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
|
+
_ 1290
|
2
|
+
' 360
|
3
|
+
a 318
|
4
|
+
k 294
|
5
|
+
t 293
|
6
|
+
n 289
|
7
|
+
e 236
|
8
|
+
� 222
|
9
|
+
h 215
|
10
|
+
u 191
|
11
|
+
y 187
|
12
|
+
s 183
|
13
|
+
w 171
|
14
|
+
� 156
|
15
|
+
'_ 141
|
16
|
+
_n 122
|
17
|
+
. 98
|
18
|
+
i 90
|
19
|
+
� 82
|
20
|
+
e_ 77
|
21
|
+
e' 76
|
22
|
+
ne 73
|
23
|
+
._ 71
|
24
|
+
a' 71
|
25
|
+
_k 66
|
26
|
+
" 65
|
27
|
+
wa 64
|
28
|
+
u' 64
|
29
|
+
� 60
|
30
|
+
_ne 59
|
31
|
+
kw 56
|
32
|
+
__ 56
|
33
|
+
_t 55
|
34
|
+
� 54
|
35
|
+
� 54
|
36
|
+
N 53
|
37
|
+
e'_ 53
|
38
|
+
hu 50
|
39
|
+
_h 49
|
40
|
+
� 48
|
41
|
+
n� 47
|
42
|
+
�' 47
|
43
|
+
at 46
|
44
|
+
ne_ 43
|
45
|
+
yu 43
|
46
|
+
_u 42
|
47
|
+
ak 42
|
48
|
+
't 42
|
49
|
+
_ne_ 41
|
50
|
+
ha 41
|
51
|
+
kh 41
|
52
|
+
w� 39
|
53
|
+
ta 38
|
54
|
+
_� 38
|
55
|
+
hs 38
|
56
|
+
�' 37
|
57
|
+
_N 36
|
58
|
+
ka 35
|
59
|
+
te 34
|
60
|
+
�n 34
|
61
|
+
s_ 33
|
62
|
+
th 32
|
63
|
+
� 30
|
64
|
+
ny 30
|
65
|
+
'. 30
|
66
|
+
� 29
|
67
|
+
_" 29
|
68
|
+
�_ 28
|
69
|
+
Ne' 28
|
70
|
+
_w 28
|
71
|
+
Ne 28
|
72
|
+
k� 27
|
73
|
+
ya 27
|
74
|
+
t_ 27
|
75
|
+
_. 27
|
76
|
+
Ne'_ 27
|
77
|
+
ty 27
|
78
|
+
_._ 26
|
79
|
+
yu' 26
|
80
|
+
'k 26
|
81
|
+
ni 26
|
82
|
+
n� 25
|
83
|
+
, 25
|
84
|
+
khu 25
|
85
|
+
w�n 25
|
86
|
+
�t 25
|
87
|
+
�_ 24
|
88
|
+
�t 24
|
89
|
+
�y 24
|
90
|
+
- 23
|
91
|
+
y� 23
|
92
|
+
kwa 23
|
93
|
+
_wa 23
|
94
|
+
_Ne' 22
|
95
|
+
ye 22
|
96
|
+
_Ne 22
|
97
|
+
ek 21
|
98
|
+
_Ne'_ 21
|
99
|
+
aw 21
|
100
|
+
_kh 21
|
101
|
+
u'_ 21
|
102
|
+
,_ 21
|
103
|
+
�'_ 21
|
104
|
+
ae 21
|
105
|
+
n�' 21
|
106
|
+
ne' 21
|
107
|
+
_khu 21
|
108
|
+
hu_ 20
|
109
|
+
sa 20
|
110
|
+
�s 20
|
111
|
+
u_ 20
|
112
|
+
? 20
|
113
|
+
un 20
|
114
|
+
ne'_ 20
|
115
|
+
n�y 19
|
116
|
+
n� 19
|
117
|
+
"_ 19
|
118
|
+
�k 19
|
119
|
+
i' 19
|
120
|
+
sh 19
|
121
|
+
y� 19
|
122
|
+
as 19
|
123
|
+
iy 19
|
124
|
+
'._ 19
|
125
|
+
k� 18
|
126
|
+
'� 18
|
127
|
+
�yu 18
|
128
|
+
'� 18
|
129
|
+
ts 18
|
130
|
+
ku 18
|
131
|
+
's 18
|
132
|
+
� 18
|
133
|
+
�_ 18
|
134
|
+
�_ 18
|
135
|
+
�h 18
|
136
|
+
�yu' 17
|
137
|
+
w�n� 17
|
138
|
+
w�n�y 17
|
139
|
+
n�yu 17
|
140
|
+
�n�yu 17
|
141
|
+
_hu 17
|
142
|
+
n�yu' 17
|
143
|
+
u't 17
|
144
|
+
�k 17
|
145
|
+
t� 17
|
146
|
+
ut 17
|
147
|
+
�n�y 17
|
148
|
+
khu_ 17
|
149
|
+
�n� 17
|
150
|
+
wa' 16
|
151
|
+
si 16
|
152
|
+
us 16
|
153
|
+
T 16
|
154
|
+
_ne' 16
|
155
|
+
_s 16
|
156
|
+
t� 16
|
157
|
+
st 16
|
158
|
+
aw� 16
|
159
|
+
na 16
|
160
|
+
_na 16
|
161
|
+
n� 16
|
162
|
+
_k� 16
|
163
|
+
ae_ 15
|
164
|
+
�k 15
|
165
|
+
an 15
|
166
|
+
n- 15
|
167
|
+
_ne'_ 15
|
168
|
+
ah 15
|
169
|
+
"N 15
|
170
|
+
yu'_ 15
|
171
|
+
_a 15
|
172
|
+
ke 15
|
173
|
+
_ha 15
|
174
|
+
w� 15
|
175
|
+
�t 15
|
176
|
+
�t 15
|
177
|
+
h� 14
|
178
|
+
_un 14
|
179
|
+
ay 14
|
180
|
+
i_ 14
|
181
|
+
_n- 14
|
182
|
+
�n 14
|
183
|
+
a't 14
|
184
|
+
_"N 14
|
185
|
+
_te 14
|
186
|
+
�hs 14
|
187
|
+
y� 14
|
188
|
+
�n 13
|
189
|
+
'�_ 13
|
190
|
+
t� 13
|
191
|
+
ta' 13
|
192
|
+
k�s 13
|
193
|
+
t� 13
|
194
|
+
he 13
|
195
|
+
_khu_ 13
|
196
|
+
." 13
|
197
|
+
K 13
|
198
|
+
aw�n 13
|
199
|
+
�_ 13
|
200
|
+
aw�n� 13
|
201
|
+
't_ 13
|
202
|
+
y�_ 12
|
203
|
+
y� 12
|
204
|
+
n�_ 12
|
205
|
+
�� 12
|
206
|
+
_ka 12
|
207
|
+
tak 12
|
208
|
+
akw 12
|
209
|
+
ey 12
|
210
|
+
-a 12
|
211
|
+
_�k 12
|
212
|
+
�k 12
|
213
|
+
tw 12
|
214
|
+
we 12
|
215
|
+
?" 12
|
216
|
+
a_ 12
|
217
|
+
�n� 12
|
218
|
+
ik 12
|
219
|
+
sy 12
|
220
|
+
�' 12
|
221
|
+
ht 12
|
222
|
+
niy 11
|
223
|
+
_K 11
|
224
|
+
_ni 11
|
225
|
+
�k 11
|
226
|
+
hsa 11
|
227
|
+
�yu'_ 11
|
228
|
+
w� 11
|
229
|
+
nae 11
|
230
|
+
h� 11
|
231
|
+
uk 11
|
232
|
+
ui 11
|
233
|
+
_nae 11
|
234
|
+
ha' 11
|
235
|
+
sat 11
|
236
|
+
�n 10
|
237
|
+
_hui 10
|
238
|
+
uik� 10
|
239
|
+
_huik 10
|
240
|
+
wat 10
|
241
|
+
�� 10
|
242
|
+
u'k 10
|
243
|
+
?"_ 10
|
244
|
+
te' 10
|
245
|
+
_�hs 10
|
246
|
+
�n 10
|
247
|
+
k�_ 10
|
248
|
+
k_ 10
|
249
|
+
huik 10
|
250
|
+
tk 10
|
251
|
+
uik�_ 10
|
252
|
+
s. 10
|
253
|
+
�h 10
|
254
|
+
_sh 10
|
255
|
+
sk 10
|
256
|
+
uik 10
|
257
|
+
huik� 10
|
258
|
+
_k�s 10
|
259
|
+
w� 10
|
260
|
+
�s_ 10
|
261
|
+
hui 10
|
262
|
+
ik� 10
|
263
|
+
ya' 10
|
264
|
+
�' 10
|
265
|
+
ik�_ 10
|
266
|
+
ti 10
|
267
|
+
_�h 10
|
268
|
+
uw 10
|
269
|
+
k�s_ 9
|
270
|
+
�' 9
|
271
|
+
k�� 9
|
272
|
+
k� 9
|
273
|
+
�'_ 9
|
274
|
+
aty 9
|
275
|
+
ai 9
|
276
|
+
y� 9
|
277
|
+
-aw 9
|
278
|
+
n�t 9
|
279
|
+
aa 9
|
280
|
+
_nae_ 9
|
281
|
+
nae_ 9
|
282
|
+
'�� 9
|
283
|
+
�s 9
|
284
|
+
sn 9
|
285
|
+
a'_ 9
|
286
|
+
k� 9
|
287
|
+
hsat 9
|
288
|
+
Ka 9
|
289
|
+
', 9
|
290
|
+
y�' 9
|
291
|
+
ekh 9
|
292
|
+
eh 9
|
293
|
+
-aw�n 8
|
294
|
+
_ut 8
|
295
|
+
hsi 8
|
296
|
+
sh� 8
|
297
|
+
wai 8
|
298
|
+
si' 8
|
299
|
+
kwa' 8
|
300
|
+
N-a 8
|
301
|
+
Kan 8
|
302
|
+
_un� 8
|
303
|
+
',_ 8
|
304
|
+
�te 8
|
305
|
+
�_ 8
|
306
|
+
un� 8
|
307
|
+
N-aw� 8
|
308
|
+
Na 8
|
309
|
+
ths 8
|
310
|
+
N-aw 8
|
311
|
+
se 8
|
312
|
+
_sh� 8
|
313
|
+
_N-a 8
|
314
|
+
_N- 8
|
315
|
+
t� 8
|
316
|
+
he_ 8
|
317
|
+
_u' 8
|
318
|
+
h� 8
|
319
|
+
N- 8
|
320
|
+
_ha' 8
|
321
|
+
tek 8
|
322
|
+
_ta 8
|
323
|
+
h�_ 8
|
324
|
+
_�t 8
|
325
|
+
_N-aw 8
|
326
|
+
un� 8
|
327
|
+
_wai 8
|
328
|
+
tey 8
|
329
|
+
_t� 8
|
330
|
+
?_ 8
|
331
|
+
_T 8
|
332
|
+
'u' 8
|
333
|
+
a'k 8
|
334
|
+
kwe 8
|
335
|
+
kw� 8
|
336
|
+
ka' 8
|
337
|
+
�n 8
|
338
|
+
-aw� 8
|
339
|
+
nek 8
|
340
|
+
twa 8
|
341
|
+
w�t 8
|
342
|
+
'u 8
|
343
|
+
kn 7
|
344
|
+
w�_ 7
|
345
|
+
_Ka 7
|
346
|
+
_y 7
|
347
|
+
a� 7
|
348
|
+
_he 7
|
349
|
+
a'u 7
|
350
|
+
kw� 7
|
351
|
+
S 7
|
352
|
+
N�_ 7
|
353
|
+
a'u' 7
|
354
|
+
niyu 7
|
355
|
+
't� 7
|
356
|
+
nya 7
|
357
|
+
�t_ 7
|
358
|
+
_wai_ 7
|
359
|
+
�'_ 7
|
360
|
+
'h 7
|
361
|
+
iyu 7
|
362
|
+
_ts 7
|
363
|
+
ya't 7
|
364
|
+
�_ 7
|
365
|
+
w�' 7
|
366
|
+
�� 7
|
367
|
+
k�' 7
|
368
|
+
u't_ 7
|
369
|
+
y� 7
|
370
|
+
�'s 7
|
371
|
+
ata 7
|
372
|
+
N� 7
|
373
|
+
u't� 7
|
374
|
+
�y 7
|
375
|
+
tsi 7
|
376
|
+
ai_ 7
|
377
|
+
_un�_ 7
|
378
|
+
_uk 7
|
379
|
+
_he_ 7
|
380
|
+
"T 7
|
381
|
+
��' 7
|
382
|
+
�th 7
|
383
|
+
�� 7
|
384
|
+
_kw 7
|
385
|
+
'� 7
|
386
|
+
ust 7
|
387
|
+
y�'_ 7
|
388
|
+
'? 7
|
389
|
+
un�_ 7
|
390
|
+
wai_ 7
|
391
|
+
s._ 7
|
392
|
+
�' 7
|
393
|
+
ku' 7
|
394
|
+
hah 7
|
395
|
+
�ka 7
|
396
|
+
a'u't 7
|
397
|
+
wi 7
|
398
|
+
�'� 7
|
399
|
+
H 7
|
400
|
+
ahs 7
|