scylla 0.1.0 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +0 -1
- data/Gemfile.lock +0 -10
- data/README.rdoc +22 -0
- data/VERSION +1 -1
- data/bin/scylla +13 -0
- data/lib/scylla/classifier.rb +2 -2
- data/lib/scylla/generator.rb +1 -1
- data/lib/scylla/lms/13375P33K.lm +400 -0
- data/lib/scylla/lms/afrikaans.lm +400 -0
- data/lib/scylla/lms/arabic.lm +400 -0
- data/lib/scylla/lms/bulgarian.lm +400 -0
- data/lib/scylla/lms/catalan.lm +400 -0
- data/lib/scylla/lms/chinese.lm +400 -0
- data/lib/scylla/lms/danish.lm +400 -0
- data/lib/scylla/lms/english.lm +400 -0
- data/lib/scylla/lms/esperanto.lm +400 -0
- data/lib/scylla/lms/finnish.lm +400 -0
- data/lib/scylla/lms/french.lm +400 -0
- data/lib/scylla/lms/german.lm +400 -0
- data/lib/scylla/lms/greek-iso8859-7.lm +400 -0
- data/lib/scylla/lms/hebrew.lm +400 -0
- data/lib/scylla/lms/hindi.lm +400 -0
- data/lib/scylla/lms/hungarian.lm +400 -0
- data/lib/scylla/lms/icelandic.lm +400 -0
- data/lib/scylla/lms/indonesian.lm +400 -0
- data/lib/scylla/lms/irish.lm +400 -0
- data/lib/scylla/lms/italian.lm +400 -0
- data/lib/scylla/lms/japanese.lm +400 -0
- data/lib/scylla/lms/kannada.lm +400 -0
- data/lib/scylla/lms/korean.lm +400 -0
- data/lib/scylla/lms/latin.lm +400 -0
- data/lib/scylla/lms/malay.lm +400 -0
- data/lib/scylla/lms/marathi.lm +400 -0
- data/lib/scylla/lms/mingo.lm +400 -0
- data/lib/scylla/lms/nepali.lm +400 -0
- data/lib/scylla/lms/norwegian.lm +400 -0
- data/lib/scylla/lms/polish.lm +400 -0
- data/lib/scylla/lms/portuguese.lm +400 -0
- data/lib/scylla/lms/quechua.lm +400 -0
- data/lib/scylla/lms/romanian.lm +400 -0
- data/lib/scylla/lms/rumantsch.lm +400 -0
- data/lib/scylla/lms/russian.lm +400 -0
- data/lib/scylla/lms/sanskrit.lm +400 -0
- data/lib/scylla/lms/scots_gaelic.lm +400 -0
- data/lib/scylla/lms/serbian-ascii.lm +400 -0
- data/lib/scylla/lms/slovak-ascii.lm +400 -0
- data/lib/scylla/lms/slovenian-ascii.lm +400 -0
- data/lib/scylla/lms/spanish.lm +400 -0
- data/lib/scylla/lms/swahili.lm +400 -0
- data/lib/scylla/lms/swedish.lm +400 -0
- data/lib/scylla/lms/tagalog.lm +400 -0
- data/lib/scylla/lms/tamil.lm +400 -0
- data/lib/scylla/lms/thai.lm +400 -0
- data/lib/scylla/lms/turkish.lm +400 -0
- data/lib/scylla/lms/ukrainian-koi8_u.lm +400 -0
- data/lib/scylla/lms/vietnamese.lm +400 -0
- data/lib/scylla/lms/welsh.lm +400 -0
- data/lib/scylla/lms/yiddish-utf.lm +400 -0
- data/lib/scylla/loader.rb +8 -1
- data/scylla-0.1.0.gem +0 -0
- data/scylla.gemspec +69 -3
- data/source_texts/kannada.txt +283 -0
- data/test/classifier_test.rb +7 -0
- data/test/fixtures/lms/13375p33k.lm +400 -0
- data/test/fixtures/lms/danish.lm +400 -0
- data/test/fixtures/lms/english.lm +400 -0
- data/test/fixtures/lms/french.lm +400 -0
- data/test/fixtures/lms/german.lm +400 -0
- data/test/fixtures/lms/japanese.lm +400 -0
- data/test/fixtures/lms/kannada.lm +400 -0
- data/test/fixtures/lms/spanish.lm +400 -0
- data/test/fixtures/source_texts/13375P33K.txt +199 -0
- data/test/fixtures/source_texts/japanese.txt +199 -0
- data/test/fixtures/source_texts/kannada.txt +283 -0
- data/test/generator_test.rb +10 -7
- data/test/helper.rb +5 -6
- data/test/loader_test.rb +1 -0
- data/test/scylla_test.rb +1 -0
- metadata +78 -14
- data/source_texts/armenian.txt +0 -86
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 14944
|
2
|
+
a 4057
|
3
|
+
e 3799
|
4
|
+
l 2679
|
5
|
+
s 2339
|
6
|
+
i 2295
|
7
|
+
n 2204
|
8
|
+
t 2164
|
9
|
+
r 1853
|
10
|
+
o 1493
|
11
|
+
c 1484
|
12
|
+
� 1204
|
13
|
+
d 1193
|
14
|
+
a_ 1153
|
15
|
+
s_ 1131
|
16
|
+
u 1083
|
17
|
+
__ 843
|
18
|
+
m 842
|
19
|
+
_d 768
|
20
|
+
es 765
|
21
|
+
en 764
|
22
|
+
p 702
|
23
|
+
_l 681
|
24
|
+
al 681
|
25
|
+
de 636
|
26
|
+
e_ 611
|
27
|
+
_e 586
|
28
|
+
ta 559
|
29
|
+
_de 544
|
30
|
+
l_ 507
|
31
|
+
g 500
|
32
|
+
, 490
|
33
|
+
,_ 480
|
34
|
+
la 470
|
35
|
+
at 463
|
36
|
+
_c 454
|
37
|
+
el 452
|
38
|
+
le 449
|
39
|
+
_a 443
|
40
|
+
ca 427
|
41
|
+
es_ 425
|
42
|
+
er 409
|
43
|
+
ci 399
|
44
|
+
_p 396
|
45
|
+
. 394
|
46
|
+
t_ 388
|
47
|
+
an 383
|
48
|
+
nt 382
|
49
|
+
à 364
|
50
|
+
� 364
|
51
|
+
re 359
|
52
|
+
st 352
|
53
|
+
ar 348
|
54
|
+
b 345
|
55
|
+
n_ 343
|
56
|
+
de_ 339
|
57
|
+
_de_ 333
|
58
|
+
ra 319
|
59
|
+
f 305
|
60
|
+
' 300
|
61
|
+
on 298
|
62
|
+
el_ 295
|
63
|
+
v 269
|
64
|
+
la_ 269
|
65
|
+
ll 266
|
66
|
+
_i 259
|
67
|
+
ic 258
|
68
|
+
._ 256
|
69
|
+
ue 253
|
70
|
+
i_ 252
|
71
|
+
or 251
|
72
|
+
_la 250
|
73
|
+
q 246
|
74
|
+
qu 242
|
75
|
+
_la_ 238
|
76
|
+
in 236
|
77
|
+
te 235
|
78
|
+
tal 233
|
79
|
+
_ca 232
|
80
|
+
it 227
|
81
|
+
ia 227
|
82
|
+
_s 220
|
83
|
+
ti 220
|
84
|
+
om 216
|
85
|
+
co 214
|
86
|
+
en_ 213
|
87
|
+
ent 212
|
88
|
+
na 211
|
89
|
+
que 211
|
90
|
+
_el 204
|
91
|
+
ri 204
|
92
|
+
_m 200
|
93
|
+
un 198
|
94
|
+
i� 197
|
95
|
+
ata 195
|
96
|
+
se 194
|
97
|
+
ns 193
|
98
|
+
x 191
|
99
|
+
E 188
|
100
|
+
atal 187
|
101
|
+
ng 183
|
102
|
+
len 181
|
103
|
+
ó 179
|
104
|
+
� 179
|
105
|
+
A 179
|
106
|
+
_a_ 179
|
107
|
+
é 177
|
108
|
+
gu 177
|
109
|
+
r_ 177
|
110
|
+
_i_ 177
|
111
|
+
� 177
|
112
|
+
nc 176
|
113
|
+
ci� 175
|
114
|
+
l� 173
|
115
|
+
�_ 171
|
116
|
+
à_ 171
|
117
|
+
di 170
|
118
|
+
_co 170
|
119
|
+
pe 169
|
120
|
+
_en 168
|
121
|
+
[ 164
|
122
|
+
] 164
|
123
|
+
li 164
|
124
|
+
C 163
|
125
|
+
ac 163
|
126
|
+
me 154
|
127
|
+
del 153
|
128
|
+
_del 152
|
129
|
+
í 152
|
130
|
+
� 152
|
131
|
+
_t 152
|
132
|
+
l' 151
|
133
|
+
lle 151
|
134
|
+
cat 151
|
135
|
+
_el_ 150
|
136
|
+
ls 149
|
137
|
+
tr 149
|
138
|
+
- 148
|
139
|
+
_es 147
|
140
|
+
pa 147
|
141
|
+
ts 146
|
142
|
+
_l' 145
|
143
|
+
) 145
|
144
|
+
là 144
|
145
|
+
_f 143
|
146
|
+
est 143
|
147
|
+
ua 142
|
148
|
+
ne 140
|
149
|
+
_ll 138
|
150
|
+
pr 138
|
151
|
+
ro 137
|
152
|
+
catal 137
|
153
|
+
cata 137
|
154
|
+
( 135
|
155
|
+
al_ 135
|
156
|
+
_cata 134
|
157
|
+
_cat 134
|
158
|
+
ma 133
|
159
|
+
ió 133
|
160
|
+
h 133
|
161
|
+
nt_ 131
|
162
|
+
_( 130
|
163
|
+
_en_ 130
|
164
|
+
oc 130
|
165
|
+
ts_ 130
|
166
|
+
_. 128
|
167
|
+
sta 127
|
168
|
+
_q 126
|
169
|
+
ls_ 126
|
170
|
+
del_ 126
|
171
|
+
_del_ 126
|
172
|
+
L 124
|
173
|
+
_qu 124
|
174
|
+
am 123
|
175
|
+
�_ 122
|
176
|
+
ó_ 122
|
177
|
+
ica 122
|
178
|
+
nci 122
|
179
|
+
no 122
|
180
|
+
�s 120
|
181
|
+
és 120
|
182
|
+
et 120
|
183
|
+
ció 120
|
184
|
+
ni 118
|
185
|
+
_._ 118
|
186
|
+
_o 118
|
187
|
+
és_ 117
|
188
|
+
�s_ 117
|
189
|
+
al� 116
|
190
|
+
ale 116
|
191
|
+
les 116
|
192
|
+
_lle 115
|
193
|
+
eng 115
|
194
|
+
leng 115
|
195
|
+
_pe 115
|
196
|
+
tal� 114
|
197
|
+
talà 114
|
198
|
+
_v 114
|
199
|
+
alà 114
|
200
|
+
atal� 114
|
201
|
+
y 113
|
202
|
+
ió_ 112
|
203
|
+
as 112
|
204
|
+
per 111
|
205
|
+
fi 111
|
206
|
+
va 111
|
207
|
+
llen 111
|
208
|
+
tat 110
|
209
|
+
ad 109
|
210
|
+
les_ 109
|
211
|
+
aci 109
|
212
|
+
là_ 109
|
213
|
+
lleng 108
|
214
|
+
at_ 108
|
215
|
+
_que 108
|
216
|
+
_pr 107
|
217
|
+
po 106
|
218
|
+
tu 106
|
219
|
+
o_ 105
|
220
|
+
m� 105
|
221
|
+
ant 104
|
222
|
+
_llen 103
|
223
|
+
� 102
|
224
|
+
è 102
|
225
|
+
g� 102
|
226
|
+
t� 102
|
227
|
+
com 102
|
228
|
+
ec 101
|
229
|
+
da 101
|
230
|
+
que_ 100
|
231
|
+
ues 100
|
232
|
+
ue_ 100
|
233
|
+
ció_ 99
|
234
|
+
_que_ 99
|
235
|
+
cia 98
|
236
|
+
na_ 98
|
237
|
+
_C 98
|
238
|
+
_r 97
|
239
|
+
_al 97
|
240
|
+
ny 97
|
241
|
+
_com 96
|
242
|
+
a, 96
|
243
|
+
_h 96
|
244
|
+
is 96
|
245
|
+
ngu 95
|
246
|
+
a,_ 94
|
247
|
+
mi 94
|
248
|
+
ia_ 93
|
249
|
+
sti 93
|
250
|
+
ix 93
|
251
|
+
ques 92
|
252
|
+
ns_ 91
|
253
|
+
enc 90
|
254
|
+
d' 90
|
255
|
+
em 90
|
256
|
+
_u 90
|
257
|
+
alà_ 90
|
258
|
+
gua 90
|
259
|
+
_d' 90
|
260
|
+
os 90
|
261
|
+
rt 89
|
262
|
+
men 89
|
263
|
+
aci� 89
|
264
|
+
r� 89
|
265
|
+
_per 89
|
266
|
+
to 89
|
267
|
+
ació 89
|
268
|
+
_se 88
|
269
|
+
ct 88
|
270
|
+
ü 87
|
271
|
+
mb 87
|
272
|
+
� 87
|
273
|
+
P 86
|
274
|
+
j 86
|
275
|
+
er_ 86
|
276
|
+
ngua 85
|
277
|
+
lengu 85
|
278
|
+
engu 85
|
279
|
+
engua 85
|
280
|
+
ol 85
|
281
|
+
I 84
|
282
|
+
ons 84
|
283
|
+
_le 84
|
284
|
+
io 84
|
285
|
+
tre 83
|
286
|
+
si 83
|
287
|
+
res 82
|
288
|
+
� 82
|
289
|
+
gü 82
|
290
|
+
ei 81
|
291
|
+
_� 81
|
292
|
+
par 80
|
293
|
+
ut 80
|
294
|
+
ent_ 79
|
295
|
+
_n 79
|
296
|
+
ng� 78
|
297
|
+
esta 78
|
298
|
+
so 78
|
299
|
+
ur 78
|
300
|
+
_[ 77
|
301
|
+
ngü 77
|
302
|
+
bl 77
|
303
|
+
: 77
|
304
|
+
eg 76
|
305
|
+
_les_ 76
|
306
|
+
�s 76
|
307
|
+
ís 76
|
308
|
+
_pa 76
|
309
|
+
_les 76
|
310
|
+
_di 76
|
311
|
+
_re 75
|
312
|
+
ha 75
|
313
|
+
con 74
|
314
|
+
_un 74
|
315
|
+
tic 73
|
316
|
+
_g 73
|
317
|
+
ran 73
|
318
|
+
mp 73
|
319
|
+
mo 72
|
320
|
+
lu 70
|
321
|
+
_po 70
|
322
|
+
els 69
|
323
|
+
Ca 69
|
324
|
+
rs 68
|
325
|
+
T 68
|
326
|
+
els_ 68
|
327
|
+
ie 68
|
328
|
+
fic 68
|
329
|
+
enci 68
|
330
|
+
amb 67
|
331
|
+
rd 67
|
332
|
+
ua_ 67
|
333
|
+
_no 66
|
334
|
+
ta_ 66
|
335
|
+
]_ 66
|
336
|
+
ot 66
|
337
|
+
m_ 65
|
338
|
+
ment 65
|
339
|
+
ial 65
|
340
|
+
ter 65
|
341
|
+
des 65
|
342
|
+
nta 65
|
343
|
+
_P 64
|
344
|
+
_b 64
|
345
|
+
ià 64
|
346
|
+
_ha 63
|
347
|
+
eix 63
|
348
|
+
�n 62
|
349
|
+
vi 62
|
350
|
+
do 62
|
351
|
+
ra_ 62
|
352
|
+
àn 62
|
353
|
+
gua_ 62
|
354
|
+
ngua_ 62
|
355
|
+
re_ 62
|
356
|
+
als 62
|
357
|
+
lenc 61
|
358
|
+
V 61
|
359
|
+
if 61
|
360
|
+
us 61
|
361
|
+
ar_ 61
|
362
|
+
nd 60
|
363
|
+
alenc 60
|
364
|
+
lenci 60
|
365
|
+
alen 60
|
366
|
+
M 60
|
367
|
+
fe 59
|
368
|
+
_, 59
|
369
|
+
� 59
|
370
|
+
lo 59
|
371
|
+
ell 59
|
372
|
+
ing 59
|
373
|
+
_ma 58
|
374
|
+
�sti 58
|
375
|
+
íst 58
|
376
|
+
ce 58
|
377
|
+
�st 58
|
378
|
+
sp 58
|
379
|
+
ísti 58
|
380
|
+
'a 58
|
381
|
+
_con 57
|
382
|
+
� 57
|
383
|
+
)_ 57
|
384
|
+
_é 57
|
385
|
+
_,_ 57
|
386
|
+
ita 57
|
387
|
+
_va 57
|
388
|
+
_és 57
|
389
|
+
_és_ 56
|
390
|
+
_E 56
|
391
|
+
om_ 56
|
392
|
+
S 56
|
393
|
+
ya 56
|
394
|
+
_A 56
|
395
|
+
D 56
|
396
|
+
_- 55
|
397
|
+
era 55
|
398
|
+
ul 55
|
399
|
+
sa 55
|
400
|
+
_� 55
|