keyphrase 0.1.3 → 0.2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +5 -4
- data/lib/keyphrase/stoplist/afr.rb +14 -0
- data/lib/keyphrase/stoplist/aka.rb +10 -0
- data/lib/keyphrase/stoplist/amh.rb +10 -0
- data/lib/keyphrase/stoplist/ara.rb +490 -0
- data/lib/keyphrase/stoplist/aze.rb +175 -0
- data/lib/keyphrase/stoplist/bel.rb +11 -0
- data/lib/keyphrase/stoplist/ben.rb +408 -0
- data/lib/keyphrase/stoplist/bul.rb +528 -0
- data/lib/keyphrase/stoplist/cat.rb +711 -0
- data/lib/keyphrase/stoplist/ces.rb +560 -0
- data/lib/keyphrase/stoplist/cmn.rb +1119 -0
- data/lib/keyphrase/stoplist/dan.rb +25 -0
- data/lib/keyphrase/stoplist/deu.rb +631 -0
- data/lib/keyphrase/stoplist/ell.rb +275 -0
- data/lib/keyphrase/stoplist/eng.rb +2 -591
- data/lib/keyphrase/stoplist/epo.rb +183 -0
- data/lib/keyphrase/stoplist/est.rb +13 -0
- data/lib/keyphrase/stoplist/fin.rb +857 -0
- data/lib/keyphrase/stoplist/fra.rb +699 -0
- data/lib/keyphrase/stoplist/guj.rb +234 -0
- data/lib/keyphrase/stoplist/heb.rb +204 -0
- data/lib/keyphrase/stoplist/hin.rb +235 -0
- data/lib/keyphrase/stoplist/hrv.rb +25 -0
- data/lib/keyphrase/stoplist/hun.rb +1195 -0
- data/lib/keyphrase/stoplist/hye.rb +55 -0
- data/lib/keyphrase/stoplist/ind.rb +768 -0
- data/lib/keyphrase/stoplist/ita.rb +670 -0
- data/lib/keyphrase/stoplist/jav.rb +10 -0
- data/lib/keyphrase/stoplist/jpn.rb +144 -0
- data/lib/keyphrase/stoplist/kan.rb +92 -0
- data/lib/keyphrase/stoplist/kat.rb +383 -0
- data/lib/keyphrase/stoplist/khm.rb +245 -0
- data/lib/keyphrase/stoplist/kor.rb +610 -0
- data/lib/keyphrase/stoplist/lat.rb +14 -0
- data/lib/keyphrase/stoplist/lav.rb +171 -0
- data/lib/keyphrase/stoplist/lit.rb +484 -0
- data/lib/keyphrase/stoplist/mal.rb +11 -0
- data/lib/keyphrase/stoplist/mar.rb +109 -0
- data/lib/keyphrase/stoplist/mkd.rb +11 -0
- data/lib/keyphrase/stoplist/mya.rb +285 -0
- data/lib/keyphrase/stoplist/nep.rb +265 -0
- data/lib/keyphrase/stoplist/nld.rb +423 -0
- data/lib/keyphrase/stoplist/nob.rb +186 -0
- data/lib/keyphrase/stoplist/ori.rb +11 -0
- data/lib/keyphrase/stoplist/pan.rb +462 -0
- data/lib/keyphrase/stoplist/pes.rb +801 -0
- data/lib/keyphrase/stoplist/pol.rb +338 -0
- data/lib/keyphrase/stoplist/por.rb +570 -0
- data/lib/keyphrase/stoplist/ron.rb +444 -0
- data/lib/keyphrase/stoplist/rus.rb +569 -0
- data/lib/keyphrase/stoplist/sin.rb +10 -0
- data/lib/keyphrase/stoplist/slk.rb +428 -0
- data/lib/keyphrase/stoplist/slv.rb +456 -0
- data/lib/keyphrase/stoplist/sna.rb +11 -0
- data/lib/keyphrase/stoplist/spa.rb +731 -0
- data/lib/keyphrase/stoplist/srp.rb +11 -0
- data/lib/keyphrase/stoplist/swe.rb +428 -0
- data/lib/keyphrase/stoplist/tam.rb +135 -0
- data/lib/keyphrase/stoplist/tel.rb +10 -0
- data/lib/keyphrase/stoplist/tgl.rb +157 -0
- data/lib/keyphrase/stoplist/tha.rb +125 -0
- data/lib/keyphrase/stoplist/tuk.rb +11 -0
- data/lib/keyphrase/stoplist/tur.rb +514 -0
- data/lib/keyphrase/stoplist/ukr.rb +38 -0
- data/lib/keyphrase/stoplist/urd.rb +527 -0
- data/lib/keyphrase/stoplist/uzb.rb +10 -0
- data/lib/keyphrase/stoplist/vie.rb +655 -0
- data/lib/keyphrase/stoplist/yid.rb +204 -0
- data/lib/keyphrase/stoplist/zul.rb +39 -0
- data/lib/keyphrase/stoplist.rb +13 -10
- data/lib/keyphrase/version.rb +1 -1
- data/lib/keyphrase.rb +20 -12
- metadata +71 -3
@@ -0,0 +1,275 @@
|
|
1
|
+
class Keyphrase
|
2
|
+
module Stoplist
|
3
|
+
class Ell
|
4
|
+
def self.stopwords
|
5
|
+
@@stopwords ||= [
|
6
|
+
"αλλα",
|
7
|
+
"αν",
|
8
|
+
"αντι",
|
9
|
+
"απο",
|
10
|
+
"αυτα",
|
11
|
+
"αυτεσ",
|
12
|
+
"αυτη",
|
13
|
+
"αυτο",
|
14
|
+
"αυτοι",
|
15
|
+
"αυτοσ",
|
16
|
+
"αυτουσ",
|
17
|
+
"αυτων",
|
18
|
+
"αἱ",
|
19
|
+
"αἳ",
|
20
|
+
"αἵ",
|
21
|
+
"αὐτόσ",
|
22
|
+
"αὐτὸς",
|
23
|
+
"αὖ",
|
24
|
+
"γάρ",
|
25
|
+
"γα",
|
26
|
+
"γα^",
|
27
|
+
"γε",
|
28
|
+
"για",
|
29
|
+
"γοῦν",
|
30
|
+
"γὰρ",
|
31
|
+
"δ'",
|
32
|
+
"δέ",
|
33
|
+
"δή",
|
34
|
+
"δαί",
|
35
|
+
"δαίσ",
|
36
|
+
"δαὶ",
|
37
|
+
"δαὶς",
|
38
|
+
"δε",
|
39
|
+
"δεν",
|
40
|
+
"δι'",
|
41
|
+
"διά",
|
42
|
+
"διὰ",
|
43
|
+
"δὲ",
|
44
|
+
"δὴ",
|
45
|
+
"δ’",
|
46
|
+
"εαν",
|
47
|
+
"ειμαι",
|
48
|
+
"ειμαστε",
|
49
|
+
"ειναι",
|
50
|
+
"εισαι",
|
51
|
+
"ειστε",
|
52
|
+
"εκεινα",
|
53
|
+
"εκεινεσ",
|
54
|
+
"εκεινη",
|
55
|
+
"εκεινο",
|
56
|
+
"εκεινοι",
|
57
|
+
"εκεινοσ",
|
58
|
+
"εκεινουσ",
|
59
|
+
"εκεινων",
|
60
|
+
"ενω",
|
61
|
+
"επ",
|
62
|
+
"επι",
|
63
|
+
"εἰ",
|
64
|
+
"εἰμί",
|
65
|
+
"εἰμὶ",
|
66
|
+
"εἰς",
|
67
|
+
"εἰσ",
|
68
|
+
"εἴ",
|
69
|
+
"εἴμι",
|
70
|
+
"εἴτε",
|
71
|
+
"η",
|
72
|
+
"θα",
|
73
|
+
"ισωσ",
|
74
|
+
"κ",
|
75
|
+
"καί",
|
76
|
+
"καίτοι",
|
77
|
+
"καθ",
|
78
|
+
"και",
|
79
|
+
"κατ",
|
80
|
+
"κατά",
|
81
|
+
"κατα",
|
82
|
+
"κατὰ",
|
83
|
+
"καὶ",
|
84
|
+
"κι",
|
85
|
+
"κἀν",
|
86
|
+
"κἂν",
|
87
|
+
"μέν",
|
88
|
+
"μή",
|
89
|
+
"μήτε",
|
90
|
+
"μα",
|
91
|
+
"με",
|
92
|
+
"μεθ",
|
93
|
+
"μετ",
|
94
|
+
"μετά",
|
95
|
+
"μετα",
|
96
|
+
"μετὰ",
|
97
|
+
"μη",
|
98
|
+
"μην",
|
99
|
+
"μἐν",
|
100
|
+
"μὲν",
|
101
|
+
"μὴ",
|
102
|
+
"μὴν",
|
103
|
+
"να",
|
104
|
+
"ο",
|
105
|
+
"οι",
|
106
|
+
"ομωσ",
|
107
|
+
"οπωσ",
|
108
|
+
"οσο",
|
109
|
+
"οτι",
|
110
|
+
"οἱ",
|
111
|
+
"οἳ",
|
112
|
+
"οἷς",
|
113
|
+
"οὐ",
|
114
|
+
"οὐδ",
|
115
|
+
"οὐδέ",
|
116
|
+
"οὐδείσ",
|
117
|
+
"οὐδεὶς",
|
118
|
+
"οὐδὲ",
|
119
|
+
"οὐδὲν",
|
120
|
+
"οὐκ",
|
121
|
+
"οὐχ",
|
122
|
+
"οὐχὶ",
|
123
|
+
"οὓς",
|
124
|
+
"οὔτε",
|
125
|
+
"οὕτω",
|
126
|
+
"οὕτως",
|
127
|
+
"οὕτωσ",
|
128
|
+
"οὖν",
|
129
|
+
"οὗ",
|
130
|
+
"οὗτος",
|
131
|
+
"οὗτοσ",
|
132
|
+
"παρ",
|
133
|
+
"παρά",
|
134
|
+
"παρα",
|
135
|
+
"παρὰ",
|
136
|
+
"περί",
|
137
|
+
"περὶ",
|
138
|
+
"ποια",
|
139
|
+
"ποιεσ",
|
140
|
+
"ποιο",
|
141
|
+
"ποιοι",
|
142
|
+
"ποιοσ",
|
143
|
+
"ποιουσ",
|
144
|
+
"ποιων",
|
145
|
+
"ποτε",
|
146
|
+
"που",
|
147
|
+
"ποῦ",
|
148
|
+
"προ",
|
149
|
+
"προσ",
|
150
|
+
"πρόσ",
|
151
|
+
"πρὸ",
|
152
|
+
"πρὸς",
|
153
|
+
"πως",
|
154
|
+
"πωσ",
|
155
|
+
"σε",
|
156
|
+
"στη",
|
157
|
+
"στην",
|
158
|
+
"στο",
|
159
|
+
"στον",
|
160
|
+
"σόσ",
|
161
|
+
"σύ",
|
162
|
+
"σύν",
|
163
|
+
"σὸς",
|
164
|
+
"σὺ",
|
165
|
+
"σὺν",
|
166
|
+
"τά",
|
167
|
+
"τήν",
|
168
|
+
"τί",
|
169
|
+
"τίς",
|
170
|
+
"τίσ",
|
171
|
+
"τα",
|
172
|
+
"ταῖς",
|
173
|
+
"τε",
|
174
|
+
"την",
|
175
|
+
"τησ",
|
176
|
+
"τι",
|
177
|
+
"τινα",
|
178
|
+
"τις",
|
179
|
+
"τισ",
|
180
|
+
"το",
|
181
|
+
"τοί",
|
182
|
+
"τοι",
|
183
|
+
"τοιοῦτος",
|
184
|
+
"τοιοῦτοσ",
|
185
|
+
"τον",
|
186
|
+
"τοτε",
|
187
|
+
"του",
|
188
|
+
"τούσ",
|
189
|
+
"τοὺς",
|
190
|
+
"τοῖς",
|
191
|
+
"τοῦ",
|
192
|
+
"των",
|
193
|
+
"τό",
|
194
|
+
"τόν",
|
195
|
+
"τότε",
|
196
|
+
"τὰ",
|
197
|
+
"τὰς",
|
198
|
+
"τὴν",
|
199
|
+
"τὸ",
|
200
|
+
"τὸν",
|
201
|
+
"τῆς",
|
202
|
+
"τῆσ",
|
203
|
+
"τῇ",
|
204
|
+
"τῶν",
|
205
|
+
"τῷ",
|
206
|
+
"ωσ",
|
207
|
+
"ἀλλ'",
|
208
|
+
"ἀλλά",
|
209
|
+
"ἀλλὰ",
|
210
|
+
"ἀλλ’",
|
211
|
+
"ἀπ",
|
212
|
+
"ἀπό",
|
213
|
+
"ἀπὸ",
|
214
|
+
"ἀφ",
|
215
|
+
"ἂν",
|
216
|
+
"ἃ",
|
217
|
+
"ἄλλος",
|
218
|
+
"ἄλλοσ",
|
219
|
+
"ἄν",
|
220
|
+
"ἄρα",
|
221
|
+
"ἅμα",
|
222
|
+
"ἐάν",
|
223
|
+
"ἐγώ",
|
224
|
+
"ἐγὼ",
|
225
|
+
"ἐκ",
|
226
|
+
"ἐμόσ",
|
227
|
+
"ἐμὸς",
|
228
|
+
"ἐν",
|
229
|
+
"ἐξ",
|
230
|
+
"ἐπί",
|
231
|
+
"ἐπεὶ",
|
232
|
+
"ἐπὶ",
|
233
|
+
"ἐστι",
|
234
|
+
"ἐφ",
|
235
|
+
"ἐὰν",
|
236
|
+
"ἑαυτοῦ",
|
237
|
+
"ἔτι",
|
238
|
+
"ἡ",
|
239
|
+
"ἢ",
|
240
|
+
"ἣ",
|
241
|
+
"ἤ",
|
242
|
+
"ἥ",
|
243
|
+
"ἧς",
|
244
|
+
"ἵνα",
|
245
|
+
"ὁ",
|
246
|
+
"ὃ",
|
247
|
+
"ὃν",
|
248
|
+
"ὃς",
|
249
|
+
"ὅ",
|
250
|
+
"ὅδε",
|
251
|
+
"ὅθεν",
|
252
|
+
"ὅπερ",
|
253
|
+
"ὅς",
|
254
|
+
"ὅσ",
|
255
|
+
"ὅστις",
|
256
|
+
"ὅστισ",
|
257
|
+
"ὅτε",
|
258
|
+
"ὅτι",
|
259
|
+
"ὑμόσ",
|
260
|
+
"ὑπ",
|
261
|
+
"ὑπέρ",
|
262
|
+
"ὑπό",
|
263
|
+
"ὑπὲρ",
|
264
|
+
"ὑπὸ",
|
265
|
+
"ὡς",
|
266
|
+
"ὡσ",
|
267
|
+
"ὥς",
|
268
|
+
"ὥστε",
|
269
|
+
"ὦ",
|
270
|
+
"ᾧ",
|
271
|
+
]
|
272
|
+
end
|
273
|
+
end
|
274
|
+
end
|
275
|
+
end
|