mirror of https://github.com/explosion/spaCy.git
63 lines
1.7 KiB
Python
63 lines
1.7 KiB
Python
# coding: utf8
|
||
from __future__ import unicode_literals
|
||
|
||
from ..char_classes import LIST_ELLIPSES, LIST_ICONS, LIST_PUNCT, LIST_QUOTES
|
||
from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
|
||
from ..char_classes import CURRENCY, PUNCT, UNITS, LIST_CURRENCY
|
||
|
||
|
||
# Punctuation adapted from Danish
|
||
_quotes = CONCAT_QUOTES.replace("'", "")
|
||
_list_punct = [x for x in LIST_PUNCT if x != "#"]
|
||
_list_icons = [x for x in LIST_ICONS if x != "°"]
|
||
_list_icons = [x.replace("\\u00B0", "") for x in _list_icons]
|
||
_list_quotes = [x for x in LIST_QUOTES if x != "\\'"]
|
||
|
||
|
||
_prefixes = (
|
||
["§", "%", "=", "—", "–", r"\+(?![0-9])"]
|
||
+ _list_punct
|
||
+ LIST_ELLIPSES
|
||
+ LIST_QUOTES
|
||
+ LIST_CURRENCY
|
||
+ LIST_ICONS
|
||
)
|
||
|
||
|
||
_infixes = (
|
||
LIST_ELLIPSES
|
||
+ _list_icons
|
||
+ [
|
||
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}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
|
||
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
|
||
]
|
||
)
|
||
|
||
_suffixes = (
|
||
LIST_PUNCT
|
||
+ LIST_ELLIPSES
|
||
+ _list_quotes
|
||
+ _list_icons
|
||
+ ["—", "–"]
|
||
+ [
|
||
r"(?<=[0-9])\+",
|
||
r"(?<=°[FfCcKk])\.",
|
||
r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
|
||
r"(?<=[0-9])(?:{u})".format(u=UNITS),
|
||
r"(?<=[{al}{e}{p}(?:{q})])\.".format(
|
||
al=ALPHA_LOWER, e=r"%²\-\+", q=_quotes, p=PUNCT
|
||
),
|
||
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
|
||
]
|
||
+ [r"(?<=[^sSxXzZ])'"]
|
||
)
|
||
|
||
|
||
TOKENIZER_PREFIXES = _prefixes
|
||
TOKENIZER_INFIXES = _infixes
|
||
TOKENIZER_SUFFIXES = _suffixes
|