scylla 0.8.32 → 0.9.0
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.
- data/lib/scylla/generator.rb +6 -2
- data/lib/scylla/lms/arabic.lm +318 -318
- data/lib/scylla/lms/bulgarian.lm +326 -326
- data/lib/scylla/lms/chinese.lm +399 -399
- data/lib/scylla/lms/french.lm +302 -302
- data/lib/scylla/lms/greek.lm +119 -119
- data/lib/scylla/lms/hebrew.lm +168 -168
- data/lib/scylla/lms/hindi.lm +108 -108
- data/lib/scylla/lms/japanese.lm +65 -65
- data/lib/scylla/lms/kannada.lm +147 -147
- data/lib/scylla/lms/korean.lm +151 -151
- data/lib/scylla/lms/marathi.lm +133 -133
- data/lib/scylla/lms/persian.lm +107 -107
- data/lib/scylla/lms/polish.lm +108 -108
- data/lib/scylla/lms/portuguese.lm +221 -221
- data/lib/scylla/lms/romanian.lm +132 -132
- data/lib/scylla/lms/russian.lm +82 -82
- data/lib/scylla/lms/thai.lm +119 -119
- data/lib/scylla/resources.rb +0 -1
- data/test/helper.rb +0 -1
- metadata +40 -55
- data/Gemfile +0 -23
- data/Gemfile.lock +0 -53
- data/Rakefile +0 -52
- data/VERSION +0 -1
- data/lib/scylla/lms/afrikaans.lm +0 -400
- data/pkg/scylla-0.5.0.gem +0 -0
- data/scylla-0.8.29.gem +0 -0
- data/scylla-0.8.31.gem +0 -0
- data/scylla.gemspec +0 -24
- data/source_texts/afrikaans.txt +0 -363
- data/source_texts/arabic.txt +0 -718
- data/source_texts/bulgarian.txt +0 -601
- data/source_texts/catalan.txt +0 -435
- data/source_texts/chinese.txt +0 -625
- data/source_texts/czech.txt +0 -237
- data/source_texts/danish.txt +0 -268
- data/source_texts/dutch.txt +0 -503
- data/source_texts/english.txt +0 -673
- data/source_texts/finnish.txt +0 -939
- data/source_texts/french.txt +0 -896
- data/source_texts/german.txt +0 -1236
- data/source_texts/greek.txt +0 -488
- data/source_texts/hebrew.txt +0 -638
- data/source_texts/hindi.txt +0 -353
- data/source_texts/icelandic.txt +0 -342
- data/source_texts/indonesian.txt +0 -509
- data/source_texts/italian.txt +0 -1066
- data/source_texts/japanese.txt +0 -1220
- data/source_texts/kannada.txt +0 -340
- data/source_texts/korean.txt +0 -343
- data/source_texts/marathi.txt +0 -237
- data/source_texts/norwegian.txt +0 -555
- data/source_texts/persian.txt +0 -886
- data/source_texts/polish.txt +0 -1014
- data/source_texts/portuguese.txt +0 -690
- data/source_texts/romanian.txt +0 -436
- data/source_texts/russian.txt +0 -1128
- data/source_texts/slovak.txt +0 -575
- data/source_texts/slovenian.txt +0 -354
- data/source_texts/spanish.txt +0 -1017
- data/source_texts/swedish.txt +0 -558
- data/source_texts/tagalog.txt +0 -426
- data/source_texts/thai.txt +0 -312
- data/source_texts/turkish.txt +0 -665
- data/source_texts/vietnamese.txt +0 -300
- data/source_texts/welsh.txt +0 -332
data/lib/scylla/lms/french.lm
CHANGED
@@ -1,400 +1,400 @@
|
|
1
|
-
_
|
2
|
-
e
|
3
|
-
s
|
4
|
-
a
|
5
|
-
n
|
6
|
-
t
|
7
|
-
i
|
8
|
-
r
|
9
|
-
l
|
10
|
-
e_
|
11
|
-
u
|
12
|
-
o
|
13
|
-
s_
|
14
|
-
d
|
15
|
-
p
|
16
|
-
�
|
17
|
-
_d
|
18
|
-
c
|
19
|
-
_l
|
20
|
-
es
|
21
|
-
m
|
22
|
-
t_
|
23
|
-
|
24
|
-
|
25
|
-
es_
|
26
|
-
de
|
27
|
-
_p
|
28
|
-
le
|
29
|
-
en
|
30
|
-
_e
|
31
|
-
_de
|
32
|
-
on
|
33
|
-
nt
|
34
|
-
an
|
35
|
-
n_
|
36
|
-
re
|
37
|
-
f
|
38
|
-
la
|
1
|
+
_ 27956
|
2
|
+
e 10117
|
3
|
+
s 5737
|
4
|
+
a 5337
|
5
|
+
n 5222
|
6
|
+
t 4948
|
7
|
+
i 4796
|
8
|
+
r 4535
|
9
|
+
l 4225
|
10
|
+
e_ 3894
|
11
|
+
u 3647
|
12
|
+
o 3476
|
13
|
+
s_ 3170
|
14
|
+
d 2874
|
15
|
+
p 2710
|
16
|
+
� 2652
|
17
|
+
_d 2221
|
18
|
+
c 2183
|
19
|
+
_l 2102
|
20
|
+
es 1987
|
21
|
+
m 1908
|
22
|
+
t_ 1887
|
23
|
+
é 1737
|
24
|
+
� 1737
|
25
|
+
es_ 1571
|
26
|
+
de 1483
|
27
|
+
_p 1432
|
28
|
+
le 1421
|
29
|
+
en 1396
|
30
|
+
_e 1379
|
31
|
+
_de 1269
|
32
|
+
on 1183
|
33
|
+
nt 1160
|
34
|
+
an 1070
|
35
|
+
n_ 1037
|
36
|
+
re 976
|
37
|
+
f 916
|
38
|
+
la 912
|
39
39
|
de_ 875
|
40
|
-
a_
|
41
|
-
_s
|
40
|
+
a_ 836
|
41
|
+
_s 828
|
42
42
|
ti 805
|
43
|
-
_le
|
44
|
-
_c
|
45
|
-
_a
|
46
|
-
is
|
47
|
-
_la
|
48
|
-
la_
|
49
|
-
ra
|
50
|
-
�
|
51
|
-
�
|
52
|
-
�
|
53
|
-
nt_
|
54
|
-
g
|
55
|
-
le_
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
v
|
60
|
-
ent
|
61
|
-
et
|
62
|
-
_f
|
63
|
-
ar
|
64
|
-
ce
|
65
|
-
u_
|
66
|
-
pa
|
67
|
-
q
|
68
|
-
te
|
69
|
-
|
70
|
-
|
71
|
-
qu
|
72
|
-
ai
|
73
|
-
me
|
74
|
-
_m
|
75
|
-
|
43
|
+
_le 802
|
44
|
+
_c 801
|
45
|
+
_a 796
|
46
|
+
is 792
|
47
|
+
_la 748
|
48
|
+
la_ 726
|
49
|
+
ra 720
|
50
|
+
� 713
|
51
|
+
� 712
|
52
|
+
� 712
|
53
|
+
nt_ 707
|
54
|
+
g 705
|
55
|
+
le_ 702
|
56
|
+
�� 678
|
57
|
+
’ 678
|
58
|
+
� 678
|
59
|
+
v 664
|
60
|
+
ent 660
|
61
|
+
et 638
|
62
|
+
_f 625
|
63
|
+
ar 597
|
64
|
+
ce 592
|
65
|
+
u_ 587
|
66
|
+
pa 583
|
67
|
+
q 576
|
68
|
+
te 575
|
69
|
+
et_ 564
|
70
|
+
it 563
|
71
|
+
qu 562
|
72
|
+
ai 557
|
73
|
+
me 551
|
74
|
+
_m 550
|
75
|
+
_� 546
|
76
|
+
r_ 546
|
77
|
+
in 544
|
76
78
|
se 542
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
_pa 460
|
91
|
-
co 459
|
79
|
+
ns 538
|
80
|
+
ur 536
|
81
|
+
_et 532
|
82
|
+
ne 509
|
83
|
+
les 499
|
84
|
+
ue 485
|
85
|
+
st 478
|
86
|
+
er 475
|
87
|
+
au 472
|
88
|
+
b 467
|
89
|
+
_pa 463
|
90
|
+
_en 462
|
91
|
+
co 461
|
92
92
|
io 451
|
93
|
-
nc
|
94
|
-
ran
|
95
|
-
ri
|
96
|
-
tr
|
93
|
+
nc 444
|
94
|
+
ran 438
|
95
|
+
ri 437
|
96
|
+
tr 433
|
97
97
|
ion 431
|
98
|
-
|
99
|
-
|
100
|
-
_r
|
101
|
-
re_
|
102
|
-
ie
|
98
|
+
ou 422
|
99
|
+
at 422
|
100
|
+
_r 415
|
101
|
+
re_ 412
|
102
|
+
ie 406
|
103
|
+
eu 404
|
103
104
|
r� 403
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
l�
|
116
|
-
|
117
|
-
_l�
|
118
|
-
|
105
|
+
par 397
|
106
|
+
en_ 394
|
107
|
+
des 388
|
108
|
+
� 387
|
109
|
+
on_ 385
|
110
|
+
li 383
|
111
|
+
fr 382
|
112
|
+
al 380
|
113
|
+
po 379
|
114
|
+
ta 378
|
115
|
+
l� 376
|
116
|
+
l� 376
|
117
|
+
ns_ 374
|
118
|
+
_l� 374
|
119
|
+
ce_ 368
|
120
|
+
_t 367
|
119
121
|
pr 365
|
120
|
-
|
121
|
-
|
122
|
-
|
123
|
-
|
124
|
-
|
125
|
-
|
126
|
-
|
127
|
-
|
128
|
-
|
129
|
-
or
|
130
|
-
ne_ 340
|
131
|
-
h 339
|
122
|
+
un 364
|
123
|
+
ro 362
|
124
|
+
em 361
|
125
|
+
_fr 361
|
126
|
+
_co 349
|
127
|
+
que 349
|
128
|
+
fra 345
|
129
|
+
ne_ 343
|
130
|
+
h 343
|
131
|
+
or 342
|
132
132
|
tio 339
|
133
|
-
rt
|
134
|
-
oi
|
135
|
-
�_
|
136
|
-
|
137
|
-
à_
|
138
|
-
|
139
|
-
du
|
140
|
-
|
141
|
-
x
|
142
|
-
|
133
|
+
rt 327
|
134
|
+
oi 326
|
135
|
+
�_ 326
|
136
|
+
à 319
|
137
|
+
à_ 319
|
138
|
+
so 318
|
139
|
+
du 316
|
140
|
+
nce 312
|
141
|
+
x 312
|
142
|
+
is_ 310
|
143
143
|
ré 309
|
144
|
-
|
145
|
-
|
146
|
-
|
144
|
+
_à 307
|
145
|
+
anc 306
|
146
|
+
_au 292
|
147
|
+
est 292
|
148
|
+
el 289
|
147
149
|
us 289
|
148
|
-
_au 288
|
149
|
-
p_ 288
|
150
150
|
_n 288
|
151
|
-
|
152
|
-
si
|
153
|
-
_u
|
154
|
-
om
|
151
|
+
p_ 288
|
152
|
+
si 286
|
153
|
+
_u 284
|
154
|
+
om 282
|
155
|
+
ue_ 282
|
156
|
+
�_ 280
|
155
157
|
pl 280
|
156
|
-
é_
|
157
|
-
�_ 279
|
158
|
-
ue_ 278
|
159
|
-
ma 276
|
158
|
+
é_ 280
|
160
159
|
ll 276
|
161
|
-
|
162
|
-
|
160
|
+
nd 276
|
161
|
+
ma 276
|
162
|
+
n� 276
|
163
163
|
è 275
|
164
|
-
|
164
|
+
� 275
|
165
165
|
ui 272
|
166
|
-
|
167
|
-
|
168
|
-
_un
|
166
|
+
ir 267
|
167
|
+
t� 266
|
168
|
+
_un 266
|
169
169
|
_pr 262
|
170
|
-
ée
|
171
|
-
�e
|
172
|
-
_du
|
170
|
+
ée 258
|
171
|
+
�e 258
|
172
|
+
_du 257
|
173
|
+
men 256
|
173
174
|
lu 255
|
174
|
-
|
175
|
+
du_ 252
|
175
176
|
ati 252
|
176
|
-
|
177
|
-
|
177
|
+
_so 250
|
178
|
+
ont 246
|
178
179
|
ve 245
|
179
|
-
st_
|
180
|
-
|
181
|
-
_q
|
182
|
-
_qu 242
|
180
|
+
st_ 245
|
181
|
+
_qu 244
|
182
|
+
_q 244
|
183
183
|
mi 241
|
184
|
-
té
|
185
|
-
és
|
186
|
-
�s
|
187
|
-
ci
|
188
|
-
di
|
189
|
-
rs
|
190
|
-
i_
|
191
|
-
ut
|
192
|
-
|
193
|
-
|
194
|
-
|
195
|
-
ss
|
196
|
-
eur
|
197
|
-
ais
|
184
|
+
té 239
|
185
|
+
és 238
|
186
|
+
�s 238
|
187
|
+
ci 235
|
188
|
+
di 234
|
189
|
+
rs 231
|
190
|
+
i_ 230
|
191
|
+
ut 227
|
192
|
+
mo 227
|
193
|
+
_o 226
|
194
|
+
_es 223
|
195
|
+
ss 222
|
196
|
+
eur 217
|
197
|
+
ais 217
|
198
|
+
_é 215
|
198
199
|
ant 214
|
199
|
-
_é 212
|
200
200
|
pe 211
|
201
|
-
res
|
202
|
-
con
|
201
|
+
res 208
|
202
|
+
con 207
|
203
|
+
au_ 206
|
204
|
+
ct 205
|
203
205
|
lle 204
|
204
|
-
_po
|
205
|
-
|
206
|
-
|
207
|
-
|
208
|
-
ep
|
209
|
-
|
210
|
-
|
206
|
+
_po 203
|
207
|
+
il 202
|
208
|
+
ux 199
|
209
|
+
iq 198
|
210
|
+
ep 198
|
211
|
+
iqu 198
|
212
|
+
na 197
|
211
213
|
d� 196
|
212
|
-
_pl 196
|
213
214
|
d� 196
|
214
|
-
|
215
|
-
|
216
|
-
|
217
|
-
|
218
|
-
_i
|
215
|
+
_pl 196
|
216
|
+
te_ 195
|
217
|
+
da 194
|
218
|
+
x_ 193
|
219
|
+
_i 193
|
220
|
+
y 191
|
221
|
+
nn 191
|
219
222
|
_d� 191
|
220
|
-
x_ 191
|
221
|
-
ol 190
|
222
|
-
nn 189
|
223
223
|
ar_ 189
|
224
|
-
|
224
|
+
ol 189
|
225
|
+
l_ 188
|
225
226
|
_se 186
|
226
|
-
|
227
|
-
|
228
|
-
|
227
|
+
rs_ 185
|
228
|
+
to 184
|
229
|
+
no 183
|
229
230
|
lo 183
|
230
231
|
me_ 183
|
231
232
|
ons 182
|
232
|
-
son
|
233
|
-
to 180
|
233
|
+
son 181
|
234
234
|
ur_ 178
|
235
|
+
ux_ 178
|
235
236
|
pp 177
|
236
|
-
|
237
|
-
|
237
|
+
eme 177
|
238
|
+
ec 175
|
238
239
|
us_ 174
|
239
|
-
ans
|
240
|
-
mp
|
241
|
-
|
242
|
-
|
240
|
+
ans 174
|
241
|
+
mp 173
|
242
|
+
_re 173
|
243
|
+
d� 173
|
243
244
|
tre 172
|
244
|
-
|
245
|
-
ire
|
245
|
+
vi 171
|
246
|
+
ire 171
|
246
247
|
lus 170
|
247
|
-
|
248
|
-
art
|
248
|
+
_mo 169
|
249
|
+
art 168
|
249
250
|
pu 167
|
250
251
|
une 166
|
251
|
-
|
252
|
-
dé
|
252
|
+
ale 165
|
253
|
+
dé 165
|
253
254
|
plu 164
|
255
|
+
un_ 164
|
256
|
+
ic 164
|
254
257
|
_ma 164
|
255
|
-
|
256
|
-
un_ 163
|
257
|
-
i� 162
|
258
|
+
ch 163
|
258
259
|
_v 162
|
259
|
-
|
260
|
-
ch 161
|
260
|
+
i� 162
|
261
261
|
gr 161
|
262
|
-
ét 159
|
263
262
|
�t 159
|
263
|
+
ét 159
|
264
|
+
dan 158
|
264
265
|
ac 158
|
265
|
-
|
266
|
+
op 157
|
267
|
+
tu 156
|
266
268
|
se_ 156
|
267
|
-
|
268
|
-
_ce
|
269
|
-
tu 154
|
270
|
-
sa 154
|
269
|
+
sa 155
|
270
|
+
_ce 155
|
271
271
|
_g 153
|
272
272
|
ul 150
|
273
273
|
�a 149
|
274
274
|
��a 149
|
275
275
|
mm 148
|
276
|
-
né
|
277
|
-
fi
|
276
|
+
né 148
|
277
|
+
fi 147
|
278
278
|
sp 144
|
279
|
-
_d�
|
279
|
+
_d� 144
|
280
|
+
ts 144
|
281
|
+
im 144
|
282
|
+
�s_ 143
|
283
|
+
j 142
|
280
284
|
_r� 142
|
281
|
-
|
282
|
-
|
283
|
-
ts 142
|
284
|
-
j 141
|
285
|
+
ts_ 139
|
286
|
+
_da 138
|
285
287
|
it_ 138
|
286
|
-
ts_ 137
|
287
288
|
bl 137
|
288
|
-
|
289
|
-
ge 135
|
289
|
+
ge 136
|
290
290
|
� 135
|
291
|
+
as 135
|
292
|
+
ell 135
|
293
|
+
rti 134
|
291
294
|
ise 134
|
292
|
-
|
293
|
-
|
294
|
-
as 131
|
295
|
+
� 132
|
296
|
+
ç 132
|
295
297
|
m� 131
|
296
|
-
|
297
|
-
� 130
|
298
|
-
our 129
|
298
|
+
our 130
|
299
299
|
ér 129
|
300
|
+
ia 129
|
300
301
|
�r 129
|
301
|
-
_no 129
|
302
|
-
ia 128
|
303
|
-
ag 128
|
304
302
|
su 128
|
303
|
+
ag 128
|
304
|
+
_no 128
|
305
|
+
nç 126
|
305
306
|
�e_ 125
|
306
|
-
|
307
|
+
�a 124
|
308
|
+
��e 124
|
309
|
+
er_ 124
|
310
|
+
ça 124
|
307
311
|
�e 124
|
308
312
|
ntr 124
|
309
|
-
|
310
|
-
pp_ 123
|
313
|
+
an� 124
|
311
314
|
ien 123
|
312
|
-
|
313
|
-
�
|
314
|
-
an� 123
|
315
|
-
er_ 122
|
315
|
+
pp_ 123
|
316
|
+
�ai 121
|
316
317
|
pr� 121
|
317
|
-
|
318
|
-
iv 119
|
319
|
-
ni 118
|
318
|
+
iv 120
|
320
319
|
ort 118
|
320
|
+
ni 118
|
321
|
+
s� 117
|
322
|
+
aux 116
|
321
323
|
rr 116
|
322
|
-
|
323
|
-
|
324
|
-
|
325
|
-
�_
|
326
|
-
|
327
|
-
��_
|
328
|
-
ui_ 111
|
329
|
-
ins 110
|
324
|
+
ond 115
|
325
|
+
com 114
|
326
|
+
ins 112
|
327
|
+
�_ 112
|
328
|
+
ui_ 112
|
329
|
+
��_ 112
|
330
330
|
_tr 110
|
331
331
|
tra 110
|
332
332
|
ca 109
|
333
333
|
iè 109
|
334
|
-
ain
|
334
|
+
ain 109
|
335
|
+
qui 106
|
336
|
+
ine 106
|
335
337
|
ses 105
|
336
|
-
|
337
|
-
ine 104
|
338
|
-
ap 103
|
338
|
+
do 103
|
339
339
|
�es 103
|
340
|
+
ect 103
|
341
|
+
ap 103
|
340
342
|
_pe 103
|
341
|
-
do 103
|
342
343
|
ie_ 103
|
343
|
-
|
344
|
+
mb 102
|
344
345
|
d_ 102
|
345
|
-
|
346
|
+
_di 102
|
346
347
|
mme 101
|
348
|
+
ép 101
|
347
349
|
_su 101
|
348
|
-
|
349
|
-
|
350
|
-
|
351
|
-
|
352
|
-
|
353
|
-
|
354
|
-
ép 98
|
355
|
-
lit 98
|
350
|
+
�p 101
|
351
|
+
éc 100
|
352
|
+
fa 100
|
353
|
+
�c 100
|
354
|
+
ig 100
|
355
|
+
sé 99
|
356
356
|
_b 98
|
357
|
-
fa 98
|
358
357
|
cu 98
|
358
|
+
br 98
|
359
359
|
mai 97
|
360
|
+
fo 97
|
360
361
|
uv 97
|
361
|
-
|
362
|
-
sé 97
|
362
|
+
ot 97
|
363
363
|
air 97
|
364
|
-
|
365
|
-
|
366
|
-
|
367
|
-
it� 96
|
364
|
+
_te 97
|
365
|
+
ter 97
|
366
|
+
lit 96
|
368
367
|
id 95
|
369
368
|
uis 95
|
370
369
|
ris 94
|
371
|
-
|
372
|
-
nne
|
373
|
-
urs
|
374
|
-
|
370
|
+
it� 94
|
371
|
+
nne 94
|
372
|
+
urs 93
|
373
|
+
iti 92
|
374
|
+
_in 91
|
375
|
+
oc 91
|
376
|
+
oir 91
|
375
377
|
cti 91
|
376
|
-
oc 90
|
377
378
|
vo 90
|
378
|
-
|
379
|
-
|
379
|
+
ill 90
|
380
|
+
mon 90
|
381
|
+
�� 89
|
382
|
+
por 89
|
380
383
|
av 89
|
381
384
|
��� 89
|
382
385
|
pro 89
|
383
|
-
por 89
|
384
|
-
�� 89
|
385
386
|
nte 89
|
386
|
-
|
387
|
+
ues 89
|
388
|
+
bre 88
|
389
|
+
ure 88
|
387
390
|
nom 88
|
388
|
-
tan 87
|
389
391
|
gi 87
|
390
|
-
|
391
|
-
ure 87
|
392
|
-
ues 86
|
393
|
-
_j 86
|
392
|
+
tan 87
|
394
393
|
_do 86
|
394
|
+
_j 86
|
395
395
|
ouv 85
|
396
|
+
va 84
|
397
|
+
�g 84
|
398
|
+
ist 84
|
396
399
|
_an 84
|
397
400
|
_m� 84
|
398
|
-
�g 84
|
399
|
-
ég 84
|
400
|
-
va 84
|