1 // Sonic 2 // 3 // Fast, lightweight and schema-less search backend 4 // Copyright: 2019, Valerian Saliou <valerian@valeriansaliou.name> 5 // License: Mozilla Public License v2.0 (MPL v2.0) 6 7 pub static STOPWORDS_ENG: &[&'static str] = &[ 8 "'ll", 9 "'tis", 10 "'twas", 11 "'ve", 12 "10", 13 "39", 14 "a", 15 "a's", 16 "able", 17 "ableabout", 18 "about", 19 "above", 20 "abroad", 21 "abst", 22 "accordance", 23 "according", 24 "accordingly", 25 "across", 26 "act", 27 "actually", 28 "ad", 29 "added", 30 "adj", 31 "adopted", 32 "ae", 33 "af", 34 "affected", 35 "affecting", 36 "affects", 37 "after", 38 "afterwards", 39 "ag", 40 "again", 41 "against", 42 "ago", 43 "ah", 44 "ahead", 45 "ai", 46 "ain't", 47 "aint", 48 "al", 49 "all", 50 "allow", 51 "allows", 52 "almost", 53 "alone", 54 "along", 55 "alongside", 56 "already", 57 "also", 58 "although", 59 "always", 60 "am", 61 "amid", 62 "amidst", 63 "among", 64 "amongst", 65 "amoungst", 66 "amount", 67 "an", 68 "and", 69 "announce", 70 "another", 71 "any", 72 "anybody", 73 "anyhow", 74 "anymore", 75 "anyone", 76 "anything", 77 "anyway", 78 "anyways", 79 "anywhere", 80 "ao", 81 "apart", 82 "apparently", 83 "appear", 84 "appreciate", 85 "appropriate", 86 "approximately", 87 "aq", 88 "ar", 89 "are", 90 "area", 91 "areas", 92 "aren", 93 "aren't", 94 "arent", 95 "arise", 96 "around", 97 "arpa", 98 "as", 99 "aside", 100 "ask", 101 "asked", 102 "asking", 103 "asks", 104 "associated", 105 "at", 106 "au", 107 "auth", 108 "available", 109 "aw", 110 "away", 111 "awfully", 112 "az", 113 "b", 114 "ba", 115 "back", 116 "backed", 117 "backing", 118 "backs", 119 "backward", 120 "backwards", 121 "bb", 122 "bd", 123 "be", 124 "became", 125 "because", 126 "become", 127 "becomes", 128 "becoming", 129 "been", 130 "before", 131 "beforehand", 132 "began", 133 "begin", 134 "beginning", 135 "beginnings", 136 "begins", 137 "behind", 138 "being", 139 "beings", 140 "believe", 141 "below", 142 "beside", 143 "besides", 144 "best", 145 "better", 146 "between", 147 "beyond", 148 "bf", 149 "bg", 150 "bh", 151 "bi", 152 "big", 153 "bill", 154 "billion", 155 "biol", 156 "bj", 157 "bm", 158 "bn", 159 "bo", 160 "both", 161 "bottom", 162 "br", 163 "brief", 164 "briefly", 165 "bs", 166 "bt", 167 "but", 168 "buy", 169 "bv", 170 "bw", 171 "by", 172 "bz", 173 "c", 174 "c'mon", 175 "c's", 176 "ca", 177 "call", 178 "came", 179 "can", 180 "can't", 181 "cannot", 182 "cant", 183 "caption", 184 "case", 185 "cases", 186 "cause", 187 "causes", 188 "cc", 189 "cd", 190 "certain", 191 "certainly", 192 "cf", 193 "cg", 194 "ch", 195 "changes", 196 "ci", 197 "ck", 198 "cl", 199 "clear", 200 "clearly", 201 "click", 202 "cm", 203 "cmon", 204 "cn", 205 "co", 206 "co.", 207 "com", 208 "come", 209 "comes", 210 "computer", 211 "con", 212 "concerning", 213 "consequently", 214 "consider", 215 "considering", 216 "contain", 217 "containing", 218 "contains", 219 "copy", 220 "corresponding", 221 "could", 222 "could've", 223 "couldn", 224 "couldn't", 225 "couldnt", 226 "course", 227 "cr", 228 "cry", 229 "cs", 230 "cu", 231 "currently", 232 "cv", 233 "cx", 234 "cy", 235 "cz", 236 "d", 237 "dare", 238 "daren't", 239 "darent", 240 "date", 241 "de", 242 "dear", 243 "definitely", 244 "describe", 245 "described", 246 "despite", 247 "detail", 248 "did", 249 "didn", 250 "didn't", 251 "didnt", 252 "differ", 253 "different", 254 "differently", 255 "directly", 256 "dj", 257 "dk", 258 "dm", 259 "do", 260 "does", 261 "doesn", 262 "doesn't", 263 "doesnt", 264 "doing", 265 "don", 266 "don't", 267 "done", 268 "dont", 269 "doubtful", 270 "down", 271 "downed", 272 "downing", 273 "downs", 274 "downwards", 275 "due", 276 "during", 277 "dz", 278 "e", 279 "each", 280 "early", 281 "ec", 282 "ed", 283 "edu", 284 "ee", 285 "effect", 286 "eg", 287 "eh", 288 "eight", 289 "eighty", 290 "either", 291 "eleven", 292 "else", 293 "elsewhere", 294 "empty", 295 "end", 296 "ended", 297 "ending", 298 "ends", 299 "enough", 300 "entirely", 301 "er", 302 "es", 303 "especially", 304 "et", 305 "et-al", 306 "etc", 307 "even", 308 "evenly", 309 "ever", 310 "evermore", 311 "every", 312 "everybody", 313 "everyone", 314 "everything", 315 "everywhere", 316 "ex", 317 "exactly", 318 "example", 319 "except", 320 "f", 321 "face", 322 "faces", 323 "fact", 324 "facts", 325 "fairly", 326 "far", 327 "farther", 328 "felt", 329 "few", 330 "fewer", 331 "ff", 332 "fi", 333 "fifteen", 334 "fifth", 335 "fifty", 336 "fify", 337 "fill", 338 "find", 339 "finds", 340 "fire", 341 "first", 342 "five", 343 "fix", 344 "fj", 345 "fk", 346 "fm", 347 "fo", 348 "followed", 349 "following", 350 "follows", 351 "for", 352 "forever", 353 "former", 354 "formerly", 355 "forth", 356 "forty", 357 "forward", 358 "found", 359 "four", 360 "fr", 361 "free", 362 "from", 363 "front", 364 "full", 365 "fully", 366 "further", 367 "furthered", 368 "furthering", 369 "furthermore", 370 "furthers", 371 "fx", 372 "g", 373 "ga", 374 "gave", 375 "gb", 376 "gd", 377 "ge", 378 "general", 379 "generally", 380 "get", 381 "gets", 382 "getting", 383 "gf", 384 "gg", 385 "gh", 386 "gi", 387 "give", 388 "given", 389 "gives", 390 "giving", 391 "gl", 392 "gm", 393 "gmt", 394 "gn", 395 "go", 396 "goes", 397 "going", 398 "gone", 399 "good", 400 "goods", 401 "got", 402 "gotten", 403 "gov", 404 "gp", 405 "gq", 406 "gr", 407 "great", 408 "greater", 409 "greatest", 410 "greetings", 411 "group", 412 "grouped", 413 "grouping", 414 "groups", 415 "gs", 416 "gt", 417 "gu", 418 "gw", 419 "gy", 420 "h", 421 "had", 422 "hadn't", 423 "hadnt", 424 "half", 425 "happens", 426 "hardly", 427 "has", 428 "hasn", 429 "hasn't", 430 "hasnt", 431 "have", 432 "haven", 433 "haven't", 434 "havent", 435 "having", 436 "he", 437 "he'd", 438 "he'll", 439 "he's", 440 "hed", 441 "hell", 442 "hello", 443 "help", 444 "hence", 445 "her", 446 "here", 447 "here's", 448 "hereafter", 449 "hereby", 450 "herein", 451 "heres", 452 "hereupon", 453 "hers", 454 "herself", 455 "herse”", 456 "hes", 457 "hi", 458 "hid", 459 "high", 460 "higher", 461 "highest", 462 "him", 463 "himself", 464 "himse”", 465 "his", 466 "hither", 467 "hk", 468 "hm", 469 "hn", 470 "home", 471 "homepage", 472 "hopefully", 473 "how", 474 "how'd", 475 "how'll", 476 "how's", 477 "howbeit", 478 "however", 479 "hr", 480 "ht", 481 "htm", 482 "html", 483 "http", 484 "hu", 485 "hundred", 486 "i", 487 "i'd", 488 "i'll", 489 "i'm", 490 "i've", 491 "i.e.", 492 "id", 493 "ie", 494 "if", 495 "ignored", 496 "ii", 497 "il", 498 "ill", 499 "im", 500 "immediate", 501 "immediately", 502 "importance", 503 "important", 504 "in", 505 "inasmuch", 506 "inc", 507 "inc.", 508 "indeed", 509 "index", 510 "indicate", 511 "indicated", 512 "indicates", 513 "information", 514 "inner", 515 "inside", 516 "insofar", 517 "instead", 518 "int", 519 "interest", 520 "interested", 521 "interesting", 522 "interests", 523 "into", 524 "invention", 525 "inward", 526 "io", 527 "iq", 528 "ir", 529 "is", 530 "isn", 531 "isn't", 532 "isnt", 533 "it", 534 "it'd", 535 "it'll", 536 "it's", 537 "itd", 538 "itll", 539 "its", 540 "itself", 541 "itse”", 542 "ive", 543 "j", 544 "je", 545 "jm", 546 "jo", 547 "join", 548 "jp", 549 "just", 550 "k", 551 "ke", 552 "keep", 553 "keeps", 554 "kept", 555 "keys", 556 "kg", 557 "kh", 558 "ki", 559 "kind", 560 "km", 561 "kn", 562 "knew", 563 "know", 564 "known", 565 "knows", 566 "kp", 567 "kr", 568 "kw", 569 "ky", 570 "kz", 571 "l", 572 "la", 573 "large", 574 "largely", 575 "last", 576 "lately", 577 "later", 578 "latest", 579 "latter", 580 "latterly", 581 "lb", 582 "lc", 583 "least", 584 "length", 585 "less", 586 "lest", 587 "let", 588 "let's", 589 "lets", 590 "li", 591 "like", 592 "liked", 593 "likely", 594 "likewise", 595 "line", 596 "little", 597 "lk", 598 "ll", 599 "long", 600 "longer", 601 "longest", 602 "look", 603 "looking", 604 "looks", 605 "low", 606 "lower", 607 "lr", 608 "ls", 609 "lt", 610 "ltd", 611 "lu", 612 "lv", 613 "ly", 614 "m", 615 "ma", 616 "made", 617 "mainly", 618 "make", 619 "makes", 620 "making", 621 "man", 622 "many", 623 "may", 624 "maybe", 625 "mayn't", 626 "maynt", 627 "mc", 628 "md", 629 "me", 630 "mean", 631 "means", 632 "meantime", 633 "meanwhile", 634 "member", 635 "members", 636 "men", 637 "merely", 638 "mg", 639 "mh", 640 "microsoft", 641 "might", 642 "might've", 643 "mightn't", 644 "mightnt", 645 "mil", 646 "mill", 647 "million", 648 "mine", 649 "minus", 650 "miss", 651 "mk", 652 "ml", 653 "mm", 654 "mn", 655 "mo", 656 "more", 657 "moreover", 658 "most", 659 "mostly", 660 "move", 661 "mp", 662 "mq", 663 "mr", 664 "mrs", 665 "ms", 666 "msie", 667 "mt", 668 "mu", 669 "much", 670 "mug", 671 "must", 672 "must've", 673 "mustn't", 674 "mustnt", 675 "mv", 676 "mw", 677 "mx", 678 "my", 679 "myself", 680 "myse”", 681 "mz", 682 "n", 683 "na", 684 "name", 685 "namely", 686 "nay", 687 "nc", 688 "nd", 689 "ne", 690 "near", 691 "nearly", 692 "necessarily", 693 "necessary", 694 "need", 695 "needed", 696 "needing", 697 "needn't", 698 "neednt", 699 "needs", 700 "neither", 701 "net", 702 "netscape", 703 "never", 704 "neverf", 705 "neverless", 706 "nevertheless", 707 "new", 708 "newer", 709 "newest", 710 "next", 711 "nf", 712 "ng", 713 "ni", 714 "nine", 715 "ninety", 716 "nl", 717 "no", 718 "no-one", 719 "nobody", 720 "non", 721 "none", 722 "nonetheless", 723 "noone", 724 "nor", 725 "normally", 726 "nos", 727 "not", 728 "noted", 729 "nothing", 730 "notwithstanding", 731 "novel", 732 "now", 733 "nowhere", 734 "np", 735 "nr", 736 "nu", 737 "null", 738 "number", 739 "numbers", 740 "nz", 741 "o", 742 "obtain", 743 "obtained", 744 "obviously", 745 "of", 746 "off", 747 "often", 748 "oh", 749 "ok", 750 "okay", 751 "old", 752 "older", 753 "oldest", 754 "om", 755 "omitted", 756 "on", 757 "once", 758 "one", 759 "one's", 760 "ones", 761 "only", 762 "onto", 763 "open", 764 "opened", 765 "opening", 766 "opens", 767 "opposite", 768 "or", 769 "ord", 770 "order", 771 "ordered", 772 "ordering", 773 "orders", 774 "org", 775 "other", 776 "others", 777 "otherwise", 778 "ought", 779 "oughtn't", 780 "oughtnt", 781 "our", 782 "ours", 783 "ourselves", 784 "out", 785 "outside", 786 "over", 787 "overall", 788 "owing", 789 "own", 790 "p", 791 "pa", 792 "page", 793 "pages", 794 "part", 795 "parted", 796 "particular", 797 "particularly", 798 "parting", 799 "parts", 800 "past", 801 "pe", 802 "per", 803 "perhaps", 804 "pf", 805 "pg", 806 "ph", 807 "pk", 808 "pl", 809 "place", 810 "placed", 811 "places", 812 "please", 813 "plus", 814 "pm", 815 "pmid", 816 "pn", 817 "point", 818 "pointed", 819 "pointing", 820 "points", 821 "poorly", 822 "possible", 823 "possibly", 824 "potentially", 825 "pp", 826 "pr", 827 "predominantly", 828 "present", 829 "presented", 830 "presenting", 831 "presents", 832 "presumably", 833 "previously", 834 "primarily", 835 "probably", 836 "problem", 837 "problems", 838 "promptly", 839 "proud", 840 "provided", 841 "provides", 842 "pt", 843 "put", 844 "puts", 845 "pw", 846 "py", 847 "q", 848 "qa", 849 "que", 850 "quickly", 851 "quite", 852 "qv", 853 "r", 854 "ran", 855 "rather", 856 "rd", 857 "re", 858 "readily", 859 "really", 860 "reasonably", 861 "recent", 862 "recently", 863 "ref", 864 "refs", 865 "regarding", 866 "regardless", 867 "regards", 868 "related", 869 "relatively", 870 "research", 871 "reserved", 872 "respectively", 873 "resulted", 874 "resulting", 875 "results", 876 "right", 877 "ring", 878 "ro", 879 "room", 880 "rooms", 881 "round", 882 "ru", 883 "run", 884 "rw", 885 "s", 886 "sa", 887 "said", 888 "same", 889 "saw", 890 "say", 891 "saying", 892 "says", 893 "sb", 894 "sc", 895 "sd", 896 "se", 897 "sec", 898 "second", 899 "secondly", 900 "seconds", 901 "section", 902 "see", 903 "seeing", 904 "seem", 905 "seemed", 906 "seeming", 907 "seems", 908 "seen", 909 "sees", 910 "self", 911 "selves", 912 "sensible", 913 "sent", 914 "serious", 915 "seriously", 916 "seven", 917 "seventy", 918 "several", 919 "sg", 920 "sh", 921 "shall", 922 "shan't", 923 "shant", 924 "she", 925 "she'd", 926 "she'll", 927 "she's", 928 "shed", 929 "shell", 930 "shes", 931 "should", 932 "should've", 933 "shouldn", 934 "shouldn't", 935 "shouldnt", 936 "show", 937 "showed", 938 "showing", 939 "shown", 940 "showns", 941 "shows", 942 "si", 943 "side", 944 "sides", 945 "significant", 946 "significantly", 947 "similar", 948 "similarly", 949 "since", 950 "sincere", 951 "site", 952 "six", 953 "sixty", 954 "sj", 955 "sk", 956 "sl", 957 "slightly", 958 "sm", 959 "small", 960 "smaller", 961 "smallest", 962 "sn", 963 "so", 964 "some", 965 "somebody", 966 "someday", 967 "somehow", 968 "someone", 969 "somethan", 970 "something", 971 "sometime", 972 "sometimes", 973 "somewhat", 974 "somewhere", 975 "soon", 976 "sorry", 977 "specifically", 978 "specified", 979 "specify", 980 "specifying", 981 "sr", 982 "st", 983 "state", 984 "states", 985 "still", 986 "stop", 987 "strongly", 988 "su", 989 "sub", 990 "substantially", 991 "successfully", 992 "such", 993 "sufficiently", 994 "suggest", 995 "sup", 996 "sure", 997 "sv", 998 "sy", 999 "system", 1000 "sz", 1001 "t", 1002 "t's", 1003 "take", 1004 "taken", 1005 "taking", 1006 "tc", 1007 "td", 1008 "tell", 1009 "ten", 1010 "tends", 1011 "test", 1012 "text", 1013 "tf", 1014 "tg", 1015 "th", 1016 "than", 1017 "thank", 1018 "thanks", 1019 "thanx", 1020 "that", 1021 "that'll", 1022 "that's", 1023 "that've", 1024 "thatll", 1025 "thats", 1026 "thatve", 1027 "the", 1028 "their", 1029 "theirs", 1030 "them", 1031 "themselves", 1032 "then", 1033 "thence", 1034 "there", 1035 "there'd", 1036 "there'll", 1037 "there're", 1038 "there's", 1039 "there've", 1040 "thereafter", 1041 "thereby", 1042 "thered", 1043 "therefore", 1044 "therein", 1045 "therell", 1046 "thereof", 1047 "therere", 1048 "theres", 1049 "thereto", 1050 "thereupon", 1051 "thereve", 1052 "these", 1053 "they", 1054 "they'd", 1055 "they'll", 1056 "they're", 1057 "they've", 1058 "theyd", 1059 "theyll", 1060 "theyre", 1061 "theyve", 1062 "thick", 1063 "thin", 1064 "thing", 1065 "things", 1066 "think", 1067 "thinks", 1068 "third", 1069 "thirty", 1070 "this", 1071 "thorough", 1072 "thoroughly", 1073 "those", 1074 "thou", 1075 "though", 1076 "thoughh", 1077 "thought", 1078 "thoughts", 1079 "thousand", 1080 "three", 1081 "throug", 1082 "through", 1083 "throughout", 1084 "thru", 1085 "thus", 1086 "til", 1087 "till", 1088 "tip", 1089 "tis", 1090 "tj", 1091 "tk", 1092 "tm", 1093 "tn", 1094 "to", 1095 "today", 1096 "together", 1097 "too", 1098 "took", 1099 "top", 1100 "toward", 1101 "towards", 1102 "tp", 1103 "tr", 1104 "tried", 1105 "tries", 1106 "trillion", 1107 "truly", 1108 "try", 1109 "trying", 1110 "ts", 1111 "tt", 1112 "turn", 1113 "turned", 1114 "turning", 1115 "turns", 1116 "tv", 1117 "tw", 1118 "twas", 1119 "twelve", 1120 "twenty", 1121 "twice", 1122 "two", 1123 "tz", 1124 "u", 1125 "ua", 1126 "ug", 1127 "uk", 1128 "um", 1129 "un", 1130 "under", 1131 "underneath", 1132 "undoing", 1133 "unfortunately", 1134 "unless", 1135 "unlike", 1136 "unlikely", 1137 "until", 1138 "unto", 1139 "up", 1140 "upon", 1141 "ups", 1142 "upwards", 1143 "us", 1144 "use", 1145 "used", 1146 "useful", 1147 "usefully", 1148 "usefulness", 1149 "uses", 1150 "using", 1151 "usually", 1152 "uucp", 1153 "uy", 1154 "uz", 1155 "v", 1156 "va", 1157 "value", 1158 "various", 1159 "vc", 1160 "ve", 1161 "versus", 1162 "very", 1163 "vg", 1164 "vi", 1165 "via", 1166 "viz", 1167 "vn", 1168 "vol", 1169 "vols", 1170 "vs", 1171 "vu", 1172 "w", 1173 "want", 1174 "wanted", 1175 "wanting", 1176 "wants", 1177 "was", 1178 "wasn", 1179 "wasn't", 1180 "wasnt", 1181 "way", 1182 "ways", 1183 "we", 1184 "we'd", 1185 "we'll", 1186 "we're", 1187 "we've", 1188 "web", 1189 "webpage", 1190 "website", 1191 "wed", 1192 "welcome", 1193 "well", 1194 "wells", 1195 "went", 1196 "were", 1197 "weren", 1198 "weren't", 1199 "werent", 1200 "weve", 1201 "wf", 1202 "what", 1203 "what'd", 1204 "what'll", 1205 "what's", 1206 "what've", 1207 "whatever", 1208 "whatll", 1209 "whats", 1210 "whatve", 1211 "when", 1212 "when'd", 1213 "when'll", 1214 "when's", 1215 "whence", 1216 "whenever", 1217 "where", 1218 "where'd", 1219 "where'll", 1220 "where's", 1221 "whereafter", 1222 "whereas", 1223 "whereby", 1224 "wherein", 1225 "wheres", 1226 "whereupon", 1227 "wherever", 1228 "whether", 1229 "which", 1230 "whichever", 1231 "while", 1232 "whilst", 1233 "whim", 1234 "whither", 1235 "who", 1236 "who'd", 1237 "who'll", 1238 "who's", 1239 "whod", 1240 "whoever", 1241 "whole", 1242 "wholl", 1243 "whom", 1244 "whomever", 1245 "whos", 1246 "whose", 1247 "why", 1248 "why'd", 1249 "why'll", 1250 "why's", 1251 "widely", 1252 "width", 1253 "will", 1254 "willing", 1255 "wish", 1256 "with", 1257 "within", 1258 "without", 1259 "won", 1260 "won't", 1261 "wonder", 1262 "wont", 1263 "words", 1264 "work", 1265 "worked", 1266 "working", 1267 "works", 1268 "world", 1269 "would", 1270 "would've", 1271 "wouldn", 1272 "wouldn't", 1273 "wouldnt", 1274 "ws", 1275 "www", 1276 "x", 1277 "y", 1278 "ye", 1279 "year", 1280 "years", 1281 "yes", 1282 "yet", 1283 "you", 1284 "you'd", 1285 "you'll", 1286 "you're", 1287 "you've", 1288 "youd", 1289 "youll", 1290 "young", 1291 "younger", 1292 "youngest", 1293 "your", 1294 "youre", 1295 "yours", 1296 "yourself", 1297 "yourselves", 1298 "youve", 1299 "yt", 1300 "yu", 1301 "z", 1302 "za", 1303 "zero", 1304 "zm", 1305 "zr", 1306 ]; 1307