mmax.py
11.6 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
import os
import shutil
from lxml import etree
from conf import CONTEXT, FREQ_LIST
from corneferencer.entities import Mention, Text
def read(inpath):
textname = os.path.splitext(os.path.basename(inpath))[0]
textdir = os.path.dirname(inpath)
mentions_path = os.path.join(textdir, '%s_mentions.xml' % textname)
words_path = os.path.join(textdir, '%s_words.xml' % textname)
text = Text(textname)
mentions = read_mentions(mentions_path, words_path)
text.mentions = mentions
return text
def read_mentions(mentions_path, words_path):
mentions = []
mentions_tree = etree.parse(mentions_path)
markables = mentions_tree.xpath("//ns:markable",
namespaces={'ns': 'www.eml.org/NameSpaces/mention'})
words = get_words(words_path)
for idx, markable in enumerate(markables):
span = markable.attrib['span']
dominant = ''
if 'dominant' in markable.attrib:
dominant = markable.attrib['dominant']
head_orth = markable.attrib['mention_head']
mention_words = span_to_words(span, words)
(prec_context, follow_context, sentence,
mnt_start_position, mnt_end_position,
paragraph_id, sentence_id,
first_in_sentence, first_in_paragraph) = get_context(mention_words, words)
head = get_head(head_orth, mention_words)
mention = Mention(mnt_id=markable.attrib['id'],
text=span_to_text(span, words, 'orth'),
lemmatized_text=span_to_text(span, words, 'base'),
words=mention_words,
span=span,
head_orth=head_orth,
head=head,
dominant=dominant,
node=markable,
prec_context=prec_context,
follow_context=follow_context,
sentence=sentence,
position_in_mentions=idx,
start_in_words=mnt_start_position,
end_in_words=mnt_end_position,
rarest=get_rarest_word(mention_words),
paragraph_id=paragraph_id,
sentence_id=sentence_id,
first_in_sentence=first_in_sentence,
first_in_paragraph=first_in_paragraph)
mentions.append(mention)
return mentions
def get_words(filepath):
tree = etree.parse(filepath)
words = []
for word in tree.xpath("//word"):
hasnps = False
if 'hasnps' in word.attrib and word.attrib['hasnps'] == 'true':
hasnps = True
lastinsent = False
if 'lastinsent' in word.attrib and word.attrib['lastinsent'] == 'true':
lastinsent = True
lastinpar = False
if 'lastinpar' in word.attrib and word.attrib['lastinpar'] == 'true':
lastinpar = True
words.append({'id': word.attrib['id'],
'orth': word.text,
'base': word.attrib['base'],
'hasnps': hasnps,
'lastinsent': lastinsent,
'lastinpar': lastinpar,
'ctag': word.attrib['ctag'],
'msd': word.attrib['msd'],
'gender': get_gender(word.attrib['msd']),
'person': get_person(word.attrib['msd']),
'number': get_number(word.attrib['msd'])})
return words
def span_to_words(span, words):
fragments = span.split(',')
mention_parts = []
for fragment in fragments:
mention_parts.extend(fragment_to_words(fragment, words))
return mention_parts
def fragment_to_words(fragment, words):
mention_parts = []
if '..' in fragment:
mention_parts.extend(get_multiword(fragment, words))
else:
mention_parts.extend(get_word(fragment, words))
return mention_parts
def get_multiword(fragment, words):
mention_parts = []
boundaries = fragment.split('..')
start_id = boundaries[0]
end_id = boundaries[1]
in_string = False
for word in words:
if word['id'] == start_id:
in_string = True
if in_string and not word_to_ignore(word):
mention_parts.append(word)
if word['id'] == end_id:
break
return mention_parts
def get_word(word_id, words):
for word in words:
if word['id'] == word_id:
if not word_to_ignore(word):
return [word]
else:
return []
return []
def word_to_ignore(word):
if word['ctag'] == 'interp':
return True
return False
def get_context(mention_words, words):
paragraph_id = 0
sentence_id = 0
prec_context = []
follow_context = []
sentence = []
mnt_start_position = -1
mnt_end_position = -1
first_word = mention_words[0]
last_word = mention_words[-1]
first_in_sentence = False
first_in_paragraph = False
for idx, word in enumerate(words):
if word['id'] == first_word['id']:
prec_context = get_prec_context(idx, words)
mnt_start_position = get_mention_start(first_word, words)
if idx == 0 or words[idx-1]['lastinsent']:
first_in_sentence = True
if idx == 0 or words[idx-1]['lastinpar']:
first_in_paragraph = True
if word['id'] == last_word['id']:
follow_context = get_follow_context(idx, words)
sentence = get_sentence(idx, words)
mnt_end_position = get_mention_end(last_word, words)
break
if word['lastinsent']:
sentence_id += 1
if word['lastinpar']:
paragraph_id += 1
return (prec_context, follow_context, sentence, mnt_start_position, mnt_end_position,
paragraph_id, sentence_id, first_in_sentence, first_in_paragraph)
def get_prec_context(mention_start, words):
context = []
context_start = mention_start - 1
while context_start >= 0:
if not word_to_ignore(words[context_start]):
context.append(words[context_start])
if len(context) == CONTEXT:
break
context_start -= 1
context.reverse()
return context
def get_mention_start(first_word, words):
start = 0
for word in words:
if not word_to_ignore(word):
start += 1
if word['id'] == first_word['id']:
break
return start
def get_mention_end(last_word, words):
end = 0
for word in words:
if not word_to_ignore(word):
end += 1
if word['id'] == last_word['id']:
break
return end
def get_follow_context(mention_end, words):
context = []
context_end = mention_end + 1
while context_end < len(words):
if not word_to_ignore(words[context_end]):
context.append(words[context_end])
if len(context) == CONTEXT:
break
context_end += 1
return context
def get_sentence(word_idx, words):
sentence_start = get_sentence_start(words, word_idx)
sentence_end = get_sentence_end(words, word_idx)
sentence = [word for word in words[sentence_start:sentence_end + 1] if not word_to_ignore(word)]
return sentence
def get_sentence_start(words, word_idx):
search_start = word_idx
while word_idx >= 0:
if words[word_idx]['lastinsent'] and search_start != word_idx:
return word_idx + 1
word_idx -= 1
return 0
def get_sentence_end(words, word_idx):
while word_idx < len(words):
if words[word_idx]['lastinsent']:
return word_idx
word_idx += 1
return len(words) - 1
def get_head(head_orth, words):
for word in words:
if word['orth'].lower() == head_orth.lower() or word['orth'] == head_orth:
return word
return None
def span_to_text(span, words, form):
fragments = span.split(',')
mention_parts = []
for fragment in fragments:
mention_parts.append(fragment_to_text(fragment, words, form))
return u' [...] '.join(mention_parts)
def fragment_to_text(fragment, words, form):
if '..' in fragment:
text = get_multiword_text(fragment, words, form)
else:
text = get_one_word_text(fragment, words, form)
return text
def get_multiword_text(fragment, words, form):
mention_parts = []
boundaries = fragment.split('..')
start_id = boundaries[0]
end_id = boundaries[1]
in_string = False
for word in words:
if word['id'] == start_id:
in_string = True
if in_string and not word_to_ignore(word):
mention_parts.append(word)
if word['id'] == end_id:
break
return to_text(mention_parts, form)
def to_text(words, form):
text = ''
for idx, word in enumerate(words):
if word['hasnps'] or idx == 0:
text += word[form]
else:
text += u' %s' % word[form]
return text
def get_one_word_text(word_id, words, form):
this_word = next(word for word in words if word['id'] == word_id)
return this_word[form]
def get_gender(msd):
tags = msd.split(':')
if 'm1' in tags:
return 'm1'
elif 'm2' in tags:
return 'm2'
elif 'm3' in tags:
return 'm3'
elif 'f' in tags:
return 'f'
elif 'n' in tags:
return 'n'
else:
return 'unk'
def get_person(msd):
tags = msd.split(':')
if 'pri' in tags:
return 'pri'
elif 'sec' in tags:
return 'sec'
elif 'ter' in tags:
return 'ter'
else:
return 'unk'
def get_number(msd):
tags = msd.split(':')
if 'sg' in tags:
return 'sg'
elif 'pl' in tags:
return 'pl'
else:
return 'unk'
def get_rarest_word(words):
min_freq = 0
rarest_word = words[0]
for i, word in enumerate(words):
word_freq = 0
if word['base'] in FREQ_LIST:
word_freq = FREQ_LIST[word['base']]
if i == 0 or word_freq < min_freq:
min_freq = word_freq
rarest_word = word
return rarest_word
def write(inpath, outpath, text):
textname = os.path.splitext(os.path.basename(inpath))[0]
intextdir = os.path.dirname(inpath)
outtextdir = os.path.dirname(outpath)
in_mmax_path = os.path.join(intextdir, '%s.mmax' % textname)
out_mmax_path = os.path.join(outtextdir, '%s.mmax' % textname)
copy_mmax(in_mmax_path, out_mmax_path)
in_words_path = os.path.join(intextdir, '%s_words.xml' % textname)
out_words_path = os.path.join(outtextdir, '%s_words.xml' % textname)
copy_words(in_words_path, out_words_path)
in_mentions_path = os.path.join(intextdir, '%s_mentions.xml' % textname)
out_mentions_path = os.path.join(outtextdir, '%s_mentions.xml' % textname)
write_mentions(in_mentions_path, out_mentions_path, text)
def copy_mmax(src, dest):
shutil.copyfile(src, dest)
def copy_words(src, dest):
shutil.copyfile(src, dest)
def write_mentions(inpath, outpath, text):
tree = etree.parse(inpath)
mentions = tree.xpath("//ns:markable", namespaces={'ns': 'www.eml.org/NameSpaces/mention'})
for mnt in mentions:
mnt_set = text.get_mention_set(mnt.attrib['id'])
if mnt_set:
mnt.attrib['mention_group'] = mnt_set
else:
mnt.attrib['mention_group'] = 'empty'
with open(outpath, 'wb') as output_file:
output_file.write(etree.tostring(tree, pretty_print=True,
xml_declaration=True, encoding='UTF-8',
doctype=u'<!DOCTYPE markables SYSTEM "markables.dtd">'))