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
|
+
# eng: 300 most frequent trigrams, most frequent first. "_" marks a word boundary.
|
|
2
|
+
# Ported from whatlang 0.18.0 (MIT), see ../LICENSE-whatlang.
|
|
3
|
+
_th
|
|
4
|
+
the
|
|
5
|
+
_an
|
|
6
|
+
he_
|
|
7
|
+
nd_
|
|
8
|
+
and
|
|
9
|
+
ion
|
|
10
|
+
_of
|
|
11
|
+
of_
|
|
12
|
+
tio
|
|
13
|
+
_to
|
|
14
|
+
to_
|
|
15
|
+
on_
|
|
16
|
+
_in
|
|
17
|
+
al_
|
|
18
|
+
ati
|
|
19
|
+
igh
|
|
20
|
+
ght
|
|
21
|
+
rig
|
|
22
|
+
_ri
|
|
23
|
+
or_
|
|
24
|
+
ent
|
|
25
|
+
as_
|
|
26
|
+
ed_
|
|
27
|
+
is_
|
|
28
|
+
ll_
|
|
29
|
+
in_
|
|
30
|
+
_be
|
|
31
|
+
e_r
|
|
32
|
+
ne_
|
|
33
|
+
one
|
|
34
|
+
ver
|
|
35
|
+
all
|
|
36
|
+
s_t
|
|
37
|
+
eve
|
|
38
|
+
t_t
|
|
39
|
+
_fr
|
|
40
|
+
s_a
|
|
41
|
+
_ha
|
|
42
|
+
_re
|
|
43
|
+
ty_
|
|
44
|
+
ery
|
|
45
|
+
_or
|
|
46
|
+
d_t
|
|
47
|
+
_pr
|
|
48
|
+
ht_
|
|
49
|
+
_co
|
|
50
|
+
_ev
|
|
51
|
+
e_h
|
|
52
|
+
e_a
|
|
53
|
+
ng_
|
|
54
|
+
ts_
|
|
55
|
+
his
|
|
56
|
+
ing
|
|
57
|
+
be_
|
|
58
|
+
yon
|
|
59
|
+
_sh
|
|
60
|
+
ce_
|
|
61
|
+
ree
|
|
62
|
+
fre
|
|
63
|
+
ryo
|
|
64
|
+
n_t
|
|
65
|
+
her
|
|
66
|
+
men
|
|
67
|
+
nat
|
|
68
|
+
sha
|
|
69
|
+
pro
|
|
70
|
+
nal
|
|
71
|
+
y_a
|
|
72
|
+
has
|
|
73
|
+
es_
|
|
74
|
+
for
|
|
75
|
+
_hi
|
|
76
|
+
hal
|
|
77
|
+
f_t
|
|
78
|
+
n_a
|
|
79
|
+
n_o
|
|
80
|
+
nt_
|
|
81
|
+
_pe
|
|
82
|
+
s_o
|
|
83
|
+
_fo
|
|
84
|
+
d_i
|
|
85
|
+
nce
|
|
86
|
+
er_
|
|
87
|
+
ons
|
|
88
|
+
res
|
|
89
|
+
e_s
|
|
90
|
+
ect
|
|
91
|
+
ity
|
|
92
|
+
ly_
|
|
93
|
+
l_b
|
|
94
|
+
ry_
|
|
95
|
+
e_e
|
|
96
|
+
ers
|
|
97
|
+
e_i
|
|
98
|
+
an_
|
|
99
|
+
e_o
|
|
100
|
+
_de
|
|
101
|
+
cti
|
|
102
|
+
dom
|
|
103
|
+
edo
|
|
104
|
+
eed
|
|
105
|
+
hts
|
|
106
|
+
ter
|
|
107
|
+
ona
|
|
108
|
+
re_
|
|
109
|
+
_no
|
|
110
|
+
_wh
|
|
111
|
+
_a_
|
|
112
|
+
_un
|
|
113
|
+
d_f
|
|
114
|
+
_as
|
|
115
|
+
ny_
|
|
116
|
+
l_a
|
|
117
|
+
e_p
|
|
118
|
+
ere
|
|
119
|
+
_en
|
|
120
|
+
_na
|
|
121
|
+
_wi
|
|
122
|
+
nit
|
|
123
|
+
nte
|
|
124
|
+
d_a
|
|
125
|
+
any
|
|
126
|
+
ted
|
|
127
|
+
_di
|
|
128
|
+
ns_
|
|
129
|
+
sta
|
|
130
|
+
th_
|
|
131
|
+
per
|
|
132
|
+
ith
|
|
133
|
+
e_t
|
|
134
|
+
st_
|
|
135
|
+
e_c
|
|
136
|
+
y_t
|
|
137
|
+
om_
|
|
138
|
+
soc
|
|
139
|
+
_ar
|
|
140
|
+
ch_
|
|
141
|
+
t_o
|
|
142
|
+
d_o
|
|
143
|
+
nti
|
|
144
|
+
s_e
|
|
145
|
+
equ
|
|
146
|
+
ve_
|
|
147
|
+
oci
|
|
148
|
+
man
|
|
149
|
+
_fu
|
|
150
|
+
ote
|
|
151
|
+
oth
|
|
152
|
+
ess
|
|
153
|
+
_al
|
|
154
|
+
_ac
|
|
155
|
+
wit
|
|
156
|
+
ial
|
|
157
|
+
_ma
|
|
158
|
+
uni
|
|
159
|
+
_se
|
|
160
|
+
rea
|
|
161
|
+
_so
|
|
162
|
+
_on
|
|
163
|
+
lit
|
|
164
|
+
int
|
|
165
|
+
r_t
|
|
166
|
+
y_o
|
|
167
|
+
enc
|
|
168
|
+
thi
|
|
169
|
+
ual
|
|
170
|
+
t_a
|
|
171
|
+
_eq
|
|
172
|
+
tat
|
|
173
|
+
qua
|
|
174
|
+
ive
|
|
175
|
+
_st
|
|
176
|
+
ali
|
|
177
|
+
e_w
|
|
178
|
+
l_o
|
|
179
|
+
are
|
|
180
|
+
f_h
|
|
181
|
+
con
|
|
182
|
+
te_
|
|
183
|
+
led
|
|
184
|
+
_is
|
|
185
|
+
und
|
|
186
|
+
cia
|
|
187
|
+
e_f
|
|
188
|
+
le_
|
|
189
|
+
_la
|
|
190
|
+
y_i
|
|
191
|
+
uma
|
|
192
|
+
by_
|
|
193
|
+
_by
|
|
194
|
+
hum
|
|
195
|
+
f_a
|
|
196
|
+
ic_
|
|
197
|
+
_hu
|
|
198
|
+
ave
|
|
199
|
+
ge_
|
|
200
|
+
r_a
|
|
201
|
+
_wo
|
|
202
|
+
o_a
|
|
203
|
+
ms_
|
|
204
|
+
com
|
|
205
|
+
_me
|
|
206
|
+
eas
|
|
207
|
+
s_d
|
|
208
|
+
tec
|
|
209
|
+
_li
|
|
210
|
+
n_e
|
|
211
|
+
en_
|
|
212
|
+
rat
|
|
213
|
+
tit
|
|
214
|
+
ple
|
|
215
|
+
whe
|
|
216
|
+
ate
|
|
217
|
+
o_t
|
|
218
|
+
s_r
|
|
219
|
+
t_f
|
|
220
|
+
rot
|
|
221
|
+
_ch
|
|
222
|
+
cie
|
|
223
|
+
dis
|
|
224
|
+
age
|
|
225
|
+
ary
|
|
226
|
+
o_o
|
|
227
|
+
anc
|
|
228
|
+
eli
|
|
229
|
+
no_
|
|
230
|
+
_fa
|
|
231
|
+
_su
|
|
232
|
+
son
|
|
233
|
+
inc
|
|
234
|
+
at_
|
|
235
|
+
nda
|
|
236
|
+
hou
|
|
237
|
+
wor
|
|
238
|
+
t_i
|
|
239
|
+
nde
|
|
240
|
+
rom
|
|
241
|
+
oms
|
|
242
|
+
_ot
|
|
243
|
+
g_t
|
|
244
|
+
eme
|
|
245
|
+
tle
|
|
246
|
+
iti
|
|
247
|
+
gni
|
|
248
|
+
s_w
|
|
249
|
+
itl
|
|
250
|
+
duc
|
|
251
|
+
d_w
|
|
252
|
+
whi
|
|
253
|
+
act
|
|
254
|
+
hic
|
|
255
|
+
aw_
|
|
256
|
+
law
|
|
257
|
+
_he
|
|
258
|
+
ich
|
|
259
|
+
min
|
|
260
|
+
imi
|
|
261
|
+
ort
|
|
262
|
+
o_s
|
|
263
|
+
se_
|
|
264
|
+
e_b
|
|
265
|
+
ntr
|
|
266
|
+
tra
|
|
267
|
+
edu
|
|
268
|
+
oun
|
|
269
|
+
tan
|
|
270
|
+
e_d
|
|
271
|
+
nst
|
|
272
|
+
l_p
|
|
273
|
+
d_n
|
|
274
|
+
ld_
|
|
275
|
+
nta
|
|
276
|
+
s_i
|
|
277
|
+
ble
|
|
278
|
+
n_p
|
|
279
|
+
_pu
|
|
280
|
+
n_s
|
|
281
|
+
_at
|
|
282
|
+
ily
|
|
283
|
+
rth
|
|
284
|
+
tho
|
|
285
|
+
ful
|
|
286
|
+
ssi
|
|
287
|
+
der
|
|
288
|
+
o_e
|
|
289
|
+
cat
|
|
290
|
+
uca
|
|
291
|
+
unt
|
|
292
|
+
ien
|
|
293
|
+
_ed
|
|
294
|
+
o_p
|
|
295
|
+
h_a
|
|
296
|
+
era
|
|
297
|
+
ind
|
|
298
|
+
pen
|
|
299
|
+
sec
|
|
300
|
+
n_w
|
|
301
|
+
omm
|
|
302
|
+
r_s
|
|
@@ -0,0 +1,302 @@
|
|
|
1
|
+
# fra: 300 most frequent trigrams, most frequent first. "_" marks a word boundary.
|
|
2
|
+
# Ported from whatlang 0.18.0 (MIT), see ../LICENSE-whatlang.
|
|
3
|
+
_de
|
|
4
|
+
es_
|
|
5
|
+
de_
|
|
6
|
+
ion
|
|
7
|
+
nt_
|
|
8
|
+
et_
|
|
9
|
+
tio
|
|
10
|
+
_et
|
|
11
|
+
ent
|
|
12
|
+
_la
|
|
13
|
+
la_
|
|
14
|
+
e_d
|
|
15
|
+
on_
|
|
16
|
+
ne_
|
|
17
|
+
oit
|
|
18
|
+
e_l
|
|
19
|
+
le_
|
|
20
|
+
_le
|
|
21
|
+
s_d
|
|
22
|
+
e_p
|
|
23
|
+
t_d
|
|
24
|
+
ati
|
|
25
|
+
roi
|
|
26
|
+
_dr
|
|
27
|
+
dro
|
|
28
|
+
it_
|
|
29
|
+
_à_
|
|
30
|
+
_co
|
|
31
|
+
té_
|
|
32
|
+
ns_
|
|
33
|
+
te_
|
|
34
|
+
e_s
|
|
35
|
+
men
|
|
36
|
+
re_
|
|
37
|
+
_to
|
|
38
|
+
con
|
|
39
|
+
_l’
|
|
40
|
+
tou
|
|
41
|
+
que
|
|
42
|
+
_qu
|
|
43
|
+
les
|
|
44
|
+
_so
|
|
45
|
+
des
|
|
46
|
+
son
|
|
47
|
+
_pe
|
|
48
|
+
ons
|
|
49
|
+
_un
|
|
50
|
+
s_l
|
|
51
|
+
s_e
|
|
52
|
+
_pr
|
|
53
|
+
ue_
|
|
54
|
+
_pa
|
|
55
|
+
e_c
|
|
56
|
+
t_l
|
|
57
|
+
ts_
|
|
58
|
+
onn
|
|
59
|
+
_au
|
|
60
|
+
e_a
|
|
61
|
+
eme
|
|
62
|
+
e_e
|
|
63
|
+
_li
|
|
64
|
+
ont
|
|
65
|
+
ant
|
|
66
|
+
out
|
|
67
|
+
ute
|
|
68
|
+
t_à
|
|
69
|
+
res
|
|
70
|
+
ers
|
|
71
|
+
_sa
|
|
72
|
+
ce_
|
|
73
|
+
_a_
|
|
74
|
+
tre
|
|
75
|
+
per
|
|
76
|
+
a_d
|
|
77
|
+
cti
|
|
78
|
+
er_
|
|
79
|
+
lib
|
|
80
|
+
ité
|
|
81
|
+
_en
|
|
82
|
+
ux_
|
|
83
|
+
_re
|
|
84
|
+
en_
|
|
85
|
+
rso
|
|
86
|
+
à_l
|
|
87
|
+
_ou
|
|
88
|
+
_in
|
|
89
|
+
lle
|
|
90
|
+
un_
|
|
91
|
+
nat
|
|
92
|
+
ou_
|
|
93
|
+
nne
|
|
94
|
+
n_d
|
|
95
|
+
une
|
|
96
|
+
_d’
|
|
97
|
+
_se
|
|
98
|
+
par
|
|
99
|
+
nte
|
|
100
|
+
us_
|
|
101
|
+
ur_
|
|
102
|
+
s_s
|
|
103
|
+
ans
|
|
104
|
+
dan
|
|
105
|
+
a_p
|
|
106
|
+
r_l
|
|
107
|
+
pro
|
|
108
|
+
its
|
|
109
|
+
és_
|
|
110
|
+
t_p
|
|
111
|
+
ire
|
|
112
|
+
e_t
|
|
113
|
+
s_p
|
|
114
|
+
sa_
|
|
115
|
+
_dé
|
|
116
|
+
ond
|
|
117
|
+
é_d
|
|
118
|
+
a_l
|
|
119
|
+
nce
|
|
120
|
+
ert
|
|
121
|
+
aux
|
|
122
|
+
omm
|
|
123
|
+
nal
|
|
124
|
+
me_
|
|
125
|
+
_na
|
|
126
|
+
_fo
|
|
127
|
+
iqu
|
|
128
|
+
_ce
|
|
129
|
+
rté
|
|
130
|
+
ect
|
|
131
|
+
ale
|
|
132
|
+
ber
|
|
133
|
+
t_a
|
|
134
|
+
s_a
|
|
135
|
+
_da
|
|
136
|
+
mme
|
|
137
|
+
ibe
|
|
138
|
+
san
|
|
139
|
+
e_r
|
|
140
|
+
_po
|
|
141
|
+
com
|
|
142
|
+
al_
|
|
143
|
+
s_c
|
|
144
|
+
qui
|
|
145
|
+
our
|
|
146
|
+
t_e
|
|
147
|
+
_ne
|
|
148
|
+
e_n
|
|
149
|
+
ous
|
|
150
|
+
r_d
|
|
151
|
+
ali
|
|
152
|
+
ter
|
|
153
|
+
_di
|
|
154
|
+
fon
|
|
155
|
+
e_o
|
|
156
|
+
au_
|
|
157
|
+
_ch
|
|
158
|
+
air
|
|
159
|
+
ui_
|
|
160
|
+
ell
|
|
161
|
+
_es
|
|
162
|
+
lit
|
|
163
|
+
s_n
|
|
164
|
+
iss
|
|
165
|
+
éra
|
|
166
|
+
tes
|
|
167
|
+
soc
|
|
168
|
+
aut
|
|
169
|
+
oci
|
|
170
|
+
êtr
|
|
171
|
+
ien
|
|
172
|
+
int
|
|
173
|
+
du_
|
|
174
|
+
est
|
|
175
|
+
été
|
|
176
|
+
tra
|
|
177
|
+
pou
|
|
178
|
+
_pl
|
|
179
|
+
rat
|
|
180
|
+
ar_
|
|
181
|
+
ran
|
|
182
|
+
rai
|
|
183
|
+
s_o
|
|
184
|
+
ona
|
|
185
|
+
ain
|
|
186
|
+
cla
|
|
187
|
+
éga
|
|
188
|
+
anc
|
|
189
|
+
rs_
|
|
190
|
+
eur
|
|
191
|
+
pri
|
|
192
|
+
n_c
|
|
193
|
+
e_m
|
|
194
|
+
s_t
|
|
195
|
+
à_u
|
|
196
|
+
_do
|
|
197
|
+
ure
|
|
198
|
+
bre
|
|
199
|
+
ut_
|
|
200
|
+
_êt
|
|
201
|
+
age
|
|
202
|
+
_ét
|
|
203
|
+
nsi
|
|
204
|
+
sur
|
|
205
|
+
ein
|
|
206
|
+
sen
|
|
207
|
+
ser
|
|
208
|
+
ndi
|
|
209
|
+
ens
|
|
210
|
+
ess
|
|
211
|
+
ntr
|
|
212
|
+
ir_
|
|
213
|
+
_ma
|
|
214
|
+
cia
|
|
215
|
+
n_p
|
|
216
|
+
st_
|
|
217
|
+
a_c
|
|
218
|
+
_du
|
|
219
|
+
l_e
|
|
220
|
+
_su
|
|
221
|
+
bli
|
|
222
|
+
ge_
|
|
223
|
+
rés
|
|
224
|
+
_ré
|
|
225
|
+
e_q
|
|
226
|
+
ass
|
|
227
|
+
nda
|
|
228
|
+
peu
|
|
229
|
+
ée_
|
|
230
|
+
l’a
|
|
231
|
+
_te
|
|
232
|
+
a_s
|
|
233
|
+
tat
|
|
234
|
+
il_
|
|
235
|
+
tés
|
|
236
|
+
ais
|
|
237
|
+
u_d
|
|
238
|
+
ine
|
|
239
|
+
ind
|
|
240
|
+
é_e
|
|
241
|
+
qu’
|
|
242
|
+
_ac
|
|
243
|
+
s_i
|
|
244
|
+
n_t
|
|
245
|
+
t_c
|
|
246
|
+
n_a
|
|
247
|
+
l’h
|
|
248
|
+
t_q
|
|
249
|
+
soi
|
|
250
|
+
t_s
|
|
251
|
+
cun
|
|
252
|
+
rit
|
|
253
|
+
_ég
|
|
254
|
+
oir
|
|
255
|
+
’en
|
|
256
|
+
nta
|
|
257
|
+
hom
|
|
258
|
+
_on
|
|
259
|
+
n_e
|
|
260
|
+
_mo
|
|
261
|
+
ie_
|
|
262
|
+
ign
|
|
263
|
+
rel
|
|
264
|
+
nna
|
|
265
|
+
t_i
|
|
266
|
+
l_n
|
|
267
|
+
_tr
|
|
268
|
+
ill
|
|
269
|
+
ple
|
|
270
|
+
s_é
|
|
271
|
+
l’e
|
|
272
|
+
rec
|
|
273
|
+
a_r
|
|
274
|
+
ote
|
|
275
|
+
sse
|
|
276
|
+
uni
|
|
277
|
+
idé
|
|
278
|
+
ive
|
|
279
|
+
s_u
|
|
280
|
+
t_ê
|
|
281
|
+
ins
|
|
282
|
+
act
|
|
283
|
+
_fa
|
|
284
|
+
n_s
|
|
285
|
+
_vi
|
|
286
|
+
gal
|
|
287
|
+
_as
|
|
288
|
+
lig
|
|
289
|
+
ssa
|
|
290
|
+
pré
|
|
291
|
+
leu
|
|
292
|
+
e_f
|
|
293
|
+
lic
|
|
294
|
+
dis
|
|
295
|
+
ver
|
|
296
|
+
_nu
|
|
297
|
+
ten
|
|
298
|
+
ssi
|
|
299
|
+
rot
|
|
300
|
+
tec
|
|
301
|
+
s_m
|
|
302
|
+
abl
|