scylla 0.8.0 → 0.8.29
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +4 -0
- data/Gemfile.lock +9 -1
- data/lib/scylla/generator.rb +46 -13
- data/lib/scylla/lms/afrikaans.lm +400 -400
- data/lib/scylla/lms/arabic.lm +400 -400
- data/lib/scylla/lms/bulgarian.lm +400 -400
- data/lib/scylla/lms/catalan.lm +399 -399
- data/lib/scylla/lms/chinese.lm +400 -400
- data/lib/scylla/lms/czech.lm +400 -0
- data/lib/scylla/lms/danish.lm +396 -396
- data/lib/scylla/lms/dutch.lm +400 -0
- data/lib/scylla/lms/english.lm +400 -400
- data/lib/scylla/lms/finnish.lm +400 -400
- data/lib/scylla/lms/french.lm +398 -398
- data/lib/scylla/lms/german.lm +400 -400
- data/lib/scylla/lms/greek.lm +400 -400
- data/lib/scylla/lms/hebrew.lm +399 -399
- data/lib/scylla/lms/hindi.lm +400 -400
- data/lib/scylla/lms/icelandic.lm +399 -399
- data/lib/scylla/lms/indonesian.lm +400 -400
- data/lib/scylla/lms/italian.lm +400 -400
- data/lib/scylla/lms/japanese.lm +399 -399
- data/lib/scylla/lms/kannada.lm +400 -0
- data/lib/scylla/lms/korean.lm +400 -400
- data/lib/scylla/lms/marathi.lm +400 -0
- data/lib/scylla/lms/norwegian.lm +400 -400
- data/lib/scylla/lms/persian.lm +400 -0
- data/lib/scylla/lms/polish.lm +400 -400
- data/lib/scylla/lms/portuguese.lm +400 -400
- data/lib/scylla/lms/romanian.lm +400 -400
- data/lib/scylla/lms/russian.lm +400 -400
- data/lib/scylla/lms/slovak.lm +400 -400
- data/lib/scylla/lms/slovenian.lm +387 -387
- data/lib/scylla/lms/spanish.lm +400 -400
- data/lib/scylla/lms/swedish.lm +399 -399
- data/lib/scylla/lms/tagalog.lm +400 -400
- data/lib/scylla/lms/thai.lm +400 -400
- data/lib/scylla/lms/turkish.lm +400 -400
- data/lib/scylla/lms/vietnamese.lm +400 -400
- data/lib/scylla/lms/welsh.lm +398 -398
- data/lib/scylla/resources.rb +43 -33
- data/lib/scylla/string.rb +2 -2
- data/lib/scylla.rb +0 -4
- data/pkg/scylla-0.5.0.gem +0 -0
- data/scylla.gemspec +1 -1
- data/source_texts/afrikaans.txt +330 -81
- data/source_texts/arabic.txt +590 -448
- data/source_texts/bulgarian.txt +588 -821
- data/source_texts/catalan.txt +435 -413
- data/source_texts/chinese.txt +526 -100
- data/source_texts/czech.txt +237 -0
- data/source_texts/danish.txt +233 -184
- data/source_texts/dutch.txt +503 -0
- data/source_texts/english.txt +673 -70
- data/source_texts/finnish.txt +939 -71
- data/source_texts/french.txt +879 -465
- data/source_texts/german.txt +1236 -137
- data/source_texts/greek.txt +488 -139
- data/source_texts/hebrew.txt +539 -100
- data/source_texts/hindi.txt +254 -100
- data/source_texts/icelandic.txt +301 -90
- data/source_texts/indonesian.txt +509 -93
- data/source_texts/italian.txt +1066 -120
- data/source_texts/japanese.txt +1217 -450
- data/source_texts/kannada.txt +340 -0
- data/source_texts/korean.txt +343 -219
- data/source_texts/marathi.txt +237 -0
- data/source_texts/norwegian.txt +555 -190
- data/source_texts/persian.txt +886 -0
- data/source_texts/polish.txt +1013 -90
- data/source_texts/portuguese.txt +690 -88
- data/source_texts/romanian.txt +436 -103
- data/source_texts/russian.txt +1029 -100
- data/source_texts/slovak.txt +575 -102
- data/source_texts/slovenian.txt +353 -99
- data/source_texts/spanish.txt +858 -675
- data/source_texts/swedish.txt +558 -488
- data/source_texts/tagalog.txt +391 -100
- data/source_texts/thai.txt +286 -60
- data/source_texts/turkish.txt +635 -87
- data/source_texts/vietnamese.txt +300 -92
- data/source_texts/welsh.txt +288 -104
- data/test/fixtures/lms/danish.lm +314 -314
- data/test/fixtures/lms/english.lm +301 -301
- data/test/fixtures/lms/french.lm +326 -326
- data/test/fixtures/lms/german.lm +331 -331
- data/test/fixtures/lms/hindi.lm +191 -191
- data/test/fixtures/lms/italian.lm +299 -299
- data/test/fixtures/lms/japanese.lm +103 -103
- data/test/fixtures/lms/norwegian.lm +309 -309
- data/test/fixtures/lms/spanish.lm +331 -331
- data/test/generator_test.rb +2 -2
- metadata +14 -3
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 20786
|
2
|
+
e 10748
|
3
|
+
n 5728
|
4
|
+
d 3982
|
5
|
+
a 3786
|
6
|
+
r 3636
|
7
|
+
i 3528
|
8
|
+
t 3355
|
9
|
+
o 3185
|
10
|
+
n_ 2897
|
11
|
+
e_ 2435
|
12
|
+
en 2373
|
13
|
+
de 2277
|
14
|
+
l 2188
|
15
|
+
s 2116
|
16
|
+
en_ 1832
|
17
|
+
_d 1624
|
18
|
+
er 1620
|
19
|
+
g 1610
|
20
|
+
v 1373
|
21
|
+
de_ 1300
|
22
|
+
t_ 1300
|
23
|
+
an 1293
|
24
|
+
h 1261
|
25
|
+
_de 1171
|
26
|
+
k 1088
|
27
|
+
_e 1061
|
28
|
+
m 1014
|
29
|
+
_v 943
|
30
|
+
u 871
|
31
|
+
te 866
|
32
|
+
nd 860
|
33
|
+
w 859
|
34
|
+
in 842
|
35
|
+
ee 839
|
36
|
+
ge 783
|
37
|
+
r_ 761
|
38
|
+
b 750
|
39
|
+
et 708
|
40
|
+
_h 706
|
41
|
+
j 705
|
42
|
+
s_ 700
|
43
|
+
p 694
|
44
|
+
he 692
|
45
|
+
c 671
|
46
|
+
d_ 669
|
47
|
+
or 667
|
48
|
+
el 634
|
49
|
+
st 623
|
50
|
+
et_ 621
|
51
|
+
ij 609
|
52
|
+
aa 596
|
53
|
+
oo 595
|
54
|
+
_i 592
|
55
|
+
ie 569
|
56
|
+
z 560
|
57
|
+
_o 546
|
58
|
+
an_ 542
|
59
|
+
_he 540
|
60
|
+
la 529
|
61
|
+
va 528
|
62
|
+
_en 506
|
63
|
+
_w 493
|
64
|
+
van 477
|
65
|
+
het 466
|
66
|
+
_va 464
|
67
|
+
_b 462
|
68
|
+
_g 460
|
69
|
+
der 451
|
70
|
+
_n 445
|
71
|
+
and 437
|
72
|
+
on 432
|
73
|
+
ed 432
|
74
|
+
me 429
|
75
|
+
_in 412
|
76
|
+
rd 411
|
77
|
+
nde 410
|
78
|
+
_m 405
|
79
|
+
lan 402
|
80
|
+
oor 395
|
81
|
+
re 389
|
82
|
+
ch 387
|
83
|
+
al 387
|
84
|
+
er_ 385
|
85
|
+
_z 381
|
86
|
+
_a 377
|
87
|
+
ng 375
|
88
|
+
_t 374
|
89
|
+
be 365
|
90
|
+
le 365
|
91
|
+
ar 359
|
92
|
+
_s 350
|
93
|
+
is 344
|
94
|
+
in_ 342
|
95
|
+
li 342
|
96
|
+
we 341
|
97
|
+
ve 339
|
98
|
+
ke 339
|
99
|
+
ne 332
|
100
|
+
f 331
|
101
|
+
den 328
|
102
|
+
ro 324
|
103
|
+
g_ 324
|
104
|
+
een 322
|
105
|
+
_ee 321
|
106
|
+
ri 320
|
107
|
+
ede 320
|
108
|
+
vo 319
|
109
|
+
ti 313
|
110
|
+
_ge 307
|
111
|
+
_be 297
|
112
|
+
at 295
|
113
|
+
it 293
|
114
|
+
l_ 279
|
115
|
+
ste 267
|
116
|
+
na 259
|
117
|
+
nd_ 256
|
118
|
+
di 256
|
119
|
+
_l 255
|
120
|
+
rl 254
|
121
|
+
te_ 251
|
122
|
+
es 249
|
123
|
+
aar 248
|
124
|
+
k_ 246
|
125
|
+
ra 232
|
126
|
+
ui 228
|
127
|
+
ing 226
|
128
|
+
op 226
|
129
|
+
_me 225
|
130
|
+
zi 224
|
131
|
+
ver 224
|
132
|
+
_vo 223
|
133
|
+
nt 220
|
134
|
+
ijk 219
|
135
|
+
jk 219
|
136
|
+
erd 218
|
137
|
+
erl 217
|
138
|
+
wa 213
|
139
|
+
ter 210
|
140
|
+
or_ 207
|
141
|
+
_k 206
|
142
|
+
_ne 206
|
143
|
+
ten 206
|
144
|
+
ie_ 204
|
145
|
+
ei 201
|
146
|
+
gen 199
|
147
|
+
_p 199
|
148
|
+
da 199
|
149
|
+
gr 195
|
150
|
+
rla 195
|
151
|
+
rs 189
|
152
|
+
ned 188
|
153
|
+
_we 188
|
154
|
+
oe 188
|
155
|
+
se 187
|
156
|
+
ond 185
|
157
|
+
is_ 184
|
158
|
+
_ve 179
|
159
|
+
_zi 177
|
160
|
+
eg 176
|
161
|
+
id 174
|
162
|
+
sc 172
|
163
|
+
ig 172
|
164
|
+
ot 171
|
165
|
+
sch 170
|
166
|
+
eer 168
|
167
|
+
ni 168
|
168
|
+
_wa 166
|
169
|
+
ng_ 166
|
170
|
+
_r 165
|
171
|
+
ta 165
|
172
|
+
_on 164
|
173
|
+
ord 161
|
174
|
+
_is 158
|
175
|
+
ere 158
|
176
|
+
ur 158
|
177
|
+
voo 157
|
178
|
+
rde 157
|
179
|
+
bi 156
|
180
|
+
lij 155
|
181
|
+
ol 154
|
182
|
+
_op 154
|
183
|
+
ev 153
|
184
|
+
cht 152
|
185
|
+
ht 152
|
186
|
+
ers 151
|
187
|
+
ds 151
|
188
|
+
p_ 148
|
189
|
+
om 148
|
190
|
+
do 147
|
191
|
+
ze 146
|
192
|
+
_te 146
|
193
|
+
to 146
|
194
|
+
_di 145
|
195
|
+
el_ 145
|
196
|
+
wo 144
|
197
|
+
ls 144
|
198
|
+
aan 143
|
199
|
+
rt 142
|
200
|
+
est 142
|
201
|
+
_la 142
|
202
|
+
ma 140
|
203
|
+
pe 140
|
204
|
+
jn 137
|
205
|
+
ijn 137
|
206
|
+
ek 137
|
207
|
+
wer 135
|
208
|
+
met 134
|
209
|
+
eu 133
|
210
|
+
doo 133
|
211
|
+
am 133
|
212
|
+
ls_ 132
|
213
|
+
ns 132
|
214
|
+
_al 131
|
215
|
+
uit 131
|
216
|
+
end 131
|
217
|
+
_da 130
|
218
|
+
ken 129
|
219
|
+
zij 129
|
220
|
+
mi 128
|
221
|
+
nge 127
|
222
|
+
tie 127
|
223
|
+
_do 127
|
224
|
+
eli 127
|
225
|
+
ts 126
|
226
|
+
no 125
|
227
|
+
jn_ 124
|
228
|
+
zo 123
|
229
|
+
rij 123
|
230
|
+
ren 122
|
231
|
+
m_ 121
|
232
|
+
gro 121
|
233
|
+
eel 120
|
234
|
+
lo 120
|
235
|
+
rd_ 120
|
236
|
+
men 119
|
237
|
+
a_ 119
|
238
|
+
ic 118
|
239
|
+
_gr 118
|
240
|
+
ar_ 118
|
241
|
+
tr 117
|
242
|
+
als 117
|
243
|
+
_na 117
|
244
|
+
ha 116
|
245
|
+
nds 116
|
246
|
+
_st 116
|
247
|
+
em 116
|
248
|
+
as 116
|
249
|
+
op_ 115
|
250
|
+
og 114
|
251
|
+
se_ 111
|
252
|
+
ang 111
|
253
|
+
ke_ 110
|
254
|
+
die 110
|
255
|
+
_aa 108
|
256
|
+
it_ 107
|
257
|
+
wi 104
|
258
|
+
tu 103
|
259
|
+
le_ 103
|
260
|
+
_u 103
|
261
|
+
wor 102
|
262
|
+
mee 102
|
263
|
+
vi 101
|
264
|
+
_wo 100
|
265
|
+
ho 99
|
266
|
+
ind 98
|
267
|
+
eid 98
|
268
|
+
al_ 98
|
269
|
+
eb 98
|
270
|
+
ege 98
|
271
|
+
ec 97
|
272
|
+
_oo 96
|
273
|
+
_zo 96
|
274
|
+
ld 95
|
275
|
+
sta 94
|
276
|
+
_to 94
|
277
|
+
_ui 92
|
278
|
+
ele 92
|
279
|
+
rk 91
|
280
|
+
jke 91
|
281
|
+
f_ 90
|
282
|
+
ich 89
|
283
|
+
ok 88
|
284
|
+
rm 88
|
285
|
+
st_ 87
|
286
|
+
j_ 87
|
287
|
+
ak 87
|
288
|
+
ij_ 86
|
289
|
+
erk 85
|
290
|
+
waa 85
|
291
|
+
uw 85
|
292
|
+
at_ 84
|
293
|
+
_f 84
|
294
|
+
_ma 83
|
295
|
+
kt 83
|
296
|
+
ko 83
|
297
|
+
_c 83
|
298
|
+
ge_ 83
|
299
|
+
ag 83
|
300
|
+
nk 82
|
301
|
+
ll 81
|
302
|
+
jk_ 81
|
303
|
+
pr 80
|
304
|
+
del 80
|
305
|
+
geb 79
|
306
|
+
_er 79
|
307
|
+
ot_ 79
|
308
|
+
pa 78
|
309
|
+
af 76
|
310
|
+
eri 76
|
311
|
+
ela 76
|
312
|
+
bij 76
|
313
|
+
ov 76
|
314
|
+
po 75
|
315
|
+
il 75
|
316
|
+
re_ 75
|
317
|
+
aat 75
|
318
|
+
ent 74
|
319
|
+
gel 74
|
320
|
+
eld 74
|
321
|
+
ch_ 73
|
322
|
+
hi 73
|
323
|
+
dt_ 73
|
324
|
+
gi 73
|
325
|
+
len 73
|
326
|
+
bel 73
|
327
|
+
dt 73
|
328
|
+
id_ 73
|
329
|
+
h_ 73
|
330
|
+
ens 72
|
331
|
+
ati 72
|
332
|
+
_re 72
|
333
|
+
rg 71
|
334
|
+
_bi 71
|
335
|
+
uu 71
|
336
|
+
ac 71
|
337
|
+
ale 71
|
338
|
+
uur 70
|
339
|
+
_mi 69
|
340
|
+
vol 69
|
341
|
+
_no 69
|
342
|
+
ok_ 68
|
343
|
+
nte 68
|
344
|
+
si 68
|
345
|
+
ran 67
|
346
|
+
ez 67
|
347
|
+
ook 66
|
348
|
+
ort 66
|
349
|
+
ied 66
|
350
|
+
lle 65
|
351
|
+
eke 65
|
352
|
+
tw 65
|
353
|
+
rs_ 65
|
354
|
+
maa 65
|
355
|
+
ru 64
|
356
|
+
ist 64
|
357
|
+
ite 64
|
358
|
+
dee 64
|
359
|
+
io 64
|
360
|
+
tot 63
|
361
|
+
taa 63
|
362
|
+
as_ 63
|
363
|
+
un 63
|
364
|
+
jd 63
|
365
|
+
ier 63
|
366
|
+
_ze 63
|
367
|
+
ijd 63
|
368
|
+
ad 63
|
369
|
+
ige 62
|
370
|
+
gev 62
|
371
|
+
so 62
|
372
|
+
euw 62
|
373
|
+
isc 62
|
374
|
+
sp 62
|
375
|
+
ep 61
|
376
|
+
per 61
|
377
|
+
du 61
|
378
|
+
� 61
|
379
|
+
tij 61
|
380
|
+
tuu 61
|
381
|
+
ed_ 60
|
382
|
+
od 60
|
383
|
+
_ko 60
|
384
|
+
ame 59
|
385
|
+
rdt 59
|
386
|
+
pro 59
|
387
|
+
ht_ 58
|
388
|
+
ew 58
|
389
|
+
_j 58
|
390
|
+
zic 58
|
391
|
+
orm 58
|
392
|
+
naa 57
|
393
|
+
ove 57
|
394
|
+
kel 57
|
395
|
+
che 57
|
396
|
+
evo 57
|
397
|
+
roo 57
|
398
|
+
ou 57
|
399
|
+
_ho 56
|
400
|
+
ef 56
|