You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

89 lines
1.6 KiB

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

from ...attrs import LIKE_NUM
# Thirteen, fifteen etc. are written separate: on üç
_num_words = [
"bir",
"iki",
"üç",
"dört",
"beş",
"altı",
"yedi",
"sekiz",
"dokuz",
"on",
"yirmi",
"otuz",
"kırk",
"elli",
"altmış",
"yetmiş",
"seksen",
"doksan",
"yüz",
"bin",
"milyon",
"milyar",
"trilyon",
"katrilyon",
"kentilyon",
]
_ordinal_words = [
"birinci",
"ikinci",
"üçüncü",
"dördüncü",
"beşinci",
"altıncı",
"yedinci",
"sekizinci",
"dokuzuncu",
"onuncu",
"yirminci",
"otuzuncu",
"kırkıncı",
"ellinci",
"altmışıncı",
"yetmişinci",
"sekseninci",
"doksanıncı",
"yüzüncü",
"bininci",
"milyonuncu",
"milyarıncı",
"trilyonuncu",
"katrilyonuncu",
"kentilyonuncu",
]
_ordinal_endings = ("inci", "ıncı", "nci", "ncı", "uncu", "üncü")
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
text_lower = text.lower()
# Check cardinal number
if text_lower in _num_words:
return True
# Check ordinal number
if text_lower in _ordinal_words:
return True
if text_lower.endswith(_ordinal_endings):
if text_lower[:-3].isdigit() or text_lower[:-4].isdigit():
return True
return False
LEX_ATTRS = {LIKE_NUM: like_num}