nltk /nltk/corpus/reader/pl196x.py

Language Python Lines 280
MD5 Hash 45474029a206be3cd4a74c229a7713e8
Repository https://github.com/BrucePHill/nltk.git View Raw File
  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
# Natural Language Toolkit:
#
# Copyright (C) 2001-2013 NLTK Project
# Author: Piotr Kasprzyk <p.j.kasprzyk@gmail.com>
# URL: <http://www.nltk.org/>
# For license information, see LICENSE.TXT

import os
import re

from nltk import compat
from nltk import tokenize, tree

from .util import *
from .api import *
from .xmldocs import XMLCorpusReader

# (?:something) -- non-grouping parentheses!

PARA = re.compile(r'<p(?: [^>]*){0,1}>(.*?)</p>')
SENT = re.compile(r'<s(?: [^>]*){0,1}>(.*?)</s>')

TAGGEDWORD = re.compile(r'<([wc](?: [^>]*){0,1}>)(.*?)</[wc]>')
WORD   =   re.compile(r'<[wc](?: [^>]*){0,1}>(.*?)</[wc]>')

TYPE = re.compile(r'type="(.*?)"')
ANA  = re.compile(r'ana="(.*?)"')

TEXTID = re.compile(r'text id="(.*?)"')


class TEICorpusView(StreamBackedCorpusView):
	def __init__(self, corpus_file,
					tagged, group_by_sent, group_by_para,
					tag_mapping_function=None, headLen=0,
					textids=None):
		self._tagged = tagged
		self._textids = textids

		self._group_by_sent = group_by_sent
		self._group_by_para = group_by_para
		# WARNING -- skip header
		StreamBackedCorpusView.__init__(self, corpus_file, startpos=headLen)

	_pagesize = 4096

	def read_block(self, stream):
		block = stream.readlines(self._pagesize)
		block = concat(block)
		while (block.count('<text id') > block.count('</text>')) \
				or block.count('<text id') == 0:
			tmp = stream.readline()
			if len(tmp) <= 0:
				break
			block += tmp

		block = block.replace('\n','')

		textids = TEXTID.findall(block)
		if self._textids:
			for tid in textids:
				if tid not in self._textids:
					beg = block.find(tid)-1
					end = block[beg: ].find('</text>')+len('</text>')
					block = block[ :beg]+block[beg+end: ]

		output = []
		for para_str in PARA.findall(block):
			para = []
			for sent_str in SENT.findall(para_str):
				if not self._tagged:
					sent = WORD.findall(sent_str)
				else:
					sent = list(map(self._parse_tag, TAGGEDWORD.findall(sent_str)))
				if self._group_by_sent:
					para.append(sent)
				else:
					para.extend(sent)
			if self._group_by_para:
				output.append(para)
			else:
				output.extend(para)
		return output

	def _parse_tag(self, tag_word_tuple):
		(tag, word) = tag_word_tuple
		if tag.startswith('w'):
			tag = ANA.search(tag).group(1)
		else: # tag.startswith('c')
			tag = TYPE.search(tag).group(1)
		return (word, tag)


class Pl196xCorpusReader(CategorizedCorpusReader, XMLCorpusReader):

	headLen = 2770

	def __init__(self, *args, **kwargs):
		if 'textid_file' in kwargs: self._textids = kwargs['textid_file']
		else: self._textids = None

		XMLCorpusReader.__init__(self, *args)
		CategorizedCorpusReader.__init__(self, kwargs)

		self._init_textids()

	def _init_textids(self):
		self._f2t = defaultdict(list)
		self._t2f = defaultdict(list)
		if self._textids is not None:
			for line in self.open(self._textids).readlines():
				line = line.strip()
				file_id, text_ids = line.split(' ', 1)
				if file_id not in self.fileids():
					raise ValueError('In text_id mapping file %s: %s '
									 'not found' % (catfile, file_id))
				for text_id in text_ids.split(self._delimiter):
					self._add_textids(file_id, text_id)

	def _add_textids(self, file_id, text_id):
		self._f2t[file_id].append(text_id)
		self._t2f[text_id].append(file_id)

	def _resolve(self, fileids, categories, textids=None):
		tmp = None
		if fileids is not None:
			if not tmp:
				tmp = fileids, None
			else:
				raise ValueError('Specify only fileids, categories or textids')
		if categories is not None:
			if not tmp:
				tmp = self.fileids(categories), None
			else:
				raise ValueError('Specify only fileids, categories or textids')
		if textids is not None:
			if not tmp:
				if isinstance(textids, compat.string_types): textids = [textids]
				files = sum((self._t2f[t] for t in textids), [])
				tdict = dict()
				for f in files:
					tdict[f] = (set(self._f2t[f]) & set(textids))
				tmp = files, tdict
			else:
				raise ValueError('Specify only fileids, categories or textids')
		return None, None

	def decode_tag(self, tag):
		# to be implemented
		return tag

	def textids(self, fileids=None, categories=None):
		"""
		In the pl196x corpus each category is stored in single
		file and thus both methods provide identical functionality. In order
		to accommodate finer granularity, a non-standard textids() method was
		implemented. All the main functions can be supplied with a list
		of required chunks---giving much more control to the user.
		"""
		fileids, _ = self._resolve(fileids, categories)
		if fileids is None: return sorted(self._t2f)

		if isinstance(fileids, compat.string_types):
			fileids = [fileids]
		return sorted(sum((self._f2t[d] for d in fileids), []))

	def words(self, fileids=None, categories=None, textids=None):
		fileids, textids = self._resolve(fileids, categories, textids)
		if fileids is None: fileids = self._fileids
		elif isinstance(fileids, compat.string_types): fileids = [fileids]

		if textids:
			return concat([TEICorpusView(self.abspath(fileid),
										False, False, False,
										headLen=self.headLen,
										textids=textids[fileid])
								for fileid in fileids])
		else:
			return concat([TEICorpusView(self.abspath(fileid),
										False, False, False,
										headLen=self.headLen)
								for fileid in fileids])

	def sents(self, fileids=None, categories=None, textids=None):
		fileids, textids = self._resolve(fileids, categories, textids)
		if fileids is None: fileids = self._fileids
		elif isinstance(fileids, compat.string_types): fileids = [fileids]

		if textids:
			return concat([TEICorpusView(self.abspath(fileid),
										False, True, False,
										headLen=self.headLen,
										textids=textids[fileid])
								for fileid in fileids])
		else:
			return concat([TEICorpusView(self.abspath(fileid),
										False, True, False,
										headLen=self.headLen)
								for fileid in fileids])

	def paras(self, fileids=None, categories=None, textids=None):
		fileids, textids = self._resolve(fileids, categories, textids)
		if fileids is None: fileids = self._fileids
		elif isinstance(fileids, compat.string_types): fileids = [fileids]

		if textids:
			return concat([TEICorpusView(self.abspath(fileid),
										False, True, True,
										headLen=self.headLen,
										textids=textids[fileid])
								for fileid in fileids])
		else:
			return concat([TEICorpusView(self.abspath(fileid),
										False, True, True,
										headLen=self.headLen)
								for fileid in fileids])

	def tagged_words(self, fileids=None, categories=None, textids=None):
		fileids, textids = self._resolve(fileids, categories, textids)
		if fileids is None: fileids = self._fileids
		elif isinstance(fileids, compat.string_types): fileids = [fileids]

		if textids:
			return concat([TEICorpusView(self.abspath(fileid),
										True, False, False,
										headLen=self.headLen,
										textids=textids[fileid])
								for fileid in fileids])
		else:
			return concat([TEICorpusView(self.abspath(fileid),
										True, False, False,
										headLen=self.headLen)
								for fileid in fileids])

	def tagged_sents(self, fileids=None, categories=None, textids=None):
		fileids, textids = self._resolve(fileids, categories, textids)
		if fileids is None: fileids = self._fileids
		elif isinstance(fileids, compat.string_types): fileids = [fileids]

		if textids:
			return concat([TEICorpusView(self.abspath(fileid),
										True, True, False,
										headLen=self.headLen,
										textids=textids[fileid])
								for fileid in fileids])
		else:
			return concat([TEICorpusView(self.abspath(fileid),
										True, True, False,
										headLen=self.headLen)
								for fileid in fileids])

	def tagged_paras(self, fileids=None, categories=None, textids=None):
		fileids, textids = self._resolve(fileids, categories, textids)
		if fileids is None: fileids = self._fileids
		elif isinstance(fileids, compat.string_types): fileids = [fileids]

		if textids:
			return concat([TEICorpusView(self.abspath(fileid),
										True, True, True,
										headLen=self.headLen,
										textids=textids[fileid])
								for fileid in fileids])
		else:
			return concat([TEICorpusView(self.abspath(fileid),
										True, True, True,
										headLen=self.headLen)
								for fileid in fileids])

	def xml(self, fileids=None, categories=None):
		fileids, _ = self._resolve(fileids, categories)
		if len(fileids) == 1: return XMLCorpusReader.xml(self, fileids[0])
		else: raise TypeError('Expected a single file')

	def raw(self, fileids=None, categories=None):
		fileids, _ = self._resolve(fileids, categories)
		if fileids is None: fileids = self._fileids
		elif isinstance(fileids, compat.string_types): fileids = [fileids]
		return concat([self.open(f).read() for f in fileids])
Back to Top