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 +1,234 @@
1
+ {
2
+ "ا": 0,
3
+ "ی": 1,
4
+ "ر": 2,
5
+ "ن": 3,
6
+ "ت": 4,
7
+ "ن ": 5,
8
+ "ان": 6,
9
+ "ان ": 7,
10
+ " ا": 8,
11
+ "س": 9,
12
+ "و": 10,
13
+ "ای": 11,
14
+ "ب": 12,
15
+ "ست": 13,
16
+ "ک": 14,
17
+ "ش": 15,
18
+ "ت ": 16,
19
+ "ران": 17,
20
+ "ر ": 18,
21
+ "ی ": 19,
22
+ "د": 20,
23
+ "را": 21,
24
+ "ز": 22,
25
+ "ه": 23,
26
+ "‌": 24,
27
+ "اس": 25,
28
+ " ای": 26,
29
+ "یرا": 27,
30
+ " اس": 28,
31
+ "است": 29,
32
+ "ر ا": 30,
33
+ "ایر": 31,
34
+ "ری": 32,
35
+ "شو": 33,
36
+ "تا": 34,
37
+ "و ": 35,
38
+ " و ": 36,
39
+ "یر": 37,
40
+ "ین ": 38,
41
+ " و": 39,
42
+ "ین": 40,
43
+ " ت": 41,
44
+ "هر": 42,
45
+ "تر": 43,
46
+ "‌ت": 44,
47
+ "ها": 45,
48
+ "می": 46,
49
+ "ی‌": 47,
50
+ "ن و": 48,
51
+ "تان": 49,
52
+ "ستا": 50,
53
+ "ن ا": 51,
54
+ "رین": 52,
55
+ "تری": 53,
56
+ "‌تر": 54,
57
+ "می‌": 55,
58
+ "بان": 56,
59
+ "زبا": 57,
60
+ " زب": 58,
61
+ "ست ": 59,
62
+ "در ": 60,
63
+ " در": 61,
64
+ "شور": 62,
65
+ "کشو": 63,
66
+ " کش": 64,
67
+ "ن ک": 65,
68
+ "در": 66,
69
+ "م": 67,
70
+ " د": 68,
71
+ "ور": 69,
72
+ "کش": 70,
73
+ "ج": 71,
74
+ "یک": 72,
75
+ "سی": 73,
76
+ " ک": 74,
77
+ "ف": 75,
78
+ " ز": 76,
79
+ "زب": 77,
80
+ "غ": 78,
81
+ "با": 79,
82
+ "هان": 80,
83
+ "ص": 81,
84
+ "ت و": 82,
85
+ "جی": 83,
86
+ "و د": 84,
87
+ "ق": 85,
88
+ " اف": 86,
89
+ "افغ": 87,
90
+ "فغا": 88,
91
+ "غان": 89,
92
+ "انس": 90,
93
+ "نست": 91,
94
+ "ز ق": 92,
95
+ " قد": 93,
96
+ "قدی": 94,
97
+ "دیم": 95,
98
+ "یمی": 96,
99
+ "ی‌ت": 97,
100
+ "گ": 98,
101
+ "خ": 99,
102
+ "پ": 100,
103
+ "ح": 101,
104
+ "ن ز": 102,
105
+ "ان‌": 103,
106
+ "ن‌ه": 104,
107
+ "‌ها": 105,
108
+ "های": 106,
109
+ "ای ": 107,
110
+ "ی ج": 108,
111
+ " جه": 109,
112
+ "جها": 110,
113
+ "آ": 111,
114
+ "هرا": 112,
115
+ "ن پ": 113,
116
+ " پا": 114,
117
+ "پای": 115,
118
+ "ایت": 116,
119
+ "یتخ": 117,
120
+ "تخت": 118,
121
+ "خت ": 119,
122
+ "ت ا": 120,
123
+ "و ب": 121,
124
+ " بز": 122,
125
+ "بزر": 123,
126
+ "زرگ": 124,
127
+ "رگ‌": 125,
128
+ "گ‌ت": 126,
129
+ "ن ش": 127,
130
+ " شه": 128,
131
+ "شهر": 129,
132
+ "هر ": 130,
133
+ "این": 131,
134
+ "ور ": 132,
135
+ "و ت": 133,
136
+ " تا": 134,
137
+ "تاج": 135,
138
+ "اجی": 136,
139
+ "جیک": 137,
140
+ "یکس": 138,
141
+ "کست": 139,
142
+ "ن ص": 140,
143
+ " صح": 141,
144
+ "صحب": 142,
145
+ "حبت": 143,
146
+ "بت ": 144,
147
+ "ت م": 145,
148
+ " می": 146,
149
+ "ی‌ش": 147,
150
+ "‌شو": 148,
151
+ "شود": 149,
152
+ "ود ": 150,
153
+ "د ت": 151,
154
+ " ته": 152,
155
+ "تهر": 153,
156
+ "کس": 154,
157
+ " ص": 155,
158
+ "صح": 156,
159
+ "حب": 157,
160
+ "بت": 158,
161
+ " م": 159,
162
+ "‌ش": 160,
163
+ "ود": 161,
164
+ "د ": 162,
165
+ "ته": 163,
166
+ " ف": 164,
167
+ " پ": 165,
168
+ "پا": 166,
169
+ "یت": 167,
170
+ "تخ": 168,
171
+ "خت": 169,
172
+ " ب": 170,
173
+ "بز": 171,
174
+ "آسی": 172,
175
+ "دی": 173,
176
+ "یم": 174,
177
+ "قد": 175,
178
+ " ق": 176,
179
+ "ز ": 177,
180
+ "از": 178,
181
+ "کی": 179,
182
+ "ن‌": 180,
183
+ "‌ه": 181,
184
+ " ج": 182,
185
+ "جه": 183,
186
+ " ی": 184,
187
+ "رس": 185,
188
+ "اف": 186,
189
+ "فغ": 187,
190
+ "غا": 188,
191
+ "نس": 189,
192
+ "ار": 190,
193
+ "فا": 191,
194
+ "اج": 192,
195
+ "سیا": 193,
196
+ "یا ": 194,
197
+ "ا ا": 195,
198
+ "غر": 196,
199
+ " غ": 197,
200
+ "ت ز": 198,
201
+ "ن ف": 199,
202
+ " فا": 200,
203
+ "فار": 201,
204
+ "ارس": 202,
205
+ "رسی": 203,
206
+ "سی ": 204,
207
+ "ی ی": 205,
208
+ " یک": 206,
209
+ "یکی": 207,
210
+ "کی ": 208,
211
+ "ی ا": 209,
212
+ " از": 210,
213
+ "از ": 211,
214
+ "زر": 212,
215
+ "رگ": 213,
216
+ "گ‌": 214,
217
+ " ش": 215,
218
+ "شه": 216,
219
+ "ا ": 217,
220
+ "یا": 218,
221
+ "آس": 219,
222
+ " آ": 220,
223
+ "وری": 221,
224
+ "ری ": 222,
225
+ "ی د": 223,
226
+ "ب ": 224,
227
+ "رب": 225,
228
+ "ر غ": 226,
229
+ " غر": 227,
230
+ "غرب": 228,
231
+ "رب ": 229,
232
+ "ب آ": 230,
233
+ " آس": 231
234
+ }
@@ -0,0 +1,284 @@
1
+ {
2
+ "a": 0,
3
+ "n": 1,
4
+ "i": 2,
5
+ "u": 3,
6
+ "s": 4,
7
+ "t": 5,
8
+ "o": 6,
9
+ "n ": 7,
10
+ "aa": 8,
11
+ "k": 9,
12
+ "ta": 10,
13
+ "e": 11,
14
+ "st": 12,
15
+ "m": 13,
16
+ "a ": 14,
17
+ "is": 15,
18
+ "an": 16,
19
+ "taa": 17,
20
+ "aan": 18,
21
+ "h": 19,
22
+ "sta": 20,
23
+ "an ": 21,
24
+ "un": 22,
25
+ "i ": 23,
26
+ "uo": 24,
27
+ "ist": 25,
28
+ "l": 26,
29
+ "r": 27,
30
+ "j": 28,
31
+ "p": 29,
32
+ "ki": 30,
33
+ " s": 31,
34
+ "suo": 32,
35
+ "uom": 33,
36
+ "tu": 34,
37
+ "ä": 35,
38
+ "su": 36,
39
+ "om": 37,
40
+ "mi": 38,
41
+ "on": 39,
42
+ "uu": 40,
43
+ "au": 41,
44
+ "ri": 42,
45
+ " k": 43,
46
+ " m": 44,
47
+ " j": 45,
48
+ "nn": 46,
49
+ "n k": 47,
50
+ " su": 48,
51
+ "ja": 49,
52
+ " ja": 50,
53
+ "ur": 51,
54
+ "ja ": 52,
55
+ " p": 53,
56
+ "as": 54,
57
+ "ne": 55,
58
+ "uur": 56,
59
+ "uri": 57,
60
+ "et": 58,
61
+ "tuu": 59,
62
+ "ris": 60,
63
+ "aun": 61,
64
+ "ka": 62,
65
+ " t": 63,
66
+ "iis": 64,
67
+ "tä ": 65,
68
+ "nki": 66,
69
+ "ki ": 67,
70
+ "n s": 68,
71
+ "en ": 69,
72
+ "men": 70,
73
+ "ome": 71,
74
+ "kau": 72,
75
+ " tu": 73,
76
+ "tun": 74,
77
+ "unn": 75,
78
+ "nne": 76,
79
+ "net": 77,
80
+ "eta": 78,
81
+ "aa ": 79,
82
+ "n m": 80,
83
+ "on ": 81,
84
+ " on": 82,
85
+ "i o": 83,
86
+ "mi ": 84,
87
+ "omi": 85,
88
+ "ii": 86,
89
+ "ast": 87,
90
+ "in": 88,
91
+ "no": 89,
92
+ "pu": 90,
93
+ "ä ": 91,
94
+ "tä": 92,
95
+ "lt": 93,
96
+ "el": 94,
97
+ "en": 95,
98
+ "me": 96,
99
+ "sa": 97,
100
+ "oo": 98,
101
+ "s ": 99,
102
+ "oi": 100,
103
+ "jo": 101,
104
+ " o": 102,
105
+ "na": 103,
106
+ " h": 104,
107
+ "nk": 105,
108
+ "n j": 106,
109
+ "si": 107,
110
+ "ink": 108,
111
+ "upu": 109,
112
+ "onn": 110,
113
+ "uon": 111,
114
+ "n p": 112,
115
+ "aup": 113,
116
+ "luo": 114,
117
+ " lu": 115,
118
+ "ltt": 116,
119
+ "a l": 117,
120
+ "ult": 118,
121
+ "ttu": 119,
122
+ " pä": 120,
123
+ "äka": 121,
124
+ "pää": 122,
125
+ "ääk": 123,
126
+ "ilj": 124,
127
+ "ljo": 125,
128
+ "joo": 126,
129
+ "oon": 127,
130
+ "ona": 128,
131
+ "ost": 129,
132
+ "naa": 130,
133
+ "a i": 131,
134
+ " ih": 132,
135
+ "ihm": 133,
136
+ "hmi": 134,
137
+ "mis": 135,
138
+ "nos": 136,
139
+ "stä": 137,
140
+ "ä h": 138,
141
+ " he": 139,
142
+ "hel": 140,
143
+ "els": 141,
144
+ "lsi": 142,
145
+ "sin": 143,
146
+ "nno": 144,
147
+ "kul": 145,
148
+ " ka": 146,
149
+ " ku": 147,
150
+ "uni": 148,
151
+ "nii": 149,
152
+ "ori": 150,
153
+ "ta ": 151,
154
+ "a a": 152,
155
+ " ar": 153,
156
+ "ark": 154,
157
+ "rkk": 155,
158
+ "kki": 156,
159
+ "kit": 157,
160
+ "ite": 158,
161
+ "ias": 159,
162
+ "teh": 160,
163
+ "eht": 161,
164
+ "htu": 162,
165
+ "ria": 163,
166
+ "pun": 164,
167
+ "unk": 165,
168
+ "i j": 166,
169
+ "nas": 167,
170
+ "una": 168,
171
+ "a t": 169,
172
+ "sau": 170,
173
+ " sa": 171,
174
+ "s s": 172,
175
+ "a h": 173,
176
+ " hi": 174,
177
+ "ös ": 175,
178
+ "his": 176,
179
+ "sto": 177,
180
+ "tor": 178,
181
+ "yös": 179,
182
+ "myö": 180,
183
+ " my": 181,
184
+ "i t": 182,
185
+ "he": 183,
186
+ "ls": 184,
187
+ "pä": 185,
188
+ "ää": 186,
189
+ "äk": 187,
190
+ "up": 188,
191
+ "ni": 189,
192
+ " a": 190,
193
+ "ar": 191,
194
+ "rk": 192,
195
+ "kk": 193,
196
+ "it": 194,
197
+ "te": 195,
198
+ "eh": 196,
199
+ "ht": 197,
200
+ "ku": 198,
201
+ "ul": 199,
202
+ "tt": 200,
203
+ "hi": 201,
204
+ "to": 202,
205
+ "or": 203,
206
+ "ia": 204,
207
+ "my": 205,
208
+ "yö": 206,
209
+ "a s": 207,
210
+ "v": 208,
211
+ "y": 209,
212
+ "ö": 210,
213
+ "ma": 211,
214
+ "po": 212,
215
+ "oh": 213,
216
+ "hj": 214,
217
+ " e": 215,
218
+ "eu": 216,
219
+ "ro": 217,
220
+ "op": 218,
221
+ "pa": 219,
222
+ "ss": 220,
223
+ "ie": 221,
224
+ "uh": 222,
225
+ "hu": 223,
226
+ "u ": 224,
227
+ " n": 225,
228
+ " v": 226,
229
+ "vi": 227,
230
+ "il": 228,
231
+ "lj": 229,
232
+ " i": 230,
233
+ "ih": 231,
234
+ "hm": 232,
235
+ " ki": 233,
236
+ "kie": 234,
237
+ "iel": 235,
238
+ "elt": 236,
239
+ "ltä": 237,
240
+ "ä p": 238,
241
+ " pu": 239,
242
+ "puh": 240,
243
+ "uhu": 241,
244
+ "huu": 242,
245
+ "uu ": 243,
246
+ "u n": 244,
247
+ " no": 245,
248
+ "noi": 246,
249
+ "oin": 247,
250
+ "in ": 248,
251
+ "n v": 249,
252
+ " vi": 250,
253
+ "vii": 251,
254
+ "isi": 252,
255
+ "si ": 253,
256
+ "i m": 254,
257
+ " mi": 255,
258
+ "mil": 256,
259
+ "ös": 257,
260
+ " l": 258,
261
+ "lu": 259,
262
+ "os": 260,
263
+ " ma": 261,
264
+ "maa": 262,
265
+ "a p": 263,
266
+ " po": 264,
267
+ "poh": 265,
268
+ "ohj": 266,
269
+ "hjo": 267,
270
+ "joi": 268,
271
+ "ois": 269,
272
+ "is ": 270,
273
+ "s e": 271,
274
+ " eu": 272,
275
+ "eur": 273,
276
+ "uro": 274,
277
+ "roo": 275,
278
+ "oop": 276,
279
+ "opa": 277,
280
+ "pas": 278,
281
+ "ass": 279,
282
+ "ssa": 280,
283
+ "sa ": 281
284
+ }