explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Reorganise Hungarian punctuation rules

Browse Source
This commit is contained in:
ines 2017-05-09 00:01:59 +02:00
parent fc0d793360
commit 9f0fd5963f
1 changed files with 24 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
spacy/lang/hu/punctuation.py
View File

@ -1,40 +1,35 @@
# coding: utf8 # coding: utf8
from __future__ import unicode_literals from __future__ import unicode_literals
from ..punctuation import TOKENIZER_INFIXES
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
from ..char_classes import QUOTES, UNITS, ALPHA, ALPHA_LOWER, ALPHA_UPPER
_currency_symbols = r"\$ ¢ £ € ¥ ฿" _currency = r'\$|¢|£|€|¥|฿'
_quotes = QUOTES.replace("'", '')
TOKENIZER_PREFIXES = ( _prefixes = ([r'\+'] + LIST_PUNCT + LIST_ELLIPSES + LIST_QUOTES)
[r'\+'] +
LIST_PUNCT + _suffixes = (LIST_PUNCT + LIST_ELLIPSES + LIST_QUOTES +
LIST_ELLIPSES + [r'(?<=[0-9])\+',
LIST_QUOTES) r'(?<=°[FfCcKk])\.',
r'(?<=[0-9])(?:{})'.format(_currency),
r'(?<=[0-9])(?:{})'.format(UNITS),
r'(?<=[{}{}{}(?:{})])\.'.format(ALPHA_LOWER, r'%²\-\)\]\+', QUOTES, _currency),
r'(?<=[{})])-e'.format(ALPHA_LOWER)])
TOKENIZER_SUFFIXES = ( _infixes = (LIST_ELLIPSES +
LIST_PUNCT + [r'(?<=[{}])\.(?=[{}])'.format(ALPHA_LOWER, ALPHA_UPPER),
LIST_ELLIPSES + r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
LIST_QUOTES + r'(?<=[{a}"])[:<>=](?=[{a}])'.format(a=ALPHA),
[ r'(?<=[{a}])--(?=[{a}])'.format(a=ALPHA),
r'(?<=[0-9])\+', r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
r'(?<=°[FfCcKk])\.', r'(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])'.format(a=ALPHA, q=_quotes)])
r'(?<=[0-9])(?:{c})'.format(c=CURRENCY),
r'(?<=[0-9])(?:{u})'.format(u=UNITS),
r'(?<=[{al}{p}{c}(?:{q})])\.'.format(al=ALPHA_LOWER, p=r'%²\-\)\]\+', q=QUOTES, c=_currency_symbols),
r'(?<=[{al})])-e'.format(al=ALPHA_LOWER)])
TOKENIZER_INFIXES = ( TOKENIZER_PREFIXES = _prefixes
LIST_ELLIPSES + TOKENIZER_SUFFIXES = _suffixes
[ TOKENIZER_INFIXES = _infixes
r'(?<=[{al}])\.(?=[{au}])'.format(al=ALPHA_LOWER, au=ALPHA_UPPER),
r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
r'(?<=[{a}"])[:<>=](?=[{a}])'.format(a=ALPHA),
r'(?<=[{a}])--(?=[{a}])'.format(a=ALPHA),
r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
r'(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])'.format(a=ALPHA, q=_QUOTES.replace("'", "").strip().replace(" ", ""))])
from ..char_classes import TOKENIZER_INFIXES, LIST_PUNCT LIST_ELLIPSES
from ..char_classes import LIST_QUOTES, CURRENCY, QUOTES, UNITS
from ..char_classes import ALPHA, ALPHA_LOWER, ALPHA_UPPER