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/welsh.lm
CHANGED
@@ -1,6 +1,6 @@
|
|
1
|
-
_
|
2
|
-
d 347
|
1
|
+
_ 1646
|
3
2
|
y 347
|
3
|
+
d 347
|
4
4
|
a 333
|
5
5
|
n 286
|
6
6
|
e 283
|
@@ -9,392 +9,392 @@ i 249
|
|
9
9
|
o 178
|
10
10
|
l 162
|
11
11
|
h 152
|
12
|
+
_y 127
|
12
13
|
g 125
|
13
14
|
f 124
|
14
|
-
t 122
|
15
15
|
w 122
|
16
|
-
|
17
|
-
n_
|
16
|
+
t 122
|
17
|
+
n_ 114
|
18
18
|
dd 106
|
19
19
|
u 98
|
20
20
|
m 88
|
21
|
-
|
21
|
+
r_ 87
|
22
22
|
s 86
|
23
|
-
|
23
|
+
yn 85
|
24
|
+
d_ 83
|
24
25
|
c 80
|
25
|
-
|
26
|
-
_a 66
|
26
|
+
_a 75
|
27
27
|
yd 65
|
28
|
-
yn_ 64
|
29
28
|
th 64
|
29
|
+
yn_ 62
|
30
|
+
u_ 60
|
31
|
+
i_ 60
|
30
32
|
. 59
|
31
|
-
|
32
|
-
|
33
|
+
._ 59
|
34
|
+
_yn 56
|
35
|
+
l_ 55
|
36
|
+
_d 54
|
37
|
+
_yn_ 52
|
33
38
|
ym 51
|
34
|
-
|
35
|
-
_d 50
|
36
|
-
u_ 49
|
39
|
+
_i 51
|
37
40
|
ydd 49
|
38
41
|
ae 48
|
39
|
-
|
40
|
-
_yn_ 46
|
41
|
-
ar 45
|
42
|
+
y_ 46
|
42
43
|
wy 44
|
43
|
-
an 43
|
44
44
|
ra 43
|
45
|
+
an 42
|
45
46
|
ol 42
|
47
|
+
h_ 41
|
46
48
|
b 41
|
47
|
-
|
48
|
-
|
49
|
+
_r 41
|
50
|
+
ar 40
|
51
|
+
_g 39
|
49
52
|
ei 39
|
50
|
-
|
51
|
-
|
53
|
+
ia 39
|
54
|
+
_y_ 37
|
55
|
+
o_ 37
|
56
|
+
dd_ 37
|
52
57
|
di 37
|
58
|
+
_c 37
|
53
59
|
ed 35
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
._ 32
|
60
|
+
th_ 34
|
61
|
+
_n 33
|
62
|
+
_r_ 32
|
58
63
|
da 31
|
59
64
|
ai 31
|
60
|
-
|
65
|
+
it 30
|
66
|
+
a_ 30
|
67
|
+
_e 30
|
68
|
+
_i_ 30
|
61
69
|
au 30
|
62
70
|
ne 30
|
63
|
-
it 30
|
64
71
|
ith 30
|
65
|
-
|
72
|
+
g_ 29
|
66
73
|
, 29
|
74
|
+
_h 29
|
75
|
+
ol_ 29
|
67
76
|
er 29
|
77
|
+
,_ 29
|
78
|
+
p 27
|
68
79
|
de 27
|
69
80
|
od 27
|
70
|
-
g_ 27
|
71
81
|
en 27
|
72
|
-
p 27
|
73
82
|
ddi 26
|
74
|
-
yr 26
|
75
83
|
ha 26
|
76
|
-
|
77
|
-
|
78
|
-
eg 25
|
84
|
+
au_ 26
|
85
|
+
yr 26
|
79
86
|
wyd 25
|
80
|
-
,_ 25
|
81
|
-
ol_ 25
|
82
87
|
mr 25
|
83
|
-
|
84
|
-
|
85
|
-
a_ 24
|
88
|
+
eg 25
|
89
|
+
_f 25
|
86
90
|
ymr 24
|
87
|
-
cy 24
|
88
|
-
_f 24
|
89
|
-
hy 24
|
90
91
|
ll 24
|
91
|
-
_p
|
92
|
-
|
92
|
+
_p 24
|
93
|
+
cy 24
|
94
|
+
_o 23
|
93
95
|
if 23
|
94
|
-
|
96
|
+
_cy 23
|
95
97
|
io 23
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
98
|
+
hy 23
|
99
|
+
_dd 23
|
100
|
+
_ar 23
|
101
|
+
_s 23
|
102
|
+
_. 22
|
100
103
|
ri 22
|
101
|
-
|
102
|
-
|
104
|
+
G 22
|
105
|
+
ad 22
|
106
|
+
_G 22
|
107
|
+
_._ 22
|
103
108
|
rae 21
|
104
|
-
__ 21
|
105
|
-
fe 21
|
106
109
|
ew 21
|
107
|
-
|
108
|
-
|
110
|
+
ny 21
|
111
|
+
wn 21
|
112
|
+
_a_ 21
|
113
|
+
_m 21
|
114
|
+
fe 21
|
115
|
+
ydd_ 20
|
109
116
|
no 20
|
110
|
-
_s 20
|
111
|
-
_cy 20
|
112
117
|
wydd 19
|
113
|
-
|
114
|
-
_G 19
|
115
|
-
or 19
|
118
|
+
ch 19
|
116
119
|
et 19
|
117
120
|
yf 19
|
118
|
-
|
119
|
-
_m 19
|
120
|
-
ch 19
|
121
|
+
eth 19
|
121
122
|
do 19
|
122
|
-
nydd 18
|
123
|
-
gy 18
|
124
|
-
nyd 18
|
125
123
|
at 18
|
126
|
-
|
124
|
+
nyd 18
|
125
|
+
s_ 18
|
126
|
+
nydd 18
|
127
|
+
ymra 17
|
128
|
+
aeg 17
|
129
|
+
ymrae 17
|
130
|
+
mraeg 17
|
127
131
|
ho 17
|
128
132
|
yr_ 17
|
129
133
|
el 17
|
130
|
-
mraeg 17
|
131
|
-
ymrae 17
|
132
|
-
aeg 17
|
133
|
-
aeth 17
|
134
|
-
rh 17
|
135
134
|
mra 17
|
136
|
-
s_ 17
|
137
|
-
ef 17
|
138
|
-
mrae 17
|
139
135
|
raeg 17
|
140
|
-
|
141
|
-
ymra 17
|
136
|
+
rh 17
|
142
137
|
aet 17
|
143
|
-
|
144
|
-
|
145
|
-
|
138
|
+
la 17
|
139
|
+
eu 17
|
140
|
+
ef 17
|
141
|
+
gy 17
|
142
|
+
mrae 17
|
143
|
+
aeth 17
|
146
144
|
fa 16
|
147
|
-
|
145
|
+
_Gy 16
|
148
146
|
ni 16
|
147
|
+
aith 16
|
148
|
+
_o_ 16
|
149
149
|
me 16
|
150
|
+
Gy 16
|
150
151
|
ait 16
|
151
|
-
|
152
|
-
|
152
|
+
er_ 16
|
153
|
+
nt 16
|
153
154
|
we 15
|
155
|
+
Gym 15
|
154
156
|
le 15
|
155
|
-
Gymr 15
|
156
|
-
ac 15
|
157
157
|
_b 15
|
158
|
+
yddi 15
|
159
|
+
eth_ 15
|
158
160
|
ff 15
|
161
|
+
ac 15
|
159
162
|
edd 15
|
160
|
-
|
163
|
+
efn 15
|
164
|
+
_w 15
|
165
|
+
_yr 15
|
166
|
+
Gymr 15
|
161
167
|
fn 15
|
162
|
-
|
163
|
-
|
164
|
-
|
168
|
+
_yr_ 15
|
169
|
+
_Gym 15
|
170
|
+
_Gymr 15
|
165
171
|
ys 14
|
166
|
-
|
167
|
-
|
168
|
-
_Gymr 14
|
169
|
-
_yr 14
|
170
|
-
eth_ 14
|
171
|
-
_Gym 14
|
172
|
+
aeth_ 14
|
173
|
+
c_ 14
|
172
174
|
ro 14
|
173
|
-
|
175
|
+
_hy 14
|
176
|
+
_ne 14
|
177
|
+
Gymra 14
|
174
178
|
nn 14
|
175
|
-
|
176
|
-
|
177
|
-
fny 13
|
178
|
-
eith 13
|
179
|
-
def 13
|
180
|
-
aeth_ 13
|
179
|
+
wn_ 13
|
180
|
+
defn 13
|
181
181
|
efnyd 13
|
182
|
+
def 13
|
183
|
+
eit 13
|
184
|
+
t_ 13
|
185
|
+
gw 13
|
186
|
+
oe 13
|
182
187
|
defny 13
|
183
188
|
fnydd 13
|
184
|
-
rha 13
|
185
|
-
oe 13
|
186
|
-
_a_ 13
|
187
|
-
efny 13
|
188
|
-
oed 13
|
189
189
|
fnyd 13
|
190
|
+
_l 13
|
191
|
+
al 13
|
192
|
+
eith 13
|
193
|
+
oed 13
|
194
|
+
fny 13
|
195
|
+
_me 13
|
196
|
+
rha 13
|
190
197
|
_ei 13
|
191
198
|
dde 13
|
192
|
-
|
193
|
-
|
194
|
-
gw 13
|
195
|
-
es 12
|
196
|
-
_ne 12
|
199
|
+
efny 13
|
200
|
+
si 13
|
197
201
|
nyddi 12
|
198
|
-
|
199
|
-
oedd 12
|
200
|
-
_hy 12
|
201
|
-
c_ 12
|
202
|
-
ng 12
|
203
|
-
ur 12
|
204
|
-
_w 12
|
202
|
+
es 12
|
205
203
|
sy 12
|
206
|
-
dol 12
|
207
|
-
ga 12
|
208
204
|
rif 12
|
205
|
+
ng 12
|
206
|
+
oedd 12
|
207
|
+
wr 12
|
208
|
+
_C 12
|
209
|
+
_da 12
|
210
|
+
_gy 12
|
211
|
+
ith_ 12
|
212
|
+
_ia 12
|
213
|
+
dol 12
|
209
214
|
C 12
|
210
|
-
|
215
|
+
ga 12
|
211
216
|
ewn 11
|
217
|
+
aith_ 11
|
218
|
+
rth 11
|
219
|
+
ei_ 11
|
220
|
+
_ei_ 11
|
212
221
|
ig 11
|
213
|
-
|
214
|
-
rt 11
|
215
|
-
ry 11
|
222
|
+
_gw 11
|
216
223
|
_ar_ 11
|
217
|
-
|
218
|
-
t_ 11
|
219
|
-
id 11
|
220
|
-
an_ 11
|
224
|
+
li 11
|
221
225
|
iaith 11
|
222
|
-
|
226
|
+
rt 11
|
223
227
|
aw 11
|
224
|
-
|
225
|
-
|
228
|
+
wydd_ 11
|
229
|
+
an_ 11
|
226
230
|
iai 11
|
227
|
-
|
231
|
+
eu_ 11
|
232
|
+
iait 11
|
233
|
+
ar_ 11
|
228
234
|
rd 11
|
229
|
-
|
230
|
-
|
231
|
-
|
232
|
-
ith_ 10
|
233
|
-
hw 10
|
234
|
-
yw 10
|
235
|
-
af 10
|
236
|
-
eg_ 10
|
235
|
+
re 11
|
236
|
+
eg_ 11
|
237
|
+
id 11
|
237
238
|
te 10
|
238
|
-
|
239
|
+
dio 10
|
239
240
|
on 10
|
240
241
|
gr 10
|
241
|
-
|
242
|
+
fo 10
|
243
|
+
S 10
|
244
|
+
_S 10
|
245
|
+
io_ 10
|
242
246
|
ddo 10
|
247
|
+
ac_ 10
|
248
|
+
fr 10
|
249
|
+
_ac 10
|
243
250
|
cr 10
|
251
|
+
_dde 10
|
252
|
+
yw 10
|
253
|
+
ad_ 10
|
244
254
|
ddio 10
|
245
|
-
|
246
|
-
|
247
|
-
|
248
|
-
or_ 10
|
249
|
-
dio 10
|
250
|
-
na 10
|
251
|
-
_da 10
|
252
|
-
ir 10
|
253
|
-
_ac 10
|
254
|
-
fr 10
|
255
|
-
S 10
|
256
|
-
eu_ 10
|
255
|
+
hw 10
|
256
|
+
f_ 10
|
257
|
+
ry 10
|
257
258
|
dda 10
|
259
|
+
_ym 10
|
260
|
+
af 10
|
261
|
+
w_ 9
|
258
262
|
_t 9
|
259
|
-
|
260
|
-
ge 9
|
263
|
+
_M 9
|
261
264
|
Cy 9
|
262
|
-
|
265
|
+
_iai 9
|
266
|
+
un 9
|
267
|
+
os 9
|
268
|
+
fer 9
|
269
|
+
fy 9
|
270
|
+
_mewn 9
|
271
|
+
og 9
|
272
|
+
_ac_ 9
|
263
273
|
st 9
|
274
|
+
A 9
|
275
|
+
_sy 9
|
276
|
+
_mew 9
|
277
|
+
_iait 9
|
278
|
+
_Cy 9
|
264
279
|
dr 9
|
265
|
-
|
266
|
-
|
280
|
+
_Y 9
|
281
|
+
Y 9
|
282
|
+
na 9
|
283
|
+
od_ 9
|
267
284
|
yddio 9
|
268
|
-
|
269
|
-
|
270
|
-
M 9
|
271
|
-
_gw 9
|
272
|
-
A 9
|
273
|
-
og 9
|
285
|
+
_new 9
|
286
|
+
mewn_ 9
|
274
287
|
mewn 9
|
275
|
-
fy 9
|
276
288
|
new 9
|
277
|
-
|
278
|
-
f_ 9
|
279
|
-
_ym 9
|
280
|
-
il 9
|
289
|
+
mew 9
|
281
290
|
sg 9
|
282
|
-
|
283
|
-
|
284
|
-
|
285
|
-
|
286
|
-
|
287
|
-
_sy 8
|
291
|
+
il 9
|
292
|
+
M 9
|
293
|
+
bl 9
|
294
|
+
ewn_ 9
|
295
|
+
dol_ 8
|
288
296
|
lw 8
|
289
|
-
|
290
|
-
|
291
|
-
E 8
|
292
|
-
_mewn 8
|
293
|
-
raeg_ 8
|
294
|
-
_r 8
|
295
|
-
_iait 8
|
296
|
-
_iai 8
|
297
|
-
_fe 8
|
298
|
-
hr 8
|
299
|
-
_mew 8
|
300
|
-
so 8
|
297
|
+
_cyf 8
|
298
|
+
is 8
|
301
299
|
aeg_ 8
|
300
|
+
raeg_ 8
|
301
|
+
gwe 8
|
302
302
|
cyf 8
|
303
|
-
|
303
|
+
_fe 8
|
304
|
+
g, 8
|
304
305
|
iad 8
|
306
|
+
dia 8
|
307
|
+
or 8
|
308
|
+
ma 8
|
305
309
|
dy 8
|
306
|
-
|
310
|
+
ge 8
|
311
|
+
ly 8
|
307
312
|
in 8
|
308
|
-
|
309
|
-
|
310
|
-
|
313
|
+
g,_ 8
|
314
|
+
edd_ 8
|
315
|
+
so 8
|
316
|
+
he 8
|
317
|
+
E 8
|
318
|
+
oedd_ 8
|
319
|
+
hr 8
|
320
|
+
odol 7
|
321
|
+
du 7
|
322
|
+
ddefn 7
|
323
|
+
odo 7
|
324
|
+
_newy 7
|
325
|
+
nol 7
|
326
|
+
g._ 7
|
327
|
+
_si 7
|
328
|
+
newy 7
|
311
329
|
m_ 7
|
312
|
-
gu 7
|
313
|
-
_eu_ 7
|
314
330
|
ent 7
|
315
|
-
|
316
|
-
|
317
|
-
|
318
|
-
|
319
|
-
|
320
|
-
|
321
|
-
|
331
|
+
_ddef 7
|
332
|
+
tr 7
|
333
|
+
ll_ 7
|
334
|
+
id_ 7
|
335
|
+
yddo 7
|
336
|
+
_eu 7
|
337
|
+
dio_ 7
|
338
|
+
_ll 7
|
339
|
+
nt_ 7
|
340
|
+
ewyd 7
|
341
|
+
ewy 7
|
322
342
|
g. 7
|
323
|
-
|
324
|
-
edd_ 7
|
325
|
-
di_ 7
|
326
|
-
Cym 7
|
343
|
+
_rh 7
|
327
344
|
my 7
|
328
|
-
|
345
|
+
ddef 7
|
329
346
|
rw 7
|
330
|
-
|
331
|
-
ewyd 7
|
332
|
-
pa 7
|
333
|
-
_M 7
|
334
|
-
_new 7
|
347
|
+
yg 7
|
335
348
|
dat 7
|
336
|
-
id_ 7
|
337
|
-
yddo 7
|
338
|
-
rth_ 7
|
339
|
-
w_ 7
|
340
|
-
nt_ 7
|
341
|
-
_ll 7
|
342
349
|
fl 7
|
343
|
-
ewn_ 7
|
344
|
-
mewn_ 7
|
345
|
-
nol 7
|
346
|
-
ddefn 7
|
347
|
-
du 7
|
348
|
-
dol_ 7
|
349
|
-
oedd_ 7
|
350
|
-
ir_ 7
|
351
|
-
ewy 7
|
352
|
-
tr 7
|
353
|
-
ig_ 7
|
354
350
|
han 7
|
355
|
-
iw 7
|
356
|
-
yd_ 7
|
357
|
-
_eu 7
|
358
|
-
newy 7
|
359
351
|
newyd 7
|
360
|
-
|
361
|
-
|
362
|
-
|
352
|
+
di_ 7
|
353
|
+
ic 7
|
354
|
+
_gwe 7
|
355
|
+
_eu_ 7
|
356
|
+
pa 7
|
357
|
+
ig_ 7
|
358
|
+
ewydd 7
|
359
|
+
gu 7
|
360
|
+
yd_ 7
|
361
|
+
_Cym 7
|
362
|
+
Cym 7
|
363
|
+
ch_ 7
|
364
|
+
B 7
|
365
|
+
fer_ 7
|
366
|
+
ddio_ 7
|
367
|
+
ob 7
|
368
|
+
rth_ 7
|
363
369
|
D 6
|
364
|
-
|
365
|
-
|
366
|
-
ynn 6
|
367
|
-
dal 6
|
368
|
-
fod 6
|
369
|
-
ian 6
|
370
|
+
fan 6
|
371
|
+
rif_ 6
|
370
372
|
_pa 6
|
371
|
-
|
372
|
-
|
373
|
-
|
374
|
-
|
373
|
+
ed_ 6
|
374
|
+
hyd 6
|
375
|
+
rdd 6
|
376
|
+
e_ 6
|
377
|
+
eg,_ 6
|
378
|
+
th. 6
|
379
|
+
pe 6
|
380
|
+
fod 6
|
375
381
|
pr 6
|
376
|
-
ant 6
|
377
382
|
ned 6
|
378
|
-
lwy 6
|
379
|
-
N 6
|
380
|
-
ann 6
|
381
|
-
cyn 6
|
382
|
-
_E 6
|
383
|
-
pe 6
|
384
|
-
_ddi 6
|
385
|
-
_def 6
|
386
|
-
ru 6
|
387
|
-
_si 6
|
388
|
-
wi 6
|
389
|
-
fle 6
|
390
|
-
as 6
|
391
|
-
yc 6
|
392
|
-
_de 6
|
393
|
-
ch_ 6
|
394
|
-
_pr 6
|
395
|
-
rwy 6
|
396
|
-
h. 6
|
397
383
|
I 6
|
384
|
+
us 6
|
385
|
+
yl 6
|
386
|
+
edi 6
|
387
|
+
h._ 6
|
388
|
+
ynn 6
|
389
|
+
yfr 6
|
390
|
+
rau 6
|
391
|
+
_ddi 6
|
392
|
+
neg 6
|
393
|
+
fel 6
|
394
|
+
cyn 6
|
395
|
+
gu_ 6
|
396
|
+
yfl 6
|
398
397
|
hau 6
|
399
|
-
|
400
|
-
|
398
|
+
ant 6
|
399
|
+
if_ 6
|
400
|
+
gh 6
|