2018-07-10 14:48:38 +03:00
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
2018-07-18 19:51:38 +03:00
|
|
|
|
from .tag_map_general import TAG_MAP
|
2018-07-10 14:48:38 +03:00
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
|
from .lex_attrs import LEX_ATTRS
|
2018-07-18 19:51:38 +03:00
|
|
|
|
from .lemmatizer import LEMMA_RULES, LEMMA_INDEX, LEMMA_EXC
|
2018-08-14 03:31:32 +03:00
|
|
|
|
from .lemmatizer.lemmatizer import GreekLemmatizer
|
|
|
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
2018-07-10 14:48:38 +03:00
|
|
|
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
2018-07-18 19:51:38 +03:00
|
|
|
|
from .norm_exceptions import NORM_EXCEPTIONS
|
2018-07-10 14:48:38 +03:00
|
|
|
|
from ..norm_exceptions import BASE_NORMS
|
|
|
|
|
from ...language import Language
|
|
|
|
|
from ...attrs import LANG, NORM
|
|
|
|
|
from ...util import update_exc, add_lookups
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class GreekDefaults(Language.Defaults):
|
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
|
lex_attr_getters.update(LEX_ATTRS)
|
💫 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 19:03:03 +03:00
|
|
|
|
lex_attr_getters[LANG] = lambda text: "el" # ISO code
|
2018-08-14 03:31:32 +03:00
|
|
|
|
lex_attr_getters[NORM] = add_lookups(
|
💫 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 19:03:03 +03:00
|
|
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS, NORM_EXCEPTIONS
|
|
|
|
|
)
|
2018-07-10 14:48:38 +03:00
|
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
|
|
|
stop_words = STOP_WORDS
|
|
|
|
|
tag_map = TAG_MAP
|
|
|
|
|
prefixes = TOKENIZER_PREFIXES
|
|
|
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
|
|
|
infixes = TOKENIZER_INFIXES
|
2018-08-14 03:31:32 +03:00
|
|
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
|
def create_lemmatizer(cls, nlp=None):
|
|
|
|
|
lemma_rules = LEMMA_RULES
|
|
|
|
|
lemma_index = LEMMA_INDEX
|
|
|
|
|
lemma_exc = LEMMA_EXC
|
💫 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 19:03:03 +03:00
|
|
|
|
return GreekLemmatizer(
|
|
|
|
|
index=lemma_index, exceptions=lemma_exc, rules=lemma_rules
|
|
|
|
|
)
|
2018-07-10 14:48:38 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class Greek(Language):
|
|
|
|
|
|
💫 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 19:03:03 +03:00
|
|
|
|
lang = "el" # ISO code
|
2018-07-10 14:48:38 +03:00
|
|
|
|
Defaults = GreekDefaults # set Defaults to custom language defaults
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# set default export – this allows the language class to be lazy-loaded
|
💫 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 19:03:03 +03:00
|
|
|
|
__all__ = ["Greek"]
|