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
|
+
# pol: 300 most frequent trigrams, most frequent first. "_" marks a word boundary.
|
|
2
|
+
# Ported from whatlang 0.18.0 (MIT), see ../LICENSE-whatlang.
|
|
3
|
+
_pr
|
|
4
|
+
nie
|
|
5
|
+
_i_
|
|
6
|
+
ie_
|
|
7
|
+
pra
|
|
8
|
+
_po
|
|
9
|
+
ani
|
|
10
|
+
raw
|
|
11
|
+
ia_
|
|
12
|
+
nia
|
|
13
|
+
wie
|
|
14
|
+
go_
|
|
15
|
+
_do
|
|
16
|
+
ch_
|
|
17
|
+
ego
|
|
18
|
+
iek
|
|
19
|
+
owi
|
|
20
|
+
_ni
|
|
21
|
+
ści
|
|
22
|
+
ci_
|
|
23
|
+
a_p
|
|
24
|
+
do_
|
|
25
|
+
awo
|
|
26
|
+
_cz
|
|
27
|
+
ośc
|
|
28
|
+
ych
|
|
29
|
+
_ma
|
|
30
|
+
ek_
|
|
31
|
+
rze
|
|
32
|
+
_na
|
|
33
|
+
prz
|
|
34
|
+
_w_
|
|
35
|
+
wo_
|
|
36
|
+
ej_
|
|
37
|
+
_za
|
|
38
|
+
noś
|
|
39
|
+
czł
|
|
40
|
+
zło
|
|
41
|
+
eni
|
|
42
|
+
wa_
|
|
43
|
+
_je
|
|
44
|
+
łow
|
|
45
|
+
i_p
|
|
46
|
+
wol
|
|
47
|
+
oln
|
|
48
|
+
_lu
|
|
49
|
+
rod
|
|
50
|
+
_ka
|
|
51
|
+
_wo
|
|
52
|
+
lno
|
|
53
|
+
wsz
|
|
54
|
+
y_c
|
|
55
|
+
ma_
|
|
56
|
+
ny_
|
|
57
|
+
każ
|
|
58
|
+
ażd
|
|
59
|
+
o_d
|
|
60
|
+
stw
|
|
61
|
+
owa
|
|
62
|
+
dy_
|
|
63
|
+
żdy
|
|
64
|
+
_wy
|
|
65
|
+
rzy
|
|
66
|
+
sta
|
|
67
|
+
ecz
|
|
68
|
+
_sw
|
|
69
|
+
dzi
|
|
70
|
+
i_w
|
|
71
|
+
e_p
|
|
72
|
+
czn
|
|
73
|
+
twa
|
|
74
|
+
na_
|
|
75
|
+
zys
|
|
76
|
+
ów_
|
|
77
|
+
szy
|
|
78
|
+
ub_
|
|
79
|
+
lub
|
|
80
|
+
a_w
|
|
81
|
+
est
|
|
82
|
+
kie
|
|
83
|
+
k_m
|
|
84
|
+
wan
|
|
85
|
+
_sp
|
|
86
|
+
ają
|
|
87
|
+
_ws
|
|
88
|
+
e_w
|
|
89
|
+
pow
|
|
90
|
+
pos
|
|
91
|
+
nyc
|
|
92
|
+
rac
|
|
93
|
+
spo
|
|
94
|
+
ać_
|
|
95
|
+
a_i
|
|
96
|
+
cze
|
|
97
|
+
sze
|
|
98
|
+
neg
|
|
99
|
+
yst
|
|
100
|
+
jak
|
|
101
|
+
_ja
|
|
102
|
+
o_p
|
|
103
|
+
pod
|
|
104
|
+
acj
|
|
105
|
+
ne_
|
|
106
|
+
ńst
|
|
107
|
+
aro
|
|
108
|
+
mi_
|
|
109
|
+
_z_
|
|
110
|
+
i_i
|
|
111
|
+
nar
|
|
112
|
+
_ko
|
|
113
|
+
obo
|
|
114
|
+
awa
|
|
115
|
+
_ro
|
|
116
|
+
i_n
|
|
117
|
+
jąc
|
|
118
|
+
zec
|
|
119
|
+
zne
|
|
120
|
+
zan
|
|
121
|
+
dow
|
|
122
|
+
_ró
|
|
123
|
+
iej
|
|
124
|
+
zy_
|
|
125
|
+
zen
|
|
126
|
+
nic
|
|
127
|
+
ony
|
|
128
|
+
aw_
|
|
129
|
+
i_z
|
|
130
|
+
czy
|
|
131
|
+
no_
|
|
132
|
+
nej
|
|
133
|
+
o_s
|
|
134
|
+
rów
|
|
135
|
+
odn
|
|
136
|
+
cy_
|
|
137
|
+
ówn
|
|
138
|
+
odz
|
|
139
|
+
o_w
|
|
140
|
+
o_z
|
|
141
|
+
jeg
|
|
142
|
+
edn
|
|
143
|
+
o_o
|
|
144
|
+
aki
|
|
145
|
+
mie
|
|
146
|
+
ien
|
|
147
|
+
kol
|
|
148
|
+
_in
|
|
149
|
+
zie
|
|
150
|
+
bez
|
|
151
|
+
ami
|
|
152
|
+
eńs
|
|
153
|
+
owo
|
|
154
|
+
dno
|
|
155
|
+
_ob
|
|
156
|
+
_or
|
|
157
|
+
_st
|
|
158
|
+
a_s
|
|
159
|
+
ni_
|
|
160
|
+
orz
|
|
161
|
+
o_u
|
|
162
|
+
ym_
|
|
163
|
+
stę
|
|
164
|
+
tęp
|
|
165
|
+
łec
|
|
166
|
+
jed
|
|
167
|
+
i_k
|
|
168
|
+
_os
|
|
169
|
+
w_c
|
|
170
|
+
lwi
|
|
171
|
+
ez_
|
|
172
|
+
olw
|
|
173
|
+
ołe
|
|
174
|
+
poł
|
|
175
|
+
cji
|
|
176
|
+
y_w
|
|
177
|
+
o_n
|
|
178
|
+
wia
|
|
179
|
+
_be
|
|
180
|
+
któ
|
|
181
|
+
a_j
|
|
182
|
+
zna
|
|
183
|
+
zyn
|
|
184
|
+
owe
|
|
185
|
+
wob
|
|
186
|
+
ka_
|
|
187
|
+
wyc
|
|
188
|
+
owy
|
|
189
|
+
ji_
|
|
190
|
+
_od
|
|
191
|
+
aln
|
|
192
|
+
inn
|
|
193
|
+
jes
|
|
194
|
+
icz
|
|
195
|
+
h_p
|
|
196
|
+
i_s
|
|
197
|
+
się
|
|
198
|
+
a_o
|
|
199
|
+
ją_
|
|
200
|
+
ost
|
|
201
|
+
kra
|
|
202
|
+
st_
|
|
203
|
+
sza
|
|
204
|
+
swo
|
|
205
|
+
war
|
|
206
|
+
cza
|
|
207
|
+
roz
|
|
208
|
+
y_s
|
|
209
|
+
raz
|
|
210
|
+
nik
|
|
211
|
+
ara
|
|
212
|
+
ora
|
|
213
|
+
lud
|
|
214
|
+
i_o
|
|
215
|
+
a_z
|
|
216
|
+
zes
|
|
217
|
+
_kr
|
|
218
|
+
ran
|
|
219
|
+
ows
|
|
220
|
+
ech
|
|
221
|
+
w_p
|
|
222
|
+
dów
|
|
223
|
+
ą_p
|
|
224
|
+
pop
|
|
225
|
+
a_n
|
|
226
|
+
tki
|
|
227
|
+
stk
|
|
228
|
+
gan
|
|
229
|
+
zon
|
|
230
|
+
raj
|
|
231
|
+
e_o
|
|
232
|
+
iec
|
|
233
|
+
i_l
|
|
234
|
+
_si
|
|
235
|
+
że_
|
|
236
|
+
eka
|
|
237
|
+
_kt
|
|
238
|
+
_de
|
|
239
|
+
em_
|
|
240
|
+
tór
|
|
241
|
+
ię_
|
|
242
|
+
wni
|
|
243
|
+
lni
|
|
244
|
+
ejs
|
|
245
|
+
ini
|
|
246
|
+
odo
|
|
247
|
+
dni
|
|
248
|
+
ełn
|
|
249
|
+
kow
|
|
250
|
+
peł
|
|
251
|
+
a_d
|
|
252
|
+
ron
|
|
253
|
+
dek
|
|
254
|
+
pie
|
|
255
|
+
udz
|
|
256
|
+
bod
|
|
257
|
+
nan
|
|
258
|
+
h_i
|
|
259
|
+
dst
|
|
260
|
+
ieg
|
|
261
|
+
taw
|
|
262
|
+
z_p
|
|
263
|
+
z_w
|
|
264
|
+
zeń
|
|
265
|
+
god
|
|
266
|
+
iu_
|
|
267
|
+
ano
|
|
268
|
+
lar
|
|
269
|
+
_to
|
|
270
|
+
y_z
|
|
271
|
+
a_k
|
|
272
|
+
ale
|
|
273
|
+
kla
|
|
274
|
+
trz
|
|
275
|
+
zaw
|
|
276
|
+
ich
|
|
277
|
+
e_i
|
|
278
|
+
ier
|
|
279
|
+
iko
|
|
280
|
+
dzy
|
|
281
|
+
chn
|
|
282
|
+
w_z
|
|
283
|
+
by_
|
|
284
|
+
ków
|
|
285
|
+
adz
|
|
286
|
+
ekl
|
|
287
|
+
ywa
|
|
288
|
+
ju_
|
|
289
|
+
och
|
|
290
|
+
kor
|
|
291
|
+
sob
|
|
292
|
+
ocz
|
|
293
|
+
oso
|
|
294
|
+
u_p
|
|
295
|
+
du_
|
|
296
|
+
tyc
|
|
297
|
+
tan
|
|
298
|
+
ędz
|
|
299
|
+
_mi
|
|
300
|
+
e_s
|
|
301
|
+
_ta
|
|
302
|
+
ki_
|
|
@@ -0,0 +1,302 @@
|
|
|
1
|
+
# por: 300 most frequent trigrams, most frequent first. "_" marks a word boundary.
|
|
2
|
+
# Ported from whatlang 0.18.0 (MIT), see ../LICENSE-whatlang.
|
|
3
|
+
os_
|
|
4
|
+
de_
|
|
5
|
+
_de
|
|
6
|
+
_a_
|
|
7
|
+
_e_
|
|
8
|
+
o_d
|
|
9
|
+
to_
|
|
10
|
+
ão_
|
|
11
|
+
_di
|
|
12
|
+
ent
|
|
13
|
+
da_
|
|
14
|
+
ito
|
|
15
|
+
em_
|
|
16
|
+
_co
|
|
17
|
+
eit
|
|
18
|
+
as_
|
|
19
|
+
dir
|
|
20
|
+
es_
|
|
21
|
+
ire
|
|
22
|
+
rei
|
|
23
|
+
_se
|
|
24
|
+
ção
|
|
25
|
+
ade
|
|
26
|
+
a_p
|
|
27
|
+
dad
|
|
28
|
+
e_d
|
|
29
|
+
s_d
|
|
30
|
+
men
|
|
31
|
+
nte
|
|
32
|
+
do_
|
|
33
|
+
s_e
|
|
34
|
+
_pr
|
|
35
|
+
_pe
|
|
36
|
+
dos
|
|
37
|
+
_to
|
|
38
|
+
_da
|
|
39
|
+
a_a
|
|
40
|
+
o_e
|
|
41
|
+
_o_
|
|
42
|
+
o_a
|
|
43
|
+
ess
|
|
44
|
+
con
|
|
45
|
+
tod
|
|
46
|
+
que
|
|
47
|
+
_qu
|
|
48
|
+
te_
|
|
49
|
+
e_a
|
|
50
|
+
_do
|
|
51
|
+
al_
|
|
52
|
+
res
|
|
53
|
+
ida
|
|
54
|
+
m_d
|
|
55
|
+
_in
|
|
56
|
+
_ou
|
|
57
|
+
er_
|
|
58
|
+
sso
|
|
59
|
+
_na
|
|
60
|
+
_re
|
|
61
|
+
_po
|
|
62
|
+
a_s
|
|
63
|
+
_li
|
|
64
|
+
uma
|
|
65
|
+
cia
|
|
66
|
+
ar_
|
|
67
|
+
pro
|
|
68
|
+
e_e
|
|
69
|
+
a_d
|
|
70
|
+
_te
|
|
71
|
+
açã
|
|
72
|
+
a_t
|
|
73
|
+
_es
|
|
74
|
+
_su
|
|
75
|
+
ou_
|
|
76
|
+
ue_
|
|
77
|
+
s_p
|
|
78
|
+
tos
|
|
79
|
+
a_e
|
|
80
|
+
des
|
|
81
|
+
ra_
|
|
82
|
+
com
|
|
83
|
+
no_
|
|
84
|
+
ame
|
|
85
|
+
ia_
|
|
86
|
+
e_p
|
|
87
|
+
tem
|
|
88
|
+
nto
|
|
89
|
+
_pa
|
|
90
|
+
is_
|
|
91
|
+
est
|
|
92
|
+
tra
|
|
93
|
+
ões
|
|
94
|
+
na_
|
|
95
|
+
s_o
|
|
96
|
+
oda
|
|
97
|
+
das
|
|
98
|
+
ser
|
|
99
|
+
soa
|
|
100
|
+
s_n
|
|
101
|
+
pes
|
|
102
|
+
o_p
|
|
103
|
+
s_a
|
|
104
|
+
o_s
|
|
105
|
+
e_o
|
|
106
|
+
_em
|
|
107
|
+
_as
|
|
108
|
+
_à_
|
|
109
|
+
o_o
|
|
110
|
+
ais
|
|
111
|
+
ber
|
|
112
|
+
ado
|
|
113
|
+
oa_
|
|
114
|
+
o_t
|
|
115
|
+
e_s
|
|
116
|
+
man
|
|
117
|
+
sua
|
|
118
|
+
ua_
|
|
119
|
+
_no
|
|
120
|
+
_os
|
|
121
|
+
a_c
|
|
122
|
+
ter
|
|
123
|
+
çõe
|
|
124
|
+
erd
|
|
125
|
+
lib
|
|
126
|
+
rda
|
|
127
|
+
s_s
|
|
128
|
+
nci
|
|
129
|
+
ibe
|
|
130
|
+
e_n
|
|
131
|
+
ica
|
|
132
|
+
odo
|
|
133
|
+
so_
|
|
134
|
+
nal
|
|
135
|
+
ntr
|
|
136
|
+
s_t
|
|
137
|
+
hum
|
|
138
|
+
ura
|
|
139
|
+
_ao
|
|
140
|
+
ona
|
|
141
|
+
ual
|
|
142
|
+
_so
|
|
143
|
+
or_
|
|
144
|
+
ma_
|
|
145
|
+
sta
|
|
146
|
+
o_c
|
|
147
|
+
a_n
|
|
148
|
+
pre
|
|
149
|
+
ara
|
|
150
|
+
era
|
|
151
|
+
ons
|
|
152
|
+
e_t
|
|
153
|
+
r_a
|
|
154
|
+
par
|
|
155
|
+
o_à
|
|
156
|
+
_hu
|
|
157
|
+
ind
|
|
158
|
+
por
|
|
159
|
+
cio
|
|
160
|
+
ria
|
|
161
|
+
m_a
|
|
162
|
+
s_c
|
|
163
|
+
_um
|
|
164
|
+
a_l
|
|
165
|
+
gua
|
|
166
|
+
ran
|
|
167
|
+
_en
|
|
168
|
+
ndi
|
|
169
|
+
o_i
|
|
170
|
+
e_c
|
|
171
|
+
raç
|
|
172
|
+
ion
|
|
173
|
+
nid
|
|
174
|
+
aci
|
|
175
|
+
ano
|
|
176
|
+
soc
|
|
177
|
+
e_r
|
|
178
|
+
oci
|
|
179
|
+
_ac
|
|
180
|
+
und
|
|
181
|
+
sen
|
|
182
|
+
nos
|
|
183
|
+
nsi
|
|
184
|
+
rec
|
|
185
|
+
ime
|
|
186
|
+
ali
|
|
187
|
+
int
|
|
188
|
+
um_
|
|
189
|
+
per
|
|
190
|
+
nac
|
|
191
|
+
_al
|
|
192
|
+
m_o
|
|
193
|
+
r_p
|
|
194
|
+
_fu
|
|
195
|
+
ndo
|
|
196
|
+
ont
|
|
197
|
+
açõ
|
|
198
|
+
_ig
|
|
199
|
+
igu
|
|
200
|
+
fun
|
|
201
|
+
nta
|
|
202
|
+
_ma
|
|
203
|
+
uni
|
|
204
|
+
cçã
|
|
205
|
+
ere
|
|
206
|
+
_ex
|
|
207
|
+
a_i
|
|
208
|
+
_me
|
|
209
|
+
ese
|
|
210
|
+
rio
|
|
211
|
+
l_d
|
|
212
|
+
a_o
|
|
213
|
+
s_h
|
|
214
|
+
pel
|
|
215
|
+
ada
|
|
216
|
+
pri
|
|
217
|
+
ide
|
|
218
|
+
am_
|
|
219
|
+
m_p
|
|
220
|
+
pod
|
|
221
|
+
s_f
|
|
222
|
+
ém_
|
|
223
|
+
a_f
|
|
224
|
+
io_
|
|
225
|
+
ode
|
|
226
|
+
ca_
|
|
227
|
+
ita
|
|
228
|
+
lid
|
|
229
|
+
tiv
|
|
230
|
+
e_f
|
|
231
|
+
vid
|
|
232
|
+
r_e
|
|
233
|
+
esp
|
|
234
|
+
nda
|
|
235
|
+
omo
|
|
236
|
+
e_l
|
|
237
|
+
naç
|
|
238
|
+
o_r
|
|
239
|
+
ant
|
|
240
|
+
a_q
|
|
241
|
+
tad
|
|
242
|
+
lic
|
|
243
|
+
iva
|
|
244
|
+
_fa
|
|
245
|
+
ver
|
|
246
|
+
s_l
|
|
247
|
+
ial
|
|
248
|
+
cla
|
|
249
|
+
ngu
|
|
250
|
+
ing
|
|
251
|
+
_ca
|
|
252
|
+
mo_
|
|
253
|
+
der
|
|
254
|
+
_vi
|
|
255
|
+
eli
|
|
256
|
+
ist
|
|
257
|
+
ta_
|
|
258
|
+
se_
|
|
259
|
+
ati
|
|
260
|
+
ios
|
|
261
|
+
ido
|
|
262
|
+
r_o
|
|
263
|
+
eci
|
|
264
|
+
dis
|
|
265
|
+
_un
|
|
266
|
+
e_i
|
|
267
|
+
r_d
|
|
268
|
+
ecç
|
|
269
|
+
o_q
|
|
270
|
+
s_i
|
|
271
|
+
qua
|
|
272
|
+
ênc
|
|
273
|
+
a_m
|
|
274
|
+
seu
|
|
275
|
+
sti
|
|
276
|
+
nin
|
|
277
|
+
uer
|
|
278
|
+
rar
|
|
279
|
+
cas
|
|
280
|
+
aos
|
|
281
|
+
ens
|
|
282
|
+
gué
|
|
283
|
+
ias
|
|
284
|
+
sid
|
|
285
|
+
uém
|
|
286
|
+
tur
|
|
287
|
+
dam
|
|
288
|
+
sse
|
|
289
|
+
ao_
|
|
290
|
+
ela
|
|
291
|
+
l_e
|
|
292
|
+
for
|
|
293
|
+
tec
|
|
294
|
+
ote
|
|
295
|
+
_pl
|
|
296
|
+
ena
|
|
297
|
+
_tr
|
|
298
|
+
m_c
|
|
299
|
+
tro
|
|
300
|
+
_ni
|
|
301
|
+
ico
|
|
302
|
+
rot
|