You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ju...@apache.org on 2011/10/11 00:25:54 UTC

svn commit: r1181278 [1/2] - in /tika/trunk/tika-core/src/main/resources/org/apache/tika/language: be.ngp ca.ngp eo.ngp gl.ngp ro.ngp sk.ngp sl.ngp tika.language.properties uk.ngp

Author: jukka
Date: Mon Oct 10 22:25:53 2011
New Revision: 1181278

URL: http://svn.apache.org/viewvc?rev=1181278&view=rev
Log:
TIKA-681: eight new n-gram language profiles

Patch by Michael Bryant

Added:
    tika/trunk/tika-core/src/main/resources/org/apache/tika/language/be.ngp   (with props)
    tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ca.ngp   (with props)
    tika/trunk/tika-core/src/main/resources/org/apache/tika/language/eo.ngp   (with props)
    tika/trunk/tika-core/src/main/resources/org/apache/tika/language/gl.ngp   (with props)
    tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ro.ngp   (with props)
    tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sk.ngp   (with props)
    tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sl.ngp   (with props)
    tika/trunk/tika-core/src/main/resources/org/apache/tika/language/uk.ngp   (with props)
Modified:
    tika/trunk/tika-core/src/main/resources/org/apache/tika/language/tika.language.properties

Added: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/be.ngp
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/language/be.ngp?rev=1181278&view=auto
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/language/be.ngp (added)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/language/be.ngp Mon Oct 10 22:25:53 2011
@@ -0,0 +1,1001 @@
+# NgramProfile generated at Wed Jun 08 14:41:42 PDT 2011 for Nutch Language Identification
+_па 3116
+_і_ 2556
+_на 2147
+_пр 2138
+на_ 2079
+ай_ 1954
+ста 1826
+_ка 1654
+пра 1646
+аў_ 1634
+_ў_ 1489
+_з_ 1484
+ава 1461
+_ст 1451
+ць_ 1391
+га_ 1369
+кі_ 1308
+ага 1303
+_у_ 1298
+ны_ 1297
+_ад 1277
+_за 1271
+_як 1261
+ска 1234
+_вы 1167
+_да 1149
+ам_ 1123
+ii_ 1108
+ых_ 1094
+пер 1074
+ара 1055
+дзе 1022
+_ра 997
+_ма 950
+ым_ 946
+ая_ 934
+най 933
+ана 932
+ыя_ 920
+ца_ 919
+не_ 899
+льн 883
+ла_ 846
+пад 842
+ван 836
+ера 832
+алі 831
+пры 819
+ае_ 818
+цца 811
+год 792
+_пе 783
+мі_ 779
+аль 776
+ня_ 773
+лі_ 772
+_th 765
+анн 760
+_i_ 748
+да_ 744
+ад_ 741
+ала 737
+ада 736
+_ii 733
+ва_ 729
+асц 724
+скі 714
+рад 710
+_не 701
+_бы 688
+рац 681
+аст 679
+кам 668
+ся_ 668
+ных 651
+_са 650
+іст 648
+ары 640
+ыі_ 636
+оль 635
+тар 633
+the 625
+ння 625
+кай 618
+ля_ 610
+_аб 607
+ка_ 607
+ама 604
+іка 604
+кар 599
+_of 594
+of_ 587
+he_ 586
+ki_ 584
+on_ 580
+дзі 580
+аны 579
+ным 579
+рам 578
+рас 577
+рав 569
+але 568
+_та 561
+er_ 561
+ры_ 555
+які 555
+ці_ 553
+дзя 552
+вал 548
+тра 548
+кан 545
+нас 544
+наг 542
+_го 540
+таг 540
+аго 539
+тва 539
+адз 536
+нік 535
+амі 534
+ні_ 533
+ран 527
+ку_ 526
+нне 517
+ата 513
+іі_ 508
+сці 507
+ski 505
+ія_ 505
+_ча 503
+раз 501
+ацы 499
+es_ 498
+зе_ 493
+нск 492
+_ва 486
+зна 485
+_лі 484
+та_ 481
+_св 480
+ую_ 476
+_co 472
+аць 471
+лас 468
+тры 466
+ддз 460
+час 460
+лад 459
+го_ 457
+ств 450
+іх_ 450
+стр 449
+ion 445
+сам 442
+_га 441
+ная 441
+чна 441
+_сі 437
+так 437
+_дз 436
+ім_ 436
+тал 435
+ныя 434
+us_ 428
+ецц 428
+_de 426
+_ал 424
+одд 424
+ра_ 424
+ыў_ 424
+iii 418
+аро 416
+лік 415
+_су 414
+кла 413
+лен 410
+таў 408
+рым 406
+вае 404
+тан 402
+еры 400
+каг 400
+_рэ 398
+энн 398
+оўн 395
+одз 394
+_ін 393
+вы_ 392
+_wi 387
+был 386
+па_ 386
+там 384
+пас 382
+раў 381
+ова 380
+дна 379
+рыс 379
+енн 373
+нав 372
+and 371
+ычн 371
+_re 370
+апа 369
+ма_ 369
+_по 368
+йск 368
+ход 368
+_ме 366
+_гр 364
+ах_ 364
+адн 363
+_in 357
+is_ 356
+ані 355
+кім 355
+рыя 355
+аве 353
+для 353
+_an 352
+_вя 351
+tio 351
+аві 349
+гра 348
+овы 348
+анс 345
+_дл 343
+_сп 343
+ача 343
+ыка 343
+ыст 343
+аўн 342
+al_ 341
+_бе 339
+_li 338
+кал 338
+_ас 337
+ows 336
+_ma 335
+_шт 335
+_ве 333
+_кр 333
+вар 333
+ьна 331
+ман 330
+стэ 330
+_ба 328
+спа 328
+оў_ 327
+ўна 327
+_ар 326
+яго 325
+кія 323
+_vi 322
+аля 319
+пар 319
+цыя 318
+кая 317
+_po 316
+_яг 316
+мен 316
+пал 316
+нач 315
+рат 312
+анд 311
+аса 309
+ой_ 308
+то_ 308
+ар_ 307
+ле_ 307
+пам 307
+_тэ 306
+ati 306
+nd_ 306
+ter 306
+_ім 303
+род 303
+an_ 302
+вай 302
+тэм 302
+цыі 301
+_а_ 300
+ваў 299
+вер 299
+мы_ 299
+нал 299
+_мо 298
+быў 298
+асн 296
+en_ 295
+ліс 295
+ак_ 291
+аўс 290
+што 290
+сва 288
+вык 287
+рус 287
+аме 286
+ака 284
+нам 284
+чны 284
+_ко 283
+рал 283
+яў_ 282
+ены 281
+чан 281
+_ат 280
+авы 280
+сту 279
+ася 276
+ахо 276
+ора 276
+сіс 276
+сто 275
+_xi 274
+аец 274
+як_ 274
+ялі 274
+гэт 273
+кра 273
+_be 272
+_ar 271
+нні 271
+одн 271
+ты_ 271
+му_ 270
+паў 269
+яка 269
+_мі 268
+іна 268
+ду_ 267
+аб_ 266
+ына 266
+ўся 266
+de_ 265
+_гэ 264
+кіх 264
+аюц 263
+уль 262
+_pr 261
+ed_ 261
+_ск 260
+ia_ 260
+чын 260
+ыма 260
+_pa 259
+ўва 259
+ало 257
+мар 257
+_ро 255
+ды_ 255
+ела 255
+сць 255
+асп 254
+кас 254
+льк 254
+оры 254
+чы_ 254
+эта 254
+азв 252
+даў 252
+іта 252
+_во 251
+_зн 249
+бел 249
+_то 248
+_гу 247
+iv_ 247
+цый 247
+зен 246
+ыла 246
+асл 245
+мал 245
+wsk 244
+атр 244
+зя_ 244
+йна 244
+ing 242
+уск 242
+кса 241
+мас 241
+чэн 241
+ады 240
+вац 240
+ода 240
+_st 239
+ch_ 239
+арт 239
+_ап 237
+_xv 236
+_ся 236
+_тр 236
+in_ 236
+вял 236
+за_ 236
+тэр 236
+цы_ 236
+ена 235
+пав 235
+_to 234
+ng_ 234
+акс 234
+_бо 233
+_ві 233
+кав 233
+іра 232
+re_ 231
+аба 231
+le_ 230
+сты 230
+ант 229
+ную 229
+яй_ 229
+раб 228
+чал 228
+іў_ 228
+sta 227
+тор 227
+амп 226
+піс 226
+ix_ 225
+нта 224
+ent 223
+to_ 223
+_no 222
+_ан 221
+дав 221
+каў 221
+тур 221
+раг 220
+_ге 219
+ist 219
+ыва 219
+ьны 219
+or_ 218
+зва 218
+_so 217
+ару 217
+нар 216
+ьні 216
+ерш 215
+рын 215
+rus 214
+at_ 213
+ве_ 213
+пач 213
+іла 213
+_ca 212
+ем_ 212
+мер 212
+ст_ 212
+_bo 211
+або 211
+ніц 210
+ымі 210
+ўны 210
+_iv 209
+іва 209
+ўля 209
+vii 208
+маг 208
+_ру 207
+вых 207
+дар 207
+_a_ 206
+_ты 206
+xvi 206
+нов 206
+юць 206
+_un 205
+_се 205
+nte 205
+аза 205
+анц 205
+ель 205
+_la 204
+ылі 204
+_ўс 203
+ыйн 203
+бра 202
+льш 202
+літ 202
+нае 202
+тым 202
+ўні 202
+_se 201
+ndo 201
+оўв 201
+пан 201
+яе_ 201
+win 200
+іцы 200
+_ды 199
+_кі 199
+наў 199
+рыі 199
+шча 199
+аты 198
+мат 198
+пол 198
+сна 198
+_mi 197
+_аў 197
+ate 197
+агр 197
+ога 197
+са_ 197
+спр 197
+dow 196
+буд 195
+лав 195
+ль_ 195
+рак 195
+гад 194
+рма 194
+мов 193
+сла 193
+ькі 193
+адк 192
+дал 192
+рык 192
+іць 192
+ind 191
+гру 191
+ічн 191
+_na 190
+et_ 190
+na_ 190
+амо 190
+_fo 189
+тна 189
+_sa 188
+асі 188
+ган 188
+ўск 188
+int 187
+рыт 187
+дам 186
+лан 186
+мпе 186
+туп 186
+імп 186
+_др 185
+_ры 185
+лар 185
+тоў 185
+_бу 184
+la_ 184
+інш 183
+ver 182
+тав 182
+ікі 182
+_le 181
+гор 181
+іза 181
+_al 180
+дра 180
+яўл 180
+vi_ 179
+ляе 179
+ту_ 179
+ta_ 177
+te_ 177
+вой 177
+вор 177
+lar 175
+аду 175
+жна 175
+ков 175
+кры 174
+нцы 174
+яко 174
+абі 173
+гал 173
+рна 173
+ік_ 173
+_му 172
+ан_ 172
+ачы 172
+ваю 172
+нен 172
+che 171
+for 171
+ліц 171
+ce_ 170
+lin 170
+адс 170
+наз 170
+_ro 169
+ws_ 169
+зі_ 169
+од_ 168
+ers 167
+st_ 167
+ас_ 167
+зіц 167
+тка 167
+ён_ 167
+_ку 166
+tor 166
+йны 166
+ne_ 165
+апі 165
+акі 164
+бар 164
+кір 164
+ліч 164
+рск 164
+тыч 164
+ыю_ 164
+_ус 163
+_do 162
+аво 162
+аўт 162
+вед 162
+дан 162
+дны 162
+_am 161
+ns_ 161
+вым 161
+ніі 161
+рап 161
+_ца 160
+os_ 160
+акт 160
+жан 160
+нак 160
+шы_ 160
+ілі 160
+_чы 159
+арм 159
+бол 159
+ей_ 159
+каз 159
+тол 159
+ума 159
+адо 158
+ейс 158
+ыкл 158
+ыць 158
+_но 157
+гар 157
+_ле 156
+пы_ 156
+рон 156
+ін_ 156
+няў 155
+скл 155
+це_ 155
+_di 154
+вет 154
+ека 154
+роў 154
+сав 154
+_fr 153
+_зв 153
+ste 153
+апр 153
+ica 152
+гер 152
+заб 152
+зін 152
+паз 152
+_mo 151
+el_ 151
+ie_ 151
+тай 151
+ызн 151
+эмы 151
+ra_ 150
+um_ 150
+гул 150
+пла 150
+руп 150
+ыні 150
+_ch 149
+_пл 149
+арэ 149
+вод 149
+рта 149
+цар 149
+am_ 148
+аму 148
+est 147
+адр 147
+лів 147
+сан 147
+as_ 146
+апе 146
+аск 146
+дад 146
+ект 146
+зас 146
+цэн 146
+іль 146
+_ак 145
+con 145
+азн 145
+кую 145
+нда 145
+нем 145
+рга 145
+ску 145
+тво 145
+цтв 145
+_c_ 144
+_яў 144
+ot_ 144
+лін 144
+нап 144
+яна 144
+яшч 144
+кол 143
+льс 143
+ну_ 143
+ршы 143
+_ne 142
+_te 142
+his 142
+блі 142
+вяр 142
+кта 142
+_me 141
+ms_ 141
+nt_ 141
+азі 141
+анг 141
+віл 141
+аін 140
+зам 140
+суп 140
+_sp 139
+_фа 139
+ari 139
+вып 139
+ент 139
+коў 139
+мін 139
+рэн 139
+тро 139
+ill 138
+ran 138
+sto 138
+амы 138
+кае 138
+роз 138
+чым 138
+іча 138
+bel 137
+кат 137
+ноў 137
+ост 137
+пак 137
+уда 137
+юцц 137
+_xx 136
+_ўз 136
+ry_ 136
+амн 136
+аўл 136
+ерс 136
+зел 136
+лам 136
+мны 136
+ншы 136
+рыз 136
+рэд 136
+ючы 136
+all 135
+ic_ 135
+пап 135
+_ba 134
+_фр 134
+_ён 134
+афі 134
+зав 134
+нія 134
+све 134
+яме 134
+_іс 133
+lan 133
+se_ 133
+айн 133
+арс 133
+ацэ 133
+раі 133
+уча 133
+іся 133
+_gr 132
+ela 132
+men 132
+uni 132
+зац 132
+ней 132
+оду 132
+энт 132
+_гі 131
+зах 131
+мац 131
+нст 131
+она 131
+спе 131
+ула 131
+_ge 130
+_v_ 130
+xii 130
+вен 130
+вік 130
+ру_ 130
+ьск 130
+_зм 129
+edi 129
+per 129
+ане 129
+мад 129
+маў 129
+фар 129
+arm 128
+bot 128
+аз_ 128
+нтр 128
+ско 128
+цэс 128
+ыяд 128
+іку 128
+ўта 128
+ета 127
+між 127
+іса 127
+_ho 126
+_ха 126
+com 126
+ome 126
+бал 126
+ярж 126
+_si 125
+_кл 125
+era 125
+атк 125
+мес 125
+ржа 125
+_su 124
+_зб 124
+ar_ 124
+nal 124
+rea 124
+він 124
+зап 124
+кул 124
+лаў 124
+ніз 124
+сля 124
+ўле 124
+_кн 123
+ani 123
+aru 123
+ich 123
+ona 123
+адп 123
+бер 123
+ваг 123
+зяр 123
+мпа 123
+цка 123
+імі 123
+_ам 122
+_ну 122
+mar 122
+ńsk 122
+асо 122
+гу_ 122
+зан 122
+нан 122
+нах 122
+lit 121
+nce 121
+sch 121
+ату 121
+уст 121
+чат 121
+ўст 121
+_at 120
+ian 120
+pol 120
+ris 120
+агу 120
+дст 119
+дын 119
+ерн 119
+зал 119
+сар 119
+тны 119
+удз 119
+_ni 118
+_ла 118
+бо_ 118
+ніч 118
+усі 118
+ive 117
+rat 117
+абр 117
+дск 117
+кцы 117
+мет 117
+нна 117
+тат 117
+ію_ 117
+_бр 116
+der 116
+no_ 116
+саб 116
+яды 116
+_г_ 115
+ens 115
+ons 115
+rs_ 115
+ано 115
+ато 115
+эра 115
+_is 114
+ali 114
+les 114
+lis 114
+man 114
+tan 114
+два 114
+дыч 114
+кты 114
+над 114
+ярэ 114
+_da 113
+ten 113
+зей 113
+ло_ 113
+льт 113
+нны 113
+нум 113
+яец 113
+_дв 112
+_лю 112
+_сл 112
+tra 112
+адм 112
+дае 112
+нек 112
+озн 112
+упы 112
+іны 112
+_жа 111
+_яе 111
+ll_ 111
+арк 111
+ліз 111
+стк 111
+цоў 111
+_ha 110
+_pe 110
+_ян 110
+ka_ 110
+дка 110
+ойс 110
+рай 110
+pro 109
+ros 109
+абл 109
+авя 109
+аха 109
+ву_ 109
+выя 109
+еда 109
+раф 109
+фра 109
+цыю 109
+_ja 108
+th_ 108
+арг 108
+пат 108
+ыло 108
+эты 108
+ях_ 108
+іцц 108
+_on 107
+ard 107
+ell 107
+lle 107
+om_ 107
+str 107
+пус 107
+_he 106
+_дэ 106
+art 106
+coa 106
+por 106
+адт 106
+аца 106
+бав 106
+эры 106
+_tr 105
+oli 105
+выс 105
+нты 105
\ No newline at end of file

Propchange: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/be.ngp
------------------------------------------------------------------------------
    svn:executable = *

Added: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ca.ngp
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ca.ngp?rev=1181278&view=auto
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ca.ngp (added)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ca.ngp Mon Oct 10 22:25:53 2011
@@ -0,0 +1,1001 @@
+# NgramProfile generated at Wed Jun 08 15:05:27 PDT 2011 for Nutch Language Identification
+_de 516022
+es_ 365077
+de_ 334150
+la_ 263275
+el_ 261190
+_el 243111
+_la 233181
+_co 177338
+_i_ 171080
+en_ 169592
+ent 166275
+que 166181
+ls_ 157560
+nt_ 150408
+_a_ 143945
+_es 142224
+_qu 141042
+_se 140738
+_en 134188
+_pe 132199
+er_ 131611
+_un 123347
+per 123282
+al_ 120012
+ia_ 118076
+del 116515
+_al 107051
+_l_ 105983
+at_ 105377
+est 105341
+men 104773
+ue_ 104665
+na_ 104442
+els 101956
+ar_ 101658
+_ca 100754
+va_ 97716
+les 97400
+ts_ 95576
+_va 93846
+_pr 91960
+_re 90487
+ió_ 89704
+és_ 87754
+ra_ 86970
+ant 86210
+_d_ 84565
+ns_ 83984
+res 79034
+con 78700
+com 76189
+re_ 75747
+_le 73315
+ció 71365
+ta_ 71034
+_ma 69384
+tat 69135
+_po 67807
+des 67019
+_pa 65755
+sta 65224
+aci 64934
+amb 64831
+_no 63591
+ica 62191
+da_ 61970
+ons 61946
+un_ 60044
+_am 59421
+tre 58786
+era 55582
+_di 55225
+ter 55129
+an_ 54289
+ca_ 54098
+_in 53935
+ita 53038
+ues 52668
+una 52339
+_an 49240
+_te 49089
+mb_ 48417
+pro 47675
+nci 47057
+_mo 47048
+cia 46374
+ion 46213
+ran 46058
+ona 45850
+par 45623
+ist 44820
+_tr 43920
+ada 43914
+tra 43026
+als 41706
+_fo 41079
+om_ 40973
+_ll 40939
+_és 40055
+ria 39718
+_ha 39263
+ir_ 38985
+tes 37588
+ame 37502
+eix 36953
+_so 36817
+os_ 36738
+rs_ 36655
+ser 36569
+nta 35894
+ell 35382
+ntr 35005
+or_ 34878
+aqu 34384
+ura 34186
+cio 33689
+ren 33576
+tan 33546
+esp 33545
+ste 33496
+ici 33411
+car 33386
+_ta 33334
+pre 33213
+any 33166
+eri 33092
+ina 32951
+tal 32531
+str 32499
+_ba 32466
+més 32434
+art 32365
+_me 32132
+lla 32045
+nts 31902
+_aq 31778
+ats 31473
+tic 31409
+_si 31263
+sa_ 31258
+_ar 31183
+bre 30897
+_to 30832
+ten 30645
+le_ 30308
+_fi 30264
+ort 30218
+man 30192
+ver 30142
+for 29957
+_ex 29143
+sti 29068
+_ac 28797
+nte 28630
+us_ 28612
+eu_ 28538
+nom 28515
+lit 28502
+sen 28418
+seg 28278
+tor 28235
+err 28123
+_vi 28083
+_mé 28005
+ers 27946
+_su 27596
+_sa 27595
+mar 27488
+ic_ 27478
+lle 27184
+ari 26678
+ont 26666
+ara 26489
+ori 26486
+_fe 26413
+seu 26393
+_gr 26304
+qua 26246
+_hi 26199
+is_ 26180
+int 25926
+gra 25649
+tar 25610
+_mi 25597
+no_ 25452
+nes 25065
+alt 24511
+ix_ 24456
+ll_ 24451
+_ve 24208
+por 24096
+ere 24061
+ans 24031
+arr 23938
+ime 23877
+fer 23807
+ali 23651
+all 23633
+ial 23506
+ass 23454
+pri 23452
+_o_ 23436
+ual 23234
+ana 23127
+rre 23061
+esc 22896
+ect 22871
+ome 22854
+nal 22845
+_s_ 22560
+ral 22518
+nic 22285
+_do 22283
+rt_ 22264
+st_ 22258
+mer 22240
+tam 22231
+uni 22189
+ma_ 22184
+ble 22180
+ene 22143
+nti 22140
+tur 22048
+van 22021
+orm 22005
+act 21946
+ins 21897
+ies 21892
+lar 21738
+_ci 21641
+cs_ 21161
+se_ 20858
+pos 20683
+rra 20605
+ava 20555
+fin 20460
+rec 20446
+tro 20443
+rac 20323
+rat 20233
+tot 20207
+ade 20156
+ssi 20136
+ner 20125
+cat 19966
+emp 19904
+sev 19886
+one 19873
+enc 19861
+rma 19747
+gen 19728
+it_ 19693
+den 19676
+lan 19577
+mat 19547
+itz 19446
+_ge 19434
+der 19382
+rta 19204
+ènc 19186
+ata 19034
+ot_ 18970
+fic 18950
+ate 18866
+nat 18829
+_cr 18819
+ide 18781
+eva 18674
+on_ 18627
+_ce 18458
+rti 18387
+tit 18385
+_mu 18237
+rim 18230
+_fa 18218
+ens 18112
+mes 18112
+cap 18107
+omp 18045
+eta 18011
+ric 17998
+reg 17890
+tri 17879
+ess 17709
+inc 17709
+ri_ 17687
+cci 17676
+_or 17654
+cte 17632
+min 17550
+ode 17544
+nar 17519
+egu 17514
+erm 17464
+sos 17459
+aix 17443
+ost 17412
+olt 17332
+cas 17292
+tza 17252
+cor 17228
+ssa 17182
+tem 16913
+qui 16901
+ili 16857
+dor 16849
+ón_ 16828
+obl 16777
+ret 16755
+bar 16710
+cal 16685
+ena 16678
+te_ 16677
+rad 16633
+alm 16596
+ien 16571
+rop 16567
+vol 16554
+obr 16529
+rme 16443
+are 16439
+mun 16433
+_fr 16417
+ven 16399
+ors 16387
+san 16350
+_im 16318
+can 16285
+dia 16285
+bé_ 16281
+mol 16137
+ill 16059
+me_ 16036
+ese 15975
+ixe 15972
+ha_ 15947
+_ai 15854
+et_ 15830
+lic 15800
+val 15792
+_ro 15789
+ale 15784
+_du 15675
+rit 15631
+cip 15576
+ert 15538
+lme 15519
+ord 15447
+and 15425
+ltr 15408
+gue 15316
+ado 15312
+ern 15098
+iqu 15087
+len 14989
+ris 14984
+nya 14948
+cul 14944
+cen 14918
+ol_ 14907
+ou_ 14906
+hi_ 14874
+rei 14862
+ula 14766
+ora 14745
+tin 14743
+pel 14711
+itu 14694
+eni 14603
+arc 14590
+dic 14407
+_ob 14388
+imp 14387
+dis 14310
+nit 14227
+ele 14009
+ani 13971
+ast 13971
+eme 13932
+ny_ 13839
+ive 13822
+_na 13820
+tua 13809
+oma 13726
+_pl 13717
+uer 13693
+osa 13686
+ron 13581
+ini 13555
+ala 13512
+ida 13500
+cie 13468
+cre 13468
+mon 13465
+end 13447
+tac 13438
+_er 13426
+mpo 13404
+ure 13374
+rie 13339
+tei 13267
+edi 13254
+unt 13234
+iu_ 13221
+nse 13173
+nen 13153
+nor 13079
+_só 13030
+rin 12959
+són 12945
+mit 12928
+oca 12908
+ine 12900
+ave 12869
+bla 12846
+mbé 12845
+mpl 12834
+_ap 12825
+ics 12814
+cad 12803
+nst 12802
+ves 12789
+nia 12782
+sit 12782
+rar 12769
+pla 12734
+_as 12727
+_gu 12721
+_ja 12720
+_ho 12715
+uta 12678
+ota 12648
+ses 12620
+via 12599
+ega 12561
+_li 12555
+lac 12526
+dre 12515
+gle 12477
+sol 12468
+pob 12447
+col 12441
+sió 12419
+anc 12363
+nca 12341
+ind 12339
+sse 12307
+rob 12271
+lat 12262
+nda 12249
+_ju 12215
+cri 12161
+rri 12146
+ane 12139
+mbr 12080
+rea 12049
+llo 11949
+ema 11932
+gua 11875
+rd_ 11866
+sar 11789
+rel 11778
+ber 11736
+erò 11715
+sic 11598
+_ne 11592
+cam 11520
+ple 11474
+pod 11458
+met 11451
+ctu 11440
+rep 11438
+pal 11427
+_da 11420
+rib 11400
+ati 11390
+ndi 11390
+rò_ 11380
+rio 11368
+esa 11341
+_ab 11328
+lli 11321
+dur 11318
+cos 11280
+iva 11228
+igu 11219
+_be 11216
+avi 11215
+ut_ 11203
+fra 11164
+bli 11153
+lem 11146
+ys_ 11134
+uan 11131
+ces 11109
+rom 11076
+ove 11038
+nys 11002
+gui 10995
+nça 10985
+tiv 10957
+egl 10943
+lia 10896
+ya_ 10893
+ult 10843
+erv 10831
+_ga 10734
+rna 10732
+_ri 10676
+_jo 10674
+ing 10662
+emb 10644
+eus 10637
+nce 10612
+nde 10594
+lor 10593
+nsi 10581
+ete 10554
+rca 10542
+ja_ 10524
+spe 10499
+lta 10474
+ifi 10465
+_em 10456
+pol 10444
+dir 10436
+ngu 10431
+nis 10409
+cer 10390
+don 10375
+_pu 10323
+eco 10300
+_ra 10262
+sob 10260
+ivi 10238
+ban 10229
+ian 10170
+sis 10162
+_fu 10153
+alg 10112
+rod 10078
+lt_ 10050
+_cl 10043
+pan 10040
+dif 10028
+ua_ 10012
+tel 9978
+li_ 9977
+cti 9957
+si_ 9943
+mor 9937
+gon 9889
+rés 9888
+egi 9884
+ni_ 9864
+abl 9848
+_bo 9844
+olu 9815
+mal 9813
+pas 9800
+ap_ 9785
+sme 9781
+cta 9727
+_ad 9715
+hav 9713
+ima 9703
+mic 9686
+apa 9669
+tru 9662
+ça_ 9643
+tir 9636
+mil 9608
+til 9572
+ego 9564
+ano 9507
+pen 9507
+_au 9488
+tge 9463
+_oc 9455
+spr 9442
+cla 9407
+orr 9393
+ciu 9374
+ola 9352
+oni 9339
+loc 9337
+ram 9321
+_on 9317
+_cu 9285
+_lo 9251
+sco 9204
+_vo 9195
+nad 9194
+ès_ 9179
+rov 9167
+esi 9153
+div 9145
+as_ 9130
+vis 9114
+fou 9048
+iut 9043
+ard 8995
+omi 8972
+nac 8969
+tiu 8965
+oc_ 8913
+aba 8860
+olo 8854
+ire 8841
+pré 8827
+il_ 8820
+oba 8808
+ang 8790
+erc 8775
+òri 8767
+_pi 8739
+ior 8736
+ite 8721
+ii_ 8705
+bra 8694
+eny 8693
+ism 8690
+exp 8687
+pot 8675
+oli 8626
+ore 8624
+_ti 8613
+ipa 8589
+din 8544
+lls 8534
+omb 8529
+mpe 8517
+cel 8502
+son 8501
+atr 8482
+dar 8460
+_at 8397
+sso 8378
+sid 8365
+its 8361
+_go 8338
+aca 8333
+pec 8306
+ga_ 8289
+ps_ 8274
+ge_ 8262
+atu 8257
+eng 8206
+rqu 8206
+etr 8170
+oci 8168
+lgu 8156
+stà 8124
+ler 8122
+lon 8118
+gun 8109
+roc 8104
+rer 8100
+lis 8081
+odu 8065
+tà_ 8062
+xen 8043
+his 7998
+ela 7945
+sem 7945
+tad 7919
+atg 7895
+in_ 7889
+sup 7878
+ote 7860
+uir 7809
+sal 7776
+ust 7768
+ama 7756
+reu 7735
+fil 7690
+spa 7671
+neg 7669
+ís_ 7662
+uns 7656
+amp 7646
+vil 7641
+ndr 7631
+adi 7617
+spo 7599
+eur 7590
+_xi 7571
+eci 7552
+tòr 7550
+reb 7523
+onc 7522
+ixa 7517
+uci 7514
+bal 7503
+eve 7490
+duc 7474
+rce 7431
+han 7411
+oss 7406
+bri 7389
+rig 7372
+vin 7362
+gut 7357
+jor 7343
+ros 7317
+eti 7308
+sca 7294
+ars 7286
+rn_ 7286
+ud_ 7268
+ucc 7258
+uit 7244
+ira 7243
+ipi 7239
+_br 7237
+var 7233
+anç 7223
+gre 7223
+ila 7217
+ei_ 7205
+rso 7194
+mpr 7170
+riu 7125
+efe 7122
+eli 7116
+isi 7105
+té_ 7098
+rem 7075
+und 7059
+ova 7043
+àni 7041
+inf 7026
+vid 7026
+sin 7008
+pon 7004
+nir 7000
+pli 6922
+ife 6896
+bas 6873
+arl 6871
+osi 6859
+aus 6851
+sia 6834
+upa 6821
+iar 6812
+_ag 6800
+scr 6758
+ovi 6753
+uen 6729
+gia 6727
+uti 6727
+xem 6727
+fon 6719
+rci 6717
+nve 6706
+iss 6705
+lin 6698
+aco 6694
+org 6677
+tim 6668
+cac 6662
+gad 6659
+ref 6647
+lec 6646
+ext 6638
+sig 6636
+stò 6622
+llu 6611
+sat 6606
+pat 6604
+acc 6577
+orn 6571
+ià_ 6556
+igi 6555
+lad 6555
+iat 6553
+ume 6547
+ajo 6541
+gan 6525
+rro 6523
+nov 6518
+ope 6518
+ba_ 6515
+tja 6512
+_ed 6493
+cit 6468
+ger 6462
+_he 6451
+fun 6434
+eda 6426
+maj 6401
+arg 6374
+_ni 6371
+pa_ 6369
+ito 6356
+enç 6344
+env 6341
+udi 6337
+ui_ 6317
+aig 6306
+dat 6296
+_eu 6285
+lim 6278
+rot 6262
+sor 6261
+iga 6249
+xa_ 6247
+íti 6224
+leg 6221
+dos 6196
+pet 6192
+au_ 6181
+olí 6152
+let 6144
+uny 6143
+_av 6136
+eso 6133
+ebr 6125
+bat 6104
+jun 6092
+tud 6092
+cto 6077
+asa 6062
+upe 6055
+tab 6053
+ben 6044
+pi_ 6039
+cle 6011
+rga 6005
+ne_ 6004
+imi 6002
+ond 5990
+rà_ 5990
+poc 5965
+tav 5944
+ges 5932
+rav 5920
+iba 5915
+tia 5906
+rev 5905
+àri 5897
+itj 5881
+lun 5875
+exe 5874
+gar 5843
+usa 5839
+abi 5825
+ots 5818
+vel 5816
+soc 5815
+aut 5798
+sio 5794
+exi 5791
+ole 5782
+tàn 5769
+mpa 5757
+lti 5752
+ac_ 5741
+elo 5728
+red 5719
+què 5714
+ogr 5712
+em_ 5710
+_bi 5697
+uro 5689
+evo 5683
+cid 5666
+ius 5663
+rte 5640
+nvi 5633
+bit 5623
+èri 5621
+òni 5609
+une 5606
+veg 5591
+evi 5576
+dem 5573
+vit 5542
+_té 5541
+uda 5491
+sub 5486
+mad 5484
+nsa 5484
+uct 5483
+uè_ 5475
+uar 5472
+opo 5470
+_af 5465
+lam 5454
+mod 5441
+eal 5429
+tig 5412
+sul 5409
+mos 5398
+obe 5388
+im_ 5375
+_ut 5373
+pit 5373
+stu 5364
+di_ 5346
+fet 5320
+ig_ 5313
+eno 5311
+ton 5311
+cis 5293
+nim 5292
+sud 5289
+ecc 5284
+uin 5245
+pul 5239
+alu 5233
+àti 5229
+fa_ 5220
+ece 5213
+dec 5200
+cep 5178
+dei 5171
+ruc 5169
+là_ 5168
+gov 5166
+due 5160
+_hu 5159
+ea_ 5159
+ixò 5154
+xò_ 5152
+dit 5145
+emi 5129
+set 5128
+ero 5125
+xí_ 5123
+gin 5117
+opi 5112
+mps 5108
+ose 5083
+ixí 5082
+mas 5078
+ono 5071
+nyo 5070
+sto 5049
+uat 5042
+dep 5035
+ocu 5033
+_of 5021
+ede 5004
+rsi 5002
+cin 5001
+cab 4986
+uei 4979
+equ 4973
+gat 4972
+_ec 4964
+uel 4957
+die 4930
+jan 4924
+ign 4916
+iet 4909
+oll 4909
+onv 4907
+lte 4905
+nqu 4905
+epr 4892
+omu 4883
+ms_ 4880
+los 4879
+um_ 4877
+isc 4871
+ltu 4866
+log 4865
+mis 4861
+dan 4844
+lít 4799
+ras 4784
+med 4778
+nvo 4770
+scu 4769
+iri 4766
+ibl 4754
+ols 4753
+ecu 4750
+sim 4733
+mac 4730
+zar 4727
+rag 4721
+bai 4720
+sec 4717
+cau 4712
+lig 4708
+agr 4687
+rla 4680
+uri 4671
+apr 4646
+odi 4637
+zac 4636
+rts 4634
+rup 4634
+cli 4629
+hor 4624
+def 4611
+fes 4607
+rol 4600

Propchange: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ca.ngp
------------------------------------------------------------------------------
    svn:executable = *

Added: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/eo.ngp
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/language/eo.ngp?rev=1181278&view=auto
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/language/eo.ngp (added)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/language/eo.ngp Mon Oct 10 22:25:53 2011
@@ -0,0 +1,1001 @@
+# NgramProfile generated at Wed Jun 08 15:06:44 PDT 2011 for Nutch Language Identification
+_la 382428
+la_ 374029
+aj_ 246196
+_de 243032
+de_ 224736
+oj_ 196353
+is_ 184184
+as_ 167445
+_ka 158716
+en_ 145494
+_en 143916
+_es 136176
+kaj 133721
+est 127476
+to_ 119334
+on_ 111006
+sta 102398
+io_ 94844
+ro_ 92272
+_pr 86851
+ta_ 84035
+_ko 81850
+_po 78991
+_li 78651
+ant 78055
+tas 76074
+jn_ 75117
+_ki 71830
+ran 67142
+_al 66971
+per 64839
+_ma 64513
+nto 63544
+an_ 63496
+ist 63058
+tis 62800
+li_ 59418
+no_ 58385
+sti 58354
+aÅ­_ 57064
+kon 56876
+do_ 56827
+ita 56600
+_re 55250
+toj 52344
+ent 51516
+_an 49254
+_in 49196
+el_ 49185
+_ti 48980
+aro 47609
+ia_ 47484
+era 46867
+_se 46678
+ter 46674
+ojn 46607
+sto 44974
+_pl 44131
+nta 42572
+lo_ 42413
+_si 41789
+pro 41744
+and 41350
+al_ 40597
+taj 40368
+_mo 39952
+_ku 39584
+nte 39520
+tra 39196
+_su 38668
+_tr 37801
+_pa 37749
+te_ 36918
+_el 36863
+_ja 35980
+lan 35290
+_no 35285
+str 35267
+int 35237
+iu_ 34758
+ĝis 34526
+mal 34395
+spe 34114
+por 34002
+ili 33780
+_ne 33742
+ono 33221
+roj 33107
+er_ 32980
+_pe 32912
+ver 32687
+kiu 32398
+ata 32238
+mo_ 32101
+_ek 31851
+par 31812
+na_ 31546
+ko_ 31323
+esp 31152
+oni 31136
+ne_ 31100
+ado 30618
+ajn 30394
+gra 30281
+pre 30086
+art 30018
+_di 29742
+ra_ 29729
+ank 29714
+_un 29391
+lin 28832
+un_ 28792
+or_ 28659
+da_ 28594
+_vi 28489
+tro 28462
+ort 28424
+mon 28335
+_du 28273
+_gr 27759
+kun 27460
+kie 27371
+iĝi 27310
+pri 27274
+_te 26849
+nda 26844
+ali 26703
+eri 26702
+jar 26668
+unu 26566
+men 26435
+_ĝi 26411
+_fa 26339
+igi 26298
+_fo 26208
+ris 26161
+lia 26035
+ori 25930
+man 25760
+iel 25478
+_me 25465
+ri_ 25226
+_ve 25125
+ndo 24996
+kom 24890
+ato 24793
+iaj 24374
+ing 24319
+loj 24202
+noj 24059
+ano 23865
+_ĉe 23736
+ost 23591
+ont 23504
+iko 23470
+ara 23402
+ari 23393
+ton 23389
+ion 23088
+_aÅ­ 23086
+_ĉi 23039
+olo 23002
+co_ 22791
+dis 22751
+tan 22705
+ero 22650
+cio 22578
+_ke 22566
+rto 22427
+ple 22424
+ona 22317
+_mi 22130
+for 22075
+vas 22049
+res 21573
+_ar 21495
+kaÅ­ 21484
+ni_ 21472
+ino 21409
+pos 21408
+ond 21383
+aci 21203
+nom 21114
+_sa 21097
+rio 20941
+don 20939
+_a_ 20895
+nis 20827
+_fi 20721
+ste 20709
+ekt 20560
+rbo 20334
+ala 20211
+nka 20005
+ova 19919
+ika 19896
+am_ 19768
+_st 19732
+tri 19715
+urb 19704
+_kr 19629
+kto 19451
+ult 19403
+enc 19375
+_mu 19363
+iuj 19315
+nti 19227
+in_ 19191
+pli 19189
+_ha 19073
+tem 18910
+_na 18887
+mil 18707
+re_ 18705
+_ba 18595
+ron 18581
+cia 18499
+ntr 18457
+ana 18423
+_fr 18310
+ani 18277
+tiu 18229
+ons 18088
+aĵo 18007
+lit 17946
+alo 17914
+ilo 17844
+bo_ 17783
+_ri 17713
+le_ 17588
+ke_ 17581
+lon 17579
+rti 17464
+nas 17458
+tur 17452
+sia 17362
+ern 17178
+go_ 17178
+uj_ 17178
+_lo 17024
+oro 16925
+ven 16925
+eno 16894
+_on 16892
+tat 16859
+ava 16840
+ian 16642
+_nu 16636
+ka_ 16588
+tik 16586
+ur_ 16573
+omo 16555
+nst 16538
+_ur 16429
+nio 16379
+vo_ 16233
+ito 16230
+tor 16132
+_il 16099
+_ge 16082
+tio 15963
+ive 15933
+ndi 15926
+raj 15875
+_or 15831
+_da 15720
+eni 15702
+_ap 15700
+eks 15621
+ten 15575
+ers 15567
+ngv 15546
+po_ 15509
+ren 15297
+ide 15274
+rma 15270
+ulo 15264
+jo_ 15216
+vis 15183
+sed 15177
+reg 15151
+bro 15138
+ed_ 15089
+son 15082
+ena 14920
+ome 14913
+doj 14875
+tar 14853
+mar 14814
+_so 14788
+eto 14735
+_ok 14593
+hav 14577
+_ho 14547
+gis 14523
+erm 14504
+end 14420
+um_ 14412
+ina 14368
+ma_ 14351
+ati 14266
+iam 14239
+rit 14234
+sen 14217
+moj 14113
+dum 14108
+eco 14094
+_vo 14090
+_ta 14053
+mul 13983
+va_ 13963
+emp 13961
+rad 13941
+cen 13928
+den 13816
+ĝo_ 13816
+lej 13808
+_ro 13735
+_le 13729
+ovi 13656
+anc 13632
+akt 13568
+dan 13568
+ejo 13532
+ĝi_ 13508
+ila 13493
+ini 13443
+lio 13402
+tru 13367
+_ak 13345
+ie_ 13328
+ame 13290
+ele 13288
+ama 13234
+mor 13229
+ora 13145
+las 13125
+elo 13065
+ioj 13044
+uni 13020
+oli 12996
+fra 12922
+so_ 12895
+es_ 12890
+ere 12858
+kis 12853
+_br 12843
+nov 12840
+ord 12810
+pol 12732
+nco 12711
+tin 12663
+_ra 12624
+_be 12621
+egi 12619
+_do 12514
+kan 12476
+nci 12449
+fer 12414
+ast 12395
+_tu 12322
+st_ 12288
+ĝas 12242
+rat 12180
+iĝa 12129
+gio 12120
+lta 12063
+rov 11941
+erk 11928
+_hi 11908
+kol 11901
+kti 11884
+iga 11863
+orm 11830
+ura 11829
+rez 11785
+ej_ 11779
+tal 11764
+emo 11739
+_he 11716
+kva 11615
+ale 11518
+van 11515
+ras 11353
+voj 11321
+_va 11270
+lig 11270
+oma 11257
+_ce 11252
+ber 11247
+ici 11247
+far 11205
+_bo 11192
+sur 11166
+ins 11159
+rig 11142
+rop 11142
+rna 11083
+oka 11064
+gvo 11044
+nua 11032
+bor 10997
+kri 10988
+ene 10942
+vid 10902
+je_ 10854
+omi 10824
+opo 10818
+ua_ 10805
+uro 10804
+gan 10751
+ien 10745
+_ju 10692
+tie 10659
+koj 10645
+ola 10592
+ebl 10591
+ate 10582
+ang 10579
+mbr 10567
+_fe 10554
+san 10539
+kta 10510
+tre 10499
+rom 10473
+sis 10433
+rin 10430
+zis 10427
+nat 10422
+ekz 10418
+_sp 10394
+duk 10386
+kre 10344
+_je 10325
+_of 10275
+nor 10263
+ong 10263
+ism 10248
+laÅ­ 10140
+tit 10138
+iti 10095
+fin 10090
+ria 10073
+rte 10044
+lek 10043
+der 10028
+rik 9921
+abo 9900
+ski 9879
+bla 9867
+kar 9850
+min 9845
+fon 9826
+taÅ­ 9780
+mat 9762
+sim 9749
+ind 9745
+ezi 9735
+iri 9728
+apa 9712
+ĉef 9708
+non 9702
+azi 9636
+rta 9611
+nac 9601
+lis 9578
+pan 9562
+avi 9551
+pov 9495
+eci 9453
+naj 9452
+ask 9416
+eta 9409
+maj 9369
+sek 9363
+tia 9287
+_am 9280
+lik 9255
+sub 9221
+omp 9208
+laj 9207
+ser 9152
+kul 9143
+ger 9128
+ial 9125
+_ru 9070
+igo 9059
+raÅ­ 9046
+me_ 9036
+ida 9030
+zo_ 9000
+_kv 8968
+git 8945
+rie 8921
+_uz 8908
+kor 8895
+nde 8895
+ti_ 8894
+rdo 8860
+ans 8847
+nca 8841
+ĵoj 8814
+nur 8812
+ĉe_ 8802
+nu_ 8775
+lib 8764
+mpe 8760
+bli 8675
+ler 8663
+mer 8651
+ert 8625
+lab 8617
+nko 8589
+ca_ 8547
+_lu 8535
+pen 8515
+var 8511
+nan 8505
+rol 8477
+eli 8446
+kci 8444
+gas 8440
+vol 8436
+iki 8433
+ago 8432
+are 8425
+pon 8425
+_ga 8379
+edi 8369
+his 8347
+adi 8332
+ami 8313
+bon 8299
+rib 8267
+nsi 8252
+rki 8225
+nga 8223
+lat 8218
+alt 8205
+uso 8173
+mun 8162
+mpl 8152
+vin 8148
+met 8128
+lar 8126
+fil 8095
+_bi 8088
+rav 8044
+rak 8006
+ral 7991
+mpo 7977
+emb 7944
+_fl 7915
+daj 7911
+ard 7894
+erv 7862
+lor 7850
+tiv 7815
+oci 7803
+mem 7792
+sam 7792
+uzi 7777
+gen 7773
+ies 7757
+rko 7735
+tig 7711
+iva 7708
+ape 7695
+_kl 7691
+ite 7671
+ema 7663
+ar_ 7661
+len 7660
+oko 7644
+reĝ 7617
+ksi 7570
+smo 7566
+rus 7562
+atu 7544
+dio 7540
+org 7527
+ĵo_ 7527
+us_ 7523
+eso 7504
+viv 7493
+plu 7487
+_ni 7483
+ove 7460
+gi_ 7444
+mas 7437
+kia 7411
+kaz 7410
+sit 7408
+tut 7380
+eko 7372
+iĝo 7331
+evi 7318
+imp 7311
+ela 7300
+ret 7277
+stu 7273
+log 7272
+kla 7264
+kiĝ 7257
+ine 7249
+ner 7249
+gar 7244
+ĉiu 7200
+_at 7195
+bel 7162
+sin 7161
+emi 7141
+rek 7131
+pla 7112
+sa_ 7108
+_sc 7082
+hom 7082
+vor 7077
+gre 7063
+red 7043
+kat 7041
+kel 7002
+pe_ 6954
+val 6945
+arc 6941
+eo_ 6903
+ldo 6869
+pra 6868
+ark 6865
+ĝin 6848
+kur 6841
+se_ 6840
+tek 6822
+soc 6804
+sig 6788
+rec 6751
+_ŝi 6742
+ido 6736
+dek 6730
+rce 6722
+con 6714
+bra 6711
+cie 6709
+anĝ 6703
+cid 6664
+lok 6655
+ga_ 6626
+ens 6623
+_sk 6586
+vaj 6584
+ĉi_ 6578
+ivi 6576
+ira 6575
+tel 6565
+_as 6562
+du_ 6561
+os_ 6560
+ust 6543
+ril 6520
+riĝ 6513
+sci 6504
+inf 6473
+rmo 6433
+rka 6415
+ska 6415
+arm 6411
+aĝo 6403
+bri 6402
+sko 6400
+nce 6349
+_pi 6346
+dia 6341
+elk 6332
+aso 6331
+rmi 6330
+ega 6321
+mis 6314
+uda 6305
+rok 6295
+eti 6293
+_pu 6285
+nun 6281
+_ol 6247
+dev 6238
+ako 6232
+odo 6209
+_us 6179
+atr 6177
+omu 6174
+ign 6161
+one 6159
+cis 6154
+rso 6153
+ula 6151
+eda 6144
+loĝ 6125
+fam 6122
+sup 6115
+idi 6105
+_bu 6102
+bar 6087
+rme 6072
+uti 6068
+lka 6044
+tiĝ 6037
+uza 6037
+kst 6015
+ofi 5991
+umo 5935
+sio 5925
+_ŝt 5905
+omb 5903
+ibe 5891
+olu 5891
+div 5889
+coj 5878
+asi 5861
+_hu 5845
+izo 5839
+und 5825
+rga 5818
+mit 5815
+pec 5814
+amo 5809
+_im 5784
+itu 5769
+rua 5762
+ve_ 5756
+ogi 5734
+flu 5727
+ice 5722
+rsa 5720
+inc 5718
+efe 5711
+hel 5698
+kde 5695
+ole 5691
+ote 5677
+ukt 5650
+imi 5622
+etr 5619
+eve 5618
+ekd 5610
+ete 5600
+_ĉa 5596
+rla 5584
+kap 5563
+oft 5563
+skr 5550
+_ŝa 5543
+ume 5537
+kro 5533
+das 5529
+una 5526
+_jo 5523
+ipo 5522
+ces 5520
+esi 5506
+upo 5488
+ol_ 5487
+ble 5474
+iun 5474
+uo_ 5471
+eze 5469
+ima 5452
+ime 5438
+ngl 5419
+spa 5416
+esk 5414
+kal 5405
+rac 5398
+kam 5397
+ric 5386
+rui 5380
+tad 5364
+rda 5359
+lud 5350
+ede 5349
+ivo 5336
+niv 5335
+nik 5332
+rem 5328
+ce_ 5318
+poj 5317
+rev 5301
+tol 5297
+iro 5292
+din 5282
+saj 5280
+leg 5275
+om_ 5275
+enk 5270
+uta 5261
+nig 5258
+cip 5254
+alp 5250
+uri 5248
+kio 5246
+oje 5244
+ram 5229
+Å­ro 5229
+imo 5221
+vil 5195
+rba 5191
+izi 5181
+lte 5179
+udo 5176
+ŝta 5169
+aga 5160
+_fu 5149
+ier 5149
+tam 5145
+boj 5103
+gru 5093
+sud 5090
+til 5088
+ndu 5087
+ĝan 5084
+pat 5076
+nit 5065
+nal 5058
+vad 5056
+_ag 5053
+dec 5047
+rup 5045
+zon 5045
+_ci 5026
+uli 5021
+goj 5018
+ore 5007
+riv 4998
+alf 4983
+_eÅ­ 4981
+eĝo 4968
+_to 4947
+foj 4935
+ubl 4922
+uis 4915
+_eb 4902
+soj 4898
+arb 4892
+apo 4887
+num 4884
+all 4855
+_ad 4837
+ald 4836
+kce 4819
+jam 4815
+rdi 4805
+opa 4802
+viĝ 4795
+edo 4791
+lim 4788
+ibr 4783
+zio 4779
+sla 4766
+eÅ­r 4764
+fte 4760
+mpa 4759
+isp 4755
+raf 4755
+erl 4751
+jun 4751
+ekv 4737
+_ca 4735
+evo 4733
+oto 4723
+kas 4714
+_ed 4711
+pas 4707
+ogr 4701
+irk 4674
+ept 4663
+mov 4645
+zid 4639
+her 4636
+tag 4636
+sol 4613
+pub 4602
+kzi 4600
+gla 4592
+rim 4571
+mio 4566
+esa 4562
+dit 4556
+ge_ 4549
+oks 4535
+eme 4533
+opr 4528
+isk 4516
+zas 4516
+tim 4503
+bur 4501
+nse 4489
+amp 4481
+rei 4480
+bat 4478
+rel 4472
+aco 4470
+fla 4468
+aÅ­t 4460
+ung 4459
+ile 4446
+iza 4443
+rsi 4443
+odi 4429
+nkt 4417
+lam 4403
+mia 4403
+eld 4402
+ksa 4397
+_ev 4394
+spo 4390
+ipe 4377
+alk 4364
+unk 4362
+nia 4361
+plo 4361
+nen 4354
+pop 4349
+als 4348
+aza 4347
+fun 4343
+vi_ 4329
+_n_ 4320
+kte 4320
+dep 4301
+joj 4301
+_co 4292
+ezo 4290
+rod 4276
+von 4262
+ea_ 4253
+rea 4249
+oku 4243
+cer 4223
+mez 4223
+sal 4204
+mi_ 4199
+riz 4195
+sil 4195
+dir 4194
+_m_ 4190
+gon 4186
+ĝoj 4180
+dik 4177
+ĝen 4167
+del 4161
+aka 4156
+mik 4147
+tud 4138
+_bl 4135
+dem 4127
+sma 4124
+fic 4119
+ego 4098
+lem 4091
+ave 4078
+iis 4076
+ire 4068
+kad 4049
+rne 4049
+rof 4046
+okc 4035
+muz 4015
+dat 4013
+gni 4007
+ngo 4000
+kze 3997
+oĝa 3988
+ĉar 3981
+ane 3979
+rap 3978
+api 3977
+rde 3969
+rot 3968
+rep 3954
+ikt 3953
+sul 3951
+nej 3948
+dua 3944
+ek_ 3932
+zik 3927
+amb 3899
+vit 3897
+kut 3887
+kvi 3880
+dor 3879
+_et 3877
+nar 3873
+hun 3869
+erb 3867
+bru 3863
+nic 3861
+zen 3853
+kit 3846
+ŝi_ 3841
+ada 3837
+eva 3817
+nge 3801

Propchange: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/eo.ngp
------------------------------------------------------------------------------
    svn:executable = *

Added: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/gl.ngp
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/language/gl.ngp?rev=1181278&view=auto
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/language/gl.ngp (added)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/language/gl.ngp Mon Oct 10 22:25:53 2011
@@ -0,0 +1,1001 @@
+# NgramProfile generated at Wed Jun 08 15:08:24 PDT 2011 for Nutch Language Identification
+_de 362561
+de_ 340477
+os_ 289211
+as_ 230680
+_co 219796
+do_ 211969
+_a_ 176030
+_e_ 148881
+ent 146587
+_o_ 144578
+da_ 144100
+que 129396
+_do 125347
+en_ 124546
+nte 124516
+es_ 123737
+_en 122599
+_po 119323
+ión 117837
+te_ 116335
+_se 116250
+_qu 114451
+ón_ 111221
+ue_ 110174
+ra_ 108855
+con 104102
+_no 103372
+_es 102588
+est 99822
+_da 97953
+_pa 96504
+_ca 95634
+_un 94718
+ció 92440
+_pr 91703
+se_ 91606
+ado 90387
+_re 88993
+to_ 86582
+no_ 82834
+on_ 82389
+ia_ 75136
+men 74366
+par 73303
+sta 72331
+ica 72002
+al_ 70803
+aci 69207
+dos 69086
+res 68742
+or_ 68497
+ta_ 68082
+ant 67278
+is_ 66568
+com 64441
+na_ 63758
+_na 62458
+ro_ 62412
+_in 62205
+_ma 60636
+ida 58388
+ar_ 57239
+des 56158
+tra 55994
+un_ 54236
+ade 54102
+ist 53931
+nha 53367
+unh 52921
+ter 52897
+ha_ 52204
+_fo 52198
+cia 52169
+ada 51535
+ou_ 51441
+ndo 50795
+por 50783
+an_ 50601
+lo_ 50452
+ara 49902
+_as 48813
+_te 48670
+dad 48495
+_pe 48329
+ca_ 48070
+and 47367
+ran 47229
+mo_ 47160
+nto 47157
+nci 47155
+co_ 46709
+_os 46533
+io_ 46177
+_me 45312
+per 44965
+pro 44009
+_an 42944
+la_ 42826
+_mo 42662
+ste 42248
+_di 42188
+eir 41812
+ns_ 41575
+ía_ 40807
+era 40030
+_é_ 38847
+nta 38725
+_so 38693
+das 38426
+ico 38241
+ntr 37887
+pre 37350
+er_ 37330
+ici 37158
+ita 37003
+pol 36612
+nde 36196
+_tr 36019
+tes 35915
+ano 35863
+ont 35798
+ali 35501
+str 34745
+_al 34459
+re_ 34247
+ina 34102
+tro 33428
+rio 33394
+tic 33180
+_ou 33167
+ito 33072
+art 32766
+ron 32618
+den 32334
+ura 31657
+tor 31585
+tos 31346
+nos 31266
+ari 31176
+tan 30842
+ons 30673
+omo 30623
+ido 30315
+for 30282
+ame 30184
+ais 30126
+cas 29991
+ort 29863
+_ba 29474
+rte 29021
+ese 28913
+eri 28638
+esp 28464
+óns 28461
+enc 28443
+end 28407
+_sa 28381
+_ex 28360
+ras 28352
+nda 28275
+_su 28176
+tad 28044
+rec 27981
+sti 27846
+ten 27829
+olo 27590
+_ao 27559
+ria 27535
+can 27525
+iro 27513
+ona 27272
+eu_ 27225
+_vi 26867
+ma_ 26654
+_li 26245
+rad 26126
+oi_ 26110
+go_ 25982
+gra 25962
+car 25913
+ros 25908
+man 25708
+nti 25581
+cid 25536
+_ac 25512
+err 25340
+_gr 25284
+ao_ 25267
+_ta 25168
+tre 25002
+mar 24844
+ira 24809
+ome 24729
+seu 24658
+_fi 24384
+sen 24324
+der 24286
+ase 24256
+_sú 24128
+pri 24061
+súa 24007
+int 23838
+ori 23784
+ver 23650
+aba 23626
+tiv 23595
+cio 23426
+_to 23407
+tal 23275
+pos 23196
+_si 23148
+_ar 22915
+esc 22887
+_du 22810
+ale 22764
+_ve 22697
+_ga 22689
+tar 22611
+ero 22392
+tas 22355
+_má 22351
+ata 22275
+ion 22168
+_fa 22134
+_at 22090
+und 21998
+ser 21863
+uni 21857
+iza 21734
+_ci 21689
+ece 21554
+foi 21482
+nic 21406
+rma 21402
+tur 21273
+llo 21264
+fic 21171
+ela 21100
+cos 20953
+qui 20792
+edi 20788
+ect 20784
+so_ 20756
+úa_ 20748
+cul 20692
+sto 20669
+lic 20603
+sa_ 20585
+nse 20508
+áis 20448
+mái 20400
+eci 20299
+inc 20223
+orm 20212
+ola 20209
+cor 20103
+ide 20102
+ría 20021
+anc 19900
+emp 19852
+_lo 19761
+non 19706
+_ch 19631
+lla 19566
+_mi 19521
+ren 19514
+tem 19491
+dor 19474
+tam 19357
+ime 19241
+min 19064
+cen 18957
+_fr 18927
+_mu 18869
+nas 18844
+nal 18819
+cal 18730
+ric 18711
+ell 18705
+ing 18689
+las 18574
+_cu 18510
+ore 18426
+egu 18394
+los 18298
+_le 18115
+ña_ 18107
+ber 18042
+ial 17988
+rim 17899
+za_ 17888
+les 17879
+ere 17782
+mpo 17780
+cad 17751
+nce 17739
+ost 17638
+ill 17603
+mai 17603
+_ce 17545
+ers 17538
+ele 17519
+rra 17518
+ema 17506
+us_ 17492
+el_ 17440
+rei 17436
+ios 17413
+_cr 17364
+ral 17314
+rti 17312
+gal 17248
+rac 17190
+act 17182
+ili 17131
+ens 17071
+are 17051
+_á_ 16946
+ern 16896
+tri 16887
+_va 16876
+seg 16856
+san 16814
+uci 16718
+out 16631
+_el 16579
+bre 16577
+lle 16456
+obr 16301
+arr 16256
+eme 16221
+lar 16216
+lan 16132
+_xe 16131
+son 16126
+ode 16058
+ind 15926
+ora 15897
+mes 15889
+_ha 15869
+oma 15822
+_la 15814
+ana 15813
+esa 15801
+én_ 15759
+nad 15707
+ior 15661
+_fe 15510
+rea 15450
+ond 15418
+exi 15350
+le_ 15347
+esi 15222
+dia 15199
+sió 15199
+_or 15171
+rit 15167
+_ne 15165
+rop 15128
+omp 15055
+dis 14925
+_ro 14913
+_im 14803
+vo_ 14698
+fer 14659
+nst 14615
+_ap 14576
+dic 14556
+bra 14554
+liz 14540
+cto 14514
+ces 14433
+ega 14361
+rre 14343
+rta 14315
+ias 14224
+_au 14207
+ban 14164
+imp 14103
+ula 14086
+mer 14081
+tin 14062
+ert 14042
+ivo 13967
+mei 13910
+ala 13877
+ndi 13833
+án_ 13824
+utr 13815
+nom 13757
+ama 13688
+ini 13619
+xa_ 13614
+odo 13596
+mun 13512
+_ti 13511
+cri 13487
+ast 13447
+oca 13409
+all 13356
+itu 13293
+alm 13278
+ga_ 13244
+smo 13209
+onc 13200
+col 13194
+oa_ 13184
+ian 13181
+sid 13175
+ulo 13143
+aro 13137
+lme 13124
+cip 13101
+gue 13066
+ato 13042
+gar 12993
+ba_ 12984
+_ho 12954
+nor 12952
+cel 12939
+cha 12923
+po_ 12920
+mos 12885
+eta 12816
+nov 12809
+cer 12788
+amé 12750
+lin 12726
+_ad 12650
+med 12649
+ir_ 12640
+fra 12610
+ati 12580
+pod 12550
+tua 12527
+ate 12524
+ino 12452
+mas 12400
+cam 12384
+me_ 12364
+dun 12354
+iva 12351
+ous 12351
+rro 12332
+nac 12329
+erm 12318
+use 12244
+_nu 12213
+va_ 12207
+eno 12141
+_am 12080
+rat 12073
+lia 11982
+rel 11982
+gun 11979
+tid 11955
+tod 11888
+_em 11870
+ans 11750
+cci 11699
+mad 11660
+xe_ 11600
+ani 11593
+spo 11587
+mén 11560
+ima 11538
+apa 11527
+ble 11527
+eit 11474
+eus 11472
+uen 11466
+fin 11465
+_xu 11360
+sco 11257
+gre 11191
+mil 11166
+_ob 11130
+arc 11089
+_go 11057
+mon 11055
+bro 11039
+tac 11030
+ace 11011
+nun 10990
+_br 10984
+ego 10983
+coa 10964
+uto 10953
+moi 10925
+rin 10892
+spa 10890
+spe 10810
+dou 10803
+_ra 10763
+ive 10735
+ven 10731
+rna 10723
+lec 10719
+vol 10680
+lid 10654
+ult 10648
+ena 10629
+uer 10628
+sic 10577
+uro 10571
+_er 10518
+iña 10499
+nsi 10498
+_ab 10492
+ses 10466
+orr 10454
+tab 10450
+_lu 10418
+asa 10411
+_fu 10365
+eco 10353
+cre 10339
+aio 10336
+_xa 10328
+stá 10311
+rex 10309
+var 10287
+vid 10281
+pal 10260
+_gu 10253
+oit 10247
+pas 10243
+mor 10211
+_be 10197
+nar 10190
+reg 10189
+asi 10187
+ien 10186
+nid 10156
+mpe 10073
+erí 10041
+rar 10037
+xo_ 10031
+bri 10026
+ite 10010
+ris 10002
+és_ 9966
+pen 9881
+_bo 9850
+nes 9833
+rib 9798
+dur 9780
+lem 9778
+lon 9765
+rom 9749
+emb 9745
+ai_ 9725
+lis 9721
+ifi 9720
+ngu 9703
+oñe 9670
+ivi 9635
+che 9622
+rep 9607
+sob 9552
+oro 9551
+_pu 9527
+_hi 9481
+ret 9476
+ce_ 9473
+ual 9446
+ipa 9417
+erc 9372
+mpl 9357
+bli 9331
+lit 9329
+obe 9280
+rod 9267
+unt 9249
+sas 9230
+lac 9226
+mpr 9180
+gua 9179
+ord 9158
+sit 9149
+isi 9129
+scr 9105
+oci 9062
+pañ 9040
+duc 9027
+axe 9009
+poi 8958
+nis 8940
+ust 8940
+ea_ 8935
+tel 8904
+uga 8901
+aña 8877
+igo 8876
+cat 8867
+ete 8867
+ago 8858
+aca 8851
+abi 8848
+bal 8808
+vis 8803
+oni 8793
+pec 8793
+xer 8788
+roc 8743
+leg 8728
+eli 8694
+ota 8684
+eo_ 8683
+úas 8682
+rno 8677
+lta 8642
+bar 8631
+ede 8630
+tit 8600
+obo 8587
+ono 8567
+sar 8551
+fun 8548
+ove 8531
+gui 8512
+rde 8509
+gan 8496
+ard 8474
+_vo 8472
+ez_ 8467
+rto 8460
+gos 8447
+_cl 8444
+eso 8436
+cti 8434
+xen 8407
+dem 8391
+dio 8391
+mat 8364
+emi 8358
+rso 8334
+_pi 8293
+osi 8293
+sis 8248
+coñ 8233
+tru 8228
+mic 8217
+rem 8197
+aso 8187
+rab 8164
+alg 8160
+índ 8157
+lor 8131
+erv 8111
+pob 8106
+nza 8104
+mit 8070
+ois 8070
+tig 8069
+_sé 8062
+cie 8048
+iu_ 8036
+lad 8034
+il_ 8000
+exa 7979
+ixi 7976
+_oc 7970
+atr 7966
+met 7951
+mbr 7949
+bas 7946
+in_ 7941
+val 7934
+ctu 7922
+alt 7902
+zad 7892
+cap 7870
+ane 7861
+adi 7858
+ume 7838
+ism 7834
+imi 7823
+ixo 7809
+ñec 7803
+ram 7798
+pa_ 7782
+elo 7769
+boa 7755
+fil 7752
+hab 7737
+exp 7725
+iga 7706
+_ó_ 7675
+ii_ 7662
+écu 7649
+ins 7643
+nve 7642
+_on 7620
+arí 7619
+osa 7619
+red 7619
+ami 7607
+pla 7596
+rov 7582
+íti 7570
+dir 7566
+día 7526
+ine 7524
+abe 7499
+sos 7496
+ecu 7478
+rca 7475
+bit 7457
+imo 7450
+nia 7423
+séc 7409
+til 7379
+eda 7317
+dec 7311
+esm 7310
+zo_ 7296
+_xo 7286
+rse 7285
+ño_ 7283
+_bi 7272
+rri 7254
+ogr 7242
+pon 7234
+dep 7233
+atu 7227
+usa 7196
+omi 7188
+rqu 7185
+aut 7173
+_ag 7131
+eal 7131
+dar 7120
+eza 7119
+ene 7106
+gad 7098
+stu 7087
+rid 7086
+oqu 7076
+_he 7072
+sup 7068
+cla 7052
+nco 7047
+erd 7044
+ovi 7026
+tud 7026
+lat 7021
+río 7019
+emo 7010
+_ni 6998
+tán 6992
+efe 6988
+sin 6964
+_il 6946
+del 6943
+bel 6936
+etr 6925
+len 6898
+_eu 6891
+loc 6890
+sca 6888
+ova 6883
+opa 6880
+dif 6865
+amp 6859
+oli 6853
+rci 6853
+sol 6818
+odu 6814
+rie 6814
+equ 6804
+oso 6804
+ler 6798
+ís_ 6780
+exe 6776
+cac 6775
+tou 6755
+deb 6739
+_is 6728
+_pl 6711
+alo 6711
+ire 6709
+bai 6685
+lev 6674
+eva 6669
+xis 6667
+aín 6665
+dan 6638
+rga 6615
+iti 6611
+ext 6592
+inf 6586
+_ri 6566
+aix 6562
+ila 6524
+_aí 6513
+aco 6499
+aís 6499
+tá_ 6488
+vas 6476
+ref 6471
+cab 6468
+olí 6448
+abr 6427
+ull 6420
+sem 6403
+edo 6393
+his 6392
+gob 6374
+tim 6361
+rmi 6329
+ogo 6321
+tiñ 6290
+abl 6288
+ose 6280
+rix 6280
+vin 6258
+ás_ 6258
+año 6250
+div 6227
+mpa 6225
+tir 6224
+nat 6222
+fac 6207
+isc 6197
+lei 6196
+ol_ 6166
+lib 6160
+ton 6141
+paí 6137
+iad 6131
+ped 6109
+sal 6086
+ner 6083
+ham 6073
+rev 6056
+lti 6054
+dei 6052
+rda 6044
+sur 6038
+uia 6008
+ías 5990
+opi 5979
+_us 5975
+ei_ 5962
+opo 5951
+aqu 5940
+mac 5923
+_of 5905
+rme 5898
+soc 5887
+amb 5874
+van 5846
+rai 5843
+zar 5841
+rou 5834
+ecc 5824
+vos 5812
+zas 5804
+cun 5799
+vil 5790
+eto 5779
+bor 5774
+mal 5716
+anz 5701
+eur 5696
+rob 5686
+adr 5682
+orn 5682
+ixe 5672
+roq 5662
+rav 5649
+oce 5641
+lab 5628
+ote 5622
+gas 5610
+rot 5605
+onv 5604
+lug 5599
+lim 5591
+mel 5589
+tec 5589
+ong 5579
+mul 5568
+lít 5564
+log 5563
+_ed 5562
+vel 5561
+amo 5554
+ovo 5553
+unc 5546
+uti 5522
+oac 5520
+ua_ 5511
+_id 5508
+ave 5505
+aos 5486
+nai 5484
+ein 5460
+ole 5452
+evi 5441
+did 5438
+sul 5432
+ur_ 5427
+ben 5419
+cur 5409
+nsa 5408
+one 5404
+uel 5398
+olu 5376
+sec 5371
+mez 5362
+cem 5356
+mod 5348
+raz 5337
+nan 5326
+pit 5325
+hom 5292
+_ec 5272
+ope 5245
+abo 5242
+rón 5228
+org 5223
+xic 5218
+ve_ 5217
+zac 5199
+scu 5182
+orí 5181
+pad 5172
+dra 5171
+ues 5167
+heg 5146
+oto 5143
+ibe 5142
+_af 5134
+así 5133
+rsi 5117
+_ig 5107
+plo 5104
+ibi 5091
+ne_ 5090
+ced 5075
+mán 5054
+xió 5043
+olv 5041
+_rí 5035
+arq 5025
+lve 5018
+ío_ 5013
+ían 5003
+iño 4995
+ves 4994
+_dí 4990
+tei 4989
+cin 4980
+edr 4980
+fal 4976
+xec 4976
+mis 4957
+ipo 4954
+ple 4954
+apo 4943
+rup 4941
+mbi 4927
+_ir 4924
+pra 4919
+ars 4917
+xun 4904
+_bu 4903
+pul 4902
+pan 4898
+arl 4897
+xía 4891
+áti 4886
+aza 4880
+bo_ 4873
+evo 4873
+ilo 4869
+tom 4860
+pio 4854
+cou 4850
+inv 4847
+sub 4846
+bil 4845
+iar 4841
+igr 4839
+nca 4830
+sí_ 4825
+_xi 4816
+pou 4796
+via 4787
+api 4775
+upo 4769
+vad 4764
+ile 4762
+egr 4759
+hai 4759
+_th 4752
+lam 4750
+aus 4736

Propchange: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/gl.ngp
------------------------------------------------------------------------------
    svn:executable = *

Added: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ro.ngp
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ro.ngp?rev=1181278&view=auto
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ro.ngp (added)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ro.ngp Mon Oct 10 22:25:53 2011
@@ -0,0 +1,1001 @@
+# NgramProfile generated at Wed Jun 08 15:09:32 PDT 2011 for Nutch Language Identification
+_de 275797
+de_ 221617
+_în 201809
+te_ 185452
+ul_ 173696
+re_ 147553
+şi_ 144596
+în_ 138751
+le_ 138646
+_a_ 133790
+_şi 129587
+are 128007
+ea_ 126532
+_ca 107537
+in_ 103624
+_di 103605
+_pr 101695
+est 101638
+_co 100783
+ui_ 98427
+ia_ 96188
+ii_ 94435
+lui 91306
+din 89879
+_pe 87943
+la_ 87244
+or_ 86340
+_la 85811
+ste 85394
+_ma 83317
+ate 82009
+_un 81730
+_al 80569
+ent 76873
+at_ 76298
+_cu 76154
+ei_ 75281
+tă_ 74565
+_re 73436
+ele 69971
+al_ 68556
+ntr 67751
+ulu 67602
+rea 66513
+tat 65973
+_se 65202
+_es 62123
+_in 61236
+eri 60921
+ie_ 60412
+car 60313
+_ce 60304
+_fo 59970
+lor 59578
+tor 56819
+con 56788
+_o_ 55465
+cu_ 55403
+_ac 54614
+că_ 54083
+tul 53892
+se_ 53831
+ori 52641
+st_ 51801
+ale 51347
+ri_ 51093
+pri 50682
+au_ 50343
+ist 49381
+_su 48666
+ter 48613
+tru 48049
+_po 47312
+ita 46805
+ile 46762
+pre 45339
+_ro 44548
+ce_ 44471
+aţi 44169
+ne_ 43210
+tre 42947
+un_ 42868
+int 42797
+_lu 42307
+nte 42206
+uri 42127
+pe_ 41815
+_sa 41679
+ar_ 41444
+ace 41264
+ai_ 41170
+ani 41113
+_fi 40769
+ru_ 40371
+ca_ 39967
+_pa 39949
+ali 39944
+rom 39778
+sta 39493
+_au 39046
+_tr 38650
+ost 38644
+_nu 38163
+pro 37941
+ilo 37912
+tra 37768
+_st 37626
+_ar 37507
+mai 37165
+nd_ 37160
+ici 37105
+să_ 37075
+_an 37073
+ra_ 37044
+art 36938
+mân 36409
+lit 36119
+era 36065
+tic 36047
+ere 35981
+tur 35373
+str 35258
+men 34656
+_mo 34654
+par 33961
+_să 33809
+it_ 32860
+rat 32832
+_or 32526
+fos 32407
+_lo 32368
+tea 32242
+nă_ 32048
+uni 31985
+pen 31966
+an_ 31682
+ată 31524
+nt_ 31441
+nia 31202
+ica 31013
+mar 30991
+ră_ 30959
+_mu 30944
+rin 30651
+mul 30630
+per 30598
+ine 30560
+eni 30285
+oar 30205
+_că 30187
+ta_ 30063
+rii 29904
+_do 29778
+ril 29631
+_si 29620
+ni_ 29000
+rul 28851
+iei 28667
+com 28654
+omâ 28575
+rit 28561
+_mi 28466
+une 28391
+ari 28066
+_li 28048
+ran 27960
+_da 27286
+Å£ii 27231
+nul 27089
+loc 27076
+rie 26978
+na_ 26900
+ice 26761
+ind 26483
+man 26445
+cel 26408
+ric 26341
+rma 26153
+ică 26017
+atu 25888
+el_ 25888
+ion 25661
+ces 25525
+num 25470
+şti 25305
+ând 25271
+Å£i_ 25157
+sti 25125
+ona 25056
+eşt 24934
+_ap 24786
+lă_ 24517
+ite 24505
+_te 24363
+_le 24038
+ili 24008
+ora 23784
+ast 23778
+ant 23667
+rec 23641
+ic_ 23606
+cal 23390
+_me 23380
+ări 23378
+_ex 23216
+ult 23097
+nic 23019
+cul 22957
+tel 22804
+_fa 22657
+iul 22622
+_pu 22592
+_du 22549
+_no 22348
+ini 22340
+edi 22323
+cea 22318
+Å£ie 22301
+chi 22228
+ită 22094
+ina 22017
+mun 21963
+ial 21869
+ara 21834
+imp 21773
+ati 21765
+Å£ia 21688
+ons 21687
+anu 21565
+înt 21525
+esc 21469
+ut_ 21469
+col 21419
+nu_ 21377
+_as 21375
+_ju 21163
+_sc 21151
+tri 21022
+ect 21010
+iun 20861
+for 20836
+rim 20699
+ci_ 20657
+nea 20620
+olo 20619
+res 20539
+_sp 20396
+ză_ 20353
+_ve 20352
+tin 20342
+mat 20314
+nal 20170
+tar 20159
+_vi 20021
+rte 19783
+ria 19682
+nde 19673
+cat 19627
+_cr 19624
+ire 19448
+min 19442
+_ba 19400
+lul 19370
+tiv 19350
+scu 19335
+itu 19309
+ura 19041
+reg 18994
+va_ 18959
+nta 18888
+oca 18815
+âni 18781
+unt 18566
+ume 18522
+tan 18465
+lic 18432
+ene 18413
+ală 18381
+cur 18370
+ti_ 18359
+elo 18349
+_so 18122
+ito 18094
+_ge 18037
+_va 18023
+and 17944
+dat 17919
+ver 17885
+nce 17880
+_ti 17757
+_ne 17693
+Å£a_ 17524
+înc 17402
+des 17256
+orm 17254
+_to 17249
+iar 17157
+nat 17137
+cia 17125
+us_ 17115
+enţ 17010
+nti 16978
+por 16959
+nst 16737
+ato 16732
+şte 16599
+oli 16590
+ort 16550
+_ad 16437
+stă 16374
+lea 16339
+_fr 16327
+der 16276
+nit 16204
+mit 16122
+ude 16097
+iu_ 16065
+_gr 15912
+fic 15902
+_bu 15804
+ian 15776
+rti 15706
+ame 15696
+ază 15645
+ral 15613
+ers 15562
+eas 15560
+tal 15544
+iţi 15504
+cri 15396
+reş 15368
+iza 15344
+_bi 15331
+tim 15305
+_im 15246
+er_ 15231
+cer 15093
+rep 15028
+raş 15027
+pă_ 15023
+bil 15010
+ocu 14954
+ier 14897
+nţi 14856
+ten 14815
+_s_ 14793
+_câ 14771
+ser 14758
+rop 14727
+ma_ 14705
+eaz 14646
+ern 14644
+_el 14613
+ont 14610
+erm 14590
+fer 14569
+nci 14556
+oni 14450
+on_ 14415
+act 14376
+pul 14374
+pol 14224
+ven 14180
+jud 14150
+_ia 14119
+inc 14114
+eze 14079
+ţă_ 14078
+_na 14076
+cre 14047
+ase 14036
+rez 14028
+sa_ 14006
+cut 13982
+deţ 13968
+alt 13958
+rel 13854
+imi 13777
+ond 13770
+ăţi 13770
+_at 13756
+nii 13750
+put 13732
+olu 13724
+egi 13722
+ndu 13588
+ide 13572
+iin 13571
+ula 13547
+Å£ul 13510
+lte 13471
+sun 13468
+ime 13442
+cţi 13421
+nsi 13400
+tăţ 13400
+iil 13387
+sit 13381
+ntu 13360
+eci 13333
+Å£io 13325
+inţ 13295
+ata 13275
+ima 13274
+gra 13272
+ris 13179
+omu 13168
+cen 13146
+ans 13128
+_pi 13115
+_ci 13026
+nţa 13012
+ive 13011
+ger 13005
+es_ 12895
+upă 12888
+ins 12825
+eţu 12816
+toa 12698
+_ră 12692
+eme 12640
+ară 12616
+me_ 12609
+dup 12591
+oma 12577
+nie 12492
+lat 12464
+unc 12455
+iti 12453
+sau 12450
+tit 12450
+ane 12440
+_er 12429
+stu 12410
+lia 12375
+nor 12349
+_av 12259
+ure 12203
+sto 12200
+Å£in 12155
+lim 12104
+lan 12054
+ope 12050
+ecu 12006
+lin 11992
+dia 11967
+nis 11947
+umi 11933
+oru 11913
+fii 11815
+_am 11811
+_ur 11803
+eco 11786
+mon 11769
+ioa 11684
+sat 11672
+sul 11665
+ute 11646
+dec 11637
+vin 11632
+_ch 11596
+dar 11594
+ord 11567
+cum 11532
+ndi 11528
+ece 11523
+lar 11483
+mer 11481
+sec 11441
+uit 11433
+den 11401
+rar 11401
+ner 11385
+_vo 11194
+cti 11181
+cep 11157
+leg 11154
+ovi 11127
+mel 11122
+can 11094
+oi_ 11066
+tem 11061
+abi 10975
+_ni 10917
+is_ 10913
+duc 10884
+_fe 10882
+imb 10857
+sup 10852
+mic 10850
+mpo 10846
+ctu 10795
+_br 10787
+bli 10786
+inu 10786
+rio 10760
+fra 10753
+um_ 10716
+eli 10698
+rta 10698
+tro 10691
+dic 10676
+ala 10593
+scr 10567
+gen 10542
+omi 10530
+zat 10487
+bri 10453
+spe 10437
+_ra 10434
+und 10427
+eta 10416
+rei 10395
+ână 10370
+oat 10362
+_bo 10357
+_pl 10357
+_af 10350
+anţ 10346
+mil 10262
+dis 10251
+nda 10243
+uno 10179
+păr 10146
+emi 10116
+ivi 10111
+ana 10107
+_dr 10102
+rad 10078
+da_ 10040
+iv_ 10031
+ise 10026
+ăto 10023
+pun 9989
+ren 9984
+uţi 9965
+ome 9936
+mbr 9881
+nei 9872
+nţe 9847
+ing 9824
+elu 9752
+one 9736
+_cl 9676
+nar 9620
+ifi 9541
+lie 9535
+pân 9508
+_pă 9502
+fi_ 9471
+ust 9457
+sub 9442
+omp 9419
+spr 9408
+cor 9392
+cip 9338
+_îm 9319
+sil 9317
+upr 9282
+vol 9273
+_is 9267
+pra 9251
+si_ 9224
+ede 9211
+ânt 9199
+log 9165
+epu 9159
+căt 9139
+iri 9115
+cii 9099
+ezi 9069
+ore 9069
+cop 9065
+sem 9020
+una 9016
+ept 9015
+ber 9012
+unu 9006
+alu 8999
+liz 8996
+dul 8976
+che 8918
+opu 8918
+ade 8878
+ege 8863
+anc 8856
+van 8851
+gin 8838
+pec 8833
+asc 8832
+tua 8806
+ela 8790
+sco 8771
+iet 8752
+oas 8741
+mpl 8721
+eve 8689
+ung 8685
+dus 8674
+ete 8671
+apa 8668
+rem 8648
+ubl 8575
+_tu 8553
+cto 8553
+atr 8508
+pop 8505
+val 8497
+esp 8495
+_i_ 8474
+il_ 8454
+_ru 8421
+iat 8412
+eti 8372
+ien 8351
+riu 8348
+ole 8340
+dev 8337
+cân 8332
+şul 8321
+ova 8315
+nil 8309
+uce 8307
+dep 8251
+împ 8243
+naţ 8143
+urm 8128
+ură 8106
+ean 8101
+ese 8040
+emb 8033
+sal 7996
+ico 7986
+org 7980
+etr 7979
+dre 7977
+_fu 7957
+_ob 7941
+ană 7928
+ât_ 7925
+fie 7882
+_pâ 7880
+nţă 7873
+sc_ 7868
+cun 7866
+gre 7811
+pat 7780
+cât 7771
+apr 7758
+ron 7747
+pub 7730
+mpu 7712
+nel 7710
+med 7706
+ret 7698
+en_ 7683
+red 7677
+fac 7670
+căr 7657
+apo 7656
+ntă 7631
+_oc 7619
+rac 7593
+eal 7591
+măr 7589
+pla 7585
+ech 7558
+los 7549
+_be 7547
+evi 7536
+til 7527
+_ta 7522
+sch 7499
+vit 7491
+osi 7488
+tr_ 7482
+asi 7472
+oci 7464
+uro 7447
+les 7433
+mod 7373
+asa 7368
+lon 7361
+bis 7338
+tei 7331
+arc 7328
+za_ 7302
+ola 7295
+ave 7291
+os_ 7288
+ină 7264
+pot 7263
+ău_ 7257
+_ga 7256
+lta 7254
+_op 7251
+oan 7248
+ami 7216
+ono 7211
+gur 7195
+mă_ 7191
+exi 7190
+rd_ 7184
+uat 7182
+luc 7171
+ge_ 7164
+ism 7155
+scă 7150
+zi_ 7130
+ogi 7121
+_fă 7118
+dă_ 7116
+lec 7080
+dea 7050
+uto 7042
+lis 7039
+enu 7029
+cte 7020
+Å£iu 7012
+_ec 7010
+aş_ 7002
+odu 6998
+tră 6984
+eor 6979
+tot 6966
+rme 6965
+riv 6960
+dov 6921
+erc 6907
+iec 6900
+_ai 6879
+imu 6878
+dom 6876
+_eu 6875
+aşu 6872
+Å£il 6870
+pie 6865
+raf 6865
+ună 6853
+cin 6852
+ove 6834
+_mă 6818
+_ha 6815
+izi 6809
+vie 6793
+ct_ 6789
+aşi 6788
+raţ 6774
+lun 6766
+rev 6763
+ict 6757
+buc 6755
+ba_ 6743
+lel 6743
+îns 6742
+ze_ 6731
+laţ 6694
+opo 6682
+ot_ 6676
+rţi 6662
+gat 6657
+udi 6656
+sin 6595
+cla 6565
+âne 6562
+apt 6555
+soc 6555
+acu 6542
+old 6542
+iva 6539
+ucr 6532
+eur 6531
+ătr 6521
+et_ 6512
+dem 6508
+esi 6508
+icu 6498
+fel 6493
+ens 6489
+ero 6453
+adi 6442
+use 6435
+adu 6429
+dez 6425
+poa 6421
+dou 6419
+_ev 6413
+opi 6405
+rus 6405
+he_ 6399
+mol 6397
+ega 6396
+mis 6396
+lum 6393
+tui 6392
+osc 6372
+ref 6366
+ves 6332
+uă_ 6331
+exp 6327
+cra 6300
+lva 6288
+ote 6263
+ol_ 6261
+zar 6260
+lt_ 6254
+clu 6251
+epr 6246
+rna 6245
+fol 6232
+cap 6227
+_zi 6219
+_sf 6217
+_of 6215
+igi 6210
+aut 6177
+eţi 6172
+răz 6168
+xis 6135
+eau 6121
+ozi 6116
+hia 6111
+cup 6106
+aju 6105
+nes 6099
+fin 6095
+pan 6093
+ndr 6091
+fil 6084
+nom 6063
+fun 6060
+giu 6057
+utu 6056
+ram 6054
+mba 6042
+pli 6036
+gan 6031
+ub_ 6016
+acă 6010
+eca 6006
+boi 5998
+zen 5995
+ns_ 5993
+ătu 5991
+erv 5985
+sur 5980
+ada 5976
+ăra 5973
+ton 5969
+ipa 5966
+rod 5936
+nui 5922
+vic 5920
+_ul 5897
+end 5888
+del 5868
+afl 5863
+mor 5861
+ouă 5857
+isc 5854
+tud 5850
+ua_ 5841
+uma 5838
+pa_ 5836
+azi 5817
+ard 5811
+nos 5811
+rân 5802
+gar 5800
+ang 5781
+zbo 5777
+inf 5776
+ăru 5770
+aru 5769
+var 5760
+Å£el 5756
+mur 5752
+_gu 5751
+urs 5744
+cie 5743
+ogr 5736
+bra 5719
+tii 5701
+du_ 5697
+las 5693
+ltu 5691
+emn 5684
+sar 5671
+cui 5668
+rui 5658
+ena 5655
+arm 5654
+_n_ 5653
+_jo 5647
+ilv 5630
+eră 5629
+evo 5613
+zon 5603
+nsu 5599
+afi 5596
+ema 5578
+met 5576
+dit 5574
+roa 5574
+olt 5571
+_ed 5569
+niv 5569
+dru 5566
+ghe 5553
+tăr 5545
+vor 5529
+eva 5527
+sen 5526
+aco 5516
+eru 5498
+obi 5496
+ără 5486
+oie 5485
+roc 5467
+ăzb 5465
+ama 5463
+rov 5461
+ual 5461
+aci 5440
+_io 5432
+mag 5426
+lem 5406
+ert 5396
+ior 5395
+reu 5389
+rup 5383
+ucu 5375
+tie 5373
+vec 5369
+dif 5343
+dac 5321
+ose 5320
+ain 5312
+ext 5290
+niu 5289
+cit 5284
+pet 5281
+sim 5281
+ape 5280
+len 5278
+agi 5272
+ban 5272
+bel 5272
+mpe 5267
+rol 5256
+onf 5255
+_en 5251
+uta 5251
+eea 5250
+rt_ 5238
+ve_ 5238
+cet 5235
+pal 5230
+cad 5218
+pus 5216
+as_ 5213
+_ri 5208
+_ab 5196
+iaţ 5196
+cas 5194
+ldo 5193
+onu 5182
+siu 5169
+_l_ 5160
+mea 5155
+gal 5154
+rmi 5149
+_d_ 5145
+ruc 5135
+sud 5130
+nou 5128
+via 5118
+mir 5117
+am_ 5113
+rtu 5095
+nez 5090
+_th 5075
+ptu 5075
+_ho 5074
+dir 5074
+uşi 5065
+vă_ 5053
+nge 5041
+eat 5030
+nse 5030
+ule 5017
+rsi 5016
+cei 4994
+pos 4987
+li_ 4983
+lti 4973
+dur 4966
+tab 4964
+ple 4956
+alb 4954

Propchange: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/ro.ngp
------------------------------------------------------------------------------
    svn:executable = *

Added: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sk.ngp
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sk.ngp?rev=1181278&view=auto
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sk.ngp (added)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sk.ngp Mon Oct 10 22:25:53 2011
@@ -0,0 +1,1001 @@
+# NgramProfile generated at Wed Jun 08 15:10:08 PDT 2011 for Nutch Language Identification
+_pr 155897
+_po 137147
+_na 121520
+ch_ 116648
+_a_ 113592
+_v_ 111891
+na_ 91317
+om_ 89631
+_je 85847
+ej_ 81274
+_sa 79764
+ho_ 76408
+sa_ 74412
+je_ 71789
+_ro 71501
+ie_ 68043
+ova 64481
+ov_ 63563
+pre 62694
+ých 62491
+ku_ 59617
+tor 56395
+ne_ 56231
+_do 56170
+ia_ 51819
+_ob 50633
+_ne 49951
+ost 49668
+sta 48663
+_bo 48630
+_za 47920
+ou_ 47508
+kto 46980
+li_ 46972
+_st 46539
+né_ 45844
+la_ 45571
+nie 42336
+rok 42247
+to_ 41499
+_vy 40339
+bol 40215
+ko_ 39864
+pri 39599
+mi_ 39465
+ick 39399
+_ma 39211
+_kt 38807
+ého 38445
+al_ 36907
+ove 36896
+nsk 36874
+sti 36793
+_ko 36701
+_me 35723
+ky_ 35264
+van 35257
+str 34549
+ný_ 34542
+ka_ 34484
+lov 33726
+ani 33554
+nej 33137
+_sp 32541
+nov 32193
+_ve 32053
+oku 32041
+rov 31196
+val 30961
+lo_ 30783
+est 30773
+_ak 30008
+_od 29711
+pod 29618
+ali 29591
+_z_ 29143
+_vo 29126
+ti_ 28958
+kov 28917
+ako 28622
+_sl 27982
+eni 27515
+ná_ 27387
+ale 27291
+ast 27112
+ven 26964
+ol_ 26614
+_sú 26468
+sto 26243
+_te 26137
+eho 26093
+_to 25870
+_s_ 25732
+ým_ 25699
+red 25580
+ny_ 25518
+_kr 25224
+voj 25217
+nos 24871
+čas 24839
+ist 24693
+kon 24605
+slo 24576
+kej 24490
+men 24473
+va_ 24440
+_sv 24363
+_vý 24006
+_al 23634
+aj_ 23234
+_pa 23203
+cho 23096
+_ná 23064
+kom 23016
+och 22649
+ens 22498
+ran 22482
+že_ 22451
+do_ 22407
+sko 22197
+olo 21954
+rie 21845
+nýc 21748
+_mo 21706
+od_ 21560
+_aj 21552
+_ka 21397
+odn 21263
+pro 21257
+il_ 21221
+re_ 20805
+len 20695
+spo 20689
+_mi 20657
+_ni 20633
+ske 20477
+tov 20429
+_zá 20362
+vo_ 20310
+ent 20271
+oko 20266
+pol 20215
+edn 19959
+za_ 19816
+roz 19730
+ať_ 19717
+_re 19695
+ate 19638
+ovi 19395
+le_ 19235
+naj 19197
+pra 19125
+_ho 19120
+ci_ 19115
+sku 19100
+_ta 19024
+ich 18959
+de_ 18775
+dov 18361
+oli 18234
+ce_ 18126
+te_ 18101
+den 18010
+jú_ 17919
+ké_ 17915
+tvo 17913
+_tr 17899
+tic 17897
+lad 17806
+nia 17801
+ba_ 17779
+ach 17662
+dy_ 17569
+hod 17544
+sť_ 17509
+mu_ 17327
+_de 17298
+ter 17273
+_in 17196
+tom 17172
+tre 16933
+rod 16925
+uje 16923
+_le 16908
+ri_ 16860
+ta_ 16765
+tra 16747
+kla 16731
+dob 16721
+_že 16627
+ak_ 16608
+ria 16575
+_ch 16503
+ský 16443
+prí 16363
+ati 16354
+tro 16312
+dne 16226
+teľ 16223
+nom 16199
+ajú 16140
+ala 16133
+tav 16085
+_ce 16017
+_št 15873
+ili 15858
+ra_ 15837
+kýc 15807
+mie 15767
+áci 15740
+jed 15628
+ký_ 15578
+stv 15552
+ské 15524
+_no 15484
+ele 15482
+rav 15346
+ový 15340
+ami 15221
+ený 15196
+po_ 15019
+tie 14862
+zna 14852
+oro 14843
+rad 14777
+_ča 14773
+vie 14760
+tu_ 14748
+ní_ 14696
+ným 14673
+res 14626
+mes 14603
+pos 14525
+iac 14523
+_o_ 14521
+alo 14437
+néh 14435
+obe 14398
+_se 14288
+by_ 14202
+_vi 14193
+_so 14177
+ver 14165
+_ok 14068
+cký 14025
+rsk 13982
+_sk 13971
+veľ 13945
+kéh 13932
+iu_ 13903
+osť 13856
+ori 13773
+mer 13669
+iek 13635
+_si 13608
+ska 13575
+rom 13573
+orý 13571
+ola 13497
+tal 13458
+áln 13397
+_vš 13392
+eto 13392
+er_ 13380
+ká_ 13363
+_di 13353
+_ja 13342
+tri 13341
+ím_ 13337
+ovo 13295
+hov 13274
+ite 13215
+oré 13210
+ebo 13191
+lav 13191
+cie 13189
+kol 13160
+áva 13148
+mal 13111
+_pl 13095
+_os 12988
+_vz 12986
+ten 12941
+vod 12922
+ste 12848
+svo 12841
+nic 12836
+hra 12822
+jeh 12717
+cké 12707
+šie 12688
+eme 12680
+en_ 12648
+nik 12648
+ty_ 12647
+odo 12610
+ies 12593
+ené 12575
+ekt 12537
+oje 12519
+_dr 12512
+vor 12489
+_zo 12479
+ca_ 12427
+sú_ 12421
+_hr 12399
+las 12376
+ych 12326
+dno 12315
+ame 12249
+ádz 12247
+stu 12075
+pov 12062
+ene 12038
+ujú 12035
+ved 12029
+ré_ 12001
+eno 11965
+nes 11946
+era 11939
+ané 11908
+výc 11868
+dza 11857
+nu_ 11849
+prv 11822
+iel 11819
+iť_ 11807
+lne 11768
+me_ 11762
+_ži 11751
+chá 11736
+_an 11726
+_br 11651
+rat 11649
+da_ 11631
+okr 11629
+ren 11578
+med 11568
+tak 11554
+ové 11548
+cov 11490
+hla 11461
+ec_ 11424
+bra 11373
+lan 11353
+_k_ 11316
+prá 11222
+ve_ 11182
+_ra 11128
+ená 11116
+ret 11041
+ok_ 11000
+leb 10986
+vé_ 10975
+ero 10969
+dom 10959
+avi 10947
+sky 10834
+ern 10774
+lit 10730
+ave 10697
+júc 10691
+el_ 10666
+ení 10635
+kra 10624
+ore 10605
+ina 10573
+stn 10552
+eri 10538
+por 10515
+ii_ 10494
+_li 10493
+hor 10466
+nam 10413
+eli 10401
+_vl 10394
+očn 10394
+adn 10379
+tan 10374
+hád 10368
+aný 10367
+du_ 10307
+_ti 10297
+nou 10296
+bo_ 10285
+ans 10279
+_be 10247
+die 10221
+ými 10193
+_pe 10187
+poč 10177
+ade 10156
+ilo 10117
+ke_ 10113
+ede 10087
+cia 10081
+ry_ 10070
+ad_ 10066
+esk 10017
+ier 9992
+oto 9968
+ľa_ 9966
+vej 9880
+mba 9853
+áro 9848
+_hl 9817
+mat 9810
+oho 9802
+edz 9743
+vať 9707
+sla 9673
+_zn 9648
+rý_ 9640
+vá_ 9611
+nem 9607
+_ba 9545
+zem 9537
+iny 9531
+ovn 9514
+ráv 9493
+kre 9407
+_mb 9395
+sle 9364
+krá 9360
+nap 9344
+kým 9342
+nen 9338
+pom 9314
+dos 9298
+_zv 9283
+raj 9238
+poz 9207
+ric 9198
+edo 9133
+si_ 9116
+pla 9103
+via 9078
+pad 9043
+_bu 9027
+_by 9006
+_ke 8986
+sob 8973
+rne 8936
+tol 8888
+ová 8884
+obc 8864
+nú_ 8863
+ľov 8818
+dzi 8813
+_či 8794
+ejš 8772
+vat 8762
+vne 8760
+ník 8745
+nár 8733
+rob 8733
+ano 8723
+pot 8722
+_op 8704
+ách 8687
+čen 8684
+nto 8662
+hu_ 8654
+cha 8636
+es_ 8612
+eľk 8587
+eko 8579
+akt 8571
+ant 8544
+cke 8539
+dný 8518
+edi 8513
+_tu 8496
+obr 8495
+_ju 8464
+_má 8421
+eck 8398
+oby 8390
+vet 8371
+cel 8368
+ech 8342
+tup 8310
+ila 8306
+obn 8300
+ari 8256
+vý_ 8251
+_fi 8194
+aní 8182
+bec 8168
+ato 8160
+del 8124
+dia 8087
+lia 8084
+no_ 8078
+sve 8077
+ine 8066
+žen 8063
+čia 8062
+vsk 8040
+ovs 8036
+ada 8018
+odi 8004
+adi 8001
+zov 8001
+kou 7998
+iat 7992
+tel 7977
+din 7955
+man 7953
+and 7914
+vše 7912
+vys 7909
+_mu 7886
+ru_ 7885
+aro 7854
+iad 7851
+ane 7845
+led 7843
+eda 7833
+tat 7813
+ino 7811
+_ar 7805
+se_ 7784
+dru 7767
+rej 7763
+tar 7754
+sia 7728
+_dv 7720
+sov 7711
+ože 7709
+dné 7696
+rá_ 7671
+vin 7624
+udo 7620
+vom 7612
+stá 7596
+ado 7588
+isk 7555
+ode 7548
+osl 7542
+zač 7521
+_ci 7517
+per 7507
+zni 7476
+avn 7469
+bud 7468
+tva 7464
+ním 7457
+ere 7443
+us_ 7434
+tia 7427
+tsk 7404
+lin 7388
+_ri 7384
+kos 7381
+orá 7381
+nci 7372
+iet 7370
+rch 7365
+ole 7345
+anc 7339
+min 7317
+raz 7307
+rát 7253
+ezd 7249
+_sy 7240
+as_ 7236
+_pô 7222
+ora 7220
+ome 7219
+_ic 7217
+on_ 7204
+mov 7200
+vy_ 7189
+žia 7181
+for 7178
+elo 7173
+or_ 7162
+obi 7146
+rot 7137
+pou 7127
+vol 7104
+uto 7098
+avo 7083
+väč 7075
+äčš 7068
+vša 7053
+etk 7038
+oti 7032
+tát 7032
+ruh 6996
+šak 6970
+ek_ 6968
+obl 6956
+ská 6945
+lu_ 6934
+_fr 6933
+až_ 6922
+met 6919
+íva 6918
+lož 6909
+emi 6907
+orm 6905
+ien 6889
+tne 6878
+pok 6875
+lic 6864
+_ku 6832
+ivo 6832
+ava 6826
+mno 6810
+atr 6806
+spr 6804
+zi_ 6799
+zal 6798
+ber 6787
+ete 6786
+apr 6784
+lat 6777
+_až 6774
+eľo 6768
+iti 6760
+cen 6759
+nám 6743
+ied 6738
+šet 6728
+jej 6723
+tok 6721
+_čl 6715
+_už 6705
+_fa 6704
+_tv 6695
+_če 6695
+lie 6691
+par 6679
+ozo 6668
+_vr 6666
+rí_ 6650
+odu 6629
+ice 6619
+nut 6615
+tin 6611
+_or 6607
+ela 6604
+ni_ 6601
+orn 6591
+ris 6584
+ín_ 6576
+ly_ 6575
+ouž 6561
+ozn 6561
+omo 6547
+amo 6544
+úci 6538
+dal 6511
+isl 6488
+enc 6487
+_ab 6485
+mor 6483
+vi_ 6481
+_lo 6479
+ici 6474
+tej 6469
+tik 6456
+lom 6439
+yst 6431
+ian 6426
+pat 6420
+ril 6400
+_da 6397
+rac 6388
+trá 6379
+rýc 6366
+žív 6361
+em_ 6360
+ara 6356
+iná 6352
+ide 6326
+úča 6268
+am_ 6267
+uží 6262
+_zm 6231
+gra 6220
+zák 6217
+_ľu 6210
+nac 6184
+obo 6178
+ed_ 6169
+ram 6169
+rak 6163
+čný 6161
+ďal 6147
+rác 6144
+dok 6125
+vil 6125
+eve 6119
+jen 6115
+zná 6112
+vu_ 6108
+ích 6096
+olu 6085
+túr 6084
+les 6079
+ust 6072
+tí_ 6064
+má_ 6041
+jav 6040
+ner 6016
+ež_ 6006
+nad 6005
+ros 5996
+dan 5994
+so_ 5984
+áto 5981
+už_ 5969
+bli 5966
+_gr 5964
+bor 5960
+rit 5950
+čin 5934
+čne 5934
+rev 5913
+rem 5893
+asť 5886
+iez 5871
+iko 5860
+žit 5858
+pis 5854
+vlá 5854
+vla 5841
+atk 5837
+ini 5804
+mar 5794
+keď 5791
+tív 5789
+aná 5786
+_bi 5782
+dol 5779
+_ru 5775
+nep 5767
+_as 5761
+_čo 5760
+ana 5759
+uho 5756
+roj 5754
+kal 5753
+aci 5752
+_kl 5749
+spe 5749
+poj 5745
+_ha 5736
+eti 5733
+not 5732
+_mn 5726
+mož 5704
+_sm 5697
+los 5677
+ačn 5645
+eď_ 5637
+ika 5635
+art 5633
+ona 5631
+ľud 5618
+tis 5606
+nil 5601
+_ex 5599
+kat 5599
+pan 5597
+dvo 5554
+asn 5553
+etr 5544
+_hi 5542
+_tý 5530
+sil 5513
+fil 5502
+_i_ 5501
+ojn 5488
+kú_ 5478
+an_ 5475
+lek 5470
+čo_ 5465
+kup 5456
+my_ 5451
+_zl 5442
+tný 5442
+_la 5439
+ral 5439
+hol 5433
+níc 5433
+_ze 5426
+živ 5416
+fra 5411
+lád 5409
+nan 5406
+neh 5405
+reb 5396
+nyc 5391
+vyš 5390
+oni 5362
+dľa 5361
+ica 5356
+nti 5349
+_ďa 5342
+mic 5333
+_us 5330
+kul 5325
+jši 5324
+ívn 5305
+ožn 5304
+vid 5303
+obj 5300
+hvi 5289
+ese 5287
+ľad 5284
+lik 5280
+ito 5275
+ces 5274
+vov 5274
+inu 5272
+uni 5272
+_au 5270
+štá 5267
+rán 5266
+iež 5263
+kor 5251
+toč 5230
+čov 5230
+žil 5230
+ýva 5228
+cky 5223
+_fo 5211
+rep 5211
+tky 5199
+zo_ 5194
+cko 5184
+nte 5165
+pís 5165
+maj 5164
+odp 5164
+orí 5159
+pôs 5157
+ajv 5146
+čné 5144
+eži 5140
+um_ 5132
+ôso 5125
+ško 5116
+asi 5107
+erá 5104
+nal 5099
+noh 5098
+ha_ 5083
+vaj 5074
+vzn 5061
+ors 5059
+dis 5056
+kam 5036
+odľ 5020
+ojo 5019
+_vä 5013
+súč 5012
+int 5004
+ma_ 5003
+čno 4994
+_um 4993
+dpo 4983
+ciu 4974
+rel 4972
+ono 4971
+tné 4969
+môž 4966
+ápa 4962
+edy 4956
+ras 4950
+kci 4944
+roc 4943
+_he 4941
+zor 4938
+koc 4925
+záp 4923
+_hu 4913
+esi 4897
+oru 4874
+mus 4869
+_hv 4862
+nka 4860
+poh 4860
+eta 4857
+_ot 4856
+bez 4854
+be_ 4846
+kar 4843
+dst 4814
+náz 4814
+ľko 4814
+_rí 4799
+nak 4799
+sad 4798
+uch 4797
+tál 4791
+sam 4790
+oci 4786
+ému 4780
+ôvo 4779
+_su 4778
+kôr 4775
+tur 4774
+dro 4752
+ôr_ 4750
+lis 4747
+_ge 4737
+vek 4729
+iál 4726
+vým 4725
+hy_ 4709
+moc 4699
+ont 4699
+ovc 4675
+tým 4673
+rál 4665
+oča 4663
+bil 4656
+rst 4655
+ted 4655
+ena 4654
+aco 4648
+omi 4641
+jaz 4639
+oji 4636
+úze 4632
+che 4628
+_šk 4627
+nač 4627
+ron 4622
+hrá 4610
+ší_ 4599
+šte 4598
+arc 4597
+_zd 4596
+aji 4596
+omu 4581
+he_ 4579
+epo 4576
+ráľ 4574
+bla 4572
+ača 4569
+skô 4568
+iar 4567
+šíc 4567
+bie 4563
+árn 4563
+nas 4553
+jov 4550
+_mô 4546
+ík_ 4544
+vot 4540
+aby 4537
+ita 4536
+kan 4533
+ote 4533
+mos 4532
+iky 4530
+_kd 4529
+izm 4524
+iku 4503
+_dn 4498
+čši 4483
+epr 4481
+dil 4466
+ult 4461
+_sc 4455
+olí 4449
+til 4449
+upi 4447
+sch 4439
+ja_ 4435
+Å¥ou 4433
+ang 4429
+let 4426
+kde 4424
+sne 4422
+íci 4421
+mec 4420
+výs 4402
+oži 4398
+rez 4391
+_dô 4390
+vit 4386
+_zr 4385
+nit 4376
+eľm 4370
+_úz 4369
+zen 4362
+hľa 4361
+ákl 4352
+iká 4345
+árs 4342
+com 4333
+onc 4325
+liv 4321

Propchange: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sk.ngp
------------------------------------------------------------------------------
    svn:executable = *

Added: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sl.ngp
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sl.ngp?rev=1181278&view=auto
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sl.ngp (added)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sl.ngp Mon Oct 10 22:25:53 2011
@@ -0,0 +1,1001 @@
+# NgramProfile generated at Wed Jun 08 15:10:56 PDT 2011 for Nutch Language Identification
+je_ 254248
+_je 175460
+_po 157653
+_pr 153889
+_na 146947
+na_ 123177
+in_ 113877
+_in 113626
+_za 108679
+_v_ 105174
+ih_ 97106
+ki_ 92808
+no_ 86653
+ja_ 85091
+_se 77030
+ni_ 76362
+ta_ 74384
+ne_ 71570
+_so 69646
+pre 69178
+ko_ 68876
+ga_ 63773
+li_ 61861
+_ko 61274
+em_ 61169
+jo_ 60836
+_le 60552
+sta 59864
+se_ 58235
+ost 57799
+so_ 56906
+ti_ 56256
+nje 54926
+la_ 53616
+let 52995
+ke_ 52660
+_ka 52035
+_ki 51309
+pri 51232
+_bi 51020
+_iz 50936
+ega 50289
+anj 49748
+_te 48980
+_do 46792
+di_ 44935
+_ve 44305
+_me 44109
+ka_ 44005
+il_ 43393
+_pa 42651
+bil 42312
+_ra 42223
+_ne 42023
+_ob 41725
+ali 41722
+_st 41402
+red 40850
+ija 40419
+_ta 40073
+eta 39957
+za_ 39902
+ov_ 39794
+ate 39283
+da_ 38884
+_de 38825
+er_ 37691
+al_ 37578
+ski 36890
+sti 36831
+_da 36544
+_od 36507
+del 36116
+lo_ 35619
+ove 34994
+ske 34973
+ter 34840
+raz 34746
+ova 34441
+nsk 34339
+ma_ 34279
+udi 33094
+nih 32076
+jen 32003
+lov 31555
+voj 31522
+nik 31499
+ji_ 31310
+ran 31287
+_ma 31099
+jem 30990
+nov 30857
+to_ 30412
+kat 30212
+_tu 30092
+eni 29985
+ori 29808
+men 29725
+sto 29672
+rij 29321
+_dr 29243
+pa_ 29163
+lje 28994
+str 28868
+en_ 28448
+_mo 28431
+lja 28205
+pos 28096
+_z_ 27873
+ani 27817
+_vo 27719
+rav 27380
+eli 27363
+pro 27329
+tud 26854
+ri_ 26093
+est 26042
+_re 25787
+lik 25711
+val 25540
+ego 25498
+nos 25415
+ist 24943
+ije 24902
+pod 24852
+_sl 24764
+sko 24588
+ila 24560
+_sv 24431
+van 24302
+_sp 24297
+va_ 24237
+ovi 24198
+ven 24181
+kov 24047
+por 23836
+ed_ 23644
+mi_ 23615
+el_ 23524
+zna 23509
+ičn 23399
+tem 23226
+ati 23225
+od_ 23218
+eno 23180
+pol 23079
+aj_ 23043
+ast 22905
+ili 22787
+tal 22700
+_kr 22621
+ime 22571
+le_ 22519
+po_ 22482
+eri 22230
+ju_ 22174
+om_ 22160
+med 22136
+avi 22104
+ora 22081
+_bo 22028
+naj 22023
+ot_ 21923
+elo 21921
+ema 21917
+lju 21876
+vo_ 21876
+_im 21781
+_nj 21706
+ve_ 21647
+pra 21642
+iko 21561
+lan 21521
+kot 21494
+nja 21463
+dru 21355
+ijo 21284
+gor 21263
+cij 21189
+teg 21149
+_to 21118
+_s_ 21054
+oli 21053
+vil 21011
+ene 20912
+vi_ 20900
+_tr 20846
+gra 20754
+jsk 20669
+tra 20502
+_la 20379
+ako 20315
+ena 20188
+_al 20104
+kih 20002
+kra 19922
+tan 19741
+elj 19717
+_si 19625
+_sk 19592
+edn 19589
+rad 19556
+_sa 19404
+ina 19337
+_ni 19252
+več 19104
+aje 19061
+slo 18658
+st_ 18647
+ral 18640
+nem 18521
+vel 18450
+im_ 18442
+jan 18400
+rat 18361
+ele 18351
+ev_ 18310
+mer 18285
+_vs 18048
+an_ 17950
+aln 17831
+_us 17830
+do_ 17794
+ajo 17770
+ala 17748
+jih 17579
+gov 17521
+ste 17511
+ska 17474
+ilo 17404
+neg 17379
+ika 17266
+ans 17152
+_en 17109
+nji 17030
+stv 16891
+eva 16874
+ira 16860
+_no 16825
+uje 16698
+ik_ 16558
+ome 16536
+te_ 16499
+tev 16473
+adi 16453
+olj 16392
+ar_ 16280
+kon 16213
+avn 16170
+vlj 16028
+ine 16020
+ane 16006
+tni 15839
+iti 15832
+ra_ 15796
+pov 15773
+ana 15735
+enj 15733
+iz_ 15711
+jev 15673
+_ce 15604
+tov 15518
+mo_ 15463
+ara 15442
+ato 15430
+tak 15418
+ank 15343
+edi 15339
+nas 15262
+tro 15252
+_os 15220
+odn 15154
+ame 15153
+čin 15104
+zaj 15089
+_čl 14978
+pom 14862
+_gl 14758
+las 14724
+aja 14713
+ovo 14692
+_o_ 14611
+olo 14555
+tav 14517
+vet 14495
+ano 14387
+_ga 14342
+iji 14320
+ini 14240
+imi 14231
+ca_ 14221
+iki 14210
+ent 14180
+tor 14180
+ogo 14169
+vni 14162
+aci 14114
+_ro 14109
+dob 14102
+ela 14020
+prv 13986
+čni 13940
+tre 13907
+_vi 13899
+svo 13875
+lni 13847
+vse 13810
+_up 13796
+še_ 13782
+_št 13712
+evi 13671
+eti 13669
+_gr 13647
+dno 13579
+nij 13550
+gla 13491
+nim 13473
+_mi 13429
+dni 13314
+oma 13289
+bi_ 13273
+ite 13266
+ari 13239
+jeg 13230
+ver 13226
+rug 13224
+nan 13126
+ede 13113
+ovn 13029
+ust 13013
+sve 12956
+ino 12871
+odo 12864
+ce_ 12845
+mes 12838
+led 12830
+rsk 12823
+nar 12810
+man 12806
+nam 12768
+tri 12761
+_pe 12712
+rej 12706
+_br 12660
+čla 12632
+rje 12616
+pot 12615
+de_ 12604
+ava 12598
+lad 12591
+dal 12536
+_go 12514
+_zn 12487
+_lj 12468
+met 12403
+ah_ 12402
+etn 12318
+re_ 12314
+eka 12311
+rab 12302
+alo 12278
+mor 12241
+ens 12239
+nek 12227
+on_ 12225
+raj 12191
+keg 12186
+eje 12182
+kol 12152
+rem 12080
+blj 12075
+_še 12003
+odi 12000
+eto 11986
+_vr 11968
+ita 11907
+tu_ 11905
+upo 11885
+ose 11836
+_pl 11830
+rja 11818
+ški 11732
+ojn 11718
+rod 11693
+dan 11674
+ica 11590
+avl 11535
+bol 11509
+bli 11497
+am_ 11491
+tel 11456
+kar 11449
+_be 11446
+pis 11401
+rim 11394
+čas 11379
+ale 11378
+če_ 11318
+nic 11300
+spo 11295
+eve 11294
+_op 11285
+jal 11282
+eda 11239
+mu_ 11236
+oko 11221
+lin 11215
+alj 11191
+ima 11161
+išk 11151
+vno 11148
+ole 11129
+_an 11122
+bra 11115
+oto 11086
+kem 11068
+ci_ 11061
+lav 11056
+eme 11036
+vod 11027
+oda 11020
+rni 10998
+arj 10997
+sku 10965
+tič 10955
+ada 10939
+_ba 10931
+dov 10926
+dnj 10923
+tno 10871
+čne 10835
+or_ 10833
+vez 10809
+mat 10732
+es_ 10699
+oje 10699
+lj_ 10655
+lah 10616
+nej 10592
+dar 10557
+šte 10546
+ave 10545
+amo 10487
+čno 10478
+sam 10431
+dil 10388
+ore 10383
+ese 10375
+rit 10311
+ice 10305
+ijs 10303
+era 10287
+spr 10138
+oči 10116
+_di 10086
+ved 10063
+_ja 10059
+kom 9989
+vin 9947
+_ok 9943
+ške 9940
+ško 9940
+top 9926
+sed 9914
+ami 9896
+ins 9864
+ače 9858
+var 9844
+ezn 9839
+obl 9818
+gle 9817
+_ju 9811
+hod 9777
+oja 9739
+dol 9734
+ris 9732
+et_ 9730
+ike 9713
+iva 9702
+kri 9688
+čen 9661
+jav 9634
+kup 9603
+nal 9602
+_že 9591
+nke 9554
+ode 9554
+ote 9508
+ahk 9499
+oro 9471
+ere 9380
+ek_ 9369
+sre 9355
+ren 9335
+_jo 9327
+nap 9263
+hko 9256
+ej_ 9246
+obi 9240
+lij 9199
+_fr 9146
+ono 9137
+_fi 9097
+_ča 9095
+log 9095
+seb 9086
+lji 9074
+bo_ 9025
+and 9015
+ona 8967
+ejo 8935
+anc 8915
+tar 8880
+nad 8879
+drž 8866
+stn 8854
+_zg 8845
+_ze 8836
+eč_ 8814
+nač 8807
+rst 8784
+ant 8759
+den 8756
+ros 8728
+tek 8721
+per 8716
+ro_ 8699
+mar 8691
+živ 8684
+nom 8675
+tur 8659
+adn 8658
+ril 8626
+_dv 8608
+res 8581
+pad 8522
+aro 8460
+ici 8429
+rek 8426
+nju 8419
+_zd 8415
+jud 8405
+_sr 8391
+rža 8375
+zar 8372
+_oz 8368
+nes 8360
+_ji 8352
+išč 8352
+sa_ 8341
+oti 8338
+lit 8337
+si_ 8335
+ete 8333
+ern 8330
+žav 8305
+tvo 8291
+omo 8272
+zem 8272
+obr 8256
+rep 8252
+_lo 8246
+_ti 8218
+ekt 8218
+_pi 8183
+_va 8164
+ozn 8144
+_li 8137
+_ar 8136
+dij 8116
+nav 8079
+rot 8076
+iln 8064
+ku_ 8060
+rom 8059
+ejš 8058
+_če 8056
+rev 8023
+tva 8011
+zap 8008
+rov 7977
+at_ 7961
+ij_ 7959
+oji 7947
+sno 7937
+isa 7920
+vne 7912
+dne 7906
+ben 7887
+be_ 7881
+oni 7850
+žen 7843
+reb 7838
+moč 7828
+emi 7815
+lno 7800
+sla 7800
+roč 7787
+čil 7763
+spe 7726
+sem 7714
+zve 7713
+jub 7702
+erj 7672
+me_ 7666
+nil 7655
+_or 7603
+nat 7593
+zač 7586
+msk 7547
+lič 7545
+iso 7536
+ubl 7500
+god 7459
+oče 7457
+eh_ 7450
+opi 7440
+azl 7437
+_ži 7431
+_hi 7419
+kor 7400
+otr 7391
+osl 7382
+tih 7354
+kan 7350
+eds 7330
+mel 7319
+emo 7315
+par 7311
+nda 7307
+izv 7305
+tne 7274
+oka 7241
+lek 7237
+dst 7228
+ruž 7191
+ade 7188
+min 7184
+fra 7182
+gos 7175
+plo 7174
+_vz 7150
+vor 7149
+ss_ 7119
+kal 7110
+zgo 7088
+ogr 7087
+riš 7081
+ec_ 7080
+orj 7080
+orn 7076
+_um 7064
+apo 7018
+rvi 7005
+_zv 6991
+ata 6978
+uni 6968
+cel 6965
+že_ 6960
+ram 6958
+izi 6934
+ero 6917
+lu_ 6909
+ge_ 6907
+arn 6878
+azi 6877
+ars 6868
+zel 6844
+nst 6835
+daj 6826
+ive 6818
+lne 6814
+pog 6807
+jer 6801
+tik 6799
+niš 6784
+zli 6777
+emb 6767
+nis 6755
+ron 6754
+poz 6750
+aka 6746
+loč 6743
+ret 6739
+rno 6738
+etu 6736
+go_ 6728
+tol 6706
+rne 6701
+nci 6699
+ča_ 6693
+isk 6687
+jši 6687
+sle 6632
+sil 6630
+avo 6615
+ba_ 6588
+ile 6588
+uss 6588
+sod 6584
+šči 6583
+bor 6581
+ner 6581
+ašk 6577
+mal 6565
+nce 6557
+_ri 6546
+mlj 6541
+tin 6533
+_kl 6530
+_ke 6528
+pla 6515
+jaj 6512
+ion 6510
+_sm 6507
+eza 6496
+are 6495
+_ge 6472
+ten 6469
+sov 6465
+ozi 6444
+dra 6437
+sel 6432
+sne 6429
+tve 6385
+zda 6368
+rog 6358
+du_ 6338
+rez 6337
+odp 6323
+zra 6322
+asn 6320
+otn 6319
+sli 6317
+eko 6316
+gan 6305
+_mu 6297
+abl 6296
+_am 6272
+itv 6254
+gij 6240
+ope 6228
+end 6218
+av_ 6214
+not 6200
+ang 6198
+ton 6195
+zij 6186
+kje 6185
+_av 6176
+bno 6167
+opa 6163
+cer 6161
+šče 6139
+ugi 6138
+kla 6137
+igr 6136
+obe 6128
+ide 6122
+obn 6121
+rop 6120
+dom 6119
+kaj 6100
+emu 6088
+ber 6084
+vit 6082
+ak_ 6067
+tom 6058
+jet 6051
+rva 6018
+jni 6006
+_kj 6003
+_el 6002
+ons 5999
+ob_ 5973
+čel 5971
+nak 5963
+nu_ 5957
+reg 5934
+les 5933
+zni 5924
+lic 5917
+kro 5908
+din 5907
+_ig 5900
+_ur 5897
+maj 5890
+asi 5882
+mem 5876
+zan 5864
+_ha 5854
+jno 5842
+enc 5823
+gen 5816
+len 5812
+ad_ 5805
+pin 5798
+eči 5787
+opo 5780
+hov 5779
+kim 5767
+rih 5765
+nte 5760
+eml 5758
+okr 5755
+nti 5731
+art 5725
+očj 5713
+pon 5703
+tis 5690
+taj 5679
+co_ 5661
+šča 5649
+dat 5632
+su_ 5627
+gi_ 5593
+naš 5591
+ogi 5587
+tiv 5587
+ivi 5578
+zav 5555
+net 5552
+cev 5546
+rin 5544
+ezi 5540
+ase 5536
+rik 5517
+lem 5513
+rip 5507
+zad 5505
+obo 5487
+niz 5485
+_ev 5474
+nta 5468
+sev 5454
+mno 5447
+esa 5427
+bni 5418
+odr 5414
+jez 5409
+mag 5407
+rič 5407
+vol 5406
+omi 5381
+jej 5369
+nit 5360
+una 5360
+vih 5354
+klj 5344
+asl 5343
+ači 5343
+upi 5339
+lom 5335
+či_ 5323
+san 5322
+ado 5308
+rok 5303
+sni 5303
+nog 5301
+ečj 5292
+rti 5285
+ses 5281
+ugo 5279
+til 5270
+bri 5262
+ume 5262
+ogl 5260
+epr 5245
+čan 5239
+leg 5227
+tok 5221
+alc 5216
+ešk 5215
+iri 5212
+pet 5212
+as_ 5205
+ru_ 5205
+reč 5199
+vaj 5176
+zik 5174
+zat 5170
+ple 5169
+_he 5160
+osk 5159
+oln 5152
+_vl 5145
+bel 5145
+son 5135
+zvo 5132
+onc 5130
+bit 5129
+zdr 5121
+tsk 5107
+vij 5101
+vir 5097
+dos 5095
+iza 5095
+imo 5089
+rel 5075
+rač 5050
+očn 5049
+ška 5048
+ard 5046
+azv 5044
+api 5027
+ši_ 5020
+žno 5019
+lat 5015
+bre 5014
+eja 5007
+esn 4997
+for 4975
+gre 4969
+vis 4969
+vid 4956
+etr 4949
+oča 4948
+dro 4947
+izr 4945
+ivn 4940
+zah 4931
+lsk 4928
+kaz 4921
+jim 4906
+vla 4892
+etj 4879
+pok 4878
+vrs 4868
+_is 4866
+rid 4861
+ker 4860
+ebn 4856
+boj 4855
+rib 4853
+lko 4839
+nič 4832
+bar 4817
+vsa 4803
+oj_ 4800
+is_ 4796
+ure 4795
+onč 4792
+rak 4789
+cen 4788
+saj 4750
+zde 4747
+rob 4738
+ito 4736
+vsk 4736
+loš 4731
+ial 4723
+žel 4719
+rož 4716
+pop 4712
+vna 4707
+čet 4700
+_un 4689
+gal 4688
+uži 4683
+evr 4680
+vro 4676
+ras 4674
+ico 4671
+zas 4664
+abi 4655
+obs 4644
+ing 4640
+org 4634
+jst 4633
+_ca 4628
+_mn 4615
+kop 4590
+čev 4570
+ago 4560
+rna 4556
+enu 4554
+opr 4549
+tru 4549
+_co 4548
+ces 4542
+_ru 4535
+_wi 4523
+_bl 4513
+elu 4508
+_ot 4501
+rma 4501
+izm 4489
+_ku 4484
+aga 4469
+mon 4454
+zal 4450
+zme 4443
+_fo 4439
+nj_ 4422
+mov 4419
+izd 4417
+oga 4417
+zvi 4405
+ojs 4403
+poj 4402

Propchange: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/sl.ngp
------------------------------------------------------------------------------
    svn:executable = *

Modified: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/tika.language.properties
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/language/tika.language.properties?rev=1181278&r1=1181277&r2=1181278&view=diff
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/language/tika.language.properties (original)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/language/tika.language.properties Mon Oct 10 22:25:53 2011
@@ -23,17 +23,21 @@
 # If there exists an ISO 639-1 2-letter code it should be used
 # If not, you can choose an ISO 639-2 3-letter code
 # See http://www.loc.gov/standards/iso639-2/php/code_list.php
-languages=da,de,et,el,en,es,fi,fr,hu,is,it,lt,nl,no,pl,pt,ru,sv,th
+languages=be,ca,da,de,eo,et,el,en,es,fi,fr,gl,hu,is,it,lt,nl,no,pl,pt,ro,ru,sk,sl,sv,th,uk
 
 # List of language names in english
+name.be=Belarusian
+name.ca=Catalan
 name.da=Danish
 name.de=German
+name.eo=Esperanto
 name.et=Estonian
 name.el=Greek
 name.en=English
 name.es=Spanish
 name.fi=Finnish
 name.fr=French
+name.gl=Galician
 name.hu=Hungarian
 name.is=Icelandic
 name.it=Italian
@@ -42,6 +46,10 @@ name.nl=Dutch
 name.no=Norwegian
 name.pl=Polish
 name.pt=Portuguese
+name.ro=Romanian
 name.ru=Russian
+name.sk=Slovakian
+name.sl=Slovenian
 name.sv=Swedish
-name.th=Thai
\ No newline at end of file
+name.th=Thai
+name.uk=Ukrainian