spaCy/spacy/lang/el/punctuation.py
Ines Montani eddeb36c96
💫 Tidy up and auto-format .py files (#2983)
<!--- 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.
2018-11-30 17:03:03 +01:00

98 lines
3.3 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_CURRENCY
from ..char_classes import LIST_ICONS, ALPHA_LOWER, ALPHA_UPPER, ALPHA, HYPHENS
from ..char_classes import QUOTES, CURRENCY
_units = (
"km km² km³ m m² m³ dm dm² dm³ cm cm² cm³ mm mm² mm³ ha µm nm yd in ft "
"kg g mg µg t lb oz m/s km/h kmh mph hPa Pa mbar mb MB kb KB gb GB tb "
"TB T G M K км км² км³ м м² м³ дм дм² дм³ см см² см³ мм мм² мм³ нм "
"кг г мг м/с км/ч кПа Па мбар Кб КБ кб Мб МБ мб Гб ГБ гб Тб ТБ тб"
)
def merge_chars(char):
return char.strip().replace(" ", "|")
UNITS = merge_chars(_units)
_prefixes = (
[
"''",
"§",
"%",
"=",
r"\+[0-9]+%", # 90%
r"\'([0-9]){2}([\-]\'([0-9]){2})*", # '12'-13
r"\-([0-9]){1,9}\.([0-9]){1,9}", # -12.13
r"\'([Α-Ωα-ωίϊΐόάέύϋΰήώ]+)\'", # 'αβγ'
r"([Α-Ωα-ωίϊΐόάέύϋΰήώ]){1,3}\'", # αβγ'
r"http://www.[A-Za-z]+\-[A-Za-z]+(\.[A-Za-z]+)+(\/[A-Za-z]+)*(\.[A-Za-z]+)*",
r"[ΈΆΊΑ-Ωα-ωίϊΐόάέύϋΰήώ]+\*", # όνομα*
r"\$([0-9])+([\,\.]([0-9])+){0,1}",
]
+ LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_CURRENCY
+ LIST_ICONS
)
_suffixes = (
LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_ICONS
+ [
r"(?<=[0-9])\+", # 12+
r"([0-9])+\'", # 12'
r"([A-Za-z])?\'", # a'
r"^([0-9]){1,2}\.", # 12.
r" ([0-9]){1,2}\.", # 12.
r"([0-9]){1}\) ", # 12)
r"^([0-9]){1}\)$", # 12)
r"(?<=°[FfCcKk])\.",
r"([0-9])+\&", # 12&
r"(?<=[0-9])(?:{})".format(CURRENCY),
r"(?<=[0-9])(?:{})".format(UNITS),
r"(?<=[0-9{}{}(?:{})])\.".format(ALPHA_LOWER, r"²\-\)\]\+", QUOTES),
r"(?<=[{a}][{a}])\.".format(a=ALPHA_UPPER),
r"(?<=[Α-Ωα-ωίϊΐόάέύϋΰήώ])\-", # όνομα-
r"(?<=[Α-Ωα-ωίϊΐόάέύϋΰήώ])\.",
r"^[Α-Ω]{1}\.",
r"\ [Α-Ω]{1}\.",
# πρώτος-δεύτερος , πρώτος-δεύτερος-τρίτος
r"[ΈΆΊΑΌ-Ωα-ωίϊΐόάέύϋΰήώ]+([\-]([ΈΆΊΑΌ-Ωα-ωίϊΐόάέύϋΰήώ]+))+",
r"([0-9]+)mg", # 13mg
r"([0-9]+)\.([0-9]+)m", # 1.2m
]
)
_infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[0-9])[+\/\-\*^](?=[0-9])", # 1/2 , 1-2 , 1*2
r"([a-zA-Z]+)\/([a-zA-Z]+)\/([a-zA-Z]+)", # name1/name2/name3
r"([0-9])+(\.([0-9]+))*([\-]([0-9])+)+", # 10.9 , 10.9.9 , 10.9-6
r"([0-9])+[,]([0-9])+[\-]([0-9])+[,]([0-9])+", # 10,11,12
r"([0-9])+[ης]+([\-]([0-9])+)+", # 1ης-2
# 15/2 , 15/2/17 , 2017/2/15
r"([0-9]){1,4}[\/]([0-9]){1,2}([\/]([0-9]){0,4}){0,1}",
r"[A-Za-z]+\@[A-Za-z]+(\-[A-Za-z]+)*\.[A-Za-z]+", # abc@cde-fgh.a
r"([a-zA-Z]+)(\-([a-zA-Z]+))+", # abc-abc
r"(?<=[{}])\.(?=[{}])".format(ALPHA_LOWER, ALPHA_UPPER),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r'(?<=[{a}])[?";:=,.]*(?:{h})(?=[{a}])'.format(a=ALPHA, h=HYPHENS),
r'(?<=[{a}"])[:<>=/](?=[{a}])'.format(a=ALPHA),
]
)
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_INFIXES = _infixes