mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +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.
61 lines
1.9 KiB
Python
61 lines
1.9 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ..punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
|
from ..char_classes import ALPHA, merge_chars, split_chars, _currency, _units
|
|
|
|
|
|
_units = (
|
|
_units + "s bit Gbps Mbps mbps Kbps kbps ƒ ppi px "
|
|
"Hz kHz MHz GHz mAh "
|
|
"ratus rb ribu ribuan "
|
|
"juta jt jutaan mill?iar million bil[l]?iun bilyun billion "
|
|
)
|
|
_currency = _currency + r" USD Rp IDR RMB SGD S\$"
|
|
_months = (
|
|
"Januari Februari Maret April Mei Juni Juli Agustus September "
|
|
"Oktober November Desember January February March May June "
|
|
"July August October December Jan Feb Mar Jun Jul Aug Sept "
|
|
"Oct Okt Nov Des "
|
|
)
|
|
|
|
|
|
UNITS = merge_chars(_units)
|
|
CURRENCY = merge_chars(_currency)
|
|
HTML_PREFIX = r"<(b|strong|i|em|p|span|div|br)\s?/>|<a([^>]+)>"
|
|
HTML_SUFFIX = r"</(b|strong|i|em|p|span|div|a)>"
|
|
MONTHS = merge_chars(_months)
|
|
LIST_CURRENCY = split_chars(_currency)
|
|
|
|
_prefixes = list(TOKENIZER_PREFIXES)
|
|
_prefixes.remove("#") # hashtag
|
|
_prefixes = _prefixes + LIST_CURRENCY + [HTML_PREFIX] + ["/", "—"]
|
|
|
|
_suffixes = (
|
|
TOKENIZER_SUFFIXES
|
|
+ [r"\-[Nn]ya", "-[KkMm]u", "[—-]"]
|
|
+ [
|
|
r"(?<={c})(?:[0-9]+)".format(c=CURRENCY),
|
|
r"(?<=[0-9])(?:{u})".format(u=UNITS),
|
|
r"(?<=[0-9])%",
|
|
r"(?<=[0-9{a}]{h})(?:[\.,:-])".format(a=ALPHA, h=HTML_SUFFIX),
|
|
r"(?<=[0-9{a}])(?:{h})".format(a=ALPHA, h=HTML_SUFFIX),
|
|
]
|
|
)
|
|
|
|
_infixes = TOKENIZER_INFIXES + [
|
|
r"(?<=[0-9])[\\/](?=[0-9%-])",
|
|
r"(?<=[0-9])%(?=[{a}0-9/])".format(a=ALPHA),
|
|
r"(?<={u})[\/-](?=[0-9])".format(u=UNITS),
|
|
r"(?<={m})[\/-](?=[0-9])".format(m=MONTHS),
|
|
r'(?<=[0-9\)][\.,])"(?=[0-9])',
|
|
r'(?<=[{a}\)][\.,\'])["—](?=[{a}])'.format(a=ALPHA),
|
|
r"(?<=[{a}])-(?=[0-9])".format(a=ALPHA),
|
|
r"(?<=[0-9])-(?=[{a}])".format(a=ALPHA),
|
|
r"(?<=[{a}])[\/-](?={c}{a})".format(a=ALPHA, c=CURRENCY),
|
|
]
|
|
|
|
TOKENIZER_PREFIXES = _prefixes
|
|
TOKENIZER_SUFFIXES = _suffixes
|
|
TOKENIZER_INFIXES = _infixes
|