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 +1,245 @@
1
+ class Keyphrase
2
+ module Stoplist
3
+ class Khm
4
+ def self.stopwords
5
+ @@stopwords ||= [
6
+ "ៗ",
7
+ "។ល។",
8
+ "៚",
9
+ "។",
10
+ "៕",
11
+ "៖",
12
+ "៙",
13
+ "០",
14
+ "១",
15
+ "២",
16
+ "៣",
17
+ "៤",
18
+ "៥",
19
+ "៦",
20
+ "៧",
21
+ "៨",
22
+ "៩",
23
+ "៛",
24
+ "នេះ",
25
+ "នោះ",
26
+ "ខ្ញុំ",
27
+ "អ្នក",
28
+ "គាត់",
29
+ "នាង",
30
+ "ពួក",
31
+ "យើង",
32
+ "ពួកគេ",
33
+ "លោក",
34
+ "អ្វី",
35
+ "បាន",
36
+ "ការ",
37
+ "នៅ",
38
+ "និង",
39
+ "ដែល",
40
+ "មាន",
41
+ "ជា",
42
+ "ថា",
43
+ "ក្នុង",
44
+ "របស់",
45
+ "ពី",
46
+ "មួយ",
47
+ "នឹង",
48
+ "ឲ្យ",
49
+ "មិន",
50
+ "ទៅ",
51
+ "តែ",
52
+ "ត្រូវ",
53
+ "ដោយ",
54
+ "ហើយ",
55
+ "ឆ្នាំ",
56
+ "ពេល",
57
+ "គេ",
58
+ "ប្រទេស",
59
+ "អាច",
60
+ "គឺ",
61
+ "ក្រុម",
62
+ "ធ្វើ",
63
+ "ក៏",
64
+ "លើ",
65
+ "នៃ",
66
+ "ដើម្បី",
67
+ "មក",
68
+ "ទី",
69
+ "តាម",
70
+ "ទេ",
71
+ "ដល់",
72
+ "វា",
73
+ "ដែរ",
74
+ "ខ្លួន",
75
+ "សម្រាប់",
76
+ "ក្រុមហ៊ុន",
77
+ "ថ្ងៃ",
78
+ "ចំនួន",
79
+ "កម្ពុជា",
80
+ "ឡើង",
81
+ "ទៀត",
82
+ "ទាំង",
83
+ "បើ",
84
+ "និយាយ",
85
+ "ទទួល",
86
+ "ដ៏",
87
+ "ច្រើន",
88
+ "ផង",
89
+ "ដឹង",
90
+ "ជាមួយ",
91
+ "គ្នា",
92
+ "ខែ",
93
+ "នាក់",
94
+ "កំពុង",
95
+ "យ៉ាង",
96
+ "តម្លៃ",
97
+ "ប្រកួត",
98
+ "ក្រុង",
99
+ "តំបន់",
100
+ "ភាព",
101
+ "យក",
102
+ "ជាង",
103
+ "ចូល",
104
+ "នូវ",
105
+ "កាលពី",
106
+ "ណា",
107
+ "បន្ត",
108
+ "ជាតិ",
109
+ "រូប",
110
+ "មនុស្ស",
111
+ "កាល",
112
+ "ចំពោះ",
113
+ "ដូច",
114
+ "ខណៈ",
115
+ "វិញ",
116
+ "មុន",
117
+ "ភ្នំពេញ",
118
+ "លើក",
119
+ "ល្អ",
120
+ "ខាង",
121
+ "ដុល្លារ",
122
+ "ឃើញ",
123
+ "បញ្ហា",
124
+ "ប្រើ",
125
+ "ចាប់",
126
+ "ទឹក",
127
+ "តើ",
128
+ "ប្រាក់",
129
+ "ធំ",
130
+ "ខ្មែរ",
131
+ "ចេញ",
132
+ "ខេត្ត",
133
+ "ផ្នែក",
134
+ "ថ្មី",
135
+ "បង្ហាញ",
136
+ "ស៊ី",
137
+ "អាមេរិក",
138
+ "គឺជា",
139
+ "លក់",
140
+ "ចង់",
141
+ "ដាក់",
142
+ "ម្នាក់",
143
+ "រួម",
144
+ "រថយន្ត",
145
+ "ផ្លូវ",
146
+ "ភាគរយ",
147
+ "កើន",
148
+ "ជួយ",
149
+ "ពីរ",
150
+ "លាន",
151
+ "ផ្តល់",
152
+ "រដ្ឋ",
153
+ "ខ្លាំង",
154
+ "ជាច្រើន",
155
+ "ទីក្រុង",
156
+ "ជន",
157
+ "កីឡា",
158
+ "ក្រោយ",
159
+ "ប្រាប់",
160
+ "រដ្ឋាភិបាល",
161
+ "កាន់",
162
+ "ការងារ",
163
+ "រក",
164
+ "ព្រោះ",
165
+ "រឿង",
166
+ "ប៉ុន្តែ",
167
+ "ឡើយ",
168
+ "មុខ",
169
+ "ថ្លែង",
170
+ "ធ្វើឲ្យ",
171
+ "បី",
172
+ "នាំ",
173
+ "ច្បាប់",
174
+ "ដី",
175
+ "ដូចជា",
176
+ "កម",
177
+ "ផ្ទះ",
178
+ "បញ្ជាក់",
179
+ "ចុះ",
180
+ "បំផុត",
181
+ "ចិត្ត",
182
+ "បែប",
183
+ "ចិន",
184
+ "កីឡាករ",
185
+ "កញ្ញា",
186
+ "គម្រោង",
187
+ "បង្កើត",
188
+ "នា",
189
+ "សារ",
190
+ "សេដ្ឋកិច្ច",
191
+ "ធនាគារ",
192
+ "អស់",
193
+ "ភាគ",
194
+ "កូន",
195
+ "ប្រធាន",
196
+ "ផ្សារ",
197
+ "ខ្ពស់",
198
+ "គ្មាន",
199
+ "ណាស់",
200
+ "សម្រេច",
201
+ "គួរ",
202
+ "គ្រប់",
203
+ "ប្រជាជន",
204
+ "បន្ថែម",
205
+ "រយៈ",
206
+ "ខ្លះ",
207
+ "បទ",
208
+ "ទិញ",
209
+ "ទើប",
210
+ "វិនិយោគ",
211
+ "មានការ",
212
+ "លេខ",
213
+ "ថៃ",
214
+ "មើល",
215
+ "បុរស",
216
+ "យុវជន",
217
+ "ស្រី",
218
+ "នយោបាយ",
219
+ "កន្លែង",
220
+ "គិត",
221
+ "បើក",
222
+ "ដូច្នេះ",
223
+ "រូបថត",
224
+ "វាយ",
225
+ "ប្រភេទ",
226
+ "សំខាន់",
227
+ "បន្ទាប់ពី",
228
+ "កម្មវិធី",
229
+ "រយៈពេល",
230
+ "ផលិត",
231
+ "ឈ្នះ",
232
+ "ពិភពលោក",
233
+ "ភ្ញៀវ",
234
+ "ដោយសារ",
235
+ "ស្រុក",
236
+ "អាយុ",
237
+ "ចំណាយ",
238
+ "អំពី",
239
+ "ហ៊ុន",
240
+ "សិក្សា",
241
+ ]
242
+ end
243
+ end
244
+ end
245
+ end