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 +1,171 @@
1
+ <?xml version="1.0"?>
2
+ <dictionary lang="esperanto">
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>ajn</word>
62
+ <word>al</word>
63
+ <word>almenaŭ</word>
64
+ <word>ambaŭ</word>
65
+ <word>ankaŭ</word>
66
+ <word>ankoraŭ</word>
67
+ <word>anstataŭ</word>
68
+ <word>antaŭ</word>
69
+ <word>antaŭen</word>
70
+ <word>apud</word>
71
+ <word>aŭ</word>
72
+ <word>baldaŭ</word>
73
+ <word>ĉar</word>
74
+ <word>ĉe</word>
75
+ <word>ĉi</word>
76
+ <word>ĉio</word>
77
+ <word>ĉirkaŭ</word>
78
+ <word>ĉiuj</word>
79
+ <word>ĉu</word>
80
+ <word>da</word>
81
+ <word>dankon</word>
82
+ <word>de</word>
83
+ <word>do</word>
84
+ <word>du</word>
85
+ <word>dum</word>
86
+ <word>eĉ</word>
87
+ <word>el</word>
88
+ <word>en</word>
89
+ <word>esti</word>
90
+ <word>ĝi</word>
91
+ <word>ha</word>
92
+ <word>havi</word>
93
+ <word>hieraŭ</word>
94
+ <word>ili</word>
95
+ <word>inter</word>
96
+ <word>iri</word>
97
+ <word>jam</word>
98
+ <word>je</word>
99
+ <word>jen</word>
100
+ <word>jes</word>
101
+ <word>ĵus</word>
102
+ <word>kaj</word>
103
+ <word>ke</word>
104
+ <word>kelkaj</word>
105
+ <word>kia</word>
106
+ <word>kial</word>
107
+ <word>kiam</word>
108
+ <word>kie</word>
109
+ <word>kiel</word>
110
+ <word>kio</word>
111
+ <word>kioj</word>
112
+ <word>kiu</word>
113
+ <word>kiuj</word>
114
+ <word>kontraŭ</word>
115
+ <word>kun</word>
116
+ <word>la</word>
117
+ <word>li</word>
118
+ <word>malantaŭ</word>
119
+ <word>malantaŭen</word>
120
+ <word>malsupren</word>
121
+ <word>mi</word>
122
+ <word>morgaŭ</word>
123
+ <word>multaj</word>
124
+ <word>ne</word>
125
+ <word>ni</word>
126
+ <word>nu</word>
127
+ <word>nun</word>
128
+ <word>nur</word>
129
+ <word>ofte</word>
130
+ <word>per</word>
131
+ <word>plej</word>
132
+ <word>pli</word>
133
+ <word>plu</word>
134
+ <word>por</word>
135
+ <word>post</word>
136
+ <word>poste</word>
137
+ <word>povi</word>
138
+ <word>preni</word>
139
+ <word>preskaŭ</word>
140
+ <word>preter</word>
141
+ <word>pri</word>
142
+ <word>pro</word>
143
+ <word>propra</word>
144
+ <word>saluton</word>
145
+ <word>se</word>
146
+ <word>sed</word>
147
+ <word>sen</word>
148
+ <word>si</word>
149
+ <word>ŝi</word>
150
+ <word>sub</word>
151
+ <word>super</word>
152
+ <word>supre</word>
153
+ <word>supren</word>
154
+ <word>sur</word>
155
+ <word>tia</word>
156
+ <word>tial</word>
157
+ <word>tie</word>
158
+ <word>tiel</word>
159
+ <word>tio</word>
160
+ <word>tioj</word>
161
+ <word>tiu</word>
162
+ <word>tiuj</word>
163
+ <word>tra</word>
164
+ <word>tre</word>
165
+ <word>tuj</word>
166
+ <word>unu</word>
167
+ <word>uzi</word>
168
+ <word>vi</word>
169
+ <word>voli</word>
170
+ </grader-tc>
171
+ </dictionary>
@@ -0,0 +1,369 @@
1
+ <?xml version="1.0"?>
2
+ <dictionary lang="spanish">
3
+ <stemmer>
4
+
5
+
6
+ <step1_pre>
7
+ <rule>"|</rule>
8
+ <rule>(|</rule>
9
+ </step1_pre>
10
+
11
+
12
+ <step1_post>
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
+ <rule>;|</rule>
22
+ <rule>!|</rule>
23
+ </step1_post>
24
+
25
+
26
+ <manual>
27
+ <rule>wrote|write</rule>
28
+ <rule>came|come</rule>
29
+ <rule>went|go</rule>
30
+ </manual>
31
+
32
+
33
+ <post>
34
+ <rule>before1|1after</rule>
35
+ </post>
36
+ <pre>
37
+ <rule>before1|1after</rule>
38
+ </pre>
39
+
40
+
41
+ <manual>
42
+ <rule>wrote|write</rule>
43
+ </manual>
44
+
45
+ <synonyms>
46
+ <rule>assist|help</rule>
47
+ </synonyms>
48
+
49
+ </stemmer>
50
+ <parser>
51
+ <linebreak>
52
+ <rule>."</rule>
53
+ <rule>?"</rule>
54
+ <rule>!"</rule>
55
+ <rule>,"</rule>
56
+ <rule>.</rule>
57
+ <rule>?</rule>
58
+ <rule>;</rule>
59
+ <rule>|</rule>
60
+ <rule>!</rule>
61
+ </linebreak>
62
+
63
+ <linedontbreak>
64
+ <rule>Dr.</rule>
65
+ <rule>Mr.</rule>
66
+ <rule>Mrs.</rule>
67
+ <rule>U.S.</rule>
68
+ <rule>Rep.</rule>
69
+ <rule>Sen.</rule>
70
+ </linedontbreak>
71
+ </parser>
72
+ <grader-tc>
73
+ <word>a</word>
74
+ <word>acá</word>
75
+ <word>además</word>
76
+ <word>adiós</word>
77
+ <word>afuera</word>
78
+ <word>ahí</word>
79
+ <word>ahora</word>
80
+ <word>al</word>
81
+ <word>algo</word>
82
+ <word>alguien</word>
83
+ <word>algún</word>
84
+ <word>alguno</word>
85
+ <word>algunos</word>
86
+ <word>alguna</word>
87
+ <word>algunas</word>
88
+ <word>allá</word>
89
+ <word>allí</word>
90
+ <word>alrededor</word>
91
+ <word>ambos</word>
92
+ <word>antes</word>
93
+ <word>apenas</word>
94
+ <word>aquel</word>
95
+ <word>aquél</word>
96
+ <word>aquello</word>
97
+ <word>aquellos</word>
98
+ <word>aquella</word>
99
+ <word>aquellas</word>
100
+ <word>aquí</word>
101
+ <word>arriba</word>
102
+ <word>así</word>
103
+ <word>aun</word>
104
+ <word>aún</word>
105
+ <word>aunque</word>
106
+ <word>ayer</word>
107
+ <word>bajo</word>
108
+ <word>bajos</word>
109
+ <word>baja</word>
110
+ <word>bajas</word>
111
+ <word>bien</word>
112
+ <word>cada</word>
113
+ <word>casi</word>
114
+ <word>cerca</word>
115
+ <word>cero</word>
116
+ <word>como</word>
117
+ <word>cómo</word>
118
+ <word>con</word>
119
+ <word>conmigo</word>
120
+ <word>contigo</word>
121
+ <word>contra</word>
122
+ <word>cual</word>
123
+ <word>cuál</word>
124
+ <word>cuales</word>
125
+ <word>cualquier</word>
126
+ <word>cualquiera</word>
127
+ <word>cuando</word>
128
+ <word>cuándo</word>
129
+ <word>cuanta</word>
130
+ <word>cuantas</word>
131
+ <word>cuanto</word>
132
+ <word>cuantos</word>
133
+ <word>cuánta</word>
134
+ <word>cuántas</word>
135
+ <word>cuánto</word>
136
+ <word>cuántos</word>
137
+ <word>cuya</word>
138
+ <word>cuyas</word>
139
+ <word>cuyo</word>
140
+ <word>cuyos</word>
141
+ <word>de</word>
142
+ <word>deber</word>
143
+ <word>decena</word>
144
+ <word>del</word>
145
+ <word>delante</word>
146
+ <word>demás</word>
147
+ <word>demasiada</word>
148
+ <word>demasiadas</word>
149
+ <word>demasiado</word>
150
+ <word>demasiados</word>
151
+ <word>dentro</word>
152
+ <word>desde</word>
153
+ <word>después</word>
154
+ <word>detrás</word>
155
+ <word>docena</word>
156
+ <word>donde</word>
157
+ <word>dónde</word>
158
+ <word>dos</word>
159
+ <word>durante</word>
160
+ <word>e</word>
161
+ <word>el</word>
162
+ <word>él</word>
163
+ <word>ella</word>
164
+ <word>ellas</word>
165
+ <word>ello</word>
166
+ <word>ellos</word>
167
+ <word>en</word>
168
+ <word>encima</word>
169
+ <word>entonces</word>
170
+ <word>entre</word>
171
+ <word>era</word>
172
+ <word>erais</word>
173
+ <word>éramos</word>
174
+ <word>eran</word>
175
+ <word>eras</word>
176
+ <word>eres</word>
177
+ <word>es</word>
178
+ <word>esa</word>
179
+ <word>esas</word>
180
+ <word>ese</word>
181
+ <word>ése</word>
182
+ <word>eso</word>
183
+ <word>esos</word>
184
+ <word>esta</word>
185
+ <word>está</word>
186
+ <word>ésta</word>
187
+ <word>estado</word>
188
+ <word>están</word>
189
+ <word>estar</word>
190
+ <word>estas</word>
191
+ <word>estás</word>
192
+ <word>este</word>
193
+ <word>éste</word>
194
+ <word>estes</word>
195
+ <word>esto</word>
196
+ <word>estoy</word>
197
+ <word>estuve</word>
198
+ <word>estuvieron</word>
199
+ <word>estuvo</word>
200
+ <word>fue</word>
201
+ <word>fuera</word>
202
+ <word>fueron</word>
203
+ <word>fui</word>
204
+ <word>gusta</word>
205
+ <word>gustan</word>
206
+ <word>gustar</word>
207
+ <word>gustas</word>
208
+ <word>ha</word>
209
+ <word>haber</word>
210
+ <word>hacer</word>
211
+ <word>hacia</word>
212
+ <word>haga</word>
213
+ <word>hagamos</word>
214
+ <word>hagan</word>
215
+ <word>hagas</word>
216
+ <word>hago</word>
217
+ <word>han</word>
218
+ <word>has</word>
219
+ <word>hasta</word>
220
+ <word>hay</word>
221
+ <word>he</word>
222
+ <word>hecho</word>
223
+ <word>hemos</word>
224
+ <word>hizo</word>
225
+ <word>hoy</word>
226
+ <word>hube</word>
227
+ <word>hubiera</word>
228
+ <word>hubo</word>
229
+ <word>iba</word>
230
+ <word>ibais</word>
231
+ <word>ibamos</word>
232
+ <word>iban</word>
233
+ <word>ibas</word>
234
+ <word>incluso</word>
235
+ <word>ir</word>
236
+ <word>jamás</word>
237
+ <word>juntos</word>
238
+ <word>la</word>
239
+ <word>las</word>
240
+ <word>le</word>
241
+ <word>les</word>
242
+ <word>lo</word>
243
+ <word>los</word>
244
+ <word>luego</word>
245
+ <word>más</word>
246
+ <word>me</word>
247
+ <word>menos</word>
248
+ <word>mi</word>
249
+ <word>mí</word>
250
+ <word>mía</word>
251
+ <word>mientras</word>
252
+ <word>mío</word>
253
+ <word>muy</word>
254
+ <word>nada</word>
255
+ <word>nadie</word>
256
+ <word>ni</word>
257
+ <word>ningún</word>
258
+ <word>ninguna</word>
259
+ <word>ningunas</word>
260
+ <word>ninguno</word>
261
+ <word>ningunos</word>
262
+ <word>no</word>
263
+ <word>nos</word>
264
+ <word>nosotros</word>
265
+ <word>nuestra</word>
266
+ <word>nuestras</word>
267
+ <word>nuestro</word>
268
+ <word>nuestros</word>
269
+ <word>nunca</word>
270
+ <word>o</word>
271
+ <word>obstante</word>
272
+ <word>otra</word>
273
+ <word>otras</word>
274
+ <word>otro</word>
275
+ <word>otros</word>
276
+ <word>para</word>
277
+ <word>pero</word>
278
+ <word>poder</word>
279
+ <word>por</word>
280
+ <word>porque</word>
281
+ <word>primer</word>
282
+ <word>primera</word>
283
+ <word>primeras</word>
284
+ <word>primero</word>
285
+ <word>primeros</word>
286
+ <word>pronto</word>
287
+ <word>propia</word>
288
+ <word>propias</word>
289
+ <word>propio</word>
290
+ <word>propios</word>
291
+ <word>pude</word>
292
+ <word>pues</word>
293
+ <word>que</word>
294
+ <word>qué</word>
295
+ <word>quien</word>
296
+ <word>quién</word>
297
+ <word>quienes</word>
298
+ <word>quiénes</word>
299
+ <word>quizá</word>
300
+ <word>quizás</word>
301
+ <word>reciente</word>
302
+ <word>se</word>
303
+ <word>según</word>
304
+ <word>segunda</word>
305
+ <word>segundo</word>
306
+ <word>ser</word>
307
+ <word>si</word>
308
+ <word>sí</word>
309
+ <word>siempre</word>
310
+ <word>sino</word>
311
+ <word>siquiera</word>
312
+ <word>sobre</word>
313
+ <word>sois</word>
314
+ <word>somos</word>
315
+ <word>son</word>
316
+ <word>sos</word>
317
+ <word>soy</word>
318
+ <word>su</word>
319
+ <word>sus</word>
320
+ <word>suya</word>
321
+ <word>suyas</word>
322
+ <word>suyo</word>
323
+ <word>suyos</word>
324
+ <word>tal</word>
325
+ <word>también</word>
326
+ <word>tampoco</word>
327
+ <word>tan</word>
328
+ <word>tanta</word>
329
+ <word>tantas</word>
330
+ <word>tanto</word>
331
+ <word>tantos</word>
332
+ <word>te</word>
333
+ <word>ten</word>
334
+ <word>tener</word>
335
+ <word>ti</word>
336
+ <word>todavía</word>
337
+ <word>toda</word>
338
+ <word>todas</word>
339
+ <word>todo</word>
340
+ <word>todos</word>
341
+ <word>tras</word>
342
+ <word>través</word>
343
+ <word>tu</word>
344
+ <word>tú</word>
345
+ <word>tuve</word>
346
+ <word>tuvo</word>
347
+ <word>tuya</word>
348
+ <word>tuyas</word>
349
+ <word>tuyo</word>
350
+ <word>tuyos</word>
351
+ <word>u</word>
352
+ <word>un</word>
353
+ <word>una</word>
354
+ <word>unas</word>
355
+ <word>única</word>
356
+ <word>único</word>
357
+ <word>uno</word>
358
+ <word>unos</word>
359
+ <word>usted</word>
360
+ <word>ustedes</word>
361
+ <word>vais</word>
362
+ <word>vos</word>
363
+ <word>vosotros</word>
364
+ <word>voy</word>
365
+ <word>y</word>
366
+ <word>ya</word>
367
+ <word>yo</word>
368
+ </grader-tc>
369
+ </dictionary>