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
+ "i": 0,
3
+ "e": 1,
4
+ "r": 2,
5
+ "a": 3,
6
+ "t": 4,
7
+ "o": 5,
8
+ "e ": 6,
9
+ "u": 7,
10
+ "m": 8,
11
+ "n": 9,
12
+ "l": 10,
13
+ "s": 11,
14
+ "ă ": 12,
15
+ "i ": 13,
16
+ "ă": 14,
17
+ "c": 15,
18
+ "ro": 16,
19
+ "st": 17,
20
+ " e": 18,
21
+ "a ": 19,
22
+ "ar": 20,
23
+ "re": 21,
24
+ "om": 22,
25
+ "rom": 23,
26
+ "ș": 24,
27
+ "ur": 25,
28
+ "tu": 26,
29
+ "mân": 27,
30
+ "omâ": 28,
31
+ " es": 29,
32
+ " ro": 30,
33
+ " r": 31,
34
+ " o": 32,
35
+ "est": 33,
36
+ "mâ": 34,
37
+ "b": 35,
38
+ "ân": 36,
39
+ "d": 37,
40
+ "re ": 38,
41
+ "ni": 39,
42
+ " c": 40,
43
+ "es": 41,
44
+ "â": 42,
45
+ "di": 43,
46
+ "ț": 44,
47
+ " d": 45,
48
+ "ste": 46,
49
+ "te ": 47,
50
+ "e o": 48,
51
+ " o ": 49,
52
+ "âni": 50,
53
+ " di": 51,
54
+ "ră ": 52,
55
+ "ul": 53,
56
+ "te": 54,
57
+ "o ": 55,
58
+ "ră": 56,
59
+ "at": 57,
60
+ " m": 58,
61
+ "ma": 59,
62
+ "are": 60,
63
+ "or": 61,
64
+ "in": 62,
65
+ "ti": 63,
66
+ "ra": 64,
67
+ "și": 65,
68
+ " ș": 66,
69
+ "ie": 67,
70
+ "tur": 68,
71
+ "ri": 69,
72
+ "ca": 70,
73
+ " a": 71,
74
+ "e b": 72,
75
+ "din": 73,
76
+ "ști": 74,
77
+ "a r": 75,
78
+ " ca": 76,
79
+ "imb": 77,
80
+ "lim": 78,
81
+ " li": 79,
82
+ "ei ": 80,
83
+ " și": 81,
84
+ "și ": 82,
85
+ " ma": 83,
86
+ "tă ": 84,
87
+ "ată": 85,
88
+ "ară": 86,
89
+ "țar": 87,
90
+ " ța": 88,
91
+ "ia ": 89,
92
+ "nia": 90,
93
+ "tă": 91,
94
+ "it": 92,
95
+ " s": 93,
96
+ "ța": 94,
97
+ " ț": 95,
98
+ "tr": 96,
99
+ "ia": 97,
100
+ "mb": 98,
101
+ "im": 99,
102
+ "li": 100,
103
+ " l": 101,
104
+ "ei": 102,
105
+ "g": 103,
106
+ "p": 104,
107
+ "ce": 105,
108
+ " b": 106,
109
+ "n ": 107,
110
+ "l ": 108,
111
+ "șt": 109,
112
+ "cu": 110,
113
+ "ala": 111,
114
+ "la ": 112,
115
+ "nie": 113,
116
+ "i m": 114,
117
+ "iei": 115,
118
+ "i ș": 116,
119
+ "i t": 117,
120
+ "ai ": 118,
121
+ "ți ": 119,
122
+ "ulț": 120,
123
+ "lți": 121,
124
+ "i c": 122,
125
+ "mai": 123,
126
+ " ce": 124,
127
+ "l m": 125,
128
+ "cel": 126,
129
+ "el ": 127,
130
+ "oma": 128,
131
+ "man": 129,
132
+ "ani": 130,
133
+ "nic": 131,
134
+ "ice": 132,
135
+ "ce ": 133,
136
+ "ișt": 134,
137
+ " bu": 135,
138
+ "buc": 136,
139
+ "riș": 137,
140
+ "ucu": 138,
141
+ "cur": 139,
142
+ "ure": 140,
143
+ "reș": 141,
144
+ "eșt": 142,
145
+ "ti ": 143,
146
+ "i e": 144,
147
+ "e c": 145,
148
+ "uri": 146,
149
+ " tu": 147,
150
+ "cap": 148,
151
+ "api": 149,
152
+ "pit": 150,
153
+ "ita": 151,
154
+ "tal": 152,
155
+ "tor": 153,
156
+ "ori": 154,
157
+ "rie": 155,
158
+ "ie ": 156,
159
+ " bo": 157,
160
+ "bog": 158,
161
+ "oga": 159,
162
+ "gat": 160,
163
+ "ă ș": 161,
164
+ "car": 162,
165
+ "i o": 163,
166
+ "o c": 164,
167
+ "ă c": 165,
168
+ "să ": 166,
169
+ " cu": 167,
170
+ "rsă": 168,
171
+ "cul": 169,
172
+ "ers": 170,
173
+ "ult": 171,
174
+ "ltu": 172,
175
+ "ver": 173,
176
+ "ură": 174,
177
+ "ă d": 175,
178
+ "ive": 176,
179
+ "div": 177,
180
+ "mar": 178,
181
+ "mul": 179,
182
+ " or": 180,
183
+ "ora": 181,
184
+ " mu": 182,
185
+ "e m": 183,
186
+ "ge ": 184,
187
+ "raș": 185,
188
+ "age": 186,
189
+ "aș ": 187,
190
+ "rag": 188,
191
+ "tra": 189,
192
+ "atr": 190,
193
+ " at": 191,
194
+ "e a": 192,
195
+ "ș d": 193,
196
+ "in ": 194,
197
+ "n ț": 195,
198
+ "ă r": 196,
199
+ "a a": 197,
200
+ " ar": 198,
201
+ "o i": 199,
202
+ " is": 200,
203
+ "ist": 201,
204
+ "sto": 202,
205
+ "eș": 203,
206
+ "ap": 204,
207
+ "pi": 205,
208
+ "ta": 206,
209
+ "al": 207,
210
+ "la": 208,
211
+ "el": 209,
212
+ "ai": 210,
213
+ "aș": 211,
214
+ "ș ": 212,
215
+ " i": 213,
216
+ "is": 214,
217
+ "to": 215,
218
+ "bo": 216,
219
+ "og": 217,
220
+ "ga": 218,
221
+ "lt": 219,
222
+ "iv": 220,
223
+ "ve": 221,
224
+ "er": 222,
225
+ "rs": 223,
226
+ "să": 224,
227
+ "ag": 225,
228
+ "ge": 226,
229
+ "mu": 227,
230
+ "î": 228,
231
+ "v": 229,
232
+ "si": 230,
233
+ "ua": 231,
234
+ " î": 232,
235
+ "în": 233,
236
+ "su": 234,
237
+ "ud": 235,
238
+ "d ": 236,
239
+ "eu": 237,
240
+ "op": 238,
241
+ "pe": 239,
242
+ "ba": 240,
243
+ "nă": 241,
244
+ " u": 242,
245
+ "un": 243,
246
+ "na": 244,
247
+ "nt": 245,
248
+ "bi": 246,
249
+ "il": 247,
250
+ "le": 248,
251
+ "an": 249,
252
+ "ic": 250,
253
+ "bu": 251,
254
+ "uc": 252,
255
+ "eur": 253,
256
+ "uro": 254,
257
+ "rop": 255,
258
+ "ope": 256,
259
+ "pei": 257,
260
+ "i l": 258,
261
+ "mba": 259,
262
+ "ba ": 260,
263
+ "ână": 261,
264
+ "nă ": 262,
265
+ "ă e": 263,
266
+ "e u": 264,
267
+ " un": 265,
268
+ "una": 266,
269
+ "na ": 267,
270
+ "a d": 268,
271
+ "int": 269,
272
+ "ntr": 270,
273
+ "tre": 271,
274
+ "e l": 272,
275
+ "mbi": 273,
276
+ "bil": 274,
277
+ "ile": 275,
278
+ "le ": 276,
279
+ "e r": 277,
280
+ "lț": 278,
281
+ "ți": 279,
282
+ " t": 280,
283
+ "iș": 281,
284
+ "a e": 282,
285
+ "o ț": 283,
286
+ "ă s": 284,
287
+ " si": 285,
288
+ "sit": 286,
289
+ "itu": 287,
290
+ "tua": 288,
291
+ "uat": 289,
292
+ "ă î": 290,
293
+ " în": 291,
294
+ "în ": 292,
295
+ "n s": 293,
296
+ " su": 294,
297
+ "sud": 295,
298
+ "ud ": 296,
299
+ "d e": 297,
300
+ "stu": 298,
301
+ "tul": 299
302
+ }
@@ -0,0 +1,297 @@
1
+ {
2
+ "р": 0,
3
+ "с": 1,
4
+ "о": 2,
5
+ "и": 3,
6
+ "я": 4,
7
+ "т": 5,
8
+ "е": 6,
9
+ "й": 7,
10
+ "а": 8,
11
+ "н": 9,
12
+ "м": 10,
13
+ "к": 11,
14
+ "й ": 12,
15
+ "в": 13,
16
+ "ст": 14,
17
+ "ей": 15,
18
+ " с": 16,
19
+ "ра": 17,
20
+ " я": 18,
21
+ "ро": 19,
22
+ "л": 20,
23
+ "у": 21,
24
+ "ы": 22,
25
+ "п": 23,
26
+ "то": 24,
27
+ "и ": 25,
28
+ " и": 26,
29
+ "я ": 27,
30
+ "ос": 28,
31
+ " ст": 29,
32
+ "ей ": 30,
33
+ "ся ": 31,
34
+ "тр": 32,
35
+ "ран": 33,
36
+ "тра": 34,
37
+ "ан": 35,
38
+ "ой": 36,
39
+ " м": 37,
40
+ "ри": 38,
41
+ "тся": 39,
42
+ "ор": 40,
43
+ "етс": 41,
44
+ " р": 42,
45
+ "м ": 43,
46
+ "яет": 44,
47
+ "рос": 45,
48
+ " яв": 46,
49
+ "стр": 47,
50
+ "явл": 48,
51
+ "вля": 49,
52
+ "ляе": 50,
53
+ "яе": 51,
54
+ "вл": 52,
55
+ "яв": 53,
56
+ "ля": 54,
57
+ "сс": 55,
58
+ "ру": 56,
59
+ "ся": 57,
60
+ " к": 58,
61
+ "тс": 59,
62
+ "ет": 60,
63
+ "з": 61,
64
+ "д": 62,
65
+ "ш": 63,
66
+ "в ": 64,
67
+ "ой ": 65,
68
+ "ны": 66,
69
+ " ми": 67,
70
+ "мир": 68,
71
+ "ых ": 69,
72
+ "х ": 70,
73
+ "ых": 71,
74
+ "кр": 72,
75
+ "и к": 73,
76
+ " и ": 74,
77
+ "х": 75,
78
+ "ейш": 76,
79
+ "ней": 77,
80
+ "пне": 78,
81
+ "упн": 79,
82
+ "сто": 80,
83
+ "руп": 81,
84
+ "кру": 82,
85
+ " кр": 83,
86
+ "г": 84,
87
+ "си": 85,
88
+ "осс": 86,
89
+ "сси": 87,
90
+ "ии ": 88,
91
+ "ии": 89,
92
+ "ир": 90,
93
+ "ск": 91,
94
+ "а ": 92,
95
+ "ми": 93,
96
+ "ори": 94,
97
+ "й и": 95,
98
+ "зык": 96,
99
+ "яз": 97,
100
+ "зы": 98,
101
+ "ык": 99,
102
+ "уп": 100,
103
+ "тор": 101,
104
+ "язы": 102,
105
+ "им ": 103,
106
+ "од": 104,
107
+ "пн": 105,
108
+ "не": 106,
109
+ "йш": 107,
110
+ " яз": 108,
111
+ "им": 109,
112
+ "ык ": 110,
113
+ "к я": 111,
114
+ "я о": 112,
115
+ " из": 113,
116
+ "ённ": 114,
117
+ "нны": 115,
118
+ "ных": 116,
119
+ "х я": 117,
120
+ "ыко": 118,
121
+ "ков": 119,
122
+ "ов ": 120,
123
+ "м и": 121,
124
+ "из ": 122,
125
+ "з с": 123,
126
+ " са": 124,
127
+ "сам": 125,
128
+ "амы": 126,
129
+ "мых": 127,
130
+ "х р": 128,
131
+ " ра": 129,
132
+ "рас": 130,
133
+ "асп": 131,
134
+ "спр": 132,
135
+ "ним": 133,
136
+ "дни": 134,
137
+ "про": 135,
138
+ "ост": 136,
139
+ "анё": 137,
140
+ "нён": 138,
141
+ "одн": 139,
142
+ " од": 140,
143
+ "в в": 141,
144
+ "род": 142,
145
+ "одо": 143,
146
+ "дом": 144,
147
+ "ом ": 145,
148
+ "м с": 146,
149
+ "аны": 147,
150
+ "ны ": 148,
151
+ "ы с": 149,
152
+ " с ": 150,
153
+ "с б": 151,
154
+ " бо": 152,
155
+ "бог": 153,
156
+ "ога": 154,
157
+ "гат": 155,
158
+ "ато": 156,
159
+ "той": 157,
160
+ " ис": 158,
161
+ "ист": 159,
162
+ "рие": 160,
163
+ "ией": 161,
164
+ " ку": 162,
165
+ "кул": 163,
166
+ "уль": 164,
167
+ "льт": 165,
168
+ "ьту": 166,
169
+ "тур": 167,
170
+ "уро": 168,
171
+ "рой": 169,
172
+ " в ": 170,
173
+ "в м": 171,
174
+ "ире": 172,
175
+ "ре ": 173,
176
+ "е м": 174,
177
+ " мо": 175,
178
+ "мос": 176,
179
+ "оск": 177,
180
+ "скв": 178,
181
+ "ква": 179,
182
+ "ва ": 180,
183
+ "а я": 181,
184
+ "я с": 182,
185
+ "тол": 183,
186
+ "оли": 184,
187
+ "лиц": 185,
188
+ "ице": 186,
189
+ "цей": 187,
190
+ "й р": 188,
191
+ " ро": 189,
192
+ "сии": 190,
193
+ "и и": 191,
194
+ "йши": 192,
195
+ "шим": 193,
196
+ "м г": 194,
197
+ " го": 195,
198
+ "гор": 196,
199
+ "оро": 197,
200
+ "ше": 198,
201
+ "нё": 199,
202
+ "ён": 200,
203
+ "нн": 201,
204
+ "ко": 202,
205
+ "ов": 203,
206
+ " в": 204,
207
+ "ре": 205,
208
+ "е ": 206,
209
+ "мо": 207,
210
+ "кв": 208,
211
+ "ва": 209,
212
+ "ол": 210,
213
+ "ли": 211,
214
+ "иц": 212,
215
+ "це": 213,
216
+ "ши": 214,
217
+ " г": 215,
218
+ "го": 216,
219
+ "до": 217,
220
+ "ом": 218,
221
+ "ы ": 219,
222
+ "с ": 220,
223
+ " б": 221,
224
+ "бо": 222,
225
+ "но": 223,
226
+ " п": 224,
227
+ "по": 225,
228
+ "о ": 226,
229
+ " т": 227,
230
+ "те": 228,
231
+ "ер": 229,
232
+ "рр": 230,
233
+ "ит": 231,
234
+ "ус": 232,
235
+ "ки": 233,
236
+ "ий": 234,
237
+ "к ": 235,
238
+ " о": 236,
239
+ "дн": 237,
240
+ "ни": 238,
241
+ "из": 239,
242
+ "з ": 240,
243
+ "са": 241,
244
+ "ам": 242,
245
+ "мы": 243,
246
+ "ас": 244,
247
+ "сп": 245,
248
+ "пр": 246,
249
+ "ной": 247,
250
+ "й м": 248,
251
+ "ира": 249,
252
+ "ра ": 250,
253
+ "а п": 251,
254
+ " по": 252,
255
+ "по ": 253,
256
+ "о т": 254,
257
+ " те": 255,
258
+ "тер": 256,
259
+ "ерр": 257,
260
+ "рри": 258,
261
+ "рит": 259,
262
+ "ито": 260,
263
+ "рии": 261,
264
+ "и р": 262,
265
+ " ру": 263,
266
+ "рус": 264,
267
+ "усс": 265,
268
+ "сск": 266,
269
+ "ски": 267,
270
+ "кий": 268,
271
+ "ий ": 269,
272
+ "й я": 270,
273
+ "ог": 271,
274
+ "га": 272,
275
+ "ат": 273,
276
+ "ис": 274,
277
+ "ие": 275,
278
+ "ку": 276,
279
+ "ул": 277,
280
+ "ль": 278,
281
+ "ьт": 279,
282
+ "ту": 280,
283
+ "ур": 281,
284
+ "сия": 282,
285
+ "ия ": 283,
286
+ "я я": 284,
287
+ "ия": 285,
288
+ "ь": 286,
289
+ "б": 287,
290
+ "ц": 288,
291
+ "я к": 289,
292
+ "йше": 290,
293
+ "шей": 291,
294
+ "ё": 292,
295
+ "й с": 293,
296
+ "ано": 294
297
+ }