# coding: utf-8
#
# Natural Language Toolkit: Twitter Tokenizer
#
# Copyright (C) 2001-2019 NLTK Project
# Author: Christopher Potts <[email protected]>
# Ewan Klein <[email protected]> (modifications)
# Pierpaolo Pantone <> (modifications)
# URL: <http://nltk.org/>
# For license information, see LICENSE.TXT
#
"""
Twitter-aware tokenizer, designed to be flexible and easy to adapt to new
domains and tasks. The basic logic is this:
1. The tuple regex_strings defines a list of regular expression
strings.
2. The regex_strings strings are put, in order, into a compiled
regular expression object called word_re.
3. The tokenization is done by word_re.findall(s), where s is the
user-supplied string, inside the tokenize() method of the class
Tokenizer.
4. When instantiating Tokenizer objects, there is a single option:
preserve_case. By default, it is set to True. If it is set to
False, then the tokenizer will downcase everything except for
emoticons.
"""
######################################################################
from __future__ import unicode_literals
import re
from six import int2byte, unichr
from six.moves import html_entities
######################################################################
# The following strings are components in the regular expression
# that is used for tokenizing. It's important that phone_number
# appears first in the final regex (since it can contain whitespace).
# It also could matter that tags comes after emoticons, due to the
# possibility of having text like
#
# <:| and some text >:)
#
# Most importantly, the final element should always be last, since it
# does a last ditch whitespace-based tokenization of whatever is left.
# ToDo: Update with http://en.wikipedia.org/wiki/List_of_emoticons ?
# This particular element is used in a couple ways, so we define it
# with a name:
EMOTICONS = r"""
(?:
[<>]?
[:;=8] # eyes
[\-o\*\']? # optional nose
[\)\]\(\[dDpP/\:\}\{@\|\\] # mouth
|
[\)\]\(\[dDpP/\:\}\{@\|\\] # mouth
[\-o\*\']? # optional nose
[:;=8] # eyes
[<>]?
|
<3 # heart
)"""
# URL pattern due to John Gruber, modified by Tom Winzig. See
# https://gist.github.com/winzig/8894715
URLS = r""" # Capture 1: entire matched URL
(?:
https?: # URL protocol and colon
(?:
/{1,3} # 1-3 slashes
| # or
[a-z0-9%] # Single letter or digit or '%'
# (Trying not to match e.g. "URI::Escape")
)
| # or
# looks like domain name followed by a slash:
[a-z0-9.\-]+[.]
(?:[a-z]{2,13})
/
)
(?: # One or more:
[^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[]
| # or
\([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (...(...)...)
|
\([^\s]+?\) # balanced parens, non-recursive: (...)
)+
(?: # End with:
\([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (...(...)...)
|
\([^\s]+?\) # balanced parens, non-recursive: (...)
| # or
[^\s`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars
)
| # OR, the following to match naked domains:
(?:
(?<!@) # not preceded by a @, avoid matching foo@_gmail.com_
[a-z0-9]+
(?:[.\-][a-z0-9]+)*
[.]
(?:[a-z]{2,13})
\b
/?
(?!@) # not succeeded by a @,
# avoid matching "foo.na" in "[email protected]"
)
"""
# The components of the tokenizer:
REGEXPS = (
URLS,
# Phone numbers:
r"""
(?:
(?: # (international)
\+?[01]
[ *\-.\)]*
)?
(?: # (area code)
[\(]?
\d{3}
[ *\-.\)]*
)?
\d{3} # exchange
[ *\-.\)]*
\d{4} # base
)""",
# ASCII Emoticons
EMOTICONS,
# HTML tags:
r"""<[^>\s]+>""",
# ASCII Arrows
r"""[\-]+>|<[\-]+""",
# Twitter username:
r"""(?:@[\w_]+)""",
# Twitter hashtags:
r"""(?:\#+[\w_]+[\w\'_\-]*[\w_]+)""",
# email addresses
r"""[\w.+-]+@[\w-]+\.(?:[\w-]\.?)+[\w-]""",
# Remaining word types:
r"""
(?:[^\W\d_](?:[^\W\d_]|['\-_])+[^\W\d_]) # Words with apostrophes or dashes.
|
(?:[+\-]?\d+[,/.:-]\d+[+\-]?) # Numbers, including fractions, decimals.
|
(?:[\w_]+) # Words without apostrophes or dashes.
|
(?:\.(?:\s*\.){1,}) # Ellipsis dots.
|
(?:\S) # Everything else that isn't whitespace.
""",
)
######################################################################
# This is the core tokenizing regex:
WORD_RE = re.compile(r"""(%s)""" % "|".join(REGEXPS), re.VERBOSE | re.I | re.UNICODE)
# WORD_RE performs poorly on these patterns:
HANG_RE = re.compile(r'([^a-zA-Z0-9])\1{3,}')
# The emoticon string gets its own regex so that we can preserve case for
# them as needed:
EMOTICON_RE = re.compile(EMOTICONS, re.VERBOSE | re.I | re.UNICODE)
# These are for regularizing HTML entities to Unicode:
ENT_RE = re.compile(r'&(#?(x?))([^&;\s]+);')
######################################################################
# Functions for converting html entities
######################################################################
def _str_to_unicode(text, encoding=None, errors='strict'):
if encoding is None:
encoding = 'utf-8'
if isinstance(text, bytes):
return text.decode(encoding, errors)
return text
def _replace_html_entities(text, keep=(), remove_illegal=True, encoding='utf-8'):
"""
Remove entities from text by converting them to their
corresponding unicode character.
:param text: a unicode string or a byte string encoded in the given
`encoding` (which defaults to 'utf-8').
:param list keep: list of entity names which should not be replaced.\
This supports both numeric entities (``&#nnnn;`` and ``&#hhhh;``)
and named entities (such as `` `` or ``>``).
:param bool remove_illegal: If `True`, entities that can't be converted are\
removed. Otherwise, entities that can't be converted are kept "as
is".
:returns: A unicode string with the entities removed.
See https://github.com/scrapy/w3lib/blob/master/w3lib/html.py
>>> from nltk.tokenize.casual import _replace_html_entities
>>> _replace_html_entities(b'Price: £100')
'Price: \\xa3100'
>>> print(_replace_html_entities(b'Price: £100'))
Price: £100
>>>
"""
def _convert_entity(match):
entity_body = match.group(3)
if match.group(1):
try:
if match.group(2):
number = int(entity_body, 16)
else:
number = int(entity_body, 10)
# Numeric character references in the 80-9F range are typically
# interpreted by browsers as representing the characters mapped
# to bytes 80-9F in the Windows-1252 encoding. For more info
# see: http://en.wikipedia.org/wiki/Character_encodings_in_HTML
if 0x80 <= number <= 0x9F:
return int2byte(number).decode('cp1252')
except ValueError:
number = None
else:
if entity_body in keep:
return match.group(0)
else:
number = html_entities.name2codepoint.get(entity_body)
if number is not None:
try:
return unichr(number)
except ValueError:
pass
return "" if remove_illegal else match.group(0)
return ENT_RE.sub(_convert_entity, _str_to_unicode(text, encoding))
######################################################################
######################################################################
# Normalization Functions
######################################################################
[docs]def reduce_lengthening(text):
"""
Replace repeated character sequences of length 3 or greater with sequences
of length 3.
"""
pattern = re.compile(r"(.)\1{2,}")
return pattern.sub(r"\1\1\1", text)
[docs]def remove_handles(text):
"""
Remove Twitter username handles from text.
"""
pattern = re.compile(
r"(?<![A-Za-z0-9_!@#\$%&*])@(([A-Za-z0-9_]){20}(?!@))|(?<![A-Za-z0-9_!@#\$%&*])@(([A-Za-z0-9_]){1,19})(?![A-Za-z0-9_]*@)"
)
# Substitute hadnles with ' ' to ensure that text on either side of removed handles are tokenized correctly
return pattern.sub(' ', text)
######################################################################
# Tokenization Function
######################################################################
[docs]def casual_tokenize(text, preserve_case=True, reduce_len=False, strip_handles=False):
"""
Convenience function for wrapping the tokenizer.
"""
return TweetTokenizer(
preserve_case=preserve_case, reduce_len=reduce_len, strip_handles=strip_handles
).tokenize(text)
###############################################################################