summarize 1.0.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (62) hide show
  1. data/.gitignore +11 -0
  2. data/README.markdown +42 -0
  3. data/Rakefile +49 -0
  4. data/ext/summarize/article.c +119 -0
  5. data/ext/summarize/dic/bg.xml +101 -0
  6. data/ext/summarize/dic/ca.xml +141 -0
  7. data/ext/summarize/dic/cs.xml +161 -0
  8. data/ext/summarize/dic/cy.xml +118 -0
  9. data/ext/summarize/dic/da.xml +129 -0
  10. data/ext/summarize/dic/de.xml +354 -0
  11. data/ext/summarize/dic/el.xml +80 -0
  12. data/ext/summarize/dic/en.xml +606 -0
  13. data/ext/summarize/dic/eo.xml +171 -0
  14. data/ext/summarize/dic/es.xml +369 -0
  15. data/ext/summarize/dic/et.xml +172 -0
  16. data/ext/summarize/dic/eu.xml +77 -0
  17. data/ext/summarize/dic/fi.xml +105 -0
  18. data/ext/summarize/dic/fr.xml +199 -0
  19. data/ext/summarize/dic/ga.xml +124 -0
  20. data/ext/summarize/dic/gl.xml +290 -0
  21. data/ext/summarize/dic/he.xml +334 -0
  22. data/ext/summarize/dic/hu.xml +280 -0
  23. data/ext/summarize/dic/ia.xml +97 -0
  24. data/ext/summarize/dic/id.xml +75 -0
  25. data/ext/summarize/dic/is.xml +201 -0
  26. data/ext/summarize/dic/it.xml +206 -0
  27. data/ext/summarize/dic/lv.xml +77 -0
  28. data/ext/summarize/dic/mi.xml +76 -0
  29. data/ext/summarize/dic/ms.xml +160 -0
  30. data/ext/summarize/dic/mt.xml +73 -0
  31. data/ext/summarize/dic/nl.xml +245 -0
  32. data/ext/summarize/dic/nn.xml +264 -0
  33. data/ext/summarize/dic/pl.xml +92 -0
  34. data/ext/summarize/dic/pt.xml +365 -0
  35. data/ext/summarize/dic/ro.xml +163 -0
  36. data/ext/summarize/dic/ru.xml +150 -0
  37. data/ext/summarize/dic/sv.xml +255 -0
  38. data/ext/summarize/dic/tl.xml +67 -0
  39. data/ext/summarize/dic/tr.xml +65 -0
  40. data/ext/summarize/dic/uk.xml +98 -0
  41. data/ext/summarize/dic/yi.xml +293 -0
  42. data/ext/summarize/dictionary.c +331 -0
  43. data/ext/summarize/extconf.rb +6 -0
  44. data/ext/summarize/grader-tc.c +185 -0
  45. data/ext/summarize/grader-tc.h +64 -0
  46. data/ext/summarize/grader-tf.c +116 -0
  47. data/ext/summarize/grader.c +85 -0
  48. data/ext/summarize/highlighter.c +128 -0
  49. data/ext/summarize/html.c +131 -0
  50. data/ext/summarize/libots.h +158 -0
  51. data/ext/summarize/parser.c +173 -0
  52. data/ext/summarize/relations.c +163 -0
  53. data/ext/summarize/stemmer.c +332 -0
  54. data/ext/summarize/summarize.c +43 -0
  55. data/ext/summarize/summarize.h +12 -0
  56. data/ext/summarize/text.c +98 -0
  57. data/ext/summarize/wordlist.c +220 -0
  58. data/lib/summarize.rb +91 -0
  59. data/lib/summarize/summarize.bundle +0 -0
  60. data/sample_data/jupiter.txt +15 -0
  61. data/summarize.gemspec +21 -0
  62. metadata +140 -0
@@ -0,0 +1,280 @@
1
+ <?xml version="1.0"?>
2
+ <dictionary lang="hungarian">
3
+ <stemmer>
4
+ <step1_pre>
5
+ <rule>"|</rule>
6
+ <rule>(|</rule>
7
+ </step1_pre>
8
+
9
+
10
+ <step1_post>
11
+ <rule>."|</rule>
12
+ <rule>,"|</rule>
13
+ <rule>.|</rule>
14
+ <rule>,|</rule>
15
+ <rule>"|</rule>
16
+ <rule>)|</rule>
17
+ <rule>?|</rule>
18
+ <rule>:|</rule>
19
+ <rule>;|</rule>
20
+ <rule>!|</rule>
21
+ </step1_post>
22
+
23
+
24
+ <manual>
25
+ <rule>wrote|write</rule>
26
+ <rule>came|come</rule>
27
+ <rule>went|go</rule>
28
+ </manual>
29
+
30
+ <post>
31
+ <rule>before1|1after</rule>
32
+ </post>
33
+ <pre>
34
+ <rule>before1|1after</rule>
35
+ </pre>
36
+ </stemmer>
37
+ <parser>
38
+
39
+ <linebreak>
40
+ <rule>."</rule>
41
+ <rule>?"</rule>
42
+ <rule>!"</rule>
43
+ <rule>,"</rule>
44
+ <rule>.</rule>
45
+ <rule>?</rule>
46
+ <rule>;</rule>
47
+ <rule>|</rule>
48
+ <rule>!</rule>
49
+ </linebreak>
50
+
51
+ <linedontbreak>
52
+ <rule>Dr.</rule>
53
+ <rule>Mr.</rule>
54
+ <rule>Mrs.</rule>
55
+ <rule>U.S.</rule>
56
+ <rule>Rep.</rule>
57
+ <rule>Sen.</rule>
58
+ </linedontbreak>
59
+ </parser>
60
+ <grader-tc>
61
+ <word>a</word>
62
+ <word>addig</word>
63
+ <word>ám</word>
64
+ <word>annak</word>
65
+ <word>annyi</word>
66
+ <word>arra</word>
67
+ <word>át</word>
68
+ <word>attól</word>
69
+ <word>az</word>
70
+ <word>azért</word>
71
+ <word>azok</word>
72
+ <word>be</word>
73
+ <word>bele</word>
74
+ <word>belé</word>
75
+ <word>beléd</word>
76
+ <word>beléjük</word>
77
+ <word>belém</word>
78
+ <word>belénk</word>
79
+ <word>belétek</word>
80
+ <word>belőle</word>
81
+ <word>belőled</word>
82
+ <word>belőlem</word>
83
+ <word>belőletek</word>
84
+ <word>belőlük</word>
85
+ <word>belőlünk</word>
86
+ <word>benne</word>
87
+ <word>benned</word>
88
+ <word>bennem</word>
89
+ <word>bennetek</word>
90
+ <word>bennük</word>
91
+ <word>bennünk</word>
92
+ <word>csak</word>
93
+ <word>de</word>
94
+ <word>e</word>
95
+ <word>eddig</word>
96
+ <word>egy</word>
97
+ <word>egyik</word>
98
+ <word>el</word>
99
+ <word>én</word>
100
+ <word>engem</word>
101
+ <word>ennek</word>
102
+ <word>ennyi</word>
103
+ <word>erre</word>
104
+ <word>érte</word>
105
+ <word>érted</word>
106
+ <word>értem</word>
107
+ <word>értetek</word>
108
+ <word>értük</word>
109
+ <word>értünk</word>
110
+ <word>és</word>
111
+ <word>év</word>
112
+ <word>ez</word>
113
+ <word>ezek</word>
114
+ <word>ezért</word>
115
+ <word>ezt</word>
116
+ <word>fel</word>
117
+ <word>fog</word>
118
+ <word>föl</word>
119
+ <word>ha</word>
120
+ <word>hanem</word>
121
+ <word>három</word>
122
+ <word>hogy</word>
123
+ <word>hol</word>
124
+ <word>honnan</word>
125
+ <word>hozzá</word>
126
+ <word>hozzád</word>
127
+ <word>hozzájuk</word>
128
+ <word>hozzám</word>
129
+ <word>hozzánk</word>
130
+ <word>hozzátok</word>
131
+ <word>ide</word>
132
+ <word>igen</word>
133
+ <word>ilyen</word>
134
+ <word>is</word>
135
+ <word>ismét</word>
136
+ <word>itt</word>
137
+ <word>jó</word>
138
+ <word>kell</word>
139
+ <word>két</word>
140
+ <word>kettő</word>
141
+ <word>ki</word>
142
+ <word>kicsi</word>
143
+ <word>kicsit</word>
144
+ <word>kis</word>
145
+ <word>le</word>
146
+ <word>lehet</word>
147
+ <word>lesz</word>
148
+ <word>lett</word>
149
+ <word>ma</word>
150
+ <word>majdnem</word>
151
+ <word>már</word>
152
+ <word>más</word>
153
+ <word>másik</word>
154
+ <word>meddig</word>
155
+ <word>meg</word>
156
+ <word>még</word>
157
+ <word>megint</word>
158
+ <word>mellett</word>
159
+ <word>mennyi</word>
160
+ <word>merre</word>
161
+ <word>mert</word>
162
+ <word>mettől</word>
163
+ <word>mi</word>
164
+ <word>miért</word>
165
+ <word>mikor</word>
166
+ <word>milyen</word>
167
+ <word>minden</word>
168
+ <word>mindenki</word>
169
+ <word>mindig</word>
170
+ <word>minket</word>
171
+ <word>most</word>
172
+ <word>nagy</word>
173
+ <word>nagyon</word>
174
+ <word>nála</word>
175
+ <word>nálad</word>
176
+ <word>nálam</word>
177
+ <word>nálatok</word>
178
+ <word>náluk</word>
179
+ <word>nálunk</word>
180
+ <word>ne</word>
181
+ <word>négy</word>
182
+ <word>neked</word>
183
+ <word>nekem</word>
184
+ <word>neki</word>
185
+ <word>nekik</word>
186
+ <word>nektek</word>
187
+ <word>nekünk</word>
188
+ <word>nem</word>
189
+ <word>ő</word>
190
+ <word>oda</word>
191
+ <word>ők</word>
192
+ <word>őket</word>
193
+ <word>olyan</word>
194
+ <word>ön</word>
195
+ <word>önbe</word>
196
+ <word>önben</word>
197
+ <word>önbol</word>
198
+ <word>önért</word>
199
+ <word>önhöz</word>
200
+ <word>önnek</word>
201
+ <word>önnel</word>
202
+ <word>önnél</word>
203
+ <word>önök</word>
204
+ <word>önökbe</word>
205
+ <word>önökben</word>
206
+ <word>önökből</word>
207
+ <word>önökért</word>
208
+ <word>önöket</word>
209
+ <word>önökhöz</word>
210
+ <word>önökkel</word>
211
+ <word>önöknek</word>
212
+ <word>önöknél</word>
213
+ <word>önökön</word>
214
+ <word>önökre</word>
215
+ <word>önökről</word>
216
+ <word>önöktől</word>
217
+ <word>önön</word>
218
+ <word>önre</word>
219
+ <word>önről</word>
220
+ <word>önt</word>
221
+ <word>öntől</word>
222
+ <word>össze</word>
223
+ <word>őt</word>
224
+ <word>ott</word>
225
+ <word>rá</word>
226
+ <word>rád</word>
227
+ <word>rajta</word>
228
+ <word>rajtad</word>
229
+ <word>rajtam</word>
230
+ <word>rajtatok</word>
231
+ <word>rajtuk</word>
232
+ <word>rajtunk</word>
233
+ <word>rájuk</word>
234
+ <word>rám</word>
235
+ <word>ránk</word>
236
+ <word>rátok</word>
237
+ <word>róla</word>
238
+ <word>rólad</word>
239
+ <word>rólam</word>
240
+ <word>rólatok</word>
241
+ <word>róluk</word>
242
+ <word>rólunk</word>
243
+ <word>rossz</word>
244
+ <word>s</word>
245
+ <word>se</word>
246
+ <word>sem</word>
247
+ <word>semmi</word>
248
+ <word>senki</word>
249
+ <word>soha</word>
250
+ <word>sok</word>
251
+ <word>stb</word>
252
+ <word>szét</word>
253
+ <word>talán</word>
254
+ <word>te</word>
255
+ <word>téged</word>
256
+ <word>ti</word>
257
+ <word>titeket</word>
258
+ <word>tőle</word>
259
+ <word>tőled</word>
260
+ <word>tolem</word>
261
+ <word>toletek</word>
262
+ <word>tőlük</word>
263
+ <word>tőlünk</word>
264
+ <word>új</word>
265
+ <word>újra</word>
266
+ <word>vagy</word>
267
+ <word>van</word>
268
+ <word>vannak</word>
269
+ <word>vele</word>
270
+ <word>veled</word>
271
+ <word>velem</word>
272
+ <word>veletek</word>
273
+ <word>velük</word>
274
+ <word>velünk</word>
275
+ <word>vissza</word>
276
+ <word>volt</word>
277
+ <word>voltak</word>
278
+ <word></word>
279
+ </grader-tc>
280
+ </dictionary>
@@ -0,0 +1,97 @@
1
+ <?xml version="1.0"?>
2
+ <dictionary lang="Interlingua">
3
+ <stemmer>
4
+ <step1_pre>
5
+ <rule>"|</rule>
6
+ <rule>(|</rule>
7
+ </step1_pre>
8
+
9
+
10
+ <step1_post>
11
+ <rule>."|</rule>
12
+ <rule>,"|</rule>
13
+ <rule>.|</rule>
14
+ <rule>,|</rule>
15
+ <rule>"|</rule>
16
+ <rule>)|</rule>
17
+ <rule>?|</rule>
18
+ <rule>:|</rule>
19
+ <rule>;|</rule>
20
+ <rule>!|</rule>
21
+ </step1_post>
22
+
23
+
24
+ <manual>
25
+ <rule>wrote|write</rule>
26
+ <rule>came|come</rule>
27
+ <rule>went|go</rule>
28
+ </manual>
29
+
30
+ <post>
31
+ <rule>before1|1after</rule>
32
+ </post>
33
+ <pre>
34
+ <rule>before1|1after</rule>
35
+ </pre>
36
+ </stemmer>
37
+ <parser>
38
+
39
+ <linebreak>
40
+ <rule>."</rule>
41
+ <rule>?"</rule>
42
+ <rule>!"</rule>
43
+ <rule>,"</rule>
44
+ <rule>.</rule>
45
+ <rule>?</rule>
46
+ <rule>;</rule>
47
+ <rule>|</rule>
48
+ <rule>!</rule>
49
+ </linebreak>
50
+
51
+ <linedontbreak>
52
+ <rule>Dr.</rule>
53
+ <rule>Mr.</rule>
54
+ <rule>Mrs.</rule>
55
+ <rule>U.S.</rule>
56
+ <rule>Rep.</rule>
57
+ <rule>Sen.</rule>
58
+ </linedontbreak>
59
+ </parser>
60
+ <grader-tc>
61
+ <word>duo</word>
62
+ <word>e</word>
63
+ <word>es</word>
64
+ <word>esser</word>
65
+ <word>ha</word>
66
+ <word>haber</word>
67
+ <word>illa</word>
68
+ <word>illas</word>
69
+ <word>ille</word>
70
+ <word>illes</word>
71
+ <word>illo</word>
72
+ <word>illos</word>
73
+ <word>in</word>
74
+ <word>io</word>
75
+ <word>la</word>
76
+ <word>las</word>
77
+ <word>le</word>
78
+ <word>les</word>
79
+ <word>lo</word>
80
+ <word>los</word>
81
+ <word>me</word>
82
+ <word>minus</word>
83
+ <word>non</word>
84
+ <word>nos</word>
85
+ <word>ora</word>
86
+ <word>plus</word>
87
+ <word>quando</word>
88
+ <word>se</word>
89
+ <word>sed</word>
90
+ <word>te</word>
91
+ <word>tu</word>
92
+ <word>un</word>
93
+ <word>va</word>
94
+ <word>vader</word>
95
+ <word>vos</word>
96
+ </grader-tc>
97
+ </dictionary>
@@ -0,0 +1,75 @@
1
+ <?xml version="1.0"?>
2
+ <dictionary lang="Indonesian">
3
+ <stemmer>
4
+ <step1_pre>
5
+ <rule>"|</rule>
6
+ <rule>(|</rule>
7
+ </step1_pre>
8
+
9
+
10
+ <step1_post>
11
+ <rule>."|</rule>
12
+ <rule>,"|</rule>
13
+ <rule>.|</rule>
14
+ <rule>,|</rule>
15
+ <rule>"|</rule>
16
+ <rule>)|</rule>
17
+ <rule>?|</rule>
18
+ <rule>:|</rule>
19
+ <rule>;|</rule>
20
+ <rule>!|</rule>
21
+ </step1_post>
22
+
23
+
24
+ <manual>
25
+ <rule>wrote|write</rule>
26
+ <rule>came|come</rule>
27
+ <rule>went|go</rule>
28
+ </manual>
29
+
30
+ <post>
31
+ <rule>before1|1after</rule>
32
+ </post>
33
+ <pre>
34
+ <rule>before1|1after</rule>
35
+ </pre>
36
+ </stemmer>
37
+ <parser>
38
+
39
+ <linebreak>
40
+ <rule>."</rule>
41
+ <rule>?"</rule>
42
+ <rule>!"</rule>
43
+ <rule>,"</rule>
44
+ <rule>.</rule>
45
+ <rule>?</rule>
46
+ <rule>;</rule>
47
+ <rule>|</rule>
48
+ <rule>!</rule>
49
+ </linebreak>
50
+
51
+ <linedontbreak>
52
+ <rule>Dr.</rule>
53
+ <rule>Mr.</rule>
54
+ <rule>Mrs.</rule>
55
+ <rule>U.S.</rule>
56
+ <rule>Rep.</rule>
57
+ <rule>Sen.</rule>
58
+ </linedontbreak>
59
+ </parser>
60
+ <grader-tc>
61
+ <word>aku</word>
62
+ <word>anda</word>
63
+ <word>bapak</word>
64
+ <word>dia</word>
65
+ <word>engkau</word>
66
+ <word>ibu</word>
67
+ <word>kalian</word>
68
+ <word>kami</word>
69
+ <word>kamu</word>
70
+ <word>kita</word>
71
+ <word>mereka</word>
72
+ <word>saudara</word>
73
+ <word>saya</word>
74
+ </grader-tc>
75
+ </dictionary>