stop-words 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +46 -0
- data/Rakefile +8 -0
- data/lib/stop/words.rb +1226 -0
- data/spec/words_spec.rb +14 -0
- data/stop-words.gemspec +24 -0
- metadata +96 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: cd85411f8290fc5644006be4da2948feadf3a359
|
4
|
+
data.tar.gz: a5a122b8d81d9079404460db588d1c29fa4c1870
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 4354bd156348cfb9d71b7f80aacdcf8699c79570e0deac616cacee19c0a29c14ddeb5c90668f7fb05518130d2c115a00c6a9f3e788afef351809dfaf66988aca
|
7
|
+
data.tar.gz: 33362fc04ef8261e1e1d5eefb441d08e83a059d3e711462f112cb805d811379cfffb1359b89b6f8fcbee74b3b9a37da36eed62a13bc308659a0ad5a271a6f12b
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2015 Christopher Petersen
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
# Stop::Words
|
2
|
+
|
3
|
+
Simple set of stop words based on [ranks.nl's](http://www.ranks.nl/stopwords) list.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'stop-words'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install stop-words
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
Get the default list of stop words using:
|
22
|
+
|
23
|
+
```ruby
|
24
|
+
Stop::Words.default
|
25
|
+
```
|
26
|
+
|
27
|
+
Get mysql's list of stop words using:
|
28
|
+
|
29
|
+
```ruby
|
30
|
+
Stop::Words.mysql
|
31
|
+
```
|
32
|
+
|
33
|
+
Get a longer list of keywords using:
|
34
|
+
|
35
|
+
```ruby
|
36
|
+
Stop::Words.long
|
37
|
+
```
|
38
|
+
|
39
|
+
|
40
|
+
## Contributing
|
41
|
+
|
42
|
+
1. Fork it
|
43
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
44
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
45
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
46
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/lib/stop/words.rb
ADDED
@@ -0,0 +1,1226 @@
|
|
1
|
+
# http://www.ranks.nl/stopwords
|
2
|
+
module Stop
|
3
|
+
class Words
|
4
|
+
VERSION = "0.0.1"
|
5
|
+
|
6
|
+
def self.default
|
7
|
+
["a",
|
8
|
+
"about",
|
9
|
+
"above",
|
10
|
+
"after",
|
11
|
+
"again",
|
12
|
+
"against",
|
13
|
+
"all",
|
14
|
+
"am",
|
15
|
+
"an",
|
16
|
+
"and",
|
17
|
+
"any",
|
18
|
+
"are",
|
19
|
+
"aren't",
|
20
|
+
"as",
|
21
|
+
"at",
|
22
|
+
"be",
|
23
|
+
"because",
|
24
|
+
"been",
|
25
|
+
"before",
|
26
|
+
"being",
|
27
|
+
"below",
|
28
|
+
"between",
|
29
|
+
"both",
|
30
|
+
"but",
|
31
|
+
"by",
|
32
|
+
"can't",
|
33
|
+
"cannot",
|
34
|
+
"could",
|
35
|
+
"couldn't",
|
36
|
+
"did",
|
37
|
+
"didn't",
|
38
|
+
"do",
|
39
|
+
"does",
|
40
|
+
"doesn't",
|
41
|
+
"doing",
|
42
|
+
"don't",
|
43
|
+
"down",
|
44
|
+
"during",
|
45
|
+
"each",
|
46
|
+
"few",
|
47
|
+
"for",
|
48
|
+
"from",
|
49
|
+
"further",
|
50
|
+
"had",
|
51
|
+
"hadn't",
|
52
|
+
"has",
|
53
|
+
"hasn't",
|
54
|
+
"have",
|
55
|
+
"haven't",
|
56
|
+
"having",
|
57
|
+
"he",
|
58
|
+
"he'd",
|
59
|
+
"he'll",
|
60
|
+
"he's",
|
61
|
+
"her",
|
62
|
+
"here",
|
63
|
+
"here's",
|
64
|
+
"hers",
|
65
|
+
"herself",
|
66
|
+
"him",
|
67
|
+
"himself",
|
68
|
+
"his",
|
69
|
+
"how",
|
70
|
+
"how's",
|
71
|
+
"i",
|
72
|
+
"i'd",
|
73
|
+
"i'll",
|
74
|
+
"i'm",
|
75
|
+
"i've",
|
76
|
+
"if",
|
77
|
+
"in",
|
78
|
+
"into",
|
79
|
+
"is",
|
80
|
+
"isn't",
|
81
|
+
"it",
|
82
|
+
"it's",
|
83
|
+
"its",
|
84
|
+
"itself",
|
85
|
+
"let's",
|
86
|
+
"me",
|
87
|
+
"more",
|
88
|
+
"most",
|
89
|
+
"mustn't",
|
90
|
+
"my",
|
91
|
+
"myself",
|
92
|
+
"no",
|
93
|
+
"nor",
|
94
|
+
"not",
|
95
|
+
"of",
|
96
|
+
"off",
|
97
|
+
"on",
|
98
|
+
"once",
|
99
|
+
"only",
|
100
|
+
"or",
|
101
|
+
"other",
|
102
|
+
"ought",
|
103
|
+
"our",
|
104
|
+
"ours ourselves",
|
105
|
+
"out",
|
106
|
+
"over",
|
107
|
+
"own",
|
108
|
+
"same",
|
109
|
+
"shan't",
|
110
|
+
"she",
|
111
|
+
"she'd",
|
112
|
+
"she'll",
|
113
|
+
"she's",
|
114
|
+
"should",
|
115
|
+
"shouldn't",
|
116
|
+
"so",
|
117
|
+
"some",
|
118
|
+
"such",
|
119
|
+
"than",
|
120
|
+
"that",
|
121
|
+
"that's",
|
122
|
+
"the",
|
123
|
+
"their",
|
124
|
+
"theirs",
|
125
|
+
"them",
|
126
|
+
"themselves",
|
127
|
+
"then",
|
128
|
+
"there",
|
129
|
+
"there's",
|
130
|
+
"these",
|
131
|
+
"they",
|
132
|
+
"they'd",
|
133
|
+
"they'll",
|
134
|
+
"they're",
|
135
|
+
"they've",
|
136
|
+
"this",
|
137
|
+
"those",
|
138
|
+
"through",
|
139
|
+
"to",
|
140
|
+
"too",
|
141
|
+
"under",
|
142
|
+
"until",
|
143
|
+
"up",
|
144
|
+
"very",
|
145
|
+
"was",
|
146
|
+
"wasn't",
|
147
|
+
"we",
|
148
|
+
"we'd",
|
149
|
+
"we'll",
|
150
|
+
"we're",
|
151
|
+
"we've",
|
152
|
+
"were",
|
153
|
+
"weren't",
|
154
|
+
"what",
|
155
|
+
"what's",
|
156
|
+
"when",
|
157
|
+
"when's",
|
158
|
+
"where",
|
159
|
+
"where's",
|
160
|
+
"which",
|
161
|
+
"while",
|
162
|
+
"who",
|
163
|
+
"who's",
|
164
|
+
"whom",
|
165
|
+
"why",
|
166
|
+
"why's",
|
167
|
+
"with",
|
168
|
+
"won't",
|
169
|
+
"would",
|
170
|
+
"wouldn't",
|
171
|
+
"you",
|
172
|
+
"you'd",
|
173
|
+
"you'll",
|
174
|
+
"you're",
|
175
|
+
"you've",
|
176
|
+
"your",
|
177
|
+
"yours",
|
178
|
+
"yourself",
|
179
|
+
"yourselves"]
|
180
|
+
end
|
181
|
+
|
182
|
+
def self.mysql
|
183
|
+
["a's",
|
184
|
+
"able",
|
185
|
+
"about",
|
186
|
+
"above",
|
187
|
+
"according",
|
188
|
+
"accordingly",
|
189
|
+
"across",
|
190
|
+
"actually",
|
191
|
+
"after",
|
192
|
+
"afterwards",
|
193
|
+
"again",
|
194
|
+
"against",
|
195
|
+
"ain't",
|
196
|
+
"all",
|
197
|
+
"allow",
|
198
|
+
"allows",
|
199
|
+
"almost",
|
200
|
+
"alone",
|
201
|
+
"along",
|
202
|
+
"already",
|
203
|
+
"also",
|
204
|
+
"although",
|
205
|
+
"always",
|
206
|
+
"am",
|
207
|
+
"among",
|
208
|
+
"amongst",
|
209
|
+
"an",
|
210
|
+
"and",
|
211
|
+
"another",
|
212
|
+
"any",
|
213
|
+
"anybody",
|
214
|
+
"anyhow",
|
215
|
+
"anyone",
|
216
|
+
"anything",
|
217
|
+
"anyway",
|
218
|
+
"anyways",
|
219
|
+
"anywhere",
|
220
|
+
"apart",
|
221
|
+
"appear",
|
222
|
+
"appreciate",
|
223
|
+
"appropriate",
|
224
|
+
"are",
|
225
|
+
"aren't",
|
226
|
+
"around",
|
227
|
+
"as",
|
228
|
+
"aside",
|
229
|
+
"ask",
|
230
|
+
"asking",
|
231
|
+
"associated",
|
232
|
+
"at",
|
233
|
+
"available",
|
234
|
+
"away",
|
235
|
+
"awfully",
|
236
|
+
"be",
|
237
|
+
"became",
|
238
|
+
"because",
|
239
|
+
"become",
|
240
|
+
"becomes",
|
241
|
+
"becoming",
|
242
|
+
"been",
|
243
|
+
"before",
|
244
|
+
"beforehand",
|
245
|
+
"behind",
|
246
|
+
"being",
|
247
|
+
"believe",
|
248
|
+
"below",
|
249
|
+
"beside",
|
250
|
+
"besides",
|
251
|
+
"best",
|
252
|
+
"better",
|
253
|
+
"between",
|
254
|
+
"beyond",
|
255
|
+
"both",
|
256
|
+
"brief",
|
257
|
+
"but",
|
258
|
+
"by",
|
259
|
+
"c'mon",
|
260
|
+
"c's",
|
261
|
+
"came",
|
262
|
+
"can",
|
263
|
+
"can't",
|
264
|
+
"cannot",
|
265
|
+
"cant",
|
266
|
+
"cause",
|
267
|
+
"causes",
|
268
|
+
"certain",
|
269
|
+
"certainly",
|
270
|
+
"changes",
|
271
|
+
"clearly",
|
272
|
+
"co",
|
273
|
+
"com",
|
274
|
+
"come",
|
275
|
+
"comes",
|
276
|
+
"concerning",
|
277
|
+
"consequently",
|
278
|
+
"consider",
|
279
|
+
"considering",
|
280
|
+
"contain",
|
281
|
+
"containing",
|
282
|
+
"contains",
|
283
|
+
"corresponding",
|
284
|
+
"could",
|
285
|
+
"couldn't",
|
286
|
+
"course",
|
287
|
+
"currently",
|
288
|
+
"definitely",
|
289
|
+
"described",
|
290
|
+
"despite",
|
291
|
+
"did",
|
292
|
+
"didn't",
|
293
|
+
"different",
|
294
|
+
"do",
|
295
|
+
"does",
|
296
|
+
"doesn't",
|
297
|
+
"doing",
|
298
|
+
"don't",
|
299
|
+
"done",
|
300
|
+
"down",
|
301
|
+
"downwards",
|
302
|
+
"during",
|
303
|
+
"each",
|
304
|
+
"edu",
|
305
|
+
"eg",
|
306
|
+
"eight",
|
307
|
+
"either",
|
308
|
+
"else",
|
309
|
+
"elsewhere",
|
310
|
+
"enough",
|
311
|
+
"entirely",
|
312
|
+
"especially",
|
313
|
+
"et",
|
314
|
+
"etc",
|
315
|
+
"even",
|
316
|
+
"ever",
|
317
|
+
"every",
|
318
|
+
"everybody",
|
319
|
+
"everyone",
|
320
|
+
"everything",
|
321
|
+
"everywhere",
|
322
|
+
"ex",
|
323
|
+
"exactly",
|
324
|
+
"example",
|
325
|
+
"except",
|
326
|
+
"far",
|
327
|
+
"few",
|
328
|
+
"fifth",
|
329
|
+
"first",
|
330
|
+
"five",
|
331
|
+
"followed",
|
332
|
+
"following",
|
333
|
+
"follows",
|
334
|
+
"for",
|
335
|
+
"former",
|
336
|
+
"formerly",
|
337
|
+
"forth",
|
338
|
+
"four",
|
339
|
+
"from",
|
340
|
+
"further",
|
341
|
+
"furthermore",
|
342
|
+
"get",
|
343
|
+
"gets",
|
344
|
+
"getting",
|
345
|
+
"given",
|
346
|
+
"gives",
|
347
|
+
"go",
|
348
|
+
"goes",
|
349
|
+
"going",
|
350
|
+
"gone",
|
351
|
+
"got",
|
352
|
+
"gotten",
|
353
|
+
"greetings",
|
354
|
+
"had",
|
355
|
+
"hadn't",
|
356
|
+
"happens",
|
357
|
+
"hardly",
|
358
|
+
"has",
|
359
|
+
"hasn't",
|
360
|
+
"have",
|
361
|
+
"haven't",
|
362
|
+
"having",
|
363
|
+
"he",
|
364
|
+
"he's",
|
365
|
+
"hello",
|
366
|
+
"help",
|
367
|
+
"hence",
|
368
|
+
"her",
|
369
|
+
"here",
|
370
|
+
"here's",
|
371
|
+
"hereafter",
|
372
|
+
"hereby",
|
373
|
+
"herein",
|
374
|
+
"hereupon",
|
375
|
+
"hers",
|
376
|
+
"herself",
|
377
|
+
"hi",
|
378
|
+
"him",
|
379
|
+
"himself",
|
380
|
+
"his",
|
381
|
+
"hither",
|
382
|
+
"hopefully",
|
383
|
+
"how",
|
384
|
+
"howbeit",
|
385
|
+
"however",
|
386
|
+
"i'd",
|
387
|
+
"i'll",
|
388
|
+
"i'm",
|
389
|
+
"i've",
|
390
|
+
"ie",
|
391
|
+
"if",
|
392
|
+
"ignored",
|
393
|
+
"immediate",
|
394
|
+
"in",
|
395
|
+
"inasmuch",
|
396
|
+
"inc",
|
397
|
+
"indeed",
|
398
|
+
"indicate",
|
399
|
+
"indicated",
|
400
|
+
"indicates",
|
401
|
+
"inner",
|
402
|
+
"insofar",
|
403
|
+
"instead",
|
404
|
+
"into",
|
405
|
+
"inward",
|
406
|
+
"is",
|
407
|
+
"isn't",
|
408
|
+
"it",
|
409
|
+
"it'd",
|
410
|
+
"it'll",
|
411
|
+
"it's",
|
412
|
+
"its",
|
413
|
+
"itself",
|
414
|
+
"just",
|
415
|
+
"keep",
|
416
|
+
"keeps",
|
417
|
+
"kept",
|
418
|
+
"know",
|
419
|
+
"known",
|
420
|
+
"knows",
|
421
|
+
"last",
|
422
|
+
"lately",
|
423
|
+
"later",
|
424
|
+
"latter",
|
425
|
+
"latterly",
|
426
|
+
"least",
|
427
|
+
"less",
|
428
|
+
"lest",
|
429
|
+
"let",
|
430
|
+
"let's",
|
431
|
+
"like",
|
432
|
+
"liked",
|
433
|
+
"likely",
|
434
|
+
"little",
|
435
|
+
"look",
|
436
|
+
"looking",
|
437
|
+
"looks",
|
438
|
+
"ltd",
|
439
|
+
"mainly",
|
440
|
+
"many",
|
441
|
+
"may",
|
442
|
+
"maybe",
|
443
|
+
"me",
|
444
|
+
"mean",
|
445
|
+
"meanwhile",
|
446
|
+
"merely",
|
447
|
+
"might",
|
448
|
+
"more",
|
449
|
+
"moreover",
|
450
|
+
"most",
|
451
|
+
"mostly",
|
452
|
+
"much",
|
453
|
+
"must",
|
454
|
+
"my",
|
455
|
+
"myself",
|
456
|
+
"name",
|
457
|
+
"namely",
|
458
|
+
"nd",
|
459
|
+
"near",
|
460
|
+
"nearly",
|
461
|
+
"necessary",
|
462
|
+
"need",
|
463
|
+
"needs",
|
464
|
+
"neither",
|
465
|
+
"never",
|
466
|
+
"nevertheless",
|
467
|
+
"new",
|
468
|
+
"next",
|
469
|
+
"nine",
|
470
|
+
"no",
|
471
|
+
"nobody",
|
472
|
+
"non",
|
473
|
+
"none",
|
474
|
+
"noone",
|
475
|
+
"nor",
|
476
|
+
"normally",
|
477
|
+
"not",
|
478
|
+
"nothing",
|
479
|
+
"novel",
|
480
|
+
"now",
|
481
|
+
"nowhere",
|
482
|
+
"obviously",
|
483
|
+
"of",
|
484
|
+
"off",
|
485
|
+
"often",
|
486
|
+
"oh",
|
487
|
+
"ok",
|
488
|
+
"okay",
|
489
|
+
"old",
|
490
|
+
"on",
|
491
|
+
"once",
|
492
|
+
"one",
|
493
|
+
"ones",
|
494
|
+
"only",
|
495
|
+
"onto",
|
496
|
+
"or",
|
497
|
+
"other",
|
498
|
+
"others",
|
499
|
+
"otherwise",
|
500
|
+
"ought",
|
501
|
+
"our",
|
502
|
+
"ours",
|
503
|
+
"ourselves",
|
504
|
+
"out",
|
505
|
+
"outside",
|
506
|
+
"over",
|
507
|
+
"overall",
|
508
|
+
"own",
|
509
|
+
"particular",
|
510
|
+
"particularly",
|
511
|
+
"per",
|
512
|
+
"perhaps",
|
513
|
+
"placed",
|
514
|
+
"please",
|
515
|
+
"plus",
|
516
|
+
"possible",
|
517
|
+
"presumably",
|
518
|
+
"probably",
|
519
|
+
"provides",
|
520
|
+
"que",
|
521
|
+
"quite",
|
522
|
+
"qv",
|
523
|
+
"rather",
|
524
|
+
"rd",
|
525
|
+
"re",
|
526
|
+
"really",
|
527
|
+
"reasonably",
|
528
|
+
"regarding",
|
529
|
+
"regardless",
|
530
|
+
"regards",
|
531
|
+
"relatively",
|
532
|
+
"respectively",
|
533
|
+
"right",
|
534
|
+
"said",
|
535
|
+
"same",
|
536
|
+
"saw",
|
537
|
+
"say",
|
538
|
+
"saying",
|
539
|
+
"says",
|
540
|
+
"second",
|
541
|
+
"secondly",
|
542
|
+
"see",
|
543
|
+
"seeing",
|
544
|
+
"seem",
|
545
|
+
"seemed",
|
546
|
+
"seeming",
|
547
|
+
"seems",
|
548
|
+
"seen",
|
549
|
+
"self",
|
550
|
+
"selves",
|
551
|
+
"sensible",
|
552
|
+
"sent",
|
553
|
+
"serious",
|
554
|
+
"seriously",
|
555
|
+
"seven",
|
556
|
+
"several",
|
557
|
+
"shall",
|
558
|
+
"she",
|
559
|
+
"should",
|
560
|
+
"shouldn't",
|
561
|
+
"since",
|
562
|
+
"six",
|
563
|
+
"so",
|
564
|
+
"some",
|
565
|
+
"somebody",
|
566
|
+
"somehow",
|
567
|
+
"someone",
|
568
|
+
"something",
|
569
|
+
"sometime",
|
570
|
+
"sometimes",
|
571
|
+
"somewhat",
|
572
|
+
"somewhere",
|
573
|
+
"soon",
|
574
|
+
"sorry",
|
575
|
+
"specified",
|
576
|
+
"specify",
|
577
|
+
"specifying",
|
578
|
+
"still",
|
579
|
+
"sub",
|
580
|
+
"such",
|
581
|
+
"sup",
|
582
|
+
"sure",
|
583
|
+
"t's",
|
584
|
+
"take",
|
585
|
+
"taken",
|
586
|
+
"tell",
|
587
|
+
"tends",
|
588
|
+
"th",
|
589
|
+
"than",
|
590
|
+
"thank",
|
591
|
+
"thanks",
|
592
|
+
"thanx",
|
593
|
+
"that",
|
594
|
+
"that's",
|
595
|
+
"thats",
|
596
|
+
"the",
|
597
|
+
"their",
|
598
|
+
"theirs",
|
599
|
+
"them",
|
600
|
+
"themselves",
|
601
|
+
"then",
|
602
|
+
"thence",
|
603
|
+
"there",
|
604
|
+
"there's",
|
605
|
+
"thereafter",
|
606
|
+
"thereby",
|
607
|
+
"therefore",
|
608
|
+
"therein",
|
609
|
+
"theres",
|
610
|
+
"thereupon",
|
611
|
+
"these",
|
612
|
+
"they",
|
613
|
+
"they'd",
|
614
|
+
"they'll",
|
615
|
+
"they're",
|
616
|
+
"they've",
|
617
|
+
"think",
|
618
|
+
"third",
|
619
|
+
"this",
|
620
|
+
"thorough",
|
621
|
+
"thoroughly",
|
622
|
+
"those",
|
623
|
+
"though",
|
624
|
+
"three",
|
625
|
+
"through",
|
626
|
+
"throughout",
|
627
|
+
"thru",
|
628
|
+
"thus",
|
629
|
+
"to",
|
630
|
+
"together",
|
631
|
+
"too",
|
632
|
+
"took",
|
633
|
+
"toward",
|
634
|
+
"towards",
|
635
|
+
"tried",
|
636
|
+
"tries",
|
637
|
+
"truly",
|
638
|
+
"try",
|
639
|
+
"trying",
|
640
|
+
"twice",
|
641
|
+
"two",
|
642
|
+
"un",
|
643
|
+
"under",
|
644
|
+
"unfortunately",
|
645
|
+
"unless",
|
646
|
+
"unlikely",
|
647
|
+
"until",
|
648
|
+
"unto",
|
649
|
+
"up",
|
650
|
+
"upon",
|
651
|
+
"us",
|
652
|
+
"use",
|
653
|
+
"used",
|
654
|
+
"useful",
|
655
|
+
"uses",
|
656
|
+
"using",
|
657
|
+
"usually",
|
658
|
+
"value",
|
659
|
+
"various",
|
660
|
+
"very",
|
661
|
+
"via",
|
662
|
+
"viz",
|
663
|
+
"vs",
|
664
|
+
"want",
|
665
|
+
"wants",
|
666
|
+
"was",
|
667
|
+
"wasn't",
|
668
|
+
"way",
|
669
|
+
"we",
|
670
|
+
"we'd",
|
671
|
+
"we'll",
|
672
|
+
"we're",
|
673
|
+
"we've",
|
674
|
+
"welcome",
|
675
|
+
"well",
|
676
|
+
"went",
|
677
|
+
"were",
|
678
|
+
"weren't",
|
679
|
+
"what",
|
680
|
+
"what's",
|
681
|
+
"whatever",
|
682
|
+
"when",
|
683
|
+
"whence",
|
684
|
+
"whenever",
|
685
|
+
"where",
|
686
|
+
"where's",
|
687
|
+
"whereafter",
|
688
|
+
"whereas",
|
689
|
+
"whereby",
|
690
|
+
"wherein",
|
691
|
+
"whereupon",
|
692
|
+
"wherever",
|
693
|
+
"whether",
|
694
|
+
"which",
|
695
|
+
"while",
|
696
|
+
"whither",
|
697
|
+
"who",
|
698
|
+
"who's",
|
699
|
+
"whoever",
|
700
|
+
"whole",
|
701
|
+
"whom",
|
702
|
+
"whose",
|
703
|
+
"why",
|
704
|
+
"will",
|
705
|
+
"willing",
|
706
|
+
"wish",
|
707
|
+
"with",
|
708
|
+
"within",
|
709
|
+
"without",
|
710
|
+
"won't",
|
711
|
+
"wonder",
|
712
|
+
"would",
|
713
|
+
"wouldn't",
|
714
|
+
"yes",
|
715
|
+
"yet",
|
716
|
+
"you",
|
717
|
+
"you'd",
|
718
|
+
"you'll",
|
719
|
+
"you're",
|
720
|
+
"you've",
|
721
|
+
"your",
|
722
|
+
"yours",
|
723
|
+
"yourself",
|
724
|
+
"yourselves",
|
725
|
+
"zero"]
|
726
|
+
end
|
727
|
+
|
728
|
+
def self.long
|
729
|
+
["a",
|
730
|
+
"able",
|
731
|
+
"about",
|
732
|
+
"above",
|
733
|
+
"abst",
|
734
|
+
"accordance",
|
735
|
+
"according",
|
736
|
+
"accordingly",
|
737
|
+
"across",
|
738
|
+
"act",
|
739
|
+
"actually",
|
740
|
+
"added",
|
741
|
+
"adj",
|
742
|
+
"affected",
|
743
|
+
"affecting",
|
744
|
+
"affects",
|
745
|
+
"after",
|
746
|
+
"afterwards",
|
747
|
+
"again",
|
748
|
+
"against",
|
749
|
+
"ah",
|
750
|
+
"all",
|
751
|
+
"almost",
|
752
|
+
"alone",
|
753
|
+
"along",
|
754
|
+
"already",
|
755
|
+
"also",
|
756
|
+
"although",
|
757
|
+
"always",
|
758
|
+
"am",
|
759
|
+
"among",
|
760
|
+
"amongst",
|
761
|
+
"an",
|
762
|
+
"and",
|
763
|
+
"announce",
|
764
|
+
"another",
|
765
|
+
"any",
|
766
|
+
"anybody",
|
767
|
+
"anyhow",
|
768
|
+
"anymore",
|
769
|
+
"anyone",
|
770
|
+
"anything",
|
771
|
+
"anyway",
|
772
|
+
"anyways",
|
773
|
+
"anywhere",
|
774
|
+
"apparently",
|
775
|
+
"approximately",
|
776
|
+
"are",
|
777
|
+
"aren",
|
778
|
+
"arent",
|
779
|
+
"arise",
|
780
|
+
"around",
|
781
|
+
"as",
|
782
|
+
"aside",
|
783
|
+
"ask",
|
784
|
+
"asking",
|
785
|
+
"at",
|
786
|
+
"auth",
|
787
|
+
"available",
|
788
|
+
"away",
|
789
|
+
"awfully",
|
790
|
+
"b",
|
791
|
+
"back",
|
792
|
+
"be",
|
793
|
+
"became",
|
794
|
+
"because",
|
795
|
+
"become",
|
796
|
+
"becomes",
|
797
|
+
"becoming",
|
798
|
+
"been",
|
799
|
+
"before",
|
800
|
+
"beforehand",
|
801
|
+
"begin",
|
802
|
+
"beginning",
|
803
|
+
"beginnings",
|
804
|
+
"begins",
|
805
|
+
"behind",
|
806
|
+
"being",
|
807
|
+
"believe",
|
808
|
+
"below",
|
809
|
+
"beside",
|
810
|
+
"besides",
|
811
|
+
"between",
|
812
|
+
"beyond",
|
813
|
+
"biol",
|
814
|
+
"both",
|
815
|
+
"brief",
|
816
|
+
"briefly",
|
817
|
+
"but",
|
818
|
+
"by",
|
819
|
+
"c",
|
820
|
+
"ca",
|
821
|
+
"came",
|
822
|
+
"can",
|
823
|
+
"cannot",
|
824
|
+
"can't",
|
825
|
+
"cause",
|
826
|
+
"causes",
|
827
|
+
"certain",
|
828
|
+
"certainly",
|
829
|
+
"co",
|
830
|
+
"com",
|
831
|
+
"come",
|
832
|
+
"comes",
|
833
|
+
"contain",
|
834
|
+
"containing",
|
835
|
+
"contains",
|
836
|
+
"could",
|
837
|
+
"couldnt",
|
838
|
+
"d",
|
839
|
+
"date",
|
840
|
+
"did",
|
841
|
+
"didn't",
|
842
|
+
"different",
|
843
|
+
"do",
|
844
|
+
"does",
|
845
|
+
"doesn't",
|
846
|
+
"doing",
|
847
|
+
"done",
|
848
|
+
"don't",
|
849
|
+
"down",
|
850
|
+
"downwards",
|
851
|
+
"due",
|
852
|
+
"during",
|
853
|
+
"e",
|
854
|
+
"each",
|
855
|
+
"ed",
|
856
|
+
"edu",
|
857
|
+
"effect",
|
858
|
+
"eg",
|
859
|
+
"eight",
|
860
|
+
"eighty",
|
861
|
+
"either",
|
862
|
+
"else",
|
863
|
+
"elsewhere",
|
864
|
+
"end",
|
865
|
+
"ending",
|
866
|
+
"enough",
|
867
|
+
"especially",
|
868
|
+
"et",
|
869
|
+
"et-al",
|
870
|
+
"etc",
|
871
|
+
"even",
|
872
|
+
"ever",
|
873
|
+
"every",
|
874
|
+
"everybody",
|
875
|
+
"everyone",
|
876
|
+
"everything",
|
877
|
+
"everywhere",
|
878
|
+
"ex",
|
879
|
+
"except",
|
880
|
+
"f",
|
881
|
+
"far",
|
882
|
+
"few",
|
883
|
+
"ff",
|
884
|
+
"fifth",
|
885
|
+
"first",
|
886
|
+
"five",
|
887
|
+
"fix",
|
888
|
+
"followed",
|
889
|
+
"following",
|
890
|
+
"follows",
|
891
|
+
"for",
|
892
|
+
"former",
|
893
|
+
"formerly",
|
894
|
+
"forth",
|
895
|
+
"found",
|
896
|
+
"four",
|
897
|
+
"from",
|
898
|
+
"further",
|
899
|
+
"furthermore",
|
900
|
+
"g",
|
901
|
+
"gave",
|
902
|
+
"get",
|
903
|
+
"gets",
|
904
|
+
"getting",
|
905
|
+
"give",
|
906
|
+
"given",
|
907
|
+
"gives",
|
908
|
+
"giving",
|
909
|
+
"go",
|
910
|
+
"goes",
|
911
|
+
"gone",
|
912
|
+
"got",
|
913
|
+
"gotten",
|
914
|
+
"h",
|
915
|
+
"had",
|
916
|
+
"happens",
|
917
|
+
"hardly",
|
918
|
+
"has",
|
919
|
+
"hasn't",
|
920
|
+
"have",
|
921
|
+
"haven't",
|
922
|
+
"having",
|
923
|
+
"he",
|
924
|
+
"hed",
|
925
|
+
"hence",
|
926
|
+
"her",
|
927
|
+
"here",
|
928
|
+
"hereafter",
|
929
|
+
"hereby",
|
930
|
+
"herein",
|
931
|
+
"heres",
|
932
|
+
"hereupon",
|
933
|
+
"hers",
|
934
|
+
"herself",
|
935
|
+
"hes",
|
936
|
+
"hi",
|
937
|
+
"hid",
|
938
|
+
"him",
|
939
|
+
"himself",
|
940
|
+
"his",
|
941
|
+
"hither",
|
942
|
+
"home",
|
943
|
+
"how",
|
944
|
+
"howbeit",
|
945
|
+
"however",
|
946
|
+
"hundred",
|
947
|
+
"i",
|
948
|
+
"id",
|
949
|
+
"ie",
|
950
|
+
"if",
|
951
|
+
"i'll",
|
952
|
+
"im",
|
953
|
+
"immediate",
|
954
|
+
"immediately",
|
955
|
+
"importance",
|
956
|
+
"important",
|
957
|
+
"in",
|
958
|
+
"inc",
|
959
|
+
"indeed",
|
960
|
+
"index",
|
961
|
+
"information",
|
962
|
+
"instead",
|
963
|
+
"into",
|
964
|
+
"invention",
|
965
|
+
"inward",
|
966
|
+
"is",
|
967
|
+
"isn't",
|
968
|
+
"it",
|
969
|
+
"itd",
|
970
|
+
"it'll",
|
971
|
+
"its",
|
972
|
+
"itself",
|
973
|
+
"i've",
|
974
|
+
"j",
|
975
|
+
"just",
|
976
|
+
"k",
|
977
|
+
"keep keeps",
|
978
|
+
"kept",
|
979
|
+
"kg",
|
980
|
+
"km",
|
981
|
+
"know",
|
982
|
+
"known",
|
983
|
+
"knows",
|
984
|
+
"l",
|
985
|
+
"largely",
|
986
|
+
"last",
|
987
|
+
"lately",
|
988
|
+
"later",
|
989
|
+
"latter",
|
990
|
+
"latterly",
|
991
|
+
"least",
|
992
|
+
"less",
|
993
|
+
"lest",
|
994
|
+
"let",
|
995
|
+
"lets",
|
996
|
+
"like",
|
997
|
+
"liked",
|
998
|
+
"likely",
|
999
|
+
"line",
|
1000
|
+
"little",
|
1001
|
+
"'ll",
|
1002
|
+
"look",
|
1003
|
+
"looking",
|
1004
|
+
"looks",
|
1005
|
+
"ltd",
|
1006
|
+
"m",
|
1007
|
+
"made",
|
1008
|
+
"mainly",
|
1009
|
+
"make",
|
1010
|
+
"makes",
|
1011
|
+
"many",
|
1012
|
+
"may",
|
1013
|
+
"maybe",
|
1014
|
+
"me",
|
1015
|
+
"mean",
|
1016
|
+
"means",
|
1017
|
+
"meantime",
|
1018
|
+
"meanwhile",
|
1019
|
+
"merely",
|
1020
|
+
"mg",
|
1021
|
+
"might",
|
1022
|
+
"million",
|
1023
|
+
"miss",
|
1024
|
+
"ml",
|
1025
|
+
"more",
|
1026
|
+
"moreover",
|
1027
|
+
"most",
|
1028
|
+
"mostly",
|
1029
|
+
"mr",
|
1030
|
+
"mrs",
|
1031
|
+
"much",
|
1032
|
+
"mug",
|
1033
|
+
"must",
|
1034
|
+
"my",
|
1035
|
+
"myself",
|
1036
|
+
"n",
|
1037
|
+
"na",
|
1038
|
+
"name",
|
1039
|
+
"namely",
|
1040
|
+
"nay",
|
1041
|
+
"nd",
|
1042
|
+
"near",
|
1043
|
+
"nearly",
|
1044
|
+
"necessarily",
|
1045
|
+
"necessary",
|
1046
|
+
"need",
|
1047
|
+
"needs",
|
1048
|
+
"neither",
|
1049
|
+
"never",
|
1050
|
+
"nevertheless",
|
1051
|
+
"new",
|
1052
|
+
"next",
|
1053
|
+
"nine",
|
1054
|
+
"ninety",
|
1055
|
+
"no",
|
1056
|
+
"nobody",
|
1057
|
+
"non",
|
1058
|
+
"none",
|
1059
|
+
"nonetheless",
|
1060
|
+
"noone",
|
1061
|
+
"nor",
|
1062
|
+
"normally",
|
1063
|
+
"nos",
|
1064
|
+
"not",
|
1065
|
+
"noted",
|
1066
|
+
"nothing",
|
1067
|
+
"now",
|
1068
|
+
"nowhere",
|
1069
|
+
"o",
|
1070
|
+
"obtain",
|
1071
|
+
"obtained",
|
1072
|
+
"obviously",
|
1073
|
+
"of",
|
1074
|
+
"off",
|
1075
|
+
"often",
|
1076
|
+
"oh",
|
1077
|
+
"ok",
|
1078
|
+
"okay",
|
1079
|
+
"old",
|
1080
|
+
"omitted",
|
1081
|
+
"on",
|
1082
|
+
"once",
|
1083
|
+
"one",
|
1084
|
+
"ones",
|
1085
|
+
"only",
|
1086
|
+
"onto",
|
1087
|
+
"or",
|
1088
|
+
"ord",
|
1089
|
+
"other",
|
1090
|
+
"others",
|
1091
|
+
"otherwise",
|
1092
|
+
"ought",
|
1093
|
+
"our",
|
1094
|
+
"ours",
|
1095
|
+
"ourselves",
|
1096
|
+
"out",
|
1097
|
+
"outside",
|
1098
|
+
"over",
|
1099
|
+
"overall",
|
1100
|
+
"owing",
|
1101
|
+
"own",
|
1102
|
+
"p",
|
1103
|
+
"page",
|
1104
|
+
"pages",
|
1105
|
+
"part",
|
1106
|
+
"particular",
|
1107
|
+
"particularly",
|
1108
|
+
"past",
|
1109
|
+
"per",
|
1110
|
+
"perhaps",
|
1111
|
+
"placed",
|
1112
|
+
"please",
|
1113
|
+
"plus",
|
1114
|
+
"poorly",
|
1115
|
+
"possible",
|
1116
|
+
"possibly",
|
1117
|
+
"potentially",
|
1118
|
+
"pp",
|
1119
|
+
"predominantly",
|
1120
|
+
"present",
|
1121
|
+
"previously",
|
1122
|
+
"primarily",
|
1123
|
+
"probably",
|
1124
|
+
"promptly",
|
1125
|
+
"proud",
|
1126
|
+
"provides",
|
1127
|
+
"put",
|
1128
|
+
"q",
|
1129
|
+
"que",
|
1130
|
+
"quickly",
|
1131
|
+
"quite",
|
1132
|
+
"qv",
|
1133
|
+
"r",
|
1134
|
+
"ran",
|
1135
|
+
"rather",
|
1136
|
+
"rd",
|
1137
|
+
"re",
|
1138
|
+
"readily",
|
1139
|
+
"really",
|
1140
|
+
"recent",
|
1141
|
+
"recently",
|
1142
|
+
"ref",
|
1143
|
+
"refs",
|
1144
|
+
"regarding",
|
1145
|
+
"regardless",
|
1146
|
+
"regards",
|
1147
|
+
"related",
|
1148
|
+
"relatively",
|
1149
|
+
"research",
|
1150
|
+
"respectively",
|
1151
|
+
"resulted",
|
1152
|
+
"resulting",
|
1153
|
+
"results",
|
1154
|
+
"right",
|
1155
|
+
"run",
|
1156
|
+
"s",
|
1157
|
+
"said",
|
1158
|
+
"same",
|
1159
|
+
"saw",
|
1160
|
+
"say",
|
1161
|
+
"saying",
|
1162
|
+
"says",
|
1163
|
+
"sec",
|
1164
|
+
"section",
|
1165
|
+
"see",
|
1166
|
+
"seeing",
|
1167
|
+
"seem",
|
1168
|
+
"seemed",
|
1169
|
+
"seeming",
|
1170
|
+
"seems",
|
1171
|
+
"seen",
|
1172
|
+
"self",
|
1173
|
+
"selves",
|
1174
|
+
"sent",
|
1175
|
+
"seven",
|
1176
|
+
"several",
|
1177
|
+
"shall",
|
1178
|
+
"she",
|
1179
|
+
"shed",
|
1180
|
+
"she'll",
|
1181
|
+
"shes",
|
1182
|
+
"should",
|
1183
|
+
"shouldn't",
|
1184
|
+
"show",
|
1185
|
+
"showed",
|
1186
|
+
"shown",
|
1187
|
+
"showns",
|
1188
|
+
"shows",
|
1189
|
+
"significant",
|
1190
|
+
"significantly",
|
1191
|
+
"similar",
|
1192
|
+
"similarly",
|
1193
|
+
"since",
|
1194
|
+
"six",
|
1195
|
+
"slightly",
|
1196
|
+
"so",
|
1197
|
+
"some",
|
1198
|
+
"somebody",
|
1199
|
+
"somehow",
|
1200
|
+
"someone",
|
1201
|
+
"somethan",
|
1202
|
+
"something",
|
1203
|
+
"sometime",
|
1204
|
+
"sometimes",
|
1205
|
+
"somewhat",
|
1206
|
+
"somewhere",
|
1207
|
+
"soon",
|
1208
|
+
"sorry",
|
1209
|
+
"specifically",
|
1210
|
+
"specified",
|
1211
|
+
"specify",
|
1212
|
+
"specifying",
|
1213
|
+
"still",
|
1214
|
+
"stop",
|
1215
|
+
"strongly",
|
1216
|
+
"sub",
|
1217
|
+
"substantially",
|
1218
|
+
"successfully",
|
1219
|
+
"such",
|
1220
|
+
"sufficiently",
|
1221
|
+
"suggest",
|
1222
|
+
"sup",
|
1223
|
+
"sure"]
|
1224
|
+
end
|
1225
|
+
end
|
1226
|
+
end
|