mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +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.
71 lines
1.3 KiB
Python
71 lines
1.3 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import unicodedata
|
|
|
|
from .punctuation import LIST_CURRENCY
|
|
from ...attrs import IS_CURRENCY, LIKE_NUM
|
|
|
|
|
|
_num_words = [
|
|
"nol",
|
|
"satu",
|
|
"dua",
|
|
"tiga",
|
|
"empat",
|
|
"lima",
|
|
"enam",
|
|
"tujuh",
|
|
"delapan",
|
|
"sembilan",
|
|
"sepuluh",
|
|
"sebelas",
|
|
"belas",
|
|
"puluh",
|
|
"ratus",
|
|
"ribu",
|
|
"juta",
|
|
"miliar",
|
|
"biliun",
|
|
"triliun",
|
|
"kuadriliun",
|
|
"kuintiliun",
|
|
"sekstiliun",
|
|
"septiliun",
|
|
"oktiliun",
|
|
"noniliun",
|
|
"desiliun",
|
|
]
|
|
|
|
|
|
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
|
|
if text.count("-") == 1:
|
|
_, num = text.split("-")
|
|
if num.isdigit() or num in _num_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
def is_currency(text):
|
|
if text in LIST_CURRENCY:
|
|
return True
|
|
|
|
for char in text:
|
|
if unicodedata.category(char) != "Sc":
|
|
return False
|
|
return True
|
|
|
|
|
|
LEX_ATTRS = {IS_CURRENCY: is_currency, LIKE_NUM: like_num}
|