scylla 0.7.0 → 0.7.5
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.
- data/lib/scylla/classifier.rb +3 -4
- data/lib/scylla/generator.rb +4 -7
- data/lib/scylla/lms/afrikaans.lm +280 -280
- data/lib/scylla/lms/arabic.lm +225 -225
- data/lib/scylla/lms/bulgarian.lm +208 -208
- data/lib/scylla/lms/catalan.lm +212 -212
- data/lib/scylla/lms/chinese.lm +201 -201
- data/lib/scylla/lms/danish.lm +155 -155
- data/lib/scylla/lms/english.lm +207 -207
- data/lib/scylla/lms/finnish.lm +259 -259
- data/lib/scylla/lms/french.lm +203 -203
- data/lib/scylla/lms/german.lm +280 -280
- data/lib/scylla/lms/greek.lm +276 -276
- data/lib/scylla/lms/hebrew.lm +170 -170
- data/lib/scylla/lms/hindi.lm +241 -241
- data/lib/scylla/lms/icelandic.lm +264 -264
- data/lib/scylla/lms/indonesian.lm +272 -272
- data/lib/scylla/lms/italian.lm +283 -283
- data/lib/scylla/lms/japanese.lm +105 -105
- data/lib/scylla/lms/korean.lm +400 -400
- data/lib/scylla/lms/norwegian.lm +235 -235
- data/lib/scylla/lms/polish.lm +264 -264
- data/lib/scylla/lms/portuguese.lm +269 -269
- data/lib/scylla/lms/romanian.lm +278 -278
- data/lib/scylla/lms/russian.lm +127 -127
- data/lib/scylla/lms/slovak.lm +281 -281
- data/lib/scylla/lms/slovenian.lm +276 -276
- data/lib/scylla/lms/spanish.lm +190 -190
- data/lib/scylla/lms/swedish.lm +195 -195
- data/lib/scylla/lms/tagalog.lm +282 -282
- data/lib/scylla/lms/thai.lm +257 -257
- data/lib/scylla/lms/turkish.lm +300 -300
- data/lib/scylla/lms/vietnamese.lm +277 -277
- data/lib/scylla/lms/welsh.lm +271 -271
- data/scylla.gemspec +3 -22
- data/source_texts/korean.txt +219 -134
- metadata +15 -14
- data/scylla-0.6.0.gem +0 -0
data/lib/scylla/lms/tagalog.lm
CHANGED
@@ -1,400 +1,400 @@
|
|
1
|
-
_
|
1
|
+
_ 1566
|
2
2
|
a 856
|
3
3
|
n 460
|
4
4
|
i 336
|
5
5
|
g 302
|
6
6
|
ng 210
|
7
|
+
g_ 192
|
7
8
|
t 183
|
8
|
-
|
9
|
+
ng_ 180
|
10
|
+
a_ 177
|
9
11
|
o 173
|
10
|
-
ng_ 170
|
11
|
-
a_ 159
|
12
12
|
k 155
|
13
|
-
an
|
13
|
+
an 154
|
14
14
|
s 150
|
15
|
+
_n 147
|
15
16
|
l 147
|
16
|
-
_n 132
|
17
17
|
m 131
|
18
|
-
p 105
|
19
18
|
y 105
|
19
|
+
p 105
|
20
20
|
u 103
|
21
21
|
na 101
|
22
22
|
ang 98
|
23
|
+
ang_ 89
|
23
24
|
. 85
|
24
|
-
|
25
|
+
_a 83
|
25
26
|
la 80
|
26
27
|
in 79
|
27
|
-
_a 77
|
28
28
|
r 77
|
29
|
-
|
29
|
+
._ 74
|
30
30
|
ka 72
|
31
|
-
|
31
|
+
b 72
|
32
|
+
_na 70
|
33
|
+
_m 70
|
34
|
+
_s 69
|
32
35
|
sa 67
|
36
|
+
ak 67
|
33
37
|
pa 65
|
34
|
-
_m 65
|
35
|
-
_s 64
|
36
38
|
ma 64
|
37
39
|
h 63
|
38
|
-
_na 61
|
39
|
-
at 57
|
40
|
-
d 57
|
41
40
|
al 57
|
41
|
+
d 57
|
42
|
+
_p 56
|
43
|
+
at 54
|
42
44
|
ag 52
|
43
|
-
|
45
|
+
t_ 49
|
46
|
+
o_ 49
|
44
47
|
ta 49
|
45
|
-
|
48
|
+
_k 48
|
49
|
+
n_ 47
|
50
|
+
_ng 46
|
51
|
+
_sa 45
|
46
52
|
ni 45
|
47
|
-
|
48
|
-
|
49
|
-
_sa 43
|
53
|
+
sa_ 43
|
54
|
+
_pa 42
|
50
55
|
ya 42
|
51
|
-
|
52
|
-
_ng 42
|
56
|
+
ay 41
|
53
57
|
it 40
|
54
|
-
_pa 40
|
55
|
-
o_ 39
|
56
58
|
on 39
|
57
59
|
e 39
|
58
|
-
|
60
|
+
_sa_ 38
|
59
61
|
y_ 38
|
60
|
-
|
61
|
-
|
62
|
+
_ng_ 37
|
63
|
+
ga 37
|
62
64
|
il 36
|
63
|
-
|
65
|
+
iy 36
|
66
|
+
_ma 35
|
64
67
|
ala 35
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
i_ 32
|
68
|
+
w 35
|
69
|
+
i_ 35
|
70
|
+
na_ 34
|
71
|
+
_t 33
|
72
|
+
am 32
|
73
|
+
_an 32
|
72
74
|
, 31
|
73
75
|
,_ 31
|
74
|
-
|
76
|
+
_ni 31
|
75
77
|
ra 31
|
78
|
+
_i 31
|
76
79
|
ba 30
|
77
|
-
|
80
|
+
_ka 30
|
81
|
+
_ang_ 30
|
82
|
+
_l 30
|
83
|
+
_ang 30
|
78
84
|
ar 29
|
79
|
-
|
80
|
-
_ni 29
|
81
|
-
_ang 29
|
85
|
+
_na_ 29
|
82
86
|
iya 29
|
83
|
-
_t 29
|
84
|
-
_i 28
|
85
|
-
_ka 28
|
86
|
-
_l 27
|
87
|
-
li 27
|
88
|
-
is 27
|
89
|
-
hi 27
|
90
87
|
ha 27
|
91
|
-
ong 27
|
92
88
|
aka 27
|
93
|
-
|
94
|
-
|
95
|
-
|
89
|
+
ong 27
|
90
|
+
is 27
|
91
|
+
li 27
|
92
|
+
hi 27
|
96
93
|
ko 26
|
97
|
-
|
94
|
+
as 26
|
95
|
+
ong_ 26
|
96
|
+
s_ 25
|
98
97
|
ri 25
|
99
98
|
to 25
|
99
|
+
ap 25
|
100
|
+
gi 24
|
101
|
+
an_ 24
|
102
|
+
ay_ 24
|
103
|
+
lan 24
|
100
104
|
ah 24
|
101
|
-
ong_ 24
|
102
105
|
un 24
|
103
|
-
lan 24
|
104
|
-
di 23
|
105
|
-
wa 23
|
106
|
-
ata 23
|
107
|
-
at_ 23
|
108
|
-
um 23
|
109
|
-
si 23
|
110
106
|
o. 23
|
111
|
-
|
107
|
+
ata 23
|
108
|
+
di 23
|
112
109
|
ing 23
|
113
|
-
|
110
|
+
si 23
|
111
|
+
um 23
|
112
|
+
wa 23
|
113
|
+
o._ 22
|
114
114
|
ki 22
|
115
|
-
|
116
|
-
|
117
|
-
_niy 21
|
118
|
-
niya 21
|
115
|
+
ti 22
|
116
|
+
ya_ 21
|
119
117
|
_d 21
|
120
|
-
an_ 21
|
121
118
|
niy 21
|
119
|
+
at_ 21
|
120
|
+
niya 21
|
121
|
+
_niya 21
|
122
|
+
_niy 21
|
122
123
|
ab 21
|
123
|
-
|
124
|
+
mo 21
|
125
|
+
a._ 20
|
124
126
|
a. 20
|
125
|
-
|
127
|
+
N 20
|
128
|
+
_mo 19
|
126
129
|
yo 19
|
127
130
|
ila 19
|
128
|
-
|
129
|
-
|
131
|
+
aw 19
|
132
|
+
iya_ 18
|
133
|
+
_b 18
|
134
|
+
ot 18
|
130
135
|
ig 18
|
131
|
-
_mo 18
|
132
|
-
A 18
|
133
136
|
_ak 18
|
134
|
-
|
137
|
+
A 18
|
135
138
|
lang 18
|
136
|
-
tu 17
|
137
|
-
ama 17
|
138
139
|
nag 17
|
139
|
-
|
140
|
-
|
140
|
+
in_ 17
|
141
|
+
_A 17
|
142
|
+
ing_ 17
|
143
|
+
tu 17
|
144
|
+
ama 16
|
145
|
+
nga 16
|
146
|
+
ali 16
|
147
|
+
_si 16
|
141
148
|
ina 16
|
142
149
|
P 16
|
143
|
-
|
150
|
+
_at 16
|
144
151
|
aki 16
|
145
152
|
ara 16
|
146
|
-
|
147
|
-
|
148
|
-
|
153
|
+
_N 16
|
154
|
+
_at_ 15
|
155
|
+
_h 15
|
149
156
|
lang_ 15
|
150
|
-
|
151
|
-
|
152
|
-
ga_ 14
|
157
|
+
ga_ 15
|
158
|
+
nd 14
|
153
159
|
ai 14
|
154
|
-
da 14
|
155
|
-
_h 14
|
156
|
-
_r 14
|
157
160
|
bi 14
|
158
|
-
|
159
|
-
|
160
|
-
|
161
|
+
_la 14
|
162
|
+
da 14
|
163
|
+
_P 14
|
161
164
|
ib 14
|
162
|
-
|
163
|
-
ro 13
|
164
|
-
ako 13
|
165
|
-
lo 13
|
166
|
-
_at_ 13
|
165
|
+
_r 14
|
167
166
|
ito 13
|
168
167
|
hin 13
|
169
|
-
|
170
|
-
|
168
|
+
ako 13
|
169
|
+
la_ 13
|
170
|
+
lo 13
|
171
|
+
ro 13
|
172
|
+
ik 13
|
173
|
+
aa 13
|
174
|
+
ahi 12
|
175
|
+
S 12
|
171
176
|
rin 12
|
172
|
-
mag 12
|
173
177
|
a, 12
|
174
|
-
|
175
|
-
_la 12
|
176
|
-
ahi 12
|
178
|
+
_Na 12
|
177
179
|
ul 12
|
178
|
-
|
180
|
+
K 12
|
181
|
+
_is 12
|
182
|
+
Na 12
|
183
|
+
_ta 12
|
184
|
+
mag 12
|
185
|
+
_K 12
|
186
|
+
_tu 12
|
187
|
+
_y 12
|
179
188
|
a,_ 12
|
180
|
-
|
181
|
-
|
182
|
-
|
183
|
-
|
184
|
-
|
189
|
+
_S 12
|
190
|
+
_y_ 11
|
191
|
+
ot_ 11
|
192
|
+
lu 11
|
193
|
+
pan 11
|
185
194
|
_di 11
|
186
|
-
apa 11
|
187
|
-
M 11
|
188
195
|
gk 11
|
189
|
-
lu 11
|
190
|
-
k_ 11
|
191
|
-
kin 11
|
192
|
-
_ri 11
|
193
|
-
_mag 11
|
194
196
|
ilan 11
|
197
|
+
niya_ 11
|
195
198
|
mi 11
|
196
|
-
|
199
|
+
k_ 11
|
200
|
+
go 11
|
201
|
+
_ri 11
|
202
|
+
man 11
|
197
203
|
ung 11
|
198
|
-
|
199
|
-
|
200
|
-
|
204
|
+
kin 11
|
205
|
+
M 11
|
206
|
+
_M 11
|
207
|
+
_mag 11
|
208
|
+
apa 11
|
201
209
|
Ma 10
|
202
|
-
|
203
|
-
|
204
|
-
|
205
|
-
|
206
|
-
ir 10
|
207
|
-
pa_ 10
|
208
|
-
uma 10
|
209
|
-
ilang 10
|
210
|
-
wal 10
|
211
|
-
mga_ 10
|
210
|
+
_Ka 10
|
211
|
+
_Ma 10
|
212
|
+
it_ 10
|
213
|
+
_mga 10
|
212
214
|
is_ 10
|
215
|
+
_mga_ 10
|
216
|
+
mg 10
|
217
|
+
ari 10
|
218
|
+
akin 10
|
219
|
+
_mg 10
|
220
|
+
l_ 10
|
213
221
|
yon 10
|
222
|
+
mo_ 10
|
223
|
+
asa 10
|
224
|
+
.. 10
|
225
|
+
pa_ 10
|
226
|
+
agk 10
|
227
|
+
to_ 10
|
228
|
+
mga_ 10
|
229
|
+
pi 10
|
230
|
+
_mo_ 10
|
231
|
+
_nag 10
|
214
232
|
yan 10
|
233
|
+
ir 10
|
234
|
+
uma 10
|
235
|
+
su 10
|
215
236
|
wala 10
|
216
|
-
|
237
|
+
wal 10
|
238
|
+
mga 10
|
239
|
+
ilang 10
|
240
|
+
nak 10
|
241
|
+
mu 10
|
217
242
|
I 10
|
218
|
-
pi 10
|
219
243
|
Ka 10
|
220
|
-
|
221
|
-
|
222
|
-
|
223
|
-
.. 10
|
224
|
-
su 10
|
225
|
-
ini 9
|
226
|
-
it_ 9
|
244
|
+
di_ 10
|
245
|
+
awa 10
|
246
|
+
_akin 9
|
227
247
|
n, 9
|
228
|
-
|
229
|
-
_N 9
|
230
|
-
n. 9
|
231
|
-
san 9
|
232
|
-
no 9
|
233
|
-
_mg 9
|
234
|
-
_Ka 9
|
235
|
-
_mga_ 9
|
248
|
+
alan 9
|
236
249
|
_ba 9
|
237
|
-
|
238
|
-
|
250
|
+
An 9
|
251
|
+
agka 9
|
252
|
+
_I 9
|
253
|
+
_An 9
|
239
254
|
isa 9
|
240
|
-
|
255
|
+
no 9
|
256
|
+
pu 9
|
257
|
+
n,_ 9
|
258
|
+
n. 9
|
259
|
+
n._ 9
|
260
|
+
gka 9
|
241
261
|
aba 9
|
242
|
-
|
243
|
-
_P 9
|
262
|
+
ini 9
|
244
263
|
_aki 9
|
245
|
-
|
246
|
-
|
247
|
-
|
248
|
-
|
249
|
-
|
250
|
-
|
251
|
-
|
252
|
-
|
253
|
-
|
264
|
+
as_ 9
|
265
|
+
_lu 9
|
266
|
+
nan 9
|
267
|
+
pag 9
|
268
|
+
_isa 9
|
269
|
+
e_ 8
|
270
|
+
yang_ 8
|
271
|
+
_ako 8
|
272
|
+
abi 8
|
273
|
+
iti 8
|
254
274
|
Pa 8
|
255
|
-
|
275
|
+
ayo 8
|
276
|
+
_wa 8
|
277
|
+
_wal 8
|
256
278
|
naka 8
|
257
|
-
|
258
|
-
_wala 8
|
259
|
-
aha 8
|
260
|
-
_nag 8
|
261
|
-
niya_ 8
|
262
|
-
yang 8
|
263
|
-
mo_ 8
|
264
|
-
t. 8
|
279
|
+
b_ 8
|
265
280
|
aman 8
|
266
|
-
|
267
|
-
_wa 8
|
268
|
-
ngi 8
|
269
|
-
_ako 8
|
270
|
-
l_ 8
|
271
|
-
king 8
|
272
|
-
di_ 8
|
281
|
+
_pag 8
|
273
282
|
tay 8
|
283
|
+
mat 8
|
284
|
+
si_ 8
|
274
285
|
aking 8
|
286
|
+
ili 8
|
287
|
+
ka_ 8
|
288
|
+
alang 8
|
289
|
+
aha 8
|
290
|
+
_pa_ 8
|
275
291
|
dib 8
|
276
292
|
umi 8
|
277
|
-
|
278
|
-
alang 8
|
279
|
-
mat 8
|
280
|
-
_wal 8
|
281
|
-
ili 8
|
282
|
-
aga 8
|
283
|
-
_lu 8
|
284
|
-
oy 8
|
293
|
+
t. 8
|
285
294
|
tan 8
|
286
|
-
|
287
|
-
|
288
|
-
|
289
|
-
|
290
|
-
|
291
|
-
|
292
|
-
|
293
|
-
|
294
|
-
|
295
|
+
yang 8
|
296
|
+
san 8
|
297
|
+
_Pa 8
|
298
|
+
p_ 8
|
299
|
+
aga 8
|
300
|
+
igi 8
|
301
|
+
king 8
|
302
|
+
_w 8
|
303
|
+
_wala 8
|
304
|
+
_iyo 7
|
305
|
+
gin 7
|
306
|
+
er 7
|
307
|
+
_ko 7
|
308
|
+
_ay 7
|
309
|
+
_pu 7
|
310
|
+
pak 7
|
295
311
|
o,_ 7
|
296
|
-
|
297
|
-
|
312
|
+
tum 7
|
313
|
+
_ha 7
|
314
|
+
tak 7
|
315
|
+
ko_ 7
|
316
|
+
_rin 7
|
317
|
+
ito_ 7
|
298
318
|
king_ 7
|
299
|
-
|
300
|
-
|
301
|
-
|
302
|
-
|
319
|
+
ail 7
|
320
|
+
iyo 7
|
321
|
+
o, 7
|
322
|
+
_iy 7
|
323
|
+
_ku 7
|
303
324
|
ala_ 7
|
304
|
-
|
325
|
+
_nak 7
|
326
|
+
ob 7
|
327
|
+
tang 7
|
328
|
+
tat 7
|
329
|
+
d_ 7
|
330
|
+
ra_ 7
|
331
|
+
ut 7
|
332
|
+
_tum 7
|
333
|
+
B 7
|
334
|
+
oo 7
|
335
|
+
_B 7
|
336
|
+
ram 7
|
337
|
+
_hi 7
|
338
|
+
tin 7
|
305
339
|
lis 7
|
306
|
-
e_ 7
|
307
|
-
er 7
|
308
|
-
_pag 7
|
309
|
-
_ko 7
|
310
|
-
ip 7
|
311
340
|
ku 7
|
312
|
-
|
313
|
-
to_ 7
|
314
|
-
_hi 7
|
315
|
-
o, 7
|
316
|
-
_mo_ 7
|
317
|
-
tum 7
|
318
|
-
pak 7
|
341
|
+
kan 7
|
319
342
|
ban 7
|
320
|
-
|
343
|
+
bo 7
|
321
344
|
_si_ 7
|
322
|
-
|
323
|
-
|
324
|
-
|
325
|
-
|
326
|
-
ka_ 7
|
327
|
-
ram 7
|
328
|
-
iyo 7
|
329
|
-
_isa 7
|
330
|
-
oo 7
|
331
|
-
_pa_ 7
|
332
|
-
ail 7
|
333
|
-
_rin 7
|
334
|
-
par 6
|
335
|
-
aila 6
|
336
|
-
_ha 6
|
345
|
+
mata 7
|
346
|
+
kat 7
|
347
|
+
ip 7
|
348
|
+
sang 6
|
337
349
|
ha_ 6
|
338
|
-
|
339
|
-
|
340
|
-
_S 6
|
341
|
-
pal 6
|
342
|
-
kun 6
|
350
|
+
gan 6
|
351
|
+
ngi 6
|
343
352
|
isan 6
|
353
|
+
una 6
|
354
|
+
os 6
|
355
|
+
_naka 6
|
356
|
+
nt 6
|
357
|
+
mba 6
|
358
|
+
man_ 6
|
359
|
+
walan 6
|
360
|
+
st 6
|
344
361
|
agi 6
|
362
|
+
_ay_ 6
|
345
363
|
Sa 6
|
346
|
-
mba 6
|
347
364
|
isang 6
|
348
|
-
|
349
|
-
kah 6
|
350
|
-
st 6
|
351
|
-
ag- 6
|
352
|
-
c 6
|
353
|
-
lis_ 6
|
354
|
-
sang 6
|
355
|
-
_nga 6
|
365
|
+
ita 6
|
356
366
|
nang 6
|
357
|
-
|
358
|
-
|
359
|
-
|
360
|
-
|
367
|
+
_kun 6
|
368
|
+
bang_ 6
|
369
|
+
tata 6
|
370
|
+
_siy 6
|
371
|
+
_siya 6
|
372
|
+
kaka 6
|
373
|
+
par 6
|
361
374
|
ig_ 6
|
362
|
-
|
363
|
-
|
364
|
-
|
375
|
+
nit 6
|
376
|
+
ago 6
|
377
|
+
siy 6
|
365
378
|
_par 6
|
379
|
+
_mu 6
|
380
|
+
kun 6
|
381
|
+
ung_ 6
|
382
|
+
ana 6
|
383
|
+
mb 6
|
384
|
+
c 6
|
385
|
+
sang_ 6
|
366
386
|
bang 6
|
367
|
-
up 6
|
368
387
|
kak 6
|
369
|
-
|
370
|
-
siya 6
|
371
|
-
ita 6
|
372
|
-
ung_ 6
|
373
|
-
yang_ 6
|
374
|
-
gan 6
|
375
|
-
d_ 6
|
376
|
-
_iyo 6
|
377
|
-
una 6
|
378
|
-
_Ma 6
|
379
|
-
ula 6
|
388
|
+
tang_ 6
|
380
389
|
im 6
|
381
|
-
|
382
|
-
|
383
|
-
|
384
|
-
|
385
|
-
|
386
|
-
|
387
|
-
|
388
|
-
|
389
|
-
|
390
|
-
|
391
|
-
|
392
|
-
han 5
|
393
|
-
nig_ 5
|
394
|
-
uh 5
|
395
|
-
bat 5
|
396
|
-
ito. 5
|
397
|
-
siya_ 5
|
398
|
-
hawak 5
|
399
|
-
go_ 5
|
400
|
-
ot. 5
|
390
|
+
ula 6
|
391
|
+
_nga 6
|
392
|
+
kah 6
|
393
|
+
_isan 6
|
394
|
+
ak_ 6
|
395
|
+
t._ 6
|
396
|
+
up 6
|
397
|
+
anga 6
|
398
|
+
ap_ 6
|
399
|
+
on_ 6
|
400
|
+
lis_ 6
|