mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 05:37:03 +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]
60 lines
1.4 KiB
Python
60 lines
1.4 KiB
Python
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_num_words = [
|
|
"ศูนย์",
|
|
"หนึ่ง",
|
|
"สอง",
|
|
"สาม",
|
|
"สี่",
|
|
"ห้า",
|
|
"หก",
|
|
"เจ็ด",
|
|
"แปด",
|
|
"เก้า",
|
|
"สิบ",
|
|
"สิบเอ็ด",
|
|
"ยี่สิบ",
|
|
"ยี่สิบเอ็ด",
|
|
"สามสิบ",
|
|
"สามสิบเอ็ด",
|
|
"สี่สิบ",
|
|
"สี่สิบเอ็ด",
|
|
"ห้าสิบ",
|
|
"ห้าสิบเอ็ด",
|
|
"หกสิบเอ็ด",
|
|
"เจ็ดสิบ",
|
|
"เจ็ดสิบเอ็ด",
|
|
"แปดสิบ",
|
|
"แปดสิบเอ็ด",
|
|
"เก้าสิบ",
|
|
"เก้าสิบเอ็ด",
|
|
"ร้อย",
|
|
"พัน",
|
|
"ล้าน",
|
|
"พันล้าน",
|
|
"หมื่นล้าน",
|
|
"แสนล้าน",
|
|
"ล้านล้าน",
|
|
"ล้านล้านล้าน",
|
|
"ล้านล้านล้านล้าน",
|
|
]
|
|
|
|
|
|
def like_num(text):
|
|
if text.startswith(("+", "-", "±", "~")):
|
|
text = text[1:]
|
|
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 in _num_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|