spaCy/spacy/lang/ca/punctuation.py
Adriane Boyd b98d216205
Update Catalan language data (#8308)
* Update Catalan language data

Update Catalan language data based on contributions from the Text Mining
Unit at the Barcelona Supercomputing Center:

https://github.com/TeMU-BSC/spacy4release/tree/main/lang_data

* Update tokenizer settings for UD Catalan AnCora

Update for UD Catalan AnCora v2.7 with merged multi-word tokens.

* Update test

* Move prefix patternt to more generic infix pattern

* Clean up
2021-06-11 10:21:22 +02:00

47 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.

from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_ICONS
from ..char_classes import CURRENCY
from ..char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA, PUNCT
from ..char_classes import merge_chars, _units
ELISION = " ' ".strip().replace(" ", "").replace("\n", "")
_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}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
r"(?<=[{a}][{el}])(?=[{a}0-9])".format(a=ALPHA, el=ELISION),
]
)
_units = _units.replace("% ", "")
UNITS = merge_chars(_units)
_suffixes = (
LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_ICONS
+ [r"-", "", ""]
+ [
r"(?<=[0-9])\+",
r"(?<=°[FfCcKk])\.",
r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
r"(?<=[0-9])(?:{u})".format(u=UNITS),
r"(?<=[0-9{al}{e}{p}(?:{q})])\.".format(
al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES, p=PUNCT
),
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
]
)
TOKENIZER_INFIXES = _infixes
TOKENIZER_SUFFIXES = _suffixes