mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
46 lines
1.2 KiB
Python
46 lines
1.2 KiB
Python
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_ICONS
|
||
from ..char_classes import ALPHA_LOWER, ALPHA, HYPHENS, CONCAT_QUOTES, UNITS
|
||
|
||
|
||
_currency = r"\$¢£€¥฿৳"
|
||
_quotes = CONCAT_QUOTES.replace("'", "")
|
||
_list_punct = LIST_PUNCT + "। ॥".strip().split()
|
||
|
||
|
||
_prefixes = [r"\+"] + _list_punct + LIST_ELLIPSES + LIST_QUOTES + LIST_ICONS
|
||
|
||
_suffixes = (
|
||
_list_punct
|
||
+ LIST_ELLIPSES
|
||
+ LIST_QUOTES
|
||
+ LIST_ICONS
|
||
+ [
|
||
r"(?<=[0-9])\+",
|
||
r"(?<=°[FfCcKk])\.",
|
||
r"(?<=[0-9])(?:[{c}])".format(c=_currency),
|
||
r"(?<=[0-9])(?:{u})".format(u=UNITS),
|
||
r"(?<=[{al}{e}{q}(?:{c})])\.".format(
|
||
al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES, c=_currency
|
||
),
|
||
]
|
||
)
|
||
|
||
_infixes = (
|
||
LIST_ELLIPSES
|
||
+ LIST_ICONS
|
||
+ [
|
||
r"(?<=[0-9{zero}-{nine}])[+\-\*^=](?=[0-9{zero}-{nine}-])".format(
|
||
zero="০", nine="৯"
|
||
),
|
||
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}])({h})(?=[{ae}])".format(a=ALPHA, h=HYPHENS, ae="এ"),
|
||
r"(?<=[{a}])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
|
||
r"(?<=[{a}])[:<>=/](?=[{a}])".format(a=ALPHA),
|
||
]
|
||
)
|
||
|
||
|
||
TOKENIZER_PREFIXES = _prefixes
|
||
TOKENIZER_SUFFIXES = _suffixes
|
||
TOKENIZER_INFIXES = _infixes
|