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]
19 lines
505 B
Python
19 lines
505 B
Python
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
|
|
from ..char_classes import UNITS, ALPHA_UPPER
|
|
|
|
_suffixes = (
|
|
LIST_PUNCT
|
|
+ LIST_ELLIPSES
|
|
+ LIST_QUOTES
|
|
+ [
|
|
r"(?<=[0-9])\+",
|
|
r"(?<=[0-9])%", # 4% -> ["4", "%"]
|
|
# Persian is written from Right-To-Left
|
|
r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
|
|
r"(?<=[0-9])(?:{u})".format(u=UNITS),
|
|
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
|
|
]
|
|
)
|
|
|
|
TOKENIZER_SUFFIXES = _suffixes
|