keyphrase 0.1.3 → 0.2.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (75) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +5 -4
  3. data/lib/keyphrase/stoplist/afr.rb +14 -0
  4. data/lib/keyphrase/stoplist/aka.rb +10 -0
  5. data/lib/keyphrase/stoplist/amh.rb +10 -0
  6. data/lib/keyphrase/stoplist/ara.rb +490 -0
  7. data/lib/keyphrase/stoplist/aze.rb +175 -0
  8. data/lib/keyphrase/stoplist/bel.rb +11 -0
  9. data/lib/keyphrase/stoplist/ben.rb +408 -0
  10. data/lib/keyphrase/stoplist/bul.rb +528 -0
  11. data/lib/keyphrase/stoplist/cat.rb +711 -0
  12. data/lib/keyphrase/stoplist/ces.rb +560 -0
  13. data/lib/keyphrase/stoplist/cmn.rb +1119 -0
  14. data/lib/keyphrase/stoplist/dan.rb +25 -0
  15. data/lib/keyphrase/stoplist/deu.rb +631 -0
  16. data/lib/keyphrase/stoplist/ell.rb +275 -0
  17. data/lib/keyphrase/stoplist/eng.rb +2 -589
  18. data/lib/keyphrase/stoplist/epo.rb +183 -0
  19. data/lib/keyphrase/stoplist/est.rb +13 -0
  20. data/lib/keyphrase/stoplist/fin.rb +857 -0
  21. data/lib/keyphrase/stoplist/fra.rb +699 -0
  22. data/lib/keyphrase/stoplist/guj.rb +234 -0
  23. data/lib/keyphrase/stoplist/heb.rb +204 -0
  24. data/lib/keyphrase/stoplist/hin.rb +235 -0
  25. data/lib/keyphrase/stoplist/hrv.rb +25 -0
  26. data/lib/keyphrase/stoplist/hun.rb +1195 -0
  27. data/lib/keyphrase/stoplist/hye.rb +55 -0
  28. data/lib/keyphrase/stoplist/ind.rb +768 -0
  29. data/lib/keyphrase/stoplist/ita.rb +670 -0
  30. data/lib/keyphrase/stoplist/jav.rb +10 -0
  31. data/lib/keyphrase/stoplist/jpn.rb +144 -0
  32. data/lib/keyphrase/stoplist/kan.rb +92 -0
  33. data/lib/keyphrase/stoplist/kat.rb +383 -0
  34. data/lib/keyphrase/stoplist/khm.rb +245 -0
  35. data/lib/keyphrase/stoplist/kor.rb +610 -0
  36. data/lib/keyphrase/stoplist/lat.rb +14 -0
  37. data/lib/keyphrase/stoplist/lav.rb +171 -0
  38. data/lib/keyphrase/stoplist/lit.rb +484 -0
  39. data/lib/keyphrase/stoplist/mal.rb +11 -0
  40. data/lib/keyphrase/stoplist/mar.rb +109 -0
  41. data/lib/keyphrase/stoplist/mkd.rb +11 -0
  42. data/lib/keyphrase/stoplist/mya.rb +285 -0
  43. data/lib/keyphrase/stoplist/nep.rb +265 -0
  44. data/lib/keyphrase/stoplist/nld.rb +423 -0
  45. data/lib/keyphrase/stoplist/nob.rb +186 -0
  46. data/lib/keyphrase/stoplist/ori.rb +11 -0
  47. data/lib/keyphrase/stoplist/pan.rb +473 -0
  48. data/lib/keyphrase/stoplist/pes.rb +801 -0
  49. data/lib/keyphrase/stoplist/pol.rb +338 -0
  50. data/lib/keyphrase/stoplist/por.rb +570 -0
  51. data/lib/keyphrase/stoplist/ron.rb +444 -0
  52. data/lib/keyphrase/stoplist/rus.rb +569 -0
  53. data/lib/keyphrase/stoplist/sin.rb +10 -0
  54. data/lib/keyphrase/stoplist/slk.rb +428 -0
  55. data/lib/keyphrase/stoplist/slv.rb +456 -0
  56. data/lib/keyphrase/stoplist/sna.rb +11 -0
  57. data/lib/keyphrase/stoplist/spa.rb +731 -0
  58. data/lib/keyphrase/stoplist/srp.rb +11 -0
  59. data/lib/keyphrase/stoplist/swe.rb +428 -0
  60. data/lib/keyphrase/stoplist/tam.rb +135 -0
  61. data/lib/keyphrase/stoplist/tel.rb +10 -0
  62. data/lib/keyphrase/stoplist/tgl.rb +157 -0
  63. data/lib/keyphrase/stoplist/tha.rb +125 -0
  64. data/lib/keyphrase/stoplist/tuk.rb +11 -0
  65. data/lib/keyphrase/stoplist/tur.rb +514 -0
  66. data/lib/keyphrase/stoplist/ukr.rb +38 -0
  67. data/lib/keyphrase/stoplist/urd.rb +527 -0
  68. data/lib/keyphrase/stoplist/uzb.rb +10 -0
  69. data/lib/keyphrase/stoplist/vie.rb +655 -0
  70. data/lib/keyphrase/stoplist/yid.rb +204 -0
  71. data/lib/keyphrase/stoplist/zul.rb +39 -0
  72. data/lib/keyphrase/stoplist.rb +13 -10
  73. data/lib/keyphrase/version.rb +1 -1
  74. data/lib/keyphrase.rb +20 -12
  75. metadata +71 -3
@@ -0,0 +1,175 @@
1
+ class Keyphrase
2
+ module Stoplist
3
+ class Aze
4
+ def self.stopwords
5
+ @@stopwords ||= [
6
+ "a",
7
+ "ad",
8
+ "altı",
9
+ "altmış",
10
+ "amma",
11
+ "arasında",
12
+ "artıq",
13
+ "ay",
14
+ "az",
15
+ "bax",
16
+ "belə",
17
+ "bəli",
18
+ "bəlkə",
19
+ "beş",
20
+ "bəy",
21
+ "bəzən",
22
+ "bəzi",
23
+ "bilər",
24
+ "bir",
25
+ "biraz",
26
+ "biri",
27
+ "birşey",
28
+ "biz",
29
+ "bizim",
30
+ "bizlər",
31
+ "bu",
32
+ "buna",
33
+ "bundan",
34
+ "bunların",
35
+ "bunu",
36
+ "bunun",
37
+ "buradan",
38
+ "bütün",
39
+ "ci",
40
+ "cı",
41
+ "çox",
42
+ "cu",
43
+ "cü",
44
+ "çünki",
45
+ "da",
46
+ "daha",
47
+ "də",
48
+ "dedi",
49
+ "dək",
50
+ "dən",
51
+ "dəqiqə",
52
+ "deyil",
53
+ "dir",
54
+ "doqquz",
55
+ "doqsan",
56
+ "dörd",
57
+ "düz",
58
+ "ə",
59
+ "edən",
60
+ "edir",
61
+ "əgər",
62
+ "əlbəttə",
63
+ "elə",
64
+ "əlli",
65
+ "ən",
66
+ "əslində",
67
+ "et",
68
+ "etdi",
69
+ "etmə",
70
+ "etmək",
71
+ "faiz",
72
+ "gilə",
73
+ "görə",
74
+ "ha",
75
+ "haqqında",
76
+ "harada",
77
+ "hə",
78
+ "heç",
79
+ "həm",
80
+ "həmin",
81
+ "həmişə",
82
+ "hər",
83
+ "ı",
84
+ "idi",
85
+ "iki",
86
+ "il",
87
+ "ildə",
88
+ "ilə",
89
+ "ilk",
90
+ "in",
91
+ "indi",
92
+ "isə",
93
+ "istifadə",
94
+ "iyirmi",
95
+ "ki",
96
+ "kim",
97
+ "kimə",
98
+ "kimi",
99
+ "lakin",
100
+ "lap",
101
+ "məhz",
102
+ "mən",
103
+ "mənə",
104
+ "mirşey",
105
+ "nə",
106
+ "nəhayət",
107
+ "niyə",
108
+ "o",
109
+ "obirisi",
110
+ "of",
111
+ "olan",
112
+ "olar",
113
+ "olaraq",
114
+ "oldu",
115
+ "olduğu",
116
+ "olmadı",
117
+ "olmaz",
118
+ "olmuşdur",
119
+ "olsun",
120
+ "olur",
121
+ "on",
122
+ "ona",
123
+ "ondan",
124
+ "onlar",
125
+ "onlardan",
126
+ "onların ",
127
+ "onsuzda",
128
+ "onu",
129
+ "onun",
130
+ "oradan",
131
+ "otuz",
132
+ "öz",
133
+ "özü",
134
+ "qarşı",
135
+ "qədər",
136
+ "qırx",
137
+ "saat",
138
+ "sadəcə",
139
+ "saniyə",
140
+ "səhv",
141
+ "səkkiz",
142
+ "səksən",
143
+ "sən",
144
+ "sənə",
145
+ "sənin",
146
+ "siz",
147
+ "sizin",
148
+ "sizlər",
149
+ "sonra",
150
+ "təəssüf",
151
+ "ü",
152
+ "üç",
153
+ "üçün",
154
+ "var",
155
+ "və",
156
+ "xan",
157
+ "xanım",
158
+ "xeyr",
159
+ "ya",
160
+ "yalnız",
161
+ "yaxşı",
162
+ "yeddi",
163
+ "yenə",
164
+ "yəni",
165
+ "yetmiş",
166
+ "yox",
167
+ "yoxdur",
168
+ "yoxsa",
169
+ "yüz",
170
+ "zaman",
171
+ ]
172
+ end
173
+ end
174
+ end
175
+ end
@@ -0,0 +1,11 @@
1
+ class Keyphrase
2
+ module Stoplist
3
+ class Bel
4
+ def self.stopwords
5
+ @@stopwords ||= [
6
+
7
+ ]
8
+ end
9
+ end
10
+ end
11
+ end
@@ -0,0 +1,408 @@
1
+ class Keyphrase
2
+ module Stoplist
3
+ class Ben
4
+ def self.stopwords
5
+ @@stopwords ||= [
6
+ "অতএব",
7
+ "অথচ",
8
+ "অথবা",
9
+ "অনুযায়ী",
10
+ "অনেক",
11
+ "অনেকে",
12
+ "অনেকেই",
13
+ "অন্তত",
14
+ "অন্য",
15
+ "অবধি",
16
+ "অবশ্য",
17
+ "অর্থাত",
18
+ "আই",
19
+ "আগামী",
20
+ "আগে",
21
+ "আগেই",
22
+ "আছে",
23
+ "আজ",
24
+ "আদ্যভাগে",
25
+ "আপনার",
26
+ "আপনি",
27
+ "আবার",
28
+ "আমরা",
29
+ "আমাকে",
30
+ "আমাদের",
31
+ "আমার",
32
+ "আমি",
33
+ "আর",
34
+ "আরও",
35
+ "ই",
36
+ "ইত্যাদি",
37
+ "ইহা",
38
+ "উচিত",
39
+ "উত্তর",
40
+ "উনি",
41
+ "উপর",
42
+ "উপরে",
43
+ "এ",
44
+ "এঁদের",
45
+ "এঁরা",
46
+ "এই",
47
+ "একই",
48
+ "একটি",
49
+ "একবার",
50
+ "একে",
51
+ "এক্",
52
+ "এখন",
53
+ "এখনও",
54
+ "এখানে",
55
+ "এখানেই",
56
+ "এটা",
57
+ "এটাই",
58
+ "এটি",
59
+ "এত",
60
+ "এতটাই",
61
+ "এতে",
62
+ "এদের",
63
+ "এব",
64
+ "এবং",
65
+ "এবার",
66
+ "এমন",
67
+ "এমনকী",
68
+ "এমনি",
69
+ "এর",
70
+ "এরা",
71
+ "এল",
72
+ "এস",
73
+ "এসে",
74
+ "ঐ",
75
+ "ও",
76
+ "ওঁদের",
77
+ "ওঁর",
78
+ "ওঁরা",
79
+ "ওই",
80
+ "ওকে",
81
+ "ওখানে",
82
+ "ওদের",
83
+ "ওর",
84
+ "ওরা",
85
+ "কখনও",
86
+ "কত",
87
+ "কবে",
88
+ "কমনে",
89
+ "কয়েক",
90
+ "কয়েকটি",
91
+ "করছে",
92
+ "করছেন",
93
+ "করতে",
94
+ "করবে",
95
+ "করবেন",
96
+ "করলে",
97
+ "করলেন",
98
+ "করা",
99
+ "করাই",
100
+ "করায়",
101
+ "করার",
102
+ "করি",
103
+ "করিতে",
104
+ "করিয়া",
105
+ "করিয়ে",
106
+ "করে",
107
+ "করেই",
108
+ "করেছিলেন",
109
+ "করেছে",
110
+ "করেছেন",
111
+ "করেন",
112
+ "কাউকে",
113
+ "কাছ",
114
+ "কাছে",
115
+ "কাজ",
116
+ "কাজে",
117
+ "কারও",
118
+ "কারণ",
119
+ "কি",
120
+ "কিংবা",
121
+ "কিছু",
122
+ "কিছুই",
123
+ "কিন্তু",
124
+ "কী",
125
+ "কে",
126
+ "কেউ",
127
+ "কেউই",
128
+ "কেখা",
129
+ "কেন",
130
+ "কোটি",
131
+ "কোন",
132
+ "কোনও",
133
+ "কোনো",
134
+ "ক্ষেত্রে",
135
+ "কয়েক",
136
+ "খুব",
137
+ "গিয়ে",
138
+ "গিয়েছে",
139
+ "গিয়ে",
140
+ "গুলি",
141
+ "গেছে",
142
+ "গেল",
143
+ "গেলে",
144
+ "গোটা",
145
+ "চলে",
146
+ "চান",
147
+ "চায়",
148
+ "চার",
149
+ "চালু",
150
+ "চেয়ে",
151
+ "চেষ্টা",
152
+ "ছাড়া",
153
+ "ছাড়াও",
154
+ "ছিল",
155
+ "ছিলেন",
156
+ "জন",
157
+ "জনকে",
158
+ "জনের",
159
+ "জন্য",
160
+ "জন্যওজে",
161
+ "জানতে",
162
+ "জানা",
163
+ "জানানো",
164
+ "জানায়",
165
+ "জানিয়ে",
166
+ "জানিয়েছে",
167
+ "জে",
168
+ "জ্নজন",
169
+ "টি",
170
+ "ঠিক",
171
+ "তখন",
172
+ "তত",
173
+ "তথা",
174
+ "তবু",
175
+ "তবে",
176
+ "তা",
177
+ "তাঁকে",
178
+ "তাঁদের",
179
+ "তাঁর",
180
+ "তাঁরা",
181
+ "তাঁাহারা",
182
+ "তাই",
183
+ "তাও",
184
+ "তাকে",
185
+ "তাতে",
186
+ "তাদের",
187
+ "তার",
188
+ "তারপর",
189
+ "তারা",
190
+ "তারৈ",
191
+ "তাহলে",
192
+ "তাহা",
193
+ "তাহাতে",
194
+ "তাহার",
195
+ "তিনঐ",
196
+ "তিনি",
197
+ "তিনিও",
198
+ "তুমি",
199
+ "তুলে",
200
+ "তেমন",
201
+ "তো",
202
+ "তোমার",
203
+ "থাকবে",
204
+ "থাকবেন",
205
+ "থাকা",
206
+ "থাকায়",
207
+ "থাকে",
208
+ "থাকেন",
209
+ "থেকে",
210
+ "থেকেই",
211
+ "থেকেও",
212
+ "দিকে",
213
+ "দিতে",
214
+ "দিন",
215
+ "দিয়ে",
216
+ "দিয়েছে",
217
+ "দিয়েছেন",
218
+ "দিলেন",
219
+ "দু",
220
+ "দুই",
221
+ "দুটি",
222
+ "দুটো",
223
+ "দেওয়া",
224
+ "দেওয়ার",
225
+ "দেওয়া",
226
+ "দেখতে",
227
+ "দেখা",
228
+ "দেখে",
229
+ "দেন",
230
+ "দেয়",
231
+ "দ্বারা",
232
+ "ধরা",
233
+ "ধরে",
234
+ "ধামার",
235
+ "নতুন",
236
+ "নয়",
237
+ "না",
238
+ "নাই",
239
+ "নাকি",
240
+ "নাগাদ",
241
+ "নানা",
242
+ "নিজে",
243
+ "নিজেই",
244
+ "নিজেদের",
245
+ "নিজের",
246
+ "নিতে",
247
+ "নিয়ে",
248
+ "নিয়ে",
249
+ "নেই",
250
+ "নেওয়া",
251
+ "নেওয়ার",
252
+ "নেওয়া",
253
+ "নয়",
254
+ "পক্ষে",
255
+ "পর",
256
+ "পরে",
257
+ "পরেই",
258
+ "পরেও",
259
+ "পর্যন্ত",
260
+ "পাওয়া",
261
+ "পাচ",
262
+ "পারি",
263
+ "পারে",
264
+ "পারেন",
265
+ "পি",
266
+ "পেয়ে",
267
+ "পেয়্র্",
268
+ "প্রতি",
269
+ "প্রথম",
270
+ "প্রভৃতি",
271
+ "প্রযন্ত",
272
+ "প্রাথমিক",
273
+ "প্রায়",
274
+ "প্রায়",
275
+ "ফলে",
276
+ "ফিরে",
277
+ "ফের",
278
+ "বক্তব্য",
279
+ "বদলে",
280
+ "বন",
281
+ "বরং",
282
+ "বলতে",
283
+ "বলল",
284
+ "বললেন",
285
+ "বলা",
286
+ "বলে",
287
+ "বলেছেন",
288
+ "বলেন",
289
+ "বসে",
290
+ "বহু",
291
+ "বা",
292
+ "বাদে",
293
+ "বার",
294
+ "বি",
295
+ "বিনা",
296
+ "বিভিন্ন",
297
+ "বিশেষ",
298
+ "বিষয়টি",
299
+ "বেশ",
300
+ "বেশি",
301
+ "ব্যবহার",
302
+ "ব্যাপারে",
303
+ "ভাবে",
304
+ "ভাবেই",
305
+ "মতো",
306
+ "মতোই",
307
+ "মধ্যভাগে",
308
+ "মধ্যে",
309
+ "মধ্যেই",
310
+ "মধ্যেও",
311
+ "মনে",
312
+ "মাত্র",
313
+ "মাধ্যমে",
314
+ "মোট",
315
+ "মোটেই",
316
+ "যখন",
317
+ "যত",
318
+ "যতটা",
319
+ "যথেষ্ট",
320
+ "যদি",
321
+ "যদিও",
322
+ "যা",
323
+ "যাঁর",
324
+ "যাঁরা",
325
+ "যাওয়া",
326
+ "যাওয়ার",
327
+ "যাওয়া",
328
+ "যাকে",
329
+ "যাচ্ছে",
330
+ "যাতে",
331
+ "যাদের",
332
+ "যান",
333
+ "যাবে",
334
+ "যায়",
335
+ "যার",
336
+ "যারা",
337
+ "যিনি",
338
+ "যে",
339
+ "যেখানে",
340
+ "যেতে",
341
+ "যেন",
342
+ "যেমন",
343
+ "র",
344
+ "রকম",
345
+ "রয়েছে",
346
+ "রাখা",
347
+ "রেখে",
348
+ "লক্ষ",
349
+ "শুধু",
350
+ "শুরু",
351
+ "সঙ্গে",
352
+ "সঙ্গেও",
353
+ "সব",
354
+ "সবার",
355
+ "সমস্ত",
356
+ "সম্প্রতি",
357
+ "সহ",
358
+ "সহিত",
359
+ "সাধারণ",
360
+ "সামনে",
361
+ "সি",
362
+ "সুতরাং",
363
+ "সে",
364
+ "সেই",
365
+ "সেখান",
366
+ "সেখানে",
367
+ "সেটা",
368
+ "সেটাই",
369
+ "সেটাও",
370
+ "সেটি",
371
+ "স্পষ্ট",
372
+ "স্বয়ং",
373
+ "হইতে",
374
+ "হইবে",
375
+ "হইয়া",
376
+ "হওয়া",
377
+ "হওয়ায়",
378
+ "হওয়ার",
379
+ "হচ্ছে",
380
+ "হত",
381
+ "হতে",
382
+ "হতেই",
383
+ "হন",
384
+ "হবে",
385
+ "হবেন",
386
+ "হয়",
387
+ "হয়তো",
388
+ "হয়নি",
389
+ "হয়ে",
390
+ "হয়েই",
391
+ "হয়েছিল",
392
+ "হয়েছে",
393
+ "হয়েছেন",
394
+ "হল",
395
+ "হলে",
396
+ "হলেই",
397
+ "হলেও",
398
+ "হলো",
399
+ "হাজার",
400
+ "হিসাবে",
401
+ "হৈলে",
402
+ "হোক",
403
+ "হয়",
404
+ ]
405
+ end
406
+ end
407
+ end
408
+ end