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
|
+
_ 36598
|
2
|
+
a 9456
|
3
|
+
o 9050
|
4
|
+
i 8526
|
5
|
+
e 7955
|
6
|
+
n 5513
|
7
|
+
j 5379
|
8
|
+
s 4971
|
9
|
+
t 4125
|
10
|
+
r 3889
|
11
|
+
u 3423
|
12
|
+
je 3281
|
13
|
+
l 3231
|
14
|
+
e_ 3177
|
15
|
+
d 3128
|
16
|
+
k 2992
|
17
|
+
v 2891
|
18
|
+
a_ 2835
|
19
|
+
o_ 2679
|
20
|
+
m 2645
|
21
|
+
p 2316
|
22
|
+
_s 2212
|
23
|
+
i_ 2205
|
24
|
+
y 2174
|
25
|
+
c 1894
|
26
|
+
z 1867
|
27
|
+
je_ 1613
|
28
|
+
_n 1593
|
29
|
+
g 1581
|
30
|
+
_p 1490
|
31
|
+
b 1386
|
32
|
+
u_ 1382
|
33
|
+
, 1208
|
34
|
+
,_ 1208
|
35
|
+
st 1203
|
36
|
+
_j 1202
|
37
|
+
na 1159
|
38
|
+
_je 1118
|
39
|
+
_d 1105
|
40
|
+
_i 1104
|
41
|
+
. 1069
|
42
|
+
._ 1058
|
43
|
+
ra 1017
|
44
|
+
ko 981
|
45
|
+
ni 980
|
46
|
+
_je_ 918
|
47
|
+
ij 914
|
48
|
+
ti 911
|
49
|
+
no 891
|
50
|
+
da 884
|
51
|
+
to 879
|
52
|
+
_k 863
|
53
|
+
_o 856
|
54
|
+
cy 839
|
55
|
+
li 838
|
56
|
+
ne 790
|
57
|
+
sy 786
|
58
|
+
- 785
|
59
|
+
pr 760
|
60
|
+
_u 748
|
61
|
+
po 734
|
62
|
+
ta 711
|
63
|
+
_b 705
|
64
|
+
_t 704
|
65
|
+
la 699
|
66
|
+
ja 699
|
67
|
+
an 691
|
68
|
+
m_ 680
|
69
|
+
ov 674
|
70
|
+
ije 673
|
71
|
+
_z 669
|
72
|
+
ka 662
|
73
|
+
ri 652
|
74
|
+
lo 651
|
75
|
+
vo 643
|
76
|
+
re 641
|
77
|
+
is 626
|
78
|
+
in 623
|
79
|
+
se 623
|
80
|
+
va 622
|
81
|
+
_m 617
|
82
|
+
oj 614
|
83
|
+
_po 594
|
84
|
+
_pr 592
|
85
|
+
bi 588
|
86
|
+
en 582
|
87
|
+
il 578
|
88
|
+
os 576
|
89
|
+
vi 572
|
90
|
+
nj 569
|
91
|
+
ak 564
|
92
|
+
_na 558
|
93
|
+
im 558
|
94
|
+
da_ 553
|
95
|
+
od 550
|
96
|
+
ao 550
|
97
|
+
al 549
|
98
|
+
om 545
|
99
|
+
na_ 533
|
100
|
+
_se 524
|
101
|
+
_i_ 523
|
102
|
+
h 517
|
103
|
+
_g 511
|
104
|
+
ma 508
|
105
|
+
at 502
|
106
|
+
cj 501
|
107
|
+
og 497
|
108
|
+
-- 493
|
109
|
+
ro 493
|
110
|
+
on 485
|
111
|
+
av 480
|
112
|
+
_da 474
|
113
|
+
_ne 474
|
114
|
+
ed 472
|
115
|
+
zy 471
|
116
|
+
se_ 466
|
117
|
+
_se_ 458
|
118
|
+
_bi 457
|
119
|
+
ao_ 452
|
120
|
+
ad 452
|
121
|
+
lj 445
|
122
|
+
es 444
|
123
|
+
ji 441
|
124
|
+
_v 433
|
125
|
+
_c 430
|
126
|
+
za 421
|
127
|
+
go 418
|
128
|
+
_r 413
|
129
|
+
_u_ 411
|
130
|
+
yi 410
|
131
|
+
ek 406
|
132
|
+
di 403
|
133
|
+
sa 396
|
134
|
+
et 393
|
135
|
+
ic 391
|
136
|
+
io 390
|
137
|
+
_da_ 389
|
138
|
+
to_ 389
|
139
|
+
as 386
|
140
|
+
_ko 383
|
141
|
+
ye 378
|
142
|
+
ar 378
|
143
|
+
mo 373
|
144
|
+
le 367
|
145
|
+
or 364
|
146
|
+
ju 363
|
147
|
+
el 354
|
148
|
+
tr 354
|
149
|
+
io_ 352
|
150
|
+
ve 345
|
151
|
+
lo_ 344
|
152
|
+
su 344
|
153
|
+
ol 344
|
154
|
+
am 344
|
155
|
+
iz 343
|
156
|
+
li_ 338
|
157
|
+
ti_ 336
|
158
|
+
sto 323
|
159
|
+
n_ 321
|
160
|
+
it 319
|
161
|
+
_za 319
|
162
|
+
sta 317
|
163
|
+
_ni 316
|
164
|
+
te 312
|
165
|
+
nu 312
|
166
|
+
a, 309
|
167
|
+
a,_ 309
|
168
|
+
ya 309
|
169
|
+
do 304
|
170
|
+
om_ 303
|
171
|
+
la_ 300
|
172
|
+
no_ 299
|
173
|
+
_na_ 299
|
174
|
+
d_ 297
|
175
|
+
ko_ 296
|
176
|
+
aj 294
|
177
|
+
ik 292
|
178
|
+
ru 291
|
179
|
+
ga 291
|
180
|
+
em 288
|
181
|
+
nje 283
|
182
|
+
dj 281
|
183
|
+
ne_ 281
|
184
|
+
k_ 277
|
185
|
+
_st 276
|
186
|
+
koj 276
|
187
|
+
ec 274
|
188
|
+
_ka 272
|
189
|
+
_su 270
|
190
|
+
ob 265
|
191
|
+
-_ 263
|
192
|
+
az 261
|
193
|
+
sv 260
|
194
|
+
_koj 260
|
195
|
+
im_ 260
|
196
|
+
ije_ 259
|
197
|
+
pa 258
|
198
|
+
ot 257
|
199
|
+
yt 256
|
200
|
+
ok 255
|
201
|
+
su_ 255
|
202
|
+
ih 254
|
203
|
+
me 253
|
204
|
+
dn 253
|
205
|
+
_cy 253
|
206
|
+
iv 251
|
207
|
+
syt 248
|
208
|
+
g_ 247
|
209
|
+
--_ 246
|
210
|
+
_- 246
|
211
|
+
kr 246
|
212
|
+
--- 246
|
213
|
+
a. 245
|
214
|
+
e,_ 245
|
215
|
+
---_ 245
|
216
|
+
e, 245
|
217
|
+
er 245
|
218
|
+
a._ 244
|
219
|
+
_iz 244
|
220
|
+
mi 243
|
221
|
+
_---_ 242
|
222
|
+
cyi 242
|
223
|
+
_-- 242
|
224
|
+
_--- 242
|
225
|
+
jed 240
|
226
|
+
h_ 239
|
227
|
+
_a 239
|
228
|
+
_sa 237
|
229
|
+
j_ 236
|
230
|
+
_l 231
|
231
|
+
_sv 229
|
232
|
+
_to 229
|
233
|
+
sk 228
|
234
|
+
ih_ 224
|
235
|
+
ja_ 223
|
236
|
+
pro 223
|
237
|
+
yn 222
|
238
|
+
t_ 222
|
239
|
+
ost 221
|
240
|
+
_do 221
|
241
|
+
oc 219
|
242
|
+
gl 218
|
243
|
+
_su_ 216
|
244
|
+
og_ 216
|
245
|
+
uc 214
|
246
|
+
s_ 214
|
247
|
+
bil 213
|
248
|
+
oz 213
|
249
|
+
ki 212
|
250
|
+
ni_ 212
|
251
|
+
nij 209
|
252
|
+
ako 208
|
253
|
+
eg 208
|
254
|
+
ut 205
|
255
|
+
pre 205
|
256
|
+
ci 204
|
257
|
+
ji_ 203
|
258
|
+
_od 203
|
259
|
+
ilo 202
|
260
|
+
ati 202
|
261
|
+
ac 201
|
262
|
+
ns 200
|
263
|
+
_mo 197
|
264
|
+
rij 196
|
265
|
+
bo 195
|
266
|
+
ovo 195
|
267
|
+
ku 195
|
268
|
+
dje 194
|
269
|
+
ma_ 192
|
270
|
+
_bil 191
|
271
|
+
cje 186
|
272
|
+
sti 186
|
273
|
+
_go 186
|
274
|
+
de 185
|
275
|
+
sl 183
|
276
|
+
_pro 182
|
277
|
+
ju_ 182
|
278
|
+
nije 181
|
279
|
+
tv 180
|
280
|
+
lje 179
|
281
|
+
isy 179
|
282
|
+
pri 178
|
283
|
+
_pre 177
|
284
|
+
dr 177
|
285
|
+
e._ 177
|
286
|
+
e. 177
|
287
|
+
op 176
|
288
|
+
ima 176
|
289
|
+
anj 175
|
290
|
+
jen 175
|
291
|
+
us 172
|
292
|
+
ilo_ 172
|
293
|
+
_ra 170
|
294
|
+
S 167
|
295
|
+
ecj 166
|
296
|
+
iti 166
|
297
|
+
sp 163
|
298
|
+
_S 161
|
299
|
+
vr 161
|
300
|
+
i. 161
|
301
|
+
i._ 161
|
302
|
+
zn 161
|
303
|
+
ali 161
|
304
|
+
i,_ 160
|
305
|
+
i, 160
|
306
|
+
ap 157
|
307
|
+
nije_ 157
|
308
|
+
nst 156
|
309
|
+
pi 156
|
310
|
+
ga_ 156
|
311
|
+
_sy 155
|
312
|
+
_nj 155
|
313
|
+
jes 155
|
314
|
+
ran 155
|
315
|
+
vo_ 155
|
316
|
+
yto 154
|
317
|
+
ev 153
|
318
|
+
_to_ 152
|
319
|
+
_pri 151
|
320
|
+
est 150
|
321
|
+
N 150
|
322
|
+
ins 150
|
323
|
+
ist 149
|
324
|
+
ir 149
|
325
|
+
o, 148
|
326
|
+
vj 148
|
327
|
+
vje 148
|
328
|
+
o,_ 148
|
329
|
+
B 148
|
330
|
+
zi 147
|
331
|
+
jec 147
|
332
|
+
gov 147
|
333
|
+
yto_ 147
|
334
|
+
syto 146
|
335
|
+
ton 146
|
336
|
+
od_ 145
|
337
|
+
O 144
|
338
|
+
rije 144
|
339
|
+
lik 143
|
340
|
+
on_ 142
|
341
|
+
ocy 142
|
342
|
+
W 142
|
343
|
+
ba 142
|
344
|
+
_W 141
|
345
|
+
kao 141
|
346
|
+
Wi 141
|
347
|
+
_N 141
|
348
|
+
inst 141
|
349
|
+
_nij 141
|
350
|
+
_nije 140
|
351
|
+
_Wi 140
|
352
|
+
syto_ 140
|
353
|
+
lic 139
|
354
|
+
P 139
|
355
|
+
ovi 138
|
356
|
+
_tr 138
|
357
|
+
rs 137
|
358
|
+
ez 137
|
359
|
+
edn 136
|
360
|
+
_P 136
|
361
|
+
si 136
|
362
|
+
ili 136
|
363
|
+
du 136
|
364
|
+
Winst 135
|
365
|
+
cye 135
|
366
|
+
nston 135
|
367
|
+
ston 135
|
368
|
+
ud 135
|
369
|
+
kao_ 135
|
370
|
+
Wins 135
|
371
|
+
insto 135
|
372
|
+
oji 135
|
373
|
+
nsto 135
|
374
|
+
Win 135
|
375
|
+
raz 135
|
376
|
+
zye 135
|
377
|
+
_Win 134
|
378
|
+
ova 134
|
379
|
+
_Wins 134
|
380
|
+
_on 133
|
381
|
+
ako_ 133
|
382
|
+
odi 133
|
383
|
+
cya 133
|
384
|
+
ila 133
|
385
|
+
icy 133
|
386
|
+
oj_ 133
|
387
|
+
ke 133
|
388
|
+
va_ 132
|
389
|
+
ija 132
|
390
|
+
_is 132
|
391
|
+
jel 132
|
392
|
+
oje 130
|
393
|
+
pu 130
|
394
|
+
cje_ 130
|
395
|
+
bi_ 129
|
396
|
+
rat 128
|
397
|
+
ce 128
|
398
|
+
tu 128
|
399
|
+
mu 128
|
400
|
+
ve_ 127
|
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 26378
|
2
|
+
o 5870
|
3
|
+
e 5354
|
4
|
+
a 4740
|
5
|
+
n 4462
|
6
|
+
t 3745
|
7
|
+
s 3438
|
8
|
+
i 3187
|
9
|
+
v 3118
|
10
|
+
l 2891
|
11
|
+
r 2754
|
12
|
+
k 2566
|
13
|
+
d 2508
|
14
|
+
m 2198
|
15
|
+
u 2197
|
16
|
+
p 2032
|
17
|
+
� 1924
|
18
|
+
c 1678
|
19
|
+
h 1572
|
20
|
+
z 1544
|
21
|
+
� 1522
|
22
|
+
_p 1299
|
23
|
+
e_ 1266
|
24
|
+
y 1231
|
25
|
+
a_ 1219
|
26
|
+
j 1219
|
27
|
+
_s 1156
|
28
|
+
b 1079
|
29
|
+
o_ 1065
|
30
|
+
� 1043
|
31
|
+
_v 1038
|
32
|
+
, 952
|
33
|
+
,_ 946
|
34
|
+
st 945
|
35
|
+
_n 911
|
36
|
+
� 878
|
37
|
+
. 870
|
38
|
+
�_ 848
|
39
|
+
� 822
|
40
|
+
._ 803
|
41
|
+
n� 782
|
42
|
+
ov 757
|
43
|
+
_z 723
|
44
|
+
i_ 716
|
45
|
+
u_ 684
|
46
|
+
ro 674
|
47
|
+
en 656
|
48
|
+
� 647
|
49
|
+
� 639
|
50
|
+
po 630
|
51
|
+
ch 629
|
52
|
+
� 625
|
53
|
+
na 599
|
54
|
+
_a 598
|
55
|
+
sk 592
|
56
|
+
� 563
|
57
|
+
ho 552
|
58
|
+
_d 551
|
59
|
+
ra 545
|
60
|
+
m_ 539
|
61
|
+
y_ 530
|
62
|
+
_t 512
|
63
|
+
ko 504
|
64
|
+
_k 503
|
65
|
+
le 502
|
66
|
+
_j 501
|
67
|
+
_o 486
|
68
|
+
to 479
|
69
|
+
pr 471
|
70
|
+
ne 468
|
71
|
+
n�_ 462
|
72
|
+
je 458
|
73
|
+
�_ 456
|
74
|
+
ti 455
|
75
|
+
od 433
|
76
|
+
li 432
|
77
|
+
va 432
|
78
|
+
_po 429
|
79
|
+
_m 428
|
80
|
+
al 424
|
81
|
+
te 424
|
82
|
+
ou 423
|
83
|
+
ed 418
|
84
|
+
se 415
|
85
|
+
la 410
|
86
|
+
no 397
|
87
|
+
os 382
|
88
|
+
lo 377
|
89
|
+
an 376
|
90
|
+
_pr 375
|
91
|
+
� 375
|
92
|
+
v_ 372
|
93
|
+
�e 370
|
94
|
+
_a_ 364
|
95
|
+
em 363
|
96
|
+
at 360
|
97
|
+
ta 359
|
98
|
+
do 357
|
99
|
+
t_ 357
|
100
|
+
_b 355
|
101
|
+
or 349
|
102
|
+
h_ 345
|
103
|
+
_v_ 338
|
104
|
+
ch_ 327
|
105
|
+
S 325
|
106
|
+
ce 323
|
107
|
+
av 323
|
108
|
+
p� 322
|
109
|
+
ni 319
|
110
|
+
k� 316
|
111
|
+
er 315
|
112
|
+
n� 315
|
113
|
+
_na 313
|
114
|
+
na_ 312
|
115
|
+
_ne 311
|
116
|
+
de 308
|
117
|
+
ic 307
|
118
|
+
in 306
|
119
|
+
_se 306
|
120
|
+
l_ 304
|
121
|
+
dn 302
|
122
|
+
za 298
|
123
|
+
_p� 293
|
124
|
+
�_ 291
|
125
|
+
ol 290
|
126
|
+
_je 281
|
127
|
+
ob 280
|
128
|
+
is 277
|
129
|
+
ve 274
|
130
|
+
ho_ 272
|
131
|
+
es 270
|
132
|
+
ot 268
|
133
|
+
ak 265
|
134
|
+
vo 263
|
135
|
+
n� 260
|
136
|
+
il 257
|
137
|
+
se_ 257
|
138
|
+
it 256
|
139
|
+
et 253
|
140
|
+
ad 250
|
141
|
+
by 249
|
142
|
+
P 242
|
143
|
+
_r 242
|
144
|
+
k_ 242
|
145
|
+
ost 241
|
146
|
+
_se_ 241
|
147
|
+
tr 238
|
148
|
+
me 237
|
149
|
+
pro 234
|
150
|
+
�e 234
|
151
|
+
ka 230
|
152
|
+
_za 227
|
153
|
+
om 224
|
154
|
+
el 223
|
155
|
+
_P 223
|
156
|
+
on 218
|
157
|
+
_pro 216
|
158
|
+
ou_ 216
|
159
|
+
tu 215
|
160
|
+
O 212
|
161
|
+
mi 212
|
162
|
+
ku 211
|
163
|
+
_u 210
|
164
|
+
_do 208
|
165
|
+
_l 207
|
166
|
+
_na_ 206
|
167
|
+
N 205
|
168
|
+
sk� 205
|
169
|
+
�m 205
|
170
|
+
�c 205
|
171
|
+
�_ 203
|
172
|
+
m� 203
|
173
|
+
_S 200
|
174
|
+
oz 200
|
175
|
+
V 200
|
176
|
+
ze 198
|
177
|
+
da 194
|
178
|
+
sl 192
|
179
|
+
�_ 191
|
180
|
+
ova 190
|
181
|
+
mo 190
|
182
|
+
re 189
|
183
|
+
so 187
|
184
|
+
vy 186
|
185
|
+
ej 185
|
186
|
+
r� 184
|
187
|
+
ar 184
|
188
|
+
s_ 183
|
189
|
+
v� 183
|
190
|
+
A 181
|
191
|
+
ru 180
|
192
|
+
_st 178
|
193
|
+
f 178
|
194
|
+
�h 177
|
195
|
+
�ho 176
|
196
|
+
kt 176
|
197
|
+
tn 175
|
198
|
+
g 174
|
199
|
+
bo 174
|
200
|
+
ez 173
|
201
|
+
ci 172
|
202
|
+
k� 172
|
203
|
+
n� 170
|
204
|
+
M 170
|
205
|
+
�n 169
|
206
|
+
as 168
|
207
|
+
vi 167
|
208
|
+
�i 167
|
209
|
+
ac 166
|
210
|
+
�e_ 165
|
211
|
+
�c 165
|
212
|
+
�_ 165
|
213
|
+
ck 164
|
214
|
+
K 164
|
215
|
+
B 164
|
216
|
+
�ch 164
|
217
|
+
v� 162
|
218
|
+
_c 162
|
219
|
+
�ho_ 162
|
220
|
+
en� 161
|
221
|
+
l� 160
|
222
|
+
_� 160
|
223
|
+
�� 160
|
224
|
+
p�e 159
|
225
|
+
ec 158
|
226
|
+
�_ 157
|
227
|
+
J 156
|
228
|
+
vn 156
|
229
|
+
_h 155
|
230
|
+
k�_ 155
|
231
|
+
ok 154
|
232
|
+
sta 154
|
233
|
+
to_ 152
|
234
|
+
v� 152
|
235
|
+
nt 151
|
236
|
+
�ch_ 149
|
237
|
+
lo_ 149
|
238
|
+
_by 149
|
239
|
+
dy 149
|
240
|
+
_p�e 148
|
241
|
+
ce_ 147
|
242
|
+
R 146
|
243
|
+
n_ 146
|
244
|
+
�d 146
|
245
|
+
pa 145
|
246
|
+
v� 145
|
247
|
+
am 145
|
248
|
+
mu 145
|
249
|
+
n� 145
|
250
|
+
ud 144
|
251
|
+
_� 144
|
252
|
+
_B 142
|
253
|
+
ter 141
|
254
|
+
n�_ 141
|
255
|
+
�e 140
|
256
|
+
�e 140
|
257
|
+
_V 140
|
258
|
+
_ko 140
|
259
|
+
li_ 139
|
260
|
+
d� 137
|
261
|
+
hl 137
|
262
|
+
je_ 137
|
263
|
+
ji 137
|
264
|
+
ist 135
|
265
|
+
j� 135
|
266
|
+
- 134
|
267
|
+
ik 133
|
268
|
+
si 133
|
269
|
+
�l 132
|
270
|
+
em_ 132
|
271
|
+
_to 132
|
272
|
+
_vy 131
|
273
|
+
sp 130
|
274
|
+
ut 130
|
275
|
+
_J 130
|
276
|
+
_�e 130
|
277
|
+
_M 129
|
278
|
+
di 129
|
279
|
+
kon 128
|
280
|
+
la_ 128
|
281
|
+
t� 128
|
282
|
+
_ro 127
|
283
|
+
ns 127
|
284
|
+
ek 126
|
285
|
+
ick 126
|
286
|
+
T 126
|
287
|
+
yl 125
|
288
|
+
�n 125
|
289
|
+
rn 125
|
290
|
+
_�e_ 124
|
291
|
+
op 124
|
292
|
+
sti 124
|
293
|
+
kte 124
|
294
|
+
�ed 124
|
295
|
+
edn 123
|
296
|
+
us 121
|
297
|
+
�m_ 120
|
298
|
+
" 119
|
299
|
+
z_ 119
|
300
|
+
str 118
|
301
|
+
ti_ 118
|
302
|
+
�m 118
|
303
|
+
vat 118
|
304
|
+
d_ 118
|
305
|
+
_ve 118
|
306
|
+
�v 118
|
307
|
+
en�_ 117
|
308
|
+
iv 117
|
309
|
+
oj 117
|
310
|
+
_kt 117
|
311
|
+
�l 117
|
312
|
+
val 116
|
313
|
+
eb 116
|
314
|
+
_K 115
|
315
|
+
t� 115
|
316
|
+
_kte 115
|
317
|
+
�t 115
|
318
|
+
_i 114
|
319
|
+
_N 114
|
320
|
+
D 114
|
321
|
+
kl 114
|
322
|
+
ny 114
|
323
|
+
byl 113
|
324
|
+
ev 113
|
325
|
+
ri 113
|
326
|
+
� 113
|
327
|
+
ky 111
|
328
|
+
sm 111
|
329
|
+
oh 111
|
330
|
+
E 110
|
331
|
+
ma 110
|
332
|
+
�t 110
|
333
|
+
sk� 110
|
334
|
+
kter 109
|
335
|
+
nu 109
|
336
|
+
le_ 108
|
337
|
+
ja 107
|
338
|
+
z� 107
|
339
|
+
t� 106
|
340
|
+
t� 106
|
341
|
+
zn 106
|
342
|
+
let 105
|
343
|
+
aj 105
|
344
|
+
sto 105
|
345
|
+
�� 105
|
346
|
+
me_ 105
|
347
|
+
-_ 105
|
348
|
+
u, 105
|
349
|
+
sv 104
|
350
|
+
_le 104
|
351
|
+
pol 104
|
352
|
+
L 104
|
353
|
+
_- 104
|
354
|
+
ln 104
|
355
|
+
pod 104
|
356
|
+
H 103
|
357
|
+
zi 103
|
358
|
+
k�h 103
|
359
|
+
k�ho 103
|
360
|
+
_n� 103
|
361
|
+
ent 102
|
362
|
+
u,_ 102
|
363
|
+
_od 102
|
364
|
+
n�_ 101
|
365
|
+
_-_ 101
|
366
|
+
al_ 101
|
367
|
+
_kter 101
|
368
|
+
do_ 100
|
369
|
+
nos 100
|
370
|
+
c� 100
|
371
|
+
rav 99
|
372
|
+
ran 99
|
373
|
+
_sv 99
|
374
|
+
k� 98
|
375
|
+
e� 98
|
376
|
+
n�m 98
|
377
|
+
bu 97
|
378
|
+
_z_ 97
|
379
|
+
�ch 97
|
380
|
+
_byl 97
|
381
|
+
�n� 96
|
382
|
+
rov 96
|
383
|
+
kr 96
|
384
|
+
d� 95
|
385
|
+
ov� 95
|
386
|
+
dl 95
|
387
|
+
uj 95
|
388
|
+
nost 95
|
389
|
+
�m_ 95
|
390
|
+
ech 94
|
391
|
+
ly 94
|
392
|
+
oc 94
|
393
|
+
v�_ 93
|
394
|
+
_o_ 93
|
395
|
+
dy_ 93
|
396
|
+
ak_ 93
|
397
|
+
nsk 93
|
398
|
+
_so 93
|
399
|
+
_ob 92
|
400
|
+
nc 92
|