Spaces:
Sleeping
Sleeping
File size: 9,366 Bytes
d916065 |
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 |
# Natural Language Toolkit: Chunked Corpus Reader
#
# Copyright (C) 2001-2023 NLTK Project
# Author: Steven Bird <[email protected]>
# Edward Loper <[email protected]>
# URL: <https://www.nltk.org/>
# For license information, see LICENSE.TXT
"""
A reader for corpora that contain chunked (and optionally tagged)
documents.
"""
import codecs
import os.path
import nltk
from nltk.chunk import tagstr2tree
from nltk.corpus.reader.api import *
from nltk.corpus.reader.bracket_parse import BracketParseCorpusReader
from nltk.corpus.reader.util import *
from nltk.tokenize import *
from nltk.tree import Tree
class ChunkedCorpusReader(CorpusReader):
"""
Reader for chunked (and optionally tagged) corpora. Paragraphs
are split using a block reader. They are then tokenized into
sentences using a sentence tokenizer. Finally, these sentences
are parsed into chunk trees using a string-to-chunktree conversion
function. Each of these steps can be performed using a default
function or a custom function. By default, paragraphs are split
on blank lines; sentences are listed one per line; and sentences
are parsed into chunk trees using ``nltk.chunk.tagstr2tree``.
"""
def __init__(
self,
root,
fileids,
extension="",
str2chunktree=tagstr2tree,
sent_tokenizer=RegexpTokenizer("\n", gaps=True),
para_block_reader=read_blankline_block,
encoding="utf8",
tagset=None,
):
"""
:param root: The root directory for this corpus.
:param fileids: A list or regexp specifying the fileids in this corpus.
"""
CorpusReader.__init__(self, root, fileids, encoding)
self._cv_args = (str2chunktree, sent_tokenizer, para_block_reader, tagset)
"""Arguments for corpus views generated by this corpus: a tuple
(str2chunktree, sent_tokenizer, para_block_tokenizer)"""
def words(self, fileids=None):
"""
:return: the given file(s) as a list of words
and punctuation symbols.
:rtype: list(str)
"""
return concat(
[
ChunkedCorpusView(f, enc, 0, 0, 0, 0, *self._cv_args)
for (f, enc) in self.abspaths(fileids, True)
]
)
def sents(self, fileids=None):
"""
:return: the given file(s) as a list of
sentences or utterances, each encoded as a list of word
strings.
:rtype: list(list(str))
"""
return concat(
[
ChunkedCorpusView(f, enc, 0, 1, 0, 0, *self._cv_args)
for (f, enc) in self.abspaths(fileids, True)
]
)
def paras(self, fileids=None):
"""
:return: the given file(s) as a list of
paragraphs, each encoded as a list of sentences, which are
in turn encoded as lists of word strings.
:rtype: list(list(list(str)))
"""
return concat(
[
ChunkedCorpusView(f, enc, 0, 1, 1, 0, *self._cv_args)
for (f, enc) in self.abspaths(fileids, True)
]
)
def tagged_words(self, fileids=None, tagset=None):
"""
:return: the given file(s) as a list of tagged
words and punctuation symbols, encoded as tuples
``(word,tag)``.
:rtype: list(tuple(str,str))
"""
return concat(
[
ChunkedCorpusView(
f, enc, 1, 0, 0, 0, *self._cv_args, target_tagset=tagset
)
for (f, enc) in self.abspaths(fileids, True)
]
)
def tagged_sents(self, fileids=None, tagset=None):
"""
:return: the given file(s) as a list of
sentences, each encoded as a list of ``(word,tag)`` tuples.
:rtype: list(list(tuple(str,str)))
"""
return concat(
[
ChunkedCorpusView(
f, enc, 1, 1, 0, 0, *self._cv_args, target_tagset=tagset
)
for (f, enc) in self.abspaths(fileids, True)
]
)
def tagged_paras(self, fileids=None, tagset=None):
"""
:return: the given file(s) as a list of
paragraphs, each encoded as a list of sentences, which are
in turn encoded as lists of ``(word,tag)`` tuples.
:rtype: list(list(list(tuple(str,str))))
"""
return concat(
[
ChunkedCorpusView(
f, enc, 1, 1, 1, 0, *self._cv_args, target_tagset=tagset
)
for (f, enc) in self.abspaths(fileids, True)
]
)
def chunked_words(self, fileids=None, tagset=None):
"""
:return: the given file(s) as a list of tagged
words and chunks. Words are encoded as ``(word, tag)``
tuples (if the corpus has tags) or word strings (if the
corpus has no tags). Chunks are encoded as depth-one
trees over ``(word,tag)`` tuples or word strings.
:rtype: list(tuple(str,str) and Tree)
"""
return concat(
[
ChunkedCorpusView(
f, enc, 1, 0, 0, 1, *self._cv_args, target_tagset=tagset
)
for (f, enc) in self.abspaths(fileids, True)
]
)
def chunked_sents(self, fileids=None, tagset=None):
"""
:return: the given file(s) as a list of
sentences, each encoded as a shallow Tree. The leaves
of these trees are encoded as ``(word, tag)`` tuples (if
the corpus has tags) or word strings (if the corpus has no
tags).
:rtype: list(Tree)
"""
return concat(
[
ChunkedCorpusView(
f, enc, 1, 1, 0, 1, *self._cv_args, target_tagset=tagset
)
for (f, enc) in self.abspaths(fileids, True)
]
)
def chunked_paras(self, fileids=None, tagset=None):
"""
:return: the given file(s) as a list of
paragraphs, each encoded as a list of sentences, which are
in turn encoded as a shallow Tree. The leaves of these
trees are encoded as ``(word, tag)`` tuples (if the corpus
has tags) or word strings (if the corpus has no tags).
:rtype: list(list(Tree))
"""
return concat(
[
ChunkedCorpusView(
f, enc, 1, 1, 1, 1, *self._cv_args, target_tagset=tagset
)
for (f, enc) in self.abspaths(fileids, True)
]
)
def _read_block(self, stream):
return [tagstr2tree(t) for t in read_blankline_block(stream)]
class ChunkedCorpusView(StreamBackedCorpusView):
def __init__(
self,
fileid,
encoding,
tagged,
group_by_sent,
group_by_para,
chunked,
str2chunktree,
sent_tokenizer,
para_block_reader,
source_tagset=None,
target_tagset=None,
):
StreamBackedCorpusView.__init__(self, fileid, encoding=encoding)
self._tagged = tagged
self._group_by_sent = group_by_sent
self._group_by_para = group_by_para
self._chunked = chunked
self._str2chunktree = str2chunktree
self._sent_tokenizer = sent_tokenizer
self._para_block_reader = para_block_reader
self._source_tagset = source_tagset
self._target_tagset = target_tagset
def read_block(self, stream):
block = []
for para_str in self._para_block_reader(stream):
para = []
for sent_str in self._sent_tokenizer.tokenize(para_str):
sent = self._str2chunktree(
sent_str,
source_tagset=self._source_tagset,
target_tagset=self._target_tagset,
)
# If requested, throw away the tags.
if not self._tagged:
sent = self._untag(sent)
# If requested, throw away the chunks.
if not self._chunked:
sent = sent.leaves()
# Add the sentence to `para`.
if self._group_by_sent:
para.append(sent)
else:
para.extend(sent)
# Add the paragraph to `block`.
if self._group_by_para:
block.append(para)
else:
block.extend(para)
# Return the block
return block
def _untag(self, tree):
for i, child in enumerate(tree):
if isinstance(child, Tree):
self._untag(child)
elif isinstance(child, tuple):
tree[i] = child[0]
else:
raise ValueError("expected child to be Tree or tuple")
return tree
|