ots 0.4.3 → 0.4.4
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +80 -0
- data/dictionaries/bg.xml +101 -0
- data/dictionaries/ca.xml +141 -0
- data/dictionaries/cs.xml +161 -0
- data/dictionaries/cy.xml +118 -0
- data/dictionaries/da.xml +129 -0
- data/dictionaries/de.xml +354 -0
- data/dictionaries/el.xml +80 -0
- data/dictionaries/en.xml +606 -0
- data/dictionaries/eo.xml +171 -0
- data/dictionaries/es.xml +369 -0
- data/dictionaries/et.xml +172 -0
- data/dictionaries/eu.xml +77 -0
- data/dictionaries/fi.xml +105 -0
- data/dictionaries/fr.xml +199 -0
- data/dictionaries/ga.xml +124 -0
- data/dictionaries/gl.xml +290 -0
- data/dictionaries/he.xml +334 -0
- data/dictionaries/hu.xml +280 -0
- data/dictionaries/ia.xml +97 -0
- data/dictionaries/id.xml +75 -0
- data/dictionaries/is.xml +201 -0
- data/dictionaries/it.xml +206 -0
- data/dictionaries/lv.xml +77 -0
- data/dictionaries/mi.xml +76 -0
- data/dictionaries/ms.xml +160 -0
- data/dictionaries/mt.xml +73 -0
- data/dictionaries/nl.xml +245 -0
- data/dictionaries/nn.xml +264 -0
- data/dictionaries/pl.xml +92 -0
- data/dictionaries/pt.xml +365 -0
- data/dictionaries/ro.xml +163 -0
- data/dictionaries/ru.xml +150 -0
- data/dictionaries/sv.xml +255 -0
- data/dictionaries/tl.xml +67 -0
- data/dictionaries/tr.xml +65 -0
- data/dictionaries/uk.xml +98 -0
- data/dictionaries/yi.xml +293 -0
- data/ext/article.c +119 -0
- data/ext/dictionary.c +335 -0
- data/ext/extconf.rb +13 -14
- data/ext/grader-tc.c +185 -0
- data/ext/grader-tc.h +64 -0
- data/ext/grader-tf.c +116 -0
- data/ext/grader.c +85 -0
- data/ext/highlighter.c +128 -0
- data/ext/html.c +131 -0
- data/ext/libots.h +158 -0
- data/ext/ots.c +130 -151
- data/ext/ots.h +15 -0
- data/ext/parser.c +173 -0
- data/ext/relations.c +163 -0
- data/ext/stemmer.c +332 -0
- data/ext/text.c +98 -0
- data/ext/version.h +2 -0
- data/ext/wordlist.c +220 -0
- data/test/helper.rb +3 -0
- data/test/test_article.rb +52 -0
- data/test/test_ots.rb +23 -0
- metadata +122 -38
- data/README +0 -25
- data/VERSION +0 -1
- data/lib/ots.rb +0 -1
- data/test/ots_test.rb +0 -62
data/dictionaries/el.xml
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
1
|
+
<?xml version="1.0"?>
|
|
2
|
+
<dictionary lang="greek">
|
|
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>από</word>
|
|
62
|
+
<word>για</word>
|
|
63
|
+
<word>δεν</word>
|
|
64
|
+
<word>επειδή</word>
|
|
65
|
+
<word>η</word>
|
|
66
|
+
<word>ή</word>
|
|
67
|
+
<word>κάθε</word>
|
|
68
|
+
<word>καθένας</word>
|
|
69
|
+
<word>και</word>
|
|
70
|
+
<word>κανείς</word>
|
|
71
|
+
<word>κατά</word>
|
|
72
|
+
<word>με</word>
|
|
73
|
+
<word>να</word>
|
|
74
|
+
<word>πρέπει</word>
|
|
75
|
+
<word>σε</word>
|
|
76
|
+
<word>τα</word>
|
|
77
|
+
<word>το</word>
|
|
78
|
+
<word>ως</word>
|
|
79
|
+
</grader-tc>
|
|
80
|
+
</dictionary>
|
data/dictionaries/en.xml
ADDED
|
@@ -0,0 +1,606 @@
|
|
|
1
|
+
<?xml version="1.0"?>
|
|
2
|
+
<dictionary lang="English" maintainer="nadav256@hotmail.com">
|
|
3
|
+
<stemmer>
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
<step1_pre>
|
|
7
|
+
<rule>"|</rule>
|
|
8
|
+
<rule>(|</rule>
|
|
9
|
+
<rule>'|</rule>
|
|
10
|
+
<rule>[|</rule>
|
|
11
|
+
<rule>{|</rule>
|
|
12
|
+
</step1_pre>
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
<step1_post>
|
|
16
|
+
<rule>."|</rule>
|
|
17
|
+
<rule>,"|</rule>
|
|
18
|
+
<rule>,'|</rule>
|
|
19
|
+
<rule>.|</rule>
|
|
20
|
+
<rule>..|</rule>
|
|
21
|
+
<rule>...|</rule>
|
|
22
|
+
<rule>,|</rule>
|
|
23
|
+
<rule>"|</rule>
|
|
24
|
+
<rule>")|</rule>
|
|
25
|
+
<rule>"?|</rule>
|
|
26
|
+
<rule>)|</rule>
|
|
27
|
+
<rule>?|</rule>
|
|
28
|
+
<rule>:|</rule>
|
|
29
|
+
<rule>;|</rule>
|
|
30
|
+
<rule>!|</rule>
|
|
31
|
+
<rule>-|</rule>
|
|
32
|
+
<rule>--|</rule>
|
|
33
|
+
<rule>'s|</rule>
|
|
34
|
+
<rule>'d|</rule>
|
|
35
|
+
<rule>n't|</rule>
|
|
36
|
+
<rule>'t|</rule>
|
|
37
|
+
<rule>'ve|</rule>
|
|
38
|
+
<rule>'re|</rule>
|
|
39
|
+
<rule>'m|</rule>
|
|
40
|
+
<rule>]|</rule>
|
|
41
|
+
<rule>}|</rule>
|
|
42
|
+
</step1_post>
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
<manual>
|
|
46
|
+
<rule>wrote|write</rule>
|
|
47
|
+
<rule>came|come</rule>
|
|
48
|
+
<rule>went|go</rule>
|
|
49
|
+
<rule>choosing|choice</rule>
|
|
50
|
+
<rule>was|be</rule>
|
|
51
|
+
<rule>were|be</rule>
|
|
52
|
+
<rule>ate|eat</rule>
|
|
53
|
+
<rule>eaten|eat</rule>
|
|
54
|
+
<rule>beaten|beat</rule>
|
|
55
|
+
<rule>became|become</rule>
|
|
56
|
+
<rule>began|begin</rule>
|
|
57
|
+
<rule>beheld|behold</rule>
|
|
58
|
+
<rule>bent|bend</rule>
|
|
59
|
+
<rule>bound|bind</rule>
|
|
60
|
+
<rule>bleed|bled</rule>
|
|
61
|
+
<rule>blown|blow</rule>
|
|
62
|
+
<rule>blew|blow</rule>
|
|
63
|
+
<rule>broken|break</rule>
|
|
64
|
+
<rule>broke|break</rule>
|
|
65
|
+
<rule>brought|bring</rule>
|
|
66
|
+
<rule>built|build</rule>
|
|
67
|
+
<rule>bought|buy</rule>
|
|
68
|
+
<rule>caught|catch</rule>
|
|
69
|
+
<rule>dealt|deal</rule>
|
|
70
|
+
<rule>dug|dig</rule>
|
|
71
|
+
<rule>dove|dive</rule>
|
|
72
|
+
<rule>done|do</rule>
|
|
73
|
+
<rule>did|do</rule>
|
|
74
|
+
<rule>died|dead</rule>
|
|
75
|
+
<rule>drawn|draw</rule>
|
|
76
|
+
<rule>dreamt|dream</rule>
|
|
77
|
+
<rule>dreamed|dream</rule>
|
|
78
|
+
<rule>drunk|drink</rule>
|
|
79
|
+
<rule>drank|drink</rule>
|
|
80
|
+
<rule>dwelt|dwell</rule>
|
|
81
|
+
<rule>fell|fall</rule>
|
|
82
|
+
<rule>fallen|fall</rule>
|
|
83
|
+
<rule>fed|feed</rule>
|
|
84
|
+
<rule>felt|feel</rule>
|
|
85
|
+
<rule>flown|fly</rule>
|
|
86
|
+
<rule>flew|fly</rule>
|
|
87
|
+
<rule>forbidden|forbid</rule>
|
|
88
|
+
<rule>forgot|forget</rule>
|
|
89
|
+
<rule>forgotten|forget</rule>
|
|
90
|
+
<rule>forsaken|forsake</rule>
|
|
91
|
+
<rule>froze|freez</rule>
|
|
92
|
+
<rule>get|got</rule>
|
|
93
|
+
<rule>gave|give</rule>
|
|
94
|
+
<rule>gone|go</rule>
|
|
95
|
+
<rule>grew|grow</rule>
|
|
96
|
+
<rule>grown|grow</rule>
|
|
97
|
+
<rule>hidden|hide</rule>
|
|
98
|
+
<rule>hung|hang</rule>
|
|
99
|
+
<rule>held|hold</rule>
|
|
100
|
+
<rule>kept|keep</rule>
|
|
101
|
+
<rule>knew|know</rule>
|
|
102
|
+
<rule>known|know</rule>
|
|
103
|
+
<rule>laid|lay</rule>
|
|
104
|
+
<rule>lead|led</rule>
|
|
105
|
+
<rule>leave|left</rule>
|
|
106
|
+
<rule>lie|lay</rule>
|
|
107
|
+
<rule>lit|light</rule>
|
|
108
|
+
<rule>lose|lost</rule>
|
|
109
|
+
<rule>meet|met</rule>
|
|
110
|
+
<rule>made|make</rule>
|
|
111
|
+
<rule>misled|mislead</rule>
|
|
112
|
+
<rule>mistook|mistake</rule>
|
|
113
|
+
<rule>mistaken|mistake</rule>
|
|
114
|
+
<rule>overdid|overdo</rule>
|
|
115
|
+
<rule>overdone|overdo</rule>
|
|
116
|
+
<rule>paid|pay</rule>
|
|
117
|
+
<rule>rode|ride</rule>
|
|
118
|
+
<rule>rang|ring</rule>
|
|
119
|
+
<rule>rung|ring</rule>
|
|
120
|
+
<rule>rose|rise</rule>
|
|
121
|
+
<rule>ran|run</rule>
|
|
122
|
+
<rule>said|say</rule>
|
|
123
|
+
<rule>shot|shoot</rule>
|
|
124
|
+
<rule>sang|sing</rule>
|
|
125
|
+
<rule>sung|sing</rule>
|
|
126
|
+
<rule>sleep|slept</rule>
|
|
127
|
+
<rule>speak|spoke</rule>
|
|
128
|
+
<rule>spend|spent</rule>
|
|
129
|
+
<rule>stood|stand</rule>
|
|
130
|
+
<rule>stuck|stick</rule>
|
|
131
|
+
<rule>satrove|strive</rule>
|
|
132
|
+
<rule>strung|string</rule>
|
|
133
|
+
<rule>swept|sweep</rule>
|
|
134
|
+
<rule>swam|swim</rule>
|
|
135
|
+
<rule>took|take</rule>
|
|
136
|
+
<rule>taken|take</rule>
|
|
137
|
+
<rule>teach|taught</rule>
|
|
138
|
+
<rule>torn|tear</rule>
|
|
139
|
+
<rule>told|tell</rule>
|
|
140
|
+
<rule>thought|think</rule>
|
|
141
|
+
<rule>threw|throw</rule>
|
|
142
|
+
<rule>woke|wake</rule>
|
|
143
|
+
<rule>wept|weep</rule>
|
|
144
|
+
<rule>won|win</rule>
|
|
145
|
+
<rule>withdrawn|withdraw</rule>
|
|
146
|
+
<rule>withdrew|withdraw</rule>
|
|
147
|
+
<rule>wrote|write</rule>
|
|
148
|
+
<rule>written|write</rule>
|
|
149
|
+
</manual>
|
|
150
|
+
|
|
151
|
+
|
|
152
|
+
<pre>
|
|
153
|
+
<rule>1before1|2after2</rule>
|
|
154
|
+
</pre>
|
|
155
|
+
|
|
156
|
+
<post>
|
|
157
|
+
<rule>tions|t</rule>
|
|
158
|
+
<rule>sions|s</rule>
|
|
159
|
+
<rule>icians|</rule>
|
|
160
|
+
<rule>ician|</rule>
|
|
161
|
+
<rule>ics|</rule>
|
|
162
|
+
<rule>ical|</rule>
|
|
163
|
+
<rule>sses|ss</rule>
|
|
164
|
+
<rule>ss|ss</rule>
|
|
165
|
+
<rule>---een|</rule>
|
|
166
|
+
<rule>iest|y</rule>
|
|
167
|
+
<rule>ily|y</rule>
|
|
168
|
+
<rule>sure|s</rule>
|
|
169
|
+
<rule>ans|</rule>
|
|
170
|
+
<rule>ian|</rule>
|
|
171
|
+
<rule>ials|</rule>
|
|
172
|
+
<rule>ial|</rule>
|
|
173
|
+
<rule>able|</rule>
|
|
174
|
+
<rule>ibility|</rule>
|
|
175
|
+
<rule>ity|</rule>
|
|
176
|
+
<rule>ble|</rule>
|
|
177
|
+
<rule>ist|</rule>
|
|
178
|
+
<rule>ence|</rule>
|
|
179
|
+
<rule>ement|</rule>
|
|
180
|
+
<rule>ment|</rule>
|
|
181
|
+
<rule>ize|y</rule>
|
|
182
|
+
<rule>ies|y</rule>
|
|
183
|
+
<rule>eed|</rule>
|
|
184
|
+
<rule>iful|</rule>
|
|
185
|
+
<rule>nning|n</rule>
|
|
186
|
+
<rule>nnable|n</rule>
|
|
187
|
+
<rule>nner|n</rule>
|
|
188
|
+
<rule>nned|n</rule>
|
|
189
|
+
<rule>nnen|n</rule>
|
|
190
|
+
<rule>gger|g</rule>
|
|
191
|
+
<rule>gged|g</rule>
|
|
192
|
+
<rule>ggen|g</rule>
|
|
193
|
+
<rule>gging|g</rule>
|
|
194
|
+
<rule>ggable|g</rule>
|
|
195
|
+
<rule>pper|p</rule>
|
|
196
|
+
<rule>pped|p</rule>
|
|
197
|
+
<rule>ppen|p</rule>
|
|
198
|
+
<rule>pping|p</rule>
|
|
199
|
+
<rule>ppable|p</rule>
|
|
200
|
+
<rule>tting|t</rule>
|
|
201
|
+
<rule>ting|t</rule>
|
|
202
|
+
<rule>tten|t</rule>
|
|
203
|
+
<rule>ttable|t</rule>
|
|
204
|
+
<rule>tter|t</rule>
|
|
205
|
+
<rule>tted|t</rule>
|
|
206
|
+
<rule>ller|ll</rule>
|
|
207
|
+
<rule>lled|ll</rule>
|
|
208
|
+
<rule>llen|ll</rule>
|
|
209
|
+
<rule>lling|ll</rule>
|
|
210
|
+
<rule>llable|ll</rule>
|
|
211
|
+
<rule>sser|ss</rule>
|
|
212
|
+
<rule>ssed|ss</rule>
|
|
213
|
+
<rule>ssen|ss</rule>
|
|
214
|
+
<rule>ssing|ss</rule>
|
|
215
|
+
<rule>ssable|s</rule>
|
|
216
|
+
<rule>dding|dd</rule>
|
|
217
|
+
<rule>eing|e</rule>
|
|
218
|
+
<rule>ing|</rule>
|
|
219
|
+
<rule>mies|my</rule>
|
|
220
|
+
<rule>ly|</rule>
|
|
221
|
+
<rule>en|</rule>
|
|
222
|
+
<rule>bl|</rule>
|
|
223
|
+
<rule>izer|y</rule>
|
|
224
|
+
<rule>eli|</rule>
|
|
225
|
+
<rule>ousli|ous</rule>
|
|
226
|
+
<rule>ization|y</rule>
|
|
227
|
+
<rule>ation|</rule>
|
|
228
|
+
<rule>ator|</rule>
|
|
229
|
+
<rule>ers|</rule>
|
|
230
|
+
<rule>ies|</rule>
|
|
231
|
+
<rule>es|</rule>
|
|
232
|
+
<rule>ied|</rule>
|
|
233
|
+
<rule>ed|</rule>
|
|
234
|
+
<rule>cy|t</rule>
|
|
235
|
+
<rule>es|</rule>
|
|
236
|
+
<rule>is|is</rule>
|
|
237
|
+
<rule>s|</rule>
|
|
238
|
+
<rule>ee|ee</rule>
|
|
239
|
+
<rule>e|</rule>
|
|
240
|
+
</post>
|
|
241
|
+
|
|
242
|
+
|
|
243
|
+
<synonyms>
|
|
244
|
+
<rule>colour|color</rule>
|
|
245
|
+
<rule>honour|honor</rule>
|
|
246
|
+
<rule>murder|kill</rule>
|
|
247
|
+
<rule>assist|help</rule>
|
|
248
|
+
<rule>simple|basic</rule>
|
|
249
|
+
<rule>winsome|charming</rule>
|
|
250
|
+
<rule>incisive|perceptive</rule>
|
|
251
|
+
<rule>bay|bark</rule>
|
|
252
|
+
<rule>verbose|wordy</rule>
|
|
253
|
+
<rule>angry|mad</rule>
|
|
254
|
+
<rule>unhappy|sad</rule>
|
|
255
|
+
<rule>depressed|sad</rule>
|
|
256
|
+
<rule>dismal|sad</rule>
|
|
257
|
+
<rule>mournful|sad</rule>
|
|
258
|
+
<rule>dreadful|sad</rule>
|
|
259
|
+
<rule>dreary|sad</rule>
|
|
260
|
+
<rule>discouraged|sad</rule>
|
|
261
|
+
<rule>fled|run</rule>
|
|
262
|
+
<rule>fearful|afraid</rule>
|
|
263
|
+
<rule>terrified|afraid</rule>
|
|
264
|
+
<rule>hysterical|afraid</rule>
|
|
265
|
+
<rule>worried|afraid</rule>
|
|
266
|
+
<rule>scared|afraid</rule>
|
|
267
|
+
<rule>petrified|afraid</rule>
|
|
268
|
+
<rule>worse|bad</rule>
|
|
269
|
+
<rule>terrible|bad</rule>
|
|
270
|
+
<rule>horrible|bad</rule>
|
|
271
|
+
<rule>wicked|evil</rule>
|
|
272
|
+
<rule>huge|big</rule>
|
|
273
|
+
<rule>massive|bug</rule>
|
|
274
|
+
<rule>giant|big</rule>
|
|
275
|
+
<rule>gigantic|big</rule>
|
|
276
|
+
<rule>monstrous|big</rule>
|
|
277
|
+
<rule>tremendous|big</rule>
|
|
278
|
+
<rule>bulky|big</rule>
|
|
279
|
+
<rule>anxious|eager</rule>
|
|
280
|
+
<rule>intent|eager</rule>
|
|
281
|
+
<rule>ardent|eager</rule>
|
|
282
|
+
<rule>avid|eager</rule>
|
|
283
|
+
<rule>brave|bold</rule>
|
|
284
|
+
<rule>excellent|good</rule>
|
|
285
|
+
<rule>worthy|good</rule>
|
|
286
|
+
<rule>proper|good</rule>
|
|
287
|
+
<rule>favored|good</rule>
|
|
288
|
+
<rule>fine|good</rule>
|
|
289
|
+
<rule>brisk|happy</rule>
|
|
290
|
+
<rule>glad|happy</rule>
|
|
291
|
+
<rule>cheerful|happy</rule>
|
|
292
|
+
<rule>jolly|happy</rule>
|
|
293
|
+
<rule>pleased|happy</rule>
|
|
294
|
+
<rule>satisfied|happy</rule>
|
|
295
|
+
<rule>vivacious|happy</rule>
|
|
296
|
+
<rule>cheery|happy</rule>
|
|
297
|
+
<rule>merry|happy</rule>
|
|
298
|
+
<rule>injured|hurt</rule>
|
|
299
|
+
<rule>offended|hurt</rule>
|
|
300
|
+
<rule>distressed|hurt</rule>
|
|
301
|
+
<rule>suffering|hurt</rule>
|
|
302
|
+
<rule>afflicted|hurt</rule>
|
|
303
|
+
<rule>little|small</rule>
|
|
304
|
+
<rule>tiny|small</rule>
|
|
305
|
+
<rule>microscopic|small</rule>
|
|
306
|
+
<rule>miniscule|small</rule>
|
|
307
|
+
<rule>slender|small</rule>
|
|
308
|
+
<rule>insignificant|small</rule>
|
|
309
|
+
<rule>gaze|look</rule>
|
|
310
|
+
<rule>stare|look</rule>
|
|
311
|
+
<rule>view|look</rule>
|
|
312
|
+
<rule>inspect|look</rule>
|
|
313
|
+
<rule>glance|look</rule>
|
|
314
|
+
<rule>announce|say</rule>
|
|
315
|
+
</synonyms>
|
|
316
|
+
|
|
317
|
+
|
|
318
|
+
</stemmer>
|
|
319
|
+
|
|
320
|
+
<parser>
|
|
321
|
+
|
|
322
|
+
<linebreak>
|
|
323
|
+
<rule>."</rule>
|
|
324
|
+
<rule>?"</rule>
|
|
325
|
+
<rule>!"</rule>
|
|
326
|
+
<rule>.</rule>
|
|
327
|
+
<rule>?</rule>
|
|
328
|
+
<rule>;</rule>
|
|
329
|
+
<rule>|</rule>
|
|
330
|
+
<rule>!</rule>
|
|
331
|
+
</linebreak>
|
|
332
|
+
|
|
333
|
+
<linedontbreak>
|
|
334
|
+
<rule>Dr.</rule>
|
|
335
|
+
<rule>Mr.</rule>
|
|
336
|
+
<rule>Mrs.</rule>
|
|
337
|
+
<rule>U.S.</rule>
|
|
338
|
+
<rule>Rep.</rule>
|
|
339
|
+
<rule>Sen.</rule>
|
|
340
|
+
<rule>St.</rule>
|
|
341
|
+
<rule>Jan.</rule>
|
|
342
|
+
<rule>Feb.</rule>
|
|
343
|
+
<rule>Mar.</rule>
|
|
344
|
+
<rule>Apr.</rule>
|
|
345
|
+
<rule>May.</rule>
|
|
346
|
+
<rule>Jun.</rule>
|
|
347
|
+
<rule>Jul.</rule>
|
|
348
|
+
<rule>Aug.</rule>
|
|
349
|
+
<rule>Sep.</rule>
|
|
350
|
+
<rule>Oct.</rule>
|
|
351
|
+
<rule>Nov.</rule>
|
|
352
|
+
<rule>Dec.</rule>
|
|
353
|
+
<rule>Lt.</rule>
|
|
354
|
+
<rule>Gov.</rule>
|
|
355
|
+
<rule>a.m.</rule>
|
|
356
|
+
<rule>p.m.</rule>
|
|
357
|
+
</linedontbreak>
|
|
358
|
+
</parser>
|
|
359
|
+
|
|
360
|
+
<grader-syn>
|
|
361
|
+
<depreciate>
|
|
362
|
+
<rule>for example</rule>
|
|
363
|
+
<rule>such as</rule>
|
|
364
|
+
</depreciate>
|
|
365
|
+
</grader-syn>
|
|
366
|
+
|
|
367
|
+
|
|
368
|
+
<grader-tf>
|
|
369
|
+
<word idf="0.002">dog</word>
|
|
370
|
+
<word idf="0.0004">house</word>
|
|
371
|
+
</grader-tf>
|
|
372
|
+
|
|
373
|
+
|
|
374
|
+
<grader-tc>
|
|
375
|
+
<word>--</word>
|
|
376
|
+
<word>-</word>
|
|
377
|
+
<word>a</word>
|
|
378
|
+
<word>about</word>
|
|
379
|
+
<word>again</word>
|
|
380
|
+
<word>all</word>
|
|
381
|
+
<word>along</word>
|
|
382
|
+
<word>almost</word>
|
|
383
|
+
<word>also</word>
|
|
384
|
+
<word>always</word>
|
|
385
|
+
<word>am</word>
|
|
386
|
+
<word>among</word>
|
|
387
|
+
<word>an</word>
|
|
388
|
+
<word>and</word>
|
|
389
|
+
<word>another</word>
|
|
390
|
+
<word>any</word>
|
|
391
|
+
<word>anybody</word>
|
|
392
|
+
<word>anything</word>
|
|
393
|
+
<word>anywhere</word>
|
|
394
|
+
<word>apart</word>
|
|
395
|
+
<word>are</word>
|
|
396
|
+
<word>around</word>
|
|
397
|
+
<word>as</word>
|
|
398
|
+
<word>at</word>
|
|
399
|
+
<word>be</word>
|
|
400
|
+
<word>because</word>
|
|
401
|
+
<word>been</word>
|
|
402
|
+
<word>before</word>
|
|
403
|
+
<word>being</word>
|
|
404
|
+
<word>between</word>
|
|
405
|
+
<word>both</word>
|
|
406
|
+
<word>but</word>
|
|
407
|
+
<word>by</word>
|
|
408
|
+
<word>can</word>
|
|
409
|
+
<word>cannot</word>
|
|
410
|
+
<word>comes</word>
|
|
411
|
+
<word>could</word>
|
|
412
|
+
<word>couldn</word>
|
|
413
|
+
<word>did</word>
|
|
414
|
+
<word>didn</word>
|
|
415
|
+
<word>different</word>
|
|
416
|
+
<word>do</word>
|
|
417
|
+
<word>does</word>
|
|
418
|
+
<word>doesn</word>
|
|
419
|
+
<word>done</word>
|
|
420
|
+
<word>don</word>
|
|
421
|
+
<word>down</word>
|
|
422
|
+
<word>during</word>
|
|
423
|
+
<word>dr</word>
|
|
424
|
+
<word>each</word>
|
|
425
|
+
<word>either</word>
|
|
426
|
+
<word>enough</word>
|
|
427
|
+
<word>etc</word>
|
|
428
|
+
<word>even</word>
|
|
429
|
+
<word>every</word>
|
|
430
|
+
<word>everybody</word>
|
|
431
|
+
<word>everything</word>
|
|
432
|
+
<word>everywhere</word>
|
|
433
|
+
<word>except</word>
|
|
434
|
+
<word>exactly</word>
|
|
435
|
+
<word>few</word>
|
|
436
|
+
<word>final</word>
|
|
437
|
+
<word>first</word>
|
|
438
|
+
<word>for</word>
|
|
439
|
+
<word>from</word>
|
|
440
|
+
<word>get</word>
|
|
441
|
+
<word>go</word>
|
|
442
|
+
<word>goes</word>
|
|
443
|
+
<word>gone</word>
|
|
444
|
+
<word>good</word>
|
|
445
|
+
<word>got</word>
|
|
446
|
+
<word>had</word>
|
|
447
|
+
<word>has</word>
|
|
448
|
+
<word>have</word>
|
|
449
|
+
<word>having</word>
|
|
450
|
+
<word>he</word>
|
|
451
|
+
<word>hence</word>
|
|
452
|
+
<word>her</word>
|
|
453
|
+
<word>him</word>
|
|
454
|
+
<word>his</word>
|
|
455
|
+
<word>how</word>
|
|
456
|
+
<word>however</word>
|
|
457
|
+
<word>I</word>
|
|
458
|
+
<word>i.e</word>
|
|
459
|
+
<word>if</word>
|
|
460
|
+
<word>in</word>
|
|
461
|
+
<word>initial</word>
|
|
462
|
+
<word>into</word>
|
|
463
|
+
<word>is</word>
|
|
464
|
+
<word>isn</word>
|
|
465
|
+
<word>it</word>
|
|
466
|
+
<word>its</word>
|
|
467
|
+
<word>it</word>
|
|
468
|
+
<word>itself</word>
|
|
469
|
+
<word>just</word>
|
|
470
|
+
<word>last</word>
|
|
471
|
+
<word>least</word>
|
|
472
|
+
<word>less</word>
|
|
473
|
+
<word>let</word>
|
|
474
|
+
<word>lets</word>
|
|
475
|
+
<word>let's</word>
|
|
476
|
+
<word>like</word>
|
|
477
|
+
<word>lot</word>
|
|
478
|
+
<word>made</word>
|
|
479
|
+
<word>make</word>
|
|
480
|
+
<word>many</word>
|
|
481
|
+
<word>may</word>
|
|
482
|
+
<word>maybe</word>
|
|
483
|
+
<word>me</word>
|
|
484
|
+
<word>might</word>
|
|
485
|
+
<word>mine</word>
|
|
486
|
+
<word>more</word>
|
|
487
|
+
<word>most</word>
|
|
488
|
+
<word>Mr</word>
|
|
489
|
+
<word>much</word>
|
|
490
|
+
<word>must</word>
|
|
491
|
+
<word>my</word>
|
|
492
|
+
<word>near</word>
|
|
493
|
+
<word>need</word>
|
|
494
|
+
<word>next</word>
|
|
495
|
+
<word>niether</word>
|
|
496
|
+
<word>no</word>
|
|
497
|
+
<word>nobody</word>
|
|
498
|
+
<word>nor</word>
|
|
499
|
+
<word>not</word>
|
|
500
|
+
<word>nothing</word>
|
|
501
|
+
<word>now</word>
|
|
502
|
+
<word>nowhere</word>
|
|
503
|
+
<word>of</word>
|
|
504
|
+
<word>off</word>
|
|
505
|
+
<word>often</word>
|
|
506
|
+
<word>oh</word>
|
|
507
|
+
<word>ok</word>
|
|
508
|
+
<word>okay</word>
|
|
509
|
+
<word>on</word>
|
|
510
|
+
<word>once</word>
|
|
511
|
+
<word>one</word>
|
|
512
|
+
<word>only</word>
|
|
513
|
+
<word>onto</word>
|
|
514
|
+
<word>or</word>
|
|
515
|
+
<word>other</word>
|
|
516
|
+
<word>our</word>
|
|
517
|
+
<word>ours</word>
|
|
518
|
+
<word>out</word>
|
|
519
|
+
<word>over</word>
|
|
520
|
+
<word>own</word>
|
|
521
|
+
<word>perhaps</word>
|
|
522
|
+
<word>please</word>
|
|
523
|
+
<word>previous</word>
|
|
524
|
+
<word>quite</word>
|
|
525
|
+
<word>rather</word>
|
|
526
|
+
<word>re</word>
|
|
527
|
+
<word>really</word>
|
|
528
|
+
<word>s</word>
|
|
529
|
+
<word>said</word>
|
|
530
|
+
<word>same</word>
|
|
531
|
+
<word>say</word>
|
|
532
|
+
<word>see</word>
|
|
533
|
+
<word>seems</word>
|
|
534
|
+
<word>several</word>
|
|
535
|
+
<word>shall</word>
|
|
536
|
+
<word>she</word>
|
|
537
|
+
<word>should</word>
|
|
538
|
+
<word>shouldn't</word>
|
|
539
|
+
<word>since</word>
|
|
540
|
+
<word>so</word>
|
|
541
|
+
<word>some</word>
|
|
542
|
+
<word>somebody</word>
|
|
543
|
+
<word>something</word>
|
|
544
|
+
<word>somewhere</word>
|
|
545
|
+
<word>still</word>
|
|
546
|
+
<word>stuff</word>
|
|
547
|
+
<word>such</word>
|
|
548
|
+
<word>than</word>
|
|
549
|
+
<word>t</word>
|
|
550
|
+
<word>that</word>
|
|
551
|
+
<word>the</word>
|
|
552
|
+
<word>their</word>
|
|
553
|
+
<word>theirs</word>
|
|
554
|
+
<word>them</word>
|
|
555
|
+
<word>then</word>
|
|
556
|
+
<word>there</word>
|
|
557
|
+
<word>these</word>
|
|
558
|
+
<word>they</word>
|
|
559
|
+
<word>thing</word>
|
|
560
|
+
<word>things</word>
|
|
561
|
+
<word>this</word>
|
|
562
|
+
<word>those</word>
|
|
563
|
+
<word>through</word>
|
|
564
|
+
<word>thus</word>
|
|
565
|
+
<word>to</word>
|
|
566
|
+
<word>too</word>
|
|
567
|
+
<word>top</word>
|
|
568
|
+
<word>two</word>
|
|
569
|
+
<word>under</word>
|
|
570
|
+
<word>unless</word>
|
|
571
|
+
<word>until</word>
|
|
572
|
+
<word>up</word>
|
|
573
|
+
<word>upon</word>
|
|
574
|
+
<word>us</word>
|
|
575
|
+
<word>use</word>
|
|
576
|
+
<word>v</word>
|
|
577
|
+
<word>ve</word>
|
|
578
|
+
<word>very</word>
|
|
579
|
+
<word>want</word>
|
|
580
|
+
<word>was</word>
|
|
581
|
+
<word>we</word>
|
|
582
|
+
<word>well</word>
|
|
583
|
+
<word>went</word>
|
|
584
|
+
<word>were</word>
|
|
585
|
+
<word>what</word>
|
|
586
|
+
<word>when</word>
|
|
587
|
+
<word>where</word>
|
|
588
|
+
<word>which</word>
|
|
589
|
+
<word>while</word>
|
|
590
|
+
<word>who</word>
|
|
591
|
+
<word>whom</word>
|
|
592
|
+
<word>why</word>
|
|
593
|
+
<word>will</word>
|
|
594
|
+
<word>with</word>
|
|
595
|
+
<word>without</word>
|
|
596
|
+
<word>won</word>
|
|
597
|
+
<word>would</word>
|
|
598
|
+
<word>x</word>
|
|
599
|
+
<word>yes</word>
|
|
600
|
+
<word>yet</word>
|
|
601
|
+
<word>you</word>
|
|
602
|
+
<word>you</word>
|
|
603
|
+
<word>your</word>
|
|
604
|
+
<word>yours</word>
|
|
605
|
+
</grader-tc>
|
|
606
|
+
</dictionary>
|