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/lib/scylla/lms/tagalog.lm CHANGED Viewed

@@ -1,400 +1,400 @@
-_	6178
-a	3506
-n	2158
-g	1432
-i	1276
-ng	952
-an	885
-g_	854
-o	847
-s	845
-ng_	814
-t	773
-a_	750
-l	728
-p	683
-m	591
-_n	517
-u	515
-ang	507
-k	473
-_a	448
-y	411
-na	411
-e	409
-r	398
-sa	367
-_p	361
-n_	336
-in	332
-_m	330
-_s	328
-at	309
-la	295
+_	6230
+a	3528
+n	2171
+g	1442
+i	1290
+ng	958
+an	887
+g_	859
+o	855
+s	852
+ng_	819
+t	782
+a_	757
+l	734
+p	688
+m	592
+u	521
+_n	521
+ang	509
+k	474
+_a	450
+e	416
+na	415
+y	414
+r	403
+sa	369
+_p	364
+n_	337
+in	336
+_m	331
+_s	331
+at	313
 ka	295
+la	295
 b	294
-ga	285
-pa	279
-o_	269
-h	263
-d	260
-al	251
-sa_	247
+ga	286
+pa	283
+o_	273
+h	267
+d	264
+al	253
+sa_	249
 _ng	239
-on	235
-ma	230
-_sa	227
-_na	215
+on	236
+ma	231
+_sa	229
+_na	217
 t_	197
-_an	196
+_an	197
 pi	194
 an_	194
-ta	192
-_pa	192
-ag	189
+ta	194
+_pa	194
+ag	191
 ay	189
 _k	186
-li	171
+li	170
+il	159
 as	159
 ga_	158
-il	158
+_mg	151
 mga	151
 mg	151
-_mg	151
 y_	148
 _ka	143
 at_	142
-ul	138
-_i	129
+ul	139
+ti	131
+na_	130
 ba	129
-na_	128
+_i	129
 ala	127
-ti	127
 s_	126
 it	125
 is	121
 no	121
 ay_	121
-_ma	120
+_ma	121
 ina	119
 _at	118
+ya	116
 _b	115
-ya	115
 ha	115
 ra	114
+_t	110
 am	110
-_t	109
+un	106
+ar	106
 pin	106
-ar	105
-un	105
-ong	103
-yo	101
-ah	101
-w	100
-si	98
+ong	104
+ah	102
+yo	102
+w	101
+si	100
 ip	97
 on_	95
+hi	93
+ap	90
 ak	90
-hi	90
-ap	88
 ili	87
 _pi	86
-lo	82
-_d	82
+_d	86
+lo	85
+c	84
+ni	82
 ipi	81
-ni	80
+i_	80
+ik	80
+pan	80
 lip	80
-pan	79
-ik	79
 _ay	79
-i_	78
-c	78
-ata	76
-to	74
-st	73
+ata	77
+to	76
+st	76
 yon	72
-tu	71
-ula	70
+tu	72
+ing	71
 ama	70
-_h	69
+_h	70
+ula	70
 mi	69
+l_	69
 gan	68
-ing	68
+re	67
+ri	67
 _ba	67
-l_	67
-as_	67
 ab	67
-re	66
-ri	66
+as_	67
+pag	66
 ns	64
-pag	64
 lan	63
-ko	62
 aha	62
 er	62
+ko	62
 san	61
+pu	61
+iy	61
 pil	61
-pu	60
-iy	60
 _e	60
-_r	59
+_r	60
+e_	59
+di	59
+da	58
 _o	58
-di	58
 _l	57
-e_	57
 ara	56
 nas	56
-en	55
+en	56
 no_	55
-da	55
-aka	55
 mu	55
 sy	55
-d_	54
-ban	54
+aka	55
 po	54
-ad	53
+ban	54
+d_	54
+es	53
 la_	53
-es	52
+ad	53
 nga	52
+_si	51
 wa	51
-_si	50
-ila	49
+or	50
 ika	49
-lu	48
-aw	48
+ila	49
 aa	48
-or	48
 yan	48
+aw	48
+lu	48
+ati	47
+al_	47
 bu	47
-al_	46
-ans	46
 um	46
-ati	45
+ans	46
+ig	45
 te	45
-asa	44
+nd	44
+ro	44
 nsa	44
 op	44
-ig	44
-nd	44
+asa	44
 nt	44
 _is	43
+gk	42
 oo	42
-ro	42
-pul	42
 bi	42
-gk	42
+pul	42
+apa	42
 nan	42
-ino	41
+to_	41
 han	41
-kas	40
-_ta	40
+ino	41
 tan	40
-ana	40
-apa	40
+_re	40
+_ta	40
 kan	40
-to_	39
+ana	40
+kas	40
 kal	39
+ya_	39
 pam	39
-_re	39
-ya_	38
 ito	38
+aga	37
 _o_	37
+in_	36
+_g	36
 nag	36
-man	36
+gu	36
 kat	36
-aga	36
-gu	35
-in_	35
+man	36
+gi	35
 su	35
-_g	35
 ali	35
-_no	34
 isa	34
-gi	33
-awa	33
-ku	33
-oon	33
-syo	33
+_no	34
 _ha	33
+oon	33
+ku	33
 os	33
+awa	33
+aya	32
+syo	32
+_di	32
 ran	32
 aan	32
+_c	32
+f	32
 do	32
-aya	32
-hal	31
 p_	31
+hal	31
 nak	31
-ub	31
-_di	31
+ulo	31
 gka	31
-om	30
+ub	31
 _po	30
-ulo	30
-_u	30
+tin	30
 wi	30
-r_	30
 im	30
-f	30
+om	30
+r_	30
+_u	30
 ung	29
 ol	29
 aba	29
 _w	29
-_c	29
-tin	28
-tag	28
-mul	28
-_mu	28
-ngg	28
+mah	28
 hiy	28
 gg	28
-mah	28
-ur	28
+ngg	28
+mul	28
 iyo	28
+_mu	28
+tag	28
+ur	28
+iya	28
+_da	28
+noo	27
 it_	27
+eh	27
+nu	27
 ra_	27
+ne	27
+ist	27
 ehi	27
 uk	27
-nu	27
-ist	27
-eh	27
-iya	27
-ne	27
-noo	27
-bo	26
 mat	26
-se	26
+ahi	26
+bo	26
 sta	26
+lo_	26
 _es	26
+se	26
+nat	26
 mal	25
-_da	25
-may	25
-ahi	25
-ka_	25
-nat	25
+ta_	25
 reh	25
-lo_	25
 _it	25
+may	25
 ita	25
+sti	25
+ka_	25
 de	25
-ta_	24
+ny	24
 ag_	24
 me	24
-ny	24
-gga	24
 ye	24
 so	24
+gga	24
+k_	24
 ib	23
-uma	23
+ent	23
+ani	23
 hin	23
-_la	23
+v	23
 ki	23
-k_	23
+_la	23
 agk	23
-sti	23
-v	23
-ent	23
-ani	23
+uma	23
+una	23
 _bi	23
-lit	22
-una	22
-atu	22
+us	23
 go	22
+_ni	22
+atu	22
+lit	22
+_tu	22
+ut	22
 nah	22
-_ti	21
-_tu	21
-os_	21
-ek	21
-ut	21
 _su	21
-min	21
-us	21
+est	21
+ngu	21
+ek	21
+ca	21
+os_	21
+_ti	21
+he	21
 tr	21
-laa	20
+min	21
 rin	20
-ca	20
-mb	20
-_ni	20
 ad_	20
-he	20
-est	20
+nap	20
+gs	20
+laa	20
 asy	20
-ngu	20
+din	20
+mb	20
 lak	20
-gs	20
-et	19
-omi	19
-din	19
-kar	19
-ngk	19
-kap	19
+ia	19
+yo_	19
 du	19
-kon	19
-lat	19
+nit	19
+gl	19
+kap	19
+ngk	19
+omi	19
 _mi	19
+et	19
 gd	19
-nap	19
-te_	19
-nit	19
+kon	19
 od	19
+te_	19
+kar	19
+pat	19
+lat	19
+kab	18
+wan	18
 sya	18
-_bu	18
+isy	18
 lin	18
+ry	18
+pop	18
+ao	18
+bin	18
+ir	18
+_bu	18
+ai	18
 gp	18
+em	18
+mo	18
+gr	18
+gal	18
 tul	18
 opu	18
-gl	18
-ir	18
+nom	18
 ro_	18
-bin	18
-ia	18
-gr	18
 ii	18
-pop	18
-ao	18
-nom	18
-kab	18
 sin	18
-yo_	18
-mo	18
-ai	18
-ry	18
-wan	18
-em	18
-isy	18
-pat	18
-ari	17
-ua	17
-ini	17
-pe	17
+ok	17
+tal	17
+agi	17
+ulu	17
 lal	17
-ags	17
-_wi	17
 agp	17
-ob	17
-ok	17
 lay	17
-gal	17
-ulu	17
-wik	17
+pe	17
+ags	17
+ob	17
 any	17
+_pu	17
+_wi	17
+lon	17
+wik	17
+ini	17
+ari	17
+ua	17
+gin	16
+buo	16
 law	16
 gay	16
-lon	16
-ind	16
-uan	16
-ado	16
+ic	16
+apu	16
+ayo	16
+le	16
+_ko	16
+alo	16
 up	16
-tal	16
+ind	16
 uo	16
-iko	16
-tat	16
-_se	16
-alo	16
-agi	16
 par	16
-_ko	16
-_hi	16
 ura	16
-apu	16
-nya	16
+ado	16