scylla 0.4.3 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +1 -0
- data/Gemfile.lock +10 -0
- data/VERSION +1 -1
- data/lib/scylla/generator.rb +1 -1
- data/lib/scylla/lms/13375P33K.lm +156 -156
- data/lib/scylla/lms/arabic.lm +133 -133
- data/lib/scylla/lms/bulgarian.lm +122 -122
- data/lib/scylla/lms/catalan.lm +151 -151
- data/lib/scylla/lms/danish.lm +137 -137
- data/lib/scylla/lms/english.lm +207 -207
- data/lib/scylla/lms/french.lm +400 -400
- data/lib/scylla/lms/japanese.lm +400 -400
- data/lib/scylla/lms/korean.lm +233 -233
- data/lib/scylla/lms/norwegian.lm +398 -398
- data/lib/scylla/lms/spanish.lm +98 -98
- data/lib/scylla/lms/swedish.lm +123 -123
- data/lib/scylla/lms/tagalog.lm +223 -223
- data/lib/scylla/lms/welsh.lm +234 -234
- data/lib/scylla/resources.rb +10 -10
- data/scylla.gemspec +17 -40
- data/source_texts/catalan.txt +28 -28
- data/source_texts/danish.txt +62 -62
- data/source_texts/english.txt +10 -10
- data/source_texts/french.txt +470 -77
- data/source_texts/japanese.txt +453 -199
- data/source_texts/norwegian.txt +96 -63
- data/source_texts/spanish.txt +269 -269
- data/test/classifier_test.rb +2 -2
- data/test/fixtures/lms/13375p33k.lm +156 -156
- data/test/fixtures/lms/danish.lm +137 -137
- data/test/fixtures/lms/english.lm +207 -207
- data/test/fixtures/lms/french.lm +400 -400
- data/test/fixtures/lms/hindi.lm +400 -0
- data/test/fixtures/lms/italian.lm +400 -0
- data/test/fixtures/lms/japanese.lm +400 -400
- data/test/fixtures/lms/norwegian.lm +400 -0
- data/test/fixtures/lms/spanish.lm +98 -98
- data/test/fixtures/source_texts/danish.txt +62 -62
- data/test/fixtures/source_texts/english.txt +10 -10
- data/test/fixtures/source_texts/french.txt +470 -77
- data/test/fixtures/source_texts/hindi.txt +199 -0
- data/test/fixtures/source_texts/italian.txt +120 -0
- data/test/fixtures/source_texts/japanese.txt +453 -199
- data/test/fixtures/source_texts/norwegian.txt +190 -0
- data/test/fixtures/source_texts/spanish.txt +269 -269
- data/test/fixtures/test_languages/english +61 -0
- data/test/fixtures/test_languages/french +0 -0
- data/test/fixtures/test_languages/german +29 -0
- data/test/fixtures/test_languages/hindi +3 -0
- data/test/fixtures/test_languages/italian +6 -0
- data/test/fixtures/test_languages/japanese +79 -0
- data/test/fixtures/test_languages/norwegian +14 -0
- data/test/fixtures/test_languages/spanish +22 -0
- data/test/generator_test.rb +0 -1
- data/test/language_test.rb +28 -0
- metadata +20 -43
- data/lib/scylla/lms/esperanto.lm +0 -400
- data/lib/scylla/lms/hungarian.lm +0 -400
- data/lib/scylla/lms/irish.lm +0 -400
- data/lib/scylla/lms/kannada.lm +0 -400
- data/lib/scylla/lms/latin.lm +0 -400
- data/lib/scylla/lms/malay.lm +0 -400
- data/lib/scylla/lms/marathi.lm +0 -400
- data/lib/scylla/lms/mingo.lm +0 -400
- data/lib/scylla/lms/nepali.lm +0 -400
- data/lib/scylla/lms/quechua.lm +0 -400
- data/lib/scylla/lms/rumantsch.lm +0 -400
- data/lib/scylla/lms/sanskrit.lm +0 -400
- data/lib/scylla/lms/scots_gaelic.lm +0 -400
- data/lib/scylla/lms/serbian.lm +0 -400
- data/lib/scylla/lms/swahili.lm +0 -400
- data/lib/scylla/lms/tamil.lm +0 -400
- data/lib/scylla/lms/ukrainian.lm +0 -400
- data/lib/scylla/lms/yiddish.lm +0 -400
- data/source_texts/esperanto.txt +0 -199
- data/source_texts/hungarian.txt +0 -102
- data/source_texts/irish.txt +0 -209
- data/source_texts/kannada.txt +0 -283
- data/source_texts/latin.txt +0 -120
- data/source_texts/malay.txt +0 -108
- data/source_texts/marathi.txt +0 -100
- data/source_texts/mingo.txt +0 -146
- data/source_texts/nepali.txt +0 -131
- data/source_texts/quechua.txt +0 -108
- data/source_texts/rumantsch.txt +0 -110
- data/source_texts/sanskrit.txt +0 -135
- data/source_texts/scots_gaelic.txt +0 -93
- data/source_texts/serbian.txt +0 -121
- data/source_texts/swahili.txt +0 -120
- data/source_texts/tamil.txt +0 -167
- data/source_texts/ukrainian.txt +0 -214
- data/source_texts/yiddish-utf.txt +0 -83
- data/test/fixtures/lms/kannada.lm +0 -400
- data/test/fixtures/source_texts/kannada.txt +0 -283
data/lib/scylla/lms/tagalog.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 1358
|
2
2
|
a 856
|
3
3
|
n 460
|
4
4
|
i 336
|
@@ -9,14 +9,14 @@ g_ 175
|
|
9
9
|
o 173
|
10
10
|
ng_ 169
|
11
11
|
a_ 156
|
12
|
-
an 155
|
13
12
|
k 155
|
13
|
+
an 155
|
14
14
|
s 150
|
15
15
|
l 147
|
16
16
|
_n 132
|
17
17
|
m 131
|
18
|
-
y 105
|
19
18
|
p 105
|
19
|
+
y 105
|
20
20
|
u 103
|
21
21
|
na 101
|
22
22
|
ang 98
|
@@ -26,14 +26,14 @@ la 80
|
|
26
26
|
in 79
|
27
27
|
_a 77
|
28
28
|
r 77
|
29
|
-
ka 72
|
30
29
|
b 72
|
30
|
+
ka 72
|
31
31
|
sa 67
|
32
32
|
ak 67
|
33
|
-
_m 65
|
34
33
|
pa 65
|
35
|
-
|
34
|
+
_m 65
|
36
35
|
ma 64
|
36
|
+
_s 64
|
37
37
|
h 63
|
38
38
|
_na 61
|
39
39
|
d 57
|
@@ -46,355 +46,355 @@ _k 45
|
|
46
46
|
ni 45
|
47
47
|
t_ 44
|
48
48
|
_sa 43
|
49
|
-
n_ 42
|
50
49
|
" 42
|
51
50
|
ya 42
|
52
51
|
_ng 42
|
52
|
+
n_ 42
|
53
53
|
ay 41
|
54
54
|
it 40
|
55
55
|
_pa 40
|
56
56
|
ga 39
|
57
|
-
on 39
|
58
57
|
e 39
|
58
|
+
on 39
|
59
59
|
sa_ 38
|
60
60
|
y_ 37
|
61
61
|
iy 36
|
62
62
|
il 36
|
63
|
-
ala 35
|
64
63
|
o_ 35
|
64
|
+
ala 35
|
65
65
|
w 35
|
66
66
|
_ng_ 34
|
67
67
|
am 34
|
68
|
+
._ 33
|
68
69
|
_sa_ 33
|
70
|
+
i_ 32
|
69
71
|
_ma 32
|
70
72
|
na_ 32
|
71
|
-
i_ 32
|
72
|
-
._ 32
|
73
73
|
_an 31
|
74
74
|
ra 31
|
75
75
|
, 31
|
76
76
|
ba 30
|
77
|
-
|
77
|
+
_t 29
|
78
|
+
iya 29
|
78
79
|
_ang_ 29
|
79
80
|
_ni 29
|
81
|
+
_ang 29
|
80
82
|
ar 29
|
81
|
-
iya 29
|
82
|
-
_t 29
|
83
83
|
_i 28
|
84
84
|
_ka 28
|
85
|
-
li 27
|
86
85
|
_l 27
|
87
|
-
|
86
|
+
,_ 27
|
88
87
|
as 27
|
89
|
-
is 27
|
90
|
-
aka 27
|
91
88
|
hi 27
|
92
|
-
,_ 27
|
93
89
|
ong 27
|
94
|
-
|
90
|
+
ha 27
|
91
|
+
is 27
|
92
|
+
aka 27
|
93
|
+
li 27
|
95
94
|
ko 26
|
96
95
|
gi 26
|
97
|
-
|
98
|
-
ap 25
|
96
|
+
_na_ 26
|
99
97
|
to 25
|
98
|
+
ap 25
|
99
|
+
ri 25
|
100
|
+
lan 24
|
101
|
+
ay_ 24
|
100
102
|
ong_ 24
|
101
103
|
un 24
|
102
104
|
ah 24
|
103
|
-
lan 24
|
104
|
-
ay_ 24
|
105
105
|
ata 23
|
106
|
+
ing 23
|
106
107
|
um 23
|
107
|
-
si 23
|
108
|
-
wa 23
|
109
108
|
o. 23
|
110
|
-
ing 23
|
111
109
|
di 23
|
112
|
-
|
110
|
+
si 23
|
111
|
+
wa 23
|
113
112
|
ti 22
|
114
113
|
s_ 22
|
115
|
-
|
114
|
+
ki 22
|
116
115
|
niy 21
|
117
|
-
_d 21
|
118
116
|
ab 21
|
119
|
-
|
120
|
-
an_ 21
|
117
|
+
_d 21
|
121
118
|
niya 21
|
119
|
+
_niy 21
|
122
120
|
mo 21
|
121
|
+
an_ 21
|
122
|
+
_niya 21
|
123
|
+
a. 20
|
123
124
|
at_ 20
|
124
125
|
N 20
|
125
|
-
a. 20
|
126
|
-
ila 19
|
127
|
-
ot 19
|
128
126
|
yo 19
|
127
|
+
ila 19
|
129
128
|
- 19
|
129
|
+
ot 19
|
130
130
|
aw 19
|
131
|
+
_mo 18
|
131
132
|
nga 18
|
132
133
|
_ak 18
|
133
134
|
ig 18
|
134
|
-
_mo 18
|
135
|
-
lang 18
|
136
135
|
A 18
|
136
|
+
lang 18
|
137
137
|
nag 17
|
138
138
|
ama 17
|
139
139
|
tu 17
|
140
|
-
in_ 16
|
141
|
-
_b 16
|
142
|
-
ali 16
|
143
140
|
ina 16
|
144
|
-
aki 16
|
145
|
-
ara 16
|
146
141
|
P 16
|
142
|
+
in_ 16
|
143
|
+
ali 16
|
147
144
|
"_ 16
|
148
|
-
|
145
|
+
ara 16
|
146
|
+
_b 16
|
147
|
+
aki 16
|
149
148
|
' 15
|
150
|
-
ing_ 15
|
151
149
|
lang_ 15
|
150
|
+
_at 15
|
152
151
|
_si 15
|
152
|
+
ing_ 15
|
153
|
+
o._ 14
|
153
154
|
ai 14
|
154
|
-
|
155
|
+
ib 14
|
156
|
+
nd 14
|
155
157
|
aa 14
|
156
158
|
_r 14
|
157
|
-
ga_ 14
|
158
|
-
o._ 14
|
159
|
-
nd 14
|
160
|
-
ib 14
|
161
159
|
da 14
|
162
|
-
|
160
|
+
bi 14
|
161
|
+
ga_ 14
|
163
162
|
ro 13
|
164
|
-
iya_ 13
|
165
|
-
lo 13
|
166
|
-
ito 13
|
167
163
|
_at_ 13
|
164
|
+
hin 13
|
165
|
+
ito 13
|
166
|
+
lo 13
|
168
167
|
ik 13
|
169
|
-
_h 13
|
170
168
|
ako 13
|
171
169
|
ya_ 13
|
172
|
-
|
173
|
-
|
170
|
+
_h 13
|
171
|
+
iya_ 13
|
174
172
|
la_ 12
|
175
|
-
_la 12
|
176
|
-
Na 12
|
177
|
-
mag 12
|
178
|
-
S 12
|
179
173
|
rin 12
|
180
|
-
|
174
|
+
Na 12
|
181
175
|
K 12
|
176
|
+
ul 12
|
177
|
+
S 12
|
182
178
|
ahi 12
|
183
|
-
|
184
|
-
|
185
|
-
|
179
|
+
_ta 12
|
180
|
+
_la 12
|
181
|
+
a, 12
|
182
|
+
mag 12
|
186
183
|
k_ 11
|
187
|
-
|
188
|
-
|
189
|
-
." 11
|
190
|
-
gk 11
|
191
|
-
kin 11
|
184
|
+
pan 11
|
185
|
+
_tu 11
|
192
186
|
mi 11
|
193
|
-
|
194
|
-
'y_ 11
|
187
|
+
a,_ 11
|
195
188
|
asa 11
|
196
|
-
M 11
|
197
|
-
_mag 11
|
198
189
|
ilan 11
|
199
190
|
apa 11
|
191
|
+
kin 11
|
192
|
+
_mag 11
|
193
|
+
'y 11
|
194
|
+
'y_ 11
|
195
|
+
gk 11
|
196
|
+
lu 11
|
197
|
+
_ri 11
|
198
|
+
man 11
|
199
|
+
go 11
|
200
|
+
M 11
|
200
201
|
ung 11
|
201
|
-
|
202
|
-
pan 11
|
202
|
+
." 11
|
203
203
|
_di 11
|
204
|
-
|
205
|
-
Ma 10
|
204
|
+
mga 10
|
206
205
|
is_ 10
|
207
206
|
wal 10
|
208
207
|
nak 10
|
209
|
-
|
210
|
-
|
211
|
-
|
208
|
+
_N 10
|
209
|
+
awa 10
|
210
|
+
ot_ 10
|
212
211
|
yon 10
|
213
|
-
|
214
|
-
|
215
|
-
ir 10
|
216
|
-
ilang 10
|
217
|
-
mga_ 10
|
212
|
+
_is 10
|
213
|
+
pa_ 10
|
218
214
|
su 10
|
219
|
-
|
220
|
-
yan 10
|
215
|
+
_K 10
|
221
216
|
agk 10
|
217
|
+
mga_ 10
|
218
|
+
mu 10
|
219
|
+
yan 10
|
222
220
|
.. 10
|
223
|
-
|
224
|
-
awa 10
|
221
|
+
ir 10
|
225
222
|
Ka 10
|
226
|
-
wala 10
|
227
|
-
pi 10
|
228
223
|
akin 10
|
224
|
+
wala 10
|
229
225
|
ari 10
|
226
|
+
ilang 10
|
227
|
+
pi 10
|
228
|
+
uma 10
|
229
|
+
I 10
|
230
|
+
mg 10
|
231
|
+
Ma 10
|
232
|
+
it_ 9
|
233
|
+
n, 9
|
234
|
+
_akin 9
|
235
|
+
gka 9
|
230
236
|
_aki 9
|
231
|
-
An 9
|
232
|
-
_K 9
|
233
|
-
ini 9
|
234
|
-
pu 9
|
235
|
-
no 9
|
236
|
-
aba 9
|
237
|
-
_mg 9
|
238
|
-
n. 9
|
239
|
-
_mga_ 9
|
240
|
-
_mga 9
|
241
237
|
agka 9
|
242
|
-
|
243
|
-
isa 9
|
244
|
-
n, 9
|
245
|
-
_A 9
|
238
|
+
n. 9
|
246
239
|
pag 9
|
247
|
-
alan 9
|
248
|
-
nan 9
|
249
240
|
san 9
|
250
|
-
|
251
|
-
|
252
|
-
|
253
|
-
|
254
|
-
|
255
|
-
|
256
|
-
|
257
|
-
|
241
|
+
no 9
|
242
|
+
isa 9
|
243
|
+
nan 9
|
244
|
+
_mga 9
|
245
|
+
_mg 9
|
246
|
+
pu 9
|
247
|
+
alan 9
|
248
|
+
_A 9
|
249
|
+
_mga_ 9
|
250
|
+
ini 9
|
251
|
+
An 9
|
252
|
+
aba 9
|
253
|
+
_Ka 9
|
258
254
|
aha 8
|
259
|
-
|
255
|
+
aman 8
|
256
|
+
p_ 8
|
260
257
|
ob 8
|
258
|
+
_lu 8
|
259
|
+
_ba 8
|
260
|
+
ayo 8
|
261
261
|
si_ 8
|
262
|
-
|
263
|
-
_nag 8
|
264
|
-
_wa 8
|
265
|
-
dib 8
|
266
|
-
niya_ 8
|
267
|
-
mat 8
|
268
|
-
alang 8
|
269
|
-
aman 8
|
270
|
-
ngi 8
|
262
|
+
_w 8
|
271
263
|
ili 8
|
272
|
-
|
273
|
-
|
274
|
-
Pa 8
|
275
|
-
l_ 8
|
264
|
+
king 8
|
265
|
+
_P 8
|
276
266
|
di_ 8
|
277
|
-
tay 8
|
278
|
-
_Ka 8
|
279
267
|
iti 8
|
280
|
-
|
268
|
+
niya_ 8
|
269
|
+
yang 8
|
270
|
+
as_ 8
|
271
|
+
mo_ 8
|
272
|
+
aga 8
|
273
|
+
_nag 8
|
281
274
|
aking 8
|
282
|
-
|
275
|
+
tan 8
|
276
|
+
tay 8
|
277
|
+
dib 8
|
278
|
+
a' 8
|
283
279
|
abi 8
|
284
|
-
|
285
|
-
|
280
|
+
l_ 8
|
281
|
+
_wala 8
|
282
|
+
naka 8
|
286
283
|
_wal 8
|
287
|
-
|
288
|
-
|
289
|
-
|
290
|
-
|
291
|
-
|
292
|
-
|
293
|
-
|
294
|
-
|
295
|
-
|
296
|
-
|
284
|
+
alang 8
|
285
|
+
t. 8
|
286
|
+
umi 8
|
287
|
+
Pa 8
|
288
|
+
ngi 8
|
289
|
+
_ako 8
|
290
|
+
_wa 8
|
291
|
+
igi 8
|
292
|
+
mat 8
|
293
|
+
e_ 7
|
297
294
|
_pag 7
|
298
|
-
|
299
|
-
|
300
|
-
|
295
|
+
tin 7
|
296
|
+
_M 7
|
297
|
+
ra_ 7
|
301
298
|
B 7
|
302
|
-
|
303
|
-
|
304
|
-
|
305
|
-
|
306
|
-
o, 7
|
299
|
+
kat 7
|
300
|
+
_Na 7
|
301
|
+
ip 7
|
302
|
+
_isa 7
|
307
303
|
king_ 7
|
308
|
-
|
309
|
-
|
304
|
+
g- 7
|
305
|
+
.n 7
|
306
|
+
ban 7
|
307
|
+
oo 7
|
308
|
+
gin 7
|
309
|
+
er 7
|
310
310
|
iyo 7
|
311
|
-
|
311
|
+
ut 7
|
312
|
+
ram 7
|
313
|
+
tak 7
|
314
|
+
_ko 7
|
315
|
+
ail 7
|
312
316
|
n,_ 7
|
313
317
|
o' 7
|
314
|
-
|
318
|
+
_An 7
|
315
319
|
_pa_ 7
|
320
|
+
lis 7
|
321
|
+
o, 7
|
316
322
|
ala_ 7
|
323
|
+
ka_ 7
|
324
|
+
ku 7
|
325
|
+
a._ 7
|
326
|
+
tat 7
|
327
|
+
kan 7
|
328
|
+
_mo_ 7
|
329
|
+
_si_ 7
|
317
330
|
bo 7
|
318
|
-
|
319
|
-
|
320
|
-
|
321
|
-
|
322
|
-
oo 7
|
323
|
-
gin 7
|
331
|
+
to_ 7
|
332
|
+
pak 7
|
333
|
+
_rin 7
|
334
|
+
tum 7
|
324
335
|
tang 7
|
325
|
-
|
326
|
-
lis 7
|
327
|
-
ban 7
|
328
|
-
_si_ 7
|
329
|
-
ram 7
|
330
|
-
ip 7
|
331
|
-
ka_ 7
|
332
|
-
tin 7
|
336
|
+
anga 7
|
333
337
|
ana 7
|
334
|
-
|
335
|
-
|
336
|
-
|
337
|
-
|
338
|
-
|
339
|
-
|
340
|
-
ago 6
|
338
|
+
mata 7
|
339
|
+
ita 6
|
340
|
+
o'y_ 6
|
341
|
+
pal 6
|
342
|
+
_iyo 6
|
343
|
+
?" 6
|
341
344
|
lis_ 6
|
342
|
-
|
343
|
-
|
344
|
-
|
345
|
-
|
346
|
-
ung_ 6
|
345
|
+
_ku 6
|
346
|
+
nit 6
|
347
|
+
up 6
|
348
|
+
st 6
|
347
349
|
par 6
|
348
|
-
|
350
|
+
_hi 6
|
351
|
+
_" 6
|
349
352
|
man_ 6
|
350
|
-
up 6
|
351
|
-
pal 6
|
352
353
|
nang 6
|
353
|
-
|
354
|
-
|
355
|
-
|
354
|
+
ung_ 6
|
355
|
+
ak_ 6
|
356
|
+
walan 6
|
357
|
+
os 6
|
356
358
|
aila 6
|
357
|
-
|
358
|
-
|
359
|
-
|
360
|
-
|
361
|
-
nit 6
|
362
|
-
isan 6
|
359
|
+
ig_ 6
|
360
|
+
ag- 6
|
361
|
+
yang_ 6
|
362
|
+
? 6
|
363
363
|
sang 6
|
364
|
-
|
364
|
+
d_ 6
|
365
365
|
_mu 6
|
366
|
+
mb 6
|
366
367
|
o'y 6
|
367
|
-
Sa 6
|
368
|
-
_S 6
|
369
|
-
c 6
|
370
368
|
_tum 6
|
371
|
-
mb 6
|
372
|
-
kun 6
|
373
|
-
tata 6
|
374
|
-
_par 6
|
375
|
-
_ha 6
|
376
|
-
? 6
|
377
|
-
mba 6
|
378
|
-
yang_ 6
|
379
|
-
gay 6
|
380
369
|
ap_ 6
|
381
370
|
bang 6
|
382
|
-
|
371
|
+
gay 6
|
372
|
+
_par 6
|
383
373
|
im 6
|
384
|
-
|
385
|
-
|
386
|
-
|
387
|
-
|
374
|
+
ago 6
|
375
|
+
_S 6
|
376
|
+
kaka 6
|
377
|
+
siya 6
|
378
|
+
_ha 6
|
379
|
+
c 6
|
380
|
+
_iy 6
|
381
|
+
siy 6
|
382
|
+
tang_ 6
|
383
|
+
_nga 6
|
384
|
+
kun 6
|
385
|
+
Sa 6
|
386
|
+
isan 6
|
387
|
+
kah 6
|
388
388
|
una 6
|
389
|
+
agi 6
|
390
|
+
.na 6
|
391
|
+
kak 6
|
389
392
|
_Ma 6
|
390
|
-
ak_ 6
|
391
|
-
_hi 6
|
392
|
-
st 6
|
393
|
-
o'y_ 6
|
394
|
-
ita 6
|
395
|
-
_ku 6
|
396
|
-
gan 6
|
397
|
-
walan 6
|
398
|
-
kaka 6
|
399
|
-
_iyo 6
|
400
393
|
o." 6
|
394
|
+
o,_ 6
|
395
|
+
_I 6
|
396
|
+
tata 6
|
397
|
+
nt 6
|
398
|
+
ula 6
|
399
|
+
mba 6
|
400
|
+
isang 6
|