spaCy/spacy/lang/vi/lex_attrs.py
Aviora 9a824255d3
Add examples and num_words for Vietnamese (#9412)
* add examples and num_words

* add contributor agreement

* Update spacy/lang/vi/examples.py

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* consistent format

add empty line at the end of file

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
2021-10-14 19:15:51 +02:00

40 lines
682 B
Python

from ...attrs import LIKE_NUM
_num_words = [
"không",
"một",
"hai",
"ba",
"bốn",
"năm",
"sáu",
"bảy",
"bẩy",
"tám",
"chín",
"mười",
"chục",
"trăm",
"nghìn",
"tỷ",
]
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}