mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-30 20:06:30 +03:00
eddeb36c96
<!--- Provide a general summary of your changes in the title. --> ## Description - [x] Use [`black`](https://github.com/ambv/black) to auto-format all `.py` files. - [x] Update flake8 config to exclude very large files (lemmatization tables etc.) - [x] Update code to be compatible with flake8 rules - [x] Fix various small bugs, inconsistencies and messy stuff in the language data - [x] Update docs to explain new code style (`black`, `flake8`, when to use `# fmt: off` and `# fmt: on` and what `# noqa` means) Once #2932 is merged, which auto-formats and tidies up the CLI, we'll be able to run `flake8 spacy` actually get meaningful results. At the moment, the code style and linting isn't applied automatically, but I'm hoping that the new [GitHub Actions](https://github.com/features/actions) will let us auto-format pull requests and post comments with relevant linting information. ### Types of change enhancement, code style ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
123 lines
2.0 KiB
Python
123 lines
2.0 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_num_words = [
|
|
"zero",
|
|
"um",
|
|
"dois",
|
|
"três",
|
|
"tres",
|
|
"quatro",
|
|
"cinco",
|
|
"seis",
|
|
"sete",
|
|
"oito",
|
|
"nove",
|
|
"dez",
|
|
"onze",
|
|
"doze",
|
|
"dúzia",
|
|
"dúzias",
|
|
"duzia",
|
|
"duzias",
|
|
"treze",
|
|
"catorze",
|
|
"quinze",
|
|
"dezasseis",
|
|
"dezassete",
|
|
"dezoito",
|
|
"dezanove",
|
|
"vinte",
|
|
"trinta",
|
|
"quarenta",
|
|
"cinquenta",
|
|
"sessenta",
|
|
"setenta",
|
|
"oitenta",
|
|
"noventa",
|
|
"cem",
|
|
"cento",
|
|
"duzentos",
|
|
"trezentos",
|
|
"quatrocentos",
|
|
"quinhentos",
|
|
"seicentos",
|
|
"setecentos",
|
|
"oitocentos",
|
|
"novecentos",
|
|
"mil",
|
|
"milhão",
|
|
"milhao",
|
|
"milhões",
|
|
"milhoes",
|
|
"bilhão",
|
|
"bilhao",
|
|
"bilhões",
|
|
"bilhoes",
|
|
"trilhão",
|
|
"trilhao",
|
|
"trilhões",
|
|
"trilhoes",
|
|
"quadrilhão",
|
|
"quadrilhao",
|
|
"quadrilhões",
|
|
"quadrilhoes",
|
|
]
|
|
|
|
|
|
_ordinal_words = [
|
|
"primeiro",
|
|
"segundo",
|
|
"terceiro",
|
|
"quarto",
|
|
"quinto",
|
|
"sexto",
|
|
"sétimo",
|
|
"oitavo",
|
|
"nono",
|
|
"décimo",
|
|
"vigésimo",
|
|
"trigésimo",
|
|
"quadragésimo",
|
|
"quinquagésimo",
|
|
"sexagésimo",
|
|
"septuagésimo",
|
|
"octogésimo",
|
|
"nonagésimo",
|
|
"centésimo",
|
|
"ducentésimo",
|
|
"trecentésimo",
|
|
"quadringentésimo",
|
|
"quingentésimo",
|
|
"sexcentésimo",
|
|
"septingentésimo",
|
|
"octingentésimo",
|
|
"nongentésimo",
|
|
"milésimo",
|
|
"milionésimo",
|
|
"bilionésimo",
|
|
]
|
|
|
|
|
|
def like_num(text):
|
|
if text.startswith(("+", "-", "±", "~")):
|
|
text = text[1:]
|
|
text = text.replace(",", "").replace(".", "").replace("º", "").replace("ª", "")
|
|
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
|
|
if text.lower() in _ordinal_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|