mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +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.
52 lines
1.3 KiB
Python
52 lines
1.3 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES
|
|
from ..char_classes import QUOTES, UNITS, ALPHA, ALPHA_LOWER, ALPHA_UPPER
|
|
|
|
LIST_ICONS = [r"[\p{So}--[°]]"]
|
|
|
|
_currency = r"\$|¢|£|€|¥|฿"
|
|
_quotes = QUOTES.replace("'", "")
|
|
|
|
_prefixes = (
|
|
[r"\+"]
|
|
+ LIST_PUNCT
|
|
+ LIST_ELLIPSES
|
|
+ LIST_QUOTES
|
|
+ LIST_ICONS
|
|
+ [r"[,.:](?=[{a}])".format(a=ALPHA)]
|
|
)
|
|
|
|
_suffixes = (
|
|
LIST_PUNCT
|
|
+ LIST_ELLIPSES
|
|
+ LIST_QUOTES
|
|
+ LIST_ICONS
|
|
+ [
|
|
r"(?<=[0-9])\+",
|
|
r"(?<=°[FfCcKk])\.",
|
|
r"(?<=[0-9])(?:{})".format(_currency),
|
|
r"(?<=[0-9])(?:{})".format(UNITS),
|
|
r"(?<=[{}{}{}(?:{})])\.".format(ALPHA_LOWER, r"%²\-\)\]\+", QUOTES, _currency),
|
|
r"(?<=[{})])-e".format(ALPHA_LOWER),
|
|
]
|
|
)
|
|
|
|
_infixes = (
|
|
LIST_ELLIPSES
|
|
+ LIST_ICONS
|
|
+ [
|
|
r"(?<=[{}])\.(?=[{}])".format(ALPHA_LOWER, ALPHA_UPPER),
|
|
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
|
|
r'(?<=[{a}"])[:<>=](?=[{a}])'.format(a=ALPHA),
|
|
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
|
|
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
|
|
r"(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])".format(a=ALPHA, q=_quotes),
|
|
]
|
|
)
|
|
|
|
TOKENIZER_PREFIXES = _prefixes
|
|
TOKENIZER_SUFFIXES = _suffixes
|
|
TOKENIZER_INFIXES = _infixes
|