spaCy/spacy/language_data/punctuation.py

116 lines
2.7 KiB
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
2016-12-08 21:46:43 +03:00
from __future__ import unicode_literals
import re
2016-12-08 21:46:43 +03:00
_ALPHA_LOWER = """
a ä à á â ǎ æ ã å ā ă ą b c ç ć č ĉ ċ c̄ d ð ď e é è ê ë ė ȅ ȩ ę f g ĝ ğ h i ı
î ï í ī ì ȉ ǐ į ĩ j k ķ l ł ļ m n ñ ń ň ņ o ö ó ò ő ô õ œ ø ō ő ǒ ơ p q r ř ŗ s
ß ś š ş ŝ t ť u ú û ù ú ū ű ǔ ů ų ư v w ŵ x y ÿ ý ŷ z ź ž ż þ
"""
_ALPHA_UPPER = """
A Ä À Á Â Ǎ Æ Ã Å Ā Ă Ą B C Ç Ć Č Ĉ Ċ C̄ D Ð Ď E É È Ê Ë Ė Ȅ Ȩ Ę F G Ĝ Ğ H I İ
Î Ï Í Ī Ì Ȉ Ǐ Į Ĩ J K Ķ L Ł Ļ M N Ñ Ń Ň Ņ O Ö Ó Ò Ő Ô Õ Œ Ø Ō Ő Ǒ Ơ P Q R Ř Ŗ S
Ś Š Ş Ŝ T Ť U Ú Û Ù Ú Ū Ű Ǔ Ů Ų Ư V W Ŵ X Y Ÿ Ý Ŷ Z Ź Ž Ż Þ
"""
_UNITS = """
km km² km³ m dm dm² dm³ cm cm² cm³ mm mm² mm³ ha µm nm yd in ft kg g mg
µg t lb oz m/s km/h kmh mph hPa Pa mbar mb MB kb KB gb GB tb
TB T G M K
"""
_CURRENCY = r"""
\$ £ ¥ ฿ US\$ C\$ A\$
"""
_QUOTES = r"""
' '' " ” “ `` ` ´ , „ » «
"""
_PUNCT = r"""
, : ; \! \? ¿ ¡ \( \) \[ \] \{ \} < > _ # \* &
"""
_HYPHENS = r"""
- -- ---
"""
LIST_ELLIPSES = [
r'\.\.+',
""
]
LIST_CURRENCY = list(_CURRENCY.strip().split())
LIST_QUOTES = list(_QUOTES.strip().split())
LIST_PUNCT = list(_PUNCT.strip().split())
LIST_HYPHENS = list(_HYPHENS.strip().split())
2017-01-14 17:51:59 +03:00
ALPHA_LOWER = _ALPHA_LOWER.strip().replace(' ', '').replace('\n', '')
ALPHA_UPPER = _ALPHA_UPPER.strip().replace(' ', '').replace('\n', '')
ALPHA = ALPHA_LOWER + ALPHA_UPPER
QUOTES = _QUOTES.strip().replace(' ', '|')
CURRENCY = _CURRENCY.strip().replace(' ', '|')
2017-01-14 17:51:59 +03:00
UNITS = _UNITS.strip().replace(' ', '|').replace('\n', '|')
HYPHENS = _HYPHENS.strip().replace(' ', '|')
# Prefixes
TOKENIZER_PREFIXES = (
2017-02-02 18:21:11 +03:00
['§', '%', '=', r'\+'] +
LIST_PUNCT +
LIST_ELLIPSES +
LIST_QUOTES +
LIST_CURRENCY
)
# Suffixes
TOKENIZER_SUFFIXES = (
LIST_PUNCT +
LIST_ELLIPSES +
LIST_QUOTES +
[
r'(?<=[0-9])\+',
r'(?<=°[FfCcKk])\.',
r'(?<=[0-9])(?:{c})'.format(c=CURRENCY),
r'(?<=[0-9])(?:{u})'.format(u=UNITS),
r'(?<=[0-9{al}{p}(?:{q})])\.'.format(al=ALPHA_LOWER, p=r'%²\-\)\]\+', q=QUOTES),
r'(?<=[{au}][{au}])\.'.format(au=ALPHA_UPPER),
"'s", "'S", "s", "S"
]
)
# Infixes
TOKENIZER_INFIXES = (
LIST_ELLIPSES +
[
r'(?<=[0-9])[+\-\*^](?=[0-9-])',
r'(?<=[{al}])\.(?=[{au}])'.format(al=ALPHA_LOWER, au=ALPHA_UPPER),
r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
r'(?<=[{a}])[?";:=,.]*(?:{h})(?=[{a}])'.format(a=ALPHA, h=HYPHENS),
r'(?<=[{a}"])[:<>=/](?=[{a}])'.format(a=ALPHA)
]
)
2016-12-08 21:46:43 +03:00
2016-12-18 17:35:56 +03:00
__all__ = ["TOKENIZER_PREFIXES", "TOKENIZER_SUFFIXES", "TOKENIZER_INFIXES"]