254k| std::string candidate(word); 715| 254k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 716| 254k| int timer = MINTIMER; ------------------ | | 110| 254k|#define MINTIMER 100 ------------------ 717| | // swap out each char one by one and try all the tryme 718| | // chars in its place to see if that makes a good word 719| 254k| for (size_t j = 0; j < ctryl; ++j) { ------------------ | Branch (719:22): [True: 0, False: 254k] ------------------ 720| 0| for (auto aI = candidate.rbegin(), aEnd = candidate.rend(); aI != aEnd; ++aI) { ------------------ | Branch (720:65): [True: 0, False: 0] ------------------ 721| 0| char tmpc = *aI; 722| 0| if (ctry[j] == tmpc) ------------------ | Branch (722:11): [True: 0, False: 0] ------------------ 723| 0| continue; 724| 0| *aI = ctry[j]; 725| 0| testsug(wlst, candidate, cpdsuggest, &timer, &timelimit, info); 726| 0| if (!timer) ------------------ | Branch (726:11): [True: 0, False: 0] ------------------ 727| 0| return wlst.size(); 728| 0| *aI = tmpc; 729| 0| } 730| 0| } 731| 254k| return wlst.size(); 732| 254k|} _ZN10SuggestMgr11badchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 737| 159k| int cpdsuggest, int& info) { 738| 159k| std::vector candidate_utf(word); 739| 159k| std::string candidate; 740| 159k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 741| 159k| int timer = MINTIMER; ------------------ | | 110| 159k|#define MINTIMER 100 ------------------ 742| | // swap out each char one by one and try all the tryme 743| | // chars in its place to see if that makes a good word 744| 177k| for (size_t j = 0; j < ctryl; ++j) { ------------------ | Branch (744:22): [True: 18.1k, False: 159k] ------------------ 745| 240k| for (auto aI = candidate_utf.rbegin(), aEnd = candidate_utf.rend(); aI != aEnd; ++aI) { ------------------ | Branch (745:73): [True: 222k, False: 18.1k] ------------------ 746| 222k| w_char tmpc = *aI; 747| 222k| if (tmpc == ctry_utf[j]) ------------------ | Branch (747:11): [True: 0, False: 222k] ------------------ 748| 0| continue; 749| 222k| *aI = ctry_utf[j]; 750| 222k| u16_u8(candidate, candidate_utf); 751| 222k| testsug(wlst, candidate, cpdsuggest, &timer, &timelimit, info); 752| 222k| if (!timer) ------------------ | Branch (752:11): [True: 0, False: 222k] ------------------ 753| 0| return wlst.size(); 754| 222k| *aI = tmpc; 755| 222k| } 756| 18.1k| } 757| 159k| return wlst.size(); 758| 159k|} _ZN10SuggestMgr13extrachar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 763| 159k| int cpdsuggest, int& info) { 764| 159k| std::vector candidate_utf(word); 765| 159k| if (candidate_utf.size() < 2) ------------------ | Branch (765:7): [True: 16.0k, False: 143k] ------------------ 766| 16.0k| return wlst.size(); 767| | // try omitting one char of word at a time 768| 2.05M| for (size_t i = 0; i < candidate_utf.size(); ++i) { ------------------ | Branch (768:22): [True: 1.91M, False: 143k] ------------------ 769| 1.91M| size_t index = candidate_utf.size() - 1 - i; 770| 1.91M| w_char tmpc = candidate_utf[index]; 771| 1.91M| candidate_utf.erase(candidate_utf.begin() + index); 772| 1.91M| std::string candidate; 773| 1.91M| u16_u8(candidate, candidate_utf); 774| 1.91M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 775| 1.91M| candidate_utf.insert(candidate_utf.begin() + index, tmpc); 776| 1.91M| } 777| 143k| return wlst.size(); 778| 159k|} _ZN10SuggestMgr9extracharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 783| 254k| int cpdsuggest, int& info) { 784| 254k| std::string candidate(word); 785| 254k| if (candidate.size() < 2) ------------------ | Branch (785:7): [True: 17.4k, False: 236k] ------------------ 786| 17.4k| return wlst.size(); 787| | // try omitting one char of word at a time 788| 5.35M| for (size_t i = 0; i < candidate.size(); ++i) { ------------------ | Branch (788:22): [True: 5.12M, False: 236k] ------------------ 789| 5.12M| size_t index = candidate.size() - 1 - i; 790| 5.12M| char tmpc = candidate[index]; 791| 5.12M| candidate.erase(candidate.begin() + index); 792| 5.12M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 793| 5.12M| candidate.insert(candidate.begin() + index, tmpc); 794| 5.12M| } 795| 236k| return wlst.size(); 796| 254k|} _ZN10SuggestMgr10forgotcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 801| 254k| int cpdsuggest, int& info) { 802| 254k| std::string candidate(word); 803| 254k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 804| 254k| int timer = MINTIMER; ------------------ | | 110| 254k|#define MINTIMER 100 ------------------ 805| | 806| | // try inserting a tryme character before every letter (and the null 807| | // terminator) 808| 254k| for (size_t k = 0; k < ctryl; ++k) { ------------------ | Branch (808:22): [True: 0, False: 254k] ------------------ 809| 0| for (size_t i = 0; i <= candidate.size(); ++i) { ------------------ | Branch (809:24): [True: 0, False: 0] ------------------ 810| 0| size_t index = candidate.size() - i; 811| 0| candidate.insert(candidate.begin() + index, ctry[k]); 812| 0| testsug(wlst, candidate, cpdsuggest, &timer, &timelimit, info); 813| 0| if (!timer) ------------------ | Branch (813:11): [True: 0, False: 0] ------------------ 814| 0| return wlst.size(); 815| 0| candidate.erase(candidate.begin() + index); 816| 0| } 817| 0| } 818| 254k| return wlst.size(); 819| 254k|} _ZN10SuggestMgr14forgotchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 824| 159k| int cpdsuggest, int& info) { 825| 159k| std::vector candidate_utf(word); 826| 159k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 827| 159k| int timer = MINTIMER; ------------------ | | 110| 159k|#define MINTIMER 100 ------------------ 828| | 829| | // try inserting a tryme character at the end of the word and before every 830| | // letter 831| 177k| for (size_t k = 0; k < ctryl; ++k) { ------------------ | Branch (831:22): [True: 18.1k, False: 159k] ------------------ 832| 259k| for (size_t i = 0; i <= candidate_utf.size(); ++i) { ------------------ | Branch (832:24): [True: 240k, False: 18.1k] ------------------ 833| 240k| size_t index = candidate_utf.size() - i; 834| 240k| candidate_utf.insert(candidate_utf.begin() + index, ctry_utf[k]); 835| 240k| std::string candidate; 836| 240k| u16_u8(candidate, candidate_utf); 837| 240k| testsug(wlst, candidate, cpdsuggest, &timer, &timelimit, info); 838| 240k| if (!timer) ------------------ | Branch (838:11): [True: 0, False: 240k] ------------------ 839| 0| return wlst.size(); 840| 240k| candidate_utf.erase(candidate_utf.begin() + index); 841| 240k| } 842| 18.1k| } 843| 159k| return wlst.size(); 844| 159k|} _ZN10SuggestMgr8twowordsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_ibRi: 854| 413k| bool good, int& info) { 855| 413k| int c2, forbidden = 0, cwrd, wl = word.size(); 856| 413k| if (wl < 3) ------------------ | Branch (856:7): [True: 52.7k, False: 360k] ------------------ 857| 52.7k| return false; 858| | 859| 360k| if (langnum == LANG_hu) ------------------ | Branch (859:7): [True: 15.1k, False: 345k] ------------------ 860| 15.1k| forbidden = check_forbidden(word); 861| | 862| 360k| char* candidate = new char[wl + 2]; 863| 360k| memcpy(candidate + 1, word.data(), wl); 864| 360k| candidate[wl + 1] = 0; 865| | 866| | // split the string into two pieces after every char 867| | // if both pieces are good words make them a suggestion 868| 4.64M| for (char* p = candidate + 1; p[1] != '\0'; p++) { ------------------ | Branch (868:33): [True: 4.31M, False: 324k] ------------------ 869| 4.31M| p[-1] = *p; 870| | // go to end of the UTF-8 character 871| 4.60M| while (utf8 && is_utf8_cont(p[1])) { ------------------ | Branch (871:12): [True: 1.59M, False: 3.01M] | Branch (871:20): [True: 292k, False: 1.30M] ------------------ 872| 292k| *p = p[1]; 873| 292k| p++; 874| 292k| } 875| 4.31M| if (utf8 && p[1] == '\0') ------------------ | Branch (875:9): [True: 1.30M, False: 3.01M] | Branch (875:17): [True: 36.2k, False: 1.26M] ------------------ 876| 36.2k| break; // last UTF-8 character 877| | 878| | // Suggest only word pairs, if they are listed in the dictionary. 879| | // For example, adding "a lot" to the English dic file will 880| | // result only "alot" -> "a lot" suggestion instead of 881| | // "alto, slot, alt, lot, allot, aloft, aloe, clot, plot, blot, a lot". 882| | // Note: using "ph:alot" keeps the other suggestions: 883| | // a lot ph:alot 884| | // alot -> a lot, alto, slot... 885| 4.28M| *p = ' '; 886| 4.28M| if (!cpdsuggest && checkword(candidate, cpdsuggest, nullptr, nullptr)) { ------------------ | Branch (886:9): [True: 1.42M, False: 2.85M] | Branch (886:9): [True: 1.37k, False: 4.27M] | Branch (886:24): [True: 1.37k, False: 1.42M] ------------------ 887| | // best solution 888| 1.37k| info |= SPELL_BEST_SUG; ------------------ | | 89| 1.37k|#define SPELL_BEST_SUG (1 << 8) // limit suggestions for the best ones, i.e. ph: ------------------ 889| | 890| | // remove not word pair suggestions 891| 1.37k| if (!good) { ------------------ | Branch (891:11): [True: 137, False: 1.23k] ------------------ 892| 137| good = true; 893| 137| wlst.clear(); 894| 137| } 895| | 896| 1.37k| wlst.insert(wlst.begin(), candidate); 897| 1.37k| } 898| | 899| | // word pairs with dash? 900| 4.28M| if (lang_with_dash_usage) { ------------------ | Branch (900:9): [True: 0, False: 4.28M] ------------------ 901| 0| *p = '-'; 902| | 903| 0| if (!cpdsuggest && checkword(candidate, cpdsuggest, nullptr, nullptr)) { ------------------ | Branch (903:11): [True: 0, False: 0] | Branch (903:11): [True: 0, False: 0] | Branch (903:26): [True: 0, False: 0] ------------------ 904| | // best solution 905| 0| info |= SPELL_BEST_SUG; ------------------ | | 89| 0|#define SPELL_BEST_SUG (1 << 8) // limit suggestions for the best ones, i.e. ph: ------------------ 906| | 907| | // remove not word pair suggestions 908| 0| if (!good) { ------------------ | Branch (908:13): [True: 0, False: 0] ------------------ 909| 0| good = true; 910| 0| wlst.clear(); 911| 0| } 912| 0| wlst.insert(wlst.begin(), candidate); 913| 0| } 914| 0| } 915| | 916| 4.28M| if (wlst.size() < maxSug && !nosplitsugs && !good) { ------------------ | Branch (916:9): [True: 4.27M, False: 496] | Branch (916:33): [True: 4.27M, False: 0] | Branch (916:49): [True: 4.27M, False: 874] ------------------ 917| 4.27M| *p = '\0'; 918| 4.27M| int c1 = checkword(candidate, cpdsuggest, nullptr, nullptr); 919| 4.27M| if (c1) { ------------------ | Branch (919:11): [True: 28.9k, False: 4.24M] ------------------ 920| 28.9k| c2 = checkword((p + 1), cpdsuggest, nullptr, nullptr); 921| 28.9k| if (c2) { ------------------ | Branch (921:13): [True: 793, False: 28.1k] ------------------ 922| | // spec. Hungarian code (TODO need a better compound word support) 923| 793| if ((langnum == LANG_hu) && !forbidden && ------------------ | Branch (923:15): [True: 7, False: 786] | Branch (923:39): [True: 7, False: 0] ------------------ 924| | // if 3 repeating letter, use - instead of space 925| 7| (((p[-1] == p[1]) && ------------------ | Branch (925:17): [True: 5, False: 2] ------------------ 926| 5| (((p > candidate + 1) && (p[-1] == p[-2])) || (p[-1] == p[2]))) || ------------------ | Branch (926:17): [True: 0, False: 5] | Branch (926:40): [True: 0, False: 0] | Branch (926:61): [True: 0, False: 5] ------------------ 927| | // or multiple compounding, with more, than 6 syllables 928| 7| ((c1 == 3) && (c2 >= 2)))) ------------------ | Branch (928:16): [True: 0, False: 7] | Branch (928:29): [True: 0, False: 0] ------------------ 929| 0| *p = '-'; 930| 793| else 931| 793| *p = ' '; 932| | 933| 793| cwrd = std::find(wlst.begin(), wlst.end(), candidate) != wlst.end() ? 0 : 1; ------------------ | Branch (933:18): [True: 1, False: 792] ------------------ 934| | 935| 793| if (cwrd && (wlst.size() < maxSug)) ------------------ | Branch (935:15): [True: 792, False: 1] | Branch (935:23): [True: 792, False: 0] ------------------ 936| 792| wlst.emplace_back(candidate); 937| | 938| | // add two word suggestion with dash, depending on the language 939| | // Note that cwrd doesn't modified for REP twoword sugg. 940| 793| if ( !nosplitsugs && lang_with_dash_usage && ------------------ | Branch (940:16): [True: 793, False: 0] | Branch (940:32): [True: 0, False: 793] ------------------ 941| 0| mystrlen(p + 1) > 1 && mystrlen(candidate) - mystrlen(p) > 1) { ------------------ | Branch (941:15): [True: 0, False: 0] | Branch (941:38): [True: 0, False: 0] ------------------ 942| 0| *p = '-'; 943| 0| for (auto& k : wlst) { ------------------ | Branch (943:26): [True: 0, False: 0] ------------------ 944| 0| if (k == candidate) { ------------------ | Branch (944:19): [True: 0, False: 0] ------------------ 945| 0| cwrd = 0; 946| 0| break; 947| 0| } 948| 0| } 949| | 950| 0| if ((wlst.size() < maxSug) && cwrd) ------------------ | Branch (950:17): [True: 0, False: 0] | Branch (950:43): [True: 0, False: 0] ------------------ 951| 0| wlst.emplace_back(candidate); 952| 0| } 953| 793| } 954| 28.9k| } 955| 4.27M| } 956| 4.28M| } 957| 360k| delete[] candidate; 958| 360k| return good; 959| 413k|} _ZN10SuggestMgr8swapcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 964| 254k| int cpdsuggest, int& info) { 965| 254k| if (word.size() < 2) ------------------ | Branch (965:7): [True: 17.4k, False: 236k] ------------------ 966| 17.4k| return wlst.size(); 967| | 968| 236k| std::string candidate(word); 969| | 970| | // try swapping adjacent chars one by one 971| 5.12M| for (size_t i = 0; i < candidate.size() - 1; ++i) { ------------------ | Branch (971:22): [True: 4.88M, False: 236k] ------------------ 972| 4.88M| std::swap(candidate[i], candidate[i+1]); 973| 4.88M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 974| 4.88M| std::swap(candidate[i], candidate[i+1]); 975| 4.88M| } 976| | 977| | // try double swaps for short words 978| | // ahev -> have, owudl -> would 979| 236k| if (candidate.size() == 4 || candidate.size() == 5) { ------------------ | Branch (979:7): [True: 11.4k, False: 225k] | Branch (979:32): [True: 10.3k, False: 215k] ------------------ 980| 21.8k| candidate[0] = word[1]; 981| 21.8k| candidate[1] = word[0]; 982| 21.8k| candidate[2] = word[2]; 983| 21.8k| candidate[candidate.size() - 2] = word[candidate.size() - 1]; 984| 21.8k| candidate[candidate.size() - 1] = word[candidate.size() - 2]; 985| 21.8k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 986| 21.8k| if (candidate.size() == 5) { ------------------ | Branch (986:9): [True: 10.3k, False: 11.4k] ------------------ 987| 10.3k| candidate[0] = word[0]; 988| 10.3k| candidate[1] = word[2]; 989| 10.3k| candidate[2] = word[1]; 990| 10.3k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 991| 10.3k| } 992| 21.8k| } 993| | 994| 236k| return wlst.size(); 995| 254k|} _ZN10SuggestMgr12swapchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 1000| 159k| int cpdsuggest, int& info) { 1001| 159k| if (word.size() < 2) ------------------ | Branch (1001:7): [True: 16.0k, False: 143k] ------------------ 1002| 16.0k| return wlst.size(); 1003| | 1004| 143k| std::vector candidate_utf(word); 1005| | 1006| 143k| std::string candidate; 1007| | // try swapping adjacent chars one by one 1008| 1.91M| for (size_t i = 0; i < candidate_utf.size() - 1; ++i) { ------------------ | Branch (1008:22): [True: 1.76M, False: 143k] ------------------ 1009| 1.76M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 1.76M|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (1009:9): [True: 0, False: 1.76M] ------------------ 1010| 0| return wlst.size(); 1011| 1.76M| std::swap(candidate_utf[i], candidate_utf[i+1]); 1012| 1.76M| u16_u8(candidate, candidate_utf); 1013| 1.76M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1014| 1.76M| std::swap(candidate_utf[i], candidate_utf[i+1]); 1015| 1.76M| } 1016| | 1017| | // try double swaps for short words 1018| | // ahev -> have, owudl -> would, suodn -> sound 1019| 143k| if (candidate_utf.size() == 4 || candidate_utf.size() == 5) { ------------------ | Branch (1019:7): [True: 18.7k, False: 124k] | Branch (1019:36): [True: 10.4k, False: 114k] ------------------ 1020| 29.2k| candidate_utf[0] = word[1]; 1021| 29.2k| candidate_utf[1] = word[0]; 1022| 29.2k| candidate_utf[2] = word[2]; 1023| 29.2k| candidate_utf[candidate_utf.size() - 2] = word[candidate_utf.size() - 1]; 1024| 29.2k| candidate_utf[candidate_utf.size() - 1] = word[candidate_utf.size() - 2]; 1025| 29.2k| u16_u8(candidate, candidate_utf); 1026| 29.2k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1027| 29.2k| if (candidate_utf.size() == 5) { ------------------ | Branch (1027:9): [True: 10.4k, False: 18.7k] ------------------ 1028| 10.4k| candidate_utf[0] = word[0]; 1029| 10.4k| candidate_utf[1] = word[2]; 1030| 10.4k| candidate_utf[2] = word[1]; 1031| 10.4k| u16_u8(candidate, candidate_utf); 1032| 10.4k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1033| 10.4k| } 1034| 29.2k| } 1035| 143k| return wlst.size(); 1036| 143k|} _ZN10SuggestMgr12longswapcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 1041| 254k| int cpdsuggest, int& info) { 1042| 254k| std::string candidate(word); 1043| | // try swapping not adjacent chars one by one 1044| 5.39M| for (auto p = candidate.begin(); p < candidate.end(); ++p) { ------------------ | Branch (1044:36): [True: 5.14M, False: 254k] ------------------ 1045| 185M| for (auto q = candidate.begin(); q < candidate.end(); ++q) { ------------------ | Branch (1045:38): [True: 180M, False: 5.14M] ------------------ 1046| 180M| const auto distance = std::abs(std::distance(q, p)); 1047| 180M| if (distance > 1 && distance <= MAX_CHAR_DISTANCE && *p != *q) { ------------------ | | 84| 346M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1047:11): [True: 165M, False: 14.9M] | Branch (1047:27): [True: 26.5M, False: 139M] | Branch (1047:60): [True: 20.1M, False: 6.44M] ------------------ 1048| 20.1M| std::swap(*p, *q); 1049| 20.1M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1050| 20.1M| std::swap(*p, *q); 1051| 20.1M| } 1052| 180M| } 1053| 5.14M| } 1054| 254k| return wlst.size(); 1055| 254k|} _ZN10SuggestMgr16longswapchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 1060| 159k| int cpdsuggest, int& info) { 1061| 159k| std::vector candidate_utf(word); 1062| | // try swapping not adjacent chars 1063| 2.08M| for (auto p = candidate_utf.begin(); p < candidate_utf.end(); ++p) { ------------------ | Branch (1063:40): [True: 1.92M, False: 159k] ------------------ 1064| 52.3M| for (auto q = candidate_utf.begin(); q < candidate_utf.end(); ++q) { ------------------ | Branch (1064:42): [True: 50.3M, False: 1.92M] ------------------ 1065| 50.3M| const auto distance = std::abs(std::distance(q, p)); 1066| 50.3M| if (distance > 1 && distance <= MAX_CHAR_DISTANCE && *p != *q) { ------------------ | | 84| 95.3M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1066:11): [True: 44.9M, False: 5.46M] | Branch (1066:27): [True: 8.97M, False: 35.9M] | Branch (1066:60): [True: 6.36M, False: 2.61M] ------------------ 1067| 6.36M| std::swap(*p, *q); 1068| 6.36M| std::string candidate; 1069| 6.36M| u16_u8(candidate, candidate_utf); 1070| 6.36M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1071| 6.36M| std::swap(*p, *q); 1072| 6.36M| } 1073| 50.3M| } 1074| 1.92M| } 1075| 159k| return wlst.size(); 1076| 159k|} _ZN10SuggestMgr8movecharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 1081| 254k| int cpdsuggest, int& info) { 1082| 254k| if (word.size() < 2) ------------------ | Branch (1082:7): [True: 17.4k, False: 236k] ------------------ 1083| 17.4k| return wlst.size(); 1084| | 1085| 236k| std::string candidate(word); 1086| | 1087| | // try moving a char 1088| 5.35M| for (auto p = candidate.begin(); p < candidate.end(); ++p) { ------------------ | Branch (1088:36): [True: 5.12M, False: 236k] ------------------ 1089| 23.2M| for (auto q = p + 1; q < candidate.end() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 22.1M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1089:26): [True: 22.1M, False: 1.11M] | Branch (1089:26): [True: 18.1M, False: 5.12M] | Branch (1089:49): [True: 18.1M, False: 4.00M] ------------------ 1090| 18.1M| std::swap(*q, *(q - 1)); 1091| 18.1M| if (std::distance(p, q) < 2) ------------------ | Branch (1091:11): [True: 4.88M, False: 13.2M] ------------------ 1092| 4.88M| continue; // omit swap char 1093| 13.2M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1094| 13.2M| } 1095| 5.12M| const auto word_iter = word.begin(); 1096| 5.12M| std::copy_n(word_iter, candidate.size(), candidate.begin()); 1097| 5.12M| } 1098| | 1099| 5.12M| for (auto p = candidate.rbegin(), pEnd = candidate.rend() - 1; p != pEnd; ++p) { ------------------ | Branch (1099:66): [True: 4.88M, False: 236k] ------------------ 1100| 23.0M| for (auto q = p + 1, qEnd = candidate.rend(); q != qEnd && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 22.1M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1100:51): [True: 22.1M, False: 880k] | Branch (1100:64): [True: 18.1M, False: 4.00M] ------------------ 1101| 18.1M| std::swap(*q, *(q - 1)); 1102| 18.1M| if (std::distance(p, q) < 2) ------------------ | Branch (1102:11): [True: 4.88M, False: 13.2M] ------------------ 1103| 4.88M| continue; // omit swap char 1104| 13.2M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1105| 13.2M| } 1106| 4.88M| const auto word_iter = word.begin(); 1107| 4.88M| std::copy_n(word_iter, candidate.size(), candidate.begin()); 1108| 4.88M| } 1109| | 1110| 236k| return wlst.size(); 1111| 254k|} _ZN10SuggestMgr12movechar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 1116| 159k| int cpdsuggest, int& info) { 1117| 159k| if (word.size() < 2) ------------------ | Branch (1117:7): [True: 16.0k, False: 143k] ------------------ 1118| 16.0k| return wlst.size(); 1119| | 1120| 143k| std::vector candidate_utf(word); 1121| | 1122| | // try moving a char 1123| 2.05M| for (auto p = candidate_utf.begin(); p < candidate_utf.end(); ++p) { ------------------ | Branch (1123:40): [True: 1.91M, False: 143k] ------------------ 1124| 8.16M| for (auto q = p + 1; q < candidate_utf.end() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 7.52M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1124:26): [True: 7.52M, False: 643k] | Branch (1124:26): [True: 6.25M, False: 1.91M] | Branch (1124:53): [True: 6.25M, False: 1.26M] ------------------ 1125| 6.25M| std::swap(*q, *(q - 1)); 1126| 6.25M| if (std::distance(p, q) < 2) ------------------ | Branch (1126:11): [True: 1.76M, False: 4.48M] ------------------ 1127| 1.76M| continue; // omit swap char 1128| 4.48M| std::string candidate; 1129| 4.48M| u16_u8(candidate, candidate_utf); 1130| 4.48M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1131| 4.48M| } 1132| 1.91M| const auto word_iter = word.begin(); 1133| 1.91M| std::copy_n(word_iter, candidate_utf.size(), candidate_utf.begin()); 1134| 1.91M| } 1135| | 1136| 2.05M| for (auto p = candidate_utf.rbegin(); p < candidate_utf.rend(); ++p) { ------------------ | Branch (1136:41): [True: 1.91M, False: 143k] ------------------ 1137| 8.16M| for (auto q = p + 1; q < candidate_utf.rend() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 7.52M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1137:26): [True: 7.52M, False: 643k] | Branch (1137:26): [True: 6.25M, False: 1.91M] | Branch (1137:54): [True: 6.25M, False: 1.26M] ------------------ 1138| 6.25M| std::swap(*q, *(q - 1)); 1139| 6.25M| if (std::distance(p, q) < 2) ------------------ | Branch (1139:11): [True: 1.76M, False: 4.48M] ------------------ 1140| 1.76M| continue; // omit swap char 1141| 4.48M| std::string candidate; 1142| 4.48M| u16_u8(candidate, candidate_utf); 1143| 4.48M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1144| 4.48M| } 1145| 1.91M| const auto word_iter = word.begin(); 1146| 1.91M| std::copy_n(word_iter, candidate_utf.size(), candidate_utf.begin()); 1147| 1.91M| } 1148| | 1149| 143k| return wlst.size(); 1150| 159k|} _ZN10SuggestMgr9ngsuggestERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEEPKcRKNS1_INS0_10unique_ptrI7HashMgrNS0_14default_deleteISE_EEEENS5_ISH_EEEEi: 1185| 61.4k| int captype) { 1186| 61.4k| int lval, sc, lp, lpphon, nonbmp = 0; 1187| | 1188| | // exhaustively search through all root words 1189| | // keeping track of the MAX_ROOTS most similar root words 1190| 61.4k| struct hentry* roots[MAX_ROOTS]; 1191| 61.4k| char* rootsphon[MAX_ROOTS]; 1192| 61.4k| int scores[MAX_ROOTS]; 1193| 61.4k| int scoresphon[MAX_ROOTS]; 1194| 6.20M| for (int i = 0; i < MAX_ROOTS; i++) { ------------------ | | 74| 6.20M|#define MAX_ROOTS 100 ------------------ | Branch (1194:19): [True: 6.14M, False: 61.4k] ------------------ 1195| 6.14M| roots[i] = nullptr; 1196| 6.14M| scores[i] = -100 * i; 1197| 6.14M| rootsphon[i] = nullptr; 1198| 6.14M| scoresphon[i] = -100 * i; 1199| 6.14M| } 1200| 61.4k| bool has_roots = false; 1201| 61.4k| bool has_rootsphon = false; 1202| 61.4k| lp = MAX_ROOTS - 1; ------------------ | | 74| 61.4k|#define MAX_ROOTS 100 ------------------ 1203| 61.4k| lpphon = MAX_ROOTS - 1; ------------------ | | 74| 61.4k|#define MAX_ROOTS 100 ------------------ 1204| 61.4k| int low = NGRAM_LOWERING; ------------------ | | 83| 61.4k|#define NGRAM_LOWERING (1 << 2) ------------------ 1205| | 1206| 61.4k| std::string w2; 1207| 61.4k| const char* word = w; 1208| | 1209| 61.4k| int nc; 1210| | // word reversing wrapper for complex prefixes 1211| 61.4k| if (complexprefixes) { ------------------ | Branch (1211:7): [True: 3.45k, False: 57.9k] ------------------ 1212| 3.45k| w2.assign(w); 1213| 3.45k| if (utf8) ------------------ | Branch (1213:9): [True: 0, False: 3.45k] ------------------ 1214| 0| reverseword_utf(w2); 1215| 3.45k| else 1216| 3.45k| reverseword(w2); 1217| 3.45k| word = w2.c_str(); 1218| 3.45k| nc = (int)w2.size(); 1219| 57.9k| } else { 1220| 57.9k| nc = (int)strlen(word); 1221| 57.9k| } 1222| | 1223| 61.4k| std::vector u8; 1224| 61.4k| int n = (utf8) ? u8_u16(u8, word) : nc; ------------------ | Branch (1224:11): [True: 26.1k, False: 35.3k] ------------------ 1225| | 1226| | // set character based ngram suggestion for words with non-BMP Unicode 1227| | // characters 1228| 61.4k| const struct cs_info* origconv = csconv; 1229| 61.4k| if (n == -1) { ------------------ | Branch (1229:7): [True: 1.71k, False: 59.7k] ------------------ 1230| 1.71k| utf8 = 0; // XXX not state-free 1231| 1.71k| if (!csconv) ------------------ | Branch (1231:9): [True: 1.71k, False: 0] ------------------ 1232| 1.71k| csconv = get_current_cs("iso88591"); // XXX not state-free 1233| 1.71k| n = nc; 1234| 1.71k| nonbmp = 1; 1235| 1.71k| low = 0; 1236| 1.71k| } 1237| 61.4k| ngsuggest_guard restore_state(nonbmp, origconv, &utf8, &csconv); 1238| 61.4k| int max_word_len = (utf8) ? MAXWORDUTF8LEN : MAXWORDLEN; ------------------ | | 85| 24.3k|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 24.3k|#define MAXWORDLEN 100 | | ------------------ ------------------ int max_word_len = (utf8) ? MAXWORDUTF8LEN : MAXWORDLEN; ------------------ | | 90| 37.0k|#define MAXWORDLEN 100 ------------------ | Branch (1238:22): [True: 24.3k, False: 37.0k] ------------------ 1239| | // ofz#59067 a replist entry can generate a very long word, abandon 1240| | // ngram if that odd-edge case arises 1241| 61.4k| if (n > max_word_len * 4) ------------------ | Branch (1241:7): [True: 0, False: 61.4k] ------------------ 1242| 0| return; 1243| | 1244| 61.4k| struct hentry* hp = nullptr; 1245| 61.4k| int col = -1; 1246| 61.4k| phonetable* ph = (pAMgr) ? pAMgr->get_phonetable() : nullptr; ------------------ | Branch (1246:20): [True: 61.4k, False: 0] ------------------ 1247| 61.4k| std::string target; 1248| 61.4k| std::string candidate; 1249| 61.4k| std::vector w_candidate; 1250| 61.4k| if (ph) { ------------------ | Branch (1250:7): [True: 3.49k, False: 57.9k] ------------------ 1251| 3.49k| if (utf8) { ------------------ | Branch (1251:9): [True: 0, False: 3.49k] ------------------ 1252| 0| u8_u16(w_candidate, word); 1253| 0| mkallcap_utf(w_candidate, langnum); 1254| 0| u16_u8(candidate, w_candidate); 1255| 3.49k| } else { 1256| 3.49k| candidate.assign(word); 1257| 3.49k| if (!nonbmp) ------------------ | Branch (1257:11): [True: 3.49k, False: 0] ------------------ 1258| 3.49k| mkallcap(candidate, csconv); 1259| 3.49k| } 1260| 3.49k| target = phonet(candidate, *ph); // XXX phonet() is 8-bit (nc, not n) 1261| 3.49k| } 1262| | 1263| 61.4k| FLAG forbiddenword = pAMgr ? pAMgr->get_forbiddenword() : FLAG_NULL; ------------------ | | 98| 61.4k|#define FLAG unsigned short ------------------ FLAG forbiddenword = pAMgr ? pAMgr->get_forbiddenword() : FLAG_NULL; ------------------ | | 99| 61.4k|#define FLAG_NULL 0x00 ------------------ | Branch (1263:24): [True: 61.4k, False: 0] ------------------ 1264| 61.4k| FLAG nosuggest = pAMgr ? pAMgr->get_nosuggest() : FLAG_NULL; ------------------ | | 98| 61.4k|#define FLAG unsigned short ------------------ FLAG nosuggest = pAMgr ? pAMgr->get_nosuggest() : FLAG_NULL; ------------------ | | 99| 61.4k|#define FLAG_NULL 0x00 ------------------ | Branch (1264:20): [True: 61.4k, False: 0] ------------------ 1265| 61.4k| FLAG nongramsuggest = pAMgr ? pAMgr->get_nongramsuggest() : FLAG_NULL; ------------------ | | 98| 61.4k|#define FLAG unsigned short ------------------ FLAG nongramsuggest = pAMgr ? pAMgr->get_nongramsuggest() : FLAG_NULL; ------------------ | | 99| 61.4k|#define FLAG_NULL 0x00 ------------------ | Branch (1265:25): [True: 61.4k, False: 0] ------------------ 1266| 61.4k| FLAG onlyincompound = pAMgr ? pAMgr->get_onlyincompound() : FLAG_NULL; ------------------ | | 98| 61.4k|#define FLAG unsigned short ------------------ FLAG onlyincompound = pAMgr ? pAMgr->get_onlyincompound() : FLAG_NULL; ------------------ | | 99| 61.4k|#define FLAG_NULL 0x00 ------------------ | Branch (1266:25): [True: 61.4k, False: 0] ------------------ 1267| | 1268| 61.4k| std::vector w_word, w_target; 1269| 61.4k| if (utf8) { ------------------ | Branch (1269:7): [True: 24.3k, False: 37.0k] ------------------ 1270| 24.3k| u8_u16(w_word, word); 1271| 24.3k| u8_u16(w_target, target); 1272| 24.3k| } 1273| | 1274| 61.4k| std::string f; 1275| 61.4k| std::vector w_f; 1276| | 1277| 61.4k| for (const auto& i : rHMgr) { ------------------ | Branch (1277:22): [True: 61.4k, False: 61.4k] ------------------ 1278| 1.98M| while (nullptr != (hp = i->walk_hashtable(col, hp))) { ------------------ | Branch (1278:12): [True: 1.92M, False: 61.4k] ------------------ 1279| | // skip exceptions 1280| 1.92M| if ( 1281| | // skip it, if the word length different by 5 or 1282| | // more characters (to avoid strange suggestions) 1283| | // (except Unicode characters over BMP) 1284| 1.92M| (((abs(n - hp->clen) > 4) && !nonbmp)) || ------------------ | Branch (1284:12): [True: 1.37M, False: 545k] | Branch (1284:14): [True: 1.29M, False: 620k] | Branch (1284:41): [True: 1.24M, False: 53.4k] ------------------ 1285| | // don't suggest capitalized dictionary words for 1286| | // lower case misspellings in ngram suggestions, except 1287| | // - PHONE usage, or 1288| | // - in the case of German, where not only proper 1289| | // nouns are capitalized, or 1290| | // - the capitalized word has special pronunciation 1291| 673k| ((captype == NOCAP) && (hp->var & H_OPT_INITCAP) && ------------------ | | 92| 673k|#define NOCAP 0 ------------------ ((captype == NOCAP) && (hp->var & H_OPT_INITCAP) && ------------------ | | 50| 161k|#define H_OPT_INITCAP (1 << 3) // is dictionary word capitalized? ------------------ | Branch (1291:13): [True: 161k, False: 512k] | Branch (1291:35): [True: 71.1k, False: 90.1k] ------------------ 1292| 71.1k| !ph && (langnum != LANG_de) && !(hp->var & H_OPT_PHON)) || ------------------ | | 49| 69.6k|#define H_OPT_PHON (1 << 2) // is there ph: field in the morphological data? ------------------ | Branch (1292:15): [True: 69.6k, False: 1.50k] | Branch (1292:22): [True: 69.6k, False: 0] | Branch (1292:46): [True: 69.6k, False: 0] ------------------ 1293| | // or it has one of the following special flags 1294| 604k| ((hp->astr) && (pAMgr) && ------------------ | Branch (1294:13): [True: 154k, False: 449k] | Branch (1294:27): [True: 154k, False: 0] ------------------ 1295| 154k| (TESTAFF(hp->astr, forbiddenword, hp->alen) || ------------------ | | 102| 309k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 2.11k, False: 152k] | | ------------------ ------------------ 1296| 152k| TESTAFF(hp->astr, ONLYUPCASEFLAG, hp->alen) || ------------------ | | 102| 307k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 56.7k, False: 96.0k] | | ------------------ ------------------ 1297| 96.0k| TESTAFF(hp->astr, nosuggest, hp->alen) || ------------------ | | 102| 250k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 96.0k] | | ------------------ ------------------ 1298| 96.0k| TESTAFF(hp->astr, nongramsuggest, hp->alen) || ------------------ | | 102| 250k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 96.0k] | | ------------------ ------------------ 1299| 96.0k| TESTAFF(hp->astr, onlyincompound, hp->alen))) ------------------ | | 102| 96.0k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 96.0k] | | ------------------ ------------------ 1300| 1.92M| ) 1301| 1.37M| continue; 1302| | 1303| 545k| if (utf8) { ------------------ | Branch (1303:11): [True: 245k, False: 300k] ------------------ 1304| 245k| u8_u16(w_f, HENTRY_WORD(hp)); ------------------ | | 54| 245k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1305| | 1306| 245k| int leftcommon = leftcommonsubstring(w_word, w_f); 1307| 245k| if (low) { ------------------ | Branch (1307:13): [True: 245k, False: 0] ------------------ 1308| | // lowering dictionary word 1309| 245k| mkallsmall_utf(w_f, langnum); 1310| 245k| } 1311| 245k| sc = ngram(3, w_word, w_f, NGRAM_LONGER_WORSE) + leftcommon; ------------------ | | 81| 245k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1312| 300k| } else { 1313| 300k| f.assign(HENTRY_WORD(hp)); ------------------ | | 54| 300k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1314| | 1315| 300k| int leftcommon = leftcommonsubstring(word, f.c_str()); 1316| 300k| if (low) { ------------------ | Branch (1316:13): [True: 278k, False: 22.2k] ------------------ 1317| | // lowering dictionary word 1318| 278k| mkallsmall(f, csconv); 1319| 278k| } 1320| 300k| sc = ngram(3, word, f, NGRAM_LONGER_WORSE) + leftcommon; ------------------ | | 81| 300k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1321| 300k| } 1322| | 1323| | // check special pronunciation 1324| 545k| f.clear(); 1325| 545k| if ((hp->var & H_OPT_PHON) && ------------------ | | 49| 545k|#define H_OPT_PHON (1 << 2) // is there ph: field in the morphological data? ------------------ | Branch (1325:11): [True: 887, False: 544k] | Branch (1325:11): [True: 887, False: 544k] ------------------ 1326| 887| copy_field(f, HENTRY_DATA(hp), MORPH_PHON)) { ------------------ | | 114| 887|#define MORPH_PHON "ph:" ------------------ | Branch (1326:11): [True: 887, False: 0] ------------------ 1327| 887| int sc2; 1328| 887| if (utf8) { ------------------ | Branch (1328:13): [True: 0, False: 887] ------------------ 1329| 0| u8_u16(w_f, f); 1330| | 1331| 0| int leftcommon = leftcommonsubstring(w_word, w_f); 1332| 0| if (low) { ------------------ | Branch (1332:15): [True: 0, False: 0] ------------------ 1333| | // lowering dictionary word 1334| 0| mkallsmall_utf(w_f, langnum); 1335| 0| } 1336| 0| sc2 = ngram(3, w_word, w_f, NGRAM_LONGER_WORSE) + leftcommon; ------------------ | | 81| 0|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1337| 887| } else { 1338| 887| int leftcommon = leftcommonsubstring(word, f.c_str()); 1339| 887| if (low) { ------------------ | Branch (1339:15): [True: 887, False: 0] ------------------ 1340| | // lowering dictionary word 1341| 887| mkallsmall(f, csconv); 1342| 887| } 1343| 887| sc2 = ngram(3, word, f, NGRAM_LONGER_WORSE) + leftcommon; ------------------ | | 81| 887|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1344| 887| } 1345| 887| if (sc2 > sc) ------------------ | Branch (1345:13): [True: 452, False: 435] ------------------ 1346| 452| sc = sc2; 1347| 887| } 1348| | 1349| 545k| int scphon = -20000; 1350| 545k| if (ph && (sc > 2) && (abs(n - (int)hp->clen) <= 3)) { ------------------ | Branch (1350:11): [True: 33.6k, False: 511k] | Branch (1350:17): [True: 7.84k, False: 25.8k] | Branch (1350:29): [True: 6.65k, False: 1.18k] ------------------ 1351| 6.65k| if (utf8) { ------------------ | Branch (1351:13): [True: 0, False: 6.65k] ------------------ 1352| 0| u8_u16(w_candidate, HENTRY_WORD(hp)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1353| 0| mkallcap_utf(w_candidate, langnum); 1354| 0| u16_u8(candidate, w_candidate); 1355| 6.65k| } else { 1356| 6.65k| candidate = HENTRY_WORD(hp); ------------------ | | 54| 6.65k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1357| 6.65k| mkallcap(candidate, csconv); 1358| 6.65k| } 1359| 6.65k| f = phonet(candidate, *ph); 1360| 6.65k| if (utf8) { ------------------ | Branch (1360:13): [True: 0, False: 6.65k] ------------------ 1361| 0| u8_u16(w_f, f); 1362| 0| scphon = 2 * ngram(3, w_target, w_f, 1363| 0| NGRAM_LONGER_WORSE); ------------------ | | 81| 0|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1364| 6.65k| } else { 1365| 6.65k| scphon = 2 * ngram(3, target, f, 1366| 6.65k| NGRAM_LONGER_WORSE); ------------------ | | 81| 6.65k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1367| 6.65k| } 1368| 6.65k| } 1369| | 1370| 545k| if (sc > scores[lp]) { ------------------ | Branch (1370:11): [True: 545k, False: 0] ------------------ 1371| 545k| scores[lp] = sc; 1372| 545k| roots[lp] = hp; 1373| 545k| has_roots = true; 1374| 545k| lval = sc; 1375| 55.0M| for (int j = 0; j < MAX_ROOTS; j++) ------------------ | | 74| 55.0M|#define MAX_ROOTS 100 ------------------ | Branch (1375:25): [True: 54.5M, False: 545k] ------------------ 1376| 54.5M| if (scores[j] < lval) { ------------------ | Branch (1376:15): [True: 45.4M, False: 9.12M] ------------------ 1377| 45.4M| lp = j; 1378| 45.4M| lval = scores[j]; 1379| 45.4M| } 1380| 545k| } 1381| | 1382| 545k| if (scphon > scoresphon[lpphon]) { ------------------ | Branch (1382:11): [True: 6.65k, False: 538k] ------------------ 1383| 6.65k| scoresphon[lpphon] = scphon; 1384| 6.65k| rootsphon[lpphon] = HENTRY_WORD(hp); ------------------ | | 54| 6.65k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1385| 6.65k| has_rootsphon = true; 1386| 6.65k| lval = scphon; 1387| 671k| for (int j = 0; j < MAX_ROOTS; j++) ------------------ | | 74| 671k|#define MAX_ROOTS 100 ------------------ | Branch (1387:25): [True: 665k, False: 6.65k] ------------------ 1388| 665k| if (scoresphon[j] < lval) { ------------------ | Branch (1388:15): [True: 583k, False: 81.8k] ------------------ 1389| 583k| lpphon = j; 1390| 583k| lval = scoresphon[j]; 1391| 583k| } 1392| 6.65k| } 1393| 545k| } 1394| 61.4k| } 1395| | 1396| 61.4k| if (!has_roots && !has_rootsphon) { ------------------ | Branch (1396:7): [True: 14.3k, False: 47.0k] | Branch (1396:21): [True: 14.3k, False: 0] ------------------ 1397| | // with no roots there will be no guesses and no point running 1398| | // ngram 1399| 14.3k| return; 1400| 14.3k| } 1401| | 1402| | // find minimum threshold for a passable suggestion 1403| | // mangle original word three differnt ways 1404| | // and score them to generate a minimum acceptable score 1405| 47.0k| std::vector w_mw; 1406| 47.0k| int thresh = 0; 1407| 188k| for (int sp = 1; sp < 4; sp++) { ------------------ | Branch (1407:20): [True: 141k, False: 47.0k] ------------------ 1408| 141k| if (utf8) { ------------------ | Branch (1408:9): [True: 59.2k, False: 81.8k] ------------------ 1409| 59.2k| w_mw = w_word; 1410| 112k| for (int k = sp; k < n; k += 4) { ------------------ | Branch (1410:24): [True: 53.2k, False: 59.2k] ------------------ 1411| 53.2k| w_mw[k].l = '*'; 1412| 53.2k| w_mw[k].h = 0; 1413| 53.2k| } 1414| | 1415| 59.2k| if (low) { ------------------ | Branch (1415:11): [True: 59.2k, False: 0] ------------------ 1416| | // lowering dictionary word 1417| 59.2k| mkallsmall_utf(w_mw, langnum); 1418| 59.2k| } 1419| | 1420| 59.2k| thresh += ngram(n, w_word, w_mw, NGRAM_ANY_MISMATCH); ------------------ | | 82| 59.2k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1421| 81.8k| } else { 1422| 81.8k| std::string mw = word; 1423| 194k| for (int k = sp; k < n; k += 4) ------------------ | Branch (1423:24): [True: 112k, False: 81.8k] ------------------ 1424| 112k| mw[k] = '*'; 1425| | 1426| 81.8k| if (low) { ------------------ | Branch (1426:11): [True: 76.6k, False: 5.13k] ------------------ 1427| | // lowering dictionary word 1428| 76.6k| mkallsmall(mw, csconv); 1429| 76.6k| } 1430| | 1431| 81.8k| thresh += ngram(n, word, mw, NGRAM_ANY_MISMATCH); ------------------ | | 82| 81.8k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1432| 81.8k| } 1433| 141k| } 1434| 47.0k| thresh = thresh / 3; 1435| 47.0k| thresh--; 1436| | 1437| | // now expand affixes on each of these root words and 1438| | // and use length adjusted ngram scores to select 1439| | // possible suggestions 1440| 47.0k| char* guess[MAX_GUESS]; 1441| 47.0k| char* guessorig[MAX_GUESS]; 1442| 47.0k| int gscore[MAX_GUESS]; 1443| 9.45M| for (int i = 0; i < MAX_GUESS; i++) { ------------------ | | 76| 9.45M|#define MAX_GUESS 200 ------------------ | Branch (1443:19): [True: 9.40M, False: 47.0k] ------------------ 1444| 9.40M| guess[i] = nullptr; 1445| 9.40M| guessorig[i] = nullptr; 1446| 9.40M| gscore[i] = -100 * i; 1447| 9.40M| } 1448| | 1449| 47.0k| lp = MAX_GUESS - 1; ------------------ | | 76| 47.0k|#define MAX_GUESS 200 ------------------ 1450| | 1451| 47.0k| std::vector glst(MAX_WORDS); ------------------ | | 75| 47.0k|#define MAX_WORDS 100 ------------------ 1452| | 1453| 4.70M| for (auto& root : roots) { ------------------ | Branch (1453:19): [True: 4.70M, False: 47.0k] ------------------ 1454| 4.70M| if (root) { ------------------ | Branch (1454:9): [True: 545k, False: 4.15M] ------------------ 1455| 545k| struct hentry* rp = root; 1456| | 1457| 545k| f.clear(); 1458| 545k| const char* field = nullptr; 1459| 545k| if ((rp->var & H_OPT_PHON) && copy_field(f, HENTRY_DATA(rp), MORPH_PHON)) ------------------ | | 49| 545k|#define H_OPT_PHON (1 << 2) // is there ph: field in the morphological data? ------------------ if ((rp->var & H_OPT_PHON) && copy_field(f, HENTRY_DATA(rp), MORPH_PHON)) ------------------ | | 114| 887|#define MORPH_PHON "ph:" ------------------ | Branch (1459:11): [True: 887, False: 544k] | Branch (1459:11): [True: 887, False: 544k] | Branch (1459:37): [True: 887, False: 0] ------------------ 1460| 887| field = f.c_str(); 1461| 545k| int nw = pAMgr->expand_rootword( 1462| 545k| glst.data(), MAX_WORDS, HENTRY_WORD(rp), rp->blen, rp->astr, rp->alen, word, ------------------ | | 75| 545k|#define MAX_WORDS 100 ------------------ glst.data(), MAX_WORDS, HENTRY_WORD(rp), rp->blen, rp->astr, rp->alen, word, ------------------ | | 54| 545k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1463| 545k| nc, field); 1464| | 1465| 1.08M| for (int k = 0; k < nw; k++) { ------------------ | Branch (1465:23): [True: 544k, False: 545k] ------------------ 1466| 544k| if (utf8) { ------------------ | Branch (1466:13): [True: 245k, False: 299k] ------------------ 1467| 245k| u8_u16(w_f, glst[k].word); 1468| | 1469| 245k| int leftcommon = leftcommonsubstring(w_word, w_f); 1470| 245k| if (low) { ------------------ | Branch (1470:15): [True: 245k, False: 0] ------------------ 1471| | // lowering dictionary word 1472| 245k| mkallsmall_utf(w_f, langnum); 1473| 245k| } 1474| | 1475| 245k| sc = ngram(n, w_word, w_f, NGRAM_ANY_MISMATCH) + leftcommon; ------------------ | | 82| 245k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1476| 299k| } else { 1477| 299k| f = glst[k].word; 1478| | 1479| 299k| int leftcommon = leftcommonsubstring(word, f.c_str()); 1480| 299k| if (low) { ------------------ | Branch (1480:15): [True: 276k, False: 22.2k] ------------------ 1481| | // lowering dictionary word 1482| 276k| mkallsmall(f, csconv); 1483| 276k| } 1484| | 1485| 299k| sc = ngram(n, word, f, NGRAM_ANY_MISMATCH) + leftcommon; ------------------ | | 82| 299k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1486| 299k| } 1487| | 1488| 544k| if (sc > thresh) { ------------------ | Branch (1488:13): [True: 98.0k, False: 446k] ------------------ 1489| 98.0k| if (sc > gscore[lp]) { ------------------ | Branch (1489:15): [True: 98.0k, False: 0] ------------------ 1490| 98.0k| if (guess[lp]) { ------------------ | Branch (1490:17): [True: 0, False: 98.0k] ------------------ 1491| 0| delete[] guess[lp]; 1492| 0| if (guessorig[lp]) { ------------------ | Branch (1492:19): [True: 0, False: 0] ------------------ 1493| 0| delete[] guessorig[lp]; 1494| 0| guessorig[lp] = nullptr; 1495| 0| } 1496| 0| } 1497| 98.0k| gscore[lp] = sc; 1498| 98.0k| guess[lp] = glst[k].word; 1499| 98.0k| guessorig[lp] = glst[k].orig; 1500| 98.0k| lval = sc; 1501| 19.7M| for (int j = 0; j < MAX_GUESS; j++) ------------------ | | 76| 19.7M|#define MAX_GUESS 200 ------------------ | Branch (1501:29): [True: 19.6M, False: 98.0k] ------------------ 1502| 19.6M| if (gscore[j] < lval) { ------------------ | Branch (1502:19): [True: 18.7M, False: 893k] ------------------ 1503| 18.7M| lp = j; 1504| 18.7M| lval = gscore[j]; 1505| 18.7M| } 1506| 98.0k| } else { 1507| 0| delete[] glst[k].word; 1508| 0| delete[] glst[k].orig; 1509| 0| } 1510| 446k| } else { 1511| 446k| delete[] glst[k].word; 1512| 446k| delete[] glst[k].orig; 1513| 446k| } 1514| 544k| } 1515| 545k| } 1516| 4.70M| } 1517| 47.0k| glst.clear(); 1518| | 1519| | // now we are done generating guesses 1520| | // sort in order of decreasing score 1521| | 1522| 47.0k| bubblesort(&guess[0], &guessorig[0], &gscore[0], MAX_GUESS); ------------------ | | 76| 47.0k|#define MAX_GUESS 200 ------------------ 1523| 47.0k| if (ph) ------------------ | Branch (1523:7): [True: 2.77k, False: 44.2k] ------------------ 1524| 2.77k| bubblesort(&rootsphon[0], nullptr, &scoresphon[0], MAX_ROOTS); ------------------ | | 74| 2.77k|#define MAX_ROOTS 100 ------------------ 1525| | 1526| | // weight suggestions with a similarity index, based on 1527| | // the longest common subsequent algorithm and resort 1528| | 1529| 47.0k| int is_swap = 0; 1530| 47.0k| int re = 0; 1531| 47.0k| double fact = 1.0; 1532| 47.0k| if (pAMgr) { ------------------ | Branch (1532:7): [True: 47.0k, False: 0] ------------------ 1533| 47.0k| int maxd = pAMgr->get_maxdiff(); 1534| 47.0k| if (maxd >= 0) ------------------ | Branch (1534:9): [True: 0, False: 47.0k] ------------------ 1535| 0| fact = (10.0 - maxd) / 5.0; 1536| 47.0k| } 1537| | 1538| 47.0k| std::vector w_gl; 1539| 9.01M| for (int i = 0; i < MAX_GUESS; i++) { ------------------ | | 76| 9.01M|#define MAX_GUESS 200 ------------------ | Branch (1539:19): [True: 8.96M, False: 44.8k] ------------------ 1540| 8.96M| if (guess[i]) { ------------------ | Branch (1540:9): [True: 78.0k, False: 8.89M] ------------------ 1541| | // lowering guess[i] 1542| 78.0k| std::string gl; 1543| 78.0k| int len; 1544| 78.0k| if (utf8) { ------------------ | Branch (1544:11): [True: 21.4k, False: 56.6k] ------------------ 1545| 21.4k| len = u8_u16(w_gl, guess[i]); 1546| 21.4k| mkallsmall_utf(w_gl, langnum); 1547| 21.4k| u16_u8(gl, w_gl); 1548| 56.6k| } else { 1549| 56.6k| gl.assign(guess[i]); 1550| 56.6k| if (!nonbmp) ------------------ | Branch (1550:13): [True: 56.5k, False: 72] ------------------ 1551| 56.5k| mkallsmall(gl, csconv); 1552| 56.6k| len = strlen(guess[i]); 1553| 56.6k| } 1554| | 1555| 78.0k| int _lcs = lcslen(word, gl.c_str()); 1556| | 1557| | // same characters with different casing 1558| 78.0k| if ((n == len) && (n == _lcs)) { ------------------ | Branch (1558:11): [True: 17.1k, False: 60.9k] | Branch (1558:25): [True: 2.19k, False: 14.9k] ------------------ 1559| 2.19k| gscore[i] += 2000; 1560| 2.19k| break; 1561| 2.19k| } 1562| | // using 2-gram instead of 3, and other weightening 1563| | 1564| 75.8k| if (utf8) { ------------------ | Branch (1564:11): [True: 19.6k, False: 56.2k] ------------------ 1565| 19.6k| u8_u16(w_gl, gl); 1566| | //w_gl is lowercase already at this point 1567| 19.6k| re = ngram(2, w_word, w_gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 19.6k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re = ngram(2, w_word, w_gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 19.6k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1568| 19.6k| if (low) { ------------------ | Branch (1568:13): [True: 19.6k, False: 0] ------------------ 1569| 19.6k| w_f = w_word; 1570| | // lowering dictionary word 1571| 19.6k| mkallsmall_utf(w_f, langnum); 1572| 19.6k| re += ngram(2, w_gl, w_f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 19.6k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re += ngram(2, w_gl, w_f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 19.6k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1573| 19.6k| } else { 1574| 0| re += ngram(2, w_gl, w_word, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 0|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re += ngram(2, w_gl, w_word, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 0|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1575| 0| } 1576| 56.2k| } else { 1577| | //gl is lowercase already at this point 1578| 56.2k| re = ngram(2, word, gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 56.2k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re = ngram(2, word, gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 56.2k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1579| 56.2k| if (low) { ------------------ | Branch (1579:13): [True: 56.1k, False: 72] ------------------ 1580| 56.1k| f = word; 1581| | // lowering dictionary word 1582| 56.1k| mkallsmall(f, csconv); 1583| 56.1k| re += ngram(2, gl, f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 56.1k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re += ngram(2, gl, f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 56.1k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1584| 56.1k| } else { 1585| 72| re += ngram(2, gl, word, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 72|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re += ngram(2, gl, word, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 72|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1586| 72| } 1587| 56.2k| } 1588| | 1589| 75.8k| int ngram_score, leftcommon_score; 1590| 75.8k| if (utf8) { ------------------ | Branch (1590:11): [True: 19.6k, False: 56.2k] ------------------ 1591| | //w_gl is lowercase already at this point 1592| 19.6k| ngram_score = ngram(4, w_word, w_gl, NGRAM_ANY_MISMATCH); ------------------ | | 82| 19.6k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1593| 19.6k| leftcommon_score = leftcommonsubstring(w_word, w_gl); 1594| 56.2k| } else { 1595| | //gl is lowercase already at this point 1596| 56.2k| ngram_score = ngram(4, word, gl, NGRAM_ANY_MISMATCH); ------------------ | | 82| 56.2k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1597| 56.2k| leftcommon_score = leftcommonsubstring(word, gl.c_str()); 1598| 56.2k| } 1599| 75.8k| gscore[i] = 1600| | // length of longest common subsequent minus length difference 1601| 75.8k| 2 * _lcs - abs((int)(n - len)) + 1602| | // weight length of the left common substring 1603| 75.8k| leftcommon_score + 1604| | // weight equal character positions 1605| 75.8k| (!nonbmp && commoncharacterpositions(word, gl.c_str(), &is_swap) ------------------ | Branch (1605:12): [True: 75.8k, False: 72] | Branch (1605:23): [True: 60.1k, False: 15.6k] ------------------ 1606| 75.8k| ? 1 1607| 75.8k| : 0) + 1608| | // swap character (not neighboring) 1609| 75.8k| ((is_swap) ? 10 : 0) + ------------------ | Branch (1609:12): [True: 128, False: 75.7k] ------------------ 1610| | // ngram 1611| 75.8k| ngram_score + 1612| | // weighted ngrams 1613| 75.8k| re + 1614| | // different limit for dictionaries with PHONE rules 1615| 75.8k| (ph ? (re < len * fact ? -1000 : 0) ------------------ | Branch (1615:12): [True: 5.44k, False: 70.4k] | Branch (1615:18): [True: 3.87k, False: 1.56k] ------------------ 1616| 75.8k| : (re < (n + len) * fact ? -1000 : 0)); ------------------ | Branch (1616:18): [True: 63.5k, False: 6.85k] ------------------ 1617| 75.8k| } 1618| 8.96M| } 1619| | 1620| 47.0k| bubblesort(&guess[0], &guessorig[0], &gscore[0], MAX_GUESS); ------------------ | | 76| 47.0k|#define MAX_GUESS 200 ------------------ 1621| | 1622| | // phonetic version 1623| 47.0k| if (ph) ------------------ | Branch (1623:7): [True: 2.77k, False: 44.2k] ------------------ 1624| 280k| for (int i = 0; i < MAX_ROOTS; i++) { ------------------ | | 74| 280k|#define MAX_ROOTS 100 ------------------ | Branch (1624:21): [True: 277k, False: 2.77k] ------------------ 1625| 277k| if (rootsphon[i]) { ------------------ | Branch (1625:11): [True: 6.65k, False: 270k] ------------------ 1626| | // lowering rootphon[i] 1627| 6.65k| std::string gl; 1628| 6.65k| int len; 1629| 6.65k| if (utf8) { ------------------ | Branch (1629:13): [True: 0, False: 6.65k] ------------------ 1630| 0| len = u8_u16(w_gl, rootsphon[i]); 1631| 0| mkallsmall_utf(w_gl, langnum); 1632| 0| u16_u8(gl, w_gl); 1633| 6.65k| } else { 1634| 6.65k| gl.assign(rootsphon[i]); 1635| 6.65k| if (!nonbmp) ------------------ | Branch (1635:15): [True: 6.65k, False: 0] ------------------ 1636| 6.65k| mkallsmall(gl, csconv); 1637| 6.65k| len = strlen(rootsphon[i]); 1638| 6.65k| } 1639| | 1640| | // weight length of the left common substring 1641| 6.65k| int leftcommon_score; 1642| 6.65k| if (utf8) ------------------ | Branch (1642:13): [True: 0, False: 6.65k] ------------------ 1643| 0| leftcommon_score = leftcommonsubstring(w_word, w_gl); 1644| 6.65k| else 1645| 6.65k| leftcommon_score = leftcommonsubstring(word, gl.c_str()); 1646| | // heuristic weigthing of ngram scores 1647| 6.65k| scoresphon[i] += 2 * lcslen(word, gl) - abs((int)(n - len)) + 1648| 6.65k| leftcommon_score; 1649| 6.65k| } 1650| 277k| } 1651| | 1652| 47.0k| if (ph) ------------------ | Branch (1652:7): [True: 2.77k, False: 44.2k] ------------------ 1653| 2.77k| bubblesort(&rootsphon[0], nullptr, &scoresphon[0], MAX_ROOTS); ------------------ | | 74| 2.77k|#define MAX_ROOTS 100 ------------------ 1654| | 1655| | // copy over 1656| 47.0k| size_t oldns = wlst.size(); 1657| | 1658| 47.0k| int same = 0; 1659| 9.45M| for (int i = 0; i < MAX_GUESS; i++) { ------------------ | | 76| 9.45M|#define MAX_GUESS 200 ------------------ | Branch (1659:19): [True: 9.40M, False: 47.0k] ------------------ 1660| 9.40M| if (guess[i]) { ------------------ | Branch (1660:9): [True: 98.0k, False: 9.30M] ------------------ 1661| 98.0k| if ((wlst.size() < oldns + maxngramsugs) && (wlst.size() < maxSug) && ------------------ | Branch (1661:11): [True: 92.1k, False: 5.85k] | Branch (1661:51): [True: 92.1k, False: 0] ------------------ 1662| 92.1k| (!same || (gscore[i] > 1000))) { ------------------ | Branch (1662:12): [True: 17.4k, False: 74.7k] | Branch (1662:21): [True: 0, False: 74.7k] ------------------ 1663| 17.4k| int unique = 1; 1664| | // leave only excellent suggestions, if exists 1665| 17.4k| if (gscore[i] > 1000) ------------------ | Branch (1665:13): [True: 2.19k, False: 15.2k] ------------------ 1666| 2.19k| same = 1; 1667| 15.2k| else if (gscore[i] < -100) { ------------------ | Branch (1667:18): [True: 8.79k, False: 6.48k] ------------------ 1668| 8.79k| same = 1; 1669| | // keep the best ngram suggestions, unless in ONLYMAXDIFF mode 1670| 8.79k| if (wlst.size() > oldns || (pAMgr && pAMgr->get_onlymaxdiff())) { ------------------ | Branch (1670:15): [True: 1.34k, False: 7.44k] | Branch (1670:39): [True: 7.44k, False: 0] | Branch (1670:48): [True: 0, False: 7.44k] ------------------ 1671| 1.34k| delete[] guess[i]; 1672| 1.34k| delete[] guessorig[i]; 1673| 1.34k| continue; 1674| 1.34k| } 1675| 8.79k| } 1676| 16.1k| for (auto& j : wlst) { ------------------ | Branch (1676:22): [True: 10.9k, False: 13.4k] ------------------ 1677| | // don't suggest previous suggestions or a previous suggestion with 1678| | // prefixes or affixes 1679| 10.9k| if ((!guessorig[i] && strstr(guess[i], j.c_str())) || (guessorig[i] && strstr(guessorig[i], j.c_str())) || ------------------ | Branch (1679:15): [True: 2.65k, False: 8.33k] | Branch (1679:16): [True: 10.9k, False: 0] | Branch (1679:33): [True: 2.65k, False: 8.33k] | Branch (1679:66): [True: 0, False: 8.33k] | Branch (1679:82): [True: 0, False: 0] ------------------ 1680| | // check forbidden words 1681| 8.33k| !checkword(guess[i], 0, nullptr, nullptr)) { ------------------ | Branch (1681:15): [True: 0, False: 8.33k] ------------------ 1682| 2.65k| unique = 0; 1683| 2.65k| break; 1684| 2.65k| } 1685| 10.9k| } 1686| 16.1k| if (unique) { ------------------ | Branch (1686:13): [True: 13.4k, False: 2.65k] ------------------ 1687| 13.4k| if (guessorig[i]) { ------------------ | Branch (1687:15): [True: 0, False: 13.4k] ------------------ 1688| 0| wlst.emplace_back(guessorig[i]); 1689| 13.4k| } else { 1690| 13.4k| wlst.emplace_back(guess[i]); 1691| 13.4k| } 1692| 13.4k| } 1693| 16.1k| delete[] guess[i]; 1694| 16.1k| delete[] guessorig[i]; 1695| 80.5k| } else { 1696| 80.5k| delete[] guess[i]; 1697| 80.5k| delete[] guessorig[i]; 1698| 80.5k| } 1699| 98.0k| } 1700| 9.40M| } 1701| | 1702| 47.0k| oldns = wlst.size(); 1703| 47.0k| if (ph) ------------------ | Branch (1703:7): [True: 2.77k, False: 44.2k] ------------------ 1704| 277k| for (auto& i : rootsphon) { ------------------ | Branch (1704:18): [True: 277k, False: 2.77k] ------------------ 1705| 277k| if (i) { ------------------ | Branch (1705:11): [True: 6.65k, False: 270k] ------------------ 1706| 6.65k| if ((wlst.size() < oldns + MAXPHONSUGS) && (wlst.size() < maxSug)) { ------------------ | | 78| 6.65k|#define MAXPHONSUGS 2 ------------------ | Branch (1706:13): [True: 2.77k, False: 3.87k] | Branch (1706:52): [True: 2.77k, False: 0] ------------------ 1707| 2.77k| int unique = 1; 1708| 5.52k| for (auto& j : wlst) { ------------------ | Branch (1708:24): [True: 5.52k, False: 984] ------------------ 1709| | // don't suggest previous suggestions or a previous suggestion with 1710| | // prefixes or affixes 1711| 5.52k| if (strstr(i, j.c_str()) || ------------------ | Branch (1711:17): [True: 1.79k, False: 3.73k] | Branch (1711:17): [True: 1.79k, False: 3.73k] ------------------ 1712| | // check forbidden words 1713| 3.73k| !checkword(i, 0, nullptr, nullptr)) { ------------------ | Branch (1713:17): [True: 0, False: 3.73k] ------------------ 1714| 1.79k| unique = 0; 1715| 1.79k| break; 1716| 1.79k| } 1717| 5.52k| } 1718| 2.77k| if (unique) { ------------------ | Branch (1718:15): [True: 984, False: 1.79k] ------------------ 1719| 984| wlst.emplace_back(i); 1720| 984| } 1721| 2.77k| } 1722| 6.65k| } 1723| 277k| } 1724| 47.0k|} _ZN10SuggestMgr9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiPiPNS0_6chrono10time_pointINSA_12steady_clockENSA_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 1735| 89.9M| std::chrono::steady_clock::time_point* timelimit) { 1736| | // check overall suggestion time limit 1737| 89.9M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 108| 89.9M|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (1737:7): [True: 7, False: 89.9M] ------------------ 1738| 7| return 0; 1739| | 1740| | // check time limit 1741| 89.9M| if (timer) { ------------------ | Branch (1741:7): [True: 3.27M, False: 86.7M] ------------------ 1742| 3.27M| (*timer)--; 1743| 3.27M| if (!(*timer) && timelimit) { ------------------ | Branch (1743:9): [True: 28.0k, False: 3.24M] | Branch (1743:22): [True: 28.0k, False: 0] ------------------ 1744| 28.0k| if (std::chrono::steady_clock::now() - *timelimit > TIMELIMIT_MS) ------------------ | | 109| 28.0k|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (1744:11): [True: 11, False: 28.0k] ------------------ 1745| 11| return 0; 1746| 28.0k| *timer = MAXPLUSTIMER; ------------------ | | 111| 28.0k|#define MAXPLUSTIMER 100 ------------------ 1747| 28.0k| } 1748| 3.27M| } 1749| | 1750| 89.9M| if (pAMgr) { ------------------ | Branch (1750:7): [True: 89.9M, False: 0] ------------------ 1751| 89.9M| struct hentry* rv = nullptr; 1752| 89.9M| int nosuffix = 0; 1753| | 1754| 89.9M| if (cpdsuggest >= 1) { ------------------ | Branch (1754:9): [True: 58.8M, False: 31.1M] ------------------ 1755| 58.8M| if (pAMgr->get_compound()) { ------------------ | Branch (1755:11): [True: 14.3M, False: 44.4M] ------------------ 1756| 14.3M| struct hentry* rv2 = nullptr; 1757| 14.3M| struct hentry* rwords[100] = {}; // buffer for COMPOUND pattern checking 1758| 14.3M| int info = (cpdsuggest == 1) ? SPELL_COMPOUND_2 : 0; ------------------ | | 88| 7.18M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ | Branch (1758:20): [True: 7.18M, False: 7.18M] ------------------ 1759| 14.3M| AffixScratch scratch; 1760| 14.3M| rv = pAMgr->compound_check(word, 0, 0, 100, 0, nullptr, (hentry**)&rwords, 0, 1, &info, scratch); // EXT 1761| | // TODO filter 3-word or more compound words, as in spell() 1762| | // (it's too slow to call suggest() here for all possible compound words) 1763| 14.3M| if (rv && ------------------ | Branch (1763:13): [True: 0, False: 14.3M] | Branch (1763:13): [True: 0, False: 14.3M] ------------------ 1764| 0| (!(rv2 = pAMgr->lookup(word.c_str(), word.size())) || !rv2->astr || ------------------ | Branch (1764:14): [True: 0, False: 0] | Branch (1764:67): [True: 0, False: 0] ------------------ 1765| 0| !(TESTAFF(rv2->astr, pAMgr->get_forbiddenword(), rv2->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1766| 0| TESTAFF(rv2->astr, pAMgr->get_nosuggest(), rv2->alen)))) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1767| 0| return 3; // XXX obsolote categorisation + only ICONV needs affix 1768| | // flag check? 1769| 14.3M| } 1770| 58.8M| return 0; 1771| 58.8M| } 1772| | 1773| 31.1M| rv = pAMgr->lookup(word.c_str(), word.size()); 1774| | 1775| 31.1M| if (rv) { ------------------ | Branch (1775:9): [True: 45.3k, False: 31.1M] ------------------ 1776| 45.3k| if ((rv->astr) && ------------------ | Branch (1776:11): [True: 143, False: 45.2k] | Branch (1776:11): [True: 0, False: 45.3k] ------------------ 1777| 143| (TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen) || ------------------ | | 102| 286|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 143] | | ------------------ ------------------ 1778| 143| TESTAFF(rv->astr, pAMgr->get_nosuggest(), rv->alen) || ------------------ | | 102| 286|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 143] | | ------------------ ------------------ 1779| 143| TESTAFF(rv->astr, pAMgr->get_substandard(), rv->alen))) ------------------ | | 102| 143|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 143] | | ------------------ ------------------ 1780| 0| return 0; 1781| 45.5k| while (rv) { ------------------ | Branch (1781:14): [True: 45.3k, False: 143] ------------------ 1782| 45.3k| if (rv->astr && ------------------ | Branch (1782:13): [True: 143, False: 45.2k] | Branch (1782:13): [True: 143, False: 45.2k] ------------------ 1783| 143| (TESTAFF(rv->astr, pAMgr->get_needaffix(), rv->alen) || ------------------ | | 102| 286|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 143] | | ------------------ ------------------ 1784| 143| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 102| 286|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 143, False: 0] | | ------------------ ------------------ 1785| 143| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) { ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1786| 143| rv = rv->next_homonym; 1787| 143| } else 1788| 45.2k| break; 1789| 45.3k| } 1790| 31.1M| } else { 1791| 31.1M| AffixScratch scratch; 1792| 31.1M| rv = pAMgr->prefix_check(word, 0, word.size(), 1793| 31.1M| 0, scratch); // only prefix, and prefix + suffix XXX 1794| 31.1M| } 1795| | 1796| 31.1M| if (rv) { ------------------ | Branch (1796:9): [True: 45.2k, False: 31.1M] ------------------ 1797| 45.2k| nosuffix = 1; 1798| 31.1M| } else { 1799| 31.1M| AffixScratch scratch; 1800| 31.1M| rv = pAMgr->suffix_check(word, 0, word.size(), 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // only suffix ------------------ | | 99| 31.1M|#define FLAG_NULL 0x00 ------------------ rv = pAMgr->suffix_check(word, 0, word.size(), 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // only suffix ------------------ | | 99| 31.1M|#define FLAG_NULL 0x00 ------------------ rv = pAMgr->suffix_check(word, 0, word.size(), 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // only suffix ------------------ | | 75| 31.1M|#define IN_CPD_NOT 0 ------------------ 1801| 31.1M| } 1802| | 1803| 31.1M| if (!rv && pAMgr->have_contclass()) { ------------------ | Branch (1803:9): [True: 31.1M, False: 45.2k] | Branch (1803:16): [True: 10.7M, False: 20.3M] ------------------ 1804| 10.7M| AffixScratch scratch; 1805| 10.7M| rv = pAMgr->suffix_check_twosfx(word, 0, word.size(), 0, nullptr, scratch, FLAG_NULL); ------------------ | | 99| 10.7M|#define FLAG_NULL 0x00 ------------------ 1806| 10.7M| if (!rv) ------------------ | Branch (1806:11): [True: 10.7M, False: 0] ------------------ 1807| 10.7M| rv = pAMgr->prefix_check_twosfx(word, 0, word.size(), 0, scratch, FLAG_NULL); ------------------ | | 99| 10.7M|#define FLAG_NULL 0x00 ------------------ 1808| 10.7M| } 1809| | 1810| | // check forbidden words 1811| 31.1M| if ((rv) && (rv->astr) && ------------------ | Branch (1811:9): [True: 45.2k, False: 31.1M] | Branch (1811:9): [True: 0, False: 31.1M] | Branch (1811:17): [True: 0, False: 45.2k] ------------------ 1812| 0| (TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1813| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1814| 0| TESTAFF(rv->astr, pAMgr->get_nosuggest(), rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1815| 0| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1816| 0| return 0; 1817| | 1818| 31.1M| if (rv) { // XXX obsolote ------------------ | Branch (1818:9): [True: 45.2k, False: 31.1M] ------------------ 1819| 45.2k| if ((pAMgr->get_compoundflag()) && ------------------ | Branch (1819:11): [True: 10.8k, False: 34.4k] | Branch (1819:11): [True: 0, False: 45.2k] ------------------ 1820| 10.8k| TESTAFF(rv->astr, pAMgr->get_compoundflag(), rv->alen)) ------------------ | | 102| 10.8k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 10.8k] | | ------------------ ------------------ 1821| 0| return 2 + nosuffix; 1822| 45.2k| return 1; 1823| 45.2k| } 1824| 31.1M| } 1825| 31.1M| return 0; 1826| 89.9M|} _ZN10SuggestMgr15check_forbiddenERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1828| 15.1k|int SuggestMgr::check_forbidden(const std::string& word) { 1829| 15.1k| if (pAMgr) { ------------------ | Branch (1829:7): [True: 15.1k, False: 0] ------------------ 1830| 15.1k| struct hentry* rv = pAMgr->lookup(word.c_str(), word.size()); 1831| 15.1k| if (rv && rv->astr && ------------------ | Branch (1831:9): [True: 0, False: 15.1k] | Branch (1831:9): [True: 0, False: 15.1k] | Branch (1831:15): [True: 0, False: 0] ------------------ 1832| 0| (TESTAFF(rv->astr, pAMgr->get_needaffix(), rv->alen) || ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1833| 0| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1834| 0| rv = nullptr; 1835| 15.1k| size_t len = word.size(); 1836| 15.1k| AffixScratch scratch; 1837| 15.1k| if (!(pAMgr->prefix_check(word, 0, len, 1, scratch))) ------------------ | Branch (1837:9): [True: 15.1k, False: 0] ------------------ 1838| 15.1k| rv = pAMgr->suffix_check(word, 0, len, 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // prefix+suffix, suffix ------------------ | | 99| 15.1k|#define FLAG_NULL 0x00 ------------------ rv = pAMgr->suffix_check(word, 0, len, 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // prefix+suffix, suffix ------------------ | | 99| 15.1k|#define FLAG_NULL 0x00 ------------------ rv = pAMgr->suffix_check(word, 0, len, 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // prefix+suffix, suffix ------------------ | | 75| 15.1k|#define IN_CPD_NOT 0 ------------------ 1839| | // check forbidden words 1840| 15.1k| if ((rv) && (rv->astr) && ------------------ | Branch (1840:9): [True: 0, False: 15.1k] | Branch (1840:9): [True: 0, False: 15.1k] | Branch (1840:17): [True: 0, False: 0] ------------------ 1841| 0| TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen)) ------------------ | | 102| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 0] | | ------------------ ------------------ 1842| 0| return 1; 1843| 15.1k| } 1844| 15.1k| return 0; 1845| 15.1k|} _ZN10SuggestMgr13suggest_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1847| 12.7k|std::string SuggestMgr::suggest_morph(const std::string& in_w) { 1848| 12.7k| std::string result; 1849| | 1850| 12.7k| struct hentry* rv = nullptr; 1851| | 1852| 12.7k| if (!pAMgr) ------------------ | Branch (1852:7): [True: 0, False: 12.7k] ------------------ 1853| 0| return {}; 1854| | 1855| 12.7k| std::string w(in_w); 1856| | 1857| | // word reversing wrapper for complex prefixes 1858| 12.7k| if (complexprefixes) { ------------------ | Branch (1858:7): [True: 643, False: 12.0k] ------------------ 1859| 643| if (utf8) ------------------ | Branch (1859:9): [True: 0, False: 643] ------------------ 1860| 0| reverseword_utf(w); 1861| 643| else 1862| 643| reverseword(w); 1863| 643| } 1864| | 1865| 12.7k| rv = pAMgr->lookup(w.c_str(), w.size()); 1866| | 1867| 14.4k| while (rv) { ------------------ | Branch (1867:10): [True: 1.73k, False: 12.7k] ------------------ 1868| 1.73k| if ((!rv->astr) || ------------------ | Branch (1868:9): [True: 1.18k, False: 556] | Branch (1868:9): [True: 1.73k, False: 0] ------------------ 1869| 556| !(TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen) || ------------------ | | 102| 1.11k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 556] | | ------------------ ------------------ 1870| 556| TESTAFF(rv->astr, pAMgr->get_needaffix(), rv->alen) || ------------------ | | 102| 1.11k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 556] | | ------------------ ------------------ 1871| 1.73k| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) { ------------------ | | 102| 556|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (102:26): [True: 0, False: 556] | | ------------------ ------------------ 1872| 1.73k| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 1.73k|#define MORPH_STEM "st:" ------------------ | Branch (1872:11): [True: 1.73k, False: 0] ------------------ 1873| 1.73k| result.push_back(MSEP_FLD); ------------------ | | 121| 1.73k|#define MSEP_FLD ' ' ------------------ 1874| 1.73k| result.append(MORPH_STEM); ------------------ | | 103| 1.73k|#define MORPH_STEM "st:" ------------------ 1875| 1.73k| result.append(w); 1876| 1.73k| } 1877| 1.73k| if (HENTRY_DATA(rv)) { ------------------ | Branch (1877:11): [True: 0, False: 1.73k] ------------------ 1878| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 1879| 0| result.append(HENTRY_DATA2(rv)); 1880| 0| } 1881| 1.73k| result.push_back(MSEP_REC); ------------------ | | 122| 1.73k|#define MSEP_REC '\n' ------------------ 1882| 1.73k| } 1883| 1.73k| rv = rv->next_homonym; 1884| 1.73k| } 1885| | 1886| 12.7k| AffixScratch scratch; 1887| 12.7k| std::string st = pAMgr->affix_check_morph(w, 0, w.size(), scratch); 1888| 12.7k| if (!st.empty()) { ------------------ | Branch (1888:7): [True: 0, False: 12.7k] ------------------ 1889| 0| result.append(st); 1890| 0| } 1891| | 1892| 12.7k| if (pAMgr->get_compound() && result.empty()) { ------------------ | Branch (1892:7): [True: 2.62k, False: 10.0k] | Branch (1892:32): [True: 2.30k, False: 325] ------------------ 1893| 2.30k| struct hentry* rwords[100] = {}; // buffer for COMPOUND pattern checking 1894| 2.30k| pAMgr->compound_check_morph(w, 0, 0, 100, 0, nullptr, (hentry**)&rwords, 0, result, nullptr, scratch); 1895| 2.30k| } 1896| | 1897| 12.7k| line_uniq(result, MSEP_REC); ------------------ | | 122| 12.7k|#define MSEP_REC '\n' ------------------ 1898| | 1899| 12.7k| return result; 1900| 12.7k|} _ZN10SuggestMgr18suggest_hentry_genEP6hentryPKc: 1925| 461k|std::string SuggestMgr::suggest_hentry_gen(hentry* rv, const char* pattern) { 1926| 461k| std::string result; 1927| 461k| int sfxcount = get_sfxcount(pattern); 1928| | 1929| 461k| if (get_sfxcount(HENTRY_DATA(rv)) > sfxcount) ------------------ | Branch (1929:7): [True: 0, False: 461k] ------------------ 1930| 0| return result; 1931| | 1932| 461k| if (HENTRY_DATA(rv)) { ------------------ | Branch (1932:7): [True: 0, False: 461k] ------------------ 1933| 0| std::string aff = pAMgr->morphgen(HENTRY_WORD(rv), rv->blen, rv->astr, rv->alen, ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1934| 0| HENTRY_DATA(rv), pattern, 0); 1935| 0| if (!aff.empty()) { ------------------ | Branch (1935:9): [True: 0, False: 0] ------------------ 1936| 0| result.append(aff); 1937| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1938| 0| } 1939| 0| } 1940| | 1941| | // check all allomorphs 1942| 461k| char* p = nullptr; 1943| 461k| if (HENTRY_DATA(rv)) ------------------ | Branch (1943:7): [True: 0, False: 461k] ------------------ 1944| 0| p = (char*)strstr(HENTRY_DATA2(rv), MORPH_ALLOMORPH); ------------------ | | 104| 0|#define MORPH_ALLOMORPH "al:" ------------------ 1945| 461k| while (p) { ------------------ | Branch (1945:10): [True: 0, False: 461k] ------------------ 1946| 0| p += MORPH_TAG_LEN; ------------------ | | 119| 0|#define MORPH_TAG_LEN strlen(MORPH_STEM) | | ------------------ | | | | 103| 0|#define MORPH_STEM "st:" | | ------------------ ------------------ 1947| 0| int plen = fieldlen(p); 1948| 0| std::string allomorph(p, plen); 1949| 0| struct hentry* rv2 = pAMgr->lookup(allomorph.c_str(), allomorph.size()); 1950| 0| while (rv2) { ------------------ | Branch (1950:12): [True: 0, False: 0] ------------------ 1951| | // if (HENTRY_DATA(rv2) && get_sfxcount(HENTRY_DATA(rv2)) <= 1952| | // sfxcount) { 1953| 0| if (HENTRY_DATA(rv2)) { ------------------ | Branch (1953:11): [True: 0, False: 0] ------------------ 1954| 0| char* st = (char*)strstr(HENTRY_DATA2(rv2), MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 1955| 0| if (st && (strncmp(st + MORPH_TAG_LEN, HENTRY_WORD(rv), ------------------ | | 119| 0|#define MORPH_TAG_LEN strlen(MORPH_STEM) | | ------------------ | | | | 103| 0|#define MORPH_STEM "st:" | | ------------------ ------------------ if (st && (strncmp(st + MORPH_TAG_LEN, HENTRY_WORD(rv), ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ | Branch (1955:13): [True: 0, False: 0] | Branch (1955:19): [True: 0, False: 0] ------------------ 1956| 0| fieldlen(st + MORPH_TAG_LEN)) == 0)) { ------------------ | | 119| 0|#define MORPH_TAG_LEN strlen(MORPH_STEM) | | ------------------ | | | | 103| 0|#define MORPH_STEM "st:" | | ------------------ ------------------ 1957| 0| std::string aff = pAMgr->morphgen(HENTRY_WORD(rv2), rv2->blen, rv2->astr, ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1958| 0| rv2->alen, HENTRY_DATA(rv2), pattern, 0); 1959| 0| if (!aff.empty()) { ------------------ | Branch (1959:15): [True: 0, False: 0] ------------------ 1960| 0| result.append(aff); 1961| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1962| 0| } 1963| 0| } 1964| 0| } 1965| 0| rv2 = rv2->next_homonym; 1966| 0| } 1967| 0| p = strstr(p + plen, MORPH_ALLOMORPH); ------------------ | | 104| 0|#define MORPH_ALLOMORPH "al:" ------------------ 1968| 0| } 1969| | 1970| 461k| return result; 1971| 461k|} _ZN10SuggestMgr11suggest_genERKNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_NS0_6chrono10time_pointINSE_12steady_clockENSE_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 1974| 416k| std::chrono::steady_clock::time_point start_time) { 1975| 416k| if (desc.empty() || !pAMgr) ------------------ | Branch (1975:7): [True: 275k, False: 141k] | Branch (1975:23): [True: 0, False: 141k] ------------------ 1976| 275k| return {}; 1977| | 1978| 141k| const char* pattern = in_pattern.c_str(); 1979| 141k| std::string result2; 1980| 141k| std::string newpattern; 1981| 141k| struct hentry* rv = nullptr; 1982| | 1983| | // search affixed forms with and without derivational suffixes 1984| 173k| while (true) { ------------------ | Branch (1984:10): [True: 173k, Folded] ------------------ 1985| 173k| for (const auto& k : desc) { ------------------ | Branch (1985:24): [True: 173k, False: 173k] ------------------ 1986| 173k| if (std::chrono::steady_clock::now() - start_time > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 173k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1986:11): [True: 0, False: 173k] ------------------ 1987| 0| return result2; 1988| 173k| std::string result; 1989| | 1990| | // add compound word parts (except the last one) 1991| 173k| const size_t lastpart = append_compound_parts(k, result); 1992| 173k| const char* s = k.c_str() + lastpart; 1993| 173k| std::string tok(k, lastpart); 1994| 173k| size_t pos = tok.find(" | "); 1995| 173k| while (pos != std::string::npos) { ------------------ | Branch (1995:14): [True: 0, False: 173k] ------------------ 1996| 0| tok[pos + 1] = MSEP_ALT; ------------------ | | 123| 0|#define MSEP_ALT '\v' ------------------ 1997| 0| pos = tok.find(" | ", pos); 1998| 0| } 1999| 173k| std::vector pl = line_tok(tok, MSEP_ALT); ------------------ | | 123| 173k|#define MSEP_ALT '\v' ------------------ 2000| 173k| for (auto& i : pl) { ------------------ | Branch (2000:20): [True: 173k, False: 173k] ------------------ 2001| | // remove inflectional and terminal suffixes 2002| 173k| size_t is = i.find(MORPH_INFL_SFX); ------------------ | | 110| 173k|#define MORPH_INFL_SFX "is:" ------------------ 2003| 173k| if (is != std::string::npos) ------------------ | Branch (2003:13): [True: 0, False: 173k] ------------------ 2004| 0| i.resize(is); 2005| 173k| size_t ts = i.find(MORPH_TERM_SFX); ------------------ | | 111| 173k|#define MORPH_TERM_SFX "ts:" ------------------ 2006| 173k| while (ts != std::string::npos) { ------------------ | Branch (2006:16): [True: 0, False: 173k] ------------------ 2007| 0| i[ts] = '_'; 2008| 0| ts = i.find(MORPH_TERM_SFX); ------------------ | | 111| 0|#define MORPH_TERM_SFX "ts:" ------------------ 2009| 0| } 2010| 173k| const char* st = strstr(s, MORPH_STEM); ------------------ | | 103| 173k|#define MORPH_STEM "st:" ------------------ 2011| 173k| if (st) { ------------------ | Branch (2011:13): [True: 158k, False: 14.2k] ------------------ 2012| 158k| copy_field(tok, st, MORPH_STEM); ------------------ | | 103| 158k|#define MORPH_STEM "st:" ------------------ 2013| 158k| rv = pAMgr->lookup(tok.c_str(), tok.size()); 2014| 389k| while (rv) { ------------------ | Branch (2014:18): [True: 230k, False: 158k] ------------------ 2015| 230k| if (std::chrono::steady_clock::now() - start_time > TIMELIMIT_GLOBAL_MS) ------------------ | | 107| 230k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (2015:17): [True: 0, False: 230k] ------------------ 2016| 0| return result2; 2017| 230k| std::string newpat(i); 2018| 230k| newpat.append(pattern); 2019| 230k| std::string sg = suggest_hentry_gen(rv, newpat.c_str()); 2020| 230k| if (sg.empty()) ------------------ | Branch (2020:17): [True: 230k, False: 0] ------------------ 2021| 230k| sg = suggest_hentry_gen(rv, pattern); 2022| 230k| if (!sg.empty()) { ------------------ | Branch (2022:17): [True: 0, False: 230k] ------------------ 2023| 0| std::vector gen = line_tok(sg, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2024| 0| for (auto& j : gen) { ------------------ | Branch (2024:28): [True: 0, False: 0] ------------------ 2025| 0| result2.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2026| 0| result2.append(result); 2027| 0| if (i.find(MORPH_SURF_PFX) != std::string::npos) { ------------------ | | 112| 0|#define MORPH_SURF_PFX "sp:" ------------------ | Branch (2027:21): [True: 0, False: 0] ------------------ 2028| 0| std::string field; 2029| 0| copy_field(field, i, MORPH_SURF_PFX); ------------------ | | 112| 0|#define MORPH_SURF_PFX "sp:" ------------------ 2030| 0| result2.append(field); 2031| 0| } 2032| 0| result2.append(j); 2033| 0| } 2034| 0| } 2035| 230k| rv = rv->next_homonym; 2036| 230k| } 2037| 158k| } 2038| 173k| } 2039| 173k| } 2040| | 2041| 173k| if (!result2.empty() || !strstr(pattern, MORPH_DERI_SFX)) ------------------ | | 109| 173k|#define MORPH_DERI_SFX "ds:" ------------------ | Branch (2041:9): [True: 0, False: 173k] | Branch (2041:29): [True: 141k, False: 32.0k] ------------------ 2042| 141k| break; 2043| | 2044| 32.0k| newpattern.assign(pattern); 2045| 32.0k| mystrrep(newpattern, MORPH_DERI_SFX, MORPH_TERM_SFX); ------------------ | | 109| 32.0k|#define MORPH_DERI_SFX "ds:" ------------------ mystrrep(newpattern, MORPH_DERI_SFX, MORPH_TERM_SFX); ------------------ | | 111| 32.0k|#define MORPH_TERM_SFX "ts:" ------------------ 2046| 32.0k| pattern = newpattern.c_str(); 2047| 32.0k| } 2048| 141k| return result2; 2049| 141k|} _ZN10SuggestMgr5ngramEiRKNSt3__16vectorI6w_charNS0_9allocatorIS2_EEEES7_i: 2055| 608k| int opt) { 2056| 608k| int nscore = 0, ns, l1 = su1.size(), l2 = su2.size(); 2057| | 2058| 608k| if (l2 == 0) ------------------ | Branch (2058:7): [True: 7.14k, False: 601k] ------------------ 2059| 7.14k| return 0; 2060| 919k| for (int j = 1; j <= n; j++) { ------------------ | Branch (2060:19): [True: 871k, False: 48.5k] ------------------ 2061| 871k| ns = 0; 2062| 4.23M| for (int i = 0; i <= (l1 - j); i++) { ------------------ | Branch (2062:21): [True: 3.36M, False: 871k] ------------------ 2063| 3.36M| int k = 0; 2064| 17.1M| for (int l = 0; l <= (l2 - j); l++) { ------------------ | Branch (2064:23): [True: 14.9M, False: 2.18M] ------------------ 2065| 25.5M| for (k = 0; k < j; k++) { ------------------ | Branch (2065:21): [True: 24.4M, False: 1.17M] ------------------ 2066| 24.4M| if (su1[i + k] != su2[l + k]) ------------------ | Branch (2066:15): [True: 13.7M, False: 10.6M] ------------------ 2067| 13.7M| break; 2068| 24.4M| } 2069| 14.9M| if (k == j) { ------------------ | Branch (2069:13): [True: 1.17M, False: 13.7M] ------------------ 2070| 1.17M| ns++; 2071| 1.17M| break; 2072| 1.17M| } 2073| 14.9M| } 2074| 3.36M| if (k != j && opt & NGRAM_WEIGHTED) { ------------------ | | 84| 2.18M|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2074:11): [True: 2.18M, False: 1.17M] | Branch (2074:21): [True: 75.1k, False: 2.10M] ------------------ 2075| 75.1k| ns--; 2076| 75.1k| if (i == 0 || i == l1 - j) ------------------ | Branch (2076:13): [True: 20.2k, False: 54.9k] | Branch (2076:23): [True: 27.7k, False: 27.2k] ------------------ 2077| 47.9k| ns--; // side weight 2078| 75.1k| } 2079| 3.36M| } 2080| 871k| nscore = nscore + ns; 2081| 871k| if (ns < 2 && !(opt & NGRAM_WEIGHTED)) ------------------ | | 84| 606k|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2081:9): [True: 606k, False: 264k] | Branch (2081:19): [True: 552k, False: 53.8k] ------------------ 2082| 552k| break; 2083| 871k| } 2084| | 2085| 601k| ns = 0; 2086| 601k| if (opt & NGRAM_LONGER_WORSE) ------------------ | | 81| 601k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ | Branch (2086:7): [True: 245k, False: 356k] ------------------ 2087| 245k| ns = (l2 - l1) - 2; 2088| 601k| if (opt & NGRAM_ANY_MISMATCH) ------------------ | | 82| 601k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ | Branch (2088:7): [True: 356k, False: 245k] ------------------ 2089| 356k| ns = abs(l2 - l1) - 2; 2090| 601k| ns = (nscore - ((ns > 0) ? ns : 0)); ------------------ | Branch (2090:19): [True: 102k, False: 499k] ------------------ 2091| 601k| return ns; 2092| 608k|} _ZN10SuggestMgr5ngramEiRKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_i: 2098| 857k| int opt) { 2099| 857k| int nscore = 0, ns, l1, l2 = s2.size(); 2100| | 2101| 857k| if (l2 == 0) ------------------ | Branch (2101:7): [True: 12.1k, False: 845k] ------------------ 2102| 12.1k| return 0; 2103| 845k| l1 = s1.size(); 2104| 1.64M| for (int j = 1; j <= n; j++) { ------------------ | Branch (2104:19): [True: 1.49M, False: 150k] ------------------ 2105| 1.49M| ns = 0; 2106| 11.6M| for (int i = 0; i <= (l1 - j); i++) { ------------------ | Branch (2106:21): [True: 10.1M, False: 1.49M] ------------------ 2107| | //s2 is haystack, s1[i..i+j) is needle 2108| 10.1M| if (s2.find(s1.c_str()+i, 0, j) != std::string::npos) { ------------------ | Branch (2108:11): [True: 4.00M, False: 6.17M] ------------------ 2109| 4.00M| ns++; 2110| 6.17M| } else if (opt & NGRAM_WEIGHTED) { ------------------ | | 84| 6.17M|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2110:18): [True: 419k, False: 5.75M] ------------------ 2111| 419k| ns--; 2112| 419k| if (i == 0 || i == l1 - j) ------------------ | Branch (2112:13): [True: 44.9k, False: 374k] | Branch (2112:23): [True: 113k, False: 260k] ------------------ 2113| 158k| ns--; // side weight 2114| 419k| } 2115| 10.1M| } 2116| 1.49M| nscore = nscore + ns; 2117| 1.49M| if (ns < 2 && !(opt & NGRAM_WEIGHTED)) ------------------ | | 84| 837k|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2117:9): [True: 837k, False: 660k] | Branch (2117:19): [True: 694k, False: 142k] ------------------ 2118| 694k| break; 2119| 1.49M| } 2120| | 2121| 845k| ns = 0; 2122| 845k| if (opt & NGRAM_LONGER_WORSE) ------------------ | | 81| 845k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ | Branch (2122:7): [True: 306k, False: 539k] ------------------ 2123| 306k| ns = (l2 - l1) - 2; 2124| 845k| if (opt & NGRAM_ANY_MISMATCH) ------------------ | | 82| 845k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ | Branch (2124:7): [True: 539k, False: 306k] ------------------ 2125| 539k| ns = abs(l2 - l1) - 2; 2126| 845k| ns = (nscore - ((ns > 0) ? ns : 0)); ------------------ | Branch (2126:19): [True: 182k, False: 662k] ------------------ 2127| 845k| return ns; 2128| 857k|} _ZN10SuggestMgr19leftcommonsubstringERKNSt3__16vectorI6w_charNS0_9allocatorIS2_EEEES7_: 2133| 510k| const std::vector& su2) { 2134| 510k| int l1 = su1.size(), l2 = su2.size(); 2135| | // decapitalize dictionary word 2136| 510k| if (complexprefixes) { ------------------ | Branch (2136:7): [True: 0, False: 510k] ------------------ 2137| 0| if (l1 && l2 && su1[l1 - 1] == su2[l2 - 1]) ------------------ | Branch (2137:9): [True: 0, False: 0] | Branch (2137:15): [True: 0, False: 0] | Branch (2137:21): [True: 0, False: 0] ------------------ 2138| 0| return 1; 2139| 510k| } else { 2140| 510k| unsigned short idx = su2.empty() ? 0 : (unsigned short)(su2[0]), ------------------ | Branch (2140:26): [True: 0, False: 510k] ------------------ 2141| 510k| otheridx = su1.empty() ? 0 : (unsigned short)(su1[0]); ------------------ | Branch (2141:31): [True: 18.7k, False: 491k] ------------------ 2142| 510k| if (otheridx != idx && (otheridx != unicodetolower(idx, langnum))) ------------------ | Branch (2142:9): [True: 478k, False: 31.5k] | Branch (2142:28): [True: 379k, False: 98.6k] ------------------ 2143| 379k| return 0; 2144| 130k| int i; 2145| 213k| for (i = 1; (i < l1) && (i < l2) && (su1[i] == su2[i]); ------------------ | Branch (2145:17): [True: 201k, False: 12.1k] | Branch (2145:29): [True: 186k, False: 15.5k] | Branch (2145:41): [True: 83.6k, False: 102k] ------------------ 2146| 130k| i++) 2147| 83.6k| ; 2148| 130k| return i; 2149| 510k| } 2150| 0| return 0; 2151| 510k|} _ZN10SuggestMgr19leftcommonsubstringEPKcS1_: 2156| 663k| const char* s2) { 2157| 663k| if (complexprefixes) { ------------------ | Branch (2157:7): [True: 54.1k, False: 608k] ------------------ 2158| 54.1k| int l1 = strlen(s1), l2 = strlen(s2); 2159| 54.1k| if (l1 && l1 <= l2 && s1[l1 - 1] == s2[l2 - 1]) ------------------ | Branch (2159:9): [True: 52.2k, False: 1.83k] | Branch (2159:15): [True: 22.9k, False: 29.3k] | Branch (2159:27): [True: 2.23k, False: 20.7k] ------------------ 2160| 2.23k| return 1; 2161| 608k| } else if (csconv) { ------------------ | Branch (2161:14): [True: 608k, False: 0] ------------------ 2162| 608k| const char* olds = s1; 2163| | // decapitalise dictionary word 2164| 608k| if ((*s1 != *s2) && (((unsigned char)*s1) != csconv[((unsigned char)*s2)].clower)) ------------------ | Branch (2164:9): [True: 545k, False: 63.5k] | Branch (2164:25): [True: 397k, False: 147k] ------------------ 2165| 397k| return 0; 2166| 477k| do { 2167| 477k| s1++; 2168| 477k| s2++; 2169| 477k| } while ((*s1 == *s2) && (*s1 != '\0')); ------------------ | Branch (2169:14): [True: 266k, False: 210k] | Branch (2169:30): [True: 266k, False: 379] ------------------ 2170| 211k| return (int)(s1 - olds); 2171| 608k| } 2172| 51.8k| return 0; 2173| 663k|} _ZN10SuggestMgr24commoncharacterpositionsEPKcS1_Pi: 2177| 75.8k| int* is_swap) { 2178| 75.8k| int num = 0, diff = 0, diffpos[2]; 2179| 75.8k| *is_swap = 0; 2180| 75.8k| if (utf8) { ------------------ | Branch (2180:7): [True: 19.6k, False: 56.1k] ------------------ 2181| 19.6k| std::vector su1; 2182| 19.6k| std::vector su2; 2183| 19.6k| int l1 = u8_u16(su1, s1), l2 = u8_u16(su2, s2); 2184| | 2185| 19.6k| if (l1 <= 0 || l2 <= 0) ------------------ | Branch (2185:9): [True: 4.22k, False: 15.4k] | Branch (2185:20): [True: 0, False: 15.4k] ------------------ 2186| 4.22k| return 0; 2187| | 2188| | // decapitalize dictionary word 2189| 15.4k| if (complexprefixes) { ------------------ | Branch (2189:9): [True: 0, False: 15.4k] ------------------ 2190| 0| su2[l2 - 1] = lower_utf(su2[l2 - 1], langnum); 2191| 15.4k| } else { 2192| 15.4k| su2[0] = lower_utf(su2[0], langnum); 2193| 15.4k| } 2194| 58.9k| for (int i = 0; (i < l1) && (i < l2); i++) { ------------------ | Branch (2194:21): [True: 48.9k, False: 9.98k] | Branch (2194:33): [True: 43.5k, False: 5.43k] ------------------ 2195| 43.5k| if (su1[i] == su2[i]) { ------------------ | Branch (2195:11): [True: 23.3k, False: 20.1k] ------------------ 2196| 23.3k| num++; 2197| 23.3k| } else { 2198| 20.1k| if (diff < 2) ------------------ | Branch (2198:13): [True: 16.9k, False: 3.17k] ------------------ 2199| 16.9k| diffpos[diff] = i; 2200| 20.1k| diff++; 2201| 20.1k| } 2202| 43.5k| } 2203| 15.4k| if ((diff == 2) && (l1 == l2) && ------------------ | Branch (2203:9): [True: 3.31k, False: 12.1k] | Branch (2203:24): [True: 827, False: 2.48k] ------------------ 2204| 827| (su1[diffpos[0]] == su2[diffpos[1]]) && ------------------ | Branch (2204:9): [True: 438, False: 389] ------------------ 2205| 438| (su1[diffpos[1]] == su2[diffpos[0]])) ------------------ | Branch (2205:9): [True: 50, False: 388] ------------------ 2206| 50| *is_swap = 1; 2207| 56.1k| } else { 2208| 56.1k| if (!*s1 || !*s2) ------------------ | Branch (2208:9): [True: 5.22k, False: 50.9k] | Branch (2208:17): [True: 0, False: 50.9k] ------------------ 2209| 5.22k| return 0; 2210| | 2211| 50.9k| size_t i; 2212| 50.9k| std::string t(s2); 2213| | // decapitalize dictionary word 2214| 50.9k| if (complexprefixes) { ------------------ | Branch (2214:9): [True: 3.43k, False: 47.5k] ------------------ 2215| 3.43k| size_t l2 = t.size(); 2216| 3.43k| t[l2 - 1] = csconv[(unsigned char)t[l2 - 1]].clower; 2217| 47.5k| } else { 2218| 47.5k| mkallsmall(t, csconv); 2219| 47.5k| } 2220| 309k| for (i = 0; i < t.size() && (*(s1 + i) != 0); ++i) { ------------------ | Branch (2220:17): [True: 278k, False: 31.4k] | Branch (2220:33): [True: 258k, False: 19.4k] ------------------ 2221| 258k| if (*(s1 + i) == t[i]) { ------------------ | Branch (2221:11): [True: 129k, False: 129k] ------------------ 2222| 129k| num++; 2223| 129k| } else { 2224| 129k| if (diff < 2) ------------------ | Branch (2224:13): [True: 71.2k, False: 58.4k] ------------------ 2225| 71.2k| diffpos[diff] = i; 2226| 129k| diff++; 2227| 129k| } 2228| 258k| } 2229| 50.9k| if ((diff == 2) && (*(s1 + i) == 0) && i == t.size() && ------------------ | Branch (2229:9): [True: 12.8k, False: 38.1k] | Branch (2229:24): [True: 8.54k, False: 4.28k] | Branch (2229:44): [True: 2.74k, False: 5.79k] ------------------ 2230| 2.74k| (*(s1 + diffpos[0]) == t[diffpos[1]]) && ------------------ | Branch (2230:9): [True: 625, False: 2.12k] ------------------ 2231| 625| (*(s1 + diffpos[1]) == t[diffpos[0]])) ------------------ | Branch (2231:9): [True: 78, False: 547] ------------------ 2232| 78| *is_swap = 1; 2233| 50.9k| } 2234| 66.3k| return num; 2235| 75.8k|} _ZN10SuggestMgr10bubblesortEPPcS1_Pii: 2246| 99.6k|void SuggestMgr::bubblesort(char** rword, char** rword2, int* rsc, int n) { 2247| 99.6k| int m = 1; 2248| 19.3M| while (m < n) { ------------------ | Branch (2248:10): [True: 19.2M, False: 99.6k] ------------------ 2249| 19.2M| int j = m; 2250| 38.7M| while (j > 0) { ------------------ | Branch (2250:12): [True: 38.7M, False: 25.1k] ------------------ 2251| 38.7M| if (rsc[j - 1] < rsc[j]) { ------------------ | Branch (2251:11): [True: 19.4M, False: 19.2M] ------------------ 2252| 19.4M| int sctmp = rsc[j - 1]; 2253| 19.4M| char* wdtmp = rword[j - 1]; 2254| 19.4M| rsc[j - 1] = rsc[j]; 2255| 19.4M| rword[j - 1] = rword[j]; 2256| 19.4M| rsc[j] = sctmp; 2257| 19.4M| rword[j] = wdtmp; 2258| 19.4M| if (rword2) { ------------------ | Branch (2258:13): [True: 18.9M, False: 540k] ------------------ 2259| 18.9M| wdtmp = rword2[j - 1]; 2260| 18.9M| rword2[j - 1] = rword2[j]; 2261| 18.9M| rword2[j] = wdtmp; 2262| 18.9M| } 2263| 19.4M| j--; 2264| 19.4M| } else 2265| 19.2M| break; 2266| 38.7M| } 2267| 19.2M| m++; 2268| 19.2M| } 2269| 99.6k|} _ZN10SuggestMgr3lcsEPKcS1_PiS2_: 2275| 84.7k| int* l2) { 2276| 84.7k| int n, m, i, j; 2277| 84.7k| std::vector su; 2278| 84.7k| std::vector su2; 2279| 84.7k| if (utf8) { ------------------ | Branch (2279:7): [True: 21.4k, False: 63.2k] ------------------ 2280| 21.4k| m = u8_u16(su, s); 2281| 21.4k| n = u8_u16(su2, s2); 2282| 63.2k| } else { 2283| 63.2k| m = strlen(s); 2284| 63.2k| n = strlen(s2); 2285| 63.2k| } 2286| 84.7k| if (m <= 0 || n <= 0) { ------------------ | Branch (2286:7): [True: 9.58k, False: 75.1k] | Branch (2286:17): [True: 0, False: 75.1k] ------------------ 2287| 9.58k| *l1 = 0; 2288| 9.58k| *l2 = 0; 2289| 9.58k| return nullptr; 2290| 9.58k| } 2291| 75.1k| char* c = new char[(m + 1) * (n + 1)](); 2292| 75.1k| char* b = new char[(m + 1) * (n + 1)](); 2293| 482k| for (i = 1; i <= m; i++) { ------------------ | Branch (2293:15): [True: 407k, False: 75.1k] ------------------ 2294| 4.35M| for (j = 1; j <= n; j++) { ------------------ | Branch (2294:17): [True: 3.94M, False: 407k] ------------------ 2295| 3.94M| if (((utf8) && (su[i - 1] == su2[j - 1])) || ------------------ | Branch (2295:12): [True: 273k, False: 3.67M] | Branch (2295:22): [True: 59.8k, False: 213k] ------------------ 2296| 3.88M| ((!utf8) && (s[i - 1] == s2[j - 1]))) { ------------------ | Branch (2296:12): [True: 3.67M, False: 213k] | Branch (2296:23): [True: 503k, False: 3.17M] ------------------ 2297| 563k| c[i * (n + 1) + j] = c[(i - 1) * (n + 1) + j - 1] + 1; 2298| 563k| b[i * (n + 1) + j] = LCS_UPLEFT; 2299| 3.38M| } else if (c[(i - 1) * (n + 1) + j] >= c[i * (n + 1) + j - 1]) { ------------------ | Branch (2299:18): [True: 2.45M, False: 928k] ------------------ 2300| 2.45M| c[i * (n + 1) + j] = c[(i - 1) * (n + 1) + j]; 2301| 2.45M| b[i * (n + 1) + j] = LCS_UP; 2302| 2.45M| } else { 2303| 928k| c[i * (n + 1) + j] = c[i * (n + 1) + j - 1]; 2304| 928k| b[i * (n + 1) + j] = LCS_LEFT; 2305| 928k| } 2306| 3.94M| } 2307| 407k| } 2308| 75.1k| delete[] c; 2309| 75.1k| *l1 = m; 2310| 75.1k| *l2 = n; 2311| 75.1k| return b; 2312| 84.7k|} _ZN10SuggestMgr6lcslenEPKcS1_: 2314| 84.7k|int SuggestMgr::lcslen(const char* s, const char* s2) { 2315| 84.7k| int m, n, len = 0; 2316| 84.7k| char* result = lcs(s, s2, &m, &n); 2317| 84.7k| if (!result) ------------------ | Branch (2317:7): [True: 9.58k, False: 75.1k] ------------------ 2318| 9.58k| return 0; 2319| 75.1k| int i = m, j = n; 2320| 630k| while ((i != 0) && (j != 0)) { ------------------ | Branch (2320:10): [True: 562k, False: 67.4k] | Branch (2320:22): [True: 554k, False: 7.73k] ------------------ 2321| 554k| if (result[i * (n + 1) + j] == LCS_UPLEFT) { ------------------ | Branch (2321:9): [True: 222k, False: 332k] ------------------ 2322| 222k| len++; 2323| 222k| i--; 2324| 222k| j--; 2325| 332k| } else if (result[i * (n + 1) + j] == LCS_UP) { ------------------ | Branch (2325:16): [True: 168k, False: 163k] ------------------ 2326| 168k| i--; 2327| 168k| } else 2328| 163k| j--; 2329| 554k| } 2330| 75.1k| delete[] result; 2331| 75.1k| return len; 2332| 84.7k|} _ZN10SuggestMgr6lcslenERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 2334| 6.65k|int SuggestMgr::lcslen(const std::string& s, const std::string& s2) { 2335| 6.65k| return lcslen(s.c_str(), s2.c_str()); 2336| 6.65k|} suggestmgr.cxx:_ZN12_GLOBAL__N_115ngsuggest_guardC2EbPK7cs_infoPiPS3_: 1164| 61.4k| : m_nonbmp(nonbmp) 1165| 61.4k| , m_origconv(origconv) 1166| 61.4k| , m_utf8(utf8) 1167| 61.4k| , m_csconv(csconv) 1168| 61.4k| { 1169| 61.4k| } suggestmgr.cxx:_ZN12_GLOBAL__N_115ngsuggest_guardD2Ev: 1172| 61.4k| { 1173| 61.4k| if (m_nonbmp) { ------------------ | Branch (1173:11): [True: 1.71k, False: 59.7k] ------------------ 1174| 1.71k| *m_csconv = m_origconv; 1175| 1.71k| *m_utf8 = 1; 1176| 1.71k| } 1177| 61.4k| } suggestmgr.cxx:_ZL12get_sfxcountPKc: 1902| 923k|static int get_sfxcount(const char* morph) { 1903| 923k| if (!morph || !*morph) ------------------ | Branch (1903:7): [True: 461k, False: 461k] | Branch (1903:17): [True: 0, False: 461k] ------------------ 1904| 461k| return 0; 1905| 461k| int n = 0; 1906| 461k| const char* old = morph; 1907| 461k| morph = strstr(morph, MORPH_DERI_SFX); ------------------ | | 109| 461k|#define MORPH_DERI_SFX "ds:" ------------------ 1908| 461k| if (!morph) ------------------ | Branch (1908:7): [True: 401k, False: 59.6k] ------------------ 1909| 401k| morph = strstr(old, MORPH_INFL_SFX); ------------------ | | 110| 401k|#define MORPH_INFL_SFX "is:" ------------------ 1910| 461k| if (!morph) ------------------ | Branch (1910:7): [True: 401k, False: 59.8k] ------------------ 1911| 401k| morph = strstr(old, MORPH_TERM_SFX); ------------------ | | 111| 401k|#define MORPH_TERM_SFX "ts:" ------------------ 1912| 629k| while (morph) { ------------------ | Branch (1912:10): [True: 167k, False: 461k] ------------------ 1913| 167k| n++; 1914| 167k| old = morph; 1915| 167k| morph = strstr(morph + 1, MORPH_DERI_SFX); ------------------ | | 109| 167k|#define MORPH_DERI_SFX "ds:" ------------------ 1916| 167k| if (!morph) ------------------ | Branch (1916:9): [True: 143k, False: 24.2k] ------------------ 1917| 143k| morph = strstr(old + 1, MORPH_INFL_SFX); ------------------ | | 110| 143k|#define MORPH_INFL_SFX "is:" ------------------ 1918| 167k| if (!morph) ------------------ | Branch (1918:9): [True: 143k, False: 24.2k] ------------------ 1919| 143k| morph = strstr(old + 1, MORPH_TERM_SFX); ------------------ | | 111| 143k|#define MORPH_TERM_SFX "ts:" ------------------ 1920| 167k| } 1921| 461k| return n; 1922| 923k|} _ZNK6w_charcvtEv: 57| 274M| { 58| 274M|#if defined(_WIN32) || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__==__ORDER_LITTLE_ENDIAN__)) || defined(__LITTLE_ENDIAN__) 59| | //use little-endian optimized version 60| |#if (__cplusplus >= 202002L || (defined(_MSVC_LANG) && _MSVC_LANG >= 202002L)) && defined __cpp_lib_bit_cast && __cpp_lib_bit_cast >= 201806L 61| | return std::bit_cast(*this); 62| |#else 63| 274M| unsigned short u; 64| 274M| memcpy(&u, this, sizeof(unsigned short)); 65| 274M| return u; 66| 274M|#endif 67| | 68| |#else 69| | return ((unsigned short)h << 8) | (unsigned short)l; 70| |#endif 71| 274M| } _Zlt6w_charS_: 73| 25.2M| friend bool operator<(const w_char a, const w_char b) { 74| 25.2M| return (unsigned short)a < (unsigned short)b; 75| 25.2M| } _Zeq6w_charS_: 77| 92.4M| friend bool operator==(const w_char a, const w_char b) { 78| 92.4M| return (unsigned short)a == (unsigned short)b; 79| 92.4M| } _Zne6w_charS_: 81| 90.1M| friend bool operator!=(const w_char a, const w_char b) { 82| 90.1M| return !(a == b); 83| 90.1M| } _Z8endswithRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEES7_: 40| 201|{ 41| 201| return str.size() >= suffix.size() && ------------------ | Branch (41:12): [True: 193, False: 8] ------------------ 42| 193| str.compare(str.size() - suffix.size(), suffix.size(), suffix) == 0; ------------------ | Branch (42:12): [True: 38, False: 155] ------------------ 43| 201|} LLVMFuzzerInitialize: 46| 2|{ 47| 2| char* exe_path = (*argv)[0]; 48| | // dirname() can modify its argument. 49| 2| char* exe_path_copy = strdup(exe_path); 50| 2| char* dir = dirname(exe_path_copy); 51| 2| DIR* d = opendir(dir); 52| 2| struct dirent *direntry; 53| 2| std::vector affs; 54| 203| while ((direntry = readdir(d)) != NULL) ------------------ | Branch (54:12): [True: 201, False: 2] ------------------ 55| 201| { 56| 201| std::string entry(direntry->d_name); 57| 201| if (endswith(entry, ".aff")) ------------------ | Branch (57:13): [True: 38, False: 163] ------------------ 58| 38| affs.push_back(std::move(entry)); 59| 201| } 60| 2| closedir(d); 61| 2| free(exe_path_copy); 62| | 63| | // sort so dict iteration order is reproducible across runs regardless of 64| | // readdir ordering; a failing input then reproduces against the same dict 65| 2| std::sort(affs.begin(), affs.end()); 66| 2| for (const auto& entry : affs) ------------------ | Branch (66:28): [True: 38, False: 2] ------------------ 67| 38| { 68| 38| std::string dic = entry.substr(0, entry.size() - 4) + ".dic"; 69| 38| dictionaries.emplace_back(new Hunspell(entry.c_str(), dic.c_str())); 70| 38| } 71| | 72| 2| return 0; 73| 2|} LLVMFuzzerTestOneInput: 76| 3.44k|{ 77| 3.44k| std::string word(data, size); 78| 3.44k| for (auto& dict : dictionaries) ------------------ | Branch (78:21): [True: 65.5k, False: 3.44k] ------------------ 79| 65.5k| { 80| 65.5k| if (!dict->spell(word)) ------------------ | Branch (80:13): [True: 64.9k, False: 539] ------------------ 81| 64.9k| dict->suggest(word); 82| 65.5k| } 83| 3.44k| return 0; 84| 3.44k|}