stemmers 0.0.1

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