spaCy/spacy/lang/fr/punctuation.py
adrianeboyd 4117a5c705
Improve French tokenization (#5202)
Improve French tokenization for UD_French-Sequoia.
2020-03-25 11:27:42 +01:00

48 lines
1.5 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 ..punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
from ..char_classes import CONCAT_QUOTES, UNITS, ALPHA, ALPHA_LOWER, ALPHA_UPPER
from ..char_classes import merge_chars
ELISION = "' ".replace(" ", "")
HYPHENS = r"- ".replace(" ", "")
_prefixes_elision = "d l n"
_prefixes_elision += " " + _prefixes_elision.upper()
_hyphen_suffixes = "ce clés elle en il ils je là moi nous on t vous"
_hyphen_suffixes += " " + _hyphen_suffixes.upper()
_prefixes = TOKENIZER_PREFIXES + [
r"(?:({pe})[{el}])(?=[{a}])".format(a=ALPHA, el=ELISION, pe=merge_chars(_prefixes_elision))
]
_suffixes = (
LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ [
r"(?<=[0-9])\+",
r"(?<=°[FfCcKk])\.", # °C. -> ["°C", "."]
r"(?<=[0-9])%", # 4% -> ["4", "%"]
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),
r"(?<=[{a}])[{h}]({hs})".format(a=ALPHA, h=HYPHENS, hs=merge_chars(_hyphen_suffixes)),
]
)
_infixes = TOKENIZER_INFIXES + [
r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION)
]
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_INFIXES = _infixes