mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +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]
55 lines
1.2 KiB
Python
55 lines
1.2 KiB
Python
from ...attrs import LIKE_NUM
|
|
|
|
_num_words = [
|
|
"సున్నా",
|
|
"శూన్యం",
|
|
"ఒకటి",
|
|
"రెండు",
|
|
"మూడు",
|
|
"నాలుగు",
|
|
"ఐదు",
|
|
"ఆరు",
|
|
"ఏడు",
|
|
"ఎనిమిది",
|
|
"తొమ్మిది",
|
|
"పది",
|
|
"పదకొండు",
|
|
"పన్నెండు",
|
|
"పదమూడు",
|
|
"పద్నాలుగు",
|
|
"పదిహేను",
|
|
"పదహారు",
|
|
"పదిహేడు",
|
|
"పద్దెనిమిది",
|
|
"పందొమ్మిది",
|
|
"ఇరవై",
|
|
"ముప్పై",
|
|
"నలభై",
|
|
"యాభై",
|
|
"అరవై",
|
|
"డెబ్బై",
|
|
"ఎనభై",
|
|
"తొంబై",
|
|
"వంద",
|
|
"నూరు",
|
|
"వెయ్యి",
|
|
"లక్ష",
|
|
"కోటి",
|
|
]
|
|
|
|
|
|
def like_num(text):
|
|
text = text.replace(",", "").replace(".", "")
|
|
if text.isdigit():
|
|
return True
|
|
if text.count("/") == 1:
|
|
num, denom = text.split("/")
|
|
if num.isdigit() and denom.isdigit():
|
|
return True
|
|
if text.lower() in _num_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|