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
|
+
_ 1216
|
2
|
+
e 644
|
3
|
+
n 386
|
4
|
+
i 318
|
5
|
+
r 306
|
6
|
+
t 253
|
7
|
+
s 218
|
8
|
+
a 197
|
9
|
+
h 190
|
10
|
+
d 187
|
11
|
+
u 161
|
12
|
+
en 137
|
13
|
+
er 137
|
14
|
+
l 131
|
15
|
+
c 125
|
16
|
+
o 116
|
17
|
+
ch 112
|
18
|
+
g 105
|
19
|
+
m 101
|
20
|
+
e_ 98
|
21
|
+
n_ 88
|
22
|
+
te 80
|
23
|
+
in 77
|
24
|
+
_d 76
|
25
|
+
de 76
|
26
|
+
ei 73
|
27
|
+
r_ 72
|
28
|
+
k 68
|
29
|
+
b 66
|
30
|
+
f 58
|
31
|
+
un 56
|
32
|
+
ie 54
|
33
|
+
er_ 53
|
34
|
+
nd 52
|
35
|
+
w 50
|
36
|
+
en_ 49
|
37
|
+
_e 48
|
38
|
+
ge 48
|
39
|
+
__ 46
|
40
|
+
ng 45
|
41
|
+
t_ 44
|
42
|
+
, 42
|
43
|
+
der 41
|
44
|
+
ne 39
|
45
|
+
st 39
|
46
|
+
. 36
|
47
|
+
,_ 36
|
48
|
+
z 36
|
49
|
+
he 36
|
50
|
+
_s 36
|
51
|
+
re 34
|
52
|
+
s_ 34
|
53
|
+
m_ 34
|
54
|
+
di 34
|
55
|
+
es 33
|
56
|
+
it 33
|
57
|
+
v 33
|
58
|
+
_de 32
|
59
|
+
ie_ 32
|
60
|
+
_i 32
|
61
|
+
be 31
|
62
|
+
au 31
|
63
|
+
ein 31
|
64
|
+
S 31
|
65
|
+
ti 30
|
66
|
+
" 30
|
67
|
+
� 29
|
68
|
+
_a 29
|
69
|
+
ic 29
|
70
|
+
_w 28
|
71
|
+
� 28
|
72
|
+
d_ 28
|
73
|
+
le 28
|
74
|
+
sch 27
|
75
|
+
sc 27
|
76
|
+
nt 26
|
77
|
+
ung 26
|
78
|
+
si 25
|
79
|
+
ich 25
|
80
|
+
die 25
|
81
|
+
is 25
|
82
|
+
an 25
|
83
|
+
p 24
|
84
|
+
che 24
|
85
|
+
or 24
|
86
|
+
el 24
|
87
|
+
al 23
|
88
|
+
der_ 23
|
89
|
+
_die 23
|
90
|
+
_di 23
|
91
|
+
nd_ 23
|
92
|
+
on 23
|
93
|
+
h_ 22
|
94
|
+
rt 22
|
95
|
+
_ei 21
|
96
|
+
li 21
|
97
|
+
_S 21
|
98
|
+
ten 21
|
99
|
+
ra 21
|
100
|
+
und 21
|
101
|
+
em 21
|
102
|
+
ht 21
|
103
|
+
_ein 21
|
104
|
+
die_ 21
|
105
|
+
ch_ 20
|
106
|
+
at 20
|
107
|
+
hr 20
|
108
|
+
ke 20
|
109
|
+
in_ 20
|
110
|
+
ur 19
|
111
|
+
_die_ 19
|
112
|
+
A 19
|
113
|
+
_v 19
|
114
|
+
me 19
|
115
|
+
ns 18
|
116
|
+
ll 18
|
117
|
+
_der 18
|
118
|
+
ine 18
|
119
|
+
_in 18
|
120
|
+
se 18
|
121
|
+
ter 17
|
122
|
+
L 17
|
123
|
+
nge 17
|
124
|
+
ri 17
|
125
|
+
eine 17
|
126
|
+
eit 17
|
127
|
+
im 17
|
128
|
+
ar 17
|
129
|
+
den 16
|
130
|
+
gen 16
|
131
|
+
D 16
|
132
|
+
da 16
|
133
|
+
we 16
|
134
|
+
_h 15
|
135
|
+
ig 15
|
136
|
+
eu 15
|
137
|
+
K 15
|
138
|
+
cht 15
|
139
|
+
._ 15
|
140
|
+
zu 15
|
141
|
+
_er 15
|
142
|
+
F 15
|
143
|
+
_au 14
|
144
|
+
ac 14
|
145
|
+
und_ 14
|
146
|
+
te_ 14
|
147
|
+
mm 14
|
148
|
+
rs 14
|
149
|
+
E 14
|
150
|
+
ach 14
|
151
|
+
eh 14
|
152
|
+
vo 14
|
153
|
+
ha 14
|
154
|
+
_A 14
|
155
|
+
nde 14
|
156
|
+
us 14
|
157
|
+
� 13
|
158
|
+
_L 13
|
159
|
+
_si 13
|
160
|
+
ls 13
|
161
|
+
fe 13
|
162
|
+
ab 13
|
163
|
+
n. 13
|
164
|
+
� 13
|
165
|
+
�r 13
|
166
|
+
B 13
|
167
|
+
et 12
|
168
|
+
lic 12
|
169
|
+
em_ 12
|
170
|
+
wi 12
|
171
|
+
nte 12
|
172
|
+
_da 12
|
173
|
+
am 12
|
174
|
+
ste 12
|
175
|
+
rn 12
|
176
|
+
lle 12
|
177
|
+
as 12
|
178
|
+
R 12
|
179
|
+
_z 12
|
180
|
+
rk 12
|
181
|
+
_u 12
|
182
|
+
rd 12
|
183
|
+
T 12
|
184
|
+
_b 12
|
185
|
+
uf 11
|
186
|
+
tr 11
|
187
|
+
U 11
|
188
|
+
rte 11
|
189
|
+
g_ 11
|
190
|
+
ge_ 11
|
191
|
+
- 11
|
192
|
+
_eine 11
|
193
|
+
hl 11
|
194
|
+
Sc 11
|
195
|
+
ck 11
|
196
|
+
ts 11
|
197
|
+
lich 11
|
198
|
+
ni 11
|
199
|
+
ers 11
|
200
|
+
_D 11
|
201
|
+
ve 11
|
202
|
+
Sch 11
|
203
|
+
_n 11
|
204
|
+
G 11
|
205
|
+
ent 11
|
206
|
+
ru 11
|
207
|
+
_der_ 11
|
208
|
+
tt 11
|
209
|
+
_in_ 11
|
210
|
+
f� 11
|
211
|
+
men 11
|
212
|
+
ren 11
|
213
|
+
nn 11
|
214
|
+
_g 10
|
215
|
+
f�r 10
|
216
|
+
na 10
|
217
|
+
rc 10
|
218
|
+
ht_ 10
|
219
|
+
nder 10
|
220
|
+
�r_ 10
|
221
|
+
hi 10
|
222
|
+
sin 10
|
223
|
+
on_ 10
|
224
|
+
_B 10
|
225
|
+
isc 10
|
226
|
+
um 10
|
227
|
+
_" 10
|
228
|
+
ut 10
|
229
|
+
isch 10
|
230
|
+
auf 10
|
231
|
+
_K 10
|
232
|
+
gs 10
|
233
|
+
n, 10
|
234
|
+
en. 10
|
235
|
+
_F 10
|
236
|
+
_vo 10
|
237
|
+
als 10
|
238
|
+
sa 10
|
239
|
+
_zu 10
|
240
|
+
nen 9
|
241
|
+
ungs 9
|
242
|
+
_be 9
|
243
|
+
_E 9
|
244
|
+
chen 9
|
245
|
+
hen 9
|
246
|
+
_Sch 9
|
247
|
+
den_ 9
|
248
|
+
it_ 9
|
249
|
+
_Sc 9
|
250
|
+
hre 9
|
251
|
+
O 9
|
252
|
+
ma 9
|
253
|
+
_T 9
|
254
|
+
ngs 9
|
255
|
+
ere 9
|
256
|
+
f�r_ 9
|
257
|
+
k_ 9
|
258
|
+
rch 9
|
259
|
+
lt 9
|
260
|
+
ze 9
|
261
|
+
ver 9
|
262
|
+
e, 9
|
263
|
+
ten_ 9
|
264
|
+
ik 9
|
265
|
+
il 9
|
266
|
+
erk 9
|
267
|
+
Un 9
|
268
|
+
no 9
|
269
|
+
M 9
|
270
|
+
so 9
|
271
|
+
om 9
|
272
|
+
_un 8
|
273
|
+
V 8
|
274
|
+
sich 8
|
275
|
+
le_ 8
|
276
|
+
sp 8
|
277
|
+
_k 8
|
278
|
+
od 8
|
279
|
+
n,_ 8
|
280
|
+
urc 8
|
281
|
+
_ha 8
|
282
|
+
uc 8
|
283
|
+
run 8
|
284
|
+
tra 8
|
285
|
+
ber 8
|
286
|
+
end 8
|
287
|
+
ir 8
|
288
|
+
du 8
|
289
|
+
ind 8
|
290
|
+
ng_ 8
|
291
|
+
bei 8
|
292
|
+
ner 8
|
293
|
+
sic 8
|
294
|
+
_Un 8
|
295
|
+
_U 8
|
296
|
+
tig 8
|
297
|
+
"_ 8
|
298
|
+
es_ 8
|
299
|
+
e,_ 8
|
300
|
+
ute 8
|
301
|
+
ft 8
|
302
|
+
mme 8
|
303
|
+
wo 8
|
304
|
+
ls_ 8
|
305
|
+
kei 8
|
306
|
+
_G 8
|
307
|
+
Le 8
|
308
|
+
das 8
|
309
|
+
_Le 8
|
310
|
+
ol 8
|
311
|
+
ens 8
|
312
|
+
rde 8
|
313
|
+
la 8
|
314
|
+
_f 8
|
315
|
+
en, 7
|
316
|
+
H 7
|
317
|
+
do 7
|
318
|
+
uch 7
|
319
|
+
_ve 7
|
320
|
+
rei 7
|
321
|
+
r� 7
|
322
|
+
eute 7
|
323
|
+
ih 7
|
324
|
+
ngen 7
|
325
|
+
ho 7
|
326
|
+
ko 7
|
327
|
+
eb 7
|
328
|
+
des 7
|
329
|
+
ne_ 7
|
330
|
+
y 7
|
331
|
+
eut 7
|
332
|
+
ein_ 7
|
333
|
+
mi 7
|
334
|
+
das_ 7
|
335
|
+
dur 7
|
336
|
+
St 7
|
337
|
+
ert 7
|
338
|
+
sti 7
|
339
|
+
von 7
|
340
|
+
_o 7
|
341
|
+
_al 7
|
342
|
+
urch 7
|
343
|
+
Leu 7
|
344
|
+
ich_ 7
|
345
|
+
tte 7
|
346
|
+
_wi 7
|
347
|
+
_und_ 7
|
348
|
+
hat 7
|
349
|
+
icht 7
|
350
|
+
durc 7
|
351
|
+
_das 7
|
352
|
+
ba 7
|
353
|
+
durch 7
|
354
|
+
ode 7
|
355
|
+
ing 7
|
356
|
+
_ver 7
|
357
|
+
_Leu 7
|
358
|
+
im_ 7
|
359
|
+
als_ 7
|
360
|
+
and 7
|
361
|
+
unge 7
|
362
|
+
P 7
|
363
|
+
f_ 7
|
364
|
+
len 7
|
365
|
+
nh 7
|
366
|
+
as_ 7
|
367
|
+
io 7
|
368
|
+
_und 7
|
369
|
+
keit 7
|
370
|
+
eg 6
|
371
|
+
eute_ 6
|
372
|
+
ren_ 6
|
373
|
+
auch 6
|
374
|
+
_von 6
|
375
|
+
erst 6
|
376
|
+
_ih 6
|
377
|
+
nge_ 6
|
378
|
+
gu 6
|
379
|
+
nsi 6
|
380
|
+
wa 6
|
381
|
+
ss 6
|
382
|
+
chl 6
|
383
|
+
dor 6
|
384
|
+
N 6
|
385
|
+
_er_ 6
|
386
|
+
ute_ 6
|
387
|
+
ue 6
|
388
|
+
lte 6
|
389
|
+
auc 6
|
390
|
+
sk 6
|
391
|
+
he_ 6
|
392
|
+
_we 6
|
393
|
+
_sich 6
|
394
|
+
l_ 6
|
395
|
+
_f�r 6
|
396
|
+
u_ 6
|
397
|
+
ene 6
|
398
|
+
ed 6
|
399
|
+
imm 6
|
400
|
+
e. 6
|