psychowl 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/CHANGELOG.md +21 -0
- data/LICENSE.txt +21 -0
- data/README.md +212 -0
- data/exe/psychowl +106 -0
- data/ext/psychowl_native/core/data/LICENSE-whatlang +26 -0
- data/ext/psychowl_native/core/data/README.md +32 -0
- data/ext/psychowl_native/core/data/alphabets.tsv +16 -0
- data/ext/psychowl_native/core/data/languages.tsv +20 -0
- data/ext/psychowl_native/core/data/scripts.tsv +28 -0
- data/ext/psychowl_native/core/data/trigrams/ara.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/deu.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/eng.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/fra.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/hin.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/ind.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/ita.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/nld.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/pol.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/por.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/rus.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/spa.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/tur.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/ukr.txt +302 -0
- data/ext/psychowl_native/core/data/trigrams/vie.txt +302 -0
- data/lib/psychowl/active_model.rb +64 -0
- data/lib/psychowl/data_file.rb +14 -0
- data/lib/psychowl/detector.rb +123 -0
- data/lib/psychowl/engine.rb +23 -0
- data/lib/psychowl/info.rb +39 -0
- data/lib/psychowl/lang.rb +55 -0
- data/lib/psychowl/locale/en.yml +6 -0
- data/lib/psychowl/lookup.rb +25 -0
- data/lib/psychowl/native_speedup.rb +46 -0
- data/lib/psychowl/postgres.rb +35 -0
- data/lib/psychowl/railtie.rb +10 -0
- data/lib/psychowl/ruby_engine/segmentation.rb +84 -0
- data/lib/psychowl/ruby_engine/trigrams.rb +74 -0
- data/lib/psychowl/ruby_engine.rb +166 -0
- data/lib/psychowl/script.rb +39 -0
- data/lib/psychowl/segment.rb +24 -0
- data/lib/psychowl/tables.rb +55 -0
- data/lib/psychowl/text.rb +26 -0
- data/lib/psychowl/version.rb +5 -0
- data/lib/psychowl.rb +82 -0
- metadata +91 -0
|
@@ -0,0 +1,302 @@
|
|
|
1
|
+
# hin: 300 most frequent trigrams, most frequent first. "_" marks a word boundary.
|
|
2
|
+
# Ported from whatlang 0.18.0 (MIT), see ../LICENSE-whatlang.
|
|
3
|
+
के_
|
|
4
|
+
प्र
|
|
5
|
+
और_
|
|
6
|
+
_और
|
|
7
|
+
_के
|
|
8
|
+
ों_
|
|
9
|
+
_का
|
|
10
|
+
कार
|
|
11
|
+
_प्
|
|
12
|
+
का_
|
|
13
|
+
_को
|
|
14
|
+
या_
|
|
15
|
+
ं_क
|
|
16
|
+
ति_
|
|
17
|
+
ार_
|
|
18
|
+
को_
|
|
19
|
+
_है
|
|
20
|
+
िका
|
|
21
|
+
ने_
|
|
22
|
+
है_
|
|
23
|
+
्रत
|
|
24
|
+
धिक
|
|
25
|
+
_अध
|
|
26
|
+
अधि
|
|
27
|
+
की_
|
|
28
|
+
ा_क
|
|
29
|
+
_कि
|
|
30
|
+
_की
|
|
31
|
+
_सम
|
|
32
|
+
ें_
|
|
33
|
+
व्य
|
|
34
|
+
्ति
|
|
35
|
+
क्त
|
|
36
|
+
से_
|
|
37
|
+
_व्
|
|
38
|
+
ा_अ
|
|
39
|
+
्यक
|
|
40
|
+
में
|
|
41
|
+
मान
|
|
42
|
+
ि_क
|
|
43
|
+
_स्
|
|
44
|
+
_मे
|
|
45
|
+
सी_
|
|
46
|
+
न्त
|
|
47
|
+
_हो
|
|
48
|
+
े_क
|
|
49
|
+
ता_
|
|
50
|
+
यक्
|
|
51
|
+
क्ष
|
|
52
|
+
ै_।
|
|
53
|
+
िक_
|
|
54
|
+
त्य
|
|
55
|
+
_कर
|
|
56
|
+
्य_
|
|
57
|
+
_या
|
|
58
|
+
भी_
|
|
59
|
+
_वि
|
|
60
|
+
रत्
|
|
61
|
+
र_स
|
|
62
|
+
ी_स
|
|
63
|
+
_जा
|
|
64
|
+
स्व
|
|
65
|
+
रों
|
|
66
|
+
्ये
|
|
67
|
+
ेक_
|
|
68
|
+
येक
|
|
69
|
+
त्र
|
|
70
|
+
िया
|
|
71
|
+
ा_ज
|
|
72
|
+
क_व
|
|
73
|
+
र_ह
|
|
74
|
+
ित_
|
|
75
|
+
्रा
|
|
76
|
+
किस
|
|
77
|
+
_अन
|
|
78
|
+
ा_स
|
|
79
|
+
िसी
|
|
80
|
+
ा_ह
|
|
81
|
+
ना_
|
|
82
|
+
_से
|
|
83
|
+
_पर
|
|
84
|
+
र_क
|
|
85
|
+
_सा
|
|
86
|
+
देश
|
|
87
|
+
गा_
|
|
88
|
+
_।_
|
|
89
|
+
_अप
|
|
90
|
+
्त्
|
|
91
|
+
े_स
|
|
92
|
+
समा
|
|
93
|
+
ान_
|
|
94
|
+
ी_क
|
|
95
|
+
्त_
|
|
96
|
+
वार
|
|
97
|
+
_।प
|
|
98
|
+
ा_प
|
|
99
|
+
_रा
|
|
100
|
+
षा_
|
|
101
|
+
न_क
|
|
102
|
+
।प्
|
|
103
|
+
ष्ट
|
|
104
|
+
था_
|
|
105
|
+
अन्
|
|
106
|
+
_मा
|
|
107
|
+
्षा
|
|
108
|
+
्वा
|
|
109
|
+
ारो
|
|
110
|
+
तन्
|
|
111
|
+
वतन
|
|
112
|
+
ट्र
|
|
113
|
+
्वत
|
|
114
|
+
प्त
|
|
115
|
+
ाप्
|
|
116
|
+
्ट्
|
|
117
|
+
राष
|
|
118
|
+
ाष्
|
|
119
|
+
_इस
|
|
120
|
+
े_अ
|
|
121
|
+
_उस
|
|
122
|
+
_सं
|
|
123
|
+
राप
|
|
124
|
+
कि_
|
|
125
|
+
त_ह
|
|
126
|
+
हो_
|
|
127
|
+
ं_औ
|
|
128
|
+
ार्
|
|
129
|
+
ा_।
|
|
130
|
+
किय
|
|
131
|
+
े_प
|
|
132
|
+
_दे
|
|
133
|
+
_भी
|
|
134
|
+
करन
|
|
135
|
+
री_
|
|
136
|
+
जाए
|
|
137
|
+
ी_प
|
|
138
|
+
_न_
|
|
139
|
+
र_अ
|
|
140
|
+
क_स
|
|
141
|
+
अपन
|
|
142
|
+
े_व
|
|
143
|
+
ाओं
|
|
144
|
+
्तर
|
|
145
|
+
ओं_
|
|
146
|
+
_नि
|
|
147
|
+
सभी
|
|
148
|
+
रा_
|
|
149
|
+
_तथ
|
|
150
|
+
तथा
|
|
151
|
+
िवा
|
|
152
|
+
यों
|
|
153
|
+
पर_
|
|
154
|
+
_ऐस
|
|
155
|
+
रता
|
|
156
|
+
ारा
|
|
157
|
+
्री
|
|
158
|
+
सम्
|
|
159
|
+
_द्
|
|
160
|
+
ीय_
|
|
161
|
+
िए_
|
|
162
|
+
व_क
|
|
163
|
+
सके
|
|
164
|
+
द्व
|
|
165
|
+
होग
|
|
166
|
+
_सभ
|
|
167
|
+
ं_म
|
|
168
|
+
माज
|
|
169
|
+
रने
|
|
170
|
+
िक्
|
|
171
|
+
्या
|
|
172
|
+
ा_व
|
|
173
|
+
र_प
|
|
174
|
+
_जि
|
|
175
|
+
ो_स
|
|
176
|
+
र_उ
|
|
177
|
+
रक्
|
|
178
|
+
े_म
|
|
179
|
+
पूर
|
|
180
|
+
_लि
|
|
181
|
+
ाएग
|
|
182
|
+
_भा
|
|
183
|
+
इस_
|
|
184
|
+
त_क
|
|
185
|
+
ाव_
|
|
186
|
+
स्थ
|
|
187
|
+
पने
|
|
188
|
+
ा_औ
|
|
189
|
+
द्ध
|
|
190
|
+
श्य
|
|
191
|
+
र्व
|
|
192
|
+
_घो
|
|
193
|
+
घोष
|
|
194
|
+
रूप
|
|
195
|
+
भाव
|
|
196
|
+
ाने
|
|
197
|
+
कृत
|
|
198
|
+
ो_प
|
|
199
|
+
े_ल
|
|
200
|
+
लिए
|
|
201
|
+
शिक
|
|
202
|
+
ूर्
|
|
203
|
+
_उन
|
|
204
|
+
।_इ
|
|
205
|
+
ं_स
|
|
206
|
+
य_क
|
|
207
|
+
्ध_
|
|
208
|
+
दी_
|
|
209
|
+
ी_र
|
|
210
|
+
र्य
|
|
211
|
+
णा_
|
|
212
|
+
एगा
|
|
213
|
+
न्य
|
|
214
|
+
रीय
|
|
215
|
+
ेश_
|
|
216
|
+
रति
|
|
217
|
+
े_ब
|
|
218
|
+
_रू
|
|
219
|
+
ूप_
|
|
220
|
+
परा
|
|
221
|
+
्र_
|
|
222
|
+
तर्
|
|
223
|
+
_पा
|
|
224
|
+
_सु
|
|
225
|
+
जिस
|
|
226
|
+
तिक
|
|
227
|
+
सार
|
|
228
|
+
जो_
|
|
229
|
+
ेशो
|
|
230
|
+
_शि
|
|
231
|
+
ानव
|
|
232
|
+
ी_अ
|
|
233
|
+
चित
|
|
234
|
+
े_औ
|
|
235
|
+
_पू
|
|
236
|
+
ियो
|
|
237
|
+
ा_उ
|
|
238
|
+
म_क
|
|
239
|
+
ी_भ
|
|
240
|
+
शों
|
|
241
|
+
_बु
|
|
242
|
+
म्म
|
|
243
|
+
स्त
|
|
244
|
+
िश्
|
|
245
|
+
्रो
|
|
246
|
+
्म_
|
|
247
|
+
ो_क
|
|
248
|
+
_यह
|
|
249
|
+
र_द
|
|
250
|
+
नव_
|
|
251
|
+
चार
|
|
252
|
+
दिय
|
|
253
|
+
े_य
|
|
254
|
+
र्ण
|
|
255
|
+
राध
|
|
256
|
+
ोगा
|
|
257
|
+
ले_
|
|
258
|
+
नून
|
|
259
|
+
ानू
|
|
260
|
+
ोषण
|
|
261
|
+
षणा
|
|
262
|
+
विश
|
|
263
|
+
_जन
|
|
264
|
+
ारी
|
|
265
|
+
परि
|
|
266
|
+
गी_
|
|
267
|
+
वाह
|
|
268
|
+
साम
|
|
269
|
+
ाना
|
|
270
|
+
रका
|
|
271
|
+
_जो
|
|
272
|
+
ाज_
|
|
273
|
+
ी_ज
|
|
274
|
+
ध_क
|
|
275
|
+
बन्
|
|
276
|
+
ताओ
|
|
277
|
+
ंकि
|
|
278
|
+
ूंक
|
|
279
|
+
ास_
|
|
280
|
+
कर_
|
|
281
|
+
चूं
|
|
282
|
+
ी_व
|
|
283
|
+
य_ह
|
|
284
|
+
ा_ग
|
|
285
|
+
य_स
|
|
286
|
+
न_स
|
|
287
|
+
त_र
|
|
288
|
+
कोई
|
|
289
|
+
ुक्
|
|
290
|
+
ोई_
|
|
291
|
+
_।क
|
|
292
|
+
ं_न
|
|
293
|
+
हित
|
|
294
|
+
निय
|
|
295
|
+
याद
|
|
296
|
+
ादी
|
|
297
|
+
्मा
|
|
298
|
+
्था
|
|
299
|
+
ामा
|
|
300
|
+
ाह_
|
|
301
|
+
ी_म
|
|
302
|
+
े_ज
|
|
@@ -0,0 +1,302 @@
|
|
|
1
|
+
# ind: 300 most frequent trigrams, most frequent first. "_" marks a word boundary.
|
|
2
|
+
# Ported from whatlang 0.18.0 (MIT), see ../LICENSE-whatlang.
|
|
3
|
+
an_
|
|
4
|
+
ang
|
|
5
|
+
_da
|
|
6
|
+
ng_
|
|
7
|
+
_pe
|
|
8
|
+
ak_
|
|
9
|
+
_ke
|
|
10
|
+
_me
|
|
11
|
+
ata
|
|
12
|
+
_se
|
|
13
|
+
dan
|
|
14
|
+
kan
|
|
15
|
+
_di
|
|
16
|
+
_be
|
|
17
|
+
hak
|
|
18
|
+
ber
|
|
19
|
+
per
|
|
20
|
+
ran
|
|
21
|
+
nga
|
|
22
|
+
yan
|
|
23
|
+
eng
|
|
24
|
+
_ya
|
|
25
|
+
_ha
|
|
26
|
+
asa
|
|
27
|
+
gan
|
|
28
|
+
men
|
|
29
|
+
ara
|
|
30
|
+
nya
|
|
31
|
+
n_p
|
|
32
|
+
n_d
|
|
33
|
+
n_k
|
|
34
|
+
a_d
|
|
35
|
+
tan
|
|
36
|
+
_at
|
|
37
|
+
at_
|
|
38
|
+
ora
|
|
39
|
+
ala
|
|
40
|
+
san
|
|
41
|
+
_ba
|
|
42
|
+
ap_
|
|
43
|
+
erh
|
|
44
|
+
n_b
|
|
45
|
+
rha
|
|
46
|
+
ya_
|
|
47
|
+
_ma
|
|
48
|
+
g_b
|
|
49
|
+
a_s
|
|
50
|
+
pen
|
|
51
|
+
eba
|
|
52
|
+
as_
|
|
53
|
+
aan
|
|
54
|
+
uk_
|
|
55
|
+
ntu
|
|
56
|
+
_or
|
|
57
|
+
eti
|
|
58
|
+
tas
|
|
59
|
+
aka
|
|
60
|
+
tia
|
|
61
|
+
ban
|
|
62
|
+
set
|
|
63
|
+
_un
|
|
64
|
+
n_s
|
|
65
|
+
ter
|
|
66
|
+
n_y
|
|
67
|
+
_te
|
|
68
|
+
k_m
|
|
69
|
+
tuk
|
|
70
|
+
bas
|
|
71
|
+
iap
|
|
72
|
+
lam
|
|
73
|
+
beb
|
|
74
|
+
am_
|
|
75
|
+
_de
|
|
76
|
+
k_a
|
|
77
|
+
keb
|
|
78
|
+
n_m
|
|
79
|
+
i_d
|
|
80
|
+
unt
|
|
81
|
+
ama
|
|
82
|
+
dal
|
|
83
|
+
ah_
|
|
84
|
+
ika
|
|
85
|
+
dak
|
|
86
|
+
ebe
|
|
87
|
+
p_o
|
|
88
|
+
sa_
|
|
89
|
+
pun
|
|
90
|
+
mem
|
|
91
|
+
n_h
|
|
92
|
+
end
|
|
93
|
+
den
|
|
94
|
+
ra_
|
|
95
|
+
ela
|
|
96
|
+
ri_
|
|
97
|
+
nda
|
|
98
|
+
_sa
|
|
99
|
+
di_
|
|
100
|
+
ma_
|
|
101
|
+
a_m
|
|
102
|
+
n_t
|
|
103
|
+
k_d
|
|
104
|
+
n_a
|
|
105
|
+
ngg
|
|
106
|
+
tau
|
|
107
|
+
man
|
|
108
|
+
gar
|
|
109
|
+
eri
|
|
110
|
+
asi
|
|
111
|
+
_ti
|
|
112
|
+
un_
|
|
113
|
+
al_
|
|
114
|
+
ada
|
|
115
|
+
um_
|
|
116
|
+
a_p
|
|
117
|
+
lak
|
|
118
|
+
ari
|
|
119
|
+
au_
|
|
120
|
+
_ne
|
|
121
|
+
neg
|
|
122
|
+
a_b
|
|
123
|
+
ngs
|
|
124
|
+
ta_
|
|
125
|
+
ole
|
|
126
|
+
leh
|
|
127
|
+
ert
|
|
128
|
+
ers
|
|
129
|
+
ida
|
|
130
|
+
k_h
|
|
131
|
+
ana
|
|
132
|
+
gsa
|
|
133
|
+
dar
|
|
134
|
+
uka
|
|
135
|
+
tid
|
|
136
|
+
bat
|
|
137
|
+
sia
|
|
138
|
+
era
|
|
139
|
+
eh_
|
|
140
|
+
dap
|
|
141
|
+
ila
|
|
142
|
+
dil
|
|
143
|
+
h_d
|
|
144
|
+
atu
|
|
145
|
+
sam
|
|
146
|
+
ia_
|
|
147
|
+
i_m
|
|
148
|
+
_in
|
|
149
|
+
lan
|
|
150
|
+
aha
|
|
151
|
+
uan
|
|
152
|
+
tu_
|
|
153
|
+
ai_
|
|
154
|
+
t_d
|
|
155
|
+
a_a
|
|
156
|
+
g_d
|
|
157
|
+
har
|
|
158
|
+
sem
|
|
159
|
+
na_
|
|
160
|
+
apa
|
|
161
|
+
ser
|
|
162
|
+
ena
|
|
163
|
+
kat
|
|
164
|
+
uat
|
|
165
|
+
erb
|
|
166
|
+
erl
|
|
167
|
+
mas
|
|
168
|
+
rta
|
|
169
|
+
ega
|
|
170
|
+
ung
|
|
171
|
+
nan
|
|
172
|
+
emp
|
|
173
|
+
n_u
|
|
174
|
+
kum
|
|
175
|
+
l_d
|
|
176
|
+
g_s
|
|
177
|
+
_hu
|
|
178
|
+
ka_
|
|
179
|
+
ent
|
|
180
|
+
pat
|
|
181
|
+
mba
|
|
182
|
+
aga
|
|
183
|
+
nta
|
|
184
|
+
adi
|
|
185
|
+
_su
|
|
186
|
+
eni
|
|
187
|
+
uku
|
|
188
|
+
n_i
|
|
189
|
+
huk
|
|
190
|
+
ind
|
|
191
|
+
ar_
|
|
192
|
+
rga
|
|
193
|
+
i_s
|
|
194
|
+
aku
|
|
195
|
+
ndi
|
|
196
|
+
sua
|
|
197
|
+
ni_
|
|
198
|
+
rus
|
|
199
|
+
han
|
|
200
|
+
si_
|
|
201
|
+
car
|
|
202
|
+
nny
|
|
203
|
+
_la
|
|
204
|
+
in_
|
|
205
|
+
u_d
|
|
206
|
+
ik_
|
|
207
|
+
ua_
|
|
208
|
+
lah
|
|
209
|
+
rik
|
|
210
|
+
usi
|
|
211
|
+
emb
|
|
212
|
+
ann
|
|
213
|
+
mer
|
|
214
|
+
ian
|
|
215
|
+
gga
|
|
216
|
+
lai
|
|
217
|
+
min
|
|
218
|
+
a_u
|
|
219
|
+
lua
|
|
220
|
+
ema
|
|
221
|
+
emu
|
|
222
|
+
arg
|
|
223
|
+
dun
|
|
224
|
+
dip
|
|
225
|
+
a_t
|
|
226
|
+
mat
|
|
227
|
+
aya
|
|
228
|
+
rbu
|
|
229
|
+
aru
|
|
230
|
+
erk
|
|
231
|
+
rka
|
|
232
|
+
ini
|
|
233
|
+
eka
|
|
234
|
+
a_k
|
|
235
|
+
rak
|
|
236
|
+
kes
|
|
237
|
+
yat
|
|
238
|
+
iba
|
|
239
|
+
nas
|
|
240
|
+
rma
|
|
241
|
+
ern
|
|
242
|
+
ese
|
|
243
|
+
s_p
|
|
244
|
+
nus
|
|
245
|
+
_pu
|
|
246
|
+
anu
|
|
247
|
+
ina
|
|
248
|
+
_ta
|
|
249
|
+
mel
|
|
250
|
+
mua
|
|
251
|
+
kel
|
|
252
|
+
k_s
|
|
253
|
+
us_
|
|
254
|
+
ndu
|
|
255
|
+
nak
|
|
256
|
+
da_
|
|
257
|
+
sya
|
|
258
|
+
das
|
|
259
|
+
pem
|
|
260
|
+
lin
|
|
261
|
+
ut_
|
|
262
|
+
yar
|
|
263
|
+
ami
|
|
264
|
+
upu
|
|
265
|
+
seo
|
|
266
|
+
aik
|
|
267
|
+
eor
|
|
268
|
+
iny
|
|
269
|
+
aup
|
|
270
|
+
tak
|
|
271
|
+
ipe
|
|
272
|
+
ing
|
|
273
|
+
tin
|
|
274
|
+
_an
|
|
275
|
+
dik
|
|
276
|
+
uar
|
|
277
|
+
ili
|
|
278
|
+
g_t
|
|
279
|
+
rse
|
|
280
|
+
sar
|
|
281
|
+
ant
|
|
282
|
+
g_p
|
|
283
|
+
a_n
|
|
284
|
+
aks
|
|
285
|
+
ain
|
|
286
|
+
_ja
|
|
287
|
+
t_p
|
|
288
|
+
_um
|
|
289
|
+
g_m
|
|
290
|
+
dir
|
|
291
|
+
ksa
|
|
292
|
+
umu
|
|
293
|
+
kep
|
|
294
|
+
mum
|
|
295
|
+
i_k
|
|
296
|
+
eca
|
|
297
|
+
rat
|
|
298
|
+
m_p
|
|
299
|
+
h_p
|
|
300
|
+
aba
|
|
301
|
+
ses
|
|
302
|
+
m_m
|