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 +1,256 @@
|
|
|
1
|
+
ačkoli
|
|
2
|
+
ahoj
|
|
3
|
+
ale
|
|
4
|
+
anebo
|
|
5
|
+
ano
|
|
6
|
+
asi
|
|
7
|
+
aspoň
|
|
8
|
+
během
|
|
9
|
+
bez
|
|
10
|
+
beze
|
|
11
|
+
blízko
|
|
12
|
+
bohužel
|
|
13
|
+
brzo
|
|
14
|
+
bude
|
|
15
|
+
budeme
|
|
16
|
+
budeš
|
|
17
|
+
budete
|
|
18
|
+
budou
|
|
19
|
+
budu
|
|
20
|
+
byl
|
|
21
|
+
byla
|
|
22
|
+
byli
|
|
23
|
+
bylo
|
|
24
|
+
byly
|
|
25
|
+
bys
|
|
26
|
+
čau
|
|
27
|
+
chce
|
|
28
|
+
chceme
|
|
29
|
+
chceš
|
|
30
|
+
chcete
|
|
31
|
+
chci
|
|
32
|
+
chtějí
|
|
33
|
+
chtít
|
|
34
|
+
chut'
|
|
35
|
+
chuti
|
|
36
|
+
co
|
|
37
|
+
čtrnáct
|
|
38
|
+
čtyři
|
|
39
|
+
dál
|
|
40
|
+
dále
|
|
41
|
+
daleko
|
|
42
|
+
děkovat
|
|
43
|
+
děkujeme
|
|
44
|
+
děkuji
|
|
45
|
+
den
|
|
46
|
+
deset
|
|
47
|
+
devatenáct
|
|
48
|
+
devět
|
|
49
|
+
do
|
|
50
|
+
dobrý
|
|
51
|
+
docela
|
|
52
|
+
dva
|
|
53
|
+
dvacet
|
|
54
|
+
dvanáct
|
|
55
|
+
dvě
|
|
56
|
+
hodně
|
|
57
|
+
já
|
|
58
|
+
jak
|
|
59
|
+
jde
|
|
60
|
+
je
|
|
61
|
+
jeden
|
|
62
|
+
jedenáct
|
|
63
|
+
jedna
|
|
64
|
+
jedno
|
|
65
|
+
jednou
|
|
66
|
+
jedou
|
|
67
|
+
jeho
|
|
68
|
+
její
|
|
69
|
+
jejich
|
|
70
|
+
jemu
|
|
71
|
+
jen
|
|
72
|
+
jenom
|
|
73
|
+
ještě
|
|
74
|
+
jestli
|
|
75
|
+
jestliže
|
|
76
|
+
jí
|
|
77
|
+
jich
|
|
78
|
+
jím
|
|
79
|
+
jimi
|
|
80
|
+
jinak
|
|
81
|
+
jsem
|
|
82
|
+
jsi
|
|
83
|
+
jsme
|
|
84
|
+
jsou
|
|
85
|
+
jste
|
|
86
|
+
kam
|
|
87
|
+
kde
|
|
88
|
+
kdo
|
|
89
|
+
kdy
|
|
90
|
+
když
|
|
91
|
+
ke
|
|
92
|
+
kolik
|
|
93
|
+
kromě
|
|
94
|
+
která
|
|
95
|
+
které
|
|
96
|
+
kteří
|
|
97
|
+
který
|
|
98
|
+
kvůli
|
|
99
|
+
má
|
|
100
|
+
mají
|
|
101
|
+
málo
|
|
102
|
+
mám
|
|
103
|
+
máme
|
|
104
|
+
máš
|
|
105
|
+
máte
|
|
106
|
+
mé
|
|
107
|
+
mě
|
|
108
|
+
mezi
|
|
109
|
+
mí
|
|
110
|
+
mít
|
|
111
|
+
mně
|
|
112
|
+
mnou
|
|
113
|
+
moc
|
|
114
|
+
mohl
|
|
115
|
+
mohou
|
|
116
|
+
moje
|
|
117
|
+
moji
|
|
118
|
+
možná
|
|
119
|
+
můj
|
|
120
|
+
musí
|
|
121
|
+
může
|
|
122
|
+
my
|
|
123
|
+
na
|
|
124
|
+
nad
|
|
125
|
+
nade
|
|
126
|
+
nám
|
|
127
|
+
námi
|
|
128
|
+
naproti
|
|
129
|
+
nás
|
|
130
|
+
náš
|
|
131
|
+
naše
|
|
132
|
+
naši
|
|
133
|
+
ne
|
|
134
|
+
ně
|
|
135
|
+
nebo
|
|
136
|
+
nebyl
|
|
137
|
+
nebyla
|
|
138
|
+
nebyli
|
|
139
|
+
nebyly
|
|
140
|
+
něco
|
|
141
|
+
nedělá
|
|
142
|
+
nedělají
|
|
143
|
+
nedělám
|
|
144
|
+
neděláme
|
|
145
|
+
neděláš
|
|
146
|
+
neděláte
|
|
147
|
+
nějak
|
|
148
|
+
nejsi
|
|
149
|
+
někde
|
|
150
|
+
někdo
|
|
151
|
+
nemají
|
|
152
|
+
nemáme
|
|
153
|
+
nemáte
|
|
154
|
+
neměl
|
|
155
|
+
němu
|
|
156
|
+
není
|
|
157
|
+
nestačí
|
|
158
|
+
nevadí
|
|
159
|
+
než
|
|
160
|
+
nic
|
|
161
|
+
nich
|
|
162
|
+
ním
|
|
163
|
+
nimi
|
|
164
|
+
nula
|
|
165
|
+
od
|
|
166
|
+
ode
|
|
167
|
+
on
|
|
168
|
+
ona
|
|
169
|
+
oni
|
|
170
|
+
ono
|
|
171
|
+
ony
|
|
172
|
+
osm
|
|
173
|
+
osmnáct
|
|
174
|
+
pak
|
|
175
|
+
patnáct
|
|
176
|
+
pět
|
|
177
|
+
po
|
|
178
|
+
pořád
|
|
179
|
+
potom
|
|
180
|
+
pozdě
|
|
181
|
+
před
|
|
182
|
+
přes
|
|
183
|
+
přese
|
|
184
|
+
pro
|
|
185
|
+
proč
|
|
186
|
+
prosím
|
|
187
|
+
prostě
|
|
188
|
+
proti
|
|
189
|
+
protože
|
|
190
|
+
rovně
|
|
191
|
+
se
|
|
192
|
+
sedm
|
|
193
|
+
sedmnáct
|
|
194
|
+
šest
|
|
195
|
+
šestnáct
|
|
196
|
+
skoro
|
|
197
|
+
smějí
|
|
198
|
+
smí
|
|
199
|
+
snad
|
|
200
|
+
spolu
|
|
201
|
+
sta
|
|
202
|
+
sté
|
|
203
|
+
sto
|
|
204
|
+
ta
|
|
205
|
+
tady
|
|
206
|
+
tak
|
|
207
|
+
takhle
|
|
208
|
+
taky
|
|
209
|
+
tam
|
|
210
|
+
tamhle
|
|
211
|
+
tamhleto
|
|
212
|
+
tamto
|
|
213
|
+
tě
|
|
214
|
+
tebe
|
|
215
|
+
tebou
|
|
216
|
+
ted'
|
|
217
|
+
tedy
|
|
218
|
+
ten
|
|
219
|
+
ti
|
|
220
|
+
tisíc
|
|
221
|
+
tisíce
|
|
222
|
+
to
|
|
223
|
+
tobě
|
|
224
|
+
tohle
|
|
225
|
+
toto
|
|
226
|
+
třeba
|
|
227
|
+
tři
|
|
228
|
+
třináct
|
|
229
|
+
trošku
|
|
230
|
+
tvá
|
|
231
|
+
tvé
|
|
232
|
+
tvoje
|
|
233
|
+
tvůj
|
|
234
|
+
ty
|
|
235
|
+
určitě
|
|
236
|
+
už
|
|
237
|
+
vám
|
|
238
|
+
vámi
|
|
239
|
+
vás
|
|
240
|
+
váš
|
|
241
|
+
vaše
|
|
242
|
+
vaši
|
|
243
|
+
ve
|
|
244
|
+
večer
|
|
245
|
+
vedle
|
|
246
|
+
vlastně
|
|
247
|
+
všechno
|
|
248
|
+
všichni
|
|
249
|
+
vůbec
|
|
250
|
+
vy
|
|
251
|
+
vždy
|
|
252
|
+
za
|
|
253
|
+
zač
|
|
254
|
+
zatímco
|
|
255
|
+
ze
|
|
256
|
+
že
|
|
@@ -0,0 +1,94 @@
|
|
|
1
|
+
og
|
|
2
|
+
i
|
|
3
|
+
jeg
|
|
4
|
+
det
|
|
5
|
+
at
|
|
6
|
+
en
|
|
7
|
+
den
|
|
8
|
+
til
|
|
9
|
+
er
|
|
10
|
+
som
|
|
11
|
+
på
|
|
12
|
+
de
|
|
13
|
+
med
|
|
14
|
+
han
|
|
15
|
+
af
|
|
16
|
+
for
|
|
17
|
+
ikke
|
|
18
|
+
der
|
|
19
|
+
var
|
|
20
|
+
mig
|
|
21
|
+
sig
|
|
22
|
+
men
|
|
23
|
+
et
|
|
24
|
+
har
|
|
25
|
+
om
|
|
26
|
+
vi
|
|
27
|
+
min
|
|
28
|
+
havde
|
|
29
|
+
ham
|
|
30
|
+
hun
|
|
31
|
+
nu
|
|
32
|
+
over
|
|
33
|
+
da
|
|
34
|
+
fra
|
|
35
|
+
du
|
|
36
|
+
ud
|
|
37
|
+
sin
|
|
38
|
+
dem
|
|
39
|
+
os
|
|
40
|
+
op
|
|
41
|
+
man
|
|
42
|
+
hans
|
|
43
|
+
hvor
|
|
44
|
+
eller
|
|
45
|
+
hvad
|
|
46
|
+
skal
|
|
47
|
+
selv
|
|
48
|
+
her
|
|
49
|
+
alle
|
|
50
|
+
vil
|
|
51
|
+
blev
|
|
52
|
+
kunne
|
|
53
|
+
ind
|
|
54
|
+
når
|
|
55
|
+
være
|
|
56
|
+
dog
|
|
57
|
+
noget
|
|
58
|
+
ville
|
|
59
|
+
jo
|
|
60
|
+
deres
|
|
61
|
+
efter
|
|
62
|
+
ned
|
|
63
|
+
skulle
|
|
64
|
+
denne
|
|
65
|
+
end
|
|
66
|
+
dette
|
|
67
|
+
mit
|
|
68
|
+
også
|
|
69
|
+
under
|
|
70
|
+
have
|
|
71
|
+
dig
|
|
72
|
+
anden
|
|
73
|
+
hende
|
|
74
|
+
mine
|
|
75
|
+
alt
|
|
76
|
+
meget
|
|
77
|
+
sit
|
|
78
|
+
sine
|
|
79
|
+
vor
|
|
80
|
+
mod
|
|
81
|
+
disse
|
|
82
|
+
hvis
|
|
83
|
+
din
|
|
84
|
+
nogle
|
|
85
|
+
hos
|
|
86
|
+
blive
|
|
87
|
+
mange
|
|
88
|
+
ad
|
|
89
|
+
bliver
|
|
90
|
+
hendes
|
|
91
|
+
været
|
|
92
|
+
thi
|
|
93
|
+
jer
|
|
94
|
+
sådan
|
|
@@ -0,0 +1,107 @@
|
|
|
1
|
+
de
|
|
2
|
+
en
|
|
3
|
+
van
|
|
4
|
+
ik
|
|
5
|
+
te
|
|
6
|
+
dat
|
|
7
|
+
die
|
|
8
|
+
in
|
|
9
|
+
een
|
|
10
|
+
hij
|
|
11
|
+
het
|
|
12
|
+
niet
|
|
13
|
+
zijn
|
|
14
|
+
is
|
|
15
|
+
was
|
|
16
|
+
op
|
|
17
|
+
aan
|
|
18
|
+
met
|
|
19
|
+
als
|
|
20
|
+
voor
|
|
21
|
+
had
|
|
22
|
+
er
|
|
23
|
+
maar
|
|
24
|
+
om
|
|
25
|
+
hem
|
|
26
|
+
dan
|
|
27
|
+
zou
|
|
28
|
+
of
|
|
29
|
+
wat
|
|
30
|
+
mijn
|
|
31
|
+
men
|
|
32
|
+
dit
|
|
33
|
+
zo
|
|
34
|
+
door
|
|
35
|
+
over
|
|
36
|
+
ze
|
|
37
|
+
zich
|
|
38
|
+
bij
|
|
39
|
+
ook
|
|
40
|
+
tot
|
|
41
|
+
je
|
|
42
|
+
mij
|
|
43
|
+
uit
|
|
44
|
+
der
|
|
45
|
+
daar
|
|
46
|
+
haar
|
|
47
|
+
naar
|
|
48
|
+
heb
|
|
49
|
+
hoe
|
|
50
|
+
heeft
|
|
51
|
+
hebben
|
|
52
|
+
deze
|
|
53
|
+
u
|
|
54
|
+
want
|
|
55
|
+
nog
|
|
56
|
+
zal
|
|
57
|
+
me
|
|
58
|
+
zij
|
|
59
|
+
nu
|
|
60
|
+
ge
|
|
61
|
+
geen
|
|
62
|
+
omdat
|
|
63
|
+
iets
|
|
64
|
+
worden
|
|
65
|
+
toch
|
|
66
|
+
al
|
|
67
|
+
waren
|
|
68
|
+
veel
|
|
69
|
+
meer
|
|
70
|
+
doen
|
|
71
|
+
toen
|
|
72
|
+
moet
|
|
73
|
+
ben
|
|
74
|
+
zonder
|
|
75
|
+
kan
|
|
76
|
+
hun
|
|
77
|
+
dus
|
|
78
|
+
alles
|
|
79
|
+
onder
|
|
80
|
+
ja
|
|
81
|
+
eens
|
|
82
|
+
hier
|
|
83
|
+
wie
|
|
84
|
+
werd
|
|
85
|
+
altijd
|
|
86
|
+
doch
|
|
87
|
+
wordt
|
|
88
|
+
wezen
|
|
89
|
+
kunnen
|
|
90
|
+
ons
|
|
91
|
+
zelf
|
|
92
|
+
tegen
|
|
93
|
+
na
|
|
94
|
+
reeds
|
|
95
|
+
wil
|
|
96
|
+
kon
|
|
97
|
+
niets
|
|
98
|
+
uw
|
|
99
|
+
iemand
|
|
100
|
+
geweest
|
|
101
|
+
andere
|
|
102
|
+
wij
|
|
103
|
+
we
|
|
104
|
+
z’n
|
|
105
|
+
z'n
|
|
106
|
+
zo’n
|
|
107
|
+
zo'n
|