2018-06-19 08:17:53 +00:00
|
|
|
|
# coding: utf8
|
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
|
|
|
💫 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 16:03:03 +00:00
|
|
|
|
_num_words = [
|
|
|
|
|
|
"нуль",
|
|
|
|
|
|
"ноль",
|
|
|
|
|
|
"бер",
|
|
|
|
|
|
"ике",
|
|
|
|
|
|
"өч",
|
|
|
|
|
|
"дүрт",
|
|
|
|
|
|
"биш",
|
|
|
|
|
|
"алты",
|
|
|
|
|
|
"җиде",
|
|
|
|
|
|
"сигез",
|
|
|
|
|
|
"тугыз",
|
|
|
|
|
|
"ун",
|
|
|
|
|
|
"унбер",
|
|
|
|
|
|
"унике",
|
|
|
|
|
|
"унөч",
|
|
|
|
|
|
"ундүрт",
|
|
|
|
|
|
"унбиш",
|
|
|
|
|
|
"уналты",
|
|
|
|
|
|
"унҗиде",
|
|
|
|
|
|
"унсигез",
|
|
|
|
|
|
"унтугыз",
|
|
|
|
|
|
"егерме",
|
|
|
|
|
|
"утыз",
|
|
|
|
|
|
"кырык",
|
|
|
|
|
|
"илле",
|
|
|
|
|
|
"алтмыш",
|
|
|
|
|
|
"җитмеш",
|
|
|
|
|
|
"сиксән",
|
|
|
|
|
|
"туксан",
|
|
|
|
|
|
"йөз",
|
|
|
|
|
|
"мең",
|
|
|
|
|
|
"төмән",
|
|
|
|
|
|
"миллион",
|
|
|
|
|
|
"миллиард",
|
|
|
|
|
|
"триллион",
|
|
|
|
|
|
"триллиард",
|
|
|
|
|
|
]
|
2018-06-19 08:17:53 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def like_num(text):
|
💫 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 16:03:03 +00:00
|
|
|
|
if text.startswith(("+", "-", "±", "~")):
|
2018-10-01 08:49:14 +00:00
|
|
|
|
text = text[1:]
|
💫 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 16:03:03 +00:00
|
|
|
|
text = text.replace(",", "").replace(".", "")
|
2018-06-19 08:17:53 +00:00
|
|
|
|
if text.isdigit():
|
|
|
|
|
|
return True
|
💫 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 16:03:03 +00:00
|
|
|
|
if text.count("/") == 1:
|
|
|
|
|
|
num, denom = text.split("/")
|
2018-06-19 08:17:53 +00:00
|
|
|
|
if num.isdigit() and denom.isdigit():
|
|
|
|
|
|
return True
|
|
|
|
|
|
if text in _num_words:
|
|
|
|
|
|
return True
|
|
|
|
|
|
return False
|
|
|
|
|
|
|
|
|
|
|
|
|
💫 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 16:03:03 +00:00
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|