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
|
+
# ara: 300 most frequent trigrams, most frequent first. "_" marks a word boundary.
|
|
2
|
+
# Ported from whatlang 0.18.0 (MIT), see ../LICENSE-whatlang.
|
|
3
|
+
_ال
|
|
4
|
+
ية_
|
|
5
|
+
_في
|
|
6
|
+
الح
|
|
7
|
+
في_
|
|
8
|
+
_وا
|
|
9
|
+
وال
|
|
10
|
+
_أو
|
|
11
|
+
ة_ا
|
|
12
|
+
أو_
|
|
13
|
+
الم
|
|
14
|
+
الت
|
|
15
|
+
لحق
|
|
16
|
+
حق_
|
|
17
|
+
لى_
|
|
18
|
+
كل_
|
|
19
|
+
ان_
|
|
20
|
+
ة_و
|
|
21
|
+
الأ
|
|
22
|
+
_لك
|
|
23
|
+
لكل
|
|
24
|
+
ن_ا
|
|
25
|
+
ها_
|
|
26
|
+
ق_ف
|
|
27
|
+
ات_
|
|
28
|
+
مة_
|
|
29
|
+
ون_
|
|
30
|
+
أن_
|
|
31
|
+
ما_
|
|
32
|
+
اء_
|
|
33
|
+
ته_
|
|
34
|
+
و_ا
|
|
35
|
+
الع
|
|
36
|
+
ي_ا
|
|
37
|
+
شخص
|
|
38
|
+
ي_أ
|
|
39
|
+
_أن
|
|
40
|
+
الإ
|
|
41
|
+
م_ا
|
|
42
|
+
حري
|
|
43
|
+
_عل
|
|
44
|
+
ة_ل
|
|
45
|
+
من_
|
|
46
|
+
الا
|
|
47
|
+
حقو
|
|
48
|
+
على
|
|
49
|
+
قوق
|
|
50
|
+
ت_ا
|
|
51
|
+
أي_
|
|
52
|
+
رد_
|
|
53
|
+
_شخ
|
|
54
|
+
_لل
|
|
55
|
+
_أي
|
|
56
|
+
ق_ا
|
|
57
|
+
لا_
|
|
58
|
+
فرد
|
|
59
|
+
رية
|
|
60
|
+
_ول
|
|
61
|
+
_من
|
|
62
|
+
د_ا
|
|
63
|
+
_كا
|
|
64
|
+
_إل
|
|
65
|
+
خص_
|
|
66
|
+
وق_
|
|
67
|
+
ا_ا
|
|
68
|
+
ة_أ
|
|
69
|
+
ا_ي
|
|
70
|
+
ل_ف
|
|
71
|
+
ه_ا
|
|
72
|
+
نسا
|
|
73
|
+
جتم
|
|
74
|
+
ن_ي
|
|
75
|
+
امة
|
|
76
|
+
كان
|
|
77
|
+
دة_
|
|
78
|
+
_حق
|
|
79
|
+
ام_
|
|
80
|
+
الق
|
|
81
|
+
ة_م
|
|
82
|
+
_فر
|
|
83
|
+
اية
|
|
84
|
+
سان
|
|
85
|
+
ل_ش
|
|
86
|
+
ين_
|
|
87
|
+
ن_ت
|
|
88
|
+
إنس
|
|
89
|
+
ا_ل
|
|
90
|
+
_لا
|
|
91
|
+
ذا_
|
|
92
|
+
هذا
|
|
93
|
+
ن_أ
|
|
94
|
+
لة_
|
|
95
|
+
ي_ح
|
|
96
|
+
_دو
|
|
97
|
+
ه_ل
|
|
98
|
+
لك_
|
|
99
|
+
ترا
|
|
100
|
+
لتع
|
|
101
|
+
اً_
|
|
102
|
+
له_
|
|
103
|
+
إلى
|
|
104
|
+
_عن
|
|
105
|
+
ى_ا
|
|
106
|
+
ه_و
|
|
107
|
+
ع_ا
|
|
108
|
+
ماع
|
|
109
|
+
د_أ
|
|
110
|
+
اسي
|
|
111
|
+
_حر
|
|
112
|
+
ة_ع
|
|
113
|
+
مع_
|
|
114
|
+
الد
|
|
115
|
+
نون
|
|
116
|
+
_با
|
|
117
|
+
لحر
|
|
118
|
+
لعا
|
|
119
|
+
ن_و
|
|
120
|
+
،_و
|
|
121
|
+
يات
|
|
122
|
+
ي_ت
|
|
123
|
+
الج
|
|
124
|
+
_هذ
|
|
125
|
+
ير_
|
|
126
|
+
بال
|
|
127
|
+
دول
|
|
128
|
+
لإن
|
|
129
|
+
عية
|
|
130
|
+
الف
|
|
131
|
+
ص_ا
|
|
132
|
+
_وي
|
|
133
|
+
الو
|
|
134
|
+
لأس
|
|
135
|
+
_إن
|
|
136
|
+
أسا
|
|
137
|
+
ساس
|
|
138
|
+
ماي
|
|
139
|
+
حما
|
|
140
|
+
رام
|
|
141
|
+
سية
|
|
142
|
+
انو
|
|
143
|
+
مل_
|
|
144
|
+
ي_و
|
|
145
|
+
عام
|
|
146
|
+
ا_و
|
|
147
|
+
تما
|
|
148
|
+
_مت
|
|
149
|
+
ة_ت
|
|
150
|
+
علي
|
|
151
|
+
ع_ب
|
|
152
|
+
ك_ا
|
|
153
|
+
_له
|
|
154
|
+
ة_ف
|
|
155
|
+
قان
|
|
156
|
+
ى_أ
|
|
157
|
+
ول_
|
|
158
|
+
هم_
|
|
159
|
+
الب
|
|
160
|
+
ة_ب
|
|
161
|
+
ساو
|
|
162
|
+
لقا
|
|
163
|
+
الر
|
|
164
|
+
لجم
|
|
165
|
+
ا_ك
|
|
166
|
+
تمت
|
|
167
|
+
ليه
|
|
168
|
+
لتم
|
|
169
|
+
لمت
|
|
170
|
+
انت
|
|
171
|
+
_قد
|
|
172
|
+
اد_
|
|
173
|
+
ه_أ
|
|
174
|
+
_يج
|
|
175
|
+
ريا
|
|
176
|
+
ق_و
|
|
177
|
+
ل_ا
|
|
178
|
+
ا_ب
|
|
179
|
+
ال_
|
|
180
|
+
يه_
|
|
181
|
+
اعي
|
|
182
|
+
لدو
|
|
183
|
+
ل_و
|
|
184
|
+
لإع
|
|
185
|
+
لمي
|
|
186
|
+
لمج
|
|
187
|
+
لأم
|
|
188
|
+
تع_
|
|
189
|
+
دم_
|
|
190
|
+
تسا
|
|
191
|
+
عمل
|
|
192
|
+
اته
|
|
193
|
+
لاد
|
|
194
|
+
رة_
|
|
195
|
+
اة_
|
|
196
|
+
غير
|
|
197
|
+
قدم
|
|
198
|
+
وز_
|
|
199
|
+
جوز
|
|
200
|
+
يجو
|
|
201
|
+
عال
|
|
202
|
+
لان
|
|
203
|
+
متع
|
|
204
|
+
مان
|
|
205
|
+
فيه
|
|
206
|
+
اجت
|
|
207
|
+
م_و
|
|
208
|
+
يد_
|
|
209
|
+
تعل
|
|
210
|
+
ن_ل
|
|
211
|
+
ر_ا
|
|
212
|
+
_يع
|
|
213
|
+
_كل
|
|
214
|
+
مم_
|
|
215
|
+
مجت
|
|
216
|
+
تمع
|
|
217
|
+
دون
|
|
218
|
+
_مع
|
|
219
|
+
تمي
|
|
220
|
+
ذلك
|
|
221
|
+
كرا
|
|
222
|
+
يها
|
|
223
|
+
_مس
|
|
224
|
+
ميع
|
|
225
|
+
إعل
|
|
226
|
+
علا
|
|
227
|
+
_تم
|
|
228
|
+
_عا
|
|
229
|
+
ملا
|
|
230
|
+
اعا
|
|
231
|
+
لاج
|
|
232
|
+
ني_
|
|
233
|
+
ليم
|
|
234
|
+
متس
|
|
235
|
+
ييز
|
|
236
|
+
يم_
|
|
237
|
+
اعت
|
|
238
|
+
الش
|
|
239
|
+
_تع
|
|
240
|
+
ميي
|
|
241
|
+
عن_
|
|
242
|
+
تنا
|
|
243
|
+
_بح
|
|
244
|
+
لما
|
|
245
|
+
ي_ي
|
|
246
|
+
يز_
|
|
247
|
+
ود_
|
|
248
|
+
أمم
|
|
249
|
+
لات
|
|
250
|
+
أسر
|
|
251
|
+
شتر
|
|
252
|
+
تي_
|
|
253
|
+
_جم
|
|
254
|
+
ه_ع
|
|
255
|
+
ر_و
|
|
256
|
+
ي_إ
|
|
257
|
+
تحد
|
|
258
|
+
حدة
|
|
259
|
+
_أس
|
|
260
|
+
عة_
|
|
261
|
+
ي_م
|
|
262
|
+
ة،_
|
|
263
|
+
معي
|
|
264
|
+
ن_م
|
|
265
|
+
لمس
|
|
266
|
+
م_ب
|
|
267
|
+
اق_
|
|
268
|
+
جمي
|
|
269
|
+
لي_
|
|
270
|
+
مية
|
|
271
|
+
الض
|
|
272
|
+
الس
|
|
273
|
+
لضم
|
|
274
|
+
ضما
|
|
275
|
+
لفر
|
|
276
|
+
_وس
|
|
277
|
+
لحم
|
|
278
|
+
امل
|
|
279
|
+
ق_م
|
|
280
|
+
را_
|
|
281
|
+
ا_ح
|
|
282
|
+
نت_
|
|
283
|
+
_تن
|
|
284
|
+
يته
|
|
285
|
+
_أم
|
|
286
|
+
إلي
|
|
287
|
+
واج
|
|
288
|
+
د_و
|
|
289
|
+
لتي
|
|
290
|
+
_مر
|
|
291
|
+
مرا
|
|
292
|
+
متح
|
|
293
|
+
_ذل
|
|
294
|
+
_وأ
|
|
295
|
+
_تح
|
|
296
|
+
ا_ف
|
|
297
|
+
_به
|
|
298
|
+
_وم
|
|
299
|
+
_بم
|
|
300
|
+
وية
|
|
301
|
+
ولي
|
|
302
|
+
لزو
|
|
@@ -0,0 +1,302 @@
|
|
|
1
|
+
# deu: 300 most frequent trigrams, most frequent first. "_" marks a word boundary.
|
|
2
|
+
# Ported from whatlang 0.18.0 (MIT), see ../LICENSE-whatlang.
|
|
3
|
+
en_
|
|
4
|
+
er_
|
|
5
|
+
der
|
|
6
|
+
_un
|
|
7
|
+
nd_
|
|
8
|
+
und
|
|
9
|
+
ein
|
|
10
|
+
ung
|
|
11
|
+
cht
|
|
12
|
+
_de
|
|
13
|
+
ich
|
|
14
|
+
sch
|
|
15
|
+
ng_
|
|
16
|
+
_ge
|
|
17
|
+
ie_
|
|
18
|
+
che
|
|
19
|
+
ech
|
|
20
|
+
_di
|
|
21
|
+
die
|
|
22
|
+
rec
|
|
23
|
+
gen
|
|
24
|
+
ine
|
|
25
|
+
eit
|
|
26
|
+
_re
|
|
27
|
+
ch_
|
|
28
|
+
_da
|
|
29
|
+
n_d
|
|
30
|
+
ver
|
|
31
|
+
hen
|
|
32
|
+
_zu
|
|
33
|
+
t_d
|
|
34
|
+
_au
|
|
35
|
+
ht_
|
|
36
|
+
_ha
|
|
37
|
+
lic
|
|
38
|
+
it_
|
|
39
|
+
ten
|
|
40
|
+
rei
|
|
41
|
+
_be
|
|
42
|
+
in_
|
|
43
|
+
_ve
|
|
44
|
+
_in
|
|
45
|
+
_ei
|
|
46
|
+
nde
|
|
47
|
+
auf
|
|
48
|
+
den
|
|
49
|
+
ede
|
|
50
|
+
zu_
|
|
51
|
+
n_s
|
|
52
|
+
uf_
|
|
53
|
+
fre
|
|
54
|
+
ne_
|
|
55
|
+
ter
|
|
56
|
+
es_
|
|
57
|
+
_je
|
|
58
|
+
jed
|
|
59
|
+
n_u
|
|
60
|
+
_an
|
|
61
|
+
sei
|
|
62
|
+
and
|
|
63
|
+
_fr
|
|
64
|
+
run
|
|
65
|
+
at_
|
|
66
|
+
_se
|
|
67
|
+
e_u
|
|
68
|
+
das
|
|
69
|
+
hei
|
|
70
|
+
s_r
|
|
71
|
+
hte
|
|
72
|
+
hat
|
|
73
|
+
nsc
|
|
74
|
+
nge
|
|
75
|
+
r_h
|
|
76
|
+
as_
|
|
77
|
+
ens
|
|
78
|
+
_al
|
|
79
|
+
ere
|
|
80
|
+
lle
|
|
81
|
+
t_a
|
|
82
|
+
_we
|
|
83
|
+
n_g
|
|
84
|
+
rde
|
|
85
|
+
nte
|
|
86
|
+
ese
|
|
87
|
+
men
|
|
88
|
+
_od
|
|
89
|
+
ode
|
|
90
|
+
ner
|
|
91
|
+
g_d
|
|
92
|
+
all
|
|
93
|
+
t_u
|
|
94
|
+
ers
|
|
95
|
+
te_
|
|
96
|
+
nen
|
|
97
|
+
_so
|
|
98
|
+
d_d
|
|
99
|
+
n_a
|
|
100
|
+
ben
|
|
101
|
+
lei
|
|
102
|
+
_gr
|
|
103
|
+
_vo
|
|
104
|
+
wer
|
|
105
|
+
e_a
|
|
106
|
+
ege
|
|
107
|
+
ion
|
|
108
|
+
_st
|
|
109
|
+
ige
|
|
110
|
+
le_
|
|
111
|
+
cha
|
|
112
|
+
_me
|
|
113
|
+
haf
|
|
114
|
+
aft
|
|
115
|
+
n_j
|
|
116
|
+
ren
|
|
117
|
+
_er
|
|
118
|
+
erk
|
|
119
|
+
ent
|
|
120
|
+
bei
|
|
121
|
+
_si
|
|
122
|
+
eih
|
|
123
|
+
ihe
|
|
124
|
+
kei
|
|
125
|
+
erd
|
|
126
|
+
tig
|
|
127
|
+
n_i
|
|
128
|
+
on_
|
|
129
|
+
lun
|
|
130
|
+
r_d
|
|
131
|
+
len
|
|
132
|
+
gem
|
|
133
|
+
ies
|
|
134
|
+
gru
|
|
135
|
+
tli
|
|
136
|
+
unt
|
|
137
|
+
chu
|
|
138
|
+
ern
|
|
139
|
+
ges
|
|
140
|
+
end
|
|
141
|
+
e_s
|
|
142
|
+
ft_
|
|
143
|
+
st_
|
|
144
|
+
ist
|
|
145
|
+
tio
|
|
146
|
+
ati
|
|
147
|
+
_gl
|
|
148
|
+
sta
|
|
149
|
+
gun
|
|
150
|
+
mit
|
|
151
|
+
sen
|
|
152
|
+
n_n
|
|
153
|
+
_na
|
|
154
|
+
n_z
|
|
155
|
+
ite
|
|
156
|
+
_wi
|
|
157
|
+
r_g
|
|
158
|
+
eic
|
|
159
|
+
e_e
|
|
160
|
+
ei_
|
|
161
|
+
lie
|
|
162
|
+
r_s
|
|
163
|
+
n_w
|
|
164
|
+
gle
|
|
165
|
+
mei
|
|
166
|
+
de_
|
|
167
|
+
uch
|
|
168
|
+
em_
|
|
169
|
+
chl
|
|
170
|
+
nat
|
|
171
|
+
rch
|
|
172
|
+
t_w
|
|
173
|
+
des
|
|
174
|
+
n_e
|
|
175
|
+
hre
|
|
176
|
+
ale
|
|
177
|
+
spr
|
|
178
|
+
d_f
|
|
179
|
+
ach
|
|
180
|
+
sse
|
|
181
|
+
r_e
|
|
182
|
+
_sc
|
|
183
|
+
urc
|
|
184
|
+
r_m
|
|
185
|
+
nie
|
|
186
|
+
e_f
|
|
187
|
+
fen
|
|
188
|
+
e_g
|
|
189
|
+
e_d
|
|
190
|
+
_ni
|
|
191
|
+
dur
|
|
192
|
+
dar
|
|
193
|
+
int
|
|
194
|
+
_du
|
|
195
|
+
geh
|
|
196
|
+
ied
|
|
197
|
+
t_s
|
|
198
|
+
_mi
|
|
199
|
+
alt
|
|
200
|
+
her
|
|
201
|
+
hab
|
|
202
|
+
f_g
|
|
203
|
+
sic
|
|
204
|
+
ste
|
|
205
|
+
taa
|
|
206
|
+
aat
|
|
207
|
+
he_
|
|
208
|
+
ang
|
|
209
|
+
ruc
|
|
210
|
+
hli
|
|
211
|
+
tz_
|
|
212
|
+
eme
|
|
213
|
+
abe
|
|
214
|
+
h_a
|
|
215
|
+
n_v
|
|
216
|
+
nun
|
|
217
|
+
geg
|
|
218
|
+
arf
|
|
219
|
+
rf_
|
|
220
|
+
ehe
|
|
221
|
+
pru
|
|
222
|
+
_is
|
|
223
|
+
erf
|
|
224
|
+
e_m
|
|
225
|
+
ans
|
|
226
|
+
ndl
|
|
227
|
+
e_b
|
|
228
|
+
tun
|
|
229
|
+
n_o
|
|
230
|
+
d_g
|
|
231
|
+
n_r
|
|
232
|
+
r_v
|
|
233
|
+
wie
|
|
234
|
+
ber
|
|
235
|
+
r_a
|
|
236
|
+
arb
|
|
237
|
+
bes
|
|
238
|
+
t_i
|
|
239
|
+
h_d
|
|
240
|
+
r_w
|
|
241
|
+
r_b
|
|
242
|
+
_ih
|
|
243
|
+
d_s
|
|
244
|
+
igk
|
|
245
|
+
gke
|
|
246
|
+
nsp
|
|
247
|
+
dig
|
|
248
|
+
ema
|
|
249
|
+
ell
|
|
250
|
+
eru
|
|
251
|
+
n_f
|
|
252
|
+
ins
|
|
253
|
+
rbe
|
|
254
|
+
ffe
|
|
255
|
+
esc
|
|
256
|
+
igu
|
|
257
|
+
ger
|
|
258
|
+
str
|
|
259
|
+
ken
|
|
260
|
+
e_v
|
|
261
|
+
gew
|
|
262
|
+
han
|
|
263
|
+
ind
|
|
264
|
+
rt_
|
|
265
|
+
_ar
|
|
266
|
+
ieß
|
|
267
|
+
n_h
|
|
268
|
+
rn_
|
|
269
|
+
man
|
|
270
|
+
r_i
|
|
271
|
+
hut
|
|
272
|
+
utz
|
|
273
|
+
d_a
|
|
274
|
+
ls_
|
|
275
|
+
ebe
|
|
276
|
+
von
|
|
277
|
+
lte
|
|
278
|
+
r_o
|
|
279
|
+
rli
|
|
280
|
+
etz
|
|
281
|
+
tra
|
|
282
|
+
aus
|
|
283
|
+
det
|
|
284
|
+
hul
|
|
285
|
+
e_i
|
|
286
|
+
one
|
|
287
|
+
nne
|
|
288
|
+
isc
|
|
289
|
+
son
|
|
290
|
+
sel
|
|
291
|
+
et_
|
|
292
|
+
ohn
|
|
293
|
+
t_g
|
|
294
|
+
sam
|
|
295
|
+
_fa
|
|
296
|
+
rst
|
|
297
|
+
rkl
|
|
298
|
+
ser
|
|
299
|
+
iem
|
|
300
|
+
g_v
|
|
301
|
+
t_z
|
|
302
|
+
err
|