mirror of https://github.com/explosion/spaCy.git
49 lines
1.3 KiB
Python
49 lines
1.3 KiB
Python
# coding: utf8
|
||
from __future__ import unicode_literals
|
||
|
||
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_ICONS
|
||
from ..char_classes import ALPHA_LOWER, ALPHA, HYPHENS, QUOTES, UNITS
|
||
|
||
|
||
_currency = r"\$|¢|£|€|¥|฿|৳"
|
||
_quotes = QUOTES.replace("'", "")
|
||
_list_punct = LIST_PUNCT + "। ॥".strip().split()
|
||
|
||
|
||
_prefixes = [r"\+"] + _list_punct + LIST_ELLIPSES + LIST_QUOTES + LIST_ICONS
|
||
|
||
_suffixes = (
|
||
_list_punct
|
||
+ LIST_ELLIPSES
|
||
+ LIST_QUOTES
|
||
+ LIST_ICONS
|
||
+ [
|
||
r"(?<=[0-9])\+",
|
||
r"(?<=°[FfCcKk])\.",
|
||
r"(?<=[0-9])(?:{})".format(_currency),
|
||
r"(?<=[0-9])(?:{})".format(UNITS),
|
||
r"(?<=[{}(?:{})])\.".format(
|
||
"|".join([ALPHA_LOWER, r"%²\-\)\]\+", QUOTES]), _currency
|
||
),
|
||
]
|
||
)
|
||
|
||
_infixes = (
|
||
LIST_ELLIPSES
|
||
+ LIST_ICONS
|
||
+ [
|
||
r"(?<=[0-9{zero}-{nine}])[+\-\*^=](?=[0-9{zero}-{nine}-])".format(
|
||
zero="০", nine="৯"
|
||
),
|
||
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}])[{h}](?={ae})".format(a=ALPHA, h=HYPHENS, ae="এ"),
|
||
r'(?<=[{a}])[?";:=,.]*(?:{h})(?=[{a}])'.format(a=ALPHA, h=HYPHENS),
|
||
r'(?<=[{a}"])[:<>=/](?=[{a}])'.format(a=ALPHA),
|
||
]
|
||
)
|
||
|
||
|
||
TOKENIZER_PREFIXES = _prefixes
|
||
TOKENIZER_SUFFIXES = _suffixes
|
||
TOKENIZER_INFIXES = _infixes
|