mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +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.
40 lines
900 B
Python
40 lines
900 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
# fmt: off
|
|
consonants = ["b", "c", "d", "f", "g", "h", "j", "k", "l", "m", "n", "p", "q", "r", "s", "t", "v", "w", "x", "z"]
|
|
broad_vowels = ["a", "á", "o", "ó", "u", "ú"]
|
|
slender_vowels = ["e", "é", "i", "í"]
|
|
vowels = broad_vowels + slender_vowels
|
|
# fmt: on
|
|
|
|
|
|
def ends_dentals(word):
|
|
if word != "" and word[-1] in ["d", "n", "t", "s"]:
|
|
return True
|
|
else:
|
|
return False
|
|
|
|
|
|
def devoice(word):
|
|
if len(word) > 2 and word[-2] == "s" and word[-1] == "d":
|
|
return word[:-1] + "t"
|
|
else:
|
|
return word
|
|
|
|
|
|
def ends_with_vowel(word):
|
|
return word != "" and word[-1] in vowels
|
|
|
|
|
|
def starts_with_vowel(word):
|
|
return word != "" and word[0] in vowels
|
|
|
|
|
|
def deduplicate(word):
|
|
if len(word) > 2 and word[-2] == word[-1] and word[-1] in consonants:
|
|
return word[:-1]
|
|
else:
|
|
return word
|