mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 01:46:28 +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]
20 lines
607 B
Python
20 lines
607 B
Python
from ..char_classes import LIST_ELLIPSES, LIST_ICONS, ALPHA, ALPHA_LOWER, ALPHA_UPPER
|
||
|
||
ELISION = " ' ’ ".strip().replace(" ", "")
|
||
|
||
_infixes = (
|
||
LIST_ELLIPSES
|
||
+ LIST_ICONS
|
||
+ [
|
||
r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION),
|
||
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
|
||
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[0-9])-(?=[0-9])",
|
||
]
|
||
)
|
||
|
||
TOKENIZER_INFIXES = _infixes
|