spaCy/spacy/lang/tr/lex_attrs.py

51 lines
863 B
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

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",
]
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.lower() in _num_words:
return True
return False
LEX_ATTRS = {LIKE_NUM: like_num}