spaCy/spacy/lang/punctuation.py
Sofie 9a478b6db8 Clean up of char classes, few tokenizer fixes and faster default French tokenizer (#3293)
* splitting up latin unicode interval

* removing hyphen as infix for French

* adding failing test for issue 1235

* test for issue #3002 which now works

* partial fix for issue #2070

* keep the hyphen as infix for French (as it was)

* restore french expressions with hyphen as infix (as it was)

* added succeeding unit test for Issue #2656

* Fix issue #2822 with custom Italian exception

* Fix issue #2926 by allowing numbers right before infix /

* splitting up latin unicode interval

* removing hyphen as infix for French

* adding failing test for issue 1235

* test for issue #3002 which now works

* partial fix for issue #2070

* keep the hyphen as infix for French (as it was)

* restore french expressions with hyphen as infix (as it was)

* added succeeding unit test for Issue #2656

* Fix issue #2822 with custom Italian exception

* Fix issue #2926 by allowing numbers right before infix /

* remove duplicate

* remove xfail for Issue #2179 fixed by Matt

* adjust documentation and remove reference to regex lib
2019-02-20 22:10:13 +01:00

52 lines
1.3 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf8
from __future__ import unicode_literals
from .char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_CURRENCY
from .char_classes import LIST_ICONS, HYPHENS, CURRENCY, UNITS
from .char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA
_prefixes = (
["§", "%", "=", "", "", r"\+(?![0-9])"]
+ LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_CURRENCY
+ LIST_ICONS
)
_suffixes = (
LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_ICONS
+ ["'s", "'S", "s", "S", "", ""]
+ [
r"(?<=[0-9])\+",
r"(?<=°[FfCcKk])\.",
r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
r"(?<=[0-9])(?:{u})".format(u=UNITS),
r"(?<=[0-9{al}{e}(?:{q})])\.".format(
al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES
),
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
]
)
_infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[0-9])[+\-\*^](?=[0-9-])",
r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
]
)
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_INFIXES = _infixes