_ZN8PfxEntryC2EP8AffixMgr: 90| 8| : pmyMgr(pmgr) 91| 8| , next(nullptr) 92| 8| , nexteq(nullptr) 93| 8| , nextne(nullptr) 94| 8| , flgnxt(nullptr) {} _ZN8PfxEntry3addEPKcm: 97| 3|std::string PfxEntry::add(const char* word, size_t len) { 98| 3| std::string result; 99| 3| if ((len > strip.size() || (len == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (99:7): [True: 3, False: 0] | Branch (99:8): [True: 3, False: 0] | Branch (99:31): [True: 0, False: 0] | Branch (99:43): [True: 0, False: 0] ------------------ 100| 3| (len >= numconds) && test_condition(word) && ------------------ | Branch (100:7): [True: 3, False: 0] | Branch (100:28): [True: 3, False: 0] ------------------ 101| 3| (strip.empty() || ------------------ | Branch (101:8): [True: 3, False: 0] ------------------ 102| 3| (len >= strip.size() && strncmp(word, strip.c_str(), strip.size()) == 0))) { ------------------ | Branch (102:8): [True: 0, False: 0] | Branch (102:31): [True: 0, False: 0] ------------------ 103| | /* we have a match so add prefix */ 104| 3| result.assign(appnd); 105| 3| result.append(word + strip.size()); 106| 3| } 107| 3| return result; 108| 3|} _ZN8PfxEntry9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 213| 1.41M| AffixScratch& scratch) { 214| 1.41M| struct hentry* he; // hash entry of root word or NULL 215| | 216| | // on entry prefix is 0 length or already matches the beginning of the word. 217| | // So if the remaining root word has positive length 218| | // and if there are enough chars in root word and added back strip chars 219| | // to meet the number of characters conditions, then test it 220| | 221| 1.41M| int tmpl = len - appnd.size(); // length of tmpword 222| | 223| 1.41M| if (tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) { ------------------ | Branch (223:7): [True: 1.41M, False: 2.49k] | Branch (223:20): [True: 2.49k, False: 0] | Branch (223:33): [True: 0, False: 2.49k] ------------------ 224| | // generate new root word by removing prefix and adding 225| | // back any characters that would have been stripped 226| | 227| 1.41M| std::string& tmpword = scratch.pfx_check_word; 228| 1.41M| tmpword.assign(strip); 229| 1.41M| tmpword.append(word, start + appnd.size(), tmpl); 230| | 231| | // now make sure all of the conditions on characters 232| | // are met. Please see the appendix at the end of 233| | // this file for more info on exactly what is being 234| | // tested 235| | 236| | // if all conditions are met then check if resulting 237| | // root word in the dictionary 238| | 239| 1.41M| if (test_condition(tmpword)) { ------------------ | Branch (239:9): [True: 15.2k, False: 1.39M] ------------------ 240| 15.2k| tmpl += strip.size(); 241| 15.2k| if ((he = pmyMgr->lookup(tmpword.c_str(), tmpword.size())) != nullptr) { ------------------ | Branch (241:11): [True: 17, False: 15.2k] ------------------ 242| 17| do { 243| 17| if (TESTAFF(he->astr, aflag, he->alen) && ------------------ | | 99| 34|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 17] | | ------------------ ------------------ | Branch (243:15): [True: 0, False: 17] ------------------ 244| | // forbid single prefixes with needaffix flag 245| 0| !TESTAFF(contclass, pmyMgr->get_needaffix(), contclasslen) && ------------------ | | 99| 17|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (245:15): [True: 0, False: 0] ------------------ 246| | // needflag 247| 0| ((!needflag) || TESTAFF(he->astr, needflag, he->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (247:16): [True: 0, False: 0] ------------------ 248| 0| (contclass && TESTAFF(contclass, needflag, contclasslen)))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (248:17): [True: 0, False: 0] ------------------ 249| 0| return he; 250| 17| he = he->next_homonym; // check homonyms 251| 17| } while (he); ------------------ | Branch (251:18): [True: 0, False: 17] ------------------ 252| 17| } 253| | 254| | // prefix matched but no root word was found 255| | // if aeXPRODUCT is allowed, try again but now 256| | // ross checked combined with a suffix 257| | 258| | // if ((opts & aeXPRODUCT) && in_compound) { 259| 15.2k| if ((opts & aeXPRODUCT)) { ------------------ | | 65| 15.2k|#define aeXPRODUCT (1 << 0) ------------------ | Branch (259:11): [True: 15.2k, False: 0] ------------------ 260| 15.2k| he = pmyMgr->suffix_check(tmpword, 0, tmpl, aeXPRODUCT, this, ------------------ | | 65| 15.2k|#define aeXPRODUCT (1 << 0) ------------------ 261| 15.2k| scratch, FLAG_NULL, needflag, in_compound); ------------------ | | 96| 15.2k|#define FLAG_NULL 0x00 ------------------ 262| 15.2k| if (he) ------------------ | Branch (262:13): [True: 0, False: 15.2k] ------------------ 263| 0| return he; 264| 15.2k| } 265| 15.2k| } 266| 1.41M| } 267| 1.41M| return nullptr; 268| 1.41M|} _ZN8PfxEntry12check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 276| 1.41M| AffixScratch& scratch) { 277| | // on entry prefix is 0 length or already matches the beginning of the word. 278| | // So if the remaining root word has positive length 279| | // and if there are enough chars in root word and added back strip chars 280| | // to meet the number of characters conditions, then test it 281| | 282| 1.41M| int tmpl = len - appnd.size(); // length of tmpword 283| | 284| 1.41M| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (284:8): [True: 1.41M, False: 2.44k] | Branch (284:21): [True: 2.44k, False: 0] | Branch (284:34): [True: 0, False: 2.44k] ------------------ 285| 1.41M| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (285:7): [True: 1.36M, False: 50.2k] ------------------ 286| | // generate new root word by removing prefix and adding 287| | // back any characters that would have been stripped 288| | 289| 1.36M| std::string& tmpword = scratch.pfx_check_twosfx; 290| 1.36M| tmpword.assign(strip); 291| 1.36M| tmpword.append(word, start + appnd.size(), tmpl); 292| | 293| | // now make sure all of the conditions on characters 294| | // are met. Please see the appendix at the end of 295| | // this file for more info on exactly what is being 296| | // tested 297| | 298| | // if all conditions are met then check if resulting 299| | // root word in the dictionary 300| | 301| 1.36M| if (test_condition(tmpword)) { ------------------ | Branch (301:9): [True: 12.4k, False: 1.34M] ------------------ 302| 12.4k| tmpl += strip.size(); 303| | 304| | // prefix matched but no root word was found 305| | // if aeXPRODUCT is allowed, try again but now 306| | // cross checked combined with a suffix 307| | 308| 12.4k| if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 65| 12.4k|#define aeXPRODUCT (1 << 0) ------------------ if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 73| 12.4k|#define IN_CPD_BEGIN 1 ------------------ | Branch (308:11): [True: 12.4k, False: 0] | Branch (308:34): [True: 12.4k, False: 0] ------------------ 309| | // hash entry of root word or NULL 310| 12.4k| struct hentry* he = pmyMgr->suffix_check_twosfx(tmpword, 0, tmpl, aeXPRODUCT, this, ------------------ | | 65| 12.4k|#define aeXPRODUCT (1 << 0) ------------------ 311| 12.4k| scratch, needflag); 312| 12.4k| if (he) ------------------ | Branch (312:13): [True: 0, False: 12.4k] ------------------ 313| 0| return he; 314| 12.4k| } 315| 12.4k| } 316| 1.36M| } 317| 1.41M| return nullptr; 318| 1.41M|} _ZN8PfxEntry18check_twosfx_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 326| 719| AffixScratch& scratch) { 327| 719| std::string result; 328| | // on entry prefix is 0 length or already matches the beginning of the word. 329| | // So if the remaining root word has positive length 330| | // and if there are enough chars in root word and added back strip chars 331| | // to meet the number of characters conditions, then test it 332| 719| int tmpl = len - appnd.size(); // length of tmpword 333| | 334| 719| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (334:8): [True: 719, False: 0] | Branch (334:21): [True: 0, False: 0] | Branch (334:34): [True: 0, False: 0] ------------------ 335| 719| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (335:7): [True: 639, False: 80] ------------------ 336| | // generate new root word by removing prefix and adding 337| | // back any characters that would have been stripped 338| | 339| 639| std::string& tmpword = scratch.pfx_check_twosfx; 340| 639| tmpword.assign(strip); 341| 639| tmpword.append(word, start + appnd.size(), tmpl); 342| | 343| | // now make sure all of the conditions on characters 344| | // are met. Please see the appendix at the end of 345| | // this file for more info on exactly what is being 346| | // tested 347| | 348| | // if all conditions are met then check if resulting 349| | // root word in the dictionary 350| | 351| 639| if (test_condition(tmpword)) { ------------------ | Branch (351:9): [True: 0, False: 639] ------------------ 352| 0| tmpl += strip.size(); 353| | 354| | // prefix matched but no root word was found 355| | // if aeXPRODUCT is allowed, try again but now 356| | // ross checked combined with a suffix 357| | 358| 0| if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (358:11): [True: 0, False: 0] | Branch (358:34): [True: 0, False: 0] ------------------ 359| 0| result = pmyMgr->suffix_check_twosfx_morph(tmpword, 0, tmpl, 360| 0| aeXPRODUCT, ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ 361| 0| this, scratch, needflag); 362| 0| } 363| 0| } 364| 639| } 365| 719| return result; 366| 719|} _ZN8PfxEntry11check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 374| 719| AffixScratch& scratch) { 375| 719| std::string result; 376| | 377| | // on entry prefix is 0 length or already matches the beginning of the word. 378| | // So if the remaining root word has positive length 379| | // and if there are enough chars in root word and added back strip chars 380| | // to meet the number of characters conditions, then test it 381| | 382| 719| int tmpl = len - appnd.size(); // length of tmpword 383| | 384| 719| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (384:8): [True: 719, False: 0] | Branch (384:21): [True: 0, False: 0] | Branch (384:34): [True: 0, False: 0] ------------------ 385| 719| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (385:7): [True: 639, False: 80] ------------------ 386| | // generate new root word by removing prefix and adding 387| | // back any characters that would have been stripped 388| | 389| 639| std::string& tmpword = scratch.pfx_check_word; 390| 639| tmpword.assign(strip); 391| 639| tmpword.append(word, start + appnd.size(), tmpl); 392| | 393| | // now make sure all of the conditions on characters 394| | // are met. Please see the appendix at the end of 395| | // this file for more info on exactly what is being 396| | // tested 397| | 398| | // if all conditions are met then check if resulting 399| | // root word in the dictionary 400| | 401| 639| if (test_condition(tmpword)) { ------------------ | Branch (401:9): [True: 0, False: 639] ------------------ 402| 0| tmpl += strip.size(); 403| 0| struct hentry* he; // hash entry of root word or NULL 404| 0| if ((he = pmyMgr->lookup(tmpword.c_str(), tmpword.size())) != nullptr) { ------------------ | Branch (404:11): [True: 0, False: 0] ------------------ 405| 0| do { 406| 0| if (TESTAFF(he->astr, aflag, he->alen) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (406:15): [True: 0, False: 0] ------------------ 407| | // forbid single prefixes with needaffix flag 408| 0| !TESTAFF(contclass, pmyMgr->get_needaffix(), contclasslen) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (408:15): [True: 0, False: 0] ------------------ 409| | // needflag 410| 0| ((!needflag) || TESTAFF(he->astr, needflag, he->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (410:16): [True: 0, False: 0] ------------------ 411| 0| (contclass && TESTAFF(contclass, needflag, contclasslen)))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (411:17): [True: 0, False: 0] ------------------ 412| 0| if (morphcode) { ------------------ | Branch (412:17): [True: 0, False: 0] ------------------ 413| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 414| 0| result.append(morphcode); 415| 0| } else 416| 0| result.append(getKey()); 417| 0| if (!HENTRY_FIND(he, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (417:17): [True: 0, False: 0] ------------------ 418| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 419| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 420| 0| result.append(HENTRY_WORD(he)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 421| 0| } 422| | // store the pointer of the hash entry 423| 0| if (HENTRY_DATA(he)) { ------------------ | Branch (423:17): [True: 0, False: 0] ------------------ 424| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 425| 0| result.append(HENTRY_DATA2(he)); 426| 0| } else { 427| | // return with debug information 428| 0| std::string flag = pmyMgr->encode_flag(getFlag()); 429| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 430| 0| result.append(MORPH_FLAG); ------------------ | | 117| 0|#define MORPH_FLAG "fl:" ------------------ 431| 0| result.append(flag); 432| 0| } 433| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 434| 0| } 435| 0| he = he->next_homonym; 436| 0| } while (he); ------------------ | Branch (436:18): [True: 0, False: 0] ------------------ 437| 0| } 438| | 439| | // prefix matched but no root word was found 440| | // if aeXPRODUCT is allowed, try again but now 441| | // ross checked combined with a suffix 442| | 443| 0| if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (443:11): [True: 0, False: 0] | Branch (443:34): [True: 0, False: 0] ------------------ 444| 0| std::string st = pmyMgr->suffix_check_morph(tmpword, 0, tmpl, aeXPRODUCT, this, ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ 445| 0| scratch, FLAG_NULL, needflag); ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ 446| 0| if (!st.empty()) { ------------------ | Branch (446:13): [True: 0, False: 0] ------------------ 447| 0| result.append(st); 448| 0| } 449| 0| } 450| 0| } 451| 639| } 452| | 453| 719| return result; 454| 719|} _ZN8SfxEntryC2EP8AffixMgr: 457| 34| : pmyMgr(pmgr) // register affix manager 458| 34| , next(nullptr) 459| 34| , nexteq(nullptr) 460| 34| , nextne(nullptr) 461| 34| , flgnxt(nullptr) 462| 34| , l_morph(nullptr) 463| 34| , r_morph(nullptr) 464| 34| , eq_morph(nullptr) {} _ZN8SfxEntry3addEPKcm: 467| 34|std::string SfxEntry::add(const char* word, size_t len) { 468| 34| std::string result; 469| | /* make sure all conditions match */ 470| 34| if ((len > strip.size() || (len == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (470:8): [True: 34, False: 0] | Branch (470:31): [True: 0, False: 0] | Branch (470:43): [True: 0, False: 0] ------------------ 471| 34| (len >= numconds) && test_condition(word + len, word) && ------------------ | Branch (471:7): [True: 34, False: 0] | Branch (471:28): [True: 34, False: 0] ------------------ 472| 34| (strip.empty() || ------------------ | Branch (472:8): [True: 34, False: 0] ------------------ 473| 34| (len >= strip.size() && strcmp(word + len - strip.size(), strip.c_str()) == 0))) { ------------------ | Branch (473:9): [True: 0, False: 0] | Branch (473:32): [True: 0, False: 0] ------------------ 474| 34| result.assign(word, len); 475| | /* we have a match so add suffix */ 476| 34| result.replace(len - strip.size(), std::string::npos, appnd); 477| 34| } 478| 34| return result; 479| 34|} _ZN8SfxEntry9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntrytttR12AffixScratch: 621| 81.4k| AffixScratch& scratch) { 622| 81.4k| struct hentry* he; // hash entry pointer 623| 81.4k| PfxEntry* ep = ppfx; 624| | 625| | // if this suffix is being cross checked with a prefix 626| | // but it does not support cross products skip it 627| | 628| 81.4k| if (((optflags & aeXPRODUCT) != 0) && ((opts & aeXPRODUCT) == 0)) ------------------ | | 65| 81.4k|#define aeXPRODUCT (1 << 0) ------------------ if (((optflags & aeXPRODUCT) != 0) && ((opts & aeXPRODUCT) == 0)) ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ | Branch (628:7): [True: 0, False: 81.4k] | Branch (628:41): [True: 0, False: 0] ------------------ 629| 0| return nullptr; 630| | 631| | // upon entry suffix is 0 length or already matches the end of the word. 632| | // So if the remaining root word has positive length 633| | // and if there are enough chars in root word and added back strip chars 634| | // to meet the number of characters conditions, then test it 635| | 636| 81.4k| int tmpl = len - appnd.size(); // length of tmpword 637| | // the second condition is not enough for UTF-8 strings 638| | // it checked in test_condition() 639| | 640| 81.4k| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (640:8): [True: 80.8k, False: 545] | Branch (640:21): [True: 545, False: 0] | Branch (640:34): [True: 0, False: 545] ------------------ 641| 80.8k| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (641:7): [True: 80.8k, False: 1] ------------------ 642| | // generate new root word by removing suffix and adding 643| | // back any characters that would have been stripped or 644| | // or null terminating the shorter string 645| | 646| 80.8k| std::string& tmpword = scratch.sfx_check_word; 647| 80.8k| tmpword.assign(word, start, tmpl); 648| 80.8k| if (!strip.empty()) { ------------------ | Branch (648:9): [True: 1, False: 80.8k] ------------------ 649| 1| tmpword.append(strip); 650| 1| } 651| | 652| 80.8k| const char* beg = tmpword.c_str(); 653| 80.8k| const char* end = beg + tmpword.size(); 654| | 655| | // now make sure all of the conditions on characters 656| | // are met. Please see the appendix at the end of 657| | // this file for more info on exactly what is being 658| | // tested 659| | 660| | // if all conditions are met then check if resulting 661| | // root word in the dictionary 662| | 663| 80.8k| if (test_condition(end, beg)) { ------------------ | Branch (663:9): [True: 80.8k, False: 3] ------------------ 664| |#ifdef SZOSZABLYA_POSSIBLE_ROOTS 665| | fprintf(stdout, "%s %s %c\n", word.c_str() + start, beg, aflag); 666| |#endif 667| 80.8k| if ((he = pmyMgr->lookup(tmpword.c_str(), tmpword.size())) != nullptr) { ------------------ | Branch (667:11): [True: 13, False: 80.8k] ------------------ 668| 13| do { 669| | // check conditional suffix (enabled by prefix) 670| 13| if ((TESTAFF(he->astr, aflag, he->alen) || ------------------ | | 99| 26|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 2, False: 11] | | ------------------ ------------------ | Branch (670:15): [True: 2, False: 11] ------------------ 671| 11| (ep && ep->getCont() && ------------------ | Branch (671:17): [True: 0, False: 11] | Branch (671:23): [True: 0, False: 0] ------------------ 672| 0| TESTAFF(ep->getCont(), aflag, ep->getContLen()))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 673| 2| (((optflags & aeXPRODUCT) == 0) || ------------------ | | 65| 2|#define aeXPRODUCT (1 << 0) ------------------ | Branch (673:16): [True: 2, False: 0] ------------------ 674| 0| (ep && TESTAFF(he->astr, ep->getFlag(), he->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (674:17): [True: 0, False: 0] ------------------ 675| | // enabled by prefix 676| 0| ((contclass) && ------------------ | Branch (676:17): [True: 0, False: 0] ------------------ 677| 0| (ep && TESTAFF(contclass, ep->getFlag(), contclasslen)))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (677:18): [True: 0, False: 0] ------------------ 678| | // handle cont. class 679| 2| ((!cclass) || ------------------ | Branch (679:16): [True: 2, False: 0] ------------------ 680| 0| ((contclass) && TESTAFF(contclass, cclass, contclasslen))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (680:17): [True: 0, False: 0] ------------------ 681| | // check only in compound homonyms (bad flags) 682| 2| (!badflag || !TESTAFF(he->astr, badflag, he->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (682:16): [True: 2, False: 0] | Branch (682:28): [True: 0, False: 0] ------------------ 683| | // handle required flag 684| 2| ((!needflag) || ------------------ | Branch (684:16): [True: 2, False: 0] ------------------ 685| 0| (TESTAFF(he->astr, needflag, he->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 686| 0| ((contclass) && TESTAFF(contclass, needflag, contclasslen))))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (686:18): [True: 0, False: 0] ------------------ 687| 2| return he; 688| 11| he = he->next_homonym; // check homonyms 689| 11| } while (he); ------------------ | Branch (689:18): [True: 0, False: 11] ------------------ 690| 13| } 691| 80.8k| } 692| 80.8k| } 693| 81.4k| return nullptr; 694| 81.4k|} _ZN8SfxEntry12check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntrytR12AffixScratch: 703| 19.2k| AffixScratch& scratch) { 704| 19.2k| PfxEntry* ep = ppfx; 705| | 706| | // if this suffix is being cross checked with a prefix 707| | // but it does not support cross products skip it 708| | 709| 19.2k| if ((optflags & aeXPRODUCT) != 0 && (opts & aeXPRODUCT) == 0) ------------------ | | 65| 19.2k|#define aeXPRODUCT (1 << 0) ------------------ if ((optflags & aeXPRODUCT) != 0 && (opts & aeXPRODUCT) == 0) ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ | Branch (709:7): [True: 0, False: 19.2k] | Branch (709:39): [True: 0, False: 0] ------------------ 710| 0| return nullptr; 711| | 712| | // upon entry suffix is 0 length or already matches the end of the word. 713| | // So if the remaining root word has positive length 714| | // and if there are enough chars in root word and added back strip chars 715| | // to meet the number of characters conditions, then test it 716| | 717| 19.2k| int tmpl = len - appnd.size(); // length of tmpword 718| | 719| 19.2k| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (719:8): [True: 19.1k, False: 25] | Branch (719:21): [True: 25, False: 0] | Branch (719:34): [True: 0, False: 25] ------------------ 720| 19.1k| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (720:7): [True: 19.1k, False: 0] ------------------ 721| | // generate new root word by removing suffix and adding 722| | // back any characters that would have been stripped or 723| | // or null terminating the shorter string 724| | 725| 19.1k| std::string& tmpword = scratch.sfx_check_twosfx; 726| 19.1k| tmpword.assign(word, start); 727| 19.1k| tmpword.resize(tmpl); 728| 19.1k| tmpword.append(strip); 729| 19.1k| tmpl += strip.size(); 730| | 731| 19.1k| const char* beg = tmpword.c_str(); 732| 19.1k| const char* end = beg + tmpl; 733| | 734| | // now make sure all of the conditions on characters 735| | // are met. Please see the appendix at the end of 736| | // this file for more info on exactly what is being 737| | // tested 738| | 739| | // if all conditions are met then recall suffix_check 740| | 741| 19.1k| if (test_condition(end, beg)) { ------------------ | Branch (741:9): [True: 19.1k, False: 0] ------------------ 742| 19.1k| struct hentry* he; // hash entry pointer 743| 19.1k| if (ppfx) { ------------------ | Branch (743:11): [True: 0, False: 19.1k] ------------------ 744| | // handle conditional suffix 745| 0| if ((contclass) && TESTAFF(contclass, ep->getFlag(), contclasslen)) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (745:13): [True: 0, False: 0] | Branch (745:13): [True: 0, False: 0] ------------------ 746| 0| he = pmyMgr->suffix_check(tmpword, 0, tmpl, 0, nullptr, scratch, (FLAG)aflag, needflag, IN_CPD_NOT); ------------------ | | 72| 0|#define IN_CPD_NOT 0 ------------------ 747| 0| else 748| 0| he = pmyMgr->suffix_check(tmpword, 0, tmpl, optflags, ppfx, 749| 0| scratch, (FLAG)aflag, needflag, IN_CPD_NOT); ------------------ | | 72| 0|#define IN_CPD_NOT 0 ------------------ 750| 19.1k| } else { 751| 19.1k| he = pmyMgr->suffix_check(tmpword, 0, tmpl, 0, nullptr, scratch, (FLAG)aflag, needflag, IN_CPD_NOT); ------------------ | | 72| 19.1k|#define IN_CPD_NOT 0 ------------------ 752| 19.1k| } 753| 19.1k| if (he) ------------------ | Branch (753:11): [True: 0, False: 19.1k] ------------------ 754| 0| return he; 755| 19.1k| } 756| 19.1k| } 757| 19.2k| return nullptr; 758| 19.2k|} _ZN8SfxEntry15initReverseWordEv: 869| 34|void SfxEntry::initReverseWord() { 870| 34| rappnd = appnd; 871| 34| reverseword(rappnd); 872| 34|} _ZN8PfxEntry14test_conditionERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 125| 2.77M|inline int PfxEntry::test_condition(const std::string& s) { 126| 2.77M| size_t st = 0; 127| 2.77M| size_t pos = std::string::npos; // group with pos input position 128| 2.77M| bool neg = false; // complementer 129| 2.77M| bool ingroup = false; // character in the group 130| 2.77M| if (numconds == 0) ------------------ | Branch (130:7): [True: 2.84k, False: 2.77M] ------------------ 131| 2.84k| return 1; 132| 2.77M| char* p = c.conds; 133| 2.89M| while (true) { ------------------ | Branch (133:10): [True: 2.89M, Folded] ------------------ 134| 2.89M| switch (*p) { 135| 0| case '\0': ------------------ | Branch (135:7): [True: 0, False: 2.89M] ------------------ 136| 0| return 1; 137| 24.8k| case '[': { ------------------ | Branch (137:7): [True: 24.8k, False: 2.87M] ------------------ 138| 24.8k| neg = false; 139| 24.8k| ingroup = false; 140| 24.8k| p = nextchar(p); 141| 24.8k| pos = st; 142| 24.8k| break; 143| 0| } 144| 24.8k| case '^': { ------------------ | Branch (144:7): [True: 24.8k, False: 2.87M] ------------------ 145| 24.8k| p = nextchar(p); 146| 24.8k| neg = true; 147| 24.8k| break; 148| 0| } 149| 24.8k| case ']': { ------------------ | Branch (149:7): [True: 24.8k, False: 2.87M] ------------------ 150| 24.8k| if (bool(neg) == bool(ingroup)) ------------------ | Branch (150:13): [True: 0, False: 24.8k] ------------------ 151| 0| return 0; 152| 24.8k| pos = std::string::npos; 153| 24.8k| p = nextchar(p); 154| | // skip the next character 155| 24.8k| if (!ingroup && st < s.size()) ------------------ | Branch (155:13): [True: 24.8k, False: 0] | Branch (155:25): [True: 23.5k, False: 1.31k] ------------------ 156| 23.5k| st = (opts & aeUTF8) ? utf8_next(s, st) : st + 1; ------------------ | | 66| 23.5k|#define aeUTF8 (1 << 1) ------------------ | Branch (156:16): [True: 23.5k, False: 0] ------------------ 157| 24.8k| if (st == s.size() && p) ------------------ | Branch (157:13): [True: 3.65k, False: 21.1k] | Branch (157:31): [True: 0, False: 3.65k] ------------------ 158| 0| return 0; // word <= condition 159| 24.8k| break; 160| 24.8k| } 161| 24.8k| case '.': ------------------ | Branch (161:7): [True: 0, False: 2.89M] ------------------ 162| 0| if (pos == std::string::npos) { // dots are not metacharacters in groups: [.] ------------------ | Branch (162:13): [True: 0, False: 0] ------------------ 163| 0| if (st == s.size()) ------------------ | Branch (163:15): [True: 0, False: 0] ------------------ 164| 0| return 0; // dot has no character to match 165| 0| p = nextchar(p); 166| | // skip the next character 167| 0| st = (opts & aeUTF8) ? utf8_next(s, st) : st + 1; ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (167:16): [True: 0, False: 0] ------------------ 168| 0| break; 169| 0| } 170| | /* FALLTHROUGH */ 171| 2.82M| default: { ------------------ | Branch (171:7): [True: 2.82M, False: 74.4k] ------------------ 172| 2.82M| if (st < s.size() && s[st] == *p) { ------------------ | Branch (172:13): [True: 2.82M, False: 2.63k] | Branch (172:30): [True: 24.9k, False: 2.79M] ------------------ 173| 24.9k| ++st; 174| 24.9k| p = nextchar(p); 175| 24.9k| if ((opts & aeUTF8) && (s[st - 1] & 0x80)) { // multibyte ------------------ | | 66| 24.9k|#define aeUTF8 (1 << 1) ------------------ | Branch (175:15): [True: 24.9k, False: 0] | Branch (175:34): [True: 24.9k, False: 0] ------------------ 176| 49.7k| while (p && is_utf8_cont(*p)) { // character ------------------ | Branch (176:20): [True: 49.7k, False: 0] | Branch (176:25): [True: 24.9k, False: 24.8k] ------------------ 177| 24.9k| if (st >= s.size() || *p != s[st]) { ------------------ | Branch (177:19): [True: 0, False: 24.9k] | Branch (177:37): [True: 132, False: 24.8k] ------------------ 178| 132| if (pos == std::string::npos) ------------------ | Branch (178:21): [True: 116, False: 16] ------------------ 179| 116| return 0; 180| 16| st = pos; 181| 16| break; 182| 132| } 183| 24.8k| p = nextchar(p); 184| 24.8k| ++st; 185| 24.8k| } 186| 24.8k| if (pos != std::string::npos && st != pos) { ------------------ | Branch (186:17): [True: 16, False: 24.8k] | Branch (186:45): [True: 0, False: 16] ------------------ 187| 0| ingroup = true; 188| 0| while (p && *p != ']' && ((p = nextchar(p)) != nullptr)) { ------------------ | Branch (188:22): [True: 0, False: 0] | Branch (188:27): [True: 0, False: 0] | Branch (188:40): [True: 0, False: 0] ------------------ 189| 0| } 190| 0| } 191| 24.8k| } else if (pos != std::string::npos) { ------------------ | Branch (191:22): [True: 0, False: 0] ------------------ 192| 0| ingroup = true; 193| 0| while (p && *p != ']' && ((p = nextchar(p)) != nullptr)) { ------------------ | Branch (193:20): [True: 0, False: 0] | Branch (193:25): [True: 0, False: 0] | Branch (193:38): [True: 0, False: 0] ------------------ 194| 0| } 195| 0| } 196| 2.79M| } else if (pos != std::string::npos) { // group ------------------ | Branch (196:20): [True: 49.6k, False: 2.75M] ------------------ 197| 49.6k| p = nextchar(p); 198| 49.6k| } else 199| 2.75M| return 0; 200| 2.82M| } 201| 2.89M| } 202| 148k| if (!p) ------------------ | Branch (202:9): [True: 24.8k, False: 124k] ------------------ 203| 24.8k| return 1; 204| 148k| } 205| 2.77M|} _ZN8PfxEntry8nextcharEPc: 110| 173k|inline char* PfxEntry::nextchar(char* p) { 111| 173k| if (p) { ------------------ | Branch (111:7): [True: 173k, False: 0] ------------------ 112| 173k| p++; 113| 173k| if (opts & aeLONGCOND) { ------------------ | | 69| 173k|#define aeLONGCOND (1 << 4) ------------------ | Branch (113:9): [True: 0, False: 173k] ------------------ 114| | // jump to the 2nd part of the condition 115| 0| if (p == c.conds + MAXCONDLEN_1) ------------------ | | 91| 0|#define MAXCONDLEN_1 (MAXCONDLEN - sizeof(char*)) | | ------------------ | | | | 90| 0|#define MAXCONDLEN 20 | | ------------------ ------------------ | Branch (115:11): [True: 0, False: 0] ------------------ 116| 0| return c.l.conds2; 117| | // end of the MAXCONDLEN length condition 118| 173k| } else if (p == c.conds + MAXCONDLEN) ------------------ | | 90| 173k|#define MAXCONDLEN 20 ------------------ | Branch (118:16): [True: 0, False: 173k] ------------------ 119| 0| return nullptr; 120| 173k| return *p ? p : nullptr; ------------------ | Branch (120:12): [True: 149k, False: 24.8k] ------------------ 121| 173k| } 122| 0| return nullptr; 123| 173k|} _ZN8SfxEntry14test_conditionEPKcS1_: 496| 100k|inline int SfxEntry::test_condition(const char* st, const char* beg) { 497| 100k| const char* pos = nullptr; // group with pos input position 498| 100k| bool neg = false; // complementer 499| 100k| bool ingroup = false; // character in the group 500| 100k| if (numconds == 0) ------------------ | Branch (500:7): [True: 100k, False: 3] ------------------ 501| 100k| return 1; 502| 3| char* p = c.conds; 503| 3| st--; 504| 3| int i = 1; 505| 17| while (true) { ------------------ | Branch (505:10): [True: 17, Folded] ------------------ 506| 17| switch (*p) { 507| 0| case '\0': ------------------ | Branch (507:7): [True: 0, False: 17] ------------------ 508| 0| return 1; 509| 2| case '[': ------------------ | Branch (509:7): [True: 2, False: 15] ------------------ 510| 2| p = nextchar(p); 511| 2| pos = st; 512| 2| break; 513| 0| case '^': ------------------ | Branch (513:7): [True: 0, False: 17] ------------------ 514| 0| p = nextchar(p); 515| 0| neg = true; 516| 0| break; 517| 2| case ']': ------------------ | Branch (517:7): [True: 2, False: 15] ------------------ 518| 2| if (!neg && !ingroup) ------------------ | Branch (518:13): [True: 2, False: 0] | Branch (518:21): [True: 2, False: 0] ------------------ 519| 2| return 0; 520| 0| i++; 521| | // skip the next character 522| 0| if (!ingroup) { ------------------ | Branch (522:13): [True: 0, False: 0] ------------------ 523| 0| for (; (opts & aeUTF8) && (st >= beg) && is_utf8_cont(*st); st--) ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (523:18): [True: 0, False: 0] | Branch (523:37): [True: 0, False: 0] | Branch (523:52): [True: 0, False: 0] ------------------ 524| 0| ; 525| 0| st--; 526| 0| } 527| 0| pos = nullptr; 528| 0| neg = false; 529| 0| ingroup = false; 530| 0| p = nextchar(p); 531| 0| if (st < beg && p) ------------------ | Branch (531:13): [True: 0, False: 0] | Branch (531:25): [True: 0, False: 0] ------------------ 532| 0| return 0; // word <= condition 533| 0| break; 534| 0| case '.': ------------------ | Branch (534:7): [True: 0, False: 17] ------------------ 535| 0| if (!pos) { ------------------ | Branch (535:13): [True: 0, False: 0] ------------------ 536| | // dots are not metacharacters in groups: [.] 537| 0| p = nextchar(p); 538| | // skip one character to the left. Walk back over any UTF-8 539| | // continuation bytes of that character to its leading byte first, 540| | // then step past it, so a single-byte match preceded by a 541| | // multibyte character does not consume the multibyte character. 542| 0| for (; (opts & aeUTF8) && (st >= beg) && is_utf8_cont(*st); st--) ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (542:18): [True: 0, False: 0] | Branch (542:37): [True: 0, False: 0] | Branch (542:52): [True: 0, False: 0] ------------------ 543| 0| ; 544| 0| st--; 545| 0| if (st < beg) { // word <= condition ------------------ | Branch (545:15): [True: 0, False: 0] ------------------ 546| 0| if (p) ------------------ | Branch (546:17): [True: 0, False: 0] ------------------ 547| 0| return 0; 548| 0| else 549| 0| return 1; 550| 0| } 551| 0| break; 552| 0| } 553| | /* FALLTHROUGH */ 554| 13| default: { ------------------ | Branch (554:7): [True: 13, False: 4] ------------------ 555| 13| if (*st == *p) { ------------------ | Branch (555:13): [True: 0, False: 13] ------------------ 556| 0| p = nextchar(p); 557| 0| if ((opts & aeUTF8) && (*st & 0x80)) { ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (557:15): [True: 0, False: 0] | Branch (557:34): [True: 0, False: 0] ------------------ 558| 0| st--; 559| 0| while (p && (st >= beg)) { ------------------ | Branch (559:20): [True: 0, False: 0] | Branch (559:25): [True: 0, False: 0] ------------------ 560| 0| if (*p != *st) { ------------------ | Branch (560:19): [True: 0, False: 0] ------------------ 561| 0| if (!pos) ------------------ | Branch (561:21): [True: 0, False: 0] ------------------ 562| 0| return 0; 563| 0| st = pos; 564| 0| break; 565| 0| } 566| | // first byte of the UTF-8 multibyte character 567| 0| if (!is_utf8_cont(*p)) ------------------ | Branch (567:19): [True: 0, False: 0] ------------------ 568| 0| break; 569| 0| p = nextchar(p); 570| 0| st--; 571| 0| } 572| 0| if (pos && st != pos) { ------------------ | Branch (572:17): [True: 0, False: 0] | Branch (572:24): [True: 0, False: 0] ------------------ 573| 0| if (neg) ------------------ | Branch (573:19): [True: 0, False: 0] ------------------ 574| 0| return 0; 575| 0| else if (i == numconds) ------------------ | Branch (575:24): [True: 0, False: 0] ------------------ 576| 0| return 1; 577| 0| ingroup = true; 578| 0| while (p && *p != ']' && ((p = nextchar(p)) != nullptr)) { ------------------ | Branch (578:22): [True: 0, False: 0] | Branch (578:27): [True: 0, False: 0] | Branch (578:40): [True: 0, False: 0] ------------------ 579| 0| } 580| 0| st--; 581| 0| } 582| 0| if (p && *p != ']') ------------------ | Branch (582:17): [True: 0, False: 0] | Branch (582:22): [True: 0, False: 0] ------------------ 583| 0| p = nextchar(p); 584| 0| } else if (pos) { ------------------ | Branch (584:22): [True: 0, False: 0] ------------------ 585| 0| if (neg) ------------------ | Branch (585:17): [True: 0, False: 0] ------------------ 586| 0| return 0; 587| 0| else if (i == numconds) ------------------ | Branch (587:22): [True: 0, False: 0] ------------------ 588| 0| return 1; 589| 0| ingroup = true; 590| 0| while (p && *p != ']' && ((p = nextchar(p)) != nullptr)) { ------------------ | Branch (590:20): [True: 0, False: 0] | Branch (590:25): [True: 0, False: 0] | Branch (590:38): [True: 0, False: 0] ------------------ 591| 0| } 592| | // if (p && *p != ']') p = nextchar(p); 593| 0| st--; 594| 0| } 595| 0| if (!pos) { ------------------ | Branch (595:15): [True: 0, False: 0] ------------------ 596| 0| i++; 597| 0| st--; 598| 0| } 599| 0| if (st < beg && p && *p != ']') ------------------ | Branch (599:15): [True: 0, False: 0] | Branch (599:27): [True: 0, False: 0] | Branch (599:32): [True: 0, False: 0] ------------------ 600| 0| return 0; // word <= condition 601| 13| } else if (pos) { // group ------------------ | Branch (601:20): [True: 12, False: 1] ------------------ 602| 12| p = nextchar(p); 603| 12| } else 604| 1| return 0; 605| 13| } 606| 17| } 607| 14| if (!p) ------------------ | Branch (607:9): [True: 0, False: 14] ------------------ 608| 0| return 1; 609| 14| } 610| 3|} _ZN8SfxEntry8nextcharEPc: 481| 14|inline char* SfxEntry::nextchar(char* p) { 482| 14| if (p) { ------------------ | Branch (482:7): [True: 14, False: 0] ------------------ 483| 14| p++; 484| 14| if (opts & aeLONGCOND) { ------------------ | | 69| 14|#define aeLONGCOND (1 << 4) ------------------ | Branch (484:9): [True: 0, False: 14] ------------------ 485| | // jump to the 2nd part of the condition 486| 0| if (p == c.l.conds1 + MAXCONDLEN_1) ------------------ | | 91| 0|#define MAXCONDLEN_1 (MAXCONDLEN - sizeof(char*)) | | ------------------ | | | | 90| 0|#define MAXCONDLEN 20 | | ------------------ ------------------ | Branch (486:11): [True: 0, False: 0] ------------------ 487| 0| return c.l.conds2; 488| | // end of the MAXCONDLEN length condition 489| 14| } else if (p == c.conds + MAXCONDLEN) ------------------ | | 90| 14|#define MAXCONDLEN 20 ------------------ | Branch (489:16): [True: 0, False: 14] ------------------ 490| 0| return nullptr; 491| 14| return *p ? p : nullptr; ------------------ | Branch (491:12): [True: 14, False: 0] ------------------ 492| 14| } 493| 0| return nullptr; 494| 14|} _ZN8PfxEntry7getNextEv: 134| 2.78M| inline PfxEntry* getNext() { return next; } _ZN8SfxEntry7getNextEv: 216| 228| inline SfxEntry* getNext() { return next; } _ZN8PfxEntry6getKeyEv: 124| 67.8k| const char* getKey() { return appnd.c_str(); } _ZN8PfxEntry7getFlagEv: 123| 779| FLAG getFlag() { return aflag; } _ZN8PfxEntry9setFlgNxtEPS_: 142| 8| inline void setFlgNxt(PfxEntry* ptr) { flgnxt = ptr; } _ZN8PfxEntry7setNextEPS_: 139| 8| inline void setNext(PfxEntry* ptr) { next = ptr; } _ZN8PfxEntry9setNextEQEPS_: 141| 14| inline void setNextEQ(PfxEntry* ptr) { nexteq = ptr; } _ZN8PfxEntry9setNextNEEPS_: 140| 16| inline void setNextNE(PfxEntry* ptr) { nextne = ptr; } _ZN8PfxEntry9getNextEQEv: 136| 49.4k| inline PfxEntry* getNextEQ() { return nexteq; } _ZN8PfxEntry9getNextNEEv: 135| 17.5k| inline PfxEntry* getNextNE() { return nextne; } _ZN8SfxEntry6getKeyEv: 205| 668k| const char* getKey() { return rappnd.c_str(); } _ZN8SfxEntry7getFlagEv: 204| 140k| FLAG getFlag() { return aflag; } _ZN8SfxEntry9setFlgNxtEPS_: 228| 34| inline void setFlgNxt(SfxEntry* ptr) { flgnxt = ptr; } _ZN8SfxEntry7setNextEPS_: 225| 34| inline void setNext(SfxEntry* ptr) { next = ptr; } _ZN8SfxEntry9setNextEQEPS_: 227| 88| inline void setNextEQ(SfxEntry* ptr) { nexteq = ptr; } _ZN8SfxEntry9setNextNEEPS_: 226| 80| inline void setNextNE(SfxEntry* ptr) { nextne = ptr; } _ZN8SfxEntry9getNextEQEv: 218| 563k| inline SfxEntry* getNextEQ() { return nexteq; } _ZN8SfxEntry9getNextNEEv: 217| 105k| inline SfxEntry* getNextNE() { return nextne; } _ZN8PfxEntry7getContEv: 131| 4.24M| inline const unsigned short* getCont() { return contclass; } _ZN8PfxEntry10getContLenEv: 132| 1.41M| inline unsigned short getContLen() { return contclasslen; } _ZN8SfxEntry7getContEv: 210| 792k| inline const unsigned short* getCont() { return contclass; } _ZN8SfxEntry10getContLenEv: 211| 112k| inline unsigned short getContLen() { return contclasslen; } _ZN8SfxEntry9getKeyLenEv: 214| 167k| inline int getKeyLen() { return appnd.size(); } _ZN8SfxEntry9getFlgNxtEv: 223| 65.4k| inline SfxEntry* getFlgNxt() { return flgnxt; } _ZN8SfxEntry8getAffixEv: 212| 36.8k| inline const char* getAffix() { return appnd.c_str(); } _ZNK8SfxEntry10allowCrossEv: 171| 34| bool allowCross() const { return ((opts & aeXPRODUCT) != 0); } ------------------ | | 65| 34|#define aeXPRODUCT (1 << 0) ------------------ _ZNK8PfxEntry10allowCrossEv: 94| 3| bool allowCross() const { return ((opts & aeXPRODUCT) != 0); } ------------------ | | 65| 3|#define aeXPRODUCT (1 << 0) ------------------ _ZN8PfxEntry9getKeyLenEv: 127| 2.31k| inline int getKeyLen() { return appnd.size(); } _ZN8PfxEntry9getFlgNxtEv: 137| 771| inline PfxEntry* getFlgNxt() { return flgnxt; } _ZN8AffixMgrC2EPKcRKNSt3__16vectorINS2_10unique_ptrI7HashMgrNS2_14default_deleteIS5_EEEENS2_9allocatorIS8_EEEES1_: 93| 38| : alldic(ptr) 94| 38| , pHMgr(ptr[0].get()) { 95| | 96| | // register hash manager and load affix data from aff file 97| 38| csconv = nullptr; 98| 38| utf8 = 0; 99| 38| complexprefixes = 0; 100| 38| parsedmaptable = false; 101| 38| parsedbreaktable = false; 102| 38| iconvtable = nullptr; 103| 38| oconvtable = nullptr; 104| | // allow simplified compound forms (see 3rd field of CHECKCOMPOUNDPATTERN) 105| 38| simplifiedcpd = 0; 106| 38| parsedcheckcpd = false; 107| 38| parseddefcpd = false; 108| 38| phone = nullptr; 109| 38| compoundflag = FLAG_NULL; // permits word in compound forms ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 110| 38| compoundbegin = FLAG_NULL; // may be first word in compound forms ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 111| 38| compoundmiddle = FLAG_NULL; // may be middle word in compound forms ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 112| 38| compoundend = FLAG_NULL; // may be last word in compound forms ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 113| 38| compoundroot = FLAG_NULL; // compound word signing flag ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 114| 38| compoundpermitflag = FLAG_NULL; // compound permitting flag for suffixed word ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 115| 38| compoundforbidflag = FLAG_NULL; // compound fordidden flag for suffixed word ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 116| 38| compoundmoresuffixes = 0; // allow more suffixes within compound words 117| 38| checkcompounddup = 0; // forbid double words in compounds 118| 38| checkcompoundrep = 0; // forbid bad compounds (may be non-compound word with 119| | // a REP substitution) 120| 38| checkcompoundcase = 121| 38| 0; // forbid upper and lowercase combinations at word bounds 122| 38| checkcompoundtriple = 0; // forbid compounds with triple letters 123| 38| simplifiedtriple = 0; // allow simplified triple letters in compounds 124| | // (Schiff+fahrt -> Schiffahrt) 125| 38| forbiddenword = FORBIDDENWORD; // forbidden word signing flag ------------------ | | 127| 38|#define FORBIDDENWORD 65510 ------------------ 126| 38| nosuggest = FLAG_NULL; // don't suggest words signed with NOSUGGEST flag ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 127| 38| nongramsuggest = FLAG_NULL; ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 128| 38| langnum = 0; // language code (see http://l10n.openoffice.org/languages.html) 129| 38| needaffix = FLAG_NULL; // forbidden root, allowed only with suffixes ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 130| 38| cpdwordmax = -1; // default: unlimited wordcount in compound words 131| 38| cpdmin = -1; // undefined 132| 38| cpdmaxsyllable = 0; // default: unlimited syllablecount in compound words 133| 38| pfxappnd = nullptr; // previous prefix for counting syllables of the prefix BUG 134| 38| sfxappnd = nullptr; // previous suffix for counting syllables of the suffix BUG 135| 38| sfxextra = 0; // modifier for syllable count of sfxappnd BUG 136| 38| checknum = 0; // checking numbers, and word with numbers 137| 38| havecontclass = 0; // flags of possible continuing classes (double affix) 138| | // LEMMA_PRESENT: not put root into the morphological output. Lemma presents 139| | // in morhological description in dictionary file. It's often combined with 140| | // PSEUDOROOT. 141| 38| lemma_present = FLAG_NULL; ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 142| 38| circumfix = FLAG_NULL; ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 143| 38| onlyincompound = FLAG_NULL; ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 144| 38| maxngramsugs = -1; // undefined 145| 38| maxdiff = -1; // undefined 146| 38| onlymaxdiff = 0; 147| 38| maxcpdsugs = -1; // undefined 148| 38| nosplitsugs = 0; 149| 38| sugswithdots = 0; 150| 38| keepcase = 0; 151| 38| forceucase = 0; 152| 38| warn = 0; 153| 38| forbidwarn = 0; 154| 38| checksharps = 0; 155| 38| substandard = FLAG_NULL; ------------------ | | 96| 38|#define FLAG_NULL 0x00 ------------------ 156| 38| fullstrip = 0; 157| | 158| 38| sfx = nullptr; 159| 38| pfx = nullptr; 160| | 161| 9.76k| for (int i = 0; i < SETSIZE; i++) { ------------------ | | 61| 9.76k|#define SETSIZE 256 ------------------ | Branch (161:19): [True: 9.72k, False: 38] ------------------ 162| 9.72k| pStart[i] = nullptr; 163| 9.72k| sStart[i] = nullptr; 164| 9.72k| pFlag[i] = nullptr; 165| 9.72k| sFlag[i] = nullptr; 166| 9.72k| } 167| | 168| 38| memset(contclasses, 0, CONTSIZE * sizeof(char)); ------------------ | | 62| 38|#define CONTSIZE 65536 ------------------ 169| | 170| 38| if (parse_file(affpath, key)) { ------------------ | Branch (170:7): [True: 0, False: 38] ------------------ 171| 0| fprintf(stderr, "Failure loading aff file %s\n", affpath); 172| 0| } 173| | 174| | /* get encoding for CHECKCOMPOUNDCASE */ 175| 38| if (!utf8) { ------------------ | Branch (175:7): [True: 20, False: 18] ------------------ 176| 20| csconv = get_current_cs(get_encoding()); 177| 5.14k| for (int i = 0; i <= 255; i++) { ------------------ | Branch (177:21): [True: 5.12k, False: 20] ------------------ 178| 5.12k| if ((csconv[i].cupper != csconv[i].clower) && ------------------ | Branch (178:11): [True: 2.24k, False: 2.88k] ------------------ 179| 2.24k| (wordchars.find((char)i) == std::string::npos)) { ------------------ | Branch (179:11): [True: 2.24k, False: 0] ------------------ 180| 2.24k| wordchars.push_back((char)i); 181| 2.24k| } 182| 5.12k| } 183| 20| } 184| | 185| | // default BREAK definition 186| 38| if (!parsedbreaktable) { ------------------ | Branch (186:7): [True: 34, False: 4] ------------------ 187| 34| breaktable.emplace_back("-"); 188| 34| breaktable.emplace_back("^-"); 189| 34| breaktable.emplace_back("-$"); 190| 34| parsedbreaktable = true; 191| 34| } 192| | 193| 38|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 194| | // not entirely sure this is invalid, so only for fuzzing for now 195| 38| if (iconvtable && !iconvtable->check_against_breaktable(breaktable)) { ------------------ | Branch (195:7): [True: 2, False: 36] | Branch (195:21): [True: 0, False: 2] ------------------ 196| 0| delete iconvtable; 197| 0| iconvtable = nullptr; 198| 0| } 199| 38|#endif 200| | 201| 38| if (cpdmin == -1) ------------------ | Branch (201:7): [True: 34, False: 4] ------------------ 202| 34| cpdmin = MINCPDLEN; ------------------ | | 88| 34|#define MINCPDLEN 3 ------------------ 203| 38|} _ZN8AffixMgr13finishFileMgrEP7FileMgr: 260| 38|void AffixMgr::finishFileMgr(FileMgr* afflst) { 261| 38| delete afflst; 262| | 263| | // convert affix trees to sorted list 264| 38| process_pfx_tree_to_list(); 265| 38| process_sfx_tree_to_list(); 266| 38|} _ZN8AffixMgr10parse_fileEPKcS1_: 269| 38|int AffixMgr::parse_file(const char* affpath, const char* key) { 270| | 271| | // checking flag duplication 272| 38| char dupflags[CONTSIZE]; 273| 38| char dupflags_ini = 1; 274| | 275| | // first line indicator for removing byte order mark 276| 38| int firstline = 1; 277| | 278| | // open the affix file 279| 38| FileMgr* afflst = new FileMgr(affpath, key); 280| | 281| | // step one is to parse the affix file building up the internal 282| | // affix data structures 283| | 284| | // read in each line ignoring any that do not 285| | // start with a known line type indicator 286| 38| std::string line; 287| 646| while (afflst->getline(line)) { ------------------ | Branch (287:10): [True: 608, False: 38] ------------------ 288| 608| mychomp(line); 289| | 290| | /* remove byte order mark */ 291| 608| if (firstline) { ------------------ | Branch (291:9): [True: 38, False: 570] ------------------ 292| 38| firstline = 0; 293| | // Affix file begins with byte order mark: possible incompatibility with 294| | // old Hunspell versions 295| 38| if (line.compare(0, 3, "\xEF\xBB\xBF", 3) == 0) { ------------------ | Branch (295:11): [True: 0, False: 38] ------------------ 296| 0| line.erase(0, 3); 297| 0| } 298| 38| } 299| | 300| | /* parse in the keyboard string */ 301| 608| if (line.compare(0, 3, "KEY", 3) == 0) { ------------------ | Branch (301:9): [True: 0, False: 608] ------------------ 302| 0| if (!parse_string(line, keystring, afflst->getlinenum())) { ------------------ | Branch (302:11): [True: 0, False: 0] ------------------ 303| 0| finishFileMgr(afflst); 304| 0| return 1; 305| 0| } 306| 0| } 307| | 308| | /* parse in the try string */ 309| 608| if (line.compare(0, 3, "TRY", 3) == 0) { ------------------ | Branch (309:9): [True: 2, False: 606] ------------------ 310| 2| if (!parse_string(line, trystring, afflst->getlinenum())) { ------------------ | Branch (310:11): [True: 0, False: 2] ------------------ 311| 0| finishFileMgr(afflst); 312| 0| return 1; 313| 0| } 314| 2| } 315| | 316| | /* parse in the name of the character set used by the .dict and .aff */ 317| 608| if (line.compare(0, 3, "SET", 3) == 0) { ------------------ | Branch (317:9): [True: 18, False: 590] ------------------ 318| 18| if (!parse_string(line, encoding, afflst->getlinenum())) { ------------------ | Branch (318:11): [True: 0, False: 18] ------------------ 319| 0| finishFileMgr(afflst); 320| 0| return 1; 321| 0| } 322| 18| if (encoding == "UTF-8") { ------------------ | Branch (322:11): [True: 18, False: 0] ------------------ 323| 18| utf8 = 1; 324| 18| } 325| 18| } 326| | 327| | /* parse COMPLEXPREFIXES for agglutinative languages with right-to-left 328| | * writing system */ 329| 608| if (line.compare(0, 15, "COMPLEXPREFIXES", 15) == 0) ------------------ | Branch (329:9): [True: 2, False: 606] ------------------ 330| 2| complexprefixes = 1; 331| | 332| | /* parse in the flag used by the controlled compound words */ 333| 608| if (line.compare(0, 12, "COMPOUNDFLAG", 12) == 0) { ------------------ | Branch (333:9): [True: 8, False: 600] ------------------ 334| 8| if (!parse_flag(line, &compoundflag, afflst)) { ------------------ | Branch (334:11): [True: 0, False: 8] ------------------ 335| 0| finishFileMgr(afflst); 336| 0| return 1; 337| 0| } 338| 8| } 339| | 340| | /* parse in the flag used by compound words */ 341| 608| if (line.compare(0, 13, "COMPOUNDBEGIN", 13) == 0) { ------------------ | Branch (341:9): [True: 0, False: 608] ------------------ 342| 0| if (complexprefixes) { ------------------ | Branch (342:11): [True: 0, False: 0] ------------------ 343| 0| if (!parse_flag(line, &compoundend, afflst)) { ------------------ | Branch (343:13): [True: 0, False: 0] ------------------ 344| 0| finishFileMgr(afflst); 345| 0| return 1; 346| 0| } 347| 0| } else { 348| 0| if (!parse_flag(line, &compoundbegin, afflst)) { ------------------ | Branch (348:13): [True: 0, False: 0] ------------------ 349| 0| finishFileMgr(afflst); 350| 0| return 1; 351| 0| } 352| 0| } 353| 0| } 354| | 355| | /* parse in the flag used by compound words */ 356| 608| if (line.compare(0, 14, "COMPOUNDMIDDLE", 14) == 0) { ------------------ | Branch (356:9): [True: 0, False: 608] ------------------ 357| 0| if (!parse_flag(line, &compoundmiddle, afflst)) { ------------------ | Branch (357:11): [True: 0, False: 0] ------------------ 358| 0| finishFileMgr(afflst); 359| 0| return 1; 360| 0| } 361| 0| } 362| | 363| | /* parse in the flag used by compound words */ 364| 608| if (line.compare(0, 11, "COMPOUNDEND", 11) == 0) { ------------------ | Branch (364:9): [True: 0, False: 608] ------------------ 365| 0| if (complexprefixes) { ------------------ | Branch (365:11): [True: 0, False: 0] ------------------ 366| 0| if (!parse_flag(line, &compoundbegin, afflst)) { ------------------ | Branch (366:13): [True: 0, False: 0] ------------------ 367| 0| finishFileMgr(afflst); 368| 0| return 1; 369| 0| } 370| 0| } else { 371| 0| if (!parse_flag(line, &compoundend, afflst)) { ------------------ | Branch (371:13): [True: 0, False: 0] ------------------ 372| 0| finishFileMgr(afflst); 373| 0| return 1; 374| 0| } 375| 0| } 376| 0| } 377| | 378| | /* parse in the data used by compound_check() method */ 379| 608| if (line.compare(0, 15, "COMPOUNDWORDMAX", 15) == 0) { ------------------ | Branch (379:9): [True: 2, False: 606] ------------------ 380| 2| if (!parse_num(line, &cpdwordmax, afflst)) { ------------------ | Branch (380:11): [True: 0, False: 2] ------------------ 381| 0| finishFileMgr(afflst); 382| 0| return 1; 383| 0| } 384| 2| } 385| | 386| | /* parse in the flag sign compounds in dictionary */ 387| 608| if (line.compare(0, 12, "COMPOUNDROOT", 12) == 0) { ------------------ | Branch (387:9): [True: 0, False: 608] ------------------ 388| 0| if (!parse_flag(line, &compoundroot, afflst)) { ------------------ | Branch (388:11): [True: 0, False: 0] ------------------ 389| 0| finishFileMgr(afflst); 390| 0| return 1; 391| 0| } 392| 0| } 393| | 394| | /* parse in the flag used by compound_check() method */ 395| 608| if (line.compare(0, 18, "COMPOUNDPERMITFLAG", 18) == 0) { ------------------ | Branch (395:9): [True: 2, False: 606] ------------------ 396| 2| if (!parse_flag(line, &compoundpermitflag, afflst)) { ------------------ | Branch (396:11): [True: 0, False: 2] ------------------ 397| 0| finishFileMgr(afflst); 398| 0| return 1; 399| 0| } 400| 2| } 401| | 402| | /* parse in the flag used by compound_check() method */ 403| 608| if (line.compare(0, 18, "COMPOUNDFORBIDFLAG", 18) == 0) { ------------------ | Branch (403:9): [True: 2, False: 606] ------------------ 404| 2| if (!parse_flag(line, &compoundforbidflag, afflst)) { ------------------ | Branch (404:11): [True: 0, False: 2] ------------------ 405| 0| finishFileMgr(afflst); 406| 0| return 1; 407| 0| } 408| 2| } 409| | 410| 608| if (line.compare(0, 20, "COMPOUNDMORESUFFIXES", 20) == 0) { ------------------ | Branch (410:9): [True: 0, False: 608] ------------------ 411| 0| compoundmoresuffixes = 1; 412| 0| } 413| | 414| 608| if (line.compare(0, 16, "CHECKCOMPOUNDDUP", 16) == 0) { ------------------ | Branch (414:9): [True: 0, False: 608] ------------------ 415| 0| checkcompounddup = 1; 416| 0| } 417| | 418| 608| if (line.compare(0, 16, "CHECKCOMPOUNDREP", 16) == 0) { ------------------ | Branch (418:9): [True: 2, False: 606] ------------------ 419| 2| checkcompoundrep = 1; 420| 2| } 421| | 422| 608| if (line.compare(0, 19, "CHECKCOMPOUNDTRIPLE", 19) == 0) { ------------------ | Branch (422:9): [True: 0, False: 608] ------------------ 423| 0| checkcompoundtriple = 1; 424| 0| } 425| | 426| 608| if (line.compare(0, 16, "SIMPLIFIEDTRIPLE", 16) == 0) { ------------------ | Branch (426:9): [True: 0, False: 608] ------------------ 427| 0| simplifiedtriple = 1; 428| 0| } 429| | 430| 608| if (line.compare(0, 17, "CHECKCOMPOUNDCASE", 17) == 0) { ------------------ | Branch (430:9): [True: 0, False: 608] ------------------ 431| 0| checkcompoundcase = 1; 432| 0| } 433| | 434| 608| if (line.compare(0, 9, "NOSUGGEST", 9) == 0) { ------------------ | Branch (434:9): [True: 0, False: 608] ------------------ 435| 0| if (!parse_flag(line, &nosuggest, afflst)) { ------------------ | Branch (435:11): [True: 0, False: 0] ------------------ 436| 0| finishFileMgr(afflst); 437| 0| return 1; 438| 0| } 439| 0| } 440| | 441| 608| if (line.compare(0, 14, "NONGRAMSUGGEST", 14) == 0) { ------------------ | Branch (441:9): [True: 0, False: 608] ------------------ 442| 0| if (!parse_flag(line, &nongramsuggest, afflst)) { ------------------ | Branch (442:11): [True: 0, False: 0] ------------------ 443| 0| finishFileMgr(afflst); 444| 0| return 1; 445| 0| } 446| 0| } 447| | 448| | /* parse in the flag used by forbidden words */ 449| 608| if (line.compare(0, 13, "FORBIDDENWORD", 13) == 0) { ------------------ | Branch (449:9): [True: 2, False: 606] ------------------ 450| 2| if (!parse_flag(line, &forbiddenword, afflst)) { ------------------ | Branch (450:11): [True: 0, False: 2] ------------------ 451| 0| finishFileMgr(afflst); 452| 0| return 1; 453| 0| } 454| 2| } 455| | 456| | /* parse in the flag used by forbidden words (is deprecated) */ 457| 608| if (line.compare(0, 13, "LEMMA_PRESENT", 13) == 0) { ------------------ | Branch (457:9): [True: 0, False: 608] ------------------ 458| 0| if (!parse_flag(line, &lemma_present, afflst)) { ------------------ | Branch (458:11): [True: 0, False: 0] ------------------ 459| 0| finishFileMgr(afflst); 460| 0| return 1; 461| 0| } 462| 0| } 463| | 464| | /* parse in the flag used by circumfixes */ 465| 608| if (line.compare(0, 9, "CIRCUMFIX", 9) == 0) { ------------------ | Branch (465:9): [True: 2, False: 606] ------------------ 466| 2| if (!parse_flag(line, &circumfix, afflst)) { ------------------ | Branch (466:11): [True: 0, False: 2] ------------------ 467| 0| finishFileMgr(afflst); 468| 0| return 1; 469| 0| } 470| 2| } 471| | 472| | /* parse in the flag used by fogemorphemes */ 473| 608| if (line.compare(0, 14, "ONLYINCOMPOUND", 14) == 0) { ------------------ | Branch (473:9): [True: 0, False: 608] ------------------ 474| 0| if (!parse_flag(line, &onlyincompound, afflst)) { ------------------ | Branch (474:11): [True: 0, False: 0] ------------------ 475| 0| finishFileMgr(afflst); 476| 0| return 1; 477| 0| } 478| 0| } 479| | 480| | /* parse in the flag used by `needaffixs' (is deprecated) */ 481| 608| if (line.compare(0, 10, "PSEUDOROOT", 10) == 0) { ------------------ | Branch (481:9): [True: 0, False: 608] ------------------ 482| 0| if (!parse_flag(line, &needaffix, afflst)) { ------------------ | Branch (482:11): [True: 0, False: 0] ------------------ 483| 0| finishFileMgr(afflst); 484| 0| return 1; 485| 0| } 486| 0| } 487| | 488| | /* parse in the flag used by `needaffixs' */ 489| 608| if (line.compare(0, 9, "NEEDAFFIX", 9) == 0) { ------------------ | Branch (489:9): [True: 2, False: 606] ------------------ 490| 2| if (!parse_flag(line, &needaffix, afflst)) { ------------------ | Branch (490:11): [True: 0, False: 2] ------------------ 491| 0| finishFileMgr(afflst); 492| 0| return 1; 493| 0| } 494| 2| } 495| | 496| | /* parse in the minimal length for words in compounds */ 497| 608| if (line.compare(0, 11, "COMPOUNDMIN", 11) == 0) { ------------------ | Branch (497:9): [True: 4, False: 604] ------------------ 498| 4| if (!parse_num(line, &cpdmin, afflst)) { ------------------ | Branch (498:11): [True: 0, False: 4] ------------------ 499| 0| finishFileMgr(afflst); 500| 0| return 1; 501| 0| } 502| 4| if (cpdmin < 1) ------------------ | Branch (502:11): [True: 0, False: 4] ------------------ 503| 0| cpdmin = 1; 504| 4| } 505| | 506| | /* parse in the max. words and syllables in compounds */ 507| 608| if (line.compare(0, 16, "COMPOUNDSYLLABLE", 16) == 0) { ------------------ | Branch (507:9): [True: 2, False: 606] ------------------ 508| 2| if (!parse_cpdsyllable(line, afflst)) { ------------------ | Branch (508:11): [True: 0, False: 2] ------------------ 509| 0| finishFileMgr(afflst); 510| 0| return 1; 511| 0| } 512| 2| } 513| | 514| | /* parse in the flag used by compound_check() method */ 515| 608| if (line.compare(0, 11, "SYLLABLENUM", 11) == 0) { ------------------ | Branch (515:9): [True: 0, False: 608] ------------------ 516| 0| if (!parse_string(line, cpdsyllablenum, afflst->getlinenum())) { ------------------ | Branch (516:11): [True: 0, False: 0] ------------------ 517| 0| finishFileMgr(afflst); 518| 0| return 1; 519| 0| } 520| 0| } 521| | 522| | /* parse in the flag used by the controlled compound words */ 523| 608| if (line.compare(0, 8, "CHECKNUM", 8) == 0) { ------------------ | Branch (523:9): [True: 0, False: 608] ------------------ 524| 0| checknum = 1; 525| 0| } 526| | 527| | /* parse in the extra word characters */ 528| 608| if (line.compare(0, 9, "WORDCHARS", 9) == 0) { ------------------ | Branch (528:9): [True: 6, False: 602] ------------------ 529| 6| if (!parse_array(line, wordchars, wordchars_utf16, ------------------ | Branch (529:11): [True: 0, False: 6] ------------------ 530| 6| utf8, afflst->getlinenum())) { 531| 0| finishFileMgr(afflst); 532| 0| return 1; 533| 0| } 534| 6| } 535| | 536| | /* parse in the ignored characters (for example, Arabic optional diacretics 537| | * charachters */ 538| 608| if (line.compare(0, 6, "IGNORE", 6) == 0) { ------------------ | Branch (538:9): [True: 4, False: 604] ------------------ 539| 4| if (!parse_array(line, ignorechars, ignorechars_utf16, ------------------ | Branch (539:11): [True: 0, False: 4] ------------------ 540| 4| utf8, afflst->getlinenum())) { 541| 0| finishFileMgr(afflst); 542| 0| return 1; 543| 0| } 544| 4| } 545| | 546| | /* parse in the input conversion table */ 547| 608| if (line.compare(0, 5, "ICONV", 5) == 0) { ------------------ | Branch (547:9): [True: 2, False: 606] ------------------ 548| 2| if (!parse_convtable(line, afflst, &iconvtable, "ICONV")) { ------------------ | Branch (548:11): [True: 0, False: 2] ------------------ 549| 0| finishFileMgr(afflst); 550| 0| return 1; 551| 0| } 552| 2| } 553| | 554| | /* parse in the output conversion table */ 555| 608| if (line.compare(0, 5, "OCONV", 5) == 0) { ------------------ | Branch (555:9): [True: 2, False: 606] ------------------ 556| 2| if (!parse_convtable(line, afflst, &oconvtable, "OCONV")) { ------------------ | Branch (556:11): [True: 0, False: 2] ------------------ 557| 0| finishFileMgr(afflst); 558| 0| return 1; 559| 0| } 560| 2| } 561| | 562| | /* parse in the phonetic translation table */ 563| 608| if (line.compare(0, 5, "PHONE", 5) == 0) { ------------------ | Branch (563:9): [True: 2, False: 606] ------------------ 564| 2| if (!parse_phonetable(line, afflst)) { ------------------ | Branch (564:11): [True: 0, False: 2] ------------------ 565| 0| finishFileMgr(afflst); 566| 0| return 1; 567| 0| } 568| 2| } 569| | 570| | /* parse in the checkcompoundpattern table */ 571| 608| if (line.compare(0, 20, "CHECKCOMPOUNDPATTERN", 20) == 0) { ------------------ | Branch (571:9): [True: 2, False: 606] ------------------ 572| 2| if (!parse_checkcpdtable(line, afflst)) { ------------------ | Branch (572:11): [True: 0, False: 2] ------------------ 573| 0| finishFileMgr(afflst); 574| 0| return 1; 575| 0| } 576| 2| } 577| | 578| | /* parse in the defcompound table */ 579| 608| if (line.compare(0, 12, "COMPOUNDRULE", 12) == 0) { ------------------ | Branch (579:9): [True: 0, False: 608] ------------------ 580| 0| if (!parse_defcpdtable(line, afflst)) { ------------------ | Branch (580:11): [True: 0, False: 0] ------------------ 581| 0| finishFileMgr(afflst); 582| 0| return 1; 583| 0| } 584| 0| } 585| | 586| | /* parse in the related character map table */ 587| 608| if (line.compare(0, 3, "MAP", 3) == 0) { ------------------ | Branch (587:9): [True: 2, False: 606] ------------------ 588| 2| if (!parse_maptable(line, afflst)) { ------------------ | Branch (588:11): [True: 0, False: 2] ------------------ 589| 0| finishFileMgr(afflst); 590| 0| return 1; 591| 0| } 592| 2| } 593| | 594| | /* parse in the word breakpoints table */ 595| 608| if (line.compare(0, 5, "BREAK", 5) == 0) { ------------------ | Branch (595:9): [True: 4, False: 604] ------------------ 596| 4| if (!parse_breaktable(line, afflst)) { ------------------ | Branch (596:11): [True: 0, False: 4] ------------------ 597| 0| finishFileMgr(afflst); 598| 0| return 1; 599| 0| } 600| 4| } 601| | 602| | /* parse in the language for language specific codes */ 603| 608| if (line.compare(0, 4, "LANG", 4) == 0) { ------------------ | Branch (603:9): [True: 2, False: 606] ------------------ 604| 2| if (!parse_string(line, lang, afflst->getlinenum())) { ------------------ | Branch (604:11): [True: 0, False: 2] ------------------ 605| 0| finishFileMgr(afflst); 606| 0| return 1; 607| 0| } 608| 2| langnum = get_lang_num(lang); 609| 2| } 610| | 611| 608| if (line.compare(0, 7, "VERSION", 7) == 0) { ------------------ | Branch (611:9): [True: 0, False: 608] ------------------ 612| 0| size_t startpos = line.find_first_not_of(" \t", 7); 613| 0| if (startpos != std::string::npos) { ------------------ | Branch (613:11): [True: 0, False: 0] ------------------ 614| 0| version = line.substr(startpos); 615| 0| } 616| 0| } 617| | 618| 608| if (line.compare(0, 12, "MAXNGRAMSUGS", 12) == 0) { ------------------ | Branch (618:9): [True: 4, False: 604] ------------------ 619| 4| if (!parse_num(line, &maxngramsugs, afflst)) { ------------------ | Branch (619:11): [True: 0, False: 4] ------------------ 620| 0| finishFileMgr(afflst); 621| 0| return 1; 622| 0| } 623| 4| } 624| | 625| 608| if (line.compare(0, 11, "ONLYMAXDIFF", 11) == 0) ------------------ | Branch (625:9): [True: 0, False: 608] ------------------ 626| 0| onlymaxdiff = 1; 627| | 628| 608| if (line.compare(0, 7, "MAXDIFF", 7) == 0) { ------------------ | Branch (628:9): [True: 0, False: 608] ------------------ 629| 0| if (!parse_num(line, &maxdiff, afflst)) { ------------------ | Branch (629:11): [True: 0, False: 0] ------------------ 630| 0| finishFileMgr(afflst); 631| 0| return 1; 632| 0| } 633| 0| } 634| | 635| 608| if (line.compare(0, 10, "MAXCPDSUGS", 10) == 0) { ------------------ | Branch (635:9): [True: 0, False: 608] ------------------ 636| 0| if (!parse_num(line, &maxcpdsugs, afflst)) { ------------------ | Branch (636:11): [True: 0, False: 0] ------------------ 637| 0| finishFileMgr(afflst); 638| 0| return 1; 639| 0| } 640| 0| } 641| | 642| 608| if (line.compare(0, 11, "NOSPLITSUGS", 11) == 0) { ------------------ | Branch (642:9): [True: 0, False: 608] ------------------ 643| 0| nosplitsugs = 1; 644| 0| } 645| | 646| 608| if (line.compare(0, 9, "FULLSTRIP", 9) == 0) { ------------------ | Branch (646:9): [True: 0, False: 608] ------------------ 647| 0| fullstrip = 1; 648| 0| } 649| | 650| 608| if (line.compare(0, 12, "SUGSWITHDOTS", 12) == 0) { ------------------ | Branch (650:9): [True: 0, False: 608] ------------------ 651| 0| sugswithdots = 1; 652| 0| } 653| | 654| | /* parse in the flag used by forbidden words */ 655| 608| if (line.compare(0, 8, "KEEPCASE", 8) == 0) { ------------------ | Branch (655:9): [True: 2, False: 606] ------------------ 656| 2| if (!parse_flag(line, &keepcase, afflst)) { ------------------ | Branch (656:11): [True: 0, False: 2] ------------------ 657| 0| finishFileMgr(afflst); 658| 0| return 1; 659| 0| } 660| 2| } 661| | 662| | /* parse in the flag used by `forceucase' */ 663| 608| if (line.compare(0, 10, "FORCEUCASE", 10) == 0) { ------------------ | Branch (663:9): [True: 0, False: 608] ------------------ 664| 0| if (!parse_flag(line, &forceucase, afflst)) { ------------------ | Branch (664:11): [True: 0, False: 0] ------------------ 665| 0| finishFileMgr(afflst); 666| 0| return 1; 667| 0| } 668| 0| } 669| | 670| | /* parse in the flag used by `warn' */ 671| 608| if (line.compare(0, 4, "WARN", 4) == 0) { ------------------ | Branch (671:9): [True: 2, False: 606] ------------------ 672| 2| if (!parse_flag(line, &warn, afflst)) { ------------------ | Branch (672:11): [True: 0, False: 2] ------------------ 673| 0| finishFileMgr(afflst); 674| 0| return 1; 675| 0| } 676| 2| } 677| | 678| 608| if (line.compare(0, 10, "FORBIDWARN", 10) == 0) { ------------------ | Branch (678:9): [True: 0, False: 608] ------------------ 679| 0| forbidwarn = 1; 680| 0| } 681| | 682| | /* parse in the flag used by the affix generator */ 683| 608| if (line.compare(0, 11, "SUBSTANDARD", 11) == 0) { ------------------ | Branch (683:9): [True: 0, False: 608] ------------------ 684| 0| if (!parse_flag(line, &substandard, afflst)) { ------------------ | Branch (684:11): [True: 0, False: 0] ------------------ 685| 0| finishFileMgr(afflst); 686| 0| return 1; 687| 0| } 688| 0| } 689| | 690| 608| if (line.compare(0, 11, "CHECKSHARPS", 11) == 0) { ------------------ | Branch (690:9): [True: 0, False: 608] ------------------ 691| 0| checksharps = 1; 692| 0| } 693| | 694| | /* parse this affix: P - prefix, S - suffix */ 695| | // affix type 696| 608| char ft = ' '; 697| 608| if (line.compare(0, 3, "PFX", 3) == 0) ------------------ | Branch (697:9): [True: 12, False: 596] ------------------ 698| 12| ft = complexprefixes ? 'S' : 'P'; ------------------ | Branch (698:12): [True: 4, False: 8] ------------------ 699| 608| if (line.compare(0, 3, "SFX", 3) == 0) ------------------ | Branch (699:9): [True: 14, False: 594] ------------------ 700| 14| ft = complexprefixes ? 'P' : 'S'; ------------------ | Branch (700:12): [True: 0, False: 14] ------------------ 701| 608| if (ft != ' ') { ------------------ | Branch (701:9): [True: 26, False: 582] ------------------ 702| 26| if (dupflags_ini) { ------------------ | Branch (702:11): [True: 18, False: 8] ------------------ 703| 18| memset(dupflags, 0, sizeof(dupflags)); 704| 18| dupflags_ini = 0; 705| 18| } 706| 26| if (!parse_affix(line, ft, afflst, dupflags)) { ------------------ | Branch (706:11): [True: 0, False: 26] ------------------ 707| 0| finishFileMgr(afflst); 708| 0| return 1; 709| 0| } 710| 26| } 711| 608| } 712| | 713| 38| finishFileMgr(afflst); 714| | // affix trees are sorted now 715| | 716| | // now we can speed up performance greatly taking advantage of the 717| | // relationship between the affixes and the idea of "subsets". 718| | 719| | // View each prefix as a potential leading subset of another and view 720| | // each suffix (reversed) as a potential trailing subset of another. 721| | 722| | // To illustrate this relationship if we know the prefix "ab" is found in the 723| | // word to examine, only prefixes that "ab" is a leading subset of need be 724| | // examined. 725| | // Furthermore is "ab" is not present then none of the prefixes that "ab" is 726| | // is a subset need be examined. 727| | // The same argument goes for suffix string that are reversed. 728| | 729| | // Then to top this off why not examine the first char of the word to quickly 730| | // limit the set of prefixes to examine (i.e. the prefixes to examine must 731| | // be leading supersets of the first character of the word (if they exist) 732| | 733| | // To take advantage of this "subset" relationship, we need to add two links 734| | // from entry. One to take next if the current prefix is found (call it 735| | // nexteq) 736| | // and one to take next if the current prefix is not found (call it nextne). 737| | 738| | // Since we have built ordered lists, all that remains is to properly 739| | // initialize 740| | // the nextne and nexteq pointers that relate them 741| | 742| 38| process_pfx_order(); 743| 38| process_sfx_order(); 744| | 745| 38| return 0; 746| 38|} _ZN8AffixMgr13build_pfxtreeEP8PfxEntry: 752| 8|int AffixMgr::build_pfxtree(PfxEntry* pfxptr) { 753| 8| PfxEntry* ptr; 754| 8| PfxEntry* pptr; 755| 8| PfxEntry* ep = pfxptr; 756| | 757| | // get the right starting points 758| 8| const char* key = ep->getKey(); 759| 8| const auto flg = (unsigned char)(ep->getFlag() & 0x00FF); 760| | 761| | // first index by flag which must exist 762| 8| ptr = pFlag[flg]; 763| 8| ep->setFlgNxt(ptr); 764| 8| pFlag[flg] = ep; 765| | 766| | // handle the special case of null affix string 767| 8| if (*key == '\0') { ------------------ | Branch (767:7): [True: 2, False: 6] ------------------ 768| | // always inset them at head of list at element 0 769| 2| ptr = pStart[0]; 770| 2| ep->setNext(ptr); 771| 2| pStart[0] = ep; 772| 2| return 0; 773| 2| } 774| | 775| | // now handle the normal case 776| 6| ep->setNextEQ(nullptr); 777| 6| ep->setNextNE(nullptr); 778| | 779| 6| unsigned char sp = *((const unsigned char*)key); 780| 6| ptr = pStart[sp]; 781| | 782| | // handle the first insert 783| 6| if (!ptr) { ------------------ | Branch (783:7): [True: 4, False: 2] ------------------ 784| 4| pStart[sp] = ep; 785| 4| return 0; 786| 4| } 787| | 788| | // otherwise use binary tree insertion so that a sorted 789| | // list can easily be generated later 790| 2| pptr = nullptr; 791| 2| for (;;) { 792| 2| pptr = ptr; 793| 2| if (strcmp(ep->getKey(), ptr->getKey()) <= 0) { ------------------ | Branch (793:9): [True: 0, False: 2] ------------------ 794| 0| ptr = ptr->getNextEQ(); 795| 0| if (!ptr) { ------------------ | Branch (795:11): [True: 0, False: 0] ------------------ 796| 0| pptr->setNextEQ(ep); 797| 0| break; 798| 0| } 799| 2| } else { 800| 2| ptr = ptr->getNextNE(); 801| 2| if (!ptr) { ------------------ | Branch (801:11): [True: 2, False: 0] ------------------ 802| 2| pptr->setNextNE(ep); 803| 2| break; 804| 2| } 805| 2| } 806| 2| } 807| 2| return 0; 808| 6|} _ZN8AffixMgr13build_sfxtreeEP8SfxEntry: 813| 34|int AffixMgr::build_sfxtree(SfxEntry* sfxptr) { 814| | 815| 34| sfxptr->initReverseWord(); 816| | 817| 34| SfxEntry* ptr; 818| 34| SfxEntry* pptr; 819| 34| SfxEntry* ep = sfxptr; 820| | 821| | /* get the right starting point */ 822| 34| const char* key = ep->getKey(); 823| 34| const auto flg = (unsigned char)(ep->getFlag() & 0x00FF); 824| | 825| | // first index by flag which must exist 826| 34| ptr = sFlag[flg]; 827| 34| ep->setFlgNxt(ptr); 828| 34| sFlag[flg] = ep; 829| | 830| | // next index by affix string 831| | 832| | // handle the special case of null affix string 833| 34| if (*key == '\0') { ------------------ | Branch (833:7): [True: 0, False: 34] ------------------ 834| | // always inset them at head of list at element 0 835| 0| ptr = sStart[0]; 836| 0| ep->setNext(ptr); 837| 0| sStart[0] = ep; 838| 0| return 0; 839| 0| } 840| | 841| | // now handle the normal case 842| 34| ep->setNextEQ(nullptr); 843| 34| ep->setNextNE(nullptr); 844| | 845| 34| unsigned char sp = *((const unsigned char*)key); 846| 34| ptr = sStart[sp]; 847| | 848| | // handle the first insert 849| 34| if (!ptr) { ------------------ | Branch (849:7): [True: 22, False: 12] ------------------ 850| 22| sStart[sp] = ep; 851| 22| return 0; 852| 22| } 853| | 854| | // otherwise use binary tree insertion so that a sorted 855| | // list can easily be generated later 856| 12| pptr = nullptr; 857| 20| for (;;) { 858| 20| pptr = ptr; 859| 20| if (strcmp(ep->getKey(), ptr->getKey()) <= 0) { ------------------ | Branch (859:9): [True: 18, False: 2] ------------------ 860| 18| ptr = ptr->getNextEQ(); 861| 18| if (!ptr) { ------------------ | Branch (861:11): [True: 10, False: 8] ------------------ 862| 10| pptr->setNextEQ(ep); 863| 10| break; 864| 10| } 865| 18| } else { 866| 2| ptr = ptr->getNextNE(); 867| 2| if (!ptr) { ------------------ | Branch (867:11): [True: 2, False: 0] ------------------ 868| 2| pptr->setNextNE(ep); 869| 2| break; 870| 2| } 871| 2| } 872| 20| } 873| 12| return 0; 874| 34|} _ZN8AffixMgr24process_pfx_tree_to_listEv: 877| 38|int AffixMgr::process_pfx_tree_to_list() { 878| 9.72k| for (int i = 1; i < SETSIZE; i++) { ------------------ | | 61| 9.72k|#define SETSIZE 256 ------------------ | Branch (878:19): [True: 9.69k, False: 38] ------------------ 879| 9.69k| pStart[i] = process_pfx_in_order(pStart[i], nullptr); 880| 9.69k| } 881| 38| return 0; 882| 38|} _ZN8AffixMgr20process_pfx_in_orderEP8PfxEntryS1_: 884| 9.70k|PfxEntry* AffixMgr::process_pfx_in_order(PfxEntry* ptr, PfxEntry* nptr) { 885| 9.70k| if (ptr) { ------------------ | Branch (885:7): [True: 6, False: 9.69k] ------------------ 886| 6| nptr = process_pfx_in_order(ptr->getNextNE(), nptr); 887| 6| ptr->setNext(nptr); 888| 6| nptr = process_pfx_in_order(ptr->getNextEQ(), ptr); 889| 6| } 890| 9.70k| return nptr; 891| 9.70k|} _ZN8AffixMgr24process_sfx_tree_to_listEv: 894| 38|int AffixMgr::process_sfx_tree_to_list() { 895| 9.72k| for (int i = 1; i < SETSIZE; i++) { ------------------ | | 61| 9.72k|#define SETSIZE 256 ------------------ | Branch (895:19): [True: 9.69k, False: 38] ------------------ 896| 9.69k| sStart[i] = process_sfx_in_order(sStart[i], nullptr); 897| 9.69k| } 898| 38| return 0; 899| 38|} _ZN8AffixMgr20process_sfx_in_orderEP8SfxEntryS1_: 901| 9.75k|SfxEntry* AffixMgr::process_sfx_in_order(SfxEntry* ptr, SfxEntry* nptr) { 902| 9.75k| if (ptr) { ------------------ | Branch (902:7): [True: 34, False: 9.72k] ------------------ 903| 34| nptr = process_sfx_in_order(ptr->getNextNE(), nptr); 904| 34| ptr->setNext(nptr); 905| 34| nptr = process_sfx_in_order(ptr->getNextEQ(), ptr); 906| 34| } 907| 9.75k| return nptr; 908| 9.75k|} _ZN8AffixMgr17process_pfx_orderEv: 912| 38|int AffixMgr::process_pfx_order() { 913| 38| PfxEntry* ptr; 914| | 915| | // loop through each prefix list starting point 916| 9.72k| for (int i = 1; i < SETSIZE; i++) { ------------------ | | 61| 9.72k|#define SETSIZE 256 ------------------ | Branch (916:19): [True: 9.69k, False: 38] ------------------ 917| 9.69k| ptr = pStart[i]; 918| | 919| | // look through the remainder of the list 920| | // and find next entry with affix that 921| | // the current one is not a subset of 922| | // mark that as destination for NextNE 923| | // use next in list that you are a subset 924| | // of as NextEQ 925| | 926| 9.69k| for (; ptr != nullptr; ptr = ptr->getNext()) { ------------------ | Branch (926:12): [True: 6, False: 9.69k] ------------------ 927| 6| PfxEntry* nptr = ptr->getNext(); 928| 8| for (; nptr != nullptr; nptr = nptr->getNext()) { ------------------ | Branch (928:14): [True: 2, False: 6] ------------------ 929| 2| if (!isSubset(ptr->getKey(), nptr->getKey())) ------------------ | Branch (929:13): [True: 0, False: 2] ------------------ 930| 0| break; 931| 2| } 932| 6| ptr->setNextNE(nptr); 933| 6| ptr->setNextEQ(nullptr); 934| 6| if ((ptr->getNext()) && ------------------ | Branch (934:11): [True: 2, False: 4] ------------------ 935| 2| isSubset(ptr->getKey(), (ptr->getNext())->getKey())) ------------------ | Branch (935:11): [True: 2, False: 0] ------------------ 936| 2| ptr->setNextEQ(ptr->getNext()); 937| 6| } 938| | 939| | // now clean up by adding smart search termination strings: 940| | // if you are already a superset of the previous prefix 941| | // but not a subset of the next, search can end here 942| | // so set NextNE properly 943| | 944| 9.69k| ptr = pStart[i]; 945| 9.69k| for (; ptr != nullptr; ptr = ptr->getNext()) { ------------------ | Branch (945:12): [True: 6, False: 9.69k] ------------------ 946| 6| PfxEntry* nptr = ptr->getNext(); 947| 6| PfxEntry* mptr = nullptr; 948| 8| for (; nptr != nullptr; nptr = nptr->getNext()) { ------------------ | Branch (948:14): [True: 2, False: 6] ------------------ 949| 2| if (!isSubset(ptr->getKey(), nptr->getKey())) ------------------ | Branch (949:13): [True: 0, False: 2] ------------------ 950| 0| break; 951| 2| mptr = nptr; 952| 2| } 953| 6| if (mptr) ------------------ | Branch (953:11): [True: 2, False: 4] ------------------ 954| 2| mptr->setNextNE(nullptr); 955| 6| } 956| 9.69k| } 957| 38| return 0; 958| 38|} _ZN8AffixMgr17process_sfx_orderEv: 962| 38|int AffixMgr::process_sfx_order() { 963| 38| SfxEntry* ptr; 964| | 965| | // loop through each prefix list starting point 966| 9.72k| for (int i = 1; i < SETSIZE; i++) { ------------------ | | 61| 9.72k|#define SETSIZE 256 ------------------ | Branch (966:19): [True: 9.69k, False: 38] ------------------ 967| 9.69k| ptr = sStart[i]; 968| | 969| | // look through the remainder of the list 970| | // and find next entry with affix that 971| | // the current one is not a subset of 972| | // mark that as destination for NextNE 973| | // use next in list that you are a subset 974| | // of as NextEQ 975| | 976| 9.72k| for (; ptr != nullptr; ptr = ptr->getNext()) { ------------------ | Branch (976:12): [True: 34, False: 9.69k] ------------------ 977| 34| SfxEntry* nptr = ptr->getNext(); 978| 52| for (; nptr != nullptr; nptr = nptr->getNext()) { ------------------ | Branch (978:14): [True: 20, False: 32] ------------------ 979| 20| if (!isSubset(ptr->getKey(), nptr->getKey())) ------------------ | Branch (979:13): [True: 2, False: 18] ------------------ 980| 2| break; 981| 20| } 982| 34| ptr->setNextNE(nptr); 983| 34| ptr->setNextEQ(nullptr); 984| 34| if ((ptr->getNext()) && ------------------ | Branch (984:11): [True: 12, False: 22] ------------------ 985| 12| isSubset(ptr->getKey(), (ptr->getNext())->getKey())) ------------------ | Branch (985:11): [True: 10, False: 2] ------------------ 986| 10| ptr->setNextEQ(ptr->getNext()); 987| 34| } 988| | 989| | // now clean up by adding smart search termination strings: 990| | // if you are already a superset of the previous suffix 991| | // but not a subset of the next, search can end here 992| | // so set NextNE properly 993| | 994| 9.69k| ptr = sStart[i]; 995| 9.72k| for (; ptr != nullptr; ptr = ptr->getNext()) { ------------------ | Branch (995:12): [True: 34, False: 9.69k] ------------------ 996| 34| SfxEntry* nptr = ptr->getNext(); 997| 34| SfxEntry* mptr = nullptr; 998| 52| for (; nptr != nullptr; nptr = nptr->getNext()) { ------------------ | Branch (998:14): [True: 20, False: 32] ------------------ 999| 20| if (!isSubset(ptr->getKey(), nptr->getKey())) ------------------ | Branch (999:13): [True: 2, False: 18] ------------------ 1000| 2| break; 1001| 18| mptr = nptr; 1002| 18| } 1003| 34| if (mptr) ------------------ | Branch (1003:11): [True: 10, False: 24] ------------------ 1004| 10| mptr->setNextNE(nullptr); 1005| 34| } 1006| 9.69k| } 1007| 38| return 0; 1008| 38|} _ZN8AffixMgr7condlenERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1021| 8|int AffixMgr::condlen(const std::string& s) { 1022| 8| int l = 0; 1023| 8| bool group = false; 1024| 8| size_t i = 0; 1025| 42| while (i < s.size()) { ------------------ | Branch (1025:10): [True: 34, False: 8] ------------------ 1026| 34| if (s[i] == '[') { ------------------ | Branch (1026:9): [True: 4, False: 30] ------------------ 1027| 4| group = true; 1028| 4| ++l; 1029| 4| ++i; 1030| 30| } else if (s[i] == ']') { ------------------ | Branch (1030:16): [True: 4, False: 26] ------------------ 1031| 4| group = false; 1032| 4| ++i; 1033| 26| } else if (group) { ------------------ | Branch (1033:16): [True: 18, False: 8] ------------------ 1034| 18| ++i; 1035| 18| } else { 1036| 8| ++l; 1037| 8| i = utf8 ? utf8_next(s, i) : i + 1; ------------------ | Branch (1037:11): [True: 8, False: 0] ------------------ 1038| 8| } 1039| 34| } 1040| 8| return l; 1041| 8|} _ZN8AffixMgr8encodeitER8AffEntryRKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEE: 1043| 42|int AffixMgr::encodeit(AffEntry& entry, const std::string& cs) { 1044| 42| if (cs.compare(".") != 0) { ------------------ | Branch (1044:7): [True: 8, False: 34] ------------------ 1045| 8| entry.numconds = (char)condlen(cs); 1046| 8| const size_t cslen = cs.size(); 1047| 8| const size_t short_part = std::min(MAXCONDLEN, cslen); ------------------ | | 90| 8|#define MAXCONDLEN 20 ------------------ 1048| 8| memcpy(entry.c.conds, cs.data(), short_part); 1049| 8| if (short_part < MAXCONDLEN) { ------------------ | | 90| 8|#define MAXCONDLEN 20 ------------------ | Branch (1049:9): [True: 8, False: 0] ------------------ 1050| | //blank out the remaining space 1051| 8| memset(entry.c.conds + short_part, 0, MAXCONDLEN - short_part); ------------------ | | 90| 8|#define MAXCONDLEN 20 ------------------ 1052| 8| } else if (cs[MAXCONDLEN]) { ------------------ | | 90| 0|#define MAXCONDLEN 20 ------------------ | Branch (1052:16): [True: 0, False: 0] ------------------ 1053| | //there is more conditions than fit in fixed space, so its 1054| | //a long condition 1055| 0| entry.opts |= aeLONGCOND; ------------------ | | 69| 0|#define aeLONGCOND (1 << 4) ------------------ 1056| 0| size_t remaining = cs.size() - MAXCONDLEN_1; ------------------ | | 91| 0|#define MAXCONDLEN_1 (MAXCONDLEN - sizeof(char*)) | | ------------------ | | | | 90| 0|#define MAXCONDLEN 20 | | ------------------ ------------------ 1057| 0| entry.c.l.conds2 = new char[1 + remaining]; 1058| 0| memcpy(entry.c.l.conds2, cs.data() + MAXCONDLEN_1, remaining); ------------------ | | 91| 0|#define MAXCONDLEN_1 (MAXCONDLEN - sizeof(char*)) | | ------------------ | | | | 90| 0|#define MAXCONDLEN 20 | | ------------------ ------------------ 1059| 0| entry.c.l.conds2[remaining] = 0; 1060| 0| } 1061| 34| } else { 1062| 34| entry.numconds = 0; 1063| 34| entry.c.conds[0] = '\0'; 1064| 34| } 1065| 42| return 0; 1066| 42|} _ZN8AffixMgr12prefix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratcht: 1083| 603M| const FLAG needflag) { 1084| 603M| struct hentry* rv = nullptr; 1085| | 1086| 603M| pfx = nullptr; 1087| 603M| pfxappnd = nullptr; 1088| 603M| sfxappnd = nullptr; 1089| 603M| sfxextra = 0; 1090| | 1091| | // first handle the special case of 0 length prefixes 1092| 603M| PfxEntry* pe = pStart[0]; 1093| 604M| while (pe) { ------------------ | Branch (1093:10): [True: 1.39M, False: 603M] ------------------ 1094| 1.39M| if ( 1095| | // fogemorpheme 1096| 1.39M| ((in_compound != IN_CPD_NOT) || ------------------ | | 72| 1.39M|#define IN_CPD_NOT 0 ------------------ | Branch (1096:10): [True: 0, False: 1.39M] ------------------ 1097| 1.39M| !(pe->getCont() && ------------------ | Branch (1097:12): [True: 1.39M, False: 0] ------------------ 1098| 1.39M| (TESTAFF(pe->getCont(), onlyincompound, pe->getContLen())))) && ------------------ | | 99| 1.39M|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1098:12): [True: 0, False: 1.39M] ------------------ 1099| | // permit prefixes in compounds 1100| 1.39M| ((in_compound != IN_CPD_END) || ------------------ | | 74| 1.39M|#define IN_CPD_END 2 ------------------ | Branch (1100:10): [True: 1.39M, False: 0] ------------------ 1101| 0| (pe->getCont() && ------------------ | Branch (1101:11): [True: 0, False: 0] ------------------ 1102| 1.39M| (TESTAFF(pe->getCont(), compoundpermitflag, pe->getContLen()))))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1102:11): [True: 0, False: 0] ------------------ 1103| | // check prefix 1104| 1.39M| rv = pe->checkword(word, start, len, in_compound, needflag, scratch); 1105| 1.39M| if (rv) { ------------------ | Branch (1105:11): [True: 0, False: 1.39M] ------------------ 1106| 0| pfx = pe; // BUG: pfx not stateless 1107| 0| return rv; 1108| 0| } 1109| 1.39M| } 1110| 1.39M| pe = pe->getNext(); 1111| 1.39M| } 1112| | 1113| | // now handle the general case 1114| 603M| unsigned char sp = word[start]; 1115| 603M| PfxEntry* pptr = pStart[sp]; 1116| | 1117| 603M| while (pptr) { ------------------ | Branch (1117:10): [True: 34.9k, False: 603M] ------------------ 1118| 34.9k| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1118:9): [True: 26.1k, False: 8.76k] ------------------ 1119| 26.1k| if ( 1120| | // fogemorpheme 1121| 26.1k| ((in_compound != IN_CPD_NOT) || ------------------ | | 72| 26.1k|#define IN_CPD_NOT 0 ------------------ | Branch (1121:12): [True: 0, False: 26.1k] ------------------ 1122| 26.1k| !(pptr->getCont() && ------------------ | Branch (1122:14): [True: 23.3k, False: 2.89k] ------------------ 1123| 23.3k| (TESTAFF(pptr->getCont(), onlyincompound, pptr->getContLen())))) && ------------------ | | 99| 23.3k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1123:14): [True: 0, False: 23.3k] ------------------ 1124| | // permit prefixes in compounds 1125| 26.1k| ((in_compound != IN_CPD_END) || ------------------ | | 74| 26.1k|#define IN_CPD_END 2 ------------------ | Branch (1125:12): [True: 26.1k, False: 0] ------------------ 1126| 0| (pptr->getCont() && (TESTAFF(pptr->getCont(), compoundpermitflag, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1126:13): [True: 0, False: 0] | Branch (1126:32): [True: 0, False: 0] ------------------ 1127| 26.1k| pptr->getContLen()))))) { 1128| | // check prefix 1129| 26.1k| rv = pptr->checkword(word, start, len, in_compound, needflag, scratch); 1130| 26.1k| if (rv) { ------------------ | Branch (1130:13): [True: 0, False: 26.1k] ------------------ 1131| 0| pfx = pptr; // BUG: pfx not stateless 1132| 0| return rv; 1133| 0| } 1134| 26.1k| } 1135| 26.1k| pptr = pptr->getNextEQ(); 1136| 26.1k| } else { 1137| 8.76k| pptr = pptr->getNextNE(); 1138| 8.76k| } 1139| 34.9k| } 1140| | 1141| 603M| return nullptr; 1142| 603M|} _ZN8AffixMgr19prefix_check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratcht: 1150| 16.2M| const FLAG needflag) { 1151| 16.2M| struct hentry* rv = nullptr; 1152| | 1153| 16.2M| pfx = nullptr; 1154| 16.2M| sfxappnd = nullptr; 1155| 16.2M| sfxextra = 0; 1156| | 1157| | // first handle the special case of 0 length prefixes 1158| 16.2M| PfxEntry* pe = pStart[0]; 1159| | 1160| 17.6M| while (pe) { ------------------ | Branch (1160:10): [True: 1.39M, False: 16.2M] ------------------ 1161| 1.39M| rv = pe->check_twosfx(word, start, len, in_compound, needflag, scratch); 1162| 1.39M| if (rv) ------------------ | Branch (1162:9): [True: 0, False: 1.39M] ------------------ 1163| 0| return rv; 1164| 1.39M| pe = pe->getNext(); 1165| 1.39M| } 1166| | 1167| | // now handle the general case 1168| 16.2M| unsigned char sp = word[start]; 1169| 16.2M| PfxEntry* pptr = pStart[sp]; 1170| | 1171| 16.2M| while (pptr) { ------------------ | Branch (1171:10): [True: 32.0k, False: 16.2M] ------------------ 1172| 32.0k| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1172:9): [True: 23.3k, False: 8.76k] ------------------ 1173| 23.3k| rv = pptr->check_twosfx(word, start, len, in_compound, needflag, scratch); 1174| 23.3k| if (rv) { ------------------ | Branch (1174:11): [True: 0, False: 23.3k] ------------------ 1175| 0| pfx = pptr; 1176| 0| return rv; 1177| 0| } 1178| 23.3k| pptr = pptr->getNextEQ(); 1179| 23.3k| } else { 1180| 8.76k| pptr = pptr->getNextNE(); 1181| 8.76k| } 1182| 32.0k| } 1183| | 1184| 16.2M| return nullptr; 1185| 16.2M|} _ZN8AffixMgr18prefix_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratcht: 1193| 13.6k| const FLAG needflag) { 1194| | 1195| 13.6k| std::string result; 1196| | 1197| 13.6k| pfx = nullptr; 1198| 13.6k| sfxappnd = nullptr; 1199| 13.6k| sfxextra = 0; 1200| | 1201| | // first handle the special case of 0 length prefixes 1202| 13.6k| PfxEntry* pe = pStart[0]; 1203| 14.3k| while (pe) { ------------------ | Branch (1203:10): [True: 719, False: 13.6k] ------------------ 1204| 719| std::string st = pe->check_morph(word, start, len, in_compound, needflag, scratch); 1205| 719| if (!st.empty()) { ------------------ | Branch (1205:9): [True: 0, False: 719] ------------------ 1206| 0| result.append(st); 1207| 0| } 1208| 719| pe = pe->getNext(); 1209| 719| } 1210| | 1211| | // now handle the general case 1212| 13.6k| unsigned char sp = word[start]; 1213| 13.6k| PfxEntry* pptr = pStart[sp]; 1214| | 1215| 13.6k| while (pptr) { ------------------ | Branch (1215:10): [True: 2, False: 13.6k] ------------------ 1216| 2| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1216:9): [True: 0, False: 2] ------------------ 1217| 0| std::string st = pptr->check_morph(word, start, len, in_compound, needflag, scratch); 1218| 0| if (!st.empty()) { ------------------ | Branch (1218:11): [True: 0, False: 0] ------------------ 1219| | // fogemorpheme 1220| 0| if ((in_compound != IN_CPD_NOT) || ------------------ | | 72| 0|#define IN_CPD_NOT 0 ------------------ | Branch (1220:13): [True: 0, False: 0] ------------------ 1221| 0| !((pptr->getCont() && (TESTAFF(pptr->getCont(), onlyincompound, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1221:16): [True: 0, False: 0] | Branch (1221:35): [True: 0, False: 0] ------------------ 1222| 0| pptr->getContLen()))))) { 1223| 0| result.append(st); 1224| 0| pfx = pptr; 1225| 0| } 1226| 0| } 1227| 0| pptr = pptr->getNextEQ(); 1228| 2| } else { 1229| 2| pptr = pptr->getNextNE(); 1230| 2| } 1231| 2| } 1232| | 1233| 13.6k| return result; 1234| 13.6k|} _ZN8AffixMgr25prefix_check_twosfx_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratcht: 1242| 4.24k| const FLAG needflag) { 1243| 4.24k| std::string result; 1244| | 1245| 4.24k| pfx = nullptr; 1246| 4.24k| sfxappnd = nullptr; 1247| 4.24k| sfxextra = 0; 1248| | 1249| | // first handle the special case of 0 length prefixes 1250| 4.24k| PfxEntry* pe = pStart[0]; 1251| 4.96k| while (pe) { ------------------ | Branch (1251:10): [True: 719, False: 4.24k] ------------------ 1252| 719| std::string st = pe->check_twosfx_morph(word, start, len, in_compound, needflag, scratch); 1253| 719| if (!st.empty()) { ------------------ | Branch (1253:9): [True: 0, False: 719] ------------------ 1254| 0| result.append(st); 1255| 0| } 1256| 719| pe = pe->getNext(); 1257| 719| } 1258| | 1259| | // now handle the general case 1260| 4.24k| unsigned char sp = word[start]; 1261| 4.24k| PfxEntry* pptr = pStart[sp]; 1262| | 1263| 4.25k| while (pptr) { ------------------ | Branch (1263:10): [True: 2, False: 4.24k] ------------------ 1264| 2| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1264:9): [True: 0, False: 2] ------------------ 1265| 0| std::string st = pptr->check_twosfx_morph(word, start, len, in_compound, needflag, scratch); 1266| 0| if (!st.empty()) { ------------------ | Branch (1266:11): [True: 0, False: 0] ------------------ 1267| 0| result.append(st); 1268| 0| pfx = pptr; 1269| 0| } 1270| 0| pptr = pptr->getNextEQ(); 1271| 2| } else { 1272| 2| pptr = pptr->getNextNE(); 1273| 2| } 1274| 2| } 1275| | 1276| 4.24k| return result; 1277| 4.24k|} _ZN8AffixMgr12get_syllableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1553| 388|short AffixMgr::get_syllable(const std::string& word) { 1554| 388| if (cpdmaxsyllable == 0) ------------------ | Branch (1554:7): [True: 0, False: 388] ------------------ 1555| 0| return 0; 1556| | 1557| 388| short num = 0; 1558| | 1559| 388| if (!utf8) { ------------------ | Branch (1559:7): [True: 0, False: 388] ------------------ 1560| 0| num = (short)std::count_if(word.begin(), word.end(), 1561| 0| [&](char c) { 1562| 0| return std::binary_search(cpdvowels.begin(), cpdvowels.end(), c); 1563| 0| }); 1564| 388| } else if (!cpdvowels_utf16.empty()) { ------------------ | Branch (1564:14): [True: 388, False: 0] ------------------ 1565| 388| std::vector w; 1566| 388| u8_u16(w, word); 1567| 388| num = (short)std::count_if(w.begin(), w.end(), 1568| 388| [&](w_char wc) { 1569| 388| return std::binary_search(cpdvowels_utf16.begin(), cpdvowels_utf16.end(), wc); 1570| 388| }); 1571| 388| } 1572| | 1573| 388| return num; 1574| 388|} _ZN8AffixMgr10setcminmaxEPmS0_PKcm: 1576| 21.9M|void AffixMgr::setcminmax(size_t* cmin, size_t* cmax, const char* word, size_t len) { 1577| 21.9M| if (utf8) { ------------------ | Branch (1577:7): [True: 1.70M, False: 20.2M] ------------------ 1578| 1.70M| int i; 1579| 5.10M| for (*cmin = 0, i = 0; (i < cpdmin) && *cmin < len; i++) { ------------------ | Branch (1579:28): [True: 3.41M, False: 1.68M] | Branch (1579:44): [True: 3.39M, False: 24.4k] ------------------ 1580| 3.86M| for ((*cmin)++; *cmin < len && is_utf8_cont(word[*cmin]); (*cmin)++) ------------------ | Branch (1580:23): [True: 3.82M, False: 42.5k] | Branch (1580:38): [True: 473k, False: 3.34M] ------------------ 1581| 473k| ; 1582| 3.39M| } 1583| 3.41M| for (*cmax = len, i = 0; (i < (cpdmin - 1)) && *cmax > 0; i++) { ------------------ | Branch (1583:30): [True: 1.70M, False: 1.70M] | Branch (1583:52): [True: 1.70M, False: 2.82k] ------------------ 1584| 2.86M| for ((*cmax)--; *cmax > 0 && is_utf8_cont(word[*cmax]); (*cmax)--) ------------------ | Branch (1584:23): [True: 2.84M, False: 21.6k] | Branch (1584:36): [True: 1.15M, False: 1.68M] ------------------ 1585| 1.15M| ; 1586| 1.70M| } 1587| 20.2M| } else { 1588| 20.2M| *cmin = cpdmin; 1589| 20.2M| *cmax = len - cpdmin + 1; 1590| 20.2M| } 1591| 21.9M|} _ZN8AffixMgr14compound_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEssssPP6hentrySB_ccPiR12AffixScratch: 1605| 21.9M| AffixScratch& scratch) { 1606| 21.9M| short oldnumsyllable, oldnumsyllable2, oldwordnum, oldwordnum2; 1607| 21.9M| hentry *rv = nullptr, *rv_first; 1608| 21.9M| std::string st; 1609| 21.9M| char ch = '\0', affixed; 1610| 21.9M| size_t cmin, cmax; 1611| 21.9M| int striple = 0, soldi = 0, oldcmin = 0, oldcmax = 0, oldlen = 0, checkedstriple = 0; 1612| 21.9M| hentry** oldwords = words; 1613| 21.9M| size_t scpd = 0, len = word.size(); 1614| | 1615| | // protect subsequent words[wnum + 1] reads and any recursion 1616| 21.9M| if (wnum + 1 >= maxwordnum) ------------------ | Branch (1616:7): [True: 0, False: 21.9M] ------------------ 1617| 0| return nullptr; 1618| | 1619| 21.9M| int checked_prefix; 1620| | 1621| | // add a time limit to handle possible 1622| | // combinatorical explosion of the overlapping words 1623| | 1624| 21.9M| HUNSPELL_THREAD_LOCAL std::chrono::steady_clock::time_point clock_time_start; ------------------ | | 60| 21.9M|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 1625| 21.9M| HUNSPELL_THREAD_LOCAL bool timelimit_exceeded; ------------------ | | 60| 21.9M|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 1626| | 1627| | // get the current time 1628| 21.9M| std::chrono::steady_clock::time_point clock_now = std::chrono::steady_clock::now(); 1629| | 1630| 21.9M| if (wnum == 0) { ------------------ | Branch (1630:7): [True: 21.9M, False: 120] ------------------ 1631| | // set the start time 1632| 21.9M| clock_time_start = clock_now; 1633| 21.9M| timelimit_exceeded = false; 1634| 21.9M| } 1635| 120| else if (clock_now - clock_time_start > TIMELIMIT_MS) ------------------ | | 106| 120|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (1635:12): [True: 0, False: 120] ------------------ 1636| 0| timelimit_exceeded = true; 1637| | 1638| 21.9M| setcminmax(&cmin, &cmax, word.c_str(), len); 1639| | 1640| 21.9M| st.assign(word); 1641| | 1642| 579M| for (size_t i = cmin; i < cmax; ++i) { ------------------ | Branch (1642:25): [True: 558M, False: 21.1M] ------------------ 1643| | // go to end of the UTF-8 character 1644| 558M| if (utf8) { ------------------ | Branch (1644:9): [True: 39.3M, False: 518M] ------------------ 1645| 49.1M| for (; is_utf8_cont(st[i]); i++) ------------------ | Branch (1645:14): [True: 9.77M, False: 39.3M] ------------------ 1646| 9.77M| ; 1647| 39.3M| if (i >= cmax) ------------------ | Branch (1647:11): [True: 187k, False: 39.1M] ------------------ 1648| 187k| return nullptr; 1649| 39.3M| } 1650| | 1651| 557M| words = oldwords; 1652| 557M| int onlycpdrule = (words) ? 1 : 0; ------------------ | Branch (1652:23): [True: 0, False: 557M] ------------------ 1653| | 1654| 557M| do { // onlycpdrule loop 1655| | 1656| 557M| oldnumsyllable = numsyllable; 1657| 557M| oldwordnum = wordnum; 1658| 557M| checked_prefix = 0; 1659| | 1660| 557M| do { // simplified checkcompoundpattern loop 1661| | 1662| 557M| if (timelimit_exceeded || ------------------ | Branch (1662:13): [True: 0, False: 557M] | Branch (1662:13): [True: 0, False: 557M] ------------------ 1663| 557M| std::chrono::steady_clock::now() - clock_time_start > TIMELIMIT_MS) { ------------------ | | 106| 557M|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (1663:13): [True: 0, False: 557M] ------------------ 1664| 0| timelimit_exceeded = true; 1665| 0| return nullptr; 1666| 0| } 1667| | 1668| 557M| if (scpd > 0) { ------------------ | Branch (1668:13): [True: 0, False: 557M] ------------------ 1669| 0| for (; scpd <= checkcpdtable.size() && ------------------ | Branch (1669:18): [True: 0, False: 0] ------------------ 1670| 0| (checkcpdtable[scpd - 1].pattern3.empty() || ------------------ | Branch (1670:19): [True: 0, False: 0] ------------------ 1671| 0| i > word.size() || ------------------ | Branch (1671:19): [True: 0, False: 0] ------------------ 1672| 0| word.compare(i, checkcpdtable[scpd - 1].pattern3.size(), checkcpdtable[scpd - 1].pattern3) != 0); ------------------ | Branch (1672:19): [True: 0, False: 0] ------------------ 1673| 0| scpd++) 1674| 0| ; 1675| | 1676| 0| if (scpd > checkcpdtable.size()) ------------------ | Branch (1676:15): [True: 0, False: 0] ------------------ 1677| 0| break; // break simplified checkcompoundpattern loop 1678| 0| st.replace(i, std::string::npos, checkcpdtable[scpd - 1].pattern); 1679| 0| soldi = i; 1680| 0| i += checkcpdtable[scpd - 1].pattern.size(); 1681| 0| st.replace(i, std::string::npos, checkcpdtable[scpd - 1].pattern2); 1682| 0| st.replace(i + checkcpdtable[scpd - 1].pattern2.size(), std::string::npos, 1683| 0| word.substr(soldi + checkcpdtable[scpd - 1].pattern3.size())); 1684| | 1685| 0| oldlen = len; 1686| 0| len += checkcpdtable[scpd - 1].pattern.size() + 1687| 0| checkcpdtable[scpd - 1].pattern2.size() - 1688| 0| checkcpdtable[scpd - 1].pattern3.size(); 1689| 0| oldcmin = cmin; 1690| 0| oldcmax = cmax; 1691| 0| setcminmax(&cmin, &cmax, st.c_str(), len); 1692| | 1693| 0| cmax = len - cpdmin + 1; 1694| 0| } 1695| | 1696| 557M| if (i >= st.size()) ------------------ | Branch (1696:13): [True: 664k, False: 557M] ------------------ 1697| 664k| return nullptr; 1698| | 1699| 557M| ch = st[i]; 1700| 557M| st[i] = '\0'; 1701| | 1702| 557M| sfx = nullptr; 1703| 557M| pfx = nullptr; 1704| | 1705| | // FIRST WORD 1706| | 1707| 557M| affixed = 1; 1708| 557M| rv = lookup(st.c_str(), i); // perhaps without prefix 1709| | 1710| | // forbid dictionary stems with COMPOUNDFORBIDFLAG in 1711| | // compound words, overriding the effect of COMPOUNDPERMITFLAG 1712| 557M| if ((rv) && compoundforbidflag && ------------------ | Branch (1712:13): [True: 1.88M, False: 555M] | Branch (1712:21): [True: 98.4k, False: 1.78M] ------------------ 1713| 98.4k| TESTAFF(rv->astr, compoundforbidflag, rv->alen) && !hu_mov_rule) { ------------------ | | 99| 557M|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 98.4k] | | ------------------ ------------------ | Branch (1713:68): [True: 0, False: 0] ------------------ 1714| 0| bool would_continue = !onlycpdrule && simplifiedcpd; ------------------ | Branch (1714:35): [True: 0, False: 0] | Branch (1714:51): [True: 0, False: 0] ------------------ 1715| 0| if (!scpd && would_continue) { ------------------ | Branch (1715:17): [True: 0, False: 0] | Branch (1715:26): [True: 0, False: 0] ------------------ 1716| | // given the while conditions that continue jumps to, this situation 1717| | // never ends 1718| 0| HUNSPELL_WARNING(stderr, "break infinite loop\n"); 1719| 0| break; 1720| 0| } 1721| | 1722| 0| if (scpd > 0 && would_continue) { ------------------ | Branch (1722:17): [True: 0, False: 0] | Branch (1722:29): [True: 0, False: 0] ------------------ 1723| | // under these conditions we loop again, but the assumption above 1724| | // appears to be that cmin and cmax are the original values they 1725| | // had in the outside loop 1726| 0| cmin = oldcmin; 1727| 0| cmax = oldcmax; 1728| 0| } 1729| 0| continue; 1730| 0| } 1731| | 1732| | // search homonym with compound flag 1733| 559M| while ((rv) && !hu_mov_rule && ------------------ | Branch (1733:16): [True: 1.88M, False: 557M] | Branch (1733:24): [True: 1.88M, False: 149] ------------------ 1734| 1.88M| ((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) || ------------------ | | 99| 597k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 597k] | | ------------------ ------------------ | Branch (1734:18): [True: 597k, False: 1.29M] ------------------ 1735| 1.88M| !((compoundflag && !words && !onlycpdrule && ------------------ | Branch (1735:20): [True: 1.88M, False: 0] | Branch (1735:36): [True: 1.88M, False: 0] | Branch (1735:46): [True: 1.88M, False: 0] ------------------ 1736| 1.88M| TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 1.88M|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 164, False: 1.88M] | | ------------------ ------------------ 1737| 1.88M| (compoundbegin && !wordnum && !onlycpdrule && ------------------ | Branch (1737:20): [True: 0, False: 1.88M] | Branch (1737:37): [True: 0, False: 0] | Branch (1737:49): [True: 0, False: 0] ------------------ 1738| 0| TESTAFF(rv->astr, compoundbegin, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1739| 1.88M| (compoundmiddle && wordnum && !words && !onlycpdrule && ------------------ | Branch (1739:20): [True: 0, False: 1.88M] | Branch (1739:38): [True: 0, False: 0] | Branch (1739:49): [True: 0, False: 0] | Branch (1739:59): [True: 0, False: 0] ------------------ 1740| 0| TESTAFF(rv->astr, compoundmiddle, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1741| 1.88M| (!defcpdtable.empty() && onlycpdrule && ------------------ | Branch (1741:20): [True: 0, False: 1.88M] | Branch (1741:44): [True: 0, False: 0] ------------------ 1742| 0| ((!words && !wordnum && ------------------ | Branch (1742:22): [True: 0, False: 0] | Branch (1742:32): [True: 0, False: 0] ------------------ 1743| 0| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0)) || ------------------ | Branch (1743:22): [True: 0, False: 0] ------------------ 1744| 0| (words && ------------------ | Branch (1744:22): [True: 0, False: 0] ------------------ 1745| 0| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0))))) || ------------------ | Branch (1745:22): [True: 0, False: 0] ------------------ 1746| 164| (scpd != 0 && checkcpdtable[scpd - 1].cond != FLAG_NULL && ------------------ | | 96| 164|#define FLAG_NULL 0x00 ------------------ | Branch (1746:18): [True: 0, False: 164] | Branch (1746:31): [True: 0, False: 0] ------------------ 1747| 1.88M| !TESTAFF(rv->astr, checkcpdtable[scpd - 1].cond, rv->alen)))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1747:18): [True: 0, False: 0] ------------------ 1748| 1.88M| rv = rv->next_homonym; 1749| 1.88M| } 1750| | 1751| 557M| if (rv) ------------------ | Branch (1751:13): [True: 313, False: 557M] ------------------ 1752| 313| affixed = 0; 1753| | 1754| 557M| if (!rv) { ------------------ | Branch (1754:13): [True: 557M, False: 313] ------------------ 1755| 557M| if (onlycpdrule) ------------------ | Branch (1755:15): [True: 0, False: 557M] ------------------ 1756| 0| break; 1757| 557M| if (compoundflag && ------------------ | Branch (1757:15): [True: 557M, False: 0] ------------------ 1758| 557M| !(rv = prefix_check(st, 0, i, ------------------ | Branch (1758:15): [True: 557M, False: 0] ------------------ 1759| 557M| hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, ------------------ | | 75| 71.2k|#define IN_CPD_OTHER 3 ------------------ hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, ------------------ | | 73| 1.11G|#define IN_CPD_BEGIN 1 ------------------ | Branch (1759:35): [True: 71.2k, False: 557M] ------------------ 1760| 557M| scratch, compoundflag))) { 1761| 557M| if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 96| 557M|#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)) || ------------------ | | 75| 71.2k|#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)) || ------------------ | | 73| 1.11G|#define IN_CPD_BEGIN 1 ------------------ | Branch (1761:18): [True: 0, False: 557M] | Branch (1761:93): [True: 71.2k, False: 557M] ------------------ 1762| 557M| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, compoundflag)))) && ------------------ | Branch (1762:19): [True: 0, False: 557M] | Branch (1762:43): [True: 0, False: 0] ------------------ 1763| 0| !hu_mov_rule && sfx->getCont() && ------------------ | Branch (1763:17): [True: 0, False: 0] | Branch (1763:33): [True: 0, False: 0] ------------------ 1764| 0| ((compoundforbidflag && TESTAFF(sfx->getCont(), compoundforbidflag, sfx->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1764:19): [True: 0, False: 0] ------------------ 1765| 0| (compoundend && TESTAFF(sfx->getCont(), compoundend, sfx->getContLen())))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1765:19): [True: 0, False: 0] ------------------ 1766| 0| rv = nullptr; 1767| 0| } 1768| 557M| } 1769| | 1770| 557M| if (rv || ------------------ | Branch (1770:15): [True: 0, False: 557M] ------------------ 1771| 557M| (((wordnum == 0) && compoundbegin && ------------------ | Branch (1771:17): [True: 557M, False: 72.0k] | Branch (1771:35): [True: 0, False: 557M] ------------------ 1772| 0| ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundbegin, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 96| 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)) || ------------------ | | 75| 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)) || ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (1772:18): [True: 0, False: 0] | Branch (1772:94): [True: 0, False: 0] ------------------ 1773| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (1773:19): [True: 0, False: 0] | Branch (1773:43): [True: 0, False: 0] ------------------ 1774| 0| compoundbegin))) || // twofold suffixes + compound 1775| 0| (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundbegin)))) || ------------------ | | 75| 0|#define IN_CPD_OTHER 3 ------------------ (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundbegin)))) || ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (1775:18): [True: 0, False: 0] | Branch (1775:47): [True: 0, False: 0] ------------------ 1776| 557M| ((wordnum > 0) && compoundmiddle && ------------------ | Branch (1776:17): [True: 612, False: 557M] | Branch (1776:34): [True: 0, False: 612] ------------------ 1777| 0| ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundmiddle, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 96| 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)) || ------------------ | | 75| 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)) || ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (1777:18): [True: 0, False: 0] | Branch (1777:95): [True: 0, False: 0] ------------------ 1778| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (1778:19): [True: 0, False: 0] | Branch (1778:43): [True: 0, False: 0] ------------------ 1779| 0| compoundmiddle))) || // twofold suffixes + compound 1780| 0| (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundmiddle)))))) ------------------ | | 75| 0|#define IN_CPD_OTHER 3 ------------------ (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundmiddle)))))) ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (1780:18): [True: 0, False: 0] | Branch (1780:47): [True: 0, False: 0] ------------------ 1781| 0| checked_prefix = 1; 1782| | // else check forbiddenwords and needaffix 1783| 557M| } else if (rv->astr && (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 99| 406|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 203] | | ------------------ ------------------ | Branch (1783:20): [True: 203, False: 110] | Branch (1783:20): [True: 1, False: 312] ------------------ 1784| 203| TESTAFF(rv->astr, needaffix, rv->alen) || ------------------ | | 99| 406|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 203] | | ------------------ ------------------ 1785| 203| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 406|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 1, False: 202] | | ------------------ ------------------ 1786| 202| (is_sug && nosuggest && ------------------ | Branch (1786:34): [True: 0, False: 202] | Branch (1786:44): [True: 0, False: 0] ------------------ 1787| 1| TESTAFF(rv->astr, nosuggest, rv->alen)))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1788| 1| st[i] = ch; 1789| | // continue; 1790| 1| break; 1791| 1| } 1792| | 1793| | // check non_compound flag in suffix and prefix 1794| 557M| if ((rv) && !hu_mov_rule && ------------------ | Branch (1794:13): [True: 312, False: 557M] | Branch (1794:21): [True: 164, False: 148] ------------------ 1795| 164| ((pfx && pfx->getCont() && ------------------ | Branch (1795:15): [True: 0, False: 164] | Branch (1795:22): [True: 0, False: 0] ------------------ 1796| 0| TESTAFF(pfx->getCont(), compoundforbidflag, pfx->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1797| 164| (sfx && sfx->getCont() && ------------------ | Branch (1797:15): [True: 0, False: 164] | Branch (1797:22): [True: 0, False: 0] ------------------ 1798| 0| TESTAFF(sfx->getCont(), compoundforbidflag, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1799| 164| sfx->getContLen())))) { 1800| 0| rv = nullptr; 1801| 0| } 1802| | 1803| | // check compoundend flag in suffix and prefix 1804| 557M| if ((rv) && !checked_prefix && compoundend && !hu_mov_rule && ------------------ | Branch (1804:13): [True: 312, False: 557M] | Branch (1804:21): [True: 312, False: 0] | Branch (1804:40): [True: 0, False: 312] | Branch (1804:55): [True: 0, False: 0] ------------------ 1805| 0| ((pfx && pfx->getCont() && ------------------ | Branch (1805:15): [True: 0, False: 0] | Branch (1805:22): [True: 0, False: 0] ------------------ 1806| 0| TESTAFF(pfx->getCont(), compoundend, pfx->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1807| 0| (sfx && sfx->getCont() && ------------------ | Branch (1807:15): [True: 0, False: 0] | Branch (1807:22): [True: 0, False: 0] ------------------ 1808| 0| TESTAFF(sfx->getCont(), compoundend, sfx->getContLen())))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1809| 0| rv = nullptr; 1810| 0| } 1811| | 1812| | // check compoundmiddle flag in suffix and prefix 1813| 557M| if ((rv) && !checked_prefix && (wordnum == 0) && compoundmiddle && ------------------ | Branch (1813:13): [True: 312, False: 557M] | Branch (1813:21): [True: 312, False: 0] | Branch (1813:40): [True: 164, False: 148] | Branch (1813:58): [True: 0, False: 164] ------------------ 1814| 0| !hu_mov_rule && ------------------ | Branch (1814:13): [True: 0, False: 0] ------------------ 1815| 0| ((pfx && pfx->getCont() && ------------------ | Branch (1815:15): [True: 0, False: 0] | Branch (1815:22): [True: 0, False: 0] ------------------ 1816| 0| TESTAFF(pfx->getCont(), compoundmiddle, pfx->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1817| 0| (sfx && sfx->getCont() && ------------------ | Branch (1817:15): [True: 0, False: 0] | Branch (1817:22): [True: 0, False: 0] ------------------ 1818| 0| TESTAFF(sfx->getCont(), compoundmiddle, sfx->getContLen())))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1819| 0| rv = nullptr; 1820| 0| } 1821| | 1822| | // check forbiddenwords 1823| 557M| if ((rv) && (rv->astr) && ------------------ | Branch (1823:13): [True: 312, False: 557M] | Branch (1823:13): [True: 0, False: 557M] | Branch (1823:21): [True: 202, False: 110] ------------------ 1824| 202| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 99| 404|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 202] | | ------------------ ------------------ 1825| 202| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 404|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 202] | | ------------------ ------------------ 1826| 202| (is_sug && nosuggest && TESTAFF(rv->astr, nosuggest, rv->alen)))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1826:15): [True: 0, False: 202] | Branch (1826:25): [True: 0, False: 0] ------------------ 1827| 0| return nullptr; 1828| 0| } 1829| | 1830| | // increment word number, if the second root has a compoundroot flag 1831| 557M| if ((rv) && compoundroot && ------------------ | Branch (1831:13): [True: 312, False: 557M] | Branch (1831:21): [True: 0, False: 312] ------------------ 1832| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1832:13): [True: 0, False: 0] ------------------ 1833| 0| wordnum++; 1834| 0| } 1835| | 1836| | // first word is acceptable in compound words? 1837| 557M| if (((rv) && ------------------ | Branch (1837:13): [True: 202, False: 557M] | Branch (1837:14): [True: 312, False: 557M] ------------------ 1838| 312| (checked_prefix || (words && words[wnum]) || ------------------ | Branch (1838:15): [True: 0, False: 312] | Branch (1838:34): [True: 0, False: 312] | Branch (1838:43): [True: 0, False: 0] ------------------ 1839| 312| (compoundflag && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 312|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 202, False: 110] | | ------------------ ------------------ | Branch (1839:16): [True: 312, False: 0] ------------------ 1840| 110| ((oldwordnum == 0) && compoundbegin && ------------------ | Branch (1840:16): [True: 0, False: 110] | Branch (1840:37): [True: 0, False: 0] ------------------ 1841| 0| TESTAFF(rv->astr, compoundbegin, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1842| 110| ((oldwordnum > 0) && compoundmiddle && ------------------ | Branch (1842:16): [True: 0, False: 110] | Branch (1842:36): [True: 0, False: 0] ------------------ 1843| 0| TESTAFF(rv->astr, compoundmiddle, rv->alen)) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1844| | 1845| | // LANG_hu section: spec. Hungarian rule 1846| 110| || ((langnum == LANG_hu) && hu_mov_rule && ------------------ | Branch (1846:19): [True: 110, False: 0] | Branch (1846:43): [True: 110, False: 0] ------------------ 1847| 110| (TESTAFF( ------------------ | | 99| 220|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 110] | | ------------------ ------------------ 1848| 110| rv->astr, 'F', 1849| 110| rv->alen) || // XXX hardwired Hungarian dictionary codes 1850| 110| TESTAFF(rv->astr, 'G', rv->alen) || ------------------ | | 99| 220|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 110] | | ------------------ ------------------ 1851| 110| TESTAFF(rv->astr, 'H', rv->alen))) ------------------ | | 99| 110|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 110] | | ------------------ ------------------ 1852| | // END of LANG_hu section 1853| 312| ) && 1854| 202| ( 1855| | // test CHECKCOMPOUNDPATTERN conditions 1856| 202| scpd == 0 || checkcpdtable[scpd - 1].cond == FLAG_NULL || ------------------ | | 96| 202|#define FLAG_NULL 0x00 ------------------ | Branch (1856:18): [True: 202, False: 0] | Branch (1856:31): [True: 0, False: 0] ------------------ 1857| 0| TESTAFF(rv->astr, checkcpdtable[scpd - 1].cond, rv->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1858| 202| !((checkcompoundtriple && scpd == 0 && ------------------ | Branch (1858:17): [True: 0, False: 202] | Branch (1858:40): [True: 0, False: 0] ------------------ 1859| 0| !words && i < word.size() && // test triple letters ------------------ | Branch (1859:17): [True: 0, False: 0] | Branch (1859:27): [True: 0, False: 0] ------------------ 1860| 0| (word[i - 1] == word[i]) && ------------------ | Branch (1860:17): [True: 0, False: 0] ------------------ 1861| 0| (((i > 1) && (word[i - 1] == word[i - 2])) || ------------------ | Branch (1861:19): [True: 0, False: 0] | Branch (1861:30): [True: 0, False: 0] ------------------ 1862| 0| ((word[i - 1] == word[i + 1])) // may be word[i+1] == '\0' ------------------ | Branch (1862:18): [True: 0, False: 0] ------------------ 1863| 0| )) || 1864| 202| (checkcompoundcase && scpd == 0 && !words && i < word.size() && ------------------ | Branch (1864:17): [True: 0, False: 202] | Branch (1864:38): [True: 0, False: 0] | Branch (1864:51): [True: 0, False: 0] | Branch (1864:61): [True: 0, False: 0] ------------------ 1865| 0| cpdcase_check(word, i)))) ------------------ | Branch (1865:17): [True: 0, False: 0] ------------------ 1866| | // LANG_hu section: spec. Hungarian rule 1867| 557M| || ((!rv) && (langnum == LANG_hu) && hu_mov_rule && ------------------ | Branch (1867:17): [True: 557M, False: 110] | Branch (1867:26): [True: 39.1M, False: 518M] | Branch (1867:50): [True: 71.2k, False: 39.0M] ------------------ 1868| 71.2k| (rv = affix_check(st, 0, i, scratch)) && ------------------ | Branch (1868:17): [True: 0, False: 71.2k] ------------------ 1869| 0| (sfx && sfx->getCont() && ------------------ | Branch (1869:18): [True: 0, False: 0] | Branch (1869:25): [True: 0, False: 0] ------------------ 1870| 0| ( // XXX hardwired Hungarian dic. codes 1871| 0| TESTAFF(sfx->getCont(), (unsigned short)'x', ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1872| 0| sfx->getContLen()) || 1873| 0| TESTAFF( ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1874| 0| sfx->getCont(), (unsigned short)'%', 1875| 202| sfx->getContLen()))))) { // first word is ok condition 1876| | 1877| | // LANG_hu section: spec. Hungarian rule 1878| 202| if (langnum == LANG_hu) { ------------------ | Branch (1878:15): [True: 194, False: 8] ------------------ 1879| | // calculate syllable number of the word 1880| 194| numsyllable += get_syllable(st.substr(0, i)); 1881| | // + 1 word, if syllable number of the prefix > 1 (hungarian 1882| | // convention) 1883| 194| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (1883:17): [True: 0, False: 194] | Branch (1883:17): [True: 0, False: 194] | Branch (1883:24): [True: 0, False: 0] ------------------ 1884| 0| wordnum++; 1885| 194| } 1886| | // END of LANG_hu section 1887| | 1888| | // NEXT WORD(S) 1889| 202| rv_first = rv; 1890| 202| st[i] = ch; 1891| | 1892| 202| do { // striple loop 1893| | 1894| | // check simplifiedtriple 1895| 202| if (simplifiedtriple) { ------------------ | Branch (1895:17): [True: 0, False: 202] ------------------ 1896| 0| if (striple) { ------------------ | Branch (1896:19): [True: 0, False: 0] ------------------ 1897| 0| checkedstriple = 1; 1898| 0| i--; // check "fahrt" instead of "ahrt" in "Schiffahrt" 1899| 0| } else if (i > 2 && i <= word.size() && word[i - 1] == word[i - 2]) ------------------ | Branch (1899:26): [True: 0, False: 0] | Branch (1899:35): [True: 0, False: 0] | Branch (1899:55): [True: 0, False: 0] ------------------ 1900| 0| striple = 1; 1901| 0| } 1902| | 1903| 202| rv = lookup(st.c_str() + i, st.size() - i); // perhaps without prefix 1904| | 1905| | // search homonym with compound flag 1906| 202| while ((rv) && ((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1906:20): [True: 0, False: 202] | Branch (1906:30): [True: 0, False: 0] ------------------ 1907| 0| !((compoundflag && !words && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1907:32): [True: 0, False: 0] | Branch (1907:48): [True: 0, False: 0] ------------------ 1908| 0| (compoundend && !words && TESTAFF(rv->astr, compoundend, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1908:32): [True: 0, False: 0] | Branch (1908:47): [True: 0, False: 0] ------------------ 1909| 0| (!defcpdtable.empty() && words && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1))) || ------------------ | Branch (1909:32): [True: 0, False: 0] | Branch (1909:56): [True: 0, False: 0] | Branch (1909:65): [True: 0, False: 0] ------------------ 1910| 0| (scpd != 0 && checkcpdtable[scpd - 1].cond2 != FLAG_NULL && ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ | Branch (1910:30): [True: 0, False: 0] | Branch (1910:43): [True: 0, False: 0] ------------------ 1911| 0| !TESTAFF(rv->astr, checkcpdtable[scpd - 1].cond2, rv->alen)))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1911:30): [True: 0, False: 0] ------------------ 1912| 0| rv = rv->next_homonym; 1913| 0| } 1914| | 1915| | // check FORCEUCASE 1916| 202| if (rv && forceucase && ------------------ | Branch (1916:17): [True: 0, False: 202] | Branch (1916:23): [True: 0, False: 0] ------------------ 1917| 0| (TESTAFF(rv->astr, forceucase, rv->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1917:17): [True: 0, False: 0] ------------------ 1918| 0| !(info && *info & SPELL_ORIGCAP)) ------------------ | | 83| 0|#define SPELL_ORIGCAP (1 << 5) ------------------ | Branch (1918:19): [True: 0, False: 0] | Branch (1918:27): [True: 0, False: 0] ------------------ 1919| 0| rv = nullptr; 1920| | 1921| 202| if (rv && words && words[wnum + 1]) ------------------ | Branch (1921:17): [True: 0, False: 202] | Branch (1921:23): [True: 0, False: 0] | Branch (1921:32): [True: 0, False: 0] ------------------ 1922| 0| return rv_first; 1923| | 1924| 202| oldnumsyllable2 = numsyllable; 1925| 202| oldwordnum2 = wordnum; 1926| | 1927| | // LANG_hu section: spec. Hungarian rule, XXX hardwired dictionary 1928| | // code 1929| 202| if ((rv) && (langnum == LANG_hu) && ------------------ | Branch (1929:17): [True: 0, False: 202] | Branch (1929:17): [True: 0, False: 202] | Branch (1929:25): [True: 0, False: 0] ------------------ 1930| 0| (TESTAFF(rv->astr, 'I', rv->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1930:17): [True: 0, False: 0] ------------------ 1931| 0| !(TESTAFF(rv->astr, 'J', rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1931:17): [True: 0, False: 0] ------------------ 1932| 0| numsyllable--; 1933| 0| } 1934| | // END of LANG_hu section 1935| | 1936| | // increment word number, if the second root has a compoundroot flag 1937| 202| if ((rv) && (compoundroot) && ------------------ | Branch (1937:17): [True: 0, False: 202] | Branch (1937:25): [True: 0, False: 0] ------------------ 1938| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1938:17): [True: 0, False: 0] ------------------ 1939| 0| wordnum++; 1940| 0| } 1941| | 1942| | // check forbiddenwords 1943| 202| if ((rv) && (rv->astr) && ------------------ | Branch (1943:17): [True: 0, False: 202] | Branch (1943:17): [True: 0, False: 202] | Branch (1943:25): [True: 0, False: 0] ------------------ 1944| 0| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1945| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1946| 0| (is_sug && nosuggest && ------------------ | Branch (1946:19): [True: 0, False: 0] | Branch (1946:29): [True: 0, False: 0] ------------------ 1947| 0| TESTAFF(rv->astr, nosuggest, rv->alen)))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1948| 0| return nullptr; 1949| | 1950| | // second word is acceptable, as a root? 1951| | // hungarian conventions: compounding is acceptable, 1952| | // when compound forms consist of 2 words, or if more, 1953| | // then the syllable number of root words must be 6, or lesser. 1954| | 1955| 202| if ((rv) && ------------------ | Branch (1955:17): [True: 0, False: 202] | Branch (1955:17): [True: 0, False: 202] ------------------ 1956| 0| ((compoundflag && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1956:19): [True: 0, False: 0] ------------------ 1957| 0| (compoundend && TESTAFF(rv->astr, compoundend, rv->alen))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1957:19): [True: 0, False: 0] ------------------ 1958| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (1958:19): [True: 0, False: 0] | Branch (1958:41): [True: 0, False: 0] ------------------ 1959| 0| ((cpdmaxsyllable != 0) && ------------------ | Branch (1959:19): [True: 0, False: 0] ------------------ 1960| 0| (numsyllable + get_syllable(std::string(HENTRY_WORD(rv), rv->blen)) <= ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ | Branch (1960:19): [True: 0, False: 0] ------------------ 1961| 0| cpdmaxsyllable))) && 1962| 0| ( 1963| | // test CHECKCOMPOUNDPATTERN 1964| 0| checkcpdtable.empty() || scpd != 0 || ------------------ | Branch (1964:21): [True: 0, False: 0] | Branch (1964:46): [True: 0, False: 0] ------------------ 1965| 0| (i < word.size() && !cpdpat_check(word, i, rv_first, rv, 0))) && ------------------ | Branch (1965:22): [True: 0, False: 0] | Branch (1965:41): [True: 0, False: 0] ------------------ 1966| 0| ((!checkcompounddup || (rv != rv_first))) ------------------ | Branch (1966:19): [True: 0, False: 0] | Branch (1966:40): [True: 0, False: 0] ------------------ 1967| | // test CHECKCOMPOUNDPATTERN conditions 1968| 0| && 1969| 0| (scpd == 0 || checkcpdtable[scpd - 1].cond2 == FLAG_NULL || ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ | Branch (1969:18): [True: 0, False: 0] | Branch (1969:31): [True: 0, False: 0] ------------------ 1970| 0| TESTAFF(rv->astr, checkcpdtable[scpd - 1].cond2, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1971| | // forbid compound word, if it is a non-compound word with typical 1972| | // fault 1973| 0| if ((checkcompoundrep && cpdrep_check(word, len, scratch, timelimit_exceeded, clock_time_start)) || ------------------ | Branch (1973:20): [True: 0, False: 0] | Branch (1973:40): [True: 0, False: 0] ------------------ 1974| 0| cpdwordpair_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (1974:19): [True: 0, False: 0] ------------------ 1975| 0| return nullptr; 1976| 0| return rv_first; 1977| 0| } 1978| | 1979| 202| numsyllable = oldnumsyllable2; 1980| 202| wordnum = oldwordnum2; 1981| | 1982| | // perhaps second word has prefix or/and suffix 1983| 202| sfx = nullptr; 1984| 202| sfxflag = FLAG_NULL; ------------------ | | 96| 202|#define FLAG_NULL 0x00 ------------------ 1985| 202| rv = (compoundflag && !onlycpdrule && i < word.size()) ? affix_check(word, i, word.size() - i, scratch, compoundflag, IN_CPD_END) ------------------ | | 74| 202|#define IN_CPD_END 2 ------------------ | Branch (1985:19): [True: 202, False: 0] | Branch (1985:35): [True: 202, False: 0] | Branch (1985:51): [True: 202, False: 0] ------------------ 1986| 202| : nullptr; 1987| 202| if (!rv && compoundend && !onlycpdrule) { ------------------ | Branch (1987:17): [True: 202, False: 0] | Branch (1987:24): [True: 0, False: 202] | Branch (1987:39): [True: 0, False: 0] ------------------ 1988| 0| sfx = nullptr; 1989| 0| pfx = nullptr; 1990| 0| if (i < word.size()) ------------------ | Branch (1990:19): [True: 0, False: 0] ------------------ 1991| 0| rv = affix_check(word, i, word.size() - i, scratch, compoundend, IN_CPD_END); ------------------ | | 74| 0|#define IN_CPD_END 2 ------------------ 1992| 0| } 1993| | 1994| 202| if (!rv && !defcpdtable.empty() && words) { ------------------ | Branch (1994:17): [True: 202, False: 0] | Branch (1994:24): [True: 0, False: 202] | Branch (1994:48): [True: 0, False: 0] ------------------ 1995| 0| if (i < word.size()) ------------------ | Branch (1995:19): [True: 0, False: 0] ------------------ 1996| 0| rv = affix_check(word, i, word.size() - i, scratch, 0, IN_CPD_END); ------------------ | | 74| 0|#define IN_CPD_END 2 ------------------ 1997| 0| if (rv && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1)) ------------------ | Branch (1997:19): [True: 0, False: 0] | Branch (1997:25): [True: 0, False: 0] ------------------ 1998| 0| return rv_first; 1999| 0| rv = nullptr; 2000| 0| } 2001| | 2002| | // test CHECKCOMPOUNDPATTERN conditions (allowed forms) 2003| 202| if (rv && ------------------ | Branch (2003:17): [True: 0, False: 202] ------------------ 2004| 0| !(scpd == 0 || checkcpdtable[scpd - 1].cond2 == FLAG_NULL || ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ | Branch (2004:19): [True: 0, False: 0] | Branch (2004:32): [True: 0, False: 0] ------------------ 2005| 0| TESTAFF(rv->astr, checkcpdtable[scpd - 1].cond2, rv->alen))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2006| 0| rv = nullptr; 2007| | 2008| | // test CHECKCOMPOUNDPATTERN conditions (forbidden compounds) 2009| 202| if (rv && !checkcpdtable.empty() && scpd == 0 && ------------------ | Branch (2009:17): [True: 0, False: 202] | Branch (2009:23): [True: 0, False: 0] | Branch (2009:49): [True: 0, False: 0] ------------------ 2010| 0| cpdpat_check(word, i, rv_first, rv, affixed)) ------------------ | Branch (2010:17): [True: 0, False: 0] ------------------ 2011| 0| rv = nullptr; 2012| | 2013| | // check non_compound flag in suffix and prefix 2014| 202| if ((rv) && ((pfx && pfx->getCont() && ------------------ | Branch (2014:17): [True: 0, False: 202] | Branch (2014:27): [True: 0, False: 0] | Branch (2014:34): [True: 0, False: 0] ------------------ 2015| 0| TESTAFF(pfx->getCont(), compoundforbidflag, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2016| 0| pfx->getContLen())) || 2017| 0| (sfx && sfx->getCont() && ------------------ | Branch (2017:27): [True: 0, False: 0] | Branch (2017:34): [True: 0, False: 0] ------------------ 2018| 0| TESTAFF(sfx->getCont(), compoundforbidflag, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2019| 0| sfx->getContLen())))) { 2020| 0| rv = nullptr; 2021| 0| } 2022| | 2023| | // check FORCEUCASE 2024| 202| if (rv && forceucase && ------------------ | Branch (2024:17): [True: 0, False: 202] | Branch (2024:23): [True: 0, False: 0] ------------------ 2025| 0| (TESTAFF(rv->astr, forceucase, rv->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2025:17): [True: 0, False: 0] ------------------ 2026| 0| !(info && *info & SPELL_ORIGCAP)) ------------------ | | 83| 0|#define SPELL_ORIGCAP (1 << 5) ------------------ | Branch (2026:19): [True: 0, False: 0] | Branch (2026:27): [True: 0, False: 0] ------------------ 2027| 0| rv = nullptr; 2028| | 2029| | // check forbiddenwords 2030| 202| if ((rv) && (rv->astr) && ------------------ | Branch (2030:17): [True: 0, False: 202] | Branch (2030:17): [True: 0, False: 202] | Branch (2030:25): [True: 0, False: 0] ------------------ 2031| 0| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2032| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2033| 0| (is_sug && nosuggest && ------------------ | Branch (2033:19): [True: 0, False: 0] | Branch (2033:29): [True: 0, False: 0] ------------------ 2034| 0| TESTAFF(rv->astr, nosuggest, rv->alen)))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2035| 0| return nullptr; 2036| | 2037| | // pfxappnd = prefix of word+i, or NULL 2038| | // calculate syllable number of prefix. 2039| | // hungarian convention: when syllable number of prefix is more, 2040| | // than 1, the prefix+word counts as two words. 2041| | 2042| 202| if (langnum == LANG_hu) { ------------------ | Branch (2042:17): [True: 194, False: 8] ------------------ 2043| 194| if (i < word.size()) { ------------------ | Branch (2043:19): [True: 194, False: 0] ------------------ 2044| | // calculate syllable number of the word 2045| 194| numsyllable += get_syllable(word.substr(i)); 2046| 194| } 2047| | 2048| | // - affix syllable num. 2049| | // XXX only second suffix (inflections, not derivations) 2050| 194| if (sfxappnd) { ------------------ | Branch (2050:19): [True: 0, False: 194] ------------------ 2051| 0| std::string tmp(sfxappnd); 2052| 0| reverseword(tmp); 2053| 0| numsyllable -= short(get_syllable(tmp) + sfxextra); 2054| 194| } else { 2055| 194| numsyllable -= short(sfxextra); 2056| 194| } 2057| | 2058| | // + 1 word, if syllable number of the prefix > 1 (hungarian 2059| | // convention) 2060| 194| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (2060:19): [True: 0, False: 194] | Branch (2060:19): [True: 0, False: 194] | Branch (2060:26): [True: 0, False: 0] ------------------ 2061| 0| wordnum++; 2062| | 2063| | // increment syllable num, if last word has a SYLLABLENUM flag 2064| | // and the suffix is beginning `s' 2065| | 2066| 194| if (!cpdsyllablenum.empty()) { ------------------ | Branch (2066:19): [True: 0, False: 194] ------------------ 2067| 0| switch (sfxflag) { ------------------ | Branch (2067:25): [True: 0, False: 0] ------------------ 2068| 0| case 'c': { ------------------ | Branch (2068:19): [True: 0, False: 0] ------------------ 2069| 0| numsyllable += 2; 2070| 0| break; 2071| 0| } 2072| 0| case 'J': { ------------------ | Branch (2072:19): [True: 0, False: 0] ------------------ 2073| 0| numsyllable += 1; 2074| 0| break; 2075| 0| } 2076| 0| case 'I': { ------------------ | Branch (2076:19): [True: 0, False: 0] ------------------ 2077| 0| if (rv && TESTAFF(rv->astr, 'J', rv->alen)) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2077:25): [True: 0, False: 0] | Branch (2077:25): [True: 0, False: 0] ------------------ 2078| 0| numsyllable += 1; 2079| 0| break; 2080| 0| } 2081| 0| } 2082| 0| } 2083| 194| } 2084| | 2085| | // increment word number, if the second word has a compoundroot flag 2086| 202| if ((rv) && (compoundroot) && ------------------ | Branch (2086:17): [True: 0, False: 202] | Branch (2086:25): [True: 0, False: 0] ------------------ 2087| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2087:17): [True: 0, False: 0] ------------------ 2088| 0| wordnum++; 2089| 0| } 2090| | // second word is acceptable, as a word with prefix or/and suffix? 2091| | // hungarian conventions: compounding is acceptable, 2092| | // when compound forms consist 2 word, otherwise 2093| | // the syllable number of root words is 6, or lesser. 2094| 202| if ((rv) && ------------------ | Branch (2094:17): [True: 0, False: 202] ------------------ 2095| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (2095:19): [True: 0, False: 0] | Branch (2095:41): [True: 0, False: 0] ------------------ 2096| 0| ((cpdmaxsyllable != 0) && (numsyllable <= cpdmaxsyllable))) && ------------------ | Branch (2096:19): [True: 0, False: 0] | Branch (2096:44): [True: 0, False: 0] ------------------ 2097| 0| ((!checkcompounddup || (rv != rv_first)))) { ------------------ | Branch (2097:19): [True: 0, False: 0] | Branch (2097:40): [True: 0, False: 0] ------------------ 2098| | // forbid compound word, if it is a non-compound word with typical 2099| | // fault 2100| 0| if ((checkcompoundrep && cpdrep_check(word, len, scratch, timelimit_exceeded, clock_time_start)) || ------------------ | Branch (2100:20): [True: 0, False: 0] | Branch (2100:40): [True: 0, False: 0] ------------------ 2101| 0| cpdwordpair_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (2101:19): [True: 0, False: 0] ------------------ 2102| 0| return nullptr; 2103| 0| return rv_first; 2104| 0| } 2105| | 2106| 202| numsyllable = oldnumsyllable2; 2107| 202| wordnum = oldwordnum2; 2108| | 2109| | // perhaps second word is a compound word (recursive call) 2110| | // (only if SPELL_COMPOUND_2 is not set and maxwordnum is not exceeded) 2111| 202| if ((!info || !(*info & SPELL_COMPOUND_2)) && wordnum + 2 < maxwordnum && wnum + 1 < maxwordnum) { ------------------ | | 85| 202|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ | Branch (2111:18): [True: 0, False: 202] | Branch (2111:27): [True: 120, False: 82] | Branch (2111:59): [True: 120, False: 0] | Branch (2111:87): [True: 120, False: 0] ------------------ 2112| 120| rv = compound_check(st.substr(i), wordnum + 1, 2113| 120| numsyllable, maxwordnum, wnum + 1, words, rwords, 0, 2114| 120| is_sug, info, scratch); 2115| | 2116| 120| if (rv && !checkcpdtable.empty() && i < word.size() && ------------------ | Branch (2116:19): [True: 0, False: 120] | Branch (2116:25): [True: 0, False: 0] | Branch (2116:51): [True: 0, False: 0] ------------------ 2117| 0| ((scpd == 0 && ------------------ | Branch (2117:21): [True: 0, False: 0] ------------------ 2118| 0| cpdpat_check(word, i, rv_first, rv, affixed)) || ------------------ | Branch (2118:21): [True: 0, False: 0] ------------------ 2119| 0| (scpd != 0 && ------------------ | Branch (2119:21): [True: 0, False: 0] ------------------ 2120| 0| !cpdpat_check(word, i, rv_first, rv, affixed)))) ------------------ | Branch (2120:21): [True: 0, False: 0] ------------------ 2121| 0| rv = nullptr; 2122| 120| } else { 2123| 82| rv = nullptr; 2124| 82| } 2125| 202| if (rv) { ------------------ | Branch (2125:17): [True: 0, False: 202] ------------------ 2126| | // forbid compound word, if it is a non-compound word with typical 2127| | // fault, or a dictionary word pair 2128| | 2129| 0| if (cpdwordpair_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (2129:19): [True: 0, False: 0] ------------------ 2130| 0| return nullptr; 2131| | 2132| 0| if (checkcompoundrep || forbiddenword) { ------------------ | Branch (2132:19): [True: 0, False: 0] | Branch (2132:39): [True: 0, False: 0] ------------------ 2133| 0| if (checkcompoundrep && cpdrep_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (2133:21): [True: 0, False: 0] | Branch (2133:41): [True: 0, False: 0] ------------------ 2134| 0| return nullptr; 2135| | 2136| | // check first part 2137| 0| if (i < word.size() && word.compare(i, rv->blen, rv->word, rv->blen) == 0) { ------------------ | Branch (2137:21): [True: 0, False: 0] | Branch (2137:40): [True: 0, False: 0] ------------------ 2138| 0| char r = st[i + rv->blen]; 2139| 0| st[i + rv->blen] = '\0'; 2140| | 2141| 0| if ((checkcompoundrep && cpdrep_check(st, i + rv->blen, scratch, timelimit_exceeded, clock_time_start)) || ------------------ | Branch (2141:24): [True: 0, False: 0] | Branch (2141:44): [True: 0, False: 0] ------------------ 2142| 0| cpdwordpair_check(st, i + rv->blen, scratch, timelimit_exceeded, clock_time_start)) { ------------------ | Branch (2142:23): [True: 0, False: 0] ------------------ 2143| 0| st[ + i + rv->blen] = r; 2144| 0| continue; 2145| 0| } 2146| | 2147| 0| if (forbiddenword) { ------------------ | Branch (2147:23): [True: 0, False: 0] ------------------ 2148| 0| struct hentry* rv2 = lookup(word.c_str(), word.size()); 2149| 0| if (!rv2 && len <= word.size()) ------------------ | Branch (2149:25): [True: 0, False: 0] | Branch (2149:33): [True: 0, False: 0] ------------------ 2150| 0| rv2 = affix_check(word, 0, len, scratch); 2151| 0| if (rv2 && rv2->astr && ------------------ | Branch (2151:25): [True: 0, False: 0] | Branch (2151:32): [True: 0, False: 0] ------------------ 2152| 0| TESTAFF(rv2->astr, forbiddenword, rv2->alen) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2153| 0| (strncmp(rv2->word, st.c_str(), i + rv->blen) == 0)) { ------------------ | Branch (2153:25): [True: 0, False: 0] ------------------ 2154| 0| return nullptr; 2155| 0| } 2156| 0| } 2157| 0| st[i + rv->blen] = r; 2158| 0| } 2159| 0| } 2160| 0| return rv_first; 2161| 0| } 2162| 202| } while (striple && !checkedstriple); // end of striple loop ------------------ | Branch (2162:20): [True: 0, False: 202] | Branch (2162:31): [True: 0, False: 0] ------------------ 2163| | 2164| 202| if (checkedstriple) { ------------------ | Branch (2164:15): [True: 0, False: 202] ------------------ 2165| 0| i++; 2166| 0| checkedstriple = 0; 2167| 0| striple = 0; 2168| 0| } 2169| | 2170| 202| } // first word is ok condition 2171| | 2172| 557M| if (soldi != 0) { ------------------ | Branch (2172:13): [True: 0, False: 557M] ------------------ 2173| 0| i = soldi; 2174| 0| soldi = 0; 2175| 0| len = oldlen; 2176| 0| cmin = oldcmin; 2177| 0| cmax = oldcmax; 2178| 0| } 2179| 557M| scpd++; 2180| | 2181| 557M| } while (!onlycpdrule && simplifiedcpd && ------------------ | Branch (2181:16): [True: 557M, False: 0] | Branch (2181:32): [True: 0, False: 557M] ------------------ 2182| 0| scpd <= checkcpdtable.size()); // end of simplifiedcpd loop ------------------ | Branch (2182:16): [True: 0, False: 0] ------------------ 2183| | 2184| 557M| scpd = 0; 2185| 557M| wordnum = oldwordnum; 2186| 557M| numsyllable = oldnumsyllable; 2187| | 2188| 557M| if (soldi != 0) { ------------------ | Branch (2188:11): [True: 0, False: 557M] ------------------ 2189| 0| i = soldi; 2190| 0| st.assign(word); // XXX add more optim. 2191| 0| soldi = 0; 2192| 0| len = oldlen; 2193| 0| cmin = oldcmin; 2194| 0| cmax = oldcmax; 2195| 0| } else 2196| 557M| st[i] = ch; 2197| | 2198| 557M| } while (!defcpdtable.empty() && oldwordnum == 0 && ------------------ | Branch (2198:14): [True: 0, False: 557M] | Branch (2198:38): [True: 0, False: 0] ------------------ 2199| 0| onlycpdrule++ < 1); // end of onlycpd loop ------------------ | Branch (2199:14): [True: 0, False: 0] ------------------ 2200| 557M| } 2201| | 2202| 21.1M| return nullptr; 2203| 21.9M|} _ZN8AffixMgr20compound_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEssssPP6hentrySB_cRS6_PS7_R12AffixScratch: 2217| 2.05k| AffixScratch& scratch) { 2218| 2.05k| short oldnumsyllable, oldnumsyllable2, oldwordnum, oldwordnum2; 2219| 2.05k| hentry *rv = nullptr, *rv_first; 2220| 2.05k| std::string st, presult; 2221| 2.05k| char ch, affixed = 0; 2222| 2.05k| int checked_prefix, ok = 0; 2223| 2.05k| size_t cmin, cmax; 2224| 2.05k| hentry** oldwords = words; 2225| 2.05k| size_t len = word.size(); 2226| | 2227| | // protect subsequent words[wnum + 1] reads and any recursion 2228| 2.05k| if (wnum + 1 >= maxwordnum) ------------------ | Branch (2228:7): [True: 0, False: 2.05k] ------------------ 2229| 0| return 0; 2230| | 2231| | // add a time limit to handle possible 2232| | // combinatorical explosion of the overlapping words 2233| | 2234| 2.05k| HUNSPELL_THREAD_LOCAL std::chrono::steady_clock::time_point clock_time_start; ------------------ | | 60| 2.05k|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 2235| 2.05k| HUNSPELL_THREAD_LOCAL bool timelimit_exceeded; ------------------ | | 60| 2.05k|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 2236| | 2237| | // get the current time 2238| 2.05k| std::chrono::steady_clock::time_point clock_now = std::chrono::steady_clock::now(); 2239| | 2240| 2.05k| if (wnum == 0) { ------------------ | Branch (2240:7): [True: 2.05k, False: 0] ------------------ 2241| | // set the start time 2242| 2.05k| clock_time_start = clock_now; 2243| 2.05k| timelimit_exceeded = false; 2244| 2.05k| } 2245| 0| else if (clock_now - clock_time_start > TIMELIMIT_MS) ------------------ | | 106| 0|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (2245:12): [True: 0, False: 0] ------------------ 2246| 0| timelimit_exceeded = true; 2247| | 2248| 2.05k| setcminmax(&cmin, &cmax, word.c_str(), len); 2249| | 2250| 2.05k| st.assign(word); 2251| | 2252| 25.7k| for (size_t i = cmin; i < cmax; ++i) { ------------------ | Branch (2252:25): [True: 23.9k, False: 1.82k] ------------------ 2253| | // go to end of the UTF-8 character 2254| 23.9k| if (utf8) { ------------------ | Branch (2254:9): [True: 8.92k, False: 15.0k] ------------------ 2255| 9.95k| for (; is_utf8_cont(st[i]); i++) ------------------ | Branch (2255:14): [True: 1.03k, False: 8.92k] ------------------ 2256| 1.03k| ; 2257| 8.92k| if (i >= cmax) ------------------ | Branch (2257:11): [True: 75, False: 8.84k] ------------------ 2258| 75| return 0; 2259| 8.92k| } 2260| | 2261| 23.8k| words = oldwords; 2262| 23.8k| int onlycpdrule = (words) ? 1 : 0; ------------------ | Branch (2262:23): [True: 0, False: 23.8k] ------------------ 2263| | 2264| 23.8k| do { // onlycpdrule loop 2265| | 2266| 23.8k| if (timelimit_exceeded || ------------------ | Branch (2266:11): [True: 0, False: 23.8k] | Branch (2266:11): [True: 0, False: 23.8k] ------------------ 2267| 23.8k| std::chrono::steady_clock::now() - clock_time_start > TIMELIMIT_MS) { ------------------ | | 106| 23.8k|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (2267:11): [True: 0, False: 23.8k] ------------------ 2268| 0| timelimit_exceeded = true; 2269| 0| return 0; 2270| 0| } 2271| | 2272| 23.8k| if (result.size() > MAXMORPHRESULT) ------------------ | | 111| 23.8k|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (2272:11): [True: 0, False: 23.8k] ------------------ 2273| 0| return 0; 2274| | 2275| 23.8k| oldnumsyllable = numsyllable; 2276| 23.8k| oldwordnum = wordnum; 2277| 23.8k| checked_prefix = 0; 2278| | 2279| 23.8k| if (i >= st.size()) ------------------ | Branch (2279:11): [True: 162, False: 23.7k] ------------------ 2280| 162| return 0; 2281| | 2282| 23.7k| ch = st[i]; 2283| 23.7k| st[i] = '\0'; 2284| 23.7k| sfx = nullptr; 2285| | 2286| | // FIRST WORD 2287| | 2288| 23.7k| affixed = 1; 2289| | 2290| 23.7k| presult.clear(); 2291| 23.7k| if (partresult) ------------------ | Branch (2291:11): [True: 0, False: 23.7k] ------------------ 2292| 0| presult.append(*partresult); 2293| | 2294| 23.7k| rv = lookup(st.c_str(), i); // perhaps without prefix 2295| | 2296| | // forbid dictionary stems with COMPOUNDFORBIDFLAG in 2297| | // compound words, overriding the effect of COMPOUNDPERMITFLAG 2298| 23.7k| if ((rv) && compoundforbidflag && ------------------ | Branch (2298:11): [True: 156, False: 23.5k] | Branch (2298:19): [True: 42, False: 114] ------------------ 2299| 42| TESTAFF(rv->astr, compoundforbidflag, rv->alen) && !hu_mov_rule) ------------------ | | 99| 23.7k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 42] | | ------------------ ------------------ | Branch (2299:66): [True: 0, False: 0] ------------------ 2300| 0| continue; 2301| | 2302| | // search homonym with compound flag 2303| 23.8k| while ((rv) && !hu_mov_rule && ------------------ | Branch (2303:14): [True: 156, False: 23.7k] | Branch (2303:22): [True: 156, False: 0] ------------------ 2304| 156| ((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) || ------------------ | | 99| 38|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 38] | | ------------------ ------------------ | Branch (2304:16): [True: 38, False: 118] ------------------ 2305| 156| !((compoundflag && !words && !onlycpdrule && ------------------ | Branch (2305:18): [True: 156, False: 0] | Branch (2305:34): [True: 156, False: 0] | Branch (2305:44): [True: 156, False: 0] ------------------ 2306| 156| TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 156|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 156] | | ------------------ ------------------ 2307| 156| (compoundbegin && !wordnum && !onlycpdrule && ------------------ | Branch (2307:18): [True: 0, False: 156] | Branch (2307:35): [True: 0, False: 0] | Branch (2307:47): [True: 0, False: 0] ------------------ 2308| 0| TESTAFF(rv->astr, compoundbegin, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2309| 156| (compoundmiddle && wordnum && !words && !onlycpdrule && ------------------ | Branch (2309:18): [True: 0, False: 156] | Branch (2309:36): [True: 0, False: 0] | Branch (2309:47): [True: 0, False: 0] | Branch (2309:57): [True: 0, False: 0] ------------------ 2310| 0| TESTAFF(rv->astr, compoundmiddle, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2311| 156| (!defcpdtable.empty() && onlycpdrule && ------------------ | Branch (2311:18): [True: 0, False: 156] | Branch (2311:42): [True: 0, False: 0] ------------------ 2312| 0| ((!words && !wordnum && ------------------ | Branch (2312:20): [True: 0, False: 0] | Branch (2312:30): [True: 0, False: 0] ------------------ 2313| 0| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0)) || ------------------ | Branch (2313:20): [True: 0, False: 0] ------------------ 2314| 0| (words && ------------------ | Branch (2314:20): [True: 0, False: 0] ------------------ 2315| 156| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0))))))) { ------------------ | Branch (2315:20): [True: 0, False: 0] ------------------ 2316| 156| rv = rv->next_homonym; 2317| 156| } 2318| | 2319| | 2320| 23.7k| if (rv) ------------------ | Branch (2320:11): [True: 0, False: 23.7k] ------------------ 2321| 0| affixed = 0; 2322| | 2323| 23.7k| if (rv) { ------------------ | Branch (2323:11): [True: 0, False: 23.7k] ------------------ 2324| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2325| 0| presult.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2326| 0| presult.append(st, 0, i); 2327| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (2327:13): [True: 0, False: 0] ------------------ 2328| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2329| 0| presult.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 2330| 0| presult.append(st, 0, i); 2331| 0| } 2332| 0| if (HENTRY_DATA(rv)) { ------------------ | Branch (2332:13): [True: 0, False: 0] ------------------ 2333| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2334| 0| presult.append(HENTRY_DATA2(rv)); 2335| 0| } 2336| 0| } 2337| | 2338| 23.7k| if (!rv) { ------------------ | Branch (2338:11): [True: 23.7k, False: 0] ------------------ 2339| 23.7k| if (compoundflag && ------------------ | Branch (2339:13): [True: 23.7k, False: 0] ------------------ 2340| 23.7k| !(rv = ------------------ | Branch (2340:13): [True: 23.7k, False: 0] ------------------ 2341| 23.7k| prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, ------------------ | | 75| 0|#define IN_CPD_OTHER 3 ------------------ prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, ------------------ | | 73| 47.4k|#define IN_CPD_BEGIN 1 ------------------ | Branch (2341:42): [True: 0, False: 23.7k] ------------------ 2342| 23.7k| scratch, compoundflag))) { 2343| 23.7k| if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 96| 23.7k|#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)) || ------------------ | | 75| 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)) || ------------------ | | 73| 47.4k|#define IN_CPD_BEGIN 1 ------------------ | Branch (2343:16): [True: 0, False: 23.7k] | Branch (2343:91): [True: 0, False: 23.7k] ------------------ 2344| 23.7k| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, compoundflag)))) && ------------------ | Branch (2344:17): [True: 0, False: 23.7k] | Branch (2344:41): [True: 0, False: 0] ------------------ 2345| 0| !hu_mov_rule && sfx->getCont() && ------------------ | Branch (2345:15): [True: 0, False: 0] | Branch (2345:31): [True: 0, False: 0] ------------------ 2346| 0| ((compoundforbidflag && TESTAFF(sfx->getCont(), compoundforbidflag, sfx->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2346:17): [True: 0, False: 0] ------------------ 2347| 0| (compoundend && TESTAFF(sfx->getCont(), compoundend, sfx->getContLen())))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2347:17): [True: 0, False: 0] ------------------ 2348| 0| rv = nullptr; 2349| 0| } 2350| 23.7k| } 2351| | 2352| 23.7k| if (rv || ------------------ | Branch (2352:13): [True: 0, False: 23.7k] ------------------ 2353| 23.7k| (((wordnum == 0) && compoundbegin && ------------------ | Branch (2353:15): [True: 23.7k, False: 0] | Branch (2353:33): [True: 0, False: 23.7k] ------------------ 2354| 0| ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundbegin, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 96| 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)) || ------------------ | | 75| 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)) || ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2354:16): [True: 0, False: 0] | Branch (2354:92): [True: 0, False: 0] ------------------ 2355| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (2355:17): [True: 0, False: 0] | Branch (2355:41): [True: 0, False: 0] ------------------ 2356| 0| compoundbegin))) || // twofold suffix+compound 2357| 0| (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundbegin)))) || ------------------ | | 75| 0|#define IN_CPD_OTHER 3 ------------------ (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundbegin)))) || ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2357:16): [True: 0, False: 0] | Branch (2357:45): [True: 0, False: 0] ------------------ 2358| 23.7k| ((wordnum > 0) && compoundmiddle && ------------------ | Branch (2358:15): [True: 0, False: 23.7k] | Branch (2358:32): [True: 0, False: 0] ------------------ 2359| 0| ((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundmiddle, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 96| 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)) || ------------------ | | 75| 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)) || ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2359:16): [True: 0, False: 0] | Branch (2359:93): [True: 0, False: 0] ------------------ 2360| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (2360:17): [True: 0, False: 0] | Branch (2360:41): [True: 0, False: 0] ------------------ 2361| 0| compoundmiddle))) || // twofold suffix+compound 2362| 0| (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundmiddle)))))) { ------------------ | | 75| 0|#define IN_CPD_OTHER 3 ------------------ (rv = prefix_check(st, 0, i, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, scratch, compoundmiddle)))))) { ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2362:16): [True: 0, False: 0] | Branch (2362:45): [True: 0, False: 0] ------------------ 2363| 0| std::string p; 2364| 0| if (compoundflag) ------------------ | Branch (2364:15): [True: 0, False: 0] ------------------ 2365| 0| p = affix_check_morph(st, 0, i, scratch, compoundflag); 2366| 0| if (p.empty()) { ------------------ | Branch (2366:15): [True: 0, False: 0] ------------------ 2367| 0| if ((wordnum == 0) && compoundbegin) { ------------------ | Branch (2367:17): [True: 0, False: 0] | Branch (2367:35): [True: 0, False: 0] ------------------ 2368| 0| p = affix_check_morph(st, 0, i, scratch, compoundbegin); 2369| 0| } else if ((wordnum > 0) && compoundmiddle) { ------------------ | Branch (2369:24): [True: 0, False: 0] | Branch (2369:41): [True: 0, False: 0] ------------------ 2370| 0| p = affix_check_morph(st, 0, i, scratch, compoundmiddle); 2371| 0| } 2372| 0| } 2373| 0| if (!p.empty()) { ------------------ | Branch (2373:15): [True: 0, False: 0] ------------------ 2374| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2375| 0| presult.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2376| 0| presult.append(st, 0, i); 2377| 0| line_uniq_app(p, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2378| 0| if (!p.empty() && p[0] != MSEP_FLD) ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ | Branch (2378:17): [True: 0, False: 0] | Branch (2378:31): [True: 0, False: 0] ------------------ 2379| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2380| 0| presult.append(p); 2381| 0| } 2382| 0| checked_prefix = 1; 2383| 0| } 2384| | // else check forbiddenwords 2385| 23.7k| } else if (rv->astr && (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2385:18): [True: 0, False: 0] | Branch (2385:18): [True: 0, False: 0] ------------------ 2386| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2387| 0| TESTAFF(rv->astr, needaffix, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2388| 0| st[i] = ch; 2389| 0| continue; 2390| 0| } 2391| | 2392| | // check non_compound flag in suffix and prefix 2393| 23.7k| if ((rv) && !hu_mov_rule && ------------------ | Branch (2393:11): [True: 0, False: 23.7k] | Branch (2393:19): [True: 0, False: 0] ------------------ 2394| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2394:13): [True: 0, False: 0] | Branch (2394:20): [True: 0, False: 0] ------------------ 2395| 0| TESTAFF(pfx->getCont(), compoundforbidflag, pfx->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2396| 0| (sfx && sfx->getCont() && ------------------ | Branch (2396:13): [True: 0, False: 0] | Branch (2396:20): [True: 0, False: 0] ------------------ 2397| 0| TESTAFF(sfx->getCont(), compoundforbidflag, sfx->getContLen())))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2398| 0| continue; 2399| 0| } 2400| | 2401| | // check compoundend flag in suffix and prefix 2402| 23.7k| if ((rv) && !checked_prefix && compoundend && !hu_mov_rule && ------------------ | Branch (2402:11): [True: 0, False: 23.7k] | Branch (2402:19): [True: 0, False: 0] | Branch (2402:38): [True: 0, False: 0] | Branch (2402:53): [True: 0, False: 0] ------------------ 2403| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2403:13): [True: 0, False: 0] | Branch (2403:20): [True: 0, False: 0] ------------------ 2404| 0| TESTAFF(pfx->getCont(), compoundend, pfx->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2405| 0| (sfx && sfx->getCont() && ------------------ | Branch (2405:13): [True: 0, False: 0] | Branch (2405:20): [True: 0, False: 0] ------------------ 2406| 0| TESTAFF(sfx->getCont(), compoundend, sfx->getContLen())))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2407| 0| continue; 2408| 0| } 2409| | 2410| | // check compoundmiddle flag in suffix and prefix 2411| 23.7k| if ((rv) && !checked_prefix && (wordnum == 0) && compoundmiddle && ------------------ | Branch (2411:11): [True: 0, False: 23.7k] | Branch (2411:19): [True: 0, False: 0] | Branch (2411:38): [True: 0, False: 0] | Branch (2411:56): [True: 0, False: 0] ------------------ 2412| 0| !hu_mov_rule && ------------------ | Branch (2412:11): [True: 0, False: 0] ------------------ 2413| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2413:13): [True: 0, False: 0] | Branch (2413:20): [True: 0, False: 0] ------------------ 2414| 0| TESTAFF(pfx->getCont(), compoundmiddle, pfx->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2415| 0| (sfx && sfx->getCont() && ------------------ | Branch (2415:13): [True: 0, False: 0] | Branch (2415:20): [True: 0, False: 0] ------------------ 2416| 0| TESTAFF(sfx->getCont(), compoundmiddle, sfx->getContLen())))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2417| 0| rv = nullptr; 2418| 0| } 2419| | 2420| | // check forbiddenwords 2421| 23.7k| if ((rv) && (rv->astr) && (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2421:11): [True: 0, False: 23.7k] | Branch (2421:11): [True: 0, False: 23.7k] | Branch (2421:19): [True: 0, False: 0] ------------------ 2422| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2423| 0| continue; 2424| | 2425| | // increment word number, if the second root has a compoundroot flag 2426| 23.7k| if ((rv) && (compoundroot) && ------------------ | Branch (2426:11): [True: 0, False: 23.7k] | Branch (2426:19): [True: 0, False: 0] ------------------ 2427| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2427:11): [True: 0, False: 0] ------------------ 2428| 0| wordnum++; 2429| 0| } 2430| | 2431| | // first word is acceptable in compound words? 2432| 23.7k| if (((rv) && ------------------ | Branch (2432:11): [True: 0, False: 23.7k] | Branch (2432:12): [True: 0, False: 23.7k] ------------------ 2433| 0| (checked_prefix || (words && words[wnum]) || (compoundflag && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2433:13): [True: 0, False: 0] | Branch (2433:32): [True: 0, False: 0] | Branch (2433:41): [True: 0, False: 0] | Branch (2433:58): [True: 0, False: 0] ------------------ 2434| 0| ((oldwordnum == 0) && compoundbegin && TESTAFF(rv->astr, compoundbegin, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2434:14): [True: 0, False: 0] | Branch (2434:35): [True: 0, False: 0] ------------------ 2435| 0| ((oldwordnum > 0) && compoundmiddle && TESTAFF(rv->astr, compoundmiddle, rv->alen)) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2435:14): [True: 0, False: 0] | Branch (2435:34): [True: 0, False: 0] ------------------ 2436| | // LANG_hu section: spec. Hungarian rule 2437| 0| || ((langnum == LANG_hu) && // hu_mov_rule ------------------ | Branch (2437:17): [True: 0, False: 0] ------------------ 2438| 0| hu_mov_rule && ------------------ | Branch (2438:17): [True: 0, False: 0] ------------------ 2439| 0| (TESTAFF(rv->astr, 'F', rv->alen) || TESTAFF(rv->astr, 'G', rv->alen) || TESTAFF(rv->astr, 'H', rv->alen))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ (TESTAFF(rv->astr, 'F', rv->alen) || TESTAFF(rv->astr, 'G', rv->alen) || TESTAFF(rv->astr, 'H', rv->alen))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ (TESTAFF(rv->astr, 'F', rv->alen) || TESTAFF(rv->astr, 'G', rv->alen) || TESTAFF(rv->astr, 'H', rv->alen))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2440| | // END of LANG_hu section 2441| 0| ) && 2442| 0| !((checkcompoundtriple && !words && // test triple letters ------------------ | Branch (2442:15): [True: 0, False: 0] | Branch (2442:38): [True: 0, False: 0] ------------------ 2443| 0| (word[i - 1] == word[i]) && ------------------ | Branch (2443:15): [True: 0, False: 0] ------------------ 2444| 0| (((i > 1) && (word[i - 1] == word[i - 2])) || ((word[i - 1] == word[i + 1])) // may be word[i+1] == '\0' ------------------ | Branch (2444:17): [True: 0, False: 0] | Branch (2444:28): [True: 0, False: 0] | Branch (2444:61): [True: 0, False: 0] ------------------ 2445| 0| )) || 2446| 0| ( 2447| | // test CHECKCOMPOUNDPATTERN 2448| 0| !checkcpdtable.empty() && !words && cpdpat_check(word, i, rv, nullptr, affixed)) || ------------------ | Branch (2448:18): [True: 0, False: 0] | Branch (2448:44): [True: 0, False: 0] | Branch (2448:54): [True: 0, False: 0] ------------------ 2449| 0| (checkcompoundcase && !words && cpdcase_check(word, i)))) ------------------ | Branch (2449:15): [True: 0, False: 0] | Branch (2449:36): [True: 0, False: 0] | Branch (2449:46): [True: 0, False: 0] ------------------ 2450| | // LANG_hu section: spec. Hungarian rule 2451| 23.7k| || ((!rv) && (langnum == LANG_hu) && hu_mov_rule && (rv = affix_check(st, 0, i, scratch)) && ------------------ | Branch (2451:15): [True: 23.7k, False: 0] | Branch (2451:24): [True: 8.84k, False: 14.8k] | Branch (2451:48): [True: 0, False: 8.84k] | Branch (2451:63): [True: 0, False: 0] ------------------ 2452| 0| (sfx && sfx->getCont() && ------------------ | Branch (2452:16): [True: 0, False: 0] | Branch (2452:23): [True: 0, False: 0] ------------------ 2453| 0| (TESTAFF(sfx->getCont(), (unsigned short)'x', sfx->getContLen()) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2454| 0| TESTAFF(sfx->getCont(), (unsigned short)'%', sfx->getContLen())))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2455| | // END of LANG_hu section 2456| 23.7k| ) { 2457| | // LANG_hu section: spec. Hungarian rule 2458| 0| if (langnum == LANG_hu) { ------------------ | Branch (2458:13): [True: 0, False: 0] ------------------ 2459| | // calculate syllable number of the word 2460| 0| numsyllable += get_syllable(st.substr(0, i)); 2461| | 2462| | // + 1 word, if syllable number of the prefix > 1 (hungarian 2463| | // convention) 2464| 0| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (2464:15): [True: 0, False: 0] | Branch (2464:15): [True: 0, False: 0] | Branch (2464:22): [True: 0, False: 0] ------------------ 2465| 0| wordnum++; 2466| 0| } 2467| | // END of LANG_hu section 2468| | 2469| | // NEXT WORD(S) 2470| 0| rv_first = rv; 2471| 0| rv = lookup(word.c_str() + i, word.size() - i); // perhaps without prefix 2472| | 2473| | // search homonym with compound flag 2474| 0| while ((rv) && ((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2474:16): [True: 0, False: 0] | Branch (2474:26): [True: 0, False: 0] ------------------ 2475| 0| !((compoundflag && !words && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2475:28): [True: 0, False: 0] | Branch (2475:44): [True: 0, False: 0] ------------------ 2476| 0| (compoundend && !words && TESTAFF(rv->astr, compoundend, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2476:28): [True: 0, False: 0] | Branch (2476:43): [True: 0, False: 0] ------------------ 2477| 0| (!defcpdtable.empty() && words && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1))))) { ------------------ | Branch (2477:28): [True: 0, False: 0] | Branch (2477:52): [True: 0, False: 0] | Branch (2477:61): [True: 0, False: 0] ------------------ 2478| 0| rv = rv->next_homonym; 2479| 0| } 2480| | 2481| 0| if (rv && words && words[wnum + 1]) { ------------------ | Branch (2481:13): [True: 0, False: 0] | Branch (2481:19): [True: 0, False: 0] | Branch (2481:28): [True: 0, False: 0] ------------------ 2482| 0| result.append(presult); 2483| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2484| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2485| 0| result.append(word, i, word.size()); 2486| 0| if (complexprefixes && HENTRY_DATA(rv)) ------------------ | Branch (2486:15): [True: 0, False: 0] | Branch (2486:34): [True: 0, False: 0] ------------------ 2487| 0| result.append(HENTRY_DATA2(rv)); 2488| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (2488:15): [True: 0, False: 0] ------------------ 2489| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2490| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 2491| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 2492| 0| } 2493| | // store the pointer of the hash entry 2494| 0| if (!complexprefixes && HENTRY_DATA(rv)) { ------------------ | Branch (2494:15): [True: 0, False: 0] | Branch (2494:35): [True: 0, False: 0] ------------------ 2495| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2496| 0| result.append(HENTRY_DATA2(rv)); 2497| 0| } 2498| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2499| 0| return 0; 2500| 0| } 2501| | 2502| 0| oldnumsyllable2 = numsyllable; 2503| 0| oldwordnum2 = wordnum; 2504| | 2505| | // LANG_hu section: spec. Hungarian rule 2506| 0| if ((rv) && (langnum == LANG_hu) && ------------------ | Branch (2506:13): [True: 0, False: 0] | Branch (2506:13): [True: 0, False: 0] | Branch (2506:21): [True: 0, False: 0] ------------------ 2507| 0| (TESTAFF(rv->astr, 'I', rv->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2507:13): [True: 0, False: 0] ------------------ 2508| 0| !(TESTAFF(rv->astr, 'J', rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2508:13): [True: 0, False: 0] ------------------ 2509| 0| numsyllable--; 2510| 0| } 2511| | // END of LANG_hu section 2512| | // increment word number, if the second root has a compoundroot flag 2513| 0| if ((rv) && (compoundroot) && ------------------ | Branch (2513:13): [True: 0, False: 0] | Branch (2513:21): [True: 0, False: 0] ------------------ 2514| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2514:13): [True: 0, False: 0] ------------------ 2515| 0| wordnum++; 2516| 0| } 2517| | 2518| | // check forbiddenwords 2519| 0| if ((rv) && (rv->astr) && ------------------ | Branch (2519:13): [True: 0, False: 0] | Branch (2519:13): [True: 0, False: 0] | Branch (2519:21): [True: 0, False: 0] ------------------ 2520| 0| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2521| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2522| 0| st[i] = ch; 2523| 0| continue; 2524| 0| } 2525| | 2526| | // second word is acceptable, as a root? 2527| | // hungarian conventions: compounding is acceptable, 2528| | // when compound forms consist of 2 words, or if more, 2529| | // then the syllable number of root words must be 6, or lesser. 2530| 0| if ((rv) && ------------------ | Branch (2530:13): [True: 0, False: 0] | Branch (2530:13): [True: 0, False: 0] ------------------ 2531| 0| ((compoundflag && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2531:15): [True: 0, False: 0] ------------------ 2532| 0| (compoundend && TESTAFF(rv->astr, compoundend, rv->alen))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2532:15): [True: 0, False: 0] ------------------ 2533| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (2533:15): [True: 0, False: 0] | Branch (2533:37): [True: 0, False: 0] ------------------ 2534| 0| ((cpdmaxsyllable != 0) && ------------------ | Branch (2534:15): [True: 0, False: 0] ------------------ 2535| 0| (numsyllable + get_syllable(std::string(HENTRY_WORD(rv), rv->blen)) <= ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ | Branch (2535:15): [True: 0, False: 0] ------------------ 2536| 0| cpdmaxsyllable))) && 2537| 0| ((!checkcompounddup || (rv != rv_first)))) { ------------------ | Branch (2537:15): [True: 0, False: 0] | Branch (2537:36): [True: 0, False: 0] ------------------ 2538| | // bad compound word 2539| 0| result.append(presult); 2540| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2541| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2542| 0| result.append(word, i, word.size()); 2543| | 2544| 0| if (HENTRY_DATA(rv)) { ------------------ | Branch (2544:15): [True: 0, False: 0] ------------------ 2545| 0| if (complexprefixes) ------------------ | Branch (2545:17): [True: 0, False: 0] ------------------ 2546| 0| result.append(HENTRY_DATA2(rv)); 2547| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (2547:17): [True: 0, False: 0] ------------------ 2548| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2549| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 2550| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 2551| 0| } 2552| | // store the pointer of the hash entry 2553| 0| if (!complexprefixes) { ------------------ | Branch (2553:17): [True: 0, False: 0] ------------------ 2554| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2555| 0| result.append(HENTRY_DATA2(rv)); 2556| 0| } 2557| 0| } 2558| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2559| 0| ok = 1; 2560| 0| } 2561| | 2562| 0| numsyllable = oldnumsyllable2; 2563| 0| wordnum = oldwordnum2; 2564| | 2565| | // perhaps second word has prefix or/and suffix 2566| 0| sfx = nullptr; 2567| 0| sfxflag = FLAG_NULL; ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ 2568| | 2569| 0| if (compoundflag && !onlycpdrule) ------------------ | Branch (2569:13): [True: 0, False: 0] | Branch (2569:29): [True: 0, False: 0] ------------------ 2570| 0| rv = affix_check(word, i, word.size() - i, scratch, compoundflag); 2571| 0| else 2572| 0| rv = nullptr; 2573| | 2574| 0| if (!rv && compoundend && !onlycpdrule) { ------------------ | Branch (2574:13): [True: 0, False: 0] | Branch (2574:20): [True: 0, False: 0] | Branch (2574:35): [True: 0, False: 0] ------------------ 2575| 0| sfx = nullptr; 2576| 0| pfx = nullptr; 2577| 0| rv = affix_check(word, i, word.size() - i, scratch, compoundend); 2578| 0| } 2579| | 2580| 0| if (!rv && !defcpdtable.empty() && words) { ------------------ | Branch (2580:13): [True: 0, False: 0] | Branch (2580:20): [True: 0, False: 0] | Branch (2580:44): [True: 0, False: 0] ------------------ 2581| 0| rv = affix_check(word, i, word.size() - i, scratch, 0, IN_CPD_END); ------------------ | | 74| 0|#define IN_CPD_END 2 ------------------ 2582| 0| if (rv && words && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1)) { ------------------ | Branch (2582:15): [True: 0, False: 0] | Branch (2582:21): [True: 0, False: 0] | Branch (2582:30): [True: 0, False: 0] ------------------ 2583| 0| std::string m; 2584| 0| if (compoundflag) ------------------ | Branch (2584:17): [True: 0, False: 0] ------------------ 2585| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundflag); 2586| 0| if (m.empty() && compoundend) { ------------------ | Branch (2586:17): [True: 0, False: 0] | Branch (2586:30): [True: 0, False: 0] ------------------ 2587| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundend); 2588| 0| } 2589| 0| result.append(presult); 2590| 0| if (!m.empty()) { ------------------ | Branch (2590:17): [True: 0, False: 0] ------------------ 2591| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2592| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2593| 0| result.append(word, i, word.size()); 2594| 0| line_uniq_app(m, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2595| 0| result.append(m); 2596| 0| } 2597| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2598| 0| ok = 1; 2599| 0| } 2600| 0| } 2601| | 2602| | // check non_compound flag in suffix and prefix 2603| 0| if ((rv) && ------------------ | Branch (2603:13): [True: 0, False: 0] ------------------ 2604| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2604:15): [True: 0, False: 0] | Branch (2604:22): [True: 0, False: 0] ------------------ 2605| 0| TESTAFF(pfx->getCont(), compoundforbidflag, pfx->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2606| 0| (sfx && sfx->getCont() && ------------------ | Branch (2606:15): [True: 0, False: 0] | Branch (2606:22): [True: 0, False: 0] ------------------ 2607| 0| TESTAFF(sfx->getCont(), compoundforbidflag, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2608| 0| sfx->getContLen())))) { 2609| 0| rv = nullptr; 2610| 0| } 2611| | 2612| | // check forbiddenwords 2613| 0| if ((rv) && (rv->astr) && ------------------ | Branch (2613:13): [True: 0, False: 0] | Branch (2613:13): [True: 0, False: 0] | Branch (2613:21): [True: 0, False: 0] ------------------ 2614| 0| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2615| 0| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2616| 0| (!TESTAFF(rv->astr, needaffix, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2616:13): [True: 0, False: 0] ------------------ 2617| 0| st[i] = ch; 2618| 0| continue; 2619| 0| } 2620| | 2621| 0| if (langnum == LANG_hu) { ------------------ | Branch (2621:13): [True: 0, False: 0] ------------------ 2622| | // calculate syllable number of the word 2623| 0| numsyllable += get_syllable(word.c_str() + i); 2624| | 2625| | // - affix syllable num. 2626| | // XXX only second suffix (inflections, not derivations) 2627| 0| if (sfxappnd) { ------------------ | Branch (2627:15): [True: 0, False: 0] ------------------ 2628| 0| std::string tmp(sfxappnd); 2629| 0| reverseword(tmp); 2630| 0| numsyllable -= short(get_syllable(tmp) + sfxextra); 2631| 0| } else { 2632| 0| numsyllable -= short(sfxextra); 2633| 0| } 2634| | 2635| | // + 1 word, if syllable number of the prefix > 1 (hungarian 2636| | // convention) 2637| 0| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (2637:15): [True: 0, False: 0] | Branch (2637:15): [True: 0, False: 0] | Branch (2637:22): [True: 0, False: 0] ------------------ 2638| 0| wordnum++; 2639| | 2640| | // increment syllable num, if last word has a SYLLABLENUM flag 2641| | // and the suffix is beginning `s' 2642| | 2643| 0| if (!cpdsyllablenum.empty()) { ------------------ | Branch (2643:15): [True: 0, False: 0] ------------------ 2644| 0| switch (sfxflag) { ------------------ | Branch (2644:21): [True: 0, False: 0] ------------------ 2645| 0| case 'c': { ------------------ | Branch (2645:15): [True: 0, False: 0] ------------------ 2646| 0| numsyllable += 2; 2647| 0| break; 2648| 0| } 2649| 0| case 'J': { ------------------ | Branch (2649:15): [True: 0, False: 0] ------------------ 2650| 0| numsyllable += 1; 2651| 0| break; 2652| 0| } 2653| 0| case 'I': { ------------------ | Branch (2653:15): [True: 0, False: 0] ------------------ 2654| 0| if (rv && TESTAFF(rv->astr, 'J', rv->alen)) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2654:21): [True: 0, False: 0] | Branch (2654:21): [True: 0, False: 0] ------------------ 2655| 0| numsyllable += 1; 2656| 0| break; 2657| 0| } 2658| 0| } 2659| 0| } 2660| 0| } 2661| | 2662| | // increment word number, if the second word has a compoundroot flag 2663| 0| if ((rv) && (compoundroot) && ------------------ | Branch (2663:13): [True: 0, False: 0] | Branch (2663:21): [True: 0, False: 0] ------------------ 2664| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2664:13): [True: 0, False: 0] ------------------ 2665| 0| wordnum++; 2666| 0| } 2667| | // second word is acceptable, as a word with prefix or/and suffix? 2668| | // hungarian conventions: compounding is acceptable, 2669| | // when compound forms consist 2 word, otherwise 2670| | // the syllable number of root words is 6, or lesser. 2671| 0| if ((rv) && ------------------ | Branch (2671:13): [True: 0, False: 0] ------------------ 2672| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (2672:15): [True: 0, False: 0] | Branch (2672:37): [True: 0, False: 0] ------------------ 2673| 0| ((cpdmaxsyllable != 0) && (numsyllable <= cpdmaxsyllable))) && ------------------ | Branch (2673:15): [True: 0, False: 0] | Branch (2673:40): [True: 0, False: 0] ------------------ 2674| 0| ((!checkcompounddup || (rv != rv_first)))) { ------------------ | Branch (2674:15): [True: 0, False: 0] | Branch (2674:36): [True: 0, False: 0] ------------------ 2675| 0| std::string m; 2676| 0| if (compoundflag) ------------------ | Branch (2676:15): [True: 0, False: 0] ------------------ 2677| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundflag); 2678| 0| if (m.empty() && compoundend) { ------------------ | Branch (2678:15): [True: 0, False: 0] | Branch (2678:28): [True: 0, False: 0] ------------------ 2679| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundend); 2680| 0| } 2681| 0| result.append(presult); 2682| 0| if (!m.empty()) { ------------------ | Branch (2682:15): [True: 0, False: 0] ------------------ 2683| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2684| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2685| 0| result.append(word, i, word.size()); 2686| 0| line_uniq_app(m, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2687| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2688| 0| result.append(m); 2689| 0| } 2690| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2691| 0| ok = 1; 2692| 0| } 2693| | 2694| 0| numsyllable = oldnumsyllable2; 2695| 0| wordnum = oldwordnum2; 2696| | 2697| | // perhaps second word is a compound word (recursive call) 2698| 0| if ((wordnum + 2 < maxwordnum) && (wnum + 1 < maxwordnum) && (ok == 0)) { ------------------ | Branch (2698:13): [True: 0, False: 0] | Branch (2698:43): [True: 0, False: 0] | Branch (2698:70): [True: 0, False: 0] ------------------ 2699| 0| compound_check_morph(word.substr(i), wordnum + 1, 2700| 0| numsyllable, maxwordnum, wnum + 1, words, rwords, 0, 2701| 0| result, &presult, scratch); 2702| 0| } else { 2703| 0| rv = nullptr; 2704| 0| } 2705| 0| } 2706| 23.7k| st[i] = ch; 2707| 23.7k| wordnum = oldwordnum; 2708| 23.7k| numsyllable = oldnumsyllable; 2709| | 2710| 23.7k| } while (!defcpdtable.empty() && oldwordnum == 0 && ------------------ | Branch (2710:14): [True: 0, False: 23.7k] | Branch (2710:38): [True: 0, False: 0] ------------------ 2711| 0| onlycpdrule++ < 1); // end of onlycpd loop ------------------ | Branch (2711:14): [True: 0, False: 0] ------------------ 2712| 23.8k| } 2713| 1.82k| return 0; 2714| 2.05k|} _ZN8AffixMgr12suffix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratchttc: 2737| 603M| char in_compound) { 2738| 603M| struct hentry* rv = nullptr; 2739| 603M| PfxEntry* ep = ppfx; 2740| | 2741| | // first handle the special case of 0 length suffixes 2742| 603M| SfxEntry* se = sStart[0]; 2743| | 2744| 603M| while (se) { ------------------ | Branch (2744:10): [True: 0, False: 603M] ------------------ 2745| 0| if (!cclass || se->getCont()) { ------------------ | Branch (2745:9): [True: 0, False: 0] | Branch (2745:20): [True: 0, False: 0] ------------------ 2746| | // suffixes are not allowed in beginning of compounds 2747| 0| if ((((in_compound != IN_CPD_BEGIN)) || // && !cclass ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2747:12): [True: 0, False: 0] ------------------ 2748| | // except when signed with compoundpermitflag flag 2749| 0| (se->getCont() && compoundpermitflag && ------------------ | Branch (2749:13): [True: 0, False: 0] | Branch (2749:30): [True: 0, False: 0] ------------------ 2750| 0| TESTAFF(se->getCont(), compoundpermitflag, se->getContLen()))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2751| 0| (!circumfix || ------------------ | Branch (2751:12): [True: 0, False: 0] ------------------ 2752| | // no circumfix flag in prefix and suffix 2753| 0| ((!ppfx || !(ep->getCont()) || ------------------ | Branch (2753:14): [True: 0, False: 0] | Branch (2753:23): [True: 0, False: 0] ------------------ 2754| 0| !TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2754:14): [True: 0, False: 0] ------------------ 2755| 0| (!se->getCont() || ------------------ | Branch (2755:14): [True: 0, False: 0] ------------------ 2756| 0| !(TESTAFF(se->getCont(), circumfix, se->getContLen())))) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2756:14): [True: 0, False: 0] ------------------ 2757| | // circumfix flag in prefix AND suffix 2758| 0| ((ppfx && (ep->getCont()) && ------------------ | Branch (2758:14): [True: 0, False: 0] | Branch (2758:22): [True: 0, False: 0] ------------------ 2759| 0| TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2760| 0| (se->getCont() && ------------------ | Branch (2760:14): [True: 0, False: 0] ------------------ 2761| 0| (TESTAFF(se->getCont(), circumfix, se->getContLen()))))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2761:14): [True: 0, False: 0] ------------------ 2762| | // fogemorpheme 2763| 0| (in_compound || ------------------ | Branch (2763:12): [True: 0, False: 0] ------------------ 2764| 0| !(se->getCont() && ------------------ | Branch (2764:14): [True: 0, False: 0] ------------------ 2765| 0| (TESTAFF(se->getCont(), onlyincompound, se->getContLen())))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2765:14): [True: 0, False: 0] ------------------ 2766| | // needaffix on prefix or first suffix 2767| 0| (cclass || ------------------ | Branch (2767:12): [True: 0, False: 0] ------------------ 2768| 0| !(se->getCont() && ------------------ | Branch (2768:14): [True: 0, False: 0] ------------------ 2769| 0| TESTAFF(se->getCont(), needaffix, se->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2770| 0| (ppfx && ------------------ | Branch (2770:13): [True: 0, False: 0] ------------------ 2771| 0| !((ep->getCont()) && ------------------ | Branch (2771:15): [True: 0, False: 0] ------------------ 2772| 0| TESTAFF(ep->getCont(), needaffix, ep->getContLen()))))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2773| 0| rv = se->checkword(word, start, len, sfxopts, ppfx, 2774| 0| (FLAG)cclass, needflag, 2775| 0| (in_compound ? 0 : onlyincompound), ------------------ | Branch (2775:29): [True: 0, False: 0] ------------------ 2776| 0| scratch); 2777| 0| if (rv) { ------------------ | Branch (2777:13): [True: 0, False: 0] ------------------ 2778| 0| sfx = se; // BUG: sfx not stateless 2779| 0| return rv; 2780| 0| } 2781| 0| } 2782| 0| } 2783| 0| se = se->getNext(); 2784| 0| } 2785| | 2786| | // now handle the general case 2787| 603M| if (len == 0) ------------------ | Branch (2787:7): [True: 38.5k, False: 603M] ------------------ 2788| 38.5k| return nullptr; // FULLSTRIP 2789| 603M| unsigned char sp = word[start + len - 1]; 2790| 603M| SfxEntry* sptr = sStart[sp]; 2791| | 2792| 603M| while (sptr) { ------------------ | Branch (2792:10): [True: 547k, False: 603M] ------------------ 2793| 547k| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (2793:9): [True: 488k, False: 58.8k] ------------------ 2794| | // suffixes are not allowed in beginning of compounds 2795| 488k| if ((((in_compound != IN_CPD_BEGIN)) || // && !cclass ------------------ | | 73| 488k|#define IN_CPD_BEGIN 1 ------------------ | Branch (2795:12): [True: 81.4k, False: 406k] ------------------ 2796| | // except when signed with compoundpermitflag flag 2797| 406k| (sptr->getCont() && compoundpermitflag && ------------------ | Branch (2797:13): [True: 406k, False: 0] | Branch (2797:32): [True: 0, False: 406k] ------------------ 2798| 0| TESTAFF(sptr->getCont(), compoundpermitflag, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2799| 406k| sptr->getContLen()))) && 2800| 81.4k| (!circumfix || ------------------ | Branch (2800:12): [True: 81.4k, False: 0] ------------------ 2801| | // no circumfix flag in prefix and suffix 2802| 0| ((!ppfx || !(ep->getCont()) || ------------------ | Branch (2802:14): [True: 0, False: 0] | Branch (2802:23): [True: 0, False: 0] ------------------ 2803| 0| !TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2803:14): [True: 0, False: 0] ------------------ 2804| 0| (!sptr->getCont() || ------------------ | Branch (2804:14): [True: 0, False: 0] ------------------ 2805| 0| !(TESTAFF(sptr->getCont(), circumfix, sptr->getContLen())))) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2805:14): [True: 0, False: 0] ------------------ 2806| | // circumfix flag in prefix AND suffix 2807| 0| ((ppfx && (ep->getCont()) && ------------------ | Branch (2807:14): [True: 0, False: 0] | Branch (2807:22): [True: 0, False: 0] ------------------ 2808| 0| TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2809| 0| (sptr->getCont() && ------------------ | Branch (2809:14): [True: 0, False: 0] ------------------ 2810| 0| (TESTAFF(sptr->getCont(), circumfix, sptr->getContLen()))))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2810:14): [True: 0, False: 0] ------------------ 2811| | // fogemorpheme 2812| 81.4k| (in_compound || ------------------ | Branch (2812:12): [True: 0, False: 81.4k] ------------------ 2813| 81.4k| !((sptr->getCont() && (TESTAFF(sptr->getCont(), onlyincompound, ------------------ | | 99| 56.2k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2813:15): [True: 56.2k, False: 25.1k] | Branch (2813:34): [True: 0, False: 56.2k] ------------------ 2814| 56.2k| sptr->getContLen()))))) && 2815| | // needaffix on prefix or first suffix 2816| 81.4k| (cclass || ------------------ | Branch (2816:12): [True: 1.42k, False: 79.9k] ------------------ 2817| 79.9k| !(sptr->getCont() && ------------------ | Branch (2817:14): [True: 55.8k, False: 24.1k] ------------------ 2818| 55.8k| TESTAFF(sptr->getCont(), needaffix, sptr->getContLen())) || ------------------ | | 99| 55.8k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 55.8k] | | ------------------ ------------------ 2819| 0| (ppfx && ------------------ | Branch (2819:13): [True: 0, False: 0] ------------------ 2820| 0| !((ep->getCont()) && ------------------ | Branch (2820:15): [True: 0, False: 0] ------------------ 2821| 0| TESTAFF(ep->getCont(), needaffix, ep->getContLen()))))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2822| 81.4k| if (in_compound != IN_CPD_END || ppfx || ------------------ | | 74| 162k|#define IN_CPD_END 2 ------------------ | Branch (2822:13): [True: 81.4k, False: 0] | Branch (2822:42): [True: 0, False: 0] ------------------ 2823| 0| !(sptr->getCont() && ------------------ | Branch (2823:15): [True: 0, False: 0] ------------------ 2824| 81.4k| TESTAFF(sptr->getCont(), onlyincompound, sptr->getContLen()))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2825| 81.4k| rv = sptr->checkword(word, start, len, sfxopts, ppfx, 2826| 81.4k| cclass, needflag, 2827| 81.4k| (in_compound ? 0 : onlyincompound), ------------------ | Branch (2827:33): [True: 0, False: 81.4k] ------------------ 2828| 81.4k| scratch); 2829| 81.4k| if (rv) { ------------------ | Branch (2829:15): [True: 2, False: 81.4k] ------------------ 2830| 2| sfx = sptr; // BUG: sfx not stateless 2831| 2| sfxflag = sptr->getFlag(); // BUG: sfxflag not stateless 2832| 2| if (!sptr->getCont()) ------------------ | Branch (2832:17): [True: 1, False: 1] ------------------ 2833| 1| sfxappnd = sptr->getKey(); // BUG: sfxappnd not stateless 2834| | // LANG_hu section: spec. Hungarian rule 2835| 1| else if (langnum == LANG_hu && sptr->getKeyLen() && ------------------ | Branch (2835:22): [True: 0, False: 1] | Branch (2835:44): [True: 0, False: 0] ------------------ 2836| 0| sptr->getKey()[0] == 'i' && sptr->getKey()[1] != 'y' && ------------------ | Branch (2836:22): [True: 0, False: 0] | Branch (2836:50): [True: 0, False: 0] ------------------ 2837| 0| sptr->getKey()[1] != 't') { ------------------ | Branch (2837:22): [True: 0, False: 0] ------------------ 2838| 0| sfxextra = 1; 2839| 0| } 2840| | // END of LANG_hu section 2841| 2| return rv; 2842| 2| } 2843| 81.4k| } 2844| 488k| sptr = sptr->getNextEQ(); 2845| 488k| } else { 2846| 58.8k| sptr = sptr->getNextNE(); 2847| 58.8k| } 2848| 547k| } 2849| | 2850| 603M| return nullptr; 2851| 603M|} _ZN8AffixMgr19suffix_check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratcht: 2860| 16.2M| const FLAG needflag) { 2861| 16.2M| struct hentry* rv = nullptr; 2862| | 2863| | // first handle the special case of 0 length suffixes 2864| 16.2M| SfxEntry* se = sStart[0]; 2865| 16.2M| while (se) { ------------------ | Branch (2865:10): [True: 0, False: 16.2M] ------------------ 2866| 0| if (contclasses[se->getFlag()]) { ------------------ | Branch (2866:9): [True: 0, False: 0] ------------------ 2867| 0| rv = se->check_twosfx(word, start, len, sfxopts, ppfx, needflag, scratch); 2868| 0| if (rv) ------------------ | Branch (2868:11): [True: 0, False: 0] ------------------ 2869| 0| return rv; 2870| 0| } 2871| 0| se = se->getNext(); 2872| 0| } 2873| | 2874| | // now handle the general case 2875| 16.2M| if (len == 0) ------------------ | Branch (2875:7): [True: 12.1k, False: 16.2M] ------------------ 2876| 12.1k| return nullptr; // FULLSTRIP 2877| 16.2M| unsigned char sp = word[start + len - 1]; 2878| 16.2M| SfxEntry* sptr = sStart[sp]; 2879| | 2880| 16.3M| while (sptr) { ------------------ | Branch (2880:10): [True: 121k, False: 16.2M] ------------------ 2881| 121k| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (2881:9): [True: 75.0k, False: 46.4k] ------------------ 2882| 75.0k| if (contclasses[sptr->getFlag()]) { ------------------ | Branch (2882:11): [True: 19.2k, False: 55.8k] ------------------ 2883| 19.2k| rv = sptr->check_twosfx(word, start, len, sfxopts, ppfx, needflag, scratch); 2884| 19.2k| if (rv) { ------------------ | Branch (2884:13): [True: 0, False: 19.2k] ------------------ 2885| 0| sfxflag = sptr->getFlag(); // BUG: sfxflag not stateless 2886| 0| if (!sptr->getCont()) ------------------ | Branch (2886:15): [True: 0, False: 0] ------------------ 2887| 0| sfxappnd = sptr->getKey(); // BUG: sfxappnd not stateless 2888| 0| return rv; 2889| 0| } 2890| 19.2k| } 2891| 75.0k| sptr = sptr->getNextEQ(); 2892| 75.0k| } else { 2893| 46.4k| sptr = sptr->getNextNE(); 2894| 46.4k| } 2895| 121k| } 2896| | 2897| 16.2M| return nullptr; 2898| 16.2M|} _ZN8AffixMgr25suffix_check_twosfx_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratcht: 2907| 4.24k| const FLAG needflag) { 2908| 4.24k| std::string result; 2909| 4.24k| std::string result2; 2910| 4.24k| std::string result3; 2911| | 2912| | // first handle the special case of 0 length suffixes 2913| 4.24k| SfxEntry* se = sStart[0]; 2914| 4.24k| while (se) { ------------------ | Branch (2914:10): [True: 0, False: 4.24k] ------------------ 2915| 0| if (contclasses[se->getFlag()]) { ------------------ | Branch (2915:9): [True: 0, False: 0] ------------------ 2916| 0| std::string st = se->check_twosfx_morph(word, start, len, sfxopts, ppfx, needflag, scratch); 2917| 0| if (!st.empty()) { ------------------ | Branch (2917:11): [True: 0, False: 0] ------------------ 2918| 0| if (ppfx) { ------------------ | Branch (2918:13): [True: 0, False: 0] ------------------ 2919| 0| if (ppfx->getMorph()) { ------------------ | Branch (2919:15): [True: 0, False: 0] ------------------ 2920| 0| result.append(ppfx->getMorph()); 2921| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2922| 0| } else 2923| 0| debugflag(result, ppfx->getFlag()); 2924| 0| } 2925| 0| result.append(st); 2926| 0| if (se->getMorph()) { ------------------ | Branch (2926:13): [True: 0, False: 0] ------------------ 2927| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2928| 0| result.append(se->getMorph()); 2929| 0| } else 2930| 0| debugflag(result, se->getFlag()); 2931| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2932| 0| } 2933| 0| } 2934| 0| se = se->getNext(); 2935| 0| } 2936| | 2937| | // now handle the general case 2938| 4.24k| if (len == 0) ------------------ | Branch (2938:7): [True: 3, False: 4.24k] ------------------ 2939| 3| return { }; // FULLSTRIP 2940| 4.24k| unsigned char sp = word[start + len - 1]; 2941| 4.24k| SfxEntry* sptr = sStart[sp]; 2942| | 2943| 4.25k| while (sptr) { ------------------ | Branch (2943:10): [True: 5, False: 4.24k] ------------------ 2944| 5| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (2944:9): [True: 0, False: 5] ------------------ 2945| 0| if (contclasses[sptr->getFlag()]) { ------------------ | Branch (2945:11): [True: 0, False: 0] ------------------ 2946| 0| std::string st = sptr->check_twosfx_morph(word, start, len, sfxopts, ppfx, needflag, scratch); 2947| 0| if (!st.empty()) { ------------------ | Branch (2947:13): [True: 0, False: 0] ------------------ 2948| 0| sfxflag = sptr->getFlag(); // BUG: sfxflag not stateless 2949| 0| if (!sptr->getCont()) ------------------ | Branch (2949:15): [True: 0, False: 0] ------------------ 2950| 0| sfxappnd = sptr->getKey(); // BUG: sfxappnd not stateless 2951| 0| result2.assign(st); 2952| | 2953| 0| result3.clear(); 2954| | 2955| 0| if (sptr->getMorph()) { ------------------ | Branch (2955:15): [True: 0, False: 0] ------------------ 2956| 0| result3.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2957| 0| result3.append(sptr->getMorph()); 2958| 0| } else 2959| 0| debugflag(result3, sptr->getFlag()); 2960| 0| strlinecat(result2, result3); 2961| 0| result2.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2962| 0| result.append(result2); 2963| 0| } 2964| 0| } 2965| 0| sptr = sptr->getNextEQ(); 2966| 5| } else { 2967| 5| sptr = sptr->getNextNE(); 2968| 5| } 2969| 5| } 2970| | 2971| 4.24k| return result; 2972| 4.24k|} _ZN8AffixMgr18suffix_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratchttc: 2982| 13.6k| char in_compound) { 2983| 13.6k| std::string result; 2984| | 2985| 13.6k| struct hentry* rv = nullptr; 2986| | 2987| 13.6k| PfxEntry* ep = ppfx; 2988| | 2989| | // first handle the special case of 0 length suffixes 2990| 13.6k| SfxEntry* se = sStart[0]; 2991| 13.6k| while (se) { ------------------ | Branch (2991:10): [True: 0, False: 13.6k] ------------------ 2992| 0| if (!cclass || se->getCont()) { ------------------ | Branch (2992:9): [True: 0, False: 0] | Branch (2992:20): [True: 0, False: 0] ------------------ 2993| | // suffixes are not allowed in beginning of compounds 2994| 0| if (((((in_compound != IN_CPD_BEGIN)) || // && !cclass ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2994:13): [True: 0, False: 0] ------------------ 2995| | // except when signed with compoundpermitflag flag 2996| 0| (se->getCont() && compoundpermitflag && ------------------ | Branch (2996:14): [True: 0, False: 0] | Branch (2996:31): [True: 0, False: 0] ------------------ 2997| 0| TESTAFF(se->getCont(), compoundpermitflag, se->getContLen()))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 2998| 0| (!circumfix || ------------------ | Branch (2998:13): [True: 0, False: 0] ------------------ 2999| | // no circumfix flag in prefix and suffix 3000| 0| ((!ppfx || !(ep->getCont()) || ------------------ | Branch (3000:15): [True: 0, False: 0] | Branch (3000:24): [True: 0, False: 0] ------------------ 3001| 0| !TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3001:15): [True: 0, False: 0] ------------------ 3002| 0| (!se->getCont() || ------------------ | Branch (3002:15): [True: 0, False: 0] ------------------ 3003| 0| !(TESTAFF(se->getCont(), circumfix, se->getContLen())))) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3003:15): [True: 0, False: 0] ------------------ 3004| | // circumfix flag in prefix AND suffix 3005| 0| ((ppfx && (ep->getCont()) && ------------------ | Branch (3005:15): [True: 0, False: 0] | Branch (3005:23): [True: 0, False: 0] ------------------ 3006| 0| TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3007| 0| (se->getCont() && ------------------ | Branch (3007:15): [True: 0, False: 0] ------------------ 3008| 0| (TESTAFF(se->getCont(), circumfix, se->getContLen()))))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3008:15): [True: 0, False: 0] ------------------ 3009| | // fogemorpheme 3010| 0| (in_compound || ------------------ | Branch (3010:13): [True: 0, False: 0] ------------------ 3011| 0| !((se->getCont() && ------------------ | Branch (3011:16): [True: 0, False: 0] ------------------ 3012| 0| (TESTAFF(se->getCont(), onlyincompound, se->getContLen()))))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3012:16): [True: 0, False: 0] ------------------ 3013| | // needaffix on prefix or first suffix 3014| 0| (cclass || ------------------ | Branch (3014:13): [True: 0, False: 0] ------------------ 3015| 0| !(se->getCont() && ------------------ | Branch (3015:15): [True: 0, False: 0] ------------------ 3016| 0| TESTAFF(se->getCont(), needaffix, se->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3017| 0| (ppfx && ------------------ | Branch (3017:14): [True: 0, False: 0] ------------------ 3018| 0| !((ep->getCont()) && ------------------ | Branch (3018:16): [True: 0, False: 0] ------------------ 3019| 0| TESTAFF(ep->getCont(), needaffix, ep->getContLen())))))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3020| 0| rv = se->checkword(word, start, len, sfxopts, ppfx, cclass, 3021| 0| needflag, FLAG_NULL, scratch); ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ 3022| 0| while (rv) { ------------------ | Branch (3022:14): [True: 0, False: 0] ------------------ 3023| 0| if (ppfx) { ------------------ | Branch (3023:13): [True: 0, False: 0] ------------------ 3024| 0| if (ppfx->getMorph()) { ------------------ | Branch (3024:15): [True: 0, False: 0] ------------------ 3025| 0| result.append(ppfx->getMorph()); 3026| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3027| 0| } else 3028| 0| debugflag(result, ppfx->getFlag()); 3029| 0| } 3030| 0| if (complexprefixes && HENTRY_DATA(rv)) ------------------ | Branch (3030:13): [True: 0, False: 0] | Branch (3030:32): [True: 0, False: 0] ------------------ 3031| 0| result.append(HENTRY_DATA2(rv)); 3032| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (3032:13): [True: 0, False: 0] ------------------ 3033| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3034| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 3035| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 3036| 0| } 3037| | 3038| 0| if (!complexprefixes && HENTRY_DATA(rv)) { ------------------ | Branch (3038:13): [True: 0, False: 0] | Branch (3038:33): [True: 0, False: 0] ------------------ 3039| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3040| 0| result.append(HENTRY_DATA2(rv)); 3041| 0| } 3042| 0| if (se->getMorph()) { ------------------ | Branch (3042:13): [True: 0, False: 0] ------------------ 3043| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3044| 0| result.append(se->getMorph()); 3045| 0| } else 3046| 0| debugflag(result, se->getFlag()); 3047| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 3048| 0| rv = se->get_next_homonym(rv, sfxopts, ppfx, cclass, needflag); 3049| 0| } 3050| 0| } 3051| 0| se = se->getNext(); 3052| 0| } 3053| | 3054| | // now handle the general case 3055| 13.6k| if (len == 0) ------------------ | Branch (3055:7): [True: 3, False: 13.6k] ------------------ 3056| 3| return { }; // FULLSTRIP 3057| 13.6k| unsigned char sp = word[start + len - 1]; 3058| 13.6k| SfxEntry* sptr = sStart[sp]; 3059| | 3060| 13.6k| while (sptr) { ------------------ | Branch (3060:10): [True: 5, False: 13.6k] ------------------ 3061| 5| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (3061:9): [True: 0, False: 5] ------------------ 3062| | // suffixes are not allowed in beginning of compounds 3063| 0| if (((((in_compound != IN_CPD_BEGIN)) || // && !cclass ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (3063:13): [True: 0, False: 0] ------------------ 3064| | // except when signed with compoundpermitflag flag 3065| 0| (sptr->getCont() && compoundpermitflag && ------------------ | Branch (3065:14): [True: 0, False: 0] | Branch (3065:33): [True: 0, False: 0] ------------------ 3066| 0| TESTAFF(sptr->getCont(), compoundpermitflag, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3067| 0| sptr->getContLen()))) && 3068| 0| (!circumfix || ------------------ | Branch (3068:13): [True: 0, False: 0] ------------------ 3069| | // no circumfix flag in prefix and suffix 3070| 0| ((!ppfx || !(ep->getCont()) || ------------------ | Branch (3070:15): [True: 0, False: 0] | Branch (3070:24): [True: 0, False: 0] ------------------ 3071| 0| !TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3071:15): [True: 0, False: 0] ------------------ 3072| 0| (!sptr->getCont() || ------------------ | Branch (3072:15): [True: 0, False: 0] ------------------ 3073| 0| !(TESTAFF(sptr->getCont(), circumfix, sptr->getContLen())))) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3073:15): [True: 0, False: 0] ------------------ 3074| | // circumfix flag in prefix AND suffix 3075| 0| ((ppfx && (ep->getCont()) && ------------------ | Branch (3075:15): [True: 0, False: 0] | Branch (3075:23): [True: 0, False: 0] ------------------ 3076| 0| TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3077| 0| (sptr->getCont() && ------------------ | Branch (3077:15): [True: 0, False: 0] ------------------ 3078| 0| (TESTAFF(sptr->getCont(), circumfix, sptr->getContLen()))))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3078:15): [True: 0, False: 0] ------------------ 3079| | // fogemorpheme 3080| 0| (in_compound || ------------------ | Branch (3080:13): [True: 0, False: 0] ------------------ 3081| 0| !((sptr->getCont() && (TESTAFF(sptr->getCont(), onlyincompound, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3081:16): [True: 0, False: 0] | Branch (3081:35): [True: 0, False: 0] ------------------ 3082| 0| sptr->getContLen()))))) && 3083| | // needaffix on first suffix 3084| 0| (cclass || ------------------ | Branch (3084:13): [True: 0, False: 0] ------------------ 3085| 0| !(sptr->getCont() && ------------------ | Branch (3085:15): [True: 0, False: 0] ------------------ 3086| 0| TESTAFF(sptr->getCont(), needaffix, sptr->getContLen()))))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3087| 0| rv = sptr->checkword(word, start, len, sfxopts, ppfx, cclass, 3088| 0| needflag, FLAG_NULL, scratch); ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ 3089| 0| while (rv) { ------------------ | Branch (3089:14): [True: 0, False: 0] ------------------ 3090| 0| if (ppfx) { ------------------ | Branch (3090:13): [True: 0, False: 0] ------------------ 3091| 0| if (ppfx->getMorph()) { ------------------ | Branch (3091:15): [True: 0, False: 0] ------------------ 3092| 0| result.append(ppfx->getMorph()); 3093| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3094| 0| } else 3095| 0| debugflag(result, ppfx->getFlag()); 3096| 0| } 3097| 0| if (complexprefixes && HENTRY_DATA(rv)) ------------------ | Branch (3097:13): [True: 0, False: 0] | Branch (3097:32): [True: 0, False: 0] ------------------ 3098| 0| result.append(HENTRY_DATA2(rv)); 3099| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (3099:13): [True: 0, False: 0] ------------------ 3100| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3101| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 3102| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 3103| 0| } 3104| | 3105| 0| if (!complexprefixes && HENTRY_DATA(rv)) { ------------------ | Branch (3105:13): [True: 0, False: 0] | Branch (3105:33): [True: 0, False: 0] ------------------ 3106| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3107| 0| result.append(HENTRY_DATA2(rv)); 3108| 0| } 3109| | 3110| 0| if (sptr->getMorph()) { ------------------ | Branch (3110:13): [True: 0, False: 0] ------------------ 3111| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3112| 0| result.append(sptr->getMorph()); 3113| 0| } else 3114| 0| debugflag(result, sptr->getFlag()); 3115| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 3116| 0| rv = sptr->get_next_homonym(rv, sfxopts, ppfx, cclass, needflag); 3117| 0| } 3118| 0| sptr = sptr->getNextEQ(); 3119| 5| } else { 3120| 5| sptr = sptr->getNextNE(); 3121| 5| } 3122| 5| } 3123| | 3124| 13.6k| return result; 3125| 13.6k|} _ZN8AffixMgr11affix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiR12AffixScratchtc: 3133| 13.3M| char in_compound) { 3134| | 3135| | // check all prefixes (also crossed with suffixes if allowed) 3136| 13.3M| struct hentry* rv = prefix_check(word, start, len, in_compound, scratch, needflag); 3137| 13.3M| if (rv) ------------------ | Branch (3137:7): [True: 0, False: 13.3M] ------------------ 3138| 0| return rv; 3139| | 3140| | // if still not found check all suffixes 3141| 13.3M| rv = suffix_check(word, start, len, 0, nullptr, scratch, FLAG_NULL, needflag, in_compound); ------------------ | | 96| 13.3M|#define FLAG_NULL 0x00 ------------------ 3142| | 3143| 13.3M| if (havecontclass) { ------------------ | Branch (3143:7): [True: 4.65M, False: 8.73M] ------------------ 3144| 4.65M| sfx = nullptr; 3145| 4.65M| pfx = nullptr; 3146| | 3147| 4.65M| if (rv) ------------------ | Branch (3147:9): [True: 0, False: 4.65M] ------------------ 3148| 0| return rv; 3149| | // if still not found check all two-level suffixes 3150| 4.65M| rv = suffix_check_twosfx(word, start, len, 0, nullptr, scratch, needflag); 3151| | 3152| 4.65M| if (rv) ------------------ | Branch (3152:9): [True: 0, False: 4.65M] ------------------ 3153| 0| return rv; 3154| | // if still not found check all two-level suffixes 3155| 4.65M| rv = prefix_check_twosfx(word, start, len, IN_CPD_NOT, scratch, needflag); ------------------ | | 72| 4.65M|#define IN_CPD_NOT 0 ------------------ 3156| 4.65M| } 3157| | 3158| 13.3M| return rv; 3159| 13.3M|} _ZN8AffixMgr17affix_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiR12AffixScratchtc: 3167| 13.6k| char in_compound) { 3168| 13.6k| std::string result; 3169| | 3170| | // check all prefixes (also crossed with suffixes if allowed) 3171| 13.6k| std::string st = prefix_check_morph(word, start, len, in_compound, scratch); 3172| 13.6k| if (!st.empty()) { ------------------ | Branch (3172:7): [True: 0, False: 13.6k] ------------------ 3173| 0| result.append(st); 3174| 0| } 3175| | 3176| | // if still not found check all suffixes 3177| 13.6k| st = suffix_check_morph(word, start, len, 0, nullptr, scratch, '\0', needflag, in_compound); 3178| 13.6k| if (!st.empty()) { ------------------ | Branch (3178:7): [True: 0, False: 13.6k] ------------------ 3179| 0| result.append(st); 3180| 0| } 3181| | 3182| 13.6k| if (havecontclass) { ------------------ | Branch (3182:7): [True: 4.24k, False: 9.38k] ------------------ 3183| 4.24k| sfx = nullptr; 3184| 4.24k| pfx = nullptr; 3185| | // if still not found check all two-level suffixes 3186| 4.24k| st = suffix_check_twosfx_morph(word, start, len, 0, nullptr, scratch, needflag); 3187| 4.24k| if (!st.empty()) { ------------------ | Branch (3187:9): [True: 0, False: 4.24k] ------------------ 3188| 0| result.append(st); 3189| 0| } 3190| | 3191| | // if still not found check all two-level suffixes 3192| 4.24k| st = prefix_check_twosfx_morph(word, start, len, IN_CPD_NOT, scratch, needflag); ------------------ | | 72| 4.24k|#define IN_CPD_NOT 0 ------------------ 3193| 4.24k| if (!st.empty()) { ------------------ | Branch (3193:9): [True: 0, False: 4.24k] ------------------ 3194| 0| result.append(st); 3195| 0| } 3196| 4.24k| } 3197| | 3198| 13.6k| return result; 3199| 13.6k|} _ZN8AffixMgr15expand_rootwordEP9guesswordiPKciPKttS3_iS3_: 3387| 602k| const char* phon) { 3388| 602k| int nh = 0; 3389| | // first add root word to list 3390| 602k| if ((nh < maxn) && ------------------ | Branch (3390:7): [True: 602k, False: 0] ------------------ 3391| 602k| !(al && ((needaffix && TESTAFF(ap, needaffix, al)) || ------------------ | | 99| 4.62k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 2.31k, False: 2.31k] | | ------------------ ------------------ | Branch (3391:9): [True: 98.1k, False: 504k] | Branch (3391:17): [True: 4.62k, False: 93.5k] ------------------ 3392| 600k| (onlyincompound && TESTAFF(ap, onlyincompound, al))))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (3392:17): [True: 0, False: 95.8k] ------------------ 3393| 600k| wlst[nh].word = mystrdup(ts); 3394| 600k| wlst[nh].allow = false; 3395| 600k| wlst[nh].orig = nullptr; 3396| 600k| nh++; 3397| | // add special phonetic version 3398| 600k| if (phon && (nh < maxn)) { ------------------ | Branch (3398:9): [True: 753, False: 599k] | Branch (3398:17): [True: 753, False: 0] ------------------ 3399| 753| wlst[nh].word = mystrdup(phon); 3400| 753| wlst[nh].allow = false; 3401| 753| wlst[nh].orig = mystrdup(ts); 3402| 753| nh++; 3403| 753| } 3404| 600k| } 3405| | 3406| | // handle suffixes 3407| 712k| for (int i = 0; i < al; i++) { ------------------ | Branch (3407:19): [True: 110k, False: 602k] ------------------ 3408| 110k| const auto c = (unsigned char)(ap[i] & 0x00FF); 3409| 110k| SfxEntry* sptr = sFlag[c]; 3410| 175k| while (sptr) { ------------------ | Branch (3410:12): [True: 65.4k, False: 110k] ------------------ 3411| 65.4k| if ((sptr->getFlag() == ap[i]) && ------------------ | Branch (3411:11): [True: 65.4k, False: 0] ------------------ 3412| 65.4k| (!sptr->getKeyLen() || ------------------ | Branch (3412:12): [True: 0, False: 65.4k] ------------------ 3413| 65.4k| ((badl > sptr->getKeyLen()) && ------------------ | Branch (3413:13): [True: 36.8k, False: 28.5k] ------------------ 3414| 36.8k| (strcmp(sptr->getAffix(), bad + badl - sptr->getKeyLen()) == 0))) && ------------------ | Branch (3414:13): [True: 34, False: 36.8k] ------------------ 3415| | // check needaffix flag 3416| 34| !(sptr->getCont() && ------------------ | Branch (3416:13): [True: 18, False: 16] ------------------ 3417| 18| ((needaffix && ------------------ | Branch (3417:15): [True: 12, False: 6] ------------------ 3418| 12| TESTAFF(sptr->getCont(), needaffix, sptr->getContLen())) || ------------------ | | 99| 12|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 12] | | ------------------ ------------------ 3419| 18| (circumfix && ------------------ | Branch (3419:15): [True: 0, False: 18] ------------------ 3420| 0| TESTAFF(sptr->getCont(), circumfix, sptr->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3421| 18| (onlyincompound && ------------------ | Branch (3421:15): [True: 0, False: 18] ------------------ 3422| 34| TESTAFF(sptr->getCont(), onlyincompound, sptr->getContLen()))))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3423| 34| std::string newword = sptr->add(ts, wl); 3424| 34| if (!newword.empty()) { ------------------ | Branch (3424:13): [True: 34, False: 0] ------------------ 3425| 34| if (nh < maxn) { ------------------ | Branch (3425:15): [True: 34, False: 0] ------------------ 3426| 34| wlst[nh].word = mystrdup(newword.c_str()); 3427| 34| wlst[nh].allow = sptr->allowCross(); 3428| 34| wlst[nh].orig = nullptr; 3429| 34| nh++; 3430| | // add special phonetic version 3431| 34| if (phon && (nh < maxn)) { ------------------ | Branch (3431:17): [True: 0, False: 34] | Branch (3431:25): [True: 0, False: 0] ------------------ 3432| 0| std::string prefix(phon); 3433| 0| std::string key(sptr->getKey()); 3434| 0| reverseword(key); 3435| 0| prefix.append(key); 3436| 0| wlst[nh].word = mystrdup(prefix.c_str()); 3437| 0| wlst[nh].allow = false; 3438| 0| wlst[nh].orig = mystrdup(newword.c_str()); 3439| 0| nh++; 3440| 0| } 3441| 34| } 3442| 34| } 3443| 34| } 3444| 65.4k| sptr = sptr->getFlgNxt(); 3445| 65.4k| } 3446| 110k| } 3447| | 3448| 602k| int n = nh; 3449| | 3450| | // handle cross products of prefixes and suffixes 3451| 603k| for (int j = 1; j < n; j++) ------------------ | Branch (3451:19): [True: 775, False: 602k] ------------------ 3452| 775| if (wlst[j].allow) { ------------------ | Branch (3452:9): [True: 22, False: 753] ------------------ 3453| 66| for (int k = 0; k < al; k++) { ------------------ | Branch (3453:23): [True: 44, False: 22] ------------------ 3454| 44| const auto c = (unsigned char)(ap[k] & 0x00FF); 3455| 44| PfxEntry* cptr = pFlag[c]; 3456| 44| while (cptr) { ------------------ | Branch (3456:16): [True: 0, False: 44] ------------------ 3457| 0| if ((cptr->getFlag() == ap[k]) && cptr->allowCross() && ------------------ | Branch (3457:15): [True: 0, False: 0] | Branch (3457:45): [True: 0, False: 0] ------------------ 3458| 0| (!cptr->getKeyLen() || ------------------ | Branch (3458:16): [True: 0, False: 0] ------------------ 3459| 0| ((badl > cptr->getKeyLen()) && ------------------ | Branch (3459:17): [True: 0, False: 0] ------------------ 3460| 0| (strncmp(cptr->getKey(), bad, cptr->getKeyLen()) == 0)))) { ------------------ | Branch (3460:17): [True: 0, False: 0] ------------------ 3461| 0| int l1 = strlen(wlst[j].word); 3462| 0| std::string newword = cptr->add(wlst[j].word, l1); 3463| 0| if (!newword.empty()) { ------------------ | Branch (3463:17): [True: 0, False: 0] ------------------ 3464| 0| if (nh < maxn) { ------------------ | Branch (3464:19): [True: 0, False: 0] ------------------ 3465| 0| wlst[nh].word = mystrdup(newword.c_str()); 3466| 0| wlst[nh].allow = cptr->allowCross(); 3467| 0| wlst[nh].orig = nullptr; 3468| 0| nh++; 3469| 0| } 3470| 0| } 3471| 0| } 3472| 0| cptr = cptr->getFlgNxt(); 3473| 0| } 3474| 44| } 3475| 22| } 3476| | 3477| | // now handle pure prefixes 3478| 712k| for (int m = 0; m < al; m++) { ------------------ | Branch (3478:19): [True: 110k, False: 602k] ------------------ 3479| 110k| const auto c = (unsigned char)(ap[m] & 0x00FF); 3480| 110k| PfxEntry* ptr = pFlag[c]; 3481| 111k| while (ptr) { ------------------ | Branch (3481:12): [True: 771, False: 110k] ------------------ 3482| 771| if ((ptr->getFlag() == ap[m]) && ------------------ | Branch (3482:11): [True: 771, False: 0] ------------------ 3483| 771| (!ptr->getKeyLen() || ------------------ | Branch (3483:12): [True: 0, False: 771] ------------------ 3484| 771| ((badl > ptr->getKeyLen()) && ------------------ | Branch (3484:13): [True: 771, False: 0] ------------------ 3485| 771| (strncmp(ptr->getKey(), bad, ptr->getKeyLen()) == 0))) && ------------------ | Branch (3485:13): [True: 3, False: 768] ------------------ 3486| | // check needaffix flag 3487| 3| !(ptr->getCont() && ------------------ | Branch (3487:13): [True: 0, False: 3] ------------------ 3488| 0| ((needaffix && ------------------ | Branch (3488:15): [True: 0, False: 0] ------------------ 3489| 0| TESTAFF(ptr->getCont(), needaffix, ptr->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3490| 0| (circumfix && ------------------ | Branch (3490:15): [True: 0, False: 0] ------------------ 3491| 0| TESTAFF(ptr->getCont(), circumfix, ptr->getContLen())) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3492| 0| (onlyincompound && ------------------ | Branch (3492:15): [True: 0, False: 0] ------------------ 3493| 3| TESTAFF(ptr->getCont(), onlyincompound, ptr->getContLen()))))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 3494| 3| std::string newword = ptr->add(ts, wl); 3495| 3| if (!newword.empty()) { ------------------ | Branch (3495:13): [True: 3, False: 0] ------------------ 3496| 3| if (nh < maxn) { ------------------ | Branch (3496:15): [True: 3, False: 0] ------------------ 3497| 3| wlst[nh].word = mystrdup(newword.c_str()); 3498| 3| wlst[nh].allow = ptr->allowCross(); 3499| 3| wlst[nh].orig = nullptr; 3500| 3| nh++; 3501| 3| } 3502| 3| } 3503| 3| } 3504| 771| ptr = ptr->getFlgNxt(); 3505| 771| } 3506| 110k| } 3507| | 3508| 602k| return nh; 3509| 602k|} _ZNK8AffixMgr12get_reptableEv: 3512| 386k|const std::vector& AffixMgr::get_reptable() const { 3513| 386k| return pHMgr->get_reptable(); 3514| 386k|} _ZNK8AffixMgr14get_iconvtableEv: 3517| 11.8M|RepList* AffixMgr::get_iconvtable() const { 3518| 11.8M| if (!iconvtable) ------------------ | Branch (3518:7): [True: 11.4M, False: 365k] ------------------ 3519| 11.4M| return nullptr; 3520| 365k| return iconvtable; 3521| 11.8M|} _ZNK8AffixMgr14get_oconvtableEv: 3524| 98.1k|RepList* AffixMgr::get_oconvtable() const { 3525| 98.1k| if (!oconvtable) ------------------ | Branch (3525:7): [True: 92.9k, False: 5.23k] ------------------ 3526| 92.9k| return nullptr; 3527| 5.23k| return oconvtable; 3528| 98.1k|} _ZNK8AffixMgr14get_phonetableEv: 3531| 62.4k|struct phonetable* AffixMgr::get_phonetable() const { 3532| 62.4k| if (!phone) ------------------ | Branch (3532:7): [True: 58.8k, False: 3.59k] ------------------ 3533| 58.8k| return nullptr; 3534| 3.59k| return phone; 3535| 62.4k|} _ZNK8AffixMgr12get_maptableEv: 3538| 386k|const std::vector& AffixMgr::get_maptable() const { 3539| 386k| return maptable; 3540| 386k|} _ZNK8AffixMgr14get_breaktableEv: 3543| 38|const std::vector& AffixMgr::get_breaktable() const { 3544| 38| return breaktable; 3545| 38|} _ZN8AffixMgr12get_encodingEv: 3548| 78|const std::string& AffixMgr::get_encoding() { 3549| 78| if (encoding.empty()) ------------------ | Branch (3549:7): [True: 20, False: 58] ------------------ 3550| 20| encoding = SPELL_ENCODING; ------------------ | | 99| 20|#define SPELL_ENCODING "ISO8859-1" ------------------ 3551| 78| return encoding; 3552| 78|} _ZNK8AffixMgr11get_langnumEv: 3555| 76|int AffixMgr::get_langnum() const { 3556| 76| return langnum; 3557| 76|} _ZNK8AffixMgr19get_complexprefixesEv: 3560| 76|int AffixMgr::get_complexprefixes() const { 3561| 76| return complexprefixes; 3562| 76|} _ZNK8AffixMgr13get_fullstripEv: 3565| 5.50k|int AffixMgr::get_fullstrip() const { 3566| 5.50k| return fullstrip; 3567| 5.50k|} _ZNK8AffixMgr12get_keepcaseEv: 3569| 101k|FLAG AffixMgr::get_keepcase() const { 3570| 101k| return keepcase; 3571| 101k|} _ZNK8AffixMgr14get_forceucaseEv: 3573| 20.1k|FLAG AffixMgr::get_forceucase() const { 3574| 20.1k| return forceucase; 3575| 20.1k|} _ZNK8AffixMgr8get_warnEv: 3577| 35.7k|FLAG AffixMgr::get_warn() const { 3578| 35.7k| return warn; 3579| 35.7k|} _ZNK8AffixMgr14get_forbidwarnEv: 3581| 1|int AffixMgr::get_forbidwarn() const { 3582| 1| return forbidwarn; 3583| 1|} _ZNK8AffixMgr15get_checksharpsEv: 3585| 187k|int AffixMgr::get_checksharps() const { 3586| 187k| return checksharps; 3587| 187k|} _ZNK8AffixMgr10get_ignoreEv: 3594| 25.2M|const char* AffixMgr::get_ignore() const { 3595| 25.2M| if (ignorechars.empty()) ------------------ | Branch (3595:7): [True: 22.6M, False: 2.56M] ------------------ 3596| 22.6M| return nullptr; 3597| 2.56M| return ignorechars.c_str(); 3598| 25.2M|} _ZNK8AffixMgr16get_ignore_utf16Ev: 3601| 600k|const std::vector& AffixMgr::get_ignore_utf16() const { 3602| 600k| return ignorechars_utf16; 3603| 600k|} _ZN8AffixMgr14get_key_stringEv: 3606| 38|const std::string& AffixMgr::get_key_string() { 3607| 38| if (keystring.empty()) ------------------ | Branch (3607:7): [True: 38, False: 0] ------------------ 3608| 38| keystring = SPELL_KEYSTRING; ------------------ | | 100| 38|#define SPELL_KEYSTRING "qwertyuiop|asdfghjkl|zxcvbnm" ------------------ 3609| 38| return keystring; 3610| 38|} _ZNK8AffixMgr14get_try_stringEv: 3613| 38|const std::string& AffixMgr::get_try_string() const { 3614| 38| return trystring; 3615| 38|} _ZNK8AffixMgr12get_compoundEv: 3627| 74.7M|int AffixMgr::get_compound() const { 3628| 74.7M| return compoundflag || compoundbegin || !defcpdtable.empty(); ------------------ | Branch (3628:10): [True: 18.7M, False: 56.0M] | Branch (3628:26): [True: 0, False: 56.0M] | Branch (3628:43): [True: 0, False: 56.0M] ------------------ 3629| 74.7M|} _ZNK8AffixMgr16get_compoundflagEv: 3632| 46.4k|FLAG AffixMgr::get_compoundflag() const { 3633| 46.4k| return compoundflag; 3634| 46.4k|} _ZNK8AffixMgr17get_forbiddenwordEv: 3637| 160k|FLAG AffixMgr::get_forbiddenword() const { 3638| 160k| return forbiddenword; 3639| 160k|} _ZNK8AffixMgr13get_nosuggestEv: 3642| 62.7k|FLAG AffixMgr::get_nosuggest() const { 3643| 62.7k| return nosuggest; 3644| 62.7k|} _ZNK8AffixMgr18get_nongramsuggestEv: 3647| 62.4k|FLAG AffixMgr::get_nongramsuggest() const { 3648| 62.4k| return nongramsuggest; 3649| 62.4k|} _ZNK8AffixMgr15get_substandardEv: 3652| 224|FLAG AffixMgr::get_substandard() const { 3653| 224| return substandard; 3654| 224|} _ZNK8AffixMgr13get_needaffixEv: 3657| 1.33k|FLAG AffixMgr::get_needaffix() const { 3658| 1.33k| return needaffix; 3659| 1.33k|} _ZNK8AffixMgr18get_onlyincompoundEv: 3662| 63.5k|FLAG AffixMgr::get_onlyincompound() const { 3663| 63.5k| return onlyincompound; 3664| 63.5k|} _ZN8AffixMgr6lookupEPKcm: 3672| 590M|struct hentry* AffixMgr::lookup(const char* word, size_t len) { 3673| 590M| struct hentry* he = nullptr; 3674| 1.18G| for (size_t i = 0; i < alldic.size() && !he; ++i) { ------------------ | Branch (3674:22): [True: 590M, False: 590M] | Branch (3674:43): [True: 590M, False: 0] ------------------ 3675| 590M| he = alldic[i]->lookup(word, len); 3676| 590M| } 3677| 590M| return he; 3678| 590M|} _ZNK8AffixMgr14have_contclassEv: 3681| 32.2M|int AffixMgr::have_contclass() const { 3682| 32.2M| return havecontclass; 3683| 32.2M|} _ZNK8AffixMgr8get_utf8Ev: 3686| 76|int AffixMgr::get_utf8() const { 3687| 76| return utf8; 3688| 76|} _ZNK8AffixMgr16get_maxngramsugsEv: 3690| 70.0k|int AffixMgr::get_maxngramsugs() const { 3691| 70.0k| return maxngramsugs; 3692| 70.0k|} _ZNK8AffixMgr14get_maxcpdsugsEv: 3694| 38|int AffixMgr::get_maxcpdsugs() const { 3695| 38| return maxcpdsugs; 3696| 38|} _ZNK8AffixMgr11get_maxdiffEv: 3698| 48.4k|int AffixMgr::get_maxdiff() const { 3699| 48.4k| return maxdiff; 3700| 48.4k|} _ZNK8AffixMgr15get_onlymaxdiffEv: 3702| 7.43k|int AffixMgr::get_onlymaxdiff() const { 3703| 7.43k| return onlymaxdiff; 3704| 7.43k|} _ZNK8AffixMgr15get_nosplitsugsEv: 3707| 38|int AffixMgr::get_nosplitsugs() const { 3708| 38| return nosplitsugs; 3709| 38|} _ZNK8AffixMgr16get_sugswithdotsEv: 3712| 3.39k|int AffixMgr::get_sugswithdots() const { 3713| 3.39k| return sugswithdots; 3714| 3.39k|} _ZN8AffixMgr10parse_flagERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPtP7FileMgr: 3717| 22|bool AffixMgr::parse_flag(const std::string& line, unsigned short* out, FileMgr* af) { 3718| 22| if (*out != FLAG_NULL && !(*out >= DEFAULTFLAGS)) { ------------------ | | 96| 44|#define FLAG_NULL 0x00 ------------------ if (*out != FLAG_NULL && !(*out >= DEFAULTFLAGS)) { ------------------ | | 126| 2|#define DEFAULTFLAGS 65510 ------------------ | Branch (3718:7): [True: 2, False: 20] | Branch (3718:28): [True: 0, False: 2] ------------------ 3719| 0| HUNSPELL_WARNING( 3720| 0| stderr, 3721| 0| "error: line %d: multiple definitions of an affix file parameter\n", 3722| 0| af->getlinenum()); 3723| 0| return false; 3724| 0| } 3725| 22| std::string s; 3726| 22| if (!parse_string(line, s, af->getlinenum())) ------------------ | Branch (3726:7): [True: 0, False: 22] ------------------ 3727| 0| return false; 3728| 22| *out = pHMgr->decode_flag(s); 3729| 22| return true; 3730| 22|} _ZN8AffixMgr9parse_numERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiP7FileMgr: 3733| 10|bool AffixMgr::parse_num(const std::string& line, int* out, FileMgr* af) { 3734| 10| if (*out != -1) { ------------------ | Branch (3734:7): [True: 0, False: 10] ------------------ 3735| 0| HUNSPELL_WARNING( 3736| 0| stderr, 3737| 0| "error: line %d: multiple definitions of an affix file parameter\n", 3738| 0| af->getlinenum()); 3739| 0| return false; 3740| 0| } 3741| 10| std::string s; 3742| 10| if (!parse_string(line, s, af->getlinenum())) ------------------ | Branch (3742:7): [True: 0, False: 10] ------------------ 3743| 0| return false; 3744| 10| *out = atoi(s.c_str()); 3745| 10| return true; 3746| 10|} _ZN8AffixMgr17parse_cpdsyllableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 3749| 2|bool AffixMgr::parse_cpdsyllable(const std::string& line, FileMgr* af) { 3750| 2| int i = 0; 3751| 2| int np = 0; 3752| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 3753| 8| while (start_piece != line.end()) { ------------------ | Branch (3753:10): [True: 6, False: 2] ------------------ 3754| 6| switch (i) { 3755| 2| case 0: { ------------------ | Branch (3755:7): [True: 2, False: 4] ------------------ 3756| 2| np++; 3757| 2| break; 3758| 0| } 3759| 2| case 1: { ------------------ | Branch (3759:7): [True: 2, False: 4] ------------------ 3760| 2| cpdmaxsyllable = atoi(std::string(start_piece, iter).c_str()); 3761| 2| np++; 3762| 2| break; 3763| 0| } 3764| 2| case 2: { ------------------ | Branch (3764:7): [True: 2, False: 4] ------------------ 3765| 2| if (!utf8) { ------------------ | Branch (3765:13): [True: 0, False: 2] ------------------ 3766| 0| cpdvowels.assign(start_piece, iter); 3767| 0| std::sort(cpdvowels.begin(), cpdvowels.end()); 3768| 2| } else { 3769| 2| std::string piece(start_piece, iter); 3770| 2| u8_u16(cpdvowels_utf16, piece); 3771| 2| std::sort(cpdvowels_utf16.begin(), cpdvowels_utf16.end()); 3772| 2| } 3773| 2| np++; 3774| 2| break; 3775| 0| } 3776| 0| default: ------------------ | Branch (3776:7): [True: 0, False: 6] ------------------ 3777| 0| break; 3778| 6| } 3779| 6| ++i; 3780| 6| start_piece = mystrsep(line, iter); 3781| 6| } 3782| 2| if (np < 2) { ------------------ | Branch (3782:7): [True: 0, False: 2] ------------------ 3783| 0| HUNSPELL_WARNING(stderr, 3784| 0| "error: line %d: missing compoundsyllable information\n", 3785| 0| af->getlinenum()); 3786| 0| return false; 3787| 0| } 3788| 2| if (np == 2) ------------------ | Branch (3788:7): [True: 0, False: 2] ------------------ 3789| 0| cpdvowels = "AEIOUaeiou"; 3790| 2| return true; 3791| 2|} _ZN8AffixMgr15parse_convtableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgrPP7RepListS8_: 3796| 4| const std::string& keyword) { 3797| 4| if (*rl) { ------------------ | Branch (3797:7): [True: 0, False: 4] ------------------ 3798| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 3799| 0| af->getlinenum()); 3800| 0| return false; 3801| 0| } 3802| 4| int i = 0; 3803| 4| int np = 0; 3804| 4| int numrl = 0; 3805| 4| auto iter = line.begin(), start_piece = mystrsep(line, iter); 3806| 18| while (start_piece != line.end()) { ------------------ | Branch (3806:10): [True: 14, False: 4] ------------------ 3807| 14| switch (i) { 3808| 4| case 0: { ------------------ | Branch (3808:7): [True: 4, False: 10] ------------------ 3809| 4| np++; 3810| 4| break; 3811| 0| } 3812| 4| case 1: { ------------------ | Branch (3812:7): [True: 4, False: 10] ------------------ 3813| 4| numrl = atoi(std::string(start_piece, iter).c_str()); 3814| 4| if (numrl < 1) { ------------------ | Branch (3814:13): [True: 0, False: 4] ------------------ 3815| 0| HUNSPELL_WARNING(stderr, "error: line %d: incorrect entry number\n", 3816| 0| af->getlinenum()); 3817| 0| return false; 3818| 0| } 3819| 4| *rl = new RepList(numrl); 3820| 4| if (!*rl) ------------------ | Branch (3820:13): [True: 0, False: 4] ------------------ 3821| 0| return false; 3822| 4| np++; 3823| 4| break; 3824| 4| } 3825| 6| default: ------------------ | Branch (3825:7): [True: 6, False: 8] ------------------ 3826| 6| break; 3827| 14| } 3828| 14| ++i; 3829| 14| start_piece = mystrsep(line, iter); 3830| 14| } 3831| 4| if (np != 2) { ------------------ | Branch (3831:7): [True: 0, False: 4] ------------------ 3832| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 3833| 0| af->getlinenum()); 3834| 0| return false; 3835| 0| } 3836| | 3837| | /* now parse the num lines to read in the remainder of the table */ 3838| 26| for (int j = 0; j < numrl; j++) { ------------------ | Branch (3838:19): [True: 22, False: 4] ------------------ 3839| 22| std::string nl; 3840| 22| if (!af->getline(nl)) ------------------ | Branch (3840:9): [True: 0, False: 22] ------------------ 3841| 0| return false; 3842| 22| mychomp(nl); 3843| 22| i = 0; 3844| 22| std::string pattern; 3845| 22| std::string pattern2; 3846| 22| iter = nl.begin(); 3847| 22| start_piece = mystrsep(nl, iter); 3848| 130| while (start_piece != nl.end()) { ------------------ | Branch (3848:12): [True: 108, False: 22] ------------------ 3849| 108| { 3850| 108| switch (i) { 3851| 22| case 0: { ------------------ | Branch (3851:11): [True: 22, False: 86] ------------------ 3852| 22| if (nl.compare(start_piece - nl.begin(), keyword.size(), keyword, 0, keyword.size()) != 0) { ------------------ | Branch (3852:17): [True: 0, False: 22] ------------------ 3853| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 3854| 0| af->getlinenum()); 3855| 0| delete *rl; 3856| 0| *rl = nullptr; 3857| 0| return false; 3858| 0| } 3859| 22| break; 3860| 22| } 3861| 22| case 1: { ------------------ | Branch (3861:11): [True: 22, False: 86] ------------------ 3862| 22| pattern.assign(start_piece, iter); 3863| 22| break; 3864| 22| } 3865| 22| case 2: { ------------------ | Branch (3865:11): [True: 22, False: 86] ------------------ 3866| 22| pattern2.assign(start_piece, iter); 3867| 22| break; 3868| 22| } 3869| 42| default: ------------------ | Branch (3869:11): [True: 42, False: 66] ------------------ 3870| 42| break; 3871| 108| } 3872| 108| ++i; 3873| 108| } 3874| 0| start_piece = mystrsep(nl, iter); 3875| 108| } 3876| 22| if (pattern.empty() || pattern2.empty()) { ------------------ | Branch (3876:9): [True: 0, False: 22] | Branch (3876:28): [True: 0, False: 22] ------------------ 3877| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 3878| 0| af->getlinenum()); 3879| 0| return false; 3880| 0| } 3881| | 3882| 22| (*rl)->add(pattern, pattern2); 3883| 22| } 3884| 4| return true; 3885| 4|} _ZN8AffixMgr16parse_phonetableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 3888| 2|bool AffixMgr::parse_phonetable(const std::string& line, FileMgr* af) { 3889| 2| if (phone) { ------------------ | Branch (3889:7): [True: 0, False: 2] ------------------ 3890| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 3891| 0| af->getlinenum()); 3892| 0| return false; 3893| 0| } 3894| 2| std::unique_ptr new_phone; 3895| 2| int num = -1; 3896| 2| int i = 0; 3897| 2| int np = 0; 3898| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 3899| 6| while (start_piece != line.end()) { ------------------ | Branch (3899:10): [True: 4, False: 2] ------------------ 3900| 4| switch (i) { 3901| 2| case 0: { ------------------ | Branch (3901:7): [True: 2, False: 2] ------------------ 3902| 2| np++; 3903| 2| break; 3904| 0| } 3905| 2| case 1: { ------------------ | Branch (3905:7): [True: 2, False: 2] ------------------ 3906| 2| num = atoi(std::string(start_piece, iter).c_str()); 3907| 2| if (num < 1) { ------------------ | Branch (3907:13): [True: 0, False: 2] ------------------ 3908| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 3909| 0| af->getlinenum()); 3910| 0| return false; 3911| 0| } 3912| 2| new_phone = std::make_unique(); 3913| 2| new_phone->utf8 = (char)utf8; 3914| 2| np++; 3915| 2| break; 3916| 2| } 3917| 0| default: ------------------ | Branch (3917:7): [True: 0, False: 4] ------------------ 3918| 0| break; 3919| 4| } 3920| 4| ++i; 3921| 4| start_piece = mystrsep(line, iter); 3922| 4| } 3923| 2| if (np != 2) { ------------------ | Branch (3923:7): [True: 0, False: 2] ------------------ 3924| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 3925| 0| af->getlinenum()); 3926| 0| return false; 3927| 0| } 3928| | 3929| | /* now parse the phone->num lines to read in the remainder of the table */ 3930| 212| for (int j = 0; j < num; ++j) { ------------------ | Branch (3930:19): [True: 210, False: 2] ------------------ 3931| 210| std::string nl; 3932| 210| if (!af->getline(nl)) ------------------ | Branch (3932:9): [True: 0, False: 210] ------------------ 3933| 0| return false; 3934| 210| mychomp(nl); 3935| 210| i = 0; 3936| 210| const size_t old_size = new_phone->rules.size(); 3937| 210| iter = nl.begin(); 3938| 210| start_piece = mystrsep(nl, iter); 3939| 840| while (start_piece != nl.end()) { ------------------ | Branch (3939:12): [True: 630, False: 210] ------------------ 3940| 630| { 3941| 630| switch (i) { 3942| 210| case 0: { ------------------ | Branch (3942:11): [True: 210, False: 420] ------------------ 3943| 210| if (nl.compare(start_piece - nl.begin(), 5, "PHONE", 5) != 0) { ------------------ | Branch (3943:17): [True: 0, False: 210] ------------------ 3944| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 3945| 0| af->getlinenum()); 3946| 0| return false; 3947| 0| } 3948| 210| break; 3949| 210| } 3950| 210| case 1: { ------------------ | Branch (3950:11): [True: 210, False: 420] ------------------ 3951| 210| new_phone->rules.emplace_back(start_piece, iter); 3952| 210| break; 3953| 210| } 3954| 210| case 2: { ------------------ | Branch (3954:11): [True: 210, False: 420] ------------------ 3955| 210| new_phone->rules.emplace_back(start_piece, iter); 3956| 210| mystrrep(new_phone->rules.back(), "_", ""); 3957| 210| break; 3958| 210| } 3959| 0| default: ------------------ | Branch (3959:11): [True: 0, False: 630] ------------------ 3960| 0| break; 3961| 630| } 3962| 630| ++i; 3963| 630| } 3964| 0| start_piece = mystrsep(nl, iter); 3965| 630| } 3966| 210| if (new_phone->rules.size() != old_size + 2) { ------------------ | Branch (3966:9): [True: 0, False: 210] ------------------ 3967| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 3968| 0| af->getlinenum()); 3969| 0| return false; 3970| 0| } 3971| 210| } 3972| 2| new_phone->rules.emplace_back(""); 3973| 2| new_phone->rules.emplace_back(""); 3974| 2| init_phonet_hash(*new_phone); 3975| 2| phone = new_phone.release(); 3976| 2| return true; 3977| 2|} _ZN8AffixMgr19parse_checkcpdtableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 3980| 2|bool AffixMgr::parse_checkcpdtable(const std::string& line, FileMgr* af) { 3981| 2| if (parsedcheckcpd) { ------------------ | Branch (3981:7): [True: 0, False: 2] ------------------ 3982| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 3983| 0| af->getlinenum()); 3984| 0| return false; 3985| 0| } 3986| 2| parsedcheckcpd = true; 3987| 2| int numcheckcpd = -1; 3988| 2| int i = 0; 3989| 2| int np = 0; 3990| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 3991| 6| while (start_piece != line.end()) { ------------------ | Branch (3991:10): [True: 4, False: 2] ------------------ 3992| 4| switch (i) { 3993| 2| case 0: { ------------------ | Branch (3993:7): [True: 2, False: 2] ------------------ 3994| 2| np++; 3995| 2| break; 3996| 0| } 3997| 2| case 1: { ------------------ | Branch (3997:7): [True: 2, False: 2] ------------------ 3998| 2| numcheckcpd = atoi(std::string(start_piece, iter).c_str()); 3999| 2| if (numcheckcpd < 1) { ------------------ | Branch (3999:13): [True: 0, False: 2] ------------------ 4000| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 4001| 0| af->getlinenum()); 4002| 0| return false; 4003| 0| } 4004| 2| checkcpdtable.reserve(std::min(numcheckcpd, 16384)); 4005| 2| np++; 4006| 2| break; 4007| 2| } 4008| 0| default: ------------------ | Branch (4008:7): [True: 0, False: 4] ------------------ 4009| 0| break; 4010| 4| } 4011| 4| ++i; 4012| 4| start_piece = mystrsep(line, iter); 4013| 4| } 4014| 2| if (np != 2) { ------------------ | Branch (4014:7): [True: 0, False: 2] ------------------ 4015| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4016| 0| af->getlinenum()); 4017| 0| return false; 4018| 0| } 4019| | 4020| | /* now parse the numcheckcpd lines to read in the remainder of the table */ 4021| 6| for (int j = 0; j < numcheckcpd; ++j) { ------------------ | Branch (4021:19): [True: 4, False: 2] ------------------ 4022| 4| std::string nl; 4023| 4| if (!af->getline(nl)) ------------------ | Branch (4023:9): [True: 0, False: 4] ------------------ 4024| 0| return false; 4025| 4| mychomp(nl); 4026| 4| i = 0; 4027| 4| checkcpdtable.emplace_back(); 4028| 4| iter = nl.begin(); 4029| 4| start_piece = mystrsep(nl, iter); 4030| 16| while (start_piece != nl.end()) { ------------------ | Branch (4030:12): [True: 12, False: 4] ------------------ 4031| 12| switch (i) { 4032| 4| case 0: { ------------------ | Branch (4032:9): [True: 4, False: 8] ------------------ 4033| 4| if (nl.compare(start_piece - nl.begin(), 20, "CHECKCOMPOUNDPATTERN", 20) != 0) { ------------------ | Branch (4033:15): [True: 0, False: 4] ------------------ 4034| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4035| 0| af->getlinenum()); 4036| 0| checkcpdtable.clear(); 4037| 0| return false; 4038| 0| } 4039| 4| break; 4040| 4| } 4041| 4| case 1: { ------------------ | Branch (4041:9): [True: 4, False: 8] ------------------ 4042| 4| checkcpdtable.back().pattern.assign(start_piece, iter); 4043| 4| size_t slash_pos = checkcpdtable.back().pattern.find('/'); 4044| 4| if (slash_pos != std::string::npos) { ------------------ | Branch (4044:15): [True: 0, False: 4] ------------------ 4045| 0| std::string chunk(checkcpdtable.back().pattern, slash_pos + 1); 4046| 0| checkcpdtable.back().pattern.resize(slash_pos); 4047| 0| checkcpdtable.back().cond = pHMgr->decode_flag(chunk); 4048| 0| } 4049| 4| break; 4050| 4| } 4051| 4| case 2: { ------------------ | Branch (4051:9): [True: 4, False: 8] ------------------ 4052| 4| checkcpdtable.back().pattern2.assign(start_piece, iter); 4053| 4| size_t slash_pos = checkcpdtable.back().pattern2.find('/'); 4054| 4| if (slash_pos != std::string::npos) { ------------------ | Branch (4054:15): [True: 0, False: 4] ------------------ 4055| 0| std::string chunk(checkcpdtable.back().pattern2, slash_pos + 1); 4056| 0| checkcpdtable.back().pattern2.resize(slash_pos); 4057| 0| checkcpdtable.back().cond2 = pHMgr->decode_flag(chunk); 4058| 0| } 4059| 4| break; 4060| 4| } 4061| 0| case 3: { ------------------ | Branch (4061:9): [True: 0, False: 12] ------------------ 4062| 0| checkcpdtable.back().pattern3.assign(start_piece, iter); 4063| 0| simplifiedcpd = 1; 4064| 0| break; 4065| 4| } 4066| 0| default: ------------------ | Branch (4066:9): [True: 0, False: 12] ------------------ 4067| 0| break; 4068| 12| } 4069| 12| i++; 4070| 12| start_piece = mystrsep(nl, iter); 4071| 12| } 4072| 4| } 4073| 2| return true; 4074| 2|} _ZN8AffixMgr14parse_maptableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 4178| 2|bool AffixMgr::parse_maptable(const std::string& line, FileMgr* af) { 4179| 2| if (parsedmaptable) { ------------------ | Branch (4179:7): [True: 0, False: 2] ------------------ 4180| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 4181| 0| af->getlinenum()); 4182| 0| return false; 4183| 0| } 4184| 2| parsedmaptable = true; 4185| 2| int nummap = -1; 4186| 2| int i = 0; 4187| 2| int np = 0; 4188| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4189| 6| while (start_piece != line.end()) { ------------------ | Branch (4189:10): [True: 4, False: 2] ------------------ 4190| 4| switch (i) { 4191| 2| case 0: { ------------------ | Branch (4191:7): [True: 2, False: 2] ------------------ 4192| 2| np++; 4193| 2| break; 4194| 0| } 4195| 2| case 1: { ------------------ | Branch (4195:7): [True: 2, False: 2] ------------------ 4196| 2| nummap = atoi(std::string(start_piece, iter).c_str()); 4197| 2| if (nummap < 1) { ------------------ | Branch (4197:13): [True: 0, False: 2] ------------------ 4198| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 4199| 0| af->getlinenum()); 4200| 0| return false; 4201| 0| } 4202| 2| maptable.reserve(std::min(nummap, 16384)); 4203| 2| np++; 4204| 2| break; 4205| 2| } 4206| 0| default: ------------------ | Branch (4206:7): [True: 0, False: 4] ------------------ 4207| 0| break; 4208| 4| } 4209| 4| ++i; 4210| 4| start_piece = mystrsep(line, iter); 4211| 4| } 4212| 2| if (np != 2) { ------------------ | Branch (4212:7): [True: 0, False: 2] ------------------ 4213| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4214| 0| af->getlinenum()); 4215| 0| return false; 4216| 0| } 4217| | 4218| | /* now parse the nummap lines to read in the remainder of the table */ 4219| 8| for (int j = 0; j < nummap; ++j) { ------------------ | Branch (4219:19): [True: 6, False: 2] ------------------ 4220| 6| std::string nl; 4221| 6| if (!af->getline(nl)) ------------------ | Branch (4221:9): [True: 0, False: 6] ------------------ 4222| 0| return false; 4223| 6| mychomp(nl); 4224| 6| i = 0; 4225| 6| maptable.emplace_back(); 4226| 6| iter = nl.begin(); 4227| 6| start_piece = mystrsep(nl, iter); 4228| 18| while (start_piece != nl.end()) { ------------------ | Branch (4228:12): [True: 12, False: 6] ------------------ 4229| 12| switch (i) { 4230| 6| case 0: { ------------------ | Branch (4230:9): [True: 6, False: 6] ------------------ 4231| 6| if (nl.compare(start_piece - nl.begin(), 3, "MAP", 3) != 0) { ------------------ | Branch (4231:15): [True: 0, False: 6] ------------------ 4232| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4233| 0| af->getlinenum()); 4234| 0| nummap = 0; 4235| 0| return false; 4236| 0| } 4237| 6| break; 4238| 6| } 4239| 6| case 1: { ------------------ | Branch (4239:9): [True: 6, False: 6] ------------------ 4240| 22| for (auto k = start_piece; k != iter; ++k) { ------------------ | Branch (4240:38): [True: 16, False: 6] ------------------ 4241| 16| auto chb = k, che = k + 1; 4242| 16| if (*k == '(') { ------------------ | Branch (4242:17): [True: 2, False: 14] ------------------ 4243| 2| auto parpos = std::find(k, iter, ')'); 4244| 2| if (parpos != iter) { ------------------ | Branch (4244:19): [True: 2, False: 0] ------------------ 4245| 2| chb = k + 1; 4246| 2| che = parpos; 4247| 2| k = parpos; 4248| 2| } 4249| 14| } else { 4250| 14| if (utf8 && (*k & 0xc0) == 0xc0) { ------------------ | Branch (4250:19): [True: 14, False: 0] | Branch (4250:27): [True: 10, False: 4] ------------------ 4251| 10| ++k; 4252| 20| while (k != iter && is_utf8_cont(*k)) ------------------ | Branch (4252:24): [True: 18, False: 2] | Branch (4252:37): [True: 10, False: 8] ------------------ 4253| 10| ++k; 4254| 10| che = k; 4255| 10| --k; 4256| 10| } 4257| 14| } 4258| 16| if (chb == che) { ------------------ | Branch (4258:17): [True: 0, False: 16] ------------------ 4259| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4260| 0| af->getlinenum()); 4261| 0| } 4262| | 4263| 16| maptable.back().emplace_back(chb, che); 4264| 16| } 4265| 6| break; 4266| 6| } 4267| 0| default: ------------------ | Branch (4267:9): [True: 0, False: 12] ------------------ 4268| 0| break; 4269| 12| } 4270| 12| ++i; 4271| 12| start_piece = mystrsep(nl, iter); 4272| 12| } 4273| 6| if (maptable.back().empty()) { ------------------ | Branch (4273:9): [True: 0, False: 6] ------------------ 4274| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4275| 0| af->getlinenum()); 4276| 0| return false; 4277| 0| } 4278| 6| } 4279| 2| return true; 4280| 2|} _ZN8AffixMgr16parse_breaktableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 4283| 4|bool AffixMgr::parse_breaktable(const std::string& line, FileMgr* af) { 4284| 4| if (parsedbreaktable) { ------------------ | Branch (4284:7): [True: 0, False: 4] ------------------ 4285| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 4286| 0| af->getlinenum()); 4287| 0| return false; 4288| 0| } 4289| 4| parsedbreaktable = true; 4290| 4| int numbreak = -1; 4291| 4| int i = 0; 4292| 4| int np = 0; 4293| 4| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4294| 12| while (start_piece != line.end()) { ------------------ | Branch (4294:10): [True: 8, False: 4] ------------------ 4295| 8| switch (i) { 4296| 4| case 0: { ------------------ | Branch (4296:7): [True: 4, False: 4] ------------------ 4297| 4| np++; 4298| 4| break; 4299| 0| } 4300| 4| case 1: { ------------------ | Branch (4300:7): [True: 4, False: 4] ------------------ 4301| 4| numbreak = atoi(std::string(start_piece, iter).c_str()); 4302| 4| if (numbreak < 0) { ------------------ | Branch (4302:13): [True: 0, False: 4] ------------------ 4303| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 4304| 0| af->getlinenum()); 4305| 0| return false; 4306| 0| } 4307| 4| if (numbreak == 0) ------------------ | Branch (4307:13): [True: 0, False: 4] ------------------ 4308| 0| return true; 4309| 4| breaktable.reserve(std::min(numbreak, 16384)); 4310| 4| np++; 4311| 4| break; 4312| 4| } 4313| 0| default: ------------------ | Branch (4313:7): [True: 0, False: 8] ------------------ 4314| 0| break; 4315| 8| } 4316| 8| ++i; 4317| 8| start_piece = mystrsep(line, iter); 4318| 8| } 4319| 4| if (np != 2) { ------------------ | Branch (4319:7): [True: 0, False: 4] ------------------ 4320| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4321| 0| af->getlinenum()); 4322| 0| return false; 4323| 0| } 4324| | 4325| | /* now parse the numbreak lines to read in the remainder of the table */ 4326| 10| for (int j = 0; j < numbreak; ++j) { ------------------ | Branch (4326:19): [True: 6, False: 4] ------------------ 4327| 6| std::string nl; 4328| 6| if (!af->getline(nl)) ------------------ | Branch (4328:9): [True: 0, False: 6] ------------------ 4329| 0| return false; 4330| 6| mychomp(nl); 4331| 6| i = 0; 4332| 6| iter = nl.begin(); 4333| 6| start_piece = mystrsep(nl, iter); 4334| 18| while (start_piece != nl.end()) { ------------------ | Branch (4334:12): [True: 12, False: 6] ------------------ 4335| 12| switch (i) { 4336| 6| case 0: { ------------------ | Branch (4336:9): [True: 6, False: 6] ------------------ 4337| 6| if (nl.compare(start_piece - nl.begin(), 5, "BREAK", 5) != 0) { ------------------ | Branch (4337:15): [True: 0, False: 6] ------------------ 4338| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4339| 0| af->getlinenum()); 4340| 0| numbreak = 0; 4341| 0| return false; 4342| 0| } 4343| 6| break; 4344| 6| } 4345| 6| case 1: { ------------------ | Branch (4345:9): [True: 6, False: 6] ------------------ 4346| 6| breaktable.emplace_back(start_piece, iter); 4347| 6| break; 4348| 6| } 4349| 0| default: ------------------ | Branch (4349:9): [True: 0, False: 12] ------------------ 4350| 0| break; 4351| 12| } 4352| 12| ++i; 4353| 12| start_piece = mystrsep(nl, iter); 4354| 12| } 4355| 6| } 4356| | 4357| 4| if (breaktable.size() != static_cast(numbreak)) { ------------------ | Branch (4357:7): [True: 0, False: 4] ------------------ 4358| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4359| 0| af->getlinenum()); 4360| 0| return false; 4361| 0| } 4362| | 4363| 4| return true; 4364| 4|} _ZN8AffixMgr17reverse_conditionERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 4366| 38|void AffixMgr::reverse_condition(std::string& piece) { 4367| 38| if (piece.empty()) ------------------ | Branch (4367:7): [True: 0, False: 38] ------------------ 4368| 0| return; 4369| | 4370| 38| int neg = 0; 4371| | // iterate backwards; k wraps to npos (SIZE_MAX) when decremented past 0 4372| 92| for (size_t k = piece.size() - 1; k != std::string::npos; --k) { ------------------ | Branch (4372:37): [True: 54, False: 38] ------------------ 4373| 54| switch (piece[k]) { 4374| 2| case '[': { ------------------ | Branch (4374:7): [True: 2, False: 52] ------------------ 4375| 2| if (neg) ------------------ | Branch (4375:13): [True: 0, False: 2] ------------------ 4376| 0| piece[k + 1] = '['; 4377| 2| else 4378| 2| piece[k] = ']'; 4379| 2| break; 4380| 0| } 4381| 2| case ']': { ------------------ | Branch (4381:7): [True: 2, False: 52] ------------------ 4382| 2| piece[k] = '['; 4383| 2| if (neg) ------------------ | Branch (4383:13): [True: 0, False: 2] ------------------ 4384| 0| piece[k + 1] = '^'; 4385| 2| neg = 0; 4386| 2| break; 4387| 0| } 4388| 0| case '^': { ------------------ | Branch (4388:7): [True: 0, False: 54] ------------------ 4389| 0| if (piece[k + 1] == ']') ------------------ | Branch (4389:13): [True: 0, False: 0] ------------------ 4390| 0| neg = 1; 4391| 0| else if (neg) ------------------ | Branch (4391:18): [True: 0, False: 0] ------------------ 4392| 0| piece[k + 1] = piece[k]; 4393| 0| break; 4394| 0| } 4395| 50| default: { ------------------ | Branch (4395:7): [True: 50, False: 4] ------------------ 4396| 50| if (neg) ------------------ | Branch (4396:13): [True: 0, False: 50] ------------------ 4397| 0| piece[k + 1] = piece[k]; 4398| 50| } 4399| 54| } 4400| 54| } 4401| 38|} _ZN8AffixMgr11parse_affixERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEcP7FileMgrPc: 4455| 26| char* dupflags) { 4456| 26| int numents = 0; // number of AffEntry structures to parse 4457| | 4458| 26| unsigned short aflag = 0; // affix char identifier 4459| | 4460| 26| char ff = 0; 4461| 26| entries_container affentries(at, this); 4462| | 4463| 26| int i = 0; 4464| | 4465| |// checking lines with bad syntax 4466| |#ifdef DEBUG 4467| | int basefieldnum = 0; 4468| |#endif 4469| | 4470| | // split affix header line into pieces 4471| | 4472| 26| int np = 0; 4473| 26| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4474| 130| while (start_piece != line.end()) { ------------------ | Branch (4474:10): [True: 104, False: 26] ------------------ 4475| 104| switch (i) { 4476| | // piece 1 - is type of affix 4477| 26| case 0: { ------------------ | Branch (4477:7): [True: 26, False: 78] ------------------ 4478| 26| np++; 4479| 26| break; 4480| 0| } 4481| | 4482| | // piece 2 - is affix char 4483| 26| case 1: { ------------------ | Branch (4483:7): [True: 26, False: 78] ------------------ 4484| 26| np++; 4485| 26| aflag = pHMgr->decode_flag(std::string(start_piece, iter)); 4486| 26| if (((at == 'S') && (dupflags[aflag] & dupSFX)) || ------------------ | | 88| 18|#define dupSFX (1 << 0) ------------------ | Branch (4486:14): [True: 18, False: 8] | Branch (4486:29): [True: 0, False: 18] ------------------ 4487| 26| ((at == 'P') && (dupflags[aflag] & dupPFX))) { ------------------ | | 89| 8|#define dupPFX (1 << 1) ------------------ | Branch (4487:14): [True: 8, False: 18] | Branch (4487:29): [True: 0, False: 8] ------------------ 4488| 0| HUNSPELL_WARNING( 4489| 0| stderr, 4490| 0| "error: line %d: multiple definitions of an affix flag\n", 4491| 0| af->getlinenum()); 4492| 0| } 4493| 26| dupflags[aflag] += (char)((at == 'S') ? dupSFX : dupPFX); ------------------ | | 88| 18|#define dupSFX (1 << 0) ------------------ dupflags[aflag] += (char)((at == 'S') ? dupSFX : dupPFX); ------------------ | | 89| 8|#define dupPFX (1 << 1) ------------------ | Branch (4493:35): [True: 18, False: 8] ------------------ 4494| 26| break; 4495| 0| } 4496| | // piece 3 - is cross product indicator 4497| 26| case 2: { ------------------ | Branch (4497:7): [True: 26, False: 78] ------------------ 4498| 26| np++; 4499| 26| if (*start_piece == 'Y') ------------------ | Branch (4499:13): [True: 26, False: 0] ------------------ 4500| 26| ff = aeXPRODUCT; ------------------ | | 65| 26|#define aeXPRODUCT (1 << 0) ------------------ 4501| 26| break; 4502| 0| } 4503| | 4504| | // piece 4 - is number of affentries 4505| 26| case 3: { ------------------ | Branch (4505:7): [True: 26, False: 78] ------------------ 4506| 26| np++; 4507| 26| numents = atoi(std::string(start_piece, iter).c_str()); 4508| 26| if ((numents <= 0) || ((std::numeric_limits::max() / ------------------ | Branch (4508:13): [True: 0, False: 26] | Branch (4508:31): [True: 0, False: 26] ------------------ 4509| 26| sizeof(AffEntry)) < static_cast(numents))) { 4510| 0| std::string err = pHMgr->encode_flag(aflag); 4511| 0| HUNSPELL_WARNING(stderr, "error: line %d: affix %s: bad entry number\n", 4512| 0| af->getlinenum(), err.c_str()); 4513| 0| return false; 4514| 0| } 4515| | 4516| 26| char opts = ff; 4517| 26| if (utf8) ------------------ | Branch (4517:13): [True: 6, False: 20] ------------------ 4518| 6| opts |= aeUTF8; ------------------ | | 66| 6|#define aeUTF8 (1 << 1) ------------------ 4519| 26| if (pHMgr->is_aliasf()) ------------------ | Branch (4519:13): [True: 4, False: 22] ------------------ 4520| 4| opts |= aeALIASF; ------------------ | | 67| 4|#define aeALIASF (1 << 2) ------------------ 4521| 26| if (pHMgr->is_aliasm()) ------------------ | Branch (4521:13): [True: 0, False: 26] ------------------ 4522| 0| opts |= aeALIASM; ------------------ | | 68| 0|#define aeALIASM (1 << 3) ------------------ 4523| 26| affentries.initialize(numents, opts, aflag); 4524| 26| } 4525| | 4526| 26| default: ------------------ | Branch (4526:7): [True: 0, False: 104] ------------------ 4527| 26| break; 4528| 104| } 4529| 104| ++i; 4530| 104| start_piece = mystrsep(line, iter); 4531| 104| } 4532| | // check to make sure we parsed enough pieces 4533| 26| if (np != 4) { ------------------ | Branch (4533:7): [True: 0, False: 26] ------------------ 4534| 0| std::string err = pHMgr->encode_flag(aflag); 4535| 0| HUNSPELL_WARNING(stderr, "error: line %d: affix %s: missing data\n", 4536| 0| af->getlinenum(), err.c_str()); 4537| 0| return false; 4538| 0| } 4539| | 4540| | // now parse numents affentries for this affix 4541| 26| AffEntry* entry = affentries.first_entry(); 4542| 68| for (int ent = 0; ent < numents; ++ent) { ------------------ | Branch (4542:21): [True: 42, False: 26] ------------------ 4543| 42| std::string nl; 4544| 42| if (!af->getline(nl)) ------------------ | Branch (4544:9): [True: 0, False: 42] ------------------ 4545| 0| return false; 4546| 42| mychomp(nl); 4547| | 4548| 42| iter = nl.begin(); 4549| 42| i = 0; 4550| 42| np = 0; 4551| | 4552| | // split line into pieces 4553| 42| start_piece = mystrsep(nl, iter); 4554| 258| while (start_piece != nl.end()) { ------------------ | Branch (4554:12): [True: 216, False: 42] ------------------ 4555| 216| switch (i) { 4556| | // piece 1 - is type 4557| 42| case 0: { ------------------ | Branch (4557:9): [True: 42, False: 174] ------------------ 4558| 42| np++; 4559| 42| if (ent != 0) ------------------ | Branch (4559:15): [True: 16, False: 26] ------------------ 4560| 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) ------------------ 4561| 42| break; 4562| 0| } 4563| | 4564| | // piece 2 - is affix char 4565| 42| case 1: { ------------------ | Branch (4565:9): [True: 42, False: 174] ------------------ 4566| 42| np++; 4567| 42| std::string chunk(start_piece, iter); 4568| 42| if (pHMgr->decode_flag(chunk) != aflag) { ------------------ | Branch (4568:15): [True: 0, False: 42] ------------------ 4569| 0| std::string err = pHMgr->encode_flag(aflag); 4570| 0| HUNSPELL_WARNING(stderr, 4571| 0| "error: line %d: affix %s is corrupt\n", 4572| 0| af->getlinenum(), err.c_str()); 4573| 0| return false; 4574| 0| } 4575| | 4576| 42| if (ent != 0) { ------------------ | Branch (4576:15): [True: 16, False: 26] ------------------ 4577| 16| AffEntry* start_entry = affentries.first_entry(); 4578| 16| entry->aflag = start_entry->aflag; 4579| 16| } 4580| 42| break; 4581| 42| } 4582| | 4583| | // piece 3 - is string to strip or 0 for null 4584| 42| case 2: { ------------------ | Branch (4584:9): [True: 42, False: 174] ------------------ 4585| 42| np++; 4586| 42| entry->strip = std::string(start_piece, iter); 4587| 42| if (complexprefixes) { ------------------ | Branch (4587:15): [True: 4, False: 38] ------------------ 4588| 4| if (utf8) ------------------ | Branch (4588:17): [True: 0, False: 4] ------------------ 4589| 0| reverseword_utf(entry->strip); 4590| 4| else 4591| 4| reverseword(entry->strip); 4592| 4| } 4593| 42| if (entry->strip.compare("0") == 0) { ------------------ | Branch (4593:15): [True: 36, False: 6] ------------------ 4594| 36| entry->strip.clear(); 4595| 36| } 4596| 42| break; 4597| 42| } 4598| | 4599| | // piece 4 - is affix string or 0 for null 4600| 42| case 3: { ------------------ | Branch (4600:9): [True: 42, False: 174] ------------------ 4601| 42| entry->morphcode = nullptr; 4602| 42| entry->contclass = nullptr; 4603| 42| entry->contclasslen = 0; 4604| 42| np++; 4605| 42| std::string::const_iterator dash = std::find(start_piece, iter, '/'); 4606| 42| if (dash != iter) { ------------------ | Branch (4606:15): [True: 18, False: 24] ------------------ 4607| 18| entry->appnd = std::string(start_piece, dash); 4608| 18| std::string dash_str(dash + 1, iter); 4609| | 4610| 18| if (!ignorechars.empty() && !has_no_ignored_chars(entry->appnd, ignorechars)) { ------------------ | Branch (4610:17): [True: 2, False: 16] | Branch (4610:41): [True: 0, False: 2] ------------------ 4611| 0| if (utf8) { ------------------ | Branch (4611:19): [True: 0, False: 0] ------------------ 4612| 0| remove_ignored_chars_utf(entry->appnd, ignorechars_utf16); 4613| 0| } else { 4614| 0| remove_ignored_chars(entry->appnd, ignorechars); 4615| 0| } 4616| 0| } 4617| | 4618| 18| if (complexprefixes) { ------------------ | Branch (4618:17): [True: 2, False: 16] ------------------ 4619| 2| if (utf8) ------------------ | Branch (4619:19): [True: 0, False: 2] ------------------ 4620| 0| reverseword_utf(entry->appnd); 4621| 2| else 4622| 2| reverseword(entry->appnd); 4623| 2| } 4624| | 4625| 18| if (pHMgr->is_aliasf()) { ------------------ | Branch (4625:17): [True: 2, False: 16] ------------------ 4626| 2| int index = atoi(dash_str.c_str()); 4627| 2| entry->contclasslen = (unsigned short)pHMgr->get_aliasf( 4628| 2| index, &(entry->contclass), af); 4629| 2| if (!entry->contclasslen) ------------------ | Branch (4629:19): [True: 0, False: 2] ------------------ 4630| 0| HUNSPELL_WARNING(stderr, 4631| 0| "error: bad affix flag alias: \"%s\"\n", 4632| 0| dash_str.c_str()); 4633| 16| } else { 4634| 16| entry->contclasslen = (unsigned short)pHMgr->decode_flags( 4635| 16| &(entry->contclass), dash_str, af); 4636| 16| std::sort(entry->contclass, entry->contclass + entry->contclasslen); 4637| 16| } 4638| | 4639| 18| havecontclass = 1; 4640| 44| for (unsigned short _i = 0; _i < entry->contclasslen; _i++) { ------------------ | Branch (4640:41): [True: 26, False: 18] ------------------ 4641| 26| contclasses[(entry->contclass)[_i]] = 1; 4642| 26| } 4643| 24| } else { 4644| 24| entry->appnd = std::string(start_piece, iter); 4645| | 4646| 24| if (!ignorechars.empty() && !has_no_ignored_chars(entry->appnd, ignorechars)) { ------------------ | Branch (4646:17): [True: 2, False: 22] | Branch (4646:41): [True: 2, False: 0] ------------------ 4647| 2| if (utf8) { ------------------ | Branch (4647:19): [True: 0, False: 2] ------------------ 4648| 0| remove_ignored_chars_utf(entry->appnd, ignorechars_utf16); 4649| 2| } else { 4650| 2| remove_ignored_chars(entry->appnd, ignorechars); 4651| 2| } 4652| 2| } 4653| | 4654| 24| if (complexprefixes) { ------------------ | Branch (4654:17): [True: 2, False: 22] ------------------ 4655| 2| if (utf8) ------------------ | Branch (4655:19): [True: 0, False: 2] ------------------ 4656| 0| reverseword_utf(entry->appnd); 4657| 2| else 4658| 2| reverseword(entry->appnd); 4659| 2| } 4660| 24| } 4661| | 4662| 42| if (entry->appnd.compare("0") == 0) { ------------------ | Branch (4662:15): [True: 2, False: 40] ------------------ 4663| 2| entry->appnd.clear(); 4664| 2| } 4665| 42| break; 4666| 42| } 4667| | 4668| | // piece 5 - is the conditions descriptions 4669| 42| case 4: { ------------------ | Branch (4669:9): [True: 42, False: 174] ------------------ 4670| 42| std::string chunk(start_piece, iter); 4671| 42| np++; 4672| 42| if (complexprefixes) { ------------------ | Branch (4672:15): [True: 4, False: 38] ------------------ 4673| 4| if (utf8) ------------------ | Branch (4673:17): [True: 0, False: 4] ------------------ 4674| 0| reverseword_utf(chunk); 4675| 4| else 4676| 4| reverseword(chunk); 4677| 4| reverse_condition(chunk); 4678| 4| } 4679| 42| if (!entry->strip.empty() && chunk != "." && ------------------ | Branch (4679:15): [True: 6, False: 36] | Branch (4679:40): [True: 6, False: 0] ------------------ 4680| 6| redundant_condition(at, entry->strip, chunk, ------------------ | Branch (4680:15): [True: 6, False: 0] ------------------ 4681| 6| af->getlinenum())) 4682| 6| chunk = "."; 4683| 42| if (at == 'S') { ------------------ | Branch (4683:15): [True: 34, False: 8] ------------------ 4684| 34| reverseword(chunk); 4685| 34| reverse_condition(chunk); 4686| 34| } 4687| 42| if (encodeit(*entry, chunk)) ------------------ | Branch (4687:15): [True: 0, False: 42] ------------------ 4688| 0| return false; 4689| 42| break; 4690| 42| } 4691| | 4692| 42| case 5: { ------------------ | Branch (4692:9): [True: 6, False: 210] ------------------ 4693| 6| std::string chunk(start_piece, iter); 4694| 6| np++; 4695| 6| if (pHMgr->is_aliasm()) { ------------------ | Branch (4695:15): [True: 0, False: 6] ------------------ 4696| 0| int index = atoi(chunk.c_str()); 4697| 0| entry->morphcode = pHMgr->get_aliasm(index); 4698| 6| } else { 4699| 6| if (complexprefixes) { // XXX - fix me for morph. gen. ------------------ | Branch (4699:17): [True: 0, False: 6] ------------------ 4700| 0| if (utf8) ------------------ | Branch (4700:19): [True: 0, False: 0] ------------------ 4701| 0| reverseword_utf(chunk); 4702| 0| else 4703| 0| reverseword(chunk); 4704| 0| } 4705| | // add the remaining of the line 4706| 6| std::string::const_iterator end = nl.end(); 4707| 6| if (iter != end) { ------------------ | Branch (4707:17): [True: 0, False: 6] ------------------ 4708| 0| chunk.append(iter, end); 4709| 0| } 4710| 6| entry->morphcode = mystrdup(chunk.c_str()); 4711| 6| } 4712| 6| break; 4713| 42| } 4714| 0| default: ------------------ | Branch (4714:9): [True: 0, False: 216] ------------------ 4715| 0| break; 4716| 216| } 4717| 216| i++; 4718| 216| start_piece = mystrsep(nl, iter); 4719| 216| } 4720| | // check to make sure we parsed enough pieces 4721| 42| if (np < 4) { ------------------ | Branch (4721:9): [True: 0, False: 42] ------------------ 4722| 0| std::string err = pHMgr->encode_flag(aflag); 4723| 0| HUNSPELL_WARNING(stderr, "error: line %d: affix %s is corrupt\n", 4724| 0| af->getlinenum(), err.c_str()); 4725| 0| return false; 4726| 0| } 4727| | 4728| |#ifdef DEBUG 4729| | // detect unnecessary fields, excepting comments 4730| | if (basefieldnum) { 4731| | int fieldnum = 4732| | !(entry->morphcode) ? 5 : ((*(entry->morphcode) == '#') ? 5 : 6); 4733| | if (fieldnum != basefieldnum) 4734| | HUNSPELL_WARNING(stderr, "warning: line %d: bad field number\n", 4735| | af->getlinenum()); 4736| | } else { 4737| | basefieldnum = 4738| | !(entry->morphcode) ? 5 : ((*(entry->morphcode) == '#') ? 5 : 6); 4739| | } 4740| |#endif 4741| 42| } 4742| | 4743| | // now create SfxEntry or PfxEntry objects and use links to 4744| | // build an ordered (sorted by affix string) list 4745| 26| auto start = affentries.begin(), end = affentries.end(); 4746| 68| for (auto affentry = start; affentry != end; ++affentry) { ------------------ | Branch (4746:31): [True: 42, False: 26] ------------------ 4747| 42| if (at == 'P') { ------------------ | Branch (4747:9): [True: 8, False: 34] ------------------ 4748| 8| build_pfxtree(static_cast(*affentry)); 4749| 34| } else { 4750| 34| build_sfxtree(static_cast(*affentry)); 4751| 34| } 4752| 42| } 4753| | 4754| | //contents belong to AffixMgr now 4755| 26| affentries.release(); 4756| | 4757| 26| return true; 4758| 26|} _ZN8AffixMgr19redundant_conditionEcRKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_i: 4763| 6| int linenum) { 4764| 6| int stripl = strip.size(), condl = cond.size(), i, j, neg, in; 4765| 6| if (ft == 'P') { // prefix ------------------ | Branch (4765:7): [True: 0, False: 6] ------------------ 4766| 0| if (strip.compare(0, condl, cond) == 0) ------------------ | Branch (4766:9): [True: 0, False: 0] ------------------ 4767| 0| return 1; 4768| 0| if (utf8) { ------------------ | Branch (4768:9): [True: 0, False: 0] ------------------ 4769| 0| } else { 4770| 0| for (i = 0, j = 0; (i < stripl) && (j < condl); i++, j++) { ------------------ | Branch (4770:26): [True: 0, False: 0] | Branch (4770:42): [True: 0, False: 0] ------------------ 4771| 0| if (cond[j] != '[') { ------------------ | Branch (4771:13): [True: 0, False: 0] ------------------ 4772| 0| if (cond[j] != strip[i]) { ------------------ | Branch (4772:15): [True: 0, False: 0] ------------------ 4773| 0| HUNSPELL_WARNING(stderr, 4774| 0| "warning: line %d: incompatible stripping " 4775| 0| "characters and condition\n", 4776| 0| linenum); 4777| 0| return 0; 4778| 0| } 4779| 0| } else { 4780| 0| neg = (cond[j + 1] == '^') ? 1 : 0; ------------------ | Branch (4780:17): [True: 0, False: 0] ------------------ 4781| 0| in = 0; 4782| 0| do { 4783| 0| j++; 4784| 0| if (strip[i] == cond[j]) ------------------ | Branch (4784:17): [True: 0, False: 0] ------------------ 4785| 0| in = 1; 4786| 0| } while ((j < (condl - 1)) && (cond[j] != ']')); ------------------ | Branch (4786:20): [True: 0, False: 0] | Branch (4786:41): [True: 0, False: 0] ------------------ 4787| 0| if (j == (condl - 1) && (cond[j] != ']')) { ------------------ | Branch (4787:15): [True: 0, False: 0] | Branch (4787:35): [True: 0, False: 0] ------------------ 4788| 0| HUNSPELL_WARNING(stderr, 4789| 0| "error: line %d: missing ] in condition:\n%s\n", 4790| 0| linenum, cond.c_str()); 4791| 0| return 0; 4792| 0| } 4793| 0| if ((!neg && !in) || (neg && in)) { ------------------ | Branch (4793:16): [True: 0, False: 0] | Branch (4793:24): [True: 0, False: 0] | Branch (4793:33): [True: 0, False: 0] | Branch (4793:40): [True: 0, False: 0] ------------------ 4794| 0| HUNSPELL_WARNING(stderr, 4795| 0| "warning: line %d: incompatible stripping " 4796| 0| "characters and condition\n", 4797| 0| linenum); 4798| 0| return 0; 4799| 0| } 4800| 0| } 4801| 0| } 4802| 0| if (j >= condl) ------------------ | Branch (4802:11): [True: 0, False: 0] ------------------ 4803| 0| return 1; 4804| 0| } 4805| 6| } else { // suffix 4806| 6| if ((stripl >= condl) && strip.compare(stripl - condl, std::string::npos, cond) == 0) ------------------ | Branch (4806:9): [True: 6, False: 0] | Branch (4806:30): [True: 6, False: 0] ------------------ 4807| 6| return 1; 4808| 0| if (utf8) { ------------------ | Branch (4808:9): [True: 0, False: 0] ------------------ 4809| 0| } else { 4810| 0| for (i = stripl - 1, j = condl - 1; (i >= 0) && (j >= 0); i--, j--) { ------------------ | Branch (4810:43): [True: 0, False: 0] | Branch (4810:55): [True: 0, False: 0] ------------------ 4811| 0| if (cond[j] != ']') { ------------------ | Branch (4811:13): [True: 0, False: 0] ------------------ 4812| 0| if (cond[j] != strip[i]) { ------------------ | Branch (4812:15): [True: 0, False: 0] ------------------ 4813| 0| HUNSPELL_WARNING(stderr, 4814| 0| "warning: line %d: incompatible stripping " 4815| 0| "characters and condition\n", 4816| 0| linenum); 4817| 0| return 0; 4818| 0| } 4819| 0| } else if (j > 0) { ------------------ | Branch (4819:20): [True: 0, False: 0] ------------------ 4820| 0| in = 0; 4821| 0| do { 4822| 0| j--; 4823| 0| if (strip[i] == cond[j]) ------------------ | Branch (4823:17): [True: 0, False: 0] ------------------ 4824| 0| in = 1; 4825| 0| } while ((j > 0) && (cond[j] != '[')); ------------------ | Branch (4825:20): [True: 0, False: 0] | Branch (4825:31): [True: 0, False: 0] ------------------ 4826| 0| if ((j == 0) && (cond[j] != '[')) { ------------------ | Branch (4826:15): [True: 0, False: 0] | Branch (4826:27): [True: 0, False: 0] ------------------ 4827| 0| HUNSPELL_WARNING(stderr, 4828| 0| "error: line: %d: missing ] in condition:\n%s\n", 4829| 0| linenum, cond.c_str()); 4830| 0| return 0; 4831| 0| } 4832| 0| neg = (cond[j + 1] == '^') ? 1 : 0; ------------------ | Branch (4832:17): [True: 0, False: 0] ------------------ 4833| 0| if ((!neg && !in) || (neg && in)) { ------------------ | Branch (4833:16): [True: 0, False: 0] | Branch (4833:24): [True: 0, False: 0] | Branch (4833:33): [True: 0, False: 0] | Branch (4833:40): [True: 0, False: 0] ------------------ 4834| 0| HUNSPELL_WARNING(stderr, 4835| 0| "warning: line %d: incompatible stripping " 4836| 0| "characters and condition\n", 4837| 0| linenum); 4838| 0| return 0; 4839| 0| } 4840| 0| } 4841| 0| } 4842| 0| if (j < 0) ------------------ | Branch (4842:11): [True: 0, False: 0] ------------------ 4843| 0| return 1; 4844| 0| } 4845| 0| } 4846| 0| return 0; 4847| 6|} _ZN8AffixMgr8isSubsetEPKcS1_: 1069| 67.0k|inline int AffixMgr::isSubset(const char* s1, const char* s2) { 1070| 87.6k| while (((*s1 == *s2) || (*s1 == '.')) && (*s1 != '\0') && (*s2 != '\0')) { ------------------ | Branch (1070:11): [True: 67.2k, False: 20.3k] | Branch (1070:27): [True: 0, False: 20.3k] | Branch (1070:44): [True: 20.5k, False: 46.7k] | Branch (1070:61): [True: 20.5k, False: 0] ------------------ 1071| 20.5k| s1++; 1072| 20.5k| s2++; 1073| 20.5k| } 1074| 67.0k| return (*s1 == '\0'); 1075| 67.0k|} _ZN8AffixMgr11isRevSubsetEPKcS1_i: 2719| 668k| int len) { 2720| 1.35M| while ((len > 0) && (*s1 != '\0') && ((*s1 == *end_of_s2) || (*s1 == '.'))) { ------------------ | Branch (2720:10): [True: 1.35M, False: 2.01k] | Branch (2720:23): [True: 791k, False: 562k] | Branch (2720:41): [True: 686k, False: 104k] | Branch (2720:64): [True: 0, False: 104k] ------------------ 2721| 686k| s1++; 2722| 686k| end_of_s2--; 2723| 686k| len--; 2724| 686k| } 2725| 668k| return (*s1 == '\0'); 2726| 668k|} affixmgr.cxx:_ZN12_GLOBAL__N_18mystrdupEPKc: 3368| 601k| char* mystrdup(const char* s) { 3369| 601k| char* d = nullptr; 3370| 601k| if (s) { ------------------ | Branch (3370:9): [True: 601k, False: 0] ------------------ 3371| 601k| size_t sl = strlen(s) + 1; 3372| 601k| d = new char[sl]; 3373| 601k| memcpy(d, s, sl); 3374| 601k| } 3375| 601k| return d; 3376| 601k| } _ZN17entries_containerC2EcP8AffixMgr: 4409| 26| : m_mgr(mgr) 4410| 26| , m_at(at) { 4411| 26| } _ZN17entries_container10initializeEict: 4416| 26| char opts, unsigned short aflag) { 4417| 26| entries.reserve(std::min(numents, 16384)); 4418| | 4419| 26| if (m_at == 'P') { ------------------ | Branch (4419:9): [True: 8, False: 18] ------------------ 4420| 8| entries.push_back(new PfxEntry(m_mgr)); 4421| 18| } else { 4422| 18| entries.push_back(new SfxEntry(m_mgr)); 4423| 18| } 4424| | 4425| 26| entries.back()->opts = opts; 4426| 26| entries.back()->aflag = aflag; 4427| 26| } _ZN17entries_container11first_entryEv: 4440| 42| AffEntry* first_entry() { return entries.empty() ? nullptr : entries[0]; } ------------------ | Branch (4440:36): [True: 0, False: 42] ------------------ _ZN17entries_container9add_entryEc: 4429| 16| AffEntry* add_entry(char opts) { 4430| 16| if (m_at == 'P') { ------------------ | Branch (4430:9): [True: 0, False: 16] ------------------ 4431| 0| entries.push_back(new PfxEntry(m_mgr)); 4432| 16| } else { 4433| 16| entries.push_back(new SfxEntry(m_mgr)); 4434| 16| } 4435| 16| AffEntry* ret = entries.back(); 4436| 16| ret->opts = entries[0]->opts & opts; 4437| 16| return ret; 4438| 16| } _ZN17entries_container5beginEv: 4448| 26| std::vector::iterator begin() { return entries.begin(); } _ZN17entries_container3endEv: 4449| 26| std::vector::iterator end() { return entries.end(); } _ZN17entries_container7releaseEv: 4412| 26| void release() { 4413| 26| entries.clear(); 4414| 26| } _ZN17entries_containerD2Ev: 4442| 26| ~entries_container() { 4443| 26| for (auto& entry : entries) { ------------------ | Branch (4443:22): [True: 0, False: 26] ------------------ 4444| 0| delete entry; 4445| 0| } 4446| 26| } affixmgr.cxx:_ZZN8AffixMgr12get_syllableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEENK3$_1clE6w_char: 1568| 2.22k| [&](w_char wc) { 1569| 2.22k| return std::binary_search(cpdvowels_utf16.begin(), cpdvowels_utf16.end(), wc); 1570| 2.22k| }); _ZN9guesswordC2Ev: 118| 4.84M| : word(nullptr) 119| 4.84M| , allow(false) 120| 4.84M| , orig(nullptr) 121| 4.84M| { 122| 4.84M| } _ZN8patentryC2Ev: 135| 4| : cond(FLAG_NULL) ------------------ | | 96| 4|#define FLAG_NULL 0x00 ------------------ 136| 4| , cond2(FLAG_NULL) { ------------------ | | 96| 4|#define FLAG_NULL 0x00 ------------------ 137| 4| } csutil.cxx:_ZL16HUNSPELL_WARNINGP8_IO_FILEPKcz: 48| 1.58M|static inline void HUNSPELL_WARNING(FILE*, const char*, ...) {} _ZN8AffEntryC2Ev: 46| 42| : morphcode(nullptr) 47| 42| , contclass(nullptr) 48| 42| , aflag(0) 49| 42| , contclasslen(0) 50| 42| , numconds(0) 51| 42| , opts(0) {} _Z6myopenRNSt3__114basic_ifstreamIcNS_11char_traitsIcEEEEPKcj: 110| 114|{ 111| |#if defined(_WIN32) && defined(_MSC_VER) 112| |#define WIN32_LONG_PATH_PREFIX "\\\\?\\" 113| | if (strncmp(path, WIN32_LONG_PATH_PREFIX, 4) == 0) { 114| | int len = MultiByteToWideChar(CP_UTF8, 0, path, -1, NULL, 0); 115| | wchar_t* buff = new wchar_t[len]; 116| | wchar_t* buff2 = new wchar_t[len]; 117| | MultiByteToWideChar(CP_UTF8, 0, path, -1, buff, len); 118| | if (_wfullpath(buff2, buff, len) != NULL) { 119| | stream.open(buff2, mode); 120| | } 121| | delete [] buff; 122| | delete [] buff2; 123| | } 124| | else 125| |#endif 126| 114| stream.open(path, mode); 127| 114|} _Z6u16_u8RNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKNS_6vectorI6w_charNS3_IS8_EEEE: 134| 22.6M|std::string& u16_u8(std::string& dest, const std::vector& src) { 135| 22.6M| dest.clear(); 136| 22.6M| dest.reserve(src.size()); 137| 600M| for (const w_char& wc : src) { ------------------ | Branch (137:25): [True: 600M, False: 22.6M] ------------------ 138| 600M| uint16_t cp = (static_cast(wc.h) << 8) | wc.l; 139| 600M| if (cp < 0x80) { ------------------ | Branch (139:9): [True: 519M, False: 81.5M] ------------------ 140| 519M| dest.push_back(static_cast(cp)); 141| 519M| } else if (cp < 0x800) { ------------------ | Branch (141:16): [True: 3.08M, False: 78.4M] ------------------ 142| 3.08M| dest.push_back(static_cast(0xc0 | (cp >> 6))); 143| 3.08M| dest.push_back(static_cast(0x80 | (cp & 0x3f))); 144| 78.4M| } else { 145| 78.4M| dest.push_back(static_cast(0xe0 | (cp >> 12))); 146| 78.4M| dest.push_back(static_cast(0x80 | ((cp >> 6) & 0x3f))); 147| 78.4M| dest.push_back(static_cast(0x80 | (cp & 0x3f))); 148| 78.4M| } 149| 600M| } 150| 22.6M| return dest; 151| 22.6M|} _Z6u8_u16RNSt3__16vectorI6w_charNS_9allocatorIS1_EEEERKNS_12basic_stringIcNS_11char_traitsIcEENS2_IcEEEEb: 169| 3.86M|int u8_u16(std::vector& dest, const std::string& src, bool only_convert_first_letter) { 170| | // faster to oversize initially, assign to elements and resize to what's used 171| | // than to reserve and push_back 172| 3.86M| dest.resize(only_convert_first_letter ? 1 : src.size()); ------------------ | Branch (172:15): [True: 0, False: 3.86M] ------------------ 173| 3.86M| auto out = dest.begin(); 174| 3.86M| auto p = src.begin(), end = src.end(); 175| | 176| 31.9M| while (p < end) { ------------------ | Branch (176:10): [True: 28.3M, False: 3.66M] ------------------ 177| 28.3M| uint8_t b0 = static_cast(*p); 178| 28.3M| uint16_t cp; 179| | 180| 28.3M| if (b0 < 0x80) { ------------------ | Branch (180:9): [True: 24.2M, False: 4.09M] ------------------ 181| | // 1-byte ASCII 182| 24.2M| cp = b0; 183| 24.2M| } else if (b0 < 0xc0) { ------------------ | Branch (183:16): [True: 565k, False: 3.52M] ------------------ 184| | // continuation byte at lead position 185| 565k| HUNSPELL_WARNING(stderr, 186| 565k| "UTF-8 encoding error. Unexpected continuation bytes " 187| 565k| "in %ld. character position\n%s\n", 188| 565k| static_cast(std::distance(src.begin(), p)), 189| 565k| src.c_str()); 190| 565k| cp = 0xfffd; 191| 3.52M| } else if (b0 < 0xe0) { ------------------ | Branch (191:16): [True: 910k, False: 2.61M] ------------------ 192| | // 2-byte sequence: 110xxxxx 10yyyyyy 193| 910k| if (p + 1 < end && is_utf8_cont(p[1])) { ------------------ | Branch (193:11): [True: 790k, False: 119k] | Branch (193:11): [True: 211k, False: 698k] | Branch (193:26): [True: 211k, False: 579k] ------------------ 194| 211k| cp = ((b0 & 0x1f) << 6) | (static_cast(p[1]) & 0x3f); 195| 211k| ++p; // step past lead; loop bottom steps past cont 196| 698k| } else { 197| 698k| warn_missing_cont(src, p); 198| 698k| cp = 0xfffd; 199| 698k| } 200| 2.61M| } else if (b0 < 0xf0) { ------------------ | Branch (200:16): [True: 2.42M, False: 196k] ------------------ 201| | // 3-byte sequence: 1110xxxx 10yyyyyy 10zzzzzz 202| 2.42M| if (p + 1 < end && is_utf8_cont(p[1])) { ------------------ | Branch (202:11): [True: 2.39M, False: 22.5k] | Branch (202:11): [True: 2.31M, False: 104k] | Branch (202:26): [True: 2.31M, False: 81.9k] ------------------ 203| 2.31M| uint8_t b1 = static_cast(p[1]); 204| 2.31M| ++p; // step past lead 205| 2.31M| if (p + 1 < end && is_utf8_cont(p[1])) { ------------------ | Branch (205:13): [True: 2.31M, False: 1.39k] | Branch (205:13): [True: 2.29M, False: 16.2k] | Branch (205:28): [True: 2.29M, False: 14.8k] ------------------ 206| 2.29M| cp = ((b0 & 0x0f) << 12) | ((b1 & 0x3f) << 6) | (static_cast(p[1]) & 0x3f); 207| 2.29M| ++p; // step past first cont; loop bottom steps past second cont 208| 2.29M| } else { 209| 16.2k| warn_missing_cont(src, p); 210| 16.2k| cp = 0xfffd; 211| 16.2k| } 212| 2.31M| } else { 213| 104k| warn_missing_cont(src, p); 214| 104k| cp = 0xfffd; 215| 104k| } 216| 2.42M| } else { 217| | // 4+ byte lead: codepoint >= U+10000, can't fit in w_char 218| 196k| HUNSPELL_WARNING(stderr, 219| 196k| "This UTF-8 encoding can't convert to UTF-16:\n%s\n", 220| 196k| src.c_str()); 221| 196k| out->h = 0xff; 222| 196k| out->l = 0xfd; 223| 196k| ++out; 224| 196k| dest.resize(out - dest.begin()); 225| 196k| return -1; 226| 196k| } 227| | 228| 28.1M| out->h = static_cast(cp >> 8); 229| 28.1M| out->l = static_cast(cp); 230| 28.1M| ++out; 231| 28.1M| if (only_convert_first_letter) ------------------ | Branch (231:9): [True: 0, False: 28.1M] ------------------ 232| 0| break; 233| 28.1M| ++p; // consume lead byte 234| 28.1M| } 235| | 236| 3.66M| int size = static_cast(out - dest.begin()); 237| 3.66M| dest.resize(size); 238| 3.66M| return size; 239| 3.86M|} _Z8mystrsepRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERNS_11__wrap_iterIPKcEE: 254| 1.80k| std::string::const_iterator& start) { 255| 1.80k| auto end = str.end(); 256| | 257| 1.80k| is_any_of op(" \t"); 258| | // don't use isspace() here, the string can be in some random charset 259| | // that's way different than the locale's 260| 1.80k| auto sp = start; 261| 5.87k| while (sp != end && op(*sp)) ------------------ | Branch (261:10): [True: 5.43k, False: 442] | Branch (261:23): [True: 4.07k, False: 1.35k] ------------------ 262| 4.07k| ++sp; 263| | 264| 1.80k| auto dp = sp; 265| 6.69k| while (dp != end && !op(*dp)) ------------------ | Branch (265:10): [True: 5.81k, False: 882] | Branch (265:23): [True: 4.89k, False: 918] ------------------ 266| 4.89k| ++dp; 267| | 268| 1.80k| start = dp; 269| 1.80k| return sp; 270| 1.80k|} _Z7mychompRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 273| 1.99k|void mychomp(std::string& s) { 274| 1.99k| size_t k = s.size(); 275| 1.99k| size_t newsize = k; 276| 1.99k| if ((k > 0) && ((s[k - 1] == '\r') || (s[k - 1] == '\n'))) ------------------ | Branch (276:7): [True: 1.80k, False: 190] | Branch (276:19): [True: 0, False: 1.80k] | Branch (276:41): [True: 0, False: 1.80k] ------------------ 277| 0| --newsize; 278| 1.99k| if ((k > 1) && (s[k - 2] == '\r')) ------------------ | Branch (278:7): [True: 1.60k, False: 384] | Branch (278:18): [True: 0, False: 1.60k] ------------------ 279| 0| --newsize; 280| 1.99k| s.resize(newsize); 281| 1.99k|} _Z8line_tokRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEc: 284| 260k|std::vector line_tok(const std::string& text, char breakchar) { 285| 260k| std::vector ret; 286| 260k| if (text.empty()) { ------------------ | Branch (286:7): [True: 10.5k, False: 249k] ------------------ 287| 10.5k| return ret; 288| 10.5k| } 289| | 290| 249k| std::stringstream ss(text); 291| 249k| std::string tok; 292| 500k| while(std::getline(ss, tok, breakchar)) { ------------------ | Branch (292:9): [True: 251k, False: 249k] ------------------ 293| 251k| if (!tok.empty()) { ------------------ | Branch (293:9): [True: 250k, False: 95] ------------------ 294| 250k| ret.push_back(tok); 295| 250k| } 296| 251k| } 297| | 298| 249k| return ret; 299| 260k|} _Z9line_uniqRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEc: 303| 13.6k|{ 304| 13.6k| std::vector lines = line_tok(text, breakchar); 305| 13.6k| text.clear(); 306| 13.6k| if (lines.empty()) { ------------------ | Branch (306:7): [True: 10.5k, False: 3.06k] ------------------ 307| 10.5k| return; 308| 10.5k| } 309| 3.06k| text = lines[0]; 310| 3.71k| for (size_t i = 1; i < lines.size(); ++i) { ------------------ | Branch (310:22): [True: 648, False: 3.06k] ------------------ 311| 648| bool dup = false; 312| 648| for (size_t j = 0; j < i; ++j) { ------------------ | Branch (312:24): [True: 648, False: 0] ------------------ 313| 648| if (lines[i] == lines[j]) { ------------------ | Branch (313:11): [True: 648, False: 0] ------------------ 314| 648| dup = true; 315| 648| break; 316| 648| } 317| 648| } 318| 648| if (!dup) { ------------------ | Branch (318:9): [True: 0, False: 648] ------------------ 319| 0| if (!text.empty()) ------------------ | Branch (319:11): [True: 0, False: 0] ------------------ 320| 0| text.push_back(breakchar); 321| 0| text.append(lines[i]); 322| 0| } 323| 648| } 324| 3.06k|} _Z10copy_fieldRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKS5_S8_: 388| 233k| const std::string& var) { 389| 233k| if (morph.empty()) ------------------ | Branch (389:7): [True: 0, False: 233k] ------------------ 390| 0| return false; 391| 233k| size_t pos = morph.find(var); 392| 233k| if (pos == std::string::npos) ------------------ | Branch (392:7): [True: 6, False: 233k] ------------------ 393| 6| return false; 394| 233k| dest.clear(); 395| 233k| std::string beg(morph.substr(pos + MORPH_TAG_LEN, std::string::npos)); ------------------ | | 119| 233k|#define MORPH_TAG_LEN strlen(MORPH_STEM) | | ------------------ | | | | 103| 233k|#define MORPH_STEM "st:" | | ------------------ ------------------ 396| | 397| 677k| for (const char c : beg) { ------------------ | Branch (397:21): [True: 677k, False: 233k] ------------------ 398| 677k| if (c == ' ' || c == '\t' || c == '\n') ------------------ | Branch (398:9): [True: 0, False: 677k] | Branch (398:21): [True: 0, False: 677k] | Branch (398:34): [True: 0, False: 677k] ------------------ 399| 0| break; 400| 677k| dest.push_back(c); 401| 677k| } 402| | 403| 233k| return true; 404| 233k|} _Z8mystrrepRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKS5_S8_: 408| 799k| const std::string& replace) { 409| 799k| size_t pos = 0; 410| 888k| while ((pos = str.find(search, pos)) != std::string::npos) { ------------------ | Branch (410:10): [True: 89.0k, False: 799k] ------------------ 411| 89.0k| str.replace(pos, search.length(), replace); 412| 89.0k| pos += replace.length(); 413| 89.0k| } 414| 799k| return str; 415| 799k|} _Z11reversewordRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 418| 1.07M|size_t reverseword(std::string& word) { 419| 1.07M| std::reverse(word.begin(), word.end()); 420| 1.07M| return word.size(); 421| 1.07M|} _Z8uniqlistRNSt3__16vectorINS_12basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS4_IS6_EEEE: 498| 6.21k|void uniqlist(std::vector& list) { 499| 6.21k| if (list.size() < 2) ------------------ | Branch (499:7): [True: 6.20k, False: 8] ------------------ 500| 6.20k| return; 501| | 502| 8| std::vector ret; 503| 8| ret.push_back(list[0]); 504| | 505| 16| for (size_t i = 1; i < list.size(); ++i) { ------------------ | Branch (505:22): [True: 8, False: 8] ------------------ 506| 8| if (std::find(ret.begin(), ret.end(), list[i]) == ret.end()) ------------------ | Branch (506:9): [True: 8, False: 0] ------------------ 507| 8| ret.push_back(list[i]); 508| 8| } 509| | 510| 8| list.swap(ret); 511| 8|} _Z9upper_utf6w_chari: 530| 4.15M|w_char upper_utf(w_char u, int langnum) { 531| | 532| 4.15M|#if defined(_WIN32) || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__==__ORDER_LITTLE_ENDIAN__)) || defined(__LITTLE_ENDIAN__) 533| | 534| |//with these optimizations, msvc can optimize this function to one jmp instruction 535| |//but g++ remains in five instructions 536| |//maybe use inline asm for g++? 537| | 538| |#if (__cplusplus >= 202002L || (defined(_MSVC_LANG) && _MSVC_LANG >= 202002L)) && defined __cpp_lib_bit_cast && __cpp_lib_bit_cast >= 201806L 539| | return std::bit_cast(unicodetoupper((unsigned short)u, langnum)); 540| |#else 541| 4.15M| const auto us = unicodetoupper((unsigned short)u, langnum); 542| 4.15M| memcpy(&u, &us, sizeof(unsigned short)); 543| 4.15M| return u; 544| 4.15M|#endif 545| | 546| |#else 547| | const auto us = unicodetoupper((unsigned short)u, langnum); 548| | u.h = (unsigned char)(us >> 8); 549| | u.l = (unsigned char)(us & 0xff); 550| | return u; 551| |#endif 552| 4.15M|} _Z9lower_utf6w_chari: 554| 6.49M|w_char lower_utf(w_char u, int langnum) { 555| | 556| 6.49M|#if defined(_WIN32) || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__==__ORDER_LITTLE_ENDIAN__)) || defined(__LITTLE_ENDIAN__) 557| | 558| |//with these optimizations, msvc can optimize this function to one jmp instruction 559| |//but g++ remains in five instructions 560| |//maybe use inline asm for g++? 561| | 562| |#if (__cplusplus >= 202002L || (defined(_MSVC_LANG) && _MSVC_LANG >= 202002L)) && defined __cpp_lib_bit_cast && __cpp_lib_bit_cast >= 201806L 563| | return std::bit_cast(unicodetolower((unsigned short)u, langnum)); 564| |#else 565| 6.49M| const auto us = unicodetolower((unsigned short)u, langnum); 566| 6.49M| memcpy(&u, &us, sizeof(unsigned short)); 567| 6.49M| return u; 568| 6.49M|#endif 569| | 570| |#else 571| | const auto us = unicodetolower((unsigned short)u, langnum); 572| | u.h = (unsigned char)(us >> 8); 573| | u.l = (unsigned char)(us & 0xff); 574| | return u; 575| |#endif 576| 6.49M|} _Z8mkallcapRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 579| 276k|std::string& mkallcap(std::string& s, const struct cs_info* csconv) { 580| 5.64M| for (char& aI : s) { ------------------ | Branch (580:17): [True: 5.64M, False: 276k] ------------------ 581| 5.64M| aI = cupper(csconv, static_cast(aI)); 582| 5.64M| } 583| 276k| return s; 584| 276k|} _Z10mkallsmallRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 587| 1.65M|std::string& mkallsmall(std::string& s, const struct cs_info* csconv) { 588| 17.6M| for (char& aI : s) { ------------------ | Branch (588:17): [True: 17.6M, False: 1.65M] ------------------ 589| 17.6M| aI = clower(csconv, static_cast(aI)); 590| 17.6M| } 591| 1.65M| return s; 592| 1.65M|} _Z14mkallsmall_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 594| 922k|std::vector& mkallsmall_utf(std::vector& u, int langnum) { 595| 6.47M| for (auto& i : u) { ------------------ | Branch (595:16): [True: 6.47M, False: 922k] ------------------ 596| 6.47M| i = lower_utf(i, langnum); 597| 6.47M| } 598| 922k| return u; 599| 922k|} _Z12mkallcap_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 601| 159k|std::vector& mkallcap_utf(std::vector& u, int langnum) { 602| 1.95M| for (auto& i : u) { ------------------ | Branch (602:16): [True: 1.95M, False: 159k] ------------------ 603| 1.95M| i = upper_utf(i, langnum); 604| 1.95M| } 605| 159k| return u; 606| 159k|} _Z9mkinitcapRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 608| 816k|std::string& mkinitcap(std::string& s, const struct cs_info* csconv) { 609| 816k| if (!s.empty()) { ------------------ | Branch (609:7): [True: 816k, False: 215] ------------------ 610| 816k| s[0] = cupper(csconv, static_cast(s[0])); 611| 816k| } 612| 816k| return s; 613| 816k|} _Z13mkinitcap_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 615| 244k|std::vector& mkinitcap_utf(std::vector& u, int langnum) { 616| 244k| if (!u.empty()) { ------------------ | Branch (616:7): [True: 244k, False: 0] ------------------ 617| 244k| u[0] = upper_utf(u[0], langnum); 618| 244k| } 619| 244k| return u; 620| 244k|} _Z11mkinitsmallRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 622| 11.0k|std::string& mkinitsmall(std::string& s, const struct cs_info* csconv) { 623| 11.0k| if (!s.empty()) { ------------------ | Branch (623:7): [True: 11.0k, False: 0] ------------------ 624| 11.0k| s[0] = clower(csconv, static_cast(s[0])); 625| 11.0k| } 626| 11.0k| return s; 627| 11.0k|} _Z15mkinitsmall_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 629| 3.28k|std::vector& mkinitsmall_utf(std::vector& u, int langnum) { 630| 3.28k| if (!u.empty()) { ------------------ | Branch (630:7): [True: 3.28k, False: 0] ------------------ 631| 3.28k| u[0] = lower_utf(u[0], langnum); 632| 3.28k| } 633| 3.28k| return u; 634| 3.28k|} _Z14get_current_csRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 2292| 1.82k|const struct cs_info* get_current_cs(const std::string& es) { 2293| 1.82k| char* normalized_encoding = new char[es.size() + 1]; 2294| 1.82k| toAsciiLowerAndRemoveNonAlphanumeric(es.c_str(), normalized_encoding); 2295| | 2296| 1.82k| const struct cs_info* ccs = nullptr; 2297| 1.82k| for (const auto& encd : encds) { ------------------ | Branch (2297:25): [True: 1.82k, False: 0] ------------------ 2298| 1.82k| if (strcmp(normalized_encoding, encd.enc_name) == 0) { ------------------ | Branch (2298:9): [True: 1.82k, False: 0] ------------------ 2299| 1.82k| ccs = encd.cs_table; 2300| 1.82k| break; 2301| 1.82k| } 2302| 1.82k| } 2303| | 2304| 1.82k| delete[] normalized_encoding; 2305| | 2306| 1.82k| if (!ccs) { ------------------ | Branch (2306:7): [True: 0, False: 1.82k] ------------------ 2307| 0| HUNSPELL_WARNING(stderr, 2308| 0| "error: unknown encoding %s: using %s as fallback\n", es.c_str(), 2309| 0| encds[0].enc_name); 2310| 0| ccs = encds[0].cs_table; 2311| 0| } 2312| | 2313| 1.82k| return ccs; 2314| 1.82k|} _Z12get_lang_numRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 2444| 4|int get_lang_num(const std::string& lang) { 2445| 72| for (const auto& i : lang2enc) { ------------------ | Branch (2445:22): [True: 72, False: 0] ------------------ 2446| 72| if (strcmp(lang.c_str(), i.lang) == 0) { ------------------ | Branch (2446:9): [True: 4, False: 68] ------------------ 2447| 4| return i.num; 2448| 4| } 2449| 72| } 2450| 0| return LANG_xx; 2451| 4|} _Z14unicodetoupperti: 2453| 23.6M|unsigned short unicodetoupper(unsigned short c, int langnum) { 2454| | // In Azeri and Turkish, I and i dictinct letters: 2455| | // There are a dotless lower case i pair of upper `I', 2456| | // and an upper I with dot pair of lower `i'. 2457| 23.6M| if (c == 0x0069 && ((langnum == LANG_az) || (langnum == LANG_tr) || (langnum == LANG_crh))) ------------------ | Branch (2457:7): [True: 53.8k, False: 23.5M] | Branch (2457:23): [True: 0, False: 53.8k] | Branch (2457:47): [True: 0, False: 53.8k] | Branch (2457:71): [True: 0, False: 53.8k] ------------------ 2458| 0| return 0x0130; 2459| |#ifdef OPENOFFICEORG 2460| | return static_cast(u_toupper(c)); 2461| |#else 2462| |#ifdef MOZILLA_CLIENT 2463| | return ToUpperCase((char16_t)c); 2464| |#else 2465| 23.6M| unsigned short up = utf_pages[utf_page_index[c >> 8]][c & 0xFF].cupper; 2466| 23.6M| return up ? up : c; ------------------ | Branch (2466:10): [True: 5.29M, False: 18.3M] ------------------ 2467| 23.6M|#endif 2468| 23.6M|#endif 2469| 23.6M|} _Z14unicodetolowerti: 2471| 26.8M|unsigned short unicodetolower(unsigned short c, int langnum) { 2472| | // In Azeri and Turkish, I and i dictinct letters: 2473| | // There are a dotless lower case i pair of upper `I', 2474| | // and an upper I with dot pair of lower `i'. 2475| 26.8M| if (c == 0x0049 && ((langnum == LANG_az) || (langnum == LANG_tr) || (langnum == LANG_crh))) ------------------ | Branch (2475:7): [True: 8.76k, False: 26.8M] | Branch (2475:23): [True: 0, False: 8.76k] | Branch (2475:47): [True: 0, False: 8.76k] | Branch (2475:71): [True: 0, False: 8.76k] ------------------ 2476| 0| return 0x0131; 2477| |#ifdef OPENOFFICEORG 2478| | return static_cast(u_tolower(c)); 2479| |#else 2480| |#ifdef MOZILLA_CLIENT 2481| | return ToLowerCase((char16_t)c); 2482| |#else 2483| 26.8M| unsigned short lo = utf_pages[utf_page_index[c >> 8]][c & 0xFF].clower; 2484| 26.8M| return lo ? lo : c; ------------------ | Branch (2484:10): [True: 2.40M, False: 24.4M] ------------------ 2485| 26.8M|#endif 2486| 26.8M|#endif 2487| 26.8M|} _Z11get_captypeRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 2498| 8.81M|int get_captype(const std::string& word, const cs_info* csconv) { 2499| | // now determine the capitalization type of the first nl letters 2500| 8.81M| size_t ncap = 0; 2501| 8.81M| size_t nneutral = 0; 2502| 8.81M| size_t firstcap = 0; 2503| 8.81M| if (csconv == nullptr) ------------------ | Branch (2503:7): [True: 0, False: 8.81M] ------------------ 2504| 0| return NOCAP; ------------------ | | 92| 0|#define NOCAP 0 ------------------ 2505| 120M| for (char q : word) { ------------------ | Branch (2505:15): [True: 120M, False: 8.81M] ------------------ 2506| 120M| const auto nIndex = static_cast(q); 2507| 120M| if (ccase(csconv, nIndex)) ------------------ | Branch (2507:9): [True: 5.29M, False: 115M] ------------------ 2508| 5.29M| ncap++; 2509| 120M| if (cupper(csconv, nIndex) == clower(csconv, nIndex)) ------------------ | Branch (2509:9): [True: 92.9M, False: 27.3M] ------------------ 2510| 92.9M| nneutral++; 2511| 120M| } 2512| 8.81M| if (ncap) { ------------------ | Branch (2512:7): [True: 1.58M, False: 7.22M] ------------------ 2513| 1.58M| const auto nIndex = static_cast(word[0]); 2514| 1.58M| firstcap = csconv[nIndex].ccase; 2515| 1.58M| } 2516| | 2517| | // now finally set the captype 2518| 8.81M| if (ncap == 0) { ------------------ | Branch (2518:7): [True: 7.22M, False: 1.58M] ------------------ 2519| 7.22M| return NOCAP; ------------------ | | 92| 7.22M|#define NOCAP 0 ------------------ 2520| 7.22M| } else if ((ncap == 1) && firstcap) { ------------------ | Branch (2520:14): [True: 803k, False: 782k] | Branch (2520:29): [True: 428k, False: 374k] ------------------ 2521| 428k| return INITCAP; ------------------ | | 93| 428k|#define INITCAP 1 ------------------ 2522| 1.15M| } else if ((ncap == word.size()) || ((ncap + nneutral) == word.size())) { ------------------ | Branch (2522:14): [True: 8.72k, False: 1.14M] | Branch (2522:39): [True: 129k, False: 1.01M] ------------------ 2523| 138k| return ALLCAP; ------------------ | | 94| 138k|#define ALLCAP 2 ------------------ 2524| 1.01M| } else if ((ncap > 1) && firstcap) { ------------------ | Branch (2524:14): [True: 700k, False: 318k] | Branch (2524:28): [True: 294k, False: 405k] ------------------ 2525| 294k| return HUHINITCAP; ------------------ | | 96| 294k|#define HUHINITCAP 4 ------------------ 2526| 294k| } 2527| 724k| return HUHCAP; ------------------ | | 95| 724k|#define HUHCAP 3 ------------------ 2528| 8.81M|} _Z16get_captype_utf8RKNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 2530| 2.39M|int get_captype_utf8(const std::vector& word, int langnum) { 2531| | // now determine the capitalization type of the first nl letters 2532| 2.39M| size_t ncap = 0; 2533| 2.39M| size_t nneutral = 0; 2534| 2.39M| size_t firstcap = 0; 2535| | 2536| 2.39M| auto it = word.begin(), it_end = word.end(); 2537| 21.7M| while (it != it_end) { ------------------ | Branch (2537:10): [True: 19.3M, False: 2.39M] ------------------ 2538| 19.3M| const auto idx = (unsigned short)*it; 2539| 19.3M| const auto lwridx = unicodetolower(idx, langnum); 2540| 19.3M| if (idx != lwridx) ------------------ | Branch (2540:9): [True: 1.01M, False: 18.3M] ------------------ 2541| 1.01M| ncap++; 2542| 19.3M| if (unicodetoupper(idx, langnum) == lwridx) ------------------ | Branch (2542:9): [True: 14.0M, False: 5.24M] ------------------ 2543| 14.0M| nneutral++; 2544| 19.3M| ++it; 2545| 19.3M| } 2546| 2.39M| if (ncap) { ------------------ | Branch (2546:7): [True: 381k, False: 2.00M] ------------------ 2547| 381k| const auto idx = (unsigned short)word[0]; 2548| 381k| firstcap = (idx != unicodetolower(idx, langnum)); 2549| 381k| } 2550| | 2551| | // now finally set the captype 2552| 2.39M| if (ncap == 0) { ------------------ | Branch (2552:7): [True: 2.00M, False: 381k] ------------------ 2553| 2.00M| return NOCAP; ------------------ | | 92| 2.00M|#define NOCAP 0 ------------------ 2554| 2.00M| } else if ((ncap == 1) && firstcap) { ------------------ | Branch (2554:14): [True: 228k, False: 152k] | Branch (2554:29): [True: 110k, False: 118k] ------------------ 2555| 110k| return INITCAP; ------------------ | | 93| 110k|#define INITCAP 1 ------------------ 2556| 270k| } else if ((ncap == word.size()) || ((ncap + nneutral) == word.size())) { ------------------ | Branch (2556:14): [True: 4.58k, False: 266k] | Branch (2556:39): [True: 57.8k, False: 208k] ------------------ 2557| 62.3k| return ALLCAP; ------------------ | | 94| 62.3k|#define ALLCAP 2 ------------------ 2558| 208k| } else if ((ncap > 1) && firstcap) { ------------------ | Branch (2558:14): [True: 100k, False: 108k] | Branch (2558:28): [True: 42.6k, False: 57.7k] ------------------ 2559| 42.6k| return HUHINITCAP; ------------------ | | 96| 42.6k|#define HUHINITCAP 4 ------------------ 2560| 42.6k| } 2561| 165k| return HUHCAP; ------------------ | | 95| 165k|#define HUHCAP 3 ------------------ 2562| 2.39M|} _Z24remove_ignored_chars_utfRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKNS_6vectorI6w_charNS3_IS8_EEEE: 2566| 600k| const std::vector& ignored_chars) { 2567| 600k| std::vector w; 2568| 600k| std::vector w2; 2569| 600k| u8_u16(w, word); 2570| | 2571| 600k| std::copy_if(w.begin(), w.end(), std::back_inserter(w2), 2572| 600k| [&ignored_chars](w_char wc) { 2573| 600k| return !std::binary_search(ignored_chars.begin(), ignored_chars.end(), wc); 2574| 600k| }); 2575| | 2576| 600k| u16_u8(word, w2); 2577| 600k| return w2.size(); 2578| 600k|} _Z20remove_ignored_charsRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKS5_: 2582| 1.96M| const std::string& ignored_chars) { 2583| 1.96M| word.erase( 2584| 1.96M| std::remove_if(word.begin(), word.end(), is_any_of(ignored_chars)), 2585| 1.96M| word.end()); 2586| 1.96M| return word.size(); 2587| 1.96M|} _Z12parse_stringRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERS5_i: 2589| 90|bool parse_string(const std::string& line, std::string& out, int ln) { 2590| 90| if (!out.empty()) { ------------------ | Branch (2590:7): [True: 0, False: 90] ------------------ 2591| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple definitions\n", ln); 2592| 0| return false; 2593| 0| } 2594| 90| int i = 0; 2595| 90| int np = 0; 2596| 90| auto iter = line.begin(), start_piece = mystrsep(line, iter); 2597| 270| while (start_piece != line.end()) { ------------------ | Branch (2597:10): [True: 180, False: 90] ------------------ 2598| 180| switch (i) { 2599| 90| case 0: { ------------------ | Branch (2599:7): [True: 90, False: 90] ------------------ 2600| 90| np++; 2601| 90| break; 2602| 0| } 2603| 90| case 1: { ------------------ | Branch (2603:7): [True: 90, False: 90] ------------------ 2604| 90| out.assign(start_piece, iter); 2605| 90| np++; 2606| 90| break; 2607| 0| } 2608| 0| default: ------------------ | Branch (2608:7): [True: 0, False: 180] ------------------ 2609| 0| break; 2610| 180| } 2611| 180| ++i; 2612| 180| start_piece = mystrsep(line, iter); 2613| 180| } 2614| 90| if (np != 2) { ------------------ | Branch (2614:7): [True: 0, False: 90] ------------------ 2615| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", ln); 2616| 0| return false; 2617| 0| } 2618| 90| return true; 2619| 90|} _Z11parse_arrayRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERS5_RNS_6vectorI6w_charNS3_ISA_EEEEii: 2625| 14| int ln) { 2626| 14| if (!parse_string(line, out, ln)) ------------------ | Branch (2626:7): [True: 0, False: 14] ------------------ 2627| 0| return false; 2628| 14| if (utf8) { ------------------ | Branch (2628:7): [True: 8, False: 6] ------------------ 2629| 8| u8_u16(out_utf16, out); 2630| 8| std::sort(out_utf16.begin(), out_utf16.end()); 2631| 8| } 2632| 14| return true; 2633| 14|} csutil.cxx:_ZL17warn_missing_contRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS_11__wrap_iterIPKcEE: 153| 819k|static void warn_missing_cont(const std::string& src, std::string::const_iterator p) { 154| | HUNSPELL_WARNING(stderr, 155| 819k| "UTF-8 encoding error. Missing continuation byte in " 156| 819k| "%ld. character position:\n%s\n", 157| 819k| static_cast(std::distance(src.begin(), p)), 158| 819k| src.c_str()); 159| 819k|} csutil.cxx:_ZN12_GLOBAL__N_19is_any_ofC2ERKNSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEE: 244| 1.97M| explicit is_any_of(const std::string& in) : chars(in) {} csutil.cxx:_ZNK12_GLOBAL__N_19is_any_ofclEc: 246| 28.2M| bool operator()(char c) const { return chars.find(c) != std::string::npos; } csutil.cxx:_ZN12_GLOBAL__N_16cupperEPK7cs_infoi: 514| 126M|unsigned char cupper(const struct cs_info* csconv, int nIndex) { 515| 126M| assert(nIndex >= 0 && nIndex <= 255); ------------------ | Branch (515:3): [True: 126M, False: 0] | Branch (515:3): [True: 126M, False: 0] | Branch (515:3): [True: 126M, False: 0] ------------------ 516| 126M| return csconv[nIndex].cupper; 517| 126M|} csutil.cxx:_ZN12_GLOBAL__N_16clowerEPK7cs_infoi: 519| 138M|unsigned char clower(const struct cs_info* csconv, int nIndex) { 520| 138M| assert(nIndex >= 0 && nIndex <= 255); ------------------ | Branch (520:3): [True: 138M, False: 0] | Branch (520:3): [True: 138M, False: 0] | Branch (520:3): [True: 138M, False: 0] ------------------ 521| 138M| return csconv[nIndex].clower; 522| 138M|} csutil.cxx:_ZL36toAsciiLowerAndRemoveNonAlphanumericPKcPc: 2272| 1.82k| char* pBuf) { 2273| 16.5k| while (*pName) { ------------------ | Branch (2273:10): [True: 14.7k, False: 1.82k] ------------------ 2274| | /* A-Z */ 2275| 14.7k| if ((*pName >= 0x41) && (*pName <= 0x5A)) { ------------------ | Branch (2275:9): [True: 5.47k, False: 9.22k] | Branch (2275:29): [True: 294, False: 5.18k] ------------------ 2276| 294| *pBuf = (*pName) + 0x20; /* toAsciiLower */ 2277| 294| pBuf++; 2278| 294| } 2279| | /* a-z, 0-9 */ 2280| 14.4k| else if (((*pName >= 0x61) && (*pName <= 0x7A)) || ------------------ | Branch (2280:15): [True: 5.18k, False: 9.22k] | Branch (2280:35): [True: 5.18k, False: 0] ------------------ 2281| 14.3k| ((*pName >= 0x30) && (*pName <= 0x39))) { ------------------ | Branch (2281:15): [True: 9.13k, False: 98] | Branch (2281:35): [True: 9.13k, False: 0] ------------------ 2282| 14.3k| *pBuf = *pName; 2283| 14.3k| pBuf++; 2284| 14.3k| } 2285| | 2286| 14.7k| pName++; 2287| 14.7k| } 2288| | 2289| 1.82k| *pBuf = '\0'; 2290| 1.82k|} csutil.cxx:_ZN12_GLOBAL__N_15ccaseEPK7cs_infoi: 524| 120M|unsigned char ccase(const struct cs_info* csconv, int nIndex) { 525| 120M| assert(nIndex >= 0 && nIndex <= 255); ------------------ | Branch (525:3): [True: 120M, False: 0] | Branch (525:3): [True: 120M, False: 0] | Branch (525:3): [True: 120M, False: 0] ------------------ 526| 120M| return csconv[nIndex].ccase; 527| 120M|} csutil.cxx:_ZZ24remove_ignored_chars_utfRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKNS_6vectorI6w_charNS3_IS8_EEEEENK3$_0clES8_: 2572| 4.88M| [&ignored_chars](w_char wc) { 2573| 4.88M| return !std::binary_search(ignored_chars.begin(), ignored_chars.end(), wc); 2574| 4.88M| }); _Z12is_utf8_contc: 143| 62.8M|inline bool is_utf8_cont(char c) { 144| 62.8M| return (static_cast(c) & 0xc0) == 0x80; 145| 62.8M|} _Z9utf8_nextRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEm: 148| 23.5k|inline size_t utf8_next(const std::string& s, size_t pos) { 149| 23.5k| if (pos < s.size()) { ------------------ | Branch (149:7): [True: 23.5k, False: 0] ------------------ 150| 23.5k| ++pos; 151| 28.0k| while (pos < s.size() && is_utf8_cont(s[pos])) ------------------ | Branch (151:12): [True: 25.7k, False: 2.34k] | Branch (151:30): [True: 4.55k, False: 21.1k] ------------------ 152| 4.55k| ++pos; 153| 23.5k| } 154| 23.5k| return pos; 155| 23.5k|} _Z20has_no_ignored_charsRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEES7_: 290| 757| const std::string& ignored_chars) { 291| 757| return std::all_of(ignored_chars.begin(), ignored_chars.end(), 292| 757| [&word](char ic) { return word.find(ic) == std::string::npos; }); 293| 757|} _Z11HENTRY_DATAP6hentry: 296| 1.68M|inline char* HENTRY_DATA(struct hentry* h) { 297| 1.68M| char* ret; 298| 1.68M| if (!(h->var & H_OPT)) ------------------ | | 47| 1.68M|#define H_OPT (1 << 0) // is there optional morphological data? ------------------ | Branch (298:7): [True: 1.68M, False: 1.51k] ------------------ 299| 1.68M| ret = nullptr; 300| 1.51k| else if (h->var & H_OPT_ALIASM) ------------------ | | 48| 1.51k|#define H_OPT_ALIASM (1 << 1) // using alias compression? ------------------ | Branch (300:12): [True: 0, False: 1.51k] ------------------ 301| 0| ret = get_stored_pointer(HENTRY_WORD(h) + h->blen + 1); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 302| 1.51k| else 303| 1.51k| ret = HENTRY_WORD(h) + h->blen + 1; ------------------ | | 54| 1.51k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 304| 1.68M| return ret; 305| 1.68M|} _Z11HENTRY_FINDP6hentryPKc: 332| 3.71k|inline char* HENTRY_FIND(struct hentry* h, const char* p) { 333| 3.71k| char* data = HENTRY_DATA(h); 334| 3.71k| return data ? strstr(data, p) : nullptr; ------------------ | Branch (334:10): [True: 4, False: 3.71k] ------------------ 335| 3.71k|} _ZZ20has_no_ignored_charsRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEES7_ENKUlcE_clEc: 292| 5.88k| [&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| 2.10k| ret = static_cast(std::getline(fin, dest)); 110| 2.10k| } else if (hin && hin->is_open()) { ------------------ | Branch (110:14): [True: 0, False: 0] | Branch (110:21): [True: 0, False: 0] ------------------ 111| 0| ret = hin->getline(dest); 112| 0| } 113| 2.10k| if (!ret) { ------------------ | Branch (113:7): [True: 112, False: 1.99k] ------------------ 114| 112| --linenum; 115| 112| } 116| 2.10k| return ret; 117| 2.10k|} _ZN7FileMgr10getlinenumEv: 119| 96|int FileMgr::getlinenum() { 120| 96| return linenum; 121| 96|} _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| 289|void HashMgr::release_flags(unsigned short* astr, bool owned) { 113| 289| if (owned) ------------------ | Branch (113:7): [True: 203, False: 86] ------------------ 114| 203| delete[] astr; 115| 289|} _ZNK7HashMgr6lookupEPKcm: 154| 603M|struct hentry* HashMgr::lookup(const char* word, size_t len) const { 155| 603M| struct hentry* dp = tableptr[hash(word, len)]; 156| 603M| if (!dp) ------------------ | Branch (156:7): [True: 542M, False: 61.0M] ------------------ 157| 542M| return nullptr; 158| 125M| for (; dp != nullptr; dp = dp->next) { ------------------ | Branch (158:10): [True: 66.7M, False: 58.9M] ------------------ 159| 66.7M| if (strcmp(word, dp->word) == 0) ------------------ | Branch (159:9): [True: 2.19M, False: 64.6M] ------------------ 160| 2.19M| return dp; 161| 66.7M| } 162| 58.9M| return nullptr; 163| 61.0M|} _ZN7HashMgr8add_wordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiPtiPS7_bib: 173| 7.40k| bool own_aff) { 174| | 175| 7.40k| if (al > std::numeric_limits::max()) { ------------------ | Branch (175:7): [True: 0, False: 7.40k] ------------------ 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| 7.40k| const std::string* word = &in_word; 182| 7.40k| const std::string* desc = in_desc; 183| | 184| 7.40k| std::string* word_copy = nullptr; 185| 7.40k| std::string* desc_copy = nullptr; 186| 7.40k| if ((!ignorechars.empty() && !has_no_ignored_chars(in_word, ignorechars)) || complexprefixes) { ------------------ | Branch (186:8): [True: 753, False: 6.65k] | Branch (186:32): [True: 121, False: 632] | Branch (186:80): [True: 463, False: 6.82k] ------------------ 187| 584| word_copy = new std::string(in_word); 188| | 189| 584| if (!ignorechars.empty()) { ------------------ | Branch (189:9): [True: 121, False: 463] ------------------ 190| 121| if (utf8) { ------------------ | Branch (190:11): [True: 33, False: 88] ------------------ 191| 33| wcl = remove_ignored_chars_utf(*word_copy, ignorechars_utf16); 192| 88| } else { 193| 88| remove_ignored_chars(*word_copy, ignorechars); 194| 88| } 195| 121| } 196| | 197| 584| if (complexprefixes) { ------------------ | Branch (197:9): [True: 463, False: 121] ------------------ 198| 463| if (utf8) ------------------ | Branch (198:11): [True: 0, False: 463] ------------------ 199| 0| wcl = reverseword_utf(*word_copy); 200| 463| else 201| 463| reverseword(*word_copy); 202| | 203| 463| if (in_desc && aliasm.empty()) { ------------------ | Branch (203:11): [True: 0, False: 463] | 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| 463| } 215| | 216| 584| word = word_copy; 217| 584| } 218| | 219| | // limit of hp->blen 220| 7.40k| if (word->size() > std::numeric_limits::max()) { ------------------ | Branch (220:7): [True: 0, False: 7.40k] ------------------ 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| 7.40k| bool upcasehomonym = false; 229| 7.40k| int descl = desc ? (!aliasm.empty() ? sizeof(char*) : desc->size() + 1) : 0; ------------------ | Branch (229:15): [True: 4, False: 7.40k] | Branch (229:23): [True: 0, False: 4] ------------------ 230| | // variable-length hash record with word and optional fields 231| 7.40k| auto hp = 232| 7.40k| (struct hentry*)arena_alloc(sizeof(struct hentry) + word->size() + descl, 233| 7.40k| alignof(struct hentry)); 234| 7.40k| if (!hp) { ------------------ | Branch (234:7): [True: 0, False: 7.40k] ------------------ 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| 7.40k| char* hpw = hp->word; 242| 7.40k| memcpy(hpw, word->data(), word->size()); 243| 7.40k| hpw[word->size()] = 0; 244| | 245| 7.40k| int i = hash(hpw, word->size()); 246| | 247| 7.40k| hp->blen = (unsigned short)word->size(); 248| 7.40k| hp->clen = (unsigned short)wcl; 249| 7.40k| hp->alen = (short)al; 250| 7.40k| hp->astr = aff; 251| 7.40k| hp->next = nullptr; 252| 7.40k| hp->next_homonym = nullptr; 253| 7.40k| hp->var = (captype == INITCAP) ? H_OPT_INITCAP : 0; ------------------ | | 93| 7.40k|#define INITCAP 1 ------------------ hp->var = (captype == INITCAP) ? H_OPT_INITCAP : 0; ------------------ | | 50| 4.55k|#define H_OPT_INITCAP (1 << 3) // is dictionary word capitalized? ------------------ | Branch (253:13): [True: 4.55k, False: 2.85k] ------------------ 254| 7.40k| if (own_aff) ------------------ | Branch (254:7): [True: 5.20k, False: 2.19k] ------------------ 255| 5.20k| hp->var |= H_OPT_OWNFLAGS; ------------------ | | 51| 5.20k|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 256| | 257| | // store the description string or its pointer 258| 7.40k| if (desc) { ------------------ | Branch (258:7): [True: 4, False: 7.40k] ------------------ 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| 7.40k| struct hentry* dp = tableptr[i]; 370| 7.40k| if (!dp) { ------------------ | Branch (370:7): [True: 5.84k, False: 1.55k] ------------------ 371| 5.84k| tableptr[i] = hp; 372| 5.84k| delete desc_copy; 373| 5.84k| delete word_copy; 374| 5.84k| return 0; 375| 5.84k| } 376| 1.88k| while (dp->next != nullptr) { ------------------ | Branch (376:10): [True: 332, False: 1.55k] ------------------ 377| 332| if ((!dp->next_homonym) && (strcmp(hp->word, dp->word) == 0)) { ------------------ | Branch (377:9): [True: 313, False: 19] | Branch (377:32): [True: 3, False: 310] ------------------ 378| | // remove hidden onlyupcase homonym 379| 3| if (!onlyupcase) { ------------------ | Branch (379:11): [True: 2, False: 1] ------------------ 380| 2| if ((dp->astr) && TESTAFF(dp->astr, ONLYUPCASEFLAG, dp->alen)) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (380:13): [True: 0, False: 2] | Branch (380:13): [True: 0, False: 2] ------------------ 381| 0| release_flags(dp->astr, dp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 382| 0| dp->astr = hp->astr; 383| 0| dp->alen = hp->alen; 384| 0| dp->var &= ~H_OPT_OWNFLAGS; ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 385| 0| dp->var |= (hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 386| 0| arena_free(hp); 387| 0| delete desc_copy; 388| 0| delete word_copy; 389| 0| return 0; 390| 2| } else if (!dp->astr && dp->alen == 0 && ------------------ | Branch (390:20): [True: 2, False: 0] | Branch (390:33): [True: 2, False: 0] ------------------ 391| 2| !hp->astr && hp->alen == 0) { ------------------ | Branch (391:20): [True: 2, False: 0] | Branch (391:33): [True: 2, False: 0] ------------------ 392| | // word already exists with no flags, skip duplicate 393| 2| release_flags(hp->astr, hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 2|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 394| 2| arena_free(hp); 395| 2| delete desc_copy; 396| 2| delete word_copy; 397| 2| return 0; 398| 2| } else { 399| 0| dp->next_homonym = hp; 400| 0| } 401| 2| } else { 402| 1| upcasehomonym = true; 403| 1| } 404| 3| } 405| 330| dp = dp->next; 406| 330| } 407| 1.55k| if (strcmp(hp->word, dp->word) == 0) { ------------------ | Branch (407:7): [True: 294, False: 1.26k] ------------------ 408| | // remove hidden onlyupcase homonym 409| 294| if (!onlyupcase) { ------------------ | Branch (409:9): [True: 209, False: 85] ------------------ 410| 209| if ((dp->astr) && TESTAFF(dp->astr, ONLYUPCASEFLAG, dp->alen)) { ------------------ | | 99| 16|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 16, False: 0] | | ------------------ ------------------ | Branch (410:11): [True: 16, False: 193] | Branch (410:11): [True: 16, False: 193] ------------------ 411| 16| release_flags(dp->astr, dp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 16|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 412| 16| dp->astr = hp->astr; 413| 16| dp->alen = hp->alen; 414| 16| dp->var &= ~H_OPT_OWNFLAGS; ------------------ | | 51| 16|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 415| 16| dp->var |= (hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 16|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 416| 16| arena_free(hp); 417| 16| delete desc_copy; 418| 16| delete word_copy; 419| 16| return 0; 420| 193| } else if (!dp->astr && dp->alen == 0 && ------------------ | Branch (420:18): [True: 193, False: 0] | Branch (420:31): [True: 193, False: 0] ------------------ 421| 193| !hp->astr && hp->alen == 0) { ------------------ | Branch (421:18): [True: 185, False: 8] | Branch (421:31): [True: 185, False: 0] ------------------ 422| | // word already exists with no flags, skip duplicate 423| 185| release_flags(hp->astr, hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 185|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 424| 185| arena_free(hp); 425| 185| delete desc_copy; 426| 185| delete word_copy; 427| 185| return 0; 428| 185| } else { 429| 8| dp->next_homonym = hp; 430| 8| } 431| 209| } else { 432| 85| upcasehomonym = true; 433| 85| } 434| 294| } 435| 1.35k| if (!upcasehomonym) { ------------------ | Branch (435:7): [True: 1.26k, False: 86] ------------------ 436| 1.26k| dp->next = hp; 437| 1.26k| } else { 438| | // remove hidden onlyupcase homonym 439| 86| release_flags(hp->astr, hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 86|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 440| 86| arena_free(hp); 441| 86| } 442| | 443| 1.35k| delete desc_copy; 444| 1.35k| delete word_copy; 445| 1.35k| return 0; 446| 1.55k|} _ZN7HashMgr27add_hidden_capitalized_wordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiPtiPS7_i: 453| 5.36k| int captype) { 454| 5.36k| if (flags == nullptr) ------------------ | Branch (454:7): [True: 5.26k, False: 106] ------------------ 455| 5.26k| 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| 5.36k| if (((captype == HUHCAP) || (captype == HUHINITCAP) || ------------------ | | 95| 5.36k|#define HUHCAP 3 ------------------ if (((captype == HUHCAP) || (captype == HUHINITCAP) || ------------------ | | 96| 5.11k|#define HUHINITCAP 4 ------------------ | Branch (460:8): [True: 252, False: 5.11k] | Branch (460:31): [True: 1.77k, False: 3.34k] ------------------ 461| 3.34k| ((captype == ALLCAP) && (flagslen != 0))) && ------------------ | | 94| 3.34k|#define ALLCAP 2 ------------------ | Branch (461:9): [True: 378, False: 2.96k] | Branch (461:32): [True: 16, False: 362] ------------------ 462| 2.03k| !((flagslen != 0) && TESTAFF(flags, forbiddenword, flagslen))) { ------------------ | | 99| 16|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 16] | | ------------------ ------------------ | Branch (462:9): [True: 16, False: 2.02k] ------------------ 463| 2.03k| auto flags2 = (unsigned short*)arena_alloc((flagslen + 1) * sizeof(unsigned short), 464| 2.03k| alignof(unsigned short)); 465| 2.03k| flags2[flagslen] = ONLYUPCASEFLAG; ------------------ | | 128| 2.03k|#define ONLYUPCASEFLAG 65511 ------------------ 466| 2.03k| if (flagslen) { ------------------ | Branch (466:9): [True: 16, False: 2.02k] ------------------ 467| 16| memcpy(flags2, flags, flagslen * sizeof(unsigned short)); 468| 16| std::sort(flags2, flags2 + flagslen + 1); 469| 16| } 470| 2.03k| if (utf8) { ------------------ | Branch (470:9): [True: 162, False: 1.87k] ------------------ 471| 162| std::string st; 472| 162| std::vector w; 473| 162| u8_u16(w, word); 474| 162| mkallsmall_utf(w, langnum); 475| 162| mkinitcap_utf(w, langnum); 476| 162| u16_u8(st, w); 477| 162| return add_word(st, wcl, flags2, flagslen + 1, dp, true, INITCAP, false); ------------------ | | 93| 162|#define INITCAP 1 ------------------ 478| 1.87k| } else { 479| 1.87k| std::string new_word(word); 480| 1.87k| mkallsmall(new_word, csconv); 481| 1.87k| mkinitcap(new_word, csconv); 482| 1.87k| int ret = add_word(new_word, wcl, flags2, flagslen + 1, dp, true, INITCAP, false); ------------------ | | 93| 1.87k|#define INITCAP 1 ------------------ 483| 1.87k| return ret; 484| 1.87k| } 485| 2.03k| } 486| 3.33k| return 0; 487| 5.36k|} _ZN7HashMgr20get_clen_and_captypeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiRNS0_6vectorI6w_charNS4_ISB_EEEE: 490| 5.36k|int HashMgr::get_clen_and_captype(const std::string& word, int* captype, std::vector &workbuf) { 491| 5.36k| int len; 492| 5.36k| if (utf8) { ------------------ | Branch (492:7): [True: 2.55k, False: 2.81k] ------------------ 493| 2.55k| len = u8_u16(workbuf, word); 494| 2.55k| *captype = get_captype_utf8(workbuf, langnum); 495| 2.81k| } else { 496| 2.81k| len = word.size(); 497| 2.81k| *captype = get_captype(word, csconv); 498| 2.81k| } 499| 5.36k| return len; 500| 5.36k|} _ZN7HashMgr20get_clen_and_captypeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPi: 502| 5.20k|int HashMgr::get_clen_and_captype(const std::string& word, int* captype) { 503| 5.20k| std::vector workbuf; 504| 5.20k| return get_clen_and_captype(word, captype, workbuf); 505| 5.20k|} _ZN7HashMgr21remove_forbidden_flagERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 528| 6.92k|void HashMgr::remove_forbidden_flag(const std::string& word) { 529| 6.92k| struct hentry* dp = lookup(word.c_str(), word.size()); 530| 6.92k| if (!dp) ------------------ | Branch (530:7): [True: 6.60k, False: 319] ------------------ 531| 6.60k| return; 532| 670| while (dp) { ------------------ | Branch (532:10): [True: 351, False: 319] ------------------ 533| 351| if (dp->astr && TESTAFF(dp->astr, forbiddenword, dp->alen)) { ------------------ | | 99| 32|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 32] | | ------------------ ------------------ | Branch (533:9): [True: 32, False: 319] ------------------ 534| 0| if (dp->alen == 1) { ------------------ | Branch (534:11): [True: 0, False: 0] ------------------ 535| 0| release_flags(dp->astr, dp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 536| 0| dp->astr = nullptr; 537| 0| dp->alen = 0; 538| 0| dp->var &= ~H_OPT_OWNFLAGS; ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 539| 0| } else { 540| 0| auto newflags = new unsigned short[dp->alen - 1]; 541| 0| int j = 0; 542| 0| for (int i = 0; i < dp->alen; i++) { ------------------ | Branch (542:25): [True: 0, False: 0] ------------------ 543| 0| if (dp->astr[i] != forbiddenword) ------------------ | Branch (543:15): [True: 0, False: 0] ------------------ 544| 0| newflags[j++] = dp->astr[i]; 545| 0| } 546| 0| release_flags(dp->astr, dp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 547| 0| dp->astr = newflags; 548| 0| dp->alen = (short)j; 549| 0| dp->var |= H_OPT_OWNFLAGS; ------------------ | | 51| 0|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 550| 0| } 551| 0| } 552| 351| dp = dp->next_homonym; 553| 351| } 554| 319|} _ZN7HashMgr3addERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 557| 5.18k|int HashMgr::add(const std::string& word) { 558| 5.18k| remove_forbidden_flag(word); 559| 5.18k| int captype, al = 0; 560| 5.18k| unsigned short* flags = nullptr; 561| 5.18k| int wcl = get_clen_and_captype(word, &captype); 562| 5.18k| if (add_word(word, wcl, flags, al, nullptr, false, captype, true)) ------------------ | Branch (562:7): [True: 0, False: 5.18k] ------------------ 563| 0| return 1; 564| 5.18k| return add_hidden_capitalized_word(word, wcl, flags, al, nullptr, captype); 565| 5.18k|} _ZN7HashMgr14add_with_affixERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 578| 1.74k|int HashMgr::add_with_affix(const std::string& word, const std::string& example) { 579| | // detect captype and modify word length for UTF-8 encoding 580| 1.74k| struct hentry* dp = lookup(example.c_str(), example.size()); 581| 1.74k| remove_forbidden_flag(word); 582| 1.74k| if (dp && dp->astr) { ------------------ | Branch (582:7): [True: 77, False: 1.66k] | Branch (582:13): [True: 24, False: 53] ------------------ 583| 24| int captype; 584| 24| int wcl = get_clen_and_captype(word, &captype); 585| 24| auto flags = new unsigned short[dp->alen]; 586| 24| memcpy(flags, dp->astr, dp->alen * sizeof(unsigned short)); 587| 24| if (add_word(word, wcl, flags, dp->alen, nullptr, false, captype, true)) ------------------ | Branch (587:9): [True: 0, False: 24] ------------------ 588| 0| return 1; 589| 24| return add_hidden_capitalized_word(word, wcl, flags, dp->alen, nullptr, captype); 590| 24| } 591| 1.71k| return 1; 592| 1.74k|} _ZNK7HashMgr14walk_hashtableERiP6hentry: 596| 2.00M|struct hentry* HashMgr::walk_hashtable(int& col, struct hentry* hp) const { 597| 2.00M| if (hp && hp->next != nullptr) ------------------ | Branch (597:7): [True: 1.94M, False: 62.4k] | Branch (597:13): [True: 135k, False: 1.80M] ------------------ 598| 135k| return hp->next; 599| 63.1M| for (col++; col < (int)tableptr.size(); ++col) { ------------------ | Branch (599:15): [True: 63.0M, False: 62.4k] ------------------ 600| 63.0M| if (tableptr[col]) ------------------ | Branch (600:9): [True: 1.80M, False: 61.2M] ------------------ 601| 1.80M| return tableptr[col]; 602| 63.0M| } 603| | // null at end and reset to start 604| 62.4k| col = -1; 605| 62.4k| return nullptr; 606| 1.86M|} _ZN7HashMgr11load_tablesEPKcS1_: 609| 38|int HashMgr::load_tables(const char* tpath, const char* key) { 610| | // open dictionary file 611| 38| FileMgr* dict = new FileMgr(tpath, key); 612| | 613| | // first read the first line of file to get hash table size 614| 38| std::string ts; 615| 38| if (!dict->getline(ts)) { ------------------ | Branch (615:7): [True: 0, False: 38] ------------------ 616| 0| fprintf(stderr, "error: empty dic file %s\n", tpath); 617| 0| delete dict; 618| 0| return 2; 619| 0| } 620| 38| mychomp(ts); 621| | 622| | /* remove byte order mark */ 623| 38| if (ts.compare(0, 3, "\xEF\xBB\xBF", 3) == 0) { ------------------ | Branch (623:7): [True: 0, False: 38] ------------------ 624| 0| ts.erase(0, 3); 625| 0| } 626| | 627| 38| int tablesize = atoi(ts.c_str()); 628| | 629| 38| const int nExtra = 5 + USERWORD; ------------------ | | 57| 38|#define USERWORD 1000 ------------------ 630| |#if !defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 631| | // covers full-form uncompressed dictionaries (~7M for uk_UA expanded) 632| | const int max_allowed = 10000000; 633| |#else 634| 38| const int max_allowed = (10000 - 1 - nExtra) / int(sizeof(struct hentry*)); 635| 38|#endif 636| | 637| 38| if (tablesize <= 0 || tablesize >= max_allowed) { ------------------ | Branch (637:7): [True: 0, False: 38] | Branch (637:25): [True: 0, False: 38] ------------------ 638| 0| fprintf(stderr, 639| 0| "error: %s: line 1: missing or bad word count in the dic file\n", 640| 0| tpath); 641| 0| delete dict; 642| 0| return 4; 643| 0| } 644| 38| tablesize += nExtra; 645| 38| if ((tablesize & 1) == 0) ------------------ | Branch (645:7): [True: 18, False: 20] ------------------ 646| 18| tablesize++; 647| | 648| | // allocate the hash table 649| 38| tableptr.resize(tablesize, nullptr); 650| | 651| | // loop through all words on much list and add to hash 652| | // table and create word and affix strings 653| | 654| 38| std::vector workbuf; 655| | 656| 38| int nLineCount(0); 657| 198| while (dict->getline(ts)) { ------------------ | Branch (657:10): [True: 160, False: 38] ------------------ 658| 160| ++nLineCount; 659| 160|#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION 660| | // limit words loaded to avoid O(n^2) hash chain walk timeout 661| 160| if (nLineCount >= tablesize) ------------------ | Branch (661:9): [True: 0, False: 160] ------------------ 662| 0| break; 663| 160|#endif 664| 160| mychomp(ts); 665| | // split each line into word and morphological description 666| 160| size_t dp_pos = 0; 667| 160| while ((dp_pos = ts.find(':', dp_pos)) != std::string::npos) { ------------------ | Branch (667:12): [True: 4, False: 156] ------------------ 668| 4| if ((dp_pos > 3) && (ts[dp_pos - 3] == ' ' || ts[dp_pos - 3] == '\t')) { ------------------ | Branch (668:11): [True: 4, False: 0] | Branch (668:28): [True: 0, False: 4] | Branch (668:53): [True: 4, False: 0] ------------------ 669| 4| for (dp_pos -= 3; dp_pos > 0 && (ts[dp_pos-1] == ' ' || ts[dp_pos-1] == '\t'); --dp_pos) ------------------ | Branch (669:27): [True: 4, False: 0] | Branch (669:42): [True: 0, False: 4] | Branch (669:65): [True: 0, False: 4] ------------------ 670| 0| ; 671| 4| if (dp_pos == 0) { // missing word ------------------ | Branch (671:13): [True: 0, False: 4] ------------------ 672| 0| dp_pos = std::string::npos; 673| 4| } else { 674| 4| ++dp_pos; 675| 4| } 676| 4| break; 677| 4| } 678| 0| ++dp_pos; 679| 0| } 680| | 681| | // tabulator is the old morphological field separator 682| 160| size_t dp2_pos = ts.find('\t'); 683| 160| if (dp2_pos != std::string::npos && (dp_pos == std::string::npos || dp2_pos < dp_pos)) { ------------------ | Branch (683:9): [True: 4, False: 156] | Branch (683:42): [True: 0, False: 4] | Branch (683:73): [True: 4, False: 0] ------------------ 684| 4| dp_pos = dp2_pos + 1; 685| 4| } 686| | 687| 160| std::string dp; 688| 160| if (dp_pos != std::string::npos) { ------------------ | Branch (688:9): [True: 4, False: 156] ------------------ 689| 4| dp.assign(ts.substr(dp_pos)); 690| 4| ts.resize(dp_pos - 1); 691| 4| } 692| | 693| | // split each line into word and affix char strings 694| | // "\/" signs slash in words (not affix separator) 695| | // "/" at beginning of the line is word character (not affix separator) 696| 160| size_t ap_pos = ts.find('/'); 697| 160| while (ap_pos != std::string::npos) { ------------------ | Branch (697:12): [True: 82, False: 78] ------------------ 698| 82| if (ap_pos == 0) { ------------------ | Branch (698:11): [True: 0, False: 82] ------------------ 699| 0| ++ap_pos; 700| 0| ap_pos = ts.find('/', ap_pos); 701| 0| continue; 702| 82| } else if (ts[ap_pos - 1] != '\\') ------------------ | Branch (702:18): [True: 82, False: 0] ------------------ 703| 82| break; 704| | // replace "\/" with "/" 705| 0| ts.erase(ap_pos - 1, 1); 706| 0| ap_pos = ts.find('/', ap_pos); 707| 0| } 708| | 709| 160| unsigned short* flags; 710| 160| int al; 711| 160| if (ap_pos != std::string::npos && ap_pos != ts.size()) { ------------------ | Branch (711:9): [True: 82, False: 78] | Branch (711:40): [True: 82, False: 0] ------------------ 712| 82| std::string ap(ts.substr(ap_pos + 1)); 713| 82| ts.resize(ap_pos); 714| 82| if (!aliasf.empty()) { ------------------ | Branch (714:11): [True: 2, False: 80] ------------------ 715| 2| int index = atoi(ap.c_str()); 716| 2| al = get_aliasf(index, &flags, dict); 717| 2| if (!al) { ------------------ | Branch (717:13): [True: 0, False: 2] ------------------ 718| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad flag vector alias\n", 719| 0| dict->getlinenum()); 720| 0| } 721| 80| } else { 722| 80| al = decode_flags(&flags, ap, dict, /* arena = */ true); 723| 80| if (al == -1) { ------------------ | Branch (723:13): [True: 0, False: 80] ------------------ 724| 0| HUNSPELL_WARNING(stderr, "Can't allocate memory.\n"); 725| 0| delete dict; 726| 0| return 6; 727| 0| } 728| 80| std::sort(flags, flags + al); 729| 80| } 730| 82| } else { 731| 78| al = 0; 732| 78| flags = nullptr; 733| 78| } 734| | 735| 160| int captype; 736| 160| int wcl = get_clen_and_captype(ts, &captype, workbuf); 737| 160| const std::string* dp_str = dp.empty() ? nullptr : &dp; ------------------ | Branch (737:33): [True: 156, False: 4] ------------------ 738| | // add the word and its index plus its capitalized form optionally 739| | // flags are arena-allocated, so own_aff must be false 740| 160| bool own = false; 741| 160| if (add_word(ts, wcl, flags, al, dp_str, false, captype, own) || ------------------ | Branch (741:9): [True: 0, False: 160] ------------------ 742| 160| add_hidden_capitalized_word(ts, wcl, flags, al, dp_str, captype)) { ------------------ | Branch (742:9): [True: 0, False: 160] ------------------ 743| 0| delete dict; 744| 0| return 5; 745| 0| } 746| 160| } 747| | 748| 38| int ret(0); 749| | 750| | // reject ludicrous tablesizes 751| 38| if (tablesize > 8192 + nExtra && tablesize > nLineCount * 10 + nExtra) { ------------------ | Branch (751:7): [True: 0, False: 38] | Branch (751:36): [True: 0, False: 0] ------------------ 752| 0| HUNSPELL_WARNING(stderr, ".dic initial approximate word count line value of %d is too large for %d lines\n", tablesize, nLineCount); 753| 0| ret = 3; 754| 0| } 755| | 756| 38| delete dict; 757| 38| return ret; 758| 38|} _ZNK7HashMgr4hashEPKcm: 762| 603M|int HashMgr::hash(const char* word, size_t len) const { 763| 603M| unsigned long hv = 0; 764| 603M| size_t i = 0; 765| 2.98G| while (i < 4 && i < len) ------------------ | Branch (765:10): [True: 2.40G, False: 578M] | Branch (765:19): [True: 2.38G, False: 24.9M] ------------------ 766| 2.38G| hv = (hv << 8) | word[i++]; 767| 13.2G| while (i < len) { ------------------ | Branch (767:10): [True: 12.6G, False: 603M] ------------------ 768| 12.6G| ROTATE(hv, ROTATE_LEN); ------------------ | | 44| 12.6G| (v) = ((v) << (q)) | (((v) >> (32 - q)) & ((1 << (q)) - 1)); ------------------ 769| 12.6G| hv ^= word[i++]; 770| 12.6G| } 771| 603M| return (unsigned long)hv % tableptr.size(); 772| 603M|} _ZNK7HashMgr12decode_flagsEPPtRKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEP7FileMgr: 774| 16|int HashMgr::decode_flags(unsigned short** result, const std::string& flags, FileMgr* af) const { 775| 16| return decode_flags(result, flags, af, /* arena = */ false); 776| 16|} _ZNK7HashMgr12decode_flagsEPPtRKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEP7FileMgrb: 778| 100|int HashMgr::decode_flags(unsigned short** result, const std::string& flags, FileMgr* af, bool use_arena) const { 779| 100| auto alloc = [&](int n) -> unsigned short* { 780| 100| return use_arena ? (unsigned short*)this->arena_alloc(n * sizeof(unsigned short), 781| 100| alignof(unsigned short)) 782| 100| : new unsigned short[n]; 783| 100| }; 784| 100| int len; 785| 100| if (flags.empty()) { ------------------ | Branch (785:7): [True: 0, False: 100] ------------------ 786| 0| *result = nullptr; 787| 0| return 0; 788| 0| } 789| 100| switch (flag_mode) { 790| 0| case FLAG_LONG: { // two-character flags (1x2yZz -> 1x 2y Zz) ------------------ | Branch (790:5): [True: 0, False: 100] ------------------ 791| 0| len = flags.size(); 792| 0| if ((len & 1) == 1 && af != nullptr) ------------------ | Branch (792:11): [True: 0, False: 0] | Branch (792:29): [True: 0, False: 0] ------------------ 793| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad flagvector\n", 794| 0| af->getlinenum()); 795| 0| len >>= 1; 796| 0| *result = alloc(len); 797| 0| for (int i = 0; i < len; i++) { ------------------ | Branch (797:23): [True: 0, False: 0] ------------------ 798| 0| unsigned short flag = ((unsigned short)((unsigned char)flags[i << 1]) << 8) | 799| 0| ((unsigned short)((unsigned char)flags[(i << 1) | 1])); 800| | 801| 0| (*result)[i] = flag; 802| 0| } 803| 0| break; 804| 0| } 805| 0| case FLAG_NUM: { // decimal numbers separated by comma (4521,23,233 -> 4521 ------------------ | Branch (805:5): [True: 0, False: 100] ------------------ 806| | // 23 233) 807| 0| len = int(1 + std::count_if(flags.begin(), flags.end(), [](char c) { return c == ','; })); 808| 0| *result = alloc(len); 809| 0| unsigned short* dest = *result; 810| 0| const char* src = flags.c_str(); 811| 0| for (size_t p = 0; p < flags.size(); ++p) { ------------------ | Branch (811:26): [True: 0, False: 0] ------------------ 812| 0| if (flags[p] == ',') { ------------------ | Branch (812:13): [True: 0, False: 0] ------------------ 813| 0| int i = atoi(src); 814| 0| if ((i > std::numeric_limits::max() || i < 0) && af != nullptr) { ------------------ | Branch (814:16): [True: 0, False: 0] | Branch (814:66): [True: 0, False: 0] | Branch (814:76): [True: 0, False: 0] ------------------ 815| 0| HUNSPELL_WARNING( 816| 0| stderr, "error: line %d: flag id %d is out of range\n", 817| 0| af->getlinenum(), i); 818| 0| i = 0; 819| 0| } 820| 0| *dest = (unsigned short)i; 821| 0| if (*dest == 0 && af != nullptr) ------------------ | Branch (821:15): [True: 0, False: 0] | Branch (821:29): [True: 0, False: 0] ------------------ 822| 0| HUNSPELL_WARNING(stderr, "error: line %d: 0 is wrong flag id\n", 823| 0| af->getlinenum()); 824| 0| src = flags.c_str() + p + 1; 825| 0| dest++; 826| 0| } 827| 0| } 828| 0| int i = atoi(src); 829| 0| if ((i > std::numeric_limits::max() || i < 0) && af) { ------------------ | Branch (829:12): [True: 0, False: 0] | Branch (829:62): [True: 0, False: 0] | Branch (829:72): [True: 0, False: 0] ------------------ 830| 0| HUNSPELL_WARNING(stderr, 831| 0| "error: line %d: flag id %d is out of range\n", 832| 0| af->getlinenum(), i); 833| 0| i = 0; 834| 0| } 835| 0| *dest = (unsigned short)i; 836| 0| if (*dest == 0 && af) ------------------ | Branch (836:11): [True: 0, False: 0] | Branch (836:25): [True: 0, False: 0] ------------------ 837| 0| HUNSPELL_WARNING(stderr, "error: line %d: 0 is wrong flag id\n", 838| 0| af->getlinenum()); 839| 0| break; 840| 0| } 841| 0| case FLAG_UNI: { // UTF-8 characters ------------------ | Branch (841:5): [True: 0, False: 100] ------------------ 842| 0| std::vector w; 843| 0| u8_u16(w, flags); 844| 0| len = w.size(); 845| 0| *result = alloc(len); 846| 0|#if defined(_WIN32) || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__==__ORDER_LITTLE_ENDIAN__)) || defined(__LITTLE_ENDIAN__) 847| 0| memcpy(*result, w.data(), len * sizeof(unsigned short)); 848| |#else 849| | unsigned short* dest = *result; 850| | for (const w_char wc : w) { 851| | *dest = (unsigned short)wc; 852| | dest++; 853| | } 854| |#endif 855| 0| break; 856| 0| } 857| 100| default: { // Ispell's one-character flags (erfg -> e r f g) ------------------ | Branch (857:5): [True: 100, False: 0] ------------------ 858| 100| len = flags.size(); 859| 100| *result = alloc(len); 860| 100| unsigned short* dest = *result; 861| 118| for (const char flag : flags) { ------------------ | Branch (861:28): [True: 118, False: 100] ------------------ 862| 118| *dest = (unsigned char)flag; 863| 118| dest++; 864| 118| } 865| 100| } 866| 100| } 867| 100| return len; 868| 100|} _ZNK7HashMgr11decode_flagERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 944| 92|unsigned short HashMgr::decode_flag(const std::string& f) const { 945| 92| unsigned short s = 0; 946| 92| int i; 947| 92| switch (flag_mode) { 948| 0| case FLAG_LONG: ------------------ | Branch (948:5): [True: 0, False: 92] ------------------ 949| 0| if (f.size() >= 2) ------------------ | Branch (949:11): [True: 0, False: 0] ------------------ 950| 0| s = ((unsigned short)((unsigned char)f[0]) << 8) | ((unsigned short)((unsigned char)f[1])); 951| 0| break; 952| 0| case FLAG_NUM: ------------------ | Branch (952:5): [True: 0, False: 92] ------------------ 953| 0| i = atoi(f.c_str()); 954| 0| if (i > std::numeric_limits::max() || i < 0) { ------------------ | Branch (954:11): [True: 0, False: 0] | Branch (954:61): [True: 0, False: 0] ------------------ 955| 0| HUNSPELL_WARNING(stderr, "error: flag id %d is out of range\n", i); 956| 0| i = 0; 957| 0| } 958| 0| s = (unsigned short)i; 959| 0| break; 960| 0| case FLAG_UNI: { ------------------ | Branch (960:5): [True: 0, False: 92] ------------------ 961| 0| std::vector w; 962| 0| u8_u16(w, f); 963| 0| if (!w.empty()) ------------------ | Branch (963:11): [True: 0, False: 0] ------------------ 964| 0| s = (unsigned short)w[0]; 965| 0| break; 966| 0| } 967| 92| default: ------------------ | Branch (967:5): [True: 92, False: 0] ------------------ 968| 92| if (!f.empty()) ------------------ | Branch (968:11): [True: 92, False: 0] ------------------ 969| 92| s = (unsigned char)f[0]; 970| 92| } 971| 92| if (s == 0) ------------------ | Branch (971:7): [True: 0, False: 92] ------------------ 972| 0| HUNSPELL_WARNING(stderr, "error: 0 is wrong flag id\n"); 973| 92| return s; 974| 92|} _ZN7HashMgr11load_configEPKcS1_: 1010| 38|int HashMgr::load_config(const char* affpath, const char* key) { 1011| 38| int firstline = 1; 1012| | 1013| | // open the affix file 1014| 38| FileMgr* afflst = new FileMgr(affpath, key); 1015| | 1016| | // read in each line ignoring any that do not 1017| | // start with a known line type indicator 1018| | 1019| 38| std::string line; 1020| 922| while (afflst->getline(line)) { ------------------ | Branch (1020:10): [True: 886, False: 36] ------------------ 1021| 886| mychomp(line); 1022| | 1023| | /* remove byte order mark */ 1024| 886| if (firstline) { ------------------ | Branch (1024:9): [True: 38, False: 848] ------------------ 1025| 38| firstline = 0; 1026| 38| if (line.compare(0, 3, "\xEF\xBB\xBF", 3) == 0) { ------------------ | Branch (1026:11): [True: 0, False: 38] ------------------ 1027| 0| line.erase(0, 3); 1028| 0| } 1029| 38| } 1030| | 1031| | /* parse in the try string */ 1032| 886| if ((line.compare(0, 4, "FLAG", 4) == 0) && line.size() > 4 && isspace(line[4])) { ------------------ | Branch (1032:9): [True: 0, False: 886] | Branch (1032:49): [True: 0, False: 0] | Branch (1032:68): [True: 0, False: 0] ------------------ 1033| 0| if (flag_mode != FLAG_CHAR) { ------------------ | Branch (1033:11): [True: 0, False: 0] ------------------ 1034| 0| HUNSPELL_WARNING(stderr, 1035| 0| "error: line %d: multiple definitions of the FLAG " 1036| 0| "affix file parameter\n", 1037| 0| afflst->getlinenum()); 1038| 0| } 1039| 0| if (line.find("long") != std::string::npos) ------------------ | Branch (1039:11): [True: 0, False: 0] ------------------ 1040| 0| flag_mode = FLAG_LONG; 1041| 0| if (line.find("num") != std::string::npos) ------------------ | Branch (1041:11): [True: 0, False: 0] ------------------ 1042| 0| flag_mode = FLAG_NUM; 1043| 0| if (line.find("UTF-8") != std::string::npos) ------------------ | Branch (1043:11): [True: 0, False: 0] ------------------ 1044| 0| flag_mode = FLAG_UNI; 1045| 0| if (flag_mode == FLAG_CHAR) { ------------------ | Branch (1045:11): [True: 0, False: 0] ------------------ 1046| 0| HUNSPELL_WARNING( 1047| 0| stderr, 1048| 0| "error: line %d: FLAG needs `num', `long' or `UTF-8' parameter\n", 1049| 0| afflst->getlinenum()); 1050| 0| } 1051| 0| } 1052| | 1053| 886| if (line.compare(0, 13, "FORBIDDENWORD", 13) == 0) { ------------------ | Branch (1053:9): [True: 2, False: 884] ------------------ 1054| 2| std::string st; 1055| 2| if (!parse_string(line, st, afflst->getlinenum())) { ------------------ | Branch (1055:11): [True: 0, False: 2] ------------------ 1056| 0| delete afflst; 1057| 0| return 1; 1058| 0| } 1059| 2| forbiddenword = decode_flag(st); 1060| 2| } 1061| | 1062| 886| if (line.compare(0, 3, "SET", 3) == 0) { ------------------ | Branch (1062:9): [True: 18, False: 868] ------------------ 1063| 18| if (!parse_string(line, enc, afflst->getlinenum())) { ------------------ | Branch (1063:11): [True: 0, False: 18] ------------------ 1064| 0| delete afflst; 1065| 0| return 1; 1066| 0| } 1067| 18| if (enc == "UTF-8") { ------------------ | Branch (1067:11): [True: 18, False: 0] ------------------ 1068| 18| utf8 = 1; 1069| 18| } else 1070| 0| csconv = get_current_cs(enc); 1071| 18| } 1072| | 1073| 886| if (line.compare(0, 4, "LANG", 4) == 0) { ------------------ | Branch (1073:9): [True: 2, False: 884] ------------------ 1074| 2| if (!parse_string(line, lang, afflst->getlinenum())) { ------------------ | Branch (1074:11): [True: 0, False: 2] ------------------ 1075| 0| delete afflst; 1076| 0| return 1; 1077| 0| } 1078| 2| langnum = get_lang_num(lang); 1079| 2| } 1080| | 1081| | /* parse in the ignored characters (for example, Arabic optional diacritics 1082| | * characters */ 1083| 886| if (line.compare(0, 6, "IGNORE", 6) == 0) { ------------------ | Branch (1083:9): [True: 4, False: 882] ------------------ 1084| 4| if (!parse_array(line, ignorechars, ignorechars_utf16, ------------------ | Branch (1084:11): [True: 0, False: 4] ------------------ 1085| 4| utf8, afflst->getlinenum())) { 1086| 0| delete afflst; 1087| 0| return 1; 1088| 0| } 1089| 4| } 1090| | 1091| 886| if ((line.compare(0, 2, "AF", 2) == 0) && line.size() > 2 && isspace(line[2])) { ------------------ | Branch (1091:9): [True: 2, False: 884] | Branch (1091:47): [True: 2, False: 0] | Branch (1091:66): [True: 2, False: 0] ------------------ 1092| 2| if (!parse_aliasf(line, afflst)) { ------------------ | Branch (1092:11): [True: 0, False: 2] ------------------ 1093| 0| delete afflst; 1094| 0| return 1; 1095| 0| } 1096| 2| } 1097| | 1098| 886| if ((line.compare(0, 2, "AM", 2) == 0) && line.size() > 2 && isspace(line[2])) { ------------------ | Branch (1098:9): [True: 0, False: 886] | Branch (1098:47): [True: 0, False: 0] | Branch (1098:66): [True: 0, False: 0] ------------------ 1099| 0| if (!parse_aliasm(line, afflst)) { ------------------ | Branch (1099:11): [True: 0, False: 0] ------------------ 1100| 0| delete afflst; 1101| 0| return 1; 1102| 0| } 1103| 0| } 1104| | 1105| 886| if (line.compare(0, 15, "COMPLEXPREFIXES", 15) == 0) ------------------ | Branch (1105:9): [True: 2, False: 884] ------------------ 1106| 2| complexprefixes = 1; 1107| | 1108| | /* parse in the typical fault correcting table */ 1109| 886| if (line.compare(0, 3, "REP", 3) == 0) { ------------------ | Branch (1109:9): [True: 6, False: 880] ------------------ 1110| 6| if (!parse_reptable(line, afflst)) { ------------------ | Branch (1110:11): [True: 0, False: 6] ------------------ 1111| 0| delete afflst; 1112| 0| return 1; 1113| 0| } 1114| 6| } 1115| | 1116| | // don't check the full affix file, yet 1117| 886| if (((line.compare(0, 3, "SFX", 3) == 0) || ------------------ | Branch (1117:10): [True: 42, False: 844] ------------------ 1118| 844| (line.compare(0, 3, "PFX", 3) == 0)) && ------------------ | Branch (1118:10): [True: 24, False: 820] ------------------ 1119| 66| line.size() > 3 && isspace(line[3]) && ------------------ | Branch (1119:13): [True: 66, False: 0] | Branch (1119:32): [True: 66, False: 0] ------------------ 1120| 66| !reptable.empty()) // (REP table is in the end of Afrikaans aff file) ------------------ | Branch (1120:13): [True: 2, False: 64] ------------------ 1121| 2| break; 1122| 886| } 1123| | 1124| 38| delete afflst; 1125| 38| return 0; 1126| 38|} _ZN7HashMgr12parse_aliasfERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 1129| 2|bool HashMgr::parse_aliasf(const std::string& line, FileMgr* af) { 1130| 2| if (!aliasf.empty()) { ------------------ | Branch (1130:7): [True: 0, False: 2] ------------------ 1131| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 1132| 0| af->getlinenum()); 1133| 0| return false; 1134| 0| } 1135| 2| int i = 0, np = 0, numaliasf = 0; 1136| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 1137| 6| while (start_piece != line.end()) { ------------------ | Branch (1137:10): [True: 4, False: 2] ------------------ 1138| 4| switch (i) { 1139| 2| case 0: { ------------------ | Branch (1139:7): [True: 2, False: 2] ------------------ 1140| 2| np++; 1141| 2| break; 1142| 0| } 1143| 2| case 1: { ------------------ | Branch (1143:7): [True: 2, False: 2] ------------------ 1144| 2| numaliasf = atoi(std::string(start_piece, iter).c_str()); 1145| 2| if (numaliasf < 1) { ------------------ | Branch (1145:13): [True: 0, False: 2] ------------------ 1146| 0| aliasf.clear(); 1147| 0| aliasflen.clear(); 1148| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 1149| 0| af->getlinenum()); 1150| 0| return false; 1151| 0| } 1152| 2| aliasf.reserve(std::min(numaliasf, 16384)); 1153| 2| aliasflen.reserve(std::min(numaliasf, 16384)); 1154| 2| np++; 1155| 2| break; 1156| 2| } 1157| 0| default: ------------------ | Branch (1157:7): [True: 0, False: 4] ------------------ 1158| 0| break; 1159| 4| } 1160| 4| ++i; 1161| 4| start_piece = mystrsep(line, iter); 1162| 4| } 1163| 2| if (np != 2) { ------------------ | Branch (1163:7): [True: 0, False: 2] ------------------ 1164| 0| aliasf.clear(); 1165| 0| aliasflen.clear(); 1166| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 1167| 0| af->getlinenum()); 1168| 0| return false; 1169| 0| } 1170| | 1171| | /* now parse the numaliasf lines to read in the remainder of the table */ 1172| 6| for (int j = 0; j < numaliasf; ++j) { ------------------ | Branch (1172:19): [True: 4, False: 2] ------------------ 1173| 4| std::string nl; 1174| 4| unsigned short* alias = nullptr; 1175| 4| unsigned aliaslen = 0; 1176| 4| i = 0; 1177| 4| if (af->getline(nl)) { ------------------ | Branch (1177:9): [True: 4, False: 0] ------------------ 1178| 4| mychomp(nl); 1179| 4| iter = nl.begin(); 1180| 4| start_piece = mystrsep(nl, iter); 1181| 4| bool errored = false; 1182| 12| while (!errored && start_piece != nl.end()) { ------------------ | Branch (1182:14): [True: 12, False: 0] | Branch (1182:14): [True: 8, False: 4] | Branch (1182:26): [True: 8, False: 4] ------------------ 1183| 8| switch (i) { 1184| 4| case 0: { ------------------ | Branch (1184:11): [True: 4, False: 4] ------------------ 1185| 4| if (nl.compare(start_piece - nl.begin(), 2, "AF", 2) != 0) { ------------------ | Branch (1185:17): [True: 0, False: 4] ------------------ 1186| 0| errored = true; 1187| 0| break; 1188| 0| } 1189| 4| break; 1190| 4| } 1191| 4| case 1: { ------------------ | Branch (1191:11): [True: 4, False: 4] ------------------ 1192| 4| std::string piece(start_piece, iter); 1193| 4| aliaslen = 1194| 4| (unsigned short)decode_flags(&alias, piece, af, /* arena = */ true); 1195| 4| std::sort(alias, alias + aliaslen); 1196| 4| break; 1197| 4| } 1198| 0| default: ------------------ | Branch (1198:11): [True: 0, False: 8] ------------------ 1199| 0| break; 1200| 8| } 1201| 8| ++i; 1202| 8| start_piece = mystrsep(nl, iter); 1203| 8| } 1204| 4| } 1205| 4| if (!alias) { ------------------ | Branch (1205:9): [True: 0, False: 4] ------------------ 1206| 0| for (int k = 0; k < j; ++k) { ------------------ | Branch (1206:23): [True: 0, False: 0] ------------------ 1207| 0| arena_free(aliasf[k]); 1208| 0| } 1209| 0| aliasf.clear(); 1210| 0| aliasflen.clear(); 1211| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 1212| 0| af->getlinenum()); 1213| 0| return false; 1214| 0| } 1215| | 1216| 4| aliasf.push_back(alias); 1217| 4| aliasflen.push_back(aliaslen); 1218| 4| } 1219| 2| return true; 1220| 2|} _ZNK7HashMgr9is_aliasfEv: 1222| 44|int HashMgr::is_aliasf() const { 1223| 44| return !aliasf.empty(); 1224| 44|} _ZNK7HashMgr10get_aliasfEiPPtP7FileMgr: 1226| 4|int HashMgr::get_aliasf(int index, unsigned short** fvec, FileMgr* af) const { 1227| 4| if (index > 0 && static_cast(index) <= aliasflen.size()) { ------------------ | Branch (1227:7): [True: 4, False: 0] | Branch (1227:20): [True: 4, False: 0] ------------------ 1228| 4| *fvec = aliasf[index - 1]; 1229| 4| return aliasflen[index - 1]; 1230| 4| } 1231| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad flag alias index: %d\n", 1232| 0| af->getlinenum(), index); 1233| 0| *fvec = nullptr; 1234| 0| return 0; 1235| 4|} _ZNK7HashMgr9is_aliasmEv: 1333| 32|int HashMgr::is_aliasm() const { 1334| 32| return !aliasm.empty(); 1335| 32|} _ZN7HashMgr14parse_reptableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 1345| 6|bool HashMgr::parse_reptable(const std::string& line, FileMgr* af) { 1346| 6| if (!reptable.empty()) { ------------------ | Branch (1346:7): [True: 0, False: 6] ------------------ 1347| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 1348| 0| af->getlinenum()); 1349| 0| return false; 1350| 0| } 1351| 6| int numrep = -1, i = 0, np = 0; 1352| 6| auto iter = line.begin(), start_piece = mystrsep(line, iter); 1353| 18| while (start_piece != line.end()) { ------------------ | Branch (1353:10): [True: 12, False: 6] ------------------ 1354| 12| switch (i) { 1355| 6| case 0: { ------------------ | Branch (1355:7): [True: 6, False: 6] ------------------ 1356| 6| np++; 1357| 6| break; 1358| 0| } 1359| 6| case 1: { ------------------ | Branch (1359:7): [True: 6, False: 6] ------------------ 1360| 6| numrep = atoi(std::string(start_piece, iter).c_str()); 1361| 6| if (numrep < 1) { ------------------ | Branch (1361:13): [True: 0, False: 6] ------------------ 1362| 0| HUNSPELL_WARNING(stderr, "error: line %d: incorrect entry number\n", 1363| 0| af->getlinenum()); 1364| 0| return false; 1365| 0| } 1366| 6| reptable.reserve(std::min(numrep, 16384)); 1367| 6| np++; 1368| 6| break; 1369| 6| } 1370| 0| default: ------------------ | Branch (1370:7): [True: 0, False: 12] ------------------ 1371| 0| break; 1372| 12| } 1373| 12| ++i; 1374| 12| start_piece = mystrsep(line, iter); 1375| 12| } 1376| 6| if (np != 2) { ------------------ | Branch (1376:7): [True: 0, False: 6] ------------------ 1377| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 1378| 0| af->getlinenum()); 1379| 0| return false; 1380| 0| } 1381| | 1382| | /* now parse the numrep lines to read in the remainder of the table */ 1383| 12| for (int j = 0; j < numrep; ++j) { ------------------ | Branch (1383:19): [True: 6, False: 6] ------------------ 1384| 6| std::string nl; 1385| 6| reptable.emplace_back(); 1386| 6| int type = 0; 1387| 6| if (af->getline(nl)) { ------------------ | Branch (1387:9): [True: 6, False: 0] ------------------ 1388| 6| mychomp(nl); 1389| 6| iter = nl.begin(); 1390| 6| i = 0; 1391| 6| start_piece = mystrsep(nl, iter); 1392| 6| bool errored = false; 1393| 24| while (!errored && start_piece != nl.end()) { ------------------ | Branch (1393:14): [True: 24, False: 0] | Branch (1393:14): [True: 18, False: 6] | Branch (1393:26): [True: 18, False: 6] ------------------ 1394| 18| switch (i) { 1395| 6| case 0: { ------------------ | Branch (1395:11): [True: 6, False: 12] ------------------ 1396| 6| if (nl.compare(start_piece - nl.begin(), 3, "REP", 3) != 0) { ------------------ | Branch (1396:17): [True: 0, False: 6] ------------------ 1397| 0| errored = true; 1398| 0| break; 1399| 0| } 1400| 6| break; 1401| 6| } 1402| 6| case 1: { ------------------ | Branch (1402:11): [True: 6, False: 12] ------------------ 1403| 6| if (*start_piece == '^') ------------------ | Branch (1403:17): [True: 0, False: 6] ------------------ 1404| 0| type = 1; 1405| 6| reptable.back().pattern.assign(start_piece + type, iter); 1406| 6| mystrrep(reptable.back().pattern, "_", " "); 1407| 6| if (!reptable.back().pattern.empty() && reptable.back().pattern[reptable.back().pattern.size() - 1] == '$') { ------------------ | Branch (1407:17): [True: 6, False: 0] | Branch (1407:53): [True: 0, False: 6] ------------------ 1408| 0| type += 2; 1409| 0| reptable.back().pattern.resize(reptable.back().pattern.size() - 1); 1410| 0| } 1411| 6| break; 1412| 6| } 1413| 6| case 2: { ------------------ | Branch (1413:11): [True: 6, False: 12] ------------------ 1414| 6| reptable.back().outstrings[type].assign(start_piece, iter); 1415| 6| mystrrep(reptable.back().outstrings[type], "_", " "); 1416| 6| break; 1417| 6| } 1418| 0| default: ------------------ | Branch (1418:11): [True: 0, False: 18] ------------------ 1419| 0| break; 1420| 18| } 1421| 18| ++i; 1422| 18| start_piece = mystrsep(nl, iter); 1423| 18| } 1424| 6| } 1425| 6| if (reptable.back().pattern.empty() || reptable.back().outstrings[type].empty()) { ------------------ | Branch (1425:9): [True: 0, False: 6] | Branch (1425:44): [True: 0, False: 6] ------------------ 1426| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 1427| 0| af->getlinenum()); 1428| 0| reptable.clear(); 1429| 0| return false; 1430| 0| } 1431| 6| } 1432| 6| return true; 1433| 6|} _ZNK7HashMgr12get_reptableEv: 1436| 386k|const std::vector& HashMgr::get_reptable() const { 1437| 386k| return reptable; 1438| 386k|} _ZNK7HashMgr11arena_allocEmm: 1440| 9.52k|void* HashMgr::arena_alloc(size_t num_bytes, size_t alignment) const { 1441| | // Fixed-size 64KB chunks: small enough to avoid significant waste on small 1442| | // dictionaries, large enough to amortize per-chunk malloc overhead on large 1443| | // ones. make_unique throws std::bad_alloc on OOM. 1444| 9.52k| static const size_t MIN_CHUNK_SIZE = 65536; 1445| 9.52k| static const size_t MAX_ALIGNMENT = alignof(max_align_t); 1446| | // Chunk sizes are rounded up to MAX_ALIGNMENT below; with this invariant, 1447| | // any alignment that divides MAX_ALIGNMENT keeps aligned_offset within bounds. 1448| 9.52k| assert(alignment > 0 && alignment <= MAX_ALIGNMENT); ------------------ | Branch (1448:3): [True: 9.52k, False: 0] | Branch (1448:3): [True: 9.52k, False: 0] | Branch (1448:3): [True: 9.52k, False: 0] ------------------ 1449| | // Pad the offset up to the requested alignment before placing this allocation. 1450| | // make_unique returns memory aligned for any scalar, so chunk-start is fine. 1451| 9.52k| size_t aligned_offset = (current_chunk_offset + alignment - 1) & ~(alignment - 1); 1452| 9.52k| if (arena.empty() || current_chunk_size - aligned_offset < num_bytes) { ------------------ | Branch (1452:7): [True: 38, False: 9.49k] | Branch (1452:24): [True: 86, False: 9.40k] ------------------ 1453| | // Round the new chunk's size up to a multiple of MAX_ALIGNMENT so that an 1454| | // oversized num_bytes (>= MIN_CHUNK_SIZE) cannot leave a non-aligned 1455| | // current_chunk_size that would later cause aligned_offset to overshoot. 1456| | // Allocate before mutating current_chunk_size so a throwing make_unique 1457| | // leaves the HashMgr in a consistent state. 1458| 124| size_t new_size = std::max(MIN_CHUNK_SIZE, num_bytes); 1459| 124| new_size = (new_size + MAX_ALIGNMENT - 1) & ~(MAX_ALIGNMENT - 1); 1460| 124| arena.push_back(std::make_unique(new_size)); 1461| 124| current_chunk_size = new_size; 1462| 124| aligned_offset = 0; 1463| 124| } 1464| | 1465| 9.52k| uint8_t* ptr = &arena.back()[aligned_offset]; 1466| 9.52k| current_chunk_offset = aligned_offset + num_bytes; 1467| 9.52k| ++outstanding_arena_allocations; 1468| 9.52k| return ptr; 1469| 9.52k|} _ZNK7HashMgr10arena_freeEPv: 1471| 289|void HashMgr::arena_free(void*) const { 1472| | // The arena vector owns all allocations and frees them in bulk at HashMgr 1473| | // destruction, so this is a no-op for the memory itself. The counter is a 1474| | // memory-safety check: more arena_free calls than arena_alloc calls would 1475| | // indicate a double-free or use-after-free in Hunspell. Abort hard rather 1476| | // than silently desynchronize tracking, even in release builds. 1477| 289| if (outstanding_arena_allocations == 0) { ------------------ | Branch (1477:7): [True: 0, False: 289] ------------------ 1478| 0| std::abort(); 1479| 0| } 1480| 289| --outstanding_arena_allocations; 1481| 289|} hashmgr.cxx:_ZZNK7HashMgr12decode_flagsEPPtRKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEP7FileMgrbENK3$_0clEi: 779| 100| auto alloc = [&](int n) -> unsigned short* { 780| 100| return use_arena ? (unsigned short*)this->arena_alloc(n * sizeof(unsigned short), ------------------ | Branch (780:12): [True: 84, False: 16] ------------------ 781| 84| alignof(unsigned short)) 782| 100| : new unsigned short[n]; 783| 100| }; _ZN12HunspellImplC2EPKcS1_S1_: 191| 38| : affixpath(affpath) { 192| 38| csconv = nullptr; 193| 38| utf8 = 0; 194| 38| complexprefixes = 0; 195| | 196| | /* first set up the hash manager */ 197| 38| m_HMgrs.push_back(std::make_unique(dpath, affpath, key)); 198| | 199| | /* next set up the affix manager */ 200| | /* it needs access to the hash manager lookup methods */ 201| 38| pAMgr = std::make_unique(affpath, m_HMgrs, key); 202| | 203| | /* get the preferred try string and the dictionary */ 204| | /* encoding from the Affix Manager for that dictionary */ 205| 38| std::string try_string = pAMgr->get_try_string(); 206| 38| encoding = pAMgr->get_encoding(); 207| 38| langnum = pAMgr->get_langnum(); 208| 38| utf8 = pAMgr->get_utf8(); 209| 38| if (!utf8) ------------------ | Branch (209:7): [True: 20, False: 18] ------------------ 210| 20| csconv = get_current_cs(encoding); 211| 38| complexprefixes = pAMgr->get_complexprefixes(); 212| 38| wordbreak = pAMgr->get_breaktable(); 213| | 214| | /* and finally set up the suggestion manager */ 215| 38| pSMgr = std::make_unique(try_string, MAXSUGGESTION, pAMgr.get()); ------------------ | | 83| 38|#define MAXSUGGESTION 15 ------------------ 216| 38|} _ZN12HunspellImpl12clean_ignoreERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKS6_: 235| 25.2M| const std::string& src) { 236| 25.2M| dest.clear(); 237| 25.2M| dest.assign(src); 238| 25.2M| const char* ignoredchars = pAMgr ? pAMgr->get_ignore() : nullptr; ------------------ | Branch (238:30): [True: 25.2M, False: 0] ------------------ 239| 25.2M| if (ignoredchars != nullptr) { ------------------ | Branch (239:7): [True: 2.56M, False: 22.6M] ------------------ 240| 2.56M| if (utf8) { ------------------ | Branch (240:9): [True: 600k, False: 1.96M] ------------------ 241| 600k| const std::vector& ignoredchars_utf16 = 242| 600k| pAMgr->get_ignore_utf16(); 243| 600k| remove_ignored_chars_utf(dest, ignoredchars_utf16); 244| 1.96M| } else { 245| 1.96M| remove_ignored_chars(dest, ignoredchars); 246| 1.96M| } 247| 2.56M| } 248| 25.2M|} _ZN12HunspellImpl10cleanword2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEERKS6_PiPm: 262| 11.8M| size_t* pabbrev) { 263| 11.8M| dest.clear(); 264| 11.8M| dest_utf.clear(); 265| | 266| | // remove IGNORE characters from the string 267| 11.8M| std::string w2; 268| 11.8M| clean_ignore(w2, src); 269| | 270| 11.8M| const char* q = w2.c_str(); 271| 11.8M| int nl = (int)w2.size(); 272| | 273| | // first skip over any leading blanks 274| 11.9M| while (*q == ' ') { ------------------ | Branch (274:10): [True: 125k, False: 11.8M] ------------------ 275| 125k| ++q; 276| 125k| nl--; 277| 125k| } 278| | 279| | // now strip off any trailing periods (recording their presence) 280| 11.8M| *pabbrev = 0; 281| | 282| 14.6M| while ((nl > 0) && (*(q + nl - 1) == '.')) { ------------------ | Branch (282:10): [True: 13.9M, False: 674k] | Branch (282:22): [True: 2.80M, False: 11.1M] ------------------ 283| 2.80M| nl--; 284| 2.80M| (*pabbrev)++; 285| 2.80M| } 286| | 287| | // if no characters are left it can't be capitalized 288| 11.8M| if (nl <= 0) { ------------------ | Branch (288:7): [True: 674k, False: 11.1M] ------------------ 289| 674k| *pcaptype = NOCAP; ------------------ | | 92| 674k|#define NOCAP 0 ------------------ 290| 674k| return 0; 291| 674k| } 292| | 293| 11.1M| dest.append(q, nl); 294| 11.1M| nl = dest.size(); 295| 11.1M| if (utf8) { ------------------ | Branch (295:7): [True: 2.38M, False: 8.80M] ------------------ 296| 2.38M| u8_u16(dest_utf, dest); 297| 2.38M| *pcaptype = get_captype_utf8(dest_utf, langnum); 298| 8.80M| } else { 299| 8.80M| *pcaptype = get_captype(dest, csconv); 300| 8.80M| } 301| 11.1M| return nl; 302| 11.8M|} _ZN12HunspellImpl9cleanwordERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKS6_PiSA_: 307| 5.64k| int* pabbrev) { 308| 5.64k| dest.clear(); 309| 5.64k| const unsigned char* q = (const unsigned char*)src.c_str(); 310| 5.64k| int firstcap = 0, nl = (int)src.size(); 311| | 312| | // first skip over any leading blanks 313| 7.10k| while (*q == ' ') { ------------------ | Branch (313:10): [True: 1.45k, False: 5.64k] ------------------ 314| 1.45k| ++q; 315| 1.45k| nl--; 316| 1.45k| } 317| | 318| | // now strip off any trailing periods (recording their presence) 319| 5.64k| *pabbrev = 0; 320| | 321| 19.1k| while ((nl > 0) && (*(q + nl - 1) == '.')) { ------------------ | Branch (321:10): [True: 18.9k, False: 171] | Branch (321:22): [True: 13.4k, False: 5.47k] ------------------ 322| 13.4k| nl--; 323| 13.4k| (*pabbrev)++; 324| 13.4k| } 325| | 326| | // if no characters are left it can't be capitalized 327| 5.64k| if (nl <= 0) { ------------------ | Branch (327:7): [True: 171, False: 5.47k] ------------------ 328| 171| *pcaptype = NOCAP; ------------------ | | 92| 171|#define NOCAP 0 ------------------ 329| 171| return; 330| 171| } 331| | 332| | // now determine the capitalization type of the first nl letters 333| 5.47k| int ncap = 0; 334| 5.47k| int nneutral = 0; 335| 5.47k| int nc = 0; 336| | 337| 5.47k| if (!utf8) { ------------------ | Branch (337:7): [True: 2.88k, False: 2.58k] ------------------ 338| 518k| while (nl > 0) { ------------------ | Branch (338:12): [True: 515k, False: 2.88k] ------------------ 339| 515k| nc++; 340| 515k| if (csconv[(*q)].ccase) ------------------ | Branch (340:11): [True: 442k, False: 72.9k] ------------------ 341| 442k| ncap++; 342| 515k| if (csconv[(*q)].cupper == csconv[(*q)].clower) ------------------ | Branch (342:11): [True: 62.4k, False: 453k] ------------------ 343| 62.4k| nneutral++; 344| 515k| dest.push_back(*q++); 345| 515k| nl--; 346| 515k| } 347| | // remember to terminate the destination string 348| 2.88k| firstcap = csconv[static_cast(dest[0])].ccase; 349| 2.88k| } else { 350| 2.58k| std::vector t; 351| 2.58k| u8_u16(t, src); 352| 125k| for (auto& wc : t) { ------------------ | Branch (352:19): [True: 125k, False: 2.58k] ------------------ 353| 125k| const auto idx = (unsigned short)wc; 354| 125k| const auto low = unicodetolower(idx, langnum); 355| 125k| if (idx != low) ------------------ | Branch (355:11): [True: 83.5k, False: 41.9k] ------------------ 356| 83.5k| ncap++; 357| 125k| if (unicodetoupper(idx, langnum) == low) ------------------ | Branch (357:11): [True: 38.2k, False: 87.3k] ------------------ 358| 38.2k| nneutral++; 359| 125k| } 360| 2.58k| u16_u8(dest, t); 361| 2.58k| if (ncap) { ------------------ | Branch (361:9): [True: 1.79k, False: 794] ------------------ 362| 1.79k| const auto idx = (unsigned short)t[0]; 363| 1.79k| firstcap = (idx != unicodetolower(idx, langnum)); 364| 1.79k| } 365| 2.58k| } 366| | 367| | // now finally set the captype 368| 5.47k| if (ncap == 0) { ------------------ | Branch (368:7): [True: 1.52k, False: 3.95k] ------------------ 369| 1.52k| *pcaptype = NOCAP; ------------------ | | 92| 1.52k|#define NOCAP 0 ------------------ 370| 3.95k| } else if ((ncap == 1) && firstcap) { ------------------ | Branch (370:14): [True: 1.90k, False: 2.05k] | Branch (370:29): [True: 846, False: 1.05k] ------------------ 371| 846| *pcaptype = INITCAP; ------------------ | | 93| 846|#define INITCAP 1 ------------------ 372| 3.10k| } else if ((ncap == nc) || ((ncap + nneutral) == nc)) { ------------------ | Branch (372:14): [True: 70, False: 3.03k] | Branch (372:30): [True: 949, False: 2.08k] ------------------ 373| 1.01k| *pcaptype = ALLCAP; ------------------ | | 94| 1.01k|#define ALLCAP 2 ------------------ 374| 2.08k| } else if ((ncap > 1) && firstcap) { ------------------ | Branch (374:14): [True: 1.06k, False: 1.02k] | Branch (374:28): [True: 654, False: 407] ------------------ 375| 654| *pcaptype = HUHINITCAP; ------------------ | | 96| 654|#define HUHINITCAP 4 ------------------ 376| 1.43k| } else { 377| 1.43k| *pcaptype = HUHCAP; ------------------ | | 95| 1.43k|#define HUHCAP 3 ------------------ 378| 1.43k| } 379| 5.47k|} _ZN12HunspellImpl8mkallcapERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 381| 3.18k|void HunspellImpl::mkallcap(std::string& u8) { 382| 3.18k| if (utf8) { ------------------ | Branch (382:7): [True: 1.66k, False: 1.52k] ------------------ 383| 1.66k| std::vector u16; 384| 1.66k| u8_u16(u16, u8); 385| 1.66k| ::mkallcap_utf(u16, langnum); 386| 1.66k| u16_u8(u8, u16); 387| 1.66k| } else { 388| 1.52k| ::mkallcap(u8, csconv); 389| 1.52k| } 390| 3.18k|} _ZN12HunspellImpl11mkallsmall2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEE: 392| 1.05M|int HunspellImpl::mkallsmall2(std::string& u8, std::vector& u16) { 393| 1.05M| if (utf8) { ------------------ | Branch (393:7): [True: 259k, False: 797k] ------------------ 394| 259k| ::mkallsmall_utf(u16, langnum); 395| 259k| u16_u8(u8, u16); 396| 797k| } else { 397| 797k| ::mkallsmall(u8, csconv); 398| 797k| } 399| 1.05M| return u8.size(); 400| 1.05M|} _ZN12HunspellImpl11is_keepcaseEPK6hentry: 438| 16.0k|int HunspellImpl::is_keepcase(const hentry* rv) { 439| 16.0k| return pAMgr && rv->astr && pAMgr->get_keepcase() && ------------------ | Branch (439:10): [True: 16.0k, False: 0] | Branch (439:19): [True: 412, False: 15.6k] | Branch (439:31): [True: 37, False: 375] ------------------ 440| 37| TESTAFF(rv->astr, pAMgr->get_keepcase(), rv->alen); ------------------ | | 99| 16.1k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 19, False: 18] | | ------------------ ------------------ 441| 16.0k|} _ZN12HunspellImpl10insert_sugERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_: 444| 13.6k|void HunspellImpl::insert_sug(std::vector& slst, const std::string& word) { 445| 13.6k| slst.insert(slst.begin(), word); 446| 13.6k|} _ZN12HunspellImpl5spellERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEEPiPS6_NS0_6chrono10time_pointINSF_12steady_clockENSF_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 450| 11.9M| std::chrono::steady_clock::time_point suggest_start) { 451| | // something very broken if spell ends up calling itself with the same word 452| 11.9M| if (std::find(candidate_stack.begin(), candidate_stack.end(), word) != candidate_stack.end()) ------------------ | Branch (452:7): [True: 0, False: 11.9M] ------------------ 453| 0| return false; 454| | 455| 11.9M| if (candidate_stack.size() >= MAXBREAKDEPTH) ------------------ | | 87| 11.9M|#define MAXBREAKDEPTH 10 ------------------ | Branch (455:7): [True: 0, False: 11.9M] ------------------ 456| 0| return false; 457| | 458| 11.9M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 11.9M|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (458:7): [True: 0, False: 11.9M] ------------------ 459| 0| return false; 460| | 461| 11.9M| candidate_stack.push_back(word); 462| 11.9M| bool r = spell_internal(word, candidate_stack, info, root, suggest_start); 463| 11.9M| candidate_stack.pop_back(); 464| | 465| 11.9M| if (r && root) { ------------------ | Branch (465:7): [True: 2.83M, False: 9.07M] | Branch (465:12): [True: 0, False: 2.83M] ------------------ 466| | // output conversion 467| 0| RepList* rl = (pAMgr) ? pAMgr->get_oconvtable() : nullptr; ------------------ | Branch (467:19): [True: 0, False: 0] ------------------ 468| 0| if (rl) { ------------------ | Branch (468:9): [True: 0, False: 0] ------------------ 469| 0| std::string wspace; 470| 0| if (rl->conv(*root, wspace)) { ------------------ | Branch (470:11): [True: 0, False: 0] ------------------ 471| 0| *root = std::move(wspace); 472| 0| } 473| 0| } 474| 0| } 475| 11.9M| return r; 476| 11.9M|} _ZN12HunspellImpl14spell_internalERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEEPiPS6_NS0_6chrono10time_pointINSF_12steady_clockENSF_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 480| 11.9M| std::chrono::steady_clock::time_point suggest_start) { 481| 11.9M| struct hentry* rv = nullptr; 482| | 483| 11.9M| int info2 = 0; 484| 11.9M| if (!info) ------------------ | Branch (484:7): [True: 11.9M, False: 25] ------------------ 485| 11.9M| info = &info2; 486| 25| else 487| 25| *info = 0; 488| | 489| | // Hunspell supports XML input of the simplified API (see manual) 490| 11.9M| if (word == SPELL_XML) ------------------ | | 80| 11.9M|#define SPELL_XML "" ------------------ | Branch (490:7): [True: 110k, False: 11.7M] ------------------ 491| 110k| return true; 492| 11.7M| if (utf8) { ------------------ | Branch (492:7): [True: 2.47M, False: 9.31M] ------------------ 493| 2.47M| if (word.size() >= MAXWORDUTF8LEN) ------------------ | | 86| 2.47M|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 2.47M|#define MAXWORDLEN 100 | | ------------------ ------------------ | Branch (493:9): [True: 3.48k, False: 2.47M] ------------------ 494| 3.48k| return false; 495| 9.31M| } else { 496| 9.31M| if (word.size() >= MAXWORDLEN) ------------------ | | 90| 9.31M|#define MAXWORDLEN 100 ------------------ | Branch (496:9): [True: 6.10k, False: 9.31M] ------------------ 497| 6.10k| return false; 498| 9.31M| } 499| 11.7M| int captype = NOCAP; ------------------ | | 92| 11.7M|#define NOCAP 0 ------------------ 500| 11.7M| size_t abbv = 0; 501| 11.7M| size_t wl = 0; 502| | 503| 11.7M| std::string scw; 504| 11.7M| std::vector sunicw; 505| | 506| | // input conversion 507| 11.7M| RepList* rl = pAMgr ? pAMgr->get_iconvtable() : nullptr; ------------------ | Branch (507:17): [True: 11.7M, False: 0] ------------------ 508| 11.7M| { 509| 11.7M| std::string wspace; 510| | 511| 11.7M| bool convstatus = rl ? rl->conv(word, wspace) : false; ------------------ | Branch (511:23): [True: 361k, False: 11.4M] ------------------ 512| 11.7M| if (convstatus) { ------------------ | Branch (512:9): [True: 0, False: 11.7M] ------------------ 513| | // the input conversion can grow the word without limit, so hold the 514| | // converted word to the same maximum length as the raw word 515| 0| if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 86| 0|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 0|#define MAXWORDLEN 100 | | ------------------ ------------------ if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 90| 0|#define MAXWORDLEN 100 ------------------ | Branch (515:11): [True: 0, False: 0] | Branch (515:11): [True: 0, False: 0] ------------------ 516| 0| return false; 517| 0| wl = cleanword2(scw, sunicw, wspace, &captype, &abbv); 518| 0| } else 519| 11.7M| wl = cleanword2(scw, sunicw, word, &captype, &abbv); 520| 11.7M| } 521| | 522| 11.7M|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 523| 11.7M| if (wl > 32768) ------------------ | Branch (523:9): [True: 0, False: 11.7M] ------------------ 524| 0| return false; 525| 11.7M|#endif 526| | 527| |#ifdef MOZILLA_CLIENT 528| | // accept the abbreviated words without dots 529| | // workaround for the incomplete tokenization of Mozilla 530| | abbv = 1; 531| |#endif 532| | 533| 11.7M| if (wl == 0 || m_HMgrs.empty()) ------------------ | Branch (533:7): [True: 673k, False: 11.1M] | Branch (533:18): [True: 0, False: 11.1M] ------------------ 534| 673k| return true; 535| 11.1M| if (root) ------------------ | Branch (535:7): [True: 0, False: 11.1M] ------------------ 536| 0| root->clear(); 537| | 538| | // allow numbers with dots, dashes and commas (but forbid double separators: 539| | // "..", "--" etc.). Besides the ASCII digits, accept the Arabic-Indic and 540| | // Extended Arabic-Indic (Persian) digit ranges so those numbers are passed 541| | // over the same way ASCII numbers are. 542| 11.1M| enum { NBEGIN, NNUM, NSEP }; 543| 11.1M| int nstate = NBEGIN; 544| 11.1M| size_t i; 545| 11.1M| size_t n = utf8 ? sunicw.size() : wl; ------------------ | Branch (545:14): [True: 2.34M, False: 8.76M] ------------------ 546| | 547| 17.5M| for (i = 0; (i < n); i++) { ------------------ | Branch (547:15): [True: 16.5M, False: 965k] ------------------ 548| 16.5M| unsigned short c = utf8 ? static_cast(sunicw[i]) : static_cast(scw[i]); ------------------ | Branch (548:24): [True: 3.65M, False: 12.9M] ------------------ 549| 16.5M| if ((c >= '0' && c <= '9') || (c >= 0x0660 && c <= 0x0669) || // Arabic-Indic digits ------------------ | Branch (549:10): [True: 11.6M, False: 4.87M] | Branch (549:22): [True: 5.80M, False: 5.89M] | Branch (549:36): [True: 320k, False: 10.4M] | Branch (549:51): [True: 0, False: 320k] ------------------ 550| 10.7M| (c >= 0x06F0 && c <= 0x06F9)) { // Extended Arabic-Indic (Persian) digits ------------------ | Branch (550:10): [True: 320k, False: 10.4M] | Branch (550:25): [True: 0, False: 320k] ------------------ 551| 5.80M| nstate = NNUM; 552| 10.7M| } else if ((c == ',') || (c == '.') || (c == '-')) { ------------------ | Branch (552:16): [True: 80.1k, False: 10.6M] | Branch (552:30): [True: 1.18M, False: 9.49M] | Branch (552:44): [True: 1.92M, False: 7.57M] ------------------ 553| 3.18M| if ((nstate == NSEP) || (i == 0)) ------------------ | Branch (553:11): [True: 112k, False: 3.07M] | Branch (553:31): [True: 2.45M, False: 622k] ------------------ 554| 2.56M| break; 555| 622k| nstate = NSEP; 556| 622k| } else 557| 7.57M| break; 558| 16.5M| } 559| 11.1M| if ((i == n) && (nstate == NNUM)) ------------------ | Branch (559:7): [True: 965k, False: 10.1M] | Branch (559:19): [True: 730k, False: 235k] ------------------ 560| 730k| return true; 561| | 562| 10.3M| switch (captype) { ------------------ | Branch (562:11): [True: 10.3M, False: 0] ------------------ 563| 873k| case HUHCAP: ------------------ | | 95| 873k|#define HUHCAP 3 ------------------ | Branch (563:5): [True: 873k, False: 9.50M] ------------------ 564| | /* FALLTHROUGH */ 565| 1.19M| case HUHINITCAP: ------------------ | | 96| 1.19M|#define HUHINITCAP 4 ------------------ | Branch (565:5): [True: 320k, False: 10.0M] ------------------ 566| 1.19M| *info |= SPELL_ORIGCAP; ------------------ | | 83| 1.19M|#define SPELL_ORIGCAP (1 << 5) ------------------ 567| | /* FALLTHROUGH */ 568| 9.67M| case NOCAP: ------------------ | | 92| 9.67M|#define NOCAP 0 ------------------ | Branch (568:5): [True: 8.47M, False: 1.90M] ------------------ 569| 9.67M| rv = checkword(scw, info, root, suggest_start); 570| 9.67M| if ((abbv) && !(rv)) { ------------------ | Branch (570:11): [True: 1.61M, False: 8.06M] | Branch (570:21): [True: 1.60M, False: 3.52k] ------------------ 571| 1.60M| std::string u8buffer(scw); 572| 1.60M| u8buffer.push_back('.'); 573| 1.60M| rv = checkword(u8buffer, info, root, suggest_start); 574| 1.60M| } 575| 9.67M| break; 576| 186k| case ALLCAP: { ------------------ | | 94| 186k|#define ALLCAP 2 ------------------ | Branch (576:5): [True: 186k, False: 10.1M] ------------------ 577| 186k| *info |= SPELL_ORIGCAP; ------------------ | | 83| 186k|#define SPELL_ORIGCAP (1 << 5) ------------------ 578| 186k| rv = checkword(scw, info, root, suggest_start); 579| 186k| if (rv) ------------------ | Branch (579:11): [True: 83, False: 186k] ------------------ 580| 83| break; 581| 186k| if (abbv) { ------------------ | Branch (581:11): [True: 27.7k, False: 158k] ------------------ 582| 27.7k| std::string u8buffer(scw); 583| 27.7k| u8buffer.push_back('.'); 584| 27.7k| rv = checkword(u8buffer, info, root, suggest_start); 585| 27.7k| if (rv) ------------------ | Branch (585:13): [True: 0, False: 27.7k] ------------------ 586| 0| break; 587| 27.7k| } 588| | // Spec. prefix handling for Catalan, French, Italian: 589| | // prefixes separated by apostrophe (SANT'ELIA -> Sant'+Elia). 590| 186k| size_t apos = pAMgr ? scw.find('\'') : std::string::npos; ------------------ | Branch (590:21): [True: 186k, False: 0] ------------------ 591| 186k| if (apos != std::string::npos) { ------------------ | Branch (591:11): [True: 69.6k, False: 117k] ------------------ 592| 69.6k| mkallsmall2(scw, sunicw); 593| | //conversion may result in string with different len to pre-mkallsmall2 594| | //so re-scan 595| 69.6k| if (apos != std::string::npos && apos < scw.size() - 1) { ------------------ | Branch (595:13): [True: 69.6k, False: 0] | Branch (595:42): [True: 62.9k, False: 6.69k] ------------------ 596| 62.9k| std::string part1 = scw.substr(0, apos + 1), part2 = scw.substr(apos + 1); 597| 62.9k| if (utf8) { ------------------ | Branch (597:15): [True: 9.63k, False: 53.2k] ------------------ 598| 9.63k| std::vector part1u, part2u; 599| 9.63k| u8_u16(part1u, part1); 600| 9.63k| u8_u16(part2u, part2); 601| 9.63k| mkinitcap2(part2, part2u); 602| 9.63k| scw = part1 + part2; 603| 9.63k| sunicw = std::move(part1u); 604| 9.63k| sunicw.insert(sunicw.end(), part2u.begin(), part2u.end()); 605| 9.63k| rv = checkword(scw, info, root, suggest_start); 606| 9.63k| if (rv) ------------------ | Branch (606:17): [True: 0, False: 9.63k] ------------------ 607| 0| break; 608| 53.2k| } else { 609| 53.2k| mkinitcap2(part2, sunicw); 610| 53.2k| scw = part1 + part2; 611| 53.2k| rv = checkword(scw, info, root, suggest_start); 612| 53.2k| if (rv) ------------------ | Branch (612:17): [True: 1, False: 53.2k] ------------------ 613| 1| break; 614| 53.2k| } 615| 62.9k| mkinitcap2(scw, sunicw); 616| 62.9k| rv = checkword(scw, info, root, suggest_start); 617| 62.9k| if (rv) ------------------ | Branch (617:15): [True: 0, False: 62.9k] ------------------ 618| 0| break; 619| 62.9k| } 620| 69.6k| } 621| 186k| if (pAMgr && pAMgr->get_checksharps() && scw.find("SS") != std::string::npos) { ------------------ | Branch (621:11): [True: 186k, False: 0] | Branch (621:20): [True: 0, False: 186k] | Branch (621:48): [True: 0, False: 0] ------------------ 622| | 623| 0| mkallsmall2(scw, sunicw); 624| 0| std::string u8buffer(scw); 625| 0| rv = spellsharps(u8buffer, 0, 0, 0, info, root, suggest_start); 626| 0| if (!rv) { ------------------ | Branch (626:13): [True: 0, False: 0] ------------------ 627| 0| mkinitcap2(scw, sunicw); 628| 0| rv = spellsharps(scw, 0, 0, 0, info, root, suggest_start); 629| 0| } 630| 0| if ((abbv) && !(rv)) { ------------------ | Branch (630:13): [True: 0, False: 0] | Branch (630:23): [True: 0, False: 0] ------------------ 631| 0| u8buffer.push_back('.'); 632| 0| rv = spellsharps(u8buffer, 0, 0, 0, info, root, suggest_start); 633| 0| if (!rv) { ------------------ | Branch (633:15): [True: 0, False: 0] ------------------ 634| 0| u8buffer = std::string(scw); 635| 0| u8buffer.push_back('.'); 636| 0| rv = spellsharps(u8buffer, 0, 0, 0, info, root, suggest_start); 637| 0| } 638| 0| } 639| 0| if (rv) ------------------ | Branch (639:13): [True: 0, False: 0] ------------------ 640| 0| break; 641| 0| } 642| 186k| } 643| | /* FALLTHROUGH */ 644| 707k| case INITCAP: { ------------------ | | 93| 707k|#define INITCAP 1 ------------------ | Branch (644:5): [True: 520k, False: 9.85M] ------------------ 645| | // handle special capitalization of dotted I 646| 707k| bool Idot = (utf8 && (unsigned char) scw[0] == 0xc4 && (unsigned char) scw[1] == 0xb0); ------------------ | Branch (646:20): [True: 154k, False: 552k] | Branch (646:28): [True: 0, False: 154k] | Branch (646:62): [True: 0, False: 0] ------------------ 647| 707k| *info |= SPELL_ORIGCAP; ------------------ | | 83| 707k|#define SPELL_ORIGCAP (1 << 5) ------------------ 648| 707k| if (captype == ALLCAP) { ------------------ | | 94| 707k|#define ALLCAP 2 ------------------ | Branch (648:11): [True: 186k, False: 520k] ------------------ 649| 186k| mkallsmall2(scw, sunicw); 650| 186k| mkinitcap2(scw, sunicw); 651| 186k| if (Idot) ------------------ | Branch (651:15): [True: 0, False: 186k] ------------------ 652| 0| scw.replace(0, 1, "\xc4\xb0"); 653| 186k| } 654| 707k| if (captype == INITCAP) ------------------ | | 93| 707k|#define INITCAP 1 ------------------ | Branch (654:11): [True: 520k, False: 186k] ------------------ 655| 520k| *info |= SPELL_INITCAP; ------------------ | | 82| 520k|#define SPELL_INITCAP (1 << 4) ------------------ 656| 707k| rv = checkword(scw, info, root, suggest_start); 657| 707k| if (captype == INITCAP) ------------------ | | 93| 707k|#define INITCAP 1 ------------------ | Branch (657:11): [True: 520k, False: 186k] ------------------ 658| 520k| *info &= ~SPELL_INITCAP; ------------------ | | 82| 520k|#define SPELL_INITCAP (1 << 4) ------------------ 659| | // forbid bad capitalization 660| | // (for example, ijs -> Ijs instead of IJs in Dutch) 661| | // use explicit forms in dic: Ijs/F (F = FORBIDDENWORD flag) 662| 707k| if (*info & SPELL_FORBIDDEN) { ------------------ | | 79| 707k|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (662:11): [True: 0, False: 707k] ------------------ 663| 0| rv = nullptr; 664| 0| break; 665| 0| } 666| 707k| if (rv && is_keepcase(rv) && (captype == ALLCAP)) ------------------ | | 94| 11|#define ALLCAP 2 ------------------ | Branch (666:11): [True: 9.26k, False: 697k] | Branch (666:17): [True: 11, False: 9.25k] | Branch (666:36): [True: 2, False: 9] ------------------ 667| 2| rv = nullptr; 668| 707k| if (rv || (Idot && langnum != LANG_az && langnum != LANG_tr && langnum != LANG_crh)) ------------------ | Branch (668:11): [True: 9.26k, False: 697k] | Branch (668:18): [True: 0, False: 697k] | Branch (668:26): [True: 0, False: 0] | Branch (668:48): [True: 0, False: 0] | Branch (668:70): [True: 0, False: 0] ------------------ 669| 9.26k| break; 670| | 671| 697k| mkallsmall2(scw, sunicw); 672| 697k| std::string u8buffer(scw); 673| 697k| mkinitcap2(scw, sunicw); 674| | 675| 697k| rv = checkword(u8buffer, info, root, suggest_start); 676| 697k| if (abbv && !rv) { ------------------ | Branch (676:11): [True: 158k, False: 539k] | Branch (676:19): [True: 156k, False: 2.19k] ------------------ 677| 156k| u8buffer.push_back('.'); 678| 156k| rv = checkword(u8buffer, info, root, suggest_start); 679| 156k| if (!rv) { ------------------ | Branch (679:13): [True: 156k, False: 0] ------------------ 680| 156k| u8buffer = scw; 681| 156k| u8buffer.push_back('.'); 682| 156k| if (captype == INITCAP) ------------------ | | 93| 156k|#define INITCAP 1 ------------------ | Branch (682:15): [True: 128k, False: 27.7k] ------------------ 683| 128k| *info |= SPELL_INITCAP; ------------------ | | 82| 128k|#define SPELL_INITCAP (1 << 4) ------------------ 684| 156k| rv = checkword(u8buffer, info, root, suggest_start); 685| 156k| if (captype == INITCAP) ------------------ | | 93| 156k|#define INITCAP 1 ------------------ | Branch (685:15): [True: 128k, False: 27.7k] ------------------ 686| 128k| *info &= ~SPELL_INITCAP; ------------------ | | 82| 128k|#define SPELL_INITCAP (1 << 4) ------------------ 687| 156k| if (rv && is_keepcase(rv) && (captype == ALLCAP)) ------------------ | | 94| 7|#define ALLCAP 2 ------------------ | Branch (687:15): [True: 7, False: 156k] | Branch (687:21): [True: 7, False: 0] | Branch (687:40): [True: 3, False: 4] ------------------ 688| 3| rv = nullptr; 689| 156k| break; 690| 156k| } 691| 156k| } 692| 541k| if (rv && is_keepcase(rv) && ------------------ | Branch (692:11): [True: 6.80k, False: 534k] | Branch (692:17): [True: 1, False: 6.80k] ------------------ 693| 1| ((captype == ALLCAP) || ------------------ | | 94| 1|#define ALLCAP 2 ------------------ | Branch (693:12): [True: 0, False: 1] ------------------ 694| | // if CHECKSHARPS: KEEPCASE words with \xDF are allowed 695| | // in INITCAP form, too. 696| 1| !(pAMgr->get_checksharps() && ------------------ | Branch (696:14): [True: 0, False: 1] ------------------ 697| 0| ((utf8 && u8buffer.find("\xC3\x9F") != std::string::npos) || ------------------ | Branch (697:16): [True: 0, False: 0] | Branch (697:24): [True: 0, False: 0] ------------------ 698| 0| (!utf8 && u8buffer.find('\xDF') != std::string::npos))))) ------------------ | Branch (698:16): [True: 0, False: 0] | Branch (698:25): [True: 0, False: 0] ------------------ 699| 1| rv = nullptr; 700| 541k| break; 701| 697k| } 702| 10.3M| } 703| | 704| 10.3M| if (rv) { ------------------ | Branch (704:7): [True: 35.7k, False: 10.3M] ------------------ 705| 35.7k| if (pAMgr && pAMgr->get_warn() && rv->astr && ------------------ | Branch (705:9): [True: 35.7k, False: 0] | Branch (705:9): [True: 1, False: 35.7k] | Branch (705:18): [True: 3.03k, False: 32.6k] | Branch (705:39): [True: 19, False: 3.02k] ------------------ 706| 19| TESTAFF(rv->astr, pAMgr->get_warn(), rv->alen)) { ------------------ | | 99| 19|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 1, False: 18] | | ------------------ ------------------ 707| 1| *info |= SPELL_WARN; ------------------ | | 84| 1|#define SPELL_WARN (1 << 6) ------------------ 708| 1| if (pAMgr->get_forbidwarn()) ------------------ | Branch (708:11): [True: 0, False: 1] ------------------ 709| 0| return false; 710| 1| return true; 711| 1| } 712| 35.7k| return true; 713| 35.7k| } 714| | 715| | // recursive breaking at break points 716| 10.3M| if (!wordbreak.empty() && !(*info & SPELL_FORBIDDEN)) { ------------------ | | 79| 10.3M|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (716:7): [True: 10.3M, False: 0] | Branch (716:29): [True: 10.3M, False: 0] ------------------ 717| | 718| 10.3M| int nbr = 0; 719| 10.3M| wl = scw.size(); 720| | 721| | // calculate break points for recursion limit 722| 30.9M| for (auto& j : wordbreak) { ------------------ | Branch (722:18): [True: 30.9M, False: 10.3M] ------------------ 723| 30.9M| size_t pos = 0; 724| 41.8M| while ((pos = scw.find(j, pos)) != std::string::npos) { ------------------ | Branch (724:14): [True: 10.8M, False: 30.9M] ------------------ 725| 10.8M| ++nbr; 726| 10.8M| pos += j.size(); 727| 10.8M| } 728| 30.9M| } 729| 10.3M| if (nbr >= MAXBREAKDEPTH) ------------------ | | 87| 10.3M|#define MAXBREAKDEPTH 10 ------------------ | Branch (729:9): [True: 2.55k, False: 10.3M] ------------------ 730| 2.55k| return false; 731| | 732| | // check boundary patterns (^begin and end$) 733| 30.8M| for (auto& j : wordbreak) { ------------------ | Branch (733:18): [True: 30.8M, False: 9.10M] ------------------ 734| 30.8M| size_t plen = j.size(); 735| 30.8M| if (plen == 1 || plen > wl) ------------------ | Branch (735:11): [True: 10.3M, False: 20.5M] | Branch (735:24): [True: 2.60M, False: 17.9M] ------------------ 736| 12.9M| continue; 737| | 738| 17.9M| if (j[0] == '^' && scw.compare(0, plen - 1, j, 1, plen - 1) == 0 && ------------------ | Branch (738:11): [True: 9.00M, False: 8.95M] | Branch (738:11): [True: 67.2k, False: 17.8M] | Branch (738:26): [True: 643k, False: 8.35M] ------------------ 739| 643k| spell(scw.substr(plen - 1), candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (739:11): [True: 67.2k, False: 576k] ------------------ 740| 67.2k| *info |= SPELL_COMPOUND; ------------------ | | 78| 67.2k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 741| 67.2k| return true; 742| 67.2k| } 743| | 744| 17.8M| if (j[plen - 1] == '$' && ------------------ | Branch (744:11): [True: 8.93M, False: 8.95M] ------------------ 745| 8.93M| scw.compare(wl - plen + 1, plen - 1, j, 0, plen - 1) == 0) { ------------------ | Branch (745:11): [True: 3.69M, False: 5.24M] ------------------ 746| 3.69M| std::string suffix(scw.substr(wl - plen + 1)); 747| 3.69M| scw.resize(wl - plen + 1); 748| 3.69M| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (748:13): [True: 1.17M, False: 2.52M] ------------------ 749| 1.17M| *info |= SPELL_COMPOUND; ------------------ | | 78| 1.17M|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 750| 1.17M| return true; 751| 1.17M| } 752| 2.52M| scw.append(suffix); 753| 2.52M| } 754| 17.8M| } 755| | 756| | // other patterns 757| 27.1M| for (auto& j : wordbreak) { ------------------ | Branch (757:18): [True: 27.1M, False: 9.06M] ------------------ 758| 27.1M| size_t plen = j.size(); 759| 27.1M| size_t found = scw.find(j); 760| 27.1M| if ((found > 0) && (found < wl - plen)) { ------------------ | Branch (760:11): [True: 25.9M, False: 1.19M] | Branch (760:26): [True: 2.96M, False: 23.0M] ------------------ 761| 2.96M| size_t found2 = scw.find(j, found + 1); 762| | // try to break at the second occurance 763| | // to recognize dictionary words with wordbreak 764| 2.96M| if (found2 > 0 && (found2 < wl - plen)) ------------------ | Branch (764:13): [True: 2.96M, False: 0] | Branch (764:27): [True: 1.09M, False: 1.86M] ------------------ 765| 1.09M| found = found2; 766| 2.96M| std::string substring(scw.substr(found + plen)); 767| 2.96M| if (!spell(substring, candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (767:13): [True: 2.12M, False: 834k] ------------------ 768| 2.12M| continue; 769| 834k| std::string suffix(scw.substr(found)); 770| 834k| scw.resize(found); 771| | // examine 2 sides of the break point 772| 834k| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (772:13): [True: 38.2k, False: 796k] ------------------ 773| 38.2k| *info |= SPELL_COMPOUND; ------------------ | | 78| 38.2k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 774| 38.2k| return true; 775| 38.2k| } 776| 796k| scw.append(suffix); 777| | 778| | // LANG_hu: spec. dash rule 779| 796k| if (langnum == LANG_hu && j == "-") { ------------------ | Branch (779:13): [True: 158, False: 796k] | Branch (779:35): [True: 158, False: 0] ------------------ 780| 158| suffix = scw.substr(found + 1); 781| 158| scw.resize(found + 1); 782| 158| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (782:15): [True: 0, False: 158] ------------------ 783| 0| *info |= SPELL_COMPOUND; ------------------ | | 78| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 784| 0| return true; // check the first part with dash 785| 0| } 786| 158| scw.append(suffix); 787| 158| } 788| | // end of LANG specific region 789| 796k| } 790| 27.1M| } 791| | 792| | // other patterns (break at first break point) 793| 27.1M| for (auto& j : wordbreak) { ------------------ | Branch (793:18): [True: 27.1M, False: 9.06M] ------------------ 794| 27.1M| size_t plen = j.size(), found = scw.find(j); 795| 27.1M| if ((found > 0) && (found < wl - plen)) { ------------------ | Branch (795:11): [True: 25.9M, False: 1.19M] | Branch (795:26): [True: 2.91M, False: 23.0M] ------------------ 796| 2.91M| if (!spell(scw.substr(found + plen), candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (796:13): [True: 2.24M, False: 667k] ------------------ 797| 2.24M| continue; 798| 667k| std::string suffix(scw.substr(found)); 799| 667k| scw.resize(found); 800| | // examine 2 sides of the break point 801| 667k| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (801:13): [True: 3.63k, False: 663k] ------------------ 802| 3.63k| *info |= SPELL_COMPOUND; ------------------ | | 78| 3.63k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 803| 3.63k| return true; 804| 3.63k| } 805| 663k| scw.append(suffix); 806| | 807| | // LANG_hu: spec. dash rule 808| 663k| if (langnum == LANG_hu && j == "-") { ------------------ | Branch (808:13): [True: 95, False: 663k] | Branch (808:35): [True: 95, False: 0] ------------------ 809| 95| suffix = scw.substr(found + 1); 810| 95| scw.resize(found + 1); 811| 95| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (811:15): [True: 0, False: 95] ------------------ 812| 0| *info |= SPELL_COMPOUND; ------------------ | | 78| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 813| 0| return true; // check the first part with dash 814| 0| } 815| 95| scw.append(suffix); 816| 95| } 817| | // end of LANG specific region 818| 663k| } 819| 27.1M| } 820| 9.06M| } 821| | 822| 9.06M| return false; 823| 10.3M|} _ZN12HunspellImpl9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiPS6_NS0_6chrono10time_pointINSB_12steady_clockENSB_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 826| 13.3M| std::chrono::steady_clock::time_point suggest_start) { 827| | // check overall suggest time limit 828| 13.3M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 13.3M|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (828:7): [True: 0, False: 13.3M] ------------------ 829| 0| return nullptr; 830| | 831| 13.3M| std::string word; 832| | 833| | // remove IGNORE characters from the string 834| 13.3M| clean_ignore(word, w); 835| | 836| 13.3M| if (word.empty()) ------------------ | Branch (836:7): [True: 1.36k, False: 13.3M] ------------------ 837| 1.36k| return nullptr; 838| | 839| | // word reversing wrapper for complex prefixes 840| 13.3M| if (complexprefixes) { ------------------ | Branch (840:7): [True: 1.05M, False: 12.2M] ------------------ 841| 1.05M| if (utf8) ------------------ | Branch (841:9): [True: 0, False: 1.05M] ------------------ 842| 0| reverseword_utf(word); 843| 1.05M| else 844| 1.05M| reverseword(word); 845| 1.05M| } 846| | 847| 13.3M| int len = word.size(); 848| | 849| | // look word in hash table 850| 13.3M| struct hentry* he = nullptr; 851| 26.6M| for (size_t i = 0; (i < m_HMgrs.size()) && !he; ++i) { ------------------ | Branch (851:22): [True: 13.3M, False: 13.3M] | Branch (851:46): [True: 13.3M, False: 0] ------------------ 852| 13.3M| he = m_HMgrs[i]->lookup(word.c_str(), word.size()); 853| | 854| | // check forbidden and onlyincompound words 855| 13.3M| if ((he) && (he->astr) && (pAMgr) && ------------------ | Branch (855:9): [True: 35.7k, False: 13.3M] | Branch (855:9): [True: 0, False: 13.3M] | Branch (855:17): [True: 428, False: 35.3k] | Branch (855:31): [True: 428, False: 0] ------------------ 856| 428| TESTAFF(he->astr, pAMgr->get_forbiddenword(), he->alen)) { ------------------ | | 99| 428|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 428] | | ------------------ ------------------ 857| 0| if (info) ------------------ | Branch (857:11): [True: 0, False: 0] ------------------ 858| 0| *info |= SPELL_FORBIDDEN; ------------------ | | 79| 0|#define SPELL_FORBIDDEN (1 << 1) ------------------ 859| | // LANG_hu section: set dash information for suggestions 860| 0| if (langnum == LANG_hu) { ------------------ | Branch (860:11): [True: 0, False: 0] ------------------ 861| 0| if (pAMgr->get_compoundflag() && ------------------ | Branch (861:13): [True: 0, False: 0] | Branch (861:13): [True: 0, False: 0] ------------------ 862| 0| TESTAFF(he->astr, pAMgr->get_compoundflag(), he->alen)) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 863| 0| if (info) ------------------ | Branch (863:15): [True: 0, False: 0] ------------------ 864| 0| *info |= SPELL_COMPOUND; ------------------ | | 78| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 865| 0| } 866| 0| } 867| 0| return nullptr; 868| 0| } 869| | 870| | // he = next not needaffix, onlyincompound homonym or onlyupcase word 871| 13.3M| while (he && (he->astr) && pAMgr && ------------------ | Branch (871:12): [True: 35.7k, False: 13.3M] | Branch (871:12): [True: 13, False: 13.3M] | Branch (871:18): [True: 428, False: 35.3k] | Branch (871:32): [True: 428, False: 0] ------------------ 872| 428| ((pAMgr->get_needaffix() && ------------------ | Branch (872:14): [True: 27, False: 401] ------------------ 873| 27| TESTAFF(he->astr, pAMgr->get_needaffix(), he->alen)) || ------------------ | | 99| 27|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 27] | | ------------------ ------------------ 874| 428| (pAMgr->get_onlyincompound() && ------------------ | Branch (874:14): [True: 0, False: 428] ------------------ 875| 0| TESTAFF(he->astr, pAMgr->get_onlyincompound(), he->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 876| 428| (info && (*info & SPELL_INITCAP) && ------------------ | | 82| 428|#define SPELL_INITCAP (1 << 4) ------------------ | Branch (876:14): [True: 428, False: 0] | Branch (876:22): [True: 26, False: 402] ------------------ 877| 26| TESTAFF(he->astr, ONLYUPCASEFLAG, he->alen)))) ------------------ | | 99| 26|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 13, False: 13] | | ------------------ ------------------ 878| 13| he = he->next_homonym; 879| 13.3M| } 880| | 881| | // check with affixes 882| 13.3M| if (!he && pAMgr) { ------------------ | Branch (882:7): [True: 13.3M, False: 35.7k] | Branch (882:14): [True: 13.3M, False: 0] ------------------ 883| | // try stripping off affixes 884| 13.3M| AffixScratch scratch; 885| 13.3M| he = pAMgr->affix_check(word, 0, len, scratch, 0); 886| | 887| | // check compound restriction and onlyupcase 888| 13.3M| if (he && he->astr && ------------------ | Branch (888:9): [True: 0, False: 13.3M] | Branch (888:9): [True: 0, False: 13.3M] | Branch (888:15): [True: 0, False: 0] ------------------ 889| 0| ((pAMgr->get_onlyincompound() && ------------------ | Branch (889:11): [True: 0, False: 0] ------------------ 890| 0| TESTAFF(he->astr, pAMgr->get_onlyincompound(), he->alen)) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 891| 0| (info && (*info & SPELL_INITCAP) && ------------------ | | 82| 0|#define SPELL_INITCAP (1 << 4) ------------------ | Branch (891:11): [True: 0, False: 0] | Branch (891:19): [True: 0, False: 0] ------------------ 892| 0| TESTAFF(he->astr, ONLYUPCASEFLAG, he->alen)))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 893| 0| he = nullptr; 894| 0| } 895| | 896| 13.3M| if (he) { ------------------ | Branch (896:9): [True: 0, False: 13.3M] ------------------ 897| 0| if ((he->astr) && (pAMgr) && ------------------ | Branch (897:11): [True: 0, False: 0] | Branch (897:11): [True: 0, False: 0] | Branch (897:25): [True: 0, False: 0] ------------------ 898| 0| TESTAFF(he->astr, pAMgr->get_forbiddenword(), he->alen)) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 899| 0| if (info) ------------------ | Branch (899:13): [True: 0, False: 0] ------------------ 900| 0| *info |= SPELL_FORBIDDEN; ------------------ | | 79| 0|#define SPELL_FORBIDDEN (1 << 1) ------------------ 901| 0| return nullptr; 902| 0| } 903| 0| if (root) { ------------------ | Branch (903:11): [True: 0, False: 0] ------------------ 904| 0| root->assign(he->word); 905| 0| if (complexprefixes) { ------------------ | Branch (905:13): [True: 0, False: 0] ------------------ 906| 0| if (utf8) ------------------ | Branch (906:15): [True: 0, False: 0] ------------------ 907| 0| reverseword_utf(*root); 908| 0| else 909| 0| reverseword(*root); 910| 0| } 911| 0| } 912| | // try check compound word 913| 13.3M| } else if (pAMgr->get_compound()) { ------------------ | Branch (913:16): [True: 3.22M, False: 10.0M] ------------------ 914| 3.22M| struct hentry* rwords[100] = {}; // buffer for COMPOUND pattern checking 915| | 916| | // first allow only 2 words in the compound 917| 3.22M| int setinfo = SPELL_COMPOUND_2; ------------------ | | 85| 3.22M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ 918| 3.22M| if (info) ------------------ | Branch (918:11): [True: 3.22M, False: 0] ------------------ 919| 3.22M| setinfo |= *info; 920| 3.22M| he = pAMgr->compound_check(word, 0, 0, 100, 0, nullptr, (hentry**)&rwords, 0, 0, &setinfo, scratch); 921| 3.22M| if (info) ------------------ | Branch (921:11): [True: 3.22M, False: 0] ------------------ 922| 3.22M| *info = setinfo & ~SPELL_COMPOUND_2; ------------------ | | 85| 3.22M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ 923| | // if not 2-word compoud word, try with 3 or more words 924| | // (only if original info didn't forbid it) 925| 3.22M| if (!he && info && !(*info & SPELL_COMPOUND_2)) { ------------------ | | 85| 3.22M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ | Branch (925:11): [True: 3.22M, False: 0] | Branch (925:18): [True: 3.22M, False: 0] | Branch (925:26): [True: 3.22M, False: 0] ------------------ 926| 3.22M| *info &= ~SPELL_COMPOUND_2; ------------------ | | 85| 3.22M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ 927| 3.22M| he = pAMgr->compound_check(word, 0, 0, 100, 0, nullptr, (hentry**)&rwords, 0, 0, info, scratch); 928| | // accept the compound with 3 or more words only if it is 929| | // - not a dictionary word with a typo and 930| | // - not two words written separately, 931| | // - or if it's an arbitrary number accepted by compound rules (e.g. 999%) 932| 3.22M| if (he && !isdigit(word[0])) ------------------ | Branch (932:13): [True: 0, False: 3.22M] | Branch (932:19): [True: 0, False: 0] ------------------ 933| 0| { 934| 0| std::vector slst; 935| 0| if (pSMgr->suggest(slst, word, nullptr, /*test_simplesug=*/true)) ------------------ | Branch (935:15): [True: 0, False: 0] ------------------ 936| 0| he = nullptr; 937| 0| } 938| 3.22M| } 939| | 940| | // LANG_hu section: `moving rule' with last dash 941| 3.22M| if ((!he) && (langnum == LANG_hu) && (word[len - 1] == '-')) { ------------------ | Branch (941:11): [True: 3.22M, False: 0] | Branch (941:20): [True: 27.1k, False: 3.19M] | Branch (941:44): [True: 10.3k, False: 16.8k] ------------------ 942| 10.3k| std::string dup(word, 0, len - 1); 943| 10.3k| he = pAMgr->compound_check(dup, -5, 0, 100, 0, nullptr, (hentry**)&rwords, 1, 0, info, scratch); 944| 10.3k| } 945| | // end of LANG specific region 946| 3.22M| if (he) { ------------------ | Branch (946:11): [True: 0, False: 3.22M] ------------------ 947| 0| if (root) { ------------------ | Branch (947:13): [True: 0, False: 0] ------------------ 948| 0| root->assign(he->word); 949| 0| if (complexprefixes) { ------------------ | Branch (949:15): [True: 0, False: 0] ------------------ 950| 0| if (utf8) ------------------ | Branch (950:17): [True: 0, False: 0] ------------------ 951| 0| reverseword_utf(*root); 952| 0| else 953| 0| reverseword(*root); 954| 0| } 955| 0| } 956| 0| if (info) ------------------ | Branch (956:13): [True: 0, False: 0] ------------------ 957| 0| *info |= SPELL_COMPOUND; ------------------ | | 78| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 958| 0| } 959| 3.22M| } 960| 13.3M| } 961| | 962| 13.3M| return he; 963| 13.3M|} _ZN12HunspellImpl7suggestERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEENS0_6chrono10time_pointINSD_12steady_clockENSD_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 971| 90.7k|std::vector HunspellImpl::suggest(const std::string& word, std::vector& suggest_candidate_stack, std::chrono::steady_clock::time_point suggest_start) { 972| | 973| 90.7k| if (suggest_candidate_stack.size() > MAX_CANDIDATE_STACK_DEPTH || // apply a fairly arbitrary depth limit ------------------ | | 966| 181k|#define MAX_CANDIDATE_STACK_DEPTH 512 ------------------ | Branch (973:7): [True: 0, False: 90.7k] | Branch (973:7): [True: 0, False: 90.7k] ------------------ 974| | // something very broken if suggest ends up calling itself with the same word 975| 90.7k| std::find(suggest_candidate_stack.begin(), suggest_candidate_stack.end(), word) != suggest_candidate_stack.end()) { ------------------ | Branch (975:7): [True: 0, False: 90.7k] ------------------ 976| 0| return { }; 977| 0| } 978| | 979| 90.7k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 90.7k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (979:7): [True: 0, False: 90.7k] ------------------ 980| 0| return { }; 981| | 982| 90.7k| bool capwords; 983| 90.7k| size_t abbv; 984| 90.7k| int captype; 985| 90.7k| std::vector spell_candidate_stack; 986| 90.7k| suggest_candidate_stack.push_back(word); 987| 90.7k| std::vector slst = suggest_internal(word, spell_candidate_stack, suggest_candidate_stack, 988| 90.7k| capwords, abbv, captype, suggest_start); 989| 90.7k| suggest_candidate_stack.pop_back(); 990| | // word reversing wrapper for complex prefixes 991| 90.7k| if (complexprefixes) { ------------------ | Branch (991:7): [True: 4.72k, False: 85.9k] ------------------ 992| 4.72k| for (auto& j : slst) { ------------------ | Branch (992:18): [True: 2.24k, False: 4.72k] ------------------ 993| 2.24k| if (utf8) ------------------ | Branch (993:11): [True: 0, False: 2.24k] ------------------ 994| 0| reverseword_utf(j); 995| 2.24k| else 996| 2.24k| reverseword(j); 997| 2.24k| } 998| 4.72k| } 999| | 1000| | // capitalize 1001| 90.7k| if (capwords) { ------------------ | Branch (1001:7): [True: 27.2k, False: 63.4k] ------------------ 1002| 27.2k| for (auto& j : slst) { ------------------ | Branch (1002:18): [True: 14.9k, False: 27.2k] ------------------ 1003| 14.9k| std::string capitalized(j); 1004| 14.9k| mkinitcap(capitalized); 1005| 14.9k| if (capitalized == word) ------------------ | Branch (1005:11): [True: 12, False: 14.9k] ------------------ 1006| 12| continue; // capitalizing would just reproduce the misspelled word 1007| 14.9k| j = std::move(capitalized); 1008| 14.9k| } 1009| 27.2k| } 1010| | 1011| | // expand suggestions with dot(s) 1012| 90.7k| if (abbv && pAMgr && pAMgr->get_sugswithdots() && word.size() >= abbv) { ------------------ | Branch (1012:7): [True: 3.39k, False: 87.3k] | Branch (1012:15): [True: 3.39k, False: 0] | Branch (1012:24): [True: 0, False: 3.39k] | Branch (1012:53): [True: 0, False: 0] ------------------ 1013| 0| for (auto& j : slst) { ------------------ | Branch (1013:18): [True: 0, False: 0] ------------------ 1014| 0| j.append(word.substr(word.size() - abbv)); 1015| 0| } 1016| 0| } 1017| | 1018| | // remove bad capitalized and forbidden forms 1019| 90.7k| if (pAMgr && (pAMgr->get_keepcase() || pAMgr->get_forbiddenword())) { ------------------ | Branch (1019:7): [True: 90.7k, False: 0] | Branch (1019:17): [True: 4.75k, False: 85.9k] | Branch (1019:42): [True: 85.9k, False: 0] ------------------ 1020| 90.7k| switch (captype) { ------------------ | Branch (1020:13): [True: 23.6k, False: 67.0k] ------------------ 1021| 12.8k| case INITCAP: ------------------ | | 93| 12.8k|#define INITCAP 1 ------------------ | Branch (1021:7): [True: 12.8k, False: 77.8k] ------------------ 1022| 23.6k| case ALLCAP: { ------------------ | | 94| 23.6k|#define ALLCAP 2 ------------------ | Branch (1022:7): [True: 10.7k, False: 79.9k] ------------------ 1023| 23.6k| size_t l = 0; 1024| 33.2k| for (size_t j = 0; j < slst.size(); ++j) { ------------------ | Branch (1024:28): [True: 9.60k, False: 23.6k] ------------------ 1025| 9.60k| if (slst[j].find(' ') == std::string::npos && !spell(slst[j], spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1025:15): [True: 9.08k, False: 522] | Branch (1025:57): [True: 4.39k, False: 4.68k] ------------------ 1026| 4.39k| std::string s; 1027| 4.39k| std::vector w; 1028| 4.39k| if (utf8) { ------------------ | Branch (1028:17): [True: 3.75k, False: 643] ------------------ 1029| 3.75k| u8_u16(w, slst[j]); 1030| 3.75k| } else { 1031| 643| s = slst[j]; 1032| 643| } 1033| 4.39k| mkallsmall2(s, w); 1034| 4.39k| if (spell(s, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1034:17): [True: 1, False: 4.39k] ------------------ 1035| 1| slst[l] = std::move(s); 1036| 1| ++l; 1037| 4.39k| } else { 1038| 4.39k| mkinitcap2(s, w); 1039| 4.39k| if (spell(s, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1039:19): [True: 5, False: 4.39k] ------------------ 1040| 5| slst[l] = std::move(s); 1041| 5| ++l; 1042| 5| } 1043| 4.39k| } 1044| 5.20k| } else { 1045| 5.20k| slst[l] = slst[j]; 1046| 5.20k| ++l; 1047| 5.20k| } 1048| 9.60k| } 1049| 23.6k| slst.resize(l); 1050| 23.6k| } 1051| 90.7k| } 1052| 90.7k| } 1053| | 1054| | // remove duplications 1055| 90.7k| size_t l = 0; 1056| 117k| for (size_t j = 0; j < slst.size(); ++j) { ------------------ | Branch (1056:22): [True: 26.4k, False: 90.7k] ------------------ 1057| 26.4k| slst[l] = slst[j]; 1058| 41.1k| for (size_t k = 0; k < l; ++k) { ------------------ | Branch (1058:24): [True: 15.6k, False: 25.4k] ------------------ 1059| 15.6k| if (slst[k] == slst[j]) { ------------------ | Branch (1059:11): [True: 918, False: 14.7k] ------------------ 1060| 918| --l; 1061| 918| break; 1062| 918| } 1063| 15.6k| } 1064| 26.4k| ++l; 1065| 26.4k| } 1066| 90.7k| slst.resize(l); 1067| | 1068| | // output conversion 1069| 90.7k| RepList* rl = (pAMgr) ? pAMgr->get_oconvtable() : nullptr; ------------------ | Branch (1069:17): [True: 90.7k, False: 0] ------------------ 1070| 90.7k| if (rl) { ------------------ | Branch (1070:7): [True: 4.84k, False: 85.8k] ------------------ 1071| 4.84k| size_t l = 0; 1072| 5.78k| for (size_t i = 0; i < slst.size(); ++i) { ------------------ | Branch (1072:24): [True: 944, False: 4.84k] ------------------ 1073| 944| std::string wspace; 1074| 944| if (rl->conv(slst[i], wspace)) { ------------------ | Branch (1074:11): [True: 317, False: 627] ------------------ 1075| 317| slst[i] = std::move(wspace); 1076| 317| } 1077| | // gh#1002: OCONV can map a generated form back to the input word 1078| | // (e.g. "románórum" -> "romanórum" when the user typed "romanórum"), 1079| | // leaving the misspelled word as its own suggestion. 1080| 944| if (slst[i] == word) ------------------ | Branch (1080:11): [True: 0, False: 944] ------------------ 1081| 0| continue; 1082| 944| if (l != i) ------------------ | Branch (1082:11): [True: 0, False: 944] ------------------ 1083| 0| slst[l] = std::move(slst[i]); 1084| 944| ++l; 1085| 944| } 1086| 4.84k| slst.resize(l); 1087| 4.84k| } 1088| 90.7k| return slst; 1089| 90.7k|} _ZN12HunspellImpl7suggestERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1091| 59.6k|std::vector HunspellImpl::suggest(const std::string& word) { 1092| 59.6k| std::vector suggest_candidate_stack; 1093| 59.6k| auto suggest_start = std::chrono::steady_clock::now(); 1094| 59.6k| return suggest(word, suggest_candidate_stack, suggest_start); 1095| 59.6k|} _ZN12HunspellImpl16suggest_internalERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEESC_RbRmRiNS0_6chrono10time_pointINSG_12steady_clockENSG_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 1101| 90.7k| std::chrono::steady_clock::time_point suggest_start) { 1102| 90.7k| captype = NOCAP; ------------------ | | 92| 90.7k|#define NOCAP 0 ------------------ 1103| 90.7k| abbv = 0; 1104| 90.7k| capwords = false; 1105| | 1106| 90.7k| std::vector slst; 1107| | 1108| 90.7k| int onlycmpdsug = 0; 1109| 90.7k| if (!pSMgr || m_HMgrs.empty()) ------------------ | Branch (1109:7): [True: 0, False: 90.7k] | Branch (1109:17): [True: 0, False: 90.7k] ------------------ 1110| 0| return slst; 1111| | 1112| | // process XML input of the simplified API (see manual) 1113| 90.7k| if (word.compare(0, sizeof(SPELL_XML) - 3, SPELL_XML, sizeof(SPELL_XML) - 3) == 0) { ------------------ | | 80| 90.7k|#define SPELL_XML "" ------------------ if (word.compare(0, sizeof(SPELL_XML) - 3, SPELL_XML, sizeof(SPELL_XML) - 3) == 0) { ------------------ | | 80| 90.7k|#define SPELL_XML "" ------------------ if (word.compare(0, sizeof(SPELL_XML) - 3, SPELL_XML, sizeof(SPELL_XML) - 3) == 0) { ------------------ | | 80| 90.7k|#define SPELL_XML "" ------------------ | Branch (1113:7): [True: 20.3k, False: 70.3k] ------------------ 1114| 20.3k| if (word.size() > MAXSPELLMLLEN) ------------------ | | 87| 20.3k|#define MAXSPELLMLLEN 8192 ------------------ | Branch (1114:9): [True: 589, False: 19.7k] ------------------ 1115| 589| return slst; 1116| 19.7k| return spellml(word); 1117| 20.3k| } 1118| 70.3k| if (utf8) { ------------------ | Branch (1118:7): [True: 33.6k, False: 36.6k] ------------------ 1119| 33.6k| if (word.size() >= MAXWORDUTF8LEN) ------------------ | | 86| 33.6k|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 33.6k|#define MAXWORDLEN 100 | | ------------------ ------------------ | Branch (1119:9): [True: 90, False: 33.5k] ------------------ 1120| 90| return slst; 1121| 36.6k| } else { 1122| 36.6k| if (word.size() >= MAXWORDLEN) ------------------ | | 90| 36.6k|#define MAXWORDLEN 100 ------------------ | Branch (1122:9): [True: 120, False: 36.5k] ------------------ 1123| 120| return slst; 1124| 36.6k| } 1125| 70.1k| size_t wl = 0; 1126| | 1127| 70.1k| std::string scw; 1128| 70.1k| std::vector sunicw; 1129| | 1130| | // input conversion 1131| 70.1k| RepList* rl = (pAMgr) ? pAMgr->get_iconvtable() : nullptr; ------------------ | Branch (1131:17): [True: 70.1k, False: 0] ------------------ 1132| 70.1k| { 1133| 70.1k| std::string wspace; 1134| | 1135| 70.1k| bool convstatus = rl ? rl->conv(word, wspace) : false; ------------------ | Branch (1135:23): [True: 3.76k, False: 66.3k] ------------------ 1136| 70.1k| if (convstatus) { ------------------ | Branch (1136:9): [True: 0, False: 70.1k] ------------------ 1137| | // the input conversion can grow the word without limit, so hold the 1138| | // converted word to the same maximum length as the raw word 1139| 0| if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 86| 0|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 0|#define MAXWORDLEN 100 | | ------------------ ------------------ if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 90| 0|#define MAXWORDLEN 100 ------------------ | Branch (1139:11): [True: 0, False: 0] | Branch (1139:11): [True: 0, False: 0] ------------------ 1140| 0| return slst; 1141| 0| wl = cleanword2(scw, sunicw, wspace, &captype, &abbv); 1142| 0| } else 1143| 70.1k| wl = cleanword2(scw, sunicw, word, &captype, &abbv); 1144| | 1145| 70.1k| if (wl == 0) ------------------ | Branch (1145:9): [True: 0, False: 70.1k] ------------------ 1146| 0| return slst; 1147| | 1148| 70.1k|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 1149| 70.1k| if (wl > 32768) ------------------ | Branch (1149:9): [True: 0, False: 70.1k] ------------------ 1150| 0| return slst; 1151| 70.1k|#endif 1152| 70.1k| } 1153| | 1154| 70.1k| bool good = false; 1155| | 1156| | // check capitalized form for FORCEUCASE 1157| 70.1k| if (pAMgr && captype == NOCAP && pAMgr->get_forceucase()) { ------------------ | | 92| 140k|#define NOCAP 0 ------------------ | Branch (1157:7): [True: 70.1k, False: 0] | Branch (1157:16): [True: 20.1k, False: 49.9k] | Branch (1157:36): [True: 0, False: 20.1k] ------------------ 1158| 0| int info = SPELL_ORIGCAP; ------------------ | | 83| 0|#define SPELL_ORIGCAP (1 << 5) ------------------ 1159| 0| if (checkword(scw, &info, nullptr, suggest_start)) { ------------------ | Branch (1159:9): [True: 0, False: 0] ------------------ 1160| 0| std::string form(std::move(scw)); 1161| 0| mkinitcap(form); 1162| 0| slst.push_back(std::move(form)); 1163| 0| return slst; 1164| 0| } 1165| 0| } 1166| | 1167| 70.1k| switch (captype) { ------------------ | Branch (1167:11): [True: 70.1k, False: 0] ------------------ 1168| 20.1k| case NOCAP: { ------------------ | | 92| 20.1k|#define NOCAP 0 ------------------ | Branch (1168:5): [True: 20.1k, False: 49.9k] ------------------ 1169| 20.1k| good |= pSMgr->suggest(slst, scw, &onlycmpdsug); 1170| 20.1k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 20.1k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1170:11): [True: 0, False: 20.1k] ------------------ 1171| 0| return slst; 1172| 20.1k| if (abbv) { ------------------ | Branch (1172:11): [True: 1.76k, False: 18.3k] ------------------ 1173| 1.76k| std::string wspace(scw); 1174| 1.76k| wspace.push_back('.'); 1175| 1.76k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1176| 1.76k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 1.76k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1176:13): [True: 0, False: 1.76k] ------------------ 1177| 0| return slst; 1178| 1.76k| } 1179| 20.1k| break; 1180| 20.1k| } 1181| | 1182| 20.1k| case INITCAP: { ------------------ | | 93| 12.8k|#define INITCAP 1 ------------------ | Branch (1182:5): [True: 12.8k, False: 57.2k] ------------------ 1183| 12.8k| capwords = true; 1184| 12.8k| good |= pSMgr->suggest(slst, scw, &onlycmpdsug); 1185| 12.8k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 12.8k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1185:11): [True: 0, False: 12.8k] ------------------ 1186| 0| return slst; 1187| 12.8k| std::string wspace(scw); 1188| 12.8k| mkallsmall2(wspace, sunicw); 1189| 12.8k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1190| 12.8k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 12.8k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1190:11): [True: 0, False: 12.8k] ------------------ 1191| 0| return slst; 1192| 12.8k| break; 1193| 12.8k| } 1194| 14.3k| case HUHINITCAP: ------------------ | | 96| 14.3k|#define HUHINITCAP 4 ------------------ | Branch (1194:5): [True: 14.3k, False: 55.7k] ------------------ 1195| 14.3k| capwords = true; 1196| | /* FALLTHROUGH */ 1197| 26.3k| case HUHCAP: { ------------------ | | 95| 26.3k|#define HUHCAP 3 ------------------ | Branch (1197:5): [True: 11.9k, False: 58.1k] ------------------ 1198| 26.3k| good |= pSMgr->suggest(slst, scw, &onlycmpdsug); 1199| 26.3k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 26.3k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1199:11): [True: 0, False: 26.3k] ------------------ 1200| 0| return slst; 1201| | // something.The -> something. The 1202| 26.3k| size_t dot_pos = scw.find('.'); 1203| 26.3k| if (dot_pos != std::string::npos) { ------------------ | Branch (1203:11): [True: 8.86k, False: 17.4k] ------------------ 1204| 8.86k| std::string postdot = scw.substr(dot_pos + 1); 1205| 8.86k| int captype_; 1206| 8.86k| if (utf8) { ------------------ | Branch (1206:13): [True: 2.18k, False: 6.67k] ------------------ 1207| 2.18k| std::vector postdotu; 1208| 2.18k| u8_u16(postdotu, postdot); 1209| 2.18k| captype_ = get_captype_utf8(postdotu, langnum); 1210| 6.67k| } else { 1211| 6.67k| captype_ = get_captype(postdot, csconv); 1212| 6.67k| } 1213| 8.86k| if (captype_ == INITCAP) { ------------------ | | 93| 8.86k|#define INITCAP 1 ------------------ | Branch (1213:13): [True: 2.21k, False: 6.64k] ------------------ 1214| 2.21k| std::string str(scw); 1215| 2.21k| str.insert(dot_pos + 1, 1, ' '); 1216| 2.21k| insert_sug(slst, str); 1217| 2.21k| } 1218| 8.86k| } 1219| | 1220| 26.3k| std::string wspace; 1221| | 1222| 26.3k| if (captype == HUHINITCAP) { ------------------ | | 96| 26.3k|#define HUHINITCAP 4 ------------------ | Branch (1222:11): [True: 14.3k, False: 11.9k] ------------------ 1223| | // TheOpenOffice.org -> The OpenOffice.org 1224| 14.3k| wspace = scw; 1225| 14.3k| mkinitsmall2(wspace, sunicw); 1226| 14.3k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1227| 14.3k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 14.3k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1227:13): [True: 0, False: 14.3k] ------------------ 1228| 0| return slst; 1229| 14.3k| } 1230| 26.3k| wspace = scw; 1231| 26.3k| mkallsmall2(wspace, sunicw); 1232| 26.3k| if (spell(wspace, spell_candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (1232:11): [True: 734, False: 25.5k] ------------------ 1233| 734| insert_sug(slst, wspace); 1234| 26.3k| size_t prevns = slst.size(); 1235| 26.3k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1236| 26.3k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 26.3k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1236:11): [True: 0, False: 26.3k] ------------------ 1237| 0| return slst; 1238| 26.3k| if (captype == HUHINITCAP) { ------------------ | | 96| 26.3k|#define HUHINITCAP 4 ------------------ | Branch (1238:11): [True: 14.3k, False: 11.9k] ------------------ 1239| 14.3k| mkinitcap2(wspace, sunicw); 1240| 14.3k| if (spell(wspace, spell_candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (1240:13): [True: 375, False: 14.0k] ------------------ 1241| 375| insert_sug(slst, wspace); 1242| 14.3k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1243| 14.3k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 14.3k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1243:13): [True: 2, False: 14.3k] ------------------ 1244| 2| return slst; 1245| 14.3k| } 1246| | // aNew -> "a New" (instead of "a new") 1247| 26.8k| for (size_t j = prevns; j < slst.size(); ++j) { ------------------ | Branch (1247:31): [True: 566, False: 26.3k] ------------------ 1248| 566| const char* space = strchr(slst[j].c_str(), ' '); 1249| 566| if (space) { ------------------ | Branch (1249:13): [True: 406, False: 160] ------------------ 1250| 406| size_t slen = strlen(space + 1); 1251| | // different case after space (need capitalisation) 1252| 406| if ((slen < wl) && strcmp(scw.c_str() + wl - slen, space + 1) != 0) { ------------------ | Branch (1252:15): [True: 406, False: 0] | Branch (1252:30): [True: 370, False: 36] ------------------ 1253| 370| std::string first(slst[j].c_str(), space + 1); 1254| 370| std::string second(space + 1); 1255| 370| std::vector w; 1256| 370| if (utf8) ------------------ | Branch (1256:17): [True: 105, False: 265] ------------------ 1257| 105| u8_u16(w, second); 1258| 370| mkinitcap2(second, w); 1259| | // set as first suggestion 1260| 370| slst.erase(slst.begin() + j); 1261| 370| slst.insert(slst.begin(), first + second); 1262| 370| } 1263| 406| } 1264| 566| } 1265| 26.3k| break; 1266| 26.3k| } 1267| | 1268| 10.7k| case ALLCAP: { ------------------ | | 94| 10.7k|#define ALLCAP 2 ------------------ | Branch (1268:5): [True: 10.7k, False: 59.3k] ------------------ 1269| 10.7k| std::string wspace(scw); 1270| 10.7k| mkallsmall2(wspace, sunicw); 1271| 10.7k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1272| 10.7k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 10.7k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1272:11): [True: 0, False: 10.7k] ------------------ 1273| 0| return slst; 1274| 10.7k| if (pAMgr && pAMgr->get_keepcase() && spell(wspace, spell_candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (1274:11): [True: 10.7k, False: 0] | Branch (1274:20): [True: 478, False: 10.3k] | Branch (1274:45): [True: 0, False: 478] ------------------ 1275| 0| insert_sug(slst, wspace); 1276| 10.7k| mkinitcap2(wspace, sunicw); 1277| 10.7k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1278| 10.7k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 10.7k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1278:11): [True: 0, False: 10.7k] ------------------ 1279| 0| return slst; 1280| 10.7k| for (auto& j : slst) { ------------------ | Branch (1280:20): [True: 605, False: 10.7k] ------------------ 1281| 605| mkallcap(j); 1282| 605| if (pAMgr && pAMgr->get_checksharps()) { ------------------ | Branch (1282:13): [True: 605, False: 0] | Branch (1282:22): [True: 0, False: 605] ------------------ 1283| 0| if (utf8) { ------------------ | Branch (1283:15): [True: 0, False: 0] ------------------ 1284| 0| mystrrep(j, "\xC3\x9F", "SS"); 1285| 0| } else { 1286| 0| mystrrep(j, "\xDF", "SS"); 1287| 0| } 1288| 0| } 1289| 605| } 1290| 10.7k| break; 1291| 10.7k| } 1292| 70.1k| } 1293| | 1294| | // LANG_hu section: replace '-' with ' ' in Hungarian 1295| 70.1k| if (langnum == LANG_hu) { ------------------ | Branch (1295:7): [True: 3.81k, False: 66.2k] ------------------ 1296| 3.81k| for (auto& j : slst) { ------------------ | Branch (1296:18): [True: 179, False: 3.81k] ------------------ 1297| 179| size_t pos = j.find('-'); 1298| 179| if (pos != std::string::npos) { ------------------ | Branch (1298:11): [True: 25, False: 154] ------------------ 1299| 25| int info = 0; 1300| 25| std::string w(j.substr(0, pos)); 1301| 25| w.append(j.substr(pos + 1)); 1302| 25| (void)spell(w, spell_candidate_stack, &info, nullptr, suggest_start); 1303| 25| if ((info & SPELL_COMPOUND) && (info & SPELL_FORBIDDEN)) { ------------------ | | 78| 25|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ if ((info & SPELL_COMPOUND) && (info & SPELL_FORBIDDEN)) { ------------------ | | 79| 0|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (1303:13): [True: 0, False: 25] | Branch (1303:40): [True: 0, False: 0] ------------------ 1304| 0| j[pos] = ' '; 1305| 0| } else 1306| 25| j[pos] = '-'; 1307| 25| } 1308| 179| } 1309| 3.81k| } 1310| | // END OF LANG_hu section 1311| | // try ngram approach since found nothing good suggestion 1312| 70.1k| if (!good && pAMgr && (slst.empty() || onlycmpdsug) && (pAMgr->get_maxngramsugs() != 0)) { ------------------ | Branch (1312:7): [True: 70.0k, False: 52] | Branch (1312:16): [True: 70.0k, False: 0] | Branch (1312:26): [True: 64.9k, False: 5.14k] | Branch (1312:42): [True: 5.10k, False: 39] | Branch (1312:58): [True: 62.4k, False: 7.53k] ------------------ 1313| 62.4k| switch (captype) { ------------------ | Branch (1313:13): [True: 62.4k, False: 0] ------------------ 1314| 17.3k| case NOCAP: { ------------------ | | 92| 17.3k|#define NOCAP 0 ------------------ | Branch (1314:7): [True: 17.3k, False: 45.0k] ------------------ 1315| 17.3k| pSMgr->ngsuggest(slst, scw.c_str(), m_HMgrs, NOCAP); ------------------ | | 92| 17.3k|#define NOCAP 0 ------------------ 1316| 17.3k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 17.3k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1316:13): [True: 0, False: 17.3k] ------------------ 1317| 0| return slst; 1318| 17.3k| break; 1319| 17.3k| } 1320| | /* FALLTHROUGH */ 1321| 17.3k| case HUHINITCAP: ------------------ | | 96| 13.6k|#define HUHINITCAP 4 ------------------ | Branch (1321:7): [True: 13.6k, False: 48.8k] ------------------ 1322| 13.6k| capwords = true; 1323| | /* FALLTHROUGH */ 1324| 24.6k| case HUHCAP: { ------------------ | | 95| 24.6k|#define HUHCAP 3 ------------------ | Branch (1324:7): [True: 11.0k, False: 51.4k] ------------------ 1325| 24.6k| std::string wspace(scw); 1326| 24.6k| mkallsmall2(wspace, sunicw); 1327| 24.6k| pSMgr->ngsuggest(slst, wspace.c_str(), m_HMgrs, HUHCAP); ------------------ | | 95| 24.6k|#define HUHCAP 3 ------------------ 1328| 24.6k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 24.6k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1328:13): [True: 0, False: 24.6k] ------------------ 1329| 0| return slst; 1330| 24.6k| break; 1331| 24.6k| } 1332| 24.6k| case INITCAP: { ------------------ | | 93| 10.9k|#define INITCAP 1 ------------------ | Branch (1332:7): [True: 10.9k, False: 51.5k] ------------------ 1333| 10.9k| capwords = true; 1334| 10.9k| std::string wspace(scw); 1335| 10.9k| mkallsmall2(wspace, sunicw); 1336| 10.9k| pSMgr->ngsuggest(slst, wspace.c_str(), m_HMgrs, INITCAP); ------------------ | | 93| 10.9k|#define INITCAP 1 ------------------ 1337| 10.9k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 10.9k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1337:13): [True: 0, False: 10.9k] ------------------ 1338| 0| return slst; 1339| 10.9k| break; 1340| 10.9k| } 1341| 10.9k| case ALLCAP: { ------------------ | | 94| 9.43k|#define ALLCAP 2 ------------------ | Branch (1341:7): [True: 9.43k, False: 53.0k] ------------------ 1342| 9.43k| std::string wspace(scw); 1343| 9.43k| mkallsmall2(wspace, sunicw); 1344| 9.43k| size_t oldns = slst.size(); 1345| 9.43k| pSMgr->ngsuggest(slst, wspace.c_str(), m_HMgrs, ALLCAP); ------------------ | | 94| 9.43k|#define ALLCAP 2 ------------------ 1346| 9.43k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 9.43k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1346:13): [True: 0, False: 9.43k] ------------------ 1347| 0| return slst; 1348| 12.0k| for (size_t j = oldns; j < slst.size(); ++j) { ------------------ | Branch (1348:32): [True: 2.58k, False: 9.43k] ------------------ 1349| 2.58k| mkallcap(slst[j]); 1350| 2.58k| } 1351| 9.43k| break; 1352| 9.43k| } 1353| 62.4k| } 1354| 62.4k| } 1355| | 1356| | // try dash suggestion (Afo-American -> Afro-American) 1357| | // Note: LibreOffice was modified to treat dashes as word 1358| | // characters to check "scot-free" etc. word forms, but 1359| | // we need to handle suggestions for "Afo-American", etc., 1360| | // while "Afro-American" is missing from the dictionary. 1361| | // TODO avoid possible overgeneration 1362| 70.1k| size_t dash_pos = scw.find('-'); 1363| 70.1k| if (dash_pos != std::string::npos) { ------------------ | Branch (1363:7): [True: 34.0k, False: 36.0k] ------------------ 1364| 34.0k| int nodashsug = 1; 1365| 40.5k| for (size_t j = 0; j < slst.size() && nodashsug == 1; ++j) { ------------------ | Branch (1365:24): [True: 6.88k, False: 33.7k] | Branch (1365:43): [True: 6.53k, False: 347] ------------------ 1366| 6.53k| if (slst[j].find('-') != std::string::npos) ------------------ | Branch (1366:11): [True: 2.40k, False: 4.12k] ------------------ 1367| 2.40k| nodashsug = 0; 1368| 6.53k| } 1369| | 1370| 34.0k| size_t prev_pos = 0; 1371| 34.0k| bool last = false; 1372| | 1373| 106k| while (!good && nodashsug && !last) { ------------------ | Branch (1373:12): [True: 106k, False: 25] | Branch (1373:21): [True: 73.3k, False: 33.4k] | Branch (1373:34): [True: 72.7k, False: 597] ------------------ 1374| 72.7k| if (dash_pos == scw.size()) ------------------ | Branch (1374:11): [True: 6.04k, False: 66.6k] ------------------ 1375| 6.04k| last = true; 1376| 72.7k| std::string chunk = scw.substr(prev_pos, dash_pos - prev_pos); 1377| 72.7k| if (chunk != word && !spell(chunk, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1377:11): [True: 72.7k, False: 0] | Branch (1377:28): [True: 31.0k, False: 41.6k] ------------------ 1378| 31.0k| std::vector nlst = suggest(chunk, suggest_candidate_stack, suggest_start); 1379| 31.0k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 31.0k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1379:13): [True: 2, False: 31.0k] ------------------ 1380| 2| return slst; 1381| 41.3k| for (auto j = nlst.rbegin(); j != nlst.rend(); ++j) { ------------------ | Branch (1381:38): [True: 10.3k, False: 31.0k] ------------------ 1382| 10.3k| std::string wspace = scw.substr(0, prev_pos); 1383| 10.3k| wspace.append(*j); 1384| 10.3k| if (!last) { ------------------ | Branch (1384:15): [True: 7.88k, False: 2.44k] ------------------ 1385| 7.88k| wspace.append("-"); 1386| 7.88k| wspace.append(scw.substr(dash_pos + 1)); 1387| 7.88k| } 1388| 10.3k| int info = 0; 1389| 10.3k| if (pAMgr && pAMgr->get_forbiddenword()) ------------------ | Branch (1389:15): [True: 10.3k, False: 0] | Branch (1389:24): [True: 10.3k, False: 0] ------------------ 1390| 10.3k| checkword(wspace, &info, nullptr, suggest_start); 1391| 10.3k| if (!(info & SPELL_FORBIDDEN)) ------------------ | | 79| 10.3k|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (1391:15): [True: 10.3k, False: 0] ------------------ 1392| 10.3k| insert_sug(slst, wspace); 1393| 10.3k| } 1394| 31.0k| nodashsug = 0; 1395| 31.0k| } 1396| 72.7k| if (!last) { ------------------ | Branch (1396:11): [True: 66.6k, False: 6.04k] ------------------ 1397| 66.6k| prev_pos = dash_pos + 1; 1398| 66.6k| dash_pos = scw.find('-', prev_pos); 1399| 66.6k| } 1400| 72.7k| if (dash_pos == std::string::npos) ------------------ | Branch (1400:11): [True: 13.4k, False: 59.2k] ------------------ 1401| 13.4k| dash_pos = scw.size(); 1402| 72.7k| } 1403| 34.0k| } 1404| 70.0k| return slst; 1405| 70.1k|} _ZN12HunspellImpl4stemERKNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEE: 1411| 931|std::vector HunspellImpl::stem(const std::vector& desc) { 1412| 931| std::vector slst; 1413| | 1414| 931| std::string result2; 1415| 931| if (desc.empty()) ------------------ | Branch (1415:7): [True: 836, False: 95] ------------------ 1416| 836| return slst; 1417| 103| for (const auto& i : desc) { ------------------ | Branch (1417:22): [True: 103, False: 95] ------------------ 1418| 103| std::string result; 1419| | 1420| | // add compound word parts (except the last one) 1421| 103| const char* s = i.c_str(); 1422| 103| const char* part = strstr(s, MORPH_PART); ------------------ | | 116| 103|#define MORPH_PART "pa:" ------------------ 1423| 103| if (part) { ------------------ | Branch (1423:9): [True: 0, False: 103] ------------------ 1424| 0| const char* nextpart = strstr(part + 1, MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 1425| 0| while (nextpart) { ------------------ | Branch (1425:14): [True: 0, False: 0] ------------------ 1426| 0| std::string field; 1427| 0| copy_field(field, part, MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 1428| 0| result.append(field); 1429| 0| part = nextpart; 1430| 0| nextpart = strstr(part + 1, MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 1431| 0| } 1432| 0| s = part; 1433| 0| } 1434| | 1435| 103| std::string tok(s); 1436| 103| size_t alt = 0; 1437| 103| while ((alt = tok.find(" | ", alt)) != std::string::npos) { ------------------ | Branch (1437:12): [True: 0, False: 103] ------------------ 1438| 0| tok[alt + 1] = MSEP_ALT; ------------------ | | 123| 0|#define MSEP_ALT '\v' ------------------ 1439| 0| } 1440| 103| std::vector pl = line_tok(tok, MSEP_ALT); ------------------ | | 123| 103|#define MSEP_ALT '\v' ------------------ 1441| 103| for (auto& k : pl) { ------------------ | Branch (1441:18): [True: 103, False: 103] ------------------ 1442| | // add derivational suffixes 1443| 103| if (k.find(MORPH_DERI_SFX) != std::string::npos) { ------------------ | | 109| 103|#define MORPH_DERI_SFX "ds:" ------------------ | Branch (1443:11): [True: 0, False: 103] ------------------ 1444| | // remove inflectional suffixes 1445| 0| const size_t is = k.find(MORPH_INFL_SFX); ------------------ | | 110| 0|#define MORPH_INFL_SFX "is:" ------------------ 1446| 0| if (is != std::string::npos) ------------------ | Branch (1446:13): [True: 0, False: 0] ------------------ 1447| 0| k.resize(is); 1448| 0| std::vector singlepl; 1449| 0| singlepl.push_back(k); 1450| 0| std::string sg = pSMgr->suggest_gen(singlepl, k); 1451| 0| if (!sg.empty()) { ------------------ | Branch (1451:13): [True: 0, False: 0] ------------------ 1452| 0| std::vector gen = line_tok(sg, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1453| 0| for (auto& j : gen) { ------------------ | Branch (1453:24): [True: 0, False: 0] ------------------ 1454| 0| result2.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1455| 0| result2.append(result); 1456| 0| result2.append(j); 1457| 0| } 1458| 0| } 1459| 103| } else { 1460| 103| result2.push_back(MSEP_REC); ------------------ | | 122| 103|#define MSEP_REC '\n' ------------------ 1461| 103| result2.append(result); 1462| 103| if (k.find(MORPH_SURF_PFX) != std::string::npos) { ------------------ | | 112| 103|#define MORPH_SURF_PFX "sp:" ------------------ | Branch (1462:13): [True: 0, False: 103] ------------------ 1463| 0| std::string field; 1464| 0| copy_field(field, k, MORPH_SURF_PFX); ------------------ | | 112| 0|#define MORPH_SURF_PFX "sp:" ------------------ 1465| 0| result2.append(field); 1466| 0| } 1467| 103| std::string field; 1468| 103| copy_field(field, k, MORPH_STEM); ------------------ | | 103| 103|#define MORPH_STEM "st:" ------------------ 1469| 103| result2.append(field); 1470| 103| } 1471| 103| } 1472| 103| } 1473| 95| slst = line_tok(result2, MSEP_REC); ------------------ | | 122| 95|#define MSEP_REC '\n' ------------------ 1474| 95| uniqlist(slst); 1475| 95| return slst; 1476| 931|} _ZN12HunspellImpl4stemERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1478| 931|std::vector HunspellImpl::stem(const std::string& word) { 1479| 931| return stem(analyze(word)); 1480| 931|} _ZN12HunspellImpl9mkinitcapERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1490| 14.9k|void HunspellImpl::mkinitcap(std::string& u8) { 1491| 14.9k| if (utf8) { ------------------ | Branch (1491:7): [True: 4.65k, False: 10.2k] ------------------ 1492| 4.65k| std::vector u16; 1493| 4.65k| u8_u16(u16, u8); 1494| 4.65k| ::mkinitcap_utf(u16, langnum); 1495| 4.65k| u16_u8(u8, u16); 1496| 10.2k| } else { 1497| 10.2k| ::mkinitcap(u8, csconv); 1498| 10.2k| } 1499| 14.9k|} _ZN12HunspellImpl10mkinitcap2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEE: 1501| 1.04M|int HunspellImpl::mkinitcap2(std::string& u8, std::vector& u16) { 1502| 1.04M| if (utf8) { ------------------ | Branch (1502:7): [True: 239k, False: 804k] ------------------ 1503| 239k| ::mkinitcap_utf(u16, langnum); 1504| 239k| u16_u8(u8, u16); 1505| 804k| } else { 1506| 804k| ::mkinitcap(u8, csconv); 1507| 804k| } 1508| 1.04M| return u8.size(); 1509| 1.04M|} _ZN12HunspellImpl12mkinitsmall2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEE: 1511| 14.3k|int HunspellImpl::mkinitsmall2(std::string& u8, std::vector& u16) { 1512| 14.3k| if (utf8) { ------------------ | Branch (1512:7): [True: 3.28k, False: 11.0k] ------------------ 1513| 3.28k| ::mkinitsmall_utf(u16, langnum); 1514| 3.28k| u16_u8(u8, u16); 1515| 11.0k| } else { 1516| 11.0k| ::mkinitsmall(u8, csconv); 1517| 11.0k| } 1518| 14.3k| return u8.size(); 1519| 14.3k|} _ZN12HunspellImpl3addERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1521| 5.18k|int HunspellImpl::add(const std::string& word) { 1522| 5.18k| if (!m_HMgrs.empty()) ------------------ | Branch (1522:7): [True: 5.18k, False: 0] ------------------ 1523| 5.18k| return m_HMgrs[0]->add(word); 1524| 0| return 0; 1525| 5.18k|} _ZN12HunspellImpl14add_with_affixERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 1533| 1.74k|int HunspellImpl::add_with_affix(const std::string& word, const std::string& example) { 1534| 1.74k| if (!m_HMgrs.empty()) ------------------ | Branch (1534:7): [True: 1.74k, False: 0] ------------------ 1535| 1.74k| return m_HMgrs[0]->add_with_affix(word, example); 1536| 0| return 0; 1537| 1.74k|} _ZN12HunspellImpl10cat_resultERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKS6_: 1556| 310k|void HunspellImpl::cat_result(std::string& result, const std::string& st) { 1557| 310k| if (!st.empty()) { ------------------ | Branch (1557:7): [True: 3.06k, False: 307k] ------------------ 1558| 3.06k| if (!result.empty()) ------------------ | Branch (1558:9): [True: 648, False: 2.41k] ------------------ 1559| 648| result.append("\n"); 1560| 3.06k| result.append(st); 1561| 3.06k| } 1562| 310k|} _ZN12HunspellImpl7analyzeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1564| 7.43k|std::vector HunspellImpl::analyze(const std::string& word) { 1565| 7.43k| std::vector slst = analyze_internal(word); 1566| | // output conversion 1567| 7.43k| RepList* rl = (pAMgr) ? pAMgr->get_oconvtable() : nullptr; ------------------ | Branch (1567:17): [True: 7.43k, False: 0] ------------------ 1568| 7.43k| if (rl) { ------------------ | Branch (1568:7): [True: 390, False: 7.04k] ------------------ 1569| 512| for (size_t i = 0; rl && i < slst.size(); ++i) { ------------------ | Branch (1569:24): [True: 512, False: 0] | Branch (1569:30): [True: 122, False: 390] ------------------ 1570| 122| std::string wspace; 1571| 122| if (rl->conv(slst[i], wspace)) { ------------------ | Branch (1571:11): [True: 0, False: 122] ------------------ 1572| 0| slst[i] = std::move(wspace); 1573| 0| } 1574| 122| } 1575| 390| } 1576| 7.43k| return slst; 1577| 7.43k|} _ZN12HunspellImpl16analyze_internalERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1579| 7.43k|std::vector HunspellImpl::analyze_internal(const std::string& word) { 1580| 7.43k| std::vector candidate_stack, slst; 1581| 7.43k| if (!pSMgr || m_HMgrs.empty()) ------------------ | Branch (1581:7): [True: 0, False: 7.43k] | Branch (1581:17): [True: 0, False: 7.43k] ------------------ 1582| 0| return slst; 1583| 7.43k| if (utf8) { ------------------ | Branch (1583:7): [True: 3.51k, False: 3.91k] ------------------ 1584| 3.51k| if (word.size() >= MAXWORDUTF8LEN) ------------------ | | 86| 3.51k|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 3.51k|#define MAXWORDLEN 100 | | ------------------ ------------------ | Branch (1584:9): [True: 262, False: 3.25k] ------------------ 1585| 262| return slst; 1586| 3.91k| } else { 1587| 3.91k| if (word.size() >= MAXWORDLEN) ------------------ | | 90| 3.91k|#define MAXWORDLEN 100 ------------------ | Branch (1587:9): [True: 520, False: 3.39k] ------------------ 1588| 520| return slst; 1589| 3.91k| } 1590| 6.65k| int captype = NOCAP; ------------------ | | 92| 6.65k|#define NOCAP 0 ------------------ 1591| 6.65k| size_t abbv = 0; 1592| 6.65k| size_t wl = 0; 1593| | 1594| 6.65k| std::string scw; 1595| 6.65k| std::vector sunicw; 1596| | 1597| | // input conversion 1598| 6.65k| RepList* rl = (pAMgr) ? pAMgr->get_iconvtable() : nullptr; ------------------ | Branch (1598:17): [True: 6.65k, False: 0] ------------------ 1599| 6.65k| { 1600| 6.65k| std::string wspace; 1601| | 1602| 6.65k| bool convstatus = rl ? rl->conv(word, wspace) : false; ------------------ | Branch (1602:23): [True: 361, False: 6.29k] ------------------ 1603| 6.65k| if (convstatus) { ------------------ | Branch (1603:9): [True: 0, False: 6.65k] ------------------ 1604| | // the input conversion can grow the word without limit, so hold the 1605| | // converted word to the same maximum length as the raw word 1606| 0| if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 86| 0|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 0|#define MAXWORDLEN 100 | | ------------------ ------------------ if (utf8 ? wspace.size() >= MAXWORDUTF8LEN : wspace.size() >= MAXWORDLEN) ------------------ | | 90| 0|#define MAXWORDLEN 100 ------------------ | Branch (1606:11): [True: 0, False: 0] | Branch (1606:11): [True: 0, False: 0] ------------------ 1607| 0| return slst; 1608| 0| wl = cleanword2(scw, sunicw, wspace, &captype, &abbv); 1609| 0| } else 1610| 6.65k| wl = cleanword2(scw, sunicw, word, &captype, &abbv); 1611| | 1612| 6.65k|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 1613| 6.65k| if (wl > 32768) ------------------ | Branch (1613:9): [True: 0, False: 6.65k] ------------------ 1614| 0| return slst; 1615| 6.65k|#endif 1616| 6.65k| } 1617| | 1618| 6.65k| if (wl == 0) { ------------------ | Branch (1618:7): [True: 402, False: 6.25k] ------------------ 1619| 402| if (abbv) { ------------------ | Branch (1619:9): [True: 266, False: 136] ------------------ 1620| 266| scw.clear(); 1621| 5.26k| for (wl = 0; wl < abbv; wl++) ------------------ | Branch (1621:20): [True: 4.99k, False: 266] ------------------ 1622| 4.99k| scw.push_back('.'); 1623| 266| abbv = 0; 1624| 266| } else 1625| 136| return slst; 1626| 402| } 1627| | 1628| 6.51k| std::string result; 1629| | 1630| 6.51k| auto suggest_start = std::chrono::steady_clock::now(); 1631| | 1632| 6.51k| size_t n = 0; 1633| | // test numbers 1634| | // LANG_hu section: set dash information for suggestions 1635| 6.51k| if (langnum == LANG_hu) { ------------------ | Branch (1635:7): [True: 355, False: 6.16k] ------------------ 1636| 355| size_t n2 = 0; 1637| 355| size_t n3 = 0; 1638| | 1639| 426| while ((n < wl) && (((scw[n] <= '9') && (scw[n] >= '0')) || ------------------ | Branch (1639:12): [True: 403, False: 23] | Branch (1639:26): [True: 236, False: 167] | Branch (1639:45): [True: 71, False: 165] ------------------ 1640| 332| (((scw[n] == '.') || (scw[n] == ',')) && (n > 0)))) { ------------------ | Branch (1640:27): [True: 19, False: 313] | Branch (1640:46): [True: 0, False: 313] | Branch (1640:66): [True: 0, False: 19] ------------------ 1641| 71| n++; 1642| 71| if ((scw[n] == '.') || (scw[n] == ',')) { ------------------ | Branch (1642:11): [True: 0, False: 71] | Branch (1642:30): [True: 0, False: 71] ------------------ 1643| 0| if (((n2 == 0) && (n > 3)) || ------------------ | Branch (1643:14): [True: 0, False: 0] | Branch (1643:27): [True: 0, False: 0] ------------------ 1644| 0| ((n2 > 0) && ((scw[n - 1] == '.') || (scw[n - 1] == ',')))) ------------------ | Branch (1644:14): [True: 0, False: 0] | Branch (1644:27): [True: 0, False: 0] | Branch (1644:50): [True: 0, False: 0] ------------------ 1645| 0| break; 1646| 0| n2++; 1647| 0| n3 = n; 1648| 0| } 1649| 71| } 1650| | 1651| 355| if ((n == wl) && (n3 > 0) && (n - n3 > 3)) ------------------ | Branch (1651:9): [True: 23, False: 332] | Branch (1651:22): [True: 0, False: 23] | Branch (1651:34): [True: 0, False: 0] ------------------ 1652| 0| return slst; 1653| 355| if ((n == wl) || ((n > 0) && ((scw[n] == '%') || (scw[n] == '\xB0')) && checkword(scw.substr(n), nullptr, nullptr, suggest_start))) { ------------------ | Branch (1653:9): [True: 23, False: 332] | Branch (1653:9): [True: 23, False: 332] | Branch (1653:23): [True: 0, False: 332] | Branch (1653:35): [True: 0, False: 0] | Branch (1653:54): [True: 0, False: 0] | Branch (1653:77): [True: 0, False: 0] ------------------ 1654| 23| result.append(scw); 1655| 23| result.resize(n - 1); 1656| 23| if (n == wl) ------------------ | Branch (1656:11): [True: 23, False: 0] ------------------ 1657| 23| cat_result(result, pSMgr->suggest_morph(scw.substr(n - 1))); 1658| 0| else { 1659| 0| std::string chunk = scw.substr(n - 1, 1); 1660| 0| cat_result(result, pSMgr->suggest_morph(chunk)); 1661| 0| result.push_back('+'); // XXX SPEC. MORPHCODE 1662| 0| cat_result(result, pSMgr->suggest_morph(scw.substr(n))); 1663| 0| } 1664| 23| return line_tok(result, MSEP_REC); ------------------ | | 122| 23|#define MSEP_REC '\n' ------------------ 1665| 23| } 1666| 355| } 1667| | // END OF LANG_hu section 1668| | 1669| 6.49k| switch (captype) { ------------------ | Branch (1669:11): [True: 6.49k, False: 0] ------------------ 1670| 756| case HUHCAP: ------------------ | | 95| 756|#define HUHCAP 3 ------------------ | Branch (1670:5): [True: 756, False: 5.73k] ------------------ 1671| 976| case HUHINITCAP: ------------------ | | 96| 976|#define HUHINITCAP 4 ------------------ | Branch (1671:5): [True: 220, False: 6.27k] ------------------ 1672| 3.08k| case NOCAP: { ------------------ | | 92| 3.08k|#define NOCAP 0 ------------------ | Branch (1672:5): [True: 2.10k, False: 4.38k] ------------------ 1673| 3.08k| cat_result(result, pSMgr->suggest_morph(scw)); 1674| 3.08k| if (abbv) { ------------------ | Branch (1674:11): [True: 268, False: 2.81k] ------------------ 1675| 268| std::string u8buffer(scw); 1676| 268| u8buffer.push_back('.'); 1677| 268| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1678| 268| } 1679| 3.08k| break; 1680| 976| } 1681| 1.24k| case INITCAP: { ------------------ | | 93| 1.24k|#define INITCAP 1 ------------------ | Branch (1681:5): [True: 1.24k, False: 5.24k] ------------------ 1682| 1.24k| mkallsmall2(scw, sunicw); 1683| 1.24k| std::string u8buffer(scw); 1684| 1.24k| mkinitcap2(scw, sunicw); 1685| 1.24k| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1686| 1.24k| cat_result(result, pSMgr->suggest_morph(scw)); 1687| 1.24k| if (abbv) { ------------------ | Branch (1687:11): [True: 279, False: 965] ------------------ 1688| 279| u8buffer.push_back('.'); 1689| 279| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1690| | 1691| 279| u8buffer = scw; 1692| 279| u8buffer.push_back('.'); 1693| | 1694| 279| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1695| 279| } 1696| 1.24k| break; 1697| 976| } 1698| 2.16k| case ALLCAP: { ------------------ | | 94| 2.16k|#define ALLCAP 2 ------------------ | Branch (1698:5): [True: 2.16k, False: 4.32k] ------------------ 1699| 2.16k| cat_result(result, pSMgr->suggest_morph(scw)); 1700| 2.16k| if (abbv) { ------------------ | Branch (1700:11): [True: 238, False: 1.92k] ------------------ 1701| 238| std::string u8buffer(scw); 1702| 238| u8buffer.push_back('.'); 1703| 238| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1704| 238| } 1705| 2.16k| mkallsmall2(scw, sunicw); 1706| 2.16k| std::string u8buffer(scw); 1707| 2.16k| mkinitcap2(scw, sunicw); 1708| | 1709| 2.16k| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1710| 2.16k| cat_result(result, pSMgr->suggest_morph(scw)); 1711| 2.16k| if (abbv) { ------------------ | Branch (1711:11): [True: 238, False: 1.92k] ------------------ 1712| 238| u8buffer.push_back('.'); 1713| 238| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1714| | 1715| 238| u8buffer = scw; 1716| 238| u8buffer.push_back('.'); 1717| | 1718| 238| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1719| 238| } 1720| 2.16k| break; 1721| 976| } 1722| 6.49k| } 1723| | 1724| 6.49k| if (!result.empty()) { ------------------ | Branch (1724:7): [True: 2.41k, False: 4.07k] ------------------ 1725| | // word reversing wrapper for complex prefixes 1726| 2.41k| if (complexprefixes) { ------------------ | Branch (1726:9): [True: 138, False: 2.27k] ------------------ 1727| 138| if (utf8) ------------------ | Branch (1727:11): [True: 0, False: 138] ------------------ 1728| 0| reverseword_utf(result); 1729| 138| else 1730| 138| reverseword(result); 1731| 138| } 1732| 2.41k| return line_tok(result, MSEP_REC); ------------------ | | 122| 2.41k|#define MSEP_REC '\n' ------------------ 1733| 2.41k| } 1734| | 1735| | // compound word with dash (HU) I18n 1736| | // LANG_hu section: set dash information for suggestions 1737| | 1738| 4.07k| size_t dash_pos = langnum == LANG_hu ? scw.find('-') : std::string::npos; ------------------ | Branch (1738:21): [True: 213, False: 3.86k] ------------------ 1739| 4.07k| if (dash_pos != std::string::npos) { ------------------ | Branch (1739:7): [True: 43, False: 4.03k] ------------------ 1740| 43| int nresult = 0; 1741| | 1742| 43| std::string part1 = scw.substr(0, dash_pos), part2 = scw.substr(dash_pos + 1); 1743| | 1744| | // examine 2 sides of the dash 1745| 43| if (part2.empty()) { // base word ending with dash ------------------ | Branch (1745:9): [True: 4, False: 39] ------------------ 1746| 4| if (spell(part1, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1746:11): [True: 0, False: 4] ------------------ 1747| 0| std::string p = pSMgr->suggest_morph(part1); 1748| 0| if (!p.empty()) { ------------------ | Branch (1748:13): [True: 0, False: 0] ------------------ 1749| 0| slst = line_tok(p, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1750| 0| return slst; 1751| 0| } 1752| 0| } 1753| 39| } else if (part2.size() == 1 && part2[0] == 'e') { // XXX (HU) -e hat. ------------------ | Branch (1753:16): [True: 5, False: 34] | Branch (1753:37): [True: 0, False: 5] ------------------ 1754| 0| if (spell(part1, candidate_stack, nullptr, nullptr, suggest_start) && ------------------ | Branch (1754:11): [True: 0, False: 0] | Branch (1754:11): [True: 0, False: 0] ------------------ 1755| 0| (spell("-e", candidate_stack, nullptr, nullptr, suggest_start))) { ------------------ | Branch (1755:11): [True: 0, False: 0] ------------------ 1756| 0| std::string st = pSMgr->suggest_morph(part1); 1757| 0| if (!st.empty()) { ------------------ | Branch (1757:13): [True: 0, False: 0] ------------------ 1758| 0| result.append(st); 1759| 0| } 1760| 0| result.push_back('+'); // XXX spec. separator in MORPHCODE 1761| 0| st = pSMgr->suggest_morph("-e"); 1762| 0| if (!st.empty()) { ------------------ | Branch (1762:13): [True: 0, False: 0] ------------------ 1763| 0| result.append(st); 1764| 0| } 1765| 0| return line_tok(result, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1766| 0| } 1767| 39| } else { 1768| | // first word ending with dash: word- XXX ??? 1769| 39| part1.push_back(' '); 1770| 39| nresult = spell(part1, candidate_stack, nullptr, nullptr, suggest_start); 1771| 39| part1.erase(part1.size() - 1); 1772| 39| if (nresult && spell(part2, candidate_stack, nullptr, nullptr, suggest_start) && ------------------ | Branch (1772:11): [True: 6, False: 33] | Branch (1772:22): [True: 3, False: 3] ------------------ 1773| 3| ((part2.size() > 1) || ((part2[0] > '0') && (part2[0] < '9')))) { ------------------ | Branch (1773:12): [True: 0, False: 3] | Branch (1773:35): [True: 3, False: 0] | Branch (1773:55): [True: 3, False: 0] ------------------ 1774| 3| std::string st = pSMgr->suggest_morph(part1); 1775| 3| if (!st.empty()) { ------------------ | Branch (1775:13): [True: 0, False: 3] ------------------ 1776| 0| result.append(st); 1777| 0| result.push_back('+'); // XXX spec. separator in MORPHCODE 1778| 0| } 1779| 3| st = pSMgr->suggest_morph(part2); 1780| 3| if (!st.empty()) { ------------------ | Branch (1780:13): [True: 0, False: 3] ------------------ 1781| 0| result.append(st); 1782| 0| } 1783| 3| return line_tok(result, MSEP_REC); ------------------ | | 122| 3|#define MSEP_REC '\n' ------------------ 1784| 3| } 1785| 39| } 1786| | // affixed number in correct word 1787| 40| if (nresult && (dash_pos > 0) && ------------------ | Branch (1787:9): [True: 3, False: 37] | Branch (1787:20): [True: 0, False: 3] ------------------ 1788| 0| (((scw[dash_pos - 1] <= '9') && (scw[dash_pos - 1] >= '0')) || ------------------ | Branch (1788:11): [True: 0, False: 0] | Branch (1788:41): [True: 0, False: 0] ------------------ 1789| 0| (scw[dash_pos - 1] == '.'))) { ------------------ | Branch (1789:10): [True: 0, False: 0] ------------------ 1790| 0| n = 1; 1791| 0| if (scw[dash_pos - n] == '.') ------------------ | Branch (1791:11): [True: 0, False: 0] ------------------ 1792| 0| n++; 1793| | // search first not a number character to left from dash 1794| 0| while ((dash_pos >= n) && ((scw[dash_pos - n] == '0') || (n < 3)) && ------------------ | Branch (1794:14): [True: 0, False: 0] | Branch (1794:34): [True: 0, False: 0] | Branch (1794:64): [True: 0, False: 0] ------------------ 1795| 0| (n < 6)) { ------------------ | Branch (1795:14): [True: 0, False: 0] ------------------ 1796| 0| n++; 1797| 0| } 1798| 0| if (dash_pos < n) ------------------ | Branch (1798:11): [True: 0, False: 0] ------------------ 1799| 0| n--; 1800| | // numbers: valami1000000-hoz 1801| | // examine 100000-hoz, 10000-hoz 1000-hoz, 10-hoz, 1802| | // 56-hoz, 6-hoz 1803| 0| for (; n >= 1; n--) { ------------------ | Branch (1803:14): [True: 0, False: 0] ------------------ 1804| 0| if (scw[dash_pos - n] < '0' || scw[dash_pos - n] > '9') { ------------------ | Branch (1804:13): [True: 0, False: 0] | Branch (1804:40): [True: 0, False: 0] ------------------ 1805| 0| continue; 1806| 0| } 1807| 0| std::string chunk = scw.substr(dash_pos - n); 1808| 0| if (checkword(chunk, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1808:13): [True: 0, False: 0] ------------------ 1809| 0| result.append(chunk); 1810| 0| std::string st = pSMgr->suggest_morph(chunk); 1811| 0| if (!st.empty()) { ------------------ | Branch (1811:15): [True: 0, False: 0] ------------------ 1812| 0| result.append(st); 1813| 0| } 1814| 0| return line_tok(result, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1815| 0| } 1816| 0| } 1817| 0| } 1818| 40| } 1819| 4.07k| return slst; 1820| 4.07k|} _ZN12HunspellImpl8generateERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKNS0_6vectorIS6_NS4_IS6_EEEE: 1822| 6.11k|std::vector HunspellImpl::generate(const std::string& word, const std::vector& pl) { 1823| 6.11k| std::vector slst; 1824| 6.11k| if (!pSMgr || pl.empty()) ------------------ | Branch (1824:7): [True: 0, False: 6.11k] | Branch (1824:17): [True: 469, False: 5.64k] ------------------ 1825| 469| return slst; 1826| 5.64k| std::vector pl2 = analyze(word); 1827| 5.64k| int captype = NOCAP, abbv = 0; ------------------ | | 92| 5.64k|#define NOCAP 0 ------------------ 1828| 5.64k| std::string cw; 1829| 5.64k| cleanword(cw, word, &captype, &abbv); 1830| 5.64k| std::string result; 1831| | 1832| 5.64k| auto suggest_start = std::chrono::steady_clock::now(); 1833| 297k| for (const auto& i : pl) { ------------------ | Branch (1833:22): [True: 297k, False: 5.64k] ------------------ 1834| 297k| cat_result(result, pSMgr->suggest_gen(pl2, i, suggest_start)); 1835| 297k| } 1836| | 1837| 5.64k| if (!result.empty()) { ------------------ | Branch (1837:7): [True: 0, False: 5.64k] ------------------ 1838| | // allcap 1839| 0| if (captype == ALLCAP) ------------------ | | 94| 0|#define ALLCAP 2 ------------------ | Branch (1839:9): [True: 0, False: 0] ------------------ 1840| 0| mkallcap(result); 1841| | 1842| | // line split 1843| 0| slst = line_tok(result, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1844| | 1845| | // capitalize 1846| 0| if (captype == INITCAP || captype == HUHINITCAP) { ------------------ | | 93| 0|#define INITCAP 1 ------------------ if (captype == INITCAP || captype == HUHINITCAP) { ------------------ | | 96| 0|#define HUHINITCAP 4 ------------------ | Branch (1846:9): [True: 0, False: 0] | Branch (1846:31): [True: 0, False: 0] ------------------ 1847| 0| for (auto& str : slst) { ------------------ | Branch (1847:22): [True: 0, False: 0] ------------------ 1848| 0| mkinitcap(str); 1849| 0| } 1850| 0| } 1851| | 1852| | // temporary filtering of prefix related errors (eg. 1853| | // generate("undrinkable", "eats") --> "undrinkables" and "*undrinks") 1854| 0| auto it = slst.begin(); 1855| 0| while (it != slst.end()) { ------------------ | Branch (1855:12): [True: 0, False: 0] ------------------ 1856| 0| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 0|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1856:11): [True: 0, False: 0] ------------------ 1857| 0| break; 1858| 0| std::vector candidate_stack; 1859| 0| if (!spell(*it, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1859:11): [True: 0, False: 0] ------------------ 1860| 0| it = slst.erase(it); 1861| 0| } else { 1862| 0| ++it; 1863| 0| } 1864| 0| } 1865| 0| } 1866| 5.64k| return slst; 1867| 6.11k|} _ZN12HunspellImpl8generateERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 1869| 646|std::vector HunspellImpl::generate(const std::string& word, const std::string& pattern) { 1870| 646| std::vector pl = analyze(pattern); 1871| 646| std::vector slst = generate(word, pl); 1872| 646| uniqlist(slst); 1873| 646| return slst; 1874| 646|} _ZN12HunspellImpl11get_xml_parERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEm: 1877| 381k|std::string HunspellImpl::get_xml_par(const std::string& in_par, std::string::size_type pos) { 1878| 381k| std::string dest; 1879| 381k| if (pos == std::string::npos) ------------------ | Branch (1879:7): [True: 5.66k, False: 375k] ------------------ 1880| 5.66k| return dest; 1881| 375k| const char* par = in_par.c_str() + pos; 1882| 375k| char end = *par; 1883| 375k| if (end == '>') ------------------ | Branch (1883:7): [True: 372k, False: 2.86k] ------------------ 1884| 372k| end = '<'; 1885| 2.86k| else if (end != '\'' && end != '"') ------------------ | Branch (1885:12): [True: 2.33k, False: 532] | Branch (1885:27): [True: 1.29k, False: 1.04k] ------------------ 1886| 1.29k| return dest; // bad XML 1887| 10.8M| for (par++; *par != '\0' && *par != end; ++par) { ------------------ | Branch (1887:15): [True: 10.7M, False: 30.3k] | Branch (1887:31): [True: 10.4M, False: 343k] ------------------ 1888| 10.4M| dest.push_back(*par); 1889| 10.4M| } 1890| 374k| mystrrep(dest, "<", "<"); 1891| 374k| mystrrep(dest, "&", "&"); 1892| 374k| return dest; 1893| 375k|} _ZN12HunspellImpl11get_xml_posERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEmPKc: 1909| 64.3k|std::string::size_type HunspellImpl::get_xml_pos(const std::string& s, std::string::size_type pos, const char* attr) { 1910| 64.3k| if (pos == std::string::npos) ------------------ | Branch (1910:7): [True: 0, False: 64.3k] ------------------ 1911| 0| return std::string::npos; 1912| | 1913| 64.3k| std::string::size_type endpos = s.find('>', pos); 1914| 64.3k| if (attr == nullptr) ------------------ | Branch (1914:7): [True: 0, False: 64.3k] ------------------ 1915| 0| return endpos; 1916| 193k| while (true) { ------------------ | Branch (1916:10): [True: 193k, Folded] ------------------ 1917| 193k| pos = s.find(attr, pos); 1918| 193k| if (pos == std::string::npos || pos >= endpos) ------------------ | Branch (1918:9): [True: 3.19k, False: 190k] | Branch (1918:37): [True: 1.52k, False: 188k] ------------------ 1919| 4.71k| return std::string::npos; 1920| 188k| if (pos == 0 || s[pos - 1] == ' ' || s[pos - 1] == '\n') ------------------ | Branch (1920:9): [True: 0, False: 188k] | Branch (1920:21): [True: 1.65k, False: 187k] | Branch (1920:42): [True: 57.9k, False: 129k] ------------------ 1921| 59.6k| break; 1922| 129k| pos += strlen(attr); 1923| 129k| } 1924| 59.6k| return pos + strlen(attr); 1925| 64.3k|} _ZN12HunspellImpl13check_xml_parERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEmPKcSA_: 1929| 64.3k| const char* value) { 1930| 64.3k| const std::string cw = get_xml_par(q, get_xml_pos(q, pos, attr)); 1931| 64.3k| return cw == value ? 1 : 0; ------------------ | Branch (1931:10): [True: 15.8k, False: 48.5k] ------------------ 1932| 64.3k|} _ZN12HunspellImpl12get_xml_listERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEmPKc: 1934| 6.23k|std::vector HunspellImpl::get_xml_list(const std::string& list, std::string::size_type pos, const char* tag) { 1935| 6.23k| std::vector slst; 1936| 6.23k| if (pos == std::string::npos) ------------------ | Branch (1936:7): [True: 38, False: 6.19k] ------------------ 1937| 38| return slst; 1938| 303k| while (true) { ------------------ | Branch (1938:10): [True: 303k, Folded] ------------------ 1939| 303k| pos = list.find(tag, pos); 1940| 303k| if (pos == std::string::npos) ------------------ | Branch (1940:9): [True: 4.80k, False: 298k] ------------------ 1941| 4.80k| break; 1942| 298k| std::string cw = get_xml_par(list, pos + strlen(tag) - 1); 1943| 298k| if (cw.empty()) { ------------------ | Branch (1943:9): [True: 1.38k, False: 296k] ------------------ 1944| 1.38k| break; 1945| 1.38k| } 1946| 296k| slst.push_back(std::move(cw)); 1947| 296k| ++pos; 1948| 296k| } 1949| 6.19k| return slst; 1950| 6.23k|} _ZN12HunspellImpl7spellmlERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1952| 19.7k|std::vector HunspellImpl::spellml(const std::string& in_word) { 1953| 19.7k| std::vector slst; 1954| | 1955| 19.7k| std::string::size_type qpos = in_word.find("', qpos); 1960| 19.3k| if (q2pos == std::string::npos) ------------------ | Branch (1960:7): [True: 133, False: 19.1k] ------------------ 1961| 133| return slst; // bad XML input 1962| | 1963| 19.1k| q2pos = in_word.find("', q2pos)); 1969| 456| if (!cw.empty()) ------------------ | Branch (1969:9): [True: 209, False: 247] ------------------ 1970| 209| slst = analyze(cw); 1971| 456| if (slst.empty()) ------------------ | Branch (1971:9): [True: 435, False: 21] ------------------ 1972| 435| return slst; 1973| | // convert the result to ana1ana2 format 1974| 21| std::string r; 1975| 21| r.append(""); 1976| 21| for (auto entry : slst) { ------------------ | Branch (1976:21): [True: 21, False: 21] ------------------ 1977| 21| r.append(""); 1978| | 1979| 21| mystrrep(entry, "\t", " "); 1980| 21| mystrrep(entry, "&", "&"); 1981| 21| mystrrep(entry, "<", "<"); 1982| 21| r.append(entry); 1983| | 1984| 21| r.append(""); 1985| 21| } 1986| 21| r.append(""); 1987| 21| slst.clear(); 1988| 21| slst.push_back(std::move(r)); 1989| 21| return slst; 1990| 18.3k| } else if (check_xml_par(in_word, qpos, "type=", "stem")) { ------------------ | Branch (1990:14): [True: 1.29k, False: 17.1k] ------------------ 1991| 1.29k| std::string cw = get_xml_par(in_word, in_word.find('>', q2pos)); 1992| 1.29k| if (!cw.empty()) ------------------ | Branch (1992:9): [True: 931, False: 361] ------------------ 1993| 931| return stem(cw); 1994| 17.1k| } else if (check_xml_par(in_word, qpos, "type=", "generate")) { ------------------ | Branch (1994:14): [True: 7.10k, False: 10.0k] ------------------ 1995| 7.10k| std::string cw = get_xml_par(in_word, in_word.find('>', q2pos)); 1996| 7.10k| if (cw.empty()) ------------------ | Branch (1996:9): [True: 95, False: 7.00k] ------------------ 1997| 95| return slst; 1998| 7.00k| std::string::size_type q3pos = in_word.find("', q3pos)); 2001| 741| if (!cw2.empty()) { ------------------ | Branch (2001:11): [True: 646, False: 95] ------------------ 2002| 646| return generate(cw, cw2); 2003| 646| } 2004| 6.26k| } else { 2005| 6.26k| q2pos = in_word.find(" slst2 = get_xml_list(in_word, in_word.find('>', q2pos), ""); 2008| 6.23k| if (!slst2.empty()) { ------------------ | Branch (2008:13): [True: 5.47k, False: 759] ------------------ 2009| 5.47k| slst = generate(cw, slst2); 2010| 5.47k| uniqlist(slst); 2011| 5.47k| return slst; 2012| 5.47k| } 2013| 6.23k| } 2014| 6.26k| } 2015| 10.0k| } else if (check_xml_par(in_word, qpos, "type=", "add")) { ------------------ | Branch (2015:14): [True: 7.00k, False: 2.99k] ------------------ 2016| 7.00k| std::string cw = get_xml_par(in_word, in_word.find('>', q2pos)); 2017| 7.00k| if (cw.empty()) ------------------ | Branch (2017:9): [True: 76, False: 6.92k] ------------------ 2018| 76| return slst; 2019| 6.92k| std::string::size_type q3pos = in_word.find("', q3pos)); 2022| 1.95k| if (!cw2.empty()) { ------------------ | Branch (2022:11): [True: 1.74k, False: 208] ------------------ 2023| 1.74k| add_with_affix(cw, cw2); 2024| 1.74k| } else { 2025| 208| add(cw); 2026| 208| } 2027| 4.97k| } else { 2028| 4.97k| add(cw); 2029| 4.97k| } 2030| 6.92k| } 2031| 11.1k| return slst; 2032| 18.8k|} _ZN8HunspellC2EPKcS1_S1_: 2182| 38| : m_Impl(new HunspellImpl(affpath, dpath, key)) { 2183| 38|} _ZN8Hunspell5spellERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiPS6_: 2194| 60.0k|bool Hunspell::spell(const std::string& word, int* info, std::string* root) { 2195| 60.0k| std::vector candidate_stack; 2196| 60.0k| return m_Impl->spell(word, candidate_stack, info, root, 2197| 60.0k| std::chrono::steady_clock::now()); 2198| 60.0k|} _ZN8Hunspell7suggestERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 2200| 59.6k|std::vector Hunspell::suggest(const std::string& word) { 2201| 59.6k| return m_Impl->suggest(word); 2202| 59.6k|} _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| 10.3k|std::string phonet(const std::string& inword, phonetable& parms) { 70| | 71| 10.3k| int i, k = 0, p, z, k0, n0, p0 = -333; 72| 10.3k| char c; 73| 10.3k| using uchar = unsigned char; 74| | 75| 10.3k| size_t len = inword.size(); 76| 10.3k| if (len > MAXPHONETUTF8LEN) ------------------ | | 35| 10.3k|#define MAXPHONETUTF8LEN (MAXPHONETLEN * 4) | | ------------------ | | | | 34| 10.3k|#define MAXPHONETLEN 256 | | ------------------ ------------------ | Branch (76:7): [True: 0, False: 10.3k] ------------------ 77| 0| return {}; 78| 10.3k| char word[MAXPHONETUTF8LEN + 1]; 79| 10.3k| strncpy(word, inword.c_str(), MAXPHONETUTF8LEN); ------------------ | | 35| 10.3k|#define MAXPHONETUTF8LEN (MAXPHONETLEN * 4) | | ------------------ | | | | 34| 10.3k|#define MAXPHONETLEN 256 | | ------------------ ------------------ 80| 10.3k| word[MAXPHONETUTF8LEN] = '\0'; ------------------ | | 35| 10.3k|#define MAXPHONETUTF8LEN (MAXPHONETLEN * 4) | | ------------------ | | | | 34| 10.3k|#define MAXPHONETLEN 256 | | ------------------ ------------------ 81| | 82| 10.3k| std::string target; 83| | /** check word **/ 84| 10.3k| i = z = 0; 85| 92.5k| while ((c = word[i]) != '\0') { ------------------ | Branch (85:10): [True: 82.1k, False: 10.3k] ------------------ 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: 25.4k, False: 56.7k] | Branch (89:19): [True: 25.4k, False: 0] ------------------ 90| | /** check all rules for the same letter **/ 91| 61.8k| while (parms.rules[n][0] == c) { ------------------ | Branch (91:14): [True: 59.9k, False: 1.86k] ------------------ 92| | /** check whole string **/ 93| 59.9k| k = 1; /** number of found letters **/ 94| 59.9k| p = 5; /** default priority **/ 95| 59.9k| const char*s = parms.rules[n].c_str(); 96| 59.9k| s++; /** important for (see below) "*(s-1)" **/ 97| | 98| 62.0k| while (*s != '\0' && word[i + k] == *s && !isdigit((unsigned char)*s) && strchr("(-<^$", *s) == nullptr) { ------------------ | Branch (98:16): [True: 40.5k, False: 21.4k] | Branch (98:30): [True: 2.06k, False: 38.5k] | Branch (98:51): [True: 2.06k, False: 0] | Branch (98:82): [True: 2.03k, False: 31] ------------------ 99| 2.03k| k++; 100| 2.03k| s++; 101| 2.03k| } 102| 59.9k| if (*s == '(') { ------------------ | Branch (102:13): [True: 3.79k, False: 56.1k] ------------------ 103| | /** check letters in "(..)" **/ 104| 3.79k| if (myisalpha(word[i + k]) // ...could be implied? ------------------ | Branch (104:15): [True: 2.66k, False: 1.12k] ------------------ 105| 2.66k| && strchr(s + 1, word[i + k]) != nullptr) { ------------------ | Branch (105:18): [True: 330, False: 2.33k] ------------------ 106| 330| k++; 107| 1.82k| while (*s && *s != ')') ------------------ | Branch (107:20): [True: 1.82k, False: 0] | Branch (107:26): [True: 1.49k, False: 330] ------------------ 108| 1.49k| s++; 109| 330| if (*s == ')') ------------------ | Branch (109:17): [True: 330, False: 0] ------------------ 110| 330| s++; 111| 330| } 112| 3.79k| } 113| 59.9k| p0 = (int)*s; 114| 59.9k| k0 = k; 115| 61.5k| while (*s == '-' && k > 1) { ------------------ | Branch (115:16): [True: 1.59k, False: 59.9k] | Branch (115:29): [True: 1.59k, False: 0] ------------------ 116| 1.59k| k--; 117| 1.59k| s++; 118| 1.59k| } 119| 59.9k| if (*s == '<') ------------------ | Branch (119:13): [True: 77, False: 59.9k] ------------------ 120| 77| s++; 121| 59.9k| if (isdigit((unsigned char)*s)) { ------------------ | Branch (121:13): [True: 0, False: 59.9k] ------------------ 122| | /** determine priority **/ 123| 0| p = *s - '0'; 124| 0| s++; 125| 0| } 126| 59.9k| if (*s == '^' && *(s + 1) == '^') ------------------ | Branch (126:13): [True: 2.42k, False: 57.5k] | Branch (126:26): [True: 0, False: 2.42k] ------------------ 127| 0| s++; 128| | 129| 59.9k| if (*s == '\0' || (*s == '^' && (i == 0 || !myisalpha(word[i - 1])) && ------------------ | Branch (129:13): [True: 23.1k, False: 36.8k] | Branch (129:28): [True: 2.42k, False: 34.4k] | Branch (129:42): [True: 113, False: 2.31k] | Branch (129:52): [True: 577, False: 1.73k] ------------------ 130| 690| (*(s + 1) != '$' || (!myisalpha(word[i + k0])))) || ------------------ | Branch (130:29): [True: 690, False: 0] | Branch (130:48): [True: 0, False: 0] ------------------ 131| 36.1k| (*s == '$' && i > 0 && myisalpha(word[i - 1]) && ------------------ | Branch (131:14): [True: 0, False: 36.1k] | Branch (131:27): [True: 0, False: 0] | Branch (131:36): [True: 0, False: 0] ------------------ 132| 23.8k| (!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| 23.8k| char c0 = word[i + k - 1]; 136| 23.8k| n0 = parms.hash[(uchar)c0]; 137| | 138| | // if (parms.followup && k > 1 && n0 >= 0 139| 23.8k| if (k > 1 && n0 >= 0 && p0 != (int)'-' && word[i + k] != '\0' && !parms.rules[n0].empty()) { ------------------ | Branch (139:15): [True: 441, False: 23.3k] | Branch (139:24): [True: 441, False: 0] | Branch (139:35): [True: 400, False: 41] | Branch (139:53): [True: 372, False: 28] | Branch (139:76): [True: 372, False: 0] ------------------ 140| | /** test follow-up rule for "word[i+k]" **/ 141| 1.00k| while (parms.rules[n0][0] == c0) { ------------------ | Branch (141:20): [True: 874, False: 130] ------------------ 142| | /** check whole string **/ 143| 874| k0 = k; 144| 874| p0 = 5; 145| 874| s = parms.rules[n0].c_str(); 146| 874| s++; 147| 1.11k| while (*s != '\0' && word[i + k0] == *s && !isdigit((unsigned char)*s) && strchr("(-<^$", *s) == nullptr) { ------------------ | Branch (147:22): [True: 744, False: 372] | Branch (147:36): [True: 242, False: 502] | Branch (147:58): [True: 242, False: 0] | Branch (147:89): [True: 242, False: 0] ------------------ 148| 242| k0++; 149| 242| s++; 150| 242| } 151| 874| if (*s == '(') { ------------------ | Branch (151:19): [True: 0, False: 874] ------------------ 152| | /** check letters **/ 153| 0| if (myisalpha(word[i + k0]) && strchr(s + 1, word[i + k0]) != nullptr) { ------------------ | Branch (153:21): [True: 0, False: 0] | Branch (153:48): [True: 0, False: 0] ------------------ 154| 0| k0++; 155| 0| while (*s != ')' && *s != '\0') ------------------ | Branch (155:26): [True: 0, False: 0] | Branch (155:39): [True: 0, False: 0] ------------------ 156| 0| s++; 157| 0| if (*s == ')') ------------------ | Branch (157:23): [True: 0, False: 0] ------------------ 158| 0| s++; 159| 0| } 160| 0| } 161| 874| while (*s == '-') { ------------------ | Branch (161:22): [True: 0, False: 874] ------------------ 162| | /** "k0" gets NOT reduced **/ 163| | /** because "if (k0 == k)" **/ 164| 0| s++; 165| 0| } 166| 874| if (*s == '<') ------------------ | Branch (166:19): [True: 0, False: 874] ------------------ 167| 0| s++; 168| 874| if (isdigit((unsigned char)*s)) { ------------------ | Branch (168:19): [True: 0, False: 874] ------------------ 169| 0| p0 = *s - '0'; 170| 0| s++; 171| 0| } 172| | 173| 874| if (*s == '\0' ------------------ | Branch (173:19): [True: 372, False: 502] ------------------ 174| | /** *s == '^' cuts **/ 175| 502| || (*s == '$' && !myisalpha(word[i + k0]))) { ------------------ | Branch (175:23): [True: 0, False: 502] | Branch (175:36): [True: 0, False: 0] ------------------ 176| 372| if (k0 == k) { ------------------ | Branch (176:21): [True: 130, False: 242] ------------------ 177| | /** this is just a piece of the string **/ 178| 130| n0 += 2; 179| 130| continue; 180| 130| } 181| | 182| 242| if (p0 < p) { ------------------ | Branch (182:21): [True: 0, False: 242] ------------------ 183| | /** priority too low **/ 184| 0| n0 += 2; 185| 0| continue; 186| 0| } 187| | /** rule fits; stop search **/ 188| 242| break; 189| 242| } 190| 502| n0 += 2; 191| 502| } /** End of "while (parms.rules[n0][0] == c0)" **/ 192| | 193| 372| if (p0 >= p && parms.rules[n0][0] == c0) { ------------------ | Branch (193:17): [True: 372, False: 0] | Branch (193:28): [True: 242, False: 130] ------------------ 194| 242| n += 2; 195| 242| continue; 196| 242| } 197| 372| } /** end of follow-up stuff **/ 198| | 199| | /** replace string **/ 200| 23.5k| s = parms.rules[n + 1].c_str(); 201| 23.5k| p0 = (!parms.rules[n].empty() && strchr(parms.rules[n].c_str() + 1, '<') != nullptr) ? 1 : 0; ------------------ | Branch (201:17): [True: 23.5k, False: 0] | Branch (201:44): [True: 77, False: 23.5k] ------------------ 202| 23.5k| if (p0 == 1 && z == 0) { ------------------ | Branch (202:15): [True: 77, False: 23.5k] | Branch (202:26): [True: 77, False: 0] ------------------ 203| | /** rule with '<' is used **/ 204| 77| if (!target.empty() && *s != '\0' && ------------------ | Branch (204:17): [True: 40, False: 37] | Branch (204:36): [True: 40, False: 0] ------------------ 205| 40| (target[target.size()-1] == c || target[target.size()-1] == *s)) { ------------------ | Branch (205:18): [True: 0, False: 40] | Branch (205:50): [True: 0, False: 40] ------------------ 206| 0| target.erase(target.size() - 1); 207| 0| } 208| 77| z0 = 1; 209| 77| z = 1; 210| 77| k0 = 0; 211| 154| while (*s != '\0' && word[i + k0] != '\0') { ------------------ | Branch (211:20): [True: 77, False: 77] | Branch (211:34): [True: 77, False: 0] ------------------ 212| 77| word[i + k0] = *s; 213| 77| k0++; 214| 77| s++; 215| 77| } 216| 77| if (k > k0) ------------------ | Branch (216:17): [True: 0, False: 77] ------------------ 217| 0| strmove(&word[0] + i + k0, &word[0] + i + k); 218| | 219| | /** new "actual letter" **/ 220| 77| c = word[i]; 221| 23.5k| } else { /** no '<' rule used **/ 222| 23.5k| i += k - 1; 223| 23.5k| z = 0; 224| 23.8k| while (*s != '\0' && *(s + 1) != '\0' && target.size() < len) { ------------------ | Branch (224:20): [True: 22.3k, False: 1.49k] | Branch (224:34): [True: 434, False: 21.9k] | Branch (224:54): [True: 382, False: 52] ------------------ 225| 382| if (target.empty() || target[target.size()-1] != *s) { ------------------ | Branch (225:19): [True: 2, False: 380] | Branch (225:37): [True: 114, False: 266] ------------------ 226| 116| target.push_back(*s); 227| 116| } 228| 382| s++; 229| 382| } 230| | /** new "actual letter" **/ 231| 23.5k| c = *s; 232| 23.5k| if (!parms.rules[n].empty() && strstr(parms.rules[n].c_str() + 1, "^^") != nullptr) { ------------------ | Branch (232:17): [True: 23.5k, False: 0] | Branch (232:44): [True: 0, False: 23.5k] ------------------ 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| 23.5k| } 241| 23.5k| break; 242| 23.8k| } /** end of follow-up stuff **/ 243| 36.1k| n += 2; 244| 36.1k| } /** end of while (parms.rules[n][0] == c) **/ 245| 25.4k| } /** end of if (n >= 0) **/ 246| 82.1k| if (z0 == 0) { ------------------ | Branch (246:9): [True: 82.0k, False: 77] ------------------ 247| 82.0k| if (k && !p0 && target.size() < len && c != '\0') { ------------------ | Branch (247:11): [True: 25.3k, False: 56.7k] | Branch (247:16): [True: 23.5k, False: 1.86k] | Branch (247:23): [True: 23.4k, False: 65] | Branch (247:46): [True: 21.9k, False: 1.49k] ------------------ 248| | /** condense only double letters **/ 249| 21.9k| target.push_back(c); 250| | /// printf("\n setting \n"); 251| 21.9k| } 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| 10.3k| return target; 260| 10.3k|} /** end of function "phonet" **/ phonet.cxx:_ZL9myisalphac: 59| 6.10k|static int myisalpha(char ch) { 60| 6.10k| if ((unsigned char)ch < 128) ------------------ | Branch (60:7): [True: 5.62k, False: 483] ------------------ 61| 5.62k| return isalpha(ch); 62| 483| return 1; 63| 6.10k|} _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_: 184| 366k|bool RepList::conv(const std::string& in_word, std::string& dest) { 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| 366k| if (can_use_trie && trie.get_status()) ------------------ | Branch (187:7): [True: 366k, False: 0] | Branch (187:23): [True: 366k, False: 0] ------------------ 188| 366k| return trie.transcode(in_word, dest) != 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; ++i) { ------------------ | Branch (196:22): [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| 366k|} _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| 366k| bool get_status() const { return status_ok; } _ZNK4TrieItLb1EE9transcodeERKNSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEERS7_: 205| 366k| TranscodeResult transcode(const std::string& src, std::string& dst) const { 206| | // Halt and return None if the trie is in an invalid memory state 207| 366k| if (!status_ok || src.empty()) return TranscodeResult::None; ------------------ | Branch (207:13): [True: 0, False: 366k] | Branch (207:27): [True: 1.77k, False: 364k] ------------------ 208| | 209| 364k| dst.clear(); 210| 364k| dst.reserve(src.size()); 211| | 212| | // State trackers for the 3-way outcome 213| 364k| bool any_substituted = false; 214| 364k| bool any_copied = false; 215| | 216| 364k| size_t i = 0; 217| | 218| 4.22M| while (i < src.size()) { ------------------ | Branch (218:16): [True: 3.85M, False: 364k] ------------------ 219| 3.85M| size_t curr_idx = 0; 220| 3.85M| size_t match_len = 0; 221| 3.85M| uint32_t best_sub = 0xFFFFFFFF; 222| | 223| 3.85M| size_t j = i; 224| | 225| | // Greedily traverse the trie to find the longest matching sequence 226| 3.86M| while (j < src.size()) { ------------------ | Branch (226:20): [True: 3.86M, False: 202] ------------------ 227| 3.86M| uint8_t byte = static_cast(src[j]); 228| | 229| 3.86M| if (UseNibbles) { ------------------ | Branch (229:21): [True: 3.86M, Folded] ------------------ 230| 3.86M| IndexType r1 = nodes[curr_idx].children[(byte >> 4) & 0x0F]; 231| 3.86M| if (r1 == 0) break; ------------------ | Branch (231:25): [True: 3.82M, False: 40.6k] ------------------ 232| 40.6k| curr_idx += r1; 233| | 234| 40.6k| IndexType r2 = nodes[curr_idx].children[byte & 0x0F]; 235| 40.6k| if (r2 == 0) break; ------------------ | Branch (235:25): [True: 37.1k, False: 3.54k] ------------------ 236| 3.54k| curr_idx += r2; 237| 3.54k| } 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| 3.54k| ++j; 244| | 245| | // Track the deepest valid match found during traversal 246| 3.54k| if (sub_info_arena[curr_idx] != 0xFFFFFFFF) { ------------------ | Branch (246:21): [True: 523, False: 3.02k] ------------------ 247| 523| best_sub = sub_info_arena[curr_idx]; 248| 523| match_len = j - i; 249| 523| } 250| 3.54k| } 251| | 252| 3.85M| if (best_sub != 0xFFFFFFFF) { ------------------ | Branch (252:17): [True: 523, False: 3.85M] ------------------ 253| | // Decode the 24-bit offset and 8-bit size, append directly from arena 254| 523| dst.append(&char_arena[best_sub >> 8], best_sub & 0xFF); 255| 523| i += match_len; 256| 523| any_substituted = true; // State update: Substitution occurred 257| 3.85M| } else { 258| | // Fallback: copy unmapped character directly to output 259| 3.85M| dst.push_back(src[i]); 260| 3.85M| ++i; 261| 3.85M| any_copied = true; // State update: Verbatim copy occurred 262| 3.85M| } 263| 3.85M| } 264| | 265| | // ALGORITHM: Outcome Evaluation 266| 364k| if (any_substituted && any_copied) { ------------------ | Branch (266:13): [True: 317, False: 364k] | Branch (266:32): [True: 310, False: 7] ------------------ 267| 310| return TranscodeResult::Partial; 268| 364k| } else if (any_substituted) { ------------------ | Branch (268:20): [True: 7, False: 364k] ------------------ 269| 7| return TranscodeResult::All; 270| 7| } 271| | 272| 364k| return TranscodeResult::None; 273| 364k| } _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| 87.1M| int& info) { 167| 87.1M| if (wlst.size() == maxSug) ------------------ | Branch (167:7): [True: 0, False: 87.1M] ------------------ 168| 0| return; 169| | 170| 87.1M| const int cwrd = std::find(wlst.begin(), wlst.end(), candidate) != wlst.end() ? 0 : 1; ------------------ | Branch (170:20): [True: 21.6k, False: 87.1M] ------------------ 171| | 172| 87.1M| if (cwrd) { ------------------ | Branch (172:7): [True: 87.1M, False: 21.6k] ------------------ 173| 87.1M| if (int result = checkword(candidate, cpdsuggest, timer, timelimit)) { ------------------ | Branch (173:13): [True: 1.51k, False: 87.1M] ------------------ 174| | // compound word in the dictionary 175| 1.51k| if (cpdsuggest == 0 && result >= 2) ------------------ | Branch (175:11): [True: 1.51k, False: 0] | Branch (175:30): [True: 0, False: 1.51k] ------------------ 176| 0| info |= SPELL_COMPOUND; ------------------ | | 78| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 177| 1.51k| wlst.push_back(candidate); 178| 1.51k| } 179| 87.1M| } 180| 87.1M|} _ZN10SuggestMgr7suggestERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_Pib: 190| 150k| int* onlycompoundsug, bool test_simplesug) { 191| 150k| int nocompoundtwowords = 0; // no second or third loops, see below 192| 150k| std::vector word_utf; 193| 150k| size_t nsugorig = slst.size(), oldSug = 0; 194| 150k| std::string w2; 195| 150k| bool good_suggestion = false; 196| | 197| | // word reversing wrapper for complex prefixes 198| 150k| if (complexprefixes) { ------------------ | Branch (198:7): [True: 8.78k, False: 141k] ------------------ 199| 8.78k| w2.assign(w); 200| 8.78k| if (utf8) ------------------ | Branch (200:9): [True: 0, False: 8.78k] ------------------ 201| 0| reverseword_utf(w2); 202| 8.78k| else 203| 8.78k| reverseword(w2); 204| 8.78k| } 205| | 206| 150k| const std::string& word = complexprefixes ? w2 : w; ------------------ | Branch (206:29): [True: 8.78k, False: 141k] ------------------ 207| | 208| 150k| suggest_start = std::chrono::steady_clock::now(); 209| | 210| 150k| if (utf8) { ------------------ | Branch (210:7): [True: 62.4k, False: 88.1k] ------------------ 211| 62.4k| int wl = u8_u16(word_utf, word); 212| 62.4k| if (wl == -1) { ------------------ | Branch (212:9): [True: 9.89k, False: 52.5k] ------------------ 213| 9.89k| return false; 214| 9.89k| } 215| 62.4k| } 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| 140k| int info = 0; 225| 562k| for (int cpdsuggest = 0; cpdsuggest < 3 && nocompoundtwowords == 0; cpdsuggest++) { ------------------ | Branch (225:28): [True: 421k, False: 140k] | Branch (225:46): [True: 421k, False: 39] ------------------ 226| | 227| | // limit compound suggestion 228| 421k| if (cpdsuggest > 0) ------------------ | Branch (228:9): [True: 281k, False: 140k] ------------------ 229| 281k| oldSug = slst.size(); 230| | 231| | // suggestions for an uppercase word (html -> HTML) 232| 421k| if (slst.size() < maxSug) { ------------------ | Branch (232:9): [True: 421k, False: 17] ------------------ 233| 421k| size_t i = slst.size(); 234| 421k| if (utf8) ------------------ | Branch (234:11): [True: 157k, False: 264k] ------------------ 235| 157k| capchars_utf(slst, word_utf, cpdsuggest, info); 236| 264k| else 237| 264k| capchars(slst, word, cpdsuggest, info); 238| 421k| if (slst.size() > i) ------------------ | Branch (238:11): [True: 39, False: 421k] ------------------ 239| 39| good_suggestion = true; 240| 421k| } 241| | 242| | // perhaps we made a typical fault of spelling 243| 421k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (243:9): [True: 421k, False: 17] | Branch (243:36): [True: 140k, False: 281k] | Branch (243:51): [True: 281k, False: 0] ------------------ 244| 421k| size_t i = slst.size(); 245| 421k| replchars(slst, word, cpdsuggest, info); 246| 421k| if (slst.size() > i) { ------------------ | Branch (246:11): [True: 0, False: 421k] ------------------ 247| 0| good_suggestion = true; 248| 0| if (info & SPELL_BEST_SUG) ------------------ | | 86| 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| 421k| } 252| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (252:9): [True: 0, False: 421k] ------------------ 253| 0| return good_suggestion; 254| 421k| if (test_simplesug && slst.size()) ------------------ | Branch (254:9): [True: 0, False: 421k] | 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| 421k| if ((slst.size() < maxSug) && ------------------ | Branch (258:9): [True: 421k, False: 17] ------------------ 259| 421k| (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (259:10): [True: 140k, False: 281k] | Branch (259:25): [True: 281k, False: 0] ------------------ 260| 421k| mapchars(slst, word, cpdsuggest, info); 261| 421k| } 262| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (262:9): [True: 6, False: 421k] ------------------ 263| 6| return good_suggestion; 264| 421k| if (test_simplesug && slst.size()) ------------------ | Branch (264:9): [True: 0, False: 421k] | Branch (264:27): [True: 0, False: 0] ------------------ 265| 0| return true; 266| | 267| | // only suggest compound words when no other ~good suggestion 268| 421k| if ((cpdsuggest == 0) && (slst.size() > nsugorig)) ------------------ | Branch (268:9): [True: 140k, False: 281k] | Branch (268:30): [True: 39, False: 140k] ------------------ 269| 39| nocompoundtwowords = 1; 270| | 271| | // did we swap the order of chars by mistake 272| 421k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (272:9): [True: 421k, False: 17] | Branch (272:36): [True: 140k, False: 281k] | Branch (272:51): [True: 281k, False: 0] ------------------ 273| 421k| if (utf8) ------------------ | Branch (273:11): [True: 157k, False: 264k] ------------------ 274| 157k| swapchar_utf(slst, word_utf, cpdsuggest, info); 275| 264k| else 276| 264k| swapchar(slst, word, cpdsuggest, info); 277| 421k| } 278| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (278:9): [True: 0, False: 421k] ------------------ 279| 0| return good_suggestion; 280| 421k| if (test_simplesug && slst.size()) ------------------ | Branch (280:9): [True: 0, False: 421k] | 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| 421k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (284:9): [True: 421k, False: 17] | Branch (284:36): [True: 140k, False: 281k] | Branch (284:51): [True: 281k, False: 0] ------------------ 285| 421k| if (utf8) ------------------ | Branch (285:11): [True: 157k, False: 264k] ------------------ 286| 157k| longswapchar_utf(slst, word_utf, cpdsuggest, info); 287| 264k| else 288| 264k| longswapchar(slst, word, cpdsuggest, info); 289| 421k| } 290| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (290:9): [True: 0, False: 421k] ------------------ 291| 0| return good_suggestion; 292| 421k| if (test_simplesug && slst.size()) ------------------ | Branch (292:9): [True: 0, False: 421k] | 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| 421k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (296:9): [True: 421k, False: 17] | Branch (296:36): [True: 140k, False: 281k] | Branch (296:51): [True: 281k, False: 0] ------------------ 297| 421k| if (utf8) ------------------ | Branch (297:11): [True: 157k, False: 264k] ------------------ 298| 157k| badcharkey_utf(slst, word_utf, cpdsuggest, info); 299| 264k| else 300| 264k| badcharkey(slst, word, cpdsuggest, info); 301| 421k| } 302| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (302:9): [True: 0, False: 421k] ------------------ 303| 0| return good_suggestion; 304| 421k| if (test_simplesug && slst.size()) ------------------ | Branch (304:9): [True: 0, False: 421k] | Branch (304:27): [True: 0, False: 0] ------------------ 305| 0| return true; 306| | 307| | // did we add a char that should not be there 308| 421k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (308:9): [True: 421k, False: 17] | Branch (308:36): [True: 140k, False: 281k] | Branch (308:51): [True: 281k, False: 0] ------------------ 309| 421k| if (utf8) ------------------ | Branch (309:11): [True: 157k, False: 264k] ------------------ 310| 157k| extrachar_utf(slst, word_utf, cpdsuggest, info); 311| 264k| else 312| 264k| extrachar(slst, word, cpdsuggest, info); 313| 421k| } 314| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (314:9): [True: 0, False: 421k] ------------------ 315| 0| return good_suggestion; 316| 421k| if (test_simplesug && slst.size()) ------------------ | Branch (316:9): [True: 0, False: 421k] | Branch (316:27): [True: 0, False: 0] ------------------ 317| 0| return true; 318| | 319| | // did we forgot a char 320| 421k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (320:9): [True: 421k, False: 17] | Branch (320:36): [True: 140k, False: 281k] | Branch (320:51): [True: 281k, False: 0] ------------------ 321| 421k| if (utf8) ------------------ | Branch (321:11): [True: 157k, False: 264k] ------------------ 322| 157k| forgotchar_utf(slst, word_utf, cpdsuggest, info); 323| 264k| else 324| 264k| forgotchar(slst, word, cpdsuggest, info); 325| 421k| } 326| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (326:9): [True: 0, False: 421k] ------------------ 327| 0| return good_suggestion; 328| 421k| if (test_simplesug && slst.size()) ------------------ | Branch (328:9): [True: 0, False: 421k] | Branch (328:27): [True: 0, False: 0] ------------------ 329| 0| return true; 330| | 331| | // did we move a char 332| 421k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (332:9): [True: 421k, False: 17] | Branch (332:36): [True: 140k, False: 281k] | Branch (332:51): [True: 281k, False: 0] ------------------ 333| 421k| if (utf8) ------------------ | Branch (333:11): [True: 157k, False: 264k] ------------------ 334| 157k| movechar_utf(slst, word_utf, cpdsuggest, info); 335| 264k| else 336| 264k| movechar(slst, word, cpdsuggest, info); 337| 421k| } 338| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (338:9): [True: 0, False: 421k] ------------------ 339| 0| return good_suggestion; 340| 421k| if (test_simplesug && slst.size()) ------------------ | Branch (340:9): [True: 0, False: 421k] | 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| 421k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (344:9): [True: 421k, False: 17] | Branch (344:36): [True: 140k, False: 281k] | Branch (344:51): [True: 281k, False: 0] ------------------ 345| 421k| if (utf8) ------------------ | Branch (345:11): [True: 157k, False: 264k] ------------------ 346| 157k| badchar_utf(slst, word_utf, cpdsuggest, info); 347| 264k| else 348| 264k| badchar(slst, word, cpdsuggest, info); 349| 421k| } 350| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (350:9): [True: 0, False: 421k] ------------------ 351| 0| return good_suggestion; 352| 421k| if (test_simplesug && slst.size()) ------------------ | Branch (352:9): [True: 0, False: 421k] | Branch (352:27): [True: 0, False: 0] ------------------ 353| 0| return true; 354| | 355| | // did we double two characters 356| 421k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (356:9): [True: 421k, False: 17] | Branch (356:36): [True: 140k, False: 281k] | Branch (356:51): [True: 281k, False: 0] ------------------ 357| 421k| if (utf8) ------------------ | Branch (357:11): [True: 157k, False: 264k] ------------------ 358| 157k| doubletwochars_utf(slst, word_utf, cpdsuggest, info); 359| 264k| else 360| 264k| doubletwochars(slst, word, cpdsuggest, info); 361| 421k| } 362| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (362:9): [True: 0, False: 421k] ------------------ 363| 0| return good_suggestion; 364| 421k| if (test_simplesug && slst.size()) ------------------ | Branch (364:9): [True: 0, False: 421k] | 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| 421k| if (!cpdsuggest || (!nosplitsugs && slst.size() < oldSug + maxcpdsugs)) { ------------------ | Branch (371:9): [True: 140k, False: 281k] | Branch (371:25): [True: 281k, False: 0] | Branch (371:41): [True: 281k, False: 0] ------------------ 372| 421k| good_suggestion = twowords(slst, word, cpdsuggest, good_suggestion, info); 373| | 374| 421k| if (info & SPELL_BEST_SUG) ------------------ | | 86| 421k|#define SPELL_BEST_SUG (1 << 8) // limit suggestions for the best ones, i.e. ph: ------------------ | Branch (374:11): [True: 128, False: 421k] ------------------ 375| 128| return true; 376| 421k| } 377| 421k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 421k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (377:9): [True: 0, False: 421k] ------------------ 378| 0| return good_suggestion; 379| | 380| | // testing returns after the first loop 381| 421k| if (test_simplesug) ------------------ | Branch (381:9): [True: 0, False: 421k] ------------------ 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| 421k| if (cpdsuggest == 1 && (slst.size() > oldSug || (info & SPELL_COMPOUND))) ------------------ | | 78| 140k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ | Branch (387:9): [True: 140k, False: 281k] | Branch (387:29): [True: 0, False: 140k] | Branch (387:53): [True: 0, False: 140k] ------------------ 388| 0| nocompoundtwowords = 1; 389| | 390| 421k| } // repeating ``for'' statement compounding support 391| | 392| 140k| if (!nocompoundtwowords && (!slst.empty()) && onlycompoundsug) ------------------ | Branch (392:7): [True: 140k, False: 39] | Branch (392:30): [True: 10.2k, False: 130k] | Branch (392:49): [True: 10.2k, False: 0] ------------------ 393| 10.2k| *onlycompoundsug = 1; 394| | 395| 140k| return good_suggestion; 396| 140k|} _ZN10SuggestMgr12capchars_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 401| 157k| int cpdsuggest, int& info) { 402| 157k| std::vector candidate_utf(word); 403| 157k| mkallcap_utf(candidate_utf, langnum); 404| 157k| std::string candidate; 405| 157k| u16_u8(candidate, candidate_utf); 406| 157k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 407| 157k|} _ZN10SuggestMgr8capcharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 412| 264k| int cpdsuggest, int& info) { 413| 264k| std::string candidate(word); 414| 264k| mkallcap(candidate, csconv); 415| 264k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 416| 264k|} _ZN10SuggestMgr8mapcharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 421| 421k| int cpdsuggest, int& info) { 422| 421k| std::string candidate; 423| 421k| std::chrono::steady_clock::time_point timelimit; 424| 421k| int timer; 425| | 426| 421k| if (word.size() < 2 || !pAMgr) ------------------ | Branch (426:7): [True: 35.2k, False: 386k] | Branch (426:26): [True: 0, False: 386k] ------------------ 427| 35.2k| return wlst.size(); 428| | 429| 386k| const std::vector& maptable = pAMgr->get_maptable(); 430| 386k| if (maptable.empty()) ------------------ | Branch (430:7): [True: 370k, False: 15.5k] ------------------ 431| 370k| return wlst.size(); 432| | 433| 15.5k| timelimit = std::chrono::steady_clock::now(); 434| 15.5k| timer = MINTIMER; ------------------ | | 107| 15.5k|#define MINTIMER 100 ------------------ 435| 15.5k| return map_related(word, candidate, 0, wlst, cpdsuggest, 436| 15.5k| maptable, &timer, &timelimit, 0, info); 437| 386k|} _ZN10SuggestMgr11map_relatedERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERS6_mRNS0_6vectorIS6_NS4_IS6_EEEEiRKNSA_ISC_NS4_ISC_EEEEPiPNS0_6chrono10time_pointINSJ_12steady_clockENSJ_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEEiRi: 447| 5.52M| int depth, int& info) { 448| 5.52M| if (word.size() == wn) { ------------------ | Branch (448:7): [True: 696k, False: 4.82M] ------------------ 449| 696k| if (candidate == word) ------------------ | Branch (449:9): [True: 15.5k, False: 680k] ------------------ 450| 15.5k| return wlst.size(); 451| 680k| const int cwrd = std::find(wlst.begin(), wlst.end(), candidate) != wlst.end() ? 0 : 1; ------------------ | Branch (451:22): [True: 0, False: 680k] ------------------ 452| 680k| if ((cwrd) && checkword(candidate, cpdsuggest, timer, timelimit)) { ------------------ | Branch (452:9): [True: 680k, False: 0] | Branch (452:19): [True: 0, False: 680k] ------------------ 453| 0| if (wlst.size() < maxSug) { ------------------ | Branch (453:11): [True: 0, False: 0] ------------------ 454| 0| wlst.push_back(candidate); 455| 0| } 456| 0| } 457| 680k| return wlst.size(); 458| 696k| } 459| | 460| 4.82M| if (depth > 0x3F00) { ------------------ | Branch (460:7): [True: 0, False: 4.82M] ------------------ 461| 0| *timer = 0; 462| 0| return wlst.size(); 463| 0| } 464| | 465| 4.82M| int in_map = 0; 466| 19.2M| for (size_t j = 0; j < maptable.size(); ++j) { ------------------ | Branch (466:22): [True: 14.4M, False: 4.82M] ------------------ 467| 53.0M| for (size_t k = 0; k < maptable[j].size(); ++k) { ------------------ | Branch (467:24): [True: 38.5M, False: 14.4M] ------------------ 468| 38.5M| size_t len = maptable[j][k].size(); 469| 38.5M| if (len && word.compare(wn, len, maptable[j][k]) == 0) { ------------------ | Branch (469:11): [True: 38.5M, False: 0] | Branch (469:18): [True: 340k, False: 38.2M] ------------------ 470| 340k| in_map = 1; 471| 340k| size_t cn = candidate.size(); 472| 1.36M| for (size_t l = 0; l < maptable[j].size(); ++l) { ------------------ | Branch (472:28): [True: 1.02M, False: 340k] ------------------ 473| 1.02M| candidate.resize(cn); 474| 1.02M| candidate.append(maptable[j][l]); 475| 1.02M| map_related(word, candidate, wn + len, wlst, 476| 1.02M| cpdsuggest, maptable, timer, timelimit, depth + 1, info); 477| 1.02M| if (!(*timer)) ------------------ | Branch (477:15): [True: 110, False: 1.02M] ------------------ 478| 110| return wlst.size(); 479| 1.02M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) { ------------------ | | 105| 1.02M|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (479:15): [True: 6, False: 1.02M] ------------------ 480| 6| *timer = 0; 481| 6| return wlst.size(); 482| 6| } 483| 1.02M| } 484| 340k| } 485| 38.5M| } 486| 14.4M| } 487| 4.82M| if (!in_map) { ------------------ | Branch (487:7): [True: 4.48M, False: 340k] ------------------ 488| 4.48M| candidate.push_back(word[wn]); 489| 4.48M| map_related(word, candidate, wn + 1, wlst, cpdsuggest, 490| 4.48M| maptable, timer, timelimit, depth + 1, info); 491| 4.48M| } 492| 4.82M| return wlst.size(); 493| 4.82M|} _ZN10SuggestMgr9replcharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 499| 421k| int cpdsuggest, int& info) { 500| 421k| std::string candidate; 501| 421k| int wl = word.size(); 502| 421k| if (wl < 2 || !pAMgr) ------------------ | Branch (502:7): [True: 35.2k, False: 386k] | Branch (502:17): [True: 0, False: 386k] ------------------ 503| 35.2k| return wlst.size(); 504| 386k| const std::vector& reptable = pAMgr->get_reptable(); 505| 386k| auto replchars_start = std::chrono::steady_clock::now(); 506| 386k| for (const auto& entry : reptable) { ------------------ | Branch (506:26): [True: 79.9k, False: 386k] ------------------ 507| 79.9k| size_t r = 0; 508| | // search every occurence of the pattern in the word 509| 79.9k| while ((r = word.find(entry.pattern, r)) != std::string::npos) { ------------------ | Branch (509:12): [True: 21, False: 79.9k] ------------------ 510| 21| if (std::chrono::steady_clock::now() - replchars_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 21|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (510:11): [True: 0, False: 21] ------------------ 511| 0| return wlst.size(); 512| 21| int type = (r == 0) ? 1 : 0; ------------------ | Branch (512:18): [True: 0, False: 21] ------------------ 513| 21| if (r + entry.pattern.size() == word.size()) ------------------ | Branch (513:11): [True: 0, False: 21] ------------------ 514| 0| type += 2; 515| 21| while (type && entry.outstrings[type].empty()) ------------------ | Branch (515:14): [True: 0, False: 21] | 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| 21| const std::string&out = entry.outstrings[type]; 518| 21| if (out.empty()) { ------------------ | Branch (518:11): [True: 0, False: 21] ------------------ 519| 0| ++r; 520| 0| continue; 521| 0| } 522| 21| candidate.assign(word, 0, r); 523| 21| candidate.append(entry.outstrings[type]); 524| 21| candidate.append(word, r + entry.pattern.size(), std::string::npos); 525| 21| size_t sp = candidate.find(' '); 526| 21| size_t oldns = wlst.size(); 527| 21| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 528| 21| if (oldns < wlst.size()) { ------------------ | Branch (528:11): [True: 0, False: 21] ------------------ 529| | // REP suggestions are the best, don't search other type of suggestions 530| 0| info |= SPELL_BEST_SUG; ------------------ | | 86| 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| 21| if (sp != std::string::npos) { ------------------ | Branch (534:11): [True: 18, False: 3] ------------------ 535| 18| size_t prev = 0; 536| 36| while (sp != std::string::npos) { ------------------ | Branch (536:16): [True: 18, False: 18] ------------------ 537| 18| std::string prev_chunk = candidate.substr(prev, sp - prev); 538| 18| if (checkword(prev_chunk, 0, nullptr, nullptr)) { ------------------ | Branch (538:15): [True: 0, False: 18] ------------------ 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| 18| prev = sp + 1; 547| 18| sp = candidate.find(' ', prev); 548| 18| } 549| 18| } 550| 21| r++; // search for the next letter 551| 21| } 552| 79.9k| } 553| 386k| return wlst.size(); 554| 386k|} _ZN10SuggestMgr14doubletwocharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 563| 264k| int cpdsuggest, int& info) { 564| 264k| size_t wl = word.size(); 565| 264k| if (wl < 5 || !pAMgr) ------------------ | Branch (565:7): [True: 59.3k, False: 204k] | Branch (565:17): [True: 0, False: 204k] ------------------ 566| 59.3k| return wlst.size(); 567| | 568| 204k| int state = 0; 569| 5.21M| for (size_t i = 2; i < wl; ++i) { ------------------ | Branch (569:22): [True: 5.01M, False: 204k] ------------------ 570| 5.01M| if (word[i] == word[i - 2]) { ------------------ | Branch (570:9): [True: 1.24M, False: 3.76M] ------------------ 571| 1.24M| state++; 572| 1.24M| if (state == 3 || (state == 2 && i >= 4)) { ------------------ | Branch (572:11): [True: 6.58k, False: 1.23M] | Branch (572:26): [True: 439k, False: 800k] | Branch (572:40): [True: 429k, False: 10.1k] ------------------ 573| 435k| auto word_iter = word.begin(); 574| 435k| std::string candidate(word_iter, word_iter + i - 1); 575| 435k| candidate.insert(candidate.end(), word_iter + i + 1, word.end()); 576| 435k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 577| 435k| state = 0; 578| 435k| } 579| 3.76M| } else { 580| 3.76M| state = 0; 581| 3.76M| } 582| 5.01M| } 583| 204k| return wlst.size(); 584| 264k|} _ZN10SuggestMgr18doubletwochars_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 593| 157k| int cpdsuggest, int& info) { 594| 157k| size_t wl = word.size(); 595| 157k| int state = 0; 596| 157k| if (wl < 5 || !pAMgr) ------------------ | Branch (596:7): [True: 57.9k, False: 99.6k] | Branch (596:17): [True: 0, False: 99.6k] ------------------ 597| 57.9k| return wlst.size(); 598| 1.70M| for (size_t i = 2; i < wl; ++i) { ------------------ | Branch (598:22): [True: 1.60M, False: 99.6k] ------------------ 599| 1.60M| if (word[i] == word[i - 2]) { ------------------ | Branch (599:9): [True: 469k, False: 1.13M] ------------------ 600| 469k| state++; 601| 469k| if (state == 3 || (state == 2 && i >= 4)) { ------------------ | Branch (601:11): [True: 4.02k, False: 465k] | Branch (601:26): [True: 160k, False: 305k] | Branch (601:40): [True: 153k, False: 6.52k] ------------------ 602| 157k| auto word_iter = word.begin(); 603| 157k| std::vector candidate_utf(word_iter, word_iter + i - 1); 604| 157k| candidate_utf.insert(candidate_utf.end(), word_iter + i + 1, word.end()); 605| 157k| std::string candidate; 606| 157k| u16_u8(candidate, candidate_utf); 607| 157k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 608| 157k| state = 0; 609| 157k| } 610| 1.13M| } else { 611| 1.13M| state = 0; 612| 1.13M| } 613| 1.60M| } 614| 99.6k| return wlst.size(); 615| 157k|} _ZN10SuggestMgr10badcharkeyERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 621| 264k| int cpdsuggest, int& info) { 622| 264k| 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| 5.82M| for (size_t i = 0, wl = candidate.size(); i < wl; ++i) { ------------------ | Branch (626:45): [True: 5.56M, False: 264k] ------------------ 627| 5.56M| char tmpc = candidate[i]; 628| | // check with uppercase letters 629| 5.56M| candidate[i] = csconv[((unsigned char)tmpc)].cupper; 630| 5.56M| if (tmpc != candidate[i]) { ------------------ | Branch (630:9): [True: 1.37M, False: 4.18M] ------------------ 631| 1.37M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 632| 1.37M| candidate[i] = tmpc; 633| 1.37M| } 634| | // check neighbor characters in keyboard string 635| 5.56M| if (ckey.empty()) ------------------ | Branch (635:9): [True: 0, False: 5.56M] ------------------ 636| 0| continue; 637| 5.56M| size_t loc = 0; 638| 145M| while ((loc < ckeyl) && ckey[loc] != tmpc) ------------------ | Branch (638:12): [True: 141M, False: 4.61M] | Branch (638:29): [True: 140M, False: 946k] ------------------ 639| 140M| ++loc; 640| 6.55M| while (loc < ckeyl) { ------------------ | Branch (640:12): [True: 999k, False: 5.56M] ------------------ 641| | // a long keyboard string can hold many neighbours for this 642| | // character, so give up once the overall time budget is spent 643| 999k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 999k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (643:11): [True: 0, False: 999k] ------------------ 644| 0| return wlst.size(); 645| 999k| if ((loc > 0) && ckey[loc - 1] != '|') { ------------------ | Branch (645:11): [True: 822k, False: 176k] | Branch (645:24): [True: 781k, False: 41.3k] ------------------ 646| 781k| candidate[i] = ckey[loc - 1]; 647| 781k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 648| 781k| } 649| 999k| if (((loc + 1) < ckeyl) && (ckey[loc + 1] != '|')) { ------------------ | Branch (649:11): [True: 924k, False: 74.8k] | Branch (649:34): [True: 839k, False: 84.3k] ------------------ 650| 839k| candidate[i] = ckey[loc + 1]; 651| 839k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 652| 839k| } 653| 15.5M| do { 654| 15.5M| loc++; 655| 15.5M| } while ((loc < ckeyl) && ckey[loc] != tmpc); ------------------ | Branch (655:16): [True: 14.6M, False: 946k] | Branch (655:33): [True: 14.5M, False: 52.2k] ------------------ 656| 999k| } 657| 5.56M| candidate[i] = tmpc; 658| 5.56M| } 659| 264k| return wlst.size(); 660| 264k|} _ZN10SuggestMgr14badcharkey_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 666| 157k| int cpdsuggest, int& info) { 667| 157k| std::string candidate; 668| 157k| 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| 2.11M| for (size_t i = 0, wl = word.size(); i < wl; ++i) { ------------------ | Branch (671:40): [True: 1.95M, False: 157k] ------------------ 672| 1.95M| w_char tmpc = candidate_utf[i]; 673| | // check with uppercase letters 674| 1.95M| candidate_utf[i] = upper_utf(candidate_utf[i], 1); 675| 1.95M| if (tmpc != candidate_utf[i]) { ------------------ | Branch (675:9): [True: 449k, False: 1.50M] ------------------ 676| 449k| u16_u8(candidate, candidate_utf); 677| 449k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 678| 449k| candidate_utf[i] = tmpc; 679| 449k| } 680| | // check neighbor characters in keyboard string 681| 1.95M| if (ckey_utf.empty()) ------------------ | Branch (681:9): [True: 0, False: 1.95M] ------------------ 682| 0| continue; 683| 1.95M| size_t loc = 0; 684| 48.9M| while ((loc < ckeyl) && ckey_utf[loc] != tmpc) ------------------ | Branch (684:12): [True: 47.4M, False: 1.49M] | Branch (684:29): [True: 47.0M, False: 459k] ------------------ 685| 47.0M| ++loc; 686| 2.42M| while (loc < ckeyl) { ------------------ | Branch (686:12): [True: 472k, False: 1.95M] ------------------ 687| | // a long keyboard string can hold many neighbours for this 688| | // character, so give up once the overall time budget is spent 689| 472k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 472k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (689:11): [True: 0, False: 472k] ------------------ 690| 0| return wlst.size(); 691| 472k| if ((loc > 0) && ckey_utf[loc - 1] != W_VLINE) { ------------------ | Branch (691:11): [True: 365k, False: 107k] | Branch (691:24): [True: 365k, False: 0] ------------------ 692| 365k| candidate_utf[i] = ckey_utf[loc - 1]; 693| 365k| u16_u8(candidate, candidate_utf); 694| 365k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 695| 365k| } 696| 472k| if (((loc + 1) < ckeyl) && (ckey_utf[loc + 1] != W_VLINE)) { ------------------ | Branch (696:11): [True: 427k, False: 44.5k] | Branch (696:34): [True: 427k, False: 0] ------------------ 697| 427k| candidate_utf[i] = ckey_utf[loc + 1]; 698| 427k| u16_u8(candidate, candidate_utf); 699| 427k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 700| 427k| } 701| 7.67M| do { 702| 7.67M| loc++; 703| 7.67M| } while ((loc < ckeyl) && ckey_utf[loc] != tmpc); ------------------ | Branch (703:16): [True: 7.21M, False: 459k] | Branch (703:33): [True: 7.20M, False: 12.7k] ------------------ 704| 472k| } 705| 1.95M| candidate_utf[i] = tmpc; 706| 1.95M| } 707| 157k| return wlst.size(); 708| 157k|} _ZN10SuggestMgr7badcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 713| 264k| int cpdsuggest, int& info) { 714| 264k| std::string candidate(word); 715| 264k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 716| 264k| int timer = MINTIMER; ------------------ | | 107| 264k|#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| 264k| for (size_t j = 0; j < ctryl; ++j) { ------------------ | Branch (719:22): [True: 0, False: 264k] ------------------ 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| 264k| return wlst.size(); 732| 264k|} _ZN10SuggestMgr11badchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 737| 157k| int cpdsuggest, int& info) { 738| 157k| std::vector candidate_utf(word); 739| 157k| std::string candidate; 740| 157k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 741| 157k| int timer = MINTIMER; ------------------ | | 107| 157k|#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| 176k| for (size_t j = 0; j < ctryl; ++j) { ------------------ | Branch (744:22): [True: 18.6k, False: 157k] ------------------ 745| 250k| for (auto aI = candidate_utf.rbegin(), aEnd = candidate_utf.rend(); aI != aEnd; ++aI) { ------------------ | Branch (745:73): [True: 231k, False: 18.6k] ------------------ 746| 231k| w_char tmpc = *aI; 747| 231k| if (tmpc == ctry_utf[j]) ------------------ | Branch (747:11): [True: 0, False: 231k] ------------------ 748| 0| continue; 749| 231k| *aI = ctry_utf[j]; 750| 231k| u16_u8(candidate, candidate_utf); 751| 231k| testsug(wlst, candidate, cpdsuggest, &timer, &timelimit, info); 752| 231k| if (!timer) ------------------ | Branch (752:11): [True: 0, False: 231k] ------------------ 753| 0| return wlst.size(); 754| 231k| *aI = tmpc; 755| 231k| } 756| 18.6k| } 757| 157k| return wlst.size(); 758| 157k|} _ZN10SuggestMgr13extrachar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 763| 157k| int cpdsuggest, int& info) { 764| 157k| std::vector candidate_utf(word); 765| 157k| if (candidate_utf.size() < 2) ------------------ | Branch (765:7): [True: 16.2k, False: 141k] ------------------ 766| 16.2k| return wlst.size(); 767| | // try omitting one char of word at a time 768| 2.07M| for (size_t i = 0; i < candidate_utf.size(); ++i) { ------------------ | Branch (768:22): [True: 1.93M, False: 141k] ------------------ 769| 1.93M| size_t index = candidate_utf.size() - 1 - i; 770| 1.93M| w_char tmpc = candidate_utf[index]; 771| 1.93M| candidate_utf.erase(candidate_utf.begin() + index); 772| 1.93M| std::string candidate; 773| 1.93M| u16_u8(candidate, candidate_utf); 774| 1.93M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 775| 1.93M| candidate_utf.insert(candidate_utf.begin() + index, tmpc); 776| 1.93M| } 777| 141k| return wlst.size(); 778| 157k|} _ZN10SuggestMgr9extracharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 783| 264k| int cpdsuggest, int& info) { 784| 264k| std::string candidate(word); 785| 264k| if (candidate.size() < 2) ------------------ | Branch (785:7): [True: 19.5k, False: 244k] ------------------ 786| 19.5k| return wlst.size(); 787| | // try omitting one char of word at a time 788| 5.78M| for (size_t i = 0; i < candidate.size(); ++i) { ------------------ | Branch (788:22): [True: 5.54M, False: 244k] ------------------ 789| 5.54M| size_t index = candidate.size() - 1 - i; 790| 5.54M| char tmpc = candidate[index]; 791| 5.54M| candidate.erase(candidate.begin() + index); 792| 5.54M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 793| 5.54M| candidate.insert(candidate.begin() + index, tmpc); 794| 5.54M| } 795| 244k| return wlst.size(); 796| 264k|} _ZN10SuggestMgr10forgotcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 801| 264k| int cpdsuggest, int& info) { 802| 264k| std::string candidate(word); 803| 264k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 804| 264k| int timer = MINTIMER; ------------------ | | 107| 264k|#define MINTIMER 100 ------------------ 805| | 806| | // try inserting a tryme character before every letter (and the null 807| | // terminator) 808| 264k| for (size_t k = 0; k < ctryl; ++k) { ------------------ | Branch (808:22): [True: 0, False: 264k] ------------------ 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| 264k| return wlst.size(); 819| 264k|} _ZN10SuggestMgr14forgotchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 824| 157k| int cpdsuggest, int& info) { 825| 157k| std::vector candidate_utf(word); 826| 157k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 827| 157k| int timer = MINTIMER; ------------------ | | 107| 157k|#define MINTIMER 100 ------------------ 828| | 829| | // try inserting a tryme character at the end of the word and before every 830| | // letter 831| 176k| for (size_t k = 0; k < ctryl; ++k) { ------------------ | Branch (831:22): [True: 18.6k, False: 157k] ------------------ 832| 268k| for (size_t i = 0; i <= candidate_utf.size(); ++i) { ------------------ | Branch (832:24): [True: 250k, False: 18.6k] ------------------ 833| 250k| size_t index = candidate_utf.size() - i; 834| 250k| candidate_utf.insert(candidate_utf.begin() + index, ctry_utf[k]); 835| 250k| std::string candidate; 836| 250k| u16_u8(candidate, candidate_utf); 837| 250k| testsug(wlst, candidate, cpdsuggest, &timer, &timelimit, info); 838| 250k| if (!timer) ------------------ | Branch (838:11): [True: 0, False: 250k] ------------------ 839| 0| return wlst.size(); 840| 250k| candidate_utf.erase(candidate_utf.begin() + index); 841| 250k| } 842| 18.6k| } 843| 157k| return wlst.size(); 844| 157k|} _ZN10SuggestMgr8twowordsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_ibRi: 854| 421k| bool good, int& info) { 855| 421k| int c2, forbidden = 0, cwrd, wl = word.size(); 856| 421k| if (wl < 3) ------------------ | Branch (856:7): [True: 58.6k, False: 363k] ------------------ 857| 58.6k| return false; 858| | 859| 363k| if (langnum == LANG_hu) ------------------ | Branch (859:7): [True: 14.7k, False: 348k] ------------------ 860| 14.7k| forbidden = check_forbidden(word); 861| | 862| 363k| char* candidate = new char[wl + 2]; 863| 363k| memcpy(candidate + 1, word.data(), wl); 864| 363k| 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| 4.80M| for (char* p = candidate + 1; p[1] != '\0'; p++) { ------------------ | Branch (868:33): [True: 4.47M, False: 323k] ------------------ 869| 4.47M| p[-1] = *p; 870| | // go to end of the UTF-8 character 871| 4.76M| while (utf8 && is_utf8_cont(p[1])) { ------------------ | Branch (871:12): [True: 1.53M, False: 3.22M] | Branch (871:20): [True: 283k, False: 1.24M] ------------------ 872| 283k| *p = p[1]; 873| 283k| p++; 874| 283k| } 875| 4.47M| if (utf8 && p[1] == '\0') ------------------ | Branch (875:9): [True: 1.24M, False: 3.22M] | Branch (875:17): [True: 39.8k, False: 1.20M] ------------------ 876| 39.8k| 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| 4.43M| *p = ' '; 886| 4.43M| if (!cpdsuggest && checkword(candidate, cpdsuggest, nullptr, nullptr)) { ------------------ | Branch (886:9): [True: 1.48M, False: 2.95M] | Branch (886:9): [True: 1.48k, False: 4.43M] | Branch (886:24): [True: 1.48k, False: 1.47M] ------------------ 887| | // best solution 888| 1.48k| info |= SPELL_BEST_SUG; ------------------ | | 86| 1.48k|#define SPELL_BEST_SUG (1 << 8) // limit suggestions for the best ones, i.e. ph: ------------------ 889| | 890| | // remove not word pair suggestions 891| 1.48k| if (!good) { ------------------ | Branch (891:11): [True: 128, False: 1.36k] ------------------ 892| 128| good = true; 893| 128| wlst.clear(); 894| 128| } 895| | 896| 1.48k| wlst.insert(wlst.begin(), candidate); 897| 1.48k| } 898| | 899| | // word pairs with dash? 900| 4.43M| if (lang_with_dash_usage) { ------------------ | Branch (900:9): [True: 0, False: 4.43M] ------------------ 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; ------------------ | | 86| 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| 4.43M| if (wlst.size() < maxSug && !nosplitsugs && !good) { ------------------ | Branch (916:9): [True: 4.43M, False: 682] | Branch (916:33): [True: 4.43M, False: 0] | Branch (916:49): [True: 4.43M, False: 807] ------------------ 917| 4.43M| *p = '\0'; 918| 4.43M| int c1 = checkword(candidate, cpdsuggest, nullptr, nullptr); 919| 4.43M| if (c1) { ------------------ | Branch (919:11): [True: 25.6k, False: 4.41M] ------------------ 920| 25.6k| c2 = checkword((p + 1), cpdsuggest, nullptr, nullptr); 921| 25.6k| if (c2) { ------------------ | Branch (921:13): [True: 643, False: 24.9k] ------------------ 922| | // spec. Hungarian code (TODO need a better compound word support) 923| 643| if ((langnum == LANG_hu) && !forbidden && ------------------ | Branch (923:15): [True: 16, False: 627] | Branch (923:39): [True: 16, False: 0] ------------------ 924| | // if 3 repeating letter, use - instead of space 925| 16| (((p[-1] == p[1]) && ------------------ | Branch (925:17): [True: 5, False: 11] ------------------ 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| 16| ((c1 == 3) && (c2 >= 2)))) ------------------ | Branch (928:16): [True: 0, False: 16] | Branch (928:29): [True: 0, False: 0] ------------------ 929| 0| *p = '-'; 930| 643| else 931| 643| *p = ' '; 932| | 933| 643| cwrd = std::find(wlst.begin(), wlst.end(), candidate) != wlst.end() ? 0 : 1; ------------------ | Branch (933:18): [True: 0, False: 643] ------------------ 934| | 935| 643| if (cwrd && (wlst.size() < maxSug)) ------------------ | Branch (935:15): [True: 643, False: 0] | Branch (935:23): [True: 643, False: 0] ------------------ 936| 643| 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| 643| if ( !nosplitsugs && lang_with_dash_usage && ------------------ | Branch (940:16): [True: 643, False: 0] | Branch (940:32): [True: 0, False: 643] ------------------ 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| 643| } 954| 25.6k| } 955| 4.43M| } 956| 4.43M| } 957| 363k| delete[] candidate; 958| 363k| return good; 959| 421k|} _ZN10SuggestMgr8swapcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 964| 264k| int cpdsuggest, int& info) { 965| 264k| if (word.size() < 2) ------------------ | Branch (965:7): [True: 19.5k, False: 244k] ------------------ 966| 19.5k| return wlst.size(); 967| | 968| 244k| std::string candidate(word); 969| | 970| | // try swapping adjacent chars one by one 971| 5.54M| for (size_t i = 0; i < candidate.size() - 1; ++i) { ------------------ | Branch (971:22): [True: 5.29M, False: 244k] ------------------ 972| 5.29M| std::swap(candidate[i], candidate[i+1]); 973| 5.29M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 974| 5.29M| std::swap(candidate[i], candidate[i+1]); 975| 5.29M| } 976| | 977| | // try double swaps for short words 978| | // ahev -> have, owudl -> would 979| 244k| if (candidate.size() == 4 || candidate.size() == 5) { ------------------ | Branch (979:7): [True: 14.7k, False: 229k] | Branch (979:32): [True: 9.94k, False: 219k] ------------------ 980| 24.7k| candidate[0] = word[1]; 981| 24.7k| candidate[1] = word[0]; 982| 24.7k| candidate[2] = word[2]; 983| 24.7k| candidate[candidate.size() - 2] = word[candidate.size() - 1]; 984| 24.7k| candidate[candidate.size() - 1] = word[candidate.size() - 2]; 985| 24.7k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 986| 24.7k| if (candidate.size() == 5) { ------------------ | Branch (986:9): [True: 9.94k, False: 14.7k] ------------------ 987| 9.94k| candidate[0] = word[0]; 988| 9.94k| candidate[1] = word[2]; 989| 9.94k| candidate[2] = word[1]; 990| 9.94k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 991| 9.94k| } 992| 24.7k| } 993| | 994| 244k| return wlst.size(); 995| 264k|} _ZN10SuggestMgr12swapchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 1000| 157k| int cpdsuggest, int& info) { 1001| 157k| if (word.size() < 2) ------------------ | Branch (1001:7): [True: 16.2k, False: 141k] ------------------ 1002| 16.2k| return wlst.size(); 1003| | 1004| 141k| std::vector candidate_utf(word); 1005| | 1006| 141k| std::string candidate; 1007| | // try swapping adjacent chars one by one 1008| 1.93M| for (size_t i = 0; i < candidate_utf.size() - 1; ++i) { ------------------ | Branch (1008:22): [True: 1.79M, False: 141k] ------------------ 1009| 1.79M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 1.79M|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (1009:9): [True: 0, False: 1.79M] ------------------ 1010| 0| return wlst.size(); 1011| 1.79M| std::swap(candidate_utf[i], candidate_utf[i+1]); 1012| 1.79M| u16_u8(candidate, candidate_utf); 1013| 1.79M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1014| 1.79M| std::swap(candidate_utf[i], candidate_utf[i+1]); 1015| 1.79M| } 1016| | 1017| | // try double swaps for short words 1018| | // ahev -> have, owudl -> would, suodn -> sound 1019| 141k| if (candidate_utf.size() == 4 || candidate_utf.size() == 5) { ------------------ | Branch (1019:7): [True: 19.0k, False: 122k] | Branch (1019:36): [True: 8.75k, False: 113k] ------------------ 1020| 27.8k| candidate_utf[0] = word[1]; 1021| 27.8k| candidate_utf[1] = word[0]; 1022| 27.8k| candidate_utf[2] = word[2]; 1023| 27.8k| candidate_utf[candidate_utf.size() - 2] = word[candidate_utf.size() - 1]; 1024| 27.8k| candidate_utf[candidate_utf.size() - 1] = word[candidate_utf.size() - 2]; 1025| 27.8k| u16_u8(candidate, candidate_utf); 1026| 27.8k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1027| 27.8k| if (candidate_utf.size() == 5) { ------------------ | Branch (1027:9): [True: 8.75k, False: 19.0k] ------------------ 1028| 8.75k| candidate_utf[0] = word[0]; 1029| 8.75k| candidate_utf[1] = word[2]; 1030| 8.75k| candidate_utf[2] = word[1]; 1031| 8.75k| u16_u8(candidate, candidate_utf); 1032| 8.75k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1033| 8.75k| } 1034| 27.8k| } 1035| 141k| return wlst.size(); 1036| 141k|} _ZN10SuggestMgr12longswapcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 1041| 264k| int cpdsuggest, int& info) { 1042| 264k| std::string candidate(word); 1043| | // try swapping not adjacent chars one by one 1044| 5.82M| for (auto p = candidate.begin(); p < candidate.end(); ++p) { ------------------ | Branch (1044:36): [True: 5.56M, False: 264k] ------------------ 1045| 211M| for (auto q = candidate.begin(); q < candidate.end(); ++q) { ------------------ | Branch (1045:38): [True: 205M, False: 5.56M] ------------------ 1046| 205M| const auto distance = std::abs(std::distance(q, p)); 1047| 205M| if (distance > 1 && distance <= MAX_CHAR_DISTANCE && *p != *q) { ------------------ | | 84| 395M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1047:11): [True: 189M, False: 16.1M] | Branch (1047:27): [True: 28.9M, False: 160M] | Branch (1047:60): [True: 22.1M, False: 6.84M] ------------------ 1048| 22.1M| std::swap(*p, *q); 1049| 22.1M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1050| 22.1M| std::swap(*p, *q); 1051| 22.1M| } 1052| 205M| } 1053| 5.56M| } 1054| 264k| return wlst.size(); 1055| 264k|} _ZN10SuggestMgr16longswapchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 1060| 157k| int cpdsuggest, int& info) { 1061| 157k| std::vector candidate_utf(word); 1062| | // try swapping not adjacent chars 1063| 2.11M| for (auto p = candidate_utf.begin(); p < candidate_utf.end(); ++p) { ------------------ | Branch (1063:40): [True: 1.95M, False: 157k] ------------------ 1064| 52.3M| for (auto q = candidate_utf.begin(); q < candidate_utf.end(); ++q) { ------------------ | Branch (1064:42): [True: 50.4M, False: 1.95M] ------------------ 1065| 50.4M| const auto distance = std::abs(std::distance(q, p)); 1066| 50.4M| if (distance > 1 && distance <= MAX_CHAR_DISTANCE && *p != *q) { ------------------ | | 84| 95.3M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1066:11): [True: 44.8M, False: 5.54M] | Branch (1066:27): [True: 9.17M, False: 35.7M] | Branch (1066:60): [True: 6.55M, False: 2.62M] ------------------ 1067| 6.55M| std::swap(*p, *q); 1068| 6.55M| std::string candidate; 1069| 6.55M| u16_u8(candidate, candidate_utf); 1070| 6.55M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1071| 6.55M| std::swap(*p, *q); 1072| 6.55M| } 1073| 50.4M| } 1074| 1.95M| } 1075| 157k| return wlst.size(); 1076| 157k|} _ZN10SuggestMgr8movecharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 1081| 264k| int cpdsuggest, int& info) { 1082| 264k| if (word.size() < 2) ------------------ | Branch (1082:7): [True: 19.5k, False: 244k] ------------------ 1083| 19.5k| return wlst.size(); 1084| | 1085| 244k| std::string candidate(word); 1086| | 1087| | // try moving a char 1088| 5.78M| for (auto p = candidate.begin(); p < candidate.end(); ++p) { ------------------ | Branch (1088:36): [True: 5.54M, False: 244k] ------------------ 1089| 25.3M| for (auto q = p + 1; q < candidate.end() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 24.1M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1089:26): [True: 24.1M, False: 1.14M] | Branch (1089:26): [True: 19.7M, False: 5.54M] | Branch (1089:49): [True: 19.7M, False: 4.39M] ------------------ 1090| 19.7M| std::swap(*q, *(q - 1)); 1091| 19.7M| if (std::distance(p, q) < 2) ------------------ | Branch (1091:11): [True: 5.29M, False: 14.4M] ------------------ 1092| 5.29M| continue; // omit swap char 1093| 14.4M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1094| 14.4M| } 1095| 5.54M| const auto word_iter = word.begin(); 1096| 5.54M| std::copy_n(word_iter, candidate.size(), candidate.begin()); 1097| 5.54M| } 1098| | 1099| 5.54M| for (auto p = candidate.rbegin(), pEnd = candidate.rend() - 1; p != pEnd; ++p) { ------------------ | Branch (1099:66): [True: 5.29M, False: 244k] ------------------ 1100| 25.0M| for (auto q = p + 1, qEnd = candidate.rend(); q != qEnd && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 24.1M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1100:51): [True: 24.1M, False: 899k] | Branch (1100:64): [True: 19.7M, False: 4.39M] ------------------ 1101| 19.7M| std::swap(*q, *(q - 1)); 1102| 19.7M| if (std::distance(p, q) < 2) ------------------ | Branch (1102:11): [True: 5.29M, False: 14.4M] ------------------ 1103| 5.29M| continue; // omit swap char 1104| 14.4M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1105| 14.4M| } 1106| 5.29M| const auto word_iter = word.begin(); 1107| 5.29M| std::copy_n(word_iter, candidate.size(), candidate.begin()); 1108| 5.29M| } 1109| | 1110| 244k| return wlst.size(); 1111| 264k|} _ZN10SuggestMgr12movechar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 1116| 157k| int cpdsuggest, int& info) { 1117| 157k| if (word.size() < 2) ------------------ | Branch (1117:7): [True: 16.2k, False: 141k] ------------------ 1118| 16.2k| return wlst.size(); 1119| | 1120| 141k| std::vector candidate_utf(word); 1121| | 1122| | // try moving a char 1123| 2.07M| for (auto p = candidate_utf.begin(); p < candidate_utf.end(); ++p) { ------------------ | Branch (1123:40): [True: 1.93M, False: 141k] ------------------ 1124| 8.31M| for (auto q = p + 1; q < candidate_utf.end() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 7.68M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1124:26): [True: 7.68M, False: 629k] | Branch (1124:26): [True: 6.38M, False: 1.93M] | Branch (1124:53): [True: 6.38M, False: 1.30M] ------------------ 1125| 6.38M| std::swap(*q, *(q - 1)); 1126| 6.38M| if (std::distance(p, q) < 2) ------------------ | Branch (1126:11): [True: 1.79M, False: 4.58M] ------------------ 1127| 1.79M| continue; // omit swap char 1128| 4.58M| std::string candidate; 1129| 4.58M| u16_u8(candidate, candidate_utf); 1130| 4.58M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1131| 4.58M| } 1132| 1.93M| const auto word_iter = word.begin(); 1133| 1.93M| std::copy_n(word_iter, candidate_utf.size(), candidate_utf.begin()); 1134| 1.93M| } 1135| | 1136| 2.07M| for (auto p = candidate_utf.rbegin(); p < candidate_utf.rend(); ++p) { ------------------ | Branch (1136:41): [True: 1.93M, False: 141k] ------------------ 1137| 8.31M| for (auto q = p + 1; q < candidate_utf.rend() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 7.68M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1137:26): [True: 7.68M, False: 629k] | Branch (1137:26): [True: 6.38M, False: 1.93M] | Branch (1137:54): [True: 6.38M, False: 1.30M] ------------------ 1138| 6.38M| std::swap(*q, *(q - 1)); 1139| 6.38M| if (std::distance(p, q) < 2) ------------------ | Branch (1139:11): [True: 1.79M, False: 4.58M] ------------------ 1140| 1.79M| continue; // omit swap char 1141| 4.58M| std::string candidate; 1142| 4.58M| u16_u8(candidate, candidate_utf); 1143| 4.58M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1144| 4.58M| } 1145| 1.93M| const auto word_iter = word.begin(); 1146| 1.93M| std::copy_n(word_iter, candidate_utf.size(), candidate_utf.begin()); 1147| 1.93M| } 1148| | 1149| 141k| return wlst.size(); 1150| 157k|} _ZN10SuggestMgr9ngsuggestERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEEPKcRKNS1_INS0_10unique_ptrI7HashMgrNS0_14default_deleteISE_EEEENS5_ISH_EEEEi: 1185| 62.4k| int captype) { 1186| 62.4k| 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| 62.4k| struct hentry* roots[MAX_ROOTS]; 1191| 62.4k| char* rootsphon[MAX_ROOTS]; 1192| 62.4k| int scores[MAX_ROOTS]; 1193| 62.4k| int scoresphon[MAX_ROOTS]; 1194| 6.30M| for (int i = 0; i < MAX_ROOTS; i++) { ------------------ | | 74| 6.30M|#define MAX_ROOTS 100 ------------------ | Branch (1194:19): [True: 6.24M, False: 62.4k] ------------------ 1195| 6.24M| roots[i] = nullptr; 1196| 6.24M| scores[i] = -100 * i; 1197| 6.24M| rootsphon[i] = nullptr; 1198| 6.24M| scoresphon[i] = -100 * i; 1199| 6.24M| } 1200| 62.4k| bool has_roots = false; 1201| 62.4k| bool has_rootsphon = false; 1202| 62.4k| lp = MAX_ROOTS - 1; ------------------ | | 74| 62.4k|#define MAX_ROOTS 100 ------------------ 1203| 62.4k| lpphon = MAX_ROOTS - 1; ------------------ | | 74| 62.4k|#define MAX_ROOTS 100 ------------------ 1204| 62.4k| int low = NGRAM_LOWERING; ------------------ | | 83| 62.4k|#define NGRAM_LOWERING (1 << 2) ------------------ 1205| | 1206| 62.4k| std::string w2; 1207| 62.4k| const char* word = w; 1208| | 1209| 62.4k| int nc; 1210| | // word reversing wrapper for complex prefixes 1211| 62.4k| if (complexprefixes) { ------------------ | Branch (1211:7): [True: 3.58k, False: 58.8k] ------------------ 1212| 3.58k| w2.assign(w); 1213| 3.58k| if (utf8) ------------------ | Branch (1213:9): [True: 0, False: 3.58k] ------------------ 1214| 0| reverseword_utf(w2); 1215| 3.58k| else 1216| 3.58k| reverseword(w2); 1217| 3.58k| word = w2.c_str(); 1218| 3.58k| nc = (int)w2.size(); 1219| 58.8k| } else { 1220| 58.8k| nc = (int)strlen(word); 1221| 58.8k| } 1222| | 1223| 62.4k| std::vector u8; 1224| 62.4k| int n = (utf8) ? u8_u16(u8, word) : nc; ------------------ | Branch (1224:11): [True: 26.0k, False: 36.4k] ------------------ 1225| | 1226| | // set character based ngram suggestion for words with non-BMP Unicode 1227| | // characters 1228| 62.4k| const struct cs_info* origconv = csconv; 1229| 62.4k| if (n == -1) { ------------------ | Branch (1229:7): [True: 1.72k, False: 60.7k] ------------------ 1230| 1.72k| utf8 = 0; // XXX not state-free 1231| 1.72k| if (!csconv) ------------------ | Branch (1231:9): [True: 1.72k, False: 0] ------------------ 1232| 1.72k| csconv = get_current_cs("iso88591"); // XXX not state-free 1233| 1.72k| n = nc; 1234| 1.72k| nonbmp = 1; 1235| 1.72k| low = 0; 1236| 1.72k| } 1237| 62.4k| ngsuggest_guard restore_state(nonbmp, origconv, &utf8, &csconv); 1238| 62.4k| int max_word_len = (utf8) ? MAXWORDUTF8LEN : MAXWORDLEN; ------------------ | | 85| 24.2k|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 24.2k|#define MAXWORDLEN 100 | | ------------------ ------------------ int max_word_len = (utf8) ? MAXWORDUTF8LEN : MAXWORDLEN; ------------------ | | 90| 38.1k|#define MAXWORDLEN 100 ------------------ | Branch (1238:22): [True: 24.2k, False: 38.1k] ------------------ 1239| | // ofz#59067 a replist entry can generate a very long word, abandon 1240| | // ngram if that odd-edge case arises 1241| 62.4k| if (n > max_word_len * 4) ------------------ | Branch (1241:7): [True: 0, False: 62.4k] ------------------ 1242| 0| return; 1243| | 1244| 62.4k| struct hentry* hp = nullptr; 1245| 62.4k| int col = -1; 1246| 62.4k| phonetable* ph = (pAMgr) ? pAMgr->get_phonetable() : nullptr; ------------------ | Branch (1246:20): [True: 62.4k, False: 0] ------------------ 1247| 62.4k| std::string target; 1248| 62.4k| std::string candidate; 1249| 62.4k| std::vector w_candidate; 1250| 62.4k| if (ph) { ------------------ | Branch (1250:7): [True: 3.59k, False: 58.8k] ------------------ 1251| 3.59k| if (utf8) { ------------------ | Branch (1251:9): [True: 0, False: 3.59k] ------------------ 1252| 0| u8_u16(w_candidate, word); 1253| 0| mkallcap_utf(w_candidate, langnum); 1254| 0| u16_u8(candidate, w_candidate); 1255| 3.59k| } else { 1256| 3.59k| candidate.assign(word); 1257| 3.59k| if (!nonbmp) ------------------ | Branch (1257:11): [True: 3.59k, False: 0] ------------------ 1258| 3.59k| mkallcap(candidate, csconv); 1259| 3.59k| } 1260| 3.59k| target = phonet(candidate, *ph); // XXX phonet() is 8-bit (nc, not n) 1261| 3.59k| } 1262| | 1263| 62.4k| FLAG forbiddenword = pAMgr ? pAMgr->get_forbiddenword() : FLAG_NULL; ------------------ | | 95| 62.4k|#define FLAG unsigned short ------------------ FLAG forbiddenword = pAMgr ? pAMgr->get_forbiddenword() : FLAG_NULL; ------------------ | | 96| 62.4k|#define FLAG_NULL 0x00 ------------------ | Branch (1263:24): [True: 62.4k, False: 0] ------------------ 1264| 62.4k| FLAG nosuggest = pAMgr ? pAMgr->get_nosuggest() : FLAG_NULL; ------------------ | | 95| 62.4k|#define FLAG unsigned short ------------------ FLAG nosuggest = pAMgr ? pAMgr->get_nosuggest() : FLAG_NULL; ------------------ | | 96| 62.4k|#define FLAG_NULL 0x00 ------------------ | Branch (1264:20): [True: 62.4k, False: 0] ------------------ 1265| 62.4k| FLAG nongramsuggest = pAMgr ? pAMgr->get_nongramsuggest() : FLAG_NULL; ------------------ | | 95| 62.4k|#define FLAG unsigned short ------------------ FLAG nongramsuggest = pAMgr ? pAMgr->get_nongramsuggest() : FLAG_NULL; ------------------ | | 96| 62.4k|#define FLAG_NULL 0x00 ------------------ | Branch (1265:25): [True: 62.4k, False: 0] ------------------ 1266| 62.4k| FLAG onlyincompound = pAMgr ? pAMgr->get_onlyincompound() : FLAG_NULL; ------------------ | | 95| 62.4k|#define FLAG unsigned short ------------------ FLAG onlyincompound = pAMgr ? pAMgr->get_onlyincompound() : FLAG_NULL; ------------------ | | 96| 62.4k|#define FLAG_NULL 0x00 ------------------ | Branch (1266:25): [True: 62.4k, False: 0] ------------------ 1267| | 1268| 62.4k| std::vector w_word, w_target; 1269| 62.4k| if (utf8) { ------------------ | Branch (1269:7): [True: 24.2k, False: 38.1k] ------------------ 1270| 24.2k| u8_u16(w_word, word); 1271| 24.2k| u8_u16(w_target, target); 1272| 24.2k| } 1273| | 1274| 62.4k| std::string f; 1275| 62.4k| std::vector w_f; 1276| | 1277| 62.4k| for (const auto& i : rHMgr) { ------------------ | Branch (1277:22): [True: 62.4k, False: 62.4k] ------------------ 1278| 2.00M| while (nullptr != (hp = i->walk_hashtable(col, hp))) { ------------------ | Branch (1278:12): [True: 1.94M, False: 62.4k] ------------------ 1279| | // skip exceptions 1280| 1.94M| 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| 1.94M| (((abs(n - hp->clen) > 4) && !nonbmp)) || ------------------ | Branch (1284:12): [True: 1.33M, False: 602k] | Branch (1284:14): [True: 1.22M, False: 716k] | Branch (1284:41): [True: 1.18M, False: 44.3k] ------------------ 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| 760k| ((captype == NOCAP) && (hp->var & H_OPT_INITCAP) && ------------------ | | 92| 760k|#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: 599k] | Branch (1291:35): [True: 69.8k, False: 91.5k] ------------------ 1292| 69.8k| !ph && (langnum != LANG_de) && !(hp->var & H_OPT_PHON)) || ------------------ | | 49| 68.0k|#define H_OPT_PHON (1 << 2) // is there ph: field in the morphological data? ------------------ | Branch (1292:15): [True: 68.0k, False: 1.76k] | Branch (1292:22): [True: 68.0k, False: 0] | Branch (1292:46): [True: 68.0k, False: 0] ------------------ 1293| | // or it has one of the following special flags 1294| 692k| ((hp->astr) && (pAMgr) && ------------------ | Branch (1294:13): [True: 187k, False: 504k] | Branch (1294:27): [True: 187k, False: 0] ------------------ 1295| 187k| (TESTAFF(hp->astr, forbiddenword, hp->alen) || ------------------ | | 99| 375k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 2.07k, False: 185k] | | ------------------ ------------------ 1296| 185k| TESTAFF(hp->astr, ONLYUPCASEFLAG, hp->alen) || ------------------ | | 99| 373k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 87.7k, False: 98.1k] | | ------------------ ------------------ 1297| 98.1k| TESTAFF(hp->astr, nosuggest, hp->alen) || ------------------ | | 99| 286k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 98.1k] | | ------------------ ------------------ 1298| 98.1k| TESTAFF(hp->astr, nongramsuggest, hp->alen) || ------------------ | | 99| 286k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 98.1k] | | ------------------ ------------------ 1299| 98.1k| TESTAFF(hp->astr, onlyincompound, hp->alen))) ------------------ | | 99| 98.1k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 98.1k] | | ------------------ ------------------ 1300| 1.94M| ) 1301| 1.33M| continue; 1302| | 1303| 602k| if (utf8) { ------------------ | Branch (1303:11): [True: 277k, False: 324k] ------------------ 1304| 277k| u8_u16(w_f, HENTRY_WORD(hp)); ------------------ | | 54| 277k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1305| | 1306| 277k| int leftcommon = leftcommonsubstring(w_word, w_f); 1307| 277k| if (low) { ------------------ | Branch (1307:13): [True: 277k, False: 0] ------------------ 1308| | // lowering dictionary word 1309| 277k| mkallsmall_utf(w_f, langnum); 1310| 277k| } 1311| 277k| sc = ngram(3, w_word, w_f, NGRAM_LONGER_WORSE) + leftcommon; ------------------ | | 81| 277k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1312| 324k| } else { 1313| 324k| f.assign(HENTRY_WORD(hp)); ------------------ | | 54| 324k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1314| | 1315| 324k| int leftcommon = leftcommonsubstring(word, f.c_str()); 1316| 324k| if (low) { ------------------ | Branch (1316:13): [True: 303k, False: 21.0k] ------------------ 1317| | // lowering dictionary word 1318| 303k| mkallsmall(f, csconv); 1319| 303k| } 1320| 324k| sc = ngram(3, word, f, NGRAM_LONGER_WORSE) + leftcommon; ------------------ | | 81| 324k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1321| 324k| } 1322| | 1323| | // check special pronunciation 1324| 602k| f.clear(); 1325| 602k| if ((hp->var & H_OPT_PHON) && ------------------ | | 49| 602k|#define H_OPT_PHON (1 << 2) // is there ph: field in the morphological data? ------------------ | Branch (1325:11): [True: 753, False: 601k] | Branch (1325:11): [True: 753, False: 601k] ------------------ 1326| 753| copy_field(f, HENTRY_DATA(hp), MORPH_PHON)) { ------------------ | | 114| 753|#define MORPH_PHON "ph:" ------------------ | Branch (1326:11): [True: 753, False: 0] ------------------ 1327| 753| int sc2; 1328| 753| if (utf8) { ------------------ | Branch (1328:13): [True: 0, False: 753] ------------------ 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| 753| } else { 1338| 753| int leftcommon = leftcommonsubstring(word, f.c_str()); 1339| 753| if (low) { ------------------ | Branch (1339:15): [True: 753, False: 0] ------------------ 1340| | // lowering dictionary word 1341| 753| mkallsmall(f, csconv); 1342| 753| } 1343| 753| sc2 = ngram(3, word, f, NGRAM_LONGER_WORSE) + leftcommon; ------------------ | | 81| 753|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1344| 753| } 1345| 753| if (sc2 > sc) ------------------ | Branch (1345:13): [True: 376, False: 377] ------------------ 1346| 376| sc = sc2; 1347| 753| } 1348| | 1349| 602k| int scphon = -20000; 1350| 602k| if (ph && (sc > 2) && (abs(n - (int)hp->clen) <= 3)) { ------------------ | Branch (1350:11): [True: 34.9k, False: 567k] | Branch (1350:17): [True: 7.81k, False: 27.1k] | Branch (1350:29): [True: 6.78k, False: 1.03k] ------------------ 1351| 6.78k| if (utf8) { ------------------ | Branch (1351:13): [True: 0, False: 6.78k] ------------------ 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| 6.78k| } else { 1356| 6.78k| candidate = HENTRY_WORD(hp); ------------------ | | 54| 6.78k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1357| 6.78k| mkallcap(candidate, csconv); 1358| 6.78k| } 1359| 6.78k| f = phonet(candidate, *ph); 1360| 6.78k| if (utf8) { ------------------ | Branch (1360:13): [True: 0, False: 6.78k] ------------------ 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| 6.78k| } else { 1365| 6.78k| scphon = 2 * ngram(3, target, f, 1366| 6.78k| NGRAM_LONGER_WORSE); ------------------ | | 81| 6.78k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1367| 6.78k| } 1368| 6.78k| } 1369| | 1370| 602k| if (sc > scores[lp]) { ------------------ | Branch (1370:11): [True: 602k, False: 0] ------------------ 1371| 602k| scores[lp] = sc; 1372| 602k| roots[lp] = hp; 1373| 602k| has_roots = true; 1374| 602k| lval = sc; 1375| 60.8M| for (int j = 0; j < MAX_ROOTS; j++) ------------------ | | 74| 60.8M|#define MAX_ROOTS 100 ------------------ | Branch (1375:25): [True: 60.2M, False: 602k] ------------------ 1376| 60.2M| if (scores[j] < lval) { ------------------ | Branch (1376:15): [True: 49.8M, False: 10.4M] ------------------ 1377| 49.8M| lp = j; 1378| 49.8M| lval = scores[j]; 1379| 49.8M| } 1380| 602k| } 1381| | 1382| 602k| if (scphon > scoresphon[lpphon]) { ------------------ | Branch (1382:11): [True: 6.78k, False: 595k] ------------------ 1383| 6.78k| scoresphon[lpphon] = scphon; 1384| 6.78k| rootsphon[lpphon] = HENTRY_WORD(hp); ------------------ | | 54| 6.78k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1385| 6.78k| has_rootsphon = true; 1386| 6.78k| lval = scphon; 1387| 685k| for (int j = 0; j < MAX_ROOTS; j++) ------------------ | | 74| 685k|#define MAX_ROOTS 100 ------------------ | Branch (1387:25): [True: 678k, False: 6.78k] ------------------ 1388| 678k| if (scoresphon[j] < lval) { ------------------ | Branch (1388:15): [True: 598k, False: 79.7k] ------------------ 1389| 598k| lpphon = j; 1390| 598k| lval = scoresphon[j]; 1391| 598k| } 1392| 6.78k| } 1393| 602k| } 1394| 62.4k| } 1395| | 1396| 62.4k| if (!has_roots && !has_rootsphon) { ------------------ | Branch (1396:7): [True: 14.0k, False: 48.4k] | Branch (1396:21): [True: 14.0k, False: 0] ------------------ 1397| | // with no roots there will be no guesses and no point running 1398| | // ngram 1399| 14.0k| return; 1400| 14.0k| } 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| 48.4k| std::vector w_mw; 1406| 48.4k| int thresh = 0; 1407| 193k| for (int sp = 1; sp < 4; sp++) { ------------------ | Branch (1407:20): [True: 145k, False: 48.4k] ------------------ 1408| 145k| if (utf8) { ------------------ | Branch (1408:9): [True: 59.6k, False: 85.6k] ------------------ 1409| 59.6k| w_mw = w_word; 1410| 111k| for (int k = sp; k < n; k += 4) { ------------------ | Branch (1410:24): [True: 51.6k, False: 59.6k] ------------------ 1411| 51.6k| w_mw[k].l = '*'; 1412| 51.6k| w_mw[k].h = 0; 1413| 51.6k| } 1414| | 1415| 59.6k| if (low) { ------------------ | Branch (1415:11): [True: 59.6k, False: 0] ------------------ 1416| | // lowering dictionary word 1417| 59.6k| mkallsmall_utf(w_mw, langnum); 1418| 59.6k| } 1419| | 1420| 59.6k| thresh += ngram(n, w_word, w_mw, NGRAM_ANY_MISMATCH); ------------------ | | 82| 59.6k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1421| 85.6k| } else { 1422| 85.6k| std::string mw = word; 1423| 201k| for (int k = sp; k < n; k += 4) ------------------ | Branch (1423:24): [True: 115k, False: 85.6k] ------------------ 1424| 115k| mw[k] = '*'; 1425| | 1426| 85.6k| if (low) { ------------------ | Branch (1426:11): [True: 80.4k, False: 5.18k] ------------------ 1427| | // lowering dictionary word 1428| 80.4k| mkallsmall(mw, csconv); 1429| 80.4k| } 1430| | 1431| 85.6k| thresh += ngram(n, word, mw, NGRAM_ANY_MISMATCH); ------------------ | | 82| 85.6k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1432| 85.6k| } 1433| 145k| } 1434| 48.4k| thresh = thresh / 3; 1435| 48.4k| 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| 48.4k| char* guess[MAX_GUESS]; 1441| 48.4k| char* guessorig[MAX_GUESS]; 1442| 48.4k| int gscore[MAX_GUESS]; 1443| 9.73M| for (int i = 0; i < MAX_GUESS; i++) { ------------------ | | 76| 9.73M|#define MAX_GUESS 200 ------------------ | Branch (1443:19): [True: 9.68M, False: 48.4k] ------------------ 1444| 9.68M| guess[i] = nullptr; 1445| 9.68M| guessorig[i] = nullptr; 1446| 9.68M| gscore[i] = -100 * i; 1447| 9.68M| } 1448| | 1449| 48.4k| lp = MAX_GUESS - 1; ------------------ | | 76| 48.4k|#define MAX_GUESS 200 ------------------ 1450| | 1451| 48.4k| std::vector glst(MAX_WORDS); ------------------ | | 75| 48.4k|#define MAX_WORDS 100 ------------------ 1452| | 1453| 4.84M| for (auto& root : roots) { ------------------ | Branch (1453:19): [True: 4.84M, False: 48.4k] ------------------ 1454| 4.84M| if (root) { ------------------ | Branch (1454:9): [True: 602k, False: 4.24M] ------------------ 1455| 602k| struct hentry* rp = root; 1456| | 1457| 602k| f.clear(); 1458| 602k| const char* field = nullptr; 1459| 602k| if ((rp->var & H_OPT_PHON) && copy_field(f, HENTRY_DATA(rp), MORPH_PHON)) ------------------ | | 49| 602k|#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| 753|#define MORPH_PHON "ph:" ------------------ | Branch (1459:11): [True: 753, False: 601k] | Branch (1459:11): [True: 753, False: 601k] | Branch (1459:37): [True: 753, False: 0] ------------------ 1460| 753| field = f.c_str(); 1461| 602k| int nw = pAMgr->expand_rootword( 1462| 602k| glst.data(), MAX_WORDS, HENTRY_WORD(rp), rp->blen, rp->astr, rp->alen, word, ------------------ | | 75| 602k|#define MAX_WORDS 100 ------------------ glst.data(), MAX_WORDS, HENTRY_WORD(rp), rp->blen, rp->astr, rp->alen, word, ------------------ | | 54| 602k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1463| 602k| nc, field); 1464| | 1465| 1.20M| for (int k = 0; k < nw; k++) { ------------------ | Branch (1465:23): [True: 601k, False: 602k] ------------------ 1466| 601k| if (utf8) { ------------------ | Branch (1466:13): [True: 277k, False: 323k] ------------------ 1467| 277k| u8_u16(w_f, glst[k].word); 1468| | 1469| 277k| int leftcommon = leftcommonsubstring(w_word, w_f); 1470| 277k| if (low) { ------------------ | Branch (1470:15): [True: 277k, False: 0] ------------------ 1471| | // lowering dictionary word 1472| 277k| mkallsmall_utf(w_f, langnum); 1473| 277k| } 1474| | 1475| 277k| sc = ngram(n, w_word, w_f, NGRAM_ANY_MISMATCH) + leftcommon; ------------------ | | 82| 277k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1476| 323k| } else { 1477| 323k| f = glst[k].word; 1478| | 1479| 323k| int leftcommon = leftcommonsubstring(word, f.c_str()); 1480| 323k| if (low) { ------------------ | Branch (1480:15): [True: 302k, False: 21.0k] ------------------ 1481| | // lowering dictionary word 1482| 302k| mkallsmall(f, csconv); 1483| 302k| } 1484| | 1485| 323k| sc = ngram(n, word, f, NGRAM_ANY_MISMATCH) + leftcommon; ------------------ | | 82| 323k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1486| 323k| } 1487| | 1488| 601k| if (sc > thresh) { ------------------ | Branch (1488:13): [True: 106k, False: 494k] ------------------ 1489| 106k| if (sc > gscore[lp]) { ------------------ | Branch (1489:15): [True: 106k, False: 0] ------------------ 1490| 106k| if (guess[lp]) { ------------------ | Branch (1490:17): [True: 0, False: 106k] ------------------ 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| 106k| gscore[lp] = sc; 1498| 106k| guess[lp] = glst[k].word; 1499| 106k| guessorig[lp] = glst[k].orig; 1500| 106k| lval = sc; 1501| 21.4M| for (int j = 0; j < MAX_GUESS; j++) ------------------ | | 76| 21.4M|#define MAX_GUESS 200 ------------------ | Branch (1501:29): [True: 21.3M, False: 106k] ------------------ 1502| 21.3M| if (gscore[j] < lval) { ------------------ | Branch (1502:19): [True: 20.4M, False: 912k] ------------------ 1503| 20.4M| lp = j; 1504| 20.4M| lval = gscore[j]; 1505| 20.4M| } 1506| 106k| } else { 1507| 0| delete[] glst[k].word; 1508| 0| delete[] glst[k].orig; 1509| 0| } 1510| 494k| } else { 1511| 494k| delete[] glst[k].word; 1512| 494k| delete[] glst[k].orig; 1513| 494k| } 1514| 601k| } 1515| 602k| } 1516| 4.84M| } 1517| 48.4k| glst.clear(); 1518| | 1519| | // now we are done generating guesses 1520| | // sort in order of decreasing score 1521| | 1522| 48.4k| bubblesort(&guess[0], &guessorig[0], &gscore[0], MAX_GUESS); ------------------ | | 76| 48.4k|#define MAX_GUESS 200 ------------------ 1523| 48.4k| if (ph) ------------------ | Branch (1523:7): [True: 2.85k, False: 45.5k] ------------------ 1524| 2.85k| bubblesort(&rootsphon[0], nullptr, &scoresphon[0], MAX_ROOTS); ------------------ | | 74| 2.85k|#define MAX_ROOTS 100 ------------------ 1525| | 1526| | // weight suggestions with a similarity index, based on 1527| | // the longest common subsequent algorithm and resort 1528| | 1529| 48.4k| int is_swap = 0; 1530| 48.4k| int re = 0; 1531| 48.4k| double fact = 1.0; 1532| 48.4k| if (pAMgr) { ------------------ | Branch (1532:7): [True: 48.4k, False: 0] ------------------ 1533| 48.4k| int maxd = pAMgr->get_maxdiff(); 1534| 48.4k| if (maxd >= 0) ------------------ | Branch (1534:9): [True: 0, False: 48.4k] ------------------ 1535| 0| fact = (10.0 - maxd) / 5.0; 1536| 48.4k| } 1537| | 1538| 48.4k| std::vector w_gl; 1539| 9.20M| for (int i = 0; i < MAX_GUESS; i++) { ------------------ | | 76| 9.20M|#define MAX_GUESS 200 ------------------ | Branch (1539:19): [True: 9.16M, False: 45.8k] ------------------ 1540| 9.16M| if (guess[i]) { ------------------ | Branch (1540:9): [True: 79.5k, False: 9.08M] ------------------ 1541| | // lowering guess[i] 1542| 79.5k| std::string gl; 1543| 79.5k| int len; 1544| 79.5k| if (utf8) { ------------------ | Branch (1544:11): [True: 25.2k, False: 54.3k] ------------------ 1545| 25.2k| len = u8_u16(w_gl, guess[i]); 1546| 25.2k| mkallsmall_utf(w_gl, langnum); 1547| 25.2k| u16_u8(gl, w_gl); 1548| 54.3k| } else { 1549| 54.3k| gl.assign(guess[i]); 1550| 54.3k| if (!nonbmp) ------------------ | Branch (1550:13): [True: 54.3k, False: 18] ------------------ 1551| 54.3k| mkallsmall(gl, csconv); 1552| 54.3k| len = strlen(guess[i]); 1553| 54.3k| } 1554| | 1555| 79.5k| int _lcs = lcslen(word, gl.c_str()); 1556| | 1557| | // same characters with different casing 1558| 79.5k| if ((n == len) && (n == _lcs)) { ------------------ | Branch (1558:11): [True: 19.5k, False: 60.0k] | Branch (1558:25): [True: 2.63k, False: 16.8k] ------------------ 1559| 2.63k| gscore[i] += 2000; 1560| 2.63k| break; 1561| 2.63k| } 1562| | // using 2-gram instead of 3, and other weightening 1563| | 1564| 76.9k| if (utf8) { ------------------ | Branch (1564:11): [True: 23.1k, False: 53.8k] ------------------ 1565| 23.1k| u8_u16(w_gl, gl); 1566| | //w_gl is lowercase already at this point 1567| 23.1k| re = ngram(2, w_word, w_gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 23.1k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re = ngram(2, w_word, w_gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 23.1k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1568| 23.1k| if (low) { ------------------ | Branch (1568:13): [True: 23.1k, False: 0] ------------------ 1569| 23.1k| w_f = w_word; 1570| | // lowering dictionary word 1571| 23.1k| mkallsmall_utf(w_f, langnum); 1572| 23.1k| re += ngram(2, w_gl, w_f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 23.1k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re += ngram(2, w_gl, w_f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 23.1k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1573| 23.1k| } 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| 53.8k| } else { 1577| | //gl is lowercase already at this point 1578| 53.8k| re = ngram(2, word, gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 53.8k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re = ngram(2, word, gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 53.8k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1579| 53.8k| if (low) { ------------------ | Branch (1579:13): [True: 53.8k, False: 18] ------------------ 1580| 53.8k| f = word; 1581| | // lowering dictionary word 1582| 53.8k| mkallsmall(f, csconv); 1583| 53.8k| re += ngram(2, gl, f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 53.8k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re += ngram(2, gl, f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 53.8k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1584| 53.8k| } else { 1585| 18| re += ngram(2, gl, word, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 18|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re += ngram(2, gl, word, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 18|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1586| 18| } 1587| 53.8k| } 1588| | 1589| 76.9k| int ngram_score, leftcommon_score; 1590| 76.9k| if (utf8) { ------------------ | Branch (1590:11): [True: 23.1k, False: 53.8k] ------------------ 1591| | //w_gl is lowercase already at this point 1592| 23.1k| ngram_score = ngram(4, w_word, w_gl, NGRAM_ANY_MISMATCH); ------------------ | | 82| 23.1k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1593| 23.1k| leftcommon_score = leftcommonsubstring(w_word, w_gl); 1594| 53.8k| } else { 1595| | //gl is lowercase already at this point 1596| 53.8k| ngram_score = ngram(4, word, gl, NGRAM_ANY_MISMATCH); ------------------ | | 82| 53.8k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1597| 53.8k| leftcommon_score = leftcommonsubstring(word, gl.c_str()); 1598| 53.8k| } 1599| 76.9k| gscore[i] = 1600| | // length of longest common subsequent minus length difference 1601| 76.9k| 2 * _lcs - abs((int)(n - len)) + 1602| | // weight length of the left common substring 1603| 76.9k| leftcommon_score + 1604| | // weight equal character positions 1605| 76.9k| (!nonbmp && commoncharacterpositions(word, gl.c_str(), &is_swap) ------------------ | Branch (1605:12): [True: 76.9k, False: 18] | Branch (1605:23): [True: 64.4k, False: 12.4k] ------------------ 1606| 76.9k| ? 1 1607| 76.9k| : 0) + 1608| | // swap character (not neighboring) 1609| 76.9k| ((is_swap) ? 10 : 0) + ------------------ | Branch (1609:12): [True: 86, False: 76.8k] ------------------ 1610| | // ngram 1611| 76.9k| ngram_score + 1612| | // weighted ngrams 1613| 76.9k| re + 1614| | // different limit for dictionaries with PHONE rules 1615| 76.9k| (ph ? (re < len * fact ? -1000 : 0) ------------------ | Branch (1615:12): [True: 5.23k, False: 71.7k] | Branch (1615:18): [True: 4.10k, False: 1.12k] ------------------ 1616| 76.9k| : (re < (n + len) * fact ? -1000 : 0)); ------------------ | Branch (1616:18): [True: 65.8k, False: 5.87k] ------------------ 1617| 76.9k| } 1618| 9.16M| } 1619| | 1620| 48.4k| bubblesort(&guess[0], &guessorig[0], &gscore[0], MAX_GUESS); ------------------ | | 76| 48.4k|#define MAX_GUESS 200 ------------------ 1621| | 1622| | // phonetic version 1623| 48.4k| if (ph) ------------------ | Branch (1623:7): [True: 2.85k, False: 45.5k] ------------------ 1624| 288k| for (int i = 0; i < MAX_ROOTS; i++) { ------------------ | | 74| 288k|#define MAX_ROOTS 100 ------------------ | Branch (1624:21): [True: 285k, False: 2.85k] ------------------ 1625| 285k| if (rootsphon[i]) { ------------------ | Branch (1625:11): [True: 6.78k, False: 278k] ------------------ 1626| | // lowering rootphon[i] 1627| 6.78k| std::string gl; 1628| 6.78k| int len; 1629| 6.78k| if (utf8) { ------------------ | Branch (1629:13): [True: 0, False: 6.78k] ------------------ 1630| 0| len = u8_u16(w_gl, rootsphon[i]); 1631| 0| mkallsmall_utf(w_gl, langnum); 1632| 0| u16_u8(gl, w_gl); 1633| 6.78k| } else { 1634| 6.78k| gl.assign(rootsphon[i]); 1635| 6.78k| if (!nonbmp) ------------------ | Branch (1635:15): [True: 6.78k, False: 0] ------------------ 1636| 6.78k| mkallsmall(gl, csconv); 1637| 6.78k| len = strlen(rootsphon[i]); 1638| 6.78k| } 1639| | 1640| | // weight length of the left common substring 1641| 6.78k| int leftcommon_score; 1642| 6.78k| if (utf8) ------------------ | Branch (1642:13): [True: 0, False: 6.78k] ------------------ 1643| 0| leftcommon_score = leftcommonsubstring(w_word, w_gl); 1644| 6.78k| else 1645| 6.78k| leftcommon_score = leftcommonsubstring(word, gl.c_str()); 1646| | // heuristic weigthing of ngram scores 1647| 6.78k| scoresphon[i] += 2 * lcslen(word, gl) - abs((int)(n - len)) + 1648| 6.78k| leftcommon_score; 1649| 6.78k| } 1650| 285k| } 1651| | 1652| 48.4k| if (ph) ------------------ | Branch (1652:7): [True: 2.85k, False: 45.5k] ------------------ 1653| 2.85k| bubblesort(&rootsphon[0], nullptr, &scoresphon[0], MAX_ROOTS); ------------------ | | 74| 2.85k|#define MAX_ROOTS 100 ------------------ 1654| | 1655| | // copy over 1656| 48.4k| size_t oldns = wlst.size(); 1657| | 1658| 48.4k| int same = 0; 1659| 9.73M| for (int i = 0; i < MAX_GUESS; i++) { ------------------ | | 76| 9.73M|#define MAX_GUESS 200 ------------------ | Branch (1659:19): [True: 9.68M, False: 48.4k] ------------------ 1660| 9.68M| if (guess[i]) { ------------------ | Branch (1660:9): [True: 106k, False: 9.58M] ------------------ 1661| 106k| if ((wlst.size() < oldns + maxngramsugs) && (wlst.size() < maxSug) && ------------------ | Branch (1661:11): [True: 102k, False: 4.69k] | Branch (1661:51): [True: 102k, False: 0] ------------------ 1662| 102k| (!same || (gscore[i] > 1000))) { ------------------ | Branch (1662:12): [True: 17.2k, False: 85.0k] | Branch (1662:21): [True: 0, False: 85.0k] ------------------ 1663| 17.2k| int unique = 1; 1664| | // leave only excellent suggestions, if exists 1665| 17.2k| if (gscore[i] > 1000) ------------------ | Branch (1665:13): [True: 2.63k, False: 14.5k] ------------------ 1666| 2.63k| same = 1; 1667| 14.5k| else if (gscore[i] < -100) { ------------------ | Branch (1667:18): [True: 8.54k, False: 6.02k] ------------------ 1668| 8.54k| same = 1; 1669| | // keep the best ngram suggestions, unless in ONLYMAXDIFF mode 1670| 8.54k| if (wlst.size() > oldns || (pAMgr && pAMgr->get_onlymaxdiff())) { ------------------ | Branch (1670:15): [True: 1.11k, False: 7.43k] | Branch (1670:39): [True: 7.43k, False: 0] | Branch (1670:48): [True: 0, False: 7.43k] ------------------ 1671| 1.11k| delete[] guess[i]; 1672| 1.11k| delete[] guessorig[i]; 1673| 1.11k| continue; 1674| 1.11k| } 1675| 8.54k| } 1676| 16.1k| for (auto& j : wlst) { ------------------ | Branch (1676:22): [True: 8.51k, False: 13.2k] ------------------ 1677| | // don't suggest previous suggestions or a previous suggestion with 1678| | // prefixes or affixes 1679| 8.51k| if ((!guessorig[i] && strstr(guess[i], j.c_str())) || (guessorig[i] && strstr(guessorig[i], j.c_str())) || ------------------ | Branch (1679:15): [True: 2.86k, False: 5.65k] | Branch (1679:16): [True: 8.51k, False: 0] | Branch (1679:33): [True: 2.86k, False: 5.65k] | Branch (1679:66): [True: 0, False: 5.65k] | Branch (1679:82): [True: 0, False: 0] ------------------ 1680| | // check forbidden words 1681| 5.65k| !checkword(guess[i], 0, nullptr, nullptr)) { ------------------ | Branch (1681:15): [True: 0, False: 5.65k] ------------------ 1682| 2.86k| unique = 0; 1683| 2.86k| break; 1684| 2.86k| } 1685| 8.51k| } 1686| 16.1k| if (unique) { ------------------ | Branch (1686:13): [True: 13.2k, False: 2.86k] ------------------ 1687| 13.2k| if (guessorig[i]) { ------------------ | Branch (1687:15): [True: 0, False: 13.2k] ------------------ 1688| 0| wlst.emplace_back(guessorig[i]); 1689| 13.2k| } else { 1690| 13.2k| wlst.emplace_back(guess[i]); 1691| 13.2k| } 1692| 13.2k| } 1693| 16.1k| delete[] guess[i]; 1694| 16.1k| delete[] guessorig[i]; 1695| 89.7k| } else { 1696| 89.7k| delete[] guess[i]; 1697| 89.7k| delete[] guessorig[i]; 1698| 89.7k| } 1699| 106k| } 1700| 9.68M| } 1701| | 1702| 48.4k| oldns = wlst.size(); 1703| 48.4k| if (ph) ------------------ | Branch (1703:7): [True: 2.85k, False: 45.5k] ------------------ 1704| 285k| for (auto& i : rootsphon) { ------------------ | Branch (1704:18): [True: 285k, False: 2.85k] ------------------ 1705| 285k| if (i) { ------------------ | Branch (1705:11): [True: 6.78k, False: 278k] ------------------ 1706| 6.78k| if ((wlst.size() < oldns + MAXPHONSUGS) && (wlst.size() < maxSug)) { ------------------ | | 78| 6.78k|#define MAXPHONSUGS 2 ------------------ | Branch (1706:13): [True: 2.41k, False: 4.36k] | Branch (1706:52): [True: 2.41k, False: 0] ------------------ 1707| 2.41k| int unique = 1; 1708| 4.09k| for (auto& j : wlst) { ------------------ | Branch (1708:24): [True: 4.09k, False: 984] ------------------ 1709| | // don't suggest previous suggestions or a previous suggestion with 1710| | // prefixes or affixes 1711| 4.09k| if (strstr(i, j.c_str()) || ------------------ | Branch (1711:17): [True: 1.43k, False: 2.66k] | Branch (1711:17): [True: 1.43k, False: 2.66k] ------------------ 1712| | // check forbidden words 1713| 2.66k| !checkword(i, 0, nullptr, nullptr)) { ------------------ | Branch (1713:17): [True: 0, False: 2.66k] ------------------ 1714| 1.43k| unique = 0; 1715| 1.43k| break; 1716| 1.43k| } 1717| 4.09k| } 1718| 2.41k| if (unique) { ------------------ | Branch (1718:15): [True: 984, False: 1.43k] ------------------ 1719| 984| wlst.emplace_back(i); 1720| 984| } 1721| 2.41k| } 1722| 6.78k| } 1723| 285k| } 1724| 48.4k|} _ZN10SuggestMgr9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiPiPNS0_6chrono10time_pointINSA_12steady_clockENSA_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 1735| 93.7M| std::chrono::steady_clock::time_point* timelimit) { 1736| | // check overall suggestion time limit 1737| 93.7M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 93.7M|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (1737:7): [True: 6, False: 93.7M] ------------------ 1738| 6| return 0; 1739| | 1740| | // check time limit 1741| 93.7M| if (timer) { ------------------ | Branch (1741:7): [True: 1.16M, False: 92.6M] ------------------ 1742| 1.16M| (*timer)--; 1743| 1.16M| if (!(*timer) && timelimit) { ------------------ | Branch (1743:9): [True: 6.69k, False: 1.15M] | Branch (1743:22): [True: 6.69k, False: 0] ------------------ 1744| 6.69k| if (std::chrono::steady_clock::now() - *timelimit > TIMELIMIT_MS) ------------------ | | 106| 6.69k|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (1744:11): [True: 6, False: 6.68k] ------------------ 1745| 6| return 0; 1746| 6.68k| *timer = MAXPLUSTIMER; ------------------ | | 108| 6.68k|#define MAXPLUSTIMER 100 ------------------ 1747| 6.68k| } 1748| 1.16M| } 1749| | 1750| 93.7M| if (pAMgr) { ------------------ | Branch (1750:7): [True: 93.7M, False: 0] ------------------ 1751| 93.7M| struct hentry* rv = nullptr; 1752| 93.7M| int nosuffix = 0; 1753| | 1754| 93.7M| if (cpdsuggest >= 1) { ------------------ | Branch (1754:9): [True: 61.4M, False: 32.3M] ------------------ 1755| 61.4M| if (pAMgr->get_compound()) { ------------------ | Branch (1755:11): [True: 15.5M, False: 45.9M] ------------------ 1756| 15.5M| struct hentry* rv2 = nullptr; 1757| 15.5M| struct hentry* rwords[100] = {}; // buffer for COMPOUND pattern checking 1758| 15.5M| int info = (cpdsuggest == 1) ? SPELL_COMPOUND_2 : 0; ------------------ | | 85| 7.75M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ | Branch (1758:20): [True: 7.75M, False: 7.75M] ------------------ 1759| 15.5M| AffixScratch scratch; 1760| 15.5M| 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| 15.5M| if (rv && ------------------ | Branch (1763:13): [True: 0, False: 15.5M] | Branch (1763:13): [True: 0, False: 15.5M] ------------------ 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) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1766| 0| TESTAFF(rv2->astr, pAMgr->get_nosuggest(), rv2->alen)))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1767| 0| return 3; // XXX obsolote categorisation + only ICONV needs affix 1768| | // flag check? 1769| 15.5M| } 1770| 61.4M| return 0; 1771| 61.4M| } 1772| | 1773| 32.3M| rv = pAMgr->lookup(word.c_str(), word.size()); 1774| | 1775| 32.3M| if (rv) { ------------------ | Branch (1775:9): [True: 37.7k, False: 32.2M] ------------------ 1776| 37.7k| if ((rv->astr) && ------------------ | Branch (1776:11): [True: 224, False: 37.5k] | Branch (1776:11): [True: 0, False: 37.7k] ------------------ 1777| 224| (TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen) || ------------------ | | 99| 448|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 224] | | ------------------ ------------------ 1778| 224| TESTAFF(rv->astr, pAMgr->get_nosuggest(), rv->alen) || ------------------ | | 99| 448|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 224] | | ------------------ ------------------ 1779| 224| TESTAFF(rv->astr, pAMgr->get_substandard(), rv->alen))) ------------------ | | 99| 224|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 224] | | ------------------ ------------------ 1780| 0| return 0; 1781| 38.0k| while (rv) { ------------------ | Branch (1781:14): [True: 37.7k, False: 214] ------------------ 1782| 37.7k| if (rv->astr && ------------------ | Branch (1782:13): [True: 224, False: 37.5k] | Branch (1782:13): [True: 214, False: 37.5k] ------------------ 1783| 224| (TESTAFF(rv->astr, pAMgr->get_needaffix(), rv->alen) || ------------------ | | 99| 448|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 224] | | ------------------ ------------------ 1784| 224| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 448|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 214, False: 10] | | ------------------ ------------------ 1785| 214| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) { ------------------ | | 99| 10|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 10] | | ------------------ ------------------ 1786| 214| rv = rv->next_homonym; 1787| 214| } else 1788| 37.5k| break; 1789| 37.7k| } 1790| 32.2M| } else { 1791| 32.2M| AffixScratch scratch; 1792| 32.2M| rv = pAMgr->prefix_check(word, 0, word.size(), 1793| 32.2M| 0, scratch); // only prefix, and prefix + suffix XXX 1794| 32.2M| } 1795| | 1796| 32.3M| if (rv) { ------------------ | Branch (1796:9): [True: 37.5k, False: 32.2M] ------------------ 1797| 37.5k| nosuffix = 1; 1798| 32.2M| } else { 1799| 32.2M| AffixScratch scratch; 1800| 32.2M| rv = pAMgr->suffix_check(word, 0, word.size(), 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // only suffix ------------------ | | 96| 32.2M|#define FLAG_NULL 0x00 ------------------ rv = pAMgr->suffix_check(word, 0, word.size(), 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // only suffix ------------------ | | 96| 32.2M|#define FLAG_NULL 0x00 ------------------ rv = pAMgr->suffix_check(word, 0, word.size(), 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // only suffix ------------------ | | 72| 32.2M|#define IN_CPD_NOT 0 ------------------ 1801| 32.2M| } 1802| | 1803| 32.3M| if (!rv && pAMgr->have_contclass()) { ------------------ | Branch (1803:9): [True: 32.2M, False: 37.5k] | Branch (1803:16): [True: 11.6M, False: 20.6M] ------------------ 1804| 11.6M| AffixScratch scratch; 1805| 11.6M| rv = pAMgr->suffix_check_twosfx(word, 0, word.size(), 0, nullptr, scratch, FLAG_NULL); ------------------ | | 96| 11.6M|#define FLAG_NULL 0x00 ------------------ 1806| 11.6M| if (!rv) ------------------ | Branch (1806:11): [True: 11.6M, False: 0] ------------------ 1807| 11.6M| rv = pAMgr->prefix_check_twosfx(word, 0, word.size(), 0, scratch, FLAG_NULL); ------------------ | | 96| 11.6M|#define FLAG_NULL 0x00 ------------------ 1808| 11.6M| } 1809| | 1810| | // check forbidden words 1811| 32.3M| if ((rv) && (rv->astr) && ------------------ | Branch (1811:9): [True: 37.5k, False: 32.2M] | Branch (1811:9): [True: 0, False: 32.3M] | Branch (1811:17): [True: 12, False: 37.5k] ------------------ 1812| 12| (TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen) || ------------------ | | 99| 24|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 12] | | ------------------ ------------------ 1813| 12| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 24|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 12] | | ------------------ ------------------ 1814| 12| TESTAFF(rv->astr, pAMgr->get_nosuggest(), rv->alen) || ------------------ | | 99| 24|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 12] | | ------------------ ------------------ 1815| 12| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) ------------------ | | 99| 12|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 12] | | ------------------ ------------------ 1816| 0| return 0; 1817| | 1818| 32.3M| if (rv) { // XXX obsolote ------------------ | Branch (1818:9): [True: 37.5k, False: 32.2M] ------------------ 1819| 37.5k| if ((pAMgr->get_compoundflag()) && ------------------ | Branch (1819:11): [True: 8.87k, False: 28.7k] | Branch (1819:11): [True: 4, False: 37.5k] ------------------ 1820| 8.87k| TESTAFF(rv->astr, pAMgr->get_compoundflag(), rv->alen)) ------------------ | | 99| 8.87k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 4, False: 8.87k] | | ------------------ ------------------ 1821| 4| return 2 + nosuffix; 1822| 37.5k| return 1; 1823| 37.5k| } 1824| 32.3M| } 1825| 32.2M| return 0; 1826| 93.7M|} _ZN10SuggestMgr15check_forbiddenERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1828| 14.7k|int SuggestMgr::check_forbidden(const std::string& word) { 1829| 14.7k| if (pAMgr) { ------------------ | Branch (1829:7): [True: 14.7k, False: 0] ------------------ 1830| 14.7k| struct hentry* rv = pAMgr->lookup(word.c_str(), word.size()); 1831| 14.7k| if (rv && rv->astr && ------------------ | Branch (1831:9): [True: 3, False: 14.7k] | Branch (1831:9): [True: 0, False: 14.7k] | Branch (1831:15): [True: 3, False: 0] ------------------ 1832| 3| (TESTAFF(rv->astr, pAMgr->get_needaffix(), rv->alen) || ------------------ | | 99| 6|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 3] | | ------------------ ------------------ 1833| 3| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) ------------------ | | 99| 3|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 3] | | ------------------ ------------------ 1834| 0| rv = nullptr; 1835| 14.7k| size_t len = word.size(); 1836| 14.7k| AffixScratch scratch; 1837| 14.7k| if (!(pAMgr->prefix_check(word, 0, len, 1, scratch))) ------------------ | Branch (1837:9): [True: 14.7k, False: 0] ------------------ 1838| 14.7k| rv = pAMgr->suffix_check(word, 0, len, 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // prefix+suffix, suffix ------------------ | | 96| 14.7k|#define FLAG_NULL 0x00 ------------------ rv = pAMgr->suffix_check(word, 0, len, 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // prefix+suffix, suffix ------------------ | | 96| 14.7k|#define FLAG_NULL 0x00 ------------------ rv = pAMgr->suffix_check(word, 0, len, 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // prefix+suffix, suffix ------------------ | | 72| 14.7k|#define IN_CPD_NOT 0 ------------------ 1839| | // check forbidden words 1840| 14.7k| if ((rv) && (rv->astr) && ------------------ | Branch (1840:9): [True: 0, False: 14.7k] | Branch (1840:9): [True: 0, False: 14.7k] | Branch (1840:17): [True: 0, False: 0] ------------------ 1841| 0| TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen)) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1842| 0| return 1; 1843| 14.7k| } 1844| 14.7k| return 0; 1845| 14.7k|} _ZN10SuggestMgr13suggest_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1847| 13.6k|std::string SuggestMgr::suggest_morph(const std::string& in_w) { 1848| 13.6k| std::string result; 1849| | 1850| 13.6k| struct hentry* rv = nullptr; 1851| | 1852| 13.6k| if (!pAMgr) ------------------ | Branch (1852:7): [True: 0, False: 13.6k] ------------------ 1853| 0| return {}; 1854| | 1855| 13.6k| std::string w(in_w); 1856| | 1857| | // word reversing wrapper for complex prefixes 1858| 13.6k| if (complexprefixes) { ------------------ | Branch (1858:7): [True: 694, False: 12.9k] ------------------ 1859| 694| if (utf8) ------------------ | Branch (1859:9): [True: 0, False: 694] ------------------ 1860| 0| reverseword_utf(w); 1861| 694| else 1862| 694| reverseword(w); 1863| 694| } 1864| | 1865| 13.6k| rv = pAMgr->lookup(w.c_str(), w.size()); 1866| | 1867| 17.3k| while (rv) { ------------------ | Branch (1867:10): [True: 3.71k, False: 13.6k] ------------------ 1868| 3.71k| if ((!rv->astr) || ------------------ | Branch (1868:9): [True: 3.06k, False: 648] | Branch (1868:9): [True: 3.71k, False: 0] ------------------ 1869| 648| !(TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen) || ------------------ | | 99| 1.29k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 648] | | ------------------ ------------------ 1870| 648| TESTAFF(rv->astr, pAMgr->get_needaffix(), rv->alen) || ------------------ | | 99| 1.29k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 648] | | ------------------ ------------------ 1871| 3.71k| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) { ------------------ | | 99| 648|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 648] | | ------------------ ------------------ 1872| 3.71k| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 3.71k|#define MORPH_STEM "st:" ------------------ | Branch (1872:11): [True: 3.71k, False: 0] ------------------ 1873| 3.71k| result.push_back(MSEP_FLD); ------------------ | | 121| 3.71k|#define MSEP_FLD ' ' ------------------ 1874| 3.71k| result.append(MORPH_STEM); ------------------ | | 103| 3.71k|#define MORPH_STEM "st:" ------------------ 1875| 3.71k| result.append(w); 1876| 3.71k| } 1877| 3.71k| if (HENTRY_DATA(rv)) { ------------------ | Branch (1877:11): [True: 0, False: 3.71k] ------------------ 1878| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 1879| 0| result.append(HENTRY_DATA2(rv)); 1880| 0| } 1881| 3.71k| result.push_back(MSEP_REC); ------------------ | | 122| 3.71k|#define MSEP_REC '\n' ------------------ 1882| 3.71k| } 1883| 3.71k| rv = rv->next_homonym; 1884| 3.71k| } 1885| | 1886| 13.6k| AffixScratch scratch; 1887| 13.6k| std::string st = pAMgr->affix_check_morph(w, 0, w.size(), scratch); 1888| 13.6k| if (!st.empty()) { ------------------ | Branch (1888:7): [True: 0, False: 13.6k] ------------------ 1889| 0| result.append(st); 1890| 0| } 1891| | 1892| 13.6k| if (pAMgr->get_compound() && result.empty()) { ------------------ | Branch (1892:7): [True: 2.83k, False: 10.8k] | Branch (1892:32): [True: 2.05k, False: 779] ------------------ 1893| 2.05k| struct hentry* rwords[100] = {}; // buffer for COMPOUND pattern checking 1894| 2.05k| pAMgr->compound_check_morph(w, 0, 0, 100, 0, nullptr, (hentry**)&rwords, 0, result, nullptr, scratch); 1895| 2.05k| } 1896| | 1897| 13.6k| line_uniq(result, MSEP_REC); ------------------ | | 122| 13.6k|#define MSEP_REC '\n' ------------------ 1898| | 1899| 13.6k| return result; 1900| 13.6k|} _ZN10SuggestMgr18suggest_hentry_genEP6hentryPKc: 1925| 558k|std::string SuggestMgr::suggest_hentry_gen(hentry* rv, const char* pattern) { 1926| 558k| std::string result; 1927| 558k| int sfxcount = get_sfxcount(pattern); 1928| | 1929| 558k| if (get_sfxcount(HENTRY_DATA(rv)) > sfxcount) ------------------ | Branch (1929:7): [True: 0, False: 558k] ------------------ 1930| 0| return result; 1931| | 1932| 558k| if (HENTRY_DATA(rv)) { ------------------ | Branch (1932:7): [True: 0, False: 558k] ------------------ 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| 558k| char* p = nullptr; 1943| 558k| if (HENTRY_DATA(rv)) ------------------ | Branch (1943:7): [True: 0, False: 558k] ------------------ 1944| 0| p = (char*)strstr(HENTRY_DATA2(rv), MORPH_ALLOMORPH); ------------------ | | 104| 0|#define MORPH_ALLOMORPH "al:" ------------------ 1945| 558k| while (p) { ------------------ | Branch (1945:10): [True: 0, False: 558k] ------------------ 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| 558k| return result; 1971| 558k|} _ZN10SuggestMgr11suggest_genERKNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_NS0_6chrono10time_pointINSE_12steady_clockENSE_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 1974| 297k| std::chrono::steady_clock::time_point start_time) { 1975| 297k| if (desc.empty() || !pAMgr) ------------------ | Branch (1975:7): [True: 150k, False: 146k] | Branch (1975:23): [True: 0, False: 146k] ------------------ 1976| 150k| return {}; 1977| | 1978| 146k| const char* pattern = in_pattern.c_str(); 1979| 146k| std::string result2; 1980| 146k| std::string newpattern; 1981| 146k| struct hentry* rv = nullptr; 1982| | 1983| | // search affixed forms with and without derivational suffixes 1984| 196k| while (true) { ------------------ | Branch (1984:10): [True: 196k, Folded] ------------------ 1985| 243k| for (const auto& k : desc) { ------------------ | Branch (1985:24): [True: 243k, False: 196k] ------------------ 1986| 243k| if (std::chrono::steady_clock::now() - start_time > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 243k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1986:11): [True: 0, False: 243k] ------------------ 1987| 0| return result2; 1988| 243k| std::string result; 1989| | 1990| | // add compound word parts (except the last one) 1991| 243k| const char* s = k.c_str(); 1992| 243k| const char* part = strstr(s, MORPH_PART); ------------------ | | 116| 243k|#define MORPH_PART "pa:" ------------------ 1993| 243k| if (part) { ------------------ | Branch (1993:11): [True: 0, False: 243k] ------------------ 1994| 0| const char* nextpart = strstr(part + 1, MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 1995| 0| while (nextpart) { ------------------ | Branch (1995:16): [True: 0, False: 0] ------------------ 1996| 0| std::string field; 1997| 0| copy_field(field, part, MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 1998| 0| result.append(field); 1999| 0| part = nextpart; 2000| 0| nextpart = strstr(part + 1, MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2001| 0| } 2002| 0| s = part; 2003| 0| } 2004| | 2005| 243k| std::string tok(s); 2006| 243k| size_t pos = tok.find(" | "); 2007| 243k| while (pos != std::string::npos) { ------------------ | Branch (2007:14): [True: 0, False: 243k] ------------------ 2008| 0| tok[pos + 1] = MSEP_ALT; ------------------ | | 123| 0|#define MSEP_ALT '\v' ------------------ 2009| 0| pos = tok.find(" | ", pos); 2010| 0| } 2011| 243k| std::vector pl = line_tok(tok, MSEP_ALT); ------------------ | | 123| 243k|#define MSEP_ALT '\v' ------------------ 2012| 243k| for (auto& i : pl) { ------------------ | Branch (2012:20): [True: 243k, False: 243k] ------------------ 2013| | // remove inflectional and terminal suffixes 2014| 243k| size_t is = i.find(MORPH_INFL_SFX); ------------------ | | 110| 243k|#define MORPH_INFL_SFX "is:" ------------------ 2015| 243k| if (is != std::string::npos) ------------------ | Branch (2015:13): [True: 0, False: 243k] ------------------ 2016| 0| i.resize(is); 2017| 243k| size_t ts = i.find(MORPH_TERM_SFX); ------------------ | | 111| 243k|#define MORPH_TERM_SFX "ts:" ------------------ 2018| 243k| while (ts != std::string::npos) { ------------------ | Branch (2018:16): [True: 0, False: 243k] ------------------ 2019| 0| i[ts] = '_'; 2020| 0| ts = i.find(MORPH_TERM_SFX); ------------------ | | 111| 0|#define MORPH_TERM_SFX "ts:" ------------------ 2021| 0| } 2022| 243k| const char* st = strstr(s, MORPH_STEM); ------------------ | | 103| 243k|#define MORPH_STEM "st:" ------------------ 2023| 243k| if (st) { ------------------ | Branch (2023:13): [True: 232k, False: 11.9k] ------------------ 2024| 232k| copy_field(tok, st, MORPH_STEM); ------------------ | | 103| 232k|#define MORPH_STEM "st:" ------------------ 2025| 232k| rv = pAMgr->lookup(tok.c_str(), tok.size()); 2026| 511k| while (rv) { ------------------ | Branch (2026:18): [True: 279k, False: 232k] ------------------ 2027| 279k| if (std::chrono::steady_clock::now() - start_time > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 279k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (2027:17): [True: 0, False: 279k] ------------------ 2028| 0| return result2; 2029| 279k| std::string newpat(i); 2030| 279k| newpat.append(pattern); 2031| 279k| std::string sg = suggest_hentry_gen(rv, newpat.c_str()); 2032| 279k| if (sg.empty()) ------------------ | Branch (2032:17): [True: 279k, False: 0] ------------------ 2033| 279k| sg = suggest_hentry_gen(rv, pattern); 2034| 279k| if (!sg.empty()) { ------------------ | Branch (2034:17): [True: 0, False: 279k] ------------------ 2035| 0| std::vector gen = line_tok(sg, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2036| 0| for (auto& j : gen) { ------------------ | Branch (2036:28): [True: 0, False: 0] ------------------ 2037| 0| result2.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2038| 0| result2.append(result); 2039| 0| if (i.find(MORPH_SURF_PFX) != std::string::npos) { ------------------ | | 112| 0|#define MORPH_SURF_PFX "sp:" ------------------ | Branch (2039:21): [True: 0, False: 0] ------------------ 2040| 0| std::string field; 2041| 0| copy_field(field, i, MORPH_SURF_PFX); ------------------ | | 112| 0|#define MORPH_SURF_PFX "sp:" ------------------ 2042| 0| result2.append(field); 2043| 0| } 2044| 0| result2.append(j); 2045| 0| } 2046| 0| } 2047| 279k| rv = rv->next_homonym; 2048| 279k| } 2049| 232k| } 2050| 243k| } 2051| 243k| } 2052| | 2053| 196k| if (!result2.empty() || !strstr(pattern, MORPH_DERI_SFX)) ------------------ | | 109| 196k|#define MORPH_DERI_SFX "ds:" ------------------ | Branch (2053:9): [True: 0, False: 196k] | Branch (2053:29): [True: 146k, False: 50.3k] ------------------ 2054| 146k| break; 2055| | 2056| 50.3k| newpattern.assign(pattern); 2057| 50.3k| mystrrep(newpattern, MORPH_DERI_SFX, MORPH_TERM_SFX); ------------------ | | 109| 50.3k|#define MORPH_DERI_SFX "ds:" ------------------ mystrrep(newpattern, MORPH_DERI_SFX, MORPH_TERM_SFX); ------------------ | | 111| 50.3k|#define MORPH_TERM_SFX "ts:" ------------------ 2058| 50.3k| pattern = newpattern.c_str(); 2059| 50.3k| } 2060| 146k| return result2; 2061| 146k|} _ZN10SuggestMgr5ngramEiRKNSt3__16vectorI6w_charNS0_9allocatorIS2_EEEES7_i: 2067| 684k| int opt) { 2068| 684k| int nscore = 0, ns, l1 = su1.size(), l2 = su2.size(); 2069| | 2070| 684k| if (l2 == 0) ------------------ | Branch (2070:7): [True: 4.92k, False: 679k] ------------------ 2071| 4.92k| return 0; 2072| 1.08M| for (int j = 1; j <= n; j++) { ------------------ | Branch (2072:19): [True: 1.02M, False: 53.8k] ------------------ 2073| 1.02M| ns = 0; 2074| 4.83M| for (int i = 0; i <= (l1 - j); i++) { ------------------ | Branch (2074:21): [True: 3.80M, False: 1.02M] ------------------ 2075| 3.80M| int k = 0; 2076| 17.0M| for (int l = 0; l <= (l2 - j); l++) { ------------------ | Branch (2076:23): [True: 14.5M, False: 2.42M] ------------------ 2077| 19.8M| for (k = 0; k < j; k++) { ------------------ | Branch (2077:21): [True: 18.5M, False: 1.37M] ------------------ 2078| 18.5M| if (su1[i + k] != su2[l + k]) ------------------ | Branch (2078:15): [True: 13.2M, False: 5.29M] ------------------ 2079| 13.2M| break; 2080| 18.5M| } 2081| 14.5M| if (k == j) { ------------------ | Branch (2081:13): [True: 1.37M, False: 13.2M] ------------------ 2082| 1.37M| ns++; 2083| 1.37M| break; 2084| 1.37M| } 2085| 14.5M| } 2086| 3.80M| if (k != j && opt & NGRAM_WEIGHTED) { ------------------ | | 84| 2.42M|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2086:11): [True: 2.42M, False: 1.37M] | Branch (2086:21): [True: 114k, False: 2.31M] ------------------ 2087| 114k| ns--; 2088| 114k| if (i == 0 || i == l1 - j) ------------------ | Branch (2088:13): [True: 26.2k, False: 87.8k] | Branch (2088:23): [True: 41.6k, False: 46.1k] ------------------ 2089| 67.9k| ns--; // side weight 2090| 114k| } 2091| 3.80M| } 2092| 1.02M| nscore = nscore + ns; 2093| 1.02M| if (ns < 2 && !(opt & NGRAM_WEIGHTED)) ------------------ | | 84| 694k|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2093:9): [True: 694k, False: 332k] | Branch (2093:19): [True: 625k, False: 68.9k] ------------------ 2094| 625k| break; 2095| 1.02M| } 2096| | 2097| 679k| ns = 0; 2098| 679k| if (opt & NGRAM_LONGER_WORSE) ------------------ | | 81| 679k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ | Branch (2098:7): [True: 277k, False: 401k] ------------------ 2099| 277k| ns = (l2 - l1) - 2; 2100| 679k| if (opt & NGRAM_ANY_MISMATCH) ------------------ | | 82| 679k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ | Branch (2100:7): [True: 401k, False: 277k] ------------------ 2101| 401k| ns = abs(l2 - l1) - 2; 2102| 679k| ns = (nscore - ((ns > 0) ? ns : 0)); ------------------ | Branch (2102:19): [True: 113k, False: 566k] ------------------ 2103| 679k| return ns; 2104| 684k|} _ZN10SuggestMgr5ngramEiRKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_i: 2110| 902k| int opt) { 2111| 902k| int nscore = 0, ns, l1, l2 = s2.size(); 2112| | 2113| 902k| if (l2 == 0) ------------------ | Branch (2113:7): [True: 10.8k, False: 891k] ------------------ 2114| 10.8k| return 0; 2115| 891k| l1 = s1.size(); 2116| 1.64M| for (int j = 1; j <= n; j++) { ------------------ | Branch (2116:19): [True: 1.51M, False: 135k] ------------------ 2117| 1.51M| ns = 0; 2118| 10.8M| for (int i = 0; i <= (l1 - j); i++) { ------------------ | Branch (2118:21): [True: 9.38M, False: 1.51M] ------------------ 2119| | //s2 is haystack, s1[i..i+j) is needle 2120| 9.38M| if (s2.find(s1.c_str()+i, 0, j) != std::string::npos) { ------------------ | Branch (2120:11): [True: 3.65M, False: 5.72M] ------------------ 2121| 3.65M| ns++; 2122| 5.72M| } else if (opt & NGRAM_WEIGHTED) { ------------------ | | 84| 5.72M|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2122:18): [True: 413k, False: 5.31M] ------------------ 2123| 413k| ns--; 2124| 413k| if (i == 0 || i == l1 - j) ------------------ | Branch (2124:13): [True: 42.0k, False: 371k] | Branch (2124:23): [True: 117k, False: 253k] ------------------ 2125| 159k| ns--; // side weight 2126| 413k| } 2127| 9.38M| } 2128| 1.51M| nscore = nscore + ns; 2129| 1.51M| if (ns < 2 && !(opt & NGRAM_WEIGHTED)) ------------------ | | 84| 903k|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2129:9): [True: 903k, False: 608k] | Branch (2129:19): [True: 756k, False: 147k] ------------------ 2130| 756k| break; 2131| 1.51M| } 2132| | 2133| 891k| ns = 0; 2134| 891k| if (opt & NGRAM_LONGER_WORSE) ------------------ | | 81| 891k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ | Branch (2134:7): [True: 330k, False: 561k] ------------------ 2135| 330k| ns = (l2 - l1) - 2; 2136| 891k| if (opt & NGRAM_ANY_MISMATCH) ------------------ | | 82| 891k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ | Branch (2136:7): [True: 561k, False: 330k] ------------------ 2137| 561k| ns = abs(l2 - l1) - 2; 2138| 891k| ns = (nscore - ((ns > 0) ? ns : 0)); ------------------ | Branch (2138:19): [True: 193k, False: 698k] ------------------ 2139| 891k| return ns; 2140| 902k|} _ZN10SuggestMgr19leftcommonsubstringERKNSt3__16vectorI6w_charNS0_9allocatorIS2_EEEES7_: 2145| 578k| const std::vector& su2) { 2146| 578k| int l1 = su1.size(), l2 = su2.size(); 2147| | // decapitalize dictionary word 2148| 578k| if (complexprefixes) { ------------------ | Branch (2148:7): [True: 0, False: 578k] ------------------ 2149| 0| if (l1 && l2 && su1[l1 - 1] == su2[l2 - 1]) ------------------ | Branch (2149:9): [True: 0, False: 0] | Branch (2149:15): [True: 0, False: 0] | Branch (2149:21): [True: 0, False: 0] ------------------ 2150| 0| return 1; 2151| 578k| } else { 2152| 578k| unsigned short idx = su2.empty() ? 0 : (unsigned short)(su2[0]), ------------------ | Branch (2152:26): [True: 0, False: 578k] ------------------ 2153| 578k| otheridx = su1.empty() ? 0 : (unsigned short)(su1[0]); ------------------ | Branch (2153:31): [True: 12.9k, False: 565k] ------------------ 2154| 578k| if (otheridx != idx && (otheridx != unicodetolower(idx, langnum))) ------------------ | Branch (2154:9): [True: 541k, False: 37.1k] | Branch (2154:28): [True: 388k, False: 152k] ------------------ 2155| 388k| return 0; 2156| 189k| int i; 2157| 294k| for (i = 1; (i < l1) && (i < l2) && (su1[i] == su2[i]); ------------------ | Branch (2157:17): [True: 282k, False: 12.2k] | Branch (2157:29): [True: 266k, False: 15.0k] | Branch (2157:41): [True: 104k, False: 162k] ------------------ 2158| 189k| i++) 2159| 104k| ; 2160| 189k| return i; 2161| 578k| } 2162| 0| return 0; 2163| 578k|} _ZN10SuggestMgr19leftcommonsubstringEPKcS1_: 2168| 709k| const char* s2) { 2169| 709k| if (complexprefixes) { ------------------ | Branch (2169:7): [True: 59.9k, False: 649k] ------------------ 2170| 59.9k| int l1 = strlen(s1), l2 = strlen(s2); 2171| 59.9k| if (l1 && l1 <= l2 && s1[l1 - 1] == s2[l2 - 1]) ------------------ | Branch (2171:9): [True: 58.5k, False: 1.35k] | Branch (2171:15): [True: 29.9k, False: 28.6k] | Branch (2171:27): [True: 2.49k, False: 27.4k] ------------------ 2172| 2.49k| return 1; 2173| 649k| } else if (csconv) { ------------------ | Branch (2173:14): [True: 649k, False: 0] ------------------ 2174| 649k| const char* olds = s1; 2175| | // decapitalise dictionary word 2176| 649k| if ((*s1 != *s2) && (((unsigned char)*s1) != csconv[((unsigned char)*s2)].clower)) ------------------ | Branch (2176:9): [True: 585k, False: 63.8k] | Branch (2176:25): [True: 424k, False: 161k] ------------------ 2177| 424k| return 0; 2178| 453k| do { 2179| 453k| s1++; 2180| 453k| s2++; 2181| 453k| } while ((*s1 == *s2) && (*s1 != '\0')); ------------------ | Branch (2181:14): [True: 228k, False: 225k] | Branch (2181:30): [True: 228k, False: 407] ------------------ 2182| 225k| return (int)(s1 - olds); 2183| 649k| } 2184| 57.4k| return 0; 2185| 709k|} _ZN10SuggestMgr24commoncharacterpositionsEPKcS1_Pi: 2189| 76.9k| int* is_swap) { 2190| 76.9k| int num = 0, diff = 0, diffpos[2]; 2191| 76.9k| *is_swap = 0; 2192| 76.9k| if (utf8) { ------------------ | Branch (2192:7): [True: 23.1k, False: 53.8k] ------------------ 2193| 23.1k| std::vector su1; 2194| 23.1k| std::vector su2; 2195| 23.1k| int l1 = u8_u16(su1, s1), l2 = u8_u16(su2, s2); 2196| | 2197| 23.1k| if (l1 <= 0 || l2 <= 0) ------------------ | Branch (2197:9): [True: 2.57k, False: 20.5k] | Branch (2197:20): [True: 0, False: 20.5k] ------------------ 2198| 2.57k| return 0; 2199| | 2200| | // decapitalize dictionary word 2201| 20.5k| if (complexprefixes) { ------------------ | Branch (2201:9): [True: 0, False: 20.5k] ------------------ 2202| 0| su2[l2 - 1] = lower_utf(su2[l2 - 1], langnum); 2203| 20.5k| } else { 2204| 20.5k| su2[0] = lower_utf(su2[0], langnum); 2205| 20.5k| } 2206| 78.9k| for (int i = 0; (i < l1) && (i < l2); i++) { ------------------ | Branch (2206:21): [True: 63.3k, False: 15.5k] | Branch (2206:33): [True: 58.3k, False: 4.95k] ------------------ 2207| 58.3k| if (su1[i] == su2[i]) { ------------------ | Branch (2207:11): [True: 30.5k, False: 27.7k] ------------------ 2208| 30.5k| num++; 2209| 30.5k| } else { 2210| 27.7k| if (diff < 2) ------------------ | Branch (2210:13): [True: 23.2k, False: 4.53k] ------------------ 2211| 23.2k| diffpos[diff] = i; 2212| 27.7k| diff++; 2213| 27.7k| } 2214| 58.3k| } 2215| 20.5k| if ((diff == 2) && (l1 == l2) && ------------------ | Branch (2215:9): [True: 4.11k, False: 16.4k] | Branch (2215:24): [True: 1.05k, False: 3.05k] ------------------ 2216| 1.05k| (su1[diffpos[0]] == su2[diffpos[1]]) && ------------------ | Branch (2216:9): [True: 175, False: 880] ------------------ 2217| 175| (su1[diffpos[1]] == su2[diffpos[0]])) ------------------ | Branch (2217:9): [True: 36, False: 139] ------------------ 2218| 36| *is_swap = 1; 2219| 53.8k| } else { 2220| 53.8k| size_t i; 2221| 53.8k| std::string t(s2); 2222| | // decapitalize dictionary word 2223| 53.8k| if (complexprefixes) { ------------------ | Branch (2223:9): [True: 3.18k, False: 50.6k] ------------------ 2224| 3.18k| size_t l2 = t.size(); 2225| 3.18k| t[l2 - 1] = csconv[(unsigned char)t[l2 - 1]].clower; 2226| 50.6k| } else { 2227| 50.6k| mkallsmall(t, csconv); 2228| 50.6k| } 2229| 292k| for (i = 0; i < t.size() && (*(s1 + i) != 0); ++i) { ------------------ | Branch (2229:17): [True: 267k, False: 25.4k] | Branch (2229:33): [True: 239k, False: 28.3k] ------------------ 2230| 239k| if (*(s1 + i) == t[i]) { ------------------ | Branch (2230:11): [True: 116k, False: 122k] ------------------ 2231| 116k| num++; 2232| 122k| } else { 2233| 122k| if (diff < 2) ------------------ | Branch (2233:13): [True: 68.0k, False: 54.1k] ------------------ 2234| 68.0k| diffpos[diff] = i; 2235| 122k| diff++; 2236| 122k| } 2237| 239k| } 2238| 53.8k| if ((diff == 2) && (*(s1 + i) == 0) && i == t.size() && ------------------ | Branch (2238:9): [True: 13.8k, False: 39.9k] | Branch (2238:24): [True: 11.1k, False: 2.69k] | Branch (2238:44): [True: 3.90k, False: 7.24k] ------------------ 2239| 3.90k| (*(s1 + diffpos[0]) == t[diffpos[1]]) && ------------------ | Branch (2239:9): [True: 687, False: 3.21k] ------------------ 2240| 687| (*(s1 + diffpos[1]) == t[diffpos[0]])) ------------------ | Branch (2240:9): [True: 50, False: 637] ------------------ 2241| 50| *is_swap = 1; 2242| 53.8k| } 2243| 74.3k| return num; 2244| 76.9k|} _ZN10SuggestMgr10bubblesortEPPcS1_Pii: 2255| 102k|void SuggestMgr::bubblesort(char** rword, char** rword2, int* rsc, int n) { 2256| 102k| int m = 1; 2257| 19.9M| while (m < n) { ------------------ | Branch (2257:10): [True: 19.8M, False: 102k] ------------------ 2258| 19.8M| int j = m; 2259| 41.1M| while (j > 0) { ------------------ | Branch (2259:12): [True: 41.0M, False: 28.7k] ------------------ 2260| 41.0M| if (rsc[j - 1] < rsc[j]) { ------------------ | Branch (2260:11): [True: 21.2M, False: 19.8M] ------------------ 2261| 21.2M| int sctmp = rsc[j - 1]; 2262| 21.2M| char* wdtmp = rword[j - 1]; 2263| 21.2M| rsc[j - 1] = rsc[j]; 2264| 21.2M| rword[j - 1] = rword[j]; 2265| 21.2M| rsc[j] = sctmp; 2266| 21.2M| rword[j] = wdtmp; 2267| 21.2M| if (rword2) { ------------------ | Branch (2267:13): [True: 20.7M, False: 563k] ------------------ 2268| 20.7M| wdtmp = rword2[j - 1]; 2269| 20.7M| rword2[j - 1] = rword2[j]; 2270| 20.7M| rword2[j] = wdtmp; 2271| 20.7M| } 2272| 21.2M| j--; 2273| 21.2M| } else 2274| 19.8M| break; 2275| 41.0M| } 2276| 19.8M| m++; 2277| 19.8M| } 2278| 102k|} _ZN10SuggestMgr3lcsEPKcS1_PiS2_: 2284| 86.3k| int* l2) { 2285| 86.3k| int n, m, i, j; 2286| 86.3k| std::vector su; 2287| 86.3k| std::vector su2; 2288| 86.3k| if (utf8) { ------------------ | Branch (2288:7): [True: 25.2k, False: 61.1k] ------------------ 2289| 25.2k| m = u8_u16(su, s); 2290| 25.2k| n = u8_u16(su2, s2); 2291| 61.1k| } else { 2292| 61.1k| m = strlen(s); 2293| 61.1k| n = strlen(s2); 2294| 61.1k| } 2295| 86.3k| if (m <= 0 || n <= 0) { ------------------ | Branch (2295:7): [True: 6.48k, False: 79.8k] | Branch (2295:17): [True: 0, False: 79.8k] ------------------ 2296| 6.48k| *l1 = 0; 2297| 6.48k| *l2 = 0; 2298| 6.48k| return nullptr; 2299| 6.48k| } 2300| 79.8k| char* c = new char[(m + 1) * (n + 1)](); 2301| 79.8k| char* b = new char[(m + 1) * (n + 1)](); 2302| 462k| for (i = 1; i <= m; i++) { ------------------ | Branch (2302:15): [True: 382k, False: 79.8k] ------------------ 2303| 4.24M| for (j = 1; j <= n; j++) { ------------------ | Branch (2303:17): [True: 3.86M, False: 382k] ------------------ 2304| 3.86M| if (((utf8) && (su[i - 1] == su2[j - 1])) || ------------------ | Branch (2304:12): [True: 332k, False: 3.53M] | Branch (2304:22): [True: 72.9k, False: 259k] ------------------ 2305| 3.79M| ((!utf8) && (s[i - 1] == s2[j - 1]))) { ------------------ | Branch (2305:12): [True: 3.53M, False: 259k] | Branch (2305:23): [True: 422k, False: 3.10M] ------------------ 2306| 494k| c[i * (n + 1) + j] = c[(i - 1) * (n + 1) + j - 1] + 1; 2307| 494k| b[i * (n + 1) + j] = LCS_UPLEFT; 2308| 3.36M| } else if (c[(i - 1) * (n + 1) + j] >= c[i * (n + 1) + j - 1]) { ------------------ | Branch (2308:18): [True: 2.51M, False: 851k] ------------------ 2309| 2.51M| c[i * (n + 1) + j] = c[(i - 1) * (n + 1) + j]; 2310| 2.51M| b[i * (n + 1) + j] = LCS_UP; 2311| 2.51M| } else { 2312| 851k| c[i * (n + 1) + j] = c[i * (n + 1) + j - 1]; 2313| 851k| b[i * (n + 1) + j] = LCS_LEFT; 2314| 851k| } 2315| 3.86M| } 2316| 382k| } 2317| 79.8k| delete[] c; 2318| 79.8k| *l1 = m; 2319| 79.8k| *l2 = n; 2320| 79.8k| return b; 2321| 86.3k|} _ZN10SuggestMgr6lcslenEPKcS1_: 2323| 86.3k|int SuggestMgr::lcslen(const char* s, const char* s2) { 2324| 86.3k| int m, n, len = 0; 2325| 86.3k| char* result = lcs(s, s2, &m, &n); 2326| 86.3k| if (!result) ------------------ | Branch (2326:7): [True: 6.48k, False: 79.8k] ------------------ 2327| 6.48k| return 0; 2328| 79.8k| int i = m, j = n; 2329| 637k| while ((i != 0) && (j != 0)) { ------------------ | Branch (2329:10): [True: 563k, False: 73.1k] | Branch (2329:22): [True: 557k, False: 6.74k] ------------------ 2330| 557k| if (result[i * (n + 1) + j] == LCS_UPLEFT) { ------------------ | Branch (2330:9): [True: 210k, False: 346k] ------------------ 2331| 210k| len++; 2332| 210k| i--; 2333| 210k| j--; 2334| 346k| } else if (result[i * (n + 1) + j] == LCS_UP) { ------------------ | Branch (2334:16): [True: 160k, False: 185k] ------------------ 2335| 160k| i--; 2336| 160k| } else 2337| 185k| j--; 2338| 557k| } 2339| 79.8k| delete[] result; 2340| 79.8k| return len; 2341| 86.3k|} _ZN10SuggestMgr6lcslenERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 2343| 6.78k|int SuggestMgr::lcslen(const std::string& s, const std::string& s2) { 2344| 6.78k| return lcslen(s.c_str(), s2.c_str()); 2345| 6.78k|} suggestmgr.cxx:_ZN12_GLOBAL__N_115ngsuggest_guardC2EbPK7cs_infoPiPS3_: 1164| 62.4k| : m_nonbmp(nonbmp) 1165| 62.4k| , m_origconv(origconv) 1166| 62.4k| , m_utf8(utf8) 1167| 62.4k| , m_csconv(csconv) 1168| 62.4k| { 1169| 62.4k| } suggestmgr.cxx:_ZN12_GLOBAL__N_115ngsuggest_guardD2Ev: 1172| 62.4k| { 1173| 62.4k| if (m_nonbmp) { ------------------ | Branch (1173:11): [True: 1.72k, False: 60.7k] ------------------ 1174| 1.72k| *m_csconv = m_origconv; 1175| 1.72k| *m_utf8 = 1; 1176| 1.72k| } 1177| 62.4k| } suggestmgr.cxx:_ZL12get_sfxcountPKc: 1902| 1.11M|static int get_sfxcount(const char* morph) { 1903| 1.11M| if (!morph || !*morph) ------------------ | Branch (1903:7): [True: 558k, False: 558k] | Branch (1903:17): [True: 0, False: 558k] ------------------ 1904| 558k| return 0; 1905| 558k| int n = 0; 1906| 558k| const char* old = morph; 1907| 558k| morph = strstr(morph, MORPH_DERI_SFX); ------------------ | | 109| 558k|#define MORPH_DERI_SFX "ds:" ------------------ 1908| 558k| if (!morph) ------------------ | Branch (1908:7): [True: 415k, False: 143k] ------------------ 1909| 415k| morph = strstr(old, MORPH_INFL_SFX); ------------------ | | 110| 415k|#define MORPH_INFL_SFX "is:" ------------------ 1910| 558k| if (!morph) ------------------ | Branch (1910:7): [True: 413k, False: 145k] ------------------ 1911| 413k| morph = strstr(old, MORPH_TERM_SFX); ------------------ | | 111| 413k|#define MORPH_TERM_SFX "ts:" ------------------ 1912| 931k| while (morph) { ------------------ | Branch (1912:10): [True: 372k, False: 558k] ------------------ 1913| 372k| n++; 1914| 372k| old = morph; 1915| 372k| morph = strstr(morph + 1, MORPH_DERI_SFX); ------------------ | | 109| 372k|#define MORPH_DERI_SFX "ds:" ------------------ 1916| 372k| if (!morph) ------------------ | Branch (1916:9): [True: 330k, False: 41.5k] ------------------ 1917| 330k| morph = strstr(old + 1, MORPH_INFL_SFX); ------------------ | | 110| 330k|#define MORPH_INFL_SFX "is:" ------------------ 1918| 372k| if (!morph) ------------------ | Branch (1918:9): [True: 330k, False: 41.6k] ------------------ 1919| 330k| morph = strstr(old + 1, MORPH_TERM_SFX); ------------------ | | 111| 330k|#define MORPH_TERM_SFX "ts:" ------------------ 1920| 372k| } 1921| 558k| return n; 1922| 1.11M|} _ZNK6w_charcvtEv: 57| 248M| { 58| 248M|#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| 248M| unsigned short u; 64| 248M| memcpy(&u, this, sizeof(unsigned short)); 65| 248M| return u; 66| 248M|#endif 67| | 68| |#else 69| | return ((unsigned short)h << 8) | (unsigned short)l; 70| |#endif 71| 248M| } _Zlt6w_charS_: 73| 18.9M| friend bool operator<(const w_char a, const w_char b) { 74| 18.9M| return (unsigned short)a < (unsigned short)b; 75| 18.9M| } _Zeq6w_charS_: 77| 87.6M| friend bool operator==(const w_char a, const w_char b) { 78| 87.6M| return (unsigned short)a == (unsigned short)b; 79| 87.6M| } _Zne6w_charS_: 81| 85.1M| friend bool operator!=(const w_char a, const w_char b) { 82| 85.1M| return !(a == b); 83| 85.1M| } _Z8endswithRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEES7_: 40| 198|{ 41| 198| return str.size() >= suffix.size() && ------------------ | Branch (41:12): [True: 190, False: 8] ------------------ 42| 190| str.compare(str.size() - suffix.size(), suffix.size(), suffix) == 0; ------------------ | Branch (42:12): [True: 38, False: 152] ------------------ 43| 198|} 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| 200| while ((direntry = readdir(d)) != NULL) ------------------ | Branch (54:12): [True: 198, False: 2] ------------------ 55| 198| { 56| 198| std::string entry(direntry->d_name); 57| 198| if (endswith(entry, ".aff")) ------------------ | Branch (57:13): [True: 38, False: 160] ------------------ 58| 38| affs.push_back(std::move(entry)); 59| 198| } 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| 3.16k|{ 77| 3.16k| std::string word(data, size); 78| 3.16k| for (auto& dict : dictionaries) ------------------ | Branch (78:21): [True: 60.0k, False: 3.16k] ------------------ 79| 60.0k| { 80| 60.0k| if (!dict->spell(word)) ------------------ | Branch (80:13): [True: 59.6k, False: 431] ------------------ 81| 59.6k| dict->suggest(word); 82| 60.0k| } 83| 3.16k| return 0; 84| 3.16k|}