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 +1,302 @@
1
+ {
2
+ "а": 0,
3
+ "у": 1,
4
+ "о": 2,
5
+ "к": 3,
6
+ "р": 4,
7
+ "т": 5,
8
+ "і": 6,
9
+ "н": 7,
10
+ "с": 8,
11
+ "и": 9,
12
+ "в": 10,
13
+ "а ": 11,
14
+ "є": 12,
15
+ "ї": 13,
16
+ "кр": 14,
17
+ "ра": 15,
18
+ "їн": 16,
19
+ "ь": 17,
20
+ "м": 18,
21
+ "аї": 19,
22
+ "аїн": 20,
23
+ "кра": 21,
24
+ "раї": 22,
25
+ " у": 23,
26
+ "л": 24,
27
+ "ю": 25,
28
+ "є ": 26,
29
+ " к": 27,
30
+ " є": 28,
31
+ "ю ": 29,
32
+ " с": 30,
33
+ "укр": 31,
34
+ " м": 32,
35
+ "ту": 33,
36
+ "в ": 34,
37
+ "ст": 35,
38
+ "ук": 36,
39
+ "б": 37,
40
+ "ов": 38,
41
+ "сто": 39,
42
+ "сь": 40,
43
+ " є ": 41,
44
+ "х": 42,
45
+ "то": 43,
46
+ " т": 44,
47
+ "у ": 45,
48
+ "на": 46,
49
+ "г": 47,
50
+ " ук": 48,
51
+ "ага": 49,
52
+ "гат": 50,
53
+ "ри": 51,
54
+ "ур": 52,
55
+ "ат": 53,
56
+ "ни": 54,
57
+ "га": 55,
58
+ "ов ": 56,
59
+ "аг": 57,
60
+ "ба": 58,
61
+ " б": 59,
62
+ "тур": 60,
63
+ "іс": 61,
64
+ "м ": 62,
65
+ "ль": 63,
66
+ "и ": 64,
67
+ "та": 65,
68
+ "їни": 66,
69
+ "нсь": 67,
70
+ "ни ": 68,
71
+ " та": 69,
72
+ "та ": 70,
73
+ "дні": 71,
74
+ "ю у": 72,
75
+ " кр": 73,
76
+ "а є": 74,
77
+ "на ": 75,
78
+ "їна": 76,
79
+ "ськ": 77,
80
+ "ка ": 78,
81
+ "а м": 79,
82
+ " мо": 80,
83
+ "іст": 81,
84
+ "є б": 82,
85
+ "мов": 83,
86
+ " ба": 84,
87
+ "ьо": 85,
88
+ "баг": 86,
89
+ "х ": 87,
90
+ "й": 88,
91
+ "ва": 89,
92
+ "ні": 90,
93
+ "п": 91,
94
+ "з": 92,
95
+ "ки": 93,
96
+ "дн": 94,
97
+ "ьк": 95,
98
+ "я": 96,
99
+ " я": 97,
100
+ "нс": 98,
101
+ "і ": 99,
102
+ " з": 100,
103
+ "ка": 101,
104
+ "д": 102,
105
+ "мо": 103,
106
+ "біл": 104,
107
+ "йбі": 105,
108
+ "айб": 106,
109
+ "най": 107,
110
+ " на": 108,
111
+ "а н": 109,
112
+ "ьог": 110,
113
+ "ого": 111,
114
+ "іль": 112,
115
+ "льш": 113,
116
+ "ьши": 114,
117
+ "шим": 115,
118
+ "им ": 116,
119
+ "сьо": 117,
120
+ "м м": 118,
121
+ "усь": 119,
122
+ " ус": 120,
123
+ "з у": 121,
124
+ " з ": 122,
125
+ " ян": 123,
126
+ "янс": 124,
127
+ "ьки": 125,
128
+ "ких": 126,
129
+ "их ": 127,
130
+ "х м": 128,
131
+ "в к": 129,
132
+ " ки": 130,
133
+ "киї": 131,
134
+ "иїв": 132,
135
+ "їв ": 133,
136
+ "в є": 134,
137
+ "є с": 135,
138
+ " ст": 136,
139
+ "тол": 137,
140
+ "іту": 138,
141
+ "оли": 139,
142
+ "віт": 140,
143
+ "сві": 141,
144
+ "лиц": 142,
145
+ " св": 143,
146
+ "ице": 144,
147
+ "цею": 145,
148
+ "ею ": 146,
149
+ "о с": 147,
150
+ "го ": 148,
151
+ "и т": 149,
152
+ "кул": 150,
153
+ "уль": 151,
154
+ "льт": 152,
155
+ "ури": 153,
156
+ " ту": 154,
157
+ "х т": 155,
158
+ "ох ": 156,
159
+ "ьту": 157,
160
+ "ьох": 158,
161
+ "уру": 159,
162
+ "ру ": 160,
163
+ "тьо": 161,
164
+ "у я": 162,
165
+ " як": 163,
166
+ "яка": 164,
167
+ "ать": 165,
168
+ "а п": 166,
169
+ " пр": 167,
170
+ "при": 168,
171
+ "рив": 169,
172
+ "ива": 170,
173
+ "ює ": 171,
174
+ "лює": 172,
175
+ "блю": 173,
176
+ "абл": 174,
177
+ "ваб": 175,
178
+ "в з": 176,
179
+ "ів ": 177,
180
+ " мі": 178,
181
+ "міс": 179,
182
+ "том": 180,
183
+ "ом ": 181,
184
+ "м к": 182,
185
+ "и у": 183,
186
+ " ма": 184,
187
+ "має": 185,
188
+ "ає ": 186,
189
+ "тів": 187,
190
+ "сті": 188,
191
+ "ист": 189,
192
+ "ату": 190,
193
+ "ту ": 191,
194
+ "у і": 192,
195
+ "рис": 193,
196
+ " іс": 194,
197
+ "тор": 195,
198
+ "орі": 196,
199
+ "рію": 197,
200
+ "ію ": 198,
201
+ "ю т": 199,
202
+ "а к": 200,
203
+ " ку": 201,
204
+ "ц": 202,
205
+ "иц": 203,
206
+ "це": 204,
207
+ "ею": 205,
208
+ " н": 206,
209
+ "ай": 207,
210
+ "йб": 208,
211
+ "бі": 209,
212
+ "іл": 210,
213
+ "ьш": 211,
214
+ "ши": 212,
215
+ "им": 213,
216
+ "мі": 214,
217
+ "ом": 215,
218
+ "ма": 216,
219
+ "ає": 217,
220
+ " і": 218,
221
+ "ор": 219,
222
+ "рі": 220,
223
+ "ію": 221,
224
+ "ку": 222,
225
+ "ул": 223,
226
+ "ьт": 224,
227
+ "ру": 225,
228
+ "як": 226,
229
+ " п": 227,
230
+ "пр": 228,
231
+ "ив": 229,
232
+ "е": 230,
233
+ "ш": 231,
234
+ "но": 232,
235
+ "ою": 233,
236
+ "сх": 234,
237
+ "хі": 235,
238
+ "ід": 236,
239
+ "ій": 237,
240
+ "й ": 238,
241
+ "єв": 239,
242
+ "вр": 240,
243
+ "ро": 241,
244
+ "оп": 242,
245
+ "пі": 243,
246
+ " о": 244,
247
+ "од": 245,
248
+ "іє": 246,
249
+ "єю": 247,
250
+ "зі": 248,
251
+ "сл": 249,
252
+ "ло": 250,
253
+ "ян": 251,
254
+ "их": 252,
255
+ "иї": 253,
256
+ "їв": 254,
257
+ "ол": 255,
258
+ "ли": 256,
259
+ "аб": 257,
260
+ "ій ": 258,
261
+ "й є": 259,
262
+ " єв": 260,
263
+ "євр": 261,
264
+ "вро": 262,
265
+ "роп": 263,
266
+ "опі": 264,
267
+ "пі ": 265,
268
+ "і у": 266,
269
+ "їнс": 267,
270
+ "ька": 268,
271
+ "ова": 269,
272
+ "ва ": 270,
273
+ "є о": 271,
274
+ " од": 272,
275
+ "одн": 273,
276
+ "ніє": 274,
277
+ "ією": 275,
278
+ "єю ": 276,
279
+ "ю з": 277,
280
+ " зі": 278,
281
+ "зі ": 279,
282
+ "і с": 280,
283
+ " сл": 281,
284
+ "сло": 282,
285
+ "лов": 283,
286
+ "в я": 284,
287
+ "бл": 285,
288
+ "лю": 286,
289
+ "ює": 287,
290
+ "ть": 288,
291
+ "ох": 289,
292
+ "ис": 290,
293
+ "ті": 291,
294
+ "ів": 292,
295
+ "з ": 293,
296
+ "ус": 294,
297
+ "ог": 295,
298
+ "го": 296,
299
+ "о ": 297,
300
+ "св": 298,
301
+ "ві": 299
302
+ }
@@ -0,0 +1,232 @@
1
+ {
2
+ "ا": 0,
3
+ "ی": 1,
4
+ "ک": 2,
5
+ "ن": 3,
6
+ "و": 4,
7
+ "ے": 5,
8
+ "س": 6,
9
+ "ان": 7,
10
+ "ب": 8,
11
+ "م": 9,
12
+ "ے ": 10,
13
+ "ی ": 11,
14
+ " ا": 12,
15
+ "ہ": 13,
16
+ "ل": 14,
17
+ "د": 15,
18
+ "ن ": 16,
19
+ "ان ": 17,
20
+ "ہے": 18,
21
+ " ز": 19,
22
+ "با": 20,
23
+ "ز": 21,
24
+ " ہ": 22,
25
+ " ہے": 23,
26
+ "ے ا": 24,
27
+ "ت": 25,
28
+ "ک ": 26,
29
+ "ں ": 27,
30
+ "زب": 28,
31
+ "می": 29,
32
+ "پ": 30,
33
+ " ک": 31,
34
+ " س": 32,
35
+ "پاک": 33,
36
+ "اکس": 34,
37
+ "کست": 35,
38
+ "ستا": 36,
39
+ "تان": 37,
40
+ " ای": 38,
41
+ "ہے ": 39,
42
+ "بان": 40,
43
+ " زب": 41,
44
+ "زبا": 42,
45
+ "ں": 43,
46
+ "ر": 44,
47
+ "پا": 45,
48
+ "اک": 46,
49
+ "کس": 47,
50
+ "ست": 48,
51
+ "تا": 49,
52
+ "ای": 50,
53
+ " م": 51,
54
+ "ا ": 52,
55
+ "یا": 53,
56
+ "سے": 54,
57
+ "اد": 55,
58
+ "لی": 56,
59
+ "ال": 57,
60
+ "لی ": 58,
61
+ "سے ": 59,
62
+ " سے": 60,
63
+ "وا": 61,
64
+ " و": 62,
65
+ "یں": 63,
66
+ "یا ": 64,
67
+ " می": 65,
68
+ "میں": 66,
69
+ "یں ": 67,
70
+ " وا": 68,
71
+ "ی ز": 69,
72
+ "ایک": 70,
73
+ "یک ": 71,
74
+ "کی ": 72,
75
+ "ک ہ": 73,
76
+ "ق": 74,
77
+ " کی": 75,
78
+ "ن ک": 76,
79
+ " پا": 77,
80
+ "ج": 78,
81
+ "نو": 79,
82
+ " د": 80,
83
+ " پ": 81,
84
+ " ج": 82,
85
+ "کی": 83,
86
+ "ار": 84,
87
+ "وم": 85,
88
+ "یک": 86,
89
+ "آبا": 87,
90
+ " دن": 88,
91
+ "ر د": 89,
92
+ "دنی": 90,
93
+ "ور ": 91,
94
+ "نیا": 92,
95
+ "اور": 93,
96
+ "ا ک": 94,
97
+ "ی س": 95,
98
+ "حکو": 96,
99
+ " سب": 97,
100
+ " او": 98,
101
+ "ن ہ": 99,
102
+ "ارا": 100,
103
+ "ت ہ": 101,
104
+ "ن پ": 102,
105
+ "کا ": 103,
106
+ " کا": 104,
107
+ "رال": 105,
108
+ "ا د": 106,
109
+ "الح": 107,
110
+ "مت ": 108,
111
+ "د پ": 109,
112
+ "ی ق": 110,
113
+ " قو": 111,
114
+ "قوم": 112,
115
+ "اد ": 113,
116
+ "باد": 114,
117
+ "ومی": 115,
118
+ "می ": 116,
119
+ "لحک": 117,
120
+ "ولی": 118,
121
+ "ی ج": 119,
122
+ " جا": 120,
123
+ "جان": 121,
124
+ "انے": 122,
125
+ "سلا": 123,
126
+ "نے ": 124,
127
+ "ے و": 125,
128
+ "اسل": 126,
129
+ "وال": 127,
130
+ "الی": 128,
131
+ "انو": 129,
132
+ "نوں": 130,
133
+ "وں ": 131,
134
+ " دا": 132,
135
+ "ں م": 133,
136
+ " اس": 134,
137
+ "ں س": 135,
138
+ "سب ": 136,
139
+ "ب س": 137,
140
+ "ومت": 138,
141
+ "کوم": 139,
142
+ " آب": 140,
143
+ "م آ": 141,
144
+ "دار": 142,
145
+ "ام ": 143,
146
+ "لام": 144,
147
+ "ے ز": 145,
148
+ " زی": 146,
149
+ "زیا": 147,
150
+ "یاد": 148,
151
+ "ادہ": 149,
152
+ "دہ ": 150,
153
+ "ہ ب": 151,
154
+ " بو": 152,
155
+ "بول": 153,
156
+ "او": 154,
157
+ "ور": 155,
158
+ "ر ": 156,
159
+ "دن": 157,
160
+ "نی": 158,
161
+ "سب": 159,
162
+ "ب ": 160,
163
+ "زی": 161,
164
+ "دہ": 162,
165
+ "ہ ": 163,
166
+ " ب": 164,
167
+ "بو": 165,
168
+ "ول": 166,
169
+ "جا": 167,
170
+ "نے": 168,
171
+ "وں": 169,
172
+ "اس": 170,
173
+ "سل": 171,
174
+ "لا": 172,
175
+ "ش": 173,
176
+ "ع": 174,
177
+ "آ": 175,
178
+ "ح": 176,
179
+ "جن": 177,
180
+ "وب": 178,
181
+ "بی": 179,
182
+ "یش": 180,
183
+ "شی": 181,
184
+ "اق": 182,
185
+ "قع": 183,
186
+ "ع ": 184,
187
+ "مل": 185,
188
+ "لک": 186,
189
+ "رد": 187,
190
+ "دو": 188,
191
+ "و ": 189,
192
+ " ق": 190,
193
+ "قو": 191,
194
+ "ی ا": 192,
195
+ "ایش": 193,
196
+ "یشی": 194,
197
+ "شیا": 195,
198
+ "ا م": 196,
199
+ "ں و": 197,
200
+ "واق": 198,
201
+ "اقع": 199,
202
+ "قع ": 200,
203
+ "ع ا": 201,
204
+ "ک م": 202,
205
+ " مل": 203,
206
+ "ملک": 204,
207
+ "لک ": 205,
208
+ " ار": 206,
209
+ "ارد": 207,
210
+ "ردو": 208,
211
+ "دو ": 209,
212
+ "و ز": 210,
213
+ "ام": 211,
214
+ "م ": 212,
215
+ " آ": 213,
216
+ "آب": 214,
217
+ "د ": 215,
218
+ "کا": 216,
219
+ "دا": 217,
220
+ "را": 218,
221
+ "لح": 219,
222
+ "حک": 220,
223
+ "کو": 221,
224
+ "مت": 222,
225
+ "ت ": 223,
226
+ "ن ج": 224,
227
+ " جن": 225,
228
+ "جنو": 226,
229
+ "نوب": 227,
230
+ "وبی": 228,
231
+ "بی ": 229
232
+ }