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
|
+
_ 34122
|
2
|
+
a 9113
|
3
|
+
o 8135
|
4
|
+
i 7736
|
5
|
+
e 7535
|
6
|
+
n 5207
|
7
|
+
s 4860
|
8
|
+
j 3995
|
9
|
+
t 3797
|
10
|
+
r 3660
|
11
|
+
u 3224
|
12
|
+
l 3065
|
13
|
+
d 3061
|
14
|
+
e_ 2941
|
15
|
+
v 2786
|
16
|
+
a_ 2746
|
17
|
+
k 2701
|
18
|
+
m 2492
|
19
|
+
o_ 2328
|
20
|
+
y 2238
|
21
|
+
p 2151
|
22
|
+
_s 2148
|
23
|
+
i_ 2094
|
24
|
+
je 1887
|
25
|
+
c 1854
|
26
|
+
z 1731
|
27
|
+
_n 1437
|
28
|
+
_p 1432
|
29
|
+
g 1418
|
30
|
+
b 1368
|
31
|
+
u_ 1333
|
32
|
+
je_ 1237
|
33
|
+
, 1226
|
34
|
+
,_ 1214
|
35
|
+
_i 1130
|
36
|
+
st 1105
|
37
|
+
na 1076
|
38
|
+
. 1056
|
39
|
+
_d 1033
|
40
|
+
._ 1030
|
41
|
+
_j 967
|
42
|
+
ra 934
|
43
|
+
ko 908
|
44
|
+
ni 900
|
45
|
+
cy 893
|
46
|
+
sy 875
|
47
|
+
_je 871
|
48
|
+
_o 824
|
49
|
+
ta 799
|
50
|
+
no 780
|
51
|
+
_u 777
|
52
|
+
re 766
|
53
|
+
_b 764
|
54
|
+
_k 763
|
55
|
+
da 760
|
56
|
+
ne 754
|
57
|
+
li 750
|
58
|
+
ti 745
|
59
|
+
se 722
|
60
|
+
po 713
|
61
|
+
to 713
|
62
|
+
_je_ 696
|
63
|
+
an 688
|
64
|
+
ja 683
|
65
|
+
pr 665
|
66
|
+
va 651
|
67
|
+
lo 634
|
68
|
+
_z 626
|
69
|
+
m_ 625
|
70
|
+
is 625
|
71
|
+
il 622
|
72
|
+
ov 621
|
73
|
+
la 621
|
74
|
+
_m 615
|
75
|
+
bi 604
|
76
|
+
_t 603
|
77
|
+
_po 594
|
78
|
+
en 586
|
79
|
+
_se 578
|
80
|
+
os 578
|
81
|
+
in 576
|
82
|
+
od 576
|
83
|
+
ka 552
|
84
|
+
ve 548
|
85
|
+
ij 538
|
86
|
+
_pr 536
|
87
|
+
al 536
|
88
|
+
vo 535
|
89
|
+
om 530
|
90
|
+
_i_ 525
|
91
|
+
nj 515
|
92
|
+
ed 509
|
93
|
+
_na 507
|
94
|
+
na_ 503
|
95
|
+
og 499
|
96
|
+
oj 498
|
97
|
+
ma 493
|
98
|
+
_bi 492
|
99
|
+
on 489
|
100
|
+
ak 482
|
101
|
+
im 481
|
102
|
+
ye 481
|
103
|
+
ro 480
|
104
|
+
vi 473
|
105
|
+
sa 469
|
106
|
+
ri 464
|
107
|
+
da_ 451
|
108
|
+
av 450
|
109
|
+
at 449
|
110
|
+
se_ 447
|
111
|
+
es 446
|
112
|
+
h 443
|
113
|
+
ao 441
|
114
|
+
ji 437
|
115
|
+
yi 436
|
116
|
+
_da 433
|
117
|
+
ad 432
|
118
|
+
_se_ 430
|
119
|
+
lj 428
|
120
|
+
zy 426
|
121
|
+
za 426
|
122
|
+
_ne 425
|
123
|
+
de 422
|
124
|
+
tr 417
|
125
|
+
cj 415
|
126
|
+
_u_ 414
|
127
|
+
_c 412
|
128
|
+
le 402
|
129
|
+
_v 397
|
130
|
+
ar 390
|
131
|
+
_g 390
|
132
|
+
ic 384
|
133
|
+
n_ 382
|
134
|
+
ju 379
|
135
|
+
lo_ 377
|
136
|
+
aj 376
|
137
|
+
_ko 369
|
138
|
+
ao_ 366
|
139
|
+
ek 361
|
140
|
+
_da_ 359
|
141
|
+
et 356
|
142
|
+
go 354
|
143
|
+
iz 346
|
144
|
+
_za 345
|
145
|
+
_r 344
|
146
|
+
or 342
|
147
|
+
mo 341
|
148
|
+
el 340
|
149
|
+
as 339
|
150
|
+
ik 336
|
151
|
+
te 332
|
152
|
+
_sa 329
|
153
|
+
d_ 323
|
154
|
+
am 320
|
155
|
+
me 318
|
156
|
+
sto 317
|
157
|
+
di 315
|
158
|
+
ec 311
|
159
|
+
ol 310
|
160
|
+
a,_ 307
|
161
|
+
a, 307
|
162
|
+
_ni 302
|
163
|
+
ya 296
|
164
|
+
do 295
|
165
|
+
yt 294
|
166
|
+
su 292
|
167
|
+
syt 289
|
168
|
+
li_ 288
|
169
|
+
sta 286
|
170
|
+
ije 284
|
171
|
+
ko_ 277
|
172
|
+
ti_ 277
|
173
|
+
la_ 277
|
174
|
+
ga 276
|
175
|
+
bil 275
|
176
|
+
no_ 274
|
177
|
+
a. 273
|
178
|
+
nu 272
|
179
|
+
a._ 271
|
180
|
+
ne_ 271
|
181
|
+
om_ 268
|
182
|
+
_cy 266
|
183
|
+
_na_ 263
|
184
|
+
_bil 263
|
185
|
+
sv 263
|
186
|
+
ru 259
|
187
|
+
to_ 256
|
188
|
+
_od 253
|
189
|
+
cyi 253
|
190
|
+
nje 251
|
191
|
+
it 251
|
192
|
+
pa 250
|
193
|
+
az 248
|
194
|
+
e,_ 245
|
195
|
+
e, 245
|
196
|
+
ob 244
|
197
|
+
dn 243
|
198
|
+
ac 242
|
199
|
+
ost 242
|
200
|
+
k_ 240
|
201
|
+
iv 239
|
202
|
+
io 238
|
203
|
+
_su 238
|
204
|
+
_iz 237
|
205
|
+
ilo 235
|
206
|
+
_sv 234
|
207
|
+
_ka 233
|
208
|
+
koj 231
|
209
|
+
mi 229
|
210
|
+
im_ 229
|
211
|
+
ije_ 227
|
212
|
+
g_ 226
|
213
|
+
em 223
|
214
|
+
su_ 223
|
215
|
+
ih 223
|
216
|
+
ji_ 221
|
217
|
+
kr 220
|
218
|
+
ut 220
|
219
|
+
_koj 220
|
220
|
+
V 218
|
221
|
+
_st 218
|
222
|
+
ye_ 217
|
223
|
+
_l 214
|
224
|
+
_V 213
|
225
|
+
ovo 211
|
226
|
+
j_ 210
|
227
|
+
uc 208
|
228
|
+
ja_ 208
|
229
|
+
h_ 207
|
230
|
+
nij 206
|
231
|
+
sk 206
|
232
|
+
ot 203
|
233
|
+
io_ 203
|
234
|
+
gl 203
|
235
|
+
_do 201
|
236
|
+
ok 200
|
237
|
+
ns 199
|
238
|
+
ilo_ 199
|
239
|
+
er 197
|
240
|
+
ih_ 195
|
241
|
+
pre 193
|
242
|
+
ci 193
|
243
|
+
og_ 193
|
244
|
+
ki 192
|
245
|
+
sl 191
|
246
|
+
t_ 189
|
247
|
+
ni_ 189
|
248
|
+
_a 189
|
249
|
+
vr 188
|
250
|
+
ati 187
|
251
|
+
_su_ 186
|
252
|
+
nije 181
|
253
|
+
pro 181
|
254
|
+
be 180
|
255
|
+
yn 179
|
256
|
+
cye 178
|
257
|
+
ju_ 178
|
258
|
+
ku 177
|
259
|
+
isy 177
|
260
|
+
ta_ 174
|
261
|
+
sye 172
|
262
|
+
_tr 172
|
263
|
+
O 172
|
264
|
+
jen 172
|
265
|
+
_to 171
|
266
|
+
pi 168
|
267
|
+
_pre 168
|
268
|
+
S 168
|
269
|
+
ima 167
|
270
|
+
nije_ 167
|
271
|
+
_mo 166
|
272
|
+
eg 166
|
273
|
+
e._ 164
|
274
|
+
za_ 164
|
275
|
+
e. 164
|
276
|
+
_pro 164
|
277
|
+
gov 163
|
278
|
+
N 162
|
279
|
+
dr 162
|
280
|
+
ako 162
|
281
|
+
tv 162
|
282
|
+
_S 160
|
283
|
+
P 159
|
284
|
+
ma_ 159
|
285
|
+
_on 159
|
286
|
+
sp 158
|
287
|
+
nst 158
|
288
|
+
anj 158
|
289
|
+
dj 157
|
290
|
+
oc 157
|
291
|
+
_sy 156
|
292
|
+
ev 155
|
293
|
+
ce 155
|
294
|
+
lik 154
|
295
|
+
_nij 153
|
296
|
+
_N 152
|
297
|
+
ist 151
|
298
|
+
_P 151
|
299
|
+
_nije 151
|
300
|
+
- 151
|
301
|
+
ba 150
|
302
|
+
jed 150
|
303
|
+
sti 150
|
304
|
+
ova 149
|
305
|
+
_is 148
|
306
|
+
id 148
|
307
|
+
ton 148
|
308
|
+
ke 147
|
309
|
+
pos 147
|
310
|
+
od_ 147
|
311
|
+
osy 146
|
312
|
+
Vi 146
|
313
|
+
ila 145
|
314
|
+
ins 145
|
315
|
+
bo 145
|
316
|
+
_Vi 145
|
317
|
+
ir 144
|
318
|
+
_za_ 144
|
319
|
+
oz 144
|
320
|
+
ecj 144
|
321
|
+
cje 143
|
322
|
+
on_ 143
|
323
|
+
zn 142
|
324
|
+
_O 141
|
325
|
+
us 141
|
326
|
+
i, 141
|
327
|
+
i,_ 141
|
328
|
+
mu 140
|
329
|
+
inst 140
|
330
|
+
cya 140
|
331
|
+
oji 139
|
332
|
+
esy 139
|
333
|
+
icy 139
|
334
|
+
lja 138
|
335
|
+
_go 138
|
336
|
+
i. 138
|
337
|
+
_re 137
|
338
|
+
_bilo 137
|
339
|
+
edn 137
|
340
|
+
acy 137
|
341
|
+
rat 137
|
342
|
+
bilo 137
|
343
|
+
ali 136
|
344
|
+
ecy 136
|
345
|
+
ija 135
|
346
|
+
pri 135
|
347
|
+
ad_ 135
|
348
|
+
lic 135
|
349
|
+
i._ 135
|
350
|
+
Vins 134
|
351
|
+
Vin 134
|
352
|
+
ston 134
|
353
|
+
Vinst 134
|
354
|
+
ga_ 134
|
355
|
+
nston 134
|
356
|
+
insto 134
|
357
|
+
nsto 134
|
358
|
+
_Vins 133
|
359
|
+
_Vin 133
|
360
|
+
zi 132
|
361
|
+
ran 131
|
362
|
+
le_ 130
|
363
|
+
ili 130
|
364
|
+
bilo_ 130
|
365
|
+
_pos 129
|
366
|
+
ila_ 129
|
367
|
+
est 128
|
368
|
+
_ve 128
|
369
|
+
tre 128
|
370
|
+
zye 127
|
371
|
+
_nj 127
|
372
|
+
si 126
|
373
|
+
f 126
|
374
|
+
alo 125
|
375
|
+
ako_ 125
|
376
|
+
tra 125
|
377
|
+
sa_ 125
|
378
|
+
pu 124
|
379
|
+
ud 124
|
380
|
+
z_ 124
|
381
|
+
_ra 124
|
382
|
+
iti 124
|
383
|
+
_de 124
|
384
|
+
odi 123
|
385
|
+
T 123
|
386
|
+
-_ 122
|
387
|
+
o,_ 121
|
388
|
+
o, 121
|
389
|
+
du 121
|
390
|
+
rs 121
|
391
|
+
B 120
|
392
|
+
ka_ 119
|
393
|
+
red 119
|
394
|
+
_od_ 118
|
395
|
+
an_ 118
|
396
|
+
nu_ 118
|
397
|
+
iko 117
|
398
|
+
dno 117
|
399
|
+
_pa 117
|
400
|
+
s_ 116
|
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 20064
|
2
|
+
a 4991
|
3
|
+
o 4983
|
4
|
+
e 3838
|
5
|
+
n 3342
|
6
|
+
i 3317
|
7
|
+
r 2583
|
8
|
+
s 2501
|
9
|
+
v 2383
|
10
|
+
t 2325
|
11
|
+
c 1918
|
12
|
+
k 1912
|
13
|
+
l 1888
|
14
|
+
d 1736
|
15
|
+
u 1725
|
16
|
+
p 1543
|
17
|
+
a_ 1527
|
18
|
+
y 1371
|
19
|
+
m 1339
|
20
|
+
z 1227
|
21
|
+
h 1194
|
22
|
+
e_ 956
|
23
|
+
_p 881
|
24
|
+
_s 828
|
25
|
+
o_ 814
|
26
|
+
na 809
|
27
|
+
b 808
|
28
|
+
_v 798
|
29
|
+
j 797
|
30
|
+
. 796
|
31
|
+
ov 795
|
32
|
+
._ 785
|
33
|
+
st 687
|
34
|
+
i_ 665
|
35
|
+
, 657
|
36
|
+
,_ 657
|
37
|
+
_n 625
|
38
|
+
ch 623
|
39
|
+
u_ 618
|
40
|
+
ro 617
|
41
|
+
po 598
|
42
|
+
_o 546
|
43
|
+
ne 529
|
44
|
+
en 520
|
45
|
+
v_ 519
|
46
|
+
_a 516
|
47
|
+
ra 506
|
48
|
+
pr 488
|
49
|
+
y_ 481
|
50
|
+
od 476
|
51
|
+
_z 467
|
52
|
+
ie 462
|
53
|
+
ni 448
|
54
|
+
an 447
|
55
|
+
vy 434
|
56
|
+
to 433
|
57
|
+
h_ 431
|
58
|
+
_na 429
|
59
|
+
re 416
|
60
|
+
ch_ 404
|
61
|
+
ho 401
|
62
|
+
al 399
|
63
|
+
ci 394
|
64
|
+
va 387
|
65
|
+
na_ 386
|
66
|
+
_pr 385
|
67
|
+
_d 384
|
68
|
+
_k 378
|
69
|
+
la 377
|
70
|
+
ko 375
|
71
|
+
do 374
|
72
|
+
_po 373
|
73
|
+
si 353
|
74
|
+
_t 346
|
75
|
+
_r 337
|
76
|
+
os 336
|
77
|
+
no 334
|
78
|
+
in 328
|
79
|
+
tr 324
|
80
|
+
om 321
|
81
|
+
_v_ 320
|
82
|
+
ny 319
|
83
|
+
m_ 319
|
84
|
+
ri 317
|
85
|
+
S 306
|
86
|
+
ac 302
|
87
|
+
sa 300
|
88
|
+
ti 300
|
89
|
+
_m 298
|
90
|
+
za 298
|
91
|
+
er 291
|
92
|
+
ia 290
|
93
|
+
ce 290
|
94
|
+
li 289
|
95
|
+
yc 286
|
96
|
+
ych 285
|
97
|
+
ed 284
|
98
|
+
at 281
|
99
|
+
ob 281
|
100
|
+
ak 280
|
101
|
+
_na_ 280
|
102
|
+
il 279
|
103
|
+
_, 279
|
104
|
+
_,_ 279
|
105
|
+
ok 277
|
106
|
+
sk 268
|
107
|
+
ych_ 265
|
108
|
+
_c 262
|
109
|
+
mi 261
|
110
|
+
ol 260
|
111
|
+
me 260
|
112
|
+
l_ 259
|
113
|
+
t_ 259
|
114
|
+
ku 258
|
115
|
+
ta 256
|
116
|
+
le 256
|
117
|
+
_b 254
|
118
|
+
or 252
|
119
|
+
_a_ 250
|
120
|
+
lo 247
|
121
|
+
oc 246
|
122
|
+
vo 246
|
123
|
+
es 244
|
124
|
+
ve 242
|
125
|
+
_vy 240
|
126
|
+
on 238
|
127
|
+
_sa 231
|
128
|
+
as 231
|
129
|
+
da 230
|
130
|
+
aj 228
|
131
|
+
av 218
|
132
|
+
el 216
|
133
|
+
ova 216
|
134
|
+
ic 215
|
135
|
+
ne_ 209
|
136
|
+
_do 208
|
137
|
+
sa_ 207
|
138
|
+
ka 205
|
139
|
+
_sa_ 204
|
140
|
+
te 203
|
141
|
+
j_ 201
|
142
|
+
_ro 199
|
143
|
+
P 198
|
144
|
+
_za 196
|
145
|
+
ky 196
|
146
|
+
_S 195
|
147
|
+
je 194
|
148
|
+
ar 193
|
149
|
+
_. 193
|
150
|
+
it 192
|
151
|
+
s_ 192
|
152
|
+
em 191
|
153
|
+
ej 191
|
154
|
+
ur 190
|
155
|
+
ad 189
|
156
|
+
_o_ 187
|
157
|
+
_._ 187
|
158
|
+
ov_ 185
|
159
|
+
de 180
|
160
|
+
_% 179
|
161
|
+
om_ 179
|
162
|
+
% 179
|
163
|
+
_u 174
|
164
|
+
pre 173
|
165
|
+
dn 173
|
166
|
+
D 172
|
167
|
+
rok 170
|
168
|
+
ie_ 170
|
169
|
+
sp 169
|
170
|
+
pri 167
|
171
|
+
_pre 167
|
172
|
+
am 165
|
173
|
+
- 164
|
174
|
+
ke 164
|
175
|
+
eh 162
|
176
|
+
oz 161
|
177
|
+
k_ 160
|
178
|
+
ost 160
|
179
|
+
_j 156
|
180
|
+
f 155
|
181
|
+
zn 153
|
182
|
+
g 152
|
183
|
+
kt 152
|
184
|
+
ho_ 151
|
185
|
+
eho 151
|
186
|
+
hod 150
|
187
|
+
ku_ 148
|
188
|
+
is 148
|
189
|
+
zi 147
|
190
|
+
cn 147
|
191
|
+
eho_ 146
|
192
|
+
ej_ 145
|
193
|
+
az 145
|
194
|
+
tu 145
|
195
|
+
_pri 144
|
196
|
+
cen 144
|
197
|
+
_st 143
|
198
|
+
ma 142
|
199
|
+
ast 141
|
200
|
+
_ce 140
|
201
|
+
rov 140
|
202
|
+
la_ 138
|
203
|
+
ot 138
|
204
|
+
nych 135
|
205
|
+
nyc 135
|
206
|
+
_ob 133
|
207
|
+
z_ 133
|
208
|
+
nych_ 131
|
209
|
+
N 130
|
210
|
+
li_ 129
|
211
|
+
ani 129
|
212
|
+
co 128
|
213
|
+
nt 128
|
214
|
+
ny_ 127
|
215
|
+
E 125
|
216
|
+
_ne 124
|
217
|
+
) 123
|
218
|
+
_( 123
|
219
|
+
sti 123
|
220
|
+
A 123
|
221
|
+
( 123
|
222
|
+
cho 122
|
223
|
+
vi 122
|
224
|
+
_sp 122
|
225
|
+
di 120
|
226
|
+
pa 120
|
227
|
+
n_ 119
|
228
|
+
ju 118
|
229
|
+
ys 117
|
230
|
+
bo 117
|
231
|
+
_P 116
|
232
|
+
_tr 115
|
233
|
+
V 114
|
234
|
+
je_ 114
|
235
|
+
ln 114
|
236
|
+
_i 113
|
237
|
+
ze 113
|
238
|
+
spo 112
|
239
|
+
_N 112
|
240
|
+
nd 111
|
241
|
+
nu 111
|
242
|
+
so 111
|
243
|
+
red 110
|
244
|
+
vn 110
|
245
|
+
kl 110
|
246
|
+
kov 110
|
247
|
+
_cen 110
|
248
|
+
_rok 109
|
249
|
+
tn 109
|
250
|
+
du 109
|
251
|
+
nc 109
|
252
|
+
ap 109
|
253
|
+
d_ 108
|
254
|
+
van 108
|
255
|
+
ca 108
|
256
|
+
M 108
|
257
|
+
chod 107
|
258
|
+
ti_ 107
|
259
|
+
U 106
|
260
|
+
_ak 106
|
261
|
+
ru 105
|
262
|
+
sta 105
|
263
|
+
ym 105
|
264
|
+
_- 104
|
265
|
+
et 103
|
266
|
+
_h 102
|
267
|
+
est 102
|
268
|
+
_je 102
|
269
|
+
nos 101
|
270
|
+
aci 101
|
271
|
+
us 100
|
272
|
+
dov 100
|
273
|
+
pod 100
|
274
|
+
_to 100
|
275
|
+
tor 99
|
276
|
+
uc 99
|
277
|
+
ras 98
|
278
|
+
ky_ 98
|
279
|
+
_s_ 98
|
280
|
+
_mi 97
|
281
|
+
* 97
|
282
|
+
uj 97
|
283
|
+
nost 97
|
284
|
+
vys 97
|
285
|
+
ovy 97
|
286
|
+
ez 97
|
287
|
+
oku 96
|
288
|
+
_V 96
|
289
|
+
op 96
|
290
|
+
bc 96
|
291
|
+
rast 96
|
292
|
+
se 95
|
293
|
+
B 95
|
294
|
+
roku 95
|
295
|
+
kto 94
|
296
|
+
ove 94
|
297
|
+
by 94
|
298
|
+
-_ 94
|
299
|
+
_ko 93
|
300
|
+
obc 92
|
301
|
+
nie 91
|
302
|
+
ia_ 91
|
303
|
+
ka_ 91
|
304
|
+
*_ 90
|
305
|
+
ali 90
|
306
|
+
lo_ 89
|
307
|
+
ovan 89
|
308
|
+
to_ 88
|
309
|
+
iz 88
|
310
|
+
_bo 88
|
311
|
+
_l 88
|
312
|
+
odo 87
|
313
|
+
bch 87
|
314
|
+
bchod 87
|
315
|
+
bcho 87
|
316
|
+
sl 86
|
317
|
+
st_ 86
|
318
|
+
pred 86
|
319
|
+
C 86
|
320
|
+
pol 85
|
321
|
+
_pred 85
|
322
|
+
R 85
|
323
|
+
ik 84
|
324
|
+
uro 84
|
325
|
+
pi 84
|
326
|
+
ek 84
|
327
|
+
zo 83
|
328
|
+
eni 83
|
329
|
+
obch 83
|
330
|
+
cie 83
|
331
|
+
oku_ 83
|
332
|
+
obcho 83
|
333
|
+
ns 83
|
334
|
+
roku_ 82
|
335
|
+
ii 82
|
336
|
+
tv 82
|
337
|
+
ba 82
|
338
|
+
ent 82
|
339
|
+
_spo 81
|
340
|
+
tov 81
|
341
|
+
pe 81
|
342
|
+
kon 80
|
343
|
+
kc 80
|
344
|
+
ec 80
|
345
|
+
kci 80
|
346
|
+
ck 80
|
347
|
+
x 79
|
348
|
+
osti 79
|
349
|
+
_Sk 79
|
350
|
+
mi_ 79
|
351
|
+
_in 79
|
352
|
+
Sk 79
|
353
|
+
sia 79
|
354
|
+
br 78
|
355
|
+
rh 78
|
356
|
+
val 78
|
357
|
+
olo 77
|
358
|
+
_pod 77
|
359
|
+
%_ 77
|
360
|
+
_%_ 77
|
361
|
+
bu 77
|
362
|
+
_f 77
|
363
|
+
iv 77
|
364
|
+
_obc 77
|
365
|
+
_obch 77
|
366
|
+
eb 76
|
367
|
+
str 76
|
368
|
+
nej 76
|
369
|
+
_D 76
|
370
|
+
ni_ 75
|
371
|
+
ou 75
|
372
|
+
im 75
|
373
|
+
ena 74
|
374
|
+
tre 74
|
375
|
+
_A 74
|
376
|
+
mo 74
|
377
|
+
su 74
|
378
|
+
rz 73
|
379
|
+
_trh 73
|
380
|
+
trh 73
|
381
|
+
_U 73
|
382
|
+
al_ 73
|
383
|
+
_ra 73
|
384
|
+
_e 72
|
385
|
+
_C 72
|
386
|
+
sti_ 72
|
387
|
+
zv 72
|
388
|
+
te_ 72
|
389
|
+
cno 72
|
390
|
+
oj 72
|
391
|
+
ktor 71
|
392
|
+
_roku 71
|
393
|
+
ocn 71
|
394
|
+
ina 71
|
395
|
+
sil 71
|
396
|
+
nov 71
|
397
|
+
alo 71
|
398
|
+
odn 70
|
399
|
+
nan 70
|
400
|
+
oh 70
|