mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 03:19:13 +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]
62 lines
1.2 KiB
Python
62 lines
1.2 KiB
Python
from ...attrs import LIKE_NUM
|
|
|
|
_num_words = [
|
|
"බින්දුව",
|
|
"බිංදුව",
|
|
"එක",
|
|
"දෙක",
|
|
"තුන",
|
|
"හතර",
|
|
"පහ",
|
|
"හය",
|
|
"හත",
|
|
"අට",
|
|
"නවය",
|
|
"නමය",
|
|
"දහය",
|
|
"එකොළහ",
|
|
"දොළහ",
|
|
"දහතුන",
|
|
"දහහතර",
|
|
"දාහතර",
|
|
"පහළව",
|
|
"පහළොව",
|
|
"දහසය",
|
|
"දහහත",
|
|
"දාහත",
|
|
"දහඅට",
|
|
"දහනවය",
|
|
"විස්ස",
|
|
"තිහ",
|
|
"හතළිහ",
|
|
"පනහ",
|
|
"හැට",
|
|
"හැත්තෑව",
|
|
"අසූව",
|
|
"අනූව",
|
|
"සියය",
|
|
"දහස",
|
|
"දාහ",
|
|
"ලක්ෂය",
|
|
"මිලියනය",
|
|
"කෝටිය",
|
|
"බිලියනය",
|
|
"ට්රිලියනය",
|
|
]
|
|
|
|
|
|
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}
|