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.
Files changed (172) hide show
  1. data/README.rdoc +24 -0
  2. data/Rakefile +18 -0
  3. data/VERSION +1 -0
  4. data/lib/language_detector.rb +232 -0
  5. data/lib/model-fm.yml +52504 -0
  6. data/lib/model-tc.yml +53985 -0
  7. data/lib/textcat_ngrams/afrikaans.lm +400 -0
  8. data/lib/textcat_ngrams/albanian.lm +400 -0
  9. data/lib/textcat_ngrams/amharic-utf.lm +400 -0
  10. data/lib/textcat_ngrams/arabic-iso8859_6.lm +400 -0
  11. data/lib/textcat_ngrams/arabic-windows1256.lm +400 -0
  12. data/lib/textcat_ngrams/armenian.lm +400 -0
  13. data/lib/textcat_ngrams/basque.lm +400 -0
  14. data/lib/textcat_ngrams/belarus-windows1251.lm +400 -0
  15. data/lib/textcat_ngrams/bosnian.lm +400 -0
  16. data/lib/textcat_ngrams/breton.lm +400 -0
  17. data/lib/textcat_ngrams/bulgarian-iso8859_5.lm +400 -0
  18. data/lib/textcat_ngrams/catalan.lm +400 -0
  19. data/lib/textcat_ngrams/chinese-big5.lm +400 -0
  20. data/lib/textcat_ngrams/chinese-gb2312.lm +400 -0
  21. data/lib/textcat_ngrams/croatian-ascii.lm +400 -0
  22. data/lib/textcat_ngrams/czech-iso8859_2.lm +400 -0
  23. data/lib/textcat_ngrams/danish.lm +400 -0
  24. data/lib/textcat_ngrams/dutch.lm +400 -0
  25. data/lib/textcat_ngrams/english.lm +400 -0
  26. data/lib/textcat_ngrams/esperanto.lm +400 -0
  27. data/lib/textcat_ngrams/estonian.lm +400 -0
  28. data/lib/textcat_ngrams/finnish.lm +400 -0
  29. data/lib/textcat_ngrams/french.lm +400 -0
  30. data/lib/textcat_ngrams/frisian.lm +400 -0
  31. data/lib/textcat_ngrams/georgian.lm +400 -0
  32. data/lib/textcat_ngrams/german.lm +400 -0
  33. data/lib/textcat_ngrams/greek-iso8859-7.lm +400 -0
  34. data/lib/textcat_ngrams/hebrew-iso8859_8.lm +400 -0
  35. data/lib/textcat_ngrams/hindi.lm +400 -0
  36. data/lib/textcat_ngrams/hungarian.lm +400 -0
  37. data/lib/textcat_ngrams/icelandic.lm +400 -0
  38. data/lib/textcat_ngrams/indonesian.lm +400 -0
  39. data/lib/textcat_ngrams/irish.lm +400 -0
  40. data/lib/textcat_ngrams/italian.lm +400 -0
  41. data/lib/textcat_ngrams/japanese-euc_jp.lm +400 -0
  42. data/lib/textcat_ngrams/japanese-shift_jis.lm +400 -0
  43. data/lib/textcat_ngrams/korean.lm +400 -0
  44. data/lib/textcat_ngrams/latin.lm +400 -0
  45. data/lib/textcat_ngrams/latvian.lm +400 -0
  46. data/lib/textcat_ngrams/lithuanian.lm +400 -0
  47. data/lib/textcat_ngrams/malay.lm +400 -0
  48. data/lib/textcat_ngrams/manx.lm +400 -0
  49. data/lib/textcat_ngrams/marathi.lm +400 -0
  50. data/lib/textcat_ngrams/mingo.lm +400 -0
  51. data/lib/textcat_ngrams/nepali.lm +400 -0
  52. data/lib/textcat_ngrams/norwegian.lm +400 -0
  53. data/lib/textcat_ngrams/persian.lm +400 -0
  54. data/lib/textcat_ngrams/polish.lm +400 -0
  55. data/lib/textcat_ngrams/portuguese.lm +400 -0
  56. data/lib/textcat_ngrams/quechua.lm +400 -0
  57. data/lib/textcat_ngrams/romanian.lm +400 -0
  58. data/lib/textcat_ngrams/rumantsch.lm +400 -0
  59. data/lib/textcat_ngrams/russian-iso8859_5.lm +400 -0
  60. data/lib/textcat_ngrams/russian-koi8_r.lm +400 -0
  61. data/lib/textcat_ngrams/russian-windows1251.lm +400 -0
  62. data/lib/textcat_ngrams/sanskrit.lm +400 -0
  63. data/lib/textcat_ngrams/scots.lm +400 -0
  64. data/lib/textcat_ngrams/scots_gaelic.lm +400 -0
  65. data/lib/textcat_ngrams/serbian-ascii.lm +400 -0
  66. data/lib/textcat_ngrams/slovak-ascii.lm +400 -0
  67. data/lib/textcat_ngrams/slovak-windows1250.lm +400 -0
  68. data/lib/textcat_ngrams/slovenian-ascii.lm +400 -0
  69. data/lib/textcat_ngrams/slovenian-iso8859_2.lm +400 -0
  70. data/lib/textcat_ngrams/spanish.lm +400 -0
  71. data/lib/textcat_ngrams/swahili.lm +400 -0
  72. data/lib/textcat_ngrams/swedish.lm +400 -0
  73. data/lib/textcat_ngrams/tagalog.lm +400 -0
  74. data/lib/textcat_ngrams/tamil.lm +400 -0
  75. data/lib/textcat_ngrams/thai.lm +400 -0
  76. data/lib/textcat_ngrams/turkish.lm +400 -0
  77. data/lib/textcat_ngrams/ukrainian-koi8_u.lm +400 -0
  78. data/lib/textcat_ngrams/vietnamese.lm +400 -0
  79. data/lib/textcat_ngrams/welsh.lm +400 -0
  80. data/lib/textcat_ngrams/yiddish-utf.lm +400 -0
  81. data/lib/training_data/ar-utf8.txt +54 -0
  82. data/lib/training_data/bg-utf8.txt +26 -0
  83. data/lib/training_data/cs-utf8.txt +48 -0
  84. data/lib/training_data/da-utf8.txt +159 -0
  85. data/lib/training_data/de-utf8.txt +569 -0
  86. data/lib/training_data/el-utf8.txt +48 -0
  87. data/lib/training_data/en-utf8.txt +81 -0
  88. data/lib/training_data/es-utf8.txt +185 -0
  89. data/lib/training_data/et-utf8.txt +50 -0
  90. data/lib/training_data/fa-utf8.txt +42 -0
  91. data/lib/training_data/fi-utf8.txt +83 -0
  92. data/lib/training_data/fr-utf8.txt +191 -0
  93. data/lib/training_data/fy-utf8.txt +22 -0
  94. data/lib/training_data/ga-utf8.txt +109 -0
  95. data/lib/training_data/he-utf8.txt +116 -0
  96. data/lib/training_data/hi-utf8.txt +49 -0
  97. data/lib/training_data/hr-utf8.txt +80 -0
  98. data/lib/training_data/hu-utf8.txt +87 -0
  99. data/lib/training_data/io-utf8.txt +41 -0
  100. data/lib/training_data/is-utf8.txt +94 -0
  101. data/lib/training_data/it-utf8.txt +228 -0
  102. data/lib/training_data/ja-utf8.txt +200 -0
  103. data/lib/training_data/ko-utf8.txt +147 -0
  104. data/lib/training_data/nl-utf8.txt +215 -0
  105. data/lib/training_data/no-utf8.txt +281 -0
  106. data/lib/training_data/pl-utf8.txt +120 -0
  107. data/lib/training_data/pt-utf8.txt +214 -0
  108. data/lib/training_data/ro-utf8.txt +66 -0
  109. data/lib/training_data/ru-utf8.txt +310 -0
  110. data/lib/training_data/sl-utf8.txt +263 -0
  111. data/lib/training_data/sv-utf8.txt +174 -0
  112. data/lib/training_data/th-utf8.txt +49 -0
  113. data/lib/training_data/tk-utf8.txt +101 -0
  114. data/lib/training_data/todo/af.txt +114 -0
  115. data/lib/training_data/todo/amharic-utf.txt +95 -0
  116. data/lib/training_data/todo/arabic-windows1256.txt +157 -0
  117. data/lib/training_data/todo/armenian.txt +86 -0
  118. data/lib/training_data/todo/basque.txt +136 -0
  119. data/lib/training_data/todo/belarus-windows1251.txt +97 -0
  120. data/lib/training_data/todo/bosnian.txt +97 -0
  121. data/lib/training_data/todo/breton.txt +159 -0
  122. data/lib/training_data/todo/bulgarian-iso8859_5.txt +115 -0
  123. data/lib/training_data/todo/catalan.txt +93 -0
  124. data/lib/training_data/todo/croatian-ascii.txt +104 -0
  125. data/lib/training_data/todo/esperanto.txt +95 -0
  126. data/lib/training_data/todo/estonian.txt +218 -0
  127. data/lib/training_data/todo/frisian.txt +99 -0
  128. data/lib/training_data/todo/georgian.txt +86 -0
  129. data/lib/training_data/todo/greek-iso8859-7.txt +139 -0
  130. data/lib/training_data/todo/hawaian.txt +108 -0
  131. data/lib/training_data/todo/hebrew-iso8859_8.txt +79 -0
  132. data/lib/training_data/todo/hindi.txt +77 -0
  133. data/lib/training_data/todo/hungarian.txt +102 -0
  134. data/lib/training_data/todo/icelandic.txt +131 -0
  135. data/lib/training_data/todo/indonesian.txt +93 -0
  136. data/lib/training_data/todo/irish.txt +209 -0
  137. data/lib/training_data/todo/latin.txt +120 -0
  138. data/lib/training_data/todo/latvian.txt +126 -0
  139. data/lib/training_data/todo/lithuanian.txt +99 -0
  140. data/lib/training_data/todo/malay.txt +108 -0
  141. data/lib/training_data/todo/manx.txt +78 -0
  142. data/lib/training_data/todo/marathi.txt +100 -0
  143. data/lib/training_data/todo/mf.txt +100 -0
  144. data/lib/training_data/todo/middle_frisian.txt +102 -0
  145. data/lib/training_data/todo/mingo.txt +146 -0
  146. data/lib/training_data/todo/nepali.txt +131 -0
  147. data/lib/training_data/todo/persian.txt +73 -0
  148. data/lib/training_data/todo/quechua.txt +108 -0
  149. data/lib/training_data/todo/romanian.txt +103 -0
  150. data/lib/training_data/todo/rumantsch.txt +110 -0
  151. data/lib/training_data/todo/sanskrit.txt +135 -0
  152. data/lib/training_data/todo/scots.txt +490 -0
  153. data/lib/training_data/todo/scots_gaelic.txt +93 -0
  154. data/lib/training_data/todo/serbian-ascii.txt +121 -0
  155. data/lib/training_data/todo/slovak-ascii.txt +102 -0
  156. data/lib/training_data/todo/slovak-windows1250.txt +115 -0
  157. data/lib/training_data/todo/slovenian-ascii.txt +100 -0
  158. data/lib/training_data/todo/slovenian-iso8859_2.txt +96 -0
  159. data/lib/training_data/todo/sq.txt +110 -0
  160. data/lib/training_data/todo/swahili.txt +120 -0
  161. data/lib/training_data/todo/tagalog.txt +135 -0
  162. data/lib/training_data/todo/tamil.txt +123 -0
  163. data/lib/training_data/todo/turkish.txt +117 -0
  164. data/lib/training_data/todo/ukrainian-koi8_r.txt +214 -0
  165. data/lib/training_data/todo/vietnamese.txt +92 -0
  166. data/lib/training_data/todo/welsh.txt +148 -0
  167. data/lib/training_data/todo/yiddish-utf.txt +83 -0
  168. data/lib/training_data/uk-utf8.txt +75 -0
  169. data/lib/training_data/vi-utf8.txt +47 -0
  170. data/lib/training_data/zh-utf8.txt +228 -0
  171. data/test/language_detector_test.rb +78 -0
  172. metadata +232 -0
@@ -0,0 +1,400 @@
1
+ _ 78614
2
+ a 18113
3
+ d 17890
4
+ y 16837
5
+ e 14108
6
+ n 13902
7
+ r 13869
8
+ i 12928
9
+ o 9972
10
+ l 9188
11
+ h 7454
12
+ g 7165
13
+ w 7010
14
+ t 6296
15
+ f 6080
16
+ u 5400
17
+ n_ 5159
18
+ _y 5051
19
+ dd 4946
20
+ s 4884
21
+ r_ 4547
22
+ m 4364
23
+ d_ 4223
24
+ yn 4082
25
+ _a 4020
26
+ c 3707
27
+ th 3301
28
+ u_ 2900
29
+ yd 2900
30
+ ae 2649
31
+ l_ 2588
32
+ _g 2547
33
+ . 2460
34
+ ' 2458
35
+ ._ 2408
36
+ wy 2334
37
+ yn_ 2331
38
+ _d 2307
39
+ b 2267
40
+ ym 2262
41
+ ra 2261
42
+ an 2235
43
+ ar 2228
44
+ ol 2218
45
+ ia 2212
46
+ i_ 2199
47
+ ed 2191
48
+ _yn 2038
49
+ _i 2020
50
+ y_ 1983
51
+ _c 1934
52
+ _yn_ 1861
53
+ ei 1815
54
+ it 1796
55
+ g_ 1787
56
+ ith 1779
57
+ dd_ 1745
58
+ h_ 1741
59
+ ydd 1731
60
+ ai 1709
61
+ au 1708
62
+ 'r_ 1655
63
+ 'r 1655
64
+ _y_ 1621
65
+ di 1615
66
+ , 1613
67
+ ,_ 1608
68
+ da 1585
69
+ od 1546
70
+ _o 1535
71
+ ad 1532
72
+ th_ 1510
73
+ ll 1494
74
+ au_ 1492
75
+ _s 1415
76
+ er 1359
77
+ o_ 1350
78
+ io 1311
79
+ a_ 1299
80
+ ol_ 1294
81
+ _e 1273
82
+ _h 1249
83
+ cy 1246
84
+ yr 1243
85
+ en 1228
86
+ p 1217
87
+ _f 1212
88
+ _cy 1203
89
+ mr 1200
90
+ gy 1193
91
+ ymr 1185
92
+ ha 1172
93
+ hy 1164
94
+ eg 1159
95
+ do 1151
96
+ edd 1147
97
+ G 1134
98
+ we 1107
99
+ C 1089
100
+ _ar 1078
101
+ _m 1075
102
+ yf 1057
103
+ de 1048
104
+ fe 1047
105
+ _G 1045
106
+ ch 1043
107
+ rae 1023
108
+ el 1016
109
+ no 1010
110
+ ni 1010
111
+ _b 1009
112
+ ne 1001
113
+ ef 992
114
+ ri 983
115
+ et 978
116
+ _C 957
117
+ _gy 952
118
+ _a_ 943
119
+ eth 943
120
+ _. 940
121
+ _._ 939
122
+ eit 930
123
+ eith 927
124
+ ys 921
125
+ wyd 912
126
+ ga 901
127
+ _i_ 893
128
+ s_ 887
129
+ mrae 878
130
+ mraeg 878
131
+ raeg 878
132
+ ymrae 878
133
+ aeg 878
134
+ ymra 878
135
+ mra 878
136
+ _p 856
137
+ aet 850
138
+ aeth 850
139
+ _n 844
140
+ un 838
141
+ on 836
142
+ ait 833
143
+ aith 833
144
+ nn 830
145
+ at 827
146
+ oe 823
147
+ li 805
148
+ _r 801
149
+ ddi 795
150
+ gw 789
151
+ ma 783
152
+ le 777
153
+ nt 772
154
+ ho 769
155
+ ff 766
156
+ yr_ 764
157
+ na 753
158
+ la 748
159
+ rh 747
160
+ eg_ 734
161
+ si 733
162
+ ng 732
163
+ dol 732
164
+ ro 718
165
+ al 712
166
+ _dd 706
167
+ wn 705
168
+ oed 705
169
+ Gy 704
170
+ dy 701
171
+ Cy 696
172
+ o' 692
173
+ ar_ 691
174
+ ny 690
175
+ Gym 678
176
+ wr 677
177
+ id 676
178
+ _Gy 672
179
+ _o_ 668
180
+ Gymr 667
181
+ if 662
182
+ ith_ 662
183
+ _ar_ 660
184
+ iad 657
185
+ _w 657
186
+ fo 656
187
+ eu 655
188
+ aeg_ 650
189
+ raeg_ 650
190
+ aith_ 648
191
+ or 648
192
+ _Gym 646
193
+ fa 642
194
+ re 638
195
+ _Cy 638
196
+ _Gymr 635
197
+ _gw 633
198
+ fy 633
199
+ oedd 633
200
+ edd_ 629
201
+ rd 627
202
+ od_ 622
203
+ ac 619
204
+ ddo 612
205
+ an_ 607
206
+ Gymra 606
207
+ er_ 605
208
+ A 604
209
+ eth_ 601
210
+ hw 596
211
+ ydd_ 591
212
+ o'r 586
213
+ o'r_ 586
214
+ es 583
215
+ ir 579
216
+ dw 573
217
+ go 559
218
+ yl 548
219
+ rw 545
220
+ aeth_ 545
221
+ wydd 543
222
+ aw 539
223
+ _rh 539
224
+ dr 537
225
+ ly 537
226
+ fn 534
227
+ dau 533
228
+ _hy 531
229
+ t_ 531
230
+ sg 529
231
+ 'n 529
232
+ * 528
233
+ 'n_ 523
234
+ _* 522
235
+ nyd 521
236
+ nydd 521
237
+ M 519
238
+ st 518
239
+ Y 516
240
+ sy 515
241
+ yd_ 513
242
+ lw 512
243
+ _ga 508
244
+ iai 503
245
+ il 502
246
+ _l 499
247
+ rt 494
248
+ ad_ 493
249
+ _yr 493
250
+ _yr_ 492
251
+ as 492
252
+ dol_ 492
253
+ f_ 491
254
+ dda 491
255
+ ig 490
256
+ og 484
257
+ wa 479
258
+ he 478
259
+ iaith 477
260
+ iait 477
261
+ oedd_ 475
262
+ _ma 473
263
+ c_ 472
264
+ Cym 470
265
+ te 469
266
+ _ym 467
267
+ am 467
268
+ _M 465
269
+ _ia 462
270
+ efn 462
271
+ i' 460
272
+ ie 458
273
+ _Cym 458
274
+ _ac 457
275
+ dau_ 456
276
+ yw 455
277
+ ew 453
278
+ fr 441
279
+ fod 441
280
+ _A 441
281
+ du 437
282
+ _sy 434
283
+ e_ 432
284
+ wi 426
285
+ Cymr 426
286
+ se 425
287
+ B 424
288
+ D 424
289
+ _Cymr 423
290
+ bl 423
291
+ lu 420
292
+ in 417
293
+ _t 417
294
+ tr 414
295
+ ac_ 413
296
+ wed 410
297
+ os 410
298
+ _iai 407
299
+ _iait 407
300
+ el_ 405
301
+ _ac_ 405
302
+ rha 404
303
+ m_ 404
304
+ is 403
305
+ on_ 401
306
+ eu_ 393
307
+ hi 393
308
+ rdd 393
309
+ id_ 389
310
+ _Y 388
311
+ ry 387
312
+ odd 387
313
+ rwy 387
314
+ rf 386
315
+ io_ 380
316
+ ynn 380
317
+ cyf 380
318
+ hr 380
319
+ _cyf 379
320
+ yddi 379
321
+ cyn 372
322
+ _de 372
323
+ rth 371
324
+ ru 368
325
+ S 363
326
+ wei 363
327
+ ysg 362
328
+ _B 362
329
+ u' 361
330
+ yddo 360
331
+ wn_ 360
332
+ so 359
333
+ dio 359
334
+ _ei 358
335
+ N 356
336
+ dwy 355
337
+ _da 353
338
+ me 353
339
+ gan 353
340
+ gyf 353
341
+ w_ 352
342
+ _o' 351
343
+ fer 349
344
+ nol 347
345
+ hyn 346
346
+ ddy 346
347
+ af 346
348
+ ta 343
349
+ ddol 343
350
+ _fe 340
351
+ nd 340
352
+ mae 338
353
+ _cyn 338
354
+ efnyd 337
355
+ fnydd 337
356
+ fny 337
357
+ efny 337
358
+ fnyd 337
359
+ iad_ 335
360
+ _mae 333
361
+ ion 333
362
+ _ll 330
363
+ def 330
364
+ _gyf 327
365
+ nt_ 326
366
+ i'r_ 326
367
+ - 326
368
+ i'r 326
369
+ weith 325
370
+ weit 325
371
+ defn 325
372
+ defny 325
373
+ bo 324
374
+ hyd 323
375
+ by 322
376
+ _si 321
377
+ ir_ 321
378
+ hau 318
379
+ nod 318
380
+ edi 315
381
+ I 314
382
+ fyd 313
383
+ wyr 313
384
+ ada 311
385
+ ddio 310
386
+ rif 309
387
+ sia 307
388
+ sa 306
389
+ fel 305
390
+ tha 305
391
+ _S 302
392
+ _ne 302
393
+ _u 301
394
+ fod_ 300
395
+ _o'r 300
396
+ yg 300
397
+ _o'r_ 300
398
+ _i' 299
399
+ ge 299
400
+ dia 299
@@ -0,0 +1,400 @@
1
+ � 29767
2
+ _ 13552
3
+ _� 6516
4
+ � 4273
5
+ � 3670
6
+ א 3670
7
+ ע 3261
8
+ � 3261
9
+ �� 2826
10
+ ע� 2826
11
+ א� 2785
12
+ �� 2785
13
+ י 2565
14
+ � 2565
15
+ � 2082
16
+ ר 2082
17
+ �� 2062
18
+ י� 2062
19
+ � 1857
20
+ ט 1857
21
+ � 1828
22
+ ַ 1828
23
+ � 1793
24
+ ן 1793
25
+ _א 1537
26
+ �_ 1532
27
+ ן_ 1532
28
+ �� 1527
29
+ ַ� 1527
30
+ אַ 1517
31
+ �ַ 1517
32
+ ר� 1355
33
+ �� 1355
34
+ � 1270
35
+ ל 1270
36
+ � 1268
37
+ אָ 1268
38
+ ָ 1268
39
+ �ָ 1268
40
+ �ַ� 1240
41
+ אַ� 1240
42
+ נ 1232
43
+ � 1232
44
+ אָ� 1229
45
+ �ָ� 1229
46
+ �� 1229
47
+ ָ� 1229
48
+ נ� 1181
49
+ �� 1181
50
+ ו 1116
51
+ � 1116
52
+ � 1031
53
+ ד 1031
54
+ ט� 1012
55
+ �� 1012
56
+ ל� 1007
57
+ �� 1007
58
+ ו� 975
59
+ �� 975
60
+ ד� 965
61
+ �� 965
62
+ פ� 929
63
+ � 929
64
+ פ 929
65
+ �� 929
66
+ �ר 873
67
+ ער 873
68
+ א� 870
69
+ �� 870
70
+ ז 868
71
+ � 868
72
+ � 832
73
+ ס 832
74
+ � 797
75
+ ק 797
76
+ _א� 784
77
+ מ 766
78
+ � 766
79
+ _א� 752
80
+ �� 747
81
+ מ� 747
82
+ � 742
83
+ ג 742
84
+ � 725
85
+ ש 725
86
+ ט_ 699
87
+ �_ 699
88
+ װ 691
89
+ � 691
90
+ װ� 674
91
+ �� 674
92
+ � 667
93
+ ײ 667
94
+ �� 664
95
+ ג� 664
96
+ � 661
97
+ ֿ 661
98
+ ק� 654
99
+ �� 654
100
+ �� 652
101
+ ֿ� 652
102
+ ש� 651
103
+ �� 651
104
+ �� 643
105
+ ז� 643
106
+ פֿ 641
107
+ �ֿ 641
108
+ פֿ� 638
109
+ �ֿ� 638
110
+ _אַ 638
111
+ ר_ 592
112
+ �_ 592
113
+ _ד 560
114
+ _ד� 554
115
+ , 551
116
+ ,_ 534
117
+ ב 517
118
+ � 517
119
+ _פ� 502
120
+ _פ 502
121
+ ב� 472
122
+ �� 472
123
+ ס� 436
124
+ �� 436
125
+ צ 436
126
+ � 436
127
+ צ� 433
128
+ �� 433
129
+ _װ 430
130
+ _װ� 429
131
+ � 410
132
+ ה 410
133
+ �ר_ 404
134
+ _פֿ 404
135
+ ער_ 404
136
+ _מ 400
137
+ _מ� 396
138
+ גע 390
139
+ �ע 390
140
+ _ז 390
141
+ _ז� 386
142
+ �ע� 384
143
+ ען 384
144
+ גע� 384
145
+ �ן 384
146
+ ער� 382
147
+ �ר� 382
148
+ . 374
149
+ אי 372
150
+ �י 372
151
+ ּ 366
152
+ � 366
153
+ �� 363
154
+ ה� 363
155
+ �י� 362
156
+ אי� 362
157
+ _ג 359
158
+ ױ 357
159
+ � 357
160
+ _ג� 356
161
+ ון 349
162
+ �ן 349
163
+ י_ 346
164
+ �_ 346
165
+ ע_ 343
166
+ �_ 343
167
+ �ן_ 337
168
+ ון_ 337
169
+ �ע 334
170
+ דע 334
171
+ _אי 331
172
+ ך 330
173
+ � 330
174
+ �ע� 323
175
+ �� 323
176
+ דע� 323
177
+ ּ� 323
178
+ �� 322
179
+ ײ� 322
180
+ ען_ 321
181
+ �ן_ 321
182
+ �� 320
183
+ ױ� 320
184
+ �י 317
185
+ די 317
186
+ �ַ 311
187
+ �ַר 311
188
+ ײ� 311
189
+ �ר 311
190
+ ַר 311
191
+ ײַ 311
192
+ �� 311
193
+ לע 310
194
+ �ע 310
195
+ ._ 307
196
+ - 305
197
+ �_ 297
198
+ ַ_ 297
199
+ � 294
200
+ כ 294
201
+ �ע 290
202
+ נע 290
203
+ ס_ 289
204
+ �_ 289
205
+ פּ 288
206
+ �ּ 288
207
+ ײַ� 287
208
+ �ַ� 287
209
+ ך_ 283
210
+ �_ 283
211
+ �ַ_ 274
212
+ אַ_ 274
213
+ ַר� 272
214
+ �ר� 272
215
+ לע� 261
216
+ �ע� 261
217
+ _ה� 260
218
+ _ה 260
219
+ _צ 259
220
+ �ש 257
221
+ יש 257
222
+ _צ� 256
223
+ זי 254
224
+ �י 254
225
+ פּ� 252
226
+ �ּ� 252
227
+ מע 248
228
+ �ע 248
229
+ _ק 247
230
+ נע� 247
231
+ �ע� 247
232
+ טע 245
233
+ �ע 245
234
+ _ק� 245
235
+ או 244
236
+ �ו� 244
237
+ �ו 244
238
+ או� 244
239
+ �ל 238
240
+ על 238
241
+ �א 235
242
+ הא 235
243
+ הא� 235
244
+ שט 235
245
+ �ט 235
246
+ �א� 235
247
+ כ� 234
248
+ �� 234
249
+ _ב� 231
250
+ �ער 231
251
+ _ב 231
252
+ ַנ 229
253
+ �נ 229
254
+ �נ� 228
255
+ ַנ� 228
256
+ _או 227
257
+ _גע 226
258
+ � 219
259
+ ם 219
260
+ " 218
261
+ �ע� 217
262
+ מע� 217
263
+ �ע 217
264
+ װע 217
265
+ �ל 216
266
+ ַל 216
267
+ _זי 215
268
+ _נ 215
269
+ על� 212
270
+ �ל� 212
271
+ �א 211
272
+ רא 211
273
+ _נ� 211
274
+ טע� 211
275
+ �ע� 211
276
+ װא 210
277
+ �א 210
278
+ _דע 210
279
+ �א� 209
280
+ װע� 209
281
+ װא� 209
282
+ �ע� 209
283
+ �ש� 208
284
+ יש� 208
285
+ �ק 207
286
+ יק 207
287
+ רא� 206
288
+ �א� 206
289
+ �_ 205
290
+ ז_ 205
291
+ �י 196
292
+ מי 196
293
+ _ש 195
294
+ מי� 195
295
+ �י� 195
296
+ �ַל 193
297
+ _ש� 191
298
+ ֿא 189
299
+ �א 189
300
+ �ֿא 189
301
+ ֿא� 188
302
+ �ו 188
303
+ ֿו� 188
304
+ ֿו 188
305
+ �ו� 188
306
+ �א� 188
307
+ �ון 187
308
+ �אָ 186
309
+ _הא 185
310
+ �ֿו 184
311
+ _ע 179
312
+ _די 178
313
+ �א 176
314
+ טא 176
315
+ טא� 175
316
+ �א� 175
317
+ ָס 174
318
+ �ָס 174
319
+ יט 174
320
+ �ט 174
321
+ �ס 174
322
+ ל_ 173
323
+ �_ 173
324
+ �י_ 173
325
+ די_ 173
326
+ ם_ 171
327
+ �ל� 171
328
+ �_ 171
329
+ ַל� 171
330
+ _ע� 171
331
+ �ָט 169
332
+ �ט 169
333
+ ָט 169
334
+ יך 168
335
+ �ך 168
336
+ �ָר 166
337
+ �י� 166
338
+ ָר 166
339
+ �ר 166
340
+ זי� 166
341
+ ני 164
342
+ ענ 164
343
+ �י 164
344
+ �נ 164
345
+ �י 163
346
+ רי 163
347
+ יך_ 163
348
+ �ך_ 163
349
+ �אָ 162
350
+ ענ� 162
351
+ �נ� 162
352
+ �אַ 160
353
+ �ט 160
354
+ עט 160
355
+ _י 158
356
+ �י� 157
357
+ �ר 157
358
+ רי� 157
359
+ יר 157
360
+ -� 156
361
+ ָס_ 155
362
+ �ס_ 155
363
+ �י 154
364
+ _מי 154
365
+ לי 154
366
+ קע 153
367
+ ונ 153
368
+ �ע 153
369
+ �נ 153
370
+ _װא 152
371
+ �י� 152
372
+ ני� 152
373
+ �ן 151
374
+ ין 151
375
+ אױ 151
376
+ �ױ 151
377
+ י� 150
378
+ �ט 150
379
+ � 150
380
+ �� 150
381
+ יִ 150
382
+ �ִ 150
383
+ ִ 150
384
+ ַט 150
385
+ ִ� 149
386
+ �ִ� 149
387
+ �� 149
388
+ יִ� 149
389
+ �י� 148
390
+ _י� 148
391
+ לי� 148
392
+ �ױ� 146
393
+ אױ� 146
394
+ �ַנ 146
395
+ _אױ 145
396
+ �ון 145
397
+ יז 143
398
+ �ז 143
399
+ �י� 142
400
+ די� 142