RubyGems - scylla - Versions diffs - 0.9.3 → 1.0.0 - Mend

scylla 0.9.3 → 1.0.0

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 (79) hide show

data/lib/scylla/lms/arabic.lm +399 -399
data/lib/scylla/lms/bulgarian.lm +400 -400
data/lib/scylla/lms/catalan.lm +323 -323
data/lib/scylla/lms/chinese.lm +389 -389
data/lib/scylla/lms/czech.lm +377 -377
data/lib/scylla/lms/danish.lm +383 -383
data/lib/scylla/lms/dutch.lm +398 -398
data/lib/scylla/lms/english.lm +355 -355
data/lib/scylla/lms/finnish.lm +381 -381
data/lib/scylla/lms/french.lm +379 -379
data/lib/scylla/lms/german.lm +382 -382
data/lib/scylla/lms/greek.lm +400 -400
data/lib/scylla/lms/hebrew.lm +400 -400
data/lib/scylla/lms/hindi.lm +400 -400
data/lib/scylla/lms/icelandic.lm +219 -219
data/lib/scylla/lms/indonesian.lm +364 -364
data/lib/scylla/lms/italian.lm +381 -381
data/lib/scylla/lms/japanese.lm +400 -400
data/lib/scylla/lms/kannada.lm +392 -392
data/lib/scylla/lms/korean.lm +389 -389
data/lib/scylla/lms/marathi.lm +364 -364
data/lib/scylla/lms/norwegian.lm +325 -325
data/lib/scylla/lms/persian.lm +397 -397
data/lib/scylla/lms/polish.lm +380 -380
data/lib/scylla/lms/portuguese.lm +375 -375
data/lib/scylla/lms/romanian.lm +318 -318
data/lib/scylla/lms/russian.lm +398 -398
data/lib/scylla/lms/slovak.lm +358 -358
data/lib/scylla/lms/slovenian.lm +256 -256
data/lib/scylla/lms/spanish.lm +353 -353
data/lib/scylla/lms/swedish.lm +400 -400
data/lib/scylla/lms/tagalog.lm +245 -245
data/lib/scylla/lms/thai.lm +400 -400
data/lib/scylla/lms/turkish.lm +379 -379
data/lib/scylla/lms/vietnamese.lm +373 -373
data/lib/scylla/lms/welsh.lm +293 -293
data/test/classifier_test.rb +5 -3
data/test/fixtures/lms/arabic.lm +400 -0
data/test/fixtures/lms/bulgarian.lm +400 -0
data/test/fixtures/lms/catalan.lm +400 -0
data/test/fixtures/lms/chinese.lm +400 -0
data/test/fixtures/lms/czech.lm +400 -0
data/test/fixtures/lms/danish.lm +399 -399
data/test/fixtures/lms/dutch.lm +400 -0
data/test/fixtures/lms/english.lm +400 -400
data/test/fixtures/lms/finnish.lm +400 -0
data/test/fixtures/lms/french.lm +397 -397
data/test/fixtures/lms/german.lm +400 -400
data/test/fixtures/lms/greek.lm +400 -0
data/test/fixtures/lms/hebrew.lm +400 -0
data/test/fixtures/lms/hindi.lm +400 -400
data/test/fixtures/lms/icelandic.lm +400 -0
data/test/fixtures/lms/indonesian.lm +400 -0
data/test/fixtures/lms/italian.lm +400 -400
data/test/fixtures/lms/japanese.lm +400 -400
data/test/fixtures/lms/kannada.lm +400 -0
data/test/fixtures/lms/korean.lm +400 -0
data/test/fixtures/lms/marathi.lm +400 -0
data/test/fixtures/lms/norwegian.lm +399 -399
data/test/fixtures/lms/persian.lm +400 -0
data/test/fixtures/lms/polish.lm +400 -0
data/test/fixtures/lms/portuguese.lm +400 -0
data/test/fixtures/lms/romanian.lm +400 -0
data/test/fixtures/lms/russian.lm +400 -0
data/test/fixtures/lms/slovak.lm +400 -0
data/test/fixtures/lms/slovenian.lm +400 -0
data/test/fixtures/lms/spanish.lm +400 -400
data/test/fixtures/lms/swedish.lm +400 -0
data/test/fixtures/lms/tagalog.lm +400 -0
data/test/fixtures/lms/thai.lm +400 -0
data/test/fixtures/lms/turkish.lm +400 -0
data/test/fixtures/lms/vietnamese.lm +400 -0
data/test/fixtures/lms/welsh.lm +400 -0
data/test/fixtures/test_languages/japanese +149 -67
data/test/generator_test.rb +1 -43
data/test/language_test.rb +5 -1
data/test/loader_test.rb +1 -1
data/test/scylla_test.rb +4 -4
metadata +105 -63

data/test/fixtures/lms/slovenian.lm ADDED Viewed

@@ -0,0 +1,400 @@
+_	1600
+a	446
+e	430
+i	393
+o	380
+n	325
+v	261
+s	260
+r	232
+l	212
+j	199
+a_	192
+t	169
+d	164
+p	140
+e_	132
+i_	122
+_s	121
+k	119
+m	103
+_p	98
+z	95
+je	92
+o_	81
+u	81
+na	75
+ov	74
+ni	73
+_n	72
+st	72
+je_	67
+_v	64
+ve	63
+en	63
+g	60
+ra	59
+_i	55
+b	55
+_j	54
+pr	54
+_d	53
+in	53
+v_	52
+_na	50
+lo	48
+_pr	46
+n_	46
+_o	46
+na_	45
+_je	44
+sk	44
+po	44
+č	44
+sl	42
+la	42
+ne	41
+no	41
+_v_	40
+lov	39
+š	38
+_po	38
+va	38
+os	37
+ro	37
+h	37
+_sl	37
+le	36
+li	36
+ja	36
+_in	36
+slo	36
+in_	36
+an	36
+_z	35
+ij	35
+av	35
+ven	33
+ove	33
+od	32
+vi	32
+ta	31
+el	31
+ž	31
+ed	31
+re	31
+ev	30
+eni	30
+t_	30
+de	29
+lj	29
+ki	29
+al	28
+ri	28
+ja_	28
+u_	27
+_r	27
+ost	26
+et	26
+se	26
+_k	26
+ti	26
+nij	25
+dn	25
+ni_	25
+h_	25
+ar	24
+vo	24
+em	24
+ih	23
+me	23
+ko	23
+ih_	23
+ad	23
+it	23
+ol	22
+aj	22
+ik	22
+_l	22
+m_	22
+la_	21
+ka	21
+za	21
+ob	21
+c	21
+raz	21
+az	21
+di	20
+del	20
+dr	20
+ki_	20
+no_	19
+nj	19
+om	19
+pre	19
+_se	19
+_ra	19
+ma	18
+to	18
+ji	18
+_le	18
+_za	18
+_g	18
+_m	18
+_t	18
+as	17
+ga	17
+let	17
+_ob	17
+er	17
+da	17
+ne_	17
+jo	16
+vn	16
+ija	16
+so	16
+_dr	16
+rs	16
+vr	16
+te	16
+_de	15
+ta_	15
+di_	15
+mo	15
+oč	15
+pro	15
+st_	15
+ga_	15
+ža	15
+red	15
+jo_	15
+or	15
+tv	15
+rž	14
+do	14
+žav	14
+im	14
+drž	14
+ke	14
+iv	14
+_so	14
+bl	14
+_u	14
+rža	14
+so_	13
+sta	13
+s_	13
+ova	13
+avn	13
+ns	13
+nsk	13
+ka_	13
+nos	13
+oz	13
+ju	13
+is	13
+il	13
+f	12
+ru	12
+va_	12
+lje	12
+val	12
+go	12
+sti	12
+eg	12
+ot	12
+ze	12
+_š	12
+pa	12
+ma_	12
+jen	12
+nje	12
+iz	12
+iva	11
+ti_	11
+d_	11
+ros	11
+_st	11
+kr	11
+sa	11
+bli	10
+op	10
+vi_	10
+elj	10
+ud	10
+pod	10
+li_	10
+_ne	10
+ske	10
+tu	10
+ir	10
+ski	10
+sto	10
+zem	10
+lja	10
+ega	10
+ej	10
+tr	10
+se_	10
+ic	10
+ič	10
+bi	10
+am	10
+ije	10
+r_	10
+kih	9
+či	9
+ji_	9
+iš	9
+_iz	9
+stv	9
+mi	9
+ča	9
+_oz	9
+pri	9
+ve_	9
+zn	9
+vl	9
+_a	9
+ge	9
+dan	9
+_e	9
+lik	9
+rad	9
+_ki	9
+_tu	9
+et_	9
+ovi	9
+_sk	9
+udi	9
+men	9
+ži	9
+em_	9
+og	9
+tud	8
+še	8
+ala	8
+ela	8
+k_	8
+pol	8
+ska	8
+dne	8
+nar	8
+nik	8
+edn	8
+tav	8
+ke_	8
+ajo	8
+_pa	8
+bo	8
+up	8
+dni	8
+ep	8
+eta	8
+iti	8
+ok	8
+zv	8
+es	8
+_s_	8
+_b	8
+gr	8
+pra	7
+pi	7
+rav	7
+van	7
+pu	7
+sv	7
+odn	7
+zg	7
+gl	7
+ši	7
+ur	7
+ani	7
+vni	7
+jih	7
+_me	7
+ez	7
+pa_	7
+eb	7
+zi	7
+čj	7
+aš	7
+iki	7
+j_	7
+ko_	7
+ars	7
+rst	7
+rsk	7
+anj	7
+ci	7
+pe	7
+ev_	7
+eno	7
+zd	7
+_da	7
+_do	7
+eo	7
+šč	7
+ogr	6
+tn	6
+ru_	6
+eve	6
+sr	6
+še_	6
+ava	6
+ak	6
+tvo	6
+iji	6
+eli	6
+ug	6
+_sv	6
+_ž	6
+jn	6
+ho	6
+ast	6
+du	6
+ave	6
+kra	6
+om_	6
+lad	6
+eds	6
+vo_	6
+ds	6
+at	6
+als	6
+ls	6
+_ka	6
+ver	6
+z_	6
+str	6
+rit	6
+gla	6
+nov	6
+ubl	6
+vro	6
+_bi	6
+ub	6
+sn	6
+sed	6
+_al	6
+eč	6
+ura	6
+sko	6
+kov	6
+obl	6
+št	6
+ml	6
+oze	6
+tev	6
+pov	6
+evi	6
+_ur	6
+ima	6
+ali	6
+oma	6
+čn	6
+gra	6
+ine	6
+_ni	6
+ede	6
+očj	5

data/test/fixtures/lms/spanish.lm CHANGED Viewed

@@ -1,400 +1,400 @@
-_	34626
-e	11141
-a	10911
-o	7205
-n	6456
-s	6294
-i	6242
-r	5717
-l	5323
-d	4722
-c	4125
-t	3987
-a_	3660
-e_	3082
-s_	2999
-u	2992
-�	2572
-p	2522
-de	2507
-_d	2443
-m	2383
-_e	2376
-o_	2213
-_de	2152
-n_	1888
-en	1833
-es	1771
-de_	1698
-_de_	1621
-_l	1599
-la	1570
-_c	1492
-l_	1375
-_p	1285
-os	1221
-_a	1212
-er	1197
-as	1140
-el	1135
-on	1125
-ci	1117
-os_	1093
-g	1078
-al	1059
-an	1056
-_la	1051
-co	1034
-ra	1021
-b	998
-_s	978
-la_	974
-te	956
-re	949
-nt	927
-ar	901
-el_	882
-ta	880
-as_	841
-ri	837
-ad	835
-or	832
-pa	817
-_la_	801
-ca	795
-_m	794
-es_	786
-v	779
-do	756
-�	756
-ó	755
-st	738
-ro	737
-_en	737
-_co	731
-na	727
-y	721
-en_	710
-f	710
-in	696
-ue	694
-_el	645
-lo	642
-ic	635
-_es	630
-da	627
-ia	621
-to	619
-_en_	609
-_el_	591
-y_	585
-r_	580
-un	563
-�	557
-_t	557
-í	557
-le	546
-ti	540
-no	540
-_y	535
-po	529
-se	523
-ent	521
-_y_	511
-ma	509
-_r	500
-io	495
-h	490
-�n	488
-ón	488
-i�	487
-_i	483
-tr	482
-a�	475
-sp	465
-do_	462
-is	461
-q	458
-con	457
-qu	457
-�n_	454
-ón_	454
-ñ	453
-�	453
-ac	439
-id	434
-ni	428
-ió	428
-om	425
-ne	422
-me	422
-al_	421
-si	421
-nte	415
-pr	415
-li	410
-nc	405
-nd	403
-ie	401
-_re	401
-añ	397
-_f	392
-te_	392
-á	391
-�	391
-_con	390
-ue_	387
-spa	380
-pa�	377
-que	375
-ión	373
-_h	369
-_se	367
-esp	365
-_po	363
-mi	363
-_pr	360
-di	357
-pe	355
-_lo	348
-ec	347
-_ca	346
-_u	344
-que_	336
-los	336
-rt	336
-los_	334
-mo	333
-_esp	331
-_o	328
-it	327
-_q	326
-_qu	326
-espa	319
-ia_	315
-pañ	315
-_que	314
-spa�	310
-_un	307
-ol	307
-su	303
-ce	301
-ci�	300
-aci	300
-ció	299
-ur	296
-ado	295
-est	293
-_los	289
-z	287
-ra_	286
-na_	285
-or_	282
-_n	281
-�a	278
-ña	278
-por	277
-on_	276
-_g	275
-del	271
-_v	271
-ica	271
-las	270
-_del	269
-_pa	269
-cia	267
-j	266
-las_	265
-tu	264
-del_	264
-am	262
-�	261
-é	261
-nci	260
-_a_	258
-nte_	257
-ña_	257
-�a_	257
-sta	254
-vi	253
-at	250
-ab	250
-ll	248
-to_	247
-so	247
-ía	243
-�a	243
-aña	243
-r�	240
-no_	240
-im	239
-cu	239
-da_	236
-_al	232
-sa	231
-em	229
-ns	228
-se_	227
-ant	226
-com	225
-_su	221
-ul	221
-ente	219
-tra	218
-rr	218
-_in	217
-ter	216
-il	215
-dad	215
-_com	215
-_las	214
-_por	212
-ca_	207
-ig	207
-d_	206
-ada	205
-m�	205
-va	204
-ba	204
-men	204
-era	202
-ran	201
-les	201
-ed	199
-ía_	196
-�a_	196
-ien	195
-_b	195
-res	195
-ha	194
-gu	191
-cio	190
-one	189
-ale	189
-ida	189
-t�	187
-des	187
-_ma	186
-bi	185
-ona	185
-les_	184
-oc	184
-ion	184
-br	183
-nes	183
-od	182
-pro	182
-x	179
-mu	179
-_si	179
-_est	178
-por_	178
-mo_	177
-ga	177
-_se_	177
-mp	177
-ist	176
-dos	175
-_pro	173
-aci�	173
-an_	173
-go	172
-nes_	172
-ct	172
-ado_	172
-ta_	171
-lo_	170
-_pe	169
-eg	167
-ero	165
-fi	165
-io_	165
-dos_	163
-iv	163
-�o	163
-ño	163
-op	162
-ment	161
-_ha	161
-za	161
-et	161
-ndo	159
-par	156
-ici	155
-ria	154
-ve	153
-ica_	153
-ron	152
-ad_	151
-fe	151
-ones	151
-año	150
-us	150
-uc	149
-_mi	149
-gr	149
-mb	149
-con_	148
-rio	147
-ncia	147
-sti	147
-ua	146
-ico	146
-_te	146
-rc	145
-art	144
-má	143
-cion	143
-tor	142
-esta	141
-ndo_	141
-ip	141
-cia_	141
-dad_	140
-ir	140
-ntr	140
-ob	140
-nto	139
-ori	139
-n�	138
-ó_	138
-�_	138
-co_	138
-ar_	138
-ante	138
-ot	138
-hi	136
-du	136
-bl	136
-ada_	135
-rm	134
-eri	134
-ro_	134
-err	134
-una	134
-ales	133
-rec	133
-nta	132
-per	131
-_me	130
-ita	129
-idad	129
-ara	129
-enc	129
-ina	128
-_di	128
-ial	128
-tan	127
-_par	127
-inc	127
-ido	127
-i_	125
-ura	125
-ut	123
-ana	123
-_ar	123
-uer	122
-uni	122
-_no	122
-pu	122
-ali	121
+_	28730
+e	9319
+a	8074
+o	5889
+n	5309
+s	5298
+i	4672
+r	4349
+l	4265
+d	3819
+t	3186
+c	3100
+a_	2764
+s_	2599
+e_	2560
+u	2374
+_e	2190
+de	2048
+_d	2014
+p	1986
+m	1873
+_de	1745
+o_	1729
+n_	1722
+en	1646
+es	1468
+_l	1453
+la	1334
+de_	1318
+l_	1220
+_c	1143
+os	1065
+_p	1060
+el	1057
+on	980
+_la	980
+_a	970
+er	960
+os_	955
+as	893
+co	891
+_s	884
+la_	859
+el_	859
+ci	829
+te	820
+re	804
+g	784
+nt	781
+an	741
+ra	736
+_en	726
+b	726
+al	719
+en_	706
+as_	691
+or	686
+y	682
+es_	678
+ta	667
+_co	663
+ad	653
+_el	650
+do	638
+pa	617
+ar	614
+ó	589
+ri	587
+_m	586
+ro	584
+st	573
+y_	572
+ue	557
+v	551
+in	551
+f	526
+_y	524
+na	520
+_es	520
+ca	520
+lo	518
+to	516
+_y_	510
+r_	490
+da	485
+un	483
+se	476
+_t	476
+no	457
+ent	455
+con	451
+ic	450
+po	432
+ia	425
+í	423
+ti	417
+_r	416
+io	408
+le	405
+tr	399
+do_	399
+qu	389
+q	389
+nte	375
+om	371
+si	367
+h	364
+te_	363
+ac	358
+me	355
+ón	353
+ie	352
+_re	352
+ue_	351
+is	351
+ió	345
+sp	344
+nd	343
+_se	341
+ma	336
+ñ	336
+pr	333
+_lo	331
+ón_	330
+que	329
+_i	326
+id	322
+ne	321
+al_	319
+mi	311
+_u	311
+añ	311
+_q	306
+_qu	306
+los	303
+_po	302
+ni	301
+di	300
+á	300
+ec	300
+_pr	293
+ión	290
+on_	288
+su	286
+_f	286
+_h	283
+nc	280
+pe	280
+li	279
+_un	277
+spa	276
+mo	270
+_o	270
+esp	268
+it	267
+or_	263
+del	262
+rt	250
+_a_	250
+est	247
+ado	245
+por	239
+aci	236
+ció	235
+las	234
+_n	231
+pañ	227
+ce	225
+so	222
+se_	221
+_pa	219
+_ca	218
+_su	213
+sta	213
+com	203
+ur	202
+tu	200
+ol	199
+ia_	198
+na_	197
+am	197
+ab	196
+ra_	196
+im	193
+tra	191
+no_	190
+men	190
+da_	190
+ter	189
+ns	188
+em	188
+cia	187
+z	185
+ña	185
+to_	184
+_al	181
+é	180
+ien	179
+ía	179
+ica	177
+_v	176
+cu	175
+_in	175
+ant	172
+des	172
+aña	170
+j	169
+ña_	169
+_g	168
+res	168
+ed	168
+pro	167
+ul	165
+ct	165
+od	165
+mo_	164
+ig	163
+vi	163
+one	162
+ll	161
+dad	161
+ha	160
+nci	160
+les	159
+_si	158
+era	158
+ada	158
+cio	156
+ion	155
+oc	155
+nes	154
+at	154
+sa	154
+va	150
+rr	150
+bi	149
+d_	149
+eg	149
+dos	148
+ist	147
+_pe	147
+ndo	147
+mp	146
+ran	145
+ño	145
+an_	144
+ida	143
+par	143
+_ha	140
+ó_	140
+gu	140
+año	139
+fi	137
+ron	136
+ale	135
+ía_	135
+us	134
+br	134
+ero	134
+mu	133
+_mi	132
+má	129
+tor	129
+x	129
+iv	128
+ona	127
+rio	127
+ntr	126
+ua	125
+bl	124
+ot	124
+ba	123
+ve	123
+il	123
+ici	123
+una	123
+_di	122
+ori	122
+ta_	122
+mb	121
+go	121
+io_	121
+lo_	120
+du	120
+_te	119
+ca_	118
+omo	118
+rec	117
+ob	117
+_no	116
+un_	116
+rm	116
+ina	115
+ad_	114
+uc	114
+nto	114
+ás	113
+re_	112
+za	112
+per	111
+ás_	110
+et	107
+_ma	107
+op	106
+pu	106
+ial	106
+ga	106
+ico	105
+ras	105
+u_	104
+más	104
+err	104
+hi	104
+ar_	103
+_tr	103
+ir	101
+ex	101
+fu	101
+gr	101
+ier	101
+ura	100
+min	100
+art	100
+ro_	99
+ido	99
+ita	99
+_so	99
+su_	99
+_b	98
+_me	98
+sti	97
+_mu	97
+tan	97
+rte	96
+_hi	95
+ú	94
+tes	94
+enc	94
+ste	94
+nom	92
+_fu	92
+fe	92
+eri	92
+ara	91
+tal	91
+nta	90
+rc	90
+_ex	90
+end	90
+ria	89
+_má	88
+ui	88
+gi	88
+nos	88
+der	87
+pre	87
+co_	86
+pi	86
+ten	86
+tur	85
+ali	85
+ut	85
+_to	85
+and	85
+ort	85
+tad	85
+tro	84
+ip	84
+tos	84
+inc	84
+tic	83
+und	82
+ios	82
+rí	81
+nal	80
+ade	79
+ep	79
+den	79
+ís	79
+man	78
+cr	78
+ula	78
+ito	77
+rn	76
+sig	76
+ene	76
+er_	75
+uer	75
+lt	75
+vo	75
+ano	74
+eci	73
+rá	73
+ons	73
+_ci	73
+au	73
+cos	73
+ros	73
+ont	72
+ma_	72