RubyGems - language_detector - Versions diffs - 0.1.0 - Mend

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

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

data/lib/textcat_ngrams/welsh.lm ADDED

@@ -0,0 +1,400 @@
+_	 78614
+a	 18113
+d	 17890
+y	 16837
+e	 14108
+n	 13902
+r	 13869
+i	 12928
+o	 9972
+l	 9188
+h	 7454
+g	 7165
+w	 7010
+t	 6296
+f	 6080
+u	 5400
+n_	 5159
+_y	 5051
+dd	 4946
+s	 4884
+r_	 4547
+m	 4364
+d_	 4223
+yn	 4082
+_a	 4020
+c	 3707
+th	 3301
+u_	 2900
+yd	 2900
+ae	 2649
+l_	 2588
+_g	 2547
+.	 2460
+'	 2458
+._	 2408
+wy	 2334
+yn_	 2331
+_d	 2307
+b	 2267
+ym	 2262
+ra	 2261
+an	 2235
+ar	 2228
+ol	 2218
+ia	 2212
+i_	 2199
+ed	 2191
+_yn	 2038
+_i	 2020
+y_	 1983
+_c	 1934
+_yn_	 1861
+ei	 1815
+it	 1796
+g_	 1787
+ith	 1779
+dd_	 1745
+h_	 1741
+ydd	 1731
+ai	 1709
+au	 1708
+'r_	 1655
+'r	 1655
+_y_	 1621
+di	 1615
+,	 1613
+,_	 1608
+da	 1585
+od	 1546
+_o	 1535
+ad	 1532
+th_	 1510
+ll	 1494
+au_	 1492
+_s	 1415
+er	 1359
+o_	 1350
+io	 1311
+a_	 1299
+ol_	 1294
+_e	 1273
+_h	 1249
+cy	 1246
+yr	 1243
+en	 1228
+p	 1217
+_f	 1212
+_cy	 1203
+mr	 1200
+gy	 1193
+ymr	 1185
+ha	 1172
+hy	 1164
+eg	 1159
+do	 1151
+edd	 1147
+G	 1134
+we	 1107
+C	 1089
+_ar	 1078
+_m	 1075
+yf	 1057
+de	 1048
+fe	 1047
+_G	 1045
+ch	 1043
+rae	 1023
+el	 1016
+no	 1010
+ni	 1010
+_b	 1009
+ne	 1001
+ef	 992
+ri	 983
+et	 978
+_C	 957
+_gy	 952
+_a_	 943
+eth	 943
+_.	 940
+_._	 939
+eit	 930
+eith	 927
+ys	 921
+wyd	 912
+ga	 901
+_i_	 893
+s_	 887
+mrae	 878
+mraeg	 878
+raeg	 878
+ymrae	 878
+aeg	 878
+ymra	 878
+mra	 878
+_p	 856
+aet	 850
+aeth	 850
+_n	 844
+un	 838
+on	 836
+ait	 833
+aith	 833
+nn	 830
+at	 827
+oe	 823
+li	 805
+_r	 801
+ddi	 795
+gw	 789
+ma	 783
+le	 777
+nt	 772
+ho	 769
+ff	 766
+yr_	 764
+na	 753
+la	 748
+rh	 747
+eg_	 734
+si	 733
+ng	 732
+dol	 732
+ro	 718
+al	 712
+_dd	 706
+wn	 705
+oed	 705
+Gy	 704
+dy	 701
+Cy	 696
+o'	 692
+ar_	 691
+ny	 690
+Gym	 678
+wr	 677
+id	 676
+_Gy	 672
+_o_	 668
+Gymr	 667
+if	 662
+ith_	 662
+_ar_	 660
+iad	 657
+_w	 657
+fo	 656
+eu	 655
+aeg_	 650
+raeg_	 650
+aith_	 648
+or	 648
+_Gym	 646
+fa	 642
+re	 638
+_Cy	 638
+_Gymr	 635
+_gw	 633
+fy	 633
+oedd	 633
+edd_	 629
+rd	 627
+od_	 622
+ac	 619
+ddo	 612
+an_	 607
+Gymra	 606
+er_	 605
+A	 604
+eth_	 601
+hw	 596
+ydd_	 591
+o'r	 586
+o'r_	 586
+es	 583
+ir	 579
+dw	 573
+go	 559
+yl	 548
+rw	 545
+aeth_	 545
+wydd	 543
+aw	 539
+_rh	 539
+dr	 537
+ly	 537
+fn	 534
+dau	 533
+_hy	 531
+t_	 531
+sg	 529
+'n	 529
+*	 528
+'n_	 523
+_*	 522
+nyd	 521
+nydd	 521
+M	 519
+st	 518
+Y	 516
+sy	 515
+yd_	 513
+lw	 512
+_ga	 508
+iai	 503
+il	 502
+_l	 499
+rt	 494
+ad_	 493
+_yr	 493
+_yr_	 492
+as	 492
+dol_	 492
+f_	 491
+dda	 491
+ig	 490
+og	 484
+wa	 479
+he	 478
+iaith	 477
+iait	 477
+oedd_	 475
+_ma	 473
+c_	 472
+Cym	 470
+te	 469
+_ym	 467
+am	 467
+_M	 465
+_ia	 462
+efn	 462
+i'	 460
+ie	 458
+_Cym	 458
+_ac	 457
+dau_	 456
+yw	 455
+ew	 453
+fr	 441
+fod	 441
+_A	 441
+du	 437
+_sy	 434
+e_	 432
+wi	 426
+Cymr	 426
+se	 425
+B	 424
+D	 424
+_Cymr	 423
+bl	 423
+lu	 420
+in	 417
+_t	 417
+tr	 414
+ac_	 413
+wed	 410
+os	 410
+_iai	 407
+_iait	 407
+el_	 405
+_ac_	 405
+rha	 404
+m_	 404
+is	 403
+on_	 401
+eu_	 393
+hi	 393
+rdd	 393
+id_	 389
+_Y	 388
+ry	 387
+odd	 387
+rwy	 387
+rf	 386
+io_	 380
+ynn	 380
+cyf	 380
+hr	 380
+_cyf	 379
+yddi	 379
+cyn	 372
+_de	 372
+rth	 371
+ru	 368
+S	 363
+wei	 363
+ysg	 362
+_B	 362
+u'	 361
+yddo	 360
+wn_	 360
+so	 359
+dio	 359
+_ei	 358
+N	 356
+dwy	 355
+_da	 353
+me	 353
+gan	 353
+gyf	 353
+w_	 352
+_o'	 351
+fer	 349
+nol	 347
+hyn	 346
+ddy	 346
+af	 346
+ta	 343
+ddol	 343
+_fe	 340
+nd	 340
+mae	 338
+_cyn	 338
+efnyd	 337
+fnydd	 337
+fny	 337
+efny	 337
+fnyd	 337
+iad_	 335
+_mae	 333
+ion	 333
+_ll	 330
+def	 330
+_gyf	 327
+nt_	 326
+i'r_	 326
+-	 326
+i'r	 326
+weith	 325
+weit	 325
+defn	 325
+defny	 325
+bo	 324
+hyd	 323
+by	 322
+_si	 321
+ir_	 321
+hau	 318
+nod	 318
+edi	 315
+I	 314
+fyd	 313
+wyr	 313
+ada	 311
+ddio	 310
+rif	 309
+sia	 307
+sa	 306
+fel	 305
+tha	 305
+_S	 302
+_ne	 302
+_u	 301
+fod_	 300
+_o'r	 300
+yg	 300
+_o'r_	 300
+_i'	 299
+ge	 299
+dia	 299

data/lib/textcat_ngrams/yiddish-utf.lm ADDED

@@ -0,0 +1,400 @@
+�	 29767
+_	 13552
+_�	 6516
+�	 4273
+�	 3670
+א	 3670
+ע	 3261
+�	 3261
+��	 2826
+ע�	 2826
+א�	 2785
+��	 2785
+י	 2565
+�	 2565
+�	 2082
+ר	 2082
+��	 2062
+י�	 2062
+�	 1857
+ט	 1857
+�	 1828
+ַ	 1828
+�	 1793
+ן	 1793
+_א	 1537
+�_	 1532
+ן_	 1532
+��	 1527
+ַ�	 1527
+אַ	 1517
+�ַ	 1517
+ר�	 1355
+��	 1355
+�	 1270
+ל	 1270
+�	 1268
+אָ	 1268
+ָ	 1268
+�ָ	 1268
+�ַ�	 1240
+אַ�	 1240
+נ	 1232
+�	 1232
+אָ�	 1229
+�ָ�	 1229
+��	 1229
+ָ�	 1229
+נ�	 1181
+��	 1181
+ו	 1116
+�	 1116
+�	 1031
+ד	 1031
+ט�	 1012
+��	 1012
+ל�	 1007
+��	 1007
+ו�	 975
+��	 975
+ד�	 965
+��	 965
+פ�	 929
+�	 929
+פ	 929
+��	 929
+�ר	 873
+ער	 873
+א�	 870
+��	 870
+ז	 868
+�	 868
+�	 832
+ס	 832
+�	 797
+ק	 797
+_א�	 784
+מ	 766
+�	 766
+_א�	 752
+��	 747
+מ�	 747
+�	 742
+ג	 742
+�	 725
+ש	 725
+ט_	 699
+�_	 699
+װ	 691
+�	 691
+װ�	 674
+��	 674
+�	 667
+ײ	 667
+��	 664
+ג�	 664
+�	 661
+ֿ	 661
+ק�	 654
+��	 654
+��	 652
+ֿ�	 652
+ש�	 651
+��	 651
+��	 643
+ז�	 643
+פֿ	 641
+�ֿ	 641
+פֿ�	 638
+�ֿ�	 638
+_אַ	 638
+ר_	 592
+�_	 592
+_ד	 560
+_ד�	 554
+,	 551
+,_	 534
+ב	 517
+�	 517
+_פ�	 502
+_פ	 502
+ב�	 472
+��	 472
+ס�	 436
+��	 436
+צ	 436
+�	 436
+צ�	 433
+��	 433
+_װ	 430
+_װ�	 429
+�	 410
+ה	 410
+�ר_	 404
+_פֿ	 404
+ער_	 404
+_מ	 400
+_מ�	 396
+גע	 390
+�ע	 390
+_ז	 390
+_ז�	 386
+�ע�	 384
+ען	 384
+גע�	 384
+�ן	 384
+ער�	 382
+�ר�	 382
+.	 374
+אי	 372
+�י	 372
+ּ	 366
+�	 366
+��	 363
+ה�	 363
+�י�	 362
+אי�	 362
+_ג	 359
+ױ	 357
+�	 357
+_ג�	 356
+ון	 349
+�ן	 349
+י_	 346
+�_	 346
+ע_	 343
+�_	 343
+�ן_	 337
+ון_	 337
+�ע	 334
+דע	 334
+_אי	 331
+ך	 330
+�	 330
+�ע�	 323
+��	 323
+דע�	 323
+ּ�	 323
+��	 322
+ײ�	 322
+ען_	 321
+�ן_	 321
+��	 320
+ױ�	 320
+�י	 317
+די	 317
+�ַ	 311
+�ַר	 311
+ײ�	 311
+�ר	 311
+ַר	 311
+ײַ	 311
+��	 311
+לע	 310
+�ע	 310
+._	 307
+-	 305
+�_	 297
+ַ_	 297
+�	 294
+כ	 294
+�ע	 290
+נע	 290
+ס_	 289
+�_	 289
+פּ	 288
+�ּ	 288
+ײַ�	 287
+�ַ�	 287
+ך_	 283
+�_	 283
+�ַ_	 274
+אַ_	 274
+ַר�	 272
+�ר�	 272
+לע�	 261
+�ע�	 261
+_ה�	 260
+_ה	 260
+_צ	 259
+�ש	 257
+יש	 257
+_צ�	 256
+זי	 254
+�י	 254
+פּ�	 252
+�ּ�	 252
+מע	 248
+�ע	 248
+_ק	 247
+נע�	 247
+�ע�	 247
+טע	 245
+�ע	 245
+_ק�	 245
+או	 244
+�ו�	 244
+�ו	 244
+או�	 244
+�ל	 238
+על	 238
+�א	 235
+הא	 235
+הא�	 235
+שט	 235
+�ט	 235
+�א�	 235
+כ�	 234
+��	 234
+_ב�	 231
+�ער	 231
+_ב	 231
+ַנ	 229
+�נ	 229
+�נ�	 228
+ַנ�	 228
+_או	 227
+_גע	 226
+�	 219
+ם	 219
+"	 218
+�ע�	 217
+מע�	 217
+�ע	 217
+װע	 217
+�ל	 216
+ַל	 216
+_זי	 215
+_נ	 215
+על�	 212
+�ל�	 212
+�א	 211
+רא	 211
+_נ�	 211
+טע�	 211
+�ע�	 211
+װא	 210
+�א	 210
+_דע	 210
+�א�	 209
+װע�	 209
+װא�	 209
+�ע�	 209
+�ש�	 208
+יש�	 208
+�ק	 207
+יק	 207
+רא�	 206
+�א�	 206
+�_	 205
+ז_	 205
+�י	 196
+מי	 196
+_ש	 195
+מי�	 195
+�י�	 195
+�ַל	 193
+_ש�	 191
+ֿא	 189
+�א	 189
+�ֿא	 189
+ֿא�	 188
+�ו	 188
+ֿו�	 188
+ֿו	 188
+�ו�	 188
+�א�	 188
+�ון	 187
+�אָ	 186
+_הא	 185
+�ֿו	 184
+_ע	 179
+_די	 178
+�א	 176
+טא	 176
+טא�	 175
+�א�	 175
+ָס	 174
+�ָס	 174
+יט	 174
+�ט	 174
+�ס	 174
+ל_	 173
+�_	 173
+�י_	 173
+די_	 173
+ם_	 171
+�ל�	 171
+�_	 171
+ַל�	 171
+_ע�	 171
+�ָט	 169
+�ט	 169
+ָט	 169
+יך	 168
+�ך	 168
+�ָר	 166
+�י�	 166
+ָר	 166
+�ר	 166
+זי�	 166
+ני	 164
+ענ	 164
+�י	 164
+�נ	 164
+�י	 163
+רי	 163
+יך_	 163
+�ך_	 163
+�אָ	 162
+ענ�	 162
+�נ�	 162
+�אַ	 160
+�ט	 160
+עט	 160
+_י	 158
+�י�	 157
+�ר	 157
+רי�	 157
+יר	 157
+-�	 156
+ָס_	 155
+�ס_	 155
+�י	 154
+_מי	 154
+לי	 154
+קע	 153
+ונ	 153
+�ע	 153
+�נ	 153
+_װא	 152
+�י�	 152
+ני�	 152
+�ן	 151
+ין	 151
+אױ	 151
+�ױ	 151
+י�	 150
+�ט	 150
+�	 150
+��	 150
+יִ	 150
+�ִ	 150
+ִ	 150
+ַט	 150
+ִ�	 149
+�ִ�	 149
+��	 149
+יִ�	 149
+�י�	 148
+_י�	 148
+לי�	 148
+�ױ�	 146
+אױ�	 146
+�ַנ	 146
+_אױ	 145
+�ון	 145
+יז	 143
+�ז	 143
+�י�	 142
+די�	 142