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
|
+
_ 8202
|
2
|
+
o 2145
|
3
|
+
a 1912
|
4
|
+
e 1763
|
5
|
+
i 1491
|
6
|
+
n 1415
|
7
|
+
r 1256
|
8
|
+
t 1127
|
9
|
+
v 1080
|
10
|
+
s 1004
|
11
|
+
k 824
|
12
|
+
d 739
|
13
|
+
p 739
|
14
|
+
l 735
|
15
|
+
m 685
|
16
|
+
c 620
|
17
|
+
u 597
|
18
|
+
h 531
|
19
|
+
a_ 467
|
20
|
+
j 449
|
21
|
+
_p 445
|
22
|
+
z 439
|
23
|
+
e_ 412
|
24
|
+
� 402
|
25
|
+
_v 369
|
26
|
+
. 361
|
27
|
+
_s 359
|
28
|
+
ov 330
|
29
|
+
b 327
|
30
|
+
st 312
|
31
|
+
y 309
|
32
|
+
pr 307
|
33
|
+
._ 300
|
34
|
+
o_ 297
|
35
|
+
� 278
|
36
|
+
, 268
|
37
|
+
,_ 260
|
38
|
+
to 258
|
39
|
+
� 256
|
40
|
+
_a 254
|
41
|
+
� 253
|
42
|
+
i_ 252
|
43
|
+
_pr 246
|
44
|
+
ch 242
|
45
|
+
re 233
|
46
|
+
_z 223
|
47
|
+
ra 220
|
48
|
+
_n 217
|
49
|
+
ne 214
|
50
|
+
ie 214
|
51
|
+
po 214
|
52
|
+
en 208
|
53
|
+
ro 205
|
54
|
+
or 204
|
55
|
+
� 199
|
56
|
+
u_ 197
|
57
|
+
an 197
|
58
|
+
ko 194
|
59
|
+
na 189
|
60
|
+
ni 187
|
61
|
+
va 183
|
62
|
+
� 182
|
63
|
+
� 180
|
64
|
+
os 179
|
65
|
+
v_ 176
|
66
|
+
� 173
|
67
|
+
_o 171
|
68
|
+
ho 170
|
69
|
+
ia 168
|
70
|
+
no 166
|
71
|
+
li 166
|
72
|
+
h_ 166
|
73
|
+
ed 164
|
74
|
+
j_ 161
|
75
|
+
om 160
|
76
|
+
_k 160
|
77
|
+
� 158
|
78
|
+
ch_ 158
|
79
|
+
ti 155
|
80
|
+
y_ 148
|
81
|
+
m_ 147
|
82
|
+
ej 147
|
83
|
+
_po 145
|
84
|
+
ci 145
|
85
|
+
_d 140
|
86
|
+
�_ 139
|
87
|
+
do 138
|
88
|
+
_t 137
|
89
|
+
_m 134
|
90
|
+
ri 129
|
91
|
+
mi 129
|
92
|
+
od 128
|
93
|
+
te 124
|
94
|
+
_a_ 124
|
95
|
+
la 122
|
96
|
+
al 121
|
97
|
+
aj 120
|
98
|
+
ej_ 120
|
99
|
+
vo 119
|
100
|
+
ol 119
|
101
|
+
in 118
|
102
|
+
ve 117
|
103
|
+
me 117
|
104
|
+
tr 116
|
105
|
+
sk 116
|
106
|
+
ova 116
|
107
|
+
S 111
|
108
|
+
er 110
|
109
|
+
ob 110
|
110
|
+
_na 109
|
111
|
+
ad 107
|
112
|
+
je 106
|
113
|
+
at 104
|
114
|
+
_v_ 103
|
115
|
+
_r 102
|
116
|
+
ic 101
|
117
|
+
�ch 100
|
118
|
+
pre 100
|
119
|
+
�c 100
|
120
|
+
av 98
|
121
|
+
es 96
|
122
|
+
ta 95
|
123
|
+
dn 94
|
124
|
+
ho_ 94
|
125
|
+
lo 94
|
126
|
+
�_ 93
|
127
|
+
_pre 93
|
128
|
+
it 93
|
129
|
+
V 92
|
130
|
+
de 92
|
131
|
+
kt 89
|
132
|
+
n� 89
|
133
|
+
za 88
|
134
|
+
A 87
|
135
|
+
le 86
|
136
|
+
�ch_ 86
|
137
|
+
ok 86
|
138
|
+
ost 85
|
139
|
+
vi 84
|
140
|
+
ie_ 83
|
141
|
+
ak 82
|
142
|
+
P 82
|
143
|
+
n� 81
|
144
|
+
R 80
|
145
|
+
sa 80
|
146
|
+
as 79
|
147
|
+
�i 78
|
148
|
+
na_ 77
|
149
|
+
a� 77
|
150
|
+
�_ 77
|
151
|
+
� 76
|
152
|
+
ar 75
|
153
|
+
di 75
|
154
|
+
_S 74
|
155
|
+
om_ 74
|
156
|
+
_V 73
|
157
|
+
_do 73
|
158
|
+
_za 72
|
159
|
+
- 72
|
160
|
+
ck 71
|
161
|
+
vy 71
|
162
|
+
ka 71
|
163
|
+
f 70
|
164
|
+
tor 70
|
165
|
+
am 70
|
166
|
+
on 70
|
167
|
+
_- 69
|
168
|
+
_P 69
|
169
|
+
M 68
|
170
|
+
_i 68
|
171
|
+
_sa 68
|
172
|
+
nos 68
|
173
|
+
n� 68
|
174
|
+
�c 67
|
175
|
+
a�_ 67
|
176
|
+
sl 66
|
177
|
+
il 66
|
178
|
+
r� 66
|
179
|
+
_c 66
|
180
|
+
_b 66
|
181
|
+
_-_ 64
|
182
|
+
sa_ 64
|
183
|
+
-_ 64
|
184
|
+
kto 64
|
185
|
+
_j 64
|
186
|
+
ani 64
|
187
|
+
kr 64
|
188
|
+
sti 63
|
189
|
+
ou 63
|
190
|
+
ot 63
|
191
|
+
ne_ 63
|
192
|
+
_sa_ 62
|
193
|
+
v� 62
|
194
|
+
_na_ 62
|
195
|
+
red 62
|
196
|
+
ku 61
|
197
|
+
is 61
|
198
|
+
n� 60
|
199
|
+
�_ 60
|
200
|
+
so 60
|
201
|
+
sp 60
|
202
|
+
_st 59
|
203
|
+
g 59
|
204
|
+
tn 59
|
205
|
+
str 58
|
206
|
+
�e 58
|
207
|
+
nt 58
|
208
|
+
et 57
|
209
|
+
pra 57
|
210
|
+
ke 57
|
211
|
+
ov_ 57
|
212
|
+
_vy 57
|
213
|
+
_M 57
|
214
|
+
nej 56
|
215
|
+
tu 56
|
216
|
+
l_ 56
|
217
|
+
_je 56
|
218
|
+
nie 56
|
219
|
+
�n 56
|
220
|
+
k_ 56
|
221
|
+
pe 56
|
222
|
+
_h 55
|
223
|
+
oz 55
|
224
|
+
�_ 55
|
225
|
+
est 55
|
226
|
+
_� 55
|
227
|
+
va� 55
|
228
|
+
ma 54
|
229
|
+
n�_ 53
|
230
|
+
t� 53
|
231
|
+
.. 53
|
232
|
+
r� 52
|
233
|
+
ran 52
|
234
|
+
bo 51
|
235
|
+
nej_ 51
|
236
|
+
ick 51
|
237
|
+
ti_ 51
|
238
|
+
ia_ 51
|
239
|
+
ktor 51
|
240
|
+
K 51
|
241
|
+
O 51
|
242
|
+
T 51
|
243
|
+
_ne 51
|
244
|
+
ou_ 50
|
245
|
+
I 50
|
246
|
+
oc 50
|
247
|
+
to_ 50
|
248
|
+
vn 50
|
249
|
+
sta 50
|
250
|
+
_. 50
|
251
|
+
da 50
|
252
|
+
�h 49
|
253
|
+
�ho 49
|
254
|
+
N 49
|
255
|
+
_ro 49
|
256
|
+
_ko 49
|
257
|
+
ac 49
|
258
|
+
ek 49
|
259
|
+
li_ 49
|
260
|
+
�a 49
|
261
|
+
rov 49
|
262
|
+
oj 48
|
263
|
+
s_ 48
|
264
|
+
s� 48
|
265
|
+
�ho_ 48
|
266
|
+
va�_ 48
|
267
|
+
je_ 48
|
268
|
+
z� 47
|
269
|
+
ik 47
|
270
|
+
mo 47
|
271
|
+
mi_ 47
|
272
|
+
si 47
|
273
|
+
_kto 46
|
274
|
+
_sp 46
|
275
|
+
_kt 46
|
276
|
+
E 46
|
277
|
+
_ktor 46
|
278
|
+
eb 46
|
279
|
+
n�c 45
|
280
|
+
_u 45
|
281
|
+
el 45
|
282
|
+
B 45
|
283
|
+
n�ch 45
|
284
|
+
pro 45
|
285
|
+
eni 44
|
286
|
+
_� 44
|
287
|
+
em 44
|
288
|
+
kon 44
|
289
|
+
pa 44
|
290
|
+
ky 44
|
291
|
+
uj 44
|
292
|
+
�e_ 44
|
293
|
+
ova� 44
|
294
|
+
cie 44
|
295
|
+
hr 44
|
296
|
+
k� 44
|
297
|
+
n�ch_ 43
|
298
|
+
pred 43
|
299
|
+
zo 43
|
300
|
+
ln 43
|
301
|
+
o� 43
|
302
|
+
tov 43
|
303
|
+
nu 43
|
304
|
+
e� 43
|
305
|
+
�c 42
|
306
|
+
�l 42
|
307
|
+
�m 42
|
308
|
+
pri 42
|
309
|
+
_to 42
|
310
|
+
l� 41
|
311
|
+
ce 41
|
312
|
+
�v 41
|
313
|
+
eh 41
|
314
|
+
_pro 41
|
315
|
+
rav 41
|
316
|
+
kej 41
|
317
|
+
ns 41
|
318
|
+
ali 41
|
319
|
+
oli 40
|
320
|
+
�_ 40
|
321
|
+
_pri 40
|
322
|
+
oh 40
|
323
|
+
ud 40
|
324
|
+
_ak 40
|
325
|
+
ent 40
|
326
|
+
e� 40
|
327
|
+
prav 39
|
328
|
+
_pred 39
|
329
|
+
�i 39
|
330
|
+
zn 39
|
331
|
+
ny 39
|
332
|
+
ove 39
|
333
|
+
pol 39
|
334
|
+
ru 39
|
335
|
+
a, 39
|
336
|
+
ah 39
|
337
|
+
kej_ 39
|
338
|
+
a,_ 38
|
339
|
+
z_ 38
|
340
|
+
aj_ 38
|
341
|
+
r_ 38
|
342
|
+
i� 38
|
343
|
+
ova�_ 38
|
344
|
+
tre 38
|
345
|
+
pod 37
|
346
|
+
_z� 37
|
347
|
+
_ob 37
|
348
|
+
nost 37
|
349
|
+
sti_ 37
|
350
|
+
van 37
|
351
|
+
up 37
|
352
|
+
osti 36
|
353
|
+
�ci 36
|
354
|
+
_�e 36
|
355
|
+
j� 36
|
356
|
+
co 36
|
357
|
+
_str 36
|
358
|
+
�i 36
|
359
|
+
_ma 36
|
360
|
+
ut 36
|
361
|
+
nsk 36
|
362
|
+
by 36
|
363
|
+
_ve 35
|
364
|
+
ko_ 35
|
365
|
+
de_ 35
|
366
|
+
�ia 35
|
367
|
+
_aj 35
|
368
|
+
_aj_ 35
|
369
|
+
op 35
|
370
|
+
_pod 34
|
371
|
+
pr� 34
|
372
|
+
_in 34
|
373
|
+
ez 34
|
374
|
+
odn 34
|
375
|
+
dne 34
|
376
|
+
Z 34
|
377
|
+
tra 34
|
378
|
+
bn 34
|
379
|
+
�d 34
|
380
|
+
_�e_ 34
|
381
|
+
_vo 34
|
382
|
+
�as 34
|
383
|
+
�t 34
|
384
|
+
d_ 34
|
385
|
+
� 34
|
386
|
+
sto 34
|
387
|
+
ky_ 34
|
388
|
+
ir 33
|
389
|
+
_z_ 33
|
390
|
+
nie_ 33
|
391
|
+
�t 33
|
392
|
+
ven 33
|
393
|
+
i�_ 33
|
394
|
+
_s_ 33
|
395
|
+
_B 33
|
396
|
+
�e 33
|
397
|
+
ens 33
|
398
|
+
spo 32
|
399
|
+
eho 32
|
400
|
+
lad 32
|
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 25262
|
2
|
+
e 6217
|
3
|
+
a 5964
|
4
|
+
i 5611
|
5
|
+
o 5538
|
6
|
+
n 4132
|
7
|
+
s 3349
|
8
|
+
l 3268
|
9
|
+
r 2913
|
10
|
+
t 2777
|
11
|
+
j 2672
|
12
|
+
v 2282
|
13
|
+
k 2175
|
14
|
+
e_ 1958
|
15
|
+
d 1953
|
16
|
+
p 1786
|
17
|
+
a_ 1700
|
18
|
+
y 1623
|
19
|
+
m 1559
|
20
|
+
o_ 1542
|
21
|
+
z 1521
|
22
|
+
i_ 1462
|
23
|
+
_s 1433
|
24
|
+
je 1383
|
25
|
+
, 1278
|
26
|
+
,_ 1278
|
27
|
+
b 1230
|
28
|
+
c 1137
|
29
|
+
_p 1130
|
30
|
+
_n 1032
|
31
|
+
je_ 997
|
32
|
+
u 986
|
33
|
+
_j 972
|
34
|
+
g 933
|
35
|
+
_je 877
|
36
|
+
cy 848
|
37
|
+
_je_ 842
|
38
|
+
_v 793
|
39
|
+
il 786
|
40
|
+
ni 782
|
41
|
+
st 779
|
42
|
+
na 743
|
43
|
+
ra 726
|
44
|
+
. 723
|
45
|
+
._ 716
|
46
|
+
_z 713
|
47
|
+
in 691
|
48
|
+
_k 685
|
49
|
+
_b 667
|
50
|
+
al 640
|
51
|
+
h 627
|
52
|
+
po 607
|
53
|
+
ti 584
|
54
|
+
pr 584
|
55
|
+
ko 584
|
56
|
+
_d 582
|
57
|
+
el 579
|
58
|
+
n_ 579
|
59
|
+
la 577
|
60
|
+
lo 573
|
61
|
+
l_ 571
|
62
|
+
_t 567
|
63
|
+
se 567
|
64
|
+
ne 562
|
65
|
+
_i 556
|
66
|
+
no 549
|
67
|
+
en 546
|
68
|
+
_o 534
|
69
|
+
re 524
|
70
|
+
bi 514
|
71
|
+
li 512
|
72
|
+
ov 496
|
73
|
+
sy 458
|
74
|
+
_na 457
|
75
|
+
te 453
|
76
|
+
da 451
|
77
|
+
_po 440
|
78
|
+
_bi 437
|
79
|
+
ye 436
|
80
|
+
to 424
|
81
|
+
ri 420
|
82
|
+
an 420
|
83
|
+
_pr 417
|
84
|
+
ve 410
|
85
|
+
nj 404
|
86
|
+
ka 403
|
87
|
+
_m 394
|
88
|
+
le 385
|
89
|
+
ja 377
|
90
|
+
va 374
|
91
|
+
de 374
|
92
|
+
is 371
|
93
|
+
ed 364
|
94
|
+
v_ 362
|
95
|
+
za 361
|
96
|
+
in_ 354
|
97
|
+
bil 353
|
98
|
+
_se 351
|
99
|
+
aj 347
|
100
|
+
ga 344
|
101
|
+
ar 343
|
102
|
+
od 339
|
103
|
+
_in 338
|
104
|
+
_in_ 333
|
105
|
+
tr 332
|
106
|
+
os 332
|
107
|
+
_bil 332
|
108
|
+
ta 328
|
109
|
+
vo 327
|
110
|
+
ki 324
|
111
|
+
ro 324
|
112
|
+
et 320
|
113
|
+
so 315
|
114
|
+
em 313
|
115
|
+
lo_ 311
|
116
|
+
na_ 306
|
117
|
+
av 305
|
118
|
+
ih 305
|
119
|
+
yi 304
|
120
|
+
h_ 295
|
121
|
+
at 294
|
122
|
+
m_ 293
|
123
|
+
ek 292
|
124
|
+
ol 289
|
125
|
+
se_ 289
|
126
|
+
as 284
|
127
|
+
lj 281
|
128
|
+
_za 277
|
129
|
+
ob 275
|
130
|
+
om 273
|
131
|
+
me 273
|
132
|
+
zy 272
|
133
|
+
mi 268
|
134
|
+
eg 265
|
135
|
+
_v_ 263
|
136
|
+
_g 260
|
137
|
+
or 260
|
138
|
+
es 259
|
139
|
+
_se_ 258
|
140
|
+
do 255
|
141
|
+
ni_ 255
|
142
|
+
ga_ 253
|
143
|
+
oc 251
|
144
|
+
il_ 250
|
145
|
+
vi 249
|
146
|
+
ak 248
|
147
|
+
no_ 243
|
148
|
+
da_ 241
|
149
|
+
pa 240
|
150
|
+
_ne 238
|
151
|
+
ot 238
|
152
|
+
_so 238
|
153
|
+
ocy 237
|
154
|
+
ya 237
|
155
|
+
la_ 234
|
156
|
+
li_ 234
|
157
|
+
ih_ 231
|
158
|
+
_c 229
|
159
|
+
az 229
|
160
|
+
ik 228
|
161
|
+
on 225
|
162
|
+
ki_ 224
|
163
|
+
go 223
|
164
|
+
im 223
|
165
|
+
sk 223
|
166
|
+
mo 221
|
167
|
+
cye 219
|
168
|
+
ti_ 217
|
169
|
+
ji 216
|
170
|
+
_da 216
|
171
|
+
iz 215
|
172
|
+
ko_ 214
|
173
|
+
ic 213
|
174
|
+
_l 209
|
175
|
+
u_ 209
|
176
|
+
pre 208
|
177
|
+
_r 208
|
178
|
+
_ko 208
|
179
|
+
t_ 207
|
180
|
+
z_ 206
|
181
|
+
er 206
|
182
|
+
so_ 206
|
183
|
+
ilo 203
|
184
|
+
r_ 201
|
185
|
+
j_ 199
|
186
|
+
ad 195
|
187
|
+
cyi 193
|
188
|
+
_na_ 193
|
189
|
+
sa 191
|
190
|
+
ev 191
|
191
|
+
i, 188
|
192
|
+
i,_ 188
|
193
|
+
it 187
|
194
|
+
sto 186
|
195
|
+
_da_ 184
|
196
|
+
_ni 183
|
197
|
+
_so_ 182
|
198
|
+
_ve 182
|
199
|
+
nje 181
|
200
|
+
a, 181
|
201
|
+
kr 181
|
202
|
+
a,_ 181
|
203
|
+
dn 177
|
204
|
+
_st 177
|
205
|
+
di 176
|
206
|
+
ega 176
|
207
|
+
og 174
|
208
|
+
o,_ 174
|
209
|
+
o, 174
|
210
|
+
ilo_ 172
|
211
|
+
_ki 171
|
212
|
+
ma 170
|
213
|
+
- 170
|
214
|
+
ij 169
|
215
|
+
_cy 169
|
216
|
+
ost 169
|
217
|
+
e, 168
|
218
|
+
e,_ 168
|
219
|
+
ne_ 168
|
220
|
+
ok 166
|
221
|
+
ke 165
|
222
|
+
_pre 165
|
223
|
+
del 165
|
224
|
+
yn 165
|
225
|
+
al_ 165
|
226
|
+
bo 164
|
227
|
+
_pa 163
|
228
|
+
_ki_ 163
|
229
|
+
am 159
|
230
|
+
ns 158
|
231
|
+
ye_ 156
|
232
|
+
sp 155
|
233
|
+
em_ 154
|
234
|
+
_ka 154
|
235
|
+
_te 153
|
236
|
+
_iz 152
|
237
|
+
ega_ 151
|
238
|
+
_ob 150
|
239
|
+
br 149
|
240
|
+
ec 149
|
241
|
+
pri 148
|
242
|
+
ap 147
|
243
|
+
ez 147
|
244
|
+
ali 147
|
245
|
+
raz 144
|
246
|
+
jo 142
|
247
|
+
to_ 141
|
248
|
+
d_ 138
|
249
|
+
a._ 137
|
250
|
+
a. 137
|
251
|
+
cya 137
|
252
|
+
ova 136
|
253
|
+
anj 136
|
254
|
+
el_ 135
|
255
|
+
V 135
|
256
|
+
si 134
|
257
|
+
sta 134
|
258
|
+
_pri 132
|
259
|
+
_to 131
|
260
|
+
_a 130
|
261
|
+
_bilo 130
|
262
|
+
bilo 130
|
263
|
+
oj 129
|
264
|
+
ecy 128
|
265
|
+
_od 128
|
266
|
+
gl 128
|
267
|
+
op 127
|
268
|
+
ju 127
|
269
|
+
rav 126
|
270
|
+
_u 125
|
271
|
+
s_ 125
|
272
|
+
_V 125
|
273
|
+
ila 125
|
274
|
+
ce 124
|
275
|
+
_mo 124
|
276
|
+
ali_ 124
|
277
|
+
ah 122
|
278
|
+
str 122
|
279
|
+
_sp 121
|
280
|
+
vr 121
|
281
|
+
aj_ 121
|
282
|
+
_do 121
|
283
|
+
bilo_ 121
|
284
|
+
N 119
|
285
|
+
iv 117
|
286
|
+
ru 116
|
287
|
+
vs 116
|
288
|
+
jal 116
|
289
|
+
pi 115
|
290
|
+
O 115
|
291
|
+
_z_ 113
|
292
|
+
icy 112
|
293
|
+
k_ 112
|
294
|
+
be 112
|
295
|
+
elo 111
|
296
|
+
dr 110
|
297
|
+
pra 110
|
298
|
+
sye 110
|
299
|
+
ved 109
|
300
|
+
rs 108
|
301
|
+
_tr 108
|
302
|
+
tv 108
|
303
|
+
oz 108
|
304
|
+
tn 107
|
305
|
+
_nj 107
|
306
|
+
le_ 107
|
307
|
+
_N 107
|
308
|
+
_ni_ 106
|
309
|
+
pa_ 106
|
310
|
+
l,_ 105
|
311
|
+
l, 105
|
312
|
+
ins 105
|
313
|
+
ako 104
|
314
|
+
ac 104
|
315
|
+
ist 104
|
316
|
+
ir 104
|
317
|
+
sl 104
|
318
|
+
ila_ 103
|
319
|
+
nik 103
|
320
|
+
bi_ 103
|
321
|
+
i. 102
|
322
|
+
i._ 102
|
323
|
+
_vs 102
|
324
|
+
iti 102
|
325
|
+
_sy 101
|
326
|
+
P 101
|
327
|
+
val 100
|
328
|
+
ku 100
|
329
|
+
_P 99
|
330
|
+
pe 99
|
331
|
+
ala 99
|
332
|
+
bil_ 98
|
333
|
+
eli 98
|
334
|
+
jen 98
|
335
|
+
ede 98
|
336
|
+
_zy 98
|
337
|
+
T 96
|
338
|
+
ja_ 96
|
339
|
+
ran 95
|
340
|
+
_bo 95
|
341
|
+
S 95
|
342
|
+
ln 95
|
343
|
+
zn 94
|
344
|
+
nst 93
|
345
|
+
_pa_ 93
|
346
|
+
_ra 93
|
347
|
+
_bil_ 93
|
348
|
+
nil 93
|
349
|
+
ati 92
|
350
|
+
ej 92
|
351
|
+
ocyi 92
|
352
|
+
e. 91
|
353
|
+
_le 91
|
354
|
+
ud 91
|
355
|
+
nov 91
|
356
|
+
nja 91
|
357
|
+
sn 91
|
358
|
+
ar_ 91
|
359
|
+
e._ 91
|
360
|
+
kl 91
|
361
|
+
isy 90
|
362
|
+
zye 90
|
363
|
+
en_ 90
|
364
|
+
sti 90
|
365
|
+
_ga 90
|
366
|
+
prav 90
|
367
|
+
_bi_ 90
|
368
|
+
za_ 89
|
369
|
+
lik 89
|
370
|
+
ton 89
|
371
|
+
kra 88
|
372
|
+
rt 88
|
373
|
+
W 88
|
374
|
+
_de 88
|
375
|
+
_ga_ 88
|
376
|
+
M 88
|
377
|
+
ep 87
|
378
|
+
cyn 87
|
379
|
+
Wi 87
|
380
|
+
_S 87
|
381
|
+
ut 87
|
382
|
+
_W 87
|
383
|
+
inst 87
|
384
|
+
insto 86
|
385
|
+
ste 86
|
386
|
+
Wins 86
|
387
|
+
gov 86
|
388
|
+
nu 86
|
389
|
+
Win 86
|
390
|
+
_Wi 86
|
391
|
+
Winst 86
|
392
|
+
nsto 86
|
393
|
+
eti 86
|
394
|
+
ston 86
|
395
|
+
nston 86
|
396
|
+
_Win 85
|
397
|
+
_Wins 85
|
398
|
+
ili 84
|
399
|
+
bra 83
|
400
|
+
rat 83
|