langdetect-ruby 0.1.1 → 0.2.0

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 (48) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +24 -13
  3. data/langdetect-ruby.gemspec +1 -1
  4. data/lib/lingua_ruby/configuration.rb +4 -1
  5. data/lib/lingua_ruby/detector.rb +59 -1
  6. data/lib/lingua_ruby/profile_loader.rb +26 -6
  7. data/lib/lingua_ruby/profiles/am.json +193 -0
  8. data/lib/lingua_ruby/profiles/bg.json +290 -0
  9. data/lib/lingua_ruby/profiles/bn.json +211 -0
  10. data/lib/lingua_ruby/profiles/cs.json +302 -0
  11. data/lib/lingua_ruby/profiles/da.json +302 -0
  12. data/lib/lingua_ruby/profiles/de.json +302 -0
  13. data/lib/lingua_ruby/profiles/el.json +302 -0
  14. data/lib/lingua_ruby/profiles/es.json +302 -0
  15. data/lib/lingua_ruby/profiles/et.json +289 -0
  16. data/lib/lingua_ruby/profiles/fa.json +234 -0
  17. data/lib/lingua_ruby/profiles/fi.json +284 -0
  18. data/lib/lingua_ruby/profiles/fr.json +302 -0
  19. data/lib/lingua_ruby/profiles/ha.json +302 -0
  20. data/lib/lingua_ruby/profiles/hi.json +255 -0
  21. data/lib/lingua_ruby/profiles/hr.json +302 -0
  22. data/lib/lingua_ruby/profiles/hu.json +302 -0
  23. data/lib/lingua_ruby/profiles/it.json +302 -0
  24. data/lib/lingua_ruby/profiles/lt.json +294 -0
  25. data/lib/lingua_ruby/profiles/lv.json +302 -0
  26. data/lib/lingua_ruby/profiles/my.json +200 -0
  27. data/lib/lingua_ruby/profiles/no.json +297 -0
  28. data/lib/lingua_ruby/profiles/pl.json +302 -0
  29. data/lib/lingua_ruby/profiles/pt.json +302 -0
  30. data/lib/lingua_ruby/profiles/ro.json +302 -0
  31. data/lib/lingua_ruby/profiles/ru.json +297 -0
  32. data/lib/lingua_ruby/profiles/sk.json +302 -0
  33. data/lib/lingua_ruby/profiles/sv.json +302 -0
  34. data/lib/lingua_ruby/profiles/sw.json +268 -0
  35. data/lib/lingua_ruby/profiles/ta.json +235 -0
  36. data/lib/lingua_ruby/profiles/te.json +254 -0
  37. data/lib/lingua_ruby/profiles/th.json +251 -0
  38. data/lib/lingua_ruby/profiles/tl.json +302 -0
  39. data/lib/lingua_ruby/profiles/tr.json +302 -0
  40. data/lib/lingua_ruby/profiles/uk.json +302 -0
  41. data/lib/lingua_ruby/profiles/ur.json +232 -0
  42. data/lib/lingua_ruby/profiles/vi.json +277 -0
  43. data/lib/lingua_ruby/profiles/yo.json +245 -0
  44. data/lib/lingua_ruby/profiles/zu.json +302 -0
  45. data/lib/lingua_ruby/result.rb +13 -26
  46. data/lib/lingua_ruby/version.rb +1 -1
  47. data/lib/lingua_ruby.rb +4 -0
  48. metadata +41 -2
@@ -0,0 +1,290 @@
1
+ {
2
+ "а": 0,
3
+ "и": 1,
4
+ "т": 2,
5
+ "о": 3,
6
+ "р": 4,
7
+ "я": 5,
8
+ "а ": 6,
9
+ "л": 7,
10
+ "с": 8,
11
+ "г": 9,
12
+ "н": 10,
13
+ "е": 11,
14
+ "ия": 12,
15
+ "к": 13,
16
+ " е": 14,
17
+ "ри": 15,
18
+ "в": 16,
19
+ "я ": 17,
20
+ "га": 18,
21
+ " с": 19,
22
+ "ст": 20,
23
+ "на": 21,
24
+ "ия ": 22,
25
+ "б": 23,
26
+ "а б": 24,
27
+ "то": 25,
28
+ "ъ": 26,
29
+ "бъл": 27,
30
+ "и ": 28,
31
+ "ра": 29,
32
+ " и": 30,
33
+ "ълг": 31,
34
+ "лга": 32,
35
+ "гар": 33,
36
+ " б": 34,
37
+ "ар": 35,
38
+ "рия": 36,
39
+ "лг": 37,
40
+ "ъл": 38,
41
+ "бъ": 39,
42
+ "ят": 40,
43
+ " ст": 41,
44
+ "ари": 42,
45
+ " е ": 43,
46
+ "на ": 44,
47
+ "т ": 45,
48
+ " бъ": 46,
49
+ "м": 47,
50
+ "у": 48,
51
+ "ата": 49,
52
+ "та ": 50,
53
+ "ат": 51,
54
+ "я и": 52,
55
+ "та": 53,
56
+ "е ": 54,
57
+ "з": 55,
58
+ "го": 56,
59
+ " н": 57,
60
+ " г": 58,
61
+ "ог": 59,
62
+ "о ": 60,
63
+ "ис": 61,
64
+ " к": 62,
65
+ "ту": 63,
66
+ "ур": 64,
67
+ "вя": 65,
68
+ "сто": 66,
69
+ " на": 67,
70
+ " и ": 68,
71
+ "ист": 69,
72
+ "ик ": 70,
73
+ "зик": 71,
74
+ "тур": 72,
75
+ "ези": 73,
76
+ " ез": 74,
77
+ "ят ": 75,
78
+ "ият": 76,
79
+ "ски": 77,
80
+ " в ": 78,
81
+ "ана": 79,
82
+ "ран": 80,
83
+ "тра": 81,
84
+ "стр": 82,
85
+ "е с": 83,
86
+ "я е": 84,
87
+ "ю": 85,
88
+ "но": 86,
89
+ "к ": 87,
90
+ "ик": 88,
91
+ "зи": 89,
92
+ "ез": 90,
93
+ "ки": 91,
94
+ "ск": 92,
95
+ "ч": 93,
96
+ "п": 94,
97
+ " ю": 95,
98
+ "ц": 96,
99
+ "в ": 97,
100
+ " в": 98,
101
+ "ан": 99,
102
+ "тр": 100,
103
+ "ол": 101,
104
+ "ли": 102,
105
+ "сл": 103,
106
+ "най": 104,
107
+ "ай ": 105,
108
+ "й г": 106,
109
+ " го": 107,
110
+ "гол": 108,
111
+ "оле": 109,
112
+ "лем": 110,
113
+ "еми": 111,
114
+ "мия": 112,
115
+ "т г": 113,
116
+ " гр": 114,
117
+ "гра": 115,
118
+ "рад": 116,
119
+ "ад ": 117,
120
+ "д в": 118,
121
+ "в с": 119,
122
+ "нат": 120,
123
+ " им": 121,
124
+ "има": 122,
125
+ "ма ": 123,
126
+ " бо": 124,
127
+ "бог": 125,
128
+ "и е": 126,
129
+ "к с": 127,
130
+ " со": 128,
131
+ "соф": 129,
132
+ "офи": 130,
133
+ "фия": 131,
134
+ "д": 132,
135
+ "тол": 133,
136
+ "оли": 134,
137
+ "лиц": 135,
138
+ "ица": 136,
139
+ "цат": 137,
140
+ "й": 138,
141
+ "вят": 139,
142
+ "свя": 140,
143
+ " св": 141,
144
+ "л с": 142,
145
+ "а н": 143,
146
+ "ф": 144,
147
+ "ж": 145,
148
+ "ял ": 146,
149
+ "и н": 147,
150
+ " ко": 148,
151
+ "коя": 149,
152
+ "оят": 150,
153
+ "ято": 151,
154
+ "то ": 152,
155
+ "о п": 153,
156
+ " пр": 154,
157
+ "при": 155,
158
+ "рив": 156,
159
+ "ивл": 157,
160
+ "вли": 158,
161
+ "лич": 159,
162
+ "ича": 160,
163
+ "ча ": 161,
164
+ "а м": 162,
165
+ " мн": 163,
166
+ "мно": 164,
167
+ "ног": 165,
168
+ "ого": 166,
169
+ "ури": 167,
170
+ "го ": 168,
171
+ "о т": 169,
172
+ " ту": 170,
173
+ "ога": 171,
174
+ "гат": 172,
175
+ "а и": 173,
176
+ " ис": 174,
177
+ "цял": 175,
178
+ "тор": 176,
179
+ " ця": 177,
180
+ "т ц": 178,
181
+ "от ": 179,
182
+ " от": 180,
183
+ "и о": 181,
184
+ "ти ": 182,
185
+ "ори": 183,
186
+ "и к": 184,
187
+ "сти": 185,
188
+ " ку": 186,
189
+ "кул": 187,
190
+ "улт": 188,
191
+ "лту": 189,
192
+ "рис": 190,
193
+ "ура": 191,
194
+ "ра ": 192,
195
+ "а к": 193,
196
+ "ко": 194,
197
+ "оя": 195,
198
+ "ос": 196,
199
+ " п": 197,
200
+ "пр": 198,
201
+ "ив": 199,
202
+ "вл": 200,
203
+ "ич": 201,
204
+ "ча": 202,
205
+ " м": 203,
206
+ "мн": 204,
207
+ " т": 205,
208
+ "ти": 206,
209
+ " о": 207,
210
+ "от": 208,
211
+ " ц": 209,
212
+ "ця": 210,
213
+ "ял": 211,
214
+ "л ": 212,
215
+ "св": 213,
216
+ "жн": 214,
217
+ "юж": 215,
218
+ "опа": 216,
219
+ "иц": 217,
220
+ "ца": 218,
221
+ "фи": 219,
222
+ "оф": 220,
223
+ "со": 221,
224
+ "ай": 222,
225
+ "й ": 223,
226
+ "нс": 224,
227
+ "ле": 225,
228
+ "ем": 226,
229
+ "ми": 227,
230
+ "гр": 228,
231
+ "ад": 229,
232
+ "д ": 230,
233
+ "им": 231,
234
+ "ма": 232,
235
+ "бо": 233,
236
+ "ян": 234,
237
+ "ор": 235,
238
+ "ав": 236,
239
+ "ку": 237,
240
+ "ул": 238,
241
+ "лт": 239,
242
+ "ла": 240,
243
+ "па ": 241,
244
+ "зт": 242,
245
+ "из": 243,
246
+ "арс": 244,
247
+ "рск": 245,
248
+ "ои": 246,
249
+ "кия": 247,
250
+ "юг": 248,
251
+ "т е": 249,
252
+ "к е": 250,
253
+ "е ю": 251,
254
+ " юж": 252,
255
+ "южн": 253,
256
+ "жно": 254,
257
+ "нос": 255,
258
+ "осл": 256,
259
+ "сла": 257,
260
+ "лав": 258,
261
+ "авя": 259,
262
+ "вян": 260,
263
+ "янс": 261,
264
+ "нск": 262,
265
+ "ки ": 263,
266
+ "рс": 264,
267
+ "па": 265,
268
+ "оп": 266,
269
+ "ро": 267,
270
+ "вр": 268,
271
+ "ев": 269,
272
+ "чн": 270,
273
+ "а в": 271,
274
+ "оч": 272,
275
+ "в ю": 273,
276
+ " юг": 274,
277
+ "юго": 275,
278
+ "гои": 276,
279
+ "оиз": 277,
280
+ "изт": 278,
281
+ "зто": 279,
282
+ "точ": 280,
283
+ "очн": 281,
284
+ "чна": 282,
285
+ "а е": 283,
286
+ " ев": 284,
287
+ "евр": 285,
288
+ "вро": 286,
289
+ "роп": 287
290
+ }
@@ -0,0 +1,211 @@
1
+ {
2
+ "া": 0,
3
+ "র": 1,
4
+ "ে": 2,
5
+ "ব": 3,
6
+ "শ": 4,
7
+ "দ": 5,
8
+ "ং": 6,
9
+ "্": 7,
10
+ "দে": 8,
11
+ "া ": 9,
12
+ "ষ": 10,
13
+ "েশ": 11,
14
+ "র ": 12,
15
+ "দেশ": 13,
16
+ " ব": 14,
17
+ "লা": 15,
18
+ "ংল": 16,
19
+ "াং": 17,
20
+ "বা": 18,
21
+ " এ": 19,
22
+ "াষ": 20,
23
+ "ংলা": 21,
24
+ "এ": 22,
25
+ "াংল": 23,
26
+ "ি": 24,
27
+ "বাং": 25,
28
+ "ল": 26,
29
+ "াষা": 27,
30
+ "ষা ": 28,
31
+ "ভাষ": 29,
32
+ "েশে": 30,
33
+ "শের": 31,
34
+ "ের ": 32,
35
+ "াদে": 33,
36
+ "লাদ": 34,
37
+ "ভা": 35,
38
+ "ষা": 36,
39
+ "শে": 37,
40
+ "ের": 38,
41
+ "ভ": 39,
42
+ "ন": 40,
43
+ "ত": 41,
44
+ "ক": 42,
45
+ " বা": 43,
46
+ "াদ": 44,
47
+ " দ": 45,
48
+ "এবং": 46,
49
+ "ট": 47,
50
+ "ধা": 48,
51
+ " র": 49,
52
+ "রা": 50,
53
+ "য": 51,
54
+ "তম": 52,
55
+ "ম ": 53,
56
+ "তম ": 54,
57
+ "ধান": 55,
58
+ "্র": 56,
59
+ "এব": 57,
60
+ "বং": 58,
61
+ "বং ": 59,
62
+ "ং ": 60,
63
+ " প": 61,
64
+ " ভা": 62,
65
+ "শ ": 63,
66
+ "হ": 64,
67
+ "া ব": 65,
68
+ " এব": 66,
69
+ "ধ": 67,
70
+ "র র": 68,
71
+ " রা": 69,
72
+ "ম": 70,
73
+ "েশ ": 71,
74
+ " দে": 72,
75
+ "ী": 73,
76
+ "ান": 74,
77
+ " ভ": 75,
78
+ "ৃ": 76,
79
+ "প": 77,
80
+ "া এ": 78,
81
+ "রভা": 79,
82
+ "ং প": 80,
83
+ " পৃ": 81,
84
+ "পৃথ": 82,
85
+ "ঢাক": 83,
86
+ "্রভ": 84,
87
+ "ট্র": 85,
88
+ "্ট্": 86,
89
+ "ষ্ট": 87,
90
+ "াষ্": 88,
91
+ "রাষ": 89,
92
+ "কটি": 90,
93
+ "টি ": 91,
94
+ "ি দ": 92,
95
+ "শ ব": 93,
96
+ "া ভ": 94,
97
+ "লা ": 95,
98
+ "াকা": 96,
99
+ "কা ": 97,
100
+ "রাজ": 98,
101
+ "াজধ": 99,
102
+ "জধা": 100,
103
+ "ানী": 101,
104
+ "নী ": 102,
105
+ "ী এ": 103,
106
+ "ং দ": 104,
107
+ "র ব": 105,
108
+ " বৃ": 106,
109
+ "বৃহ": 107,
110
+ "ৃহত": 108,
111
+ "হত্": 109,
112
+ "ত্ত": 110,
113
+ "্তম": 111,
114
+ "ম শ": 112,
115
+ " শহ": 113,
116
+ "শহর": 114,
117
+ "ৃথি": 115,
118
+ "থিব": 116,
119
+ "িবী": 117,
120
+ "বীর": 118,
121
+ "ীর ": 119,
122
+ "র অ": 120,
123
+ " অন": 121,
124
+ "অন্": 122,
125
+ "ন্য": 123,
126
+ "্যত": 124,
127
+ "যতম": 125,
128
+ "ম প": 126,
129
+ " প্": 127,
130
+ "প্র": 128,
131
+ "্রধ": 129,
132
+ "রধা": 130,
133
+ "ান ": 131,
134
+ "ন ভ": 132,
135
+ "া ঢ": 133,
136
+ " ঢা": 134,
137
+ "ণ": 135,
138
+ "কট": 136,
139
+ "টি": 137,
140
+ "ি ": 138,
141
+ "ষ্": 139,
142
+ "্ট": 140,
143
+ "ট্": 141,
144
+ "রভ": 142,
145
+ "পৃ": 143,
146
+ "ৃথ": 144,
147
+ "থি": 145,
148
+ "িব": 146,
149
+ "বী": 147,
150
+ "ীর": 148,
151
+ " অ": 149,
152
+ "অন": 150,
153
+ "ন্": 151,
154
+ "্য": 152,
155
+ "যত": 153,
156
+ "়": 154,
157
+ "থ": 155,
158
+ "অ": 156,
159
+ "ঢ": 157,
160
+ "জ": 158,
161
+ "দক": 159,
162
+ "ক্": 160,
163
+ "্ষ": 161,
164
+ "ষি": 162,
165
+ "িণ": 163,
166
+ "ণ ": 164,
167
+ "এশ": 165,
168
+ "শি": 166,
169
+ "িয": 167,
170
+ "য়": 168,
171
+ "়া": 169,
172
+ "ার": 170,
173
+ "এক": 171,
174
+ "প্": 172,
175
+ "শ দ": 173,
176
+ " দক": 174,
177
+ "দক্": 175,
178
+ "ক্ষ": 176,
179
+ "্ষি": 177,
180
+ "ষিণ": 178,
181
+ "িণ ": 179,
182
+ "ণ এ": 180,
183
+ " এশ": 181,
184
+ "এশি": 182,
185
+ "শিয": 183,
186
+ "িয়": 184,
187
+ "য়া": 185,
188
+ "়ার": 186,
189
+ "ার ": 187,
190
+ "র এ": 188,
191
+ " এক": 189,
192
+ "একট": 190,
193
+ "রধ": 191,
194
+ "ন ": 192,
195
+ " ঢ": 193,
196
+ "ঢা": 194,
197
+ "াক": 195,
198
+ "কা": 196,
199
+ "াজ": 197,
200
+ "জধ": 198,
201
+ "নী": 199,
202
+ "ী ": 200,
203
+ "বৃ": 201,
204
+ "ৃহ": 202,
205
+ "হত": 203,
206
+ "ত্": 204,
207
+ "্ত": 205,
208
+ " শ": 206,
209
+ "শহ": 207,
210
+ "হর": 208
211
+ }