language_detector 0.1.0

data/lib/textcat_ngrams/malay.lm

@@ -0,0 +1,400 @@
+_	 87128
+a	 50232
+n	 25424
+e	 18746
+i	 18605
+an	 14419
+u	 12470
+k	 11955
+t	 11875
+r	 11007
+d	 9856
+g	 9545
+m	 9390
+s	 8926
+l	 8631
+n_	 8004
+an_	 7095
+p	 6890
+a_	 6739
+b	 6645
+ng	 6630
+h	 5964
+da	 5153
+_d	 5107
+er	 4625
+ka	 4448
+la	 4339
+y	 4323
+i_	 4295
+en	 4159
+ya	 3800
+ang	 3778
+_m	 3750
+o	 3593
+.	 3539
+._	 3310
+at	 3288
+ah	 3216
+_b	 3199
+_s	 3177
+ta	 3076
+ra	 3036
+_k	 2949
+g_	 2939
+ng_	 2933
+ar	 2915
+_p	 2906
+me	 2884
+ga	 2781
+di	 2778
+ak	 2727
+al	 2705
+_me	 2671
+ang_	 2524
+h_	 2509
+ba	 2508
+pa	 2454
+kan	 2449
+in	 2437
+tu	 2411
+_t	 2376
+sa	 2338
+_da	 2276
+j	 2276
+pe	 2225
+,	 2150
+k_	 2147
+ma	 2143
+se	 2138
+am	 2131
+kan_	 2117
+_di	 2082
+,_	 2079
+ke	 2048
+un	 2004
+be	 1947
+_a	 1925
+na	 1871
+ti	 1868
+ri	 1861
+u_	 1857
+as	 1854
+ny	 1827
+ha	 1789
+te	 1788
+_pe	 1768
+em	 1750
+it	 1737
+_i	 1732
+_ke	 1711
+yan	 1706
+ad	 1698
+ia	 1673
+yang	 1673
+_y	 1668
+_ya	 1655
+yang_	 1653
+_se	 1648
+ah_	 1646
+_yan	 1639
+_yang	 1639
+ala	 1612
+nya	 1587
+el	 1576
+ik	 1571
+t_	 1568
+ai	 1549
+men	 1531
+eng	 1522
+_men	 1464
+nga	 1441
+dan	 1366
+_be	 1365
+si	 1343
+uk	 1328
+ada	 1299
+nt	 1291
+__	 1287
+ap	 1276
+ua	 1265
+___	 1238
+-	 1213
+ja	 1211
+ber	 1204
+gan	 1203
+_ba	 1193
+____	 1189
+ni	 1181
+_te	 1169
+c	 1143
+ran	 1141
+_____	 1140
+m_	 1127
+ara	 1118
+per	 1099
+le	 1084
+_dan	 1083
+dan_	 1079
+ngan	 1060
+_dan_	 1050
+ya_	 1046
+at_	 1044
+da_	 1021
+li	 1016
+aka	 1013
+A	 999
+r_	 999
+w	 997
+eb	 995
+lah	 980
+ata	 980
+ak_	 978
+nd	 974
+_ber	 955
+gi	 936
+is	 933
+il	 931
+tu_	 923
+s_	 920
+gan_	 915
+mb	 913
+wa	 904
+ag	 903
+ngan_	 898
+ter	 887
+nya_	 877
+S	 873
+ek	 853
+ru	 852
+_l	 838
+ela	 828
+itu	 824
+ol	 822
+aha	 822
+ada_	 820
+pu	 812
+di_	 807
+bu	 807
+am_	 804
+ur	 801
+tan	 790
+mp	 790
+_per	 786
+_sa	 784
+M	 782
+ut	 781
+us	 779
+era	 779
+lam	 778
+lah_	 775
+asa	 767
+ki	 761
+ir	 759
+de	 756
+enga	 750
+su	 748
+du	 741
+id	 739
+"	 733
+akan	 732
+apa	 728
+_S	 724
+ul	 721
+lu	 717
+ari	 717
+dal	 704
+et	 698
+es	 698
+pad	 688
+_ma	 688
+_M	 685
+ana	 684
+bi	 679
+pada	 673
+dala	 673
+l_	 671
+ep	 664
+f	 662
+_di_	 658
+B	 655
+ing	 655
+_j	 654
+ika	 653
+ku	 650
+_.	 644
+akan_	 642
+ama	 637
+pen	 636
+alam	 634
+eh	 634
+pada_	 633
+ai_	 632
+_ter	 632
+K	 631
+mu	 628
+ju	 628
+P	 626
+mem	 625
+au	 622
+_mem	 614
+lan	 612
+_._	 611
+ntu	 608
+lam_	 605
+um	 601
+on	 600
+gk	 597
+_in	 597
+ngk	 597
+a.	 584
+meng	 582
+_meng	 578
+alam_	 577
+_A	 576
+aa	 575
+uk_	 572
+_pen	 569
+ban	 569
+or	 569
+st	 566
+ay	 566
+dar	 565
+_pa	 564
+a._	 564
+_h	 562
+bah	 562
+_P	 560
+D	 559
+ri_	 558
+ini	 552
+_de	 551
+rt	 550
+aan	 545
+_it	 542
+_itu	 542
+nda	 540
+eri	 540
+dalam	 537
+_B	 533
+_dal	 532
+ip	 532
+_dala	 532
+ta_	 528
+_u	 527
+ung	 525
+ih	 524
+aw	 520
+_n	 519
+atu	 517
+ila	 513
+mi	 513
+leh	 513
+ian	 512
+tuk	 509
+awa	 508
+gu	 506
+ert	 506
+engan	 505
+ole	 504
+_K	 501
+seb	 497
+ca	 496
+gg	 493
+_ta	 489
+ra_	 488
+ngg	 488
+itu_	 487
+emb	 482
+ni_	 482
+ida	 482
+nj	 482
+_ti	 479
+man	 478
+den	 477
+_D	 474
+_ka	 473
+aj	 470
+oleh	 468
+n.	 468
+n._	 464
+ngka	 464
+gka	 464
+dak	 464
+anga	 461
+ena	 459
+san	 458
+pat	 458
+rk	 458
+(	 455
+ent	 454
+agi	 453
+)	 451
+ia_	 450
+ge	 450
+ab	 449
+im	 447
+_ini	 446
+ntuk	 445
+I	 445
+ar_	 440
+N	 439
+aan_	 436
+_la	 433
+pi	 432
+baha	 431
+deng	 430
+han	 430
+bag	 429
+eh_	 429
+hu	 429
+denga	 428
+_o	 427
+na_	 427
+T	 425
+leh_	 422
+_den	 422
+ka_	 419
+any	 415
+ud	 415
+rang	 414
+anya	 413
+gi_	 412
+angan	 412
+a,	 411
+_deng	 410
+ita	 409
+kat	 408
+re	 408
+_(	 406
+tuk_	 403
+aga	 401
+ne	 400
+and	 399
+aya	 398
+_dar	 397
+a,_	 396
+ro	 396
+ntuk_	 393
+eba	 392
+aran	 390
+_"	 387
+ed	 385
+end	 384
+ko	 383
+sa_	 381
+p_	 381
+ara_	 380
+_seb	 379
+alah	 379
+oleh_	 379
+an.	 378
+dak_	 378
+eg	 378
+hi	 376
+dari	 375
+an._	 375
+au_	 373
+bo	 373
+ti_	 371
+ula	 371

data/lib/textcat_ngrams/manx.lm

@@ -0,0 +1,400 @@
+_	 36004
+e	 9455
+a	 8302
+y	 6395
+n	 6395
+h	 5736
+r	 4939
+s	 4799
+o	 4429
+i	 4129
+l	 3462
+y_	 2896
+g	 2731
+n_	 2549
+d	 2232
+t	 2160
+_a	 1836
+m	 1823
+sh	 1774
+e_	 1746
+h_	 1645
+yn	 1550
+c	 1531
+ee	 1515
+gh	 1461
+s_	 1460
+_s	 1388
+ey	 1345
+_e	 1316
+ag	 1312
+a_	 1201
+r_	 1173
+agh	 1165
+in	 1148
+as	 1136
+_d	 1136
+u	 1124
+he	 1060
+yn_	 1025
+oo	 1012
+ey_	 1005
+_m	 1002
+er	 965
+v	 949
+_y	 941
+_v	 895
+_c	 891
+_as	 880
+'	 869
+,	 866
+_n	 832
+ll	 828
+,_	 827
+_sh	 818
+.	 802
+hi	 797
+as_	 770
+ee_	 768
+ne	 767
+_as_	 764
+b	 762
+re	 735
+ay	 730
+._	 730
+an	 726
+ar	 725
+gh_	 722
+ny	 709
+en	 703
+_r	 697
+ch	 688
+agh_	 687
+dy	 686
+t_	 677
+le	 667
+k	 658
+er_	 616
+oi	 612
+ea	 607
+_t	 601
+yr	 596
+_er	 585
+ra	 574
+_dy	 572
+in_	 570
+l_	 564
+f	 557
+_l	 556
+ha	 551
+_g	 548
+_ny	 534
+nn	 530
+"	 528
+_ch	 527
+_y_	 524
+ie	 514
+dy_	 514
+_dy_	 513
+aa	 510
+_f	 509
+j	 504
+sh_	 487
+oa	 480
+is	 478
+_h	 470
+rr	 468
+ny_	 467
+_ny_	 463
+_er_	 454
+ish	 445
+ho	 442
+ai	 441
+d_	 435
+ro	 423
+ht	 418
+ei	 417
+shi	 416
+il	 409
+me	 408
+_ay	 403
+_b	 403
+la	 400
+_j	 400
+my	 394
+va	 391
+ns	 386
+on	 385
+_o	 381
+ys	 380
+_shi	 379
+ia	 377
+ayn	 373
+_va	 371
+hen	 362
+she	 356
+ri	 345
+lle	 342
+ooi	 342
+mee	 340
+ley	 335
+_me	 331
+el	 330
+rt	 328
+ie_	 327
+eh	 324
+w	 316
+_ayn	 313
+al	 311
+g_	 309
+ish_	 308
+lley	 307
+mee_	 305
+_mee	 304
+ill	 301
+es	 299
+na	 299
+je	 298
+yns	 296
+C	 294
+_my	 291
+_she	 290
+ley_	 282
+V	 280
+_yn	 278
+_"	 278
+_mee_	 277
+ta	 272
+_V	 271
+ys_	 268
+-	 268
+lley_	 265
+hin	 264
+_ro	 259
+shin	 256
+_yn_	 255
+_je	 255
+do	 253
+va_	 253
+ne_	 253
+_va_	 252
+ns_	 252
+_shin	 251
+yns_	 250
+ayns	 248
+en_	 247
+che	 246
+_ayns	 246
+eh_	 246
+_do	 242
+ad	 241
+ney	 240
+o_	 240
+ym	 240
+ed	 239
+yr_	 239
+ayns_	 237
+ur	 237
+st	 234
+_C	 234
+rt_	 234
+'n	 232
+m_	 232
+p	 231
+li	 231
+or	 230
+ow	 228
+hin_	 225
+da	 225
+shen	 223
+"_	 223
+'n_	 223
+Va	 221
+ght	 220
+shin_	 219
+tr	 217
+_Va	 217
+ry	 216
+ve	 216
+_shen	 215
+ty	 214
+mo	 206
+_'	 205
+_ve	 205
+ma	 203
+be	 203
+te	 203
+hie	 203
+hey	 203
+nag	 202
+ll_	 201
+yl	 200
+w_	 200
+ss	 200
+aa_	 198
+nagh	 198
+an_	 197
+io	 195
+ow_	 194
+it	 194
+sy	 193
+ayr	 193
+ney_	 192
+E	 192
+sht	 192
+ni	 191
+_k	 190
+ha_	 190
+ain	 189
+u_	 189
+hy	 189
+aght	 188
+oo_	 188
+ree	 188
+lh	 187
+_tr	 186
+esh	 186
+_che	 183
+yrt	 182
+_da	 182
+oar	 182
+doo	 181
+k_	 181
+se	 180
+au	 180
+ille	 179
+ar_	 179
+_lh	 179
+ki	 177
+arr	 176
+ec	 176
+ol	 175
+_doo	 175
+T	 175
+row	 175
+_row	 174
+ge	 173
+so	 172
+oy	 171
+oil	 170
+_re	 170
+_ag	 170
+'e	 169
+rey	 169
+illey	 169
+ck	 168
+ad_	 168
+ann	 168
+n,	 166
+eea	 166
+_ta	 166
+ht_	 165
+ae	 162
+_row_	 162
+!	 162
+row_	 162
+ane	 161
+fe	 161
+dd	 160
+go	 159
+tyn	 159
+oin	 158
+ooa	 158
+n.	 158
+eg	 156
+_ec	 156
+_ma	 156
+_agh	 155
+n,_	 154
+_fe	 154
+Ch	 154
+nyn	 153
+fo	 152
+eay	 152
+nagh_	 152
+n._	 152
+_go	 151
+S	 150
+ke	 150
+hey_	 150
+enn	 150
+cha	 149
+rre	 149
+_fo	 149
+ghe	 149
+raa	 149
+G	 148
+lan	 148
+mm	 147
+ym_	 147
+A	 146
+c_	 146
+oill	 145
+hee	 144
+ooar	 144
+_E	 144
+nne	 143
+tey	 142
+ir	 141
+de	 141
+hyn	 140
+_he	 140
+nyn_	 140
+'s	 139
+_gh	 139
+_cha	 138
+L	 138
+yrt_	 138
+_Ch	 137
+e,	 137
+lla	 136
+Va_	 136
+ooin	 136
+ell	 135
+a'	 135
+os	 135
+_oo	 134
+am	 134
+rish	 133
+th	 133
+_mo	 133
+ris	 133
+iag	 133
+gg	 133
+_Va_	 132
+iagh	 132
+_G	 132
+e,_	 132
+ass	 132
+!_	 132
+my_	 132
+hoo	 131
+_T	 131
+nee	 130
+a'n_	 129
+rag	 129
+a'n	 129
+_'s	 129
+_so	 128
+co	 128
+rey_	 128
+_eh	 126
+_my_	 126
+nni	 126
+ou	 126
+_'sy	 125
+'sy	 125
+_p	 125
+vo	 125
+_S	 125
+H	 125
+_agh_	 125
+tra	 124
+moo	 124
+hu	 123
+ooy	 123
+ragh	 123
+al_	 123
+it_	 123
+hia	 122
+id	 122