mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +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.
47 lines
1.4 KiB
Python
47 lines
1.4 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_num_words = set(
|
|
"""
|
|
nul een één twee drie vier vijf zes zeven acht negen tien elf twaalf dertien
|
|
veertien twintig dertig veertig vijftig zestig zeventig tachtig negentig honderd
|
|
duizend miljoen miljard biljoen biljard triljoen triljard
|
|
""".split()
|
|
)
|
|
|
|
_ordinal_words = set(
|
|
"""
|
|
eerste tweede derde vierde vijfde zesde zevende achtste negende tiende elfde
|
|
twaalfde dertiende veertiende twintigste dertigste veertigste vijftigste
|
|
zestigste zeventigste tachtigste negentigste honderdste duizendste miljoenste
|
|
miljardste biljoenste biljardste triljoenste triljardste
|
|
""".split()
|
|
)
|
|
|
|
|
|
def like_num(text):
|
|
# This only does the most basic check for whether a token is a digit
|
|
# or matches one of the number words. In order to handle numbers like
|
|
# "drieëntwintig", more work is required.
|
|
# See this discussion: https://github.com/explosion/spaCy/pull/1177
|
|
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.lower() in _ordinal_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|