ruby_wordcram 1.0.1 → 2.0.0
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 +4 -4
- data/.gitignore +3 -0
- data/.mvn/extensions.xml +8 -0
- data/.mvn/wrapper/maven-wrapper.properties +1 -0
- data/Rakefile +28 -5
- data/docs/_posts/2017-03-07-getting_started.md +3 -2
- data/docs/_posts/2017-03-07-under_the_hood.md +33 -0
- data/lib/WordCram.jar +0 -0
- data/lib/jsoup-1.10.2.jar +0 -0
- data/lib/ruby_wordcram/version.rb +1 -1
- data/lib/ruby_wordcram.rb +1 -2
- data/pom.rb +53 -0
- data/pom.xml +87 -0
- data/ruby_wordcram.gemspec +1 -2
- data/src/cue/lang/Counter.java +141 -0
- data/src/cue/lang/IterableText.java +10 -0
- data/src/cue/lang/NGramIterator.java +151 -0
- data/src/cue/lang/SentenceIterator.java +86 -0
- data/src/cue/lang/WordIterator.java +60 -0
- data/src/cue/lang/stop/StopWords.java +114 -0
- data/src/cue/lang/stop/arabic +351 -0
- data/src/cue/lang/stop/armenian +45 -0
- data/src/cue/lang/stop/catalan +219 -0
- data/src/cue/lang/stop/croatian +2024 -0
- data/src/cue/lang/stop/czech +256 -0
- data/src/cue/lang/stop/danish +94 -0
- data/src/cue/lang/stop/dutch +107 -0
- data/src/cue/lang/stop/english +183 -0
- data/src/cue/lang/stop/esperanto +180 -0
- data/src/cue/lang/stop/farsi +966 -0
- data/src/cue/lang/stop/finnish +235 -0
- data/src/cue/lang/stop/french +543 -0
- data/src/cue/lang/stop/german +231 -0
- data/src/cue/lang/stop/greek +637 -0
- data/src/cue/lang/stop/hebrew +220 -0
- data/src/cue/lang/stop/hindi +97 -0
- data/src/cue/lang/stop/hungarian +202 -0
- data/src/cue/lang/stop/italian +279 -0
- data/src/cue/lang/stop/latin +1 -0
- data/src/cue/lang/stop/norwegian +176 -0
- data/src/cue/lang/stop/polish +138 -0
- data/src/cue/lang/stop/portuguese +204 -0
- data/src/cue/lang/stop/romanian +284 -0
- data/src/cue/lang/stop/russian +652 -0
- data/src/cue/lang/stop/slovak +110 -0
- data/src/cue/lang/stop/slovenian +448 -0
- data/src/cue/lang/stop/spanish +308 -0
- data/src/cue/lang/stop/swedish +114 -0
- data/src/cue/lang/stop/turkish +117 -0
- data/src/cue/lang/unicode/BlockUtil.java +103 -0
- data/src/cue/lang/unicode/Normalizer.java +55 -0
- data/src/cue/lang/unicode/Normalizer6.java +32 -0
- data/src/license.txt +201 -0
- data/src/wordcram/Anglers.java +137 -0
- data/src/wordcram/BBTree.java +133 -0
- data/src/wordcram/BBTreeBuilder.java +61 -0
- data/src/wordcram/Colorers.java +52 -0
- data/src/wordcram/EngineWord.java +73 -0
- data/src/wordcram/Fonters.java +17 -0
- data/src/wordcram/HsbWordColorer.java +28 -0
- data/src/wordcram/ImageShaper.java +91 -0
- data/src/wordcram/Observer.java +9 -0
- data/src/wordcram/PlacerHeatMap.java +134 -0
- data/src/wordcram/Placers.java +74 -0
- data/src/wordcram/PlottingWordNudger.java +38 -0
- data/src/wordcram/PlottingWordPlacer.java +36 -0
- data/src/wordcram/ProcessingWordRenderer.java +42 -0
- data/src/wordcram/RandomWordNudger.java +44 -0
- data/src/wordcram/RenderOptions.java +10 -0
- data/src/wordcram/ShapeBasedPlacer.java +66 -0
- data/src/wordcram/Sizers.java +54 -0
- data/src/wordcram/SketchCallbackObserver.java +70 -0
- data/src/wordcram/SpiralWordNudger.java +31 -0
- data/src/wordcram/SvgWordRenderer.java +110 -0
- data/src/wordcram/SwirlWordPlacer.java +25 -0
- data/src/wordcram/UpperLeftWordPlacer.java +27 -0
- data/src/wordcram/WaveWordPlacer.java +25 -0
- data/src/wordcram/Word.java +357 -0
- data/src/wordcram/WordAngler.java +20 -0
- data/src/wordcram/WordArray.java +18 -0
- data/src/wordcram/WordBag.java +31 -0
- data/src/wordcram/WordColorer.java +25 -0
- data/src/wordcram/WordCounter.java +96 -0
- data/src/wordcram/WordCram.java +920 -0
- data/src/wordcram/WordCramEngine.java +196 -0
- data/src/wordcram/WordFonter.java +24 -0
- data/src/wordcram/WordNudger.java +44 -0
- data/src/wordcram/WordPlacer.java +44 -0
- data/src/wordcram/WordRenderer.java +10 -0
- data/src/wordcram/WordShaper.java +78 -0
- data/src/wordcram/WordSizer.java +46 -0
- data/src/wordcram/WordSkipReason.java +42 -0
- data/src/wordcram/WordSorterAndScaler.java +31 -0
- data/src/wordcram/WordSource.java +5 -0
- data/src/wordcram/text/Html.java +15 -0
- data/src/wordcram/text/Html2Text.java +17 -0
- data/src/wordcram/text/Text.java +15 -0
- data/src/wordcram/text/TextFile.java +23 -0
- data/src/wordcram/text/TextSource.java +5 -0
- data/src/wordcram/text/WebPage.java +23 -0
- metadata +94 -5
- data/lib/cue.language.jar +0 -0
- data/lib/jsoup-1.7.2.jar +0 -0
- data/vendors/Rakefile +0 -51
|
@@ -0,0 +1,110 @@
|
|
|
1
|
+
a
|
|
2
|
+
aby
|
|
3
|
+
aj
|
|
4
|
+
ako
|
|
5
|
+
aký
|
|
6
|
+
ale
|
|
7
|
+
alebo
|
|
8
|
+
ani
|
|
9
|
+
avšak
|
|
10
|
+
ba
|
|
11
|
+
bez
|
|
12
|
+
buï
|
|
13
|
+
cez
|
|
14
|
+
èi
|
|
15
|
+
èí
|
|
16
|
+
èo
|
|
17
|
+
do
|
|
18
|
+
ho
|
|
19
|
+
hoci
|
|
20
|
+
i
|
|
21
|
+
ich
|
|
22
|
+
im
|
|
23
|
+
ja
|
|
24
|
+
jeho
|
|
25
|
+
jej
|
|
26
|
+
jemu
|
|
27
|
+
ju
|
|
28
|
+
k
|
|
29
|
+
kam
|
|
30
|
+
kde
|
|
31
|
+
keï
|
|
32
|
+
kedže
|
|
33
|
+
kto
|
|
34
|
+
ktorý
|
|
35
|
+
ku
|
|
36
|
+
lebo
|
|
37
|
+
ma
|
|
38
|
+
mi
|
|
39
|
+
mòa
|
|
40
|
+
mne
|
|
41
|
+
mnou
|
|
42
|
+
môj
|
|
43
|
+
mu
|
|
44
|
+
my
|
|
45
|
+
na
|
|
46
|
+
nad
|
|
47
|
+
nám
|
|
48
|
+
nami
|
|
49
|
+
nás
|
|
50
|
+
náš
|
|
51
|
+
neho
|
|
52
|
+
nej
|
|
53
|
+
nemu
|
|
54
|
+
nielen
|
|
55
|
+
nich
|
|
56
|
+
nim
|
|
57
|
+
ním
|
|
58
|
+
no
|
|
59
|
+
òom
|
|
60
|
+
òou
|
|
61
|
+
òu
|
|
62
|
+
o
|
|
63
|
+
od
|
|
64
|
+
on
|
|
65
|
+
ona
|
|
66
|
+
oni
|
|
67
|
+
ono
|
|
68
|
+
ony
|
|
69
|
+
po
|
|
70
|
+
pod
|
|
71
|
+
pre
|
|
72
|
+
pred
|
|
73
|
+
pri
|
|
74
|
+
s
|
|
75
|
+
sa
|
|
76
|
+
seba
|
|
77
|
+
sem
|
|
78
|
+
so
|
|
79
|
+
svoj
|
|
80
|
+
tá
|
|
81
|
+
a
|
|
82
|
+
taký
|
|
83
|
+
tam
|
|
84
|
+
teba
|
|
85
|
+
tebe
|
|
86
|
+
tebou
|
|
87
|
+
tej
|
|
88
|
+
ten
|
|
89
|
+
ti
|
|
90
|
+
tie
|
|
91
|
+
to
|
|
92
|
+
toho
|
|
93
|
+
tomu
|
|
94
|
+
tou
|
|
95
|
+
tvoj
|
|
96
|
+
ty
|
|
97
|
+
tým
|
|
98
|
+
v
|
|
99
|
+
vám
|
|
100
|
+
vami
|
|
101
|
+
vás
|
|
102
|
+
váš
|
|
103
|
+
veï
|
|
104
|
+
vo
|
|
105
|
+
však
|
|
106
|
+
vy
|
|
107
|
+
z
|
|
108
|
+
za
|
|
109
|
+
zo
|
|
110
|
+
že
|
|
@@ -0,0 +1,448 @@
|
|
|
1
|
+
a
|
|
2
|
+
ali
|
|
3
|
+
april
|
|
4
|
+
avgust
|
|
5
|
+
b
|
|
6
|
+
bi
|
|
7
|
+
bil
|
|
8
|
+
bila
|
|
9
|
+
bile
|
|
10
|
+
bili
|
|
11
|
+
bilo
|
|
12
|
+
biti
|
|
13
|
+
blizu
|
|
14
|
+
bo
|
|
15
|
+
bodo
|
|
16
|
+
bojo
|
|
17
|
+
bolj
|
|
18
|
+
bom
|
|
19
|
+
bomo
|
|
20
|
+
boste
|
|
21
|
+
boš
|
|
22
|
+
bova
|
|
23
|
+
brez
|
|
24
|
+
c
|
|
25
|
+
cel
|
|
26
|
+
cela
|
|
27
|
+
celi
|
|
28
|
+
celo
|
|
29
|
+
č
|
|
30
|
+
če
|
|
31
|
+
često
|
|
32
|
+
četrta
|
|
33
|
+
četrtek
|
|
34
|
+
četrti
|
|
35
|
+
četrto
|
|
36
|
+
čez
|
|
37
|
+
čigav
|
|
38
|
+
d
|
|
39
|
+
da
|
|
40
|
+
daleč
|
|
41
|
+
dan
|
|
42
|
+
danes
|
|
43
|
+
datum
|
|
44
|
+
december
|
|
45
|
+
deset
|
|
46
|
+
deseta
|
|
47
|
+
deseti
|
|
48
|
+
deseto
|
|
49
|
+
devet
|
|
50
|
+
deveta
|
|
51
|
+
deveti
|
|
52
|
+
deveto
|
|
53
|
+
do
|
|
54
|
+
dober
|
|
55
|
+
dobra
|
|
56
|
+
dobri
|
|
57
|
+
dobro
|
|
58
|
+
dokler
|
|
59
|
+
dol
|
|
60
|
+
dolg
|
|
61
|
+
dolga
|
|
62
|
+
dolgi
|
|
63
|
+
dovolj
|
|
64
|
+
drug
|
|
65
|
+
druga
|
|
66
|
+
drugi
|
|
67
|
+
drugo
|
|
68
|
+
dva
|
|
69
|
+
dve
|
|
70
|
+
e
|
|
71
|
+
eden
|
|
72
|
+
en
|
|
73
|
+
ena
|
|
74
|
+
ene
|
|
75
|
+
eni
|
|
76
|
+
enkrat
|
|
77
|
+
eno
|
|
78
|
+
etc.
|
|
79
|
+
f
|
|
80
|
+
februar
|
|
81
|
+
g
|
|
82
|
+
g.
|
|
83
|
+
ga
|
|
84
|
+
ga.
|
|
85
|
+
gor
|
|
86
|
+
gospa
|
|
87
|
+
gospod
|
|
88
|
+
h
|
|
89
|
+
halo
|
|
90
|
+
i
|
|
91
|
+
idr.
|
|
92
|
+
ii
|
|
93
|
+
iii
|
|
94
|
+
in
|
|
95
|
+
iv
|
|
96
|
+
ix
|
|
97
|
+
iz
|
|
98
|
+
j
|
|
99
|
+
januar
|
|
100
|
+
jaz
|
|
101
|
+
je
|
|
102
|
+
ji
|
|
103
|
+
jih
|
|
104
|
+
jim
|
|
105
|
+
jo
|
|
106
|
+
julij
|
|
107
|
+
junij
|
|
108
|
+
jutri
|
|
109
|
+
k
|
|
110
|
+
kadarkoli
|
|
111
|
+
kaj
|
|
112
|
+
kajti
|
|
113
|
+
kako
|
|
114
|
+
kakor
|
|
115
|
+
kamor
|
|
116
|
+
kamorkoli
|
|
117
|
+
kar
|
|
118
|
+
karkoli
|
|
119
|
+
katerikoli
|
|
120
|
+
kdaj
|
|
121
|
+
kdo
|
|
122
|
+
kdorkoli
|
|
123
|
+
ker
|
|
124
|
+
ki
|
|
125
|
+
kje
|
|
126
|
+
kjer
|
|
127
|
+
kjerkoli
|
|
128
|
+
ko
|
|
129
|
+
koder
|
|
130
|
+
koderkoli
|
|
131
|
+
koga
|
|
132
|
+
komu
|
|
133
|
+
kot
|
|
134
|
+
kratek
|
|
135
|
+
kratka
|
|
136
|
+
kratke
|
|
137
|
+
kratki
|
|
138
|
+
l
|
|
139
|
+
lahka
|
|
140
|
+
lahke
|
|
141
|
+
lahki
|
|
142
|
+
lahko
|
|
143
|
+
le
|
|
144
|
+
lep
|
|
145
|
+
lepa
|
|
146
|
+
lepe
|
|
147
|
+
lepi
|
|
148
|
+
lepo
|
|
149
|
+
leto
|
|
150
|
+
m
|
|
151
|
+
maj
|
|
152
|
+
majhen
|
|
153
|
+
majhna
|
|
154
|
+
majhni
|
|
155
|
+
malce
|
|
156
|
+
malo
|
|
157
|
+
manj
|
|
158
|
+
marec
|
|
159
|
+
me
|
|
160
|
+
med
|
|
161
|
+
medtem
|
|
162
|
+
mene
|
|
163
|
+
mesec
|
|
164
|
+
me
|
|
165
|
+
mi
|
|
166
|
+
midva
|
|
167
|
+
midve
|
|
168
|
+
mnogo
|
|
169
|
+
moj
|
|
170
|
+
moja
|
|
171
|
+
moje
|
|
172
|
+
mora
|
|
173
|
+
morajo
|
|
174
|
+
moram
|
|
175
|
+
moramo
|
|
176
|
+
moraš
|
|
177
|
+
morate
|
|
178
|
+
morem
|
|
179
|
+
mu
|
|
180
|
+
n
|
|
181
|
+
na
|
|
182
|
+
nad
|
|
183
|
+
naj
|
|
184
|
+
najina
|
|
185
|
+
najino
|
|
186
|
+
najmanj
|
|
187
|
+
naju
|
|
188
|
+
največ
|
|
189
|
+
nam
|
|
190
|
+
narobe
|
|
191
|
+
nas
|
|
192
|
+
naš
|
|
193
|
+
naša
|
|
194
|
+
naše
|
|
195
|
+
nato
|
|
196
|
+
nazaj
|
|
197
|
+
ne
|
|
198
|
+
nedavno
|
|
199
|
+
nedelja
|
|
200
|
+
nek
|
|
201
|
+
neka
|
|
202
|
+
nekaj
|
|
203
|
+
nekatere
|
|
204
|
+
nekateri
|
|
205
|
+
nekatero
|
|
206
|
+
nekdo
|
|
207
|
+
neke
|
|
208
|
+
nekega
|
|
209
|
+
neki
|
|
210
|
+
nekje
|
|
211
|
+
neko
|
|
212
|
+
nekoč
|
|
213
|
+
nekoga
|
|
214
|
+
ni
|
|
215
|
+
nič
|
|
216
|
+
nikamor
|
|
217
|
+
nikdar
|
|
218
|
+
nikjer
|
|
219
|
+
nikoli
|
|
220
|
+
nje
|
|
221
|
+
njega
|
|
222
|
+
njegov
|
|
223
|
+
njegova
|
|
224
|
+
njegovo
|
|
225
|
+
njej
|
|
226
|
+
njemu
|
|
227
|
+
njen
|
|
228
|
+
njena
|
|
229
|
+
njeno
|
|
230
|
+
nji
|
|
231
|
+
njih
|
|
232
|
+
njihov
|
|
233
|
+
njihova
|
|
234
|
+
njihovo
|
|
235
|
+
njiju
|
|
236
|
+
njim
|
|
237
|
+
njo
|
|
238
|
+
njo
|
|
239
|
+
njun
|
|
240
|
+
njuna
|
|
241
|
+
njuno
|
|
242
|
+
no
|
|
243
|
+
nocoj
|
|
244
|
+
november
|
|
245
|
+
npr.
|
|
246
|
+
o
|
|
247
|
+
ob
|
|
248
|
+
oba
|
|
249
|
+
obe
|
|
250
|
+
oboje
|
|
251
|
+
od
|
|
252
|
+
odprt
|
|
253
|
+
odprta
|
|
254
|
+
odprti
|
|
255
|
+
okoli
|
|
256
|
+
oktober
|
|
257
|
+
on
|
|
258
|
+
onadva
|
|
259
|
+
one
|
|
260
|
+
oni
|
|
261
|
+
onidve
|
|
262
|
+
osem
|
|
263
|
+
osma
|
|
264
|
+
osmi
|
|
265
|
+
osmo
|
|
266
|
+
oz.
|
|
267
|
+
p
|
|
268
|
+
pa
|
|
269
|
+
pet
|
|
270
|
+
peta
|
|
271
|
+
petek
|
|
272
|
+
peti
|
|
273
|
+
peto
|
|
274
|
+
po
|
|
275
|
+
pod
|
|
276
|
+
pogosto
|
|
277
|
+
poleg
|
|
278
|
+
poln
|
|
279
|
+
polna
|
|
280
|
+
polni
|
|
281
|
+
polno
|
|
282
|
+
ponavadi
|
|
283
|
+
ponedeljek
|
|
284
|
+
ponovno
|
|
285
|
+
potem
|
|
286
|
+
povsod
|
|
287
|
+
pozdravljen
|
|
288
|
+
pozdravljeni
|
|
289
|
+
prav
|
|
290
|
+
prava
|
|
291
|
+
prave
|
|
292
|
+
pravi
|
|
293
|
+
pravo
|
|
294
|
+
prazen
|
|
295
|
+
prazna
|
|
296
|
+
prazno
|
|
297
|
+
prbl.
|
|
298
|
+
pribl.
|
|
299
|
+
precej
|
|
300
|
+
pred
|
|
301
|
+
prej
|
|
302
|
+
preko
|
|
303
|
+
pri
|
|
304
|
+
približno
|
|
305
|
+
primer
|
|
306
|
+
pripravljen
|
|
307
|
+
pripravljena
|
|
308
|
+
pripravljeni
|
|
309
|
+
proti
|
|
310
|
+
prva
|
|
311
|
+
prvi
|
|
312
|
+
prvo
|
|
313
|
+
r
|
|
314
|
+
ravno
|
|
315
|
+
reč
|
|
316
|
+
redko
|
|
317
|
+
res
|
|
318
|
+
s
|
|
319
|
+
saj
|
|
320
|
+
sam
|
|
321
|
+
sama
|
|
322
|
+
same
|
|
323
|
+
sami
|
|
324
|
+
samo
|
|
325
|
+
se
|
|
326
|
+
sebe
|
|
327
|
+
sebi
|
|
328
|
+
sedaj
|
|
329
|
+
sedem
|
|
330
|
+
sedma
|
|
331
|
+
sedmi
|
|
332
|
+
sedmo
|
|
333
|
+
sem
|
|
334
|
+
september
|
|
335
|
+
seveda
|
|
336
|
+
si
|
|
337
|
+
sicer
|
|
338
|
+
skoraj
|
|
339
|
+
skozi
|
|
340
|
+
slab
|
|
341
|
+
smo
|
|
342
|
+
so
|
|
343
|
+
sobota
|
|
344
|
+
spet
|
|
345
|
+
sreda
|
|
346
|
+
srednja
|
|
347
|
+
srednji
|
|
348
|
+
sta
|
|
349
|
+
ste
|
|
350
|
+
stran
|
|
351
|
+
stvar
|
|
352
|
+
sva
|
|
353
|
+
š
|
|
354
|
+
šest
|
|
355
|
+
šesta
|
|
356
|
+
šesti
|
|
357
|
+
šesto
|
|
358
|
+
štiri
|
|
359
|
+
t
|
|
360
|
+
ta
|
|
361
|
+
tak
|
|
362
|
+
taka
|
|
363
|
+
take
|
|
364
|
+
taki
|
|
365
|
+
tako
|
|
366
|
+
takoj
|
|
367
|
+
tam
|
|
368
|
+
te
|
|
369
|
+
tebe
|
|
370
|
+
tebi
|
|
371
|
+
tega
|
|
372
|
+
težak
|
|
373
|
+
težka
|
|
374
|
+
težki
|
|
375
|
+
težko
|
|
376
|
+
ti
|
|
377
|
+
tista
|
|
378
|
+
tiste
|
|
379
|
+
tisti
|
|
380
|
+
tisto
|
|
381
|
+
tj.
|
|
382
|
+
tja
|
|
383
|
+
to
|
|
384
|
+
toda
|
|
385
|
+
torek
|
|
386
|
+
tretja
|
|
387
|
+
tretje
|
|
388
|
+
tretji
|
|
389
|
+
tri
|
|
390
|
+
tu
|
|
391
|
+
tudi
|
|
392
|
+
tukaj
|
|
393
|
+
tvoj
|
|
394
|
+
tvoja
|
|
395
|
+
tvoje
|
|
396
|
+
u
|
|
397
|
+
v
|
|
398
|
+
vaju
|
|
399
|
+
vam
|
|
400
|
+
vas
|
|
401
|
+
vaš
|
|
402
|
+
vaša
|
|
403
|
+
vaše
|
|
404
|
+
včasih
|
|
405
|
+
včeraj
|
|
406
|
+
ve
|
|
407
|
+
več
|
|
408
|
+
vedno
|
|
409
|
+
velik
|
|
410
|
+
velika
|
|
411
|
+
veliki
|
|
412
|
+
veliko
|
|
413
|
+
vendar
|
|
414
|
+
ves
|
|
415
|
+
vi
|
|
416
|
+
vidva
|
|
417
|
+
vii
|
|
418
|
+
viii
|
|
419
|
+
visok
|
|
420
|
+
visoka
|
|
421
|
+
visoke
|
|
422
|
+
visoki
|
|
423
|
+
vsa
|
|
424
|
+
vsaj
|
|
425
|
+
vsak
|
|
426
|
+
vsake
|
|
427
|
+
vsaka
|
|
428
|
+
vsakdo
|
|
429
|
+
vsaki
|
|
430
|
+
vsakomur
|
|
431
|
+
vse
|
|
432
|
+
vsega
|
|
433
|
+
vsi
|
|
434
|
+
vso
|
|
435
|
+
x
|
|
436
|
+
z
|
|
437
|
+
za
|
|
438
|
+
zadaj
|
|
439
|
+
zadnji
|
|
440
|
+
zakaj
|
|
441
|
+
zaprta
|
|
442
|
+
zaprti
|
|
443
|
+
zaprto
|
|
444
|
+
zdaj
|
|
445
|
+
zelo
|
|
446
|
+
zunaj
|
|
447
|
+
ž
|
|
448
|
+
že
|