explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Reorganise Bengali punctuation rules

Browse Source
This commit is contained in:
ines 2017-05-09 00:01:52 +02:00
parent e895d1afd7
commit fc0d793360
1 changed files with 28 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
spacy/lang/bn/punctuation.py
View File

@ -1,45 +1,33 @@
# coding: utf8 # coding: utf8
from __future__ import unicode_literals from __future__ import unicode_literals
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, UNITS
from ..char_classes import ALPHA_LOWER, ALPHA_UPPER, ALPHA, HYPHENS, QUOTES
CURRENCY_SYMBOLS = r"\$ ¢ £ € ¥ ฿ ৳" _currency = r"\$|¢|£|€|¥|฿|৳"
_quotes = QUOTES.replace("'", '')
_list_punct = LIST_PUNCT + '। ॥'.strip().split()
_PUNCT = '। ॥'
LIST_PUNCT.extend(_PUNCT.strip().split()) _prefixes = ([r'\+'] + _list_punct + LIST_ELLIPSES + LIST_QUOTES)
TOKENIZER_PREFIXES = ( _suffixes = (_list_punct + LIST_ELLIPSES + LIST_QUOTES +
[r'\+'] + [r'(?<=[0-9])\+',
LIST_PUNCT +
LIST_ELLIPSES +
LIST_QUOTES
)
TOKENIZER_SUFFIXES = (
LIST_PUNCT +
LIST_ELLIPSES +
LIST_QUOTES +
[
r'(?<=[0-9])\+',
r'(?<=°[FfCcKk])\.', r'(?<=°[FfCcKk])\.',
r'(?<=[0-9])(?:{c})'.format(c=CURRENCY), r'(?<=[0-9])(?:{})'.format(_currency),
r'(?<=[0-9])(?:{u})'.format(u=UNITS), r'(?<=[0-9])(?:{})'.format(UNITS),
r'(?<=[{al}{p}{c}(?:{q})])\.'.format(al=ALPHA_LOWER, p=r'%²\-\)\]\+', q=QUOTES, c=CURRENCY_SYMBOLS), r'(?<=[{}(?:{})])\.'.format('|'.join([ALPHA_LOWER, r'%²\-\)\]\+', QUOTES]), _currency)])
r'(?<=[{al})])-e'.format(al=ALPHA_LOWER)
]
)
TOKENIZER_INFIXES = ( _infixes = (LIST_ELLIPSES +
LIST_ELLIPSES + [r'(?<=[{}])\.(?=[{}])'.format(ALPHA_LOWER, ALPHA_UPPER),
[
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}])--(?=[{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(" ", "")), r'(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])'.format(a=ALPHA, q=_quotes)])
]
)
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, UNITS TOKENIZER_PREFIXES = _prefixes
from ..char_classes import ALPHA_LOWER, ALPHA_UPPER, ALPHA, HYPHENS, QUOTES TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_INFIXES = _infixes