mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
e626a011cc
* Enable lex_attrs on Finnish * Copy the Danish tokenizer rules to Finnish Specifically, don't break hyphenated compound words * Contributor agreement * A new file for Finnish tokenizer rules instead of including the Danish ones
60 lines
1.1 KiB
Python
60 lines
1.1 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_num_words = [
|
|
"nolla",
|
|
"yksi",
|
|
"kaksi",
|
|
"kolme",
|
|
"neljä",
|
|
"viisi",
|
|
"kuusi",
|
|
"seitsemän",
|
|
"kahdeksan",
|
|
"yhdeksän",
|
|
"kymmenen",
|
|
"yksitoista",
|
|
"kaksitoista",
|
|
"kolmetoista",
|
|
"neljätoista",
|
|
"viisitoista",
|
|
"kuusitoista",
|
|
"seitsemäntoista",
|
|
"kahdeksantoista",
|
|
"yhdeksäntoista",
|
|
"kaksikymmentä",
|
|
"kolmekymmentä",
|
|
"neljäkymmentä",
|
|
"viisikymmentä",
|
|
"kuusikymmentä",
|
|
"seitsemänkymmentä",
|
|
"kahdeksankymmentä",
|
|
"yhdeksänkymmentä",
|
|
"sata",
|
|
"tuhat",
|
|
"miljoona",
|
|
"miljardi",
|
|
"triljoona",
|
|
]
|
|
|
|
|
|
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}
|