_ZN8PfxEntryC2EP8AffixMgr: 90| 8| : pmyMgr(pmgr) 91| 8| , next(nullptr) 92| 8| , nexteq(nullptr) 93| 8| , nextne(nullptr) 94| 8| , flgnxt(nullptr) {} _ZN8PfxEntry3addEPKcm: 97| 11|std::string PfxEntry::add(const char* word, size_t len) { 98| 11| std::string result; 99| 11| if ((len > strip.size() || (len == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (99:7): [True: 11, False: 0] | Branch (99:8): [True: 11, False: 0] | Branch (99:31): [True: 0, False: 0] | Branch (99:43): [True: 0, False: 0] ------------------ 100| 11| (len >= numconds) && test_condition(word) && ------------------ | Branch (100:7): [True: 11, False: 0] | Branch (100:28): [True: 11, False: 0] ------------------ 101| 11| (strip.empty() || ------------------ | Branch (101:8): [True: 11, False: 0] ------------------ 102| 11| (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| 11| result.assign(appnd); 105| 11| result.append(word + strip.size()); 106| 11| } 107| 11| return result; 108| 11|} _ZN8PfxEntry9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 213| 1.36M| AffixScratch& scratch) { 214| 1.36M| 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| 1.36M| int tmpl = len - appnd.size(); // length of tmpword 222| | 223| 1.36M| if (tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) { ------------------ | Branch (223:7): [True: 1.36M, False: 2.77k] | Branch (223:20): [True: 2.77k, False: 0] | Branch (223:33): [True: 0, False: 2.77k] ------------------ 224| | // generate new root word by removing prefix and adding 225| | // back any characters that would have been stripped 226| | 227| 1.36M| std::string& tmpword = scratch.pfx_check_word; 228| 1.36M| tmpword.assign(strip); 229| 1.36M| 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| 1.36M| if (test_condition(tmpword)) { ------------------ | Branch (239:9): [True: 16.4k, False: 1.34M] ------------------ 240| 16.4k| tmpl += strip.size(); 241| 16.4k| if ((he = pmyMgr->lookup(tmpword.c_str(), tmpword.size())) != nullptr) { ------------------ | Branch (241:11): [True: 3, False: 16.4k] ------------------ 242| 3| do { 243| 3| if (TESTAFF(he->astr, aflag, he->alen) && ------------------ | | 99| 6|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 3] | | ------------------ ------------------ | Branch (243:15): [True: 0, False: 3] ------------------ 244| | // forbid single prefixes with needaffix flag 245| 0| !TESTAFF(contclass, pmyMgr->get_needaffix(), contclasslen) && ------------------ | | 99| 3|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (245:15): [True: 0, False: 0] ------------------ 246| | // a circumfix prefix needs a matching circumfix suffix, so it 247| | // cannot stand on its own 248| 0| !TESTAFF(contclass, pmyMgr->get_circumfix(), contclasslen) && ------------------ | | 99| 3|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (248:15): [True: 0, False: 0] ------------------ 249| | // needflag 250| 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 (250:16): [True: 0, False: 0] ------------------ 251| 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 (251:17): [True: 0, False: 0] ------------------ 252| 0| return he; 253| 3| he = he->next_homonym; // check homonyms 254| 3| } while (he); ------------------ | Branch (254:18): [True: 0, False: 3] ------------------ 255| 3| } 256| | 257| | // prefix matched but no root word was found 258| | // if aeXPRODUCT is allowed, try again but now 259| | // ross checked combined with a suffix 260| | 261| | // if ((opts & aeXPRODUCT) && in_compound) { 262| 16.4k| if ((opts & aeXPRODUCT)) { ------------------ | | 65| 16.4k|#define aeXPRODUCT (1 << 0) ------------------ | Branch (262:11): [True: 16.4k, False: 0] ------------------ 263| 16.4k| he = pmyMgr->suffix_check(tmpword, 0, tmpl, aeXPRODUCT, this, ------------------ | | 65| 16.4k|#define aeXPRODUCT (1 << 0) ------------------ 264| 16.4k| scratch, FLAG_NULL, needflag, in_compound); ------------------ | | 96| 16.4k|#define FLAG_NULL 0x00 ------------------ 265| 16.4k| if (he) ------------------ | Branch (265:13): [True: 0, False: 16.4k] ------------------ 266| 0| return he; 267| 16.4k| } 268| 16.4k| } 269| 1.36M| } 270| 1.36M| return nullptr; 271| 1.36M|} _ZN8PfxEntry12check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 279| 1.35M| AffixScratch& scratch) { 280| | // on entry prefix is 0 length or already matches the beginning of the word. 281| | // So if the remaining root word has positive length 282| | // and if there are enough chars in root word and added back strip chars 283| | // to meet the number of characters conditions, then test it 284| | 285| 1.35M| int tmpl = len - appnd.size(); // length of tmpword 286| | 287| 1.35M| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (287:8): [True: 1.35M, False: 2.70k] | Branch (287:21): [True: 2.70k, False: 0] | Branch (287:34): [True: 0, False: 2.70k] ------------------ 288| 1.35M| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (288:7): [True: 1.30M, False: 50.9k] ------------------ 289| | // generate new root word by removing prefix and adding 290| | // back any characters that would have been stripped 291| | 292| 1.30M| std::string& tmpword = scratch.pfx_check_twosfx; 293| 1.30M| tmpword.assign(strip); 294| 1.30M| tmpword.append(word, start + appnd.size(), tmpl); 295| | 296| | // now make sure all of the conditions on characters 297| | // are met. Please see the appendix at the end of 298| | // this file for more info on exactly what is being 299| | // tested 300| | 301| | // if all conditions are met then check if resulting 302| | // root word in the dictionary 303| | 304| 1.30M| if (test_condition(tmpword)) { ------------------ | Branch (304:9): [True: 11.6k, False: 1.29M] ------------------ 305| 11.6k| tmpl += strip.size(); 306| | 307| | // prefix matched but no root word was found 308| | // if aeXPRODUCT is allowed, try again but now 309| | // cross checked combined with a suffix 310| | 311| 11.6k| if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 65| 11.6k|#define aeXPRODUCT (1 << 0) ------------------ if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 73| 11.6k|#define IN_CPD_BEGIN 1 ------------------ | Branch (311:11): [True: 11.6k, False: 0] | Branch (311:34): [True: 11.6k, False: 0] ------------------ 312| | // hash entry of root word or NULL 313| 11.6k| struct hentry* he = pmyMgr->suffix_check_twosfx(tmpword, 0, tmpl, aeXPRODUCT, this, ------------------ | | 65| 11.6k|#define aeXPRODUCT (1 << 0) ------------------ 314| 11.6k| scratch, needflag); 315| 11.6k| if (he) ------------------ | Branch (315:13): [True: 0, False: 11.6k] ------------------ 316| 0| return he; 317| 11.6k| } 318| 11.6k| } 319| 1.30M| } 320| 1.35M| return nullptr; 321| 1.35M|} _ZN8PfxEntry18check_twosfx_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 329| 575| AffixScratch& scratch) { 330| 575| std::string result; 331| | // on entry prefix is 0 length or already matches the beginning of the word. 332| | // So if the remaining root word has positive length 333| | // and if there are enough chars in root word and added back strip chars 334| | // to meet the number of characters conditions, then test it 335| 575| int tmpl = len - appnd.size(); // length of tmpword 336| | 337| 575| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (337:8): [True: 575, False: 0] | Branch (337:21): [True: 0, False: 0] | Branch (337:34): [True: 0, False: 0] ------------------ 338| 575| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (338:7): [True: 484, False: 91] ------------------ 339| | // generate new root word by removing prefix and adding 340| | // back any characters that would have been stripped 341| | 342| 484| std::string& tmpword = scratch.pfx_check_twosfx; 343| 484| tmpword.assign(strip); 344| 484| tmpword.append(word, start + appnd.size(), tmpl); 345| | 346| | // now make sure all of the conditions on characters 347| | // are met. Please see the appendix at the end of 348| | // this file for more info on exactly what is being 349| | // tested 350| | 351| | // if all conditions are met then check if resulting 352| | // root word in the dictionary 353| | 354| 484| if (test_condition(tmpword)) { ------------------ | Branch (354:9): [True: 0, False: 484] ------------------ 355| 0| tmpl += strip.size(); 356| | 357| | // prefix matched but no root word was found 358| | // if aeXPRODUCT is allowed, try again but now 359| | // ross checked combined with a suffix 360| | 361| 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 (361:11): [True: 0, False: 0] | Branch (361:34): [True: 0, False: 0] ------------------ 362| 0| result = pmyMgr->suffix_check_twosfx_morph(tmpword, 0, tmpl, 363| 0| aeXPRODUCT, ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ 364| 0| this, scratch, needflag); 365| 0| } 366| 0| } 367| 484| } 368| 575| return result; 369| 575|} _ZN8PfxEntry11check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiictR12AffixScratch: 377| 576| AffixScratch& scratch) { 378| 576| std::string result; 379| | 380| | // on entry prefix is 0 length or already matches the beginning of the word. 381| | // So if the remaining root word has positive length 382| | // and if there are enough chars in root word and added back strip chars 383| | // to meet the number of characters conditions, then test it 384| | 385| 576| int tmpl = len - appnd.size(); // length of tmpword 386| | 387| 576| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (387:8): [True: 576, False: 0] | Branch (387:21): [True: 0, False: 0] | Branch (387:34): [True: 0, False: 0] ------------------ 388| 576| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (388:7): [True: 485, False: 91] ------------------ 389| | // generate new root word by removing prefix and adding 390| | // back any characters that would have been stripped 391| | 392| 485| std::string& tmpword = scratch.pfx_check_word; 393| 485| tmpword.assign(strip); 394| 485| tmpword.append(word, start + appnd.size(), tmpl); 395| | 396| | // now make sure all of the conditions on characters 397| | // are met. Please see the appendix at the end of 398| | // this file for more info on exactly what is being 399| | // tested 400| | 401| | // if all conditions are met then check if resulting 402| | // root word in the dictionary 403| | 404| 485| if (test_condition(tmpword)) { ------------------ | Branch (404:9): [True: 1, False: 484] ------------------ 405| 1| tmpl += strip.size(); 406| 1| struct hentry* he; // hash entry of root word or NULL 407| 1| if ((he = pmyMgr->lookup(tmpword.c_str(), tmpword.size())) != nullptr) { ------------------ | Branch (407:11): [True: 0, False: 1] ------------------ 408| 0| do { 409| 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 (409:15): [True: 0, False: 0] ------------------ 410| | // forbid single prefixes with needaffix flag 411| 0| !TESTAFF(contclass, pmyMgr->get_needaffix(), contclasslen) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (411:15): [True: 0, False: 0] ------------------ 412| | // a circumfix prefix needs a matching circumfix suffix, so it 413| | // cannot stand on its own 414| 0| !TESTAFF(contclass, pmyMgr->get_circumfix(), contclasslen) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (414:15): [True: 0, False: 0] ------------------ 415| | // needflag 416| 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 (416:16): [True: 0, False: 0] ------------------ 417| 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 (417:17): [True: 0, False: 0] ------------------ 418| 0| if (morphcode) { ------------------ | Branch (418:17): [True: 0, False: 0] ------------------ 419| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 420| 0| result.append(morphcode); 421| 0| } else 422| 0| result.append(getKey()); 423| 0| if (!HENTRY_FIND(he, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (423:17): [True: 0, False: 0] ------------------ 424| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 425| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 426| 0| result.append(HENTRY_WORD(he)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 427| 0| } 428| | // store the pointer of the hash entry 429| 0| if (HENTRY_DATA(he)) { ------------------ | Branch (429:17): [True: 0, False: 0] ------------------ 430| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 431| 0| result.append(HENTRY_DATA2(he)); 432| 0| } else { 433| | // return with debug information 434| 0| std::string flag = pmyMgr->encode_flag(getFlag()); 435| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 436| 0| result.append(MORPH_FLAG); ------------------ | | 117| 0|#define MORPH_FLAG "fl:" ------------------ 437| 0| result.append(flag); 438| 0| } 439| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 440| 0| } 441| 0| he = he->next_homonym; 442| 0| } while (he); ------------------ | Branch (442:18): [True: 0, False: 0] ------------------ 443| 0| } 444| | 445| | // prefix matched but no root word was found 446| | // if aeXPRODUCT is allowed, try again but now 447| | // ross checked combined with a suffix 448| | 449| 1| if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 65| 1|#define aeXPRODUCT (1 << 0) ------------------ if ((opts & aeXPRODUCT) && (in_compound != IN_CPD_BEGIN)) { ------------------ | | 73| 1|#define IN_CPD_BEGIN 1 ------------------ | Branch (449:11): [True: 1, False: 0] | Branch (449:34): [True: 1, False: 0] ------------------ 450| 1| std::string st = pmyMgr->suffix_check_morph(tmpword, 0, tmpl, aeXPRODUCT, this, ------------------ | | 65| 1|#define aeXPRODUCT (1 << 0) ------------------ 451| 1| scratch, FLAG_NULL, needflag); ------------------ | | 96| 1|#define FLAG_NULL 0x00 ------------------ 452| 1| if (!st.empty()) { ------------------ | Branch (452:13): [True: 0, False: 1] ------------------ 453| 0| result.append(st); 454| 0| } 455| 1| } 456| 1| } 457| 485| } 458| | 459| 576| return result; 460| 576|} _ZN8SfxEntryC2EP8AffixMgr: 463| 34| : pmyMgr(pmgr) // register affix manager 464| 34| , next(nullptr) 465| 34| , nexteq(nullptr) 466| 34| , nextne(nullptr) 467| 34| , flgnxt(nullptr) 468| 34| , l_morph(nullptr) 469| 34| , r_morph(nullptr) 470| 34| , eq_morph(nullptr) {} _ZN8SfxEntry3addEPKcm: 473| 28|std::string SfxEntry::add(const char* word, size_t len) { 474| 28| std::string result; 475| | /* make sure all conditions match */ 476| 28| if ((len > strip.size() || (len == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (476:8): [True: 28, False: 0] | Branch (476:31): [True: 0, False: 0] | Branch (476:43): [True: 0, False: 0] ------------------ 477| 28| (len >= numconds) && test_condition(word + len, word) && ------------------ | Branch (477:7): [True: 28, False: 0] | Branch (477:28): [True: 28, False: 0] ------------------ 478| 28| (strip.empty() || ------------------ | Branch (478:8): [True: 28, False: 0] ------------------ 479| 28| (len >= strip.size() && strcmp(word + len - strip.size(), strip.c_str()) == 0))) { ------------------ | Branch (479:9): [True: 0, False: 0] | Branch (479:32): [True: 0, False: 0] ------------------ 480| 28| result.assign(word, len); 481| | /* we have a match so add suffix */ 482| 28| result.replace(len - strip.size(), std::string::npos, appnd); 483| 28| } 484| 28| return result; 485| 28|} _ZN8SfxEntry9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntrytttR12AffixScratch: 627| 73.5k| AffixScratch& scratch) { 628| 73.5k| struct hentry* he; // hash entry pointer 629| 73.5k| PfxEntry* ep = ppfx; 630| | 631| | // if this suffix is being cross checked with a prefix 632| | // but it does not support cross products skip it 633| | 634| 73.5k| if (((optflags & aeXPRODUCT) != 0) && ((opts & aeXPRODUCT) == 0)) ------------------ | | 65| 73.5k|#define aeXPRODUCT (1 << 0) ------------------ if (((optflags & aeXPRODUCT) != 0) && ((opts & aeXPRODUCT) == 0)) ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ | Branch (634:7): [True: 0, False: 73.5k] | Branch (634:41): [True: 0, False: 0] ------------------ 635| 0| return nullptr; 636| | 637| | // upon entry suffix is 0 length or already matches the end of the word. 638| | // So if the remaining root word has positive length 639| | // and if there are enough chars in root word and added back strip chars 640| | // to meet the number of characters conditions, then test it 641| | 642| 73.5k| int tmpl = len - appnd.size(); // length of tmpword 643| | // the second condition is not enough for UTF-8 strings 644| | // it checked in test_condition() 645| | 646| 73.5k| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (646:8): [True: 72.2k, False: 1.31k] | Branch (646:21): [True: 1.31k, False: 0] | Branch (646:34): [True: 0, False: 1.31k] ------------------ 647| 72.2k| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (647:7): [True: 72.2k, False: 0] ------------------ 648| | // generate new root word by removing suffix and adding 649| | // back any characters that would have been stripped or 650| | // or null terminating the shorter string 651| | 652| 72.2k| std::string& tmpword = scratch.sfx_check_word; 653| 72.2k| tmpword.assign(word, start, tmpl); 654| 72.2k| if (!strip.empty()) { ------------------ | Branch (654:9): [True: 0, False: 72.2k] ------------------ 655| 0| tmpword.append(strip); 656| 0| } 657| | 658| 72.2k| const char* beg = tmpword.c_str(); 659| 72.2k| const char* end = beg + tmpword.size(); 660| | 661| | // now make sure all of the conditions on characters 662| | // are met. Please see the appendix at the end of 663| | // this file for more info on exactly what is being 664| | // tested 665| | 666| | // if all conditions are met then check if resulting 667| | // root word in the dictionary 668| | 669| 72.2k| if (test_condition(end, beg)) { ------------------ | Branch (669:9): [True: 72.2k, False: 3] ------------------ 670| |#ifdef SZOSZABLYA_POSSIBLE_ROOTS 671| | fprintf(stdout, "%s %s %c\n", word.c_str() + start, beg, aflag); 672| |#endif 673| 72.2k| if ((he = pmyMgr->lookup(tmpword.c_str(), tmpword.size())) != nullptr) { ------------------ | Branch (673:11): [True: 102, False: 72.1k] ------------------ 674| 102| do { 675| | // check conditional suffix (enabled by prefix) 676| 102| if ((TESTAFF(he->astr, aflag, he->alen) || ------------------ | | 99| 204|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 102] | | ------------------ ------------------ | Branch (676:15): [True: 0, False: 102] ------------------ 677| 102| (ep && ep->getCont() && ------------------ | Branch (677:17): [True: 0, False: 102] | Branch (677:23): [True: 0, False: 0] ------------------ 678| 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] | | ------------------ ------------------ 679| 0| (((optflags & aeXPRODUCT) == 0) || ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ | Branch (679:16): [True: 0, False: 0] ------------------ 680| 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 (680:17): [True: 0, False: 0] ------------------ 681| | // enabled by prefix 682| 0| ((contclass) && ------------------ | Branch (682:17): [True: 0, False: 0] ------------------ 683| 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 (683:18): [True: 0, False: 0] ------------------ 684| | // handle cont. class 685| 0| ((!cclass) || ------------------ | Branch (685:16): [True: 0, False: 0] ------------------ 686| 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 (686:17): [True: 0, False: 0] ------------------ 687| | // check only in compound homonyms (bad flags) 688| 0| (!badflag || !TESTAFF(he->astr, badflag, he->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (688:16): [True: 0, False: 0] | Branch (688:28): [True: 0, False: 0] ------------------ 689| | // handle required flag 690| 0| ((!needflag) || ------------------ | Branch (690:16): [True: 0, False: 0] ------------------ 691| 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] | | ------------------ ------------------ 692| 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 (692:18): [True: 0, False: 0] ------------------ 693| 0| return he; 694| 102| he = he->next_homonym; // check homonyms 695| 102| } while (he); ------------------ | Branch (695:18): [True: 0, False: 102] ------------------ 696| 102| } 697| 72.2k| } 698| 72.2k| } 699| 73.5k| return nullptr; 700| 73.5k|} _ZN8SfxEntry12check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntrytR12AffixScratch: 709| 36.4k| AffixScratch& scratch) { 710| 36.4k| PfxEntry* ep = ppfx; 711| | 712| | // if this suffix is being cross checked with a prefix 713| | // but it does not support cross products skip it 714| | 715| 36.4k| if ((optflags & aeXPRODUCT) != 0 && (opts & aeXPRODUCT) == 0) ------------------ | | 65| 36.4k|#define aeXPRODUCT (1 << 0) ------------------ if ((optflags & aeXPRODUCT) != 0 && (opts & aeXPRODUCT) == 0) ------------------ | | 65| 0|#define aeXPRODUCT (1 << 0) ------------------ | Branch (715:7): [True: 0, False: 36.4k] | Branch (715:39): [True: 0, False: 0] ------------------ 716| 0| return nullptr; 717| | 718| | // upon entry suffix is 0 length or already matches the end of the word. 719| | // So if the remaining root word has positive length 720| | // and if there are enough chars in root word and added back strip chars 721| | // to meet the number of characters conditions, then test it 722| | 723| 36.4k| int tmpl = len - appnd.size(); // length of tmpword 724| | 725| 36.4k| if ((tmpl > 0 || (tmpl == 0 && pmyMgr->get_fullstrip())) && ------------------ | Branch (725:8): [True: 36.3k, False: 105] | Branch (725:21): [True: 105, False: 0] | Branch (725:34): [True: 0, False: 105] ------------------ 726| 36.3k| (tmpl + strip.size() >= numconds)) { ------------------ | Branch (726:7): [True: 36.3k, False: 0] ------------------ 727| | // generate new root word by removing suffix and adding 728| | // back any characters that would have been stripped or 729| | // or null terminating the shorter string 730| | 731| 36.3k| std::string& tmpword = scratch.sfx_check_twosfx; 732| 36.3k| tmpword.assign(word, start); 733| 36.3k| tmpword.resize(tmpl); 734| 36.3k| tmpword.append(strip); 735| 36.3k| tmpl += strip.size(); 736| | 737| 36.3k| const char* beg = tmpword.c_str(); 738| 36.3k| const char* end = beg + tmpl; 739| | 740| | // now make sure all of the conditions on characters 741| | // are met. Please see the appendix at the end of 742| | // this file for more info on exactly what is being 743| | // tested 744| | 745| | // if all conditions are met then recall suffix_check 746| | 747| 36.3k| if (test_condition(end, beg)) { ------------------ | Branch (747:9): [True: 36.3k, False: 0] ------------------ 748| 36.3k| struct hentry* he; // hash entry pointer 749| 36.3k| if (ppfx) { ------------------ | Branch (749:11): [True: 0, False: 36.3k] ------------------ 750| | // handle conditional suffix 751| 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 (751:13): [True: 0, False: 0] | Branch (751:13): [True: 0, False: 0] ------------------ 752| 0| he = pmyMgr->suffix_check(tmpword, 0, tmpl, 0, nullptr, scratch, (FLAG)aflag, needflag, IN_CPD_NOT); ------------------ | | 72| 0|#define IN_CPD_NOT 0 ------------------ 753| 0| else 754| 0| he = pmyMgr->suffix_check(tmpword, 0, tmpl, optflags, ppfx, 755| 0| scratch, (FLAG)aflag, needflag, IN_CPD_NOT); ------------------ | | 72| 0|#define IN_CPD_NOT 0 ------------------ 756| 36.3k| } else { 757| 36.3k| he = pmyMgr->suffix_check(tmpword, 0, tmpl, 0, nullptr, scratch, (FLAG)aflag, needflag, IN_CPD_NOT); ------------------ | | 72| 36.3k|#define IN_CPD_NOT 0 ------------------ 758| 36.3k| } 759| 36.3k| if (he) ------------------ | Branch (759:11): [True: 0, False: 36.3k] ------------------ 760| 0| return he; 761| 36.3k| } 762| 36.3k| } 763| 36.4k| return nullptr; 764| 36.4k|} _ZN8SfxEntry15initReverseWordEv: 875| 34|void SfxEntry::initReverseWord() { 876| 34| rappnd = appnd; 877| 34| reverseword(rappnd); 878| 34|} _ZN8PfxEntry14test_conditionERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 125| 2.66M|inline int PfxEntry::test_condition(const std::string& s) { 126| 2.66M| size_t st = 0; 127| 2.66M| size_t pos = std::string::npos; // group with pos input position 128| 2.66M| bool neg = false; // complementer 129| 2.66M| bool ingroup = false; // character in the group 130| 2.66M| if (numconds == 0) ------------------ | Branch (130:7): [True: 4.81k, False: 2.66M] ------------------ 131| 4.81k| return 1; 132| 2.66M| char* p = c.conds; 133| 2.77M| while (true) { ------------------ | Branch (133:10): [True: 2.77M, Folded] ------------------ 134| 2.77M| switch (*p) { 135| 0| case '\0': ------------------ | Branch (135:7): [True: 0, False: 2.77M] ------------------ 136| 0| return 1; 137| 23.3k| case '[': { ------------------ | Branch (137:7): [True: 23.3k, False: 2.75M] ------------------ 138| 23.3k| neg = false; 139| 23.3k| ingroup = false; 140| 23.3k| p = nextchar(p); 141| 23.3k| pos = st; 142| 23.3k| break; 143| 0| } 144| 23.3k| case '^': { ------------------ | Branch (144:7): [True: 23.3k, False: 2.75M] ------------------ 145| 23.3k| p = nextchar(p); 146| 23.3k| neg = true; 147| 23.3k| break; 148| 0| } 149| 23.3k| case ']': { ------------------ | Branch (149:7): [True: 23.3k, False: 2.75M] ------------------ 150| 23.3k| if (bool(neg) == bool(ingroup)) ------------------ | Branch (150:13): [True: 0, False: 23.3k] ------------------ 151| 0| return 0; 152| 23.3k| pos = std::string::npos; 153| 23.3k| p = nextchar(p); 154| | // skip the next character 155| 23.3k| if (!ingroup && st < s.size()) ------------------ | Branch (155:13): [True: 23.3k, False: 0] | Branch (155:25): [True: 22.0k, False: 1.35k] ------------------ 156| 22.0k| st = (opts & aeUTF8) ? utf8_next(s, st) : st + 1; ------------------ | | 66| 22.0k|#define aeUTF8 (1 << 1) ------------------ | Branch (156:16): [True: 22.0k, False: 0] ------------------ 157| 23.3k| if (st == s.size() && p) ------------------ | Branch (157:13): [True: 3.63k, False: 19.7k] | Branch (157:31): [True: 0, False: 3.63k] ------------------ 158| 0| return 0; // word <= condition 159| 23.3k| break; 160| 23.3k| } 161| 23.3k| case '.': ------------------ | Branch (161:7): [True: 0, False: 2.77M] ------------------ 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| 2.70M| default: { ------------------ | Branch (171:7): [True: 2.70M, False: 70.1k] ------------------ 172| 2.70M| if (st < s.size() && s[st] == *p) { ------------------ | Branch (172:13): [True: 2.70M, False: 2.70k] | Branch (172:30): [True: 23.5k, False: 2.68M] ------------------ 173| 23.5k| ++st; 174| 23.5k| p = nextchar(p); 175| 23.5k| if ((opts & aeUTF8) && (s[st - 1] & 0x80)) { // multibyte ------------------ | | 66| 23.5k|#define aeUTF8 (1 << 1) ------------------ | Branch (175:15): [True: 23.5k, False: 0] | Branch (175:34): [True: 23.5k, False: 0] ------------------ 176| 46.8k| while (p && is_utf8_cont(*p)) { // character ------------------ | Branch (176:20): [True: 46.8k, False: 0] | Branch (176:25): [True: 23.5k, False: 23.3k] ------------------ 177| 23.5k| if (st >= s.size() || *p != s[st]) { ------------------ | Branch (177:19): [True: 0, False: 23.5k] | Branch (177:37): [True: 110, False: 23.3k] ------------------ 178| 110| if (pos == std::string::npos) ------------------ | Branch (178:21): [True: 78, False: 32] ------------------ 179| 78| return 0; 180| 32| st = pos; 181| 32| break; 182| 110| } 183| 23.3k| p = nextchar(p); 184| 23.3k| ++st; 185| 23.3k| } 186| 23.4k| if (pos != std::string::npos && st != pos) { ------------------ | Branch (186:17): [True: 32, False: 23.3k] | Branch (186:45): [True: 0, False: 32] ------------------ 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| 23.4k| } 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| 2.68M| } else if (pos != std::string::npos) { // group ------------------ | Branch (196:20): [True: 46.7k, False: 2.63M] ------------------ 197| 46.7k| p = nextchar(p); 198| 46.7k| } else 199| 2.63M| return 0; 200| 2.70M| } 201| 2.77M| } 202| 140k| if (!p) ------------------ | Branch (202:9): [True: 23.3k, False: 116k] ------------------ 203| 23.3k| return 1; 204| 140k| } 205| 2.66M|} _ZN8PfxEntry8nextcharEPc: 110| 163k|inline char* PfxEntry::nextchar(char* p) { 111| 163k| if (p) { ------------------ | Branch (111:7): [True: 163k, False: 0] ------------------ 112| 163k| p++; 113| 163k| if (opts & aeLONGCOND) { ------------------ | | 69| 163k|#define aeLONGCOND (1 << 4) ------------------ | Branch (113:9): [True: 0, False: 163k] ------------------ 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| 163k| } else if (p == c.conds + MAXCONDLEN) ------------------ | | 90| 163k|#define MAXCONDLEN 20 ------------------ | Branch (118:16): [True: 0, False: 163k] ------------------ 119| 0| return nullptr; 120| 163k| return *p ? p : nullptr; ------------------ | Branch (120:12): [True: 140k, False: 23.3k] ------------------ 121| 163k| } 122| 0| return nullptr; 123| 163k|} _ZN8SfxEntry14test_conditionEPKcS1_: 502| 108k|inline int SfxEntry::test_condition(const char* st, const char* beg) { 503| 108k| const char* pos = nullptr; // group with pos input position 504| 108k| bool neg = false; // complementer 505| 108k| bool ingroup = false; // character in the group 506| 108k| if (numconds == 0) ------------------ | Branch (506:7): [True: 108k, False: 3] ------------------ 507| 108k| return 1; 508| 3| char* p = c.conds; 509| 3| st--; 510| 3| int i = 1; 511| 24| while (true) { ------------------ | Branch (511:10): [True: 24, Folded] ------------------ 512| 24| switch (*p) { 513| 0| case '\0': ------------------ | Branch (513:7): [True: 0, False: 24] ------------------ 514| 0| return 1; 515| 3| case '[': ------------------ | Branch (515:7): [True: 3, False: 21] ------------------ 516| 3| p = nextchar(p); 517| 3| pos = st; 518| 3| break; 519| 0| case '^': ------------------ | Branch (519:7): [True: 0, False: 24] ------------------ 520| 0| p = nextchar(p); 521| 0| neg = true; 522| 0| break; 523| 3| case ']': ------------------ | Branch (523:7): [True: 3, False: 21] ------------------ 524| 3| if (!neg && !ingroup) ------------------ | Branch (524:13): [True: 3, False: 0] | Branch (524:21): [True: 3, False: 0] ------------------ 525| 3| return 0; 526| 0| i++; 527| | // skip the next character 528| 0| if (!ingroup) { ------------------ | Branch (528:13): [True: 0, False: 0] ------------------ 529| 0| for (; (opts & aeUTF8) && (st >= beg) && is_utf8_cont(*st); st--) ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (529:18): [True: 0, False: 0] | Branch (529:37): [True: 0, False: 0] | Branch (529:52): [True: 0, False: 0] ------------------ 530| 0| ; 531| 0| st--; 532| 0| } 533| 0| pos = nullptr; 534| 0| neg = false; 535| 0| ingroup = false; 536| 0| p = nextchar(p); 537| 0| if (st < beg && p) ------------------ | Branch (537:13): [True: 0, False: 0] | Branch (537:25): [True: 0, False: 0] ------------------ 538| 0| return 0; // word <= condition 539| 0| break; 540| 0| case '.': ------------------ | Branch (540:7): [True: 0, False: 24] ------------------ 541| 0| if (!pos) { ------------------ | Branch (541:13): [True: 0, False: 0] ------------------ 542| | // dots are not metacharacters in groups: [.] 543| 0| p = nextchar(p); 544| | // skip one character to the left. Walk back over any UTF-8 545| | // continuation bytes of that character to its leading byte first, 546| | // then step past it, so a single-byte match preceded by a 547| | // multibyte character does not consume the multibyte character. 548| 0| for (; (opts & aeUTF8) && (st >= beg) && is_utf8_cont(*st); st--) ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (548:18): [True: 0, False: 0] | Branch (548:37): [True: 0, False: 0] | Branch (548:52): [True: 0, False: 0] ------------------ 549| 0| ; 550| 0| st--; 551| 0| if (st < beg) { // word <= condition ------------------ | Branch (551:15): [True: 0, False: 0] ------------------ 552| 0| if (p) ------------------ | Branch (552:17): [True: 0, False: 0] ------------------ 553| 0| return 0; 554| 0| else 555| 0| return 1; 556| 0| } 557| 0| break; 558| 0| } 559| | /* FALLTHROUGH */ 560| 18| default: { ------------------ | Branch (560:7): [True: 18, False: 6] ------------------ 561| 18| if (*st == *p) { ------------------ | Branch (561:13): [True: 0, False: 18] ------------------ 562| 0| p = nextchar(p); 563| 0| if ((opts & aeUTF8) && (*st & 0x80)) { ------------------ | | 66| 0|#define aeUTF8 (1 << 1) ------------------ | Branch (563:15): [True: 0, False: 0] | Branch (563:34): [True: 0, False: 0] ------------------ 564| 0| st--; 565| 0| while (p && (st >= beg)) { ------------------ | Branch (565:20): [True: 0, False: 0] | Branch (565:25): [True: 0, False: 0] ------------------ 566| 0| if (*p != *st) { ------------------ | Branch (566:19): [True: 0, False: 0] ------------------ 567| 0| if (!pos) ------------------ | Branch (567:21): [True: 0, False: 0] ------------------ 568| 0| return 0; 569| 0| st = pos; 570| 0| break; 571| 0| } 572| | // first byte of the UTF-8 multibyte character 573| 0| if (!is_utf8_cont(*p)) ------------------ | Branch (573:19): [True: 0, False: 0] ------------------ 574| 0| break; 575| 0| p = nextchar(p); 576| 0| st--; 577| 0| } 578| 0| if (pos && st != pos) { ------------------ | Branch (578:17): [True: 0, False: 0] | Branch (578:24): [True: 0, False: 0] ------------------ 579| 0| if (neg) ------------------ | Branch (579:19): [True: 0, False: 0] ------------------ 580| 0| return 0; 581| 0| else if (i == numconds) ------------------ | Branch (581:24): [True: 0, False: 0] ------------------ 582| 0| return 1; 583| 0| ingroup = true; 584| 0| while (p && *p != ']' && ((p = nextchar(p)) != nullptr)) { ------------------ | Branch (584:22): [True: 0, False: 0] | Branch (584:27): [True: 0, False: 0] | Branch (584:40): [True: 0, False: 0] ------------------ 585| 0| } 586| 0| st--; 587| 0| } 588| 0| if (p && *p != ']') ------------------ | Branch (588:17): [True: 0, False: 0] | Branch (588:22): [True: 0, False: 0] ------------------ 589| 0| p = nextchar(p); 590| 0| } else if (pos) { ------------------ | Branch (590:22): [True: 0, False: 0] ------------------ 591| 0| if (neg) ------------------ | Branch (591:17): [True: 0, False: 0] ------------------ 592| 0| return 0; 593| 0| else if (i == numconds) ------------------ | Branch (593:22): [True: 0, False: 0] ------------------ 594| 0| return 1; 595| 0| ingroup = true; 596| 0| while (p && *p != ']' && ((p = nextchar(p)) != nullptr)) { ------------------ | Branch (596:20): [True: 0, False: 0] | Branch (596:25): [True: 0, False: 0] | Branch (596:38): [True: 0, False: 0] ------------------ 597| 0| } 598| | // if (p && *p != ']') p = nextchar(p); 599| 0| st--; 600| 0| } 601| 0| if (!pos) { ------------------ | Branch (601:15): [True: 0, False: 0] ------------------ 602| 0| i++; 603| 0| st--; 604| 0| } 605| 0| if (st < beg && p && *p != ']') ------------------ | Branch (605:15): [True: 0, False: 0] | Branch (605:27): [True: 0, False: 0] | Branch (605:32): [True: 0, False: 0] ------------------ 606| 0| return 0; // word <= condition 607| 18| } else if (pos) { // group ------------------ | Branch (607:20): [True: 18, False: 0] ------------------ 608| 18| p = nextchar(p); 609| 18| } else 610| 0| return 0; 611| 18| } 612| 24| } 613| 21| if (!p) ------------------ | Branch (613:9): [True: 0, False: 21] ------------------ 614| 0| return 1; 615| 21| } 616| 3|} _ZN8SfxEntry8nextcharEPc: 487| 21|inline char* SfxEntry::nextchar(char* p) { 488| 21| if (p) { ------------------ | Branch (488:7): [True: 21, False: 0] ------------------ 489| 21| p++; 490| 21| if (opts & aeLONGCOND) { ------------------ | | 69| 21|#define aeLONGCOND (1 << 4) ------------------ | Branch (490:9): [True: 0, False: 21] ------------------ 491| | // jump to the 2nd part of the condition 492| 0| if (p == c.l.conds1 + MAXCONDLEN_1) ------------------ | | 91| 0|#define MAXCONDLEN_1 (MAXCONDLEN - sizeof(char*)) | | ------------------ | | | | 90| 0|#define MAXCONDLEN 20 | | ------------------ ------------------ | Branch (492:11): [True: 0, False: 0] ------------------ 493| 0| return c.l.conds2; 494| | // end of the MAXCONDLEN length condition 495| 21| } else if (p == c.conds + MAXCONDLEN) ------------------ | | 90| 21|#define MAXCONDLEN 20 ------------------ | Branch (495:16): [True: 0, False: 21] ------------------ 496| 0| return nullptr; 497| 21| return *p ? p : nullptr; ------------------ | Branch (497:12): [True: 21, False: 0] ------------------ 498| 21| } 499| 0| return nullptr; 500| 21|} _ZN8PfxEntry7getNextEv: 134| 2.66M| inline PfxEntry* getNext() { return next; } _ZN8SfxEntry7getNextEv: 216| 228| inline SfxEntry* getNext() { return next; } _ZN8PfxEntry6getKeyEv: 124| 76.4k| const char* getKey() { return appnd.c_str(); } _ZN8PfxEntry7getFlagEv: 123| 839| 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| 54.8k| inline PfxEntry* getNextEQ() { return nexteq; } _ZN8PfxEntry9getNextNEEv: 135| 20.7k| inline PfxEntry* getNextNE() { return nextne; } _ZN8SfxEntry6getKeyEv: 205| 473k| const char* getKey() { return rappnd.c_str(); } _ZN8SfxEntry7getFlagEv: 204| 127k| 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| 366k| inline SfxEntry* getNextEQ() { return nexteq; } _ZN8SfxEntry9getNextNEEv: 217| 107k| inline SfxEntry* getNextNE() { return nextne; } _ZN8PfxEntry7getContEv: 131| 4.07M| inline const unsigned short* getCont() { return contclass; } _ZN8PfxEntry10getContLenEv: 132| 1.35M| inline unsigned short getContLen() { return contclasslen; } _ZN8SfxEntry7getContEv: 210| 486k| inline const unsigned short* getCont() { return contclass; } _ZN8SfxEntry10getContLenEv: 211| 57.8k| inline unsigned short getContLen() { return contclasslen; } _ZN8SfxEntry9getKeyLenEv: 214| 158k| inline int getKeyLen() { return appnd.size(); } _ZN8SfxEntry9getFlgNxtEv: 223| 62.1k| inline SfxEntry* getFlgNxt() { return flgnxt; } _ZN8SfxEntry8getAffixEv: 212| 34.6k| inline const char* getAffix() { return appnd.c_str(); } _ZNK8SfxEntry10allowCrossEv: 171| 28| bool allowCross() const { return ((opts & aeXPRODUCT) != 0); } ------------------ | | 65| 28|#define aeXPRODUCT (1 << 0) ------------------ _ZNK8PfxEntry10allowCrossEv: 94| 11| bool allowCross() const { return ((opts & aeXPRODUCT) != 0); } ------------------ | | 65| 11|#define aeXPRODUCT (1 << 0) ------------------ _ZN8PfxEntry9getKeyLenEv: 127| 2.49k| inline int getKeyLen() { return appnd.size(); } _ZN8PfxEntry9getFlgNxtEv: 137| 831| 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_9allocatorIcEEEEiicR12AffixScratchtt: 1084| 512M| const FLAG avoidflag) { 1085| 512M| struct hentry* rv = nullptr; 1086| | 1087| 512M| pfx = nullptr; 1088| 512M| pfxappnd = nullptr; 1089| 512M| sfxappnd = nullptr; 1090| 512M| sfxextra = 0; 1091| | 1092| | // first handle the special case of 0 length prefixes 1093| 512M| PfxEntry* pe = pStart[0]; 1094| 513M| while (pe) { ------------------ | Branch (1094:10): [True: 1.33M, False: 512M] ------------------ 1095| 1.33M| if ( 1096| | // fogemorpheme 1097| 1.33M| ((in_compound != IN_CPD_NOT) || ------------------ | | 72| 1.33M|#define IN_CPD_NOT 0 ------------------ | Branch (1097:10): [True: 0, False: 1.33M] ------------------ 1098| 1.33M| !(pe->getCont() && ------------------ | Branch (1098:12): [True: 1.33M, False: 0] ------------------ 1099| 1.33M| (TESTAFF(pe->getCont(), onlyincompound, pe->getContLen())))) && ------------------ | | 99| 1.33M|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1099:12): [True: 0, False: 1.33M] ------------------ 1100| | // permit prefixes in compounds 1101| 1.33M| ((in_compound != IN_CPD_END) || ------------------ | | 74| 1.33M|#define IN_CPD_END 2 ------------------ | Branch (1101:10): [True: 1.33M, False: 0] ------------------ 1102| 0| (pe->getCont() && ------------------ | Branch (1102:11): [True: 0, False: 0] ------------------ 1103| 1.33M| (TESTAFF(pe->getCont(), compoundpermitflag, pe->getContLen()))))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1103:11): [True: 0, False: 0] ------------------ 1104| | // check prefix 1105| 1.33M| rv = pe->checkword(word, start, len, in_compound, needflag, scratch); 1106| | // Skip a stem with the avoid flag and keep scanning the other prefixes. 1107| 1.33M| if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) ------------------ | | 96| 1.33M|#define FLAG_NULL 0x00 ------------------ if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1107:11): [True: 0, False: 1.33M] | Branch (1107:17): [True: 0, False: 0] ------------------ 1108| 0| rv = nullptr; 1109| 1.33M| if (rv) { ------------------ | Branch (1109:11): [True: 0, False: 1.33M] ------------------ 1110| 0| pfx = pe; // BUG: pfx not stateless 1111| 0| return rv; 1112| 0| } 1113| 1.33M| } 1114| 1.33M| pe = pe->getNext(); 1115| 1.33M| } 1116| | 1117| | // now handle the general case 1118| 512M| unsigned char sp = word[start]; 1119| 512M| PfxEntry* pptr = pStart[sp]; 1120| | 1121| 512M| while (pptr) { ------------------ | Branch (1121:10): [True: 40.2k, False: 512M] ------------------ 1122| 40.2k| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1122:9): [True: 29.8k, False: 10.3k] ------------------ 1123| 29.8k| if ( 1124| | // fogemorpheme 1125| 29.8k| ((in_compound != IN_CPD_NOT) || ------------------ | | 72| 29.8k|#define IN_CPD_NOT 0 ------------------ | Branch (1125:12): [True: 0, False: 29.8k] ------------------ 1126| 29.8k| !(pptr->getCont() && ------------------ | Branch (1126:14): [True: 24.9k, False: 4.87k] ------------------ 1127| 24.9k| (TESTAFF(pptr->getCont(), onlyincompound, pptr->getContLen())))) && ------------------ | | 99| 24.9k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1127:14): [True: 0, False: 24.9k] ------------------ 1128| | // permit prefixes in compounds 1129| 29.8k| ((in_compound != IN_CPD_END) || ------------------ | | 74| 29.8k|#define IN_CPD_END 2 ------------------ | Branch (1129:12): [True: 29.8k, False: 0] ------------------ 1130| 0| (pptr->getCont() && (TESTAFF(pptr->getCont(), compoundpermitflag, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1130:13): [True: 0, False: 0] | Branch (1130:32): [True: 0, False: 0] ------------------ 1131| 29.8k| pptr->getContLen()))))) { 1132| | // check prefix 1133| 29.8k| rv = pptr->checkword(word, start, len, in_compound, needflag, scratch); 1134| 29.8k| if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) ------------------ | | 96| 29.8k|#define FLAG_NULL 0x00 ------------------ if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (1134:13): [True: 0, False: 29.8k] | Branch (1134:19): [True: 0, False: 0] ------------------ 1135| 0| rv = nullptr; 1136| 29.8k| if (rv) { ------------------ | Branch (1136:13): [True: 0, False: 29.8k] ------------------ 1137| 0| pfx = pptr; // BUG: pfx not stateless 1138| 0| return rv; 1139| 0| } 1140| 29.8k| } 1141| 29.8k| pptr = pptr->getNextEQ(); 1142| 29.8k| } else { 1143| 10.3k| pptr = pptr->getNextNE(); 1144| 10.3k| } 1145| 40.2k| } 1146| | 1147| 512M| return nullptr; 1148| 512M|} _ZN8AffixMgr19prefix_check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratcht: 1156| 15.7M| const FLAG needflag) { 1157| 15.7M| struct hentry* rv = nullptr; 1158| | 1159| 15.7M| pfx = nullptr; 1160| 15.7M| sfxappnd = nullptr; 1161| 15.7M| sfxextra = 0; 1162| | 1163| | // first handle the special case of 0 length prefixes 1164| 15.7M| PfxEntry* pe = pStart[0]; 1165| | 1166| 17.0M| while (pe) { ------------------ | Branch (1166:10): [True: 1.33M, False: 15.7M] ------------------ 1167| 1.33M| rv = pe->check_twosfx(word, start, len, in_compound, needflag, scratch); 1168| 1.33M| if (rv) ------------------ | Branch (1168:9): [True: 0, False: 1.33M] ------------------ 1169| 0| return rv; 1170| 1.33M| pe = pe->getNext(); 1171| 1.33M| } 1172| | 1173| | // now handle the general case 1174| 15.7M| unsigned char sp = word[start]; 1175| 15.7M| PfxEntry* pptr = pStart[sp]; 1176| | 1177| 15.7M| while (pptr) { ------------------ | Branch (1177:10): [True: 35.3k, False: 15.7M] ------------------ 1178| 35.3k| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1178:9): [True: 24.9k, False: 10.3k] ------------------ 1179| 24.9k| rv = pptr->check_twosfx(word, start, len, in_compound, needflag, scratch); 1180| 24.9k| if (rv) { ------------------ | Branch (1180:11): [True: 0, False: 24.9k] ------------------ 1181| 0| pfx = pptr; 1182| 0| return rv; 1183| 0| } 1184| 24.9k| pptr = pptr->getNextEQ(); 1185| 24.9k| } else { 1186| 10.3k| pptr = pptr->getNextNE(); 1187| 10.3k| } 1188| 35.3k| } 1189| | 1190| 15.7M| return nullptr; 1191| 15.7M|} _ZN8AffixMgr18prefix_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratcht: 1199| 10.7k| const FLAG needflag) { 1200| | 1201| 10.7k| std::string result; 1202| | 1203| 10.7k| pfx = nullptr; 1204| 10.7k| sfxappnd = nullptr; 1205| 10.7k| sfxextra = 0; 1206| | 1207| | // first handle the special case of 0 length prefixes 1208| 10.7k| PfxEntry* pe = pStart[0]; 1209| 11.3k| while (pe) { ------------------ | Branch (1209:10): [True: 575, False: 10.7k] ------------------ 1210| 575| std::string st = pe->check_morph(word, start, len, in_compound, needflag, scratch); 1211| 575| if (!st.empty()) { ------------------ | Branch (1211:9): [True: 0, False: 575] ------------------ 1212| 0| result.append(st); 1213| 0| } 1214| 575| pe = pe->getNext(); 1215| 575| } 1216| | 1217| | // now handle the general case 1218| 10.7k| unsigned char sp = word[start]; 1219| 10.7k| PfxEntry* pptr = pStart[sp]; 1220| | 1221| 10.7k| while (pptr) { ------------------ | Branch (1221:10): [True: 3, False: 10.7k] ------------------ 1222| 3| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1222:9): [True: 1, False: 2] ------------------ 1223| 1| std::string st = pptr->check_morph(word, start, len, in_compound, needflag, scratch); 1224| 1| if (!st.empty()) { ------------------ | Branch (1224:11): [True: 0, False: 1] ------------------ 1225| | // fogemorpheme 1226| 0| if ((in_compound != IN_CPD_NOT) || ------------------ | | 72| 0|#define IN_CPD_NOT 0 ------------------ | Branch (1226:13): [True: 0, False: 0] ------------------ 1227| 0| !((pptr->getCont() && (TESTAFF(pptr->getCont(), onlyincompound, ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1227:16): [True: 0, False: 0] | Branch (1227:35): [True: 0, False: 0] ------------------ 1228| 0| pptr->getContLen()))))) { 1229| 0| result.append(st); 1230| 0| pfx = pptr; 1231| 0| } 1232| 0| } 1233| 1| pptr = pptr->getNextEQ(); 1234| 2| } else { 1235| 2| pptr = pptr->getNextNE(); 1236| 2| } 1237| 3| } 1238| | 1239| 10.7k| return result; 1240| 10.7k|} _ZN8AffixMgr25prefix_check_twosfx_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiicR12AffixScratcht: 1248| 3.36k| const FLAG needflag) { 1249| 3.36k| std::string result; 1250| | 1251| 3.36k| pfx = nullptr; 1252| 3.36k| sfxappnd = nullptr; 1253| 3.36k| sfxextra = 0; 1254| | 1255| | // first handle the special case of 0 length prefixes 1256| 3.36k| PfxEntry* pe = pStart[0]; 1257| 3.94k| while (pe) { ------------------ | Branch (1257:10): [True: 575, False: 3.36k] ------------------ 1258| 575| std::string st = pe->check_twosfx_morph(word, start, len, in_compound, needflag, scratch); 1259| 575| if (!st.empty()) { ------------------ | Branch (1259:9): [True: 0, False: 575] ------------------ 1260| 0| result.append(st); 1261| 0| } 1262| 575| pe = pe->getNext(); 1263| 575| } 1264| | 1265| | // now handle the general case 1266| 3.36k| unsigned char sp = word[start]; 1267| 3.36k| PfxEntry* pptr = pStart[sp]; 1268| | 1269| 3.37k| while (pptr) { ------------------ | Branch (1269:10): [True: 2, False: 3.36k] ------------------ 1270| 2| if (isSubset(pptr->getKey(), word.c_str() + start)) { ------------------ | Branch (1270:9): [True: 0, False: 2] ------------------ 1271| 0| std::string st = pptr->check_twosfx_morph(word, start, len, in_compound, needflag, scratch); 1272| 0| if (!st.empty()) { ------------------ | Branch (1272:11): [True: 0, False: 0] ------------------ 1273| 0| result.append(st); 1274| 0| pfx = pptr; 1275| 0| } 1276| 0| pptr = pptr->getNextEQ(); 1277| 2| } else { 1278| 2| pptr = pptr->getNextNE(); 1279| 2| } 1280| 2| } 1281| | 1282| 3.36k| return result; 1283| 3.36k|} _ZN8AffixMgr12get_syllableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1559| 442|short AffixMgr::get_syllable(const std::string& word) { 1560| 442| if (cpdmaxsyllable == 0) ------------------ | Branch (1560:7): [True: 0, False: 442] ------------------ 1561| 0| return 0; 1562| | 1563| 442| short num = 0; 1564| | 1565| 442| if (!utf8) { ------------------ | Branch (1565:7): [True: 0, False: 442] ------------------ 1566| 0| num = (short)std::count_if(word.begin(), word.end(), 1567| 0| [&](char c) { 1568| 0| return std::binary_search(cpdvowels.begin(), cpdvowels.end(), c); 1569| 0| }); 1570| 442| } else if (!cpdvowels_utf16.empty()) { ------------------ | Branch (1570:14): [True: 442, False: 0] ------------------ 1571| 442| std::vector w; 1572| 442| u8_u16(w, word); 1573| 442| num = (short)std::count_if(w.begin(), w.end(), 1574| 442| [&](w_char wc) { 1575| 442| return std::binary_search(cpdvowels_utf16.begin(), cpdvowels_utf16.end(), wc); 1576| 442| }); 1577| 442| } 1578| | 1579| 442| return num; 1580| 442|} _ZN8AffixMgr10setcminmaxEPmS0_PKcm: 1582| 21.7M|void AffixMgr::setcminmax(size_t* cmin, size_t* cmax, const char* word, size_t len) { 1583| 21.7M| if (utf8) { ------------------ | Branch (1583:7): [True: 1.55M, False: 20.1M] ------------------ 1584| 1.55M| int i; 1585| 4.64M| for (*cmin = 0, i = 0; (i < cpdmin) && *cmin < len; i++) { ------------------ | Branch (1585:28): [True: 3.11M, False: 1.53M] | Branch (1585:44): [True: 3.08M, False: 24.4k] ------------------ 1586| 3.41M| for ((*cmin)++; *cmin < len && is_utf8_cont(word[*cmin]); (*cmin)++) ------------------ | Branch (1586:23): [True: 3.37M, False: 42.2k] | Branch (1586:38): [True: 328k, False: 3.04M] ------------------ 1587| 328k| ; 1588| 3.08M| } 1589| 3.11M| for (*cmax = len, i = 0; (i < (cpdmin - 1)) && *cmax > 0; i++) { ------------------ | Branch (1589:30): [True: 1.55M, False: 1.55M] | Branch (1589:52): [True: 1.55M, False: 3.01k] ------------------ 1590| 2.47M| for ((*cmax)--; *cmax > 0 && is_utf8_cont(word[*cmax]); (*cmax)--) ------------------ | Branch (1590:23): [True: 2.45M, False: 21.4k] | Branch (1590:36): [True: 923k, False: 1.53M] ------------------ 1591| 923k| ; 1592| 1.55M| } 1593| 20.1M| } else { 1594| 20.1M| *cmin = cpdmin; 1595| 20.1M| *cmax = len - cpdmin + 1; 1596| 20.1M| } 1597| 21.7M|} _ZN8AffixMgr14compound_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEssssPP6hentrySB_ccPiR12AffixScratch: 1611| 21.7M| AffixScratch& scratch) { 1612| 21.7M| short oldnumsyllable, oldnumsyllable2, oldwordnum, oldwordnum2; 1613| 21.7M| hentry *rv = nullptr, *rv_first; 1614| 21.7M| std::string st; 1615| 21.7M| char ch = '\0', affixed; 1616| 21.7M| size_t cmin, cmax; 1617| 21.7M| int striple = 0, soldi = 0, oldcmin = 0, oldcmax = 0, oldlen = 0, checkedstriple = 0; 1618| 21.7M| hentry** oldwords = words; 1619| 21.7M| size_t scpd = 0, len = word.size(); 1620| | 1621| | // protect subsequent words[wnum + 1] reads and any recursion 1622| 21.7M| if (wnum + 1 >= maxwordnum) ------------------ | Branch (1622:7): [True: 0, False: 21.7M] ------------------ 1623| 0| return nullptr; 1624| | 1625| 21.7M| int checked_prefix; 1626| | 1627| | // add a time limit to handle possible 1628| | // combinatorical explosion of the overlapping words 1629| | 1630| 21.7M| HUNSPELL_THREAD_LOCAL std::chrono::steady_clock::time_point clock_time_start; ------------------ | | 60| 21.7M|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 1631| 21.7M| HUNSPELL_THREAD_LOCAL bool timelimit_exceeded; ------------------ | | 60| 21.7M|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 1632| | 1633| | // get the current time 1634| 21.7M| std::chrono::steady_clock::time_point clock_now = std::chrono::steady_clock::now(); 1635| | 1636| 21.7M| if (wnum == 0) { ------------------ | Branch (1636:7): [True: 21.7M, False: 287] ------------------ 1637| | // set the start time 1638| 21.7M| clock_time_start = clock_now; 1639| 21.7M| timelimit_exceeded = false; 1640| 21.7M| } 1641| 287| else if (clock_now - clock_time_start > TIMELIMIT_MS) ------------------ | | 106| 287|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (1641:12): [True: 0, False: 287] ------------------ 1642| 0| timelimit_exceeded = true; 1643| | 1644| 21.7M| setcminmax(&cmin, &cmax, word.c_str(), len); 1645| | 1646| 21.7M| st.assign(word); 1647| | 1648| 488M| for (size_t i = cmin; i < cmax; ++i) { ------------------ | Branch (1648:25): [True: 467M, False: 20.8M] ------------------ 1649| | // go to end of the UTF-8 character 1650| 467M| if (utf8) { ------------------ | Branch (1650:9): [True: 35.4M, False: 432M] ------------------ 1651| 42.8M| for (; is_utf8_cont(st[i]); i++) ------------------ | Branch (1651:14): [True: 7.34M, False: 35.4M] ------------------ 1652| 7.34M| ; 1653| 35.4M| if (i >= cmax) ------------------ | Branch (1653:11): [True: 147k, False: 35.3M] ------------------ 1654| 147k| return nullptr; 1655| 35.4M| } 1656| | 1657| 467M| words = oldwords; 1658| 467M| int onlycpdrule = (words) ? 1 : 0; ------------------ | Branch (1658:23): [True: 0, False: 467M] ------------------ 1659| | 1660| 467M| do { // onlycpdrule loop 1661| | 1662| 467M| oldnumsyllable = numsyllable; 1663| 467M| oldwordnum = wordnum; 1664| 467M| checked_prefix = 0; 1665| | 1666| 467M| do { // simplified checkcompoundpattern loop 1667| | 1668| 467M| if (timelimit_exceeded || ------------------ | Branch (1668:13): [True: 0, False: 467M] | Branch (1668:13): [True: 0, False: 467M] ------------------ 1669| 467M| std::chrono::steady_clock::now() - clock_time_start > TIMELIMIT_MS) { ------------------ | | 106| 467M|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (1669:13): [True: 0, False: 467M] ------------------ 1670| 0| timelimit_exceeded = true; 1671| 0| return nullptr; 1672| 0| } 1673| | 1674| 467M| if (scpd > 0) { ------------------ | Branch (1674:13): [True: 0, False: 467M] ------------------ 1675| 0| for (; scpd <= checkcpdtable.size() && ------------------ | Branch (1675:18): [True: 0, False: 0] ------------------ 1676| 0| (checkcpdtable[scpd - 1].pattern3.empty() || ------------------ | Branch (1676:19): [True: 0, False: 0] ------------------ 1677| 0| i > word.size() || ------------------ | Branch (1677:19): [True: 0, False: 0] ------------------ 1678| 0| word.compare(i, checkcpdtable[scpd - 1].pattern3.size(), checkcpdtable[scpd - 1].pattern3) != 0); ------------------ | Branch (1678:19): [True: 0, False: 0] ------------------ 1679| 0| scpd++) 1680| 0| ; 1681| | 1682| 0| if (scpd > checkcpdtable.size()) ------------------ | Branch (1682:15): [True: 0, False: 0] ------------------ 1683| 0| break; // break simplified checkcompoundpattern loop 1684| 0| st.replace(i, std::string::npos, checkcpdtable[scpd - 1].pattern); 1685| 0| soldi = i; 1686| 0| i += checkcpdtable[scpd - 1].pattern.size(); 1687| 0| st.replace(i, std::string::npos, checkcpdtable[scpd - 1].pattern2); 1688| 0| st.replace(i + checkcpdtable[scpd - 1].pattern2.size(), std::string::npos, 1689| 0| word.substr(soldi + checkcpdtable[scpd - 1].pattern3.size())); 1690| | 1691| 0| oldlen = len; 1692| 0| len += checkcpdtable[scpd - 1].pattern.size() + 1693| 0| checkcpdtable[scpd - 1].pattern2.size() - 1694| 0| checkcpdtable[scpd - 1].pattern3.size(); 1695| 0| oldcmin = cmin; 1696| 0| oldcmax = cmax; 1697| 0| setcminmax(&cmin, &cmax, st.c_str(), len); 1698| | 1699| 0| cmax = len - cpdmin + 1; 1700| 0| } 1701| | 1702| 467M| if (i >= st.size()) ------------------ | Branch (1702:13): [True: 710k, False: 466M] ------------------ 1703| 710k| return nullptr; 1704| | 1705| 466M| ch = st[i]; 1706| 466M| st[i] = '\0'; 1707| | 1708| 466M| sfx = nullptr; 1709| 466M| pfx = nullptr; 1710| | 1711| | // FIRST WORD 1712| | 1713| 466M| affixed = 1; 1714| 466M| rv = lookup(st.c_str(), i); // perhaps without prefix 1715| | 1716| | // forbid dictionary stems with COMPOUNDFORBIDFLAG in 1717| | // compound words, overriding the effect of COMPOUNDPERMITFLAG 1718| 466M| if ((rv) && compoundforbidflag && ------------------ | Branch (1718:13): [True: 2.57M, False: 464M] | Branch (1718:21): [True: 107k, False: 2.46M] ------------------ 1719| 107k| TESTAFF(rv->astr, compoundforbidflag, rv->alen) && !hu_mov_rule) { ------------------ | | 99| 466M|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 107k] | | ------------------ ------------------ | Branch (1719:68): [True: 0, False: 0] ------------------ 1720| 0| bool would_continue = !onlycpdrule && simplifiedcpd; ------------------ | Branch (1720:35): [True: 0, False: 0] | Branch (1720:51): [True: 0, False: 0] ------------------ 1721| 0| if (!scpd && would_continue) { ------------------ | Branch (1721:17): [True: 0, False: 0] | Branch (1721:26): [True: 0, False: 0] ------------------ 1722| | // given the while conditions that continue jumps to, this situation 1723| | // never ends 1724| 0| HUNSPELL_WARNING(stderr, "break infinite loop\n"); 1725| 0| break; 1726| 0| } 1727| | 1728| 0| if (scpd > 0 && would_continue) { ------------------ | Branch (1728:17): [True: 0, False: 0] | Branch (1728:29): [True: 0, False: 0] ------------------ 1729| | // under these conditions we loop again, but the assumption above 1730| | // appears to be that cmin and cmax are the original values they 1731| | // had in the outside loop 1732| 0| cmin = oldcmin; 1733| 0| cmax = oldcmax; 1734| 0| } 1735| 0| continue; 1736| 0| } 1737| | 1738| | // search homonym with compound flag 1739| 469M| while ((rv) && !hu_mov_rule && ------------------ | Branch (1739:16): [True: 2.57M, False: 466M] | Branch (1739:24): [True: 2.57M, False: 425] ------------------ 1740| 2.57M| ((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) || ------------------ | | 99| 823k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 823k] | | ------------------ ------------------ | Branch (1740:18): [True: 823k, False: 1.74M] ------------------ 1741| 2.57M| !((compoundflag && !words && !onlycpdrule && ------------------ | Branch (1741:20): [True: 2.57M, False: 0] | Branch (1741:36): [True: 2.57M, False: 0] | Branch (1741:46): [True: 2.57M, False: 0] ------------------ 1742| 2.57M| TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 2.57M|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 516, False: 2.57M] | | ------------------ ------------------ 1743| 2.57M| (compoundbegin && !wordnum && !onlycpdrule && ------------------ | Branch (1743:20): [True: 0, False: 2.57M] | Branch (1743:37): [True: 0, False: 0] | Branch (1743:49): [True: 0, False: 0] ------------------ 1744| 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] | | ------------------ ------------------ 1745| 2.57M| (compoundmiddle && wordnum && !words && !onlycpdrule && ------------------ | Branch (1745:20): [True: 0, False: 2.57M] | Branch (1745:38): [True: 0, False: 0] | Branch (1745:49): [True: 0, False: 0] | Branch (1745:59): [True: 0, False: 0] ------------------ 1746| 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] | | ------------------ ------------------ 1747| 2.57M| (!defcpdtable.empty() && onlycpdrule && ------------------ | Branch (1747:20): [True: 0, False: 2.57M] | Branch (1747:44): [True: 0, False: 0] ------------------ 1748| 0| ((!words && !wordnum && ------------------ | Branch (1748:22): [True: 0, False: 0] | Branch (1748:32): [True: 0, False: 0] ------------------ 1749| 0| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0)) || ------------------ | Branch (1749:22): [True: 0, False: 0] ------------------ 1750| 0| (words && ------------------ | Branch (1750:22): [True: 0, False: 0] ------------------ 1751| 0| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0))))) || ------------------ | Branch (1751:22): [True: 0, False: 0] ------------------ 1752| 516| (scpd != 0 && checkcpdtable[scpd - 1].cond != FLAG_NULL && ------------------ | | 96| 516|#define FLAG_NULL 0x00 ------------------ | Branch (1752:18): [True: 0, False: 516] | Branch (1752:31): [True: 0, False: 0] ------------------ 1753| 2.57M| !TESTAFF(rv->astr, checkcpdtable[scpd - 1].cond, rv->alen)))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1753:18): [True: 0, False: 0] ------------------ 1754| 2.57M| rv = rv->next_homonym; 1755| 2.57M| } 1756| | 1757| 466M| if (rv) ------------------ | Branch (1757:13): [True: 941, False: 466M] ------------------ 1758| 941| affixed = 0; 1759| | 1760| 466M| if (!rv) { ------------------ | Branch (1760:13): [True: 466M, False: 941] ------------------ 1761| 466M| if (onlycpdrule) ------------------ | Branch (1761:15): [True: 0, False: 466M] ------------------ 1762| 0| break; 1763| 466M| if (compoundflag && ------------------ | Branch (1763:15): [True: 466M, False: 0] ------------------ 1764| 466M| !(rv = prefix_check(st, 0, i, ------------------ | Branch (1764:15): [True: 466M, False: 0] ------------------ 1765| 466M| hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, ------------------ | | 75| 99.0k|#define IN_CPD_OTHER 3 ------------------ hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN, ------------------ | | 73| 933M|#define IN_CPD_BEGIN 1 ------------------ | Branch (1765:35): [True: 99.0k, False: 466M] ------------------ 1766| 466M| scratch, compoundflag))) { 1767| 466M| if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 96| 466M|#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| 99.0k|#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| 933M|#define IN_CPD_BEGIN 1 ------------------ | Branch (1767:18): [True: 0, False: 466M] | Branch (1767:93): [True: 99.0k, False: 466M] ------------------ 1768| 466M| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, compoundflag)))) && ------------------ | Branch (1768:19): [True: 0, False: 466M] | Branch (1768:43): [True: 0, False: 0] ------------------ 1769| 0| !hu_mov_rule && sfx->getCont() && ------------------ | Branch (1769:17): [True: 0, False: 0] | Branch (1769:33): [True: 0, False: 0] ------------------ 1770| 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 (1770:19): [True: 0, False: 0] ------------------ 1771| 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 (1771:19): [True: 0, False: 0] ------------------ 1772| 0| rv = nullptr; 1773| 0| } 1774| 466M| } 1775| | 1776| 466M| if (rv || ------------------ | Branch (1776:15): [True: 0, False: 466M] ------------------ 1777| 466M| (((wordnum == 0) && compoundbegin && ------------------ | Branch (1777:17): [True: 466M, False: 99.8k] | Branch (1777:35): [True: 0, False: 466M] ------------------ 1778| 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 (1778:18): [True: 0, False: 0] | Branch (1778:94): [True: 0, False: 0] ------------------ 1779| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (1779:19): [True: 0, False: 0] | Branch (1779:43): [True: 0, False: 0] ------------------ 1780| 0| compoundbegin))) || // twofold suffixes + compound 1781| 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 (1781:18): [True: 0, False: 0] | Branch (1781:47): [True: 0, False: 0] ------------------ 1782| 466M| ((wordnum > 0) && compoundmiddle && ------------------ | Branch (1782:17): [True: 714, False: 466M] | Branch (1782:34): [True: 0, False: 714] ------------------ 1783| 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 (1783:18): [True: 0, False: 0] | Branch (1783:95): [True: 0, False: 0] ------------------ 1784| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (1784:19): [True: 0, False: 0] | Branch (1784:43): [True: 0, False: 0] ------------------ 1785| 0| compoundmiddle))) || // twofold suffixes + compound 1786| 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 (1786:18): [True: 0, False: 0] | Branch (1786:47): [True: 0, False: 0] ------------------ 1787| 0| checked_prefix = 1; 1788| | // else check forbiddenwords and needaffix 1789| 466M| } else if (rv->astr && (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 99| 1.09k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 545] | | ------------------ ------------------ | Branch (1789:20): [True: 545, False: 396] | Branch (1789:20): [True: 0, False: 941] ------------------ 1790| 545| TESTAFF(rv->astr, needaffix, rv->alen) || ------------------ | | 99| 1.09k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 545] | | ------------------ ------------------ 1791| 545| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 1.09k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 545] | | ------------------ ------------------ 1792| 545| (is_sug && nosuggest && ------------------ | Branch (1792:34): [True: 0, False: 545] | Branch (1792:44): [True: 0, False: 0] ------------------ 1793| 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] | | ------------------ ------------------ 1794| 0| st[i] = ch; 1795| | // continue; 1796| 0| break; 1797| 0| } 1798| | 1799| | // check non_compound flag in suffix and prefix 1800| 466M| if ((rv) && !hu_mov_rule && ------------------ | Branch (1800:13): [True: 941, False: 466M] | Branch (1800:21): [True: 516, False: 425] ------------------ 1801| 516| ((pfx && pfx->getCont() && ------------------ | Branch (1801:15): [True: 0, False: 516] | Branch (1801:22): [True: 0, False: 0] ------------------ 1802| 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] | | ------------------ ------------------ 1803| 516| (sfx && sfx->getCont() && ------------------ | Branch (1803:15): [True: 0, False: 516] | Branch (1803:22): [True: 0, False: 0] ------------------ 1804| 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] | | ------------------ ------------------ 1805| 516| sfx->getContLen())))) { 1806| 0| rv = nullptr; 1807| 0| } 1808| | 1809| | // check compoundend flag in suffix and prefix 1810| 466M| if ((rv) && !checked_prefix && compoundend && !hu_mov_rule && ------------------ | Branch (1810:13): [True: 941, False: 466M] | Branch (1810:21): [True: 941, False: 0] | Branch (1810:40): [True: 0, False: 941] | Branch (1810:55): [True: 0, False: 0] ------------------ 1811| 0| ((pfx && pfx->getCont() && ------------------ | Branch (1811:15): [True: 0, False: 0] | Branch (1811:22): [True: 0, False: 0] ------------------ 1812| 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] | | ------------------ ------------------ 1813| 0| (sfx && sfx->getCont() && ------------------ | Branch (1813:15): [True: 0, False: 0] | Branch (1813:22): [True: 0, False: 0] ------------------ 1814| 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] | | ------------------ ------------------ 1815| 0| rv = nullptr; 1816| 0| } 1817| | 1818| | // check compoundmiddle flag in suffix and prefix 1819| 466M| if ((rv) && !checked_prefix && (wordnum == 0) && compoundmiddle && ------------------ | Branch (1819:13): [True: 941, False: 466M] | Branch (1819:21): [True: 941, False: 0] | Branch (1819:40): [True: 516, False: 425] | Branch (1819:58): [True: 0, False: 516] ------------------ 1820| 0| !hu_mov_rule && ------------------ | Branch (1820:13): [True: 0, False: 0] ------------------ 1821| 0| ((pfx && pfx->getCont() && ------------------ | Branch (1821:15): [True: 0, False: 0] | Branch (1821:22): [True: 0, False: 0] ------------------ 1822| 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] | | ------------------ ------------------ 1823| 0| (sfx && sfx->getCont() && ------------------ | Branch (1823:15): [True: 0, False: 0] | Branch (1823:22): [True: 0, False: 0] ------------------ 1824| 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] | | ------------------ ------------------ 1825| 0| rv = nullptr; 1826| 0| } 1827| | 1828| | // check forbiddenwords 1829| 466M| if ((rv) && (rv->astr) && ------------------ | Branch (1829:13): [True: 941, False: 466M] | Branch (1829:13): [True: 0, False: 466M] | Branch (1829:21): [True: 545, False: 396] ------------------ 1830| 545| (TESTAFF(rv->astr, forbiddenword, rv->alen) || ------------------ | | 99| 1.09k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 545] | | ------------------ ------------------ 1831| 545| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 1.09k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 545] | | ------------------ ------------------ 1832| 545| (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 (1832:15): [True: 0, False: 545] | Branch (1832:25): [True: 0, False: 0] ------------------ 1833| 0| return nullptr; 1834| 0| } 1835| | 1836| | // increment word number, if the second root has a compoundroot flag 1837| 466M| if ((rv) && compoundroot && ------------------ | Branch (1837:13): [True: 941, False: 466M] | Branch (1837:21): [True: 0, False: 941] ------------------ 1838| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1838:13): [True: 0, False: 0] ------------------ 1839| 0| wordnum++; 1840| 0| } 1841| | 1842| | // first word is acceptable in compound words? 1843| 466M| if (((rv) && ------------------ | Branch (1843:13): [True: 545, False: 466M] | Branch (1843:14): [True: 941, False: 466M] ------------------ 1844| 941| (checked_prefix || (words && words[wnum]) || ------------------ | Branch (1844:15): [True: 0, False: 941] | Branch (1844:34): [True: 0, False: 941] | Branch (1844:43): [True: 0, False: 0] ------------------ 1845| 941| (compoundflag && TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 941|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 545, False: 396] | | ------------------ ------------------ | Branch (1845:16): [True: 941, False: 0] ------------------ 1846| 396| ((oldwordnum == 0) && compoundbegin && ------------------ | Branch (1846:16): [True: 0, False: 396] | Branch (1846:37): [True: 0, False: 0] ------------------ 1847| 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] | | ------------------ ------------------ 1848| 396| ((oldwordnum > 0) && compoundmiddle && ------------------ | Branch (1848:16): [True: 0, False: 396] | Branch (1848:36): [True: 0, False: 0] ------------------ 1849| 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] | | ------------------ ------------------ 1850| | 1851| | // LANG_hu section: spec. Hungarian rule 1852| 396| || ((langnum == LANG_hu) && hu_mov_rule && ------------------ | Branch (1852:19): [True: 396, False: 0] | Branch (1852:43): [True: 396, False: 0] ------------------ 1853| 396| (TESTAFF( ------------------ | | 99| 792|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 396] | | ------------------ ------------------ 1854| 396| rv->astr, 'F', 1855| 396| rv->alen) || // XXX hardwired Hungarian dictionary codes 1856| 396| TESTAFF(rv->astr, 'G', rv->alen) || ------------------ | | 99| 792|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 396] | | ------------------ ------------------ 1857| 396| TESTAFF(rv->astr, 'H', rv->alen))) ------------------ | | 99| 396|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 396] | | ------------------ ------------------ 1858| | // END of LANG_hu section 1859| 941| ) && 1860| 545| ( 1861| | // test CHECKCOMPOUNDPATTERN conditions 1862| 545| scpd == 0 || checkcpdtable[scpd - 1].cond == FLAG_NULL || ------------------ | | 96| 545|#define FLAG_NULL 0x00 ------------------ | Branch (1862:18): [True: 545, False: 0] | Branch (1862:31): [True: 0, False: 0] ------------------ 1863| 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] | | ------------------ ------------------ 1864| 545| !((checkcompoundtriple && scpd == 0 && ------------------ | Branch (1864:17): [True: 0, False: 545] | Branch (1864:40): [True: 0, False: 0] ------------------ 1865| 0| !words && i < word.size() && // test triple letters ------------------ | Branch (1865:17): [True: 0, False: 0] | Branch (1865:27): [True: 0, False: 0] ------------------ 1866| 0| (word[i - 1] == word[i]) && ------------------ | Branch (1866:17): [True: 0, False: 0] ------------------ 1867| 0| (((i > 1) && (word[i - 1] == word[i - 2])) || ------------------ | Branch (1867:19): [True: 0, False: 0] | Branch (1867:30): [True: 0, False: 0] ------------------ 1868| 0| ((word[i - 1] == word[i + 1])) // may be word[i+1] == '\0' ------------------ | Branch (1868:18): [True: 0, False: 0] ------------------ 1869| 0| )) || 1870| 545| (checkcompoundcase && scpd == 0 && !words && i < word.size() && ------------------ | Branch (1870:17): [True: 0, False: 545] | Branch (1870:38): [True: 0, False: 0] | Branch (1870:51): [True: 0, False: 0] | Branch (1870:61): [True: 0, False: 0] ------------------ 1871| 0| cpdcase_check(word, i)))) ------------------ | Branch (1871:17): [True: 0, False: 0] ------------------ 1872| | // LANG_hu section: spec. Hungarian rule 1873| 466M| || ((!rv) && (langnum == LANG_hu) && hu_mov_rule && ------------------ | Branch (1873:17): [True: 466M, False: 396] | Branch (1873:26): [True: 35.3M, False: 431M] | Branch (1873:50): [True: 99.0k, False: 35.2M] ------------------ 1874| 99.0k| (rv = affix_check(st, 0, i, scratch)) && ------------------ | Branch (1874:17): [True: 0, False: 99.0k] ------------------ 1875| 0| (sfx && sfx->getCont() && ------------------ | Branch (1875:18): [True: 0, False: 0] | Branch (1875:25): [True: 0, False: 0] ------------------ 1876| 0| ( // XXX hardwired Hungarian dic. codes 1877| 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] | | ------------------ ------------------ 1878| 0| sfx->getContLen()) || 1879| 0| TESTAFF( ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1880| 0| sfx->getCont(), (unsigned short)'%', 1881| 545| sfx->getContLen()))))) { // first word is ok condition 1882| | 1883| | // LANG_hu section: spec. Hungarian rule 1884| 545| if (langnum == LANG_hu) { ------------------ | Branch (1884:15): [True: 221, False: 324] ------------------ 1885| | // calculate syllable number of the word 1886| 221| numsyllable += get_syllable(st.substr(0, i)); 1887| | // + 1 word, if syllable number of the prefix > 1 (hungarian 1888| | // convention) 1889| 221| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (1889:17): [True: 0, False: 221] | Branch (1889:17): [True: 0, False: 221] | Branch (1889:24): [True: 0, False: 0] ------------------ 1890| 0| wordnum++; 1891| 221| } 1892| | // END of LANG_hu section 1893| | 1894| | // NEXT WORD(S) 1895| 545| rv_first = rv; 1896| 545| st[i] = ch; 1897| | 1898| 545| do { // striple loop 1899| | 1900| | // check simplifiedtriple 1901| 545| if (simplifiedtriple) { ------------------ | Branch (1901:17): [True: 0, False: 545] ------------------ 1902| 0| if (striple) { ------------------ | Branch (1902:19): [True: 0, False: 0] ------------------ 1903| 0| checkedstriple = 1; 1904| 0| i--; // check "fahrt" instead of "ahrt" in "Schiffahrt" 1905| 0| } else if (i > 2 && i <= word.size() && word[i - 1] == word[i - 2]) ------------------ | Branch (1905:26): [True: 0, False: 0] | Branch (1905:35): [True: 0, False: 0] | Branch (1905:55): [True: 0, False: 0] ------------------ 1906| 0| striple = 1; 1907| 0| } 1908| | 1909| 545| rv = lookup(st.c_str() + i, st.size() - i); // perhaps without prefix 1910| | 1911| | // search homonym with compound flag 1912| 545| 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 (1912:20): [True: 0, False: 545] | Branch (1912:30): [True: 0, False: 0] ------------------ 1913| 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 (1913:32): [True: 0, False: 0] | Branch (1913:48): [True: 0, False: 0] ------------------ 1914| 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 (1914:32): [True: 0, False: 0] | Branch (1914:47): [True: 0, False: 0] ------------------ 1915| 0| (!defcpdtable.empty() && words && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1))) || ------------------ | Branch (1915:32): [True: 0, False: 0] | Branch (1915:56): [True: 0, False: 0] | Branch (1915:65): [True: 0, False: 0] ------------------ 1916| 0| (scpd != 0 && checkcpdtable[scpd - 1].cond2 != FLAG_NULL && ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ | Branch (1916:30): [True: 0, False: 0] | Branch (1916:43): [True: 0, False: 0] ------------------ 1917| 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 (1917:30): [True: 0, False: 0] ------------------ 1918| 0| rv = rv->next_homonym; 1919| 0| } 1920| | 1921| | // check FORCEUCASE 1922| 545| if (rv && forceucase && ------------------ | Branch (1922:17): [True: 0, False: 545] | Branch (1922:23): [True: 0, False: 0] ------------------ 1923| 0| (TESTAFF(rv->astr, forceucase, rv->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1923:17): [True: 0, False: 0] ------------------ 1924| 0| !(info && *info & SPELL_ORIGCAP)) ------------------ | | 83| 0|#define SPELL_ORIGCAP (1 << 5) ------------------ | Branch (1924:19): [True: 0, False: 0] | Branch (1924:27): [True: 0, False: 0] ------------------ 1925| 0| rv = nullptr; 1926| | 1927| 545| if (rv && words && words[wnum + 1]) ------------------ | Branch (1927:17): [True: 0, False: 545] | Branch (1927:23): [True: 0, False: 0] | Branch (1927:32): [True: 0, False: 0] ------------------ 1928| 0| return rv_first; 1929| | 1930| 545| oldnumsyllable2 = numsyllable; 1931| 545| oldwordnum2 = wordnum; 1932| | 1933| | // LANG_hu section: spec. Hungarian rule, XXX hardwired dictionary 1934| | // code 1935| 545| if ((rv) && (langnum == LANG_hu) && ------------------ | Branch (1935:17): [True: 0, False: 545] | Branch (1935:17): [True: 0, False: 545] | Branch (1935:25): [True: 0, False: 0] ------------------ 1936| 0| (TESTAFF(rv->astr, 'I', rv->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1936:17): [True: 0, False: 0] ------------------ 1937| 0| !(TESTAFF(rv->astr, 'J', rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1937:17): [True: 0, False: 0] ------------------ 1938| 0| numsyllable--; 1939| 0| } 1940| | // END of LANG_hu section 1941| | 1942| | // increment word number, if the second root has a compoundroot flag 1943| 545| if ((rv) && (compoundroot) && ------------------ | Branch (1943:17): [True: 0, False: 545] | Branch (1943:25): [True: 0, False: 0] ------------------ 1944| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (1944:17): [True: 0, False: 0] ------------------ 1945| 0| wordnum++; 1946| 0| } 1947| | 1948| | // check forbiddenwords 1949| 545| if ((rv) && (rv->astr) && ------------------ | Branch (1949:17): [True: 0, False: 545] | Branch (1949:17): [True: 0, False: 545] | Branch (1949:25): [True: 0, False: 0] ------------------ 1950| 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] | | ------------------ ------------------ 1951| 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] | | ------------------ ------------------ 1952| 0| (is_sug && nosuggest && ------------------ | Branch (1952:19): [True: 0, False: 0] | Branch (1952:29): [True: 0, False: 0] ------------------ 1953| 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] | | ------------------ ------------------ 1954| 0| return nullptr; 1955| | 1956| | // second word is acceptable, as a root? 1957| | // hungarian conventions: compounding is acceptable, 1958| | // when compound forms consist of 2 words, or if more, 1959| | // then the syllable number of root words must be 6, or lesser. 1960| | 1961| 545| if ((rv) && ------------------ | Branch (1961:17): [True: 0, False: 545] | Branch (1961:17): [True: 0, False: 545] ------------------ 1962| 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 (1962:19): [True: 0, False: 0] ------------------ 1963| 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 (1963:19): [True: 0, False: 0] ------------------ 1964| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (1964:19): [True: 0, False: 0] | Branch (1964:41): [True: 0, False: 0] ------------------ 1965| 0| ((cpdmaxsyllable != 0) && ------------------ | Branch (1965:19): [True: 0, False: 0] ------------------ 1966| 0| (numsyllable + get_syllable(std::string(HENTRY_WORD(rv), rv->blen)) <= ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ | Branch (1966:19): [True: 0, False: 0] ------------------ 1967| 0| cpdmaxsyllable))) && 1968| 0| ( 1969| | // test CHECKCOMPOUNDPATTERN 1970| 0| checkcpdtable.empty() || scpd != 0 || ------------------ | Branch (1970:21): [True: 0, False: 0] | Branch (1970:46): [True: 0, False: 0] ------------------ 1971| 0| (i < word.size() && !cpdpat_check(word, i, rv_first, rv, 0))) && ------------------ | Branch (1971:22): [True: 0, False: 0] | Branch (1971:41): [True: 0, False: 0] ------------------ 1972| 0| ((!checkcompounddup || (rv != rv_first))) ------------------ | Branch (1972:19): [True: 0, False: 0] | Branch (1972:40): [True: 0, False: 0] ------------------ 1973| | // test CHECKCOMPOUNDPATTERN conditions 1974| 0| && 1975| 0| (scpd == 0 || checkcpdtable[scpd - 1].cond2 == FLAG_NULL || ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ | Branch (1975:18): [True: 0, False: 0] | Branch (1975:31): [True: 0, False: 0] ------------------ 1976| 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] | | ------------------ ------------------ 1977| | // forbid compound word, if it is a non-compound word with typical 1978| | // fault 1979| 0| if ((checkcompoundrep && cpdrep_check(word, len, scratch, timelimit_exceeded, clock_time_start)) || ------------------ | Branch (1979:20): [True: 0, False: 0] | Branch (1979:40): [True: 0, False: 0] ------------------ 1980| 0| cpdwordpair_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (1980:19): [True: 0, False: 0] ------------------ 1981| 0| return nullptr; 1982| 0| return rv_first; 1983| 0| } 1984| | 1985| 545| numsyllable = oldnumsyllable2; 1986| 545| wordnum = oldwordnum2; 1987| | 1988| | // perhaps second word has prefix or/and suffix 1989| 545| sfx = nullptr; 1990| 545| sfxflag = FLAG_NULL; ------------------ | | 96| 545|#define FLAG_NULL 0x00 ------------------ 1991| 545| rv = (compoundflag && !onlycpdrule && i < word.size()) ? affix_check(word, i, word.size() - i, scratch, compoundflag, IN_CPD_END) ------------------ | | 74| 545|#define IN_CPD_END 2 ------------------ | Branch (1991:19): [True: 545, False: 0] | Branch (1991:35): [True: 545, False: 0] | Branch (1991:51): [True: 545, False: 0] ------------------ 1992| 545| : nullptr; 1993| 545| if (!rv && compoundend && !onlycpdrule) { ------------------ | Branch (1993:17): [True: 545, False: 0] | Branch (1993:24): [True: 0, False: 545] | Branch (1993:39): [True: 0, False: 0] ------------------ 1994| 0| sfx = nullptr; 1995| 0| pfx = nullptr; 1996| 0| if (i < word.size()) ------------------ | Branch (1996:19): [True: 0, False: 0] ------------------ 1997| 0| rv = affix_check(word, i, word.size() - i, scratch, compoundend, IN_CPD_END); ------------------ | | 74| 0|#define IN_CPD_END 2 ------------------ 1998| 0| } 1999| | 2000| 545| if (!rv && !defcpdtable.empty() && words) { ------------------ | Branch (2000:17): [True: 545, False: 0] | Branch (2000:24): [True: 0, False: 545] | Branch (2000:48): [True: 0, False: 0] ------------------ 2001| 0| if (i < word.size()) ------------------ | Branch (2001:19): [True: 0, False: 0] ------------------ 2002| 0| rv = affix_check(word, i, word.size() - i, scratch, 0, IN_CPD_END); ------------------ | | 74| 0|#define IN_CPD_END 2 ------------------ 2003| 0| if (rv && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1)) ------------------ | Branch (2003:19): [True: 0, False: 0] | Branch (2003:25): [True: 0, False: 0] ------------------ 2004| 0| return rv_first; 2005| 0| rv = nullptr; 2006| 0| } 2007| | 2008| | // test CHECKCOMPOUNDPATTERN conditions (allowed forms) 2009| 545| if (rv && ------------------ | Branch (2009:17): [True: 0, False: 545] ------------------ 2010| 0| !(scpd == 0 || checkcpdtable[scpd - 1].cond2 == FLAG_NULL || ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ | Branch (2010:19): [True: 0, False: 0] | Branch (2010:32): [True: 0, False: 0] ------------------ 2011| 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] | | ------------------ ------------------ 2012| 0| rv = nullptr; 2013| | 2014| | // test CHECKCOMPOUNDPATTERN conditions (forbidden compounds) 2015| 545| if (rv && !checkcpdtable.empty() && scpd == 0 && ------------------ | Branch (2015:17): [True: 0, False: 545] | Branch (2015:23): [True: 0, False: 0] | Branch (2015:49): [True: 0, False: 0] ------------------ 2016| 0| cpdpat_check(word, i, rv_first, rv, affixed)) ------------------ | Branch (2016:17): [True: 0, False: 0] ------------------ 2017| 0| rv = nullptr; 2018| | 2019| | // check non_compound flag in suffix and prefix 2020| 545| if ((rv) && ((pfx && pfx->getCont() && ------------------ | Branch (2020:17): [True: 0, False: 545] | Branch (2020:27): [True: 0, False: 0] | Branch (2020:34): [True: 0, False: 0] ------------------ 2021| 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] | | ------------------ ------------------ 2022| 0| pfx->getContLen())) || 2023| 0| (sfx && sfx->getCont() && ------------------ | Branch (2023:27): [True: 0, False: 0] | Branch (2023:34): [True: 0, False: 0] ------------------ 2024| 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] | | ------------------ ------------------ 2025| 0| sfx->getContLen())))) { 2026| 0| rv = nullptr; 2027| 0| } 2028| | 2029| | // check FORCEUCASE 2030| 545| if (rv && forceucase && ------------------ | Branch (2030:17): [True: 0, False: 545] | Branch (2030:23): [True: 0, False: 0] ------------------ 2031| 0| (TESTAFF(rv->astr, forceucase, rv->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2031:17): [True: 0, False: 0] ------------------ 2032| 0| !(info && *info & SPELL_ORIGCAP)) ------------------ | | 83| 0|#define SPELL_ORIGCAP (1 << 5) ------------------ | Branch (2032:19): [True: 0, False: 0] | Branch (2032:27): [True: 0, False: 0] ------------------ 2033| 0| rv = nullptr; 2034| | 2035| | // check forbiddenwords 2036| 545| if ((rv) && (rv->astr) && ------------------ | Branch (2036:17): [True: 0, False: 545] | Branch (2036:17): [True: 0, False: 545] | Branch (2036:25): [True: 0, False: 0] ------------------ 2037| 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] | | ------------------ ------------------ 2038| 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] | | ------------------ ------------------ 2039| 0| (is_sug && nosuggest && ------------------ | Branch (2039:19): [True: 0, False: 0] | Branch (2039:29): [True: 0, False: 0] ------------------ 2040| 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] | | ------------------ ------------------ 2041| 0| return nullptr; 2042| | 2043| | // pfxappnd = prefix of word+i, or NULL 2044| | // calculate syllable number of prefix. 2045| | // hungarian convention: when syllable number of prefix is more, 2046| | // than 1, the prefix+word counts as two words. 2047| | 2048| 545| if (langnum == LANG_hu) { ------------------ | Branch (2048:17): [True: 221, False: 324] ------------------ 2049| 221| if (i < word.size()) { ------------------ | Branch (2049:19): [True: 221, False: 0] ------------------ 2050| | // calculate syllable number of the word 2051| 221| numsyllable += get_syllable(word.substr(i)); 2052| 221| } 2053| | 2054| | // - affix syllable num. 2055| | // XXX only second suffix (inflections, not derivations) 2056| 221| if (sfxappnd) { ------------------ | Branch (2056:19): [True: 0, False: 221] ------------------ 2057| 0| std::string tmp(sfxappnd); 2058| 0| reverseword(tmp); 2059| 0| numsyllable -= short(get_syllable(tmp) + sfxextra); 2060| 221| } else { 2061| 221| numsyllable -= short(sfxextra); 2062| 221| } 2063| | 2064| | // + 1 word, if syllable number of the prefix > 1 (hungarian 2065| | // convention) 2066| 221| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (2066:19): [True: 0, False: 221] | Branch (2066:19): [True: 0, False: 221] | Branch (2066:26): [True: 0, False: 0] ------------------ 2067| 0| wordnum++; 2068| | 2069| | // increment syllable num, if last word has a SYLLABLENUM flag 2070| | // and the suffix is beginning `s' 2071| | 2072| 221| if (!cpdsyllablenum.empty()) { ------------------ | Branch (2072:19): [True: 0, False: 221] ------------------ 2073| 0| switch (sfxflag) { ------------------ | Branch (2073:25): [True: 0, False: 0] ------------------ 2074| 0| case 'c': { ------------------ | Branch (2074:19): [True: 0, False: 0] ------------------ 2075| 0| numsyllable += 2; 2076| 0| break; 2077| 0| } 2078| 0| case 'J': { ------------------ | Branch (2078:19): [True: 0, False: 0] ------------------ 2079| 0| numsyllable += 1; 2080| 0| break; 2081| 0| } 2082| 0| case 'I': { ------------------ | Branch (2082:19): [True: 0, False: 0] ------------------ 2083| 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 (2083:25): [True: 0, False: 0] | Branch (2083:25): [True: 0, False: 0] ------------------ 2084| 0| numsyllable += 1; 2085| 0| break; 2086| 0| } 2087| 0| } 2088| 0| } 2089| 221| } 2090| | 2091| | // increment word number, if the second word has a compoundroot flag 2092| 545| if ((rv) && (compoundroot) && ------------------ | Branch (2092:17): [True: 0, False: 545] | Branch (2092:25): [True: 0, False: 0] ------------------ 2093| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2093:17): [True: 0, False: 0] ------------------ 2094| 0| wordnum++; 2095| 0| } 2096| | // second word is acceptable, as a word with prefix or/and suffix? 2097| | // hungarian conventions: compounding is acceptable, 2098| | // when compound forms consist 2 word, otherwise 2099| | // the syllable number of root words is 6, or lesser. 2100| 545| if ((rv) && ------------------ | Branch (2100:17): [True: 0, False: 545] ------------------ 2101| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (2101:19): [True: 0, False: 0] | Branch (2101:41): [True: 0, False: 0] ------------------ 2102| 0| ((cpdmaxsyllable != 0) && (numsyllable <= cpdmaxsyllable))) && ------------------ | Branch (2102:19): [True: 0, False: 0] | Branch (2102:44): [True: 0, False: 0] ------------------ 2103| 0| ((!checkcompounddup || (rv != rv_first)))) { ------------------ | Branch (2103:19): [True: 0, False: 0] | Branch (2103:40): [True: 0, False: 0] ------------------ 2104| | // forbid compound word, if it is a non-compound word with typical 2105| | // fault 2106| 0| if ((checkcompoundrep && cpdrep_check(word, len, scratch, timelimit_exceeded, clock_time_start)) || ------------------ | Branch (2106:20): [True: 0, False: 0] | Branch (2106:40): [True: 0, False: 0] ------------------ 2107| 0| cpdwordpair_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (2107:19): [True: 0, False: 0] ------------------ 2108| 0| return nullptr; 2109| 0| return rv_first; 2110| 0| } 2111| | 2112| 545| numsyllable = oldnumsyllable2; 2113| 545| wordnum = oldwordnum2; 2114| | 2115| | // perhaps second word is a compound word (recursive call) 2116| | // (only if SPELL_COMPOUND_2 is not set and maxwordnum is not exceeded) 2117| 545| if ((!info || !(*info & SPELL_COMPOUND_2)) && wordnum + 2 < maxwordnum && wnum + 1 < maxwordnum) { ------------------ | | 85| 545|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ | Branch (2117:18): [True: 0, False: 545] | Branch (2117:27): [True: 287, False: 258] | Branch (2117:59): [True: 287, False: 0] | Branch (2117:87): [True: 287, False: 0] ------------------ 2118| 287| rv = compound_check(st.substr(i), wordnum + 1, 2119| 287| numsyllable, maxwordnum, wnum + 1, words, rwords, 0, 2120| 287| is_sug, info, scratch); 2121| | 2122| 287| if (rv && !checkcpdtable.empty() && i < word.size() && ------------------ | Branch (2122:19): [True: 0, False: 287] | Branch (2122:25): [True: 0, False: 0] | Branch (2122:51): [True: 0, False: 0] ------------------ 2123| 0| ((scpd == 0 && ------------------ | Branch (2123:21): [True: 0, False: 0] ------------------ 2124| 0| cpdpat_check(word, i, rv_first, rv, affixed)) || ------------------ | Branch (2124:21): [True: 0, False: 0] ------------------ 2125| 0| (scpd != 0 && ------------------ | Branch (2125:21): [True: 0, False: 0] ------------------ 2126| 0| !cpdpat_check(word, i, rv_first, rv, affixed)))) ------------------ | Branch (2126:21): [True: 0, False: 0] ------------------ 2127| 0| rv = nullptr; 2128| 287| } else { 2129| 258| rv = nullptr; 2130| 258| } 2131| 545| if (rv) { ------------------ | Branch (2131:17): [True: 0, False: 545] ------------------ 2132| | // forbid compound word, if it is a non-compound word with typical 2133| | // fault, or a dictionary word pair 2134| | 2135| 0| if (cpdwordpair_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (2135:19): [True: 0, False: 0] ------------------ 2136| 0| return nullptr; 2137| | 2138| 0| if (checkcompoundrep || forbiddenword) { ------------------ | Branch (2138:19): [True: 0, False: 0] | Branch (2138:39): [True: 0, False: 0] ------------------ 2139| 0| if (checkcompoundrep && cpdrep_check(word, len, scratch, timelimit_exceeded, clock_time_start)) ------------------ | Branch (2139:21): [True: 0, False: 0] | Branch (2139:41): [True: 0, False: 0] ------------------ 2140| 0| return nullptr; 2141| | 2142| | // check first part 2143| 0| if (i < word.size() && word.compare(i, rv->blen, rv->word, rv->blen) == 0) { ------------------ | Branch (2143:21): [True: 0, False: 0] | Branch (2143:40): [True: 0, False: 0] ------------------ 2144| 0| char r = st[i + rv->blen]; 2145| 0| st[i + rv->blen] = '\0'; 2146| | 2147| 0| if ((checkcompoundrep && cpdrep_check(st, i + rv->blen, scratch, timelimit_exceeded, clock_time_start)) || ------------------ | Branch (2147:24): [True: 0, False: 0] | Branch (2147:44): [True: 0, False: 0] ------------------ 2148| 0| cpdwordpair_check(st, i + rv->blen, scratch, timelimit_exceeded, clock_time_start)) { ------------------ | Branch (2148:23): [True: 0, False: 0] ------------------ 2149| 0| st[ + i + rv->blen] = r; 2150| 0| continue; 2151| 0| } 2152| | 2153| 0| if (forbiddenword) { ------------------ | Branch (2153:23): [True: 0, False: 0] ------------------ 2154| 0| struct hentry* rv2 = lookup(word.c_str(), word.size()); 2155| 0| if (!rv2 && len <= word.size()) ------------------ | Branch (2155:25): [True: 0, False: 0] | Branch (2155:33): [True: 0, False: 0] ------------------ 2156| 0| rv2 = affix_check(word, 0, len, scratch); 2157| 0| if (rv2 && rv2->astr && ------------------ | Branch (2157:25): [True: 0, False: 0] | Branch (2157:32): [True: 0, False: 0] ------------------ 2158| 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] | | ------------------ ------------------ 2159| 0| (strncmp(rv2->word, st.c_str(), i + rv->blen) == 0)) { ------------------ | Branch (2159:25): [True: 0, False: 0] ------------------ 2160| 0| return nullptr; 2161| 0| } 2162| 0| } 2163| 0| st[i + rv->blen] = r; 2164| 0| } 2165| 0| } 2166| 0| return rv_first; 2167| 0| } 2168| 545| } while (striple && !checkedstriple); // end of striple loop ------------------ | Branch (2168:20): [True: 0, False: 545] | Branch (2168:31): [True: 0, False: 0] ------------------ 2169| | 2170| 545| if (checkedstriple) { ------------------ | Branch (2170:15): [True: 0, False: 545] ------------------ 2171| 0| i++; 2172| 0| checkedstriple = 0; 2173| 0| striple = 0; 2174| 0| } 2175| | 2176| 545| } // first word is ok condition 2177| | 2178| 466M| if (soldi != 0) { ------------------ | Branch (2178:13): [True: 0, False: 466M] ------------------ 2179| 0| i = soldi; 2180| 0| soldi = 0; 2181| 0| len = oldlen; 2182| 0| cmin = oldcmin; 2183| 0| cmax = oldcmax; 2184| 0| } 2185| 466M| scpd++; 2186| | 2187| 466M| } while (!onlycpdrule && simplifiedcpd && ------------------ | Branch (2187:16): [True: 466M, False: 0] | Branch (2187:32): [True: 0, False: 466M] ------------------ 2188| 0| scpd <= checkcpdtable.size()); // end of simplifiedcpd loop ------------------ | Branch (2188:16): [True: 0, False: 0] ------------------ 2189| | 2190| 466M| scpd = 0; 2191| 466M| wordnum = oldwordnum; 2192| 466M| numsyllable = oldnumsyllable; 2193| | 2194| 466M| if (soldi != 0) { ------------------ | Branch (2194:11): [True: 0, False: 466M] ------------------ 2195| 0| i = soldi; 2196| 0| st.assign(word); // XXX add more optim. 2197| 0| soldi = 0; 2198| 0| len = oldlen; 2199| 0| cmin = oldcmin; 2200| 0| cmax = oldcmax; 2201| 0| } else 2202| 466M| st[i] = ch; 2203| | 2204| 466M| } while (!defcpdtable.empty() && oldwordnum == 0 && ------------------ | Branch (2204:14): [True: 0, False: 466M] | Branch (2204:38): [True: 0, False: 0] ------------------ 2205| 0| onlycpdrule++ < 1); // end of onlycpd loop ------------------ | Branch (2205:14): [True: 0, False: 0] ------------------ 2206| 467M| } 2207| | 2208| 20.8M| return nullptr; 2209| 21.7M|} _ZN8AffixMgr20compound_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEssssPP6hentrySB_cRS6_PS7_R12AffixScratch: 2223| 1.75k| AffixScratch& scratch) { 2224| 1.75k| short oldnumsyllable, oldnumsyllable2, oldwordnum, oldwordnum2; 2225| 1.75k| hentry *rv = nullptr, *rv_first; 2226| 1.75k| std::string st, presult; 2227| 1.75k| char ch, affixed = 0; 2228| 1.75k| int checked_prefix, ok = 0; 2229| 1.75k| size_t cmin, cmax; 2230| 1.75k| hentry** oldwords = words; 2231| 1.75k| size_t len = word.size(); 2232| | 2233| | // protect subsequent words[wnum + 1] reads and any recursion 2234| 1.75k| if (wnum + 1 >= maxwordnum) ------------------ | Branch (2234:7): [True: 0, False: 1.75k] ------------------ 2235| 0| return 0; 2236| | 2237| | // add a time limit to handle possible 2238| | // combinatorical explosion of the overlapping words 2239| | 2240| 1.75k| HUNSPELL_THREAD_LOCAL std::chrono::steady_clock::time_point clock_time_start; ------------------ | | 60| 1.75k|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 2241| 1.75k| HUNSPELL_THREAD_LOCAL bool timelimit_exceeded; ------------------ | | 60| 1.75k|# define HUNSPELL_THREAD_LOCAL thread_local ------------------ 2242| | 2243| | // get the current time 2244| 1.75k| std::chrono::steady_clock::time_point clock_now = std::chrono::steady_clock::now(); 2245| | 2246| 1.75k| if (wnum == 0) { ------------------ | Branch (2246:7): [True: 1.75k, False: 0] ------------------ 2247| | // set the start time 2248| 1.75k| clock_time_start = clock_now; 2249| 1.75k| timelimit_exceeded = false; 2250| 1.75k| } 2251| 0| else if (clock_now - clock_time_start > TIMELIMIT_MS) ------------------ | | 106| 0|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (2251:12): [True: 0, False: 0] ------------------ 2252| 0| timelimit_exceeded = true; 2253| | 2254| 1.75k| setcminmax(&cmin, &cmax, word.c_str(), len); 2255| | 2256| 1.75k| st.assign(word); 2257| | 2258| 28.7k| for (size_t i = cmin; i < cmax; ++i) { ------------------ | Branch (2258:25): [True: 27.1k, False: 1.56k] ------------------ 2259| | // go to end of the UTF-8 character 2260| 27.1k| if (utf8) { ------------------ | Branch (2260:9): [True: 7.63k, False: 19.5k] ------------------ 2261| 10.0k| for (; is_utf8_cont(st[i]); i++) ------------------ | Branch (2261:14): [True: 2.37k, False: 7.63k] ------------------ 2262| 2.37k| ; 2263| 7.63k| if (i >= cmax) ------------------ | Branch (2263:11): [True: 58, False: 7.57k] ------------------ 2264| 58| return 0; 2265| 7.63k| } 2266| | 2267| 27.1k| words = oldwords; 2268| 27.1k| int onlycpdrule = (words) ? 1 : 0; ------------------ | Branch (2268:23): [True: 0, False: 27.1k] ------------------ 2269| | 2270| 27.1k| do { // onlycpdrule loop 2271| | 2272| 27.1k| if (timelimit_exceeded || ------------------ | Branch (2272:11): [True: 0, False: 27.1k] | Branch (2272:11): [True: 0, False: 27.1k] ------------------ 2273| 27.1k| std::chrono::steady_clock::now() - clock_time_start > TIMELIMIT_MS) { ------------------ | | 106| 27.1k|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (2273:11): [True: 0, False: 27.1k] ------------------ 2274| 0| timelimit_exceeded = true; 2275| 0| return 0; 2276| 0| } 2277| | 2278| 27.1k| if (result.size() > MAXMORPHRESULT) ------------------ | | 111| 27.1k|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (2278:11): [True: 0, False: 27.1k] ------------------ 2279| 0| return 0; 2280| | 2281| 27.1k| oldnumsyllable = numsyllable; 2282| 27.1k| oldwordnum = wordnum; 2283| 27.1k| checked_prefix = 0; 2284| | 2285| 27.1k| if (i >= st.size()) ------------------ | Branch (2285:11): [True: 138, False: 26.9k] ------------------ 2286| 138| return 0; 2287| | 2288| 26.9k| ch = st[i]; 2289| 26.9k| st[i] = '\0'; 2290| 26.9k| sfx = nullptr; 2291| | 2292| | // FIRST WORD 2293| | 2294| 26.9k| affixed = 1; 2295| | 2296| 26.9k| presult.clear(); 2297| 26.9k| if (partresult) ------------------ | Branch (2297:11): [True: 0, False: 26.9k] ------------------ 2298| 0| presult.append(*partresult); 2299| | 2300| 26.9k| rv = lookup(st.c_str(), i); // perhaps without prefix 2301| | 2302| | // forbid dictionary stems with COMPOUNDFORBIDFLAG in 2303| | // compound words, overriding the effect of COMPOUNDPERMITFLAG 2304| 26.9k| if ((rv) && compoundforbidflag && ------------------ | Branch (2304:11): [True: 116, False: 26.8k] | Branch (2304:19): [True: 68, False: 48] ------------------ 2305| 68| TESTAFF(rv->astr, compoundforbidflag, rv->alen) && !hu_mov_rule) ------------------ | | 99| 27.0k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 68] | | ------------------ ------------------ | Branch (2305:66): [True: 0, False: 0] ------------------ 2306| 0| continue; 2307| | 2308| | // search homonym with compound flag 2309| 27.1k| while ((rv) && !hu_mov_rule && ------------------ | Branch (2309:14): [True: 116, False: 26.9k] | Branch (2309:22): [True: 116, False: 0] ------------------ 2310| 116| ((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) || ------------------ | | 99| 16|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 16] | | ------------------ ------------------ | Branch (2310:16): [True: 16, False: 100] ------------------ 2311| 116| !((compoundflag && !words && !onlycpdrule && ------------------ | Branch (2311:18): [True: 116, False: 0] | Branch (2311:34): [True: 116, False: 0] | Branch (2311:44): [True: 116, False: 0] ------------------ 2312| 116| TESTAFF(rv->astr, compoundflag, rv->alen)) || ------------------ | | 99| 116|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 116] | | ------------------ ------------------ 2313| 116| (compoundbegin && !wordnum && !onlycpdrule && ------------------ | Branch (2313:18): [True: 0, False: 116] | Branch (2313:35): [True: 0, False: 0] | Branch (2313:47): [True: 0, False: 0] ------------------ 2314| 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] | | ------------------ ------------------ 2315| 116| (compoundmiddle && wordnum && !words && !onlycpdrule && ------------------ | Branch (2315:18): [True: 0, False: 116] | Branch (2315:36): [True: 0, False: 0] | Branch (2315:47): [True: 0, False: 0] | Branch (2315:57): [True: 0, False: 0] ------------------ 2316| 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] | | ------------------ ------------------ 2317| 116| (!defcpdtable.empty() && onlycpdrule && ------------------ | Branch (2317:18): [True: 0, False: 116] | Branch (2317:42): [True: 0, False: 0] ------------------ 2318| 0| ((!words && !wordnum && ------------------ | Branch (2318:20): [True: 0, False: 0] | Branch (2318:30): [True: 0, False: 0] ------------------ 2319| 0| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0)) || ------------------ | Branch (2319:20): [True: 0, False: 0] ------------------ 2320| 0| (words && ------------------ | Branch (2320:20): [True: 0, False: 0] ------------------ 2321| 116| defcpd_check(&words, wnum, maxwordnum, rv, rwords, 0))))))) { ------------------ | Branch (2321:20): [True: 0, False: 0] ------------------ 2322| 116| rv = rv->next_homonym; 2323| 116| } 2324| | 2325| | 2326| 26.9k| if (rv) ------------------ | Branch (2326:11): [True: 0, False: 26.9k] ------------------ 2327| 0| affixed = 0; 2328| | 2329| 26.9k| if (rv) { ------------------ | Branch (2329:11): [True: 0, False: 26.9k] ------------------ 2330| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2331| 0| presult.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2332| 0| presult.append(st, 0, i); 2333| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (2333:13): [True: 0, False: 0] ------------------ 2334| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2335| 0| presult.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 2336| 0| presult.append(st, 0, i); 2337| 0| } 2338| 0| if (HENTRY_DATA(rv)) { ------------------ | Branch (2338:13): [True: 0, False: 0] ------------------ 2339| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2340| 0| presult.append(HENTRY_DATA2(rv)); 2341| 0| } 2342| 0| } 2343| | 2344| 26.9k| if (!rv) { ------------------ | Branch (2344:11): [True: 26.9k, False: 0] ------------------ 2345| 26.9k| if (compoundflag && ------------------ | Branch (2345:13): [True: 26.9k, False: 0] ------------------ 2346| 26.9k| !(rv = ------------------ | Branch (2346:13): [True: 26.9k, False: 0] ------------------ 2347| 26.9k| 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| 53.9k|#define IN_CPD_BEGIN 1 ------------------ | Branch (2347:42): [True: 0, False: 26.9k] ------------------ 2348| 26.9k| scratch, compoundflag))) { 2349| 26.9k| if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 96| 26.9k|#define FLAG_NULL 0x00 ------------------ if (((rv = suffix_check(st, 0, i, 0, nullptr, scratch, FLAG_NULL, compoundflag, hu_mov_rule ? IN_CPD_OTHER : IN_CPD_BEGIN)) || ------------------ | | 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| 53.9k|#define IN_CPD_BEGIN 1 ------------------ | Branch (2349:16): [True: 0, False: 26.9k] | Branch (2349:91): [True: 0, False: 26.9k] ------------------ 2350| 26.9k| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, compoundflag)))) && ------------------ | Branch (2350:17): [True: 0, False: 26.9k] | Branch (2350:41): [True: 0, False: 0] ------------------ 2351| 0| !hu_mov_rule && sfx->getCont() && ------------------ | Branch (2351:15): [True: 0, False: 0] | Branch (2351:31): [True: 0, False: 0] ------------------ 2352| 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 (2352:17): [True: 0, False: 0] ------------------ 2353| 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 (2353:17): [True: 0, False: 0] ------------------ 2354| 0| rv = nullptr; 2355| 0| } 2356| 26.9k| } 2357| | 2358| 26.9k| if (rv || ------------------ | Branch (2358:13): [True: 0, False: 26.9k] ------------------ 2359| 26.9k| (((wordnum == 0) && compoundbegin && ------------------ | Branch (2359:15): [True: 26.9k, False: 0] | Branch (2359:33): [True: 0, False: 26.9k] ------------------ 2360| 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 (2360:16): [True: 0, False: 0] | Branch (2360:92): [True: 0, False: 0] ------------------ 2361| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (2361:17): [True: 0, False: 0] | Branch (2361:41): [True: 0, False: 0] ------------------ 2362| 0| compoundbegin))) || // twofold suffix+compound 2363| 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 (2363:16): [True: 0, False: 0] | Branch (2363:45): [True: 0, False: 0] ------------------ 2364| 26.9k| ((wordnum > 0) && compoundmiddle && ------------------ | Branch (2364:15): [True: 0, False: 26.9k] | Branch (2364:32): [True: 0, False: 0] ------------------ 2365| 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 (2365:16): [True: 0, False: 0] | Branch (2365:93): [True: 0, False: 0] ------------------ 2366| 0| (compoundmoresuffixes && (rv = suffix_check_twosfx(st, 0, i, 0, nullptr, scratch, ------------------ | Branch (2366:17): [True: 0, False: 0] | Branch (2366:41): [True: 0, False: 0] ------------------ 2367| 0| compoundmiddle))) || // twofold suffix+compound 2368| 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 (2368:16): [True: 0, False: 0] | Branch (2368:45): [True: 0, False: 0] ------------------ 2369| 0| std::string p; 2370| 0| if (compoundflag) ------------------ | Branch (2370:15): [True: 0, False: 0] ------------------ 2371| 0| p = affix_check_morph(st, 0, i, scratch, compoundflag); 2372| 0| if (p.empty()) { ------------------ | Branch (2372:15): [True: 0, False: 0] ------------------ 2373| 0| if ((wordnum == 0) && compoundbegin) { ------------------ | Branch (2373:17): [True: 0, False: 0] | Branch (2373:35): [True: 0, False: 0] ------------------ 2374| 0| p = affix_check_morph(st, 0, i, scratch, compoundbegin); 2375| 0| } else if ((wordnum > 0) && compoundmiddle) { ------------------ | Branch (2375:24): [True: 0, False: 0] | Branch (2375:41): [True: 0, False: 0] ------------------ 2376| 0| p = affix_check_morph(st, 0, i, scratch, compoundmiddle); 2377| 0| } 2378| 0| } 2379| 0| if (!p.empty()) { ------------------ | Branch (2379:15): [True: 0, False: 0] ------------------ 2380| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2381| 0| presult.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2382| 0| presult.append(st, 0, i); 2383| 0| line_uniq_app(p, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2384| 0| if (!p.empty() && p[0] != MSEP_FLD) ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ | Branch (2384:17): [True: 0, False: 0] | Branch (2384:31): [True: 0, False: 0] ------------------ 2385| 0| presult.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2386| 0| presult.append(p); 2387| 0| } 2388| 0| checked_prefix = 1; 2389| 0| } 2390| | // else check forbiddenwords 2391| 26.9k| } 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 (2391:18): [True: 0, False: 0] | Branch (2391:18): [True: 0, False: 0] ------------------ 2392| 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] | | ------------------ ------------------ 2393| 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] | | ------------------ ------------------ 2394| 0| st[i] = ch; 2395| 0| continue; 2396| 0| } 2397| | 2398| | // check non_compound flag in suffix and prefix 2399| 26.9k| if ((rv) && !hu_mov_rule && ------------------ | Branch (2399:11): [True: 0, False: 26.9k] | Branch (2399:19): [True: 0, False: 0] ------------------ 2400| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2400:13): [True: 0, False: 0] | Branch (2400:20): [True: 0, False: 0] ------------------ 2401| 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] | | ------------------ ------------------ 2402| 0| (sfx && sfx->getCont() && ------------------ | Branch (2402:13): [True: 0, False: 0] | Branch (2402:20): [True: 0, False: 0] ------------------ 2403| 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] | | ------------------ ------------------ 2404| 0| continue; 2405| 0| } 2406| | 2407| | // check compoundend flag in suffix and prefix 2408| 26.9k| if ((rv) && !checked_prefix && compoundend && !hu_mov_rule && ------------------ | Branch (2408:11): [True: 0, False: 26.9k] | Branch (2408:19): [True: 0, False: 0] | Branch (2408:38): [True: 0, False: 0] | Branch (2408:53): [True: 0, False: 0] ------------------ 2409| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2409:13): [True: 0, False: 0] | Branch (2409:20): [True: 0, False: 0] ------------------ 2410| 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] | | ------------------ ------------------ 2411| 0| (sfx && sfx->getCont() && ------------------ | Branch (2411:13): [True: 0, False: 0] | Branch (2411:20): [True: 0, False: 0] ------------------ 2412| 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] | | ------------------ ------------------ 2413| 0| continue; 2414| 0| } 2415| | 2416| | // check compoundmiddle flag in suffix and prefix 2417| 26.9k| if ((rv) && !checked_prefix && (wordnum == 0) && compoundmiddle && ------------------ | Branch (2417:11): [True: 0, False: 26.9k] | Branch (2417:19): [True: 0, False: 0] | Branch (2417:38): [True: 0, False: 0] | Branch (2417:56): [True: 0, False: 0] ------------------ 2418| 0| !hu_mov_rule && ------------------ | Branch (2418:11): [True: 0, False: 0] ------------------ 2419| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2419:13): [True: 0, False: 0] | Branch (2419:20): [True: 0, False: 0] ------------------ 2420| 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] | | ------------------ ------------------ 2421| 0| (sfx && sfx->getCont() && ------------------ | Branch (2421:13): [True: 0, False: 0] | Branch (2421:20): [True: 0, False: 0] ------------------ 2422| 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] | | ------------------ ------------------ 2423| 0| rv = nullptr; 2424| 0| } 2425| | 2426| | // check forbiddenwords 2427| 26.9k| 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 (2427:11): [True: 0, False: 26.9k] | Branch (2427:11): [True: 0, False: 26.9k] | Branch (2427:19): [True: 0, False: 0] ------------------ 2428| 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] | | ------------------ ------------------ 2429| 0| continue; 2430| | 2431| | // increment word number, if the second root has a compoundroot flag 2432| 26.9k| if ((rv) && (compoundroot) && ------------------ | Branch (2432:11): [True: 0, False: 26.9k] | Branch (2432:19): [True: 0, False: 0] ------------------ 2433| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2433:11): [True: 0, False: 0] ------------------ 2434| 0| wordnum++; 2435| 0| } 2436| | 2437| | // first word is acceptable in compound words? 2438| 26.9k| if (((rv) && ------------------ | Branch (2438:11): [True: 0, False: 26.9k] | Branch (2438:12): [True: 0, False: 26.9k] ------------------ 2439| 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 (2439:13): [True: 0, False: 0] | Branch (2439:32): [True: 0, False: 0] | Branch (2439:41): [True: 0, False: 0] | Branch (2439:58): [True: 0, False: 0] ------------------ 2440| 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 (2440:14): [True: 0, False: 0] | Branch (2440:35): [True: 0, False: 0] ------------------ 2441| 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 (2441:14): [True: 0, False: 0] | Branch (2441:34): [True: 0, False: 0] ------------------ 2442| | // LANG_hu section: spec. Hungarian rule 2443| 0| || ((langnum == LANG_hu) && // hu_mov_rule ------------------ | Branch (2443:17): [True: 0, False: 0] ------------------ 2444| 0| hu_mov_rule && ------------------ | Branch (2444:17): [True: 0, False: 0] ------------------ 2445| 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] | | ------------------ ------------------ 2446| | // END of LANG_hu section 2447| 0| ) && 2448| 0| !((checkcompoundtriple && !words && // test triple letters ------------------ | Branch (2448:15): [True: 0, False: 0] | Branch (2448:38): [True: 0, False: 0] ------------------ 2449| 0| (word[i - 1] == word[i]) && ------------------ | Branch (2449:15): [True: 0, False: 0] ------------------ 2450| 0| (((i > 1) && (word[i - 1] == word[i - 2])) || ((word[i - 1] == word[i + 1])) // may be word[i+1] == '\0' ------------------ | Branch (2450:17): [True: 0, False: 0] | Branch (2450:28): [True: 0, False: 0] | Branch (2450:61): [True: 0, False: 0] ------------------ 2451| 0| )) || 2452| 0| ( 2453| | // test CHECKCOMPOUNDPATTERN 2454| 0| !checkcpdtable.empty() && !words && cpdpat_check(word, i, rv, nullptr, affixed)) || ------------------ | Branch (2454:18): [True: 0, False: 0] | Branch (2454:44): [True: 0, False: 0] | Branch (2454:54): [True: 0, False: 0] ------------------ 2455| 0| (checkcompoundcase && !words && cpdcase_check(word, i)))) ------------------ | Branch (2455:15): [True: 0, False: 0] | Branch (2455:36): [True: 0, False: 0] | Branch (2455:46): [True: 0, False: 0] ------------------ 2456| | // LANG_hu section: spec. Hungarian rule 2457| 26.9k| || ((!rv) && (langnum == LANG_hu) && hu_mov_rule && (rv = affix_check(st, 0, i, scratch)) && ------------------ | Branch (2457:15): [True: 26.9k, False: 0] | Branch (2457:24): [True: 7.57k, False: 19.4k] | Branch (2457:48): [True: 0, False: 7.57k] | Branch (2457:63): [True: 0, False: 0] ------------------ 2458| 0| (sfx && sfx->getCont() && ------------------ | Branch (2458:16): [True: 0, False: 0] | Branch (2458:23): [True: 0, False: 0] ------------------ 2459| 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] | | ------------------ ------------------ 2460| 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] | | ------------------ ------------------ 2461| | // END of LANG_hu section 2462| 26.9k| ) { 2463| | // LANG_hu section: spec. Hungarian rule 2464| 0| if (langnum == LANG_hu) { ------------------ | Branch (2464:13): [True: 0, False: 0] ------------------ 2465| | // calculate syllable number of the word 2466| 0| numsyllable += get_syllable(st.substr(0, i)); 2467| | 2468| | // + 1 word, if syllable number of the prefix > 1 (hungarian 2469| | // convention) 2470| 0| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (2470:15): [True: 0, False: 0] | Branch (2470:15): [True: 0, False: 0] | Branch (2470:22): [True: 0, False: 0] ------------------ 2471| 0| wordnum++; 2472| 0| } 2473| | // END of LANG_hu section 2474| | 2475| | // NEXT WORD(S) 2476| 0| rv_first = rv; 2477| 0| rv = lookup(word.c_str() + i, word.size() - i); // perhaps without prefix 2478| | 2479| | // search homonym with compound flag 2480| 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 (2480:16): [True: 0, False: 0] | Branch (2480:26): [True: 0, False: 0] ------------------ 2481| 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 (2481:28): [True: 0, False: 0] | Branch (2481:44): [True: 0, False: 0] ------------------ 2482| 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 (2482:28): [True: 0, False: 0] | Branch (2482:43): [True: 0, False: 0] ------------------ 2483| 0| (!defcpdtable.empty() && words && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1))))) { ------------------ | Branch (2483:28): [True: 0, False: 0] | Branch (2483:52): [True: 0, False: 0] | Branch (2483:61): [True: 0, False: 0] ------------------ 2484| 0| rv = rv->next_homonym; 2485| 0| } 2486| | 2487| 0| if (rv && words && words[wnum + 1]) { ------------------ | Branch (2487:13): [True: 0, False: 0] | Branch (2487:19): [True: 0, False: 0] | Branch (2487:28): [True: 0, False: 0] ------------------ 2488| 0| result.append(presult); 2489| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2490| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2491| 0| result.append(word, i, word.size()); 2492| 0| if (complexprefixes && HENTRY_DATA(rv)) ------------------ | Branch (2492:15): [True: 0, False: 0] | Branch (2492:34): [True: 0, False: 0] ------------------ 2493| 0| result.append(HENTRY_DATA2(rv)); 2494| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (2494:15): [True: 0, False: 0] ------------------ 2495| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2496| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 2497| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 2498| 0| } 2499| | // store the pointer of the hash entry 2500| 0| if (!complexprefixes && HENTRY_DATA(rv)) { ------------------ | Branch (2500:15): [True: 0, False: 0] | Branch (2500:35): [True: 0, False: 0] ------------------ 2501| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2502| 0| result.append(HENTRY_DATA2(rv)); 2503| 0| } 2504| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2505| 0| return 0; 2506| 0| } 2507| | 2508| 0| oldnumsyllable2 = numsyllable; 2509| 0| oldwordnum2 = wordnum; 2510| | 2511| | // LANG_hu section: spec. Hungarian rule 2512| 0| if ((rv) && (langnum == LANG_hu) && ------------------ | Branch (2512:13): [True: 0, False: 0] | Branch (2512:13): [True: 0, False: 0] | Branch (2512:21): [True: 0, False: 0] ------------------ 2513| 0| (TESTAFF(rv->astr, 'I', rv->alen)) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2513:13): [True: 0, False: 0] ------------------ 2514| 0| !(TESTAFF(rv->astr, 'J', 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| numsyllable--; 2516| 0| } 2517| | // END of LANG_hu section 2518| | // increment word number, if the second root has a compoundroot flag 2519| 0| if ((rv) && (compoundroot) && ------------------ | Branch (2519:13): [True: 0, False: 0] | Branch (2519:21): [True: 0, False: 0] ------------------ 2520| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2520:13): [True: 0, False: 0] ------------------ 2521| 0| wordnum++; 2522| 0| } 2523| | 2524| | // check forbiddenwords 2525| 0| if ((rv) && (rv->astr) && ------------------ | Branch (2525:13): [True: 0, False: 0] | Branch (2525:13): [True: 0, False: 0] | Branch (2525:21): [True: 0, False: 0] ------------------ 2526| 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] | | ------------------ ------------------ 2527| 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] | | ------------------ ------------------ 2528| 0| st[i] = ch; 2529| 0| continue; 2530| 0| } 2531| | 2532| | // second word is acceptable, as a root? 2533| | // hungarian conventions: compounding is acceptable, 2534| | // when compound forms consist of 2 words, or if more, 2535| | // then the syllable number of root words must be 6, or lesser. 2536| 0| if ((rv) && ------------------ | Branch (2536:13): [True: 0, False: 0] | Branch (2536:13): [True: 0, False: 0] ------------------ 2537| 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 (2537:15): [True: 0, False: 0] ------------------ 2538| 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 (2538:15): [True: 0, False: 0] ------------------ 2539| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (2539:15): [True: 0, False: 0] | Branch (2539:37): [True: 0, False: 0] ------------------ 2540| 0| ((cpdmaxsyllable != 0) && ------------------ | Branch (2540:15): [True: 0, False: 0] ------------------ 2541| 0| (numsyllable + get_syllable(std::string(HENTRY_WORD(rv), rv->blen)) <= ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ | Branch (2541:15): [True: 0, False: 0] ------------------ 2542| 0| cpdmaxsyllable))) && 2543| 0| ((!checkcompounddup || (rv != rv_first)))) { ------------------ | Branch (2543:15): [True: 0, False: 0] | Branch (2543:36): [True: 0, False: 0] ------------------ 2544| | // bad compound word 2545| 0| result.append(presult); 2546| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2547| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2548| 0| result.append(word, i, word.size()); 2549| | 2550| 0| if (HENTRY_DATA(rv)) { ------------------ | Branch (2550:15): [True: 0, False: 0] ------------------ 2551| 0| if (complexprefixes) ------------------ | Branch (2551:17): [True: 0, False: 0] ------------------ 2552| 0| result.append(HENTRY_DATA2(rv)); 2553| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (2553:17): [True: 0, False: 0] ------------------ 2554| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2555| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 2556| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 2557| 0| } 2558| | // store the pointer of the hash entry 2559| 0| if (!complexprefixes) { ------------------ | Branch (2559:17): [True: 0, False: 0] ------------------ 2560| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2561| 0| result.append(HENTRY_DATA2(rv)); 2562| 0| } 2563| 0| } 2564| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2565| 0| ok = 1; 2566| 0| } 2567| | 2568| 0| numsyllable = oldnumsyllable2; 2569| 0| wordnum = oldwordnum2; 2570| | 2571| | // perhaps second word has prefix or/and suffix 2572| 0| sfx = nullptr; 2573| 0| sfxflag = FLAG_NULL; ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ 2574| | 2575| 0| if (compoundflag && !onlycpdrule) ------------------ | Branch (2575:13): [True: 0, False: 0] | Branch (2575:29): [True: 0, False: 0] ------------------ 2576| 0| rv = affix_check(word, i, word.size() - i, scratch, compoundflag); 2577| 0| else 2578| 0| rv = nullptr; 2579| | 2580| 0| if (!rv && compoundend && !onlycpdrule) { ------------------ | Branch (2580:13): [True: 0, False: 0] | Branch (2580:20): [True: 0, False: 0] | Branch (2580:35): [True: 0, False: 0] ------------------ 2581| 0| sfx = nullptr; 2582| 0| pfx = nullptr; 2583| 0| rv = affix_check(word, i, word.size() - i, scratch, compoundend); 2584| 0| } 2585| | 2586| 0| if (!rv && !defcpdtable.empty() && words) { ------------------ | Branch (2586:13): [True: 0, False: 0] | Branch (2586:20): [True: 0, False: 0] | Branch (2586:44): [True: 0, False: 0] ------------------ 2587| 0| rv = affix_check(word, i, word.size() - i, scratch, 0, IN_CPD_END); ------------------ | | 74| 0|#define IN_CPD_END 2 ------------------ 2588| 0| if (rv && words && defcpd_check(&words, wnum + 1, maxwordnum, rv, nullptr, 1)) { ------------------ | Branch (2588:15): [True: 0, False: 0] | Branch (2588:21): [True: 0, False: 0] | Branch (2588:30): [True: 0, False: 0] ------------------ 2589| 0| std::string m; 2590| 0| if (compoundflag) ------------------ | Branch (2590:17): [True: 0, False: 0] ------------------ 2591| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundflag); 2592| 0| if (m.empty() && compoundend) { ------------------ | Branch (2592:17): [True: 0, False: 0] | Branch (2592:30): [True: 0, False: 0] ------------------ 2593| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundend); 2594| 0| } 2595| 0| result.append(presult); 2596| 0| if (!m.empty()) { ------------------ | Branch (2596:17): [True: 0, False: 0] ------------------ 2597| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2598| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2599| 0| result.append(word, i, word.size()); 2600| 0| line_uniq_app(m, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2601| 0| result.append(m); 2602| 0| } 2603| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2604| 0| ok = 1; 2605| 0| } 2606| 0| } 2607| | 2608| | // check non_compound flag in suffix and prefix 2609| 0| if ((rv) && ------------------ | Branch (2609:13): [True: 0, False: 0] ------------------ 2610| 0| ((pfx && pfx->getCont() && ------------------ | Branch (2610:15): [True: 0, False: 0] | Branch (2610:22): [True: 0, False: 0] ------------------ 2611| 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] | | ------------------ ------------------ 2612| 0| (sfx && sfx->getCont() && ------------------ | Branch (2612:15): [True: 0, False: 0] | Branch (2612:22): [True: 0, False: 0] ------------------ 2613| 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] | | ------------------ ------------------ 2614| 0| sfx->getContLen())))) { 2615| 0| rv = nullptr; 2616| 0| } 2617| | 2618| | // check forbiddenwords 2619| 0| if ((rv) && (rv->astr) && ------------------ | Branch (2619:13): [True: 0, False: 0] | Branch (2619:13): [True: 0, False: 0] | Branch (2619:21): [True: 0, False: 0] ------------------ 2620| 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] | | ------------------ ------------------ 2621| 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] | | ------------------ ------------------ 2622| 0| (!TESTAFF(rv->astr, needaffix, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2622:13): [True: 0, False: 0] ------------------ 2623| 0| st[i] = ch; 2624| 0| continue; 2625| 0| } 2626| | 2627| 0| if (langnum == LANG_hu) { ------------------ | Branch (2627:13): [True: 0, False: 0] ------------------ 2628| | // calculate syllable number of the word 2629| 0| numsyllable += get_syllable(word.c_str() + i); 2630| | 2631| | // - affix syllable num. 2632| | // XXX only second suffix (inflections, not derivations) 2633| 0| if (sfxappnd) { ------------------ | Branch (2633:15): [True: 0, False: 0] ------------------ 2634| 0| std::string tmp(sfxappnd); 2635| 0| reverseword(tmp); 2636| 0| numsyllable -= short(get_syllable(tmp) + sfxextra); 2637| 0| } else { 2638| 0| numsyllable -= short(sfxextra); 2639| 0| } 2640| | 2641| | // + 1 word, if syllable number of the prefix > 1 (hungarian 2642| | // convention) 2643| 0| if (pfx && (get_syllable(pfx->getKey()) > 1)) ------------------ | Branch (2643:15): [True: 0, False: 0] | Branch (2643:15): [True: 0, False: 0] | Branch (2643:22): [True: 0, False: 0] ------------------ 2644| 0| wordnum++; 2645| | 2646| | // increment syllable num, if last word has a SYLLABLENUM flag 2647| | // and the suffix is beginning `s' 2648| | 2649| 0| if (!cpdsyllablenum.empty()) { ------------------ | Branch (2649:15): [True: 0, False: 0] ------------------ 2650| 0| switch (sfxflag) { ------------------ | Branch (2650:21): [True: 0, False: 0] ------------------ 2651| 0| case 'c': { ------------------ | Branch (2651:15): [True: 0, False: 0] ------------------ 2652| 0| numsyllable += 2; 2653| 0| break; 2654| 0| } 2655| 0| case 'J': { ------------------ | Branch (2655:15): [True: 0, False: 0] ------------------ 2656| 0| numsyllable += 1; 2657| 0| break; 2658| 0| } 2659| 0| case 'I': { ------------------ | Branch (2659:15): [True: 0, False: 0] ------------------ 2660| 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 (2660:21): [True: 0, False: 0] | Branch (2660:21): [True: 0, False: 0] ------------------ 2661| 0| numsyllable += 1; 2662| 0| break; 2663| 0| } 2664| 0| } 2665| 0| } 2666| 0| } 2667| | 2668| | // increment word number, if the second word has a compoundroot flag 2669| 0| if ((rv) && (compoundroot) && ------------------ | Branch (2669:13): [True: 0, False: 0] | Branch (2669:21): [True: 0, False: 0] ------------------ 2670| 0| (TESTAFF(rv->astr, compoundroot, rv->alen))) { ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2670:13): [True: 0, False: 0] ------------------ 2671| 0| wordnum++; 2672| 0| } 2673| | // second word is acceptable, as a word with prefix or/and suffix? 2674| | // hungarian conventions: compounding is acceptable, 2675| | // when compound forms consist 2 word, otherwise 2676| | // the syllable number of root words is 6, or lesser. 2677| 0| if ((rv) && ------------------ | Branch (2677:13): [True: 0, False: 0] ------------------ 2678| 0| (((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) || ------------------ | Branch (2678:15): [True: 0, False: 0] | Branch (2678:37): [True: 0, False: 0] ------------------ 2679| 0| ((cpdmaxsyllable != 0) && (numsyllable <= cpdmaxsyllable))) && ------------------ | Branch (2679:15): [True: 0, False: 0] | Branch (2679:40): [True: 0, False: 0] ------------------ 2680| 0| ((!checkcompounddup || (rv != rv_first)))) { ------------------ | Branch (2680:15): [True: 0, False: 0] | Branch (2680:36): [True: 0, False: 0] ------------------ 2681| 0| std::string m; 2682| 0| if (compoundflag) ------------------ | Branch (2682:15): [True: 0, False: 0] ------------------ 2683| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundflag); 2684| 0| if (m.empty() && compoundend) { ------------------ | Branch (2684:15): [True: 0, False: 0] | Branch (2684:28): [True: 0, False: 0] ------------------ 2685| 0| m = affix_check_morph(word, i, word.size() - i, scratch, compoundend); 2686| 0| } 2687| 0| result.append(presult); 2688| 0| if (!m.empty()) { ------------------ | Branch (2688:15): [True: 0, False: 0] ------------------ 2689| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2690| 0| result.append(MORPH_PART); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 2691| 0| result.append(word, i, word.size()); 2692| 0| line_uniq_app(m, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2693| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2694| 0| result.append(m); 2695| 0| } 2696| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2697| 0| ok = 1; 2698| 0| } 2699| | 2700| 0| numsyllable = oldnumsyllable2; 2701| 0| wordnum = oldwordnum2; 2702| | 2703| | // perhaps second word is a compound word (recursive call) 2704| 0| if ((wordnum + 2 < maxwordnum) && (wnum + 1 < maxwordnum) && (ok == 0)) { ------------------ | Branch (2704:13): [True: 0, False: 0] | Branch (2704:43): [True: 0, False: 0] | Branch (2704:70): [True: 0, False: 0] ------------------ 2705| 0| compound_check_morph(word.substr(i), wordnum + 1, 2706| 0| numsyllable, maxwordnum, wnum + 1, words, rwords, 0, 2707| 0| result, &presult, scratch); 2708| 0| } else { 2709| 0| rv = nullptr; 2710| 0| } 2711| 0| } 2712| 26.9k| st[i] = ch; 2713| 26.9k| wordnum = oldwordnum; 2714| 26.9k| numsyllable = oldnumsyllable; 2715| | 2716| 26.9k| } while (!defcpdtable.empty() && oldwordnum == 0 && ------------------ | Branch (2716:14): [True: 0, False: 26.9k] | Branch (2716:38): [True: 0, False: 0] ------------------ 2717| 0| onlycpdrule++ < 1); // end of onlycpd loop ------------------ | Branch (2717:14): [True: 0, False: 0] ------------------ 2718| 27.1k| } 2719| 1.56k| return 0; 2720| 1.75k|} _ZN8AffixMgr12suffix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratchttct: 2744| 512M| const FLAG avoidflag) { 2745| 512M| struct hentry* rv = nullptr; 2746| 512M| PfxEntry* ep = ppfx; 2747| | 2748| | // first handle the special case of 0 length suffixes 2749| 512M| SfxEntry* se = sStart[0]; 2750| | 2751| 512M| while (se) { ------------------ | Branch (2751:10): [True: 0, False: 512M] ------------------ 2752| 0| if (!cclass || se->getCont()) { ------------------ | Branch (2752:9): [True: 0, False: 0] | Branch (2752:20): [True: 0, False: 0] ------------------ 2753| | // suffixes are not allowed in beginning of compounds 2754| 0| if ((((in_compound != IN_CPD_BEGIN)) || // && !cclass ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (2754:12): [True: 0, False: 0] ------------------ 2755| | // except when signed with compoundpermitflag flag 2756| 0| (se->getCont() && compoundpermitflag && ------------------ | Branch (2756:13): [True: 0, False: 0] | Branch (2756:30): [True: 0, False: 0] ------------------ 2757| 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] | | ------------------ ------------------ 2758| 0| (!circumfix || ------------------ | Branch (2758:12): [True: 0, False: 0] ------------------ 2759| | // no circumfix flag in prefix and suffix 2760| 0| ((!ppfx || !(ep->getCont()) || ------------------ | Branch (2760:14): [True: 0, False: 0] | Branch (2760:23): [True: 0, False: 0] ------------------ 2761| 0| !TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2761:14): [True: 0, False: 0] ------------------ 2762| 0| (!se->getCont() || ------------------ | Branch (2762:14): [True: 0, False: 0] ------------------ 2763| 0| !(TESTAFF(se->getCont(), circumfix, se->getContLen())))) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2763:14): [True: 0, False: 0] ------------------ 2764| | // circumfix flag in prefix AND suffix 2765| 0| ((ppfx && (ep->getCont()) && ------------------ | Branch (2765:14): [True: 0, False: 0] | Branch (2765:22): [True: 0, False: 0] ------------------ 2766| 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] | | ------------------ ------------------ 2767| 0| (se->getCont() && ------------------ | Branch (2767:14): [True: 0, False: 0] ------------------ 2768| 0| (TESTAFF(se->getCont(), circumfix, se->getContLen()))))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2768:14): [True: 0, False: 0] ------------------ 2769| | // fogemorpheme 2770| 0| (in_compound || ------------------ | Branch (2770:12): [True: 0, False: 0] ------------------ 2771| 0| !(se->getCont() && ------------------ | Branch (2771:14): [True: 0, False: 0] ------------------ 2772| 0| (TESTAFF(se->getCont(), onlyincompound, se->getContLen())))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2772:14): [True: 0, False: 0] ------------------ 2773| | // needaffix on prefix or first suffix 2774| 0| (cclass || ------------------ | Branch (2774:12): [True: 0, False: 0] ------------------ 2775| 0| !(se->getCont() && ------------------ | Branch (2775:14): [True: 0, False: 0] ------------------ 2776| 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] | | ------------------ ------------------ 2777| 0| (ppfx && ------------------ | Branch (2777:13): [True: 0, False: 0] ------------------ 2778| 0| !((ep->getCont()) && ------------------ | Branch (2778:15): [True: 0, False: 0] ------------------ 2779| 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] | | ------------------ ------------------ 2780| 0| rv = se->checkword(word, start, len, sfxopts, ppfx, 2781| 0| (FLAG)cclass, needflag, 2782| 0| (in_compound ? 0 : onlyincompound), ------------------ | Branch (2782:29): [True: 0, False: 0] ------------------ 2783| 0| scratch); 2784| | // Skip a stem with the avoid flag and keep scanning the other suffixes. 2785| 0| if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2785:13): [True: 0, False: 0] | Branch (2785:19): [True: 0, False: 0] ------------------ 2786| 0| rv = nullptr; 2787| 0| if (rv) { ------------------ | Branch (2787:13): [True: 0, False: 0] ------------------ 2788| 0| sfx = se; // BUG: sfx not stateless 2789| 0| return rv; 2790| 0| } 2791| 0| } 2792| 0| } 2793| 0| se = se->getNext(); 2794| 0| } 2795| | 2796| | // now handle the general case 2797| 512M| if (len == 0) ------------------ | Branch (2797:7): [True: 41.6k, False: 512M] ------------------ 2798| 41.6k| return nullptr; // FULLSTRIP 2799| 512M| unsigned char sp = word[start + len - 1]; 2800| 512M| SfxEntry* sptr = sStart[sp]; 2801| | 2802| 512M| while (sptr) { ------------------ | Branch (2802:10): [True: 357k, False: 512M] ------------------ 2803| 357k| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (2803:9): [True: 300k, False: 56.7k] ------------------ 2804| | // suffixes are not allowed in beginning of compounds 2805| 300k| if ((((in_compound != IN_CPD_BEGIN)) || // && !cclass ------------------ | | 73| 300k|#define IN_CPD_BEGIN 1 ------------------ | Branch (2805:12): [True: 73.5k, False: 227k] ------------------ 2806| | // except when signed with compoundpermitflag flag 2807| 227k| (sptr->getCont() && compoundpermitflag && ------------------ | Branch (2807:13): [True: 227k, False: 0] | Branch (2807:32): [True: 0, False: 227k] ------------------ 2808| 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] | | ------------------ ------------------ 2809| 227k| sptr->getContLen()))) && 2810| 73.5k| (!circumfix || ------------------ | Branch (2810:12): [True: 73.5k, False: 0] ------------------ 2811| | // no circumfix flag in prefix and suffix 2812| 0| ((!ppfx || !(ep->getCont()) || ------------------ | Branch (2812:14): [True: 0, False: 0] | Branch (2812:23): [True: 0, False: 0] ------------------ 2813| 0| !TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2813:14): [True: 0, False: 0] ------------------ 2814| 0| (!sptr->getCont() || ------------------ | Branch (2814:14): [True: 0, False: 0] ------------------ 2815| 0| !(TESTAFF(sptr->getCont(), circumfix, sptr->getContLen())))) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2815:14): [True: 0, False: 0] ------------------ 2816| | // circumfix flag in prefix AND suffix 2817| 0| ((ppfx && (ep->getCont()) && ------------------ | Branch (2817:14): [True: 0, False: 0] | Branch (2817:22): [True: 0, False: 0] ------------------ 2818| 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] | | ------------------ ------------------ 2819| 0| (sptr->getCont() && ------------------ | Branch (2819:14): [True: 0, False: 0] ------------------ 2820| 0| (TESTAFF(sptr->getCont(), circumfix, sptr->getContLen()))))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2820:14): [True: 0, False: 0] ------------------ 2821| | // fogemorpheme 2822| 73.5k| (in_compound || ------------------ | Branch (2822:12): [True: 0, False: 73.5k] ------------------ 2823| 73.5k| !((sptr->getCont() && (TESTAFF(sptr->getCont(), onlyincompound, ------------------ | | 99| 28.9k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (2823:15): [True: 28.9k, False: 44.5k] | Branch (2823:34): [True: 0, False: 28.9k] ------------------ 2824| 28.9k| sptr->getContLen()))))) && 2825| | // needaffix on prefix or first suffix 2826| 73.5k| (cclass || ------------------ | Branch (2826:12): [True: 3.42k, False: 70.1k] ------------------ 2827| 70.1k| !(sptr->getCont() && ------------------ | Branch (2827:14): [True: 28.9k, False: 41.1k] ------------------ 2828| 28.9k| TESTAFF(sptr->getCont(), needaffix, sptr->getContLen())) || ------------------ | | 99| 28.9k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 28.9k] | | ------------------ ------------------ 2829| 0| (ppfx && ------------------ | Branch (2829:13): [True: 0, False: 0] ------------------ 2830| 0| !((ep->getCont()) && ------------------ | Branch (2830:15): [True: 0, False: 0] ------------------ 2831| 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] | | ------------------ ------------------ 2832| 73.5k| if (in_compound != IN_CPD_END || ppfx || ------------------ | | 74| 147k|#define IN_CPD_END 2 ------------------ | Branch (2832:13): [True: 73.5k, False: 0] | Branch (2832:42): [True: 0, False: 0] ------------------ 2833| 0| !(sptr->getCont() && ------------------ | Branch (2833:15): [True: 0, False: 0] ------------------ 2834| 73.5k| 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] | | ------------------ ------------------ 2835| 73.5k| rv = sptr->checkword(word, start, len, sfxopts, ppfx, 2836| 73.5k| cclass, needflag, 2837| 73.5k| (in_compound ? 0 : onlyincompound), ------------------ | Branch (2837:33): [True: 0, False: 73.5k] ------------------ 2838| 73.5k| scratch); 2839| 73.5k| if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) ------------------ | | 96| 73.5k|#define FLAG_NULL 0x00 ------------------ if (rv && avoidflag != FLAG_NULL && TESTAFF(rv->astr, avoidflag, rv->alen)) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ | Branch (2839:15): [True: 0, False: 73.5k] | Branch (2839:21): [True: 0, False: 0] ------------------ 2840| 0| rv = nullptr; 2841| 73.5k| if (rv) { ------------------ | Branch (2841:15): [True: 0, False: 73.5k] ------------------ 2842| 0| sfx = sptr; // BUG: sfx not stateless 2843| 0| sfxflag = sptr->getFlag(); // BUG: sfxflag not stateless 2844| 0| if (!sptr->getCont()) ------------------ | Branch (2844:17): [True: 0, False: 0] ------------------ 2845| 0| sfxappnd = sptr->getKey(); // BUG: sfxappnd not stateless 2846| | // LANG_hu section: spec. Hungarian rule 2847| 0| else if (langnum == LANG_hu && sptr->getKeyLen() && ------------------ | Branch (2847:22): [True: 0, False: 0] | Branch (2847:44): [True: 0, False: 0] ------------------ 2848| 0| sptr->getKey()[0] == 'i' && sptr->getKey()[1] != 'y' && ------------------ | Branch (2848:22): [True: 0, False: 0] | Branch (2848:50): [True: 0, False: 0] ------------------ 2849| 0| sptr->getKey()[1] != 't') { ------------------ | Branch (2849:22): [True: 0, False: 0] ------------------ 2850| 0| sfxextra = 1; 2851| 0| } 2852| | // END of LANG_hu section 2853| 0| return rv; 2854| 0| } 2855| 73.5k| } 2856| 300k| sptr = sptr->getNextEQ(); 2857| 300k| } else { 2858| 56.7k| sptr = sptr->getNextNE(); 2859| 56.7k| } 2860| 357k| } 2861| | 2862| 512M| return nullptr; 2863| 512M|} _ZN8AffixMgr19suffix_check_twosfxERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratcht: 2872| 15.7M| const FLAG needflag) { 2873| 15.7M| struct hentry* rv = nullptr; 2874| | 2875| | // first handle the special case of 0 length suffixes 2876| 15.7M| SfxEntry* se = sStart[0]; 2877| 15.7M| while (se) { ------------------ | Branch (2877:10): [True: 0, False: 15.7M] ------------------ 2878| 0| if (contclasses[se->getFlag()]) { ------------------ | Branch (2878:9): [True: 0, False: 0] ------------------ 2879| 0| rv = se->check_twosfx(word, start, len, sfxopts, ppfx, needflag, scratch); 2880| 0| if (rv) ------------------ | Branch (2880:11): [True: 0, False: 0] ------------------ 2881| 0| return rv; 2882| 0| } 2883| 0| se = se->getNext(); 2884| 0| } 2885| | 2886| | // now handle the general case 2887| 15.7M| if (len == 0) ------------------ | Branch (2887:7): [True: 12.7k, False: 15.7M] ------------------ 2888| 12.7k| return nullptr; // FULLSTRIP 2889| 15.7M| unsigned char sp = word[start + len - 1]; 2890| 15.7M| SfxEntry* sptr = sStart[sp]; 2891| | 2892| 15.8M| while (sptr) { ------------------ | Branch (2892:10): [True: 115k, False: 15.7M] ------------------ 2893| 115k| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (2893:9): [True: 65.4k, False: 50.5k] ------------------ 2894| 65.4k| if (contclasses[sptr->getFlag()]) { ------------------ | Branch (2894:11): [True: 36.4k, False: 28.9k] ------------------ 2895| 36.4k| rv = sptr->check_twosfx(word, start, len, sfxopts, ppfx, needflag, scratch); 2896| 36.4k| if (rv) { ------------------ | Branch (2896:13): [True: 0, False: 36.4k] ------------------ 2897| 0| sfxflag = sptr->getFlag(); // BUG: sfxflag not stateless 2898| 0| if (!sptr->getCont()) ------------------ | Branch (2898:15): [True: 0, False: 0] ------------------ 2899| 0| sfxappnd = sptr->getKey(); // BUG: sfxappnd not stateless 2900| 0| return rv; 2901| 0| } 2902| 36.4k| } 2903| 65.4k| sptr = sptr->getNextEQ(); 2904| 65.4k| } else { 2905| 50.5k| sptr = sptr->getNextNE(); 2906| 50.5k| } 2907| 115k| } 2908| | 2909| 15.7M| return nullptr; 2910| 15.7M|} _ZN8AffixMgr25suffix_check_twosfx_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratcht: 2919| 3.36k| const FLAG needflag) { 2920| 3.36k| std::string result; 2921| 3.36k| std::string result2; 2922| 3.36k| std::string result3; 2923| | 2924| | // first handle the special case of 0 length suffixes 2925| 3.36k| SfxEntry* se = sStart[0]; 2926| 3.36k| while (se) { ------------------ | Branch (2926:10): [True: 0, False: 3.36k] ------------------ 2927| 0| if (contclasses[se->getFlag()]) { ------------------ | Branch (2927:9): [True: 0, False: 0] ------------------ 2928| 0| std::string st = se->check_twosfx_morph(word, start, len, sfxopts, ppfx, needflag, scratch); 2929| 0| if (!st.empty()) { ------------------ | Branch (2929:11): [True: 0, False: 0] ------------------ 2930| 0| if (ppfx) { ------------------ | Branch (2930:13): [True: 0, False: 0] ------------------ 2931| 0| if (ppfx->getMorph()) { ------------------ | Branch (2931:15): [True: 0, False: 0] ------------------ 2932| 0| result.append(ppfx->getMorph()); 2933| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2934| 0| } else 2935| 0| debugflag(result, ppfx->getFlag()); 2936| 0| } 2937| 0| result.append(st); 2938| 0| if (se->getMorph()) { ------------------ | Branch (2938:13): [True: 0, False: 0] ------------------ 2939| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2940| 0| result.append(se->getMorph()); 2941| 0| } else 2942| 0| debugflag(result, se->getFlag()); 2943| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2944| 0| } 2945| 0| } 2946| 0| se = se->getNext(); 2947| 0| } 2948| | 2949| | // now handle the general case 2950| 3.36k| if (len == 0) ------------------ | Branch (2950:7): [True: 0, False: 3.36k] ------------------ 2951| 0| return { }; // FULLSTRIP 2952| 3.36k| unsigned char sp = word[start + len - 1]; 2953| 3.36k| SfxEntry* sptr = sStart[sp]; 2954| | 2955| 3.37k| while (sptr) { ------------------ | Branch (2955:10): [True: 5, False: 3.36k] ------------------ 2956| 5| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (2956:9): [True: 1, False: 4] ------------------ 2957| 1| if (contclasses[sptr->getFlag()]) { ------------------ | Branch (2957:11): [True: 0, False: 1] ------------------ 2958| 0| std::string st = sptr->check_twosfx_morph(word, start, len, sfxopts, ppfx, needflag, scratch); 2959| 0| if (!st.empty()) { ------------------ | Branch (2959:13): [True: 0, False: 0] ------------------ 2960| 0| sfxflag = sptr->getFlag(); // BUG: sfxflag not stateless 2961| 0| if (!sptr->getCont()) ------------------ | Branch (2961:15): [True: 0, False: 0] ------------------ 2962| 0| sfxappnd = sptr->getKey(); // BUG: sfxappnd not stateless 2963| 0| result2.assign(st); 2964| | 2965| 0| result3.clear(); 2966| | 2967| 0| if (sptr->getMorph()) { ------------------ | Branch (2967:15): [True: 0, False: 0] ------------------ 2968| 0| result3.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 2969| 0| result3.append(sptr->getMorph()); 2970| 0| } else 2971| 0| debugflag(result3, sptr->getFlag()); 2972| 0| strlinecat(result2, result3); 2973| 0| result2.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2974| 0| result.append(result2); 2975| 0| } 2976| 0| } 2977| 1| sptr = sptr->getNextEQ(); 2978| 4| } else { 2979| 4| sptr = sptr->getNextNE(); 2980| 4| } 2981| 5| } 2982| | 2983| 3.36k| return result; 2984| 3.36k|} _ZN8AffixMgr18suffix_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiiP8PfxEntryR12AffixScratchttc: 2994| 10.7k| char in_compound) { 2995| 10.7k| std::string result; 2996| | 2997| 10.7k| struct hentry* rv = nullptr; 2998| | 2999| 10.7k| PfxEntry* ep = ppfx; 3000| | 3001| | // first handle the special case of 0 length suffixes 3002| 10.7k| SfxEntry* se = sStart[0]; 3003| 10.7k| while (se) { ------------------ | Branch (3003:10): [True: 0, False: 10.7k] ------------------ 3004| 0| if (!cclass || se->getCont()) { ------------------ | Branch (3004:9): [True: 0, False: 0] | Branch (3004:20): [True: 0, False: 0] ------------------ 3005| | // suffixes are not allowed in beginning of compounds 3006| 0| if (((((in_compound != IN_CPD_BEGIN)) || // && !cclass ------------------ | | 73| 0|#define IN_CPD_BEGIN 1 ------------------ | Branch (3006:13): [True: 0, False: 0] ------------------ 3007| | // except when signed with compoundpermitflag flag 3008| 0| (se->getCont() && compoundpermitflag && ------------------ | Branch (3008:14): [True: 0, False: 0] | Branch (3008:31): [True: 0, False: 0] ------------------ 3009| 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] | | ------------------ ------------------ 3010| 0| (!circumfix || ------------------ | Branch (3010:13): [True: 0, False: 0] ------------------ 3011| | // no circumfix flag in prefix and suffix 3012| 0| ((!ppfx || !(ep->getCont()) || ------------------ | Branch (3012:15): [True: 0, False: 0] | Branch (3012:24): [True: 0, False: 0] ------------------ 3013| 0| !TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3013:15): [True: 0, False: 0] ------------------ 3014| 0| (!se->getCont() || ------------------ | Branch (3014:15): [True: 0, False: 0] ------------------ 3015| 0| !(TESTAFF(se->getCont(), circumfix, se->getContLen())))) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3015:15): [True: 0, False: 0] ------------------ 3016| | // circumfix flag in prefix AND suffix 3017| 0| ((ppfx && (ep->getCont()) && ------------------ | Branch (3017:15): [True: 0, False: 0] | Branch (3017:23): [True: 0, False: 0] ------------------ 3018| 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] | | ------------------ ------------------ 3019| 0| (se->getCont() && ------------------ | Branch (3019:15): [True: 0, False: 0] ------------------ 3020| 0| (TESTAFF(se->getCont(), circumfix, se->getContLen()))))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3020:15): [True: 0, False: 0] ------------------ 3021| | // fogemorpheme 3022| 0| (in_compound || ------------------ | Branch (3022:13): [True: 0, False: 0] ------------------ 3023| 0| !((se->getCont() && ------------------ | Branch (3023:16): [True: 0, False: 0] ------------------ 3024| 0| (TESTAFF(se->getCont(), onlyincompound, se->getContLen()))))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3024:16): [True: 0, False: 0] ------------------ 3025| | // needaffix on prefix or first suffix 3026| 0| (cclass || ------------------ | Branch (3026:13): [True: 0, False: 0] ------------------ 3027| 0| !(se->getCont() && ------------------ | Branch (3027:15): [True: 0, False: 0] ------------------ 3028| 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] | | ------------------ ------------------ 3029| 0| (ppfx && ------------------ | Branch (3029:14): [True: 0, False: 0] ------------------ 3030| 0| !((ep->getCont()) && ------------------ | Branch (3030:16): [True: 0, False: 0] ------------------ 3031| 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] | | ------------------ ------------------ 3032| 0| rv = se->checkword(word, start, len, sfxopts, ppfx, cclass, 3033| 0| needflag, FLAG_NULL, scratch); ------------------ | | 96| 0|#define FLAG_NULL 0x00 ------------------ 3034| 0| while (rv) { ------------------ | Branch (3034:14): [True: 0, False: 0] ------------------ 3035| 0| if (ppfx) { ------------------ | Branch (3035:13): [True: 0, False: 0] ------------------ 3036| 0| if (ppfx->getMorph()) { ------------------ | Branch (3036:15): [True: 0, False: 0] ------------------ 3037| 0| result.append(ppfx->getMorph()); 3038| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3039| 0| } else 3040| 0| debugflag(result, ppfx->getFlag()); 3041| 0| } 3042| 0| if (complexprefixes && HENTRY_DATA(rv)) ------------------ | Branch (3042:13): [True: 0, False: 0] | Branch (3042:32): [True: 0, False: 0] ------------------ 3043| 0| result.append(HENTRY_DATA2(rv)); 3044| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (3044:13): [True: 0, False: 0] ------------------ 3045| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3046| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 3047| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 3048| 0| } 3049| | 3050| 0| if (!complexprefixes && HENTRY_DATA(rv)) { ------------------ | Branch (3050:13): [True: 0, False: 0] | Branch (3050:33): [True: 0, False: 0] ------------------ 3051| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3052| 0| result.append(HENTRY_DATA2(rv)); 3053| 0| } 3054| 0| if (se->getMorph()) { ------------------ | Branch (3054:13): [True: 0, False: 0] ------------------ 3055| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3056| 0| result.append(se->getMorph()); 3057| 0| } else 3058| 0| debugflag(result, se->getFlag()); 3059| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 3060| 0| rv = se->get_next_homonym(rv, sfxopts, ppfx, cclass, needflag); 3061| 0| } 3062| 0| } 3063| 0| se = se->getNext(); 3064| 0| } 3065| | 3066| | // now handle the general case 3067| 10.7k| if (len == 0) ------------------ | Branch (3067:7): [True: 0, False: 10.7k] ------------------ 3068| 0| return { }; // FULLSTRIP 3069| 10.7k| unsigned char sp = word[start + len - 1]; 3070| 10.7k| SfxEntry* sptr = sStart[sp]; 3071| | 3072| 10.7k| while (sptr) { ------------------ | Branch (3072:10): [True: 6, False: 10.7k] ------------------ 3073| 6| if (isRevSubset(sptr->getKey(), word.c_str() + start + len - 1, len)) { ------------------ | Branch (3073:9): [True: 2, False: 4] ------------------ 3074| | // suffixes are not allowed in beginning of compounds 3075| 2| if (((((in_compound != IN_CPD_BEGIN)) || // && !cclass ------------------ | | 73| 2|#define IN_CPD_BEGIN 1 ------------------ | Branch (3075:13): [True: 2, False: 0] ------------------ 3076| | // except when signed with compoundpermitflag flag 3077| 0| (sptr->getCont() && compoundpermitflag && ------------------ | Branch (3077:14): [True: 0, False: 0] | Branch (3077:33): [True: 0, False: 0] ------------------ 3078| 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] | | ------------------ ------------------ 3079| 0| sptr->getContLen()))) && 3080| 2| (!circumfix || ------------------ | Branch (3080:13): [True: 2, False: 0] ------------------ 3081| | // no circumfix flag in prefix and suffix 3082| 0| ((!ppfx || !(ep->getCont()) || ------------------ | Branch (3082:15): [True: 0, False: 0] | Branch (3082:24): [True: 0, False: 0] ------------------ 3083| 0| !TESTAFF(ep->getCont(), circumfix, ep->getContLen())) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3083:15): [True: 0, False: 0] ------------------ 3084| 0| (!sptr->getCont() || ------------------ | Branch (3084:15): [True: 0, False: 0] ------------------ 3085| 0| !(TESTAFF(sptr->getCont(), circumfix, sptr->getContLen())))) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3085:15): [True: 0, False: 0] ------------------ 3086| | // circumfix flag in prefix AND suffix 3087| 0| ((ppfx && (ep->getCont()) && ------------------ | Branch (3087:15): [True: 0, False: 0] | Branch (3087:23): [True: 0, False: 0] ------------------ 3088| 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] | | ------------------ ------------------ 3089| 0| (sptr->getCont() && ------------------ | Branch (3089:15): [True: 0, False: 0] ------------------ 3090| 0| (TESTAFF(sptr->getCont(), circumfix, sptr->getContLen()))))) && ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3090:15): [True: 0, False: 0] ------------------ 3091| | // fogemorpheme 3092| 2| (in_compound || ------------------ | Branch (3092:13): [True: 0, False: 2] ------------------ 3093| 2| !((sptr->getCont() && (TESTAFF(sptr->getCont(), onlyincompound, ------------------ | | 99| 1|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) ------------------ | Branch (3093:16): [True: 1, False: 1] | Branch (3093:35): [True: 0, False: 1] ------------------ 3094| 1| sptr->getContLen()))))) && 3095| | // needaffix on first suffix 3096| 2| (cclass || ------------------ | Branch (3096:13): [True: 0, False: 2] ------------------ 3097| 2| !(sptr->getCont() && ------------------ | Branch (3097:15): [True: 1, False: 1] ------------------ 3098| 1| TESTAFF(sptr->getCont(), needaffix, sptr->getContLen()))))) ------------------ | | 99| 1|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 1] | | ------------------ ------------------ 3099| 2| rv = sptr->checkword(word, start, len, sfxopts, ppfx, cclass, 3100| 2| needflag, FLAG_NULL, scratch); ------------------ | | 96| 2|#define FLAG_NULL 0x00 ------------------ 3101| 2| while (rv) { ------------------ | Branch (3101:14): [True: 0, False: 2] ------------------ 3102| 0| if (ppfx) { ------------------ | Branch (3102:13): [True: 0, False: 0] ------------------ 3103| 0| if (ppfx->getMorph()) { ------------------ | Branch (3103:15): [True: 0, False: 0] ------------------ 3104| 0| result.append(ppfx->getMorph()); 3105| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3106| 0| } else 3107| 0| debugflag(result, ppfx->getFlag()); 3108| 0| } 3109| 0| if (complexprefixes && HENTRY_DATA(rv)) ------------------ | Branch (3109:13): [True: 0, False: 0] | Branch (3109:32): [True: 0, False: 0] ------------------ 3110| 0| result.append(HENTRY_DATA2(rv)); 3111| 0| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ | Branch (3111:13): [True: 0, False: 0] ------------------ 3112| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3113| 0| result.append(MORPH_STEM); ------------------ | | 103| 0|#define MORPH_STEM "st:" ------------------ 3114| 0| result.append(HENTRY_WORD(rv)); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 3115| 0| } 3116| | 3117| 0| if (!complexprefixes && HENTRY_DATA(rv)) { ------------------ | Branch (3117:13): [True: 0, False: 0] | Branch (3117:33): [True: 0, False: 0] ------------------ 3118| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3119| 0| result.append(HENTRY_DATA2(rv)); 3120| 0| } 3121| | 3122| 0| if (sptr->getMorph()) { ------------------ | Branch (3122:13): [True: 0, False: 0] ------------------ 3123| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 3124| 0| result.append(sptr->getMorph()); 3125| 0| } else 3126| 0| debugflag(result, sptr->getFlag()); 3127| 0| result.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 3128| 0| rv = sptr->get_next_homonym(rv, sfxopts, ppfx, cclass, needflag); 3129| 0| } 3130| 2| sptr = sptr->getNextEQ(); 3131| 4| } else { 3132| 4| sptr = sptr->getNextNE(); 3133| 4| } 3134| 6| } 3135| | 3136| 10.7k| return result; 3137| 10.7k|} _ZN8AffixMgr11affix_checkERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiR12AffixScratchtct: 3146| 15.8M| const FLAG avoidflag) { 3147| | 3148| | // check all prefixes (also crossed with suffixes if allowed) 3149| 15.8M| struct hentry* rv = prefix_check(word, start, len, in_compound, scratch, needflag, avoidflag); 3150| 15.8M| if (rv) ------------------ | Branch (3150:7): [True: 0, False: 15.8M] ------------------ 3151| 0| return rv; 3152| | 3153| | // if still not found check all suffixes 3154| 15.8M| rv = suffix_check(word, start, len, 0, nullptr, scratch, FLAG_NULL, needflag, in_compound, avoidflag); ------------------ | | 96| 15.8M|#define FLAG_NULL 0x00 ------------------ 3155| | 3156| 15.8M| if (havecontclass) { ------------------ | Branch (3156:7): [True: 5.32M, False: 10.5M] ------------------ 3157| 5.32M| sfx = nullptr; 3158| 5.32M| pfx = nullptr; 3159| | 3160| 5.32M| if (rv) ------------------ | Branch (3160:9): [True: 0, False: 5.32M] ------------------ 3161| 0| return rv; 3162| | // if still not found check all two-level suffixes 3163| 5.32M| rv = suffix_check_twosfx(word, start, len, 0, nullptr, scratch, needflag); 3164| | 3165| 5.32M| if (rv) ------------------ | Branch (3165:9): [True: 0, False: 5.32M] ------------------ 3166| 0| return rv; 3167| | // if still not found check all two-level suffixes 3168| 5.32M| rv = prefix_check_twosfx(word, start, len, IN_CPD_NOT, scratch, needflag); ------------------ | | 72| 5.32M|#define IN_CPD_NOT 0 ------------------ 3169| 5.32M| } 3170| | 3171| 15.8M| return rv; 3172| 15.8M|} _ZN8AffixMgr17affix_check_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiiR12AffixScratchtc: 3180| 10.7k| char in_compound) { 3181| 10.7k| std::string result; 3182| | 3183| | // check all prefixes (also crossed with suffixes if allowed) 3184| 10.7k| std::string st = prefix_check_morph(word, start, len, in_compound, scratch); 3185| 10.7k| if (!st.empty()) { ------------------ | Branch (3185:7): [True: 0, False: 10.7k] ------------------ 3186| 0| result.append(st); 3187| 0| } 3188| | 3189| | // if still not found check all suffixes 3190| 10.7k| st = suffix_check_morph(word, start, len, 0, nullptr, scratch, '\0', needflag, in_compound); 3191| 10.7k| if (!st.empty()) { ------------------ | Branch (3191:7): [True: 0, False: 10.7k] ------------------ 3192| 0| result.append(st); 3193| 0| } 3194| | 3195| 10.7k| if (havecontclass) { ------------------ | Branch (3195:7): [True: 3.36k, False: 7.42k] ------------------ 3196| 3.36k| sfx = nullptr; 3197| 3.36k| pfx = nullptr; 3198| | // if still not found check all two-level suffixes 3199| 3.36k| st = suffix_check_twosfx_morph(word, start, len, 0, nullptr, scratch, needflag); 3200| 3.36k| if (!st.empty()) { ------------------ | Branch (3200:9): [True: 0, False: 3.36k] ------------------ 3201| 0| result.append(st); 3202| 0| } 3203| | 3204| | // if still not found check all two-level suffixes 3205| 3.36k| st = prefix_check_twosfx_morph(word, start, len, IN_CPD_NOT, scratch, needflag); ------------------ | | 72| 3.36k|#define IN_CPD_NOT 0 ------------------ 3206| 3.36k| if (!st.empty()) { ------------------ | Branch (3206:9): [True: 0, False: 3.36k] ------------------ 3207| 0| result.append(st); 3208| 0| } 3209| 3.36k| } 3210| | 3211| 10.7k| return result; 3212| 10.7k|} _ZN8AffixMgr15expand_rootwordEP9guesswordiPKciPKttS3_iS3_: 3408| 529k| const char* phon) { 3409| 529k| int nh = 0; 3410| | // first add root word to list 3411| 529k| if ((nh < maxn) && ------------------ | Branch (3411:7): [True: 529k, False: 0] ------------------ 3412| 529k| !(al && ((needaffix && TESTAFF(ap, needaffix, al)) || ------------------ | | 99| 4.29k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 2.14k, False: 2.14k] | | ------------------ ------------------ | Branch (3412:9): [True: 93.2k, False: 436k] | Branch (3412:17): [True: 4.29k, False: 88.9k] ------------------ 3413| 527k| (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 (3413:17): [True: 0, False: 91.1k] ------------------ 3414| 527k| wlst[nh].word = mystrdup(ts); 3415| 527k| wlst[nh].allow = false; 3416| 527k| wlst[nh].orig = nullptr; 3417| 527k| nh++; 3418| | // add special phonetic version 3419| 527k| if (phon && (nh < maxn)) { ------------------ | Branch (3419:9): [True: 817, False: 526k] | Branch (3419:17): [True: 817, False: 0] ------------------ 3420| 817| wlst[nh].word = mystrdup(phon); 3421| 817| wlst[nh].allow = false; 3422| 817| wlst[nh].orig = mystrdup(ts); 3423| 817| nh++; 3424| 817| } 3425| 527k| } 3426| | 3427| | // handle suffixes 3428| 634k| for (int i = 0; i < al; i++) { ------------------ | Branch (3428:19): [True: 104k, False: 529k] ------------------ 3429| 104k| const auto c = (unsigned char)(ap[i] & 0x00FF); 3430| 104k| SfxEntry* sptr = sFlag[c]; 3431| 166k| while (sptr) { ------------------ | Branch (3431:12): [True: 62.1k, False: 104k] ------------------ 3432| 62.1k| if ((sptr->getFlag() == ap[i]) && ------------------ | Branch (3432:11): [True: 62.1k, False: 0] ------------------ 3433| 62.1k| (!sptr->getKeyLen() || ------------------ | Branch (3433:12): [True: 0, False: 62.1k] ------------------ 3434| 62.1k| ((badl > sptr->getKeyLen()) && ------------------ | Branch (3434:13): [True: 34.6k, False: 27.4k] ------------------ 3435| 34.6k| (strcmp(sptr->getAffix(), bad + badl - sptr->getKeyLen()) == 0))) && ------------------ | Branch (3435:13): [True: 28, False: 34.6k] ------------------ 3436| | // check needaffix flag 3437| 28| !(sptr->getCont() && ------------------ | Branch (3437:13): [True: 15, False: 13] ------------------ 3438| 15| ((needaffix && ------------------ | Branch (3438:15): [True: 10, False: 5] ------------------ 3439| 10| TESTAFF(sptr->getCont(), needaffix, sptr->getContLen())) || ------------------ | | 99| 10|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 10] | | ------------------ ------------------ 3440| 15| (circumfix && ------------------ | Branch (3440:15): [True: 0, False: 15] ------------------ 3441| 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] | | ------------------ ------------------ 3442| 15| (onlyincompound && ------------------ | Branch (3442:15): [True: 0, False: 15] ------------------ 3443| 28| 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] | | ------------------ ------------------ 3444| 28| std::string newword = sptr->add(ts, wl); 3445| 28| if (!newword.empty()) { ------------------ | Branch (3445:13): [True: 28, False: 0] ------------------ 3446| 28| if (nh < maxn) { ------------------ | Branch (3446:15): [True: 28, False: 0] ------------------ 3447| 28| wlst[nh].word = mystrdup(newword.c_str()); 3448| 28| wlst[nh].allow = sptr->allowCross(); 3449| 28| wlst[nh].orig = nullptr; 3450| 28| nh++; 3451| | // add special phonetic version 3452| 28| if (phon && (nh < maxn)) { ------------------ | Branch (3452:17): [True: 0, False: 28] | Branch (3452:25): [True: 0, False: 0] ------------------ 3453| 0| std::string prefix(phon); 3454| 0| std::string key(sptr->getKey()); 3455| 0| reverseword(key); 3456| 0| prefix.append(key); 3457| 0| wlst[nh].word = mystrdup(prefix.c_str()); 3458| 0| wlst[nh].allow = false; 3459| 0| wlst[nh].orig = mystrdup(newword.c_str()); 3460| 0| nh++; 3461| 0| } 3462| 28| } 3463| 28| } 3464| 28| } 3465| 62.1k| sptr = sptr->getFlgNxt(); 3466| 62.1k| } 3467| 104k| } 3468| | 3469| 529k| int n = nh; 3470| | 3471| | // handle cross products of prefixes and suffixes 3472| 530k| for (int j = 1; j < n; j++) ------------------ | Branch (3472:19): [True: 835, False: 529k] ------------------ 3473| 835| if (wlst[j].allow) { ------------------ | Branch (3473:9): [True: 18, False: 817] ------------------ 3474| 54| for (int k = 0; k < al; k++) { ------------------ | Branch (3474:23): [True: 36, False: 18] ------------------ 3475| 36| const auto c = (unsigned char)(ap[k] & 0x00FF); 3476| 36| PfxEntry* cptr = pFlag[c]; 3477| 36| while (cptr) { ------------------ | Branch (3477:16): [True: 0, False: 36] ------------------ 3478| 0| if ((cptr->getFlag() == ap[k]) && cptr->allowCross() && ------------------ | Branch (3478:15): [True: 0, False: 0] | Branch (3478:45): [True: 0, False: 0] ------------------ 3479| 0| (!cptr->getKeyLen() || ------------------ | Branch (3479:16): [True: 0, False: 0] ------------------ 3480| 0| ((badl > cptr->getKeyLen()) && ------------------ | Branch (3480:17): [True: 0, False: 0] ------------------ 3481| 0| (strncmp(cptr->getKey(), bad, cptr->getKeyLen()) == 0)))) { ------------------ | Branch (3481:17): [True: 0, False: 0] ------------------ 3482| 0| int l1 = strlen(wlst[j].word); 3483| 0| std::string newword = cptr->add(wlst[j].word, l1); 3484| 0| if (!newword.empty()) { ------------------ | Branch (3484:17): [True: 0, False: 0] ------------------ 3485| 0| if (nh < maxn) { ------------------ | Branch (3485:19): [True: 0, False: 0] ------------------ 3486| 0| wlst[nh].word = mystrdup(newword.c_str()); 3487| 0| wlst[nh].allow = cptr->allowCross(); 3488| 0| wlst[nh].orig = nullptr; 3489| 0| nh++; 3490| 0| } 3491| 0| } 3492| 0| } 3493| 0| cptr = cptr->getFlgNxt(); 3494| 0| } 3495| 36| } 3496| 18| } 3497| | 3498| | // now handle pure prefixes 3499| 634k| for (int m = 0; m < al; m++) { ------------------ | Branch (3499:19): [True: 104k, False: 529k] ------------------ 3500| 104k| const auto c = (unsigned char)(ap[m] & 0x00FF); 3501| 104k| PfxEntry* ptr = pFlag[c]; 3502| 105k| while (ptr) { ------------------ | Branch (3502:12): [True: 831, False: 104k] ------------------ 3503| 831| if ((ptr->getFlag() == ap[m]) && ------------------ | Branch (3503:11): [True: 831, False: 0] ------------------ 3504| 831| (!ptr->getKeyLen() || ------------------ | Branch (3504:12): [True: 0, False: 831] ------------------ 3505| 831| ((badl > ptr->getKeyLen()) && ------------------ | Branch (3505:13): [True: 831, False: 0] ------------------ 3506| 831| (strncmp(ptr->getKey(), bad, ptr->getKeyLen()) == 0))) && ------------------ | Branch (3506:13): [True: 11, False: 820] ------------------ 3507| | // check needaffix flag 3508| 11| !(ptr->getCont() && ------------------ | Branch (3508:13): [True: 0, False: 11] ------------------ 3509| 0| ((needaffix && ------------------ | Branch (3509:15): [True: 0, False: 0] ------------------ 3510| 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] | | ------------------ ------------------ 3511| 0| (circumfix && ------------------ | Branch (3511:15): [True: 0, False: 0] ------------------ 3512| 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] | | ------------------ ------------------ 3513| 0| (onlyincompound && ------------------ | Branch (3513:15): [True: 0, False: 0] ------------------ 3514| 11| 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] | | ------------------ ------------------ 3515| 11| std::string newword = ptr->add(ts, wl); 3516| 11| if (!newword.empty()) { ------------------ | Branch (3516:13): [True: 11, False: 0] ------------------ 3517| 11| if (nh < maxn) { ------------------ | Branch (3517:15): [True: 11, False: 0] ------------------ 3518| 11| wlst[nh].word = mystrdup(newword.c_str()); 3519| 11| wlst[nh].allow = ptr->allowCross(); 3520| 11| wlst[nh].orig = nullptr; 3521| 11| nh++; 3522| 11| } 3523| 11| } 3524| 11| } 3525| 831| ptr = ptr->getFlgNxt(); 3526| 831| } 3527| 104k| } 3528| | 3529| 529k| return nh; 3530| 529k|} _ZNK8AffixMgr12get_reptableEv: 3533| 362k|const std::vector& AffixMgr::get_reptable() const { 3534| 362k| return pHMgr->get_reptable(); 3535| 362k|} _ZNK8AffixMgr14get_iconvtableEv: 3538| 13.3M|RepList* AffixMgr::get_iconvtable() const { 3539| 13.3M| if (!iconvtable) ------------------ | Branch (3539:7): [True: 12.9M, False: 418k] ------------------ 3540| 12.9M| return nullptr; 3541| 418k| return iconvtable; 3542| 13.3M|} _ZNK8AffixMgr14get_oconvtableEv: 3545| 96.1k|RepList* AffixMgr::get_oconvtable() const { 3546| 96.1k| if (!oconvtable) ------------------ | Branch (3546:7): [True: 90.9k, False: 5.15k] ------------------ 3547| 90.9k| return nullptr; 3548| 5.15k| return oconvtable; 3549| 96.1k|} _ZNK8AffixMgr14get_phonetableEv: 3552| 59.9k|struct phonetable* AffixMgr::get_phonetable() const { 3553| 59.9k| if (!phone) ------------------ | Branch (3553:7): [True: 56.4k, False: 3.42k] ------------------ 3554| 56.4k| return nullptr; 3555| 3.42k| return phone; 3556| 59.9k|} _ZNK8AffixMgr12get_maptableEv: 3559| 362k|const std::vector& AffixMgr::get_maptable() const { 3560| 362k| return maptable; 3561| 362k|} _ZNK8AffixMgr14get_breaktableEv: 3564| 38|const std::vector& AffixMgr::get_breaktable() const { 3565| 38| return breaktable; 3566| 38|} _ZN8AffixMgr12get_encodingEv: 3569| 78|const std::string& AffixMgr::get_encoding() { 3570| 78| if (encoding.empty()) ------------------ | Branch (3570:7): [True: 20, False: 58] ------------------ 3571| 20| encoding = SPELL_ENCODING; ------------------ | | 99| 20|#define SPELL_ENCODING "ISO8859-1" ------------------ 3572| 78| return encoding; 3573| 78|} _ZNK8AffixMgr11get_langnumEv: 3576| 76|int AffixMgr::get_langnum() const { 3577| 76| return langnum; 3578| 76|} _ZNK8AffixMgr19get_complexprefixesEv: 3581| 76|int AffixMgr::get_complexprefixes() const { 3582| 76| return complexprefixes; 3583| 76|} _ZNK8AffixMgr13get_fullstripEv: 3586| 6.89k|int AffixMgr::get_fullstrip() const { 3587| 6.89k| return fullstrip; 3588| 6.89k|} _ZNK8AffixMgr12get_keepcaseEv: 3590| 98.8k|FLAG AffixMgr::get_keepcase() const { 3591| 98.8k| return keepcase; 3592| 98.8k|} _ZNK8AffixMgr14get_forceucaseEv: 3594| 20.5k|FLAG AffixMgr::get_forceucase() const { 3595| 20.5k| return forceucase; 3596| 20.5k|} _ZNK8AffixMgr8get_warnEv: 3598| 119k|FLAG AffixMgr::get_warn() const { 3599| 119k| return warn; 3600| 119k|} _ZNK8AffixMgr14get_forbidwarnEv: 3602| 6|int AffixMgr::get_forbidwarn() const { 3603| 6| return forbidwarn; 3604| 6|} _ZNK8AffixMgr15get_checksharpsEv: 3606| 323k|int AffixMgr::get_checksharps() const { 3607| 323k| return checksharps; 3608| 323k|} _ZNK8AffixMgr10get_ignoreEv: 3615| 29.2M|const char* AffixMgr::get_ignore() const { 3616| 29.2M| if (ignorechars.empty()) ------------------ | Branch (3616:7): [True: 26.4M, False: 2.84M] ------------------ 3617| 26.4M| return nullptr; 3618| 2.84M| return ignorechars.c_str(); 3619| 29.2M|} _ZNK8AffixMgr16get_ignore_utf16Ev: 3622| 684k|const std::vector& AffixMgr::get_ignore_utf16() const { 3623| 684k| return ignorechars_utf16; 3624| 684k|} _ZN8AffixMgr14get_key_stringEv: 3627| 38|const std::string& AffixMgr::get_key_string() { 3628| 38| if (keystring.empty()) ------------------ | Branch (3628:7): [True: 38, False: 0] ------------------ 3629| 38| keystring = SPELL_KEYSTRING; ------------------ | | 100| 38|#define SPELL_KEYSTRING "qwertyuiop|asdfghjkl|zxcvbnm" ------------------ 3630| 38| return keystring; 3631| 38|} _ZNK8AffixMgr14get_try_stringEv: 3634| 38|const std::string& AffixMgr::get_try_string() const { 3635| 38| return trystring; 3636| 38|} _ZNK8AffixMgr12get_compoundEv: 3648| 71.6M|int AffixMgr::get_compound() const { 3649| 71.6M| return compoundflag || compoundbegin || !defcpdtable.empty(); ------------------ | Branch (3649:10): [True: 17.8M, False: 53.8M] | Branch (3649:26): [True: 0, False: 53.8M] | Branch (3649:43): [True: 0, False: 53.8M] ------------------ 3650| 71.6M|} _ZNK8AffixMgr16get_compoundflagEv: 3653| 60.8k|FLAG AffixMgr::get_compoundflag() const { 3654| 60.8k| return compoundflag; 3655| 60.8k|} _ZNK8AffixMgr17get_forbiddenwordEv: 3658| 155k|FLAG AffixMgr::get_forbiddenword() const { 3659| 155k| return forbiddenword; 3660| 155k|} _ZNK8AffixMgr13get_nosuggestEv: 3663| 60.1k|FLAG AffixMgr::get_nosuggest() const { 3664| 60.1k| return nosuggest; 3665| 60.1k|} _ZNK8AffixMgr18get_nongramsuggestEv: 3668| 59.9k|FLAG AffixMgr::get_nongramsuggest() const { 3669| 59.9k| return nongramsuggest; 3670| 59.9k|} _ZNK8AffixMgr15get_substandardEv: 3673| 258|FLAG AffixMgr::get_substandard() const { 3674| 258| return substandard; 3675| 258|} _ZNK8AffixMgr13get_needaffixEv: 3678| 960|FLAG AffixMgr::get_needaffix() const { 3679| 960| return needaffix; 3680| 960|} _ZNK8AffixMgr18get_onlyincompoundEv: 3688| 60.5k|FLAG AffixMgr::get_onlyincompound() const { 3689| 60.5k| return onlyincompound; 3690| 60.5k|} _ZN8AffixMgr6lookupEPKcm: 3698| 496M|struct hentry* AffixMgr::lookup(const char* word, size_t len) { 3699| 496M| struct hentry* he = nullptr; 3700| 993M| for (size_t i = 0; i < alldic.size() && !he; ++i) { ------------------ | Branch (3700:22): [True: 496M, False: 496M] | Branch (3700:43): [True: 496M, False: 0] ------------------ 3701| 496M| he = alldic[i]->lookup(word, len); 3702| 496M| } 3703| 496M| return he; 3704| 496M|} _ZNK8AffixMgr14have_contclassEv: 3707| 29.4M|int AffixMgr::have_contclass() const { 3708| 29.4M| return havecontclass; 3709| 29.4M|} _ZNK8AffixMgr8get_utf8Ev: 3712| 76|int AffixMgr::get_utf8() const { 3713| 76| return utf8; 3714| 76|} _ZNK8AffixMgr16get_maxngramsugsEv: 3716| 67.2k|int AffixMgr::get_maxngramsugs() const { 3717| 67.2k| return maxngramsugs; 3718| 67.2k|} _ZNK8AffixMgr14get_maxcpdsugsEv: 3720| 38|int AffixMgr::get_maxcpdsugs() const { 3721| 38| return maxcpdsugs; 3722| 38|} _ZNK8AffixMgr11get_maxdiffEv: 3724| 45.9k|int AffixMgr::get_maxdiff() const { 3725| 45.9k| return maxdiff; 3726| 45.9k|} _ZNK8AffixMgr15get_onlymaxdiffEv: 3728| 7.67k|int AffixMgr::get_onlymaxdiff() const { 3729| 7.67k| return onlymaxdiff; 3730| 7.67k|} _ZNK8AffixMgr15get_nosplitsugsEv: 3733| 38|int AffixMgr::get_nosplitsugs() const { 3734| 38| return nosplitsugs; 3735| 38|} _ZNK8AffixMgr16get_sugswithdotsEv: 3738| 3.67k|int AffixMgr::get_sugswithdots() const { 3739| 3.67k| return sugswithdots; 3740| 3.67k|} _ZN8AffixMgr10parse_flagERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPtP7FileMgr: 3743| 22|bool AffixMgr::parse_flag(const std::string& line, unsigned short* out, FileMgr* af) { 3744| 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 (3744:7): [True: 2, False: 20] | Branch (3744:28): [True: 0, False: 2] ------------------ 3745| 0| HUNSPELL_WARNING( 3746| 0| stderr, 3747| 0| "error: line %d: multiple definitions of an affix file parameter\n", 3748| 0| af->getlinenum()); 3749| 0| return false; 3750| 0| } 3751| 22| std::string s; 3752| 22| if (!parse_string(line, s, af->getlinenum())) ------------------ | Branch (3752:7): [True: 0, False: 22] ------------------ 3753| 0| return false; 3754| 22| *out = pHMgr->decode_flag(s); 3755| 22| return true; 3756| 22|} _ZN8AffixMgr9parse_numERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiP7FileMgr: 3759| 10|bool AffixMgr::parse_num(const std::string& line, int* out, FileMgr* af) { 3760| 10| if (*out != -1) { ------------------ | Branch (3760:7): [True: 0, False: 10] ------------------ 3761| 0| HUNSPELL_WARNING( 3762| 0| stderr, 3763| 0| "error: line %d: multiple definitions of an affix file parameter\n", 3764| 0| af->getlinenum()); 3765| 0| return false; 3766| 0| } 3767| 10| std::string s; 3768| 10| if (!parse_string(line, s, af->getlinenum())) ------------------ | Branch (3768:7): [True: 0, False: 10] ------------------ 3769| 0| return false; 3770| 10| *out = atoi(s.c_str()); 3771| 10| return true; 3772| 10|} _ZN8AffixMgr17parse_cpdsyllableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 3775| 2|bool AffixMgr::parse_cpdsyllable(const std::string& line, FileMgr* af) { 3776| 2| int i = 0; 3777| 2| int np = 0; 3778| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 3779| 8| while (start_piece != line.end()) { ------------------ | Branch (3779:10): [True: 6, False: 2] ------------------ 3780| 6| switch (i) { 3781| 2| case 0: { ------------------ | Branch (3781:7): [True: 2, False: 4] ------------------ 3782| 2| np++; 3783| 2| break; 3784| 0| } 3785| 2| case 1: { ------------------ | Branch (3785:7): [True: 2, False: 4] ------------------ 3786| 2| cpdmaxsyllable = atoi(std::string(start_piece, iter).c_str()); 3787| 2| np++; 3788| 2| break; 3789| 0| } 3790| 2| case 2: { ------------------ | Branch (3790:7): [True: 2, False: 4] ------------------ 3791| 2| if (!utf8) { ------------------ | Branch (3791:13): [True: 0, False: 2] ------------------ 3792| 0| cpdvowels.assign(start_piece, iter); 3793| 0| std::sort(cpdvowels.begin(), cpdvowels.end()); 3794| 2| } else { 3795| 2| std::string piece(start_piece, iter); 3796| 2| u8_u16(cpdvowels_utf16, piece); 3797| 2| std::sort(cpdvowels_utf16.begin(), cpdvowels_utf16.end()); 3798| 2| } 3799| 2| np++; 3800| 2| break; 3801| 0| } 3802| 0| default: ------------------ | Branch (3802:7): [True: 0, False: 6] ------------------ 3803| 0| break; 3804| 6| } 3805| 6| ++i; 3806| 6| start_piece = mystrsep(line, iter); 3807| 6| } 3808| 2| if (np < 2) { ------------------ | Branch (3808:7): [True: 0, False: 2] ------------------ 3809| 0| HUNSPELL_WARNING(stderr, 3810| 0| "error: line %d: missing compoundsyllable information\n", 3811| 0| af->getlinenum()); 3812| 0| return false; 3813| 0| } 3814| 2| if (np == 2) ------------------ | Branch (3814:7): [True: 0, False: 2] ------------------ 3815| 0| cpdvowels = "AEIOUaeiou"; 3816| 2| return true; 3817| 2|} _ZN8AffixMgr15parse_convtableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgrPP7RepListS8_: 3822| 4| const std::string& keyword) { 3823| 4| if (*rl) { ------------------ | Branch (3823:7): [True: 0, False: 4] ------------------ 3824| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 3825| 0| af->getlinenum()); 3826| 0| return false; 3827| 0| } 3828| 4| int i = 0; 3829| 4| int np = 0; 3830| 4| int numrl = 0; 3831| 4| auto iter = line.begin(), start_piece = mystrsep(line, iter); 3832| 18| while (start_piece != line.end()) { ------------------ | Branch (3832:10): [True: 14, False: 4] ------------------ 3833| 14| switch (i) { 3834| 4| case 0: { ------------------ | Branch (3834:7): [True: 4, False: 10] ------------------ 3835| 4| np++; 3836| 4| break; 3837| 0| } 3838| 4| case 1: { ------------------ | Branch (3838:7): [True: 4, False: 10] ------------------ 3839| 4| numrl = atoi(std::string(start_piece, iter).c_str()); 3840| 4| if (numrl < 1) { ------------------ | Branch (3840:13): [True: 0, False: 4] ------------------ 3841| 0| HUNSPELL_WARNING(stderr, "error: line %d: incorrect entry number\n", 3842| 0| af->getlinenum()); 3843| 0| return false; 3844| 0| } 3845| 4| *rl = new RepList(numrl); 3846| 4| if (!*rl) ------------------ | Branch (3846:13): [True: 0, False: 4] ------------------ 3847| 0| return false; 3848| 4| np++; 3849| 4| break; 3850| 4| } 3851| 6| default: ------------------ | Branch (3851:7): [True: 6, False: 8] ------------------ 3852| 6| break; 3853| 14| } 3854| 14| ++i; 3855| 14| start_piece = mystrsep(line, iter); 3856| 14| } 3857| 4| if (np != 2) { ------------------ | Branch (3857:7): [True: 0, False: 4] ------------------ 3858| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 3859| 0| af->getlinenum()); 3860| 0| return false; 3861| 0| } 3862| | 3863| | /* now parse the num lines to read in the remainder of the table */ 3864| 26| for (int j = 0; j < numrl; j++) { ------------------ | Branch (3864:19): [True: 22, False: 4] ------------------ 3865| 22| std::string nl; 3866| 22| if (!af->getline(nl)) ------------------ | Branch (3866:9): [True: 0, False: 22] ------------------ 3867| 0| return false; 3868| 22| mychomp(nl); 3869| 22| i = 0; 3870| 22| std::string pattern; 3871| 22| std::string pattern2; 3872| 22| iter = nl.begin(); 3873| 22| start_piece = mystrsep(nl, iter); 3874| 130| while (start_piece != nl.end()) { ------------------ | Branch (3874:12): [True: 108, False: 22] ------------------ 3875| 108| { 3876| 108| switch (i) { 3877| 22| case 0: { ------------------ | Branch (3877:11): [True: 22, False: 86] ------------------ 3878| 22| if (nl.compare(start_piece - nl.begin(), keyword.size(), keyword, 0, keyword.size()) != 0) { ------------------ | Branch (3878:17): [True: 0, False: 22] ------------------ 3879| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 3880| 0| af->getlinenum()); 3881| 0| delete *rl; 3882| 0| *rl = nullptr; 3883| 0| return false; 3884| 0| } 3885| 22| break; 3886| 22| } 3887| 22| case 1: { ------------------ | Branch (3887:11): [True: 22, False: 86] ------------------ 3888| 22| pattern.assign(start_piece, iter); 3889| 22| break; 3890| 22| } 3891| 22| case 2: { ------------------ | Branch (3891:11): [True: 22, False: 86] ------------------ 3892| 22| pattern2.assign(start_piece, iter); 3893| 22| break; 3894| 22| } 3895| 42| default: ------------------ | Branch (3895:11): [True: 42, False: 66] ------------------ 3896| 42| break; 3897| 108| } 3898| 108| ++i; 3899| 108| } 3900| 0| start_piece = mystrsep(nl, iter); 3901| 108| } 3902| 22| if (pattern.empty() || pattern2.empty()) { ------------------ | Branch (3902:9): [True: 0, False: 22] | Branch (3902:28): [True: 0, False: 22] ------------------ 3903| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 3904| 0| af->getlinenum()); 3905| 0| return false; 3906| 0| } 3907| | 3908| 22| (*rl)->add(pattern, pattern2); 3909| 22| } 3910| 4| return true; 3911| 4|} _ZN8AffixMgr16parse_phonetableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 3914| 2|bool AffixMgr::parse_phonetable(const std::string& line, FileMgr* af) { 3915| 2| if (phone) { ------------------ | Branch (3915:7): [True: 0, False: 2] ------------------ 3916| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 3917| 0| af->getlinenum()); 3918| 0| return false; 3919| 0| } 3920| 2| std::unique_ptr new_phone; 3921| 2| int num = -1; 3922| 2| int i = 0; 3923| 2| int np = 0; 3924| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 3925| 6| while (start_piece != line.end()) { ------------------ | Branch (3925:10): [True: 4, False: 2] ------------------ 3926| 4| switch (i) { 3927| 2| case 0: { ------------------ | Branch (3927:7): [True: 2, False: 2] ------------------ 3928| 2| np++; 3929| 2| break; 3930| 0| } 3931| 2| case 1: { ------------------ | Branch (3931:7): [True: 2, False: 2] ------------------ 3932| 2| num = atoi(std::string(start_piece, iter).c_str()); 3933| 2| if (num < 1) { ------------------ | Branch (3933:13): [True: 0, False: 2] ------------------ 3934| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 3935| 0| af->getlinenum()); 3936| 0| return false; 3937| 0| } 3938| 2| new_phone = std::make_unique(); 3939| 2| new_phone->utf8 = (char)utf8; 3940| 2| np++; 3941| 2| break; 3942| 2| } 3943| 0| default: ------------------ | Branch (3943:7): [True: 0, False: 4] ------------------ 3944| 0| break; 3945| 4| } 3946| 4| ++i; 3947| 4| start_piece = mystrsep(line, iter); 3948| 4| } 3949| 2| if (np != 2) { ------------------ | Branch (3949:7): [True: 0, False: 2] ------------------ 3950| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 3951| 0| af->getlinenum()); 3952| 0| return false; 3953| 0| } 3954| | 3955| | /* now parse the phone->num lines to read in the remainder of the table */ 3956| 212| for (int j = 0; j < num; ++j) { ------------------ | Branch (3956:19): [True: 210, False: 2] ------------------ 3957| 210| std::string nl; 3958| 210| if (!af->getline(nl)) ------------------ | Branch (3958:9): [True: 0, False: 210] ------------------ 3959| 0| return false; 3960| 210| mychomp(nl); 3961| 210| i = 0; 3962| 210| const size_t old_size = new_phone->rules.size(); 3963| 210| iter = nl.begin(); 3964| 210| start_piece = mystrsep(nl, iter); 3965| 840| while (start_piece != nl.end()) { ------------------ | Branch (3965:12): [True: 630, False: 210] ------------------ 3966| 630| { 3967| 630| switch (i) { 3968| 210| case 0: { ------------------ | Branch (3968:11): [True: 210, False: 420] ------------------ 3969| 210| if (nl.compare(start_piece - nl.begin(), 5, "PHONE", 5) != 0) { ------------------ | Branch (3969:17): [True: 0, False: 210] ------------------ 3970| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 3971| 0| af->getlinenum()); 3972| 0| return false; 3973| 0| } 3974| 210| break; 3975| 210| } 3976| 210| case 1: { ------------------ | Branch (3976:11): [True: 210, False: 420] ------------------ 3977| 210| new_phone->rules.emplace_back(start_piece, iter); 3978| 210| break; 3979| 210| } 3980| 210| case 2: { ------------------ | Branch (3980:11): [True: 210, False: 420] ------------------ 3981| 210| new_phone->rules.emplace_back(start_piece, iter); 3982| 210| mystrrep(new_phone->rules.back(), "_", ""); 3983| 210| break; 3984| 210| } 3985| 0| default: ------------------ | Branch (3985:11): [True: 0, False: 630] ------------------ 3986| 0| break; 3987| 630| } 3988| 630| ++i; 3989| 630| } 3990| 0| start_piece = mystrsep(nl, iter); 3991| 630| } 3992| 210| if (new_phone->rules.size() != old_size + 2) { ------------------ | Branch (3992:9): [True: 0, False: 210] ------------------ 3993| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 3994| 0| af->getlinenum()); 3995| 0| return false; 3996| 0| } 3997| 210| } 3998| 2| new_phone->rules.emplace_back(""); 3999| 2| new_phone->rules.emplace_back(""); 4000| 2| init_phonet_hash(*new_phone); 4001| 2| phone = new_phone.release(); 4002| 2| return true; 4003| 2|} _ZN8AffixMgr19parse_checkcpdtableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 4006| 2|bool AffixMgr::parse_checkcpdtable(const std::string& line, FileMgr* af) { 4007| 2| if (parsedcheckcpd) { ------------------ | Branch (4007:7): [True: 0, False: 2] ------------------ 4008| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 4009| 0| af->getlinenum()); 4010| 0| return false; 4011| 0| } 4012| 2| parsedcheckcpd = true; 4013| 2| int numcheckcpd = -1; 4014| 2| int i = 0; 4015| 2| int np = 0; 4016| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4017| 6| while (start_piece != line.end()) { ------------------ | Branch (4017:10): [True: 4, False: 2] ------------------ 4018| 4| switch (i) { 4019| 2| case 0: { ------------------ | Branch (4019:7): [True: 2, False: 2] ------------------ 4020| 2| np++; 4021| 2| break; 4022| 0| } 4023| 2| case 1: { ------------------ | Branch (4023:7): [True: 2, False: 2] ------------------ 4024| 2| numcheckcpd = atoi(std::string(start_piece, iter).c_str()); 4025| 2| if (numcheckcpd < 1) { ------------------ | Branch (4025:13): [True: 0, False: 2] ------------------ 4026| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 4027| 0| af->getlinenum()); 4028| 0| return false; 4029| 0| } 4030| 2| checkcpdtable.reserve(std::min(numcheckcpd, 16384)); 4031| 2| np++; 4032| 2| break; 4033| 2| } 4034| 0| default: ------------------ | Branch (4034:7): [True: 0, False: 4] ------------------ 4035| 0| break; 4036| 4| } 4037| 4| ++i; 4038| 4| start_piece = mystrsep(line, iter); 4039| 4| } 4040| 2| if (np != 2) { ------------------ | Branch (4040:7): [True: 0, False: 2] ------------------ 4041| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4042| 0| af->getlinenum()); 4043| 0| return false; 4044| 0| } 4045| | 4046| | /* now parse the numcheckcpd lines to read in the remainder of the table */ 4047| 6| for (int j = 0; j < numcheckcpd; ++j) { ------------------ | Branch (4047:19): [True: 4, False: 2] ------------------ 4048| 4| std::string nl; 4049| 4| if (!af->getline(nl)) ------------------ | Branch (4049:9): [True: 0, False: 4] ------------------ 4050| 0| return false; 4051| 4| mychomp(nl); 4052| 4| i = 0; 4053| 4| checkcpdtable.emplace_back(); 4054| 4| iter = nl.begin(); 4055| 4| start_piece = mystrsep(nl, iter); 4056| 16| while (start_piece != nl.end()) { ------------------ | Branch (4056:12): [True: 12, False: 4] ------------------ 4057| 12| switch (i) { 4058| 4| case 0: { ------------------ | Branch (4058:9): [True: 4, False: 8] ------------------ 4059| 4| if (nl.compare(start_piece - nl.begin(), 20, "CHECKCOMPOUNDPATTERN", 20) != 0) { ------------------ | Branch (4059:15): [True: 0, False: 4] ------------------ 4060| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4061| 0| af->getlinenum()); 4062| 0| checkcpdtable.clear(); 4063| 0| return false; 4064| 0| } 4065| 4| break; 4066| 4| } 4067| 4| case 1: { ------------------ | Branch (4067:9): [True: 4, False: 8] ------------------ 4068| 4| checkcpdtable.back().pattern.assign(start_piece, iter); 4069| 4| size_t slash_pos = checkcpdtable.back().pattern.find('/'); 4070| 4| if (slash_pos != std::string::npos) { ------------------ | Branch (4070:15): [True: 0, False: 4] ------------------ 4071| 0| std::string chunk(checkcpdtable.back().pattern, slash_pos + 1); 4072| 0| checkcpdtable.back().pattern.resize(slash_pos); 4073| 0| checkcpdtable.back().cond = pHMgr->decode_flag(chunk); 4074| 0| } 4075| 4| break; 4076| 4| } 4077| 4| case 2: { ------------------ | Branch (4077:9): [True: 4, False: 8] ------------------ 4078| 4| checkcpdtable.back().pattern2.assign(start_piece, iter); 4079| 4| size_t slash_pos = checkcpdtable.back().pattern2.find('/'); 4080| 4| if (slash_pos != std::string::npos) { ------------------ | Branch (4080:15): [True: 0, False: 4] ------------------ 4081| 0| std::string chunk(checkcpdtable.back().pattern2, slash_pos + 1); 4082| 0| checkcpdtable.back().pattern2.resize(slash_pos); 4083| 0| checkcpdtable.back().cond2 = pHMgr->decode_flag(chunk); 4084| 0| } 4085| 4| break; 4086| 4| } 4087| 0| case 3: { ------------------ | Branch (4087:9): [True: 0, False: 12] ------------------ 4088| 0| checkcpdtable.back().pattern3.assign(start_piece, iter); 4089| 0| simplifiedcpd = 1; 4090| 0| break; 4091| 4| } 4092| 0| default: ------------------ | Branch (4092:9): [True: 0, False: 12] ------------------ 4093| 0| break; 4094| 12| } 4095| 12| i++; 4096| 12| start_piece = mystrsep(nl, iter); 4097| 12| } 4098| 4| } 4099| 2| return true; 4100| 2|} _ZN8AffixMgr14parse_maptableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 4204| 2|bool AffixMgr::parse_maptable(const std::string& line, FileMgr* af) { 4205| 2| if (parsedmaptable) { ------------------ | Branch (4205:7): [True: 0, False: 2] ------------------ 4206| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 4207| 0| af->getlinenum()); 4208| 0| return false; 4209| 0| } 4210| 2| parsedmaptable = true; 4211| 2| int nummap = -1; 4212| 2| int i = 0; 4213| 2| int np = 0; 4214| 2| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4215| 6| while (start_piece != line.end()) { ------------------ | Branch (4215:10): [True: 4, False: 2] ------------------ 4216| 4| switch (i) { 4217| 2| case 0: { ------------------ | Branch (4217:7): [True: 2, False: 2] ------------------ 4218| 2| np++; 4219| 2| break; 4220| 0| } 4221| 2| case 1: { ------------------ | Branch (4221:7): [True: 2, False: 2] ------------------ 4222| 2| nummap = atoi(std::string(start_piece, iter).c_str()); 4223| 2| if (nummap < 1) { ------------------ | Branch (4223:13): [True: 0, False: 2] ------------------ 4224| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 4225| 0| af->getlinenum()); 4226| 0| return false; 4227| 0| } 4228| 2| maptable.reserve(std::min(nummap, 16384)); 4229| 2| np++; 4230| 2| break; 4231| 2| } 4232| 0| default: ------------------ | Branch (4232:7): [True: 0, False: 4] ------------------ 4233| 0| break; 4234| 4| } 4235| 4| ++i; 4236| 4| start_piece = mystrsep(line, iter); 4237| 4| } 4238| 2| if (np != 2) { ------------------ | Branch (4238:7): [True: 0, False: 2] ------------------ 4239| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4240| 0| af->getlinenum()); 4241| 0| return false; 4242| 0| } 4243| | 4244| | /* now parse the nummap lines to read in the remainder of the table */ 4245| 8| for (int j = 0; j < nummap; ++j) { ------------------ | Branch (4245:19): [True: 6, False: 2] ------------------ 4246| 6| std::string nl; 4247| 6| if (!af->getline(nl)) ------------------ | Branch (4247:9): [True: 0, False: 6] ------------------ 4248| 0| return false; 4249| 6| mychomp(nl); 4250| 6| i = 0; 4251| 6| maptable.emplace_back(); 4252| 6| iter = nl.begin(); 4253| 6| start_piece = mystrsep(nl, iter); 4254| 18| while (start_piece != nl.end()) { ------------------ | Branch (4254:12): [True: 12, False: 6] ------------------ 4255| 12| switch (i) { 4256| 6| case 0: { ------------------ | Branch (4256:9): [True: 6, False: 6] ------------------ 4257| 6| if (nl.compare(start_piece - nl.begin(), 3, "MAP", 3) != 0) { ------------------ | Branch (4257:15): [True: 0, False: 6] ------------------ 4258| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4259| 0| af->getlinenum()); 4260| 0| nummap = 0; 4261| 0| return false; 4262| 0| } 4263| 6| break; 4264| 6| } 4265| 6| case 1: { ------------------ | Branch (4265:9): [True: 6, False: 6] ------------------ 4266| 22| for (auto k = start_piece; k != iter; ++k) { ------------------ | Branch (4266:38): [True: 16, False: 6] ------------------ 4267| 16| auto chb = k, che = k + 1; 4268| 16| if (*k == '(') { ------------------ | Branch (4268:17): [True: 2, False: 14] ------------------ 4269| 2| auto parpos = std::find(k, iter, ')'); 4270| 2| if (parpos != iter) { ------------------ | Branch (4270:19): [True: 2, False: 0] ------------------ 4271| 2| chb = k + 1; 4272| 2| che = parpos; 4273| 2| k = parpos; 4274| 2| } 4275| 14| } else { 4276| 14| if (utf8 && (*k & 0xc0) == 0xc0) { ------------------ | Branch (4276:19): [True: 14, False: 0] | Branch (4276:27): [True: 10, False: 4] ------------------ 4277| 10| ++k; 4278| 20| while (k != iter && is_utf8_cont(*k)) ------------------ | Branch (4278:24): [True: 18, False: 2] | Branch (4278:37): [True: 10, False: 8] ------------------ 4279| 10| ++k; 4280| 10| che = k; 4281| 10| --k; 4282| 10| } 4283| 14| } 4284| 16| if (chb == che) { ------------------ | Branch (4284:17): [True: 0, False: 16] ------------------ 4285| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4286| 0| af->getlinenum()); 4287| 0| } 4288| | 4289| 16| maptable.back().emplace_back(chb, che); 4290| 16| } 4291| 6| break; 4292| 6| } 4293| 0| default: ------------------ | Branch (4293:9): [True: 0, False: 12] ------------------ 4294| 0| break; 4295| 12| } 4296| 12| ++i; 4297| 12| start_piece = mystrsep(nl, iter); 4298| 12| } 4299| 6| if (maptable.back().empty()) { ------------------ | Branch (4299:9): [True: 0, False: 6] ------------------ 4300| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4301| 0| af->getlinenum()); 4302| 0| return false; 4303| 0| } 4304| 6| } 4305| 2| return true; 4306| 2|} _ZN8AffixMgr16parse_breaktableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEP7FileMgr: 4309| 4|bool AffixMgr::parse_breaktable(const std::string& line, FileMgr* af) { 4310| 4| if (parsedbreaktable) { ------------------ | Branch (4310:7): [True: 0, False: 4] ------------------ 4311| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n", 4312| 0| af->getlinenum()); 4313| 0| return false; 4314| 0| } 4315| 4| parsedbreaktable = true; 4316| 4| int numbreak = -1; 4317| 4| int i = 0; 4318| 4| int np = 0; 4319| 4| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4320| 12| while (start_piece != line.end()) { ------------------ | Branch (4320:10): [True: 8, False: 4] ------------------ 4321| 8| switch (i) { 4322| 4| case 0: { ------------------ | Branch (4322:7): [True: 4, False: 4] ------------------ 4323| 4| np++; 4324| 4| break; 4325| 0| } 4326| 4| case 1: { ------------------ | Branch (4326:7): [True: 4, False: 4] ------------------ 4327| 4| numbreak = atoi(std::string(start_piece, iter).c_str()); 4328| 4| if (numbreak < 0) { ------------------ | Branch (4328:13): [True: 0, False: 4] ------------------ 4329| 0| HUNSPELL_WARNING(stderr, "error: line %d: bad entry number\n", 4330| 0| af->getlinenum()); 4331| 0| return false; 4332| 0| } 4333| 4| if (numbreak == 0) ------------------ | Branch (4333:13): [True: 0, False: 4] ------------------ 4334| 0| return true; 4335| 4| breaktable.reserve(std::min(numbreak, 16384)); 4336| 4| np++; 4337| 4| break; 4338| 4| } 4339| 0| default: ------------------ | Branch (4339:7): [True: 0, False: 8] ------------------ 4340| 0| break; 4341| 8| } 4342| 8| ++i; 4343| 8| start_piece = mystrsep(line, iter); 4344| 8| } 4345| 4| if (np != 2) { ------------------ | Branch (4345:7): [True: 0, False: 4] ------------------ 4346| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", 4347| 0| af->getlinenum()); 4348| 0| return false; 4349| 0| } 4350| | 4351| | /* now parse the numbreak lines to read in the remainder of the table */ 4352| 10| for (int j = 0; j < numbreak; ++j) { ------------------ | Branch (4352:19): [True: 6, False: 4] ------------------ 4353| 6| std::string nl; 4354| 6| if (!af->getline(nl)) ------------------ | Branch (4354:9): [True: 0, False: 6] ------------------ 4355| 0| return false; 4356| 6| mychomp(nl); 4357| 6| i = 0; 4358| 6| iter = nl.begin(); 4359| 6| start_piece = mystrsep(nl, iter); 4360| 18| while (start_piece != nl.end()) { ------------------ | Branch (4360:12): [True: 12, False: 6] ------------------ 4361| 12| switch (i) { 4362| 6| case 0: { ------------------ | Branch (4362:9): [True: 6, False: 6] ------------------ 4363| 6| if (nl.compare(start_piece - nl.begin(), 5, "BREAK", 5) != 0) { ------------------ | Branch (4363:15): [True: 0, False: 6] ------------------ 4364| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4365| 0| af->getlinenum()); 4366| 0| numbreak = 0; 4367| 0| return false; 4368| 0| } 4369| 6| break; 4370| 6| } 4371| 6| case 1: { ------------------ | Branch (4371:9): [True: 6, False: 6] ------------------ 4372| 6| breaktable.emplace_back(start_piece, iter); 4373| 6| break; 4374| 6| } 4375| 0| default: ------------------ | Branch (4375:9): [True: 0, False: 12] ------------------ 4376| 0| break; 4377| 12| } 4378| 12| ++i; 4379| 12| start_piece = mystrsep(nl, iter); 4380| 12| } 4381| 6| } 4382| | 4383| 4| if (breaktable.size() != static_cast(numbreak)) { ------------------ | Branch (4383:7): [True: 0, False: 4] ------------------ 4384| 0| HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n", 4385| 0| af->getlinenum()); 4386| 0| return false; 4387| 0| } 4388| | 4389| 4| return true; 4390| 4|} _ZN8AffixMgr17reverse_conditionERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 4392| 38|void AffixMgr::reverse_condition(std::string& piece) { 4393| 38| if (piece.empty()) ------------------ | Branch (4393:7): [True: 0, False: 38] ------------------ 4394| 0| return; 4395| | 4396| 38| int neg = 0; 4397| | // iterate backwards; k wraps to npos (SIZE_MAX) when decremented past 0 4398| 92| for (size_t k = piece.size() - 1; k != std::string::npos; --k) { ------------------ | Branch (4398:37): [True: 54, False: 38] ------------------ 4399| 54| switch (piece[k]) { 4400| 2| case '[': { ------------------ | Branch (4400:7): [True: 2, False: 52] ------------------ 4401| 2| if (neg) ------------------ | Branch (4401:13): [True: 0, False: 2] ------------------ 4402| 0| piece[k + 1] = '['; 4403| 2| else 4404| 2| piece[k] = ']'; 4405| 2| break; 4406| 0| } 4407| 2| case ']': { ------------------ | Branch (4407:7): [True: 2, False: 52] ------------------ 4408| 2| piece[k] = '['; 4409| 2| if (neg) ------------------ | Branch (4409:13): [True: 0, False: 2] ------------------ 4410| 0| piece[k + 1] = '^'; 4411| 2| neg = 0; 4412| 2| break; 4413| 0| } 4414| 0| case '^': { ------------------ | Branch (4414:7): [True: 0, False: 54] ------------------ 4415| 0| if (piece[k + 1] == ']') ------------------ | Branch (4415:13): [True: 0, False: 0] ------------------ 4416| 0| neg = 1; 4417| 0| else if (neg) ------------------ | Branch (4417:18): [True: 0, False: 0] ------------------ 4418| 0| piece[k + 1] = piece[k]; 4419| 0| break; 4420| 0| } 4421| 50| default: { ------------------ | Branch (4421:7): [True: 50, False: 4] ------------------ 4422| 50| if (neg) ------------------ | Branch (4422:13): [True: 0, False: 50] ------------------ 4423| 0| piece[k + 1] = piece[k]; 4424| 50| } 4425| 54| } 4426| 54| } 4427| 38|} _ZN8AffixMgr11parse_affixERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEcP7FileMgrPc: 4481| 26| char* dupflags) { 4482| 26| int numents = 0; // number of AffEntry structures to parse 4483| | 4484| 26| unsigned short aflag = 0; // affix char identifier 4485| | 4486| 26| char ff = 0; 4487| 26| entries_container affentries(at, this); 4488| | 4489| 26| int i = 0; 4490| | 4491| |// checking lines with bad syntax 4492| |#ifdef DEBUG 4493| | int basefieldnum = 0; 4494| |#endif 4495| | 4496| | // split affix header line into pieces 4497| | 4498| 26| int np = 0; 4499| 26| auto iter = line.begin(), start_piece = mystrsep(line, iter); 4500| 130| while (start_piece != line.end()) { ------------------ | Branch (4500:10): [True: 104, False: 26] ------------------ 4501| 104| switch (i) { 4502| | // piece 1 - is type of affix 4503| 26| case 0: { ------------------ | Branch (4503:7): [True: 26, False: 78] ------------------ 4504| 26| np++; 4505| 26| break; 4506| 0| } 4507| | 4508| | // piece 2 - is affix char 4509| 26| case 1: { ------------------ | Branch (4509:7): [True: 26, False: 78] ------------------ 4510| 26| np++; 4511| 26| aflag = pHMgr->decode_flag(std::string(start_piece, iter)); 4512| 26| if (((at == 'S') && (dupflags[aflag] & dupSFX)) || ------------------ | | 88| 18|#define dupSFX (1 << 0) ------------------ | Branch (4512:14): [True: 18, False: 8] | Branch (4512:29): [True: 0, False: 18] ------------------ 4513| 26| ((at == 'P') && (dupflags[aflag] & dupPFX))) { ------------------ | | 89| 8|#define dupPFX (1 << 1) ------------------ | Branch (4513:14): [True: 8, False: 18] | Branch (4513:29): [True: 0, False: 8] ------------------ 4514| 0| HUNSPELL_WARNING( 4515| 0| stderr, 4516| 0| "error: line %d: multiple definitions of an affix flag\n", 4517| 0| af->getlinenum()); 4518| 0| } 4519| 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 (4519:35): [True: 18, False: 8] ------------------ 4520| 26| break; 4521| 0| } 4522| | // piece 3 - is cross product indicator 4523| 26| case 2: { ------------------ | Branch (4523:7): [True: 26, False: 78] ------------------ 4524| 26| np++; 4525| 26| if (*start_piece == 'Y') ------------------ | Branch (4525:13): [True: 26, False: 0] ------------------ 4526| 26| ff = aeXPRODUCT; ------------------ | | 65| 26|#define aeXPRODUCT (1 << 0) ------------------ 4527| 26| break; 4528| 0| } 4529| | 4530| | // piece 4 - is number of affentries 4531| 26| case 3: { ------------------ | Branch (4531:7): [True: 26, False: 78] ------------------ 4532| 26| np++; 4533| 26| numents = atoi(std::string(start_piece, iter).c_str()); 4534| 26| if ((numents <= 0) || ((std::numeric_limits::max() / ------------------ | Branch (4534:13): [True: 0, False: 26] | Branch (4534:31): [True: 0, False: 26] ------------------ 4535| 26| sizeof(AffEntry)) < static_cast(numents))) { 4536| 0| std::string err = pHMgr->encode_flag(aflag); 4537| 0| HUNSPELL_WARNING(stderr, "error: line %d: affix %s: bad entry number\n", 4538| 0| af->getlinenum(), err.c_str()); 4539| 0| return false; 4540| 0| } 4541| | 4542| 26| char opts = ff; 4543| 26| if (utf8) ------------------ | Branch (4543:13): [True: 6, False: 20] ------------------ 4544| 6| opts |= aeUTF8; ------------------ | | 66| 6|#define aeUTF8 (1 << 1) ------------------ 4545| 26| if (pHMgr->is_aliasf()) ------------------ | Branch (4545:13): [True: 4, False: 22] ------------------ 4546| 4| opts |= aeALIASF; ------------------ | | 67| 4|#define aeALIASF (1 << 2) ------------------ 4547| 26| if (pHMgr->is_aliasm()) ------------------ | Branch (4547:13): [True: 0, False: 26] ------------------ 4548| 0| opts |= aeALIASM; ------------------ | | 68| 0|#define aeALIASM (1 << 3) ------------------ 4549| 26| affentries.initialize(numents, opts, aflag); 4550| 26| } 4551| | 4552| 26| default: ------------------ | Branch (4552:7): [True: 0, False: 104] ------------------ 4553| 26| break; 4554| 104| } 4555| 104| ++i; 4556| 104| start_piece = mystrsep(line, iter); 4557| 104| } 4558| | // check to make sure we parsed enough pieces 4559| 26| if (np != 4) { ------------------ | Branch (4559:7): [True: 0, False: 26] ------------------ 4560| 0| std::string err = pHMgr->encode_flag(aflag); 4561| 0| HUNSPELL_WARNING(stderr, "error: line %d: affix %s: missing data\n", 4562| 0| af->getlinenum(), err.c_str()); 4563| 0| return false; 4564| 0| } 4565| | 4566| | // now parse numents affentries for this affix 4567| 26| AffEntry* entry = affentries.first_entry(); 4568| 68| for (int ent = 0; ent < numents; ++ent) { ------------------ | Branch (4568:21): [True: 42, False: 26] ------------------ 4569| 42| std::string nl; 4570| 42| if (!af->getline(nl)) ------------------ | Branch (4570:9): [True: 0, False: 42] ------------------ 4571| 0| return false; 4572| 42| mychomp(nl); 4573| | 4574| 42| iter = nl.begin(); 4575| 42| i = 0; 4576| 42| np = 0; 4577| | 4578| | // split line into pieces 4579| 42| start_piece = mystrsep(nl, iter); 4580| 258| while (start_piece != nl.end()) { ------------------ | Branch (4580:12): [True: 216, False: 42] ------------------ 4581| 216| switch (i) { 4582| | // piece 1 - is type 4583| 42| case 0: { ------------------ | Branch (4583:9): [True: 42, False: 174] ------------------ 4584| 42| np++; 4585| 42| if (ent != 0) ------------------ | Branch (4585:15): [True: 16, False: 26] ------------------ 4586| 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) ------------------ 4587| 42| break; 4588| 0| } 4589| | 4590| | // piece 2 - is affix char 4591| 42| case 1: { ------------------ | Branch (4591:9): [True: 42, False: 174] ------------------ 4592| 42| np++; 4593| 42| std::string chunk(start_piece, iter); 4594| 42| if (pHMgr->decode_flag(chunk) != aflag) { ------------------ | Branch (4594:15): [True: 0, False: 42] ------------------ 4595| 0| std::string err = pHMgr->encode_flag(aflag); 4596| 0| HUNSPELL_WARNING(stderr, 4597| 0| "error: line %d: affix %s is corrupt\n", 4598| 0| af->getlinenum(), err.c_str()); 4599| 0| return false; 4600| 0| } 4601| | 4602| 42| if (ent != 0) { ------------------ | Branch (4602:15): [True: 16, False: 26] ------------------ 4603| 16| AffEntry* start_entry = affentries.first_entry(); 4604| 16| entry->aflag = start_entry->aflag; 4605| 16| } 4606| 42| break; 4607| 42| } 4608| | 4609| | // piece 3 - is string to strip or 0 for null 4610| 42| case 2: { ------------------ | Branch (4610:9): [True: 42, False: 174] ------------------ 4611| 42| np++; 4612| 42| entry->strip = std::string(start_piece, iter); 4613| 42| if (complexprefixes) { ------------------ | Branch (4613:15): [True: 4, False: 38] ------------------ 4614| 4| if (utf8) ------------------ | Branch (4614:17): [True: 0, False: 4] ------------------ 4615| 0| reverseword_utf(entry->strip); 4616| 4| else 4617| 4| reverseword(entry->strip); 4618| 4| } 4619| 42| if (entry->strip.compare("0") == 0) { ------------------ | Branch (4619:15): [True: 36, False: 6] ------------------ 4620| 36| entry->strip.clear(); 4621| 36| } 4622| 42| break; 4623| 42| } 4624| | 4625| | // piece 4 - is affix string or 0 for null 4626| 42| case 3: { ------------------ | Branch (4626:9): [True: 42, False: 174] ------------------ 4627| 42| entry->morphcode = nullptr; 4628| 42| entry->contclass = nullptr; 4629| 42| entry->contclasslen = 0; 4630| 42| np++; 4631| 42| std::string::const_iterator dash = std::find(start_piece, iter, '/'); 4632| 42| if (dash != iter) { ------------------ | Branch (4632:15): [True: 18, False: 24] ------------------ 4633| 18| entry->appnd = std::string(start_piece, dash); 4634| 18| std::string dash_str(dash + 1, iter); 4635| | 4636| 18| if (!ignorechars.empty() && !has_no_ignored_chars(entry->appnd, ignorechars)) { ------------------ | Branch (4636:17): [True: 2, False: 16] | Branch (4636:41): [True: 0, False: 2] ------------------ 4637| 0| if (utf8) { ------------------ | Branch (4637:19): [True: 0, False: 0] ------------------ 4638| 0| remove_ignored_chars_utf(entry->appnd, ignorechars_utf16); 4639| 0| } else { 4640| 0| remove_ignored_chars(entry->appnd, ignorechars); 4641| 0| } 4642| 0| } 4643| | 4644| 18| if (complexprefixes) { ------------------ | Branch (4644:17): [True: 2, False: 16] ------------------ 4645| 2| if (utf8) ------------------ | Branch (4645:19): [True: 0, False: 2] ------------------ 4646| 0| reverseword_utf(entry->appnd); 4647| 2| else 4648| 2| reverseword(entry->appnd); 4649| 2| } 4650| | 4651| 18| if (pHMgr->is_aliasf()) { ------------------ | Branch (4651:17): [True: 2, False: 16] ------------------ 4652| 2| int index = atoi(dash_str.c_str()); 4653| 2| entry->contclasslen = (unsigned short)pHMgr->get_aliasf( 4654| 2| index, &(entry->contclass), af); 4655| 2| if (!entry->contclasslen) ------------------ | Branch (4655:19): [True: 0, False: 2] ------------------ 4656| 0| HUNSPELL_WARNING(stderr, 4657| 0| "error: bad affix flag alias: \"%s\"\n", 4658| 0| dash_str.c_str()); 4659| 16| } else { 4660| 16| entry->contclasslen = (unsigned short)pHMgr->decode_flags( 4661| 16| &(entry->contclass), dash_str, af); 4662| 16| std::sort(entry->contclass, entry->contclass + entry->contclasslen); 4663| 16| } 4664| | 4665| 18| havecontclass = 1; 4666| 44| for (unsigned short _i = 0; _i < entry->contclasslen; _i++) { ------------------ | Branch (4666:41): [True: 26, False: 18] ------------------ 4667| 26| contclasses[(entry->contclass)[_i]] = 1; 4668| 26| } 4669| 24| } else { 4670| 24| entry->appnd = std::string(start_piece, iter); 4671| | 4672| 24| if (!ignorechars.empty() && !has_no_ignored_chars(entry->appnd, ignorechars)) { ------------------ | Branch (4672:17): [True: 2, False: 22] | Branch (4672:41): [True: 2, False: 0] ------------------ 4673| 2| if (utf8) { ------------------ | Branch (4673:19): [True: 0, False: 2] ------------------ 4674| 0| remove_ignored_chars_utf(entry->appnd, ignorechars_utf16); 4675| 2| } else { 4676| 2| remove_ignored_chars(entry->appnd, ignorechars); 4677| 2| } 4678| 2| } 4679| | 4680| 24| if (complexprefixes) { ------------------ | Branch (4680:17): [True: 2, False: 22] ------------------ 4681| 2| if (utf8) ------------------ | Branch (4681:19): [True: 0, False: 2] ------------------ 4682| 0| reverseword_utf(entry->appnd); 4683| 2| else 4684| 2| reverseword(entry->appnd); 4685| 2| } 4686| 24| } 4687| | 4688| 42| if (entry->appnd.compare("0") == 0) { ------------------ | Branch (4688:15): [True: 2, False: 40] ------------------ 4689| 2| entry->appnd.clear(); 4690| 2| } 4691| 42| break; 4692| 42| } 4693| | 4694| | // piece 5 - is the conditions descriptions 4695| 42| case 4: { ------------------ | Branch (4695:9): [True: 42, False: 174] ------------------ 4696| 42| std::string chunk(start_piece, iter); 4697| 42| np++; 4698| 42| if (complexprefixes) { ------------------ | Branch (4698:15): [True: 4, False: 38] ------------------ 4699| 4| if (utf8) ------------------ | Branch (4699:17): [True: 0, False: 4] ------------------ 4700| 0| reverseword_utf(chunk); 4701| 4| else 4702| 4| reverseword(chunk); 4703| 4| reverse_condition(chunk); 4704| 4| } 4705| 42| if (!entry->strip.empty() && chunk != "." && ------------------ | Branch (4705:15): [True: 6, False: 36] | Branch (4705:40): [True: 6, False: 0] ------------------ 4706| 6| redundant_condition(at, entry->strip, chunk, ------------------ | Branch (4706:15): [True: 6, False: 0] ------------------ 4707| 6| af->getlinenum())) 4708| 6| chunk = "."; 4709| 42| if (at == 'S') { ------------------ | Branch (4709:15): [True: 34, False: 8] ------------------ 4710| 34| reverseword(chunk); 4711| 34| reverse_condition(chunk); 4712| 34| } 4713| 42| if (encodeit(*entry, chunk)) ------------------ | Branch (4713:15): [True: 0, False: 42] ------------------ 4714| 0| return false; 4715| 42| break; 4716| 42| } 4717| | 4718| 42| case 5: { ------------------ | Branch (4718:9): [True: 6, False: 210] ------------------ 4719| 6| std::string chunk(start_piece, iter); 4720| 6| np++; 4721| 6| if (pHMgr->is_aliasm()) { ------------------ | Branch (4721:15): [True: 0, False: 6] ------------------ 4722| 0| int index = atoi(chunk.c_str()); 4723| 0| entry->morphcode = pHMgr->get_aliasm(index); 4724| 6| } else { 4725| 6| if (complexprefixes) { // XXX - fix me for morph. gen. ------------------ | Branch (4725:17): [True: 0, False: 6] ------------------ 4726| 0| if (utf8) ------------------ | Branch (4726:19): [True: 0, False: 0] ------------------ 4727| 0| reverseword_utf(chunk); 4728| 0| else 4729| 0| reverseword(chunk); 4730| 0| } 4731| | // add the remaining of the line 4732| 6| std::string::const_iterator end = nl.end(); 4733| 6| if (iter != end) { ------------------ | Branch (4733:17): [True: 0, False: 6] ------------------ 4734| 0| chunk.append(iter, end); 4735| 0| } 4736| 6| entry->morphcode = mystrdup(chunk.c_str()); 4737| 6| } 4738| 6| break; 4739| 42| } 4740| 0| default: ------------------ | Branch (4740:9): [True: 0, False: 216] ------------------ 4741| 0| break; 4742| 216| } 4743| 216| i++; 4744| 216| start_piece = mystrsep(nl, iter); 4745| 216| } 4746| | // check to make sure we parsed enough pieces 4747| 42| if (np < 4) { ------------------ | Branch (4747:9): [True: 0, False: 42] ------------------ 4748| 0| std::string err = pHMgr->encode_flag(aflag); 4749| 0| HUNSPELL_WARNING(stderr, "error: line %d: affix %s is corrupt\n", 4750| 0| af->getlinenum(), err.c_str()); 4751| 0| return false; 4752| 0| } 4753| | 4754| |#ifdef DEBUG 4755| | // detect unnecessary fields, excepting comments 4756| | if (basefieldnum) { 4757| | int fieldnum = 4758| | !(entry->morphcode) ? 5 : ((*(entry->morphcode) == '#') ? 5 : 6); 4759| | if (fieldnum != basefieldnum) 4760| | HUNSPELL_WARNING(stderr, "warning: line %d: bad field number\n", 4761| | af->getlinenum()); 4762| | } else { 4763| | basefieldnum = 4764| | !(entry->morphcode) ? 5 : ((*(entry->morphcode) == '#') ? 5 : 6); 4765| | } 4766| |#endif 4767| 42| } 4768| | 4769| | // now create SfxEntry or PfxEntry objects and use links to 4770| | // build an ordered (sorted by affix string) list 4771| 26| auto start = affentries.begin(), end = affentries.end(); 4772| 68| for (auto affentry = start; affentry != end; ++affentry) { ------------------ | Branch (4772:31): [True: 42, False: 26] ------------------ 4773| 42| if (at == 'P') { ------------------ | Branch (4773:9): [True: 8, False: 34] ------------------ 4774| 8| build_pfxtree(static_cast(*affentry)); 4775| 34| } else { 4776| 34| build_sfxtree(static_cast(*affentry)); 4777| 34| } 4778| 42| } 4779| | 4780| | //contents belong to AffixMgr now 4781| 26| affentries.release(); 4782| | 4783| 26| return true; 4784| 26|} _ZN8AffixMgr19redundant_conditionEcRKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_i: 4789| 6| int linenum) { 4790| 6| int stripl = strip.size(), condl = cond.size(), i, j, neg, in; 4791| 6| if (ft == 'P') { // prefix ------------------ | Branch (4791:7): [True: 0, False: 6] ------------------ 4792| 0| if (strip.compare(0, condl, cond) == 0) ------------------ | Branch (4792:9): [True: 0, False: 0] ------------------ 4793| 0| return 1; 4794| 0| if (utf8) { ------------------ | Branch (4794:9): [True: 0, False: 0] ------------------ 4795| 0| } else { 4796| 0| for (i = 0, j = 0; (i < stripl) && (j < condl); i++, j++) { ------------------ | Branch (4796:26): [True: 0, False: 0] | Branch (4796:42): [True: 0, False: 0] ------------------ 4797| 0| if (cond[j] != '[') { ------------------ | Branch (4797:13): [True: 0, False: 0] ------------------ 4798| 0| if (cond[j] != strip[i]) { ------------------ | Branch (4798:15): [True: 0, False: 0] ------------------ 4799| 0| HUNSPELL_WARNING(stderr, 4800| 0| "warning: line %d: incompatible stripping " 4801| 0| "characters and condition\n", 4802| 0| linenum); 4803| 0| return 0; 4804| 0| } 4805| 0| } else { 4806| 0| neg = (cond[j + 1] == '^') ? 1 : 0; ------------------ | Branch (4806:17): [True: 0, False: 0] ------------------ 4807| 0| in = 0; 4808| 0| do { 4809| 0| j++; 4810| 0| if (strip[i] == cond[j]) ------------------ | Branch (4810:17): [True: 0, False: 0] ------------------ 4811| 0| in = 1; 4812| 0| } while ((j < (condl - 1)) && (cond[j] != ']')); ------------------ | Branch (4812:20): [True: 0, False: 0] | Branch (4812:41): [True: 0, False: 0] ------------------ 4813| 0| if (j == (condl - 1) && (cond[j] != ']')) { ------------------ | Branch (4813:15): [True: 0, False: 0] | Branch (4813:35): [True: 0, False: 0] ------------------ 4814| 0| HUNSPELL_WARNING(stderr, 4815| 0| "error: line %d: missing ] in condition:\n%s\n", 4816| 0| linenum, cond.c_str()); 4817| 0| return 0; 4818| 0| } 4819| 0| if ((!neg && !in) || (neg && in)) { ------------------ | Branch (4819:16): [True: 0, False: 0] | Branch (4819:24): [True: 0, False: 0] | Branch (4819:33): [True: 0, False: 0] | Branch (4819:40): [True: 0, False: 0] ------------------ 4820| 0| HUNSPELL_WARNING(stderr, 4821| 0| "warning: line %d: incompatible stripping " 4822| 0| "characters and condition\n", 4823| 0| linenum); 4824| 0| return 0; 4825| 0| } 4826| 0| } 4827| 0| } 4828| 0| if (j >= condl) ------------------ | Branch (4828:11): [True: 0, False: 0] ------------------ 4829| 0| return 1; 4830| 0| } 4831| 6| } else { // suffix 4832| 6| if ((stripl >= condl) && strip.compare(stripl - condl, std::string::npos, cond) == 0) ------------------ | Branch (4832:9): [True: 6, False: 0] | Branch (4832:30): [True: 6, False: 0] ------------------ 4833| 6| return 1; 4834| 0| if (utf8) { ------------------ | Branch (4834:9): [True: 0, False: 0] ------------------ 4835| 0| } else { 4836| 0| for (i = stripl - 1, j = condl - 1; (i >= 0) && (j >= 0); i--, j--) { ------------------ | Branch (4836:43): [True: 0, False: 0] | Branch (4836:55): [True: 0, False: 0] ------------------ 4837| 0| if (cond[j] != ']') { ------------------ | Branch (4837:13): [True: 0, False: 0] ------------------ 4838| 0| if (cond[j] != strip[i]) { ------------------ | Branch (4838:15): [True: 0, False: 0] ------------------ 4839| 0| HUNSPELL_WARNING(stderr, 4840| 0| "warning: line %d: incompatible stripping " 4841| 0| "characters and condition\n", 4842| 0| linenum); 4843| 0| return 0; 4844| 0| } 4845| 0| } else if (j > 0) { ------------------ | Branch (4845:20): [True: 0, False: 0] ------------------ 4846| 0| in = 0; 4847| 0| do { 4848| 0| j--; 4849| 0| if (strip[i] == cond[j]) ------------------ | Branch (4849:17): [True: 0, False: 0] ------------------ 4850| 0| in = 1; 4851| 0| } while ((j > 0) && (cond[j] != '[')); ------------------ | Branch (4851:20): [True: 0, False: 0] | Branch (4851:31): [True: 0, False: 0] ------------------ 4852| 0| if ((j == 0) && (cond[j] != '[')) { ------------------ | Branch (4852:15): [True: 0, False: 0] | Branch (4852:27): [True: 0, False: 0] ------------------ 4853| 0| HUNSPELL_WARNING(stderr, 4854| 0| "error: line: %d: missing ] in condition:\n%s\n", 4855| 0| linenum, cond.c_str()); 4856| 0| return 0; 4857| 0| } 4858| 0| neg = (cond[j + 1] == '^') ? 1 : 0; ------------------ | Branch (4858:17): [True: 0, False: 0] ------------------ 4859| 0| if ((!neg && !in) || (neg && in)) { ------------------ | Branch (4859:16): [True: 0, False: 0] | Branch (4859:24): [True: 0, False: 0] | Branch (4859:33): [True: 0, False: 0] | Branch (4859:40): [True: 0, False: 0] ------------------ 4860| 0| HUNSPELL_WARNING(stderr, 4861| 0| "warning: line %d: incompatible stripping " 4862| 0| "characters and condition\n", 4863| 0| linenum); 4864| 0| return 0; 4865| 0| } 4866| 0| } 4867| 0| } 4868| 0| if (j < 0) ------------------ | Branch (4868:11): [True: 0, False: 0] ------------------ 4869| 0| return 1; 4870| 0| } 4871| 0| } 4872| 0| return 0; 4873| 6|} _ZN8AffixMgr8isSubsetEPKcS1_: 1069| 75.6k|inline int AffixMgr::isSubset(const char* s1, const char* s2) { 1070| 101k| while (((*s1 == *s2) || (*s1 == '.')) && (*s1 != '\0') && (*s2 != '\0')) { ------------------ | Branch (1070:11): [True: 76.1k, False: 25.1k] | Branch (1070:27): [True: 0, False: 25.1k] | Branch (1070:44): [True: 25.7k, False: 50.4k] | Branch (1070:61): [True: 25.7k, False: 0] ------------------ 1071| 25.7k| s1++; 1072| 25.7k| s2++; 1073| 25.7k| } 1074| 75.6k| return (*s1 == '\0'); 1075| 75.6k|} _ZN8AffixMgr11isRevSubsetEPKcS1_i: 2725| 473k| int len) { 2726| 948k| while ((len > 0) && (*s1 != '\0') && ((*s1 == *end_of_s2) || (*s1 == '.'))) { ------------------ | Branch (2726:10): [True: 942k, False: 6.56k] | Branch (2726:23): [True: 578k, False: 363k] | Branch (2726:41): [True: 475k, False: 103k] | Branch (2726:64): [True: 0, False: 103k] ------------------ 2727| 475k| s1++; 2728| 475k| end_of_s2--; 2729| 475k| len--; 2730| 475k| } 2731| 473k| return (*s1 == '\0'); 2732| 473k|} affixmgr.cxx:_ZN12_GLOBAL__N_18mystrdupEPKc: 3389| 529k| char* mystrdup(const char* s) { 3390| 529k| char* d = nullptr; 3391| 529k| if (s) { ------------------ | Branch (3391:9): [True: 529k, False: 0] ------------------ 3392| 529k| size_t sl = strlen(s) + 1; 3393| 529k| d = new char[sl]; 3394| 529k| memcpy(d, s, sl); 3395| 529k| } 3396| 529k| return d; 3397| 529k| } _ZN17entries_containerC2EcP8AffixMgr: 4435| 26| : m_mgr(mgr) 4436| 26| , m_at(at) { 4437| 26| } _ZN17entries_container10initializeEict: 4442| 26| char opts, unsigned short aflag) { 4443| 26| entries.reserve(std::min(numents, 16384)); 4444| | 4445| 26| if (m_at == 'P') { ------------------ | Branch (4445:9): [True: 8, False: 18] ------------------ 4446| 8| entries.push_back(new PfxEntry(m_mgr)); 4447| 18| } else { 4448| 18| entries.push_back(new SfxEntry(m_mgr)); 4449| 18| } 4450| | 4451| 26| entries.back()->opts = opts; 4452| 26| entries.back()->aflag = aflag; 4453| 26| } _ZN17entries_container11first_entryEv: 4466| 42| AffEntry* first_entry() { return entries.empty() ? nullptr : entries[0]; } ------------------ | Branch (4466:36): [True: 0, False: 42] ------------------ _ZN17entries_container9add_entryEc: 4455| 16| AffEntry* add_entry(char opts) { 4456| 16| if (m_at == 'P') { ------------------ | Branch (4456:9): [True: 0, False: 16] ------------------ 4457| 0| entries.push_back(new PfxEntry(m_mgr)); 4458| 16| } else { 4459| 16| entries.push_back(new SfxEntry(m_mgr)); 4460| 16| } 4461| 16| AffEntry* ret = entries.back(); 4462| 16| ret->opts = entries[0]->opts & opts; 4463| 16| return ret; 4464| 16| } _ZN17entries_container5beginEv: 4474| 26| std::vector::iterator begin() { return entries.begin(); } _ZN17entries_container3endEv: 4475| 26| std::vector::iterator end() { return entries.end(); } _ZN17entries_container7releaseEv: 4438| 26| void release() { 4439| 26| entries.clear(); 4440| 26| } _ZN17entries_containerD2Ev: 4468| 26| ~entries_container() { 4469| 26| for (auto& entry : entries) { ------------------ | Branch (4469:22): [True: 0, False: 26] ------------------ 4470| 0| delete entry; 4471| 0| } 4472| 26| } affixmgr.cxx:_ZZN8AffixMgr12get_syllableERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEENK3$_1clE6w_char: 1574| 1.71k| [&](w_char wc) { 1575| 1.71k| return std::binary_search(cpdvowels_utf16.begin(), cpdvowels_utf16.end(), wc); 1576| 1.71k| }); _ZN9guesswordC2Ev: 118| 4.59M| : word(nullptr) 119| 4.59M| , allow(false) 120| 4.59M| , orig(nullptr) 121| 4.59M| { 122| 4.59M| } _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| 1.33M|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: 111| 114|{ 112| |#if defined(_WIN32) && defined(_MSC_VER) 113| |#define WIN32_LONG_PATH_PREFIX "\\\\?\\" 114| | if (strncmp(path, WIN32_LONG_PATH_PREFIX, 4) == 0) { 115| | int len = MultiByteToWideChar(CP_UTF8, 0, path, -1, NULL, 0); 116| | wchar_t* buff = new wchar_t[len]; 117| | wchar_t* buff2 = new wchar_t[len]; 118| | MultiByteToWideChar(CP_UTF8, 0, path, -1, buff, len); 119| | if (_wfullpath(buff2, buff, len) != NULL) { 120| | stream.open(buff2, mode); 121| | } 122| | delete [] buff; 123| | delete [] buff2; 124| | } 125| | else 126| |#endif 127| 114| stream.open(path, mode); 128| 114|} _Z6u16_u8RNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKNS_6vectorI6w_charNS3_IS8_EEEE: 135| 20.6M|std::string& u16_u8(std::string& dest, const std::vector& src) { 136| 20.6M| dest.clear(); 137| 20.6M| dest.reserve(src.size()); 138| 539M| for (const w_char& wc : src) { ------------------ | Branch (138:25): [True: 539M, False: 20.6M] ------------------ 139| 539M| uint16_t cp = (static_cast(wc.h) << 8) | wc.l; 140| 539M| if (cp < 0x80) { ------------------ | Branch (140:9): [True: 478M, False: 60.7M] ------------------ 141| 478M| dest.push_back(static_cast(cp)); 142| 478M| } else if (cp < 0x800) { ------------------ | Branch (142:16): [True: 2.31M, False: 58.4M] ------------------ 143| 2.31M| dest.push_back(static_cast(0xc0 | (cp >> 6))); 144| 2.31M| dest.push_back(static_cast(0x80 | (cp & 0x3f))); 145| 58.4M| } else { 146| 58.4M| dest.push_back(static_cast(0xe0 | (cp >> 12))); 147| 58.4M| dest.push_back(static_cast(0x80 | ((cp >> 6) & 0x3f))); 148| 58.4M| dest.push_back(static_cast(0x80 | (cp & 0x3f))); 149| 58.4M| } 150| 539M| } 151| 20.6M| return dest; 152| 20.6M|} _Z6u8_u16RNSt3__16vectorI6w_charNS_9allocatorIS1_EEEERKNS_12basic_stringIcNS_11char_traitsIcEENS2_IcEEEEb: 170| 4.27M|int u8_u16(std::vector& dest, const std::string& src, bool only_convert_first_letter) { 171| | // faster to oversize initially, assign to elements and resize to what's used 172| | // than to reserve and push_back 173| 4.27M| dest.resize(only_convert_first_letter ? 1 : src.size()); ------------------ | Branch (173:15): [True: 0, False: 4.27M] ------------------ 174| 4.27M| auto out = dest.begin(); 175| 4.27M| auto p = src.begin(), end = src.end(); 176| | 177| 36.5M| while (p < end) { ------------------ | Branch (177:10): [True: 32.5M, False: 4.07M] ------------------ 178| 32.5M| uint8_t b0 = static_cast(*p); 179| 32.5M| uint16_t cp; 180| | 181| 32.5M| if (b0 < 0x80) { ------------------ | Branch (181:9): [True: 29.3M, False: 3.12M] ------------------ 182| | // 1-byte ASCII 183| 29.3M| cp = b0; 184| 29.3M| } else if (b0 < 0xc0) { ------------------ | Branch (184:16): [True: 451k, False: 2.67M] ------------------ 185| | // continuation byte at lead position 186| 451k| HUNSPELL_WARNING(stderr, 187| 451k| "UTF-8 encoding error. Unexpected continuation bytes " 188| 451k| "in %ld. character position\n%s\n", 189| 451k| static_cast(std::distance(src.begin(), p)), 190| 451k| src.c_str()); 191| 451k| cp = 0xfffd; 192| 2.67M| } else if (b0 < 0xe0) { ------------------ | Branch (192:16): [True: 821k, False: 1.85M] ------------------ 193| | // 2-byte sequence: 110xxxxx 10yyyyyy 194| 821k| if (p + 1 < end && is_utf8_cont(p[1])) { ------------------ | Branch (194:11): [True: 716k, False: 105k] | Branch (194:11): [True: 220k, False: 600k] | Branch (194:26): [True: 220k, False: 495k] ------------------ 195| 220k| cp = ((b0 & 0x1f) << 6) | (static_cast(p[1]) & 0x3f); 196| 220k| ++p; // step past lead; loop bottom steps past cont 197| 600k| } else { 198| 600k| warn_missing_cont(src, p); 199| 600k| cp = 0xfffd; 200| 600k| } 201| 1.85M| } else if (b0 < 0xf0) { ------------------ | Branch (201:16): [True: 1.65M, False: 194k] ------------------ 202| | // 3-byte sequence: 1110xxxx 10yyyyyy 10zzzzzz 203| 1.65M| if (p + 1 < end && is_utf8_cont(p[1])) { ------------------ | Branch (203:11): [True: 1.63M, False: 22.9k] | Branch (203:11): [True: 1.58M, False: 78.1k] | Branch (203:26): [True: 1.58M, False: 55.2k] ------------------ 204| 1.58M| uint8_t b1 = static_cast(p[1]); 205| 1.58M| ++p; // step past lead 206| 1.58M| if (p + 1 < end && is_utf8_cont(p[1])) { ------------------ | Branch (206:13): [True: 1.57M, False: 6.47k] | Branch (206:13): [True: 1.57M, False: 8.16k] | Branch (206:28): [True: 1.57M, False: 1.69k] ------------------ 207| 1.57M| cp = ((b0 & 0x0f) << 12) | ((b1 & 0x3f) << 6) | (static_cast(p[1]) & 0x3f); 208| 1.57M| ++p; // step past first cont; loop bottom steps past second cont 209| 1.57M| } else { 210| 8.16k| warn_missing_cont(src, p); 211| 8.16k| cp = 0xfffd; 212| 8.16k| } 213| 1.58M| } else { 214| 78.1k| warn_missing_cont(src, p); 215| 78.1k| cp = 0xfffd; 216| 78.1k| } 217| 1.65M| } else { 218| | // 4+ byte lead: codepoint >= U+10000, can't fit in w_char 219| 194k| HUNSPELL_WARNING(stderr, 220| 194k| "This UTF-8 encoding can't convert to UTF-16:\n%s\n", 221| 194k| src.c_str()); 222| 194k| out->h = 0xff; 223| 194k| out->l = 0xfd; 224| 194k| ++out; 225| 194k| dest.resize(out - dest.begin()); 226| 194k| return -1; 227| 194k| } 228| | 229| 32.3M| out->h = static_cast(cp >> 8); 230| 32.3M| out->l = static_cast(cp); 231| 32.3M| ++out; 232| 32.3M| if (only_convert_first_letter) ------------------ | Branch (232:9): [True: 0, False: 32.3M] ------------------ 233| 0| break; 234| 32.3M| ++p; // consume lead byte 235| 32.3M| } 236| | 237| 4.07M| int size = static_cast(out - dest.begin()); 238| 4.07M| dest.resize(size); 239| 4.07M| return size; 240| 4.27M|} _Z8mystrsepRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERNS_11__wrap_iterIPKcEE: 255| 1.80k| std::string::const_iterator& start) { 256| 1.80k| auto end = str.end(); 257| | 258| 1.80k| is_any_of op(" \t"); 259| | // don't use isspace() here, the string can be in some random charset 260| | // that's way different than the locale's 261| 1.80k| auto sp = start; 262| 5.87k| while (sp != end && op(*sp)) ------------------ | Branch (262:10): [True: 5.43k, False: 442] | Branch (262:23): [True: 4.07k, False: 1.35k] ------------------ 263| 4.07k| ++sp; 264| | 265| 1.80k| auto dp = sp; 266| 6.69k| while (dp != end && !op(*dp)) ------------------ | Branch (266:10): [True: 5.81k, False: 882] | Branch (266:23): [True: 4.89k, False: 918] ------------------ 267| 4.89k| ++dp; 268| | 269| 1.80k| start = dp; 270| 1.80k| return sp; 271| 1.80k|} _Z7mychompRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 274| 1.99k|void mychomp(std::string& s) { 275| 1.99k| size_t k = s.size(); 276| 1.99k| size_t newsize = k; 277| 1.99k| if ((k > 0) && ((s[k - 1] == '\r') || (s[k - 1] == '\n'))) ------------------ | Branch (277:7): [True: 1.80k, False: 190] | Branch (277:19): [True: 0, False: 1.80k] | Branch (277:41): [True: 0, False: 1.80k] ------------------ 278| 0| --newsize; 279| 1.99k| if ((k > 1) && (s[k - 2] == '\r')) ------------------ | Branch (279:7): [True: 1.60k, False: 384] | Branch (279:18): [True: 0, False: 1.60k] ------------------ 280| 0| --newsize; 281| 1.99k| s.resize(newsize); 282| 1.99k|} _Z8line_tokRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEc: 285| 243k|std::vector line_tok(const std::string& text, char breakchar) { 286| 243k| std::vector ret; 287| 243k| if (text.empty()) { ------------------ | Branch (287:7): [True: 8.69k, False: 234k] ------------------ 288| 8.69k| return ret; 289| 8.69k| } 290| | 291| 234k| std::stringstream ss(text); 292| 234k| std::string tok; 293| 482k| while(std::getline(ss, tok, breakchar)) { ------------------ | Branch (293:9): [True: 248k, False: 234k] ------------------ 294| 248k| if (!tok.empty()) { ------------------ | Branch (294:9): [True: 248k, False: 71] ------------------ 295| 248k| ret.push_back(tok); 296| 248k| } 297| 248k| } 298| | 299| 234k| return ret; 300| 243k|} _Z9line_uniqRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEc: 312| 10.7k|{ 313| 10.7k| std::vector lines = line_tok(text, breakchar); 314| 10.7k| text.clear(); 315| 10.7k| if (lines.empty()) { ------------------ | Branch (315:7): [True: 8.68k, False: 2.10k] ------------------ 316| 8.68k| return; 317| 8.68k| } 318| | 319| 2.10k| drop_repeated_lines(lines); 320| | 321| 2.10k| text = lines[0]; 322| 2.11k| for (size_t i = 1; i < lines.size(); ++i) { ------------------ | Branch (322:22): [True: 10, False: 2.10k] ------------------ 323| 10| text.push_back(breakchar); 324| 10| text.append(lines[i]); 325| 10| } 326| 2.10k|} _Z21append_compound_partsRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERS5_: 375| 230k|size_t append_compound_parts(const std::string& desc, std::string& result) { 376| | // find by offset, a search from a bare pointer remeasures the rest of desc on every step 377| 230k| size_t part = desc.find(MORPH_PART); ------------------ | | 116| 230k|#define MORPH_PART "pa:" ------------------ 378| 230k| if (part == std::string::npos) ------------------ | Branch (378:7): [True: 230k, False: 0] ------------------ 379| 230k| return 0; 380| 0| size_t nextpart = desc.find(MORPH_PART, part + 1); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 381| 0| while (nextpart != std::string::npos) { ------------------ | Branch (381:10): [True: 0, False: 0] ------------------ 382| 0| const char* field = desc.c_str() + part + MORPH_TAG_LEN; ------------------ | | 119| 0|#define MORPH_TAG_LEN strlen(MORPH_STEM) | | ------------------ | | | | 103| 0|#define MORPH_STEM "st:" | | ------------------ ------------------ 383| 0| result.append(field, fieldlen(field)); 384| 0| part = nextpart; 385| 0| nextpart = desc.find(MORPH_PART, part + 1); ------------------ | | 116| 0|#define MORPH_PART "pa:" ------------------ 386| 0| } 387| 0| return part; 388| 230k|} _Z10copy_fieldRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKS5_S8_: 392| 229k| const std::string& var) { 393| 229k| if (morph.empty()) ------------------ | Branch (393:7): [True: 0, False: 229k] ------------------ 394| 0| return false; 395| 229k| size_t pos = morph.find(var); 396| 229k| if (pos == std::string::npos) ------------------ | Branch (396:7): [True: 15, False: 229k] ------------------ 397| 15| return false; 398| 229k| pos += MORPH_TAG_LEN; ------------------ | | 119| 229k|#define MORPH_TAG_LEN strlen(MORPH_STEM) | | ------------------ | | | | 103| 229k|#define MORPH_STEM "st:" | | ------------------ ------------------ 399| | // copy the field value up to the next whitespace, without first 400| | // making a throwaway copy of the whole remaining tail of the string 401| 229k| size_t end = morph.find_first_of(" \t\n", pos); 402| 229k| dest.assign(morph, pos, end == std::string::npos ? std::string::npos : end - pos); ------------------ | Branch (402:27): [True: 229k, False: 0] ------------------ 403| | 404| 229k| return true; 405| 229k|} _Z8mystrrepRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKS5_S8_: 409| 927k| const std::string& replace) { 410| 927k| size_t pos = 0; 411| 1.05M| while ((pos = str.find(search, pos)) != std::string::npos) { ------------------ | Branch (411:10): [True: 128k, False: 927k] ------------------ 412| 128k| str.replace(pos, search.length(), replace); 413| 128k| pos += replace.length(); 414| 128k| } 415| 927k| return str; 416| 927k|} _Z11reversewordRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 419| 1.00M|size_t reverseword(std::string& word) { 420| 1.00M| std::reverse(word.begin(), word.end()); 421| 1.00M| return word.size(); 422| 1.00M|} _Z8uniqlistRNSt3__16vectorINS_12basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS4_IS6_EEEE: 499| 5.84k|void uniqlist(std::vector& list) { 500| 5.84k| if (list.size() < 2) ------------------ | Branch (500:7): [True: 5.84k, False: 0] ------------------ 501| 5.84k| return; 502| | 503| 0| std::vector ret; 504| 0| ret.push_back(list[0]); 505| | 506| 0| for (size_t i = 1; i < list.size(); ++i) { ------------------ | Branch (506:22): [True: 0, False: 0] ------------------ 507| 0| if (std::find(ret.begin(), ret.end(), list[i]) == ret.end()) ------------------ | Branch (507:9): [True: 0, False: 0] ------------------ 508| 0| ret.push_back(list[i]); 509| 0| } 510| | 511| 0| list.swap(ret); 512| 0|} _Z9upper_utf6w_chari: 531| 3.87M|w_char upper_utf(w_char u, int langnum) { 532| | 533| 3.87M|#if defined(_WIN32) || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__==__ORDER_LITTLE_ENDIAN__)) || defined(__LITTLE_ENDIAN__) 534| | 535| |//with these optimizations, msvc can optimize this function to one jmp instruction 536| |//but g++ remains in five instructions 537| |//maybe use inline asm for g++? 538| | 539| |#if (__cplusplus >= 202002L || (defined(_MSVC_LANG) && _MSVC_LANG >= 202002L)) && defined __cpp_lib_bit_cast && __cpp_lib_bit_cast >= 201806L 540| | return std::bit_cast(unicodetoupper((unsigned short)u, langnum)); 541| |#else 542| 3.87M| const auto us = unicodetoupper((unsigned short)u, langnum); 543| 3.87M| memcpy(&u, &us, sizeof(unsigned short)); 544| 3.87M| return u; 545| 3.87M|#endif 546| | 547| |#else 548| | const auto us = unicodetoupper((unsigned short)u, langnum); 549| | u.h = (unsigned char)(us >> 8); 550| | u.l = (unsigned char)(us & 0xff); 551| | return u; 552| |#endif 553| 3.87M|} _Z9lower_utf6w_chari: 555| 6.17M|w_char lower_utf(w_char u, int langnum) { 556| | 557| 6.17M|#if defined(_WIN32) || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__==__ORDER_LITTLE_ENDIAN__)) || defined(__LITTLE_ENDIAN__) 558| | 559| |//with these optimizations, msvc can optimize this function to one jmp instruction 560| |//but g++ remains in five instructions 561| |//maybe use inline asm for g++? 562| | 563| |#if (__cplusplus >= 202002L || (defined(_MSVC_LANG) && _MSVC_LANG >= 202002L)) && defined __cpp_lib_bit_cast && __cpp_lib_bit_cast >= 201806L 564| | return std::bit_cast(unicodetolower((unsigned short)u, langnum)); 565| |#else 566| 6.17M| const auto us = unicodetolower((unsigned short)u, langnum); 567| 6.17M| memcpy(&u, &us, sizeof(unsigned short)); 568| 6.17M| return u; 569| 6.17M|#endif 570| | 571| |#else 572| | const auto us = unicodetolower((unsigned short)u, langnum); 573| | u.h = (unsigned char)(us >> 8); 574| | u.l = (unsigned char)(us & 0xff); 575| | return u; 576| |#endif 577| 6.17M|} _Z8mkallcapRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 580| 259k|std::string& mkallcap(std::string& s, const struct cs_info* csconv) { 581| 5.12M| for (char& aI : s) { ------------------ | Branch (581:17): [True: 5.12M, False: 259k] ------------------ 582| 5.12M| aI = cupper(csconv, static_cast(aI)); 583| 5.12M| } 584| 259k| return s; 585| 259k|} _Z10mkallsmallRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 588| 1.85M|std::string& mkallsmall(std::string& s, const struct cs_info* csconv) { 589| 20.2M| for (char& aI : s) { ------------------ | Branch (589:17): [True: 20.2M, False: 1.85M] ------------------ 590| 20.2M| aI = clower(csconv, static_cast(aI)); 591| 20.2M| } 592| 1.85M| return s; 593| 1.85M|} _Z14mkallsmall_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 595| 882k|std::vector& mkallsmall_utf(std::vector& u, int langnum) { 596| 6.12M| for (auto& i : u) { ------------------ | Branch (596:16): [True: 6.12M, False: 882k] ------------------ 597| 6.12M| i = lower_utf(i, langnum); 598| 6.12M| } 599| 882k| return u; 600| 882k|} _Z12mkallcap_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 602| 150k|std::vector& mkallcap_utf(std::vector& u, int langnum) { 603| 1.78M| for (auto& i : u) { ------------------ | Branch (603:16): [True: 1.78M, False: 150k] ------------------ 604| 1.78M| i = upper_utf(i, langnum); 605| 1.78M| } 606| 150k| return u; 607| 150k|} _Z9mkinitcapRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 609| 1.14M|std::string& mkinitcap(std::string& s, const struct cs_info* csconv) { 610| 1.14M| if (!s.empty()) { ------------------ | Branch (610:7): [True: 1.14M, False: 213] ------------------ 611| 1.14M| s[0] = cupper(csconv, static_cast(s[0])); 612| 1.14M| } 613| 1.14M| return s; 614| 1.14M|} _Z13mkinitcap_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 616| 317k|std::vector& mkinitcap_utf(std::vector& u, int langnum) { 617| 317k| if (!u.empty()) { ------------------ | Branch (617:7): [True: 317k, False: 0] ------------------ 618| 317k| u[0] = upper_utf(u[0], langnum); 619| 317k| } 620| 317k| return u; 621| 317k|} _Z11mkinitsmallRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 623| 216k|std::string& mkinitsmall(std::string& s, const struct cs_info* csconv) { 624| 216k| if (!s.empty()) { ------------------ | Branch (624:7): [True: 216k, False: 0] ------------------ 625| 216k| s[0] = clower(csconv, static_cast(s[0])); 626| 216k| } 627| 216k| return s; 628| 216k|} _Z15mkinitsmall_utfRNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 630| 31.1k|std::vector& mkinitsmall_utf(std::vector& u, int langnum) { 631| 31.1k| if (!u.empty()) { ------------------ | Branch (631:7): [True: 31.1k, False: 0] ------------------ 632| 31.1k| u[0] = lower_utf(u[0], langnum); 633| 31.1k| } 634| 31.1k| return u; 635| 31.1k|} _Z14get_current_csRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 2293| 2.22k|const struct cs_info* get_current_cs(const std::string& es) { 2294| 2.22k| char* normalized_encoding = new char[es.size() + 1]; 2295| 2.22k| toAsciiLowerAndRemoveNonAlphanumeric(es.c_str(), normalized_encoding); 2296| | 2297| 2.22k| const struct cs_info* ccs = nullptr; 2298| 2.22k| for (const auto& encd : encds) { ------------------ | Branch (2298:25): [True: 2.22k, False: 0] ------------------ 2299| 2.22k| if (strcmp(normalized_encoding, encd.enc_name) == 0) { ------------------ | Branch (2299:9): [True: 2.22k, False: 0] ------------------ 2300| 2.22k| ccs = encd.cs_table; 2301| 2.22k| break; 2302| 2.22k| } 2303| 2.22k| } 2304| | 2305| 2.22k| delete[] normalized_encoding; 2306| | 2307| 2.22k| if (!ccs) { ------------------ | Branch (2307:7): [True: 0, False: 2.22k] ------------------ 2308| 0| HUNSPELL_WARNING(stderr, 2309| 0| "error: unknown encoding %s: using %s as fallback\n", es.c_str(), 2310| 0| encds[0].enc_name); 2311| 0| ccs = encds[0].cs_table; 2312| 0| } 2313| | 2314| 2.22k| return ccs; 2315| 2.22k|} _Z12get_lang_numRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEE: 2445| 4|int get_lang_num(const std::string& lang) { 2446| 72| for (const auto& i : lang2enc) { ------------------ | Branch (2446:22): [True: 72, False: 0] ------------------ 2447| 72| if (strcmp(lang.c_str(), i.lang) == 0) { ------------------ | Branch (2447:9): [True: 4, False: 68] ------------------ 2448| 4| return i.num; 2449| 4| } 2450| 72| } 2451| 0| return LANG_xx; 2452| 4|} _Z14unicodetoupperti: 2454| 26.6M|unsigned short unicodetoupper(unsigned short c, int langnum) { 2455| | // In Azeri and Turkish, I and i dictinct letters: 2456| | // There are a dotless lower case i pair of upper `I', 2457| | // and an upper I with dot pair of lower `i'. 2458| 26.6M| if (c == 0x0069 && ((langnum == LANG_az) || (langnum == LANG_tr) || (langnum == LANG_crh))) ------------------ | Branch (2458:7): [True: 219k, False: 26.4M] | Branch (2458:23): [True: 0, False: 219k] | Branch (2458:47): [True: 0, False: 219k] | Branch (2458:71): [True: 0, False: 219k] ------------------ 2459| 0| return 0x0130; 2460| |#ifdef OPENOFFICEORG 2461| | return static_cast(u_toupper(c)); 2462| |#else 2463| |#ifdef MOZILLA_CLIENT 2464| | return ToUpperCase((char16_t)c); 2465| |#else 2466| 26.6M| unsigned short up = utf_pages[utf_page_index[c >> 8]][c & 0xFF].cupper; 2467| 26.6M| return up ? up : c; ------------------ | Branch (2467:10): [True: 4.25M, False: 22.4M] ------------------ 2468| 26.6M|#endif 2469| 26.6M|#endif 2470| 26.6M|} _Z14unicodetolowerti: 2472| 29.8M|unsigned short unicodetolower(unsigned short c, int langnum) { 2473| | // In Azeri and Turkish, I and i dictinct letters: 2474| | // There are a dotless lower case i pair of upper `I', 2475| | // and an upper I with dot pair of lower `i'. 2476| 29.8M| if (c == 0x0049 && ((langnum == LANG_az) || (langnum == LANG_tr) || (langnum == LANG_crh))) ------------------ | Branch (2476:7): [True: 131k, False: 29.6M] | Branch (2476:23): [True: 0, False: 131k] | Branch (2476:47): [True: 0, False: 131k] | Branch (2476:71): [True: 0, False: 131k] ------------------ 2477| 0| return 0x0131; 2478| |#ifdef OPENOFFICEORG 2479| | return static_cast(u_tolower(c)); 2480| |#else 2481| |#ifdef MOZILLA_CLIENT 2482| | return ToLowerCase((char16_t)c); 2483| |#else 2484| 29.8M| unsigned short lo = utf_pages[utf_page_index[c >> 8]][c & 0xFF].clower; 2485| 29.8M| return lo ? lo : c; ------------------ | Branch (2485:10): [True: 2.61M, False: 27.1M] ------------------ 2486| 29.8M|#endif 2487| 29.8M|#endif 2488| 29.8M|} _Z11get_captypeRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEPK7cs_info: 2499| 10.1M|int get_captype(const std::string& word, const cs_info* csconv) { 2500| | // now determine the capitalization type of the first nl letters 2501| 10.1M| size_t ncap = 0; 2502| 10.1M| size_t nneutral = 0; 2503| 10.1M| size_t firstcap = 0; 2504| 10.1M| if (csconv == nullptr) ------------------ | Branch (2504:7): [True: 0, False: 10.1M] ------------------ 2505| 0| return NOCAP; ------------------ | | 92| 0|#define NOCAP 0 ------------------ 2506| 107M| for (char q : word) { ------------------ | Branch (2506:15): [True: 107M, False: 10.1M] ------------------ 2507| 107M| const auto nIndex = static_cast(q); 2508| 107M| if (ccase(csconv, nIndex)) ------------------ | Branch (2508:9): [True: 4.04M, False: 103M] ------------------ 2509| 4.04M| ncap++; 2510| 107M| if (cupper(csconv, nIndex) == clower(csconv, nIndex)) ------------------ | Branch (2510:9): [True: 84.6M, False: 23.0M] ------------------ 2511| 84.6M| nneutral++; 2512| 107M| } 2513| 10.1M| if (ncap) { ------------------ | Branch (2513:7): [True: 1.75M, False: 8.37M] ------------------ 2514| 1.75M| const auto nIndex = static_cast(word[0]); 2515| 1.75M| firstcap = csconv[nIndex].ccase; 2516| 1.75M| } 2517| | 2518| | // now finally set the captype 2519| 10.1M| if (ncap == 0) { ------------------ | Branch (2519:7): [True: 8.37M, False: 1.75M] ------------------ 2520| 8.37M| return NOCAP; ------------------ | | 92| 8.37M|#define NOCAP 0 ------------------ 2521| 8.37M| } else if ((ncap == 1) && firstcap) { ------------------ | Branch (2521:14): [True: 1.01M, False: 739k] | Branch (2521:29): [True: 488k, False: 523k] ------------------ 2522| 488k| return INITCAP; ------------------ | | 93| 488k|#define INITCAP 1 ------------------ 2523| 1.26M| } else if ((ncap == word.size()) || ((ncap + nneutral) == word.size())) { ------------------ | Branch (2523:14): [True: 8.08k, False: 1.25M] | Branch (2523:39): [True: 244k, False: 1.01M] ------------------ 2524| 252k| return ALLCAP; ------------------ | | 94| 252k|#define ALLCAP 2 ------------------ 2525| 1.01M| } else if ((ncap > 1) && firstcap) { ------------------ | Branch (2525:14): [True: 594k, False: 415k] | Branch (2525:28): [True: 221k, False: 373k] ------------------ 2526| 221k| return HUHINITCAP; ------------------ | | 96| 221k|#define HUHINITCAP 4 ------------------ 2527| 221k| } 2528| 788k| return HUHCAP; ------------------ | | 95| 788k|#define HUHCAP 3 ------------------ 2529| 10.1M|} _Z16get_captype_utf8RKNSt3__16vectorI6w_charNS_9allocatorIS1_EEEEi: 2531| 2.79M|int get_captype_utf8(const std::vector& word, int langnum) { 2532| | // now determine the capitalization type of the first nl letters 2533| 2.79M| size_t ncap = 0; 2534| 2.79M| size_t nneutral = 0; 2535| 2.79M| size_t firstcap = 0; 2536| | 2537| 2.79M| auto it = word.begin(), it_end = word.end(); 2538| 25.4M| while (it != it_end) { ------------------ | Branch (2538:10): [True: 22.6M, False: 2.79M] ------------------ 2539| 22.6M| const auto idx = (unsigned short)*it; 2540| 22.6M| const auto lwridx = unicodetolower(idx, langnum); 2541| 22.6M| if (idx != lwridx) ------------------ | Branch (2541:9): [True: 1.12M, False: 21.5M] ------------------ 2542| 1.12M| ncap++; 2543| 22.6M| if (unicodetoupper(idx, langnum) == lwridx) ------------------ | Branch (2543:9): [True: 18.2M, False: 4.38M] ------------------ 2544| 18.2M| nneutral++; 2545| 22.6M| ++it; 2546| 22.6M| } 2547| 2.79M| if (ncap) { ------------------ | Branch (2547:7): [True: 355k, False: 2.43M] ------------------ 2548| 355k| const auto idx = (unsigned short)word[0]; 2549| 355k| firstcap = (idx != unicodetolower(idx, langnum)); 2550| 355k| } 2551| | 2552| | // now finally set the captype 2553| 2.79M| if (ncap == 0) { ------------------ | Branch (2553:7): [True: 2.43M, False: 355k] ------------------ 2554| 2.43M| return NOCAP; ------------------ | | 92| 2.43M|#define NOCAP 0 ------------------ 2555| 2.43M| } else if ((ncap == 1) && firstcap) { ------------------ | Branch (2555:14): [True: 210k, False: 144k] | Branch (2555:29): [True: 109k, False: 101k] ------------------ 2556| 109k| return INITCAP; ------------------ | | 93| 109k|#define INITCAP 1 ------------------ 2557| 246k| } else if ((ncap == word.size()) || ((ncap + nneutral) == word.size())) { ------------------ | Branch (2557:14): [True: 4.51k, False: 241k] | Branch (2557:39): [True: 76.6k, False: 164k] ------------------ 2558| 81.2k| return ALLCAP; ------------------ | | 94| 81.2k|#define ALLCAP 2 ------------------ 2559| 164k| } else if ((ncap > 1) && firstcap) { ------------------ | Branch (2559:14): [True: 88.1k, False: 76.6k] | Branch (2559:28): [True: 31.6k, False: 56.5k] ------------------ 2560| 31.6k| return HUHINITCAP; ------------------ | | 96| 31.6k|#define HUHINITCAP 4 ------------------ 2561| 31.6k| } 2562| 133k| return HUHCAP; ------------------ | | 95| 133k|#define HUHCAP 3 ------------------ 2563| 2.79M|} _Z24remove_ignored_chars_utfRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKNS_6vectorI6w_charNS3_IS8_EEEE: 2567| 685k| const std::vector& ignored_chars) { 2568| 685k| std::vector w; 2569| 685k| std::vector w2; 2570| 685k| u8_u16(w, word); 2571| | 2572| 685k| std::copy_if(w.begin(), w.end(), std::back_inserter(w2), 2573| 685k| [&ignored_chars](w_char wc) { 2574| 685k| return !std::binary_search(ignored_chars.begin(), ignored_chars.end(), wc); 2575| 685k| }); 2576| | 2577| 685k| u16_u8(word, w2); 2578| 685k| return w2.size(); 2579| 685k|} _Z20remove_ignored_charsRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKS5_: 2583| 2.16M| const std::string& ignored_chars) { 2584| 2.16M| word.erase( 2585| 2.16M| std::remove_if(word.begin(), word.end(), is_any_of(ignored_chars)), 2586| 2.16M| word.end()); 2587| 2.16M| return word.size(); 2588| 2.16M|} _Z12parse_stringRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERS5_i: 2590| 90|bool parse_string(const std::string& line, std::string& out, int ln) { 2591| 90| if (!out.empty()) { ------------------ | Branch (2591:7): [True: 0, False: 90] ------------------ 2592| 0| HUNSPELL_WARNING(stderr, "error: line %d: multiple definitions\n", ln); 2593| 0| return false; 2594| 0| } 2595| 90| int i = 0; 2596| 90| int np = 0; 2597| 90| auto iter = line.begin(), start_piece = mystrsep(line, iter); 2598| 270| while (start_piece != line.end()) { ------------------ | Branch (2598:10): [True: 180, False: 90] ------------------ 2599| 180| switch (i) { 2600| 90| case 0: { ------------------ | Branch (2600:7): [True: 90, False: 90] ------------------ 2601| 90| np++; 2602| 90| break; 2603| 0| } 2604| 90| case 1: { ------------------ | Branch (2604:7): [True: 90, False: 90] ------------------ 2605| 90| out.assign(start_piece, iter); 2606| 90| np++; 2607| 90| break; 2608| 0| } 2609| 0| default: ------------------ | Branch (2609:7): [True: 0, False: 180] ------------------ 2610| 0| break; 2611| 180| } 2612| 180| ++i; 2613| 180| start_piece = mystrsep(line, iter); 2614| 180| } 2615| 90| if (np != 2) { ------------------ | Branch (2615:7): [True: 0, False: 90] ------------------ 2616| 0| HUNSPELL_WARNING(stderr, "error: line %d: missing data\n", ln); 2617| 0| return false; 2618| 0| } 2619| 90| return true; 2620| 90|} _Z11parse_arrayRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERS5_RNS_6vectorI6w_charNS3_ISA_EEEEii: 2626| 14| int ln) { 2627| 14| if (!parse_string(line, out, ln)) ------------------ | Branch (2627:7): [True: 0, False: 14] ------------------ 2628| 0| return false; 2629| 14| if (utf8) { ------------------ | Branch (2629:7): [True: 8, False: 6] ------------------ 2630| 8| u8_u16(out_utf16, out); 2631| 8| std::sort(out_utf16.begin(), out_utf16.end()); 2632| 8| } 2633| 14| return true; 2634| 14|} csutil.cxx:_ZL17warn_missing_contRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS_11__wrap_iterIPKcEE: 154| 687k|static void warn_missing_cont(const std::string& src, std::string::const_iterator p) { 155| | HUNSPELL_WARNING(stderr, 156| 687k| "UTF-8 encoding error. Missing continuation byte in " 157| 687k| "%ld. character position:\n%s\n", 158| 687k| static_cast(std::distance(src.begin(), p)), 159| 687k| src.c_str()); 160| 687k|} csutil.cxx:_ZN12_GLOBAL__N_19is_any_ofC2ERKNSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEE: 245| 2.16M| explicit is_any_of(const std::string& in) : chars(in) {} csutil.cxx:_ZNK12_GLOBAL__N_19is_any_ofclEc: 247| 24.3M| bool operator()(char c) const { return chars.find(c) != std::string::npos; } csutil.cxx:_ZL19drop_repeated_linesRNSt3__16vectorINS_12basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS4_IS6_EEEE: 303| 2.10k|static void drop_repeated_lines(std::vector& lines) { 304| 2.10k| std::unordered_set seen; 305| 2.10k| auto firstrepeat = std::remove_if(lines.begin(), lines.end(), 306| 2.10k| [&seen](const std::string& line) { return !seen.insert(line).second; }); 307| 2.10k| lines.erase(firstrepeat, lines.end()); 308| 2.10k|} csutil.cxx:_ZZL19drop_repeated_linesRNSt3__16vectorINS_12basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS4_IS6_EEEEENK3$_0clERKS6_: 306| 2.13k| [&seen](const std::string& line) { return !seen.insert(line).second; }); csutil.cxx:_ZN12_GLOBAL__N_16cupperEPK7cs_infoi: 515| 113M|unsigned char cupper(const struct cs_info* csconv, int nIndex) { 516| 113M| assert(nIndex >= 0 && nIndex <= 255); ------------------ | Branch (516:3): [True: 113M, False: 0] | Branch (516:3): [True: 113M, False: 0] | Branch (516:3): [True: 113M, False: 0] ------------------ 517| 113M| return csconv[nIndex].cupper; 518| 113M|} csutil.cxx:_ZN12_GLOBAL__N_16clowerEPK7cs_infoi: 520| 128M|unsigned char clower(const struct cs_info* csconv, int nIndex) { 521| 128M| assert(nIndex >= 0 && nIndex <= 255); ------------------ | Branch (521:3): [True: 128M, False: 0] | Branch (521:3): [True: 128M, False: 0] | Branch (521:3): [True: 128M, False: 0] ------------------ 522| 128M| return csconv[nIndex].clower; 523| 128M|} csutil.cxx:_ZL36toAsciiLowerAndRemoveNonAlphanumericPKcPc: 2273| 2.22k| char* pBuf) { 2274| 20.1k| while (*pName) { ------------------ | Branch (2274:10): [True: 17.9k, False: 2.22k] ------------------ 2275| | /* A-Z */ 2276| 17.9k| if ((*pName >= 0x41) && (*pName <= 0x5A)) { ------------------ | Branch (2276:9): [True: 6.68k, False: 11.2k] | Branch (2276:29): [True: 294, False: 6.39k] ------------------ 2277| 294| *pBuf = (*pName) + 0x20; /* toAsciiLower */ 2278| 294| pBuf++; 2279| 294| } 2280| | /* a-z, 0-9 */ 2281| 17.6k| else if (((*pName >= 0x61) && (*pName <= 0x7A)) || ------------------ | Branch (2281:15): [True: 6.39k, False: 11.2k] | Branch (2281:35): [True: 6.39k, False: 0] ------------------ 2282| 17.5k| ((*pName >= 0x30) && (*pName <= 0x39))) { ------------------ | Branch (2282:15): [True: 11.1k, False: 98] | Branch (2282:35): [True: 11.1k, False: 0] ------------------ 2283| 17.5k| *pBuf = *pName; 2284| 17.5k| pBuf++; 2285| 17.5k| } 2286| | 2287| 17.9k| pName++; 2288| 17.9k| } 2289| | 2290| 2.22k| *pBuf = '\0'; 2291| 2.22k|} csutil.cxx:_ZN12_GLOBAL__N_15ccaseEPK7cs_infoi: 525| 107M|unsigned char ccase(const struct cs_info* csconv, int nIndex) { 526| 107M| assert(nIndex >= 0 && nIndex <= 255); ------------------ | Branch (526:3): [True: 107M, False: 0] | Branch (526:3): [True: 107M, False: 0] | Branch (526:3): [True: 107M, False: 0] ------------------ 527| 107M| return csconv[nIndex].ccase; 528| 107M|} csutil.cxx:_ZZ24remove_ignored_chars_utfRNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEERKNS_6vectorI6w_charNS3_IS8_EEEEENK3$_0clES8_: 2573| 5.81M| [&ignored_chars](w_char wc) { 2574| 5.81M| return !std::binary_search(ignored_chars.begin(), ignored_chars.end(), wc); 2575| 5.81M| }); _Z12is_utf8_contc: 143| 54.0M|inline bool is_utf8_cont(char c) { 144| 54.0M| return (static_cast(c) & 0xc0) == 0x80; 145| 54.0M|} _Z9utf8_nextRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEEm: 148| 22.0k|inline size_t utf8_next(const std::string& s, size_t pos) { 149| 22.0k| if (pos < s.size()) { ------------------ | Branch (149:7): [True: 22.0k, False: 0] ------------------ 150| 22.0k| ++pos; 151| 25.9k| while (pos < s.size() && is_utf8_cont(s[pos])) ------------------ | Branch (151:12): [True: 23.6k, False: 2.28k] | Branch (151:30): [True: 3.93k, False: 19.7k] ------------------ 152| 3.93k| ++pos; 153| 22.0k| } 154| 22.0k| return pos; 155| 22.0k|} _Z20has_no_ignored_charsRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEES7_: 295| 799| const std::string& ignored_chars) { 296| 799| return std::all_of(ignored_chars.begin(), ignored_chars.end(), 297| 799| [&word](char ic) { return word.find(ic) == std::string::npos; }); 298| 799|} _Z11HENTRY_DATAP6hentry: 301| 1.37M|inline char* HENTRY_DATA(struct hentry* h) { 302| 1.37M| char* ret; 303| 1.37M| if (!(h->var & H_OPT)) ------------------ | | 47| 1.37M|#define H_OPT (1 << 0) // is there optional morphological data? ------------------ | Branch (303:7): [True: 1.37M, False: 1.64k] ------------------ 304| 1.37M| ret = nullptr; 305| 1.64k| else if (h->var & H_OPT_ALIASM) ------------------ | | 48| 1.64k|#define H_OPT_ALIASM (1 << 1) // using alias compression? ------------------ | Branch (305:12): [True: 0, False: 1.64k] ------------------ 306| 0| ret = get_stored_pointer(HENTRY_WORD(h) + h->blen + 1); ------------------ | | 54| 0|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 307| 1.64k| else 308| 1.64k| ret = HENTRY_WORD(h) + h->blen + 1; ------------------ | | 54| 1.64k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 309| 1.37M| return ret; 310| 1.37M|} _Z11HENTRY_FINDP6hentryPKc: 337| 2.12k|inline char* HENTRY_FIND(struct hentry* h, const char* p) { 338| 2.12k| char* data = HENTRY_DATA(h); 339| 2.12k| return data ? strstr(data, p) : nullptr; ------------------ | Branch (339:10): [True: 4, False: 2.12k] ------------------ 340| 2.12k|} _ZZ20has_no_ignored_charsRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEES7_ENKUlcE_clEc: 297| 6.14k| [&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| 383|void HashMgr::release_flags(unsigned short* astr, bool owned) { 113| 383| if (owned) ------------------ | Branch (113:7): [True: 206, False: 177] ------------------ 114| 206| delete[] astr; 115| 383|} _ZNK7HashMgr6lookupEPKcm: 154| 512M|struct hentry* HashMgr::lookup(const char* word, size_t len) const { 155| 512M| struct hentry* dp = tableptr[hash(word, len)]; 156| 512M| if (!dp) ------------------ | Branch (156:7): [True: 460M, False: 51.7M] ------------------ 157| 460M| return nullptr; 158| 107M| for (; dp != nullptr; dp = dp->next) { ------------------ | Branch (158:10): [True: 59.0M, False: 48.7M] ------------------ 159| 59.0M| if (strcmp(word, dp->word) == 0) ------------------ | Branch (159:9): [True: 2.97M, False: 56.0M] ------------------ 160| 2.97M| return dp; 161| 59.0M| } 162| 48.7M| return nullptr; 163| 51.7M|} _ZN7HashMgr8add_wordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiPtiPS7_bib: 173| 7.79k| bool own_aff) { 174| | 175| 7.79k| if (al > std::numeric_limits::max()) { ------------------ | Branch (175:7): [True: 0, False: 7.79k] ------------------ 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| 7.79k| const std::string* word = &in_word; 182| 7.79k| const std::string* desc = in_desc; 183| | 184| 7.79k| std::string* word_copy = nullptr; 185| 7.79k| std::string* desc_copy = nullptr; 186| 7.79k| if ((!ignorechars.empty() && !has_no_ignored_chars(in_word, ignorechars)) || complexprefixes) { ------------------ | Branch (186:8): [True: 795, False: 7.00k] | Branch (186:32): [True: 181, False: 614] | Branch (186:80): [True: 476, False: 7.14k] ------------------ 187| 657| word_copy = new std::string(in_word); 188| | 189| 657| if (!ignorechars.empty()) { ------------------ | Branch (189:9): [True: 181, False: 476] ------------------ 190| 181| if (utf8) { ------------------ | Branch (190:11): [True: 39, False: 142] ------------------ 191| 39| wcl = remove_ignored_chars_utf(*word_copy, ignorechars_utf16); 192| 142| } else { 193| 142| remove_ignored_chars(*word_copy, ignorechars); 194| 142| } 195| 181| } 196| | 197| 657| if (complexprefixes) { ------------------ | Branch (197:9): [True: 476, False: 181] ------------------ 198| 476| if (utf8) ------------------ | Branch (198:11): [True: 0, False: 476] ------------------ 199| 0| wcl = reverseword_utf(*word_copy); 200| 476| else 201| 476| reverseword(*word_copy); 202| | 203| 476| if (in_desc && aliasm.empty()) { ------------------ | Branch (203:11): [True: 0, False: 476] | 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| 476| } 215| | 216| 657| word = word_copy; 217| 657| } 218| | 219| | // limit of hp->blen 220| 7.79k| if (word->size() > std::numeric_limits::max()) { ------------------ | Branch (220:7): [True: 0, False: 7.79k] ------------------ 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| 7.79k| bool upcasehomonym = false; 229| 7.79k| int descl = desc ? (!aliasm.empty() ? sizeof(char*) : desc->size() + 1) : 0; ------------------ | Branch (229:15): [True: 4, False: 7.79k] | Branch (229:23): [True: 0, False: 4] ------------------ 230| | // variable-length hash record with word and optional fields 231| 7.79k| auto hp = 232| 7.79k| (struct hentry*)arena_alloc(sizeof(struct hentry) + word->size() + descl, 233| 7.79k| alignof(struct hentry)); 234| 7.79k| if (!hp) { ------------------ | Branch (234:7): [True: 0, False: 7.79k] ------------------ 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| 7.79k| char* hpw = hp->word; 242| 7.79k| memcpy(hpw, word->data(), word->size()); 243| 7.79k| hpw[word->size()] = 0; 244| | 245| 7.79k| int i = hash(hpw, word->size()); 246| | 247| 7.79k| hp->blen = (unsigned short)word->size(); 248| 7.79k| hp->clen = (unsigned short)wcl; 249| 7.79k| hp->alen = (short)al; 250| 7.79k| hp->astr = aff; 251| 7.79k| hp->next = nullptr; 252| 7.79k| hp->next_homonym = nullptr; 253| 7.79k| hp->var = (captype == INITCAP) ? H_OPT_INITCAP : 0; ------------------ | | 93| 7.79k|#define INITCAP 1 ------------------ hp->var = (captype == INITCAP) ? H_OPT_INITCAP : 0; ------------------ | | 50| 4.74k|#define H_OPT_INITCAP (1 << 3) // is dictionary word capitalized? ------------------ | Branch (253:13): [True: 4.74k, False: 3.05k] ------------------ 254| 7.79k| if (own_aff) ------------------ | Branch (254:7): [True: 5.23k, False: 2.56k] ------------------ 255| 5.23k| hp->var |= H_OPT_OWNFLAGS; ------------------ | | 51| 5.23k|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 256| | 257| | // store the description string or its pointer 258| 7.79k| if (desc) { ------------------ | Branch (258:7): [True: 4, False: 7.79k] ------------------ 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| 7.79k| struct hentry* dp = tableptr[i]; 370| 7.79k| if (!dp) { ------------------ | Branch (370:7): [True: 6.05k, False: 1.74k] ------------------ 371| 6.05k| tableptr[i] = hp; 372| 6.05k| delete desc_copy; 373| 6.05k| delete word_copy; 374| 6.05k| return 0; 375| 6.05k| } 376| 2.16k| while (dp->next != nullptr) { ------------------ | Branch (376:10): [True: 455, False: 1.71k] ------------------ 377| 455| if ((!dp->next_homonym) && (strcmp(hp->word, dp->word) == 0)) { ------------------ | Branch (377:9): [True: 392, False: 63] | Branch (377:32): [True: 43, False: 349] ------------------ 378| | // remove hidden onlyupcase homonym 379| 43| if (!onlyupcase) { ------------------ | Branch (379:11): [True: 32, False: 11] ------------------ 380| 32| if ((dp->astr) && TESTAFF(dp->astr, ONLYUPCASEFLAG, dp->alen)) { ------------------ | | 99| 8|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 8, False: 0] | | ------------------ ------------------ | Branch (380:13): [True: 8, False: 24] | Branch (380:13): [True: 8, False: 24] ------------------ 381| 8| release_flags(dp->astr, dp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 8|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 382| 8| dp->astr = hp->astr; 383| 8| dp->alen = hp->alen; 384| 8| dp->var &= ~H_OPT_OWNFLAGS; ------------------ | | 51| 8|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 385| 8| dp->var |= (hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 8|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 386| 8| arena_free(hp); 387| 8| delete desc_copy; 388| 8| delete word_copy; 389| 8| return 0; 390| 24| } else if (!dp->astr && dp->alen == 0 && ------------------ | Branch (390:20): [True: 24, False: 0] | Branch (390:33): [True: 24, False: 0] ------------------ 391| 24| !hp->astr && hp->alen == 0) { ------------------ | Branch (391:20): [True: 24, False: 0] | Branch (391:33): [True: 24, False: 0] ------------------ 392| | // word already exists with no flags, skip duplicate 393| 24| release_flags(hp->astr, hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 24|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 394| 24| arena_free(hp); 395| 24| delete desc_copy; 396| 24| delete word_copy; 397| 24| return 0; 398| 24| } else { 399| 0| dp->next_homonym = hp; 400| 0| } 401| 32| } else { 402| 11| upcasehomonym = true; 403| 11| } 404| 43| } 405| 423| dp = dp->next; 406| 423| } 407| 1.71k| if (strcmp(hp->word, dp->word) == 0) { ------------------ | Branch (407:7): [True: 358, False: 1.35k] ------------------ 408| | // remove hidden onlyupcase homonym 409| 358| if (!onlyupcase) { ------------------ | Branch (409:9): [True: 220, False: 138] ------------------ 410| 220| if ((dp->astr) && TESTAFF(dp->astr, ONLYUPCASEFLAG, dp->alen)) { ------------------ | | 99| 56|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 56, False: 0] | | ------------------ ------------------ | Branch (410:11): [True: 56, False: 164] | Branch (410:11): [True: 56, False: 164] ------------------ 411| 56| release_flags(dp->astr, dp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 56|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 412| 56| dp->astr = hp->astr; 413| 56| dp->alen = hp->alen; 414| 56| dp->var &= ~H_OPT_OWNFLAGS; ------------------ | | 51| 56|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 415| 56| dp->var |= (hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 56|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 416| 56| arena_free(hp); 417| 56| delete desc_copy; 418| 56| delete word_copy; 419| 56| return 0; 420| 164| } else if (!dp->astr && dp->alen == 0 && ------------------ | Branch (420:18): [True: 164, False: 0] | Branch (420:31): [True: 164, False: 0] ------------------ 421| 164| !hp->astr && hp->alen == 0) { ------------------ | Branch (421:18): [True: 146, False: 18] | Branch (421:31): [True: 146, False: 0] ------------------ 422| | // word already exists with no flags, skip duplicate 423| 146| release_flags(hp->astr, hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 146|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 424| 146| arena_free(hp); 425| 146| delete desc_copy; 426| 146| delete word_copy; 427| 146| return 0; 428| 146| } else { 429| 18| dp->next_homonym = hp; 430| 18| } 431| 220| } else { 432| 138| upcasehomonym = true; 433| 138| } 434| 358| } 435| 1.50k| if (!upcasehomonym) { ------------------ | Branch (435:7): [True: 1.35k, False: 149] ------------------ 436| 1.35k| dp->next = hp; 437| 1.35k| } else { 438| | // remove hidden onlyupcase homonym 439| 149| release_flags(hp->astr, hp->var & H_OPT_OWNFLAGS); ------------------ | | 51| 149|#define H_OPT_OWNFLAGS (1 << 4) // astr is independently allocated? ------------------ 440| 149| arena_free(hp); 441| 149| } 442| | 443| 1.50k| delete desc_copy; 444| 1.50k| delete word_copy; 445| 1.50k| return 0; 446| 1.71k|} _ZN7HashMgr27add_hidden_capitalized_wordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiPtiPS7_i: 453| 5.39k| int captype) { 454| 5.39k| if (flags == nullptr) ------------------ | Branch (454:7): [True: 5.26k, False: 136] ------------------ 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| 5.39k| if (((captype == HUHCAP) || (captype == HUHINITCAP) || ------------------ | | 95| 5.39k|#define HUHCAP 3 ------------------ if (((captype == HUHCAP) || (captype == HUHINITCAP) || ------------------ | | 96| 5.01k|#define HUHINITCAP 4 ------------------ | Branch (460:8): [True: 382, False: 5.01k] | Branch (460:31): [True: 2.01k, False: 3.00k] ------------------ 461| 3.00k| ((captype == ALLCAP) && (flagslen != 0))) && ------------------ | | 94| 3.00k|#define ALLCAP 2 ------------------ | Branch (461:9): [True: 187, False: 2.81k] | Branch (461:32): [True: 9, False: 178] ------------------ 462| 2.40k| !((flagslen != 0) && TESTAFF(flags, forbiddenword, flagslen))) { ------------------ | | 99| 54|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 54] | | ------------------ ------------------ | Branch (462:9): [True: 54, False: 2.34k] ------------------ 463| 2.40k| auto flags2 = (unsigned short*)arena_alloc((flagslen + 1) * sizeof(unsigned short), 464| 2.40k| alignof(unsigned short)); 465| 2.40k| flags2[flagslen] = ONLYUPCASEFLAG; ------------------ | | 128| 2.40k|#define ONLYUPCASEFLAG 65511 ------------------ 466| 2.40k| if (flagslen) { ------------------ | Branch (466:9): [True: 54, False: 2.34k] ------------------ 467| 54| memcpy(flags2, flags, flagslen * sizeof(unsigned short)); 468| 54| std::sort(flags2, flags2 + flagslen + 1); 469| 54| } 470| 2.40k| if (utf8) { ------------------ | Branch (470:9): [True: 360, False: 2.04k] ------------------ 471| 360| std::string st; 472| 360| std::vector w; 473| 360| u8_u16(w, word); 474| 360| mkallsmall_utf(w, langnum); 475| 360| mkinitcap_utf(w, langnum); 476| 360| u16_u8(st, w); 477| 360| return add_word(st, wcl, flags2, flagslen + 1, dp, true, INITCAP, false); ------------------ | | 93| 360|#define INITCAP 1 ------------------ 478| 2.04k| } else { 479| 2.04k| std::string new_word(word); 480| 2.04k| mkallsmall(new_word, csconv); 481| 2.04k| mkinitcap(new_word, csconv); 482| 2.04k| int ret = add_word(new_word, wcl, flags2, flagslen + 1, dp, true, INITCAP, false); ------------------ | | 93| 2.04k|#define INITCAP 1 ------------------ 483| 2.04k| return ret; 484| 2.04k| } 485| 2.40k| } 486| 2.99k| return 0; 487| 5.39k|} _ZN7HashMgr20get_clen_and_captypeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiRNS0_6vectorI6w_charNS4_ISB_EEEE: 490| 5.39k|int HashMgr::get_clen_and_captype(const std::string& word, int* captype, std::vector &workbuf) { 491| 5.39k| int len; 492| 5.39k| if (utf8) { ------------------ | Branch (492:7): [True: 2.55k, False: 2.84k] ------------------ 493| 2.55k| len = u8_u16(workbuf, word); 494| 2.55k| *captype = get_captype_utf8(workbuf, langnum); 495| 2.84k| } else { 496| 2.84k| len = word.size(); 497| 2.84k| *captype = get_captype(word, csconv); 498| 2.84k| } 499| 5.39k| return len; 500| 5.39k|} _ZN7HashMgr20get_clen_and_captypeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPi: 502| 5.23k|int HashMgr::get_clen_and_captype(const std::string& word, int* captype) { 503| 5.23k| std::vector workbuf; 504| 5.23k| return get_clen_and_captype(word, captype, workbuf); 505| 5.23k|} _ZN7HashMgr21remove_forbidden_flagERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 528| 7.21k|void HashMgr::remove_forbidden_flag(const std::string& word) { 529| 7.21k| struct hentry* dp = lookup(word.c_str(), word.size()); 530| 7.21k| if (!dp) ------------------ | Branch (530:7): [True: 6.77k, False: 438] ------------------ 531| 6.77k| return; 532| 948| while (dp) { ------------------ | Branch (532:10): [True: 510, False: 438] ------------------ 533| 510| if (dp->astr && TESTAFF(dp->astr, forbiddenword, dp->alen)) { ------------------ | | 99| 71|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 71] | | ------------------ ------------------ | Branch (533:9): [True: 71, False: 439] ------------------ 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| 510| dp = dp->next_homonym; 553| 510| } 554| 438|} _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| 2.03k|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| 2.03k| struct hentry* dp = lookup(example.c_str(), example.size()); 581| 2.03k| remove_forbidden_flag(word); 582| 2.03k| if (dp && dp->astr) { ------------------ | Branch (582:7): [True: 254, False: 1.77k] | Branch (582:13): [True: 54, False: 200] ------------------ 583| 54| int captype; 584| 54| int wcl = get_clen_and_captype(word, &captype); 585| 54| auto flags = new unsigned short[dp->alen]; 586| 54| memcpy(flags, dp->astr, dp->alen * sizeof(unsigned short)); 587| 54| if (add_word(word, wcl, flags, dp->alen, nullptr, false, captype, true)) ------------------ | Branch (587:9): [True: 0, False: 54] ------------------ 588| 0| return 1; 589| 54| return add_hidden_capitalized_word(word, wcl, flags, dp->alen, nullptr, captype); 590| 54| } 591| 1.97k| return 1; 592| 2.03k|} _ZNK7HashMgr14walk_hashtableERiP6hentry: 596| 1.92M|struct hentry* HashMgr::walk_hashtable(int& col, struct hentry* hp) const { 597| 1.92M| if (hp && hp->next != nullptr) ------------------ | Branch (597:7): [True: 1.86M, False: 59.9k] | Branch (597:13): [True: 155k, False: 1.71M] ------------------ 598| 155k| return hp->next; 599| 60.5M| for (col++; col < (int)tableptr.size(); ++col) { ------------------ | Branch (599:15): [True: 60.4M, False: 59.9k] ------------------ 600| 60.4M| if (tableptr[col]) ------------------ | Branch (600:9): [True: 1.71M, False: 58.7M] ------------------ 601| 1.71M| return tableptr[col]; 602| 60.4M| } 603| | // null at end and reset to start 604| 59.9k| col = -1; 605| 59.9k| return nullptr; 606| 1.77M|} _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| 512M|int HashMgr::hash(const char* word, size_t len) const { 763| 512M| unsigned long hv = 0; 764| 512M| size_t i = 0; 765| 2.53G| while (i < 4 && i < len) ------------------ | Branch (765:10): [True: 2.04G, False: 487M] | Branch (765:19): [True: 2.01G, False: 24.7M] ------------------ 766| 2.01G| hv = (hv << 8) | word[i++]; 767| 9.97G| while (i < len) { ------------------ | Branch (767:10): [True: 9.46G, False: 512M] ------------------ 768| 9.46G| ROTATE(hv, ROTATE_LEN); ------------------ | | 44| 9.46G| (v) = ((v) << (q)) | (((v) >> (32 - q)) & ((1 << (q)) - 1)); ------------------ 769| 9.46G| hv ^= word[i++]; 770| 9.46G| } 771| 512M| return (unsigned long)hv % tableptr.size(); 772| 512M|} _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| 362k|const std::vector& HashMgr::get_reptable() const { 1437| 362k| return reptable; 1438| 362k|} _ZNK7HashMgr11arena_allocEmm: 1440| 10.2k|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| 10.2k| static const size_t MIN_CHUNK_SIZE = 65536; 1445| 10.2k| 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| 10.2k| assert(alignment > 0 && alignment <= MAX_ALIGNMENT); ------------------ | Branch (1448:3): [True: 10.2k, False: 0] | Branch (1448:3): [True: 10.2k, False: 0] | Branch (1448:3): [True: 10.2k, 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| 10.2k| size_t aligned_offset = (current_chunk_offset + alignment - 1) & ~(alignment - 1); 1452| 10.2k| if (arena.empty() || current_chunk_size - aligned_offset < num_bytes) { ------------------ | Branch (1452:7): [True: 38, False: 10.2k] | Branch (1452:24): [True: 76, False: 10.1k] ------------------ 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| 114| size_t new_size = std::max(MIN_CHUNK_SIZE, num_bytes); 1459| 114| new_size = (new_size + MAX_ALIGNMENT - 1) & ~(MAX_ALIGNMENT - 1); 1460| 114| arena.push_back(std::make_unique(new_size)); 1461| 114| current_chunk_size = new_size; 1462| 114| aligned_offset = 0; 1463| 114| } 1464| | 1465| 10.2k| uint8_t* ptr = &arena.back()[aligned_offset]; 1466| 10.2k| current_chunk_offset = aligned_offset + num_bytes; 1467| 10.2k| ++outstanding_arena_allocations; 1468| 10.2k| return ptr; 1469| 10.2k|} _ZNK7HashMgr10arena_freeEPv: 1471| 383|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| 383| if (outstanding_arena_allocations == 0) { ------------------ | Branch (1477:7): [True: 0, False: 383] ------------------ 1478| 0| std::abort(); 1479| 0| } 1480| 383| --outstanding_arena_allocations; 1481| 383|} 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| 29.2M| const std::string& src) { 236| 29.2M| dest.clear(); 237| 29.2M| dest.assign(src); 238| 29.2M| const char* ignoredchars = pAMgr ? pAMgr->get_ignore() : nullptr; ------------------ | Branch (238:30): [True: 29.2M, False: 0] ------------------ 239| 29.2M| if (ignoredchars != nullptr) { ------------------ | Branch (239:7): [True: 2.84M, False: 26.4M] ------------------ 240| 2.84M| if (utf8) { ------------------ | Branch (240:9): [True: 684k, False: 2.16M] ------------------ 241| 684k| const std::vector& ignoredchars_utf16 = 242| 684k| pAMgr->get_ignore_utf16(); 243| 684k| remove_ignored_chars_utf(dest, ignoredchars_utf16); 244| 2.16M| } else { 245| 2.16M| remove_ignored_chars(dest, ignoredchars); 246| 2.16M| } 247| 2.84M| } 248| 29.2M|} _ZN12HunspellImpl10cleanword2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEERKS6_PiPm: 262| 13.3M| size_t* pabbrev) { 263| 13.3M| dest.clear(); 264| 13.3M| dest_utf.clear(); 265| | 266| | // remove IGNORE characters from the string 267| 13.3M| std::string w2; 268| 13.3M| clean_ignore(w2, src); 269| | 270| 13.3M| const char* q = w2.c_str(); 271| 13.3M| int nl = (int)w2.size(); 272| | 273| | // first skip over any leading blanks 274| 13.5M| while (*q == ' ') { ------------------ | Branch (274:10): [True: 183k, False: 13.3M] ------------------ 275| 183k| ++q; 276| 183k| nl--; 277| 183k| } 278| | 279| | // now strip off any trailing periods (recording their presence) 280| 13.3M| *pabbrev = 0; 281| | 282| 15.8M| while ((nl > 0) && (*(q + nl - 1) == '.')) { ------------------ | Branch (282:10): [True: 15.3M, False: 479k] | Branch (282:22): [True: 2.48M, False: 12.9M] ------------------ 283| 2.48M| nl--; 284| 2.48M| (*pabbrev)++; 285| 2.48M| } 286| | 287| | // if no characters are left it can't be capitalized 288| 13.3M| if (nl <= 0) { ------------------ | Branch (288:7): [True: 479k, False: 12.9M] ------------------ 289| 479k| *pcaptype = NOCAP; ------------------ | | 92| 479k|#define NOCAP 0 ------------------ 290| 479k| return 0; 291| 479k| } 292| | 293| 12.9M| dest.append(q, nl); 294| 12.9M| nl = dest.size(); 295| 12.9M| if (utf8) { ------------------ | Branch (295:7): [True: 2.78M, False: 10.1M] ------------------ 296| 2.78M| u8_u16(dest_utf, dest); 297| 2.78M| *pcaptype = get_captype_utf8(dest_utf, langnum); 298| 10.1M| } else { 299| 10.1M| *pcaptype = get_captype(dest, csconv); 300| 10.1M| } 301| 12.9M| return nl; 302| 13.3M|} _ZN12HunspellImpl9cleanwordERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKS6_PiSA_: 307| 5.35k| int* pabbrev) { 308| 5.35k| dest.clear(); 309| 5.35k| const unsigned char* q = (const unsigned char*)src.c_str(); 310| 5.35k| int firstcap = 0, nl = (int)src.size(); 311| | 312| | // first skip over any leading blanks 313| 9.17k| while (*q == ' ') { ------------------ | Branch (313:10): [True: 3.81k, False: 5.35k] ------------------ 314| 3.81k| ++q; 315| 3.81k| nl--; 316| 3.81k| } 317| | 318| | // now strip off any trailing periods (recording their presence) 319| 5.35k| *pabbrev = 0; 320| | 321| 17.5k| while ((nl > 0) && (*(q + nl - 1) == '.')) { ------------------ | Branch (321:10): [True: 17.3k, False: 171] | Branch (321:22): [True: 12.1k, False: 5.18k] ------------------ 322| 12.1k| nl--; 323| 12.1k| (*pabbrev)++; 324| 12.1k| } 325| | 326| | // if no characters are left it can't be capitalized 327| 5.35k| if (nl <= 0) { ------------------ | Branch (327:7): [True: 171, False: 5.18k] ------------------ 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| 5.18k| int ncap = 0; 334| 5.18k| int nneutral = 0; 335| 5.18k| int nc = 0; 336| | 337| 5.18k| if (!utf8) { ------------------ | Branch (337:7): [True: 2.74k, False: 2.44k] ------------------ 338| 690k| while (nl > 0) { ------------------ | Branch (338:12): [True: 687k, False: 2.74k] ------------------ 339| 687k| nc++; 340| 687k| if (csconv[(*q)].ccase) ------------------ | Branch (340:11): [True: 597k, False: 90.6k] ------------------ 341| 597k| ncap++; 342| 687k| if (csconv[(*q)].cupper == csconv[(*q)].clower) ------------------ | Branch (342:11): [True: 80.1k, False: 607k] ------------------ 343| 80.1k| nneutral++; 344| 687k| dest.push_back(*q++); 345| 687k| nl--; 346| 687k| } 347| | // remember to terminate the destination string 348| 2.74k| firstcap = csconv[static_cast(dest[0])].ccase; 349| 2.74k| } else { 350| 2.44k| std::vector t; 351| 2.44k| u8_u16(t, src); 352| 188k| for (auto& wc : t) { ------------------ | Branch (352:19): [True: 188k, False: 2.44k] ------------------ 353| 188k| const auto idx = (unsigned short)wc; 354| 188k| const auto low = unicodetolower(idx, langnum); 355| 188k| if (idx != low) ------------------ | Branch (355:11): [True: 130k, False: 57.9k] ------------------ 356| 130k| ncap++; 357| 188k| if (unicodetoupper(idx, langnum) == low) ------------------ | Branch (357:11): [True: 54.9k, False: 134k] ------------------ 358| 54.9k| nneutral++; 359| 188k| } 360| 2.44k| u16_u8(dest, t); 361| 2.44k| if (ncap) { ------------------ | Branch (361:9): [True: 1.43k, False: 1.00k] ------------------ 362| 1.43k| const auto idx = (unsigned short)t[0]; 363| 1.43k| firstcap = (idx != unicodetolower(idx, langnum)); 364| 1.43k| } 365| 2.44k| } 366| | 367| | // now finally set the captype 368| 5.18k| if (ncap == 0) { ------------------ | Branch (368:7): [True: 1.97k, False: 3.20k] ------------------ 369| 1.97k| *pcaptype = NOCAP; ------------------ | | 92| 1.97k|#define NOCAP 0 ------------------ 370| 3.20k| } else if ((ncap == 1) && firstcap) { ------------------ | Branch (370:14): [True: 1.72k, False: 1.48k] | Branch (370:29): [True: 1.36k, False: 363] ------------------ 371| 1.36k| *pcaptype = INITCAP; ------------------ | | 93| 1.36k|#define INITCAP 1 ------------------ 372| 1.84k| } else if ((ncap == nc) || ((ncap + nneutral) == nc)) { ------------------ | Branch (372:14): [True: 100, False: 1.74k] | Branch (372:30): [True: 350, False: 1.39k] ------------------ 373| 450| *pcaptype = ALLCAP; ------------------ | | 94| 450|#define ALLCAP 2 ------------------ 374| 1.39k| } else if ((ncap > 1) && firstcap) { ------------------ | Branch (374:14): [True: 1.06k, False: 333] | Branch (374:28): [True: 881, False: 181] ------------------ 375| 881| *pcaptype = HUHINITCAP; ------------------ | | 96| 881|#define HUHINITCAP 4 ------------------ 376| 881| } else { 377| 514| *pcaptype = HUHCAP; ------------------ | | 95| 514|#define HUHCAP 3 ------------------ 378| 514| } 379| 5.18k|} _ZN12HunspellImpl8mkallcapERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 381| 2.30k|void HunspellImpl::mkallcap(std::string& u8) { 382| 2.30k| if (utf8) { ------------------ | Branch (382:7): [True: 1.21k, False: 1.08k] ------------------ 383| 1.21k| std::vector u16; 384| 1.21k| u8_u16(u16, u8); 385| 1.21k| ::mkallcap_utf(u16, langnum); 386| 1.21k| u16_u8(u8, u16); 387| 1.21k| } else { 388| 1.08k| ::mkallcap(u8, csconv); 389| 1.08k| } 390| 2.30k|} _ZN12HunspellImpl11mkallsmall2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEE: 392| 1.41M|int HunspellImpl::mkallsmall2(std::string& u8, std::vector& u16) { 393| 1.41M| if (utf8) { ------------------ | Branch (393:7): [True: 313k, False: 1.10M] ------------------ 394| 313k| ::mkallsmall_utf(u16, langnum); 395| 313k| u16_u8(u8, u16); 396| 1.10M| } else { 397| 1.10M| ::mkallsmall(u8, csconv); 398| 1.10M| } 399| 1.41M| return u8.size(); 400| 1.41M|} _ZN12HunspellImpl11is_keepcaseEPK6hentry: 438| 29.8k|int HunspellImpl::is_keepcase(const hentry* rv) { 439| 29.8k| return pAMgr && rv->astr && pAMgr->get_keepcase() && ------------------ | Branch (439:10): [True: 29.8k, False: 0] | Branch (439:19): [True: 611, False: 29.2k] | Branch (439:31): [True: 61, False: 550] ------------------ 440| 61| TESTAFF(rv->astr, pAMgr->get_keepcase(), rv->alen); ------------------ | | 99| 29.9k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 38, False: 23] | | ------------------ ------------------ 441| 29.8k|} _ZN12HunspellImpl10insert_sugERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_: 444| 15.1k|void HunspellImpl::insert_sug(std::vector& slst, const std::string& word) { 445| 15.1k| slst.insert(slst.begin(), word); 446| 15.1k|} _ZN12HunspellImpl5spellERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEEPiPS6_NS0_6chrono10time_pointINSF_12steady_clockENSF_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 450| 13.7M| std::chrono::steady_clock::time_point suggest_start) { 451| | // something very broken if spell ends up calling itself with the same word 452| 13.7M| if (std::find(candidate_stack.begin(), candidate_stack.end(), word) != candidate_stack.end()) ------------------ | Branch (452:7): [True: 0, False: 13.7M] ------------------ 453| 0| return false; 454| | 455| 13.7M| if (candidate_stack.size() >= MAXBREAKDEPTH) ------------------ | | 87| 13.7M|#define MAXBREAKDEPTH 10 ------------------ | Branch (455:7): [True: 0, False: 13.7M] ------------------ 456| 0| return false; 457| | 458| 13.7M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 13.7M|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (458:7): [True: 0, False: 13.7M] ------------------ 459| 0| return false; 460| | 461| 13.7M| candidate_stack.push_back(word); 462| 13.7M| bool r = spell_internal(word, candidate_stack, info, root, suggest_start); 463| 13.7M| candidate_stack.pop_back(); 464| | 465| 13.7M| if (r && root) { ------------------ | Branch (465:7): [True: 2.94M, False: 10.8M] | Branch (465:12): [True: 0, False: 2.94M] ------------------ 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| 13.7M| return r; 476| 13.7M|} _ZN12HunspellImpl14spell_internalERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEEPiPS6_NS0_6chrono10time_pointINSF_12steady_clockENSF_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 480| 13.7M| std::chrono::steady_clock::time_point suggest_start) { 481| 13.7M| struct hentry* rv = nullptr; 482| | 483| 13.7M| int info2 = 0; 484| 13.7M| if (!info) ------------------ | Branch (484:7): [True: 13.7M, False: 89] ------------------ 485| 13.7M| info = &info2; 486| 89| else 487| 89| *info = 0; 488| | 489| | // Hunspell supports XML input of the simplified API (see manual) 490| 13.7M| if (word == SPELL_XML) ------------------ | | 80| 13.7M|#define SPELL_XML "" ------------------ | Branch (490:7): [True: 461k, False: 13.3M] ------------------ 491| 461k| return true; 492| 13.3M| if (utf8) { ------------------ | Branch (492:7): [True: 2.86M, False: 10.4M] ------------------ 493| 2.86M| if (word.size() >= MAXWORDUTF8LEN) ------------------ | | 86| 2.86M|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 2.86M|#define MAXWORDLEN 100 | | ------------------ ------------------ | Branch (493:9): [True: 3.78k, False: 2.85M] ------------------ 494| 3.78k| return false; 495| 10.4M| } else { 496| 10.4M| if (word.size() >= MAXWORDLEN) ------------------ | | 90| 10.4M|#define MAXWORDLEN 100 ------------------ | Branch (496:9): [True: 6.36k, False: 10.4M] ------------------ 497| 6.36k| return false; 498| 10.4M| } 499| 13.3M| int captype = NOCAP; ------------------ | | 92| 13.3M|#define NOCAP 0 ------------------ 500| 13.3M| size_t abbv = 0; 501| 13.3M| size_t wl = 0; 502| | 503| 13.3M| std::string scw; 504| 13.3M| std::vector sunicw; 505| | 506| | // input conversion 507| 13.3M| RepList* rl = pAMgr ? pAMgr->get_iconvtable() : nullptr; ------------------ | Branch (507:17): [True: 13.3M, False: 0] ------------------ 508| 13.3M| { 509| 13.3M| std::string wspace; 510| | 511| 13.3M| bool convstatus = rl ? rl->conv(word, wspace) : false; ------------------ | Branch (511:23): [True: 414k, False: 12.8M] ------------------ 512| 13.3M| if (convstatus) { ------------------ | Branch (512:9): [True: 0, False: 13.3M] ------------------ 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| 13.3M| wl = cleanword2(scw, sunicw, word, &captype, &abbv); 520| 13.3M| } 521| | 522| 13.3M|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 523| 13.3M| if (wl > 32768) ------------------ | Branch (523:9): [True: 0, False: 13.3M] ------------------ 524| 0| return false; 525| 13.3M|#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| 13.3M| if (wl == 0 || m_HMgrs.empty()) ------------------ | Branch (533:7): [True: 479k, False: 12.8M] | Branch (533:18): [True: 0, False: 12.8M] ------------------ 534| 479k| return true; 535| 12.8M| if (root) ------------------ | Branch (535:7): [True: 0, False: 12.8M] ------------------ 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| 12.8M| enum { NBEGIN, NNUM, NSEP }; 543| 12.8M| int nstate = NBEGIN; 544| 12.8M| size_t i; 545| 12.8M| size_t n = utf8 ? sunicw.size() : wl; ------------------ | Branch (545:14): [True: 2.75M, False: 10.0M] ------------------ 546| | 547| 21.7M| for (i = 0; (i < n); i++) { ------------------ | Branch (547:15): [True: 20.9M, False: 816k] ------------------ 548| 20.9M| unsigned short c = utf8 ? static_cast(sunicw[i]) : static_cast(scw[i]); ------------------ | Branch (548:24): [True: 5.08M, False: 15.8M] ------------------ 549| 20.9M| if ((c >= '0' && c <= '9') || (c >= 0x0660 && c <= 0x0669) || // Arabic-Indic digits ------------------ | Branch (549:10): [True: 14.4M, False: 6.45M] | Branch (549:22): [True: 8.41M, False: 6.06M] | Branch (549:36): [True: 283k, False: 12.2M] | Branch (549:51): [True: 0, False: 283k] ------------------ 550| 12.5M| (c >= 0x06F0 && c <= 0x06F9)) { // Extended Arabic-Indic (Persian) digits ------------------ | Branch (550:10): [True: 283k, False: 12.2M] | Branch (550:25): [True: 0, False: 283k] ------------------ 551| 8.41M| nstate = NNUM; 552| 12.5M| } else if ((c == ',') || (c == '.') || (c == '-')) { ------------------ | Branch (552:16): [True: 65.5k, False: 12.4M] | Branch (552:30): [True: 944k, False: 11.5M] | Branch (552:44): [True: 2.18M, False: 9.33M] ------------------ 553| 3.19M| if ((nstate == NSEP) || (i == 0)) ------------------ | Branch (553:11): [True: 141k, False: 3.05M] | Branch (553:31): [True: 2.54M, False: 515k] ------------------ 554| 2.68M| break; 555| 515k| nstate = NSEP; 556| 515k| } else 557| 9.33M| break; 558| 20.9M| } 559| 12.8M| if ((i == n) && (nstate == NNUM)) ------------------ | Branch (559:7): [True: 816k, False: 12.0M] | Branch (559:19): [True: 628k, False: 188k] ------------------ 560| 628k| return true; 561| | 562| 12.2M| switch (captype) { ------------------ | Branch (562:11): [True: 12.2M, False: 0] ------------------ 563| 905k| case HUHCAP: ------------------ | | 95| 905k|#define HUHCAP 3 ------------------ | Branch (563:5): [True: 905k, False: 11.2M] ------------------ 564| | /* FALLTHROUGH */ 565| 1.14M| case HUHINITCAP: ------------------ | | 96| 1.14M|#define HUHINITCAP 4 ------------------ | Branch (565:5): [True: 236k, False: 11.9M] ------------------ 566| 1.14M| *info |= SPELL_ORIGCAP; ------------------ | | 83| 1.14M|#define SPELL_ORIGCAP (1 << 5) ------------------ 567| | /* FALLTHROUGH */ 568| 11.3M| case NOCAP: ------------------ | | 92| 11.3M|#define NOCAP 0 ------------------ | Branch (568:5): [True: 10.1M, False: 2.04M] ------------------ 569| 11.3M| rv = checkword(scw, info, root, suggest_start); 570| 11.3M| if ((abbv) && !(rv)) { ------------------ | Branch (570:11): [True: 1.56M, False: 9.73M] | Branch (570:21): [True: 1.53M, False: 31.5k] ------------------ 571| 1.53M| std::string u8buffer(scw); 572| 1.53M| u8buffer.push_back('.'); 573| 1.53M| rv = checkword(u8buffer, info, root, suggest_start); 574| 1.53M| } 575| | // A stem with an inner capital, capitalised at the start of a sentence 576| | // (uLinda written ULinda), is found by lowering only the first letter. 577| 11.3M| if (!rv && captype == HUHINITCAP) { ------------------ | | 96| 11.2M|#define HUHINITCAP 4 ------------------ | Branch (577:11): [True: 11.2M, False: 89.1k] | Branch (577:18): [True: 233k, False: 10.9M] ------------------ 578| 233k| std::string u8buffer(scw); 579| 233k| std::vector u16buffer(sunicw); 580| 233k| mkinitsmall2(u8buffer, u16buffer); 581| 233k| rv = checkword(u8buffer, info, root, suggest_start); 582| 233k| if (rv && is_keepcase(rv)) ------------------ | Branch (582:13): [True: 5, False: 233k] | Branch (582:19): [True: 0, False: 5] ------------------ 583| 0| rv = nullptr; 584| 233k| } 585| 11.3M| break; 586| 323k| case ALLCAP: { ------------------ | | 94| 323k|#define ALLCAP 2 ------------------ | Branch (586:5): [True: 323k, False: 11.8M] ------------------ 587| 323k| *info |= SPELL_ORIGCAP; ------------------ | | 83| 323k|#define SPELL_ORIGCAP (1 << 5) ------------------ 588| 323k| rv = checkword(scw, info, root, suggest_start); 589| 323k| if (rv) ------------------ | Branch (589:11): [True: 151, False: 322k] ------------------ 590| 151| break; 591| 322k| if (abbv) { ------------------ | Branch (591:11): [True: 84.7k, False: 238k] ------------------ 592| 84.7k| std::string u8buffer(scw); 593| 84.7k| u8buffer.push_back('.'); 594| 84.7k| rv = checkword(u8buffer, info, root, suggest_start); 595| 84.7k| if (rv) ------------------ | Branch (595:13): [True: 0, False: 84.7k] ------------------ 596| 0| break; 597| 84.7k| } 598| | // Spec. prefix handling for Catalan, French, Italian: 599| | // prefixes separated by apostrophe (SANT'ELIA -> Sant'+Elia). 600| 322k| size_t apos = pAMgr ? scw.find('\'') : std::string::npos; ------------------ | Branch (600:21): [True: 322k, False: 0] ------------------ 601| 322k| if (apos != std::string::npos) { ------------------ | Branch (601:11): [True: 102k, False: 220k] ------------------ 602| 102k| mkallsmall2(scw, sunicw); 603| | //conversion may result in string with different len to pre-mkallsmall2 604| | //so re-scan 605| 102k| if (apos != std::string::npos && apos < scw.size() - 1) { ------------------ | Branch (605:13): [True: 102k, False: 0] | Branch (605:42): [True: 96.9k, False: 5.86k] ------------------ 606| 96.9k| std::string part1 = scw.substr(0, apos + 1), part2 = scw.substr(apos + 1); 607| 96.9k| if (utf8) { ------------------ | Branch (607:15): [True: 26.0k, False: 70.8k] ------------------ 608| 26.0k| std::vector part1u, part2u; 609| 26.0k| u8_u16(part1u, part1); 610| 26.0k| u8_u16(part2u, part2); 611| 26.0k| mkinitcap2(part2, part2u); 612| 26.0k| scw = part1 + part2; 613| 26.0k| sunicw = std::move(part1u); 614| 26.0k| sunicw.insert(sunicw.end(), part2u.begin(), part2u.end()); 615| 26.0k| rv = checkword(scw, info, root, suggest_start); 616| 26.0k| if (rv) ------------------ | Branch (616:17): [True: 0, False: 26.0k] ------------------ 617| 0| break; 618| 70.8k| } else { 619| 70.8k| mkinitcap2(part2, sunicw); 620| 70.8k| scw = part1 + part2; 621| 70.8k| rv = checkword(scw, info, root, suggest_start); 622| 70.8k| if (rv) ------------------ | Branch (622:17): [True: 2, False: 70.8k] ------------------ 623| 2| break; 624| 70.8k| } 625| 96.9k| mkinitcap2(scw, sunicw); 626| 96.9k| rv = checkword(scw, info, root, suggest_start); 627| 96.9k| if (rv) ------------------ | Branch (627:15): [True: 0, False: 96.9k] ------------------ 628| 0| break; 629| 96.9k| } 630| 102k| } 631| 322k| if (pAMgr && pAMgr->get_checksharps() && scw.find("SS") != std::string::npos) { ------------------ | Branch (631:11): [True: 322k, False: 0] | Branch (631:20): [True: 0, False: 322k] | Branch (631:48): [True: 0, False: 0] ------------------ 632| | 633| 0| mkallsmall2(scw, sunicw); 634| 0| std::string u8buffer(scw); 635| 0| rv = spellsharps(u8buffer, 0, 0, 0, info, root, suggest_start); 636| 0| if (!rv) { ------------------ | Branch (636:13): [True: 0, False: 0] ------------------ 637| 0| mkinitcap2(scw, sunicw); 638| 0| rv = spellsharps(scw, 0, 0, 0, info, root, suggest_start); 639| 0| } 640| 0| if ((abbv) && !(rv)) { ------------------ | Branch (640:13): [True: 0, False: 0] | Branch (640:23): [True: 0, False: 0] ------------------ 641| 0| u8buffer.push_back('.'); 642| 0| rv = spellsharps(u8buffer, 0, 0, 0, info, root, suggest_start); 643| 0| if (!rv) { ------------------ | Branch (643:15): [True: 0, False: 0] ------------------ 644| 0| u8buffer = std::string(scw); 645| 0| u8buffer.push_back('.'); 646| 0| rv = spellsharps(u8buffer, 0, 0, 0, info, root, suggest_start); 647| 0| } 648| 0| } 649| 0| if (rv) ------------------ | Branch (649:13): [True: 0, False: 0] ------------------ 650| 0| break; 651| 0| } 652| 322k| } 653| | /* FALLTHROUGH */ 654| 901k| case INITCAP: { ------------------ | | 93| 901k|#define INITCAP 1 ------------------ | Branch (654:5): [True: 578k, False: 11.6M] ------------------ 655| | // handle special capitalization of dotted I 656| 901k| bool Idot = (utf8 && (unsigned char) scw[0] == 0xc4 && (unsigned char) scw[1] == 0xb0); ------------------ | Branch (656:20): [True: 173k, False: 727k] | Branch (656:28): [True: 0, False: 173k] | Branch (656:62): [True: 0, False: 0] ------------------ 657| 901k| *info |= SPELL_ORIGCAP; ------------------ | | 83| 901k|#define SPELL_ORIGCAP (1 << 5) ------------------ 658| 901k| if (captype == ALLCAP) { ------------------ | | 94| 901k|#define ALLCAP 2 ------------------ | Branch (658:11): [True: 322k, False: 578k] ------------------ 659| 322k| mkallsmall2(scw, sunicw); 660| 322k| mkinitcap2(scw, sunicw); 661| 322k| if (Idot) ------------------ | Branch (661:15): [True: 0, False: 322k] ------------------ 662| 0| scw.replace(0, 1, "\xc4\xb0"); 663| 322k| } 664| 901k| if (captype == INITCAP) ------------------ | | 93| 901k|#define INITCAP 1 ------------------ | Branch (664:11): [True: 578k, False: 322k] ------------------ 665| 578k| *info |= SPELL_INITCAP; ------------------ | | 82| 578k|#define SPELL_INITCAP (1 << 4) ------------------ 666| 901k| rv = checkword(scw, info, root, suggest_start); 667| 901k| if (captype == INITCAP) ------------------ | | 93| 901k|#define INITCAP 1 ------------------ | Branch (667:11): [True: 578k, False: 322k] ------------------ 668| 578k| *info &= ~SPELL_INITCAP; ------------------ | | 82| 578k|#define SPELL_INITCAP (1 << 4) ------------------ 669| | // forbid bad capitalization 670| | // (for example, ijs -> Ijs instead of IJs in Dutch) 671| | // use explicit forms in dic: Ijs/F (F = FORBIDDENWORD flag) 672| 901k| if (*info & SPELL_FORBIDDEN) { ------------------ | | 79| 901k|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (672:11): [True: 0, False: 901k] ------------------ 673| 0| rv = nullptr; 674| 0| break; 675| 0| } 676| 901k| if (rv && is_keepcase(rv) && (captype == ALLCAP)) ------------------ | | 94| 13|#define ALLCAP 2 ------------------ | Branch (676:11): [True: 15.7k, False: 885k] | Branch (676:17): [True: 13, False: 15.7k] | Branch (676:36): [True: 1, False: 12] ------------------ 677| 1| rv = nullptr; 678| 901k| if (rv || (Idot && langnum != LANG_az && langnum != LANG_tr && langnum != LANG_crh)) ------------------ | Branch (678:11): [True: 15.7k, False: 885k] | Branch (678:18): [True: 0, False: 885k] | Branch (678:26): [True: 0, False: 0] | Branch (678:48): [True: 0, False: 0] | Branch (678:70): [True: 0, False: 0] ------------------ 679| 15.7k| break; 680| | 681| 885k| mkallsmall2(scw, sunicw); 682| 885k| std::string u8buffer(scw); 683| 885k| mkinitcap2(scw, sunicw); 684| | 685| 885k| rv = checkword(u8buffer, info, root, suggest_start); 686| 885k| if (abbv && !rv) { ------------------ | Branch (686:11): [True: 217k, False: 668k] | Branch (686:19): [True: 213k, False: 4.17k] ------------------ 687| 213k| u8buffer.push_back('.'); 688| 213k| rv = checkword(u8buffer, info, root, suggest_start); 689| 213k| if (!rv) { ------------------ | Branch (689:13): [True: 213k, False: 0] ------------------ 690| 213k| u8buffer = scw; 691| 213k| u8buffer.push_back('.'); 692| 213k| if (captype == INITCAP) ------------------ | | 93| 213k|#define INITCAP 1 ------------------ | Branch (692:15): [True: 128k, False: 84.7k] ------------------ 693| 128k| *info |= SPELL_INITCAP; ------------------ | | 82| 128k|#define SPELL_INITCAP (1 << 4) ------------------ 694| 213k| rv = checkword(u8buffer, info, root, suggest_start); 695| 213k| if (captype == INITCAP) ------------------ | | 93| 213k|#define INITCAP 1 ------------------ | Branch (695:15): [True: 128k, False: 84.7k] ------------------ 696| 128k| *info &= ~SPELL_INITCAP; ------------------ | | 82| 128k|#define SPELL_INITCAP (1 << 4) ------------------ 697| 213k| if (rv && is_keepcase(rv) && (captype == ALLCAP)) ------------------ | | 94| 22|#define ALLCAP 2 ------------------ | Branch (697:15): [True: 22, False: 213k] | Branch (697:21): [True: 22, False: 0] | Branch (697:40): [True: 7, False: 15] ------------------ 698| 7| rv = nullptr; 699| 213k| break; 700| 213k| } 701| 213k| } 702| 672k| if (rv && is_keepcase(rv) && ------------------ | Branch (702:11): [True: 14.0k, False: 658k] | Branch (702:17): [True: 3, False: 14.0k] ------------------ 703| 3| ((captype == ALLCAP) || ------------------ | | 94| 3|#define ALLCAP 2 ------------------ | Branch (703:12): [True: 0, False: 3] ------------------ 704| | // if CHECKSHARPS: KEEPCASE words with \xDF are allowed 705| | // in INITCAP form, too. 706| 3| !(pAMgr->get_checksharps() && ------------------ | Branch (706:14): [True: 0, False: 3] ------------------ 707| 0| ((utf8 && u8buffer.find("\xC3\x9F") != std::string::npos) || ------------------ | Branch (707:16): [True: 0, False: 0] | Branch (707:24): [True: 0, False: 0] ------------------ 708| 0| (!utf8 && u8buffer.find('\xDF') != std::string::npos))))) ------------------ | Branch (708:16): [True: 0, False: 0] | Branch (708:25): [True: 0, False: 0] ------------------ 709| 3| rv = nullptr; 710| 672k| break; 711| 885k| } 712| 12.2M| } 713| | 714| 12.2M| if (rv) { ------------------ | Branch (714:7): [True: 119k, False: 12.0M] ------------------ 715| 119k| if (pAMgr && pAMgr->get_warn() && rv->astr && ------------------ | Branch (715:9): [True: 119k, False: 0] | Branch (715:9): [True: 6, False: 119k] | Branch (715:18): [True: 10.4k, False: 108k] | Branch (715:39): [True: 29, False: 10.4k] ------------------ 716| 29| TESTAFF(rv->astr, pAMgr->get_warn(), rv->alen)) { ------------------ | | 99| 29|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 6, False: 23] | | ------------------ ------------------ 717| 6| *info |= SPELL_WARN; ------------------ | | 84| 6|#define SPELL_WARN (1 << 6) ------------------ 718| 6| if (pAMgr->get_forbidwarn()) ------------------ | Branch (718:11): [True: 0, False: 6] ------------------ 719| 0| return false; 720| 6| return true; 721| 6| } 722| 119k| return true; 723| 119k| } 724| | 725| | // recursive breaking at break points 726| 12.0M| if (!wordbreak.empty() && !(*info & SPELL_FORBIDDEN)) { ------------------ | | 79| 12.0M|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (726:7): [True: 12.0M, False: 0] | Branch (726:29): [True: 12.0M, False: 0] ------------------ 727| | 728| 12.0M| int nbr = 0; 729| 12.0M| wl = scw.size(); 730| | 731| | // calculate break points for recursion limit 732| 36.1M| for (auto& j : wordbreak) { ------------------ | Branch (732:18): [True: 36.1M, False: 12.0M] ------------------ 733| 36.1M| size_t pos = 0; 734| 49.1M| while ((pos = scw.find(j, pos)) != std::string::npos) { ------------------ | Branch (734:14): [True: 12.9M, False: 36.1M] ------------------ 735| 12.9M| ++nbr; 736| 12.9M| pos += j.size(); 737| 12.9M| } 738| 36.1M| } 739| 12.0M| if (nbr >= MAXBREAKDEPTH) ------------------ | | 87| 12.0M|#define MAXBREAKDEPTH 10 ------------------ | Branch (739:9): [True: 5.67k, False: 12.0M] ------------------ 740| 5.67k| return false; 741| | 742| | // check boundary patterns (^begin and end$) 743| 36.0M| for (auto& j : wordbreak) { ------------------ | Branch (743:18): [True: 36.0M, False: 10.8M] ------------------ 744| 36.0M| size_t plen = j.size(); 745| 36.0M| if (plen == 1 || plen > wl) ------------------ | Branch (745:11): [True: 12.0M, False: 23.9M] | Branch (745:24): [True: 2.81M, False: 21.1M] ------------------ 746| 14.8M| continue; 747| | 748| 21.1M| if (j[0] == '^' && scw.compare(0, plen - 1, j, 1, plen - 1) == 0 && ------------------ | Branch (748:11): [True: 10.6M, False: 10.5M] | Branch (748:11): [True: 96.9k, False: 21.0M] | Branch (748:26): [True: 920k, False: 9.70M] ------------------ 749| 920k| spell(scw.substr(plen - 1), candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (749:11): [True: 96.9k, False: 823k] ------------------ 750| 96.9k| *info |= SPELL_COMPOUND; ------------------ | | 78| 96.9k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 751| 96.9k| return true; 752| 96.9k| } 753| | 754| 21.0M| if (j[plen - 1] == '$' && ------------------ | Branch (754:11): [True: 10.5M, False: 10.5M] ------------------ 755| 10.5M| scw.compare(wl - plen + 1, plen - 1, j, 0, plen - 1) == 0) { ------------------ | Branch (755:11): [True: 3.93M, False: 6.59M] ------------------ 756| 3.93M| std::string suffix(scw.substr(wl - plen + 1)); 757| 3.93M| scw.resize(wl - plen + 1); 758| 3.93M| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (758:13): [True: 1.10M, False: 2.82M] ------------------ 759| 1.10M| *info |= SPELL_COMPOUND; ------------------ | | 78| 1.10M|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 760| 1.10M| return true; 761| 1.10M| } 762| 2.82M| scw.append(suffix); 763| 2.82M| } 764| 21.0M| } 765| | 766| | // other patterns 767| 32.4M| for (auto& j : wordbreak) { ------------------ | Branch (767:18): [True: 32.4M, False: 10.8M] ------------------ 768| 32.4M| size_t plen = j.size(); 769| 32.4M| size_t found = scw.find(j); 770| 32.4M| if ((found > 0) && (found < wl - plen)) { ------------------ | Branch (770:11): [True: 30.9M, False: 1.55M] | Branch (770:26): [True: 3.56M, False: 27.3M] ------------------ 771| 3.56M| size_t found2 = scw.find(j, found + 1); 772| | // try to break at the second occurance 773| | // to recognize dictionary words with wordbreak 774| 3.56M| if (found2 > 0 && (found2 < wl - plen)) ------------------ | Branch (774:13): [True: 3.56M, False: 0] | Branch (774:27): [True: 1.38M, False: 2.17M] ------------------ 775| 1.38M| found = found2; 776| 3.56M| std::string substring(scw.substr(found + plen)); 777| 3.56M| if (!spell(substring, candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (777:13): [True: 2.64M, False: 915k] ------------------ 778| 2.64M| continue; 779| 915k| std::string suffix(scw.substr(found)); 780| 915k| scw.resize(found); 781| | // examine 2 sides of the break point 782| 915k| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (782:13): [True: 48.7k, False: 866k] ------------------ 783| 48.7k| *info |= SPELL_COMPOUND; ------------------ | | 78| 48.7k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 784| 48.7k| return true; 785| 48.7k| } 786| 866k| scw.append(suffix); 787| | 788| | // LANG_hu: spec. dash rule 789| 866k| if (langnum == LANG_hu && j == "-") { ------------------ | Branch (789:13): [True: 198, False: 866k] | Branch (789:35): [True: 198, False: 0] ------------------ 790| 198| suffix = scw.substr(found + 1); 791| 198| scw.resize(found + 1); 792| 198| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (792:15): [True: 0, False: 198] ------------------ 793| 0| *info |= SPELL_COMPOUND; ------------------ | | 78| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 794| 0| return true; // check the first part with dash 795| 0| } 796| 198| scw.append(suffix); 797| 198| } 798| | // end of LANG specific region 799| 866k| } 800| 32.4M| } 801| | 802| | // other patterns (break at first break point) 803| 32.3M| for (auto& j : wordbreak) { ------------------ | Branch (803:18): [True: 32.3M, False: 10.8M] ------------------ 804| 32.3M| size_t plen = j.size(), found = scw.find(j); 805| 32.3M| if ((found > 0) && (found < wl - plen)) { ------------------ | Branch (805:11): [True: 30.8M, False: 1.55M] | Branch (805:26): [True: 3.50M, False: 27.3M] ------------------ 806| 3.50M| if (!spell(scw.substr(found + plen), candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (806:13): [True: 2.79M, False: 709k] ------------------ 807| 2.79M| continue; 808| 709k| std::string suffix(scw.substr(found)); 809| 709k| scw.resize(found); 810| | // examine 2 sides of the break point 811| 709k| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (811:13): [True: 4.51k, False: 704k] ------------------ 812| 4.51k| *info |= SPELL_COMPOUND; ------------------ | | 78| 4.51k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 813| 4.51k| return true; 814| 4.51k| } 815| 704k| scw.append(suffix); 816| | 817| | // LANG_hu: spec. dash rule 818| 704k| if (langnum == LANG_hu && j == "-") { ------------------ | Branch (818:13): [True: 103, False: 704k] | Branch (818:35): [True: 103, False: 0] ------------------ 819| 103| suffix = scw.substr(found + 1); 820| 103| scw.resize(found + 1); 821| 103| if (spell(scw, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (821:15): [True: 0, False: 103] ------------------ 822| 0| *info |= SPELL_COMPOUND; ------------------ | | 78| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 823| 0| return true; // check the first part with dash 824| 0| } 825| 103| scw.append(suffix); 826| 103| } 827| | // end of LANG specific region 828| 704k| } 829| 32.3M| } 830| 10.8M| } 831| | 832| 10.8M| return false; 833| 12.0M|} _ZN12HunspellImpl9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiPS6_NS0_6chrono10time_pointINSB_12steady_clockENSB_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 836| 15.8M| std::chrono::steady_clock::time_point suggest_start) { 837| | // check overall suggest time limit 838| 15.8M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 15.8M|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (838:7): [True: 0, False: 15.8M] ------------------ 839| 0| return nullptr; 840| | 841| 15.8M| std::string word; 842| | 843| | // remove IGNORE characters from the string 844| 15.8M| clean_ignore(word, w); 845| | 846| 15.8M| if (word.empty()) ------------------ | Branch (846:7): [True: 133, False: 15.8M] ------------------ 847| 133| return nullptr; 848| | 849| | // word reversing wrapper for complex prefixes 850| 15.8M| if (complexprefixes) { ------------------ | Branch (850:7): [True: 987k, False: 14.9M] ------------------ 851| 987k| if (utf8) ------------------ | Branch (851:9): [True: 0, False: 987k] ------------------ 852| 0| reverseword_utf(word); 853| 987k| else 854| 987k| reverseword(word); 855| 987k| } 856| | 857| 15.8M| int len = word.size(); 858| | 859| | // look word in hash table 860| 15.8M| struct hentry* he = nullptr; 861| 31.7M| for (size_t i = 0; (i < m_HMgrs.size()) && !he; ++i) { ------------------ | Branch (861:22): [True: 15.8M, False: 15.8M] | Branch (861:46): [True: 15.8M, False: 0] ------------------ 862| 15.8M| he = m_HMgrs[i]->lookup(word.c_str(), word.size()); 863| | 864| | // check forbidden and onlyincompound words 865| 15.8M| if ((he) && (he->astr) && (pAMgr) && ------------------ | Branch (865:9): [True: 119k, False: 15.7M] | Branch (865:9): [True: 0, False: 15.8M] | Branch (865:17): [True: 658, False: 118k] | Branch (865:31): [True: 658, False: 0] ------------------ 866| 658| TESTAFF(he->astr, pAMgr->get_forbiddenword(), he->alen)) { ------------------ | | 99| 658|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 658] | | ------------------ ------------------ 867| 0| if (info) ------------------ | Branch (867:11): [True: 0, False: 0] ------------------ 868| 0| *info |= SPELL_FORBIDDEN; ------------------ | | 79| 0|#define SPELL_FORBIDDEN (1 << 1) ------------------ 869| | // LANG_hu section: set dash information for suggestions 870| 0| if (langnum == LANG_hu) { ------------------ | Branch (870:11): [True: 0, False: 0] ------------------ 871| 0| if (pAMgr->get_compoundflag() && ------------------ | Branch (871:13): [True: 0, False: 0] | Branch (871:13): [True: 0, False: 0] ------------------ 872| 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] | | ------------------ ------------------ 873| 0| if (info) ------------------ | Branch (873:15): [True: 0, False: 0] ------------------ 874| 0| *info |= SPELL_COMPOUND; ------------------ | | 78| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 875| 0| } 876| 0| } 877| 0| return nullptr; 878| 0| } 879| | 880| | // he = next not needaffix, onlyincompound homonym or onlyupcase word 881| 15.8M| while (he && (he->astr) && pAMgr && ------------------ | Branch (881:12): [True: 119k, False: 15.7M] | Branch (881:12): [True: 0, False: 15.8M] | Branch (881:18): [True: 658, False: 118k] | Branch (881:32): [True: 658, False: 0] ------------------ 882| 658| ((pAMgr->get_needaffix() && ------------------ | Branch (882:14): [True: 35, False: 623] ------------------ 883| 35| TESTAFF(he->astr, pAMgr->get_needaffix(), he->alen)) || ------------------ | | 99| 35|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 35] | | ------------------ ------------------ 884| 658| (pAMgr->get_onlyincompound() && ------------------ | Branch (884:14): [True: 0, False: 658] ------------------ 885| 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] | | ------------------ ------------------ 886| 658| (info && (*info & SPELL_INITCAP) && ------------------ | | 82| 658|#define SPELL_INITCAP (1 << 4) ------------------ | Branch (886:14): [True: 658, False: 0] | Branch (886:22): [True: 27, False: 631] ------------------ 887| 27| TESTAFF(he->astr, ONLYUPCASEFLAG, he->alen)))) ------------------ | | 99| 27|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 27] | | ------------------ ------------------ 888| 0| he = he->next_homonym; 889| 15.8M| } 890| | 891| | // check with affixes 892| 15.8M| if (!he && pAMgr) { ------------------ | Branch (892:7): [True: 15.7M, False: 119k] | Branch (892:14): [True: 15.7M, False: 0] ------------------ 893| | // try stripping off affixes 894| 15.7M| AffixScratch scratch; 895| | // For an initial-capital query, make affix_check skip an all-uppercase-only 896| | // stem and keep looking, so a valid mixed-case match behind it is found. 897| 15.7M| FLAG avoidflag = (info && (*info & SPELL_INITCAP)) ? ONLYUPCASEFLAG : FLAG_NULL; ------------------ | | 95| 15.7M|#define FLAG unsigned short ------------------ FLAG avoidflag = (info && (*info & SPELL_INITCAP)) ? ONLYUPCASEFLAG : FLAG_NULL; ------------------ | | 82| 15.7M|#define SPELL_INITCAP (1 << 4) ------------------ FLAG avoidflag = (info && (*info & SPELL_INITCAP)) ? ONLYUPCASEFLAG : FLAG_NULL; ------------------ | | 128| 692k|#define ONLYUPCASEFLAG 65511 ------------------ FLAG avoidflag = (info && (*info & SPELL_INITCAP)) ? ONLYUPCASEFLAG : FLAG_NULL; ------------------ | | 96| 30.8M|#define FLAG_NULL 0x00 ------------------ | Branch (897:23): [True: 15.7M, False: 0] | Branch (897:31): [True: 692k, False: 15.0M] ------------------ 898| 15.7M| he = pAMgr->affix_check(word, 0, len, scratch, 0, IN_CPD_NOT, avoidflag); ------------------ | | 72| 15.7M|#define IN_CPD_NOT 0 ------------------ 899| | 900| | // check compound restriction and onlyupcase 901| 15.7M| if (he && he->astr && ------------------ | Branch (901:9): [True: 0, False: 15.7M] | Branch (901:9): [True: 0, False: 15.7M] | Branch (901:15): [True: 0, False: 0] ------------------ 902| 0| ((pAMgr->get_onlyincompound() && ------------------ | Branch (902:11): [True: 0, False: 0] ------------------ 903| 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] | | ------------------ ------------------ 904| 0| (info && (*info & SPELL_INITCAP) && ------------------ | | 82| 0|#define SPELL_INITCAP (1 << 4) ------------------ | Branch (904:11): [True: 0, False: 0] | Branch (904:19): [True: 0, False: 0] ------------------ 905| 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] | | ------------------ ------------------ 906| 0| he = nullptr; 907| 0| } 908| | 909| 15.7M| if (he) { ------------------ | Branch (909:9): [True: 0, False: 15.7M] ------------------ 910| 0| if ((he->astr) && (pAMgr) && ------------------ | Branch (910:11): [True: 0, False: 0] | Branch (910:11): [True: 0, False: 0] | Branch (910:25): [True: 0, False: 0] ------------------ 911| 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] | | ------------------ ------------------ 912| 0| if (info) ------------------ | Branch (912:13): [True: 0, False: 0] ------------------ 913| 0| *info |= SPELL_FORBIDDEN; ------------------ | | 79| 0|#define SPELL_FORBIDDEN (1 << 1) ------------------ 914| 0| return nullptr; 915| 0| } 916| 0| if (root) { ------------------ | Branch (916:11): [True: 0, False: 0] ------------------ 917| 0| root->assign(he->word); 918| 0| if (complexprefixes) { ------------------ | Branch (918:13): [True: 0, False: 0] ------------------ 919| 0| if (utf8) ------------------ | Branch (919:15): [True: 0, False: 0] ------------------ 920| 0| reverseword_utf(*root); 921| 0| else 922| 0| reverseword(*root); 923| 0| } 924| 0| } 925| | // try check compound word 926| 15.7M| } else if (pAMgr->get_compound()) { ------------------ | Branch (926:16): [True: 3.91M, False: 11.8M] ------------------ 927| 3.91M| struct hentry* rwords[100] = {}; // buffer for COMPOUND pattern checking 928| | 929| | // first allow only 2 words in the compound 930| 3.91M| int setinfo = SPELL_COMPOUND_2; ------------------ | | 85| 3.91M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ 931| 3.91M| if (info) ------------------ | Branch (931:11): [True: 3.91M, False: 0] ------------------ 932| 3.91M| setinfo |= *info; 933| 3.91M| he = pAMgr->compound_check(word, 0, 0, 100, 0, nullptr, (hentry**)&rwords, 0, 0, &setinfo, scratch); 934| 3.91M| if (info) ------------------ | Branch (934:11): [True: 3.91M, False: 0] ------------------ 935| 3.91M| *info = setinfo & ~SPELL_COMPOUND_2; ------------------ | | 85| 3.91M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ 936| | // if not 2-word compoud word, try with 3 or more words 937| | // (only if original info didn't forbid it) 938| 3.91M| if (!he && info && !(*info & SPELL_COMPOUND_2)) { ------------------ | | 85| 3.91M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ | Branch (938:11): [True: 3.91M, False: 0] | Branch (938:18): [True: 3.91M, False: 0] | Branch (938:26): [True: 3.91M, False: 0] ------------------ 939| 3.91M| *info &= ~SPELL_COMPOUND_2; ------------------ | | 85| 3.91M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ 940| 3.91M| he = pAMgr->compound_check(word, 0, 0, 100, 0, nullptr, (hentry**)&rwords, 0, 0, info, scratch); 941| | // accept the compound with 3 or more words only if it is 942| | // - not a dictionary word with a typo and 943| | // - not two words written separately, 944| | // - or if it's an arbitrary number accepted by compound rules (e.g. 999%) 945| 3.91M| if (he && !isdigit(word[0])) ------------------ | Branch (945:13): [True: 0, False: 3.91M] | Branch (945:19): [True: 0, False: 0] ------------------ 946| 0| { 947| 0| std::vector slst; 948| 0| if (pSMgr->suggest(slst, word, nullptr, /*test_simplesug=*/true)) ------------------ | Branch (948:15): [True: 0, False: 0] ------------------ 949| 0| he = nullptr; 950| 0| } 951| 3.91M| } 952| | 953| | // LANG_hu section: `moving rule' with last dash 954| 3.91M| if ((!he) && (langnum == LANG_hu) && (word[len - 1] == '-')) { ------------------ | Branch (954:11): [True: 3.91M, False: 0] | Branch (954:20): [True: 32.4k, False: 3.88M] | Branch (954:44): [True: 12.1k, False: 20.2k] ------------------ 955| 12.1k| std::string dup(word, 0, len - 1); 956| 12.1k| he = pAMgr->compound_check(dup, -5, 0, 100, 0, nullptr, (hentry**)&rwords, 1, 0, info, scratch); 957| 12.1k| } 958| | // end of LANG specific region 959| 3.91M| if (he) { ------------------ | Branch (959:11): [True: 0, False: 3.91M] ------------------ 960| 0| if (root) { ------------------ | Branch (960:13): [True: 0, False: 0] ------------------ 961| 0| root->assign(he->word); 962| 0| if (complexprefixes) { ------------------ | Branch (962:15): [True: 0, False: 0] ------------------ 963| 0| if (utf8) ------------------ | Branch (963:17): [True: 0, False: 0] ------------------ 964| 0| reverseword_utf(*root); 965| 0| else 966| 0| reverseword(*root); 967| 0| } 968| 0| } 969| 0| if (info) ------------------ | Branch (969:13): [True: 0, False: 0] ------------------ 970| 0| *info |= SPELL_COMPOUND; ------------------ | | 78| 0|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 971| 0| } 972| 3.91M| } 973| 15.7M| } 974| | 975| 15.8M| return he; 976| 15.8M|} _ZN12HunspellImpl7suggestERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEENS0_6chrono10time_pointINSD_12steady_clockENSD_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 984| 89.0k|std::vector HunspellImpl::suggest(const std::string& word, std::vector& suggest_candidate_stack, std::chrono::steady_clock::time_point suggest_start) { 985| | 986| 89.0k| if (suggest_candidate_stack.size() > MAX_CANDIDATE_STACK_DEPTH || // apply a fairly arbitrary depth limit ------------------ | | 979| 178k|#define MAX_CANDIDATE_STACK_DEPTH 512 ------------------ | Branch (986:7): [True: 0, False: 89.0k] | Branch (986:7): [True: 0, False: 89.0k] ------------------ 987| | // something very broken if suggest ends up calling itself with the same word 988| 89.0k| std::find(suggest_candidate_stack.begin(), suggest_candidate_stack.end(), word) != suggest_candidate_stack.end()) { ------------------ | Branch (988:7): [True: 0, False: 89.0k] ------------------ 989| 0| return { }; 990| 0| } 991| | 992| 89.0k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 89.0k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (992:7): [True: 0, False: 89.0k] ------------------ 993| 0| return { }; 994| | 995| 89.0k| bool capwords; 996| 89.0k| size_t abbv; 997| 89.0k| int captype; 998| 89.0k| std::vector spell_candidate_stack; 999| 89.0k| suggest_candidate_stack.push_back(word); 1000| 89.0k| std::vector slst = suggest_internal(word, spell_candidate_stack, suggest_candidate_stack, 1001| 89.0k| capwords, abbv, captype, suggest_start); 1002| 89.0k| suggest_candidate_stack.pop_back(); 1003| | // word reversing wrapper for complex prefixes 1004| 89.0k| if (complexprefixes) { ------------------ | Branch (1004:7): [True: 4.59k, False: 84.4k] ------------------ 1005| 4.59k| for (auto& j : slst) { ------------------ | Branch (1005:18): [True: 2.08k, False: 4.59k] ------------------ 1006| 2.08k| if (utf8) ------------------ | Branch (1006:11): [True: 0, False: 2.08k] ------------------ 1007| 0| reverseword_utf(j); 1008| 2.08k| else 1009| 2.08k| reverseword(j); 1010| 2.08k| } 1011| 4.59k| } 1012| | 1013| | // capitalize 1014| 89.0k| if (capwords) { ------------------ | Branch (1014:7): [True: 24.5k, False: 64.4k] ------------------ 1015| 24.5k| for (auto& j : slst) { ------------------ | Branch (1015:18): [True: 16.0k, False: 24.5k] ------------------ 1016| 16.0k| std::string capitalized(j); 1017| 16.0k| mkinitcap(capitalized); 1018| 16.0k| if (capitalized == word) ------------------ | Branch (1018:11): [True: 13, False: 16.0k] ------------------ 1019| 13| continue; // capitalizing would just reproduce the misspelled word 1020| 16.0k| j = std::move(capitalized); 1021| 16.0k| } 1022| 24.5k| } 1023| | 1024| | // expand suggestions with dot(s) 1025| 89.0k| if (abbv && pAMgr && pAMgr->get_sugswithdots() && word.size() >= abbv) { ------------------ | Branch (1025:7): [True: 3.67k, False: 85.3k] | Branch (1025:15): [True: 3.67k, False: 0] | Branch (1025:24): [True: 0, False: 3.67k] | Branch (1025:53): [True: 0, False: 0] ------------------ 1026| 0| for (auto& j : slst) { ------------------ | Branch (1026:18): [True: 0, False: 0] ------------------ 1027| 0| j.append(word.substr(word.size() - abbv)); 1028| 0| } 1029| 0| } 1030| | 1031| | // remove bad capitalized and forbidden forms 1032| 89.0k| if (pAMgr && (pAMgr->get_keepcase() || pAMgr->get_forbiddenword())) { ------------------ | Branch (1032:7): [True: 89.0k, False: 0] | Branch (1032:17): [True: 4.63k, False: 84.3k] | Branch (1032:42): [True: 84.3k, False: 0] ------------------ 1033| 89.0k| switch (captype) { ------------------ | Branch (1033:13): [True: 46.8k, False: 42.1k] ------------------ 1034| 11.2k| case INITCAP: ------------------ | | 93| 11.2k|#define INITCAP 1 ------------------ | Branch (1034:7): [True: 11.2k, False: 77.7k] ------------------ 1035| 20.3k| case ALLCAP: ------------------ | | 94| 20.3k|#define ALLCAP 2 ------------------ | Branch (1035:7): [True: 9.14k, False: 79.8k] ------------------ 1036| 33.5k| case HUHCAP: ------------------ | | 95| 33.5k|#define HUHCAP 3 ------------------ | Branch (1036:7): [True: 13.1k, False: 75.8k] ------------------ 1037| 46.8k| case HUHINITCAP: { ------------------ | | 96| 46.8k|#define HUHINITCAP 4 ------------------ | Branch (1037:7): [True: 13.3k, False: 75.6k] ------------------ 1038| 46.8k| size_t l = 0; 1039| 76.3k| for (size_t j = 0; j < slst.size(); ++j) { ------------------ | Branch (1039:28): [True: 29.4k, False: 46.8k] ------------------ 1040| | // A space-containing suggestion can be an "insert a space" split 1041| | // whose parts each spell on their own, so it is good when every 1042| | // part spells even though the whole string does not. 1043| 29.4k| bool bad = !spell(slst[j], spell_candidate_stack, nullptr, nullptr, suggest_start); 1044| 29.4k| if (bad && slst[j].find(' ') != std::string::npos) { ------------------ | Branch (1044:15): [True: 15.0k, False: 14.3k] | Branch (1044:22): [True: 6.77k, False: 8.28k] ------------------ 1045| 6.77k| bad = false; 1046| 14.9k| for (size_t start = 0; start <= slst[j].size(); ) { ------------------ | Branch (1046:36): [True: 14.9k, False: 0] ------------------ 1047| 14.9k| size_t sp = slst[j].find(' ', start); 1048| 14.9k| size_t end = (sp == std::string::npos) ? slst[j].size() : sp; ------------------ | Branch (1048:28): [True: 2.11k, False: 12.8k] ------------------ 1049| 14.9k| std::string part = slst[j].substr(start, end - start); 1050| 14.9k| if (!part.empty() && ------------------ | Branch (1050:19): [True: 9.49k, False: 5.46k] ------------------ 1051| 9.49k| !spell(part, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1051:19): [True: 5.66k, False: 3.83k] ------------------ 1052| 5.66k| bad = true; 1053| 5.66k| break; 1054| 5.66k| } 1055| 9.29k| if (sp == std::string::npos) ------------------ | Branch (1055:19): [True: 1.11k, False: 8.17k] ------------------ 1056| 1.11k| break; 1057| 8.17k| start = sp + 1; 1058| 8.17k| } 1059| 6.77k| } 1060| 29.4k| if (bad) { ------------------ | Branch (1060:15): [True: 13.9k, False: 15.5k] ------------------ 1061| 13.9k| std::string s; 1062| 13.9k| std::vector w; 1063| 13.9k| if (utf8) { ------------------ | Branch (1063:17): [True: 5.76k, False: 8.18k] ------------------ 1064| 5.76k| u8_u16(w, slst[j]); 1065| 8.18k| } else { 1066| 8.18k| s = slst[j]; 1067| 8.18k| } 1068| 13.9k| mkallsmall2(s, w); 1069| 13.9k| if (spell(s, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1069:17): [True: 20, False: 13.9k] ------------------ 1070| 20| slst[l] = std::move(s); 1071| 20| ++l; 1072| 13.9k| } else { 1073| 13.9k| mkinitcap2(s, w); 1074| 13.9k| if (spell(s, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1074:19): [True: 8, False: 13.9k] ------------------ 1075| 8| slst[l] = std::move(s); 1076| 8| ++l; 1077| 8| } 1078| 13.9k| } 1079| 15.5k| } else { 1080| 15.5k| slst[l] = slst[j]; 1081| 15.5k| ++l; 1082| 15.5k| } 1083| 29.4k| } 1084| 46.8k| slst.resize(l); 1085| 46.8k| } 1086| 89.0k| } 1087| 89.0k| } 1088| | 1089| | // remove duplications 1090| 89.0k| size_t l = 0; 1091| 107k| for (size_t j = 0; j < slst.size(); ++j) { ------------------ | Branch (1091:22): [True: 18.0k, False: 89.0k] ------------------ 1092| 18.0k| slst[l] = slst[j]; 1093| 26.8k| for (size_t k = 0; k < l; ++k) { ------------------ | Branch (1093:24): [True: 9.65k, False: 17.2k] ------------------ 1094| 9.65k| if (slst[k] == slst[j]) { ------------------ | Branch (1094:11): [True: 785, False: 8.87k] ------------------ 1095| 785| --l; 1096| 785| break; 1097| 785| } 1098| 9.65k| } 1099| 18.0k| ++l; 1100| 18.0k| } 1101| 89.0k| slst.resize(l); 1102| | 1103| | // output conversion 1104| 89.0k| RepList* rl = (pAMgr) ? pAMgr->get_oconvtable() : nullptr; ------------------ | Branch (1104:17): [True: 89.0k, False: 0] ------------------ 1105| 89.0k| if (rl) { ------------------ | Branch (1105:7): [True: 4.78k, False: 84.2k] ------------------ 1106| 4.78k| size_t l = 0; 1107| 5.55k| for (size_t i = 0; i < slst.size(); ++i) { ------------------ | Branch (1107:24): [True: 770, False: 4.78k] ------------------ 1108| 770| std::string wspace; 1109| 770| if (rl->conv(slst[i], wspace)) { ------------------ | Branch (1109:11): [True: 213, False: 557] ------------------ 1110| 213| slst[i] = std::move(wspace); 1111| 213| } 1112| | // gh#1002: OCONV can map a generated form back to the input word 1113| | // (e.g. "románórum" -> "romanórum" when the user typed "romanórum"), 1114| | // leaving the misspelled word as its own suggestion. 1115| 770| if (slst[i] == word) ------------------ | Branch (1115:11): [True: 0, False: 770] ------------------ 1116| 0| continue; 1117| 770| if (l != i) ------------------ | Branch (1117:11): [True: 0, False: 770] ------------------ 1118| 0| slst[l] = std::move(slst[i]); 1119| 770| ++l; 1120| 770| } 1121| 4.78k| slst.resize(l); 1122| 4.78k| } 1123| 89.0k| return slst; 1124| 89.0k|} _ZN12HunspellImpl7suggestERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1126| 60.4k|std::vector HunspellImpl::suggest(const std::string& word) { 1127| 60.4k| std::vector suggest_candidate_stack; 1128| 60.4k| auto suggest_start = std::chrono::steady_clock::now(); 1129| 60.4k| return suggest(word, suggest_candidate_stack, suggest_start); 1130| 60.4k|} _ZN12HunspellImpl16suggest_internalERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorIS6_NS4_IS6_EEEESC_RbRmRiNS0_6chrono10time_pointINSG_12steady_clockENSG_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 1136| 89.0k| std::chrono::steady_clock::time_point suggest_start) { 1137| 89.0k| captype = NOCAP; ------------------ | | 92| 89.0k|#define NOCAP 0 ------------------ 1138| 89.0k| abbv = 0; 1139| 89.0k| capwords = false; 1140| | 1141| 89.0k| std::vector slst; 1142| | 1143| 89.0k| int onlycmpdsug = 0; 1144| 89.0k| if (!pSMgr || m_HMgrs.empty()) ------------------ | Branch (1144:7): [True: 0, False: 89.0k] | Branch (1144:17): [True: 0, False: 89.0k] ------------------ 1145| 0| return slst; 1146| | 1147| | // process XML input of the simplified API (see manual) 1148| 89.0k| if (word.compare(0, sizeof(SPELL_XML) - 3, SPELL_XML, sizeof(SPELL_XML) - 3) == 0) { ------------------ | | 80| 89.0k|#define SPELL_XML "" ------------------ if (word.compare(0, sizeof(SPELL_XML) - 3, SPELL_XML, sizeof(SPELL_XML) - 3) == 0) { ------------------ | | 80| 89.0k|#define SPELL_XML "" ------------------ if (word.compare(0, sizeof(SPELL_XML) - 3, SPELL_XML, sizeof(SPELL_XML) - 3) == 0) { ------------------ | | 80| 89.0k|#define SPELL_XML "" ------------------ | Branch (1148:7): [True: 21.2k, False: 67.7k] ------------------ 1149| 21.2k| if (word.size() > MAXSPELLMLLEN) ------------------ | | 87| 21.2k|#define MAXSPELLMLLEN 8192 ------------------ | Branch (1149:9): [True: 589, False: 20.6k] ------------------ 1150| 589| return slst; 1151| 20.6k| return spellml(word); 1152| 21.2k| } 1153| 67.7k| if (utf8) { ------------------ | Branch (1153:7): [True: 32.6k, False: 35.0k] ------------------ 1154| 32.6k| if (word.size() >= MAXWORDUTF8LEN) ------------------ | | 86| 32.6k|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 32.6k|#define MAXWORDLEN 100 | | ------------------ ------------------ | Branch (1154:9): [True: 126, False: 32.5k] ------------------ 1155| 126| return slst; 1156| 35.0k| } else { 1157| 35.0k| if (word.size() >= MAXWORDLEN) ------------------ | | 90| 35.0k|#define MAXWORDLEN 100 ------------------ | Branch (1157:9): [True: 170, False: 34.9k] ------------------ 1158| 170| return slst; 1159| 35.0k| } 1160| 67.4k| size_t wl = 0; 1161| | 1162| 67.4k| std::string scw; 1163| 67.4k| std::vector sunicw; 1164| | 1165| | // input conversion 1166| 67.4k| RepList* rl = (pAMgr) ? pAMgr->get_iconvtable() : nullptr; ------------------ | Branch (1166:17): [True: 67.4k, False: 0] ------------------ 1167| 67.4k| { 1168| 67.4k| std::string wspace; 1169| | 1170| 67.4k| bool convstatus = rl ? rl->conv(word, wspace) : false; ------------------ | Branch (1170:23): [True: 3.64k, False: 63.7k] ------------------ 1171| 67.4k| if (convstatus) { ------------------ | Branch (1171:9): [True: 0, False: 67.4k] ------------------ 1172| | // the input conversion can grow the word without limit, so hold the 1173| | // converted word to the same maximum length as the raw word 1174| 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 (1174:11): [True: 0, False: 0] | Branch (1174:11): [True: 0, False: 0] ------------------ 1175| 0| return slst; 1176| 0| wl = cleanword2(scw, sunicw, wspace, &captype, &abbv); 1177| 0| } else 1178| 67.4k| wl = cleanword2(scw, sunicw, word, &captype, &abbv); 1179| | 1180| 67.4k| if (wl == 0) ------------------ | Branch (1180:9): [True: 0, False: 67.4k] ------------------ 1181| 0| return slst; 1182| | 1183| 67.4k|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 1184| 67.4k| if (wl > 32768) ------------------ | Branch (1184:9): [True: 0, False: 67.4k] ------------------ 1185| 0| return slst; 1186| 67.4k|#endif 1187| 67.4k| } 1188| | 1189| 67.4k| bool good = false; 1190| | 1191| | // check capitalized form for FORCEUCASE 1192| 67.4k| if (pAMgr && captype == NOCAP && pAMgr->get_forceucase()) { ------------------ | | 92| 134k|#define NOCAP 0 ------------------ | Branch (1192:7): [True: 67.4k, False: 0] | Branch (1192:16): [True: 20.5k, False: 46.8k] | Branch (1192:36): [True: 0, False: 20.5k] ------------------ 1193| 0| int info = SPELL_ORIGCAP; ------------------ | | 83| 0|#define SPELL_ORIGCAP (1 << 5) ------------------ 1194| 0| if (checkword(scw, &info, nullptr, suggest_start)) { ------------------ | Branch (1194:9): [True: 0, False: 0] ------------------ 1195| 0| std::string form(std::move(scw)); 1196| 0| mkinitcap(form); 1197| 0| slst.push_back(std::move(form)); 1198| 0| return slst; 1199| 0| } 1200| 0| } 1201| | 1202| 67.4k| switch (captype) { ------------------ | Branch (1202:11): [True: 67.4k, False: 0] ------------------ 1203| 20.5k| case NOCAP: { ------------------ | | 92| 20.5k|#define NOCAP 0 ------------------ | Branch (1203:5): [True: 20.5k, False: 46.8k] ------------------ 1204| 20.5k| good |= pSMgr->suggest(slst, scw, &onlycmpdsug); 1205| 20.5k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 20.5k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1205:11): [True: 0, False: 20.5k] ------------------ 1206| 0| return slst; 1207| 20.5k| if (abbv) { ------------------ | Branch (1207:11): [True: 1.69k, False: 18.8k] ------------------ 1208| 1.69k| std::string wspace(scw); 1209| 1.69k| wspace.push_back('.'); 1210| 1.69k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1211| 1.69k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 1.69k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1211:13): [True: 0, False: 1.69k] ------------------ 1212| 0| return slst; 1213| 1.69k| } 1214| 20.5k| break; 1215| 20.5k| } 1216| | 1217| 20.5k| case INITCAP: { ------------------ | | 93| 11.2k|#define INITCAP 1 ------------------ | Branch (1217:5): [True: 11.2k, False: 56.2k] ------------------ 1218| 11.2k| capwords = true; 1219| 11.2k| good |= pSMgr->suggest(slst, scw, &onlycmpdsug); 1220| 11.2k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 11.2k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1220:11): [True: 0, False: 11.2k] ------------------ 1221| 0| return slst; 1222| 11.2k| std::string wspace(scw); 1223| 11.2k| mkallsmall2(wspace, sunicw); 1224| 11.2k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1225| 11.2k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 11.2k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1225:11): [True: 0, False: 11.2k] ------------------ 1226| 0| return slst; 1227| 11.2k| break; 1228| 11.2k| } 1229| 13.3k| case HUHINITCAP: ------------------ | | 96| 13.3k|#define HUHINITCAP 4 ------------------ | Branch (1229:5): [True: 13.3k, False: 54.0k] ------------------ 1230| 13.3k| capwords = true; 1231| | /* FALLTHROUGH */ 1232| 26.5k| case HUHCAP: { ------------------ | | 95| 26.5k|#define HUHCAP 3 ------------------ | Branch (1232:5): [True: 13.1k, False: 54.2k] ------------------ 1233| 26.5k| good |= pSMgr->suggest(slst, scw, &onlycmpdsug); 1234| 26.5k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 26.5k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1234:11): [True: 0, False: 26.5k] ------------------ 1235| 0| return slst; 1236| | // something.The -> something. The 1237| 26.5k| size_t dot_pos = scw.find('.'); 1238| 26.5k| if (dot_pos != std::string::npos) { ------------------ | Branch (1238:11): [True: 8.65k, False: 17.8k] ------------------ 1239| 8.65k| std::string postdot = scw.substr(dot_pos + 1); 1240| 8.65k| int captype_; 1241| 8.65k| if (utf8) { ------------------ | Branch (1241:13): [True: 2.08k, False: 6.56k] ------------------ 1242| 2.08k| std::vector postdotu; 1243| 2.08k| u8_u16(postdotu, postdot); 1244| 2.08k| captype_ = get_captype_utf8(postdotu, langnum); 1245| 6.56k| } else { 1246| 6.56k| captype_ = get_captype(postdot, csconv); 1247| 6.56k| } 1248| 8.65k| if (captype_ == INITCAP) { ------------------ | | 93| 8.65k|#define INITCAP 1 ------------------ | Branch (1248:13): [True: 3.72k, False: 4.92k] ------------------ 1249| 3.72k| std::string str(scw); 1250| 3.72k| str.insert(dot_pos + 1, 1, ' '); 1251| 3.72k| insert_sug(slst, str); 1252| 3.72k| } 1253| 8.65k| } 1254| | 1255| 26.5k| std::string wspace; 1256| | 1257| 26.5k| if (captype == HUHINITCAP) { ------------------ | | 96| 26.5k|#define HUHINITCAP 4 ------------------ | Branch (1257:11): [True: 13.3k, False: 13.1k] ------------------ 1258| | // TheOpenOffice.org -> The OpenOffice.org 1259| 13.3k| wspace = scw; 1260| 13.3k| mkinitsmall2(wspace, sunicw); 1261| 13.3k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1262| 13.3k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 13.3k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1262:13): [True: 0, False: 13.3k] ------------------ 1263| 0| return slst; 1264| 13.3k| } 1265| 26.5k| wspace = scw; 1266| 26.5k| mkallsmall2(wspace, sunicw); 1267| 26.5k| if (spell(wspace, spell_candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (1267:11): [True: 1.18k, False: 25.3k] ------------------ 1268| 1.18k| insert_sug(slst, wspace); 1269| 26.5k| size_t prevns = slst.size(); 1270| 26.5k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1271| 26.5k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 26.5k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1271:11): [True: 0, False: 26.5k] ------------------ 1272| 0| return slst; 1273| 26.5k| if (captype == HUHINITCAP) { ------------------ | | 96| 26.5k|#define HUHINITCAP 4 ------------------ | Branch (1273:11): [True: 13.3k, False: 13.1k] ------------------ 1274| 13.3k| mkinitcap2(wspace, sunicw); 1275| 13.3k| if (spell(wspace, spell_candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (1275:13): [True: 424, False: 12.9k] ------------------ 1276| 424| insert_sug(slst, wspace); 1277| 13.3k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1278| 13.3k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 13.3k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1278:13): [True: 0, False: 13.3k] ------------------ 1279| 0| return slst; 1280| 13.3k| } 1281| | // aNew -> "a New" (instead of "a new") 1282| 27.4k| for (size_t j = prevns; j < slst.size(); ++j) { ------------------ | Branch (1282:31): [True: 920, False: 26.5k] ------------------ 1283| 920| const char* space = strchr(slst[j].c_str(), ' '); 1284| 920| if (space) { ------------------ | Branch (1284:13): [True: 374, False: 546] ------------------ 1285| 374| size_t slen = strlen(space + 1); 1286| | // different case after space (need capitalisation) 1287| 374| if ((slen < wl) && strcmp(scw.c_str() + wl - slen, space + 1) != 0) { ------------------ | Branch (1287:15): [True: 374, False: 0] | Branch (1287:30): [True: 364, False: 10] ------------------ 1288| 364| std::string first(slst[j].c_str(), space + 1); 1289| 364| std::string second(space + 1); 1290| 364| std::vector w; 1291| 364| if (utf8) ------------------ | Branch (1291:17): [True: 116, False: 248] ------------------ 1292| 116| u8_u16(w, second); 1293| 364| mkinitcap2(second, w); 1294| | // set as first suggestion 1295| 364| slst.erase(slst.begin() + j); 1296| 364| slst.insert(slst.begin(), first + second); 1297| 364| } 1298| 374| } 1299| 920| } 1300| 26.5k| break; 1301| 26.5k| } 1302| | 1303| 9.14k| case ALLCAP: { ------------------ | | 94| 9.14k|#define ALLCAP 2 ------------------ | Branch (1303:5): [True: 9.14k, False: 58.2k] ------------------ 1304| 9.14k| std::string wspace(scw); 1305| 9.14k| mkallsmall2(wspace, sunicw); 1306| 9.14k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1307| 9.14k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 9.14k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1307:11): [True: 0, False: 9.14k] ------------------ 1308| 0| return slst; 1309| 9.14k| if (pAMgr && pAMgr->get_keepcase() && spell(wspace, spell_candidate_stack, nullptr, nullptr, suggest_start)) ------------------ | Branch (1309:11): [True: 9.14k, False: 0] | Branch (1309:20): [True: 407, False: 8.74k] | Branch (1309:45): [True: 0, False: 407] ------------------ 1310| 0| insert_sug(slst, wspace); 1311| 9.14k| mkinitcap2(wspace, sunicw); 1312| 9.14k| good |= pSMgr->suggest(slst, wspace, &onlycmpdsug); 1313| 9.14k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 9.14k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1313:11): [True: 0, False: 9.14k] ------------------ 1314| 0| return slst; 1315| 9.14k| for (auto& j : slst) { ------------------ | Branch (1315:20): [True: 473, False: 9.14k] ------------------ 1316| 473| mkallcap(j); 1317| 473| if (pAMgr && pAMgr->get_checksharps()) { ------------------ | Branch (1317:13): [True: 473, False: 0] | Branch (1317:22): [True: 0, False: 473] ------------------ 1318| 0| if (utf8) { ------------------ | Branch (1318:15): [True: 0, False: 0] ------------------ 1319| 0| mystrrep(j, "\xC3\x9F", "SS"); 1320| 0| } else { 1321| 0| mystrrep(j, "\xDF", "SS"); 1322| 0| } 1323| 0| } 1324| 473| } 1325| 9.14k| break; 1326| 9.14k| } 1327| 67.4k| } 1328| | 1329| | // LANG_hu section: replace '-' with ' ' in Hungarian 1330| 67.4k| if (langnum == LANG_hu) { ------------------ | Branch (1330:7): [True: 3.70k, False: 63.7k] ------------------ 1331| 3.70k| for (auto& j : slst) { ------------------ | Branch (1331:18): [True: 314, False: 3.70k] ------------------ 1332| 314| size_t pos = j.find('-'); 1333| 314| if (pos != std::string::npos) { ------------------ | Branch (1333:11): [True: 89, False: 225] ------------------ 1334| 89| int info = 0; 1335| 89| std::string w(j.substr(0, pos)); 1336| 89| w.append(j.substr(pos + 1)); 1337| 89| (void)spell(w, spell_candidate_stack, &info, nullptr, suggest_start); 1338| 89| if ((info & SPELL_COMPOUND) && (info & SPELL_FORBIDDEN)) { ------------------ | | 78| 89|#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 (1338:13): [True: 0, False: 89] | Branch (1338:40): [True: 0, False: 0] ------------------ 1339| 0| j[pos] = ' '; 1340| 0| } else 1341| 89| j[pos] = '-'; 1342| 89| } 1343| 314| } 1344| 3.70k| } 1345| | // END OF LANG_hu section 1346| | // try ngram approach since found nothing good suggestion 1347| 67.4k| if (!good && pAMgr && (slst.empty() || onlycmpdsug) && (pAMgr->get_maxngramsugs() != 0)) { ------------------ | Branch (1347:7): [True: 67.3k, False: 56] | Branch (1347:16): [True: 67.3k, False: 0] | Branch (1347:26): [True: 59.6k, False: 7.68k] | Branch (1347:42): [True: 7.51k, False: 171] | Branch (1347:58): [True: 59.9k, False: 7.29k] ------------------ 1348| 59.9k| switch (captype) { ------------------ | Branch (1348:13): [True: 59.9k, False: 0] ------------------ 1349| 17.5k| case NOCAP: { ------------------ | | 92| 17.5k|#define NOCAP 0 ------------------ | Branch (1349:7): [True: 17.5k, False: 42.4k] ------------------ 1350| 17.5k| pSMgr->ngsuggest(slst, scw.c_str(), m_HMgrs, NOCAP); ------------------ | | 92| 17.5k|#define NOCAP 0 ------------------ 1351| 17.5k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 17.5k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1351:13): [True: 0, False: 17.5k] ------------------ 1352| 0| return slst; 1353| 17.5k| break; 1354| 17.5k| } 1355| | /* FALLTHROUGH */ 1356| 17.5k| case HUHINITCAP: ------------------ | | 96| 12.6k|#define HUHINITCAP 4 ------------------ | Branch (1356:7): [True: 12.6k, False: 47.3k] ------------------ 1357| 12.6k| capwords = true; 1358| | /* FALLTHROUGH */ 1359| 24.8k| case HUHCAP: { ------------------ | | 95| 24.8k|#define HUHCAP 3 ------------------ | Branch (1359:7): [True: 12.2k, False: 47.6k] ------------------ 1360| 24.8k| std::string wspace(scw); 1361| 24.8k| mkallsmall2(wspace, sunicw); 1362| 24.8k| pSMgr->ngsuggest(slst, wspace.c_str(), m_HMgrs, HUHCAP); ------------------ | | 95| 24.8k|#define HUHCAP 3 ------------------ 1363| 24.8k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 24.8k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1363:13): [True: 0, False: 24.8k] ------------------ 1364| 0| return slst; 1365| 24.8k| break; 1366| 24.8k| } 1367| 24.8k| case INITCAP: { ------------------ | | 93| 9.56k|#define INITCAP 1 ------------------ | Branch (1367:7): [True: 9.56k, False: 50.3k] ------------------ 1368| 9.56k| capwords = true; 1369| 9.56k| std::string wspace(scw); 1370| 9.56k| mkallsmall2(wspace, sunicw); 1371| 9.56k| pSMgr->ngsuggest(slst, wspace.c_str(), m_HMgrs, INITCAP); ------------------ | | 93| 9.56k|#define INITCAP 1 ------------------ 1372| 9.56k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 9.56k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1372:13): [True: 0, False: 9.56k] ------------------ 1373| 0| return slst; 1374| 9.56k| break; 1375| 9.56k| } 1376| 9.56k| case ALLCAP: { ------------------ | | 94| 8.01k|#define ALLCAP 2 ------------------ | Branch (1376:7): [True: 8.01k, False: 51.8k] ------------------ 1377| 8.01k| std::string wspace(scw); 1378| 8.01k| mkallsmall2(wspace, sunicw); 1379| 8.01k| size_t oldns = slst.size(); 1380| 8.01k| pSMgr->ngsuggest(slst, wspace.c_str(), m_HMgrs, ALLCAP); ------------------ | | 94| 8.01k|#define ALLCAP 2 ------------------ 1381| 8.01k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 8.01k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1381:13): [True: 0, False: 8.01k] ------------------ 1382| 0| return slst; 1383| 9.84k| for (size_t j = oldns; j < slst.size(); ++j) { ------------------ | Branch (1383:32): [True: 1.83k, False: 8.01k] ------------------ 1384| 1.83k| mkallcap(slst[j]); 1385| 1.83k| } 1386| 8.01k| break; 1387| 8.01k| } 1388| 59.9k| } 1389| 59.9k| } 1390| | 1391| | // try dash suggestion (Afo-American -> Afro-American) 1392| | // Note: LibreOffice was modified to treat dashes as word 1393| | // characters to check "scot-free" etc. word forms, but 1394| | // we need to handle suggestions for "Afo-American", etc., 1395| | // while "Afro-American" is missing from the dictionary. 1396| | // TODO avoid possible overgeneration 1397| 67.4k| size_t dash_pos = scw.find('-'); 1398| 67.4k| if (dash_pos != std::string::npos) { ------------------ | Branch (1398:7): [True: 33.2k, False: 34.2k] ------------------ 1399| 33.2k| int nodashsug = 1; 1400| 40.7k| for (size_t j = 0; j < slst.size() && nodashsug == 1; ++j) { ------------------ | Branch (1400:24): [True: 8.02k, False: 32.7k] | Branch (1400:43): [True: 7.57k, False: 456] ------------------ 1401| 7.57k| if (slst[j].find('-') != std::string::npos) ------------------ | Branch (1401:11): [True: 3.97k, False: 3.59k] ------------------ 1402| 3.97k| nodashsug = 0; 1403| 7.57k| } 1404| | 1405| 33.2k| size_t prev_pos = 0; 1406| 33.2k| bool last = false; 1407| | 1408| 104k| while (!good && nodashsug && !last) { ------------------ | Branch (1408:12): [True: 104k, False: 33] | Branch (1408:21): [True: 71.7k, False: 32.5k] | Branch (1408:34): [True: 71.1k, False: 620] ------------------ 1409| 71.1k| if (dash_pos == scw.size()) ------------------ | Branch (1409:11): [True: 5.81k, False: 65.3k] ------------------ 1410| 5.81k| last = true; 1411| 71.1k| std::string chunk = scw.substr(prev_pos, dash_pos - prev_pos); 1412| 71.1k| if (chunk != word && !spell(chunk, spell_candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1412:11): [True: 71.1k, False: 0] | Branch (1412:28): [True: 28.5k, False: 42.5k] ------------------ 1413| 28.5k| std::vector nlst = suggest(chunk, suggest_candidate_stack, suggest_start); 1414| 28.5k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 28.5k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1414:13): [True: 0, False: 28.5k] ------------------ 1415| 0| return slst; 1416| 38.3k| for (auto j = nlst.rbegin(); j != nlst.rend(); ++j) { ------------------ | Branch (1416:38): [True: 9.79k, False: 28.5k] ------------------ 1417| 9.79k| std::string wspace = scw.substr(0, prev_pos); 1418| 9.79k| wspace.append(*j); 1419| 9.79k| if (!last) { ------------------ | Branch (1419:15): [True: 7.93k, False: 1.85k] ------------------ 1420| 7.93k| wspace.append("-"); 1421| 7.93k| wspace.append(scw.substr(dash_pos + 1)); 1422| 7.93k| } 1423| 9.79k| int info = 0; 1424| 9.79k| if (pAMgr && pAMgr->get_forbiddenword()) ------------------ | Branch (1424:15): [True: 9.79k, False: 0] | Branch (1424:24): [True: 9.79k, False: 0] ------------------ 1425| 9.79k| checkword(wspace, &info, nullptr, suggest_start); 1426| 9.79k| if (!(info & SPELL_FORBIDDEN)) ------------------ | | 79| 9.79k|#define SPELL_FORBIDDEN (1 << 1) ------------------ | Branch (1426:15): [True: 9.79k, False: 0] ------------------ 1427| 9.79k| insert_sug(slst, wspace); 1428| 9.79k| } 1429| 28.5k| nodashsug = 0; 1430| 28.5k| } 1431| 71.1k| if (!last) { ------------------ | Branch (1431:11): [True: 65.3k, False: 5.81k] ------------------ 1432| 65.3k| prev_pos = dash_pos + 1; 1433| 65.3k| dash_pos = scw.find('-', prev_pos); 1434| 65.3k| } 1435| 71.1k| if (dash_pos == std::string::npos) ------------------ | Branch (1435:11): [True: 12.7k, False: 58.4k] ------------------ 1436| 12.7k| dash_pos = scw.size(); 1437| 71.1k| } 1438| 33.2k| } 1439| 67.4k| return slst; 1440| 67.4k|} _ZN12HunspellImpl4stemERKNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEE: 1446| 1.04k|std::vector HunspellImpl::stem(const std::vector& desc) { 1447| 1.04k| std::vector slst; 1448| | 1449| 1.04k| std::string result2; 1450| 1.04k| if (desc.empty()) ------------------ | Branch (1450:7): [True: 975, False: 70] ------------------ 1451| 975| return slst; 1452| 80| for (const auto& i : desc) { ------------------ | Branch (1452:22): [True: 80, False: 70] ------------------ 1453| 80| std::string result; 1454| | 1455| | // add compound word parts (except the last one) 1456| 80| std::string tok(i, append_compound_parts(i, result)); 1457| 80| size_t alt = 0; 1458| 80| while ((alt = tok.find(" | ", alt)) != std::string::npos) { ------------------ | Branch (1458:12): [True: 0, False: 80] ------------------ 1459| 0| tok[alt + 1] = MSEP_ALT; ------------------ | | 123| 0|#define MSEP_ALT '\v' ------------------ 1460| 0| } 1461| 80| std::vector pl = line_tok(tok, MSEP_ALT); ------------------ | | 123| 80|#define MSEP_ALT '\v' ------------------ 1462| 80| for (auto& k : pl) { ------------------ | Branch (1462:18): [True: 80, False: 80] ------------------ 1463| | // add derivational suffixes 1464| 80| if (k.find(MORPH_DERI_SFX) != std::string::npos) { ------------------ | | 109| 80|#define MORPH_DERI_SFX "ds:" ------------------ | Branch (1464:11): [True: 0, False: 80] ------------------ 1465| | // remove inflectional suffixes 1466| 0| const size_t is = k.find(MORPH_INFL_SFX); ------------------ | | 110| 0|#define MORPH_INFL_SFX "is:" ------------------ 1467| 0| if (is != std::string::npos) ------------------ | Branch (1467:13): [True: 0, False: 0] ------------------ 1468| 0| k.resize(is); 1469| 0| std::vector singlepl; 1470| 0| singlepl.push_back(k); 1471| 0| std::string sg = pSMgr->suggest_gen(singlepl, k); 1472| 0| if (!sg.empty()) { ------------------ | Branch (1472:13): [True: 0, False: 0] ------------------ 1473| 0| std::vector gen = line_tok(sg, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1474| 0| for (auto& j : gen) { ------------------ | Branch (1474:24): [True: 0, False: 0] ------------------ 1475| 0| result2.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1476| 0| result2.append(result); 1477| 0| result2.append(j); 1478| 0| } 1479| 0| } 1480| 80| } else { 1481| 80| result2.push_back(MSEP_REC); ------------------ | | 122| 80|#define MSEP_REC '\n' ------------------ 1482| 80| result2.append(result); 1483| 80| if (k.find(MORPH_SURF_PFX) != std::string::npos) { ------------------ | | 112| 80|#define MORPH_SURF_PFX "sp:" ------------------ | Branch (1483:13): [True: 0, False: 80] ------------------ 1484| 0| std::string field; 1485| 0| copy_field(field, k, MORPH_SURF_PFX); ------------------ | | 112| 0|#define MORPH_SURF_PFX "sp:" ------------------ 1486| 0| result2.append(field); 1487| 0| } 1488| 80| std::string field; 1489| 80| copy_field(field, k, MORPH_STEM); ------------------ | | 103| 80|#define MORPH_STEM "st:" ------------------ 1490| 80| result2.append(field); 1491| 80| } 1492| 80| } 1493| 80| } 1494| 70| slst = line_tok(result2, MSEP_REC); ------------------ | | 122| 70|#define MSEP_REC '\n' ------------------ 1495| 70| uniqlist(slst); 1496| 70| return slst; 1497| 1.04k|} _ZN12HunspellImpl4stemERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1499| 1.04k|std::vector HunspellImpl::stem(const std::string& word) { 1500| 1.04k| return stem(analyze(word)); 1501| 1.04k|} _ZN12HunspellImpl9mkinitcapERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1511| 16.0k|void HunspellImpl::mkinitcap(std::string& u8) { 1512| 16.0k| if (utf8) { ------------------ | Branch (1512:7): [True: 5.03k, False: 10.9k] ------------------ 1513| 5.03k| std::vector u16; 1514| 5.03k| u8_u16(u16, u8); 1515| 5.03k| ::mkinitcap_utf(u16, langnum); 1516| 5.03k| u16_u8(u8, u16); 1517| 10.9k| } else { 1518| 10.9k| ::mkinitcap(u8, csconv); 1519| 10.9k| } 1520| 16.0k|} _ZN12HunspellImpl10mkinitcap2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEE: 1522| 1.44M|int HunspellImpl::mkinitcap2(std::string& u8, std::vector& u16) { 1523| 1.44M| if (utf8) { ------------------ | Branch (1523:7): [True: 311k, False: 1.13M] ------------------ 1524| 311k| ::mkinitcap_utf(u16, langnum); 1525| 311k| u16_u8(u8, u16); 1526| 1.13M| } else { 1527| 1.13M| ::mkinitcap(u8, csconv); 1528| 1.13M| } 1529| 1.44M| return u8.size(); 1530| 1.44M|} _ZN12HunspellImpl12mkinitsmall2ERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERNS0_6vectorI6w_charNS4_IS9_EEEE: 1532| 247k|int HunspellImpl::mkinitsmall2(std::string& u8, std::vector& u16) { 1533| 247k| if (utf8) { ------------------ | Branch (1533:7): [True: 31.1k, False: 216k] ------------------ 1534| 31.1k| ::mkinitsmall_utf(u16, langnum); 1535| 31.1k| u16_u8(u8, u16); 1536| 216k| } else { 1537| 216k| ::mkinitsmall(u8, csconv); 1538| 216k| } 1539| 247k| return u8.size(); 1540| 247k|} _ZN12HunspellImpl3addERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1542| 5.18k|int HunspellImpl::add(const std::string& word) { 1543| 5.18k| if (!m_HMgrs.empty()) ------------------ | Branch (1543:7): [True: 5.18k, False: 0] ------------------ 1544| 5.18k| return m_HMgrs[0]->add(word); 1545| 0| return 0; 1546| 5.18k|} _ZN12HunspellImpl14add_with_affixERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 1554| 2.03k|int HunspellImpl::add_with_affix(const std::string& word, const std::string& example) { 1555| 2.03k| if (!m_HMgrs.empty()) ------------------ | Branch (1555:7): [True: 2.03k, False: 0] ------------------ 1556| 2.03k| return m_HMgrs[0]->add_with_affix(word, example); 1557| 0| return 0; 1558| 2.03k|} _ZN12HunspellImpl10cat_resultERNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKS6_: 1577| 362k|void HunspellImpl::cat_result(std::string& result, const std::string& st) { 1578| 362k| if (!st.empty()) { ------------------ | Branch (1578:7): [True: 2.10k, False: 360k] ------------------ 1579| 2.10k| if (!result.empty()) ------------------ | Branch (1579:9): [True: 0, False: 2.10k] ------------------ 1580| 0| result.append("\n"); 1581| 2.10k| result.append(st); 1582| 2.10k| } 1583| 362k|} _ZN12HunspellImpl7analyzeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1585| 7.10k|std::vector HunspellImpl::analyze(const std::string& word) { 1586| 7.10k| std::vector slst = analyze_internal(word); 1587| | // output conversion 1588| 7.10k| RepList* rl = (pAMgr) ? pAMgr->get_oconvtable() : nullptr; ------------------ | Branch (1588:17): [True: 7.10k, False: 0] ------------------ 1589| 7.10k| if (rl) { ------------------ | Branch (1589:7): [True: 372, False: 6.73k] ------------------ 1590| | // the output conversion can multiply the length of every line, so hold the 1591| | // converted analysis to the same ceiling as the raw analysis 1592| 372| size_t total = 0; 1593| 372| size_t i = 0; 1594| 448| for (; i < slst.size(); ++i) { ------------------ | Branch (1594:12): [True: 76, False: 372] ------------------ 1595| 76| std::string wspace; 1596| 76| if (rl->conv(slst[i], wspace)) { ------------------ | Branch (1596:11): [True: 0, False: 76] ------------------ 1597| 0| slst[i] = std::move(wspace); 1598| 0| } 1599| 76| total += slst[i].size(); 1600| 76| if (total > MAXMORPHRESULT) { ------------------ | | 111| 76|#define MAXMORPHRESULT (4 * 1024 * 1024) ------------------ | Branch (1600:11): [True: 0, False: 76] ------------------ 1601| 0| ++i; 1602| 0| break; 1603| 0| } 1604| 76| } 1605| 372| slst.resize(i); 1606| 372| } 1607| 7.10k| return slst; 1608| 7.10k|} _ZN12HunspellImpl16analyze_internalERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1610| 7.10k|std::vector HunspellImpl::analyze_internal(const std::string& word) { 1611| 7.10k| std::vector candidate_stack, slst; 1612| 7.10k| if (!pSMgr || m_HMgrs.empty()) ------------------ | Branch (1612:7): [True: 0, False: 7.10k] | Branch (1612:17): [True: 0, False: 7.10k] ------------------ 1613| 0| return slst; 1614| 7.10k| if (utf8) { ------------------ | Branch (1614:7): [True: 3.35k, False: 3.75k] ------------------ 1615| 3.35k| if (word.size() >= MAXWORDUTF8LEN) ------------------ | | 86| 3.35k|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 3.35k|#define MAXWORDLEN 100 | | ------------------ ------------------ | Branch (1615:9): [True: 360, False: 2.99k] ------------------ 1616| 360| return slst; 1617| 3.75k| } else { 1618| 3.75k| if (word.size() >= MAXWORDLEN) ------------------ | | 90| 3.75k|#define MAXWORDLEN 100 ------------------ | Branch (1618:9): [True: 600, False: 3.15k] ------------------ 1619| 600| return slst; 1620| 3.75k| } 1621| 6.14k| int captype = NOCAP; ------------------ | | 92| 6.14k|#define NOCAP 0 ------------------ 1622| 6.14k| size_t abbv = 0; 1623| 6.14k| size_t wl = 0; 1624| | 1625| 6.14k| std::string scw; 1626| 6.14k| std::vector sunicw; 1627| | 1628| | // input conversion 1629| 6.14k| RepList* rl = (pAMgr) ? pAMgr->get_iconvtable() : nullptr; ------------------ | Branch (1629:17): [True: 6.14k, False: 0] ------------------ 1630| 6.14k| { 1631| 6.14k| std::string wspace; 1632| | 1633| 6.14k| bool convstatus = rl ? rl->conv(word, wspace) : false; ------------------ | Branch (1633:23): [True: 332, False: 5.81k] ------------------ 1634| 6.14k| if (convstatus) { ------------------ | Branch (1634:9): [True: 0, False: 6.14k] ------------------ 1635| | // the input conversion can grow the word without limit, so hold the 1636| | // converted word to the same maximum length as the raw word 1637| 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 (1637:11): [True: 0, False: 0] | Branch (1637:11): [True: 0, False: 0] ------------------ 1638| 0| return slst; 1639| 0| wl = cleanword2(scw, sunicw, wspace, &captype, &abbv); 1640| 0| } else 1641| 6.14k| wl = cleanword2(scw, sunicw, word, &captype, &abbv); 1642| | 1643| 6.14k|#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) 1644| 6.14k| if (wl > 32768) ------------------ | Branch (1644:9): [True: 0, False: 6.14k] ------------------ 1645| 0| return slst; 1646| 6.14k|#endif 1647| 6.14k| } 1648| | 1649| 6.14k| if (wl == 0) { ------------------ | Branch (1649:7): [True: 411, False: 5.73k] ------------------ 1650| 411| if (abbv) { ------------------ | Branch (1650:9): [True: 247, False: 164] ------------------ 1651| 247| scw.clear(); 1652| 4.57k| for (wl = 0; wl < abbv; wl++) ------------------ | Branch (1652:20): [True: 4.33k, False: 247] ------------------ 1653| 4.33k| scw.push_back('.'); 1654| 247| abbv = 0; 1655| 247| } else 1656| 164| return slst; 1657| 411| } 1658| | 1659| 5.98k| std::string result; 1660| | 1661| 5.98k| auto suggest_start = std::chrono::steady_clock::now(); 1662| | 1663| 5.98k| size_t n = 0; 1664| | // test numbers 1665| | // LANG_hu section: set dash information for suggestions 1666| 5.98k| if (langnum == LANG_hu) { ------------------ | Branch (1666:7): [True: 324, False: 5.65k] ------------------ 1667| 324| size_t n2 = 0; 1668| 324| size_t n3 = 0; 1669| | 1670| 478| while ((n < wl) && (((scw[n] <= '9') && (scw[n] >= '0')) || ------------------ | Branch (1670:12): [True: 458, False: 20] | Branch (1670:26): [True: 252, False: 206] | Branch (1670:45): [True: 154, False: 98] ------------------ 1671| 304| (((scw[n] == '.') || (scw[n] == ',')) && (n > 0)))) { ------------------ | Branch (1671:27): [True: 22, False: 282] | Branch (1671:46): [True: 0, False: 282] | Branch (1671:66): [True: 0, False: 22] ------------------ 1672| 154| n++; 1673| 154| if ((scw[n] == '.') || (scw[n] == ',')) { ------------------ | Branch (1673:11): [True: 0, False: 154] | Branch (1673:30): [True: 0, False: 154] ------------------ 1674| 0| if (((n2 == 0) && (n > 3)) || ------------------ | Branch (1674:14): [True: 0, False: 0] | Branch (1674:27): [True: 0, False: 0] ------------------ 1675| 0| ((n2 > 0) && ((scw[n - 1] == '.') || (scw[n - 1] == ',')))) ------------------ | Branch (1675:14): [True: 0, False: 0] | Branch (1675:27): [True: 0, False: 0] | Branch (1675:50): [True: 0, False: 0] ------------------ 1676| 0| break; 1677| 0| n2++; 1678| 0| n3 = n; 1679| 0| } 1680| 154| } 1681| | 1682| 324| if ((n == wl) && (n3 > 0) && (n - n3 > 3)) ------------------ | Branch (1682:9): [True: 20, False: 304] | Branch (1682:22): [True: 0, False: 20] | Branch (1682:34): [True: 0, False: 0] ------------------ 1683| 0| return slst; 1684| 324| if ((n == wl) || ((n > 0) && ((scw[n] == '%') || (scw[n] == '\xB0')) && checkword(scw.substr(n), nullptr, nullptr, suggest_start))) { ------------------ | Branch (1684:9): [True: 20, False: 304] | Branch (1684:9): [True: 20, False: 304] | Branch (1684:23): [True: 8, False: 296] | Branch (1684:35): [True: 0, False: 8] | Branch (1684:54): [True: 0, False: 8] | Branch (1684:77): [True: 0, False: 0] ------------------ 1685| 20| result.append(scw); 1686| 20| result.resize(n - 1); 1687| 20| if (n == wl) ------------------ | Branch (1687:11): [True: 20, False: 0] ------------------ 1688| 20| cat_result(result, pSMgr->suggest_morph(scw.substr(n - 1))); 1689| 0| else { 1690| 0| std::string chunk = scw.substr(n - 1, 1); 1691| 0| cat_result(result, pSMgr->suggest_morph(chunk)); 1692| 0| result.push_back('+'); // XXX SPEC. MORPHCODE 1693| 0| cat_result(result, pSMgr->suggest_morph(scw.substr(n))); 1694| 0| } 1695| 20| return line_tok(result, MSEP_REC); ------------------ | | 122| 20|#define MSEP_REC '\n' ------------------ 1696| 20| } 1697| 324| } 1698| | // END OF LANG_hu section 1699| | 1700| 5.96k| switch (captype) { ------------------ | Branch (1700:11): [True: 5.96k, False: 0] ------------------ 1701| 289| case HUHCAP: ------------------ | | 95| 289|#define HUHCAP 3 ------------------ | Branch (1701:5): [True: 289, False: 5.67k] ------------------ 1702| 627| case HUHINITCAP: ------------------ | | 96| 627|#define HUHINITCAP 4 ------------------ | Branch (1702:5): [True: 338, False: 5.62k] ------------------ 1703| 3.18k| case NOCAP: { ------------------ | | 92| 3.18k|#define NOCAP 0 ------------------ | Branch (1703:5): [True: 2.55k, False: 3.40k] ------------------ 1704| 3.18k| cat_result(result, pSMgr->suggest_morph(scw)); 1705| 3.18k| if (abbv) { ------------------ | Branch (1705:11): [True: 289, False: 2.89k] ------------------ 1706| 289| std::string u8buffer(scw); 1707| 289| u8buffer.push_back('.'); 1708| 289| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1709| 289| } 1710| 3.18k| break; 1711| 627| } 1712| 1.72k| case INITCAP: { ------------------ | | 93| 1.72k|#define INITCAP 1 ------------------ | Branch (1712:5): [True: 1.72k, False: 4.23k] ------------------ 1713| 1.72k| mkallsmall2(scw, sunicw); 1714| 1.72k| std::string u8buffer(scw); 1715| 1.72k| mkinitcap2(scw, sunicw); 1716| 1.72k| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1717| 1.72k| cat_result(result, pSMgr->suggest_morph(scw)); 1718| 1.72k| if (abbv) { ------------------ | Branch (1718:11): [True: 183, False: 1.54k] ------------------ 1719| 183| u8buffer.push_back('.'); 1720| 183| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1721| | 1722| 183| u8buffer = scw; 1723| 183| u8buffer.push_back('.'); 1724| | 1725| 183| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1726| 183| } 1727| 1.72k| break; 1728| 627| } 1729| 1.04k| case ALLCAP: { ------------------ | | 94| 1.04k|#define ALLCAP 2 ------------------ | Branch (1729:5): [True: 1.04k, False: 4.91k] ------------------ 1730| 1.04k| cat_result(result, pSMgr->suggest_morph(scw)); 1731| 1.04k| if (abbv) { ------------------ | Branch (1731:11): [True: 110, False: 938] ------------------ 1732| 110| std::string u8buffer(scw); 1733| 110| u8buffer.push_back('.'); 1734| 110| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1735| 110| } 1736| 1.04k| mkallsmall2(scw, sunicw); 1737| 1.04k| std::string u8buffer(scw); 1738| 1.04k| mkinitcap2(scw, sunicw); 1739| | 1740| 1.04k| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1741| 1.04k| cat_result(result, pSMgr->suggest_morph(scw)); 1742| 1.04k| if (abbv) { ------------------ | Branch (1742:11): [True: 110, False: 938] ------------------ 1743| 110| u8buffer.push_back('.'); 1744| 110| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1745| | 1746| 110| u8buffer = scw; 1747| 110| u8buffer.push_back('.'); 1748| | 1749| 110| cat_result(result, pSMgr->suggest_morph(u8buffer)); 1750| 110| } 1751| 1.04k| break; 1752| 627| } 1753| 5.96k| } 1754| | 1755| 5.96k| if (!result.empty()) { ------------------ | Branch (1755:7): [True: 2.09k, False: 3.86k] ------------------ 1756| | // word reversing wrapper for complex prefixes 1757| 2.09k| if (complexprefixes) { ------------------ | Branch (1757:9): [True: 137, False: 1.95k] ------------------ 1758| 137| if (utf8) ------------------ | Branch (1758:11): [True: 0, False: 137] ------------------ 1759| 0| reverseword_utf(result); 1760| 137| else 1761| 137| reverseword(result); 1762| 137| } 1763| 2.09k| return line_tok(result, MSEP_REC); ------------------ | | 122| 2.09k|#define MSEP_REC '\n' ------------------ 1764| 2.09k| } 1765| | 1766| | // compound word with dash (HU) I18n 1767| | // LANG_hu section: set dash information for suggestions 1768| | 1769| 3.86k| size_t dash_pos = langnum == LANG_hu ? scw.find('-') : std::string::npos; ------------------ | Branch (1769:21): [True: 240, False: 3.62k] ------------------ 1770| 3.86k| if (dash_pos != std::string::npos) { ------------------ | Branch (1770:7): [True: 20, False: 3.84k] ------------------ 1771| 20| int nresult = 0; 1772| | 1773| 20| std::string part1 = scw.substr(0, dash_pos), part2 = scw.substr(dash_pos + 1); 1774| | 1775| | // examine 2 sides of the dash 1776| 20| if (part2.empty()) { // base word ending with dash ------------------ | Branch (1776:9): [True: 6, False: 14] ------------------ 1777| 6| if (spell(part1, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1777:11): [True: 1, False: 5] ------------------ 1778| 1| std::string p = pSMgr->suggest_morph(part1); 1779| 1| if (!p.empty()) { ------------------ | Branch (1779:13): [True: 0, False: 1] ------------------ 1780| 0| slst = line_tok(p, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1781| 0| return slst; 1782| 0| } 1783| 1| } 1784| 14| } else if (part2.size() == 1 && part2[0] == 'e') { // XXX (HU) -e hat. ------------------ | Branch (1784:16): [True: 1, False: 13] | Branch (1784:37): [True: 0, False: 1] ------------------ 1785| 0| if (spell(part1, candidate_stack, nullptr, nullptr, suggest_start) && ------------------ | Branch (1785:11): [True: 0, False: 0] | Branch (1785:11): [True: 0, False: 0] ------------------ 1786| 0| (spell("-e", candidate_stack, nullptr, nullptr, suggest_start))) { ------------------ | Branch (1786:11): [True: 0, False: 0] ------------------ 1787| 0| std::string st = pSMgr->suggest_morph(part1); 1788| 0| if (!st.empty()) { ------------------ | Branch (1788:13): [True: 0, False: 0] ------------------ 1789| 0| result.append(st); 1790| 0| } 1791| 0| result.push_back('+'); // XXX spec. separator in MORPHCODE 1792| 0| st = pSMgr->suggest_morph("-e"); 1793| 0| if (!st.empty()) { ------------------ | Branch (1793:13): [True: 0, False: 0] ------------------ 1794| 0| result.append(st); 1795| 0| } 1796| 0| return line_tok(result, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1797| 0| } 1798| 14| } else { 1799| | // first word ending with dash: word- XXX ??? 1800| 14| part1.push_back(' '); 1801| 14| nresult = spell(part1, candidate_stack, nullptr, nullptr, suggest_start); 1802| 14| part1.erase(part1.size() - 1); 1803| 14| if (nresult && spell(part2, candidate_stack, nullptr, nullptr, suggest_start) && ------------------ | Branch (1803:11): [True: 0, False: 14] | Branch (1803:22): [True: 0, False: 0] ------------------ 1804| 0| ((part2.size() > 1) || ((part2[0] > '0') && (part2[0] < '9')))) { ------------------ | Branch (1804:12): [True: 0, False: 0] | Branch (1804:35): [True: 0, False: 0] | Branch (1804:55): [True: 0, False: 0] ------------------ 1805| 0| std::string st = pSMgr->suggest_morph(part1); 1806| 0| if (!st.empty()) { ------------------ | Branch (1806:13): [True: 0, False: 0] ------------------ 1807| 0| result.append(st); 1808| 0| result.push_back('+'); // XXX spec. separator in MORPHCODE 1809| 0| } 1810| 0| st = pSMgr->suggest_morph(part2); 1811| 0| if (!st.empty()) { ------------------ | Branch (1811:13): [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| 14| } 1817| | // affixed number in correct word 1818| 20| if (nresult && (dash_pos > 0) && ------------------ | Branch (1818:9): [True: 0, False: 20] | Branch (1818:20): [True: 0, False: 0] ------------------ 1819| 0| (((scw[dash_pos - 1] <= '9') && (scw[dash_pos - 1] >= '0')) || ------------------ | Branch (1819:11): [True: 0, False: 0] | Branch (1819:41): [True: 0, False: 0] ------------------ 1820| 0| (scw[dash_pos - 1] == '.'))) { ------------------ | Branch (1820:10): [True: 0, False: 0] ------------------ 1821| 0| n = 1; 1822| 0| if (scw[dash_pos - n] == '.') ------------------ | Branch (1822:11): [True: 0, False: 0] ------------------ 1823| 0| n++; 1824| | // search first not a number character to left from dash 1825| 0| while ((dash_pos >= n) && ((scw[dash_pos - n] == '0') || (n < 3)) && ------------------ | Branch (1825:14): [True: 0, False: 0] | Branch (1825:34): [True: 0, False: 0] | Branch (1825:64): [True: 0, False: 0] ------------------ 1826| 0| (n < 6)) { ------------------ | Branch (1826:14): [True: 0, False: 0] ------------------ 1827| 0| n++; 1828| 0| } 1829| 0| if (dash_pos < n) ------------------ | Branch (1829:11): [True: 0, False: 0] ------------------ 1830| 0| n--; 1831| | // numbers: valami1000000-hoz 1832| | // examine 100000-hoz, 10000-hoz 1000-hoz, 10-hoz, 1833| | // 56-hoz, 6-hoz 1834| 0| for (; n >= 1; n--) { ------------------ | Branch (1834:14): [True: 0, False: 0] ------------------ 1835| 0| if (scw[dash_pos - n] < '0' || scw[dash_pos - n] > '9') { ------------------ | Branch (1835:13): [True: 0, False: 0] | Branch (1835:40): [True: 0, False: 0] ------------------ 1836| 0| continue; 1837| 0| } 1838| 0| std::string chunk = scw.substr(dash_pos - n); 1839| 0| if (checkword(chunk, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1839:13): [True: 0, False: 0] ------------------ 1840| 0| result.append(chunk); 1841| 0| std::string st = pSMgr->suggest_morph(chunk); 1842| 0| if (!st.empty()) { ------------------ | Branch (1842:15): [True: 0, False: 0] ------------------ 1843| 0| result.append(st); 1844| 0| } 1845| 0| return line_tok(result, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1846| 0| } 1847| 0| } 1848| 0| } 1849| 20| } 1850| 3.86k| return slst; 1851| 3.86k|} _ZN12HunspellImpl8generateERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERKNS0_6vectorIS6_NS4_IS6_EEEE: 1853| 5.77k|std::vector HunspellImpl::generate(const std::string& word, const std::vector& pl) { 1854| 5.77k| std::vector slst; 1855| 5.77k| if (!pSMgr || pl.empty()) ------------------ | Branch (1855:7): [True: 0, False: 5.77k] | Branch (1855:17): [True: 420, False: 5.35k] ------------------ 1856| 420| return slst; 1857| 5.35k| std::vector pl2 = analyze(word); 1858| 5.35k| int captype = NOCAP, abbv = 0; ------------------ | | 92| 5.35k|#define NOCAP 0 ------------------ 1859| 5.35k| std::string cw; 1860| 5.35k| cleanword(cw, word, &captype, &abbv); 1861| 5.35k| std::string result; 1862| | 1863| 5.35k| auto suggest_start = std::chrono::steady_clock::now(); 1864| 351k| for (const auto& i : pl) { ------------------ | Branch (1864:22): [True: 351k, False: 5.35k] ------------------ 1865| 351k| cat_result(result, pSMgr->suggest_gen(pl2, i, suggest_start)); 1866| 351k| } 1867| | 1868| 5.35k| if (!result.empty()) { ------------------ | Branch (1868:7): [True: 0, False: 5.35k] ------------------ 1869| | // allcap 1870| 0| if (captype == ALLCAP) ------------------ | | 94| 0|#define ALLCAP 2 ------------------ | Branch (1870:9): [True: 0, False: 0] ------------------ 1871| 0| mkallcap(result); 1872| | 1873| | // line split 1874| 0| slst = line_tok(result, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 1875| | 1876| | // capitalize 1877| 0| if (captype == INITCAP || captype == HUHINITCAP) { ------------------ | | 93| 0|#define INITCAP 1 ------------------ if (captype == INITCAP || captype == HUHINITCAP) { ------------------ | | 96| 0|#define HUHINITCAP 4 ------------------ | Branch (1877:9): [True: 0, False: 0] | Branch (1877:31): [True: 0, False: 0] ------------------ 1878| 0| for (auto& str : slst) { ------------------ | Branch (1878:22): [True: 0, False: 0] ------------------ 1879| 0| mkinitcap(str); 1880| 0| } 1881| 0| } 1882| | 1883| | // temporary filtering of prefix related errors (eg. 1884| | // generate("undrinkable", "eats") --> "undrinkables" and "*undrinks") 1885| 0| auto it = slst.begin(); 1886| 0| while (it != slst.end()) { ------------------ | Branch (1886:12): [True: 0, False: 0] ------------------ 1887| 0| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 0|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1887:11): [True: 0, False: 0] ------------------ 1888| 0| break; 1889| 0| std::vector candidate_stack; 1890| 0| if (!spell(*it, candidate_stack, nullptr, nullptr, suggest_start)) { ------------------ | Branch (1890:11): [True: 0, False: 0] ------------------ 1891| 0| it = slst.erase(it); 1892| 0| } else { 1893| 0| ++it; 1894| 0| } 1895| 0| } 1896| 0| } 1897| 5.35k| return slst; 1898| 5.77k|} _ZN12HunspellImpl8generateERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 1900| 551|std::vector HunspellImpl::generate(const std::string& word, const std::string& pattern) { 1901| 551| std::vector pl = analyze(pattern); 1902| 551| std::vector slst = generate(word, pl); 1903| 551| uniqlist(slst); 1904| 551| return slst; 1905| 551|} _ZN12HunspellImpl11get_xml_parERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEm: 1908| 438k|std::string HunspellImpl::get_xml_par(const std::string& in_par, std::string::size_type pos) { 1909| 438k| std::string dest; 1910| 438k| if (pos == std::string::npos) ------------------ | Branch (1910:7): [True: 6.40k, False: 432k] ------------------ 1911| 6.40k| return dest; 1912| 432k| const char* par = in_par.c_str() + pos; 1913| 432k| char end = *par; 1914| 432k| if (end == '>') ------------------ | Branch (1914:7): [True: 429k, False: 3.17k] ------------------ 1915| 429k| end = '<'; 1916| 3.17k| else if (end != '\'' && end != '"') ------------------ | Branch (1916:12): [True: 2.64k, False: 532] | Branch (1916:27): [True: 1.21k, False: 1.42k] ------------------ 1917| 1.21k| return dest; // bad XML 1918| 11.8M| for (par++; *par != '\0' && *par != end; ++par) { ------------------ | Branch (1918:15): [True: 11.8M, False: 33.7k] | Branch (1918:31): [True: 11.4M, False: 397k] ------------------ 1919| 11.4M| dest.push_back(*par); 1920| 11.4M| } 1921| 431k| mystrrep(dest, "<", "<"); 1922| 431k| mystrrep(dest, "&", "&"); 1923| 431k| return dest; 1924| 432k|} _ZN12HunspellImpl11get_xml_posERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEmPKc: 1940| 66.9k|std::string::size_type HunspellImpl::get_xml_pos(const std::string& s, std::string::size_type pos, const char* attr) { 1941| 66.9k| if (pos == std::string::npos) ------------------ | Branch (1941:7): [True: 0, False: 66.9k] ------------------ 1942| 0| return std::string::npos; 1943| | 1944| 66.9k| std::string::size_type endpos = s.find('>', pos); 1945| 66.9k| if (attr == nullptr) ------------------ | Branch (1945:7): [True: 0, False: 66.9k] ------------------ 1946| 0| return endpos; 1947| 212k| while (true) { ------------------ | Branch (1947:10): [True: 212k, Folded] ------------------ 1948| 212k| pos = s.find(attr, pos); 1949| 212k| if (pos == std::string::npos || pos >= endpos) ------------------ | Branch (1949:9): [True: 3.72k, False: 208k] | Branch (1949:37): [True: 1.52k, False: 207k] ------------------ 1950| 5.24k| return std::string::npos; 1951| 207k| if (pos == 0 || s[pos - 1] == ' ' || s[pos - 1] == '\n') ------------------ | Branch (1951:9): [True: 0, False: 207k] | Branch (1951:21): [True: 1.74k, False: 205k] | Branch (1951:42): [True: 59.9k, False: 145k] ------------------ 1952| 61.7k| break; 1953| 145k| pos += strlen(attr); 1954| 145k| } 1955| 61.7k| return pos + strlen(attr); 1956| 66.9k|} _ZN12HunspellImpl13check_xml_parERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEmPKcSA_: 1960| 66.9k| const char* value) { 1961| 66.9k| const std::string cw = get_xml_par(q, get_xml_pos(q, pos, attr)); 1962| 66.9k| return cw == value ? 1 : 0; ------------------ | Branch (1962:10): [True: 16.4k, False: 50.5k] ------------------ 1963| 66.9k|} _ZN12HunspellImpl12get_xml_listERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEmPKc: 1965| 6.09k|std::vector HunspellImpl::get_xml_list(const std::string& list, std::string::size_type pos, const char* tag) { 1966| 6.09k| std::vector slst; 1967| 6.09k| if (pos == std::string::npos) ------------------ | Branch (1967:7): [True: 57, False: 6.04k] ------------------ 1968| 57| return slst; 1969| 357k| while (true) { ------------------ | Branch (1969:10): [True: 357k, Folded] ------------------ 1970| 357k| pos = list.find(tag, pos); 1971| 357k| if (pos == std::string::npos) ------------------ | Branch (1971:9): [True: 5.03k, False: 352k] ------------------ 1972| 5.03k| break; 1973| 352k| std::string cw = get_xml_par(list, pos + strlen(tag) - 1); 1974| 352k| if (cw.empty()) { ------------------ | Branch (1974:9): [True: 1.00k, False: 351k] ------------------ 1975| 1.00k| break; 1976| 1.00k| } 1977| 351k| slst.push_back(std::move(cw)); 1978| 351k| ++pos; 1979| 351k| } 1980| 6.04k| return slst; 1981| 6.09k|} _ZN12HunspellImpl7spellmlERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1983| 20.6k|std::vector HunspellImpl::spellml(const std::string& in_word) { 1984| 20.6k| std::vector slst; 1985| | 1986| 20.6k| std::string::size_type qpos = in_word.find("', qpos); 1991| 20.1k| if (q2pos == std::string::npos) ------------------ | Branch (1991:7): [True: 209, False: 19.9k] ------------------ 1992| 209| return slst; // bad XML input 1993| | 1994| 19.9k| q2pos = in_word.find("', q2pos)); 2000| 551| if (!cw.empty()) ------------------ | Branch (2000:9): [True: 152, False: 399] ------------------ 2001| 152| slst = analyze(cw); 2002| 551| if (slst.empty()) ------------------ | Branch (2002:9): [True: 530, False: 21] ------------------ 2003| 530| return slst; 2004| | // convert the result to ana1ana2 format 2005| 21| std::string r; 2006| 21| r.append(""); 2007| 21| for (auto entry : slst) { ------------------ | Branch (2007:21): [True: 21, False: 21] ------------------ 2008| 21| r.append(""); 2009| | 2010| 21| mystrrep(entry, "\t", " "); 2011| 21| mystrrep(entry, "&", "&"); 2012| 21| mystrrep(entry, "<", "<"); 2013| 21| r.append(entry); 2014| | 2015| 21| r.append(""); 2016| 21| } 2017| 21| r.append(""); 2018| 21| slst.clear(); 2019| 21| slst.push_back(std::move(r)); 2020| 21| return slst; 2021| 19.1k| } else if (check_xml_par(in_word, qpos, "type=", "stem")) { ------------------ | Branch (2021:14): [True: 1.53k, False: 17.5k] ------------------ 2022| 1.53k| std::string cw = get_xml_par(in_word, in_word.find('>', q2pos)); 2023| 1.53k| if (!cw.empty()) ------------------ | Branch (2023:9): [True: 1.04k, False: 494] ------------------ 2024| 1.04k| return stem(cw); 2025| 17.5k| } else if (check_xml_par(in_word, qpos, "type=", "generate")) { ------------------ | Branch (2025:14): [True: 7.01k, False: 10.5k] ------------------ 2026| 7.01k| std::string cw = get_xml_par(in_word, in_word.find('>', q2pos)); 2027| 7.01k| if (cw.empty()) ------------------ | Branch (2027:9): [True: 171, False: 6.84k] ------------------ 2028| 171| return slst; 2029| 6.84k| std::string::size_type q3pos = in_word.find("', q3pos)); 2032| 627| if (!cw2.empty()) { ------------------ | Branch (2032:11): [True: 551, False: 76] ------------------ 2033| 551| return generate(cw, cw2); 2034| 551| } 2035| 6.21k| } else { 2036| 6.21k| q2pos = in_word.find(" slst2 = get_xml_list(in_word, in_word.find('>', q2pos), ""); 2039| 6.09k| if (!slst2.empty()) { ------------------ | Branch (2039:13): [True: 5.22k, False: 874] ------------------ 2040| 5.22k| slst = generate(cw, slst2); 2041| 5.22k| uniqlist(slst); 2042| 5.22k| return slst; 2043| 5.22k| } 2044| 6.09k| } 2045| 6.21k| } 2046| 10.5k| } else if (check_xml_par(in_word, qpos, "type=", "add")) { ------------------ | Branch (2046:14): [True: 7.32k, False: 3.24k] ------------------ 2047| 7.32k| std::string cw = get_xml_par(in_word, in_word.find('>', q2pos)); 2048| 7.32k| if (cw.empty()) ------------------ | Branch (2048:9): [True: 114, False: 7.21k] ------------------ 2049| 114| return slst; 2050| 7.21k| std::string::size_type q3pos = in_word.find("', q3pos)); 2053| 2.22k| if (!cw2.empty()) { ------------------ | Branch (2053:11): [True: 2.03k, False: 190] ------------------ 2054| 2.03k| add_with_affix(cw, cw2); 2055| 2.03k| } else { 2056| 190| add(cw); 2057| 190| } 2058| 4.99k| } else { 2059| 4.99k| add(cw); 2060| 4.99k| } 2061| 7.21k| } 2062| 12.0k| return slst; 2063| 19.6k|} _ZN8HunspellC2EPKcS1_S1_: 2213| 38| : m_Impl(new HunspellImpl(affpath, dpath, key)) { 2214| 38|} _ZN8Hunspell5spellERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPiPS6_: 2225| 60.9k|bool Hunspell::spell(const std::string& word, int* info, std::string* root) { 2226| 60.9k| std::vector candidate_stack; 2227| 60.9k| return m_Impl->spell(word, candidate_stack, info, root, 2228| 60.9k| std::chrono::steady_clock::now()); 2229| 60.9k|} _ZN8Hunspell7suggestERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 2231| 60.4k|std::vector Hunspell::suggest(const std::string& word) { 2232| 60.4k| return m_Impl->suggest(word); 2233| 60.4k|} _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| 9.27k|std::string phonet(const std::string& inword, phonetable& parms) { 70| | 71| 9.27k| int i, k = 0, p, z, k0, n0, p0 = -333; 72| 9.27k| char c; 73| 9.27k| using uchar = unsigned char; 74| | 75| 9.27k| size_t len = inword.size(); 76| 9.27k| if (len > MAXPHONETUTF8LEN) ------------------ | | 35| 9.27k|#define MAXPHONETUTF8LEN (MAXPHONETLEN * 4) | | ------------------ | | | | 34| 9.27k|#define MAXPHONETLEN 256 | | ------------------ ------------------ | Branch (76:7): [True: 0, False: 9.27k] ------------------ 77| 0| return {}; 78| 9.27k| char word[MAXPHONETUTF8LEN + 1]; 79| 9.27k| strncpy(word, inword.c_str(), MAXPHONETUTF8LEN); ------------------ | | 35| 9.27k|#define MAXPHONETUTF8LEN (MAXPHONETLEN * 4) | | ------------------ | | | | 34| 9.27k|#define MAXPHONETLEN 256 | | ------------------ ------------------ 80| 9.27k| word[MAXPHONETUTF8LEN] = '\0'; ------------------ | | 35| 9.27k|#define MAXPHONETUTF8LEN (MAXPHONETLEN * 4) | | ------------------ | | | | 34| 9.27k|#define MAXPHONETLEN 256 | | ------------------ ------------------ 81| | 82| 9.27k| std::string target; 83| | /** check word **/ 84| 9.27k| i = z = 0; 85| 84.3k| while ((c = word[i]) != '\0') { ------------------ | Branch (85:10): [True: 75.0k, False: 9.27k] ------------------ 86| 75.0k| int n = parms.hash[(uchar)c]; 87| 75.0k| int z0 = 0; 88| | 89| 75.0k| if (n >= 0 && !parms.rules[n].empty()) { ------------------ | Branch (89:9): [True: 23.0k, False: 52.0k] | Branch (89:19): [True: 23.0k, False: 0] ------------------ 90| | /** check all rules for the same letter **/ 91| 62.6k| while (parms.rules[n][0] == c) { ------------------ | Branch (91:14): [True: 60.3k, False: 2.27k] ------------------ 92| | /** check whole string **/ 93| 60.3k| k = 1; /** number of found letters **/ 94| 60.3k| p = 5; /** default priority **/ 95| 60.3k| const char*s = parms.rules[n].c_str(); 96| 60.3k| s++; /** important for (see below) "*(s-1)" **/ 97| | 98| 62.1k| while (*s != '\0' && word[i + k] == *s && !isdigit((unsigned char)*s) && strchr("(-<^$", *s) == nullptr) { ------------------ | Branch (98:16): [True: 43.2k, False: 18.9k] | Branch (98:30): [True: 1.87k, False: 41.3k] | Branch (98:51): [True: 1.87k, False: 0] | Branch (98:82): [True: 1.83k, False: 40] ------------------ 99| 1.83k| k++; 100| 1.83k| s++; 101| 1.83k| } 102| 60.3k| if (*s == '(') { ------------------ | Branch (102:13): [True: 4.59k, False: 55.7k] ------------------ 103| | /** check letters in "(..)" **/ 104| 4.59k| if (myisalpha(word[i + k]) // ...could be implied? ------------------ | Branch (104:15): [True: 3.10k, False: 1.48k] ------------------ 105| 3.10k| && strchr(s + 1, word[i + k]) != nullptr) { ------------------ | Branch (105:18): [True: 251, False: 2.85k] ------------------ 106| 251| k++; 107| 1.33k| while (*s && *s != ')') ------------------ | Branch (107:20): [True: 1.33k, False: 0] | Branch (107:26): [True: 1.08k, False: 251] ------------------ 108| 1.08k| s++; 109| 251| if (*s == ')') ------------------ | Branch (109:17): [True: 251, False: 0] ------------------ 110| 251| s++; 111| 251| } 112| 4.59k| } 113| 60.3k| p0 = (int)*s; 114| 60.3k| k0 = k; 115| 61.5k| while (*s == '-' && k > 1) { ------------------ | Branch (115:16): [True: 1.16k, False: 60.3k] | Branch (115:29): [True: 1.16k, False: 0] ------------------ 116| 1.16k| k--; 117| 1.16k| s++; 118| 1.16k| } 119| 60.3k| if (*s == '<') ------------------ | Branch (119:13): [True: 174, False: 60.1k] ------------------ 120| 174| s++; 121| 60.3k| if (isdigit((unsigned char)*s)) { ------------------ | Branch (121:13): [True: 2, False: 60.3k] ------------------ 122| | /** determine priority **/ 123| 2| p = *s - '0'; 124| 2| s++; 125| 2| } 126| 60.3k| if (*s == '^' && *(s + 1) == '^') ------------------ | Branch (126:13): [True: 3.14k, False: 57.2k] | Branch (126:26): [True: 0, False: 3.14k] ------------------ 127| 0| s++; 128| | 129| 60.3k| if (*s == '\0' || (*s == '^' && (i == 0 || !myisalpha(word[i - 1])) && ------------------ | Branch (129:13): [True: 20.2k, False: 40.0k] | Branch (129:28): [True: 3.14k, False: 36.9k] | Branch (129:42): [True: 122, False: 3.02k] | Branch (129:52): [True: 764, False: 2.26k] ------------------ 130| 886| (*(s + 1) != '$' || (!myisalpha(word[i + k0])))) || ------------------ | Branch (130:29): [True: 886, False: 0] | Branch (130:48): [True: 0, False: 0] ------------------ 131| 39.1k| (*s == '$' && i > 0 && myisalpha(word[i - 1]) && ------------------ | Branch (131:14): [True: 0, False: 39.1k] | Branch (131:27): [True: 0, False: 0] | Branch (131:36): [True: 0, False: 0] ------------------ 132| 21.1k| (!myisalpha(word[i + k0])))) { ------------------ | Branch (132:14): [True: 0, False: 0] ------------------ 133| | /** search for followup rules, if: **/ 134| | /** parms.followup and k > 1 and NO '-' in searchstring **/ 135| 21.1k| char c0 = word[i + k - 1]; 136| 21.1k| n0 = parms.hash[(uchar)c0]; 137| | 138| | // if (parms.followup && k > 1 && n0 >= 0 139| 21.1k| if (k > 1 && n0 >= 0 && p0 != (int)'-' && word[i + k] != '\0' && !parms.rules[n0].empty()) { ------------------ | Branch (139:15): [True: 648, False: 20.5k] | Branch (139:24): [True: 648, False: 0] | Branch (139:35): [True: 622, False: 26] | Branch (139:53): [True: 553, False: 69] | Branch (139:76): [True: 553, False: 0] ------------------ 140| | /** test follow-up rule for "word[i+k]" **/ 141| 1.42k| while (parms.rules[n0][0] == c0) { ------------------ | Branch (141:20): [True: 1.28k, False: 145] ------------------ 142| | /** check whole string **/ 143| 1.28k| k0 = k; 144| 1.28k| p0 = 5; 145| 1.28k| s = parms.rules[n0].c_str(); 146| 1.28k| s++; 147| 1.69k| while (*s != '\0' && word[i + k0] == *s && !isdigit((unsigned char)*s) && strchr("(-<^$", *s) == nullptr) { ------------------ | Branch (147:22): [True: 1.14k, False: 545] | Branch (147:36): [True: 412, False: 735] | Branch (147:58): [True: 412, False: 0] | Branch (147:89): [True: 408, False: 4] ------------------ 148| 408| k0++; 149| 408| s++; 150| 408| } 151| 1.28k| if (*s == '(') { ------------------ | Branch (151:19): [True: 12, False: 1.27k] ------------------ 152| | /** check letters **/ 153| 12| if (myisalpha(word[i + k0]) && strchr(s + 1, word[i + k0]) != nullptr) { ------------------ | Branch (153:21): [True: 8, False: 4] | Branch (153:48): [True: 0, False: 8] ------------------ 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| 12| } 161| 1.28k| while (*s == '-') { ------------------ | Branch (161:22): [True: 0, False: 1.28k] ------------------ 162| | /** "k0" gets NOT reduced **/ 163| | /** because "if (k0 == k)" **/ 164| 0| s++; 165| 0| } 166| 1.28k| if (*s == '<') ------------------ | Branch (166:19): [True: 8, False: 1.27k] ------------------ 167| 8| s++; 168| 1.28k| if (isdigit((unsigned char)*s)) { ------------------ | Branch (168:19): [True: 0, False: 1.28k] ------------------ 169| 0| p0 = *s - '0'; 170| 0| s++; 171| 0| } 172| | 173| 1.28k| if (*s == '\0' ------------------ | Branch (173:19): [True: 553, False: 731] ------------------ 174| | /** *s == '^' cuts **/ 175| 731| || (*s == '$' && !myisalpha(word[i + k0]))) { ------------------ | Branch (175:23): [True: 0, False: 731] | Branch (175:36): [True: 0, False: 0] ------------------ 176| 553| if (k0 == k) { ------------------ | Branch (176:21): [True: 145, False: 408] ------------------ 177| | /** this is just a piece of the string **/ 178| 145| n0 += 2; 179| 145| continue; 180| 145| } 181| | 182| 408| if (p0 < p) { ------------------ | Branch (182:21): [True: 0, False: 408] ------------------ 183| | /** priority too low **/ 184| 0| n0 += 2; 185| 0| continue; 186| 0| } 187| | /** rule fits; stop search **/ 188| 408| break; 189| 408| } 190| 731| n0 += 2; 191| 731| } /** End of "while (parms.rules[n0][0] == c0)" **/ 192| | 193| 553| if (p0 >= p && parms.rules[n0][0] == c0) { ------------------ | Branch (193:17): [True: 552, False: 1] | Branch (193:28): [True: 408, False: 144] ------------------ 194| 408| n += 2; 195| 408| continue; 196| 408| } 197| 553| } /** end of follow-up stuff **/ 198| | 199| | /** replace string **/ 200| 20.7k| s = parms.rules[n + 1].c_str(); 201| 20.7k| p0 = (!parms.rules[n].empty() && strchr(parms.rules[n].c_str() + 1, '<') != nullptr) ? 1 : 0; ------------------ | Branch (201:17): [True: 20.7k, False: 0] | Branch (201:44): [True: 166, False: 20.6k] ------------------ 202| 20.7k| if (p0 == 1 && z == 0) { ------------------ | Branch (202:15): [True: 166, False: 20.6k] | Branch (202:26): [True: 166, False: 0] ------------------ 203| | /** rule with '<' is used **/ 204| 166| if (!target.empty() && *s != '\0' && ------------------ | Branch (204:17): [True: 137, False: 29] | Branch (204:36): [True: 137, False: 0] ------------------ 205| 137| (target[target.size()-1] == c || target[target.size()-1] == *s)) { ------------------ | Branch (205:18): [True: 0, False: 137] | Branch (205:50): [True: 0, False: 137] ------------------ 206| 0| target.erase(target.size() - 1); 207| 0| } 208| 166| z0 = 1; 209| 166| z = 1; 210| 166| k0 = 0; 211| 332| while (*s != '\0' && word[i + k0] != '\0') { ------------------ | Branch (211:20): [True: 166, False: 166] | Branch (211:34): [True: 166, False: 0] ------------------ 212| 166| word[i + k0] = *s; 213| 166| k0++; 214| 166| s++; 215| 166| } 216| 166| if (k > k0) ------------------ | Branch (216:17): [True: 4, False: 162] ------------------ 217| 4| strmove(&word[0] + i + k0, &word[0] + i + k); 218| | 219| | /** new "actual letter" **/ 220| 166| c = word[i]; 221| 20.6k| } else { /** no '<' rule used **/ 222| 20.6k| i += k - 1; 223| 20.6k| z = 0; 224| 20.9k| while (*s != '\0' && *(s + 1) != '\0' && target.size() < len) { ------------------ | Branch (224:20): [True: 19.8k, False: 1.09k] | Branch (224:34): [True: 458, False: 19.4k] | Branch (224:54): [True: 378, False: 80] ------------------ 225| 378| if (target.empty() || target[target.size()-1] != *s) { ------------------ | Branch (225:19): [True: 10, False: 368] | Branch (225:37): [True: 170, False: 198] ------------------ 226| 180| target.push_back(*s); 227| 180| } 228| 378| s++; 229| 378| } 230| | /** new "actual letter" **/ 231| 20.6k| c = *s; 232| 20.6k| if (!parms.rules[n].empty() && strstr(parms.rules[n].c_str() + 1, "^^") != nullptr) { ------------------ | Branch (232:17): [True: 20.6k, False: 0] | Branch (232:44): [True: 0, False: 20.6k] ------------------ 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| 20.6k| } 241| 20.7k| break; 242| 21.1k| } /** end of follow-up stuff **/ 243| 39.1k| n += 2; 244| 39.1k| } /** end of while (parms.rules[n][0] == c) **/ 245| 23.0k| } /** end of if (n >= 0) **/ 246| 75.0k| if (z0 == 0) { ------------------ | Branch (246:9): [True: 74.9k, False: 166] ------------------ 247| 74.9k| if (k && !p0 && target.size() < len && c != '\0') { ------------------ | Branch (247:11): [True: 22.8k, False: 52.0k] | Branch (247:16): [True: 20.6k, False: 2.27k] | Branch (247:23): [True: 20.5k, False: 100] | Branch (247:46): [True: 19.4k, False: 1.09k] ------------------ 248| | /** condense only double letters **/ 249| 19.4k| target.push_back(c); 250| | /// printf("\n setting \n"); 251| 19.4k| } 252| | 253| 74.9k| i++; 254| 74.9k| z = 0; 255| 74.9k| k = 0; 256| 74.9k| } 257| 75.0k| } /** end of while ((c = word[i]) != '\0') **/ 258| | 259| 9.27k| return target; 260| 9.27k|} /** end of function "phonet" **/ phonet.cxx:_ZL9myisalphac: 59| 7.62k|static int myisalpha(char ch) { 60| 7.62k| if ((unsigned char)ch < 128) ------------------ | Branch (60:7): [True: 7.12k, False: 505] ------------------ 61| 7.12k| return isalpha(ch); 62| 505| return 1; 63| 7.62k|} phonet.cxx:_ZL7strmovePcS_: 53| 4|static inline void strmove(char* dest, char* src) { 54| 98| while (*src) ------------------ | Branch (54:10): [True: 94, False: 4] ------------------ 55| 94| *dest++ = *src++; 56| 4| *dest = '\0'; 57| 4|} _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| 419k|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| 419k| if (can_use_trie && trie.get_status()) ------------------ | Branch (187:7): [True: 419k, False: 0] | Branch (187:23): [True: 419k, False: 0] ------------------ 188| 419k| 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| 419k|} _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| 419k| bool get_status() const { return status_ok; } _ZNK4TrieItLb1EE9transcodeERKNSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEERS7_: 205| 419k| 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| 419k| if (!status_ok || src.empty()) return TranscodeResult::None; ------------------ | Branch (207:13): [True: 0, False: 419k] | Branch (207:27): [True: 1.85k, False: 417k] ------------------ 208| | 209| 417k| dst.clear(); 210| 417k| dst.reserve(src.size()); 211| | 212| | // State trackers for the 3-way outcome 213| 417k| bool any_substituted = false; 214| 417k| bool any_copied = false; 215| | 216| 417k| size_t i = 0; 217| | 218| 4.54M| while (i < src.size()) { ------------------ | Branch (218:16): [True: 4.13M, False: 417k] ------------------ 219| 4.13M| size_t curr_idx = 0; 220| 4.13M| size_t match_len = 0; 221| 4.13M| uint32_t best_sub = 0xFFFFFFFF; 222| | 223| 4.13M| size_t j = i; 224| | 225| | // Greedily traverse the trie to find the longest matching sequence 226| 4.13M| while (j < src.size()) { ------------------ | Branch (226:20): [True: 4.13M, False: 152] ------------------ 227| 4.13M| uint8_t byte = static_cast(src[j]); 228| | 229| 4.13M| if (UseNibbles) { ------------------ | Branch (229:21): [True: 4.13M, Folded] ------------------ 230| 4.13M| IndexType r1 = nodes[curr_idx].children[(byte >> 4) & 0x0F]; 231| 4.13M| if (r1 == 0) break; ------------------ | Branch (231:25): [True: 4.09M, False: 38.3k] ------------------ 232| 38.3k| curr_idx += r1; 233| | 234| 38.3k| IndexType r2 = nodes[curr_idx].children[byte & 0x0F]; 235| 38.3k| if (r2 == 0) break; ------------------ | Branch (235:25): [True: 37.4k, False: 818] ------------------ 236| 818| curr_idx += r2; 237| 818| } 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| 818| ++j; 244| | 245| | // Track the deepest valid match found during traversal 246| 818| if (sub_info_arena[curr_idx] != 0xFFFFFFFF) { ------------------ | Branch (246:21): [True: 338, False: 480] ------------------ 247| 338| best_sub = sub_info_arena[curr_idx]; 248| 338| match_len = j - i; 249| 338| } 250| 818| } 251| | 252| 4.13M| if (best_sub != 0xFFFFFFFF) { ------------------ | Branch (252:17): [True: 338, False: 4.13M] ------------------ 253| | // Decode the 24-bit offset and 8-bit size, append directly from arena 254| 338| dst.append(&char_arena[best_sub >> 8], best_sub & 0xFF); 255| 338| i += match_len; 256| 338| any_substituted = true; // State update: Substitution occurred 257| 4.13M| } else { 258| | // Fallback: copy unmapped character directly to output 259| 4.13M| dst.push_back(src[i]); 260| 4.13M| ++i; 261| 4.13M| any_copied = true; // State update: Verbatim copy occurred 262| 4.13M| } 263| 4.13M| } 264| | 265| | // ALGORITHM: Outcome Evaluation 266| 417k| if (any_substituted && any_copied) { ------------------ | Branch (266:13): [True: 213, False: 417k] | Branch (266:32): [True: 207, False: 6] ------------------ 267| 207| return TranscodeResult::Partial; 268| 417k| } else if (any_substituted) { ------------------ | Branch (268:20): [True: 6, False: 417k] ------------------ 269| 6| return TranscodeResult::All; 270| 6| } 271| | 272| 417k| return TranscodeResult::None; 273| 417k| } _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| 78.1M| int& info) { 167| 78.1M| if (wlst.size() == maxSug) ------------------ | Branch (167:7): [True: 0, False: 78.1M] ------------------ 168| 0| return; 169| | 170| 78.1M| const int cwrd = std::find(wlst.begin(), wlst.end(), candidate) != wlst.end() ? 0 : 1; ------------------ | Branch (170:20): [True: 45.3k, False: 78.0M] ------------------ 171| | 172| 78.1M| if (cwrd) { ------------------ | Branch (172:7): [True: 78.0M, False: 45.3k] ------------------ 173| 78.0M| if (int result = checkword(candidate, cpdsuggest, timer, timelimit)) { ------------------ | Branch (173:13): [True: 2.23k, False: 78.0M] ------------------ 174| | // compound word in the dictionary 175| 2.23k| if (cpdsuggest == 0 && result >= 2) ------------------ | Branch (175:11): [True: 2.23k, False: 0] | Branch (175:30): [True: 1, False: 2.22k] ------------------ 176| 1| info |= SPELL_COMPOUND; ------------------ | | 78| 1|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ 177| 2.23k| wlst.push_back(candidate); 178| 2.23k| } 179| 78.0M| } 180| 78.1M|} _ZN10SuggestMgr7suggestERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_Pib: 190| 142k| int* onlycompoundsug, bool test_simplesug) { 191| 142k| int nocompoundtwowords = 0; // no second or third loops, see below 192| 142k| std::vector word_utf; 193| 142k| size_t nsugorig = slst.size(), oldSug = 0; 194| 142k| std::string w2; 195| 142k| bool good_suggestion = false; 196| | 197| | // word reversing wrapper for complex prefixes 198| 142k| if (complexprefixes) { ------------------ | Branch (198:7): [True: 8.27k, False: 134k] ------------------ 199| 8.27k| w2.assign(w); 200| 8.27k| if (utf8) ------------------ | Branch (200:9): [True: 0, False: 8.27k] ------------------ 201| 0| reverseword_utf(w2); 202| 8.27k| else 203| 8.27k| reverseword(w2); 204| 8.27k| } 205| | 206| 142k| const std::string& word = complexprefixes ? w2 : w; ------------------ | Branch (206:29): [True: 8.27k, False: 134k] ------------------ 207| | 208| 142k| suggest_start = std::chrono::steady_clock::now(); 209| | 210| 142k| if (utf8) { ------------------ | Branch (210:7): [True: 59.5k, False: 83.1k] ------------------ 211| 59.5k| int wl = u8_u16(word_utf, word); 212| 59.5k| if (wl == -1) { ------------------ | Branch (212:9): [True: 9.85k, False: 49.6k] ------------------ 213| 9.85k| return false; 214| 9.85k| } 215| 59.5k| } 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| 132k| int info = 0; 225| 530k| for (int cpdsuggest = 0; cpdsuggest < 3 && nocompoundtwowords == 0; cpdsuggest++) { ------------------ | Branch (225:28): [True: 398k, False: 132k] | Branch (225:46): [True: 397k, False: 181] ------------------ 226| | 227| | // limit compound suggestion 228| 397k| if (cpdsuggest > 0) ------------------ | Branch (228:9): [True: 265k, False: 132k] ------------------ 229| 265k| oldSug = slst.size(); 230| | 231| | // suggestions for an uppercase word (html -> HTML) 232| 397k| if (slst.size() < maxSug) { ------------------ | Branch (232:9): [True: 397k, False: 15] ------------------ 233| 397k| size_t i = slst.size(); 234| 397k| if (utf8) ------------------ | Branch (234:11): [True: 148k, False: 248k] ------------------ 235| 148k| capchars_utf(slst, word_utf, cpdsuggest, info); 236| 248k| else 237| 248k| capchars(slst, word, cpdsuggest, info); 238| 397k| if (slst.size() > i) ------------------ | Branch (238:11): [True: 180, False: 397k] ------------------ 239| 180| good_suggestion = true; 240| 397k| } 241| | 242| | // perhaps we made a typical fault of spelling 243| 397k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (243:9): [True: 397k, False: 15] | Branch (243:36): [True: 132k, False: 265k] | Branch (243:51): [True: 265k, False: 0] ------------------ 244| 397k| size_t i = slst.size(); 245| 397k| replchars(slst, word, cpdsuggest, info); 246| 397k| if (slst.size() > i) { ------------------ | Branch (246:11): [True: 0, False: 397k] ------------------ 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| 397k| } 252| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (252:9): [True: 0, False: 397k] ------------------ 253| 0| return good_suggestion; 254| 397k| if (test_simplesug && slst.size()) ------------------ | Branch (254:9): [True: 0, False: 397k] | 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| 397k| if ((slst.size() < maxSug) && ------------------ | Branch (258:9): [True: 397k, False: 15] ------------------ 259| 397k| (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (259:10): [True: 132k, False: 265k] | Branch (259:25): [True: 265k, False: 0] ------------------ 260| 397k| mapchars(slst, word, cpdsuggest, info); 261| 397k| } 262| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (262:9): [True: 4, False: 397k] ------------------ 263| 4| return good_suggestion; 264| 397k| if (test_simplesug && slst.size()) ------------------ | Branch (264:9): [True: 0, False: 397k] | Branch (264:27): [True: 0, False: 0] ------------------ 265| 0| return true; 266| | 267| | // only suggest compound words when no other ~good suggestion 268| 397k| if ((cpdsuggest == 0) && (slst.size() > nsugorig)) ------------------ | Branch (268:9): [True: 132k, False: 265k] | Branch (268:30): [True: 180, False: 132k] ------------------ 269| 180| nocompoundtwowords = 1; 270| | 271| | // did we swap the order of chars by mistake 272| 397k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (272:9): [True: 397k, False: 15] | Branch (272:36): [True: 132k, False: 265k] | Branch (272:51): [True: 265k, False: 0] ------------------ 273| 397k| if (utf8) ------------------ | Branch (273:11): [True: 148k, False: 248k] ------------------ 274| 148k| swapchar_utf(slst, word_utf, cpdsuggest, info); 275| 248k| else 276| 248k| swapchar(slst, word, cpdsuggest, info); 277| 397k| } 278| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (278:9): [True: 0, False: 397k] ------------------ 279| 0| return good_suggestion; 280| 397k| if (test_simplesug && slst.size()) ------------------ | Branch (280:9): [True: 0, False: 397k] | 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| 397k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (284:9): [True: 397k, False: 15] | Branch (284:36): [True: 132k, False: 265k] | Branch (284:51): [True: 265k, False: 0] ------------------ 285| 397k| if (utf8) ------------------ | Branch (285:11): [True: 148k, False: 248k] ------------------ 286| 148k| longswapchar_utf(slst, word_utf, cpdsuggest, info); 287| 248k| else 288| 248k| longswapchar(slst, word, cpdsuggest, info); 289| 397k| } 290| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (290:9): [True: 0, False: 397k] ------------------ 291| 0| return good_suggestion; 292| 397k| if (test_simplesug && slst.size()) ------------------ | Branch (292:9): [True: 0, False: 397k] | 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| 397k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (296:9): [True: 397k, False: 15] | Branch (296:36): [True: 132k, False: 265k] | Branch (296:51): [True: 265k, False: 0] ------------------ 297| 397k| if (utf8) ------------------ | Branch (297:11): [True: 148k, False: 248k] ------------------ 298| 148k| badcharkey_utf(slst, word_utf, cpdsuggest, info); 299| 248k| else 300| 248k| badcharkey(slst, word, cpdsuggest, info); 301| 397k| } 302| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (302:9): [True: 0, False: 397k] ------------------ 303| 0| return good_suggestion; 304| 397k| if (test_simplesug && slst.size()) ------------------ | Branch (304:9): [True: 0, False: 397k] | Branch (304:27): [True: 0, False: 0] ------------------ 305| 0| return true; 306| | 307| | // did we add a char that should not be there 308| 397k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (308:9): [True: 397k, False: 15] | Branch (308:36): [True: 132k, False: 265k] | Branch (308:51): [True: 265k, False: 0] ------------------ 309| 397k| if (utf8) ------------------ | Branch (309:11): [True: 148k, False: 248k] ------------------ 310| 148k| extrachar_utf(slst, word_utf, cpdsuggest, info); 311| 248k| else 312| 248k| extrachar(slst, word, cpdsuggest, info); 313| 397k| } 314| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (314:9): [True: 0, False: 397k] ------------------ 315| 0| return good_suggestion; 316| 397k| if (test_simplesug && slst.size()) ------------------ | Branch (316:9): [True: 0, False: 397k] | Branch (316:27): [True: 0, False: 0] ------------------ 317| 0| return true; 318| | 319| | // did we forgot a char 320| 397k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (320:9): [True: 397k, False: 15] | Branch (320:36): [True: 132k, False: 265k] | Branch (320:51): [True: 265k, False: 0] ------------------ 321| 397k| if (utf8) ------------------ | Branch (321:11): [True: 148k, False: 248k] ------------------ 322| 148k| forgotchar_utf(slst, word_utf, cpdsuggest, info); 323| 248k| else 324| 248k| forgotchar(slst, word, cpdsuggest, info); 325| 397k| } 326| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (326:9): [True: 0, False: 397k] ------------------ 327| 0| return good_suggestion; 328| 397k| if (test_simplesug && slst.size()) ------------------ | Branch (328:9): [True: 0, False: 397k] | Branch (328:27): [True: 0, False: 0] ------------------ 329| 0| return true; 330| | 331| | // did we move a char 332| 397k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (332:9): [True: 397k, False: 15] | Branch (332:36): [True: 132k, False: 265k] | Branch (332:51): [True: 265k, False: 0] ------------------ 333| 397k| if (utf8) ------------------ | Branch (333:11): [True: 148k, False: 248k] ------------------ 334| 148k| movechar_utf(slst, word_utf, cpdsuggest, info); 335| 248k| else 336| 248k| movechar(slst, word, cpdsuggest, info); 337| 397k| } 338| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (338:9): [True: 0, False: 397k] ------------------ 339| 0| return good_suggestion; 340| 397k| if (test_simplesug && slst.size()) ------------------ | Branch (340:9): [True: 0, False: 397k] | 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| 397k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (344:9): [True: 397k, False: 15] | Branch (344:36): [True: 132k, False: 265k] | Branch (344:51): [True: 265k, False: 0] ------------------ 345| 397k| if (utf8) ------------------ | Branch (345:11): [True: 148k, False: 248k] ------------------ 346| 148k| badchar_utf(slst, word_utf, cpdsuggest, info); 347| 248k| else 348| 248k| badchar(slst, word, cpdsuggest, info); 349| 397k| } 350| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (350:9): [True: 0, False: 397k] ------------------ 351| 0| return good_suggestion; 352| 397k| if (test_simplesug && slst.size()) ------------------ | Branch (352:9): [True: 0, False: 397k] | Branch (352:27): [True: 0, False: 0] ------------------ 353| 0| return true; 354| | 355| | // did we double two characters 356| 397k| if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) { ------------------ | Branch (356:9): [True: 397k, False: 15] | Branch (356:36): [True: 132k, False: 265k] | Branch (356:51): [True: 265k, False: 0] ------------------ 357| 397k| if (utf8) ------------------ | Branch (357:11): [True: 148k, False: 248k] ------------------ 358| 148k| doubletwochars_utf(slst, word_utf, cpdsuggest, info); 359| 248k| else 360| 248k| doubletwochars(slst, word, cpdsuggest, info); 361| 397k| } 362| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (362:9): [True: 0, False: 397k] ------------------ 363| 0| return good_suggestion; 364| 397k| if (test_simplesug && slst.size()) ------------------ | Branch (364:9): [True: 0, False: 397k] | 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| 397k| if (!cpdsuggest || (!nosplitsugs && slst.size() < oldSug + maxcpdsugs)) { ------------------ | Branch (371:9): [True: 132k, False: 265k] | Branch (371:25): [True: 265k, False: 0] | Branch (371:41): [True: 265k, False: 0] ------------------ 372| 397k| good_suggestion = twowords(slst, word, cpdsuggest, good_suggestion, info); 373| | 374| 397k| if (info & SPELL_BEST_SUG) ------------------ | | 86| 397k|#define SPELL_BEST_SUG (1 << 8) // limit suggestions for the best ones, i.e. ph: ------------------ | Branch (374:11): [True: 131, False: 397k] ------------------ 375| 131| return true; 376| 397k| } 377| 397k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 397k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (377:9): [True: 0, False: 397k] ------------------ 378| 0| return good_suggestion; 379| | 380| | // testing returns after the first loop 381| 397k| if (test_simplesug) ------------------ | Branch (381:9): [True: 0, False: 397k] ------------------ 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| 397k| if (cpdsuggest == 1 && (slst.size() > oldSug || (info & SPELL_COMPOUND))) ------------------ | | 78| 132k|#define SPELL_COMPOUND (1 << 0) // the result is a compound word ------------------ | Branch (387:9): [True: 132k, False: 265k] | Branch (387:29): [True: 0, False: 132k] | Branch (387:53): [True: 1, False: 132k] ------------------ 388| 1| nocompoundtwowords = 1; 389| | 390| 397k| } // repeating ``for'' statement compounding support 391| | 392| 132k| if (!nocompoundtwowords && (!slst.empty()) && onlycompoundsug) ------------------ | Branch (392:7): [True: 132k, False: 181] | Branch (392:30): [True: 15.1k, False: 117k] | Branch (392:49): [True: 15.1k, False: 0] ------------------ 393| 15.1k| *onlycompoundsug = 1; 394| | 395| 132k| return good_suggestion; 396| 132k|} _ZN10SuggestMgr12capchars_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 401| 148k| int cpdsuggest, int& info) { 402| 148k| std::vector candidate_utf(word); 403| 148k| mkallcap_utf(candidate_utf, langnum); 404| 148k| std::string candidate; 405| 148k| u16_u8(candidate, candidate_utf); 406| 148k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 407| 148k|} _ZN10SuggestMgr8capcharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 412| 248k| int cpdsuggest, int& info) { 413| 248k| std::string candidate(word); 414| 248k| mkallcap(candidate, csconv); 415| 248k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 416| 248k|} _ZN10SuggestMgr8mapcharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 421| 397k| int cpdsuggest, int& info) { 422| 397k| std::string candidate; 423| 397k| std::chrono::steady_clock::time_point timelimit; 424| 397k| int timer; 425| | 426| 397k| if (word.size() < 2 || !pAMgr) ------------------ | Branch (426:7): [True: 35.6k, False: 362k] | Branch (426:26): [True: 0, False: 362k] ------------------ 427| 35.6k| return wlst.size(); 428| | 429| 362k| const std::vector& maptable = pAMgr->get_maptable(); 430| 362k| if (maptable.empty()) ------------------ | Branch (430:7): [True: 347k, False: 14.5k] ------------------ 431| 347k| return wlst.size(); 432| | 433| 14.5k| timelimit = std::chrono::steady_clock::now(); 434| 14.5k| timer = MINTIMER; ------------------ | | 107| 14.5k|#define MINTIMER 100 ------------------ 435| 14.5k| return map_related(word, candidate, 0, wlst, cpdsuggest, 436| 14.5k| maptable, &timer, &timelimit, 0, info); 437| 362k|} _ZN10SuggestMgr11map_relatedERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERS6_mRNS0_6vectorIS6_NS4_IS6_EEEEiRKNSA_ISC_NS4_ISC_EEEEPiPNS0_6chrono10time_pointINSJ_12steady_clockENSJ_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEEiRi: 447| 3.62M| int depth, int& info) { 448| 3.62M| if (word.size() == wn) { ------------------ | Branch (448:7): [True: 1.76M, False: 1.86M] ------------------ 449| 1.76M| if (candidate == word) ------------------ | Branch (449:9): [True: 14.5k, False: 1.74M] ------------------ 450| 14.5k| return wlst.size(); 451| 1.74M| const int cwrd = std::find(wlst.begin(), wlst.end(), candidate) != wlst.end() ? 0 : 1; ------------------ | Branch (451:22): [True: 0, False: 1.74M] ------------------ 452| 1.74M| if ((cwrd) && checkword(candidate, cpdsuggest, timer, timelimit)) { ------------------ | Branch (452:9): [True: 1.74M, False: 0] | Branch (452:19): [True: 0, False: 1.74M] ------------------ 453| 0| if (wlst.size() < maxSug) { ------------------ | Branch (453:11): [True: 0, False: 0] ------------------ 454| 0| wlst.push_back(candidate); 455| 0| } 456| 0| } 457| 1.74M| return wlst.size(); 458| 1.76M| } 459| | 460| 1.86M| if (depth > 0x3F00) { ------------------ | Branch (460:7): [True: 0, False: 1.86M] ------------------ 461| 0| *timer = 0; 462| 0| return wlst.size(); 463| 0| } 464| | 465| 1.86M| int in_map = 0; 466| 7.44M| for (size_t j = 0; j < maptable.size(); ++j) { ------------------ | Branch (466:22): [True: 5.58M, False: 1.86M] ------------------ 467| 20.4M| for (size_t k = 0; k < maptable[j].size(); ++k) { ------------------ | Branch (467:24): [True: 14.8M, False: 5.58M] ------------------ 468| 14.8M| size_t len = maptable[j][k].size(); 469| 14.8M| if (len && word.compare(wn, len, maptable[j][k]) == 0) { ------------------ | Branch (469:11): [True: 14.8M, False: 0] | Branch (469:18): [True: 875k, False: 14.0M] ------------------ 470| 875k| in_map = 1; 471| 875k| size_t cn = candidate.size(); 472| 3.49M| for (size_t l = 0; l < maptable[j].size(); ++l) { ------------------ | Branch (472:28): [True: 2.62M, False: 874k] ------------------ 473| 2.62M| candidate.resize(cn); 474| 2.62M| candidate.append(maptable[j][l]); 475| 2.62M| map_related(word, candidate, wn + len, wlst, 476| 2.62M| cpdsuggest, maptable, timer, timelimit, depth + 1, info); 477| 2.62M| if (!(*timer)) ------------------ | Branch (477:15): [True: 484, False: 2.62M] ------------------ 478| 484| return wlst.size(); 479| 2.62M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) { ------------------ | | 105| 2.62M|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (479:15): [True: 4, False: 2.62M] ------------------ 480| 4| *timer = 0; 481| 4| return wlst.size(); 482| 4| } 483| 2.62M| } 484| 875k| } 485| 14.8M| } 486| 5.58M| } 487| 1.86M| if (!in_map) { ------------------ | Branch (487:7): [True: 987k, False: 874k] ------------------ 488| 987k| candidate.push_back(word[wn]); 489| 987k| map_related(word, candidate, wn + 1, wlst, cpdsuggest, 490| 987k| maptable, timer, timelimit, depth + 1, info); 491| 987k| } 492| 1.86M| return wlst.size(); 493| 1.86M|} _ZN10SuggestMgr9replcharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 499| 397k| int cpdsuggest, int& info) { 500| 397k| std::string candidate; 501| 397k| int wl = word.size(); 502| 397k| if (wl < 2 || !pAMgr) ------------------ | Branch (502:7): [True: 35.6k, False: 362k] | Branch (502:17): [True: 0, False: 362k] ------------------ 503| 35.6k| return wlst.size(); 504| 362k| const std::vector& reptable = pAMgr->get_reptable(); 505| 362k| auto replchars_start = std::chrono::steady_clock::now(); 506| 362k| for (const auto& entry : reptable) { ------------------ | Branch (506:26): [True: 74.9k, False: 362k] ------------------ 507| 74.9k| size_t r = 0; 508| | // search every occurence of the pattern in the word 509| 74.9k| while ((r = word.find(entry.pattern, r)) != std::string::npos) { ------------------ | Branch (509:12): [True: 12, False: 74.9k] ------------------ 510| 12| if (std::chrono::steady_clock::now() - replchars_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 12|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (510:11): [True: 0, False: 12] ------------------ 511| 0| return wlst.size(); 512| 12| int type = (r == 0) ? 1 : 0; ------------------ | Branch (512:18): [True: 0, False: 12] ------------------ 513| 12| if (r + entry.pattern.size() == word.size()) ------------------ | Branch (513:11): [True: 0, False: 12] ------------------ 514| 0| type += 2; 515| 12| while (type && entry.outstrings[type].empty()) ------------------ | Branch (515:14): [True: 0, False: 12] | 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| 12| const std::string&out = entry.outstrings[type]; 518| 12| if (out.empty()) { ------------------ | Branch (518:11): [True: 0, False: 12] ------------------ 519| 0| ++r; 520| 0| continue; 521| 0| } 522| 12| candidate.assign(word, 0, r); 523| 12| candidate.append(entry.outstrings[type]); 524| 12| candidate.append(word, r + entry.pattern.size(), std::string::npos); 525| 12| size_t sp = candidate.find(' '); 526| 12| size_t oldns = wlst.size(); 527| 12| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 528| 12| if (oldns < wlst.size()) { ------------------ | Branch (528:11): [True: 0, False: 12] ------------------ 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| 12| if (sp != std::string::npos) { ------------------ | Branch (534:11): [True: 0, False: 12] ------------------ 535| 0| size_t prev = 0; 536| 0| while (sp != std::string::npos) { ------------------ | Branch (536:16): [True: 0, False: 0] ------------------ 537| 0| std::string prev_chunk = candidate.substr(prev, sp - prev); 538| 0| if (checkword(prev_chunk, 0, nullptr, nullptr)) { ------------------ | Branch (538:15): [True: 0, False: 0] ------------------ 539| 0| oldns = wlst.size(); 540| 0| std::string post_chunk = candidate.substr(sp + 1); 541| 0| testsug(wlst, post_chunk, cpdsuggest, nullptr, nullptr, info); 542| 0| if (oldns < wlst.size()) { ------------------ | Branch (542:17): [True: 0, False: 0] ------------------ 543| 0| wlst[wlst.size() - 1] = candidate; 544| 0| } 545| 0| } 546| 0| prev = sp + 1; 547| 0| sp = candidate.find(' ', prev); 548| 0| } 549| 0| } 550| 12| r++; // search for the next letter 551| 12| } 552| 74.9k| } 553| 362k| return wlst.size(); 554| 362k|} _ZN10SuggestMgr14doubletwocharsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 563| 248k| int cpdsuggest, int& info) { 564| 248k| size_t wl = word.size(); 565| 248k| if (wl < 5 || !pAMgr) ------------------ | Branch (565:7): [True: 55.4k, False: 193k] | Branch (565:17): [True: 0, False: 193k] ------------------ 566| 55.4k| return wlst.size(); 567| | 568| 193k| int state = 0; 569| 4.72M| for (size_t i = 2; i < wl; ++i) { ------------------ | Branch (569:22): [True: 4.52M, False: 193k] ------------------ 570| 4.52M| if (word[i] == word[i - 2]) { ------------------ | Branch (570:9): [True: 1.21M, False: 3.31M] ------------------ 571| 1.21M| state++; 572| 1.21M| if (state == 3 || (state == 2 && i >= 4)) { ------------------ | Branch (572:11): [True: 6.82k, False: 1.20M] | Branch (572:26): [True: 448k, False: 759k] | Branch (572:40): [True: 439k, False: 9.50k] ------------------ 573| 446k| auto word_iter = word.begin(); 574| 446k| std::string candidate(word_iter, word_iter + i - 1); 575| 446k| candidate.insert(candidate.end(), word_iter + i + 1, word.end()); 576| 446k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 577| 446k| state = 0; 578| 446k| } 579| 3.31M| } else { 580| 3.31M| state = 0; 581| 3.31M| } 582| 4.52M| } 583| 193k| return wlst.size(); 584| 248k|} _ZN10SuggestMgr18doubletwochars_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 593| 148k| int cpdsuggest, int& info) { 594| 148k| size_t wl = word.size(); 595| 148k| int state = 0; 596| 148k| if (wl < 5 || !pAMgr) ------------------ | Branch (596:7): [True: 54.2k, False: 94.6k] | Branch (596:17): [True: 0, False: 94.6k] ------------------ 597| 54.2k| return wlst.size(); 598| 1.54M| for (size_t i = 2; i < wl; ++i) { ------------------ | Branch (598:22): [True: 1.45M, False: 94.6k] ------------------ 599| 1.45M| if (word[i] == word[i - 2]) { ------------------ | Branch (599:9): [True: 462k, False: 990k] ------------------ 600| 462k| state++; 601| 462k| if (state == 3 || (state == 2 && i >= 4)) { ------------------ | Branch (601:11): [True: 3.84k, False: 458k] | Branch (601:26): [True: 167k, False: 291k] | Branch (601:40): [True: 161k, False: 5.73k] ------------------ 602| 165k| auto word_iter = word.begin(); 603| 165k| std::vector candidate_utf(word_iter, word_iter + i - 1); 604| 165k| candidate_utf.insert(candidate_utf.end(), word_iter + i + 1, word.end()); 605| 165k| std::string candidate; 606| 165k| u16_u8(candidate, candidate_utf); 607| 165k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 608| 165k| state = 0; 609| 165k| } 610| 990k| } else { 611| 990k| state = 0; 612| 990k| } 613| 1.45M| } 614| 94.6k| return wlst.size(); 615| 148k|} _ZN10SuggestMgr10badcharkeyERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 621| 248k| int cpdsuggest, int& info) { 622| 248k| 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| 5.29M| for (size_t i = 0, wl = candidate.size(); i < wl; ++i) { ------------------ | Branch (626:45): [True: 5.04M, False: 248k] ------------------ 627| 5.04M| char tmpc = candidate[i]; 628| | // check with uppercase letters 629| 5.04M| candidate[i] = csconv[((unsigned char)tmpc)].cupper; 630| 5.04M| if (tmpc != candidate[i]) { ------------------ | Branch (630:9): [True: 1.23M, False: 3.80M] ------------------ 631| 1.23M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 632| 1.23M| candidate[i] = tmpc; 633| 1.23M| } 634| | // check neighbor characters in keyboard string 635| 5.04M| if (ckey.empty()) ------------------ | Branch (635:9): [True: 0, False: 5.04M] ------------------ 636| 0| continue; 637| 5.04M| size_t loc = 0; 638| 132M| while ((loc < ckeyl) && ckey[loc] != tmpc) ------------------ | Branch (638:12): [True: 127M, False: 4.17M] | Branch (638:29): [True: 127M, False: 864k] ------------------ 639| 127M| ++loc; 640| 5.93M| while (loc < ckeyl) { ------------------ | Branch (640:12): [True: 896k, False: 5.04M] ------------------ 641| | // a long keyboard string can hold many neighbours for this 642| | // character, so give up once the overall time budget is spent 643| 896k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 896k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (643:11): [True: 0, False: 896k] ------------------ 644| 0| return wlst.size(); 645| 896k| if ((loc > 0) && ckey[loc - 1] != '|') { ------------------ | Branch (645:11): [True: 748k, False: 147k] | Branch (645:24): [True: 719k, False: 29.0k] ------------------ 646| 719k| candidate[i] = ckey[loc - 1]; 647| 719k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 648| 719k| } 649| 896k| if (((loc + 1) < ckeyl) && (ckey[loc + 1] != '|')) { ------------------ | Branch (649:11): [True: 803k, False: 92.2k] | Branch (649:34): [True: 739k, False: 64.2k] ------------------ 650| 739k| candidate[i] = ckey[loc + 1]; 651| 739k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 652| 739k| } 653| 14.0M| do { 654| 14.0M| loc++; 655| 14.0M| } while ((loc < ckeyl) && ckey[loc] != tmpc); ------------------ | Branch (655:16): [True: 13.2M, False: 864k] | Branch (655:33): [True: 13.1M, False: 31.1k] ------------------ 656| 896k| } 657| 5.04M| candidate[i] = tmpc; 658| 5.04M| } 659| 248k| return wlst.size(); 660| 248k|} _ZN10SuggestMgr14badcharkey_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 666| 148k| int cpdsuggest, int& info) { 667| 148k| std::string candidate; 668| 148k| 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| 1.92M| for (size_t i = 0, wl = word.size(); i < wl; ++i) { ------------------ | Branch (671:40): [True: 1.77M, False: 148k] ------------------ 672| 1.77M| w_char tmpc = candidate_utf[i]; 673| | // check with uppercase letters 674| 1.77M| candidate_utf[i] = upper_utf(candidate_utf[i], 1); 675| 1.77M| if (tmpc != candidate_utf[i]) { ------------------ | Branch (675:9): [True: 408k, False: 1.36M] ------------------ 676| 408k| u16_u8(candidate, candidate_utf); 677| 408k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 678| 408k| candidate_utf[i] = tmpc; 679| 408k| } 680| | // check neighbor characters in keyboard string 681| 1.77M| if (ckey_utf.empty()) ------------------ | Branch (681:9): [True: 0, False: 1.77M] ------------------ 682| 0| continue; 683| 1.77M| size_t loc = 0; 684| 44.5M| while ((loc < ckeyl) && ckey_utf[loc] != tmpc) ------------------ | Branch (684:12): [True: 43.2M, False: 1.35M] | Branch (684:29): [True: 42.7M, False: 420k] ------------------ 685| 42.7M| ++loc; 686| 2.21M| while (loc < ckeyl) { ------------------ | Branch (686:12): [True: 433k, False: 1.77M] ------------------ 687| | // a long keyboard string can hold many neighbours for this 688| | // character, so give up once the overall time budget is spent 689| 433k| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 433k|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (689:11): [True: 0, False: 433k] ------------------ 690| 0| return wlst.size(); 691| 433k| if ((loc > 0) && ckey_utf[loc - 1] != W_VLINE) { ------------------ | Branch (691:11): [True: 342k, False: 91.0k] | Branch (691:24): [True: 342k, False: 0] ------------------ 692| 342k| candidate_utf[i] = ckey_utf[loc - 1]; 693| 342k| u16_u8(candidate, candidate_utf); 694| 342k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 695| 342k| } 696| 433k| if (((loc + 1) < ckeyl) && (ckey_utf[loc + 1] != W_VLINE)) { ------------------ | Branch (696:11): [True: 393k, False: 40.4k] | Branch (696:34): [True: 393k, False: 0] ------------------ 697| 393k| candidate_utf[i] = ckey_utf[loc + 1]; 698| 393k| u16_u8(candidate, candidate_utf); 699| 393k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 700| 393k| } 701| 6.95M| do { 702| 6.95M| loc++; 703| 6.95M| } while ((loc < ckeyl) && ckey_utf[loc] != tmpc); ------------------ | Branch (703:16): [True: 6.53M, False: 420k] | Branch (703:33): [True: 6.52M, False: 13.7k] ------------------ 704| 433k| } 705| 1.77M| candidate_utf[i] = tmpc; 706| 1.77M| } 707| 148k| return wlst.size(); 708| 148k|} _ZN10SuggestMgr7badcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 713| 248k| int cpdsuggest, int& info) { 714| 248k| std::string candidate(word); 715| 248k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 716| 248k| int timer = MINTIMER; ------------------ | | 107| 248k|#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| 248k| for (size_t j = 0; j < ctryl; ++j) { ------------------ | Branch (719:22): [True: 0, False: 248k] ------------------ 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| 248k| return wlst.size(); 732| 248k|} _ZN10SuggestMgr11badchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 737| 148k| int cpdsuggest, int& info) { 738| 148k| std::vector candidate_utf(word); 739| 148k| std::string candidate; 740| 148k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 741| 148k| int timer = MINTIMER; ------------------ | | 107| 148k|#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| 166k| for (size_t j = 0; j < ctryl; ++j) { ------------------ | Branch (744:22): [True: 17.5k, False: 148k] ------------------ 745| 227k| for (auto aI = candidate_utf.rbegin(), aEnd = candidate_utf.rend(); aI != aEnd; ++aI) { ------------------ | Branch (745:73): [True: 210k, False: 17.5k] ------------------ 746| 210k| w_char tmpc = *aI; 747| 210k| if (tmpc == ctry_utf[j]) ------------------ | Branch (747:11): [True: 0, False: 210k] ------------------ 748| 0| continue; 749| 210k| *aI = ctry_utf[j]; 750| 210k| u16_u8(candidate, candidate_utf); 751| 210k| testsug(wlst, candidate, cpdsuggest, &timer, &timelimit, info); 752| 210k| if (!timer) ------------------ | Branch (752:11): [True: 0, False: 210k] ------------------ 753| 0| return wlst.size(); 754| 210k| *aI = tmpc; 755| 210k| } 756| 17.5k| } 757| 148k| return wlst.size(); 758| 148k|} _ZN10SuggestMgr13extrachar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 763| 148k| int cpdsuggest, int& info) { 764| 148k| std::vector candidate_utf(word); 765| 148k| if (candidate_utf.size() < 2) ------------------ | Branch (765:7): [True: 16.3k, False: 132k] ------------------ 766| 16.3k| return wlst.size(); 767| | // try omitting one char of word at a time 768| 1.89M| for (size_t i = 0; i < candidate_utf.size(); ++i) { ------------------ | Branch (768:22): [True: 1.76M, False: 132k] ------------------ 769| 1.76M| size_t index = candidate_utf.size() - 1 - i; 770| 1.76M| w_char tmpc = candidate_utf[index]; 771| 1.76M| candidate_utf.erase(candidate_utf.begin() + index); 772| 1.76M| std::string candidate; 773| 1.76M| u16_u8(candidate, candidate_utf); 774| 1.76M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 775| 1.76M| candidate_utf.insert(candidate_utf.begin() + index, tmpc); 776| 1.76M| } 777| 132k| return wlst.size(); 778| 148k|} _ZN10SuggestMgr9extracharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 783| 248k| int cpdsuggest, int& info) { 784| 248k| std::string candidate(word); 785| 248k| if (candidate.size() < 2) ------------------ | Branch (785:7): [True: 19.9k, False: 229k] ------------------ 786| 19.9k| return wlst.size(); 787| | // try omitting one char of word at a time 788| 5.25M| for (size_t i = 0; i < candidate.size(); ++i) { ------------------ | Branch (788:22): [True: 5.02M, False: 229k] ------------------ 789| 5.02M| size_t index = candidate.size() - 1 - i; 790| 5.02M| char tmpc = candidate[index]; 791| 5.02M| candidate.erase(candidate.begin() + index); 792| 5.02M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 793| 5.02M| candidate.insert(candidate.begin() + index, tmpc); 794| 5.02M| } 795| 229k| return wlst.size(); 796| 248k|} _ZN10SuggestMgr10forgotcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 801| 248k| int cpdsuggest, int& info) { 802| 248k| std::string candidate(word); 803| 248k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 804| 248k| int timer = MINTIMER; ------------------ | | 107| 248k|#define MINTIMER 100 ------------------ 805| | 806| | // try inserting a tryme character before every letter (and the null 807| | // terminator) 808| 248k| for (size_t k = 0; k < ctryl; ++k) { ------------------ | Branch (808:22): [True: 0, False: 248k] ------------------ 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| 248k| return wlst.size(); 819| 248k|} _ZN10SuggestMgr14forgotchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 824| 148k| int cpdsuggest, int& info) { 825| 148k| std::vector candidate_utf(word); 826| 148k| std::chrono::steady_clock::time_point timelimit = std::chrono::steady_clock::now(); 827| 148k| int timer = MINTIMER; ------------------ | | 107| 148k|#define MINTIMER 100 ------------------ 828| | 829| | // try inserting a tryme character at the end of the word and before every 830| | // letter 831| 166k| for (size_t k = 0; k < ctryl; ++k) { ------------------ | Branch (831:22): [True: 17.5k, False: 148k] ------------------ 832| 245k| for (size_t i = 0; i <= candidate_utf.size(); ++i) { ------------------ | Branch (832:24): [True: 227k, False: 17.5k] ------------------ 833| 227k| size_t index = candidate_utf.size() - i; 834| 227k| candidate_utf.insert(candidate_utf.begin() + index, ctry_utf[k]); 835| 227k| std::string candidate; 836| 227k| u16_u8(candidate, candidate_utf); 837| 227k| testsug(wlst, candidate, cpdsuggest, &timer, &timelimit, info); 838| 227k| if (!timer) ------------------ | Branch (838:11): [True: 0, False: 227k] ------------------ 839| 0| return wlst.size(); 840| 227k| candidate_utf.erase(candidate_utf.begin() + index); 841| 227k| } 842| 17.5k| } 843| 148k| return wlst.size(); 844| 148k|} _ZN10SuggestMgr8twowordsERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_ibRi: 854| 397k| bool good, int& info) { 855| 397k| int c2, forbidden = 0, cwrd, wl = word.size(); 856| 397k| if (wl < 3) ------------------ | Branch (856:7): [True: 57.4k, False: 340k] ------------------ 857| 57.4k| return false; 858| | 859| 340k| if (langnum == LANG_hu) ------------------ | Branch (859:7): [True: 13.8k, False: 326k] ------------------ 860| 13.8k| forbidden = check_forbidden(word); 861| | 862| 340k| char* candidate = new char[wl + 2]; 863| 340k| memcpy(candidate + 1, word.data(), wl); 864| 340k| 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| 4.44M| for (char* p = candidate + 1; p[1] != '\0'; p++) { ------------------ | Branch (868:33): [True: 4.13M, False: 306k] ------------------ 869| 4.13M| p[-1] = *p; 870| | // go to end of the UTF-8 character 871| 4.35M| while (utf8 && is_utf8_cont(p[1])) { ------------------ | Branch (871:12): [True: 1.39M, False: 2.96M] | Branch (871:20): [True: 219k, False: 1.17M] ------------------ 872| 219k| *p = p[1]; 873| 219k| p++; 874| 219k| } 875| 4.13M| if (utf8 && p[1] == '\0') ------------------ | Branch (875:9): [True: 1.17M, False: 2.96M] | Branch (875:17): [True: 34.4k, False: 1.13M] ------------------ 876| 34.4k| 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| 4.10M| *p = ' '; 886| 4.10M| if (!cpdsuggest && checkword(candidate, cpdsuggest, nullptr, nullptr)) { ------------------ | Branch (886:9): [True: 1.36M, False: 2.73M] | Branch (886:9): [True: 1.29k, False: 4.10M] | Branch (886:24): [True: 1.29k, False: 1.36M] ------------------ 887| | // best solution 888| 1.29k| info |= SPELL_BEST_SUG; ------------------ | | 86| 1.29k|#define SPELL_BEST_SUG (1 << 8) // limit suggestions for the best ones, i.e. ph: ------------------ 889| | 890| | // remove not word pair suggestions 891| 1.29k| if (!good) { ------------------ | Branch (891:11): [True: 131, False: 1.16k] ------------------ 892| 131| good = true; 893| 131| wlst.clear(); 894| 131| } 895| | 896| 1.29k| wlst.insert(wlst.begin(), candidate); 897| 1.29k| } 898| | 899| | // word pairs with dash? 900| 4.10M| if (lang_with_dash_usage) { ------------------ | Branch (900:9): [True: 0, False: 4.10M] ------------------ 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| 4.10M| if (wlst.size() < maxSug && !nosplitsugs && !good) { ------------------ | Branch (916:9): [True: 4.10M, False: 473] | Branch (916:33): [True: 4.10M, False: 0] | Branch (916:49): [True: 4.10M, False: 821] ------------------ 917| 4.10M| *p = '\0'; 918| 4.10M| int c1 = checkword(candidate, cpdsuggest, nullptr, nullptr); 919| 4.10M| if (c1) { ------------------ | Branch (919:11): [True: 33.8k, False: 4.06M] ------------------ 920| 33.8k| c2 = checkword((p + 1), cpdsuggest, nullptr, nullptr); 921| 33.8k| if (c2) { ------------------ | Branch (921:13): [True: 1.07k, False: 32.8k] ------------------ 922| | // spec. Hungarian code (TODO need a better compound word support) 923| 1.07k| if ((langnum == LANG_hu) && !forbidden && ------------------ | Branch (923:15): [True: 27, False: 1.04k] | Branch (923:39): [True: 27, False: 0] ------------------ 924| | // if 3 repeating letter, use - instead of space 925| 27| (((p[-1] == p[1]) && ------------------ | Branch (925:17): [True: 14, False: 13] ------------------ 926| 14| (((p > candidate + 1) && (p[-1] == p[-2])) || (p[-1] == p[2]))) || ------------------ | Branch (926:17): [True: 0, False: 14] | Branch (926:40): [True: 0, False: 0] | Branch (926:61): [True: 0, False: 14] ------------------ 927| | // or multiple compounding, with more, than 6 syllables 928| 27| ((c1 == 3) && (c2 >= 2)))) ------------------ | Branch (928:16): [True: 0, False: 27] | Branch (928:29): [True: 0, False: 0] ------------------ 929| 0| *p = '-'; 930| 1.07k| else 931| 1.07k| *p = ' '; 932| | 933| 1.07k| cwrd = std::find(wlst.begin(), wlst.end(), candidate) != wlst.end() ? 0 : 1; ------------------ | Branch (933:18): [True: 35, False: 1.04k] ------------------ 934| | 935| 1.07k| if (cwrd && (wlst.size() < maxSug)) ------------------ | Branch (935:15): [True: 1.04k, False: 35] | Branch (935:23): [True: 1.04k, False: 0] ------------------ 936| 1.04k| 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| 1.07k| if ( !nosplitsugs && lang_with_dash_usage && ------------------ | Branch (940:16): [True: 1.07k, False: 0] | Branch (940:32): [True: 0, False: 1.07k] ------------------ 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| 1.07k| } 954| 33.8k| } 955| 4.10M| } 956| 4.10M| } 957| 340k| delete[] candidate; 958| 340k| return good; 959| 397k|} _ZN10SuggestMgr8swapcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 964| 248k| int cpdsuggest, int& info) { 965| 248k| if (word.size() < 2) ------------------ | Branch (965:7): [True: 19.9k, False: 229k] ------------------ 966| 19.9k| return wlst.size(); 967| | 968| 229k| std::string candidate(word); 969| | 970| | // try swapping adjacent chars one by one 971| 5.02M| for (size_t i = 0; i < candidate.size() - 1; ++i) { ------------------ | Branch (971:22): [True: 4.79M, False: 229k] ------------------ 972| 4.79M| std::swap(candidate[i], candidate[i+1]); 973| 4.79M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 974| 4.79M| std::swap(candidate[i], candidate[i+1]); 975| 4.79M| } 976| | 977| | // try double swaps for short words 978| | // ahev -> have, owudl -> would 979| 229k| if (candidate.size() == 4 || candidate.size() == 5) { ------------------ | Branch (979:7): [True: 12.9k, False: 216k] | Branch (979:32): [True: 8.96k, False: 207k] ------------------ 980| 21.9k| candidate[0] = word[1]; 981| 21.9k| candidate[1] = word[0]; 982| 21.9k| candidate[2] = word[2]; 983| 21.9k| candidate[candidate.size() - 2] = word[candidate.size() - 1]; 984| 21.9k| candidate[candidate.size() - 1] = word[candidate.size() - 2]; 985| 21.9k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 986| 21.9k| if (candidate.size() == 5) { ------------------ | Branch (986:9): [True: 8.96k, False: 12.9k] ------------------ 987| 8.96k| candidate[0] = word[0]; 988| 8.96k| candidate[1] = word[2]; 989| 8.96k| candidate[2] = word[1]; 990| 8.96k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 991| 8.96k| } 992| 21.9k| } 993| | 994| 229k| return wlst.size(); 995| 248k|} _ZN10SuggestMgr12swapchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 1000| 148k| int cpdsuggest, int& info) { 1001| 148k| if (word.size() < 2) ------------------ | Branch (1001:7): [True: 16.3k, False: 132k] ------------------ 1002| 16.3k| return wlst.size(); 1003| | 1004| 132k| std::vector candidate_utf(word); 1005| | 1006| 132k| std::string candidate; 1007| | // try swapping adjacent chars one by one 1008| 1.76M| for (size_t i = 0; i < candidate_utf.size() - 1; ++i) { ------------------ | Branch (1008:22): [True: 1.62M, False: 132k] ------------------ 1009| 1.62M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 1.62M|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (1009:9): [True: 0, False: 1.62M] ------------------ 1010| 0| return wlst.size(); 1011| 1.62M| std::swap(candidate_utf[i], candidate_utf[i+1]); 1012| 1.62M| u16_u8(candidate, candidate_utf); 1013| 1.62M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1014| 1.62M| std::swap(candidate_utf[i], candidate_utf[i+1]); 1015| 1.62M| } 1016| | 1017| | // try double swaps for short words 1018| | // ahev -> have, owudl -> would, suodn -> sound 1019| 132k| if (candidate_utf.size() == 4 || candidate_utf.size() == 5) { ------------------ | Branch (1019:7): [True: 16.9k, False: 115k] | Branch (1019:36): [True: 10.1k, False: 105k] ------------------ 1020| 27.0k| candidate_utf[0] = word[1]; 1021| 27.0k| candidate_utf[1] = word[0]; 1022| 27.0k| candidate_utf[2] = word[2]; 1023| 27.0k| candidate_utf[candidate_utf.size() - 2] = word[candidate_utf.size() - 1]; 1024| 27.0k| candidate_utf[candidate_utf.size() - 1] = word[candidate_utf.size() - 2]; 1025| 27.0k| u16_u8(candidate, candidate_utf); 1026| 27.0k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1027| 27.0k| if (candidate_utf.size() == 5) { ------------------ | Branch (1027:9): [True: 10.1k, False: 16.9k] ------------------ 1028| 10.1k| candidate_utf[0] = word[0]; 1029| 10.1k| candidate_utf[1] = word[2]; 1030| 10.1k| candidate_utf[2] = word[1]; 1031| 10.1k| u16_u8(candidate, candidate_utf); 1032| 10.1k| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1033| 10.1k| } 1034| 27.0k| } 1035| 132k| return wlst.size(); 1036| 132k|} _ZN10SuggestMgr12longswapcharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 1041| 248k| int cpdsuggest, int& info) { 1042| 248k| std::string candidate(word); 1043| | // try swapping not adjacent chars one by one 1044| 5.29M| for (auto p = candidate.begin(); p < candidate.end(); ++p) { ------------------ | Branch (1044:36): [True: 5.04M, False: 248k] ------------------ 1045| 181M| for (auto q = candidate.begin(); q < candidate.end(); ++q) { ------------------ | Branch (1045:38): [True: 176M, False: 5.04M] ------------------ 1046| 176M| const auto distance = std::abs(std::distance(q, p)); 1047| 176M| if (distance > 1 && distance <= MAX_CHAR_DISTANCE && *p != *q) { ------------------ | | 84| 338M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1047:11): [True: 161M, False: 14.6M] | Branch (1047:27): [True: 26.1M, False: 135M] | Branch (1047:60): [True: 19.4M, False: 6.64M] ------------------ 1048| 19.4M| std::swap(*p, *q); 1049| 19.4M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1050| 19.4M| std::swap(*p, *q); 1051| 19.4M| } 1052| 176M| } 1053| 5.04M| } 1054| 248k| return wlst.size(); 1055| 248k|} _ZN10SuggestMgr16longswapchar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 1060| 148k| int cpdsuggest, int& info) { 1061| 148k| std::vector candidate_utf(word); 1062| | // try swapping not adjacent chars 1063| 1.92M| for (auto p = candidate_utf.begin(); p < candidate_utf.end(); ++p) { ------------------ | Branch (1063:40): [True: 1.77M, False: 148k] ------------------ 1064| 47.8M| for (auto q = candidate_utf.begin(); q < candidate_utf.end(); ++q) { ------------------ | Branch (1064:42): [True: 46.1M, False: 1.77M] ------------------ 1065| 46.1M| const auto distance = std::abs(std::distance(q, p)); 1066| 46.1M| if (distance > 1 && distance <= MAX_CHAR_DISTANCE && *p != *q) { ------------------ | | 84| 87.1M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1066:11): [True: 41.0M, False: 5.03M] | Branch (1066:27): [True: 8.26M, False: 32.8M] | Branch (1066:60): [True: 5.70M, False: 2.56M] ------------------ 1067| 5.70M| std::swap(*p, *q); 1068| 5.70M| std::string candidate; 1069| 5.70M| u16_u8(candidate, candidate_utf); 1070| 5.70M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1071| 5.70M| std::swap(*p, *q); 1072| 5.70M| } 1073| 46.1M| } 1074| 1.77M| } 1075| 148k| return wlst.size(); 1076| 148k|} _ZN10SuggestMgr8movecharERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_iRi: 1081| 248k| int cpdsuggest, int& info) { 1082| 248k| if (word.size() < 2) ------------------ | Branch (1082:7): [True: 19.9k, False: 229k] ------------------ 1083| 19.9k| return wlst.size(); 1084| | 1085| 229k| std::string candidate(word); 1086| | 1087| | // try moving a char 1088| 5.25M| for (auto p = candidate.begin(); p < candidate.end(); ++p) { ------------------ | Branch (1088:36): [True: 5.02M, False: 229k] ------------------ 1089| 22.8M| for (auto q = p + 1; q < candidate.end() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 21.7M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1089:26): [True: 21.7M, False: 1.07M] | Branch (1089:26): [True: 17.8M, False: 5.02M] | Branch (1089:49): [True: 17.8M, False: 3.94M] ------------------ 1090| 17.8M| std::swap(*q, *(q - 1)); 1091| 17.8M| if (std::distance(p, q) < 2) ------------------ | Branch (1091:11): [True: 4.79M, False: 13.0M] ------------------ 1092| 4.79M| continue; // omit swap char 1093| 13.0M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1094| 13.0M| } 1095| 5.02M| const auto word_iter = word.begin(); 1096| 5.02M| std::copy_n(word_iter, candidate.size(), candidate.begin()); 1097| 5.02M| } 1098| | 1099| 5.02M| for (auto p = candidate.rbegin(), pEnd = candidate.rend() - 1; p != pEnd; ++p) { ------------------ | Branch (1099:66): [True: 4.79M, False: 229k] ------------------ 1100| 22.6M| for (auto q = p + 1, qEnd = candidate.rend(); q != qEnd && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 21.7M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1100:51): [True: 21.7M, False: 845k] | Branch (1100:64): [True: 17.8M, False: 3.94M] ------------------ 1101| 17.8M| std::swap(*q, *(q - 1)); 1102| 17.8M| if (std::distance(p, q) < 2) ------------------ | Branch (1102:11): [True: 4.79M, False: 13.0M] ------------------ 1103| 4.79M| continue; // omit swap char 1104| 13.0M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1105| 13.0M| } 1106| 4.79M| const auto word_iter = word.begin(); 1107| 4.79M| std::copy_n(word_iter, candidate.size(), candidate.begin()); 1108| 4.79M| } 1109| | 1110| 229k| return wlst.size(); 1111| 248k|} _ZN10SuggestMgr12movechar_utfERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKNS1_I6w_charNS5_ISB_EEEEiRi: 1116| 148k| int cpdsuggest, int& info) { 1117| 148k| if (word.size() < 2) ------------------ | Branch (1117:7): [True: 16.3k, False: 132k] ------------------ 1118| 16.3k| return wlst.size(); 1119| | 1120| 132k| std::vector candidate_utf(word); 1121| | 1122| | // try moving a char 1123| 1.89M| for (auto p = candidate_utf.begin(); p < candidate_utf.end(); ++p) { ------------------ | Branch (1123:40): [True: 1.76M, False: 132k] ------------------ 1124| 7.52M| for (auto q = p + 1; q < candidate_utf.end() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 6.92M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1124:26): [True: 6.92M, False: 592k] | Branch (1124:26): [True: 5.76M, False: 1.76M] | Branch (1124:53): [True: 5.76M, False: 1.16M] ------------------ 1125| 5.76M| std::swap(*q, *(q - 1)); 1126| 5.76M| if (std::distance(p, q) < 2) ------------------ | Branch (1126:11): [True: 1.62M, False: 4.13M] ------------------ 1127| 1.62M| continue; // omit swap char 1128| 4.13M| std::string candidate; 1129| 4.13M| u16_u8(candidate, candidate_utf); 1130| 4.13M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1131| 4.13M| } 1132| 1.76M| const auto word_iter = word.begin(); 1133| 1.76M| std::copy_n(word_iter, candidate_utf.size(), candidate_utf.begin()); 1134| 1.76M| } 1135| | 1136| 1.89M| for (auto p = candidate_utf.rbegin(); p < candidate_utf.rend(); ++p) { ------------------ | Branch (1136:41): [True: 1.76M, False: 132k] ------------------ 1137| 7.52M| for (auto q = p + 1; q < candidate_utf.rend() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) { ------------------ | | 84| 6.92M|#define MAX_CHAR_DISTANCE 4 ------------------ | Branch (1137:26): [True: 6.92M, False: 592k] | Branch (1137:26): [True: 5.76M, False: 1.76M] | Branch (1137:54): [True: 5.76M, False: 1.16M] ------------------ 1138| 5.76M| std::swap(*q, *(q - 1)); 1139| 5.76M| if (std::distance(p, q) < 2) ------------------ | Branch (1139:11): [True: 1.62M, False: 4.13M] ------------------ 1140| 1.62M| continue; // omit swap char 1141| 4.13M| std::string candidate; 1142| 4.13M| u16_u8(candidate, candidate_utf); 1143| 4.13M| testsug(wlst, candidate, cpdsuggest, nullptr, nullptr, info); 1144| 4.13M| } 1145| 1.76M| const auto word_iter = word.begin(); 1146| 1.76M| std::copy_n(word_iter, candidate_utf.size(), candidate_utf.begin()); 1147| 1.76M| } 1148| | 1149| 132k| return wlst.size(); 1150| 148k|} _ZN10SuggestMgr9ngsuggestERNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEEPKcRKNS1_INS0_10unique_ptrI7HashMgrNS0_14default_deleteISE_EEEENS5_ISH_EEEEi: 1185| 59.9k| int captype) { 1186| 59.9k| 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| 59.9k| struct hentry* roots[MAX_ROOTS]; 1191| 59.9k| char* rootsphon[MAX_ROOTS]; 1192| 59.9k| int scores[MAX_ROOTS]; 1193| 59.9k| int scoresphon[MAX_ROOTS]; 1194| 6.05M| for (int i = 0; i < MAX_ROOTS; i++) { ------------------ | | 74| 6.05M|#define MAX_ROOTS 100 ------------------ | Branch (1194:19): [True: 5.99M, False: 59.9k] ------------------ 1195| 5.99M| roots[i] = nullptr; 1196| 5.99M| scores[i] = -100 * i; 1197| 5.99M| rootsphon[i] = nullptr; 1198| 5.99M| scoresphon[i] = -100 * i; 1199| 5.99M| } 1200| 59.9k| bool has_roots = false; 1201| 59.9k| bool has_rootsphon = false; 1202| 59.9k| lp = MAX_ROOTS - 1; ------------------ | | 74| 59.9k|#define MAX_ROOTS 100 ------------------ 1203| 59.9k| lpphon = MAX_ROOTS - 1; ------------------ | | 74| 59.9k|#define MAX_ROOTS 100 ------------------ 1204| 59.9k| int low = NGRAM_LOWERING; ------------------ | | 83| 59.9k|#define NGRAM_LOWERING (1 << 2) ------------------ 1205| | 1206| 59.9k| std::string w2; 1207| 59.9k| const char* word = w; 1208| | 1209| 59.9k| int nc; 1210| | // word reversing wrapper for complex prefixes 1211| 59.9k| if (complexprefixes) { ------------------ | Branch (1211:7): [True: 3.40k, False: 56.5k] ------------------ 1212| 3.40k| w2.assign(w); 1213| 3.40k| if (utf8) ------------------ | Branch (1213:9): [True: 0, False: 3.40k] ------------------ 1214| 0| reverseword_utf(w2); 1215| 3.40k| else 1216| 3.40k| reverseword(w2); 1217| 3.40k| word = w2.c_str(); 1218| 3.40k| nc = (int)w2.size(); 1219| 56.5k| } else { 1220| 56.5k| nc = (int)strlen(word); 1221| 56.5k| } 1222| | 1223| 59.9k| std::vector u8; 1224| 59.9k| int n = (utf8) ? u8_u16(u8, word) : nc; ------------------ | Branch (1224:11): [True: 25.1k, False: 34.7k] ------------------ 1225| | 1226| | // set character based ngram suggestion for words with non-BMP Unicode 1227| | // characters 1228| 59.9k| const struct cs_info* origconv = csconv; 1229| 59.9k| if (n == -1) { ------------------ | Branch (1229:7): [True: 2.13k, False: 57.7k] ------------------ 1230| 2.13k| utf8 = 0; // XXX not state-free 1231| 2.13k| if (!csconv) ------------------ | Branch (1231:9): [True: 2.13k, False: 0] ------------------ 1232| 2.13k| csconv = get_current_cs("iso88591"); // XXX not state-free 1233| 2.13k| n = nc; 1234| 2.13k| nonbmp = 1; 1235| 2.13k| low = 0; 1236| 2.13k| } 1237| 59.9k| ngsuggest_guard restore_state(nonbmp, origconv, &utf8, &csconv); 1238| 59.9k| int max_word_len = (utf8) ? MAXWORDUTF8LEN : MAXWORDLEN; ------------------ | | 85| 23.0k|#define MAXWORDUTF8LEN (MAXWORDLEN * 3) | | ------------------ | | | | 90| 23.0k|#define MAXWORDLEN 100 | | ------------------ ------------------ int max_word_len = (utf8) ? MAXWORDUTF8LEN : MAXWORDLEN; ------------------ | | 90| 36.8k|#define MAXWORDLEN 100 ------------------ | Branch (1238:22): [True: 23.0k, False: 36.8k] ------------------ 1239| | // ofz#59067 a replist entry can generate a very long word, abandon 1240| | // ngram if that odd-edge case arises 1241| 59.9k| if (n > max_word_len * 4) ------------------ | Branch (1241:7): [True: 0, False: 59.9k] ------------------ 1242| 0| return; 1243| | 1244| 59.9k| struct hentry* hp = nullptr; 1245| 59.9k| int col = -1; 1246| 59.9k| phonetable* ph = (pAMgr) ? pAMgr->get_phonetable() : nullptr; ------------------ | Branch (1246:20): [True: 59.9k, False: 0] ------------------ 1247| 59.9k| std::string target; 1248| 59.9k| std::string candidate; 1249| 59.9k| std::vector w_candidate; 1250| 59.9k| if (ph) { ------------------ | Branch (1250:7): [True: 3.42k, False: 56.4k] ------------------ 1251| 3.42k| if (utf8) { ------------------ | Branch (1251:9): [True: 0, False: 3.42k] ------------------ 1252| 0| u8_u16(w_candidate, word); 1253| 0| mkallcap_utf(w_candidate, langnum); 1254| 0| u16_u8(candidate, w_candidate); 1255| 3.42k| } else { 1256| 3.42k| candidate.assign(word); 1257| 3.42k| if (!nonbmp) ------------------ | Branch (1257:11): [True: 3.42k, False: 0] ------------------ 1258| 3.42k| mkallcap(candidate, csconv); 1259| 3.42k| } 1260| 3.42k| target = phonet(candidate, *ph); // XXX phonet() is 8-bit (nc, not n) 1261| 3.42k| } 1262| | 1263| 59.9k| FLAG forbiddenword = pAMgr ? pAMgr->get_forbiddenword() : FLAG_NULL; ------------------ | | 95| 59.9k|#define FLAG unsigned short ------------------ FLAG forbiddenword = pAMgr ? pAMgr->get_forbiddenword() : FLAG_NULL; ------------------ | | 96| 59.9k|#define FLAG_NULL 0x00 ------------------ | Branch (1263:24): [True: 59.9k, False: 0] ------------------ 1264| 59.9k| FLAG nosuggest = pAMgr ? pAMgr->get_nosuggest() : FLAG_NULL; ------------------ | | 95| 59.9k|#define FLAG unsigned short ------------------ FLAG nosuggest = pAMgr ? pAMgr->get_nosuggest() : FLAG_NULL; ------------------ | | 96| 59.9k|#define FLAG_NULL 0x00 ------------------ | Branch (1264:20): [True: 59.9k, False: 0] ------------------ 1265| 59.9k| FLAG nongramsuggest = pAMgr ? pAMgr->get_nongramsuggest() : FLAG_NULL; ------------------ | | 95| 59.9k|#define FLAG unsigned short ------------------ FLAG nongramsuggest = pAMgr ? pAMgr->get_nongramsuggest() : FLAG_NULL; ------------------ | | 96| 59.9k|#define FLAG_NULL 0x00 ------------------ | Branch (1265:25): [True: 59.9k, False: 0] ------------------ 1266| 59.9k| FLAG onlyincompound = pAMgr ? pAMgr->get_onlyincompound() : FLAG_NULL; ------------------ | | 95| 59.9k|#define FLAG unsigned short ------------------ FLAG onlyincompound = pAMgr ? pAMgr->get_onlyincompound() : FLAG_NULL; ------------------ | | 96| 59.9k|#define FLAG_NULL 0x00 ------------------ | Branch (1266:25): [True: 59.9k, False: 0] ------------------ 1267| | 1268| 59.9k| std::vector w_word, w_target; 1269| 59.9k| if (utf8) { ------------------ | Branch (1269:7): [True: 23.0k, False: 36.8k] ------------------ 1270| 23.0k| u8_u16(w_word, word); 1271| 23.0k| u8_u16(w_target, target); 1272| 23.0k| } 1273| | 1274| 59.9k| std::string f; 1275| 59.9k| std::vector w_f; 1276| | 1277| 59.9k| for (const auto& i : rHMgr) { ------------------ | Branch (1277:22): [True: 59.9k, False: 59.9k] ------------------ 1278| 1.92M| while (nullptr != (hp = i->walk_hashtable(col, hp))) { ------------------ | Branch (1278:12): [True: 1.86M, False: 59.9k] ------------------ 1279| | // skip exceptions 1280| 1.86M| 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| 1.86M| (((abs(n - hp->clen) > 4) && !nonbmp)) || ------------------ | Branch (1284:12): [True: 1.33M, False: 529k] | Branch (1284:14): [True: 1.24M, False: 625k] | Branch (1284:41): [True: 1.18M, False: 61.6k] ------------------ 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| 687k| ((captype == NOCAP) && (hp->var & H_OPT_INITCAP) && ------------------ | | 92| 687k|#define NOCAP 0 ------------------ ((captype == NOCAP) && (hp->var & H_OPT_INITCAP) && ------------------ | | 50| 184k|#define H_OPT_INITCAP (1 << 3) // is dictionary word capitalized? ------------------ | Branch (1291:13): [True: 184k, False: 502k] | Branch (1291:35): [True: 83.4k, False: 101k] ------------------ 1292| 83.4k| !ph && (langnum != LANG_de) && !(hp->var & H_OPT_PHON)) || ------------------ | | 49| 81.7k|#define H_OPT_PHON (1 << 2) // is there ph: field in the morphological data? ------------------ | Branch (1292:15): [True: 81.7k, False: 1.68k] | Branch (1292:22): [True: 81.7k, False: 0] | Branch (1292:46): [True: 81.7k, False: 0] ------------------ 1293| | // or it has one of the following special flags 1294| 605k| ((hp->astr) && (pAMgr) && ------------------ | Branch (1294:13): [True: 168k, False: 436k] | Branch (1294:27): [True: 168k, False: 0] ------------------ 1295| 168k| (TESTAFF(hp->astr, forbiddenword, hp->alen) || ------------------ | | 99| 337k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 2.06k, False: 166k] | | ------------------ ------------------ 1296| 166k| TESTAFF(hp->astr, ONLYUPCASEFLAG, hp->alen) || ------------------ | | 99| 335k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 73.4k, False: 93.2k] | | ------------------ ------------------ 1297| 93.2k| TESTAFF(hp->astr, nosuggest, hp->alen) || ------------------ | | 99| 262k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 93.2k] | | ------------------ ------------------ 1298| 93.2k| TESTAFF(hp->astr, nongramsuggest, hp->alen) || ------------------ | | 99| 262k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 93.2k] | | ------------------ ------------------ 1299| 93.2k| TESTAFF(hp->astr, onlyincompound, hp->alen))) ------------------ | | 99| 93.2k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 93.2k] | | ------------------ ------------------ 1300| 1.86M| ) 1301| 1.33M| continue; 1302| | 1303| 529k| if (utf8) { ------------------ | Branch (1303:11): [True: 235k, False: 294k] ------------------ 1304| 235k| u8_u16(w_f, HENTRY_WORD(hp)); ------------------ | | 54| 235k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1305| | 1306| 235k| int leftcommon = leftcommonsubstring(w_word, w_f); 1307| 235k| if (low) { ------------------ | Branch (1307:13): [True: 235k, False: 0] ------------------ 1308| | // lowering dictionary word 1309| 235k| mkallsmall_utf(w_f, langnum); 1310| 235k| } 1311| 235k| sc = ngram(3, w_word, w_f, NGRAM_LONGER_WORSE) + leftcommon; ------------------ | | 81| 235k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1312| 294k| } else { 1313| 294k| f.assign(HENTRY_WORD(hp)); ------------------ | | 54| 294k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1314| | 1315| 294k| int leftcommon = leftcommonsubstring(word, f.c_str()); 1316| 294k| if (low) { ------------------ | Branch (1316:13): [True: 266k, False: 27.9k] ------------------ 1317| | // lowering dictionary word 1318| 266k| mkallsmall(f, csconv); 1319| 266k| } 1320| 294k| sc = ngram(3, word, f, NGRAM_LONGER_WORSE) + leftcommon; ------------------ | | 81| 294k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1321| 294k| } 1322| | 1323| | // check special pronunciation 1324| 529k| f.clear(); 1325| 529k| if ((hp->var & H_OPT_PHON) && ------------------ | | 49| 529k|#define H_OPT_PHON (1 << 2) // is there ph: field in the morphological data? ------------------ | Branch (1325:11): [True: 817, False: 529k] | Branch (1325:11): [True: 817, False: 529k] ------------------ 1326| 817| copy_field(f, HENTRY_DATA(hp), MORPH_PHON)) { ------------------ | | 114| 817|#define MORPH_PHON "ph:" ------------------ | Branch (1326:11): [True: 817, False: 0] ------------------ 1327| 817| int sc2; 1328| 817| if (utf8) { ------------------ | Branch (1328:13): [True: 0, False: 817] ------------------ 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| 817| } else { 1338| 817| int leftcommon = leftcommonsubstring(word, f.c_str()); 1339| 817| if (low) { ------------------ | Branch (1339:15): [True: 817, False: 0] ------------------ 1340| | // lowering dictionary word 1341| 817| mkallsmall(f, csconv); 1342| 817| } 1343| 817| sc2 = ngram(3, word, f, NGRAM_LONGER_WORSE) + leftcommon; ------------------ | | 81| 817|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1344| 817| } 1345| 817| if (sc2 > sc) ------------------ | Branch (1345:13): [True: 412, False: 405] ------------------ 1346| 412| sc = sc2; 1347| 817| } 1348| | 1349| 529k| int scphon = -20000; 1350| 529k| if (ph && (sc > 2) && (abs(n - (int)hp->clen) <= 3)) { ------------------ | Branch (1350:11): [True: 31.7k, False: 498k] | Branch (1350:17): [True: 6.98k, False: 24.7k] | Branch (1350:29): [True: 5.84k, False: 1.14k] ------------------ 1351| 5.84k| if (utf8) { ------------------ | Branch (1351:13): [True: 0, False: 5.84k] ------------------ 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| 5.84k| } else { 1356| 5.84k| candidate = HENTRY_WORD(hp); ------------------ | | 54| 5.84k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1357| 5.84k| mkallcap(candidate, csconv); 1358| 5.84k| } 1359| 5.84k| f = phonet(candidate, *ph); 1360| 5.84k| if (utf8) { ------------------ | Branch (1360:13): [True: 0, False: 5.84k] ------------------ 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| 5.84k| } else { 1365| 5.84k| scphon = 2 * ngram(3, target, f, 1366| 5.84k| NGRAM_LONGER_WORSE); ------------------ | | 81| 5.84k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ 1367| 5.84k| } 1368| 5.84k| } 1369| | 1370| 529k| if (sc > scores[lp]) { ------------------ | Branch (1370:11): [True: 529k, False: 0] ------------------ 1371| 529k| scores[lp] = sc; 1372| 529k| roots[lp] = hp; 1373| 529k| has_roots = true; 1374| 529k| lval = sc; 1375| 53.5M| for (int j = 0; j < MAX_ROOTS; j++) ------------------ | | 74| 53.5M|#define MAX_ROOTS 100 ------------------ | Branch (1375:25): [True: 52.9M, False: 529k] ------------------ 1376| 52.9M| if (scores[j] < lval) { ------------------ | Branch (1376:15): [True: 44.5M, False: 8.48M] ------------------ 1377| 44.5M| lp = j; 1378| 44.5M| lval = scores[j]; 1379| 44.5M| } 1380| 529k| } 1381| | 1382| 529k| if (scphon > scoresphon[lpphon]) { ------------------ | Branch (1382:11): [True: 5.84k, False: 524k] ------------------ 1383| 5.84k| scoresphon[lpphon] = scphon; 1384| 5.84k| rootsphon[lpphon] = HENTRY_WORD(hp); ------------------ | | 54| 5.84k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1385| 5.84k| has_rootsphon = true; 1386| 5.84k| lval = scphon; 1387| 590k| for (int j = 0; j < MAX_ROOTS; j++) ------------------ | | 74| 590k|#define MAX_ROOTS 100 ------------------ | Branch (1387:25): [True: 584k, False: 5.84k] ------------------ 1388| 584k| if (scoresphon[j] < lval) { ------------------ | Branch (1388:15): [True: 517k, False: 66.5k] ------------------ 1389| 517k| lpphon = j; 1390| 517k| lval = scoresphon[j]; 1391| 517k| } 1392| 5.84k| } 1393| 529k| } 1394| 59.9k| } 1395| | 1396| 59.9k| if (!has_roots && !has_rootsphon) { ------------------ | Branch (1396:7): [True: 13.9k, False: 45.9k] | Branch (1396:21): [True: 13.9k, False: 0] ------------------ 1397| | // with no roots there will be no guesses and no point running 1398| | // ngram 1399| 13.9k| return; 1400| 13.9k| } 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| 45.9k| std::vector w_mw; 1406| 45.9k| int thresh = 0; 1407| 183k| for (int sp = 1; sp < 4; sp++) { ------------------ | Branch (1407:20): [True: 137k, False: 45.9k] ------------------ 1408| 137k| if (utf8) { ------------------ | Branch (1408:9): [True: 55.9k, False: 82.0k] ------------------ 1409| 55.9k| w_mw = w_word; 1410| 103k| for (int k = sp; k < n; k += 4) { ------------------ | Branch (1410:24): [True: 47.7k, False: 55.9k] ------------------ 1411| 47.7k| w_mw[k].l = '*'; 1412| 47.7k| w_mw[k].h = 0; 1413| 47.7k| } 1414| | 1415| 55.9k| if (low) { ------------------ | Branch (1415:11): [True: 55.9k, False: 0] ------------------ 1416| | // lowering dictionary word 1417| 55.9k| mkallsmall_utf(w_mw, langnum); 1418| 55.9k| } 1419| | 1420| 55.9k| thresh += ngram(n, w_word, w_mw, NGRAM_ANY_MISMATCH); ------------------ | | 82| 55.9k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1421| 82.0k| } else { 1422| 82.0k| std::string mw = word; 1423| 195k| for (int k = sp; k < n; k += 4) ------------------ | Branch (1423:24): [True: 113k, False: 82.0k] ------------------ 1424| 113k| mw[k] = '*'; 1425| | 1426| 82.0k| if (low) { ------------------ | Branch (1426:11): [True: 75.6k, False: 6.39k] ------------------ 1427| | // lowering dictionary word 1428| 75.6k| mkallsmall(mw, csconv); 1429| 75.6k| } 1430| | 1431| 82.0k| thresh += ngram(n, word, mw, NGRAM_ANY_MISMATCH); ------------------ | | 82| 82.0k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1432| 82.0k| } 1433| 137k| } 1434| 45.9k| thresh = thresh / 3; 1435| 45.9k| 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| 45.9k| char* guess[MAX_GUESS]; 1441| 45.9k| char* guessorig[MAX_GUESS]; 1442| 45.9k| int gscore[MAX_GUESS]; 1443| 9.24M| for (int i = 0; i < MAX_GUESS; i++) { ------------------ | | 76| 9.24M|#define MAX_GUESS 200 ------------------ | Branch (1443:19): [True: 9.19M, False: 45.9k] ------------------ 1444| 9.19M| guess[i] = nullptr; 1445| 9.19M| guessorig[i] = nullptr; 1446| 9.19M| gscore[i] = -100 * i; 1447| 9.19M| } 1448| | 1449| 45.9k| lp = MAX_GUESS - 1; ------------------ | | 76| 45.9k|#define MAX_GUESS 200 ------------------ 1450| | 1451| 45.9k| std::vector glst(MAX_WORDS); ------------------ | | 75| 45.9k|#define MAX_WORDS 100 ------------------ 1452| | 1453| 4.59M| for (auto& root : roots) { ------------------ | Branch (1453:19): [True: 4.59M, False: 45.9k] ------------------ 1454| 4.59M| if (root) { ------------------ | Branch (1454:9): [True: 529k, False: 4.06M] ------------------ 1455| 529k| struct hentry* rp = root; 1456| | 1457| 529k| f.clear(); 1458| 529k| const char* field = nullptr; 1459| 529k| if ((rp->var & H_OPT_PHON) && copy_field(f, HENTRY_DATA(rp), MORPH_PHON)) ------------------ | | 49| 529k|#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| 817|#define MORPH_PHON "ph:" ------------------ | Branch (1459:11): [True: 817, False: 529k] | Branch (1459:11): [True: 817, False: 529k] | Branch (1459:37): [True: 817, False: 0] ------------------ 1460| 817| field = f.c_str(); 1461| 529k| int nw = pAMgr->expand_rootword( 1462| 529k| glst.data(), MAX_WORDS, HENTRY_WORD(rp), rp->blen, rp->astr, rp->alen, word, ------------------ | | 75| 529k|#define MAX_WORDS 100 ------------------ glst.data(), MAX_WORDS, HENTRY_WORD(rp), rp->blen, rp->astr, rp->alen, word, ------------------ | | 54| 529k|#define HENTRY_WORD(h) &(h->word[0]) ------------------ 1463| 529k| nc, field); 1464| | 1465| 1.05M| for (int k = 0; k < nw; k++) { ------------------ | Branch (1465:23): [True: 528k, False: 529k] ------------------ 1466| 528k| if (utf8) { ------------------ | Branch (1466:13): [True: 235k, False: 293k] ------------------ 1467| 235k| u8_u16(w_f, glst[k].word); 1468| | 1469| 235k| int leftcommon = leftcommonsubstring(w_word, w_f); 1470| 235k| if (low) { ------------------ | Branch (1470:15): [True: 235k, False: 0] ------------------ 1471| | // lowering dictionary word 1472| 235k| mkallsmall_utf(w_f, langnum); 1473| 235k| } 1474| | 1475| 235k| sc = ngram(n, w_word, w_f, NGRAM_ANY_MISMATCH) + leftcommon; ------------------ | | 82| 235k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1476| 293k| } else { 1477| 293k| f = glst[k].word; 1478| | 1479| 293k| int leftcommon = leftcommonsubstring(word, f.c_str()); 1480| 293k| if (low) { ------------------ | Branch (1480:15): [True: 265k, False: 27.9k] ------------------ 1481| | // lowering dictionary word 1482| 265k| mkallsmall(f, csconv); 1483| 265k| } 1484| | 1485| 293k| sc = ngram(n, word, f, NGRAM_ANY_MISMATCH) + leftcommon; ------------------ | | 82| 293k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1486| 293k| } 1487| | 1488| 528k| if (sc > thresh) { ------------------ | Branch (1488:13): [True: 88.1k, False: 440k] ------------------ 1489| 88.1k| if (sc > gscore[lp]) { ------------------ | Branch (1489:15): [True: 88.1k, False: 0] ------------------ 1490| 88.1k| if (guess[lp]) { ------------------ | Branch (1490:17): [True: 0, False: 88.1k] ------------------ 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| 88.1k| gscore[lp] = sc; 1498| 88.1k| guess[lp] = glst[k].word; 1499| 88.1k| guessorig[lp] = glst[k].orig; 1500| 88.1k| lval = sc; 1501| 17.7M| for (int j = 0; j < MAX_GUESS; j++) ------------------ | | 76| 17.7M|#define MAX_GUESS 200 ------------------ | Branch (1501:29): [True: 17.6M, False: 88.1k] ------------------ 1502| 17.6M| if (gscore[j] < lval) { ------------------ | Branch (1502:19): [True: 16.8M, False: 758k] ------------------ 1503| 16.8M| lp = j; 1504| 16.8M| lval = gscore[j]; 1505| 16.8M| } 1506| 88.1k| } else { 1507| 0| delete[] glst[k].word; 1508| 0| delete[] glst[k].orig; 1509| 0| } 1510| 440k| } else { 1511| 440k| delete[] glst[k].word; 1512| 440k| delete[] glst[k].orig; 1513| 440k| } 1514| 528k| } 1515| 529k| } 1516| 4.59M| } 1517| 45.9k| glst.clear(); 1518| | 1519| | // now we are done generating guesses 1520| | // sort in order of decreasing score 1521| | 1522| 45.9k| bubblesort(&guess[0], &guessorig[0], &gscore[0], MAX_GUESS); ------------------ | | 76| 45.9k|#define MAX_GUESS 200 ------------------ 1523| 45.9k| if (ph) ------------------ | Branch (1523:7): [True: 2.73k, False: 43.2k] ------------------ 1524| 2.73k| bubblesort(&rootsphon[0], nullptr, &scoresphon[0], MAX_ROOTS); ------------------ | | 74| 2.73k|#define MAX_ROOTS 100 ------------------ 1525| | 1526| | // weight suggestions with a similarity index, based on 1527| | // the longest common subsequent algorithm and resort 1528| | 1529| 45.9k| int is_swap = 0; 1530| 45.9k| int re = 0; 1531| 45.9k| double fact = 1.0; 1532| 45.9k| if (pAMgr) { ------------------ | Branch (1532:7): [True: 45.9k, False: 0] ------------------ 1533| 45.9k| int maxd = pAMgr->get_maxdiff(); 1534| 45.9k| if (maxd >= 0) ------------------ | Branch (1534:9): [True: 0, False: 45.9k] ------------------ 1535| 0| fact = (10.0 - maxd) / 5.0; 1536| 45.9k| } 1537| | 1538| 45.9k| std::vector w_gl; 1539| 8.88M| for (int i = 0; i < MAX_GUESS; i++) { ------------------ | | 76| 8.88M|#define MAX_GUESS 200 ------------------ | Branch (1539:19): [True: 8.84M, False: 44.2k] ------------------ 1540| 8.84M| if (guess[i]) { ------------------ | Branch (1540:9): [True: 69.2k, False: 8.77M] ------------------ 1541| | // lowering guess[i] 1542| 69.2k| std::string gl; 1543| 69.2k| int len; 1544| 69.2k| if (utf8) { ------------------ | Branch (1544:11): [True: 21.4k, False: 47.7k] ------------------ 1545| 21.4k| len = u8_u16(w_gl, guess[i]); 1546| 21.4k| mkallsmall_utf(w_gl, langnum); 1547| 21.4k| u16_u8(gl, w_gl); 1548| 47.7k| } else { 1549| 47.7k| gl.assign(guess[i]); 1550| 47.7k| if (!nonbmp) ------------------ | Branch (1550:13): [True: 47.6k, False: 78] ------------------ 1551| 47.6k| mkallsmall(gl, csconv); 1552| 47.7k| len = strlen(guess[i]); 1553| 47.7k| } 1554| | 1555| 69.2k| int _lcs = lcslen(word, gl.c_str()); 1556| | 1557| | // same characters with different casing 1558| 69.2k| if ((n == len) && (n == _lcs)) { ------------------ | Branch (1558:11): [True: 17.2k, False: 51.9k] | Branch (1558:25): [True: 1.78k, False: 15.4k] ------------------ 1559| 1.78k| gscore[i] += 2000; 1560| 1.78k| break; 1561| 1.78k| } 1562| | // using 2-gram instead of 3, and other weightening 1563| | 1564| 67.4k| if (utf8) { ------------------ | Branch (1564:11): [True: 20.0k, False: 47.3k] ------------------ 1565| 20.0k| u8_u16(w_gl, gl); 1566| | //w_gl is lowercase already at this point 1567| 20.0k| re = ngram(2, w_word, w_gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 20.0k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re = ngram(2, w_word, w_gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 20.0k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1568| 20.0k| if (low) { ------------------ | Branch (1568:13): [True: 20.0k, False: 0] ------------------ 1569| 20.0k| w_f = w_word; 1570| | // lowering dictionary word 1571| 20.0k| mkallsmall_utf(w_f, langnum); 1572| 20.0k| re += ngram(2, w_gl, w_f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 20.0k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re += ngram(2, w_gl, w_f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 20.0k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1573| 20.0k| } 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| 47.3k| } else { 1577| | //gl is lowercase already at this point 1578| 47.3k| re = ngram(2, word, gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 47.3k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re = ngram(2, word, gl, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 47.3k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1579| 47.3k| if (low) { ------------------ | Branch (1579:13): [True: 47.2k, False: 78] ------------------ 1580| 47.2k| f = word; 1581| | // lowering dictionary word 1582| 47.2k| mkallsmall(f, csconv); 1583| 47.2k| re += ngram(2, gl, f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 47.2k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re += ngram(2, gl, f, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 47.2k|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1584| 47.2k| } else { 1585| 78| re += ngram(2, gl, word, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 82| 78|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ re += ngram(2, gl, word, NGRAM_ANY_MISMATCH | NGRAM_WEIGHTED); ------------------ | | 84| 78|#define NGRAM_WEIGHTED (1 << 3) ------------------ 1586| 78| } 1587| 47.3k| } 1588| | 1589| 67.4k| int ngram_score, leftcommon_score; 1590| 67.4k| if (utf8) { ------------------ | Branch (1590:11): [True: 20.0k, False: 47.3k] ------------------ 1591| | //w_gl is lowercase already at this point 1592| 20.0k| ngram_score = ngram(4, w_word, w_gl, NGRAM_ANY_MISMATCH); ------------------ | | 82| 20.0k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1593| 20.0k| leftcommon_score = leftcommonsubstring(w_word, w_gl); 1594| 47.3k| } else { 1595| | //gl is lowercase already at this point 1596| 47.3k| ngram_score = ngram(4, word, gl, NGRAM_ANY_MISMATCH); ------------------ | | 82| 47.3k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ 1597| 47.3k| leftcommon_score = leftcommonsubstring(word, gl.c_str()); 1598| 47.3k| } 1599| 67.4k| gscore[i] = 1600| | // length of longest common subsequent minus length difference 1601| 67.4k| 2 * _lcs - abs((int)(n - len)) + 1602| | // weight length of the left common substring 1603| 67.4k| leftcommon_score + 1604| | // weight equal character positions 1605| 67.4k| (!nonbmp && commoncharacterpositions(word, gl.c_str(), &is_swap) ------------------ | Branch (1605:12): [True: 67.3k, False: 78] | Branch (1605:23): [True: 55.9k, False: 11.3k] ------------------ 1606| 67.4k| ? 1 1607| 67.4k| : 0) + 1608| | // swap character (not neighboring) 1609| 67.4k| ((is_swap) ? 10 : 0) + ------------------ | Branch (1609:12): [True: 134, False: 67.3k] ------------------ 1610| | // ngram 1611| 67.4k| ngram_score + 1612| | // weighted ngrams 1613| 67.4k| re + 1614| | // different limit for dictionaries with PHONE rules 1615| 67.4k| (ph ? (re < len * fact ? -1000 : 0) ------------------ | Branch (1615:12): [True: 4.51k, False: 62.9k] | Branch (1615:18): [True: 3.34k, False: 1.16k] ------------------ 1616| 67.4k| : (re < (n + len) * fact ? -1000 : 0)); ------------------ | Branch (1616:18): [True: 57.7k, False: 5.20k] ------------------ 1617| 67.4k| } 1618| 8.84M| } 1619| | 1620| 45.9k| bubblesort(&guess[0], &guessorig[0], &gscore[0], MAX_GUESS); ------------------ | | 76| 45.9k|#define MAX_GUESS 200 ------------------ 1621| | 1622| | // phonetic version 1623| 45.9k| if (ph) ------------------ | Branch (1623:7): [True: 2.73k, False: 43.2k] ------------------ 1624| 275k| for (int i = 0; i < MAX_ROOTS; i++) { ------------------ | | 74| 275k|#define MAX_ROOTS 100 ------------------ | Branch (1624:21): [True: 273k, False: 2.73k] ------------------ 1625| 273k| if (rootsphon[i]) { ------------------ | Branch (1625:11): [True: 5.84k, False: 267k] ------------------ 1626| | // lowering rootphon[i] 1627| 5.84k| std::string gl; 1628| 5.84k| int len; 1629| 5.84k| if (utf8) { ------------------ | Branch (1629:13): [True: 0, False: 5.84k] ------------------ 1630| 0| len = u8_u16(w_gl, rootsphon[i]); 1631| 0| mkallsmall_utf(w_gl, langnum); 1632| 0| u16_u8(gl, w_gl); 1633| 5.84k| } else { 1634| 5.84k| gl.assign(rootsphon[i]); 1635| 5.84k| if (!nonbmp) ------------------ | Branch (1635:15): [True: 5.84k, False: 0] ------------------ 1636| 5.84k| mkallsmall(gl, csconv); 1637| 5.84k| len = strlen(rootsphon[i]); 1638| 5.84k| } 1639| | 1640| | // weight length of the left common substring 1641| 5.84k| int leftcommon_score; 1642| 5.84k| if (utf8) ------------------ | Branch (1642:13): [True: 0, False: 5.84k] ------------------ 1643| 0| leftcommon_score = leftcommonsubstring(w_word, w_gl); 1644| 5.84k| else 1645| 5.84k| leftcommon_score = leftcommonsubstring(word, gl.c_str()); 1646| | // heuristic weigthing of ngram scores 1647| 5.84k| scoresphon[i] += 2 * lcslen(word, gl) - abs((int)(n - len)) + 1648| 5.84k| leftcommon_score; 1649| 5.84k| } 1650| 273k| } 1651| | 1652| 45.9k| if (ph) ------------------ | Branch (1652:7): [True: 2.73k, False: 43.2k] ------------------ 1653| 2.73k| bubblesort(&rootsphon[0], nullptr, &scoresphon[0], MAX_ROOTS); ------------------ | | 74| 2.73k|#define MAX_ROOTS 100 ------------------ 1654| | 1655| | // copy over 1656| 45.9k| size_t oldns = wlst.size(); 1657| | 1658| 45.9k| int same = 0; 1659| 9.24M| for (int i = 0; i < MAX_GUESS; i++) { ------------------ | | 76| 9.24M|#define MAX_GUESS 200 ------------------ | Branch (1659:19): [True: 9.19M, False: 45.9k] ------------------ 1660| 9.19M| if (guess[i]) { ------------------ | Branch (1660:9): [True: 88.1k, False: 9.11M] ------------------ 1661| 88.1k| if ((wlst.size() < oldns + maxngramsugs) && (wlst.size() < maxSug) && ------------------ | Branch (1661:11): [True: 82.6k, False: 5.50k] | Branch (1661:51): [True: 82.6k, False: 0] ------------------ 1662| 82.6k| (!same || (gscore[i] > 1000))) { ------------------ | Branch (1662:12): [True: 14.8k, False: 67.8k] | Branch (1662:21): [True: 0, False: 67.8k] ------------------ 1663| 14.8k| int unique = 1; 1664| | // leave only excellent suggestions, if exists 1665| 14.8k| if (gscore[i] > 1000) ------------------ | Branch (1665:13): [True: 1.78k, False: 13.0k] ------------------ 1666| 1.78k| same = 1; 1667| 13.0k| else if (gscore[i] < -100) { ------------------ | Branch (1667:18): [True: 8.50k, False: 4.50k] ------------------ 1668| 8.50k| same = 1; 1669| | // keep the best ngram suggestions, unless in ONLYMAXDIFF mode 1670| 8.50k| if (wlst.size() > oldns || (pAMgr && pAMgr->get_onlymaxdiff())) { ------------------ | Branch (1670:15): [True: 828, False: 7.67k] | Branch (1670:39): [True: 7.67k, False: 0] | Branch (1670:48): [True: 0, False: 7.67k] ------------------ 1671| 828| delete[] guess[i]; 1672| 828| delete[] guessorig[i]; 1673| 828| continue; 1674| 828| } 1675| 8.50k| } 1676| 13.9k| for (auto& j : wlst) { ------------------ | Branch (1676:22): [True: 8.97k, False: 12.1k] ------------------ 1677| | // don't suggest previous suggestions or a previous suggestion with 1678| | // prefixes or affixes 1679| 8.97k| if ((!guessorig[i] && strstr(guess[i], j.c_str())) || (guessorig[i] && strstr(guessorig[i], j.c_str())) || ------------------ | Branch (1679:15): [True: 1.86k, False: 7.10k] | Branch (1679:16): [True: 8.97k, False: 0] | Branch (1679:33): [True: 1.86k, False: 7.10k] | Branch (1679:66): [True: 0, False: 7.10k] | Branch (1679:82): [True: 0, False: 0] ------------------ 1680| | // check forbidden words 1681| 7.10k| !checkword(guess[i], 0, nullptr, nullptr)) { ------------------ | Branch (1681:15): [True: 0, False: 7.10k] ------------------ 1682| 1.86k| unique = 0; 1683| 1.86k| break; 1684| 1.86k| } 1685| 8.97k| } 1686| 13.9k| if (unique) { ------------------ | Branch (1686:13): [True: 12.1k, False: 1.86k] ------------------ 1687| 12.1k| if (guessorig[i]) { ------------------ | Branch (1687:15): [True: 0, False: 12.1k] ------------------ 1688| 0| wlst.emplace_back(guessorig[i]); 1689| 12.1k| } else { 1690| 12.1k| wlst.emplace_back(guess[i]); 1691| 12.1k| } 1692| 12.1k| } 1693| 13.9k| delete[] guess[i]; 1694| 13.9k| delete[] guessorig[i]; 1695| 73.3k| } else { 1696| 73.3k| delete[] guess[i]; 1697| 73.3k| delete[] guessorig[i]; 1698| 73.3k| } 1699| 88.1k| } 1700| 9.19M| } 1701| | 1702| 45.9k| oldns = wlst.size(); 1703| 45.9k| if (ph) ------------------ | Branch (1703:7): [True: 2.73k, False: 43.2k] ------------------ 1704| 273k| for (auto& i : rootsphon) { ------------------ | Branch (1704:18): [True: 273k, False: 2.73k] ------------------ 1705| 273k| if (i) { ------------------ | Branch (1705:11): [True: 5.84k, False: 267k] ------------------ 1706| 5.84k| if ((wlst.size() < oldns + MAXPHONSUGS) && (wlst.size() < maxSug)) { ------------------ | | 78| 5.84k|#define MAXPHONSUGS 2 ------------------ | Branch (1706:13): [True: 2.79k, False: 3.05k] | Branch (1706:52): [True: 2.79k, False: 0] ------------------ 1707| 2.79k| int unique = 1; 1708| 5.16k| for (auto& j : wlst) { ------------------ | Branch (1708:24): [True: 5.16k, False: 862] ------------------ 1709| | // don't suggest previous suggestions or a previous suggestion with 1710| | // prefixes or affixes 1711| 5.16k| if (strstr(i, j.c_str()) || ------------------ | Branch (1711:17): [True: 1.92k, False: 3.24k] | Branch (1711:17): [True: 1.92k, False: 3.24k] ------------------ 1712| | // check forbidden words 1713| 3.24k| !checkword(i, 0, nullptr, nullptr)) { ------------------ | Branch (1713:17): [True: 0, False: 3.24k] ------------------ 1714| 1.92k| unique = 0; 1715| 1.92k| break; 1716| 1.92k| } 1717| 5.16k| } 1718| 2.79k| if (unique) { ------------------ | Branch (1718:15): [True: 862, False: 1.92k] ------------------ 1719| 862| wlst.emplace_back(i); 1720| 862| } 1721| 2.79k| } 1722| 5.84k| } 1723| 273k| } 1724| 45.9k|} _ZN10SuggestMgr9checkwordERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEiPiPNS0_6chrono10time_pointINSA_12steady_clockENSA_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 1735| 85.3M| std::chrono::steady_clock::time_point* timelimit) { 1736| | // check overall suggestion time limit 1737| 85.3M| if (std::chrono::steady_clock::now() - suggest_start > TIMELIMIT_SUGGESTION_MS) ------------------ | | 105| 85.3M|#define TIMELIMIT_SUGGESTION_MS std::chrono::milliseconds(100) ------------------ | Branch (1737:7): [True: 1, False: 85.3M] ------------------ 1738| 1| return 0; 1739| | 1740| | // check time limit 1741| 85.3M| if (timer) { ------------------ | Branch (1741:7): [True: 2.18M, False: 83.1M] ------------------ 1742| 2.18M| (*timer)--; 1743| 2.18M| if (!(*timer) && timelimit) { ------------------ | Branch (1743:9): [True: 17.4k, False: 2.17M] | Branch (1743:22): [True: 17.4k, False: 0] ------------------ 1744| 17.4k| if (std::chrono::steady_clock::now() - *timelimit > TIMELIMIT_MS) ------------------ | | 106| 17.4k|#define TIMELIMIT_MS std::chrono::milliseconds(50) ------------------ | Branch (1744:11): [True: 4, False: 17.4k] ------------------ 1745| 4| return 0; 1746| 17.4k| *timer = MAXPLUSTIMER; ------------------ | | 108| 17.4k|#define MAXPLUSTIMER 100 ------------------ 1747| 17.4k| } 1748| 2.18M| } 1749| | 1750| 85.3M| if (pAMgr) { ------------------ | Branch (1750:7): [True: 85.3M, False: 0] ------------------ 1751| 85.3M| struct hentry* rv = nullptr; 1752| 85.3M| int nosuffix = 0; 1753| | 1754| 85.3M| if (cpdsuggest >= 1) { ------------------ | Branch (1754:9): [True: 55.8M, False: 29.4M] ------------------ 1755| 55.8M| if (pAMgr->get_compound()) { ------------------ | Branch (1755:11): [True: 13.9M, False: 41.9M] ------------------ 1756| 13.9M| struct hentry* rv2 = nullptr; 1757| 13.9M| struct hentry* rwords[100] = {}; // buffer for COMPOUND pattern checking 1758| 13.9M| int info = (cpdsuggest == 1) ? SPELL_COMPOUND_2 : 0; ------------------ | | 85| 6.95M|#define SPELL_COMPOUND_2 (1 << 7) // permit only 2 dictionary words in the compound ------------------ | Branch (1758:20): [True: 6.95M, False: 6.95M] ------------------ 1759| 13.9M| AffixScratch scratch; 1760| 13.9M| 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| 13.9M| if (rv && ------------------ | Branch (1763:13): [True: 0, False: 13.9M] | Branch (1763:13): [True: 0, False: 13.9M] ------------------ 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| 13.9M| } 1770| 55.8M| return 0; 1771| 55.8M| } 1772| | 1773| 29.4M| rv = pAMgr->lookup(word.c_str(), word.size()); 1774| | 1775| 29.4M| if (rv) { ------------------ | Branch (1775:9): [True: 49.0k, False: 29.4M] ------------------ 1776| 49.0k| if ((rv->astr) && ------------------ | Branch (1776:11): [True: 258, False: 48.8k] | Branch (1776:11): [True: 0, False: 49.0k] ------------------ 1777| 258| (TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen) || ------------------ | | 99| 516|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 258] | | ------------------ ------------------ 1778| 258| TESTAFF(rv->astr, pAMgr->get_nosuggest(), rv->alen) || ------------------ | | 99| 516|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 258] | | ------------------ ------------------ 1779| 258| TESTAFF(rv->astr, pAMgr->get_substandard(), rv->alen))) ------------------ | | 99| 258|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 258] | | ------------------ ------------------ 1780| 0| return 0; 1781| 49.3k| while (rv) { ------------------ | Branch (1781:14): [True: 49.0k, False: 249] ------------------ 1782| 49.0k| if (rv->astr && ------------------ | Branch (1782:13): [True: 258, False: 48.8k] | Branch (1782:13): [True: 249, False: 48.8k] ------------------ 1783| 258| (TESTAFF(rv->astr, pAMgr->get_needaffix(), rv->alen) || ------------------ | | 99| 516|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 258] | | ------------------ ------------------ 1784| 258| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 516|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 249, False: 9] | | ------------------ ------------------ 1785| 249| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) { ------------------ | | 99| 9|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 9] | | ------------------ ------------------ 1786| 249| rv = rv->next_homonym; 1787| 249| } else 1788| 48.8k| break; 1789| 49.0k| } 1790| 29.4M| } else { 1791| 29.4M| AffixScratch scratch; 1792| 29.4M| rv = pAMgr->prefix_check(word, 0, word.size(), 1793| 29.4M| 0, scratch); // only prefix, and prefix + suffix XXX 1794| 29.4M| } 1795| | 1796| 29.4M| if (rv) { ------------------ | Branch (1796:9): [True: 48.8k, False: 29.4M] ------------------ 1797| 48.8k| nosuffix = 1; 1798| 29.4M| } else { 1799| 29.4M| AffixScratch scratch; 1800| 29.4M| rv = pAMgr->suffix_check(word, 0, word.size(), 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // only suffix ------------------ | | 96| 29.4M|#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| 29.4M|#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| 29.4M|#define IN_CPD_NOT 0 ------------------ 1801| 29.4M| } 1802| | 1803| 29.4M| if (!rv && pAMgr->have_contclass()) { ------------------ | Branch (1803:9): [True: 29.4M, False: 48.8k] | Branch (1803:16): [True: 10.4M, False: 18.9M] ------------------ 1804| 10.4M| AffixScratch scratch; 1805| 10.4M| rv = pAMgr->suffix_check_twosfx(word, 0, word.size(), 0, nullptr, scratch, FLAG_NULL); ------------------ | | 96| 10.4M|#define FLAG_NULL 0x00 ------------------ 1806| 10.4M| if (!rv) ------------------ | Branch (1806:11): [True: 10.4M, False: 0] ------------------ 1807| 10.4M| rv = pAMgr->prefix_check_twosfx(word, 0, word.size(), 0, scratch, FLAG_NULL); ------------------ | | 96| 10.4M|#define FLAG_NULL 0x00 ------------------ 1808| 10.4M| } 1809| | 1810| | // check forbidden words 1811| 29.4M| if ((rv) && (rv->astr) && ------------------ | Branch (1811:9): [True: 48.8k, False: 29.4M] | Branch (1811:9): [True: 0, False: 29.4M] | Branch (1811:17): [True: 9, False: 48.8k] ------------------ 1812| 9| (TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen) || ------------------ | | 99| 18|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 9] | | ------------------ ------------------ 1813| 9| TESTAFF(rv->astr, ONLYUPCASEFLAG, rv->alen) || ------------------ | | 99| 18|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 9] | | ------------------ ------------------ 1814| 9| TESTAFF(rv->astr, pAMgr->get_nosuggest(), rv->alen) || ------------------ | | 99| 18|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 9] | | ------------------ ------------------ 1815| 9| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) ------------------ | | 99| 9|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 9] | | ------------------ ------------------ 1816| 0| return 0; 1817| | 1818| 29.4M| if (rv) { // XXX obsolote ------------------ | Branch (1818:9): [True: 48.8k, False: 29.4M] ------------------ 1819| 48.8k| if ((pAMgr->get_compoundflag()) && ------------------ | Branch (1819:11): [True: 12.0k, False: 36.8k] | Branch (1819:11): [True: 6, False: 48.8k] ------------------ 1820| 12.0k| TESTAFF(rv->astr, pAMgr->get_compoundflag(), rv->alen)) ------------------ | | 99| 12.0k|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 6, False: 12.0k] | | ------------------ ------------------ 1821| 6| return 2 + nosuffix; 1822| 48.8k| return 1; 1823| 48.8k| } 1824| 29.4M| } 1825| 29.4M| return 0; 1826| 85.3M|} _ZN10SuggestMgr15check_forbiddenERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1828| 13.8k|int SuggestMgr::check_forbidden(const std::string& word) { 1829| 13.8k| if (pAMgr) { ------------------ | Branch (1829:7): [True: 13.8k, False: 0] ------------------ 1830| 13.8k| struct hentry* rv = pAMgr->lookup(word.c_str(), word.size()); 1831| 13.8k| if (rv && rv->astr && ------------------ | Branch (1831:9): [True: 0, False: 13.8k] | Branch (1831:9): [True: 0, False: 13.8k] | Branch (1831:15): [True: 0, False: 0] ------------------ 1832| 0| (TESTAFF(rv->astr, pAMgr->get_needaffix(), rv->alen) || ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1833| 0| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) ------------------ | | 99| 0|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 0] | | ------------------ ------------------ 1834| 0| rv = nullptr; 1835| 13.8k| size_t len = word.size(); 1836| 13.8k| AffixScratch scratch; 1837| 13.8k| if (!(pAMgr->prefix_check(word, 0, len, 1, scratch))) ------------------ | Branch (1837:9): [True: 13.8k, False: 0] ------------------ 1838| 13.8k| rv = pAMgr->suffix_check(word, 0, len, 0, nullptr, scratch, FLAG_NULL, FLAG_NULL, IN_CPD_NOT); // prefix+suffix, suffix ------------------ | | 96| 13.8k|#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| 13.8k|#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| 13.8k|#define IN_CPD_NOT 0 ------------------ 1839| | // check forbidden words 1840| 13.8k| if ((rv) && (rv->astr) && ------------------ | Branch (1840:9): [True: 0, False: 13.8k] | Branch (1840:9): [True: 0, False: 13.8k] | 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| 13.8k| } 1844| 13.8k| return 0; 1845| 13.8k|} _ZN10SuggestMgr13suggest_morphERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE: 1847| 10.7k|std::string SuggestMgr::suggest_morph(const std::string& in_w) { 1848| 10.7k| std::string result; 1849| | 1850| 10.7k| struct hentry* rv = nullptr; 1851| | 1852| 10.7k| if (!pAMgr) ------------------ | Branch (1852:7): [True: 0, False: 10.7k] ------------------ 1853| 0| return {}; 1854| | 1855| 10.7k| std::string w(in_w); 1856| | 1857| | // word reversing wrapper for complex prefixes 1858| 10.7k| if (complexprefixes) { ------------------ | Branch (1858:7): [True: 551, False: 10.2k] ------------------ 1859| 551| if (utf8) ------------------ | Branch (1859:9): [True: 0, False: 551] ------------------ 1860| 0| reverseword_utf(w); 1861| 551| else 1862| 551| reverseword(w); 1863| 551| } 1864| | 1865| 10.7k| rv = pAMgr->lookup(w.c_str(), w.size()); 1866| | 1867| 12.9k| while (rv) { ------------------ | Branch (1867:10): [True: 2.12k, False: 10.7k] ------------------ 1868| 2.12k| if ((!rv->astr) || ------------------ | Branch (1868:9): [True: 2.11k, False: 9] | Branch (1868:9): [True: 2.12k, False: 0] ------------------ 1869| 9| !(TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen) || ------------------ | | 99| 18|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 9] | | ------------------ ------------------ 1870| 9| TESTAFF(rv->astr, pAMgr->get_needaffix(), rv->alen) || ------------------ | | 99| 18|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 9] | | ------------------ ------------------ 1871| 2.12k| TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) { ------------------ | | 99| 9|#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b)) | | ------------------ | | | Branch (99:26): [True: 0, False: 9] | | ------------------ ------------------ 1872| 2.12k| if (!HENTRY_FIND(rv, MORPH_STEM)) { ------------------ | | 103| 2.12k|#define MORPH_STEM "st:" ------------------ | Branch (1872:11): [True: 2.12k, False: 0] ------------------ 1873| 2.12k| result.push_back(MSEP_FLD); ------------------ | | 121| 2.12k|#define MSEP_FLD ' ' ------------------ 1874| 2.12k| result.append(MORPH_STEM); ------------------ | | 103| 2.12k|#define MORPH_STEM "st:" ------------------ 1875| 2.12k| result.append(w); 1876| 2.12k| } 1877| 2.12k| if (HENTRY_DATA(rv)) { ------------------ | Branch (1877:11): [True: 0, False: 2.12k] ------------------ 1878| 0| result.push_back(MSEP_FLD); ------------------ | | 121| 0|#define MSEP_FLD ' ' ------------------ 1879| 0| result.append(HENTRY_DATA2(rv)); 1880| 0| } 1881| 2.12k| result.push_back(MSEP_REC); ------------------ | | 122| 2.12k|#define MSEP_REC '\n' ------------------ 1882| 2.12k| } 1883| 2.12k| rv = rv->next_homonym; 1884| 2.12k| } 1885| | 1886| 10.7k| AffixScratch scratch; 1887| 10.7k| std::string st = pAMgr->affix_check_morph(w, 0, w.size(), scratch); 1888| 10.7k| if (!st.empty()) { ------------------ | Branch (1888:7): [True: 0, False: 10.7k] ------------------ 1889| 0| result.append(st); 1890| 0| } 1891| | 1892| 10.7k| if (pAMgr->get_compound() && result.empty()) { ------------------ | Branch (1892:7): [True: 2.24k, False: 8.54k] | Branch (1892:32): [True: 1.75k, False: 487] ------------------ 1893| 1.75k| struct hentry* rwords[100] = {}; // buffer for COMPOUND pattern checking 1894| 1.75k| pAMgr->compound_check_morph(w, 0, 0, 100, 0, nullptr, (hentry**)&rwords, 0, result, nullptr, scratch); 1895| 1.75k| } 1896| | 1897| 10.7k| line_uniq(result, MSEP_REC); ------------------ | | 122| 10.7k|#define MSEP_REC '\n' ------------------ 1898| | 1899| 10.7k| return result; 1900| 10.7k|} _ZN10SuggestMgr18suggest_hentry_genEP6hentryPKc: 1925| 455k|std::string SuggestMgr::suggest_hentry_gen(hentry* rv, const char* pattern) { 1926| 455k| std::string result; 1927| 455k| int sfxcount = get_sfxcount(pattern); 1928| | 1929| 455k| if (get_sfxcount(HENTRY_DATA(rv)) > sfxcount) ------------------ | Branch (1929:7): [True: 0, False: 455k] ------------------ 1930| 0| return result; 1931| | 1932| 455k| if (HENTRY_DATA(rv)) { ------------------ | Branch (1932:7): [True: 0, False: 455k] ------------------ 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| 455k| char* p = nullptr; 1943| 455k| if (HENTRY_DATA(rv)) ------------------ | Branch (1943:7): [True: 0, False: 455k] ------------------ 1944| 0| p = (char*)strstr(HENTRY_DATA2(rv), MORPH_ALLOMORPH); ------------------ | | 104| 0|#define MORPH_ALLOMORPH "al:" ------------------ 1945| 455k| while (p) { ------------------ | Branch (1945:10): [True: 0, False: 455k] ------------------ 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| 455k| return result; 1971| 455k|} _ZN10SuggestMgr11suggest_genERKNSt3__16vectorINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEENS5_IS7_EEEERKS7_NS0_6chrono10time_pointINSE_12steady_clockENSE_8durationIxNS0_5ratioILl1ELl1000000000EEEEEEE: 1974| 351k| std::chrono::steady_clock::time_point start_time) { 1975| 351k| if (desc.empty() || !pAMgr) ------------------ | Branch (1975:7): [True: 186k, False: 165k] | Branch (1975:23): [True: 0, False: 165k] ------------------ 1976| 186k| return {}; 1977| | 1978| 165k| const char* pattern = in_pattern.c_str(); 1979| 165k| std::string result2; 1980| 165k| std::string newpattern; 1981| 165k| struct hentry* rv = nullptr; 1982| | 1983| | // search affixed forms with and without derivational suffixes 1984| 230k| while (true) { ------------------ | Branch (1984:10): [True: 230k, Folded] ------------------ 1985| 230k| for (const auto& k : desc) { ------------------ | Branch (1985:24): [True: 230k, False: 230k] ------------------ 1986| 230k| if (std::chrono::steady_clock::now() - start_time > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 230k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (1986:11): [True: 0, False: 230k] ------------------ 1987| 0| return result2; 1988| 230k| std::string result; 1989| | 1990| | // add compound word parts (except the last one) 1991| 230k| const size_t lastpart = append_compound_parts(k, result); 1992| 230k| const char* s = k.c_str() + lastpart; 1993| 230k| std::string tok(k, lastpart); 1994| 230k| size_t pos = tok.find(" | "); 1995| 230k| while (pos != std::string::npos) { ------------------ | Branch (1995:14): [True: 0, False: 230k] ------------------ 1996| 0| tok[pos + 1] = MSEP_ALT; ------------------ | | 123| 0|#define MSEP_ALT '\v' ------------------ 1997| 0| pos = tok.find(" | ", pos); 1998| 0| } 1999| 230k| std::vector pl = line_tok(tok, MSEP_ALT); ------------------ | | 123| 230k|#define MSEP_ALT '\v' ------------------ 2000| 243k| for (auto& i : pl) { ------------------ | Branch (2000:20): [True: 243k, False: 230k] ------------------ 2001| | // remove inflectional and terminal suffixes 2002| 243k| size_t is = i.find(MORPH_INFL_SFX); ------------------ | | 110| 243k|#define MORPH_INFL_SFX "is:" ------------------ 2003| 243k| if (is != std::string::npos) ------------------ | Branch (2003:13): [True: 0, False: 243k] ------------------ 2004| 0| i.resize(is); 2005| 243k| size_t ts = i.find(MORPH_TERM_SFX); ------------------ | | 111| 243k|#define MORPH_TERM_SFX "ts:" ------------------ 2006| 243k| while (ts != std::string::npos) { ------------------ | Branch (2006:16): [True: 0, False: 243k] ------------------ 2007| 0| i[ts] = '_'; 2008| 0| ts = i.find(MORPH_TERM_SFX); ------------------ | | 111| 0|#define MORPH_TERM_SFX "ts:" ------------------ 2009| 0| } 2010| 243k| const char* st = strstr(s, MORPH_STEM); ------------------ | | 103| 243k|#define MORPH_STEM "st:" ------------------ 2011| 243k| if (st) { ------------------ | Branch (2011:13): [True: 227k, False: 15.9k] ------------------ 2012| 227k| copy_field(tok, st, MORPH_STEM); ------------------ | | 103| 227k|#define MORPH_STEM "st:" ------------------ 2013| 227k| rv = pAMgr->lookup(tok.c_str(), tok.size()); 2014| 455k| while (rv) { ------------------ | Branch (2014:18): [True: 227k, False: 227k] ------------------ 2015| 227k| if (std::chrono::steady_clock::now() - start_time > TIMELIMIT_GLOBAL_MS) ------------------ | | 104| 227k|#define TIMELIMIT_GLOBAL_MS std::chrono::milliseconds(250) ------------------ | Branch (2015:17): [True: 0, False: 227k] ------------------ 2016| 0| return result2; 2017| 227k| std::string newpat(i); 2018| 227k| newpat.append(pattern); 2019| 227k| std::string sg = suggest_hentry_gen(rv, newpat.c_str()); 2020| 227k| if (sg.empty()) ------------------ | Branch (2020:17): [True: 227k, False: 0] ------------------ 2021| 227k| sg = suggest_hentry_gen(rv, pattern); 2022| 227k| if (!sg.empty()) { ------------------ | Branch (2022:17): [True: 0, False: 227k] ------------------ 2023| 0| std::vector gen = line_tok(sg, MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2024| 0| for (auto& j : gen) { ------------------ | Branch (2024:28): [True: 0, False: 0] ------------------ 2025| 0| result2.push_back(MSEP_REC); ------------------ | | 122| 0|#define MSEP_REC '\n' ------------------ 2026| 0| result2.append(result); 2027| 0| if (i.find(MORPH_SURF_PFX) != std::string::npos) { ------------------ | | 112| 0|#define MORPH_SURF_PFX "sp:" ------------------ | Branch (2027:21): [True: 0, False: 0] ------------------ 2028| 0| std::string field; 2029| 0| copy_field(field, i, MORPH_SURF_PFX); ------------------ | | 112| 0|#define MORPH_SURF_PFX "sp:" ------------------ 2030| 0| result2.append(field); 2031| 0| } 2032| 0| result2.append(j); 2033| 0| } 2034| 0| } 2035| 227k| rv = rv->next_homonym; 2036| 227k| } 2037| 227k| } 2038| 243k| } 2039| 230k| } 2040| | 2041| 230k| if (!result2.empty() || !strstr(pattern, MORPH_DERI_SFX)) ------------------ | | 109| 230k|#define MORPH_DERI_SFX "ds:" ------------------ | Branch (2041:9): [True: 0, False: 230k] | Branch (2041:29): [True: 165k, False: 64.8k] ------------------ 2042| 165k| break; 2043| | 2044| 64.8k| newpattern.assign(pattern); 2045| 64.8k| mystrrep(newpattern, MORPH_DERI_SFX, MORPH_TERM_SFX); ------------------ | | 109| 64.8k|#define MORPH_DERI_SFX "ds:" ------------------ mystrrep(newpattern, MORPH_DERI_SFX, MORPH_TERM_SFX); ------------------ | | 111| 64.8k|#define MORPH_TERM_SFX "ts:" ------------------ 2046| 64.8k| pattern = newpattern.c_str(); 2047| 64.8k| } 2048| 165k| return result2; 2049| 165k|} _ZN10SuggestMgr5ngramEiRKNSt3__16vectorI6w_charNS0_9allocatorIS2_EEEES7_i: 2055| 587k| int opt) { 2056| 587k| int nscore = 0, ns, l1 = su1.size(), l2 = su2.size(); 2057| | 2058| 587k| if (l2 == 0) ------------------ | Branch (2058:7): [True: 5.45k, False: 581k] ------------------ 2059| 5.45k| return 0; 2060| 886k| for (int j = 1; j <= n; j++) { ------------------ | Branch (2060:19): [True: 837k, False: 48.3k] ------------------ 2061| 837k| ns = 0; 2062| 3.98M| for (int i = 0; i <= (l1 - j); i++) { ------------------ | Branch (2062:21): [True: 3.14M, False: 837k] ------------------ 2063| 3.14M| int k = 0; 2064| 14.9M| for (int l = 0; l <= (l2 - j); l++) { ------------------ | Branch (2064:23): [True: 12.8M, False: 2.04M] ------------------ 2065| 22.2M| for (k = 0; k < j; k++) { ------------------ | Branch (2065:21): [True: 21.1M, False: 1.09M] ------------------ 2066| 21.1M| if (su1[i + k] != su2[l + k]) ------------------ | Branch (2066:15): [True: 11.7M, False: 9.35M] ------------------ 2067| 11.7M| break; 2068| 21.1M| } 2069| 12.8M| if (k == j) { ------------------ | Branch (2069:13): [True: 1.09M, False: 11.7M] ------------------ 2070| 1.09M| ns++; 2071| 1.09M| break; 2072| 1.09M| } 2073| 12.8M| } 2074| 3.14M| if (k != j && opt & NGRAM_WEIGHTED) { ------------------ | | 84| 2.04M|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2074:11): [True: 2.04M, False: 1.09M] | Branch (2074:21): [True: 87.5k, False: 1.95M] ------------------ 2075| 87.5k| ns--; 2076| 87.5k| if (i == 0 || i == l1 - j) ------------------ | Branch (2076:13): [True: 21.9k, False: 65.6k] | Branch (2076:23): [True: 31.9k, False: 33.6k] ------------------ 2077| 53.8k| ns--; // side weight 2078| 87.5k| } 2079| 3.14M| } 2080| 837k| nscore = nscore + ns; 2081| 837k| if (ns < 2 && !(opt & NGRAM_WEIGHTED)) ------------------ | | 84| 592k|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2081:9): [True: 592k, False: 245k] | Branch (2081:19): [True: 533k, False: 58.5k] ------------------ 2082| 533k| break; 2083| 837k| } 2084| | 2085| 581k| ns = 0; 2086| 581k| if (opt & NGRAM_LONGER_WORSE) ------------------ | | 81| 581k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ | Branch (2086:7): [True: 235k, False: 346k] ------------------ 2087| 235k| ns = (l2 - l1) - 2; 2088| 581k| if (opt & NGRAM_ANY_MISMATCH) ------------------ | | 82| 581k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ | Branch (2088:7): [True: 346k, False: 235k] ------------------ 2089| 346k| ns = abs(l2 - l1) - 2; 2090| 581k| ns = (nscore - ((ns > 0) ? ns : 0)); ------------------ | Branch (2090:19): [True: 95.2k, False: 486k] ------------------ 2091| 581k| return ns; 2092| 587k|} _ZN10SuggestMgr5ngramEiRKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_i: 2098| 818k| int opt) { 2099| 818k| int nscore = 0, ns, l1, l2 = s2.size(); 2100| | 2101| 818k| if (l2 == 0) ------------------ | Branch (2101:7): [True: 10.5k, False: 807k] ------------------ 2102| 10.5k| return 0; 2103| 807k| l1 = s1.size(); 2104| 1.51M| for (int j = 1; j <= n; j++) { ------------------ | Branch (2104:19): [True: 1.38M, False: 126k] ------------------ 2105| 1.38M| ns = 0; 2106| 10.5M| for (int i = 0; i <= (l1 - j); i++) { ------------------ | Branch (2106:21): [True: 9.16M, False: 1.38M] ------------------ 2107| | //s2 is haystack, s1[i..i+j) is needle 2108| 9.16M| if (s2.find(s1.c_str()+i, 0, j) != std::string::npos) { ------------------ | Branch (2108:11): [True: 3.52M, False: 5.63M] ------------------ 2109| 3.52M| ns++; 2110| 5.63M| } else if (opt & NGRAM_WEIGHTED) { ------------------ | | 84| 5.63M|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2110:18): [True: 331k, False: 5.30M] ------------------ 2111| 331k| ns--; 2112| 331k| if (i == 0 || i == l1 - j) ------------------ | Branch (2112:13): [True: 42.3k, False: 289k] | Branch (2112:23): [True: 100k, False: 188k] ------------------ 2113| 143k| ns--; // side weight 2114| 331k| } 2115| 9.16M| } 2116| 1.38M| nscore = nscore + ns; 2117| 1.38M| if (ns < 2 && !(opt & NGRAM_WEIGHTED)) ------------------ | | 84| 804k|#define NGRAM_WEIGHTED (1 << 3) ------------------ | Branch (2117:9): [True: 804k, False: 584k] | Branch (2117:19): [True: 681k, False: 123k] ------------------ 2118| 681k| break; 2119| 1.38M| } 2120| | 2121| 807k| ns = 0; 2122| 807k| if (opt & NGRAM_LONGER_WORSE) ------------------ | | 81| 807k|#define NGRAM_LONGER_WORSE (1 << 0) ------------------ | Branch (2122:7): [True: 299k, False: 508k] ------------------ 2123| 299k| ns = (l2 - l1) - 2; 2124| 807k| if (opt & NGRAM_ANY_MISMATCH) ------------------ | | 82| 807k|#define NGRAM_ANY_MISMATCH (1 << 1) ------------------ | Branch (2124:7): [True: 508k, False: 299k] ------------------ 2125| 508k| ns = abs(l2 - l1) - 2; 2126| 807k| ns = (nscore - ((ns > 0) ? ns : 0)); ------------------ | Branch (2126:19): [True: 171k, False: 636k] ------------------ 2127| 807k| return ns; 2128| 818k|} _ZN10SuggestMgr19leftcommonsubstringERKNSt3__16vectorI6w_charNS0_9allocatorIS2_EEEES7_: 2133| 491k| const std::vector& su2) { 2134| 491k| int l1 = su1.size(), l2 = su2.size(); 2135| | // decapitalize dictionary word 2136| 491k| if (complexprefixes) { ------------------ | Branch (2136:7): [True: 0, False: 491k] ------------------ 2137| 0| if (l1 && l2 && su1[l1 - 1] == su2[l2 - 1]) ------------------ | Branch (2137:9): [True: 0, False: 0] | Branch (2137:15): [True: 0, False: 0] | Branch (2137:21): [True: 0, False: 0] ------------------ 2138| 0| return 1; 2139| 491k| } else { 2140| 491k| unsigned short idx = su2.empty() ? 0 : (unsigned short)(su2[0]), ------------------ | Branch (2140:26): [True: 0, False: 491k] ------------------ 2141| 491k| otheridx = su1.empty() ? 0 : (unsigned short)(su1[0]); ------------------ | Branch (2141:31): [True: 14.2k, False: 477k] ------------------ 2142| 491k| if (otheridx != idx && (otheridx != unicodetolower(idx, langnum))) ------------------ | Branch (2142:9): [True: 465k, False: 25.5k] | Branch (2142:28): [True: 364k, False: 101k] ------------------ 2143| 364k| return 0; 2144| 126k| int i; 2145| 204k| for (i = 1; (i < l1) && (i < l2) && (su1[i] == su2[i]); ------------------ | Branch (2145:17): [True: 192k, False: 12.6k] | Branch (2145:29): [True: 175k, False: 16.6k] | Branch (2145:41): [True: 78.1k, False: 97.2k] ------------------ 2146| 126k| i++) 2147| 78.1k| ; 2148| 126k| return i; 2149| 491k| } 2150| 0| return 0; 2151| 491k|} _ZN10SuggestMgr19leftcommonsubstringEPKcS1_: 2156| 641k| const char* s2) { 2157| 641k| if (complexprefixes) { ------------------ | Branch (2157:7): [True: 51.7k, False: 589k] ------------------ 2158| 51.7k| int l1 = strlen(s1), l2 = strlen(s2); 2159| 51.7k| if (l1 && l1 <= l2 && s1[l1 - 1] == s2[l2 - 1]) ------------------ | Branch (2159:9): [True: 50.3k, False: 1.42k] | Branch (2159:15): [True: 22.9k, False: 27.3k] | Branch (2159:27): [True: 1.83k, False: 21.1k] ------------------ 2160| 1.83k| return 1; 2161| 589k| } else if (csconv) { ------------------ | Branch (2161:14): [True: 589k, False: 0] ------------------ 2162| 589k| const char* olds = s1; 2163| | // decapitalise dictionary word 2164| 589k| if ((*s1 != *s2) && (((unsigned char)*s1) != csconv[((unsigned char)*s2)].clower)) ------------------ | Branch (2164:9): [True: 539k, False: 50.2k] | Branch (2164:25): [True: 409k, False: 130k] ------------------ 2165| 409k| return 0; 2166| 403k| do { 2167| 403k| s1++; 2168| 403k| s2++; 2169| 403k| } while ((*s1 == *s2) && (*s1 != '\0')); ------------------ | Branch (2169:14): [True: 223k, False: 180k] | Branch (2169:30): [True: 222k, False: 334] ------------------ 2170| 180k| return (int)(s1 - olds); 2171| 589k| } 2172| 49.9k| return 0; 2173| 641k|} _ZN10SuggestMgr24commoncharacterpositionsEPKcS1_Pi: 2177| 67.3k| int* is_swap) { 2178| 67.3k| int num = 0, diff = 0, diffpos[2]; 2179| 67.3k| *is_swap = 0; 2180| 67.3k| if (utf8) { ------------------ | Branch (2180:7): [True: 20.0k, False: 47.2k] ------------------ 2181| 20.0k| std::vector su1; 2182| 20.0k| std::vector su2; 2183| 20.0k| int l1 = u8_u16(su1, s1), l2 = u8_u16(su2, s2); 2184| | 2185| 20.0k| if (l1 <= 0 || l2 <= 0) ------------------ | Branch (2185:9): [True: 3.12k, False: 16.9k] | Branch (2185:20): [True: 0, False: 16.9k] ------------------ 2186| 3.12k| return 0; 2187| | 2188| | // decapitalize dictionary word 2189| 16.9k| if (complexprefixes) { ------------------ | Branch (2189:9): [True: 0, False: 16.9k] ------------------ 2190| 0| su2[l2 - 1] = lower_utf(su2[l2 - 1], langnum); 2191| 16.9k| } else { 2192| 16.9k| su2[0] = lower_utf(su2[0], langnum); 2193| 16.9k| } 2194| 63.6k| for (int i = 0; (i < l1) && (i < l2); i++) { ------------------ | Branch (2194:21): [True: 51.8k, False: 11.8k] | Branch (2194:33): [True: 46.6k, False: 5.13k] ------------------ 2195| 46.6k| if (su1[i] == su2[i]) { ------------------ | Branch (2195:11): [True: 24.5k, False: 22.1k] ------------------ 2196| 24.5k| num++; 2197| 24.5k| } else { 2198| 22.1k| if (diff < 2) ------------------ | Branch (2198:13): [True: 17.8k, False: 4.29k] ------------------ 2199| 17.8k| diffpos[diff] = i; 2200| 22.1k| diff++; 2201| 22.1k| } 2202| 46.6k| } 2203| 16.9k| if ((diff == 2) && (l1 == l2) && ------------------ | Branch (2203:9): [True: 2.74k, False: 14.1k] | Branch (2203:24): [True: 558, False: 2.18k] ------------------ 2204| 558| (su1[diffpos[0]] == su2[diffpos[1]]) && ------------------ | Branch (2204:9): [True: 195, False: 363] ------------------ 2205| 195| (su1[diffpos[1]] == su2[diffpos[0]])) ------------------ | Branch (2205:9): [True: 56, False: 139] ------------------ 2206| 56| *is_swap = 1; 2207| 47.2k| } else { 2208| 47.2k| size_t i; 2209| 47.2k| std::string t(s2); 2210| | // decapitalize dictionary word 2211| 47.2k| if (complexprefixes) { ------------------ | Branch (2211:9): [True: 2.87k, False: 44.4k] ------------------ 2212| 2.87k| size_t l2 = t.size(); 2213| 2.87k| t[l2 - 1] = csconv[(unsigned char)t[l2 - 1]].clower; 2214| 44.4k| } else { 2215| 44.4k| mkallsmall(t, csconv); 2216| 44.4k| } 2217| 251k| for (i = 0; i < t.size() && (*(s1 + i) != 0); ++i) { ------------------ | Branch (2217:17): [True: 225k, False: 26.6k] | Branch (2217:33): [True: 204k, False: 20.6k] ------------------ 2218| 204k| if (*(s1 + i) == t[i]) { ------------------ | Branch (2218:11): [True: 107k, False: 96.4k] ------------------ 2219| 107k| num++; 2220| 107k| } else { 2221| 96.4k| if (diff < 2) ------------------ | Branch (2221:13): [True: 57.2k, False: 39.2k] ------------------ 2222| 57.2k| diffpos[diff] = i; 2223| 96.4k| diff++; 2224| 96.4k| } 2225| 204k| } 2226| 47.2k| if ((diff == 2) && (*(s1 + i) == 0) && i == t.size() && ------------------ | Branch (2226:9): [True: 8.68k, False: 38.6k] | Branch (2226:24): [True: 5.55k, False: 3.12k] | Branch (2226:44): [True: 2.02k, False: 3.52k] ------------------ 2227| 2.02k| (*(s1 + diffpos[0]) == t[diffpos[1]]) && ------------------ | Branch (2227:9): [True: 388, False: 1.64k] ------------------ 2228| 388| (*(s1 + diffpos[1]) == t[diffpos[0]])) ------------------ | Branch (2228:9): [True: 78, False: 310] ------------------ 2229| 78| *is_swap = 1; 2230| 47.2k| } 2231| 64.2k| return num; 2232| 67.3k|} _ZN10SuggestMgr10bubblesortEPPcS1_Pii: 2243| 97.4k|void SuggestMgr::bubblesort(char** rword, char** rword2, int* rsc, int n) { 2244| 97.4k| int m = 1; 2245| 18.9M| while (m < n) { ------------------ | Branch (2245:10): [True: 18.8M, False: 97.4k] ------------------ 2246| 18.8M| int j = m; 2247| 36.4M| while (j > 0) { ------------------ | Branch (2247:12): [True: 36.4M, False: 25.5k] ------------------ 2248| 36.4M| if (rsc[j - 1] < rsc[j]) { ------------------ | Branch (2248:11): [True: 17.5M, False: 18.8M] ------------------ 2249| 17.5M| int sctmp = rsc[j - 1]; 2250| 17.5M| char* wdtmp = rword[j - 1]; 2251| 17.5M| rsc[j - 1] = rsc[j]; 2252| 17.5M| rword[j - 1] = rword[j]; 2253| 17.5M| rsc[j] = sctmp; 2254| 17.5M| rword[j] = wdtmp; 2255| 17.5M| if (rword2) { ------------------ | Branch (2255:13): [True: 17.1M, False: 487k] ------------------ 2256| 17.1M| wdtmp = rword2[j - 1]; 2257| 17.1M| rword2[j - 1] = rword2[j]; 2258| 17.1M| rword2[j] = wdtmp; 2259| 17.1M| } 2260| 17.5M| j--; 2261| 17.5M| } else 2262| 18.8M| break; 2263| 36.4M| } 2264| 18.8M| m++; 2265| 18.8M| } 2266| 97.4k|} _ZN10SuggestMgr3lcsEPKcS1_PiS2_: 2272| 75.0k| int* l2) { 2273| 75.0k| int n, m, i, j; 2274| 75.0k| std::vector su; 2275| 75.0k| std::vector su2; 2276| 75.0k| if (utf8) { ------------------ | Branch (2276:7): [True: 21.4k, False: 53.5k] ------------------ 2277| 21.4k| m = u8_u16(su, s); 2278| 21.4k| n = u8_u16(su2, s2); 2279| 53.5k| } else { 2280| 53.5k| m = strlen(s); 2281| 53.5k| n = strlen(s2); 2282| 53.5k| } 2283| 75.0k| if (m <= 0 || n <= 0) { ------------------ | Branch (2283:7): [True: 7.18k, False: 67.8k] | Branch (2283:17): [True: 0, False: 67.8k] ------------------ 2284| 7.18k| *l1 = 0; 2285| 7.18k| *l2 = 0; 2286| 7.18k| return nullptr; 2287| 7.18k| } 2288| 67.8k| char* c = new char[(m + 1) * (n + 1)](); 2289| 67.8k| char* b = new char[(m + 1) * (n + 1)](); 2290| 406k| for (i = 1; i <= m; i++) { ------------------ | Branch (2290:15): [True: 338k, False: 67.8k] ------------------ 2291| 3.28M| for (j = 1; j <= n; j++) { ------------------ | Branch (2291:17): [True: 2.94M, False: 338k] ------------------ 2292| 2.94M| if (((utf8) && (su[i - 1] == su2[j - 1])) || ------------------ | Branch (2292:12): [True: 273k, False: 2.66M] | Branch (2292:22): [True: 51.3k, False: 222k] ------------------ 2293| 2.89M| ((!utf8) && (s[i - 1] == s2[j - 1]))) { ------------------ | Branch (2293:12): [True: 2.66M, False: 222k] | Branch (2293:23): [True: 438k, False: 2.23M] ------------------ 2294| 489k| c[i * (n + 1) + j] = c[(i - 1) * (n + 1) + j - 1] + 1; 2295| 489k| b[i * (n + 1) + j] = LCS_UPLEFT; 2296| 2.45M| } else if (c[(i - 1) * (n + 1) + j] >= c[i * (n + 1) + j - 1]) { ------------------ | Branch (2296:18): [True: 1.77M, False: 683k] ------------------ 2297| 1.77M| c[i * (n + 1) + j] = c[(i - 1) * (n + 1) + j]; 2298| 1.77M| b[i * (n + 1) + j] = LCS_UP; 2299| 1.77M| } else { 2300| 683k| c[i * (n + 1) + j] = c[i * (n + 1) + j - 1]; 2301| 683k| b[i * (n + 1) + j] = LCS_LEFT; 2302| 683k| } 2303| 2.94M| } 2304| 338k| } 2305| 67.8k| delete[] c; 2306| 67.8k| *l1 = m; 2307| 67.8k| *l2 = n; 2308| 67.8k| return b; 2309| 75.0k|} _ZN10SuggestMgr6lcslenEPKcS1_: 2311| 75.0k|int SuggestMgr::lcslen(const char* s, const char* s2) { 2312| 75.0k| int m, n, len = 0; 2313| 75.0k| char* result = lcs(s, s2, &m, &n); 2314| 75.0k| if (!result) ------------------ | Branch (2314:7): [True: 7.18k, False: 67.8k] ------------------ 2315| 7.18k| return 0; 2316| 67.8k| int i = m, j = n; 2317| 528k| while ((i != 0) && (j != 0)) { ------------------ | Branch (2317:10): [True: 467k, False: 60.9k] | Branch (2317:22): [True: 460k, False: 6.97k] ------------------ 2318| 460k| if (result[i * (n + 1) + j] == LCS_UPLEFT) { ------------------ | Branch (2318:9): [True: 184k, False: 275k] ------------------ 2319| 184k| len++; 2320| 184k| i--; 2321| 184k| j--; 2322| 275k| } else if (result[i * (n + 1) + j] == LCS_UP) { ------------------ | Branch (2322:16): [True: 139k, False: 136k] ------------------ 2323| 139k| i--; 2324| 139k| } else 2325| 136k| j--; 2326| 460k| } 2327| 67.8k| delete[] result; 2328| 67.8k| return len; 2329| 75.0k|} _ZN10SuggestMgr6lcslenERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_: 2331| 5.84k|int SuggestMgr::lcslen(const std::string& s, const std::string& s2) { 2332| 5.84k| return lcslen(s.c_str(), s2.c_str()); 2333| 5.84k|} suggestmgr.cxx:_ZN12_GLOBAL__N_115ngsuggest_guardC2EbPK7cs_infoPiPS3_: 1164| 59.9k| : m_nonbmp(nonbmp) 1165| 59.9k| , m_origconv(origconv) 1166| 59.9k| , m_utf8(utf8) 1167| 59.9k| , m_csconv(csconv) 1168| 59.9k| { 1169| 59.9k| } suggestmgr.cxx:_ZN12_GLOBAL__N_115ngsuggest_guardD2Ev: 1172| 59.9k| { 1173| 59.9k| if (m_nonbmp) { ------------------ | Branch (1173:11): [True: 2.13k, False: 57.7k] ------------------ 1174| 2.13k| *m_csconv = m_origconv; 1175| 2.13k| *m_utf8 = 1; 1176| 2.13k| } 1177| 59.9k| } suggestmgr.cxx:_ZL12get_sfxcountPKc: 1902| 911k|static int get_sfxcount(const char* morph) { 1903| 911k| if (!morph || !*morph) ------------------ | Branch (1903:7): [True: 455k, False: 455k] | Branch (1903:17): [True: 0, False: 455k] ------------------ 1904| 455k| return 0; 1905| 455k| int n = 0; 1906| 455k| const char* old = morph; 1907| 455k| morph = strstr(morph, MORPH_DERI_SFX); ------------------ | | 109| 455k|#define MORPH_DERI_SFX "ds:" ------------------ 1908| 455k| if (!morph) ------------------ | Branch (1908:7): [True: 330k, False: 124k] ------------------ 1909| 330k| morph = strstr(old, MORPH_INFL_SFX); ------------------ | | 110| 330k|#define MORPH_INFL_SFX "is:" ------------------ 1910| 455k| if (!morph) ------------------ | Branch (1910:7): [True: 330k, False: 125k] ------------------ 1911| 330k| morph = strstr(old, MORPH_TERM_SFX); ------------------ | | 111| 330k|#define MORPH_TERM_SFX "ts:" ------------------ 1912| 826k| while (morph) { ------------------ | Branch (1912:10): [True: 370k, False: 455k] ------------------ 1913| 370k| n++; 1914| 370k| old = morph; 1915| 370k| morph = strstr(morph + 1, MORPH_DERI_SFX); ------------------ | | 109| 370k|#define MORPH_DERI_SFX "ds:" ------------------ 1916| 370k| if (!morph) ------------------ | Branch (1916:9): [True: 310k, False: 59.9k] ------------------ 1917| 310k| morph = strstr(old + 1, MORPH_INFL_SFX); ------------------ | | 110| 310k|#define MORPH_INFL_SFX "is:" ------------------ 1918| 370k| if (!morph) ------------------ | Branch (1918:9): [True: 310k, False: 59.9k] ------------------ 1919| 310k| morph = strstr(old + 1, MORPH_TERM_SFX); ------------------ | | 111| 310k|#define MORPH_TERM_SFX "ts:" ------------------ 1920| 370k| } 1921| 455k| return n; 1922| 911k|} _ZNK6w_charcvtEv: 57| 252M| { 58| 252M|#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| 252M| unsigned short u; 64| 252M| memcpy(&u, this, sizeof(unsigned short)); 65| 252M| return u; 66| 252M|#endif 67| | 68| |#else 69| | return ((unsigned short)h << 8) | (unsigned short)l; 70| |#endif 71| 252M| } _Zlt6w_charS_: 73| 22.9M| friend bool operator<(const w_char a, const w_char b) { 74| 22.9M| return (unsigned short)a < (unsigned short)b; 75| 22.9M| } _Zeq6w_charS_: 77| 83.8M| friend bool operator==(const w_char a, const w_char b) { 78| 83.8M| return (unsigned short)a == (unsigned short)b; 79| 83.8M| } _Zne6w_charS_: 81| 81.6M| friend bool operator!=(const w_char a, const w_char b) { 82| 81.6M| return !(a == b); 83| 81.6M| } _Z8endswithRKNSt3__112basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEES7_: 40| 200|{ 41| 200| return str.size() >= suffix.size() && ------------------ | Branch (41:12): [True: 192, False: 8] ------------------ 42| 192| str.compare(str.size() - suffix.size(), suffix.size(), suffix) == 0; ------------------ | Branch (42:12): [True: 38, False: 154] ------------------ 43| 200|} 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| 202| while ((direntry = readdir(d)) != NULL) ------------------ | Branch (54:12): [True: 200, False: 2] ------------------ 55| 200| { 56| 200| std::string entry(direntry->d_name); 57| 200| if (endswith(entry, ".aff")) ------------------ | Branch (57:13): [True: 38, False: 162] ------------------ 58| 38| affs.push_back(std::move(entry)); 59| 200| } 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| 3.21k|{ 77| 3.21k| std::string word(data, size); 78| 3.21k| for (auto& dict : dictionaries) ------------------ | Branch (78:21): [True: 60.9k, False: 3.21k] ------------------ 79| 60.9k| { 80| 60.9k| if (!dict->spell(word)) ------------------ | Branch (80:13): [True: 60.4k, False: 572] ------------------ 81| 60.4k| dict->suggest(word); 82| 60.9k| } 83| 3.21k| return 0; 84| 3.21k|}