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
|
+
# ita: 300 most frequent trigrams, most frequent first. "_" marks a word boundary.
|
|
2
|
+
# Ported from whatlang 0.18.0 (MIT), see ../LICENSE-whatlang.
|
|
3
|
+
_di
|
|
4
|
+
to_
|
|
5
|
+
_de
|
|
6
|
+
ion
|
|
7
|
+
_in
|
|
8
|
+
la_
|
|
9
|
+
e_d
|
|
10
|
+
di_
|
|
11
|
+
ne_
|
|
12
|
+
_e_
|
|
13
|
+
zio
|
|
14
|
+
re_
|
|
15
|
+
le_
|
|
16
|
+
ni_
|
|
17
|
+
ell
|
|
18
|
+
one
|
|
19
|
+
lla
|
|
20
|
+
rit
|
|
21
|
+
a_d
|
|
22
|
+
o_d
|
|
23
|
+
del
|
|
24
|
+
itt
|
|
25
|
+
iri
|
|
26
|
+
dir
|
|
27
|
+
_co
|
|
28
|
+
ti_
|
|
29
|
+
ess
|
|
30
|
+
ent
|
|
31
|
+
_al
|
|
32
|
+
azi
|
|
33
|
+
tto
|
|
34
|
+
te_
|
|
35
|
+
i_d
|
|
36
|
+
i_i
|
|
37
|
+
ere
|
|
38
|
+
tà_
|
|
39
|
+
_pr
|
|
40
|
+
ndi
|
|
41
|
+
e_l
|
|
42
|
+
ale
|
|
43
|
+
o_a
|
|
44
|
+
ind
|
|
45
|
+
e_e
|
|
46
|
+
e_i
|
|
47
|
+
gni
|
|
48
|
+
nte
|
|
49
|
+
con
|
|
50
|
+
i_e
|
|
51
|
+
li_
|
|
52
|
+
a_s
|
|
53
|
+
_un
|
|
54
|
+
men
|
|
55
|
+
ogn
|
|
56
|
+
_ne
|
|
57
|
+
uo_
|
|
58
|
+
_og
|
|
59
|
+
idu
|
|
60
|
+
e_a
|
|
61
|
+
ivi
|
|
62
|
+
duo
|
|
63
|
+
vid
|
|
64
|
+
_es
|
|
65
|
+
tti
|
|
66
|
+
_ha
|
|
67
|
+
div
|
|
68
|
+
_li
|
|
69
|
+
a_p
|
|
70
|
+
no_
|
|
71
|
+
all
|
|
72
|
+
pro
|
|
73
|
+
za_
|
|
74
|
+
ato
|
|
75
|
+
per
|
|
76
|
+
sse
|
|
77
|
+
ser
|
|
78
|
+
_so
|
|
79
|
+
i_s
|
|
80
|
+
_la
|
|
81
|
+
_su
|
|
82
|
+
e_p
|
|
83
|
+
_pe
|
|
84
|
+
ibe
|
|
85
|
+
na_
|
|
86
|
+
a_l
|
|
87
|
+
_il
|
|
88
|
+
ber
|
|
89
|
+
e_n
|
|
90
|
+
il_
|
|
91
|
+
ali
|
|
92
|
+
lib
|
|
93
|
+
ha_
|
|
94
|
+
che
|
|
95
|
+
in_
|
|
96
|
+
o_s
|
|
97
|
+
e_s
|
|
98
|
+
_qu
|
|
99
|
+
o_e
|
|
100
|
+
ia_
|
|
101
|
+
e_c
|
|
102
|
+
_ri
|
|
103
|
+
nza
|
|
104
|
+
ta_
|
|
105
|
+
nto
|
|
106
|
+
he_
|
|
107
|
+
oni
|
|
108
|
+
o_i
|
|
109
|
+
_o_
|
|
110
|
+
sta
|
|
111
|
+
o_c
|
|
112
|
+
nel
|
|
113
|
+
_a_
|
|
114
|
+
o_p
|
|
115
|
+
naz
|
|
116
|
+
e_o
|
|
117
|
+
so_
|
|
118
|
+
_po
|
|
119
|
+
o_h
|
|
120
|
+
gli
|
|
121
|
+
i_u
|
|
122
|
+
ond
|
|
123
|
+
i_c
|
|
124
|
+
ers
|
|
125
|
+
ame
|
|
126
|
+
i_p
|
|
127
|
+
lle
|
|
128
|
+
un_
|
|
129
|
+
era
|
|
130
|
+
ri_
|
|
131
|
+
ver
|
|
132
|
+
ro_
|
|
133
|
+
el_
|
|
134
|
+
una
|
|
135
|
+
a_c
|
|
136
|
+
_ch
|
|
137
|
+
ert
|
|
138
|
+
ua_
|
|
139
|
+
i_a
|
|
140
|
+
ssi
|
|
141
|
+
rtà
|
|
142
|
+
a_e
|
|
143
|
+
ei_
|
|
144
|
+
dis
|
|
145
|
+
ant
|
|
146
|
+
_l_
|
|
147
|
+
tat
|
|
148
|
+
a_a
|
|
149
|
+
ona
|
|
150
|
+
ual
|
|
151
|
+
_le
|
|
152
|
+
ità
|
|
153
|
+
are
|
|
154
|
+
ter
|
|
155
|
+
_ad
|
|
156
|
+
nit
|
|
157
|
+
_da
|
|
158
|
+
pri
|
|
159
|
+
dei
|
|
160
|
+
à_e
|
|
161
|
+
cia
|
|
162
|
+
_st
|
|
163
|
+
_si
|
|
164
|
+
nal
|
|
165
|
+
est
|
|
166
|
+
tut
|
|
167
|
+
ist
|
|
168
|
+
com
|
|
169
|
+
uni
|
|
170
|
+
_ed
|
|
171
|
+
ono
|
|
172
|
+
_na
|
|
173
|
+
sua
|
|
174
|
+
al_
|
|
175
|
+
si_
|
|
176
|
+
anz
|
|
177
|
+
_pa
|
|
178
|
+
_re
|
|
179
|
+
raz
|
|
180
|
+
gua
|
|
181
|
+
ita
|
|
182
|
+
res
|
|
183
|
+
der
|
|
184
|
+
soc
|
|
185
|
+
man
|
|
186
|
+
o_o
|
|
187
|
+
ad_
|
|
188
|
+
i_o
|
|
189
|
+
ese
|
|
190
|
+
que
|
|
191
|
+
enz
|
|
192
|
+
ed_
|
|
193
|
+
_se
|
|
194
|
+
io_
|
|
195
|
+
ett
|
|
196
|
+
on_
|
|
197
|
+
_tu
|
|
198
|
+
dic
|
|
199
|
+
à_d
|
|
200
|
+
sia
|
|
201
|
+
i_r
|
|
202
|
+
rso
|
|
203
|
+
oci
|
|
204
|
+
rio
|
|
205
|
+
ari
|
|
206
|
+
qua
|
|
207
|
+
ial
|
|
208
|
+
pre
|
|
209
|
+
ich
|
|
210
|
+
rat
|
|
211
|
+
ien
|
|
212
|
+
tra
|
|
213
|
+
ani
|
|
214
|
+
uma
|
|
215
|
+
se_
|
|
216
|
+
ll_
|
|
217
|
+
eri
|
|
218
|
+
a_n
|
|
219
|
+
o_n
|
|
220
|
+
_um
|
|
221
|
+
do_
|
|
222
|
+
ara
|
|
223
|
+
a_t
|
|
224
|
+
zza
|
|
225
|
+
er_
|
|
226
|
+
tri
|
|
227
|
+
att
|
|
228
|
+
ico
|
|
229
|
+
pos
|
|
230
|
+
sci
|
|
231
|
+
i_l
|
|
232
|
+
son
|
|
233
|
+
nda
|
|
234
|
+
par
|
|
235
|
+
e_u
|
|
236
|
+
fon
|
|
237
|
+
_fo
|
|
238
|
+
nti
|
|
239
|
+
uzi
|
|
240
|
+
str
|
|
241
|
+
utt
|
|
242
|
+
ati
|
|
243
|
+
sen
|
|
244
|
+
int
|
|
245
|
+
nes
|
|
246
|
+
iar
|
|
247
|
+
_i_
|
|
248
|
+
hia
|
|
249
|
+
n_c
|
|
250
|
+
sti
|
|
251
|
+
chi
|
|
252
|
+
ann
|
|
253
|
+
ra_
|
|
254
|
+
_eg
|
|
255
|
+
egu
|
|
256
|
+
isp
|
|
257
|
+
bil
|
|
258
|
+
ont
|
|
259
|
+
a_r
|
|
260
|
+
_no
|
|
261
|
+
rop
|
|
262
|
+
_me
|
|
263
|
+
opr
|
|
264
|
+
ost
|
|
265
|
+
_ma
|
|
266
|
+
ues
|
|
267
|
+
ica
|
|
268
|
+
sso
|
|
269
|
+
tal
|
|
270
|
+
cie
|
|
271
|
+
sun
|
|
272
|
+
lit
|
|
273
|
+
ore
|
|
274
|
+
ina
|
|
275
|
+
ite
|
|
276
|
+
tan
|
|
277
|
+
_ra
|
|
278
|
+
non
|
|
279
|
+
gio
|
|
280
|
+
d_a
|
|
281
|
+
e_r
|
|
282
|
+
dev
|
|
283
|
+
i_m
|
|
284
|
+
l_i
|
|
285
|
+
ezz
|
|
286
|
+
izi
|
|
287
|
+
_cu
|
|
288
|
+
nno
|
|
289
|
+
rà_
|
|
290
|
+
a_i
|
|
291
|
+
tta
|
|
292
|
+
ria
|
|
293
|
+
lia
|
|
294
|
+
cos
|
|
295
|
+
ssu
|
|
296
|
+
dal
|
|
297
|
+
l_p
|
|
298
|
+
_as
|
|
299
|
+
ass
|
|
300
|
+
opo
|
|
301
|
+
ve_
|
|
302
|
+
eve
|
|
@@ -0,0 +1,302 @@
|
|
|
1
|
+
# nld: 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
|
+
de_
|
|
5
|
+
an_
|
|
6
|
+
_de
|
|
7
|
+
van
|
|
8
|
+
_va
|
|
9
|
+
_en
|
|
10
|
+
_he
|
|
11
|
+
ing
|
|
12
|
+
cht
|
|
13
|
+
der
|
|
14
|
+
ng_
|
|
15
|
+
n_d
|
|
16
|
+
n_v
|
|
17
|
+
et_
|
|
18
|
+
een
|
|
19
|
+
_ge
|
|
20
|
+
ech
|
|
21
|
+
n_e
|
|
22
|
+
ver
|
|
23
|
+
rec
|
|
24
|
+
nde
|
|
25
|
+
_ee
|
|
26
|
+
_re
|
|
27
|
+
_be
|
|
28
|
+
ede
|
|
29
|
+
er_
|
|
30
|
+
e_v
|
|
31
|
+
gen
|
|
32
|
+
den
|
|
33
|
+
het
|
|
34
|
+
ten
|
|
35
|
+
_te
|
|
36
|
+
_in
|
|
37
|
+
_op
|
|
38
|
+
n_i
|
|
39
|
+
_ve
|
|
40
|
+
lij
|
|
41
|
+
_zi
|
|
42
|
+
ere
|
|
43
|
+
eli
|
|
44
|
+
zij
|
|
45
|
+
ijk
|
|
46
|
+
te_
|
|
47
|
+
oor
|
|
48
|
+
ht_
|
|
49
|
+
ens
|
|
50
|
+
n_o
|
|
51
|
+
and
|
|
52
|
+
t_o
|
|
53
|
+
ijn
|
|
54
|
+
ied
|
|
55
|
+
ke_
|
|
56
|
+
_on
|
|
57
|
+
eid
|
|
58
|
+
op_
|
|
59
|
+
_vo
|
|
60
|
+
jn_
|
|
61
|
+
id_
|
|
62
|
+
ond
|
|
63
|
+
in_
|
|
64
|
+
sch
|
|
65
|
+
_vr
|
|
66
|
+
aar
|
|
67
|
+
n_z
|
|
68
|
+
aan
|
|
69
|
+
_ie
|
|
70
|
+
rde
|
|
71
|
+
rij
|
|
72
|
+
men
|
|
73
|
+
ren
|
|
74
|
+
ord
|
|
75
|
+
hei
|
|
76
|
+
hte
|
|
77
|
+
_we
|
|
78
|
+
eft
|
|
79
|
+
n_g
|
|
80
|
+
ft_
|
|
81
|
+
n_w
|
|
82
|
+
or_
|
|
83
|
+
n_h
|
|
84
|
+
eef
|
|
85
|
+
vri
|
|
86
|
+
wor
|
|
87
|
+
_me
|
|
88
|
+
hee
|
|
89
|
+
al_
|
|
90
|
+
t_r
|
|
91
|
+
of_
|
|
92
|
+
le_
|
|
93
|
+
_of
|
|
94
|
+
ati
|
|
95
|
+
g_v
|
|
96
|
+
e_b
|
|
97
|
+
eni
|
|
98
|
+
_aa
|
|
99
|
+
lle
|
|
100
|
+
_wo
|
|
101
|
+
n_a
|
|
102
|
+
e_o
|
|
103
|
+
nd_
|
|
104
|
+
r_h
|
|
105
|
+
voo
|
|
106
|
+
_al
|
|
107
|
+
ege
|
|
108
|
+
n_t
|
|
109
|
+
erk
|
|
110
|
+
_da
|
|
111
|
+
_na
|
|
112
|
+
t_h
|
|
113
|
+
sta
|
|
114
|
+
jke
|
|
115
|
+
at_
|
|
116
|
+
nat
|
|
117
|
+
nge
|
|
118
|
+
e_e
|
|
119
|
+
end
|
|
120
|
+
_st
|
|
121
|
+
om_
|
|
122
|
+
e_g
|
|
123
|
+
tie
|
|
124
|
+
n_b
|
|
125
|
+
ste
|
|
126
|
+
die
|
|
127
|
+
e_r
|
|
128
|
+
erw
|
|
129
|
+
wel
|
|
130
|
+
e_s
|
|
131
|
+
r_d
|
|
132
|
+
_om
|
|
133
|
+
ij_
|
|
134
|
+
dig
|
|
135
|
+
t_e
|
|
136
|
+
ige
|
|
137
|
+
ter
|
|
138
|
+
ie_
|
|
139
|
+
gel
|
|
140
|
+
re_
|
|
141
|
+
jhe
|
|
142
|
+
t_d
|
|
143
|
+
_za
|
|
144
|
+
e_m
|
|
145
|
+
ers
|
|
146
|
+
ijh
|
|
147
|
+
nig
|
|
148
|
+
zal
|
|
149
|
+
nie
|
|
150
|
+
d_v
|
|
151
|
+
ns_
|
|
152
|
+
d_e
|
|
153
|
+
e_w
|
|
154
|
+
e_n
|
|
155
|
+
est
|
|
156
|
+
ele
|
|
157
|
+
bes
|
|
158
|
+
_do
|
|
159
|
+
g_e
|
|
160
|
+
che
|
|
161
|
+
vol
|
|
162
|
+
ge_
|
|
163
|
+
eze
|
|
164
|
+
e_d
|
|
165
|
+
ig_
|
|
166
|
+
gin
|
|
167
|
+
dat
|
|
168
|
+
hap
|
|
169
|
+
cha
|
|
170
|
+
eke
|
|
171
|
+
_di
|
|
172
|
+
ona
|
|
173
|
+
e_a
|
|
174
|
+
lke
|
|
175
|
+
nst
|
|
176
|
+
ard
|
|
177
|
+
_gr
|
|
178
|
+
tel
|
|
179
|
+
min
|
|
180
|
+
_to
|
|
181
|
+
waa
|
|
182
|
+
len
|
|
183
|
+
elk
|
|
184
|
+
lin
|
|
185
|
+
eme
|
|
186
|
+
jk_
|
|
187
|
+
n_s
|
|
188
|
+
del
|
|
189
|
+
str
|
|
190
|
+
han
|
|
191
|
+
eve
|
|
192
|
+
gro
|
|
193
|
+
ich
|
|
194
|
+
ven
|
|
195
|
+
doo
|
|
196
|
+
_wa
|
|
197
|
+
t_v
|
|
198
|
+
it_
|
|
199
|
+
ove
|
|
200
|
+
rin
|
|
201
|
+
aat
|
|
202
|
+
n_n
|
|
203
|
+
wet
|
|
204
|
+
uit
|
|
205
|
+
ijd
|
|
206
|
+
ze_
|
|
207
|
+
_zo
|
|
208
|
+
ion
|
|
209
|
+
_ov
|
|
210
|
+
dez
|
|
211
|
+
gem
|
|
212
|
+
met
|
|
213
|
+
tio
|
|
214
|
+
bbe
|
|
215
|
+
ach
|
|
216
|
+
_ni
|
|
217
|
+
hed
|
|
218
|
+
st_
|
|
219
|
+
all
|
|
220
|
+
ies
|
|
221
|
+
per
|
|
222
|
+
heb
|
|
223
|
+
ebb
|
|
224
|
+
e_i
|
|
225
|
+
toe
|
|
226
|
+
es_
|
|
227
|
+
taa
|
|
228
|
+
n_m
|
|
229
|
+
nte
|
|
230
|
+
ien
|
|
231
|
+
el_
|
|
232
|
+
nin
|
|
233
|
+
ale
|
|
234
|
+
ben
|
|
235
|
+
daa
|
|
236
|
+
sti
|
|
237
|
+
_ma
|
|
238
|
+
mee
|
|
239
|
+
kin
|
|
240
|
+
pen
|
|
241
|
+
e_h
|
|
242
|
+
wer
|
|
243
|
+
ont
|
|
244
|
+
iet
|
|
245
|
+
tig
|
|
246
|
+
g_o
|
|
247
|
+
s_e
|
|
248
|
+
_er
|
|
249
|
+
igd
|
|
250
|
+
ete
|
|
251
|
+
ang
|
|
252
|
+
lan
|
|
253
|
+
nsc
|
|
254
|
+
ema
|
|
255
|
+
man
|
|
256
|
+
t_g
|
|
257
|
+
is_
|
|
258
|
+
beg
|
|
259
|
+
her
|
|
260
|
+
esc
|
|
261
|
+
bij
|
|
262
|
+
d_o
|
|
263
|
+
ron
|
|
264
|
+
tin
|
|
265
|
+
nal
|
|
266
|
+
eer
|
|
267
|
+
p_v
|
|
268
|
+
edi
|
|
269
|
+
erm
|
|
270
|
+
ite
|
|
271
|
+
t_w
|
|
272
|
+
t_a
|
|
273
|
+
_hu
|
|
274
|
+
rwi
|
|
275
|
+
wij
|
|
276
|
+
ijs
|
|
277
|
+
r_e
|
|
278
|
+
weg
|
|
279
|
+
js_
|
|
280
|
+
rmi
|
|
281
|
+
naa
|
|
282
|
+
t_b
|
|
283
|
+
app
|
|
284
|
+
rwe
|
|
285
|
+
_bi
|
|
286
|
+
t_z
|
|
287
|
+
ker
|
|
288
|
+
ame
|
|
289
|
+
eri
|
|
290
|
+
ken
|
|
291
|
+
_an
|
|
292
|
+
ar_
|
|
293
|
+
_la
|
|
294
|
+
tre
|
|
295
|
+
ger
|
|
296
|
+
rdi
|
|
297
|
+
tan
|
|
298
|
+
eit
|
|
299
|
+
gde
|
|
300
|
+
g_i
|
|
301
|
+
d_z
|
|
302
|
+
oep
|