PCQRSCANER/venv/Lib/site-packages/nltk/tokenize/__init__.py

148 lines
5.8 KiB
Python
Raw Normal View History

2019-12-22 21:51:47 +01:00
# -*- coding: utf-8 -*-
# Natural Language Toolkit: Tokenizers
#
# Copyright (C) 2001-2019 NLTK Project
# Author: Edward Loper <edloper@gmail.com>
# Steven Bird <stevenbird1@gmail.com> (minor additions)
# Contributors: matthewmc, clouds56
# URL: <http://nltk.org/>
# For license information, see LICENSE.TXT
r"""
NLTK Tokenizer Package
Tokenizers divide strings into lists of substrings. For example,
tokenizers can be used to find the words and punctuation in a string:
>>> from nltk.tokenize import word_tokenize
>>> s = '''Good muffins cost $3.88\nin New York. Please buy me
... two of them.\n\nThanks.'''
>>> word_tokenize(s)
['Good', 'muffins', 'cost', '$', '3.88', 'in', 'New', 'York', '.',
'Please', 'buy', 'me', 'two', 'of', 'them', '.', 'Thanks', '.']
This particular tokenizer requires the Punkt sentence tokenization
models to be installed. NLTK also provides a simpler,
regular-expression based tokenizer, which splits text on whitespace
and punctuation:
>>> from nltk.tokenize import wordpunct_tokenize
>>> wordpunct_tokenize(s)
['Good', 'muffins', 'cost', '$', '3', '.', '88', 'in', 'New', 'York', '.',
'Please', 'buy', 'me', 'two', 'of', 'them', '.', 'Thanks', '.']
We can also operate at the level of sentences, using the sentence
tokenizer directly as follows:
>>> from nltk.tokenize import sent_tokenize, word_tokenize
>>> sent_tokenize(s)
['Good muffins cost $3.88\nin New York.', 'Please buy me\ntwo of them.', 'Thanks.']
>>> [word_tokenize(t) for t in sent_tokenize(s)]
[['Good', 'muffins', 'cost', '$', '3.88', 'in', 'New', 'York', '.'],
['Please', 'buy', 'me', 'two', 'of', 'them', '.'], ['Thanks', '.']]
Caution: when tokenizing a Unicode string, make sure you are not
using an encoded version of the string (it may be necessary to
decode it first, e.g. with ``s.decode("utf8")``.
NLTK tokenizers can produce token-spans, represented as tuples of integers
having the same semantics as string slices, to support efficient comparison
of tokenizers. (These methods are implemented as generators.)
>>> from nltk.tokenize import WhitespaceTokenizer
>>> list(WhitespaceTokenizer().span_tokenize(s))
[(0, 4), (5, 12), (13, 17), (18, 23), (24, 26), (27, 30), (31, 36), (38, 44),
(45, 48), (49, 51), (52, 55), (56, 58), (59, 64), (66, 73)]
There are numerous ways to tokenize text. If you need more control over
tokenization, see the other methods provided in this package.
For further information, please see Chapter 3 of the NLTK book.
"""
import re
from nltk.data import load
from nltk.tokenize.casual import TweetTokenizer, casual_tokenize
from nltk.tokenize.mwe import MWETokenizer
from nltk.tokenize.punkt import PunktSentenceTokenizer
from nltk.tokenize.regexp import (
RegexpTokenizer,
WhitespaceTokenizer,
BlanklineTokenizer,
WordPunctTokenizer,
wordpunct_tokenize,
regexp_tokenize,
blankline_tokenize,
)
from nltk.tokenize.repp import ReppTokenizer
from nltk.tokenize.sexpr import SExprTokenizer, sexpr_tokenize
from nltk.tokenize.simple import (
SpaceTokenizer,
TabTokenizer,
LineTokenizer,
line_tokenize,
)
from nltk.tokenize.texttiling import TextTilingTokenizer
from nltk.tokenize.toktok import ToktokTokenizer
from nltk.tokenize.treebank import TreebankWordTokenizer
from nltk.tokenize.util import string_span_tokenize, regexp_span_tokenize
from nltk.tokenize.stanford_segmenter import StanfordSegmenter
from nltk.tokenize.sonority_sequencing import SyllableTokenizer
# Standard sentence tokenizer.
def sent_tokenize(text, language='english'):
"""
Return a sentence-tokenized copy of *text*,
using NLTK's recommended sentence tokenizer
(currently :class:`.PunktSentenceTokenizer`
for the specified language).
:param text: text to split into sentences
:param language: the model name in the Punkt corpus
"""
tokenizer = load('tokenizers/punkt/{0}.pickle'.format(language))
return tokenizer.tokenize(text)
# Standard word tokenizer.
_treebank_word_tokenizer = TreebankWordTokenizer()
# See discussion on https://github.com/nltk/nltk/pull/1437
# Adding to TreebankWordTokenizer, nltk.word_tokenize now splits on
# - chervon quotes u'\xab' and u'\xbb' .
# - unicode quotes u'\u2018', u'\u2019', u'\u201c' and u'\u201d'
# See https://github.com/nltk/nltk/issues/1995#issuecomment-376741608
# Also, behavior of splitting on clitics now follows Stanford CoreNLP
# - clitics covered (?!re|ve|ll|m|t|s|d)(\w)\b
improved_open_quote_regex = re.compile(u'([«“‘„]|[`]+)', re.U)
improved_open_single_quote_regex = re.compile(r"(?i)(\')(?!re|ve|ll|m|t|s|d)(\w)\b", re.U)
improved_close_quote_regex = re.compile(u'([»”’])', re.U)
improved_punct_regex = re.compile(r'([^\.])(\.)([\]\)}>"\'' u'»”’ ' r']*)\s*$', re.U)
_treebank_word_tokenizer.STARTING_QUOTES.insert(0, (improved_open_quote_regex, r' \1 '))
_treebank_word_tokenizer.STARTING_QUOTES.append((improved_open_single_quote_regex, r'\1 \2'))
_treebank_word_tokenizer.ENDING_QUOTES.insert(0, (improved_close_quote_regex, r' \1 '))
_treebank_word_tokenizer.PUNCTUATION.insert(0, (improved_punct_regex, r'\1 \2 \3 '))
def word_tokenize(text, language='english', preserve_line=False):
"""
Return a tokenized copy of *text*,
using NLTK's recommended word tokenizer
(currently an improved :class:`.TreebankWordTokenizer`
along with :class:`.PunktSentenceTokenizer`
for the specified language).
:param text: text to split into words
:type text: str
:param language: the model name in the Punkt corpus
:type language: str
:param preserve_line: An option to keep the preserve the sentence and not sentence tokenize it.
:type preserve_line: bool
"""
sentences = [text] if preserve_line else sent_tokenize(text, language)
return [
token for sent in sentences for token in _treebank_word_tokenizer.tokenize(sent)
]