language_detector 0.1.0
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.
- data/README.rdoc +24 -0
- data/Rakefile +18 -0
- data/VERSION +1 -0
- data/lib/language_detector.rb +232 -0
- data/lib/model-fm.yml +52504 -0
- data/lib/model-tc.yml +53985 -0
- data/lib/textcat_ngrams/afrikaans.lm +400 -0
- data/lib/textcat_ngrams/albanian.lm +400 -0
- data/lib/textcat_ngrams/amharic-utf.lm +400 -0
- data/lib/textcat_ngrams/arabic-iso8859_6.lm +400 -0
- data/lib/textcat_ngrams/arabic-windows1256.lm +400 -0
- data/lib/textcat_ngrams/armenian.lm +400 -0
- data/lib/textcat_ngrams/basque.lm +400 -0
- data/lib/textcat_ngrams/belarus-windows1251.lm +400 -0
- data/lib/textcat_ngrams/bosnian.lm +400 -0
- data/lib/textcat_ngrams/breton.lm +400 -0
- data/lib/textcat_ngrams/bulgarian-iso8859_5.lm +400 -0
- data/lib/textcat_ngrams/catalan.lm +400 -0
- data/lib/textcat_ngrams/chinese-big5.lm +400 -0
- data/lib/textcat_ngrams/chinese-gb2312.lm +400 -0
- data/lib/textcat_ngrams/croatian-ascii.lm +400 -0
- data/lib/textcat_ngrams/czech-iso8859_2.lm +400 -0
- data/lib/textcat_ngrams/danish.lm +400 -0
- data/lib/textcat_ngrams/dutch.lm +400 -0
- data/lib/textcat_ngrams/english.lm +400 -0
- data/lib/textcat_ngrams/esperanto.lm +400 -0
- data/lib/textcat_ngrams/estonian.lm +400 -0
- data/lib/textcat_ngrams/finnish.lm +400 -0
- data/lib/textcat_ngrams/french.lm +400 -0
- data/lib/textcat_ngrams/frisian.lm +400 -0
- data/lib/textcat_ngrams/georgian.lm +400 -0
- data/lib/textcat_ngrams/german.lm +400 -0
- data/lib/textcat_ngrams/greek-iso8859-7.lm +400 -0
- data/lib/textcat_ngrams/hebrew-iso8859_8.lm +400 -0
- data/lib/textcat_ngrams/hindi.lm +400 -0
- data/lib/textcat_ngrams/hungarian.lm +400 -0
- data/lib/textcat_ngrams/icelandic.lm +400 -0
- data/lib/textcat_ngrams/indonesian.lm +400 -0
- data/lib/textcat_ngrams/irish.lm +400 -0
- data/lib/textcat_ngrams/italian.lm +400 -0
- data/lib/textcat_ngrams/japanese-euc_jp.lm +400 -0
- data/lib/textcat_ngrams/japanese-shift_jis.lm +400 -0
- data/lib/textcat_ngrams/korean.lm +400 -0
- data/lib/textcat_ngrams/latin.lm +400 -0
- data/lib/textcat_ngrams/latvian.lm +400 -0
- data/lib/textcat_ngrams/lithuanian.lm +400 -0
- data/lib/textcat_ngrams/malay.lm +400 -0
- data/lib/textcat_ngrams/manx.lm +400 -0
- data/lib/textcat_ngrams/marathi.lm +400 -0
- data/lib/textcat_ngrams/mingo.lm +400 -0
- data/lib/textcat_ngrams/nepali.lm +400 -0
- data/lib/textcat_ngrams/norwegian.lm +400 -0
- data/lib/textcat_ngrams/persian.lm +400 -0
- data/lib/textcat_ngrams/polish.lm +400 -0
- data/lib/textcat_ngrams/portuguese.lm +400 -0
- data/lib/textcat_ngrams/quechua.lm +400 -0
- data/lib/textcat_ngrams/romanian.lm +400 -0
- data/lib/textcat_ngrams/rumantsch.lm +400 -0
- data/lib/textcat_ngrams/russian-iso8859_5.lm +400 -0
- data/lib/textcat_ngrams/russian-koi8_r.lm +400 -0
- data/lib/textcat_ngrams/russian-windows1251.lm +400 -0
- data/lib/textcat_ngrams/sanskrit.lm +400 -0
- data/lib/textcat_ngrams/scots.lm +400 -0
- data/lib/textcat_ngrams/scots_gaelic.lm +400 -0
- data/lib/textcat_ngrams/serbian-ascii.lm +400 -0
- data/lib/textcat_ngrams/slovak-ascii.lm +400 -0
- data/lib/textcat_ngrams/slovak-windows1250.lm +400 -0
- data/lib/textcat_ngrams/slovenian-ascii.lm +400 -0
- data/lib/textcat_ngrams/slovenian-iso8859_2.lm +400 -0
- data/lib/textcat_ngrams/spanish.lm +400 -0
- data/lib/textcat_ngrams/swahili.lm +400 -0
- data/lib/textcat_ngrams/swedish.lm +400 -0
- data/lib/textcat_ngrams/tagalog.lm +400 -0
- data/lib/textcat_ngrams/tamil.lm +400 -0
- data/lib/textcat_ngrams/thai.lm +400 -0
- data/lib/textcat_ngrams/turkish.lm +400 -0
- data/lib/textcat_ngrams/ukrainian-koi8_u.lm +400 -0
- data/lib/textcat_ngrams/vietnamese.lm +400 -0
- data/lib/textcat_ngrams/welsh.lm +400 -0
- data/lib/textcat_ngrams/yiddish-utf.lm +400 -0
- data/lib/training_data/ar-utf8.txt +54 -0
- data/lib/training_data/bg-utf8.txt +26 -0
- data/lib/training_data/cs-utf8.txt +48 -0
- data/lib/training_data/da-utf8.txt +159 -0
- data/lib/training_data/de-utf8.txt +569 -0
- data/lib/training_data/el-utf8.txt +48 -0
- data/lib/training_data/en-utf8.txt +81 -0
- data/lib/training_data/es-utf8.txt +185 -0
- data/lib/training_data/et-utf8.txt +50 -0
- data/lib/training_data/fa-utf8.txt +42 -0
- data/lib/training_data/fi-utf8.txt +83 -0
- data/lib/training_data/fr-utf8.txt +191 -0
- data/lib/training_data/fy-utf8.txt +22 -0
- data/lib/training_data/ga-utf8.txt +109 -0
- data/lib/training_data/he-utf8.txt +116 -0
- data/lib/training_data/hi-utf8.txt +49 -0
- data/lib/training_data/hr-utf8.txt +80 -0
- data/lib/training_data/hu-utf8.txt +87 -0
- data/lib/training_data/io-utf8.txt +41 -0
- data/lib/training_data/is-utf8.txt +94 -0
- data/lib/training_data/it-utf8.txt +228 -0
- data/lib/training_data/ja-utf8.txt +200 -0
- data/lib/training_data/ko-utf8.txt +147 -0
- data/lib/training_data/nl-utf8.txt +215 -0
- data/lib/training_data/no-utf8.txt +281 -0
- data/lib/training_data/pl-utf8.txt +120 -0
- data/lib/training_data/pt-utf8.txt +214 -0
- data/lib/training_data/ro-utf8.txt +66 -0
- data/lib/training_data/ru-utf8.txt +310 -0
- data/lib/training_data/sl-utf8.txt +263 -0
- data/lib/training_data/sv-utf8.txt +174 -0
- data/lib/training_data/th-utf8.txt +49 -0
- data/lib/training_data/tk-utf8.txt +101 -0
- data/lib/training_data/todo/af.txt +114 -0
- data/lib/training_data/todo/amharic-utf.txt +95 -0
- data/lib/training_data/todo/arabic-windows1256.txt +157 -0
- data/lib/training_data/todo/armenian.txt +86 -0
- data/lib/training_data/todo/basque.txt +136 -0
- data/lib/training_data/todo/belarus-windows1251.txt +97 -0
- data/lib/training_data/todo/bosnian.txt +97 -0
- data/lib/training_data/todo/breton.txt +159 -0
- data/lib/training_data/todo/bulgarian-iso8859_5.txt +115 -0
- data/lib/training_data/todo/catalan.txt +93 -0
- data/lib/training_data/todo/croatian-ascii.txt +104 -0
- data/lib/training_data/todo/esperanto.txt +95 -0
- data/lib/training_data/todo/estonian.txt +218 -0
- data/lib/training_data/todo/frisian.txt +99 -0
- data/lib/training_data/todo/georgian.txt +86 -0
- data/lib/training_data/todo/greek-iso8859-7.txt +139 -0
- data/lib/training_data/todo/hawaian.txt +108 -0
- data/lib/training_data/todo/hebrew-iso8859_8.txt +79 -0
- data/lib/training_data/todo/hindi.txt +77 -0
- data/lib/training_data/todo/hungarian.txt +102 -0
- data/lib/training_data/todo/icelandic.txt +131 -0
- data/lib/training_data/todo/indonesian.txt +93 -0
- data/lib/training_data/todo/irish.txt +209 -0
- data/lib/training_data/todo/latin.txt +120 -0
- data/lib/training_data/todo/latvian.txt +126 -0
- data/lib/training_data/todo/lithuanian.txt +99 -0
- data/lib/training_data/todo/malay.txt +108 -0
- data/lib/training_data/todo/manx.txt +78 -0
- data/lib/training_data/todo/marathi.txt +100 -0
- data/lib/training_data/todo/mf.txt +100 -0
- data/lib/training_data/todo/middle_frisian.txt +102 -0
- data/lib/training_data/todo/mingo.txt +146 -0
- data/lib/training_data/todo/nepali.txt +131 -0
- data/lib/training_data/todo/persian.txt +73 -0
- data/lib/training_data/todo/quechua.txt +108 -0
- data/lib/training_data/todo/romanian.txt +103 -0
- data/lib/training_data/todo/rumantsch.txt +110 -0
- data/lib/training_data/todo/sanskrit.txt +135 -0
- data/lib/training_data/todo/scots.txt +490 -0
- data/lib/training_data/todo/scots_gaelic.txt +93 -0
- data/lib/training_data/todo/serbian-ascii.txt +121 -0
- data/lib/training_data/todo/slovak-ascii.txt +102 -0
- data/lib/training_data/todo/slovak-windows1250.txt +115 -0
- data/lib/training_data/todo/slovenian-ascii.txt +100 -0
- data/lib/training_data/todo/slovenian-iso8859_2.txt +96 -0
- data/lib/training_data/todo/sq.txt +110 -0
- data/lib/training_data/todo/swahili.txt +120 -0
- data/lib/training_data/todo/tagalog.txt +135 -0
- data/lib/training_data/todo/tamil.txt +123 -0
- data/lib/training_data/todo/turkish.txt +117 -0
- data/lib/training_data/todo/ukrainian-koi8_r.txt +214 -0
- data/lib/training_data/todo/vietnamese.txt +92 -0
- data/lib/training_data/todo/welsh.txt +148 -0
- data/lib/training_data/todo/yiddish-utf.txt +83 -0
- data/lib/training_data/uk-utf8.txt +75 -0
- data/lib/training_data/vi-utf8.txt +47 -0
- data/lib/training_data/zh-utf8.txt +228 -0
- data/test/language_detector_test.rb +78 -0
- metadata +232 -0
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 23602
|
2
|
+
e 8036
|
3
|
+
a 4087
|
4
|
+
n 3782
|
5
|
+
i 3726
|
6
|
+
o 3314
|
7
|
+
r 2951
|
8
|
+
s 2885
|
9
|
+
t 2749
|
10
|
+
d 2479
|
11
|
+
e_ 2118
|
12
|
+
l 1854
|
13
|
+
k 1741
|
14
|
+
ie 1670
|
15
|
+
g 1601
|
16
|
+
n_ 1447
|
17
|
+
m 1440
|
18
|
+
_d 1219
|
19
|
+
t_ 1143
|
20
|
+
er 1124
|
21
|
+
h 1124
|
22
|
+
u 1110
|
23
|
+
ie_ 1079
|
24
|
+
y 1048
|
25
|
+
w 986
|
26
|
+
s_ 982
|
27
|
+
_s 969
|
28
|
+
_h 956
|
29
|
+
di 924
|
30
|
+
an 922
|
31
|
+
r_ 912
|
32
|
+
aa 882
|
33
|
+
v 876
|
34
|
+
en 807
|
35
|
+
_di 807
|
36
|
+
. 790
|
37
|
+
y_ 747
|
38
|
+
_v 709
|
39
|
+
et 706
|
40
|
+
._ 694
|
41
|
+
die 691
|
42
|
+
die_ 667
|
43
|
+
_n 666
|
44
|
+
_die 651
|
45
|
+
p 639
|
46
|
+
_m 634
|
47
|
+
_die_ 633
|
48
|
+
_w 632
|
49
|
+
ee 607
|
50
|
+
ge 606
|
51
|
+
_o 598
|
52
|
+
b 586
|
53
|
+
te 568
|
54
|
+
, 560
|
55
|
+
in 555
|
56
|
+
k_ 550
|
57
|
+
_e 550
|
58
|
+
,_ 548
|
59
|
+
oo 516
|
60
|
+
et_ 511
|
61
|
+
de 509
|
62
|
+
el 489
|
63
|
+
_g 486
|
64
|
+
f 461
|
65
|
+
ar 451
|
66
|
+
ni 450
|
67
|
+
nd 442
|
68
|
+
an_ 440
|
69
|
+
en_ 437
|
70
|
+
_i 426
|
71
|
+
he 423
|
72
|
+
g_ 418
|
73
|
+
_t 412
|
74
|
+
oe 410
|
75
|
+
at 406
|
76
|
+
er_ 400
|
77
|
+
om 381
|
78
|
+
wa 378
|
79
|
+
_a 378
|
80
|
+
_b 377
|
81
|
+
_k 371
|
82
|
+
nie 371
|
83
|
+
_he 370
|
84
|
+
aar 355
|
85
|
+
_ge 351
|
86
|
+
es 351
|
87
|
+
_ni 348
|
88
|
+
da 346
|
89
|
+
m_ 342
|
90
|
+
ou 338
|
91
|
+
it 335
|
92
|
+
_nie 335
|
93
|
+
d_ 332
|
94
|
+
l_ 330
|
95
|
+
_wa 329
|
96
|
+
or 327
|
97
|
+
le 326
|
98
|
+
we 326
|
99
|
+
ek 324
|
100
|
+
het 321
|
101
|
+
me 319
|
102
|
+
_het 319
|
103
|
+
is 318
|
104
|
+
j 315
|
105
|
+
at_ 311
|
106
|
+
on 309
|
107
|
+
se 308
|
108
|
+
_en 298
|
109
|
+
ma 294
|
110
|
+
st 291
|
111
|
+
as 280
|
112
|
+
va 277
|
113
|
+
_en_ 270
|
114
|
+
re 270
|
115
|
+
" 269
|
116
|
+
' 265
|
117
|
+
het_ 261
|
118
|
+
_het_ 260
|
119
|
+
om_ 254
|
120
|
+
al 252
|
121
|
+
ar_ 250
|
122
|
+
li 248
|
123
|
+
te_ 247
|
124
|
+
aar_ 247
|
125
|
+
_da 245
|
126
|
+
u_ 242
|
127
|
+
nde 241
|
128
|
+
ou_ 237
|
129
|
+
_l 231
|
130
|
+
be 229
|
131
|
+
_' 226
|
132
|
+
rd 224
|
133
|
+
_va 224
|
134
|
+
ig 223
|
135
|
+
ng 222
|
136
|
+
ns 221
|
137
|
+
ve 220
|
138
|
+
it_ 218
|
139
|
+
_j 216
|
140
|
+
_me 216
|
141
|
+
sy 215
|
142
|
+
ke 213
|
143
|
+
_sy 212
|
144
|
+
aan 212
|
145
|
+
van 212
|
146
|
+
_in 210
|
147
|
+
is_ 210
|
148
|
+
in_ 208
|
149
|
+
sy_ 206
|
150
|
+
_sy_ 206
|
151
|
+
'n 205
|
152
|
+
ro 205
|
153
|
+
ko 204
|
154
|
+
_'n 203
|
155
|
+
ra 203
|
156
|
+
'n_ 203
|
157
|
+
_'n_ 202
|
158
|
+
so 202
|
159
|
+
D 202
|
160
|
+
ho 201
|
161
|
+
rs 200
|
162
|
+
eer 200
|
163
|
+
ik 199
|
164
|
+
la 198
|
165
|
+
_te 196
|
166
|
+
_van 196
|
167
|
+
_ma 195
|
168
|
+
as_ 194
|
169
|
+
ui 194
|
170
|
+
ver 192
|
171
|
+
e. 192
|
172
|
+
der 191
|
173
|
+
to 188
|
174
|
+
op 187
|
175
|
+
van_ 184
|
176
|
+
ag 184
|
177
|
+
_ve 182
|
178
|
+
and 180
|
179
|
+
_van_ 178
|
180
|
+
ha 178
|
181
|
+
f_ 176
|
182
|
+
ka 176
|
183
|
+
ne 175
|
184
|
+
_is 175
|
185
|
+
sk 174
|
186
|
+
e._ 174
|
187
|
+
oor 174
|
188
|
+
_ver 170
|
189
|
+
ek_ 170
|
190
|
+
_hy 170
|
191
|
+
hy 170
|
192
|
+
p_ 168
|
193
|
+
_be 168
|
194
|
+
ri 168
|
195
|
+
ur 167
|
196
|
+
nie_ 165
|
197
|
+
_so 165
|
198
|
+
_D 164
|
199
|
+
si 164
|
200
|
+
ll 164
|
201
|
+
no 164
|
202
|
+
_in_ 163
|
203
|
+
_hy_ 162
|
204
|
+
hy_ 162
|
205
|
+
ed 161
|
206
|
+
ers 160
|
207
|
+
_r 156
|
208
|
+
ak 156
|
209
|
+
_ho 155
|
210
|
+
_nie_ 153
|
211
|
+
eg 153
|
212
|
+
nt 152
|
213
|
+
de_ 152
|
214
|
+
_p 151
|
215
|
+
_we 148
|
216
|
+
_is_ 148
|
217
|
+
ei 147
|
218
|
+
es_ 142
|
219
|
+
maa 142
|
220
|
+
wee 142
|
221
|
+
na 141
|
222
|
+
nder 139
|
223
|
+
a_ 138
|
224
|
+
ing 138
|
225
|
+
ew 138
|
226
|
+
S 135
|
227
|
+
lle 135
|
228
|
+
_om 135
|
229
|
+
_te_ 134
|
230
|
+
eu 134
|
231
|
+
ie. 134
|
232
|
+
wo 132
|
233
|
+
em 132
|
234
|
+
wat 131
|
235
|
+
_no 130
|
236
|
+
_" 130
|
237
|
+
vo 130
|
238
|
+
E 129
|
239
|
+
H 128
|
240
|
+
_wat 127
|
241
|
+
ti 126
|
242
|
+
mo 126
|
243
|
+
A 126
|
244
|
+
e, 126
|
245
|
+
_ha 125
|
246
|
+
vi 125
|
247
|
+
el_ 125
|
248
|
+
ter 125
|
249
|
+
e,_ 124
|
250
|
+
dat 124
|
251
|
+
eer_ 124
|
252
|
+
wat_ 124
|
253
|
+
le_ 124
|
254
|
+
ta 124
|
255
|
+
Di 123
|
256
|
+
dat_ 123
|
257
|
+
_wat_ 122
|
258
|
+
ie._ 122
|
259
|
+
was 121
|
260
|
+
ste 121
|
261
|
+
_H 121
|
262
|
+
_se 121
|
263
|
+
se_ 120
|
264
|
+
ul 120
|
265
|
+
al_ 120
|
266
|
+
_was 120
|
267
|
+
_om_ 119
|
268
|
+
_st 119
|
269
|
+
lik 118
|
270
|
+
"_ 118
|
271
|
+
_ko 118
|
272
|
+
_maa 118
|
273
|
+
lo 117
|
274
|
+
_to 117
|
275
|
+
ns_ 115
|
276
|
+
aan_ 115
|
277
|
+
nie. 114
|
278
|
+
_vi 114
|
279
|
+
met 114
|
280
|
+
_nie. 111
|
281
|
+
nk 110
|
282
|
+
_Di 110
|
283
|
+
- 110
|
284
|
+
_op 109
|
285
|
+
_oo 109
|
286
|
+
_on 108
|
287
|
+
ir 108
|
288
|
+
ord 108
|
289
|
+
uit 106
|
290
|
+
ens 105
|
291
|
+
_was_ 105
|
292
|
+
was_ 105
|
293
|
+
een 105
|
294
|
+
_met 105
|
295
|
+
os 105
|
296
|
+
_S 104
|
297
|
+
nie._ 104
|
298
|
+
ig_ 103
|
299
|
+
_sk 102
|
300
|
+
op_ 101
|
301
|
+
_ek 101
|
302
|
+
_wee 101
|
303
|
+
ir_ 101
|
304
|
+
met_ 100
|
305
|
+
_met_ 100
|
306
|
+
rt 100
|
307
|
+
ik_ 99
|
308
|
+
end 99
|
309
|
+
nd_ 99
|
310
|
+
gt 99
|
311
|
+
ond 98
|
312
|
+
ot 98
|
313
|
+
_aa 97
|
314
|
+
og 97
|
315
|
+
vir_ 95
|
316
|
+
vir 95
|
317
|
+
_ka 94
|
318
|
+
hu 94
|
319
|
+
_mo 94
|
320
|
+
_vir_ 94
|
321
|
+
_vir 94
|
322
|
+
_dit 93
|
323
|
+
kr 93
|
324
|
+
am 93
|
325
|
+
ol 93
|
326
|
+
dit 93
|
327
|
+
_ek_ 93
|
328
|
+
ki 93
|
329
|
+
sa 93
|
330
|
+
_aan 92
|
331
|
+
man 92
|
332
|
+
jy 92
|
333
|
+
ng_ 92
|
334
|
+
aak 92
|
335
|
+
lle_ 91
|
336
|
+
_hu 91
|
337
|
+
_na 91
|
338
|
+
_vo 90
|
339
|
+
ewe 90
|
340
|
+
of 90
|
341
|
+
jy_ 90
|
342
|
+
_dit_ 90
|
343
|
+
dit_ 90
|
344
|
+
_jy 89
|
345
|
+
der_ 89
|
346
|
+
jo 89
|
347
|
+
_f 88
|
348
|
+
_u 88
|
349
|
+
sie 87
|
350
|
+
_dat 87
|
351
|
+
_jy_ 87
|
352
|
+
daa 87
|
353
|
+
do 87
|
354
|
+
vr 87
|
355
|
+
wi 86
|
356
|
+
ry 86
|
357
|
+
_dat_ 86
|
358
|
+
eur 86
|
359
|
+
rs_ 85
|
360
|
+
_jo 85
|
361
|
+
_wo 84
|
362
|
+
_ne 84
|
363
|
+
jie 84
|
364
|
+
ji 84
|
365
|
+
pe 83
|
366
|
+
moe 83
|
367
|
+
my 82
|
368
|
+
ull 82
|
369
|
+
Die 81
|
370
|
+
maar 81
|
371
|
+
_hom 81
|
372
|
+
ulle 81
|
373
|
+
_maar 81
|
374
|
+
hom 81
|
375
|
+
_uit 80
|
376
|
+
_ui 80
|
377
|
+
ges 80
|
378
|
+
raa 80
|
379
|
+
or_ 80
|
380
|
+
ies 80
|
381
|
+
jou 79
|
382
|
+
_la 79
|
383
|
+
maar_ 79
|
384
|
+
ulle_ 79
|
385
|
+
_daa 79
|
386
|
+
Die_ 79
|
387
|
+
daar 78
|
388
|
+
_daar 78
|
389
|
+
ien 78
|
390
|
+
_my 78
|
391
|
+
_jou 78
|
392
|
+
ok 78
|
393
|
+
il 78
|
394
|
+
lik_ 77
|
395
|
+
sta 77
|
396
|
+
_Die 77
|
397
|
+
ur_ 77
|
398
|
+
ga 77
|
399
|
+
ag_ 77
|
400
|
+
kan 77
|
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 19480
|
2
|
+
� 4099
|
3
|
+
e 4082
|
4
|
+
t 3635
|
5
|
+
i 3134
|
6
|
+
a 2893
|
7
|
+
r 2820
|
8
|
+
n 2610
|
9
|
+
s 2380
|
10
|
+
h 2060
|
11
|
+
�_ 2055
|
12
|
+
e_ 1825
|
13
|
+
j 1677
|
14
|
+
u 1489
|
15
|
+
d 1381
|
16
|
+
o 1370
|
17
|
+
m 1318
|
18
|
+
k 1264
|
19
|
+
t� 1091
|
20
|
+
p 1072
|
21
|
+
_t 1068
|
22
|
+
sh 998
|
23
|
+
l 936
|
24
|
+
_n 876
|
25
|
+
a_ 822
|
26
|
+
, 816
|
27
|
+
,_ 808
|
28
|
+
t�_ 795
|
29
|
+
i_ 770
|
30
|
+
_p 739
|
31
|
+
_m 702
|
32
|
+
_s 700
|
33
|
+
te 653
|
34
|
+
�r 620
|
35
|
+
_d 613
|
36
|
+
_e 607
|
37
|
+
g 602
|
38
|
+
_k 601
|
39
|
+
_t� 593
|
40
|
+
. 575
|
41
|
+
_t�_ 574
|
42
|
+
v 567
|
43
|
+
_e_ 554
|
44
|
+
r_ 525
|
45
|
+
._ 523
|
46
|
+
ht 503
|
47
|
+
n_ 480
|
48
|
+
he 473
|
49
|
+
n� 462
|
50
|
+
sht 461
|
51
|
+
te_ 457
|
52
|
+
q 454
|
53
|
+
nd 436
|
54
|
+
ri 432
|
55
|
+
is 414
|
56
|
+
et 403
|
57
|
+
b 402
|
58
|
+
je 401
|
59
|
+
me 395
|
60
|
+
in 391
|
61
|
+
it 381
|
62
|
+
r� 374
|
63
|
+
_a 374
|
64
|
+
t_ 359
|
65
|
+
ur 353
|
66
|
+
_i 346
|
67
|
+
ar 342
|
68
|
+
�s 339
|
69
|
+
er 338
|
70
|
+
n�_ 338
|
71
|
+
�n 338
|
72
|
+
dh 337
|
73
|
+
en 336
|
74
|
+
p� 334
|
75
|
+
f 328
|
76
|
+
_v 323
|
77
|
+
j� 318
|
78
|
+
nj 313
|
79
|
+
ish 312
|
80
|
+
p�r 294
|
81
|
+
y 285
|
82
|
+
z 282
|
83
|
+
es 281
|
84
|
+
at 274
|
85
|
+
_me 273
|
86
|
+
_q 273
|
87
|
+
gj 269
|
88
|
+
ra 261
|
89
|
+
as 258
|
90
|
+
_n� 256
|
91
|
+
ku 256
|
92
|
+
j_ 250
|
93
|
+
ta 249
|
94
|
+
re 246
|
95
|
+
nj� 245
|
96
|
+
o_ 243
|
97
|
+
ni 243
|
98
|
+
_p� 240
|
99
|
+
hte 240
|
100
|
+
_nj 239
|
101
|
+
on 239
|
102
|
+
isht 236
|
103
|
+
pa 234
|
104
|
+
th 233
|
105
|
+
shte 233
|
106
|
+
_p�r 232
|
107
|
+
se 228
|
108
|
+
_g 223
|
109
|
+
ve 221
|
110
|
+
in_ 220
|
111
|
+
s_ 219
|
112
|
+
_n�_ 219
|
113
|
+
do 218
|
114
|
+
hte_ 218
|
115
|
+
m� 216
|
116
|
+
ti 215
|
117
|
+
aj 212
|
118
|
+
shte_ 212
|
119
|
+
ej 212
|
120
|
+
u_ 211
|
121
|
+
q� 211
|
122
|
+
_sh 210
|
123
|
+
nt 207
|
124
|
+
j�_ 206
|
125
|
+
_b 205
|
126
|
+
_nj� 203
|
127
|
+
di 202
|
128
|
+
_pa 201
|
129
|
+
_i_ 201
|
130
|
+
ll 199
|
131
|
+
_f 199
|
132
|
+
k� 198
|
133
|
+
me_ 197
|
134
|
+
dhe 195
|
135
|
+
ishte 195
|
136
|
+
si 194
|
137
|
+
hi 191
|
138
|
+
he_ 188
|
139
|
+
- 187
|
140
|
+
ja 187
|
141
|
+
_q� 187
|
142
|
+
ua 186
|
143
|
+
il 184
|
144
|
+
_dh 184
|
145
|
+
ur_ 183
|
146
|
+
�r_ 182
|
147
|
+
or 180
|
148
|
+
se_ 179
|
149
|
+
q�_ 178
|
150
|
+
S 176
|
151
|
+
� 175
|
152
|
+
_h 173
|
153
|
+
an 172
|
154
|
+
nj�_ 172
|
155
|
+
ng 170
|
156
|
+
nte 170
|
157
|
+
_q�_ 169
|
158
|
+
_S 169
|
159
|
+
r�_ 166
|
160
|
+
dhe_ 165
|
161
|
+
_me_ 164
|
162
|
+
ka 162
|
163
|
+
im 159
|
164
|
+
h� 158
|
165
|
+
mi 157
|
166
|
+
to 156
|
167
|
+
tu 156
|
168
|
+
�n_ 155
|
169
|
+
_nj�_ 154
|
170
|
+
ha 153
|
171
|
+
nte_ 150
|
172
|
+
tr 148
|
173
|
+
sa 148
|
174
|
+
�t 148
|
175
|
+
_gj 148
|
176
|
+
un 147
|
177
|
+
rr 147
|
178
|
+
�, 147
|
179
|
+
_dhe 147
|
180
|
+
ej_ 147
|
181
|
+
ki 146
|
182
|
+
�,_ 146
|
183
|
+
_ku 145
|
184
|
+
_- 144
|
185
|
+
_ng 142
|
186
|
+
ik 141
|
187
|
+
_nd 140
|
188
|
+
end 138
|
189
|
+
uk 137
|
190
|
+
et� 135
|
191
|
+
ko 135
|
192
|
+
_dhe_ 135
|
193
|
+
_ve 132
|
194
|
+
va 131
|
195
|
+
_l 131
|
196
|
+
p�r_ 131
|
197
|
+
shi 131
|
198
|
+
er� 129
|
199
|
+
ke 127
|
200
|
+
kis 127
|
201
|
+
s� 126
|
202
|
+
jo 125
|
203
|
+
li 124
|
204
|
+
ga 124
|
205
|
+
kish 123
|
206
|
+
_ki 122
|
207
|
+
po 122
|
208
|
+
_se 122
|
209
|
+
' 121
|
210
|
+
du 120
|
211
|
+
mb 120
|
212
|
+
_m� 119
|
213
|
+
Si 115
|
214
|
+
m�_ 115
|
215
|
+
esh 115
|
216
|
+
_si 114
|
217
|
+
qe 114
|
218
|
+
l� 114
|
219
|
+
_kis 113
|
220
|
+
oh 113
|
221
|
+
_kish 113
|
222
|
+
_Si 113
|
223
|
+
pr 112
|
224
|
+
_u 112
|
225
|
+
uar 111
|
226
|
+
de 111
|
227
|
+
hu 111
|
228
|
+
_th 111
|
229
|
+
al 111
|
230
|
+
ta_ 109
|
231
|
+
ilv 108
|
232
|
+
Sil 108
|
233
|
+
Silv 108
|
234
|
+
lv 108
|
235
|
+
k_ 108
|
236
|
+
e, 108
|
237
|
+
ji 107
|
238
|
+
e,_ 106
|
239
|
+
_Sil 106
|
240
|
+
_Silv 106
|
241
|
+
_r 105
|
242
|
+
os 104
|
243
|
+
_se_ 104
|
244
|
+
kisht 102
|
245
|
+
_di 102
|
246
|
+
st 101
|
247
|
+
_p�r_ 101
|
248
|
+
b� 101
|
249
|
+
tj 100
|
250
|
+
_nga 99
|
251
|
+
nga 99
|
252
|
+
_du 98
|
253
|
+
ra_ 98
|
254
|
+
v� 98
|
255
|
+
gji 98
|
256
|
+
_ish 96
|
257
|
+
rt 96
|
258
|
+
_is 96
|
259
|
+
ro 95
|
260
|
+
ir 94
|
261
|
+
ga_ 94
|
262
|
+
�sh 94
|
263
|
+
ont 93
|
264
|
+
c 93
|
265
|
+
t, 93
|
266
|
+
t,_ 93
|
267
|
+
hin 92
|
268
|
+
a, 92
|
269
|
+
_at 92
|
270
|
+
und 92
|
271
|
+
jt 91
|
272
|
+
_mb 91
|
273
|
+
a,_ 91
|
274
|
+
tje 90
|
275
|
+
_nga_ 90
|
276
|
+
_do 90
|
277
|
+
_pr 90
|
278
|
+
rit 90
|
279
|
+
men 90
|
280
|
+
nga_ 90
|
281
|
+
ri_ 89
|
282
|
+
N 89
|
283
|
+
ma 89
|
284
|
+
it_ 88
|
285
|
+
_k� 88
|
286
|
+
-_ 88
|
287
|
+
m_ 87
|
288
|
+
jo_ 87
|
289
|
+
onte 87
|
290
|
+
at� 87
|
291
|
+
la 87
|
292
|
+
�ri 87
|
293
|
+
ilva 86
|
294
|
+
shin 86
|
295
|
+
�. 86
|
296
|
+
Silva 86
|
297
|
+
lva 86
|
298
|
+
s�_ 85
|
299
|
+
jer 85
|
300
|
+
et_ 85
|
301
|
+
_po 85
|
302
|
+
�s_ 84
|
303
|
+
kur 84
|
304
|
+
ru 84
|
305
|
+
nin 83
|
306
|
+
ot 83
|
307
|
+
hin_ 83
|
308
|
+
_N 83
|
309
|
+
her 83
|
310
|
+
ht� 82
|
311
|
+
ap 82
|
312
|
+
shin_ 82
|
313
|
+
mo 81
|
314
|
+
ash 81
|
315
|
+
tha 81
|
316
|
+
_� 81
|
317
|
+
�._ 81
|
318
|
+
�m 81
|
319
|
+
jit 80
|
320
|
+
_ta 80
|
321
|
+
ul 80
|
322
|
+
le 80
|
323
|
+
ho 80
|
324
|
+
_z 79
|
325
|
+
dr 78
|
326
|
+
jet 78
|
327
|
+
nin_ 78
|
328
|
+
_m�_ 78
|
329
|
+
gjit 78
|
330
|
+
A 78
|
331
|
+
hk 78
|
332
|
+
onte_ 78
|
333
|
+
oni 77
|
334
|
+
lo 77
|
335
|
+
ba 77
|
336
|
+
her� 77
|
337
|
+
ndo 76
|
338
|
+
shk 76
|
339
|
+
mend 75
|
340
|
+
_v� 75
|
341
|
+
ha_ 75
|
342
|
+
d� 75
|
343
|
+
tur 74
|
344
|
+
_A 74
|
345
|
+
el 74
|
346
|
+
bi 74
|
347
|
+
_ko 74
|
348
|
+
uk_ 73
|
349
|
+
er�_ 73
|
350
|
+
si_ 73
|
351
|
+
_sa 73
|
352
|
+
ar_ 72
|
353
|
+
P 72
|
354
|
+
rs 72
|
355
|
+
pas 72
|
356
|
+
ith 72
|
357
|
+
uar_ 71
|
358
|
+
_isht 71
|
359
|
+
ai 70
|
360
|
+
e. 70
|
361
|
+
_vet 70
|
362
|
+
vet 70
|
363
|
+
_b� 70
|
364
|
+
zi 70
|
365
|
+
d_ 70
|
366
|
+
jith 70
|
367
|
+
da 70
|
368
|
+
gjith 69
|
369
|
+
duk 69
|
370
|
+
na 69
|
371
|
+
hej 69
|
372
|
+
t�r 68
|
373
|
+
_men 68
|
374
|
+
_ka 68
|
375
|
+
am 68
|
376
|
+
nd_ 68
|
377
|
+
_c 67
|
378
|
+
_pas 67
|
379
|
+
_duk 67
|
380
|
+
jes 67
|
381
|
+
ak 67
|
382
|
+
s, 67
|
383
|
+
e._ 67
|
384
|
+
s,_ 67
|
385
|
+
K 67
|
386
|
+
�sht 67
|
387
|
+
mu 66
|
388
|
+
kur_ 66
|
389
|
+
yr 66
|
390
|
+
em 65
|
391
|
+
_s� 65
|
392
|
+
tha_ 65
|
393
|
+
imi 65
|
394
|
+
ie 65
|
395
|
+
hej_ 64
|
396
|
+
_s�_ 64
|
397
|
+
_u_ 64
|
398
|
+
? 64
|
399
|
+
fu 64
|
400
|
+
_P 64
|