mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 03:19:13 +03:00
e2b70df012
* Use isort with Black profile * isort all the things * Fix import cycles as a result of import sorting * Add DOCBIN_ALL_ATTRS type definition * Add isort to requirements * Remove isort from build dependencies check * Typo
79 lines
2.2 KiB
Python
79 lines
2.2 KiB
Python
from .char_classes import (
|
||
ALPHA,
|
||
ALPHA_LOWER,
|
||
ALPHA_UPPER,
|
||
COMBINING_DIACRITICS,
|
||
CONCAT_QUOTES,
|
||
CURRENCY,
|
||
HYPHENS,
|
||
LIST_CURRENCY,
|
||
LIST_ELLIPSES,
|
||
LIST_ICONS,
|
||
LIST_PUNCT,
|
||
LIST_QUOTES,
|
||
PUNCT,
|
||
UNITS,
|
||
)
|
||
|
||
TOKENIZER_PREFIXES = (
|
||
["§", "%", "=", "—", "–", r"\+(?![0-9])"]
|
||
+ LIST_PUNCT
|
||
+ LIST_ELLIPSES
|
||
+ LIST_QUOTES
|
||
+ LIST_CURRENCY
|
||
+ LIST_ICONS
|
||
)
|
||
|
||
|
||
TOKENIZER_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}{p}(?:{q})])\.".format(
|
||
al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES, p=PUNCT
|
||
),
|
||
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
|
||
]
|
||
)
|
||
|
||
TOKENIZER_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),
|
||
]
|
||
)
|
||
|
||
|
||
# Some languages e.g. written with the Cyrillic alphabet permit the use of diacritics
|
||
# to mark stressed syllables in words where stress is distinctive. Such languages
|
||
# should use the COMBINING_DIACRITICS... suffix and infix regex lists in
|
||
# place of the standard ones.
|
||
COMBINING_DIACRITICS_TOKENIZER_SUFFIXES = list(TOKENIZER_SUFFIXES) + [
|
||
r"(?<=[{a}][{d}])\.".format(a=ALPHA, d=COMBINING_DIACRITICS),
|
||
]
|
||
|
||
COMBINING_DIACRITICS_TOKENIZER_INFIXES = list(TOKENIZER_INFIXES) + [
|
||
r"(?<=[{al}][{d}])\.(?=[{au}{q}])".format(
|
||
al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES, d=COMBINING_DIACRITICS
|
||
),
|
||
r"(?<=[{a}][{d}]),(?=[{a}])".format(a=ALPHA, d=COMBINING_DIACRITICS),
|
||
r"(?<=[{a}][{d}])(?:{h})(?=[{a}])".format(
|
||
a=ALPHA, d=COMBINING_DIACRITICS, h=HYPHENS
|
||
),
|
||
r"(?<=[{a}][{d}])[:<>=/](?=[{a}])".format(a=ALPHA, d=COMBINING_DIACRITICS),
|
||
]
|