spaCy/spacy/lang/fr/punctuation.py

48 lines
1.5 KiB
Python
Raw Normal View History

2017-03-12 12:07:28 +00:00
# coding: utf8
2017-01-24 08:47:13 +00:00
from __future__ import unicode_literals
from ..punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
2017-05-08 22:00:54 +00:00
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
2017-01-24 08:47:13 +00:00
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),
2019-03-09 11:40:58 +00:00
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)
]
2017-05-08 22:00:54 +00:00
TOKENIZER_PREFIXES = _prefixes
2017-05-08 22:00:54 +00:00
TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_INFIXES = _infixes