Import Upstream version 1.4.0
This commit is contained in:
su-fang
commit
f531b4c05c
|
|
@ -0,0 +1,28 @@
|
|||
[flake8]
|
||||
min_python_version = 3.7.0
|
||||
max-line-length = 88
|
||||
ban-relative-imports = True
|
||||
# flake8-use-fstring: https://github.com/MichaelKim0407/flake8-use-fstring#--percent-greedy-and---format-greedy
|
||||
format-greedy = 1
|
||||
inline-quotes = double
|
||||
enable-extensions = TC, TC1
|
||||
type-checking-strict = true
|
||||
eradicate-whitelist-extend = ^-.*;
|
||||
extend-ignore =
|
||||
# E203: Whitespace before ':' (pycqa/pycodestyle#373)
|
||||
E203,
|
||||
# E501: Line too long
|
||||
E501,
|
||||
# SIM106: Handle error-cases first
|
||||
SIM106,
|
||||
# ANN101: Missing type annotation for self in method
|
||||
ANN101,
|
||||
# ANN102: Missing type annotation for cls in classmethod
|
||||
ANN102,
|
||||
per-file-ignores =
|
||||
tests/test_*:ANN201
|
||||
tests/**/test_*:ANN201
|
||||
extend-exclude =
|
||||
src/poetry/core/_vendor/*
|
||||
tests/fixtures/*
|
||||
tests/**/fixtures/*
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
poetry.lock linguist-generated=true
|
||||
vendors/poetry.lock linguist-generated=true
|
||||
poetry/core/_vendor/** linguist-generated=true
|
||||
poetry/core/_vendor/vendor.txt linguist-generated=false
|
||||
|
|
@ -0,0 +1,12 @@
|
|||
# Ref: https://help.github.com/en/github/building-a-strong-community/configuring-issue-templates-for-your-repository#configuring-the-template-chooser
|
||||
blank_issues_enabled: false
|
||||
contact_links:
|
||||
- name: '✏️ Poetry Issue Tracker'
|
||||
url: https://github.com/python-poetry/poetry/issues/new/choose
|
||||
about: |
|
||||
Submit your issues to the Poetry issue tracker. Bug reports and feature requests
|
||||
will be tracked there.
|
||||
- name: '💬 Discord Server'
|
||||
url: https://discordapp.com/invite/awxPgve
|
||||
about: |
|
||||
Chat with the community, ask questions and learn about best practices.
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
Resolves: python-poetry#<!-- add issue number/link here -->
|
||||
|
||||
<!-- This is just a reminder about the most common mistakes. Please make sure that you tick all *appropriate* boxes. But please read our [contribution guide](https://python-poetry.org/docs/contributing/) at least once, it will save you unnecessary review cycles! -->
|
||||
|
||||
- [ ] Added **tests** for changed code.
|
||||
- [ ] Updated **documentation** for changed code.
|
||||
|
||||
<!--
|
||||
**Note**: If your Pull Request introduces a new feature or changes the current behavior, it should be based
|
||||
on the `develop` branch. If it's a bug fix or only a documentation update, it should be based on the `master` branch.
|
||||
|
||||
If you have *any* questions to *any* of the points above, just **submit and ask**! This checklist is here to *help* you, not to deter you from contributing!
|
||||
-->
|
||||
|
|
@ -0,0 +1,76 @@
|
|||
name: Poetry Downstream Tests
|
||||
|
||||
on:
|
||||
pull_request: {}
|
||||
push:
|
||||
branches: [main]
|
||||
|
||||
jobs:
|
||||
Tests:
|
||||
name: ${{ matrix.ref }}
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
matrix:
|
||||
ref: ["master", "1.2"]
|
||||
fail-fast: false
|
||||
defaults:
|
||||
run:
|
||||
shell: bash
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
with:
|
||||
path: poetry-core
|
||||
|
||||
- uses: actions/checkout@v3
|
||||
with:
|
||||
path: poetry
|
||||
repository: python-poetry/poetry
|
||||
ref: ${{ matrix.ref }}
|
||||
|
||||
- name: Set up Python 3.10
|
||||
uses: actions/setup-python@v3
|
||||
with:
|
||||
python-version: "3.10"
|
||||
|
||||
- name: Get full python version
|
||||
id: full-python-version
|
||||
run: echo ::set-output name=version::$(python -c "import sys; print('-'.join(str(v) for v in sys.version_info))")
|
||||
|
||||
- name: Set up Poetry
|
||||
run: |
|
||||
pip install poetry
|
||||
poetry config virtualenvs.in-project true
|
||||
|
||||
- name: Set up cache
|
||||
uses: actions/cache@v3
|
||||
id: cache
|
||||
with:
|
||||
path: ./poetry/.venv
|
||||
key: venv-${{ steps.full-python-version.outputs.version }}-${{ hashFiles('**/poetry.lock') }}
|
||||
|
||||
- name: Ensure cache is healthy
|
||||
if: steps.cache.outputs.cache-hit == 'true'
|
||||
working-directory: ./poetry
|
||||
run: timeout 10s poetry run pip --version >/dev/null 2>&1 || rm -rf .venv
|
||||
|
||||
- name: Switch downstream to development poetry-core
|
||||
working-directory: ./poetry
|
||||
run: |
|
||||
# remove poetry-core from main group to avoid version conflicts
|
||||
# with a potential entry in the test group
|
||||
poetry remove poetry-core
|
||||
# add to test group to overwrite a potential entry in that group
|
||||
poetry add --lock --group test ../poetry-core
|
||||
|
||||
- name: Install downstream dependencies
|
||||
working-directory: ./poetry
|
||||
run: |
|
||||
# force update of directory dependency in cached venv
|
||||
# (even if directory dependency with same version is already installed)
|
||||
poetry run pip uninstall -y poetry-core
|
||||
poetry install
|
||||
|
||||
# TODO: mark run as success even when this fails and add comment to PR instead
|
||||
- name: Run downstream test suite
|
||||
working-directory: ./poetry
|
||||
run: poetry run pytest
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
name: Integration
|
||||
|
||||
on:
|
||||
pull_request: {}
|
||||
push:
|
||||
branches: [main]
|
||||
|
||||
jobs:
|
||||
Tests:
|
||||
name: ${{ matrix.os }} / ${{ matrix.python-version }}
|
||||
runs-on: "${{ matrix.os }}-latest"
|
||||
strategy:
|
||||
matrix:
|
||||
os: [Ubuntu, MacOS, Windows]
|
||||
python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
|
||||
fail-fast: false
|
||||
defaults:
|
||||
run:
|
||||
shell: bash
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v3
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Install tox
|
||||
run: pip install --upgrade tox
|
||||
|
||||
- name: Execute integration tests
|
||||
run: tox -e integration
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
name: Release
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- '*.*.*'
|
||||
|
||||
jobs:
|
||||
Release:
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v3
|
||||
|
||||
- name: Get tag
|
||||
id: tag
|
||||
run: echo ::set-output name=tag::${GITHUB_REF#refs/tags/}
|
||||
|
||||
- name: Set up Python 3.9
|
||||
uses: actions/setup-python@v3
|
||||
with:
|
||||
python-version: "3.9"
|
||||
|
||||
- name: Install Poetry
|
||||
run: |
|
||||
curl -sSL https://install.python-poetry.org | python - -y
|
||||
|
||||
- name: Update PATH
|
||||
run: echo "$HOME/.local/bin" >> $GITHUB_PATH
|
||||
|
||||
- name: Build project for distribution
|
||||
run: poetry build
|
||||
|
||||
- name: Check Version
|
||||
id: check-version
|
||||
run: |
|
||||
[[ "$(poetry version --short)" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]] \
|
||||
|| echo ::set-output name=prerelease::true
|
||||
|
||||
- name: Create Release
|
||||
uses: ncipollo/release-action@v1
|
||||
with:
|
||||
artifacts: "dist/*"
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
draft: false
|
||||
prerelease: steps.check-version.outputs.prerelease == 'true'
|
||||
|
||||
- name: Publish to PyPI
|
||||
env:
|
||||
POETRY_PYPI_TOKEN_PYPI: ${{ secrets.PYPI_TOKEN }}
|
||||
run: poetry publish
|
||||
|
|
@ -0,0 +1,72 @@
|
|||
name: Tests
|
||||
|
||||
on:
|
||||
pull_request: {}
|
||||
push:
|
||||
branches: [main]
|
||||
|
||||
jobs:
|
||||
tests:
|
||||
name: ${{ matrix.os }} / ${{ matrix.python-version }}
|
||||
runs-on: "${{ matrix.os }}-latest"
|
||||
strategy:
|
||||
matrix:
|
||||
os: [Ubuntu, MacOS, Windows]
|
||||
python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
|
||||
include:
|
||||
- os: Ubuntu
|
||||
python-version: pypy-3.8
|
||||
fail-fast: false
|
||||
defaults:
|
||||
run:
|
||||
shell: bash
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v3
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Get full Python version
|
||||
id: full-python-version
|
||||
run: echo ::set-output name=version::$(python -c "import sys; print('-'.join(str(v) for v in sys.version_info))")
|
||||
|
||||
- name: Bootstrap poetry
|
||||
run: |
|
||||
curl -sSL https://install.python-poetry.org | python - -y
|
||||
|
||||
- name: Update PATH
|
||||
if: ${{ matrix.os != 'Windows' }}
|
||||
run: echo "$HOME/.local/bin" >> $GITHUB_PATH
|
||||
|
||||
- name: Update Path for Windows
|
||||
if: ${{ matrix.os == 'Windows' }}
|
||||
run: echo "$APPDATA\Python\Scripts" >> $GITHUB_PATH
|
||||
|
||||
- name: Configure poetry
|
||||
run: poetry config virtualenvs.in-project true
|
||||
|
||||
- name: Set up cache
|
||||
uses: actions/cache@v3
|
||||
id: cache
|
||||
with:
|
||||
path: .venv
|
||||
key: venv-${{ runner.os }}-${{ steps.full-python-version.outputs.version }}-${{ hashFiles('**/poetry.lock') }}
|
||||
|
||||
- name: Ensure cache is healthy
|
||||
if: steps.cache.outputs.cache-hit == 'true'
|
||||
run: |
|
||||
# `timeout` is not available on macOS, so we define a custom function.
|
||||
[ "$(command -v timeout)" ] || function timeout() { perl -e 'alarm shift; exec @ARGV' "$@"; }
|
||||
# Using `timeout` is a safeguard against the Poetry command hanging for some reason.
|
||||
timeout 10s poetry run pip --version || rm -rf .venv
|
||||
|
||||
- name: Install dependencies
|
||||
run: poetry install
|
||||
|
||||
- name: Run pytest
|
||||
run: poetry run python -m pytest -p no:sugar -q tests/
|
||||
|
||||
- name: Run mypy
|
||||
run: poetry run mypy
|
||||
|
|
@ -0,0 +1,41 @@
|
|||
*.pyc
|
||||
|
||||
# Packages
|
||||
*.egg
|
||||
!/tests/**/*.egg
|
||||
/*.egg-info
|
||||
/tests/fixtures/**/*.egg-info
|
||||
/dist/*
|
||||
build
|
||||
_build
|
||||
.cache
|
||||
*.so
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
.coverage
|
||||
.tox
|
||||
.pytest_cache
|
||||
|
||||
.DS_Store
|
||||
.idea/*
|
||||
.python-version
|
||||
.vscode/*
|
||||
|
||||
/test.py
|
||||
/test_*.*
|
||||
|
||||
/setup.cfg
|
||||
MANIFEST.in
|
||||
/setup.py
|
||||
/docs/site/*
|
||||
/tests/fixtures/simple_project/setup.py
|
||||
/tests/fixtures/project_with_extras/setup.py
|
||||
.mypy_cache
|
||||
|
||||
.venv
|
||||
/releases/*
|
||||
pip-wheel-metadata
|
||||
/poetry.toml
|
||||
|
|
@ -0,0 +1,87 @@
|
|||
exclude: |
|
||||
(?x)(
|
||||
^tests/.*/fixtures/.*
|
||||
| ^src/poetry/core/_vendor
|
||||
)
|
||||
|
||||
repos:
|
||||
- repo: https://github.com/pre-commit/pre-commit-hooks
|
||||
rev: v4.3.0
|
||||
hooks:
|
||||
- id: trailing-whitespace
|
||||
exclude: "vendors/patches/jsonschema.patch"
|
||||
- id: end-of-file-fixer
|
||||
- id: debug-statements
|
||||
- id: check-merge-conflict
|
||||
- id: check-case-conflict
|
||||
- id: check-json
|
||||
- id: check-toml
|
||||
- id: check-yaml
|
||||
- id: pretty-format-json
|
||||
args:
|
||||
- --autofix
|
||||
- --no-ensure-ascii
|
||||
- --no-sort-keys
|
||||
- id: check-ast
|
||||
- id: debug-statements
|
||||
- id: check-docstring-first
|
||||
|
||||
- repo: https://github.com/pre-commit/pygrep-hooks
|
||||
rev: v1.9.0
|
||||
hooks:
|
||||
- id: python-check-mock-methods
|
||||
- id: python-use-type-annotations
|
||||
- id: python-check-blanket-noqa
|
||||
|
||||
- repo: https://github.com/asottile/yesqa
|
||||
rev: v1.4.0
|
||||
hooks:
|
||||
- id: yesqa
|
||||
additional_dependencies: &flake8_deps
|
||||
- flake8-annotations==2.9.0
|
||||
- flake8-broken-line==0.5.0
|
||||
- flake8-bugbear==22.7.1
|
||||
- flake8-comprehensions==3.10.0
|
||||
- flake8-eradicate==1.3.0
|
||||
- flake8-quotes==3.3.1
|
||||
- flake8-simplify==0.19.3
|
||||
- flake8-tidy-imports==4.8.0
|
||||
- flake8-type-checking==2.2.0
|
||||
- flake8-typing-imports==1.12.0
|
||||
- flake8-use-fstring==1.4
|
||||
- pep8-naming==0.13.1
|
||||
|
||||
- repo: https://github.com/asottile/pyupgrade
|
||||
rev: v3.2.2
|
||||
hooks:
|
||||
- id: pyupgrade
|
||||
args:
|
||||
- --py37-plus
|
||||
|
||||
- repo: https://github.com/hadialqattan/pycln
|
||||
rev: v2.1.2
|
||||
hooks:
|
||||
- id: pycln
|
||||
args: [--all]
|
||||
|
||||
- repo: https://github.com/pycqa/isort
|
||||
rev: 5.10.1
|
||||
hooks:
|
||||
- id: isort
|
||||
args: [--add-import, from __future__ import annotations]
|
||||
exclude: |
|
||||
(?x)(
|
||||
^.*/?setup\.py$
|
||||
| tests/.*\.pyi$
|
||||
)
|
||||
|
||||
- repo: https://github.com/psf/black
|
||||
rev: 22.10.0
|
||||
hooks:
|
||||
- id: black
|
||||
|
||||
- repo: https://github.com/pycqa/flake8
|
||||
rev: 5.0.4
|
||||
hooks:
|
||||
- id: flake8
|
||||
additional_dependencies: *flake8_deps
|
||||
|
|
@ -0,0 +1,476 @@
|
|||
# Change Log
|
||||
|
||||
## [1.4.0] - 2022-11-22
|
||||
|
||||
### Added
|
||||
|
||||
- The PEP 517 `metadata_directory` is now respected as an input to the `build_wheel` hook ([#487](https://github.com/python-poetry/poetry-core/pull/487)).
|
||||
|
||||
### Changed
|
||||
|
||||
- Sources are now considered more carefully when dealing with dependencies with environment markers ([#497](https://github.com/python-poetry/poetry-core/pull/497)).
|
||||
- `EmptyConstraint` is now hashable ([#513](https://github.com/python-poetry/poetry-core/pull/513)).
|
||||
- `ParseConstraintError` is now raised on version and constraint parsing errors, and includes information on the package that caused the error ([#514](https://github.com/python-poetry/poetry-core/pull/514)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fix an issue where invalid PEP 508 requirements were generated due to a missing space before semicolons ([#510](https://github.com/python-poetry/poetry-core/pull/510)).
|
||||
- Fix an issue where relative paths were encoded into package requirements, instead of a file:// URL as required by PEP 508 ([#512](https://github.com/python-poetry/poetry-core/pull/512)).
|
||||
|
||||
### Vendoring
|
||||
|
||||
- [`jsonschema==4.17.0`](https://github.com/python-jsonschema/jsonschema/blob/main/CHANGELOG.rst)
|
||||
- [`lark==1.1.14`](https://github.com/lark-parser/lark/releases/tag/1.1.4)
|
||||
- [`pyrsistent==0.19.2`](https://github.com/tobgu/pyrsistent/blob/master/CHANGES.txt)
|
||||
- [`tomlkit==0.11.6`](https://github.com/sdispater/tomlkit/blob/master/CHANGELOG.md)
|
||||
- [`typing-extensions==4.4.0`](https://github.com/python/typing_extensions/blob/main/CHANGELOG.md)
|
||||
|
||||
## [1.3.2] - 2022-10-07
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fix an issue where the normalization was not applied to the path of an sdist built using a PEP 517 frontend ([#495](https://github.com/python-poetry/poetry-core/pull/495)).
|
||||
|
||||
## [1.3.1] - 2022-10-05
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fix an issue where a typing-driven assertion could be false at runtime, causing a failure during prepare_metadata_for_build_wheel ([#492](https://github.com/python-poetry/poetry-core/pull/492)).
|
||||
|
||||
## [1.3.0] - 2022-10-05
|
||||
|
||||
### Added
|
||||
|
||||
- Add `3.11` to the list of available Python versions ([#477](https://github.com/python-poetry/poetry-core/pull/477)).
|
||||
|
||||
### Changed
|
||||
|
||||
- Deprecate `poetry.core.constraints.generic`, which is replaced by `poetry.core.packages.constraints` ([#482](https://github.com/python-poetry/poetry-core/pull/482)).
|
||||
- Deprecate `poetry.core.semver`, which is replaced by `poetry.core.constraints.version` ([#482](https://github.com/python-poetry/poetry-core/pull/482)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fix an issue where versions were escaped wrongly when building the wheel name ([#469](https://github.com/python-poetry/poetry-core/pull/469)).
|
||||
- Fix an issue where caret constraints of pre-releases with a major version of 0 resulted in an empty version range ([#475](https://github.com/python-poetry/poetry-core/pull/475)).
|
||||
- Fix an issue where the names of extras were not normalized according to PEP 685 ([#476](https://github.com/python-poetry/poetry-core/pull/476)).
|
||||
- Fix an issue where sdist names were not normalized ([#484](https://github.com/python-poetry/poetry-core/pull/484)).
|
||||
|
||||
|
||||
## [1.2.0] - 2022-09-13
|
||||
|
||||
### Added
|
||||
|
||||
- Added support for subdirectories in `url` dependencies ([#398](https://github.com/python-poetry/poetry-core/pull/398)).
|
||||
|
||||
### Changed
|
||||
|
||||
- When setting an invalid version constraint an error is raised instead of silently setting "any version" ([#461](https://github.com/python-poetry/poetry-core/pull/461)).
|
||||
- Allow more characters in author name ([#411](https://github.com/python-poetry/poetry-core/pull/411)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue where incorrect `Requires-Dist` information was generated when environment markers where used for optional packages ([#462](https://github.com/python-poetry/poetry-core/pull/462)).
|
||||
- Fixed an issue where incorrect python constraints were parsed from environment markers ([#457](https://github.com/python-poetry/poetry-core/pull/457)).
|
||||
- Fixed the hashing of markers and constraints ([#466](https://github.com/python-poetry/poetry-core/pull/466)).
|
||||
- Fixed an issue where the PEP 508 name of directory dependencies used platform paths ([#463](https://github.com/python-poetry/poetry-core/pull/463)).
|
||||
|
||||
|
||||
## [1.1.0] - 2022-08-31
|
||||
|
||||
- No functional changes.
|
||||
|
||||
|
||||
## [1.1.0rc3] - 2022-08-26
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue where a malformed URL was passed to pip when installing from a git subdirectory ([#451](https://github.com/python-poetry/poetry-core/pull/451)).
|
||||
|
||||
|
||||
## [1.1.0rc2] - 2022-08-26
|
||||
|
||||
### Changed
|
||||
|
||||
- Enabled setting `version` of `ProjectPackage` to support dynamically setting the project's package version (e.g. from a plugin) ([#447](https://github.com/python-poetry/poetry-core/pull/447)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue where `authors` property was not detected ([#437](https://github.com/python-poetry/poetry-core/pull/437)).
|
||||
- Fixed an issue where submodules of git dependencies was not checked out ([#439](https://github.com/python-poetry/poetry-core/pull/439)).
|
||||
- Fixed an issue with Python constraints from markers ([#448](https://github.com/python-poetry/poetry-core/pull/448)).
|
||||
- Fixed an issue where the latest version of git dependency was selected instead of the locked one ([#449](https://github.com/python-poetry/poetry-core/pull/449)).
|
||||
|
||||
|
||||
## [1.1.0rc1] - 2022-08-17
|
||||
|
||||
### Changed
|
||||
|
||||
- Replaced Poetry's helper method `canonicalize_name()` by `packaging.utils.canonicalize_name()` ([#418](https://github.com/python-poetry/poetry-core/pull/418)).
|
||||
- Removed unused code ([#419](https://github.com/python-poetry/poetry-core/pull/419)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue with markers, that results in incorrectly resolved extra dependencies ([#415](https://github.com/python-poetry/poetry-core/pull/415)).
|
||||
- Fixed an issue where equal markers had not the same hash ([#417](https://github.com/python-poetry/poetry-core/pull/417)).
|
||||
- Fixed `allows_any()` for local versions ([#433](https://github.com/python-poetry/poetry-core/pull/433)).
|
||||
- Fixed special cases of `next_major()`, `next_minor()`, etc. and deprecated ambiguous usage ([#434](https://github.com/python-poetry/poetry-core/pull/434)).
|
||||
- Fixed an issue with Python constraints from markers ([#436](https://github.com/python-poetry/poetry-core/pull/436)).
|
||||
|
||||
|
||||
## [1.1.0b3] - 2022-07-09
|
||||
|
||||
### Added
|
||||
|
||||
- Added support for valid PEP 517 projects with another build-system than poetry-core as directory dependencies ([#368](https://github.com/python-poetry/poetry-core/pull/368), [#377](https://github.com/python-poetry/poetry-core/pull/377)).
|
||||
- Added support for yanked files and releases according to PEP 592 ([#400](https://github.com/python-poetry/poetry-core/pull/400)).
|
||||
|
||||
### Changed
|
||||
|
||||
- Relaxed schema validation to allow additional properties ([#369](https://github.com/python-poetry/poetry-core/pull/369)).
|
||||
- Harmonized string representation of dependencies ([#393](https://github.com/python-poetry/poetry-core/pull/393)).
|
||||
- Changed wheel name normalization to follow most recent packaging specification ([#394](https://github.com/python-poetry/poetry-core/pull/394)).
|
||||
- Changed equality check of direct origin dependencies, so that constraints are not considered anymore ([#405](https://github.com/python-poetry/poetry-core/pull/405)).
|
||||
- Deprecated `Dependency.set_constraint()` and replaced it by a `constraint` property for consistency ([#370](https://github.com/python-poetry/poetry-core/pull/370)).
|
||||
- Removed `Package.requires_extras` ([#374](https://github.com/python-poetry/poetry-core/pull/374)).
|
||||
- Improved marker handling ([#380](https://github.com/python-poetry/poetry-core/pull/380),
|
||||
[#383](https://github.com/python-poetry/poetry-core/pull/383),
|
||||
[#384](https://github.com/python-poetry/poetry-core/pull/384),
|
||||
[#390](https://github.com/python-poetry/poetry-core/pull/390),
|
||||
[#395](https://github.com/python-poetry/poetry-core/pull/395)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed hash method for `PackageSpecification`, `Package`, `Dependency` and their sub classes ([#370](https://github.com/python-poetry/poetry-core/pull/370)).
|
||||
- Fixed merging of markers `python_version` and `python_full_version` ([#382](https://github.com/python-poetry/poetry-core/pull/382), [#388](https://github.com/python-poetry/poetry-core/pull/388)).
|
||||
- Fixed python version normalization ([#385](https://github.com/python-poetry/poetry-core/pull/385), [#407](https://github.com/python-poetry/poetry-core/pull/407)).
|
||||
- Fixed an issue where version identifiers with a local version segment allowed non local versions ([#396](https://github.com/python-poetry/poetry-core/pull/396)).
|
||||
- Fixed an issue where version identifiers without a post release segment allowed post releases ([#396](https://github.com/python-poetry/poetry-core/pull/396)).
|
||||
- Fixed script definitions that didn't work when extras were not explicitly defined ([#404](https://github.com/python-poetry/poetry-core/pull/404)).
|
||||
|
||||
|
||||
## [1.1.0b2] - 2022-05-24
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed a regression where `poetry-core` no longer handled improper Python version constraints from package metadata ([#371](https://github.com/python-poetry/poetry-core/pull/371))
|
||||
- Fixed missing version bump in `poetry.core.__version__` ([#367](https://github.com/python-poetry/poetry-core/pull/367))
|
||||
|
||||
### Improvements
|
||||
|
||||
- `poetry-core` generated wheel's now correctly identify `Generator` metadata as `poetry-core` instead of `poetry` ([#367](https://github.com/python-poetry/poetry-core/pull/367))
|
||||
|
||||
|
||||
## [1.1.0b1] - 2022-05-23
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue where canonicalize package names leads to infinite loops ([#328](https://github.com/python-poetry/poetry-core/pull/328)).
|
||||
- Fixed an issue where versions wasn't correct normalized to PEP-440 ([#344](https://github.com/python-poetry/poetry-core/pull/344)).
|
||||
- Fixed an issue with union of multi markers if one marker is a subset of the other marker ([#352](https://github.com/python-poetry/poetry-core/pull/352)).
|
||||
- Fixed an issue with markers which are not in disjunctive normal form (DNF) ([#347](https://github.com/python-poetry/poetry-core/pull/347)).
|
||||
- Fixed an issue where stub-only partial namespace packages were not recognized as packages ([#221](https://github.com/python-poetry/poetry-core/pull/221)).
|
||||
- Fixed an issue where PEP-508 url requirements with extras were not parsed correctly ([#345](https://github.com/python-poetry/poetry-core/pull/345)).
|
||||
- Fixed an issue where PEP-508 strings with wildcard exclusion constraints were incorrectly exported ([#343](https://github.com/python-poetry/poetry-core/pull/343)).
|
||||
- Allow hidden directories on Windows bare repos ([#341](https://github.com/python-poetry/poetry-core/pull/341)).
|
||||
- Fixed an issue where dependencies with an epoch are parsed as empty ([#316](https://github.com/python-poetry/poetry-core/pull/316)).
|
||||
- Fixed an issue where a package consisting of multiple packages wasn't build correctly ([#292](https://github.com/python-poetry/poetry-core/pull/292)).
|
||||
|
||||
### Added
|
||||
|
||||
- Added support for handling git urls with subdirectory ([#288](https://github.com/python-poetry/poetry-core/pull/288)).
|
||||
- Added support for metadata files as described in PEP-658 for PEP-503 "simple" API repositories ([#333](https://github.com/python-poetry/poetry-core/pull/333)).
|
||||
|
||||
### Changed
|
||||
|
||||
- Renamed dependency group of runtime dependencies to from `default` to `main` ([#326](https://github.com/python-poetry/poetry-core/pull/326)).
|
||||
|
||||
### Improvements
|
||||
|
||||
- `poetry-core` is now completely type checked.
|
||||
- Improved the SemVer constraint parsing ([#327](https://github.com/python-poetry/poetry-core/pull/327)).
|
||||
- Improved the speed when cloning git repositories ([#290](https://github.com/python-poetry/poetry-core/pull/290)).
|
||||
|
||||
|
||||
## [1.1.0a7] - 2022-03-05
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue when evaluate `in/not in` markers ([#188](https://github.com/python-poetry/poetry-core/pull/188)).
|
||||
- Fixed an issue when parsing of caret constraint with leading zero ([#201](https://github.com/python-poetry/poetry-core/pull/201)).
|
||||
- Respect format for explicit included files when finding excluded files ([#228](https://github.com/python-poetry/poetry-core/pull/228)).
|
||||
- Fixed an issue where only the last location was used when multiple packages should be included ([#108](https://github.com/python-poetry/poetry-core/pull/108)).
|
||||
- Ensure that package `description` contains no new line ([#219](https://github.com/python-poetry/poetry-core/pull/219)).
|
||||
- Fixed an issue where all default dependencies were removed instead of just the selected one ([#220](https://github.com/python-poetry/poetry-core/pull/220)).
|
||||
- Ensure that authors and maintainers are normalized ([#276](https://github.com/python-poetry/poetry-core/pull/276)).
|
||||
|
||||
### Added
|
||||
|
||||
- Add support for most of the guaranteed hashes ([#207](https://github.com/python-poetry/poetry-core/pull/207)).
|
||||
- Add support to declare multiple README files ([#248](https://github.com/python-poetry/poetry-core/pull/248)).
|
||||
- Add support for git sub directories ([#192](https://github.com/python-poetry/poetry-core/pull/192)).
|
||||
- Add hooks according to PEP-660 for editable installs ([#182](https://github.com/python-poetry/poetry-core/pull/182)).
|
||||
- Add support for version epochs ([#264](https://github.com/python-poetry/poetry-core/pull/264)).
|
||||
|
||||
### Changed
|
||||
|
||||
- Drop python3.6 support ([#263](https://github.com/python-poetry/poetry-core/pull/263)).
|
||||
- Loose the strictness when parsing version constraint to support invalid use of wildcards, e.g. `>=3.*` ([#186](https://github.com/python-poetry/poetry-core/pull/186)).
|
||||
- No longer assume a default git branch name ([#192](https://github.com/python-poetry/poetry-core/pull/192)).
|
||||
- Sort package name in extras to make it reproducible ([#280](https://github.com/python-poetry/poetry-core/pull/280)).
|
||||
|
||||
### Improvements
|
||||
|
||||
- Improve marker handling ([#208](https://github.com/python-poetry/poetry-core/pull/208),
|
||||
[#282](https://github.com/python-poetry/poetry-core/pull/282),
|
||||
[#283](https://github.com/python-poetry/poetry-core/pull/283),
|
||||
[#284](https://github.com/python-poetry/poetry-core/pull/284),
|
||||
[#286](https://github.com/python-poetry/poetry-core/pull/286),
|
||||
[#291](https://github.com/python-poetry/poetry-core/pull/291),
|
||||
[#293](https://github.com/python-poetry/poetry-core/pull/293),
|
||||
[#294](https://github.com/python-poetry/poetry-core/pull/294),
|
||||
[#297](https://github.com/python-poetry/poetry-core/pull/297)).
|
||||
|
||||
|
||||
## [1.1.0a6] - 2021-07-30
|
||||
|
||||
### Added
|
||||
|
||||
- Added support for dependency groups. ([#183](https://github.com/python-poetry/poetry-core/pull/183))
|
||||
|
||||
|
||||
## [1.1.0a5] - 2021-05-21
|
||||
|
||||
### Added
|
||||
|
||||
- Added support for script files in addition to standard entry points. ([#40](https://github.com/python-poetry/poetry-core/pull/40))
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an error in the way python markers with a precision >= 3 were handled. ([#178](https://github.com/python-poetry/poetry-core/pull/178))
|
||||
|
||||
|
||||
## [1.1.0a4] - 2021-04-30
|
||||
|
||||
### Changed
|
||||
|
||||
- Files in source distributions now have a deterministic time to improve reproducibility. ([#142](https://github.com/python-poetry/poetry-core/pull/142))
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an error where leading zeros in the local build part of version specifications were discarded. ([#167](https://github.com/python-poetry/poetry-core/pull/167))
|
||||
- Fixed the PEP 508 representation of file dependencies. ([#153](https://github.com/python-poetry/poetry-core/pull/153))
|
||||
- Fixed the copy of `Package` instances which led to file hashes not being available. ([#159](https://github.com/python-poetry/poetry-core/pull/159))
|
||||
- Fixed an error in the parsing of caret requirements with a pre-release lower bound. ([#171](https://github.com/python-poetry/poetry-core/pull/171))
|
||||
- Fixed an error where some pre-release versions were not flagged as pre-releases. ([#170](https://github.com/python-poetry/poetry-core/pull/170))
|
||||
|
||||
|
||||
## [1.1.0a3] - 2021-04-09
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed dependency markers not being properly copied when changing the constraint ([#162](https://github.com/python-poetry/poetry-core/pull/162)).
|
||||
|
||||
|
||||
## [1.1.0a2] - 2021-04-08
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed performance regressions when parsing version constraints ([#152](https://github.com/python-poetry/poetry-core/pull/152)).
|
||||
- Fixed how local build versions are handled and compared ([#157](https://github.com/python-poetry/poetry-core/pull/157), [#158](https://github.com/python-poetry/poetry-core/pull/158)).
|
||||
- Fixed errors when parsing some environment markers ([#155](https://github.com/python-poetry/poetry-core/pull/155)).
|
||||
|
||||
|
||||
## [1.1.0a1] - 2021-03-30
|
||||
|
||||
This version is the first to drop support for Python 2.7 and 3.5.
|
||||
|
||||
If you are still using these versions you should update the `requires` property of the `build-system` section
|
||||
to restrict the version of `poetry-core`:
|
||||
|
||||
```toml
|
||||
[build-system]
|
||||
requires = ["poetry-core<1.1.0"]
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
```
|
||||
|
||||
### Changed
|
||||
|
||||
- Dropped support for Python 2.7 and 3.5 ([#131](https://github.com/python-poetry/poetry-core/pull/131)).
|
||||
- Reorganized imports internally to improve performances ([#131](https://github.com/python-poetry/poetry-core/pull/131)).
|
||||
- Directory dependencies are now in non-develop mode by default ([#98](https://github.com/python-poetry/poetry-core/pull/98)).
|
||||
- Improved support for PEP 440 specific versions that do not abide by semantic versioning ([#140](https://github.com/python-poetry/poetry-core/pull/140)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed path dependencies PEP 508 representation ([#141](https://github.com/python-poetry/poetry-core/pull/141)).
|
||||
|
||||
|
||||
## [1.0.2] - 2021-02-05
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed a missing import causing an error in Poetry ([#134](https://github.com/python-poetry/poetry-core/pull/134)).
|
||||
|
||||
|
||||
## [1.0.1] - 2021-02-05
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed PEP 508 representation of dependency without extras ([#102](https://github.com/python-poetry/poetry-core/pull/102)).
|
||||
- Fixed an error where development dependencies were being resolved when invoking the PEP-517 backend ([#101](https://github.com/python-poetry/poetry-core/pull/101)).
|
||||
- Fixed source distribution not being deterministic ([#105](https://github.com/python-poetry/poetry-core/pull/105)).
|
||||
- Fixed an error where zip files were left open when building wheels ([#122](https://github.com/python-poetry/poetry-core/pull/122)).
|
||||
- Fixed an error where explicitly included files were still not present in final distributions ([#124](https://github.com/python-poetry/poetry-core/pull/124)).
|
||||
- Fixed wheel filename matching for recent architecture ([#125](https://github.com/python-poetry/poetry-core/pull/125), [#129](https://github.com/python-poetry/poetry-core/pull/129)).
|
||||
- Fixed an error where the `&` character was not accepted for author names ([#120](https://github.com/python-poetry/poetry-core/pull/120)).
|
||||
- Fixed the PEP-508 representation of some dependencies ([#103](https://github.com/python-poetry/poetry-core/pull/103)).
|
||||
- Fixed the `Requires-Python` metadata generation ([#127](https://github.com/python-poetry/poetry-core/pull/127)).
|
||||
- Fixed an error where pre-release versions were accepted in version constraints ([#128](https://github.com/python-poetry/poetry-core/pull/128)).
|
||||
|
||||
|
||||
## [1.0.0] - 2020-09-30
|
||||
|
||||
No changes.
|
||||
|
||||
|
||||
## [1.0.0rc3] - 2020-09-30
|
||||
|
||||
### Changed
|
||||
|
||||
- Removed `intreehooks` build backend in favor of the `backend-path` mechanism ([#90](https://github.com/python-poetry/poetry-core/pull/90)).
|
||||
- Directory dependencies will now always use a posix path for their representation ([#90](https://github.com/python-poetry/poetry-core/pull/91)).
|
||||
- Dependency constraints can now be set directly via a proper setter ([#90](https://github.com/python-poetry/poetry-core/pull/90)).
|
||||
|
||||
|
||||
## [1.0.0rc2] - 2020-09-25
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed `python_full_version` markers conversion to version constraints ([#86](https://github.com/python-poetry/core/pull/86)).
|
||||
|
||||
|
||||
## [1.0.0rc1] - 2020-09-25
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed Python constraint propagation when converting a package to a dependency ([#84](https://github.com/python-poetry/core/pull/84)).
|
||||
- Fixed VCS ignored files being included in wheel distributions for projects using the `src` layout ([#81](https://github.com/python-poetry/core/pull/81))
|
||||
|
||||
|
||||
## [1.0.0b1] - 2020-09-18
|
||||
|
||||
### Added
|
||||
|
||||
- Added support for build executable for wheels ([#72](https://github.com/python-poetry/core/pull/72)).
|
||||
|
||||
### Changed
|
||||
|
||||
- Improved packages with sources equality comparison ([#53](https://github.com/python-poetry/core/pull/53)).
|
||||
- Improved licenses handling and packaging in builders ([#57](https://github.com/python-poetry/core/pull/57)).
|
||||
- Refactored packages and dependencies classes to improve comparison between bare packages and packages with extras ([#78](https://github.com/python-poetry/core/pull/78)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed PEP-508 representation of URL dependencies ([#60](https://github.com/python-poetry/core/pull/60)).
|
||||
- Fixed generated `RECORD` files in some cases by ensuring it's a valid CSV file ([#61](https://github.com/python-poetry/core/pull/61)).
|
||||
- Fixed an error when parsing some version constraints if they contained wildcard elements ([#56](https://github.com/python-poetry/core/pull/56)).
|
||||
- Fixed errors when using the `exclude` property ([#62](https://github.com/python-poetry/core/pull/62)).
|
||||
- Fixed the way git revisions are retrieved ([#69](https://github.com/python-poetry/core/pull/69)).
|
||||
- Fixed dependency constraint PEP-508 compatibility when generating metadata ([#79](https://github.com/python-poetry/core/pull/79)).
|
||||
- Fixed potential errors on Python 3.5 when building with the `include` property set ([#75](https://github.com/python-poetry/core/pull/75)).
|
||||
|
||||
|
||||
## [1.0.0a9] - 2020-07-24
|
||||
|
||||
### Added
|
||||
|
||||
- Added support for build scripts without `setup.py` generation ([#45](https://github.com/python-poetry/core/pull/45)).
|
||||
|
||||
### Changed
|
||||
|
||||
- Improved the parsing of requirements and environment markers ([#44](https://github.com/python-poetry/core/pull/44)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed the default value used for the `build.generate-setup-file` settings ([#43](https://github.com/python-poetry/core/pull/43)).
|
||||
- Fixed error messages when the authors specified in the pyproject.toml file are invalid ([#49](https://github.com/python-poetry/core/pull/49)).
|
||||
- Fixed distributions build when using the PEP-517 backend for packages with includes ([#47](https://github.com/python-poetry/core/pull/47)).
|
||||
|
||||
|
||||
## [1.0.0a8] - 2020-06-26
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed errors in the way Python environment markers were parsed and generated ([#36](https://github.com/python-poetry/core/pull/36)).
|
||||
|
||||
|
||||
## [1.0.0a7] - 2020-05-06
|
||||
|
||||
### Added
|
||||
|
||||
- Added support for format-specific includes via the `include` property ([#6](https://github.com/python-poetry/core/pull/6)).
|
||||
|
||||
### Changed
|
||||
|
||||
- Allow url dependencies in multiple constraints dependencies ([#32](https://github.com/python-poetry/core/pull/32)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed PEP 508 representation and parsing of VCS dependencies ([#30](https://github.com/python-poetry/core/pull/30)).
|
||||
|
||||
|
||||
## [1.0.0a6] - 2020-04-24
|
||||
|
||||
### Added
|
||||
|
||||
- Added support for markers inverse ([#21](https://github.com/python-poetry/core/pull/21)).
|
||||
- Added support for specifying that `git` dependencies should be installed in develop mode ([#23](https://github.com/python-poetry/core/pull/23)).
|
||||
- Added the ability to specify build settings from the Poetry main configuration file ([#26](https://github.com/python-poetry/core/pull/26)).
|
||||
- Added the ability to disable the generation of the `setup.py` file when building ([#26](https://github.com/python-poetry/core/pull/26)).
|
||||
|
||||
### Changed
|
||||
|
||||
- Relaxed licence restrictions to support custom licences ([#5](https://github.com/python-poetry/core/pull/5)).
|
||||
- Improved support for PEP-440 direct references ([#22](https://github.com/python-poetry/core/pull/22)).
|
||||
- Improved dependency vendoring ([#25](https://github.com/python-poetry/core/pull/25)).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed the inability to make the url dependencies optional ([#13](https://github.com/python-poetry/core/pull/13)).
|
||||
- Fixed whitespaces in PEP-440 constraints causing an error ([#16](https://github.com/python-poetry/core/pull/16)).
|
||||
- Fixed subpackage check when generating the `setup.py` file ([#17](https://github.com/python-poetry/core/pull/17)).
|
||||
- Fix PEP-517 issues for projects using build scripts ([#12](https://github.com/python-poetry/core/pull/12)).
|
||||
- Fixed support for stub-only packages ([#28](https://github.com/python-poetry/core/pull/28)).
|
||||
|
||||
|
||||
[Unreleased]: https://github.com/python-poetry/poetry-core/compare/1.4.0...main
|
||||
[1.4.0]: https://github.com/python-poetry/poetry-core/releases/tag/1.4.0
|
||||
[1.3.2]: https://github.com/python-poetry/poetry-core/releases/tag/1.3.2
|
||||
[1.3.1]: https://github.com/python-poetry/poetry-core/releases/tag/1.3.1
|
||||
[1.3.0]: https://github.com/python-poetry/poetry-core/releases/tag/1.3.0
|
||||
[1.2.0]: https://github.com/python-poetry/poetry-core/releases/tag/1.2.0
|
||||
[1.1.0]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0
|
||||
[1.1.0rc3]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0rc3
|
||||
[1.1.0rc2]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0rc2
|
||||
[1.1.0rc1]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0rc1
|
||||
[1.1.0b3]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0b3
|
||||
[1.1.0b2]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0b2
|
||||
[1.1.0b1]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0b1
|
||||
[1.1.0a7]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0a7
|
||||
[1.1.0a6]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0a6
|
||||
[1.1.0a5]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0a5
|
||||
[1.1.0a4]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0a4
|
||||
[1.1.0a3]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0a3
|
||||
[1.1.0a2]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0a2
|
||||
[1.1.0a1]: https://github.com/python-poetry/poetry-core/releases/tag/1.1.0a1
|
||||
[1.0.2]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.2
|
||||
[1.0.1]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.1
|
||||
[1.0.0]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.0
|
||||
[1.0.0rc3]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.0rc3
|
||||
[1.0.0rc2]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.0rc2
|
||||
[1.0.0rc1]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.0rc1
|
||||
[1.0.0b1]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.0b1
|
||||
[1.0.0a9]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.0a9
|
||||
[1.0.0a8]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.0a8
|
||||
[1.0.0a7]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.0a7
|
||||
[1.0.0a6]: https://github.com/python-poetry/poetry-core/releases/tag/1.0.0a6
|
||||
|
|
@ -0,0 +1,20 @@
|
|||
Copyright (c) 2020 Sébastien Eustace
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining
|
||||
a copy of this software and associated documentation files (the
|
||||
"Software"), to deal in the Software without restriction, including
|
||||
without limitation the rights to use, copy, modify, merge, publish,
|
||||
distribute, sublicense, and/or sell copies of the Software, and to
|
||||
permit persons to whom the Software is furnished to do so, subject to
|
||||
the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be
|
||||
included in all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
||||
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
||||
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
||||
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
SHELL := $(shell which bash) -e
|
||||
MAKEFILE_PATH := $(abspath $(lastword $(MAKEFILE_LIST)))
|
||||
ROOT_DIR := $(patsubst %/,%,$(dir $(MAKEFILE_PATH)))
|
||||
|
||||
VENDOR_SRC := $(ROOT_DIR)/vendors
|
||||
VENDOR_DIR := $(ROOT_DIR)/src/poetry/core/_vendor
|
||||
VENDOR_TXT := $(VENDOR_DIR)/vendor.txt
|
||||
POETRY_BIN ?= $(shell which poetry)
|
||||
|
||||
.PHONY: vendor/lock
|
||||
vendor/lock: $(VENDOR_LOCK)
|
||||
# regenerate lock file
|
||||
@pushd $(VENDOR_SRC) && $(POETRY_BIN) lock --no-update
|
||||
|
||||
.PHONY: vendor/sync
|
||||
vendor/sync:
|
||||
# regenerate vendor.txt file (exported from lockfile)
|
||||
@pushd $(VENDOR_SRC) && $(POETRY_BIN) export --without-hashes 2> /dev/null \
|
||||
| grep -E -v "(importlib|zipp)" \
|
||||
| sort > $(VENDOR_TXT)
|
||||
|
||||
# vendor packages
|
||||
@$(POETRY_BIN) run vendoring sync
|
||||
|
||||
# strip out *.pyi stubs
|
||||
@find "$(VENDOR_DIR)" -type f -name "*.pyi" -exec rm {} \;
|
||||
|
||||
.PHONY: vendor/update
|
||||
vendor/update: | vendor/lock vendor/sync
|
||||
@:
|
||||
|
|
@ -0,0 +1,45 @@
|
|||
# Poetry Core
|
||||
[](https://pypi.org/project/poetry-core/)
|
||||
[](https://pypi.org/project/poetry-core/)
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
[](https://github.com/psf/black)
|
||||
[](https://github.com/python-poetry/poetry-core/actions?query=workflow%3ATests)
|
||||
|
||||
A [PEP 517](https://www.python.org/dev/peps/pep-0517/) build backend implementation developed for
|
||||
[Poetry](https://github.com/python-poetry/poetry). This project is intended to be a light weight, fully compliant,
|
||||
self-contained package allowing PEP 517 compatible build frontends to build Poetry managed projects.
|
||||
|
||||
## Usage
|
||||
In most cases, the usage of this package is transparent to the end-user as it is either made use by Poetry itself
|
||||
or a PEP 517 frontend (eg: `pip`).
|
||||
|
||||
In order to enable the use `poetry-core` as your build backend, the following snippet must be present in your
|
||||
project's `pyproject.toml` file.
|
||||
|
||||
```toml
|
||||
[build-system]
|
||||
requires = ["poetry-core"]
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
```
|
||||
|
||||
Once this is present, a PEP 517 frontend like `pip` can build and install your project from source without the need
|
||||
for Poetry or any of its dependencies.
|
||||
|
||||
```shell
|
||||
# install to current environment
|
||||
pip install /path/to/poetry/managed/project
|
||||
|
||||
# build a wheel package
|
||||
pip wheel /path/to/poetry/managed/project
|
||||
```
|
||||
|
||||
## Why is this required?
|
||||
Prior to the release of version `1.1.0`, Poetry was a project management tool that included a PEP 517
|
||||
build backend. This was inefficient and time consuming when a PEP 517 build was required. For example,
|
||||
both `pip` and `tox` (with isolated builds) would install Poetry and all dependencies it required. Most of these
|
||||
dependencies are not required when the objective is to simply build either a source or binary distribution of your
|
||||
project.
|
||||
|
||||
In order to improve the above situation, `poetry-core` was created. Shared functionality pertaining to PEP 517 build
|
||||
backends, including reading lock file, `pyproject.toml` and building wheel/sdist, were implemented in this package. This
|
||||
makes PEP 517 builds extremely fast for Poetry managed packages.
|
||||
|
|
@ -0,0 +1,917 @@
|
|||
[[package]]
|
||||
name = "atomicwrites"
|
||||
version = "1.4.0"
|
||||
description = "Atomic file writes."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
|
||||
|
||||
[[package]]
|
||||
name = "attrs"
|
||||
version = "21.4.0"
|
||||
description = "Classes Without Boilerplate"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
|
||||
|
||||
[package.extras]
|
||||
dev = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "furo", "sphinx", "sphinx-notfound-page", "pre-commit", "cloudpickle"]
|
||||
docs = ["furo", "sphinx", "zope.interface", "sphinx-notfound-page"]
|
||||
tests = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "cloudpickle"]
|
||||
tests_no_zope = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "cloudpickle"]
|
||||
|
||||
[[package]]
|
||||
name = "build"
|
||||
version = "0.7.0"
|
||||
description = "A simple, correct PEP517 package builder"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
|
||||
[package.dependencies]
|
||||
colorama = {version = "*", markers = "os_name == \"nt\""}
|
||||
importlib-metadata = {version = ">=0.22", markers = "python_version < \"3.8\""}
|
||||
packaging = ">=19.0"
|
||||
pep517 = ">=0.9.1"
|
||||
tomli = ">=1.0.0"
|
||||
|
||||
[package.extras]
|
||||
docs = ["furo (>=2020.11.19b18)", "sphinx (>=3.0,<4.0)", "sphinx-argparse-cli (>=1.5)", "sphinx-autodoc-typehints (>=1.10)"]
|
||||
test = ["filelock (>=3)", "pytest (>=6.2.4)", "pytest-cov (>=2)", "pytest-mock (>=2)", "pytest-rerunfailures (>=9.1)", "pytest-xdist (>=1.34)", "setuptools (>=42.0.0)", "toml (>=0.10.0)", "wheel (>=0.36.0)"]
|
||||
typing = ["importlib-metadata (>=4.6.4)", "mypy (==0.910)", "typing-extensions (>=3.7.4.3)"]
|
||||
virtualenv = ["virtualenv (>=20.0.35)"]
|
||||
|
||||
[[package]]
|
||||
name = "certifi"
|
||||
version = "2021.10.8"
|
||||
description = "Python package for providing Mozilla's CA Bundle."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
|
||||
[[package]]
|
||||
name = "cfgv"
|
||||
version = "3.3.1"
|
||||
description = "Validate configuration and produce human readable error messages."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6.1"
|
||||
|
||||
[[package]]
|
||||
name = "charset-normalizer"
|
||||
version = "2.0.12"
|
||||
description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.5.0"
|
||||
|
||||
[package.extras]
|
||||
unicode_backport = ["unicodedata2"]
|
||||
|
||||
[[package]]
|
||||
name = "click"
|
||||
version = "8.1.3"
|
||||
description = "Composable command line interface toolkit"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.dependencies]
|
||||
colorama = {version = "*", markers = "platform_system == \"Windows\""}
|
||||
importlib-metadata = {version = "*", markers = "python_version < \"3.8\""}
|
||||
|
||||
[[package]]
|
||||
name = "colorama"
|
||||
version = "0.4.4"
|
||||
description = "Cross-platform colored terminal text."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
|
||||
|
||||
[[package]]
|
||||
name = "commonmark"
|
||||
version = "0.9.1"
|
||||
description = "Python parser for the CommonMark Markdown spec"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
|
||||
[package.extras]
|
||||
test = ["flake8 (==3.7.8)", "hypothesis (==3.55.3)"]
|
||||
|
||||
[[package]]
|
||||
name = "coverage"
|
||||
version = "6.4"
|
||||
description = "Code coverage measurement for Python"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.dependencies]
|
||||
tomli = {version = "*", optional = true, markers = "python_version < \"3.11\" and extra == \"toml\""}
|
||||
|
||||
[package.extras]
|
||||
toml = ["tomli"]
|
||||
|
||||
[[package]]
|
||||
name = "distlib"
|
||||
version = "0.3.4"
|
||||
description = "Distribution utilities"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
|
||||
[[package]]
|
||||
name = "filelock"
|
||||
version = "3.7.0"
|
||||
description = "A platform independent file lock."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.extras]
|
||||
docs = ["furo (>=2021.8.17b43)", "sphinx (>=4.1)", "sphinx-autodoc-typehints (>=1.12)"]
|
||||
testing = ["covdefaults (>=1.2.0)", "coverage (>=4)", "pytest (>=4)", "pytest-cov", "pytest-timeout (>=1.4.2)"]
|
||||
|
||||
[[package]]
|
||||
name = "identify"
|
||||
version = "2.5.0"
|
||||
description = "File identification library for Python"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.extras]
|
||||
license = ["ukkonen"]
|
||||
|
||||
[[package]]
|
||||
name = "idna"
|
||||
version = "3.3"
|
||||
description = "Internationalized Domain Names in Applications (IDNA)"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.5"
|
||||
|
||||
[[package]]
|
||||
name = "importlib-metadata"
|
||||
version = "4.11.3"
|
||||
description = "Read metadata from Python packages"
|
||||
category = "main"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.dependencies]
|
||||
typing-extensions = {version = ">=3.6.4", markers = "python_version < \"3.8\""}
|
||||
zipp = ">=0.5"
|
||||
|
||||
[package.extras]
|
||||
docs = ["sphinx", "jaraco.packaging (>=9)", "rst.linker (>=1.9)"]
|
||||
perf = ["ipython"]
|
||||
testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.0.1)", "packaging", "pyfakefs", "flufl.flake8", "pytest-perf (>=0.9.2)", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)", "importlib-resources (>=1.3)"]
|
||||
|
||||
[[package]]
|
||||
name = "importlib-resources"
|
||||
version = "5.7.1"
|
||||
description = "Read resources from Python packages"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.dependencies]
|
||||
zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}
|
||||
|
||||
[package.extras]
|
||||
docs = ["sphinx", "jaraco.packaging (>=9)", "rst.linker (>=1.9)"]
|
||||
testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.0.1)", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)"]
|
||||
|
||||
[[package]]
|
||||
name = "iniconfig"
|
||||
version = "1.1.1"
|
||||
description = "iniconfig: brain-dead simple config-ini parsing"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
|
||||
[[package]]
|
||||
name = "jsonschema"
|
||||
version = "4.5.1"
|
||||
description = "An implementation of JSON Schema validation for Python"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.dependencies]
|
||||
attrs = ">=17.4.0"
|
||||
importlib-metadata = {version = "*", markers = "python_version < \"3.8\""}
|
||||
importlib-resources = {version = ">=1.4.0", markers = "python_version < \"3.9\""}
|
||||
pyrsistent = ">=0.14.0,<0.17.0 || >0.17.0,<0.17.1 || >0.17.1,<0.17.2 || >0.17.2"
|
||||
typing-extensions = {version = "*", markers = "python_version < \"3.8\""}
|
||||
|
||||
[package.extras]
|
||||
format = ["fqdn", "idna", "isoduration", "jsonpointer (>1.13)", "rfc3339-validator", "rfc3987", "uri-template", "webcolors (>=1.11)"]
|
||||
format_nongpl = ["fqdn", "idna", "isoduration", "jsonpointer (>1.13)", "rfc3339-validator", "rfc3986-validator (>0.1.0)", "uri-template", "webcolors (>=1.11)"]
|
||||
|
||||
[[package]]
|
||||
name = "mypy"
|
||||
version = "0.960"
|
||||
description = "Optional static typing for Python"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
|
||||
[package.dependencies]
|
||||
mypy-extensions = ">=0.4.3"
|
||||
tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
|
||||
typed-ast = {version = ">=1.4.0,<2", markers = "python_version < \"3.8\""}
|
||||
typing-extensions = ">=3.10"
|
||||
|
||||
[package.extras]
|
||||
dmypy = ["psutil (>=4.0)"]
|
||||
python2 = ["typed-ast (>=1.4.0,<2)"]
|
||||
reports = ["lxml"]
|
||||
|
||||
[[package]]
|
||||
name = "mypy-extensions"
|
||||
version = "0.4.3"
|
||||
description = "Experimental type system extensions for programs checked with the mypy typechecker."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
|
||||
[[package]]
|
||||
name = "nodeenv"
|
||||
version = "1.6.0"
|
||||
description = "Node.js virtual environment builder"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
|
||||
[[package]]
|
||||
name = "packaging"
|
||||
version = "21.3"
|
||||
description = "Core utilities for Python packages"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
|
||||
[package.dependencies]
|
||||
pyparsing = ">=2.0.2,<3.0.5 || >3.0.5"
|
||||
|
||||
[[package]]
|
||||
name = "pep517"
|
||||
version = "0.12.0"
|
||||
description = "Wrappers to build Python packages using PEP 517 hooks"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
|
||||
[package.dependencies]
|
||||
importlib_metadata = {version = "*", markers = "python_version < \"3.8\""}
|
||||
tomli = {version = ">=1.1.0", markers = "python_version >= \"3.6\""}
|
||||
zipp = {version = "*", markers = "python_version < \"3.8\""}
|
||||
|
||||
[[package]]
|
||||
name = "platformdirs"
|
||||
version = "2.5.2"
|
||||
description = "A small Python module for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.extras]
|
||||
docs = ["furo (>=2021.7.5b38)", "proselint (>=0.10.2)", "sphinx-autodoc-typehints (>=1.12)", "sphinx (>=4)"]
|
||||
test = ["appdirs (==1.4.4)", "pytest-cov (>=2.7)", "pytest-mock (>=3.6)", "pytest (>=6)"]
|
||||
|
||||
[[package]]
|
||||
name = "pluggy"
|
||||
version = "1.0.0"
|
||||
description = "plugin and hook calling mechanisms for python"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
|
||||
[package.dependencies]
|
||||
importlib-metadata = {version = ">=0.12", markers = "python_version < \"3.8\""}
|
||||
|
||||
[package.extras]
|
||||
dev = ["pre-commit", "tox"]
|
||||
testing = ["pytest", "pytest-benchmark"]
|
||||
|
||||
[[package]]
|
||||
name = "pre-commit"
|
||||
version = "2.19.0"
|
||||
description = "A framework for managing and maintaining multi-language pre-commit hooks."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.dependencies]
|
||||
cfgv = ">=2.0.0"
|
||||
identify = ">=1.0.0"
|
||||
importlib-metadata = {version = "*", markers = "python_version < \"3.8\""}
|
||||
nodeenv = ">=0.11.1"
|
||||
pyyaml = ">=5.1"
|
||||
toml = "*"
|
||||
virtualenv = ">=20.0.8"
|
||||
|
||||
[[package]]
|
||||
name = "py"
|
||||
version = "1.11.0"
|
||||
description = "library with cross-python path, ini-parsing, io, code, log facilities"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
|
||||
|
||||
[[package]]
|
||||
name = "pygments"
|
||||
version = "2.12.0"
|
||||
description = "Pygments is a syntax highlighting package written in Python."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
|
||||
[[package]]
|
||||
name = "pyparsing"
|
||||
version = "3.0.9"
|
||||
description = "pyparsing module - Classes and methods to define and execute parsing grammars"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6.8"
|
||||
|
||||
[package.extras]
|
||||
diagrams = ["railroad-diagrams", "jinja2"]
|
||||
|
||||
[[package]]
|
||||
name = "pyrsistent"
|
||||
version = "0.18.1"
|
||||
description = "Persistent/Functional/Immutable data structures"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[[package]]
|
||||
name = "pytest"
|
||||
version = "7.1.2"
|
||||
description = "pytest: simple powerful testing with Python"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.dependencies]
|
||||
atomicwrites = {version = ">=1.0", markers = "sys_platform == \"win32\""}
|
||||
attrs = ">=19.2.0"
|
||||
colorama = {version = "*", markers = "sys_platform == \"win32\""}
|
||||
importlib-metadata = {version = ">=0.12", markers = "python_version < \"3.8\""}
|
||||
iniconfig = "*"
|
||||
packaging = "*"
|
||||
pluggy = ">=0.12,<2.0"
|
||||
py = ">=1.8.2"
|
||||
tomli = ">=1.0.0"
|
||||
|
||||
[package.extras]
|
||||
testing = ["argcomplete", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "xmlschema"]
|
||||
|
||||
[[package]]
|
||||
name = "pytest-cov"
|
||||
version = "3.0.0"
|
||||
description = "Pytest plugin for measuring coverage."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
|
||||
[package.dependencies]
|
||||
coverage = {version = ">=5.2.1", extras = ["toml"]}
|
||||
pytest = ">=4.6"
|
||||
|
||||
[package.extras]
|
||||
testing = ["fields", "hunter", "process-tests", "six", "pytest-xdist", "virtualenv"]
|
||||
|
||||
[[package]]
|
||||
name = "pytest-mock"
|
||||
version = "3.7.0"
|
||||
description = "Thin-wrapper around the mock package for easier use with pytest"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.dependencies]
|
||||
pytest = ">=5.0"
|
||||
|
||||
[package.extras]
|
||||
dev = ["pre-commit", "tox", "pytest-asyncio"]
|
||||
|
||||
[[package]]
|
||||
name = "pyyaml"
|
||||
version = "6.0"
|
||||
description = "YAML parser and emitter for Python"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
|
||||
[[package]]
|
||||
name = "requests"
|
||||
version = "2.27.1"
|
||||
description = "Python HTTP for Humans."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
|
||||
|
||||
[package.dependencies]
|
||||
certifi = ">=2017.4.17"
|
||||
charset-normalizer = {version = ">=2.0.0,<2.1.0", markers = "python_version >= \"3\""}
|
||||
idna = {version = ">=2.5,<4", markers = "python_version >= \"3\""}
|
||||
urllib3 = ">=1.21.1,<1.27"
|
||||
|
||||
[package.extras]
|
||||
socks = ["PySocks (>=1.5.6,!=1.5.7)", "win-inet-pton"]
|
||||
use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"]
|
||||
|
||||
[[package]]
|
||||
name = "rich"
|
||||
version = "12.4.1"
|
||||
description = "Render rich text, tables, progress bars, syntax highlighting, markdown and more to the terminal"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6.3,<4.0.0"
|
||||
|
||||
[package.dependencies]
|
||||
commonmark = ">=0.9.0,<0.10.0"
|
||||
pygments = ">=2.6.0,<3.0.0"
|
||||
typing-extensions = {version = ">=4.0.0,<5.0", markers = "python_version < \"3.9\""}
|
||||
|
||||
[package.extras]
|
||||
jupyter = ["ipywidgets (>=7.5.1,<8.0.0)"]
|
||||
|
||||
[[package]]
|
||||
name = "six"
|
||||
version = "1.16.0"
|
||||
description = "Python 2 and 3 compatibility utilities"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
|
||||
|
||||
[[package]]
|
||||
name = "toml"
|
||||
version = "0.10.2"
|
||||
description = "Python Library for Tom's Obvious, Minimal Language"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*"
|
||||
|
||||
[[package]]
|
||||
name = "tomli"
|
||||
version = "2.0.1"
|
||||
description = "A lil' TOML parser"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[[package]]
|
||||
name = "tox"
|
||||
version = "3.25.0"
|
||||
description = "tox is a generic virtualenv management and test command line tool"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
|
||||
|
||||
[package.dependencies]
|
||||
colorama = {version = ">=0.4.1", markers = "platform_system == \"Windows\""}
|
||||
filelock = ">=3.0.0"
|
||||
importlib-metadata = {version = ">=0.12", markers = "python_version < \"3.8\""}
|
||||
packaging = ">=14"
|
||||
pluggy = ">=0.12.0"
|
||||
py = ">=1.4.17"
|
||||
six = ">=1.14.0"
|
||||
toml = ">=0.9.4"
|
||||
virtualenv = ">=16.0.0,<20.0.0 || >20.0.0,<20.0.1 || >20.0.1,<20.0.2 || >20.0.2,<20.0.3 || >20.0.3,<20.0.4 || >20.0.4,<20.0.5 || >20.0.5,<20.0.6 || >20.0.6,<20.0.7 || >20.0.7"
|
||||
|
||||
[package.extras]
|
||||
docs = ["pygments-github-lexers (>=0.0.5)", "sphinx (>=2.0.0)", "sphinxcontrib-autoprogram (>=0.1.5)", "towncrier (>=18.5.0)"]
|
||||
testing = ["flaky (>=3.4.0)", "freezegun (>=0.3.11)", "pytest (>=4.0.0)", "pytest-cov (>=2.5.1)", "pytest-mock (>=1.10.0)", "pytest-randomly (>=1.0.0)", "psutil (>=5.6.1)", "pathlib2 (>=2.3.3)"]
|
||||
|
||||
[[package]]
|
||||
name = "typed-ast"
|
||||
version = "1.5.4"
|
||||
description = "a fork of Python 2 and 3 ast modules with type comment support"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
|
||||
[[package]]
|
||||
name = "types-jsonschema"
|
||||
version = "4.4.4"
|
||||
description = "Typing stubs for jsonschema"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
|
||||
[[package]]
|
||||
name = "types-setuptools"
|
||||
version = "57.4.14"
|
||||
description = "Typing stubs for setuptools"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
|
||||
[[package]]
|
||||
name = "typing-extensions"
|
||||
version = "4.2.0"
|
||||
description = "Backported and Experimental Type Hints for Python 3.7+"
|
||||
category = "main"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[[package]]
|
||||
name = "urllib3"
|
||||
version = "1.26.9"
|
||||
description = "HTTP library with thread-safe connection pooling, file post, and more."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, <4"
|
||||
|
||||
[package.extras]
|
||||
brotli = ["brotlicffi (>=0.8.0)", "brotli (>=1.0.9)", "brotlipy (>=0.6.0)"]
|
||||
secure = ["pyOpenSSL (>=0.14)", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "certifi", "ipaddress"]
|
||||
socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
|
||||
|
||||
[[package]]
|
||||
name = "vendoring"
|
||||
version = "1.2.0"
|
||||
description = "A command line tool, to simplify vendoring pure Python dependencies."
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "~= 3.8"
|
||||
|
||||
[package.dependencies]
|
||||
click = "*"
|
||||
jsonschema = "*"
|
||||
packaging = "*"
|
||||
requests = "*"
|
||||
rich = "*"
|
||||
toml = "*"
|
||||
|
||||
[package.extras]
|
||||
doc = ["sphinx"]
|
||||
test = ["pytest", "pytest-cov", "pytest-mock"]
|
||||
|
||||
[[package]]
|
||||
name = "virtualenv"
|
||||
version = "20.14.1"
|
||||
description = "Virtual Python Environment builder"
|
||||
category = "dev"
|
||||
optional = false
|
||||
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
|
||||
|
||||
[package.dependencies]
|
||||
distlib = ">=0.3.1,<1"
|
||||
filelock = ">=3.2,<4"
|
||||
importlib-metadata = {version = ">=0.12", markers = "python_version < \"3.8\""}
|
||||
platformdirs = ">=2,<3"
|
||||
six = ">=1.9.0,<2"
|
||||
|
||||
[package.extras]
|
||||
docs = ["proselint (>=0.10.2)", "sphinx (>=3)", "sphinx-argparse (>=0.2.5)", "sphinx-rtd-theme (>=0.4.3)", "towncrier (>=21.3)"]
|
||||
testing = ["coverage (>=4)", "coverage-enable-subprocess (>=1)", "flaky (>=3)", "pytest (>=4)", "pytest-env (>=0.6.2)", "pytest-freezegun (>=0.4.1)", "pytest-mock (>=2)", "pytest-randomly (>=1)", "pytest-timeout (>=1)", "packaging (>=20.0)"]
|
||||
|
||||
[[package]]
|
||||
name = "zipp"
|
||||
version = "3.8.0"
|
||||
description = "Backport of pathlib-compatible object wrapper for zip files"
|
||||
category = "main"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
|
||||
[package.extras]
|
||||
docs = ["sphinx", "jaraco.packaging (>=9)", "rst.linker (>=1.9)"]
|
||||
testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.0.1)", "jaraco.itertools", "func-timeout", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)"]
|
||||
|
||||
[metadata]
|
||||
lock-version = "1.1"
|
||||
python-versions = "^3.7"
|
||||
content-hash = "942983e12963ee3294081a5f38b6a66034dc7cd350b48a65f21e706a77f160d7"
|
||||
|
||||
[metadata.files]
|
||||
atomicwrites = [
|
||||
{file = "atomicwrites-1.4.0-py2.py3-none-any.whl", hash = "sha256:6d1784dea7c0c8d4a5172b6c620f40b6e4cbfdf96d783691f2e1302a7b88e197"},
|
||||
{file = "atomicwrites-1.4.0.tar.gz", hash = "sha256:ae70396ad1a434f9c7046fd2dd196fc04b12f9e91ffb859164193be8b6168a7a"},
|
||||
]
|
||||
attrs = [
|
||||
{file = "attrs-21.4.0-py2.py3-none-any.whl", hash = "sha256:2d27e3784d7a565d36ab851fe94887c5eccd6a463168875832a1be79c82828b4"},
|
||||
{file = "attrs-21.4.0.tar.gz", hash = "sha256:626ba8234211db98e869df76230a137c4c40a12d72445c45d5f5b716f076e2fd"},
|
||||
]
|
||||
build = [
|
||||
{file = "build-0.7.0-py3-none-any.whl", hash = "sha256:21b7ebbd1b22499c4dac536abc7606696ea4d909fd755e00f09f3c0f2c05e3c8"},
|
||||
{file = "build-0.7.0.tar.gz", hash = "sha256:1aaadcd69338252ade4f7ec1265e1a19184bf916d84c9b7df095f423948cb89f"},
|
||||
]
|
||||
certifi = [
|
||||
{file = "certifi-2021.10.8-py2.py3-none-any.whl", hash = "sha256:d62a0163eb4c2344ac042ab2bdf75399a71a2d8c7d47eac2e2ee91b9d6339569"},
|
||||
{file = "certifi-2021.10.8.tar.gz", hash = "sha256:78884e7c1d4b00ce3cea67b44566851c4343c120abd683433ce934a68ea58872"},
|
||||
]
|
||||
cfgv = [
|
||||
{file = "cfgv-3.3.1-py2.py3-none-any.whl", hash = "sha256:c6a0883f3917a037485059700b9e75da2464e6c27051014ad85ba6aaa5884426"},
|
||||
{file = "cfgv-3.3.1.tar.gz", hash = "sha256:f5a830efb9ce7a445376bb66ec94c638a9787422f96264c98edc6bdeed8ab736"},
|
||||
]
|
||||
charset-normalizer = [
|
||||
{file = "charset-normalizer-2.0.12.tar.gz", hash = "sha256:2857e29ff0d34db842cd7ca3230549d1a697f96ee6d3fb071cfa6c7393832597"},
|
||||
{file = "charset_normalizer-2.0.12-py3-none-any.whl", hash = "sha256:6881edbebdb17b39b4eaaa821b438bf6eddffb4468cf344f09f89def34a8b1df"},
|
||||
]
|
||||
click = [
|
||||
{file = "click-8.1.3-py3-none-any.whl", hash = "sha256:bb4d8133cb15a609f44e8213d9b391b0809795062913b383c62be0ee95b1db48"},
|
||||
{file = "click-8.1.3.tar.gz", hash = "sha256:7682dc8afb30297001674575ea00d1814d808d6a36af415a82bd481d37ba7b8e"},
|
||||
]
|
||||
colorama = [
|
||||
{file = "colorama-0.4.4-py2.py3-none-any.whl", hash = "sha256:9f47eda37229f68eee03b24b9748937c7dc3868f906e8ba69fbcbdd3bc5dc3e2"},
|
||||
{file = "colorama-0.4.4.tar.gz", hash = "sha256:5941b2b48a20143d2267e95b1c2a7603ce057ee39fd88e7329b0c292aa16869b"},
|
||||
]
|
||||
commonmark = [
|
||||
{file = "commonmark-0.9.1-py2.py3-none-any.whl", hash = "sha256:da2f38c92590f83de410ba1a3cbceafbc74fee9def35f9251ba9a971d6d66fd9"},
|
||||
{file = "commonmark-0.9.1.tar.gz", hash = "sha256:452f9dc859be7f06631ddcb328b6919c67984aca654e5fefb3914d54691aed60"},
|
||||
]
|
||||
coverage = [
|
||||
{file = "coverage-6.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:50ed480b798febce113709846b11f5d5ed1e529c88d8ae92f707806c50297abf"},
|
||||
{file = "coverage-6.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:26f8f92699756cb7af2b30720de0c5bb8d028e923a95b6d0c891088025a1ac8f"},
|
||||
{file = "coverage-6.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:60c2147921da7f4d2d04f570e1838db32b95c5509d248f3fe6417e91437eaf41"},
|
||||
{file = "coverage-6.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:750e13834b597eeb8ae6e72aa58d1d831b96beec5ad1d04479ae3772373a8088"},
|
||||
{file = "coverage-6.4-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:af5b9ee0fc146e907aa0f5fb858c3b3da9199d78b7bb2c9973d95550bd40f701"},
|
||||
{file = "coverage-6.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:a022394996419142b33a0cf7274cb444c01d2bb123727c4bb0b9acabcb515dea"},
|
||||
{file = "coverage-6.4-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:5a78cf2c43b13aa6b56003707c5203f28585944c277c1f3f109c7b041b16bd39"},
|
||||
{file = "coverage-6.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:9229d074e097f21dfe0643d9d0140ee7433814b3f0fc3706b4abffd1e3038632"},
|
||||
{file = "coverage-6.4-cp310-cp310-win32.whl", hash = "sha256:fb45fe08e1abc64eb836d187b20a59172053999823f7f6ef4f18a819c44ba16f"},
|
||||
{file = "coverage-6.4-cp310-cp310-win_amd64.whl", hash = "sha256:3cfd07c5889ddb96a401449109a8b97a165be9d67077df6802f59708bfb07720"},
|
||||
{file = "coverage-6.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:03014a74023abaf5a591eeeaf1ac66a73d54eba178ff4cb1fa0c0a44aae70383"},
|
||||
{file = "coverage-6.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c82f2cd69c71698152e943f4a5a6b83a3ab1db73b88f6e769fabc86074c3b08"},
|
||||
{file = "coverage-6.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7b546cf2b1974ddc2cb222a109b37c6ed1778b9be7e6b0c0bc0cf0438d9e45a6"},
|
||||
{file = "coverage-6.4-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc173f1ce9ffb16b299f51c9ce53f66a62f4d975abe5640e976904066f3c835d"},
|
||||
{file = "coverage-6.4-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:c53ad261dfc8695062fc8811ac7c162bd6096a05a19f26097f411bdf5747aee7"},
|
||||
{file = "coverage-6.4-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:eef5292b60b6de753d6e7f2d128d5841c7915fb1e3321c3a1fe6acfe76c38052"},
|
||||
{file = "coverage-6.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:543e172ce4c0de533fa892034cce260467b213c0ea8e39da2f65f9a477425211"},
|
||||
{file = "coverage-6.4-cp37-cp37m-win32.whl", hash = "sha256:00c8544510f3c98476bbd58201ac2b150ffbcce46a8c3e4fb89ebf01998f806a"},
|
||||
{file = "coverage-6.4-cp37-cp37m-win_amd64.whl", hash = "sha256:b84ab65444dcc68d761e95d4d70f3cfd347ceca5a029f2ffec37d4f124f61311"},
|
||||
{file = "coverage-6.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:d548edacbf16a8276af13063a2b0669d58bbcfca7c55a255f84aac2870786a61"},
|
||||
{file = "coverage-6.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:033ebec282793bd9eb988d0271c211e58442c31077976c19c442e24d827d356f"},
|
||||
{file = "coverage-6.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:742fb8b43835078dd7496c3c25a1ec8d15351df49fb0037bffb4754291ef30ce"},
|
||||
{file = "coverage-6.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d55fae115ef9f67934e9f1103c9ba826b4c690e4c5bcf94482b8b2398311bf9c"},
|
||||
{file = "coverage-6.4-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5cd698341626f3c77784858427bad0cdd54a713115b423d22ac83a28303d1d95"},
|
||||
{file = "coverage-6.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:62d382f7d77eeeaff14b30516b17bcbe80f645f5cf02bb755baac376591c653c"},
|
||||
{file = "coverage-6.4-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:016d7f5cf1c8c84f533a3c1f8f36126fbe00b2ec0ccca47cc5731c3723d327c6"},
|
||||
{file = "coverage-6.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:69432946f154c6add0e9ede03cc43b96e2ef2733110a77444823c053b1ff5166"},
|
||||
{file = "coverage-6.4-cp38-cp38-win32.whl", hash = "sha256:83bd142cdec5e4a5c4ca1d4ff6fa807d28460f9db919f9f6a31babaaa8b88426"},
|
||||
{file = "coverage-6.4-cp38-cp38-win_amd64.whl", hash = "sha256:4002f9e8c1f286e986fe96ec58742b93484195defc01d5cc7809b8f7acb5ece3"},
|
||||
{file = "coverage-6.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:e4f52c272fdc82e7c65ff3f17a7179bc5f710ebc8ce8a5cadac81215e8326740"},
|
||||
{file = "coverage-6.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b5578efe4038be02d76c344007b13119b2b20acd009a88dde8adec2de4f630b5"},
|
||||
{file = "coverage-6.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8099ea680201c2221f8468c372198ceba9338a5fec0e940111962b03b3f716a"},
|
||||
{file = "coverage-6.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a00441f5ea4504f5abbc047589d09e0dc33eb447dc45a1a527c8b74bfdd32c65"},
|
||||
{file = "coverage-6.4-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2e76bd16f0e31bc2b07e0fb1379551fcd40daf8cdf7e24f31a29e442878a827c"},
|
||||
{file = "coverage-6.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:8d2e80dd3438e93b19e1223a9850fa65425e77f2607a364b6fd134fcd52dc9df"},
|
||||
{file = "coverage-6.4-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:341e9c2008c481c5c72d0e0dbf64980a4b2238631a7f9780b0fe2e95755fb018"},
|
||||
{file = "coverage-6.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:21e6686a95025927775ac501e74f5940cdf6fe052292f3a3f7349b0abae6d00f"},
|
||||
{file = "coverage-6.4-cp39-cp39-win32.whl", hash = "sha256:968ed5407f9460bd5a591cefd1388cc00a8f5099de9e76234655ae48cfdbe2c3"},
|
||||
{file = "coverage-6.4-cp39-cp39-win_amd64.whl", hash = "sha256:e35217031e4b534b09f9b9a5841b9344a30a6357627761d4218818b865d45055"},
|
||||
{file = "coverage-6.4-pp36.pp37.pp38-none-any.whl", hash = "sha256:e637ae0b7b481905358624ef2e81d7fb0b1af55f5ff99f9ba05442a444b11e45"},
|
||||
{file = "coverage-6.4.tar.gz", hash = "sha256:727dafd7f67a6e1cad808dc884bd9c5a2f6ef1f8f6d2f22b37b96cb0080d4f49"},
|
||||
]
|
||||
distlib = [
|
||||
{file = "distlib-0.3.4-py2.py3-none-any.whl", hash = "sha256:6564fe0a8f51e734df6333d08b8b94d4ea8ee6b99b5ed50613f731fd4089f34b"},
|
||||
{file = "distlib-0.3.4.zip", hash = "sha256:e4b58818180336dc9c529bfb9a0b58728ffc09ad92027a3f30b7cd91e3458579"},
|
||||
]
|
||||
filelock = [
|
||||
{file = "filelock-3.7.0-py3-none-any.whl", hash = "sha256:c7b5fdb219b398a5b28c8e4c1893ef5f98ece6a38c6ab2c22e26ec161556fed6"},
|
||||
{file = "filelock-3.7.0.tar.gz", hash = "sha256:b795f1b42a61bbf8ec7113c341dad679d772567b936fbd1bf43c9a238e673e20"},
|
||||
]
|
||||
identify = [
|
||||
{file = "identify-2.5.0-py2.py3-none-any.whl", hash = "sha256:3acfe15a96e4272b4ec5662ee3e231ceba976ef63fd9980ed2ce9cc415df393f"},
|
||||
{file = "identify-2.5.0.tar.gz", hash = "sha256:c83af514ea50bf2be2c4a3f2fb349442b59dc87284558ae9ff54191bff3541d2"},
|
||||
]
|
||||
idna = [
|
||||
{file = "idna-3.3-py3-none-any.whl", hash = "sha256:84d9dd047ffa80596e0f246e2eab0b391788b0503584e8945f2368256d2735ff"},
|
||||
{file = "idna-3.3.tar.gz", hash = "sha256:9d643ff0a55b762d5cdb124b8eaa99c66322e2157b69160bc32796e824360e6d"},
|
||||
]
|
||||
importlib-metadata = [
|
||||
{file = "importlib_metadata-4.11.3-py3-none-any.whl", hash = "sha256:1208431ca90a8cca1a6b8af391bb53c1a2db74e5d1cef6ddced95d4b2062edc6"},
|
||||
{file = "importlib_metadata-4.11.3.tar.gz", hash = "sha256:ea4c597ebf37142f827b8f39299579e31685c31d3a438b59f469406afd0f2539"},
|
||||
]
|
||||
importlib-resources = [
|
||||
{file = "importlib_resources-5.7.1-py3-none-any.whl", hash = "sha256:e447dc01619b1e951286f3929be820029d48c75eb25d265c28b92a16548212b8"},
|
||||
{file = "importlib_resources-5.7.1.tar.gz", hash = "sha256:b6062987dfc51f0fcb809187cffbd60f35df7acb4589091f154214af6d0d49d3"},
|
||||
]
|
||||
iniconfig = [
|
||||
{file = "iniconfig-1.1.1-py2.py3-none-any.whl", hash = "sha256:011e24c64b7f47f6ebd835bb12a743f2fbe9a26d4cecaa7f53bc4f35ee9da8b3"},
|
||||
{file = "iniconfig-1.1.1.tar.gz", hash = "sha256:bc3af051d7d14b2ee5ef9969666def0cd1a000e121eaea580d4a313df4b37f32"},
|
||||
]
|
||||
jsonschema = [
|
||||
{file = "jsonschema-4.5.1-py3-none-any.whl", hash = "sha256:71b5e39324422543546572954ce71c67728922c104902cb7ce252e522235b33f"},
|
||||
{file = "jsonschema-4.5.1.tar.gz", hash = "sha256:7c6d882619340c3347a1bf7315e147e6d3dae439033ae6383d6acb908c101dfc"},
|
||||
]
|
||||
mypy = [
|
||||
{file = "mypy-0.960-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:3a3e525cd76c2c4f90f1449fd034ba21fcca68050ff7c8397bb7dd25dd8b8248"},
|
||||
{file = "mypy-0.960-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:7a76dc4f91e92db119b1be293892df8379b08fd31795bb44e0ff84256d34c251"},
|
||||
{file = "mypy-0.960-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ffdad80a92c100d1b0fe3d3cf1a4724136029a29afe8566404c0146747114382"},
|
||||
{file = "mypy-0.960-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7d390248ec07fa344b9f365e6ed9d205bd0205e485c555bed37c4235c868e9d5"},
|
||||
{file = "mypy-0.960-cp310-cp310-win_amd64.whl", hash = "sha256:925aa84369a07846b7f3b8556ccade1f371aa554f2bd4fb31cb97a24b73b036e"},
|
||||
{file = "mypy-0.960-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:239d6b2242d6c7f5822163ee082ef7a28ee02e7ac86c35593ef923796826a385"},
|
||||
{file = "mypy-0.960-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f1ba54d440d4feee49d8768ea952137316d454b15301c44403db3f2cb51af024"},
|
||||
{file = "mypy-0.960-cp36-cp36m-win_amd64.whl", hash = "sha256:cb7752b24528c118a7403ee955b6a578bfcf5879d5ee91790667c8ea511d2085"},
|
||||
{file = "mypy-0.960-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:826a2917c275e2ee05b7c7b736c1e6549a35b7ea5a198ca457f8c2ebea2cbecf"},
|
||||
{file = "mypy-0.960-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:3eabcbd2525f295da322dff8175258f3fc4c3eb53f6d1929644ef4d99b92e72d"},
|
||||
{file = "mypy-0.960-cp37-cp37m-win_amd64.whl", hash = "sha256:f47322796c412271f5aea48381a528a613f33e0a115452d03ae35d673e6064f8"},
|
||||
{file = "mypy-0.960-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:2c7f8bb9619290836a4e167e2ef1f2cf14d70e0bc36c04441e41487456561409"},
|
||||
{file = "mypy-0.960-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:fbfb873cf2b8d8c3c513367febde932e061a5f73f762896826ba06391d932b2a"},
|
||||
{file = "mypy-0.960-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cc537885891382e08129d9862553b3d00d4be3eb15b8cae9e2466452f52b0117"},
|
||||
{file = "mypy-0.960-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:481f98c6b24383188c928f33dd2f0776690807e12e9989dd0419edd5c74aa53b"},
|
||||
{file = "mypy-0.960-cp38-cp38-win_amd64.whl", hash = "sha256:29dc94d9215c3eb80ac3c2ad29d0c22628accfb060348fd23d73abe3ace6c10d"},
|
||||
{file = "mypy-0.960-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:33d53a232bb79057f33332dbbb6393e68acbcb776d2f571ba4b1d50a2c8ba873"},
|
||||
{file = "mypy-0.960-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8d645e9e7f7a5da3ec3bbcc314ebb9bb22c7ce39e70367830eb3c08d0140b9ce"},
|
||||
{file = "mypy-0.960-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:85cf2b14d32b61db24ade8ac9ae7691bdfc572a403e3cb8537da936e74713275"},
|
||||
{file = "mypy-0.960-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:a85a20b43fa69efc0b955eba1db435e2ffecb1ca695fe359768e0503b91ea89f"},
|
||||
{file = "mypy-0.960-cp39-cp39-win_amd64.whl", hash = "sha256:0ebfb3f414204b98c06791af37a3a96772203da60636e2897408517fcfeee7a8"},
|
||||
{file = "mypy-0.960-py3-none-any.whl", hash = "sha256:bfd4f6536bd384c27c392a8b8f790fd0ed5c0cf2f63fc2fed7bce56751d53026"},
|
||||
{file = "mypy-0.960.tar.gz", hash = "sha256:d4fccf04c1acf750babd74252e0f2db6bd2ac3aa8fe960797d9f3ef41cf2bfd4"},
|
||||
]
|
||||
mypy-extensions = [
|
||||
{file = "mypy_extensions-0.4.3-py2.py3-none-any.whl", hash = "sha256:090fedd75945a69ae91ce1303b5824f428daf5a028d2f6ab8a299250a846f15d"},
|
||||
{file = "mypy_extensions-0.4.3.tar.gz", hash = "sha256:2d82818f5bb3e369420cb3c4060a7970edba416647068eb4c5343488a6c604a8"},
|
||||
]
|
||||
nodeenv = [
|
||||
{file = "nodeenv-1.6.0-py2.py3-none-any.whl", hash = "sha256:621e6b7076565ddcacd2db0294c0381e01fd28945ab36bcf00f41c5daf63bef7"},
|
||||
{file = "nodeenv-1.6.0.tar.gz", hash = "sha256:3ef13ff90291ba2a4a7a4ff9a979b63ffdd00a464dbe04acf0ea6471517a4c2b"},
|
||||
]
|
||||
packaging = [
|
||||
{file = "packaging-21.3-py3-none-any.whl", hash = "sha256:ef103e05f519cdc783ae24ea4e2e0f508a9c99b2d4969652eed6a2e1ea5bd522"},
|
||||
{file = "packaging-21.3.tar.gz", hash = "sha256:dd47c42927d89ab911e606518907cc2d3a1f38bbd026385970643f9c5b8ecfeb"},
|
||||
]
|
||||
pep517 = [
|
||||
{file = "pep517-0.12.0-py2.py3-none-any.whl", hash = "sha256:dd884c326898e2c6e11f9e0b64940606a93eb10ea022a2e067959f3a110cf161"},
|
||||
{file = "pep517-0.12.0.tar.gz", hash = "sha256:931378d93d11b298cf511dd634cf5ea4cb249a28ef84160b3247ee9afb4e8ab0"},
|
||||
]
|
||||
platformdirs = [
|
||||
{file = "platformdirs-2.5.2-py3-none-any.whl", hash = "sha256:027d8e83a2d7de06bbac4e5ef7e023c02b863d7ea5d079477e722bb41ab25788"},
|
||||
{file = "platformdirs-2.5.2.tar.gz", hash = "sha256:58c8abb07dcb441e6ee4b11d8df0ac856038f944ab98b7be6b27b2a3c7feef19"},
|
||||
]
|
||||
pluggy = [
|
||||
{file = "pluggy-1.0.0-py2.py3-none-any.whl", hash = "sha256:74134bbf457f031a36d68416e1509f34bd5ccc019f0bcc952c7b909d06b37bd3"},
|
||||
{file = "pluggy-1.0.0.tar.gz", hash = "sha256:4224373bacce55f955a878bf9cfa763c1e360858e330072059e10bad68531159"},
|
||||
]
|
||||
pre-commit = [
|
||||
{file = "pre_commit-2.19.0-py2.py3-none-any.whl", hash = "sha256:10c62741aa5704faea2ad69cb550ca78082efe5697d6f04e5710c3c229afdd10"},
|
||||
{file = "pre_commit-2.19.0.tar.gz", hash = "sha256:4233a1e38621c87d9dda9808c6606d7e7ba0e087cd56d3fe03202a01d2919615"},
|
||||
]
|
||||
py = [
|
||||
{file = "py-1.11.0-py2.py3-none-any.whl", hash = "sha256:607c53218732647dff4acdfcd50cb62615cedf612e72d1724fb1a0cc6405b378"},
|
||||
{file = "py-1.11.0.tar.gz", hash = "sha256:51c75c4126074b472f746a24399ad32f6053d1b34b68d2fa41e558e6f4a98719"},
|
||||
]
|
||||
pygments = [
|
||||
{file = "Pygments-2.12.0-py3-none-any.whl", hash = "sha256:dc9c10fb40944260f6ed4c688ece0cd2048414940f1cea51b8b226318411c519"},
|
||||
{file = "Pygments-2.12.0.tar.gz", hash = "sha256:5eb116118f9612ff1ee89ac96437bb6b49e8f04d8a13b514ba26f620208e26eb"},
|
||||
]
|
||||
pyparsing = [
|
||||
{file = "pyparsing-3.0.9-py3-none-any.whl", hash = "sha256:5026bae9a10eeaefb61dab2f09052b9f4307d44aee4eda64b309723d8d206bbc"},
|
||||
{file = "pyparsing-3.0.9.tar.gz", hash = "sha256:2b020ecf7d21b687f219b71ecad3631f644a47f01403fa1d1036b0c6416d70fb"},
|
||||
]
|
||||
pyrsistent = [
|
||||
{file = "pyrsistent-0.18.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:df46c854f490f81210870e509818b729db4488e1f30f2a1ce1698b2295a878d1"},
|
||||
{file = "pyrsistent-0.18.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d45866ececf4a5fff8742c25722da6d4c9e180daa7b405dc0a2a2790d668c26"},
|
||||
{file = "pyrsistent-0.18.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4ed6784ceac462a7d6fcb7e9b663e93b9a6fb373b7f43594f9ff68875788e01e"},
|
||||
{file = "pyrsistent-0.18.1-cp310-cp310-win32.whl", hash = "sha256:e4f3149fd5eb9b285d6bfb54d2e5173f6a116fe19172686797c056672689daf6"},
|
||||
{file = "pyrsistent-0.18.1-cp310-cp310-win_amd64.whl", hash = "sha256:636ce2dc235046ccd3d8c56a7ad54e99d5c1cd0ef07d9ae847306c91d11b5fec"},
|
||||
{file = "pyrsistent-0.18.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e92a52c166426efbe0d1ec1332ee9119b6d32fc1f0bbfd55d5c1088070e7fc1b"},
|
||||
{file = "pyrsistent-0.18.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7a096646eab884bf8bed965bad63ea327e0d0c38989fc83c5ea7b8a87037bfc"},
|
||||
{file = "pyrsistent-0.18.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cdfd2c361b8a8e5d9499b9082b501c452ade8bbf42aef97ea04854f4a3f43b22"},
|
||||
{file = "pyrsistent-0.18.1-cp37-cp37m-win32.whl", hash = "sha256:7ec335fc998faa4febe75cc5268a9eac0478b3f681602c1f27befaf2a1abe1d8"},
|
||||
{file = "pyrsistent-0.18.1-cp37-cp37m-win_amd64.whl", hash = "sha256:6455fc599df93d1f60e1c5c4fe471499f08d190d57eca040c0ea182301321286"},
|
||||
{file = "pyrsistent-0.18.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:fd8da6d0124efa2f67d86fa70c851022f87c98e205f0594e1fae044e7119a5a6"},
|
||||
{file = "pyrsistent-0.18.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7bfe2388663fd18bd8ce7db2c91c7400bf3e1a9e8bd7d63bf7e77d39051b85ec"},
|
||||
{file = "pyrsistent-0.18.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0e3e1fcc45199df76053026a51cc59ab2ea3fc7c094c6627e93b7b44cdae2c8c"},
|
||||
{file = "pyrsistent-0.18.1-cp38-cp38-win32.whl", hash = "sha256:b568f35ad53a7b07ed9b1b2bae09eb15cdd671a5ba5d2c66caee40dbf91c68ca"},
|
||||
{file = "pyrsistent-0.18.1-cp38-cp38-win_amd64.whl", hash = "sha256:d1b96547410f76078eaf66d282ddca2e4baae8964364abb4f4dcdde855cd123a"},
|
||||
{file = "pyrsistent-0.18.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:f87cc2863ef33c709e237d4b5f4502a62a00fab450c9e020892e8e2ede5847f5"},
|
||||
{file = "pyrsistent-0.18.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6bc66318fb7ee012071b2792024564973ecc80e9522842eb4e17743604b5e045"},
|
||||
{file = "pyrsistent-0.18.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:914474c9f1d93080338ace89cb2acee74f4f666fb0424896fcfb8d86058bf17c"},
|
||||
{file = "pyrsistent-0.18.1-cp39-cp39-win32.whl", hash = "sha256:1b34eedd6812bf4d33814fca1b66005805d3640ce53140ab8bbb1e2651b0d9bc"},
|
||||
{file = "pyrsistent-0.18.1-cp39-cp39-win_amd64.whl", hash = "sha256:e24a828f57e0c337c8d8bb9f6b12f09dfdf0273da25fda9e314f0b684b415a07"},
|
||||
{file = "pyrsistent-0.18.1.tar.gz", hash = "sha256:d4d61f8b993a7255ba714df3aca52700f8125289f84f704cf80916517c46eb96"},
|
||||
]
|
||||
pytest = [
|
||||
{file = "pytest-7.1.2-py3-none-any.whl", hash = "sha256:13d0e3ccfc2b6e26be000cb6568c832ba67ba32e719443bfe725814d3c42433c"},
|
||||
{file = "pytest-7.1.2.tar.gz", hash = "sha256:a06a0425453864a270bc45e71f783330a7428defb4230fb5e6a731fde06ecd45"},
|
||||
]
|
||||
pytest-cov = [
|
||||
{file = "pytest-cov-3.0.0.tar.gz", hash = "sha256:e7f0f5b1617d2210a2cabc266dfe2f4c75a8d32fb89eafb7ad9d06f6d076d470"},
|
||||
{file = "pytest_cov-3.0.0-py3-none-any.whl", hash = "sha256:578d5d15ac4a25e5f961c938b85a05b09fdaae9deef3bb6de9a6e766622ca7a6"},
|
||||
]
|
||||
pytest-mock = [
|
||||
{file = "pytest-mock-3.7.0.tar.gz", hash = "sha256:5112bd92cc9f186ee96e1a92efc84969ea494939c3aead39c50f421c4cc69534"},
|
||||
{file = "pytest_mock-3.7.0-py3-none-any.whl", hash = "sha256:6cff27cec936bf81dc5ee87f07132b807bcda51106b5ec4b90a04331cba76231"},
|
||||
]
|
||||
pyyaml = [
|
||||
{file = "PyYAML-6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d4db7c7aef085872ef65a8fd7d6d09a14ae91f691dec3e87ee5ee0539d516f53"},
|
||||
{file = "PyYAML-6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9df7ed3b3d2e0ecfe09e14741b857df43adb5a3ddadc919a2d94fbdf78fea53c"},
|
||||
{file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77f396e6ef4c73fdc33a9157446466f1cff553d979bd00ecb64385760c6babdc"},
|
||||
{file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a80a78046a72361de73f8f395f1f1e49f956c6be882eed58505a15f3e430962b"},
|
||||
{file = "PyYAML-6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f84fbc98b019fef2ee9a1cb3ce93e3187a6df0b2538a651bfb890254ba9f90b5"},
|
||||
{file = "PyYAML-6.0-cp310-cp310-win32.whl", hash = "sha256:2cd5df3de48857ed0544b34e2d40e9fac445930039f3cfe4bcc592a1f836d513"},
|
||||
{file = "PyYAML-6.0-cp310-cp310-win_amd64.whl", hash = "sha256:daf496c58a8c52083df09b80c860005194014c3698698d1a57cbcfa182142a3a"},
|
||||
{file = "PyYAML-6.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:897b80890765f037df3403d22bab41627ca8811ae55e9a722fd0392850ec4d86"},
|
||||
{file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:50602afada6d6cbfad699b0c7bb50d5ccffa7e46a3d738092afddc1f9758427f"},
|
||||
{file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:48c346915c114f5fdb3ead70312bd042a953a8ce5c7106d5bfb1a5254e47da92"},
|
||||
{file = "PyYAML-6.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:98c4d36e99714e55cfbaaee6dd5badbc9a1ec339ebfc3b1f52e293aee6bb71a4"},
|
||||
{file = "PyYAML-6.0-cp36-cp36m-win32.whl", hash = "sha256:0283c35a6a9fbf047493e3a0ce8d79ef5030852c51e9d911a27badfde0605293"},
|
||||
{file = "PyYAML-6.0-cp36-cp36m-win_amd64.whl", hash = "sha256:07751360502caac1c067a8132d150cf3d61339af5691fe9e87803040dbc5db57"},
|
||||
{file = "PyYAML-6.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:819b3830a1543db06c4d4b865e70ded25be52a2e0631ccd2f6a47a2822f2fd7c"},
|
||||
{file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:473f9edb243cb1935ab5a084eb238d842fb8f404ed2193a915d1784b5a6b5fc0"},
|
||||
{file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0ce82d761c532fe4ec3f87fc45688bdd3a4c1dc5e0b4a19814b9009a29baefd4"},
|
||||
{file = "PyYAML-6.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:231710d57adfd809ef5d34183b8ed1eeae3f76459c18fb4a0b373ad56bedcdd9"},
|
||||
{file = "PyYAML-6.0-cp37-cp37m-win32.whl", hash = "sha256:c5687b8d43cf58545ade1fe3e055f70eac7a5a1a0bf42824308d868289a95737"},
|
||||
{file = "PyYAML-6.0-cp37-cp37m-win_amd64.whl", hash = "sha256:d15a181d1ecd0d4270dc32edb46f7cb7733c7c508857278d3d378d14d606db2d"},
|
||||
{file = "PyYAML-6.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:0b4624f379dab24d3725ffde76559cff63d9ec94e1736b556dacdfebe5ab6d4b"},
|
||||
{file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:213c60cd50106436cc818accf5baa1aba61c0189ff610f64f4a3e8c6726218ba"},
|
||||
{file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9fa600030013c4de8165339db93d182b9431076eb98eb40ee068700c9c813e34"},
|
||||
{file = "PyYAML-6.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:277a0ef2981ca40581a47093e9e2d13b3f1fbbeffae064c1d21bfceba2030287"},
|
||||
{file = "PyYAML-6.0-cp38-cp38-win32.whl", hash = "sha256:d4eccecf9adf6fbcc6861a38015c2a64f38b9d94838ac1810a9023a0609e1b78"},
|
||||
{file = "PyYAML-6.0-cp38-cp38-win_amd64.whl", hash = "sha256:1e4747bc279b4f613a09eb64bba2ba602d8a6664c6ce6396a4d0cd413a50ce07"},
|
||||
{file = "PyYAML-6.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:055d937d65826939cb044fc8c9b08889e8c743fdc6a32b33e2390f66013e449b"},
|
||||
{file = "PyYAML-6.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e61ceaab6f49fb8bdfaa0f92c4b57bcfbea54c09277b1b4f7ac376bfb7a7c174"},
|
||||
{file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d67d839ede4ed1b28a4e8909735fc992a923cdb84e618544973d7dfc71540803"},
|
||||
{file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cba8c411ef271aa037d7357a2bc8f9ee8b58b9965831d9e51baf703280dc73d3"},
|
||||
{file = "PyYAML-6.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:40527857252b61eacd1d9af500c3337ba8deb8fc298940291486c465c8b46ec0"},
|
||||
{file = "PyYAML-6.0-cp39-cp39-win32.whl", hash = "sha256:b5b9eccad747aabaaffbc6064800670f0c297e52c12754eb1d976c57e4f74dcb"},
|
||||
{file = "PyYAML-6.0-cp39-cp39-win_amd64.whl", hash = "sha256:b3d267842bf12586ba6c734f89d1f5b871df0273157918b0ccefa29deb05c21c"},
|
||||
{file = "PyYAML-6.0.tar.gz", hash = "sha256:68fb519c14306fec9720a2a5b45bc9f0c8d1b9c72adf45c37baedfcd949c35a2"},
|
||||
]
|
||||
requests = [
|
||||
{file = "requests-2.27.1-py2.py3-none-any.whl", hash = "sha256:f22fa1e554c9ddfd16e6e41ac79759e17be9e492b3587efa038054674760e72d"},
|
||||
{file = "requests-2.27.1.tar.gz", hash = "sha256:68d7c56fd5a8999887728ef304a6d12edc7be74f1cfa47714fc8b414525c9a61"},
|
||||
]
|
||||
rich = [
|
||||
{file = "rich-12.4.1-py3-none-any.whl", hash = "sha256:d13c6c90c42e24eb7ce660db397e8c398edd58acb7f92a2a88a95572b838aaa4"},
|
||||
{file = "rich-12.4.1.tar.gz", hash = "sha256:d239001c0fb7de985e21ec9a4bb542b5150350330bbc1849f835b9cbc8923b91"},
|
||||
]
|
||||
six = [
|
||||
{file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
|
||||
{file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
|
||||
]
|
||||
toml = [
|
||||
{file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"},
|
||||
{file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
|
||||
]
|
||||
tomli = [
|
||||
{file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
|
||||
{file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
|
||||
]
|
||||
tox = [
|
||||
{file = "tox-3.25.0-py2.py3-none-any.whl", hash = "sha256:0805727eb4d6b049de304977dfc9ce315a1938e6619c3ab9f38682bb04662a5a"},
|
||||
{file = "tox-3.25.0.tar.gz", hash = "sha256:37888f3092aa4e9f835fc8cc6dadbaaa0782651c41ef359e3a5743fcb0308160"},
|
||||
]
|
||||
typed-ast = [
|
||||
{file = "typed_ast-1.5.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:669dd0c4167f6f2cd9f57041e03c3c2ebf9063d0757dc89f79ba1daa2bfca9d4"},
|
||||
{file = "typed_ast-1.5.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:211260621ab1cd7324e0798d6be953d00b74e0428382991adfddb352252f1d62"},
|
||||
{file = "typed_ast-1.5.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:267e3f78697a6c00c689c03db4876dd1efdfea2f251a5ad6555e82a26847b4ac"},
|
||||
{file = "typed_ast-1.5.4-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:c542eeda69212fa10a7ada75e668876fdec5f856cd3d06829e6aa64ad17c8dfe"},
|
||||
{file = "typed_ast-1.5.4-cp310-cp310-win_amd64.whl", hash = "sha256:a9916d2bb8865f973824fb47436fa45e1ebf2efd920f2b9f99342cb7fab93f72"},
|
||||
{file = "typed_ast-1.5.4-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:79b1e0869db7c830ba6a981d58711c88b6677506e648496b1f64ac7d15633aec"},
|
||||
{file = "typed_ast-1.5.4-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a94d55d142c9265f4ea46fab70977a1944ecae359ae867397757d836ea5a3f47"},
|
||||
{file = "typed_ast-1.5.4-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:183afdf0ec5b1b211724dfef3d2cad2d767cbefac291f24d69b00546c1837fb6"},
|
||||
{file = "typed_ast-1.5.4-cp36-cp36m-win_amd64.whl", hash = "sha256:639c5f0b21776605dd6c9dbe592d5228f021404dafd377e2b7ac046b0349b1a1"},
|
||||
{file = "typed_ast-1.5.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:cf4afcfac006ece570e32d6fa90ab74a17245b83dfd6655a6f68568098345ff6"},
|
||||
{file = "typed_ast-1.5.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ed855bbe3eb3715fca349c80174cfcfd699c2f9de574d40527b8429acae23a66"},
|
||||
{file = "typed_ast-1.5.4-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:6778e1b2f81dfc7bc58e4b259363b83d2e509a65198e85d5700dfae4c6c8ff1c"},
|
||||
{file = "typed_ast-1.5.4-cp37-cp37m-win_amd64.whl", hash = "sha256:0261195c2062caf107831e92a76764c81227dae162c4f75192c0d489faf751a2"},
|
||||
{file = "typed_ast-1.5.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2efae9db7a8c05ad5547d522e7dbe62c83d838d3906a3716d1478b6c1d61388d"},
|
||||
{file = "typed_ast-1.5.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:7d5d014b7daa8b0bf2eaef684295acae12b036d79f54178b92a2b6a56f92278f"},
|
||||
{file = "typed_ast-1.5.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:370788a63915e82fd6f212865a596a0fefcbb7d408bbbb13dea723d971ed8bdc"},
|
||||
{file = "typed_ast-1.5.4-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:4e964b4ff86550a7a7d56345c7864b18f403f5bd7380edf44a3c1fb4ee7ac6c6"},
|
||||
{file = "typed_ast-1.5.4-cp38-cp38-win_amd64.whl", hash = "sha256:683407d92dc953c8a7347119596f0b0e6c55eb98ebebd9b23437501b28dcbb8e"},
|
||||
{file = "typed_ast-1.5.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4879da6c9b73443f97e731b617184a596ac1235fe91f98d279a7af36c796da35"},
|
||||
{file = "typed_ast-1.5.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3e123d878ba170397916557d31c8f589951e353cc95fb7f24f6bb69adc1a8a97"},
|
||||
{file = "typed_ast-1.5.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ebd9d7f80ccf7a82ac5f88c521115cc55d84e35bf8b446fcd7836eb6b98929a3"},
|
||||
{file = "typed_ast-1.5.4-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:98f80dee3c03455e92796b58b98ff6ca0b2a6f652120c263efdba4d6c5e58f72"},
|
||||
{file = "typed_ast-1.5.4-cp39-cp39-win_amd64.whl", hash = "sha256:0fdbcf2fef0ca421a3f5912555804296f0b0960f0418c440f5d6d3abb549f3e1"},
|
||||
{file = "typed_ast-1.5.4.tar.gz", hash = "sha256:39e21ceb7388e4bb37f4c679d72707ed46c2fbf2a5609b8b8ebc4b067d977df2"},
|
||||
]
|
||||
types-jsonschema = [
|
||||
{file = "types-jsonschema-4.4.4.tar.gz", hash = "sha256:d03f0c1a97ff06dda9535dfa51916a98f38bf40d6828ef4d93bc40708effe507"},
|
||||
{file = "types_jsonschema-4.4.4-py3-none-any.whl", hash = "sha256:294d2de9ea3564fbec6c56153e84d1f3f7d9b2ada36e183d88a63c126da7bc3d"},
|
||||
]
|
||||
types-setuptools = [
|
||||
{file = "types-setuptools-57.4.14.tar.gz", hash = "sha256:df02fe1dd244f58cf4e67cfc3d0a97930a2d61a72dd89f21d81c71017cd83f9a"},
|
||||
{file = "types_setuptools-57.4.14-py3-none-any.whl", hash = "sha256:828f7e7e51e157876f47c80518b23ba0c3c36aa8081efd39d5d39f393938aec9"},
|
||||
]
|
||||
typing-extensions = [
|
||||
{file = "typing_extensions-4.2.0-py3-none-any.whl", hash = "sha256:6657594ee297170d19f67d55c05852a874e7eb634f4f753dbd667855e07c1708"},
|
||||
{file = "typing_extensions-4.2.0.tar.gz", hash = "sha256:f1c24655a0da0d1b67f07e17a5e6b2a105894e6824b92096378bb3668ef02376"},
|
||||
]
|
||||
urllib3 = [
|
||||
{file = "urllib3-1.26.9-py2.py3-none-any.whl", hash = "sha256:44ece4d53fb1706f667c9bd1c648f5469a2ec925fcf3a776667042d645472c14"},
|
||||
{file = "urllib3-1.26.9.tar.gz", hash = "sha256:aabaf16477806a5e1dd19aa41f8c2b7950dd3c746362d7e3223dbe6de6ac448e"},
|
||||
]
|
||||
vendoring = [
|
||||
{file = "vendoring-1.2.0-py2.py3-none-any.whl", hash = "sha256:35b5fca683264e69e851a7580bb6a6f9848af024ffc8382ed5491bcfa55750c6"},
|
||||
{file = "vendoring-1.2.0.tar.gz", hash = "sha256:6340a84bf542222c96f22ebc3cb87e4d86932dc04bc8d446e38285594702c00e"},
|
||||
]
|
||||
virtualenv = [
|
||||
{file = "virtualenv-20.14.1-py2.py3-none-any.whl", hash = "sha256:e617f16e25b42eb4f6e74096b9c9e37713cf10bf30168fb4a739f3fa8f898a3a"},
|
||||
{file = "virtualenv-20.14.1.tar.gz", hash = "sha256:ef589a79795589aada0c1c5b319486797c03b67ac3984c48c669c0e4f50df3a5"},
|
||||
]
|
||||
zipp = [
|
||||
{file = "zipp-3.8.0-py3-none-any.whl", hash = "sha256:c4f6e5bbf48e74f7a38e7cc5b0480ff42b0ae5178957d564d18932525d5cf099"},
|
||||
{file = "zipp-3.8.0.tar.gz", hash = "sha256:56bf8aadb83c24db6c4b577e13de374ccfb67da2078beba1d037c17980bf43ad"},
|
||||
]
|
||||
|
|
@ -0,0 +1,121 @@
|
|||
[tool.poetry]
|
||||
name = "poetry-core"
|
||||
version = "1.4.0"
|
||||
description = "Poetry PEP 517 Build Backend"
|
||||
authors = ["Sébastien Eustace <sebastien@eustace.io>"]
|
||||
|
||||
license = "MIT"
|
||||
|
||||
readme = "README.md"
|
||||
|
||||
homepage = "https://github.com/python-poetry/poetry-core"
|
||||
repository = "https://github.com/python-poetry/poetry-core"
|
||||
|
||||
keywords = ["packaging", "dependency", "poetry"]
|
||||
|
||||
classifiers = [
|
||||
"Topic :: Software Development :: Build Tools",
|
||||
"Topic :: Software Development :: Libraries :: Python Modules"
|
||||
]
|
||||
|
||||
packages = [
|
||||
{ include = "poetry", from = "src" },
|
||||
]
|
||||
include = [
|
||||
{ path = "tests", format = "sdist" },
|
||||
]
|
||||
exclude = [
|
||||
"**/*.pyc",
|
||||
"**/*.pyi",
|
||||
]
|
||||
|
||||
[tool.poetry.build]
|
||||
generate-setup-file = false
|
||||
|
||||
[tool.poetry.urls]
|
||||
"Bug Tracker" = "https://github.com/python-poetry/poetry/issues"
|
||||
|
||||
[tool.poetry.dependencies]
|
||||
python = "^3.7"
|
||||
|
||||
# required for compatibility
|
||||
importlib-metadata = {version = ">=1.7.0", python = "<3.8"}
|
||||
|
||||
[tool.poetry.dev-dependencies]
|
||||
pre-commit = "^2.15.0"
|
||||
pyrsistent = "^0.18.0"
|
||||
pytest = "^7.1.2"
|
||||
pytest-cov = "^3.0.0"
|
||||
pytest-mock = "^3.5"
|
||||
tox = "^3.0"
|
||||
vendoring = {version = "^1.0", python = "^3.8"}
|
||||
build = "^0.7.0"
|
||||
mypy = ">=0.960"
|
||||
types-jsonschema = ">=4.4.4"
|
||||
types-setuptools = ">=57.4.14"
|
||||
|
||||
[tool.black]
|
||||
line-length = 88
|
||||
preview = true
|
||||
include = '\.pyi?$'
|
||||
extend-exclude = "src/poetry/core/_vendor/*"
|
||||
|
||||
[tool.isort]
|
||||
profile = "black"
|
||||
force_single_line = true
|
||||
atomic = true
|
||||
include_trailing_comma = true
|
||||
lines_after_imports = 2
|
||||
lines_between_types = 1
|
||||
use_parentheses = true
|
||||
skip_glob = ["*/setup.py", "*/poetry/core/_vendor/*"]
|
||||
filter_files = true
|
||||
|
||||
known_first_party = "poetry.core"
|
||||
known_third_party = ["poetry.core._vendor"]
|
||||
|
||||
[tool.mypy]
|
||||
strict = true
|
||||
explicit_package_bases = true
|
||||
namespace_packages = true
|
||||
show_error_codes = true
|
||||
enable_error_code = [
|
||||
"ignore-without-code",
|
||||
"redundant-expr",
|
||||
"truthy-bool",
|
||||
]
|
||||
mypy_path = "src"
|
||||
files = "src, tests"
|
||||
exclude = "(?x)(^tests/.*/fixtures | ^src/poetry/core/_vendor)"
|
||||
|
||||
[[tool.mypy.overrides]]
|
||||
module = [
|
||||
'lark.*',
|
||||
'tomlkit.*',
|
||||
'virtualenv.*',
|
||||
]
|
||||
ignore_missing_imports = true
|
||||
|
||||
[tool.vendoring]
|
||||
destination = "src/poetry/core/_vendor/"
|
||||
requirements = "src/poetry/core/_vendor/vendor.txt"
|
||||
namespace = ""
|
||||
|
||||
protected-files = ["vendor.txt"]
|
||||
patches-dir = "vendors/patches"
|
||||
|
||||
[tool.vendoring.transformations]
|
||||
drop = [
|
||||
"bin/",
|
||||
"*.so",
|
||||
"typing.*",
|
||||
"*/tests/"
|
||||
]
|
||||
|
||||
[tool.vendoring.license.fallback-urls]
|
||||
pyrsistent = "https://raw.githubusercontent.com/tobgu/pyrsistent/master/LICENSE.mit"
|
||||
|
||||
[build-system]
|
||||
requires = []
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
backend-path = ["src"]
|
||||
|
|
@ -0,0 +1,15 @@
|
|||
from __future__ import annotations
|
||||
|
||||
import sys
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
# this cannot presently be replaced with importlib.metadata.version as when building
|
||||
# itself, poetry-core is not available as an installed distribution.
|
||||
__version__ = "1.4.0"
|
||||
|
||||
__vendor_site__ = (Path(__file__).parent / "_vendor").as_posix()
|
||||
|
||||
if __vendor_site__ not in sys.path:
|
||||
sys.path.insert(0, __vendor_site__)
|
||||
|
|
@ -0,0 +1 @@
|
|||
__version__ = '0.19.2'
|
||||
|
|
@ -0,0 +1,79 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
|
||||
import sys
|
||||
|
||||
from functools import partial
|
||||
|
||||
from . import converters, exceptions, filters, setters, validators
|
||||
from ._cmp import cmp_using
|
||||
from ._config import get_run_validators, set_run_validators
|
||||
from ._funcs import asdict, assoc, astuple, evolve, has, resolve_types
|
||||
from ._make import (
|
||||
NOTHING,
|
||||
Attribute,
|
||||
Factory,
|
||||
attrib,
|
||||
attrs,
|
||||
fields,
|
||||
fields_dict,
|
||||
make_class,
|
||||
validate,
|
||||
)
|
||||
from ._version_info import VersionInfo
|
||||
|
||||
|
||||
__version__ = "22.1.0"
|
||||
__version_info__ = VersionInfo._from_version_string(__version__)
|
||||
|
||||
__title__ = "attrs"
|
||||
__description__ = "Classes Without Boilerplate"
|
||||
__url__ = "https://www.attrs.org/"
|
||||
__uri__ = __url__
|
||||
__doc__ = __description__ + " <" + __uri__ + ">"
|
||||
|
||||
__author__ = "Hynek Schlawack"
|
||||
__email__ = "hs@ox.cx"
|
||||
|
||||
__license__ = "MIT"
|
||||
__copyright__ = "Copyright (c) 2015 Hynek Schlawack"
|
||||
|
||||
|
||||
s = attributes = attrs
|
||||
ib = attr = attrib
|
||||
dataclass = partial(attrs, auto_attribs=True) # happy Easter ;)
|
||||
|
||||
__all__ = [
|
||||
"Attribute",
|
||||
"Factory",
|
||||
"NOTHING",
|
||||
"asdict",
|
||||
"assoc",
|
||||
"astuple",
|
||||
"attr",
|
||||
"attrib",
|
||||
"attributes",
|
||||
"attrs",
|
||||
"cmp_using",
|
||||
"converters",
|
||||
"evolve",
|
||||
"exceptions",
|
||||
"fields",
|
||||
"fields_dict",
|
||||
"filters",
|
||||
"get_run_validators",
|
||||
"has",
|
||||
"ib",
|
||||
"make_class",
|
||||
"resolve_types",
|
||||
"s",
|
||||
"set_run_validators",
|
||||
"setters",
|
||||
"validate",
|
||||
"validators",
|
||||
]
|
||||
|
||||
if sys.version_info[:2] >= (3, 6):
|
||||
from ._next_gen import define, field, frozen, mutable # noqa: F401
|
||||
|
||||
__all__.extend(("define", "field", "frozen", "mutable"))
|
||||
|
|
@ -0,0 +1,155 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
|
||||
import functools
|
||||
import types
|
||||
|
||||
from ._make import _make_ne
|
||||
|
||||
|
||||
_operation_names = {"eq": "==", "lt": "<", "le": "<=", "gt": ">", "ge": ">="}
|
||||
|
||||
|
||||
def cmp_using(
|
||||
eq=None,
|
||||
lt=None,
|
||||
le=None,
|
||||
gt=None,
|
||||
ge=None,
|
||||
require_same_type=True,
|
||||
class_name="Comparable",
|
||||
):
|
||||
"""
|
||||
Create a class that can be passed into `attr.ib`'s ``eq``, ``order``, and
|
||||
``cmp`` arguments to customize field comparison.
|
||||
|
||||
The resulting class will have a full set of ordering methods if
|
||||
at least one of ``{lt, le, gt, ge}`` and ``eq`` are provided.
|
||||
|
||||
:param Optional[callable] eq: `callable` used to evaluate equality
|
||||
of two objects.
|
||||
:param Optional[callable] lt: `callable` used to evaluate whether
|
||||
one object is less than another object.
|
||||
:param Optional[callable] le: `callable` used to evaluate whether
|
||||
one object is less than or equal to another object.
|
||||
:param Optional[callable] gt: `callable` used to evaluate whether
|
||||
one object is greater than another object.
|
||||
:param Optional[callable] ge: `callable` used to evaluate whether
|
||||
one object is greater than or equal to another object.
|
||||
|
||||
:param bool require_same_type: When `True`, equality and ordering methods
|
||||
will return `NotImplemented` if objects are not of the same type.
|
||||
|
||||
:param Optional[str] class_name: Name of class. Defaults to 'Comparable'.
|
||||
|
||||
See `comparison` for more details.
|
||||
|
||||
.. versionadded:: 21.1.0
|
||||
"""
|
||||
|
||||
body = {
|
||||
"__slots__": ["value"],
|
||||
"__init__": _make_init(),
|
||||
"_requirements": [],
|
||||
"_is_comparable_to": _is_comparable_to,
|
||||
}
|
||||
|
||||
# Add operations.
|
||||
num_order_functions = 0
|
||||
has_eq_function = False
|
||||
|
||||
if eq is not None:
|
||||
has_eq_function = True
|
||||
body["__eq__"] = _make_operator("eq", eq)
|
||||
body["__ne__"] = _make_ne()
|
||||
|
||||
if lt is not None:
|
||||
num_order_functions += 1
|
||||
body["__lt__"] = _make_operator("lt", lt)
|
||||
|
||||
if le is not None:
|
||||
num_order_functions += 1
|
||||
body["__le__"] = _make_operator("le", le)
|
||||
|
||||
if gt is not None:
|
||||
num_order_functions += 1
|
||||
body["__gt__"] = _make_operator("gt", gt)
|
||||
|
||||
if ge is not None:
|
||||
num_order_functions += 1
|
||||
body["__ge__"] = _make_operator("ge", ge)
|
||||
|
||||
type_ = types.new_class(
|
||||
class_name, (object,), {}, lambda ns: ns.update(body)
|
||||
)
|
||||
|
||||
# Add same type requirement.
|
||||
if require_same_type:
|
||||
type_._requirements.append(_check_same_type)
|
||||
|
||||
# Add total ordering if at least one operation was defined.
|
||||
if 0 < num_order_functions < 4:
|
||||
if not has_eq_function:
|
||||
# functools.total_ordering requires __eq__ to be defined,
|
||||
# so raise early error here to keep a nice stack.
|
||||
raise ValueError(
|
||||
"eq must be define is order to complete ordering from "
|
||||
"lt, le, gt, ge."
|
||||
)
|
||||
type_ = functools.total_ordering(type_)
|
||||
|
||||
return type_
|
||||
|
||||
|
||||
def _make_init():
|
||||
"""
|
||||
Create __init__ method.
|
||||
"""
|
||||
|
||||
def __init__(self, value):
|
||||
"""
|
||||
Initialize object with *value*.
|
||||
"""
|
||||
self.value = value
|
||||
|
||||
return __init__
|
||||
|
||||
|
||||
def _make_operator(name, func):
|
||||
"""
|
||||
Create operator method.
|
||||
"""
|
||||
|
||||
def method(self, other):
|
||||
if not self._is_comparable_to(other):
|
||||
return NotImplemented
|
||||
|
||||
result = func(self.value, other.value)
|
||||
if result is NotImplemented:
|
||||
return NotImplemented
|
||||
|
||||
return result
|
||||
|
||||
method.__name__ = "__%s__" % (name,)
|
||||
method.__doc__ = "Return a %s b. Computed by attrs." % (
|
||||
_operation_names[name],
|
||||
)
|
||||
|
||||
return method
|
||||
|
||||
|
||||
def _is_comparable_to(self, other):
|
||||
"""
|
||||
Check whether `other` is comparable to `self`.
|
||||
"""
|
||||
for func in self._requirements:
|
||||
if not func(self, other):
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def _check_same_type(self, other):
|
||||
"""
|
||||
Return True if *self* and *other* are of the same type, False otherwise.
|
||||
"""
|
||||
return other.value.__class__ is self.value.__class__
|
||||
|
|
@ -0,0 +1,185 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
|
||||
import inspect
|
||||
import platform
|
||||
import sys
|
||||
import threading
|
||||
import types
|
||||
import warnings
|
||||
|
||||
from collections.abc import Mapping, Sequence # noqa
|
||||
|
||||
|
||||
PYPY = platform.python_implementation() == "PyPy"
|
||||
PY36 = sys.version_info[:2] >= (3, 6)
|
||||
HAS_F_STRINGS = PY36
|
||||
PY310 = sys.version_info[:2] >= (3, 10)
|
||||
|
||||
|
||||
if PYPY or PY36:
|
||||
ordered_dict = dict
|
||||
else:
|
||||
from collections import OrderedDict
|
||||
|
||||
ordered_dict = OrderedDict
|
||||
|
||||
|
||||
def just_warn(*args, **kw):
|
||||
warnings.warn(
|
||||
"Running interpreter doesn't sufficiently support code object "
|
||||
"introspection. Some features like bare super() or accessing "
|
||||
"__class__ will not work with slotted classes.",
|
||||
RuntimeWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
|
||||
|
||||
class _AnnotationExtractor:
|
||||
"""
|
||||
Extract type annotations from a callable, returning None whenever there
|
||||
is none.
|
||||
"""
|
||||
|
||||
__slots__ = ["sig"]
|
||||
|
||||
def __init__(self, callable):
|
||||
try:
|
||||
self.sig = inspect.signature(callable)
|
||||
except (ValueError, TypeError): # inspect failed
|
||||
self.sig = None
|
||||
|
||||
def get_first_param_type(self):
|
||||
"""
|
||||
Return the type annotation of the first argument if it's not empty.
|
||||
"""
|
||||
if not self.sig:
|
||||
return None
|
||||
|
||||
params = list(self.sig.parameters.values())
|
||||
if params and params[0].annotation is not inspect.Parameter.empty:
|
||||
return params[0].annotation
|
||||
|
||||
return None
|
||||
|
||||
def get_return_type(self):
|
||||
"""
|
||||
Return the return type if it's not empty.
|
||||
"""
|
||||
if (
|
||||
self.sig
|
||||
and self.sig.return_annotation is not inspect.Signature.empty
|
||||
):
|
||||
return self.sig.return_annotation
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def make_set_closure_cell():
|
||||
"""Return a function of two arguments (cell, value) which sets
|
||||
the value stored in the closure cell `cell` to `value`.
|
||||
"""
|
||||
# pypy makes this easy. (It also supports the logic below, but
|
||||
# why not do the easy/fast thing?)
|
||||
if PYPY:
|
||||
|
||||
def set_closure_cell(cell, value):
|
||||
cell.__setstate__((value,))
|
||||
|
||||
return set_closure_cell
|
||||
|
||||
# Otherwise gotta do it the hard way.
|
||||
|
||||
# Create a function that will set its first cellvar to `value`.
|
||||
def set_first_cellvar_to(value):
|
||||
x = value
|
||||
return
|
||||
|
||||
# This function will be eliminated as dead code, but
|
||||
# not before its reference to `x` forces `x` to be
|
||||
# represented as a closure cell rather than a local.
|
||||
def force_x_to_be_a_cell(): # pragma: no cover
|
||||
return x
|
||||
|
||||
try:
|
||||
# Extract the code object and make sure our assumptions about
|
||||
# the closure behavior are correct.
|
||||
co = set_first_cellvar_to.__code__
|
||||
if co.co_cellvars != ("x",) or co.co_freevars != ():
|
||||
raise AssertionError # pragma: no cover
|
||||
|
||||
# Convert this code object to a code object that sets the
|
||||
# function's first _freevar_ (not cellvar) to the argument.
|
||||
if sys.version_info >= (3, 8):
|
||||
|
||||
def set_closure_cell(cell, value):
|
||||
cell.cell_contents = value
|
||||
|
||||
else:
|
||||
args = [co.co_argcount]
|
||||
args.append(co.co_kwonlyargcount)
|
||||
args.extend(
|
||||
[
|
||||
co.co_nlocals,
|
||||
co.co_stacksize,
|
||||
co.co_flags,
|
||||
co.co_code,
|
||||
co.co_consts,
|
||||
co.co_names,
|
||||
co.co_varnames,
|
||||
co.co_filename,
|
||||
co.co_name,
|
||||
co.co_firstlineno,
|
||||
co.co_lnotab,
|
||||
# These two arguments are reversed:
|
||||
co.co_cellvars,
|
||||
co.co_freevars,
|
||||
]
|
||||
)
|
||||
set_first_freevar_code = types.CodeType(*args)
|
||||
|
||||
def set_closure_cell(cell, value):
|
||||
# Create a function using the set_first_freevar_code,
|
||||
# whose first closure cell is `cell`. Calling it will
|
||||
# change the value of that cell.
|
||||
setter = types.FunctionType(
|
||||
set_first_freevar_code, {}, "setter", (), (cell,)
|
||||
)
|
||||
# And call it to set the cell.
|
||||
setter(value)
|
||||
|
||||
# Make sure it works on this interpreter:
|
||||
def make_func_with_cell():
|
||||
x = None
|
||||
|
||||
def func():
|
||||
return x # pragma: no cover
|
||||
|
||||
return func
|
||||
|
||||
cell = make_func_with_cell().__closure__[0]
|
||||
set_closure_cell(cell, 100)
|
||||
if cell.cell_contents != 100:
|
||||
raise AssertionError # pragma: no cover
|
||||
|
||||
except Exception:
|
||||
return just_warn
|
||||
else:
|
||||
return set_closure_cell
|
||||
|
||||
|
||||
set_closure_cell = make_set_closure_cell()
|
||||
|
||||
# Thread-local global to track attrs instances which are already being repr'd.
|
||||
# This is needed because there is no other (thread-safe) way to pass info
|
||||
# about the instances that are already being repr'd through the call stack
|
||||
# in order to ensure we don't perform infinite recursion.
|
||||
#
|
||||
# For instance, if an instance contains a dict which contains that instance,
|
||||
# we need to know that we're already repr'ing the outside instance from within
|
||||
# the dict's repr() call.
|
||||
#
|
||||
# This lives here rather than in _make.py so that the functions in _make.py
|
||||
# don't have a direct reference to the thread-local in their globals dict.
|
||||
# If they have such a reference, it breaks cloudpickle.
|
||||
repr_context = threading.local()
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
|
||||
__all__ = ["set_run_validators", "get_run_validators"]
|
||||
|
||||
_run_validators = True
|
||||
|
||||
|
||||
def set_run_validators(run):
|
||||
"""
|
||||
Set whether or not validators are run. By default, they are run.
|
||||
|
||||
.. deprecated:: 21.3.0 It will not be removed, but it also will not be
|
||||
moved to new ``attrs`` namespace. Use `attrs.validators.set_disabled()`
|
||||
instead.
|
||||
"""
|
||||
if not isinstance(run, bool):
|
||||
raise TypeError("'run' must be bool.")
|
||||
global _run_validators
|
||||
_run_validators = run
|
||||
|
||||
|
||||
def get_run_validators():
|
||||
"""
|
||||
Return whether or not validators are run.
|
||||
|
||||
.. deprecated:: 21.3.0 It will not be removed, but it also will not be
|
||||
moved to new ``attrs`` namespace. Use `attrs.validators.get_disabled()`
|
||||
instead.
|
||||
"""
|
||||
return _run_validators
|
||||
|
|
@ -0,0 +1,420 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
|
||||
import copy
|
||||
|
||||
from ._make import NOTHING, _obj_setattr, fields
|
||||
from .exceptions import AttrsAttributeNotFoundError
|
||||
|
||||
|
||||
def asdict(
|
||||
inst,
|
||||
recurse=True,
|
||||
filter=None,
|
||||
dict_factory=dict,
|
||||
retain_collection_types=False,
|
||||
value_serializer=None,
|
||||
):
|
||||
"""
|
||||
Return the ``attrs`` attribute values of *inst* as a dict.
|
||||
|
||||
Optionally recurse into other ``attrs``-decorated classes.
|
||||
|
||||
:param inst: Instance of an ``attrs``-decorated class.
|
||||
:param bool recurse: Recurse into classes that are also
|
||||
``attrs``-decorated.
|
||||
:param callable filter: A callable whose return code determines whether an
|
||||
attribute or element is included (``True``) or dropped (``False``). Is
|
||||
called with the `attrs.Attribute` as the first argument and the
|
||||
value as the second argument.
|
||||
:param callable dict_factory: A callable to produce dictionaries from. For
|
||||
example, to produce ordered dictionaries instead of normal Python
|
||||
dictionaries, pass in ``collections.OrderedDict``.
|
||||
:param bool retain_collection_types: Do not convert to ``list`` when
|
||||
encountering an attribute whose type is ``tuple`` or ``set``. Only
|
||||
meaningful if ``recurse`` is ``True``.
|
||||
:param Optional[callable] value_serializer: A hook that is called for every
|
||||
attribute or dict key/value. It receives the current instance, field
|
||||
and value and must return the (updated) value. The hook is run *after*
|
||||
the optional *filter* has been applied.
|
||||
|
||||
:rtype: return type of *dict_factory*
|
||||
|
||||
:raise attr.exceptions.NotAnAttrsClassError: If *cls* is not an ``attrs``
|
||||
class.
|
||||
|
||||
.. versionadded:: 16.0.0 *dict_factory*
|
||||
.. versionadded:: 16.1.0 *retain_collection_types*
|
||||
.. versionadded:: 20.3.0 *value_serializer*
|
||||
.. versionadded:: 21.3.0 If a dict has a collection for a key, it is
|
||||
serialized as a tuple.
|
||||
"""
|
||||
attrs = fields(inst.__class__)
|
||||
rv = dict_factory()
|
||||
for a in attrs:
|
||||
v = getattr(inst, a.name)
|
||||
if filter is not None and not filter(a, v):
|
||||
continue
|
||||
|
||||
if value_serializer is not None:
|
||||
v = value_serializer(inst, a, v)
|
||||
|
||||
if recurse is True:
|
||||
if has(v.__class__):
|
||||
rv[a.name] = asdict(
|
||||
v,
|
||||
recurse=True,
|
||||
filter=filter,
|
||||
dict_factory=dict_factory,
|
||||
retain_collection_types=retain_collection_types,
|
||||
value_serializer=value_serializer,
|
||||
)
|
||||
elif isinstance(v, (tuple, list, set, frozenset)):
|
||||
cf = v.__class__ if retain_collection_types is True else list
|
||||
rv[a.name] = cf(
|
||||
[
|
||||
_asdict_anything(
|
||||
i,
|
||||
is_key=False,
|
||||
filter=filter,
|
||||
dict_factory=dict_factory,
|
||||
retain_collection_types=retain_collection_types,
|
||||
value_serializer=value_serializer,
|
||||
)
|
||||
for i in v
|
||||
]
|
||||
)
|
||||
elif isinstance(v, dict):
|
||||
df = dict_factory
|
||||
rv[a.name] = df(
|
||||
(
|
||||
_asdict_anything(
|
||||
kk,
|
||||
is_key=True,
|
||||
filter=filter,
|
||||
dict_factory=df,
|
||||
retain_collection_types=retain_collection_types,
|
||||
value_serializer=value_serializer,
|
||||
),
|
||||
_asdict_anything(
|
||||
vv,
|
||||
is_key=False,
|
||||
filter=filter,
|
||||
dict_factory=df,
|
||||
retain_collection_types=retain_collection_types,
|
||||
value_serializer=value_serializer,
|
||||
),
|
||||
)
|
||||
for kk, vv in v.items()
|
||||
)
|
||||
else:
|
||||
rv[a.name] = v
|
||||
else:
|
||||
rv[a.name] = v
|
||||
return rv
|
||||
|
||||
|
||||
def _asdict_anything(
|
||||
val,
|
||||
is_key,
|
||||
filter,
|
||||
dict_factory,
|
||||
retain_collection_types,
|
||||
value_serializer,
|
||||
):
|
||||
"""
|
||||
``asdict`` only works on attrs instances, this works on anything.
|
||||
"""
|
||||
if getattr(val.__class__, "__attrs_attrs__", None) is not None:
|
||||
# Attrs class.
|
||||
rv = asdict(
|
||||
val,
|
||||
recurse=True,
|
||||
filter=filter,
|
||||
dict_factory=dict_factory,
|
||||
retain_collection_types=retain_collection_types,
|
||||
value_serializer=value_serializer,
|
||||
)
|
||||
elif isinstance(val, (tuple, list, set, frozenset)):
|
||||
if retain_collection_types is True:
|
||||
cf = val.__class__
|
||||
elif is_key:
|
||||
cf = tuple
|
||||
else:
|
||||
cf = list
|
||||
|
||||
rv = cf(
|
||||
[
|
||||
_asdict_anything(
|
||||
i,
|
||||
is_key=False,
|
||||
filter=filter,
|
||||
dict_factory=dict_factory,
|
||||
retain_collection_types=retain_collection_types,
|
||||
value_serializer=value_serializer,
|
||||
)
|
||||
for i in val
|
||||
]
|
||||
)
|
||||
elif isinstance(val, dict):
|
||||
df = dict_factory
|
||||
rv = df(
|
||||
(
|
||||
_asdict_anything(
|
||||
kk,
|
||||
is_key=True,
|
||||
filter=filter,
|
||||
dict_factory=df,
|
||||
retain_collection_types=retain_collection_types,
|
||||
value_serializer=value_serializer,
|
||||
),
|
||||
_asdict_anything(
|
||||
vv,
|
||||
is_key=False,
|
||||
filter=filter,
|
||||
dict_factory=df,
|
||||
retain_collection_types=retain_collection_types,
|
||||
value_serializer=value_serializer,
|
||||
),
|
||||
)
|
||||
for kk, vv in val.items()
|
||||
)
|
||||
else:
|
||||
rv = val
|
||||
if value_serializer is not None:
|
||||
rv = value_serializer(None, None, rv)
|
||||
|
||||
return rv
|
||||
|
||||
|
||||
def astuple(
|
||||
inst,
|
||||
recurse=True,
|
||||
filter=None,
|
||||
tuple_factory=tuple,
|
||||
retain_collection_types=False,
|
||||
):
|
||||
"""
|
||||
Return the ``attrs`` attribute values of *inst* as a tuple.
|
||||
|
||||
Optionally recurse into other ``attrs``-decorated classes.
|
||||
|
||||
:param inst: Instance of an ``attrs``-decorated class.
|
||||
:param bool recurse: Recurse into classes that are also
|
||||
``attrs``-decorated.
|
||||
:param callable filter: A callable whose return code determines whether an
|
||||
attribute or element is included (``True``) or dropped (``False``). Is
|
||||
called with the `attrs.Attribute` as the first argument and the
|
||||
value as the second argument.
|
||||
:param callable tuple_factory: A callable to produce tuples from. For
|
||||
example, to produce lists instead of tuples.
|
||||
:param bool retain_collection_types: Do not convert to ``list``
|
||||
or ``dict`` when encountering an attribute which type is
|
||||
``tuple``, ``dict`` or ``set``. Only meaningful if ``recurse`` is
|
||||
``True``.
|
||||
|
||||
:rtype: return type of *tuple_factory*
|
||||
|
||||
:raise attr.exceptions.NotAnAttrsClassError: If *cls* is not an ``attrs``
|
||||
class.
|
||||
|
||||
.. versionadded:: 16.2.0
|
||||
"""
|
||||
attrs = fields(inst.__class__)
|
||||
rv = []
|
||||
retain = retain_collection_types # Very long. :/
|
||||
for a in attrs:
|
||||
v = getattr(inst, a.name)
|
||||
if filter is not None and not filter(a, v):
|
||||
continue
|
||||
if recurse is True:
|
||||
if has(v.__class__):
|
||||
rv.append(
|
||||
astuple(
|
||||
v,
|
||||
recurse=True,
|
||||
filter=filter,
|
||||
tuple_factory=tuple_factory,
|
||||
retain_collection_types=retain,
|
||||
)
|
||||
)
|
||||
elif isinstance(v, (tuple, list, set, frozenset)):
|
||||
cf = v.__class__ if retain is True else list
|
||||
rv.append(
|
||||
cf(
|
||||
[
|
||||
astuple(
|
||||
j,
|
||||
recurse=True,
|
||||
filter=filter,
|
||||
tuple_factory=tuple_factory,
|
||||
retain_collection_types=retain,
|
||||
)
|
||||
if has(j.__class__)
|
||||
else j
|
||||
for j in v
|
||||
]
|
||||
)
|
||||
)
|
||||
elif isinstance(v, dict):
|
||||
df = v.__class__ if retain is True else dict
|
||||
rv.append(
|
||||
df(
|
||||
(
|
||||
astuple(
|
||||
kk,
|
||||
tuple_factory=tuple_factory,
|
||||
retain_collection_types=retain,
|
||||
)
|
||||
if has(kk.__class__)
|
||||
else kk,
|
||||
astuple(
|
||||
vv,
|
||||
tuple_factory=tuple_factory,
|
||||
retain_collection_types=retain,
|
||||
)
|
||||
if has(vv.__class__)
|
||||
else vv,
|
||||
)
|
||||
for kk, vv in v.items()
|
||||
)
|
||||
)
|
||||
else:
|
||||
rv.append(v)
|
||||
else:
|
||||
rv.append(v)
|
||||
|
||||
return rv if tuple_factory is list else tuple_factory(rv)
|
||||
|
||||
|
||||
def has(cls):
|
||||
"""
|
||||
Check whether *cls* is a class with ``attrs`` attributes.
|
||||
|
||||
:param type cls: Class to introspect.
|
||||
:raise TypeError: If *cls* is not a class.
|
||||
|
||||
:rtype: bool
|
||||
"""
|
||||
return getattr(cls, "__attrs_attrs__", None) is not None
|
||||
|
||||
|
||||
def assoc(inst, **changes):
|
||||
"""
|
||||
Copy *inst* and apply *changes*.
|
||||
|
||||
:param inst: Instance of a class with ``attrs`` attributes.
|
||||
:param changes: Keyword changes in the new copy.
|
||||
|
||||
:return: A copy of inst with *changes* incorporated.
|
||||
|
||||
:raise attr.exceptions.AttrsAttributeNotFoundError: If *attr_name* couldn't
|
||||
be found on *cls*.
|
||||
:raise attr.exceptions.NotAnAttrsClassError: If *cls* is not an ``attrs``
|
||||
class.
|
||||
|
||||
.. deprecated:: 17.1.0
|
||||
Use `attrs.evolve` instead if you can.
|
||||
This function will not be removed du to the slightly different approach
|
||||
compared to `attrs.evolve`.
|
||||
"""
|
||||
import warnings
|
||||
|
||||
warnings.warn(
|
||||
"assoc is deprecated and will be removed after 2018/01.",
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
new = copy.copy(inst)
|
||||
attrs = fields(inst.__class__)
|
||||
for k, v in changes.items():
|
||||
a = getattr(attrs, k, NOTHING)
|
||||
if a is NOTHING:
|
||||
raise AttrsAttributeNotFoundError(
|
||||
"{k} is not an attrs attribute on {cl}.".format(
|
||||
k=k, cl=new.__class__
|
||||
)
|
||||
)
|
||||
_obj_setattr(new, k, v)
|
||||
return new
|
||||
|
||||
|
||||
def evolve(inst, **changes):
|
||||
"""
|
||||
Create a new instance, based on *inst* with *changes* applied.
|
||||
|
||||
:param inst: Instance of a class with ``attrs`` attributes.
|
||||
:param changes: Keyword changes in the new copy.
|
||||
|
||||
:return: A copy of inst with *changes* incorporated.
|
||||
|
||||
:raise TypeError: If *attr_name* couldn't be found in the class
|
||||
``__init__``.
|
||||
:raise attr.exceptions.NotAnAttrsClassError: If *cls* is not an ``attrs``
|
||||
class.
|
||||
|
||||
.. versionadded:: 17.1.0
|
||||
"""
|
||||
cls = inst.__class__
|
||||
attrs = fields(cls)
|
||||
for a in attrs:
|
||||
if not a.init:
|
||||
continue
|
||||
attr_name = a.name # To deal with private attributes.
|
||||
init_name = attr_name if attr_name[0] != "_" else attr_name[1:]
|
||||
if init_name not in changes:
|
||||
changes[init_name] = getattr(inst, attr_name)
|
||||
|
||||
return cls(**changes)
|
||||
|
||||
|
||||
def resolve_types(cls, globalns=None, localns=None, attribs=None):
|
||||
"""
|
||||
Resolve any strings and forward annotations in type annotations.
|
||||
|
||||
This is only required if you need concrete types in `Attribute`'s *type*
|
||||
field. In other words, you don't need to resolve your types if you only
|
||||
use them for static type checking.
|
||||
|
||||
With no arguments, names will be looked up in the module in which the class
|
||||
was created. If this is not what you want, e.g. if the name only exists
|
||||
inside a method, you may pass *globalns* or *localns* to specify other
|
||||
dictionaries in which to look up these names. See the docs of
|
||||
`typing.get_type_hints` for more details.
|
||||
|
||||
:param type cls: Class to resolve.
|
||||
:param Optional[dict] globalns: Dictionary containing global variables.
|
||||
:param Optional[dict] localns: Dictionary containing local variables.
|
||||
:param Optional[list] attribs: List of attribs for the given class.
|
||||
This is necessary when calling from inside a ``field_transformer``
|
||||
since *cls* is not an ``attrs`` class yet.
|
||||
|
||||
:raise TypeError: If *cls* is not a class.
|
||||
:raise attr.exceptions.NotAnAttrsClassError: If *cls* is not an ``attrs``
|
||||
class and you didn't pass any attribs.
|
||||
:raise NameError: If types cannot be resolved because of missing variables.
|
||||
|
||||
:returns: *cls* so you can use this function also as a class decorator.
|
||||
Please note that you have to apply it **after** `attrs.define`. That
|
||||
means the decorator has to come in the line **before** `attrs.define`.
|
||||
|
||||
.. versionadded:: 20.1.0
|
||||
.. versionadded:: 21.1.0 *attribs*
|
||||
|
||||
"""
|
||||
# Since calling get_type_hints is expensive we cache whether we've
|
||||
# done it already.
|
||||
if getattr(cls, "__attrs_types_resolved__", None) != cls:
|
||||
import typing
|
||||
|
||||
hints = typing.get_type_hints(cls, globalns=globalns, localns=localns)
|
||||
for field in fields(cls) if attribs is None else attribs:
|
||||
if field.name in hints:
|
||||
# Since fields have been frozen we must work around it.
|
||||
_obj_setattr(field, "type", hints[field.name])
|
||||
# We store the class we resolved so that subclasses know they haven't
|
||||
# been resolved.
|
||||
cls.__attrs_types_resolved__ = cls
|
||||
|
||||
# Return the class so you can use it as a decorator too.
|
||||
return cls
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,220 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
"""
|
||||
These are Python 3.6+-only and keyword-only APIs that call `attr.s` and
|
||||
`attr.ib` with different default values.
|
||||
"""
|
||||
|
||||
|
||||
from functools import partial
|
||||
|
||||
from . import setters
|
||||
from ._funcs import asdict as _asdict
|
||||
from ._funcs import astuple as _astuple
|
||||
from ._make import (
|
||||
NOTHING,
|
||||
_frozen_setattrs,
|
||||
_ng_default_on_setattr,
|
||||
attrib,
|
||||
attrs,
|
||||
)
|
||||
from .exceptions import UnannotatedAttributeError
|
||||
|
||||
|
||||
def define(
|
||||
maybe_cls=None,
|
||||
*,
|
||||
these=None,
|
||||
repr=None,
|
||||
hash=None,
|
||||
init=None,
|
||||
slots=True,
|
||||
frozen=False,
|
||||
weakref_slot=True,
|
||||
str=False,
|
||||
auto_attribs=None,
|
||||
kw_only=False,
|
||||
cache_hash=False,
|
||||
auto_exc=True,
|
||||
eq=None,
|
||||
order=False,
|
||||
auto_detect=True,
|
||||
getstate_setstate=None,
|
||||
on_setattr=None,
|
||||
field_transformer=None,
|
||||
match_args=True,
|
||||
):
|
||||
r"""
|
||||
Define an ``attrs`` class.
|
||||
|
||||
Differences to the classic `attr.s` that it uses underneath:
|
||||
|
||||
- Automatically detect whether or not *auto_attribs* should be `True` (c.f.
|
||||
*auto_attribs* parameter).
|
||||
- If *frozen* is `False`, run converters and validators when setting an
|
||||
attribute by default.
|
||||
- *slots=True*
|
||||
|
||||
.. caution::
|
||||
|
||||
Usually this has only upsides and few visible effects in everyday
|
||||
programming. But it *can* lead to some suprising behaviors, so please
|
||||
make sure to read :term:`slotted classes`.
|
||||
- *auto_exc=True*
|
||||
- *auto_detect=True*
|
||||
- *order=False*
|
||||
- Some options that were only relevant on Python 2 or were kept around for
|
||||
backwards-compatibility have been removed.
|
||||
|
||||
Please note that these are all defaults and you can change them as you
|
||||
wish.
|
||||
|
||||
:param Optional[bool] auto_attribs: If set to `True` or `False`, it behaves
|
||||
exactly like `attr.s`. If left `None`, `attr.s` will try to guess:
|
||||
|
||||
1. If any attributes are annotated and no unannotated `attrs.fields`\ s
|
||||
are found, it assumes *auto_attribs=True*.
|
||||
2. Otherwise it assumes *auto_attribs=False* and tries to collect
|
||||
`attrs.fields`\ s.
|
||||
|
||||
For now, please refer to `attr.s` for the rest of the parameters.
|
||||
|
||||
.. versionadded:: 20.1.0
|
||||
.. versionchanged:: 21.3.0 Converters are also run ``on_setattr``.
|
||||
"""
|
||||
|
||||
def do_it(cls, auto_attribs):
|
||||
return attrs(
|
||||
maybe_cls=cls,
|
||||
these=these,
|
||||
repr=repr,
|
||||
hash=hash,
|
||||
init=init,
|
||||
slots=slots,
|
||||
frozen=frozen,
|
||||
weakref_slot=weakref_slot,
|
||||
str=str,
|
||||
auto_attribs=auto_attribs,
|
||||
kw_only=kw_only,
|
||||
cache_hash=cache_hash,
|
||||
auto_exc=auto_exc,
|
||||
eq=eq,
|
||||
order=order,
|
||||
auto_detect=auto_detect,
|
||||
collect_by_mro=True,
|
||||
getstate_setstate=getstate_setstate,
|
||||
on_setattr=on_setattr,
|
||||
field_transformer=field_transformer,
|
||||
match_args=match_args,
|
||||
)
|
||||
|
||||
def wrap(cls):
|
||||
"""
|
||||
Making this a wrapper ensures this code runs during class creation.
|
||||
|
||||
We also ensure that frozen-ness of classes is inherited.
|
||||
"""
|
||||
nonlocal frozen, on_setattr
|
||||
|
||||
had_on_setattr = on_setattr not in (None, setters.NO_OP)
|
||||
|
||||
# By default, mutable classes convert & validate on setattr.
|
||||
if frozen is False and on_setattr is None:
|
||||
on_setattr = _ng_default_on_setattr
|
||||
|
||||
# However, if we subclass a frozen class, we inherit the immutability
|
||||
# and disable on_setattr.
|
||||
for base_cls in cls.__bases__:
|
||||
if base_cls.__setattr__ is _frozen_setattrs:
|
||||
if had_on_setattr:
|
||||
raise ValueError(
|
||||
"Frozen classes can't use on_setattr "
|
||||
"(frozen-ness was inherited)."
|
||||
)
|
||||
|
||||
on_setattr = setters.NO_OP
|
||||
break
|
||||
|
||||
if auto_attribs is not None:
|
||||
return do_it(cls, auto_attribs)
|
||||
|
||||
try:
|
||||
return do_it(cls, True)
|
||||
except UnannotatedAttributeError:
|
||||
return do_it(cls, False)
|
||||
|
||||
# maybe_cls's type depends on the usage of the decorator. It's a class
|
||||
# if it's used as `@attrs` but ``None`` if used as `@attrs()`.
|
||||
if maybe_cls is None:
|
||||
return wrap
|
||||
else:
|
||||
return wrap(maybe_cls)
|
||||
|
||||
|
||||
mutable = define
|
||||
frozen = partial(define, frozen=True, on_setattr=None)
|
||||
|
||||
|
||||
def field(
|
||||
*,
|
||||
default=NOTHING,
|
||||
validator=None,
|
||||
repr=True,
|
||||
hash=None,
|
||||
init=True,
|
||||
metadata=None,
|
||||
converter=None,
|
||||
factory=None,
|
||||
kw_only=False,
|
||||
eq=None,
|
||||
order=None,
|
||||
on_setattr=None,
|
||||
):
|
||||
"""
|
||||
Identical to `attr.ib`, except keyword-only and with some arguments
|
||||
removed.
|
||||
|
||||
.. versionadded:: 20.1.0
|
||||
"""
|
||||
return attrib(
|
||||
default=default,
|
||||
validator=validator,
|
||||
repr=repr,
|
||||
hash=hash,
|
||||
init=init,
|
||||
metadata=metadata,
|
||||
converter=converter,
|
||||
factory=factory,
|
||||
kw_only=kw_only,
|
||||
eq=eq,
|
||||
order=order,
|
||||
on_setattr=on_setattr,
|
||||
)
|
||||
|
||||
|
||||
def asdict(inst, *, recurse=True, filter=None, value_serializer=None):
|
||||
"""
|
||||
Same as `attr.asdict`, except that collections types are always retained
|
||||
and dict is always used as *dict_factory*.
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
return _asdict(
|
||||
inst=inst,
|
||||
recurse=recurse,
|
||||
filter=filter,
|
||||
value_serializer=value_serializer,
|
||||
retain_collection_types=True,
|
||||
)
|
||||
|
||||
|
||||
def astuple(inst, *, recurse=True, filter=None):
|
||||
"""
|
||||
Same as `attr.astuple`, except that collections types are always retained
|
||||
and `tuple` is always used as the *tuple_factory*.
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
return _astuple(
|
||||
inst=inst, recurse=recurse, filter=filter, retain_collection_types=True
|
||||
)
|
||||
|
|
@ -0,0 +1,86 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
|
||||
from functools import total_ordering
|
||||
|
||||
from ._funcs import astuple
|
||||
from ._make import attrib, attrs
|
||||
|
||||
|
||||
@total_ordering
|
||||
@attrs(eq=False, order=False, slots=True, frozen=True)
|
||||
class VersionInfo:
|
||||
"""
|
||||
A version object that can be compared to tuple of length 1--4:
|
||||
|
||||
>>> attr.VersionInfo(19, 1, 0, "final") <= (19, 2)
|
||||
True
|
||||
>>> attr.VersionInfo(19, 1, 0, "final") < (19, 1, 1)
|
||||
True
|
||||
>>> vi = attr.VersionInfo(19, 2, 0, "final")
|
||||
>>> vi < (19, 1, 1)
|
||||
False
|
||||
>>> vi < (19,)
|
||||
False
|
||||
>>> vi == (19, 2,)
|
||||
True
|
||||
>>> vi == (19, 2, 1)
|
||||
False
|
||||
|
||||
.. versionadded:: 19.2
|
||||
"""
|
||||
|
||||
year = attrib(type=int)
|
||||
minor = attrib(type=int)
|
||||
micro = attrib(type=int)
|
||||
releaselevel = attrib(type=str)
|
||||
|
||||
@classmethod
|
||||
def _from_version_string(cls, s):
|
||||
"""
|
||||
Parse *s* and return a _VersionInfo.
|
||||
"""
|
||||
v = s.split(".")
|
||||
if len(v) == 3:
|
||||
v.append("final")
|
||||
|
||||
return cls(
|
||||
year=int(v[0]), minor=int(v[1]), micro=int(v[2]), releaselevel=v[3]
|
||||
)
|
||||
|
||||
def _ensure_tuple(self, other):
|
||||
"""
|
||||
Ensure *other* is a tuple of a valid length.
|
||||
|
||||
Returns a possibly transformed *other* and ourselves as a tuple of
|
||||
the same length as *other*.
|
||||
"""
|
||||
|
||||
if self.__class__ is other.__class__:
|
||||
other = astuple(other)
|
||||
|
||||
if not isinstance(other, tuple):
|
||||
raise NotImplementedError
|
||||
|
||||
if not (1 <= len(other) <= 4):
|
||||
raise NotImplementedError
|
||||
|
||||
return astuple(self)[: len(other)], other
|
||||
|
||||
def __eq__(self, other):
|
||||
try:
|
||||
us, them = self._ensure_tuple(other)
|
||||
except NotImplementedError:
|
||||
return NotImplemented
|
||||
|
||||
return us == them
|
||||
|
||||
def __lt__(self, other):
|
||||
try:
|
||||
us, them = self._ensure_tuple(other)
|
||||
except NotImplementedError:
|
||||
return NotImplemented
|
||||
|
||||
# Since alphabetically "dev0" < "final" < "post1" < "post2", we don't
|
||||
# have to do anything special with releaselevel for now.
|
||||
return us < them
|
||||
|
|
@ -0,0 +1,144 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
"""
|
||||
Commonly useful converters.
|
||||
"""
|
||||
|
||||
|
||||
import typing
|
||||
|
||||
from ._compat import _AnnotationExtractor
|
||||
from ._make import NOTHING, Factory, pipe
|
||||
|
||||
|
||||
__all__ = [
|
||||
"default_if_none",
|
||||
"optional",
|
||||
"pipe",
|
||||
"to_bool",
|
||||
]
|
||||
|
||||
|
||||
def optional(converter):
|
||||
"""
|
||||
A converter that allows an attribute to be optional. An optional attribute
|
||||
is one which can be set to ``None``.
|
||||
|
||||
Type annotations will be inferred from the wrapped converter's, if it
|
||||
has any.
|
||||
|
||||
:param callable converter: the converter that is used for non-``None``
|
||||
values.
|
||||
|
||||
.. versionadded:: 17.1.0
|
||||
"""
|
||||
|
||||
def optional_converter(val):
|
||||
if val is None:
|
||||
return None
|
||||
return converter(val)
|
||||
|
||||
xtr = _AnnotationExtractor(converter)
|
||||
|
||||
t = xtr.get_first_param_type()
|
||||
if t:
|
||||
optional_converter.__annotations__["val"] = typing.Optional[t]
|
||||
|
||||
rt = xtr.get_return_type()
|
||||
if rt:
|
||||
optional_converter.__annotations__["return"] = typing.Optional[rt]
|
||||
|
||||
return optional_converter
|
||||
|
||||
|
||||
def default_if_none(default=NOTHING, factory=None):
|
||||
"""
|
||||
A converter that allows to replace ``None`` values by *default* or the
|
||||
result of *factory*.
|
||||
|
||||
:param default: Value to be used if ``None`` is passed. Passing an instance
|
||||
of `attrs.Factory` is supported, however the ``takes_self`` option
|
||||
is *not*.
|
||||
:param callable factory: A callable that takes no parameters whose result
|
||||
is used if ``None`` is passed.
|
||||
|
||||
:raises TypeError: If **neither** *default* or *factory* is passed.
|
||||
:raises TypeError: If **both** *default* and *factory* are passed.
|
||||
:raises ValueError: If an instance of `attrs.Factory` is passed with
|
||||
``takes_self=True``.
|
||||
|
||||
.. versionadded:: 18.2.0
|
||||
"""
|
||||
if default is NOTHING and factory is None:
|
||||
raise TypeError("Must pass either `default` or `factory`.")
|
||||
|
||||
if default is not NOTHING and factory is not None:
|
||||
raise TypeError(
|
||||
"Must pass either `default` or `factory` but not both."
|
||||
)
|
||||
|
||||
if factory is not None:
|
||||
default = Factory(factory)
|
||||
|
||||
if isinstance(default, Factory):
|
||||
if default.takes_self:
|
||||
raise ValueError(
|
||||
"`takes_self` is not supported by default_if_none."
|
||||
)
|
||||
|
||||
def default_if_none_converter(val):
|
||||
if val is not None:
|
||||
return val
|
||||
|
||||
return default.factory()
|
||||
|
||||
else:
|
||||
|
||||
def default_if_none_converter(val):
|
||||
if val is not None:
|
||||
return val
|
||||
|
||||
return default
|
||||
|
||||
return default_if_none_converter
|
||||
|
||||
|
||||
def to_bool(val):
|
||||
"""
|
||||
Convert "boolean" strings (e.g., from env. vars.) to real booleans.
|
||||
|
||||
Values mapping to :code:`True`:
|
||||
|
||||
- :code:`True`
|
||||
- :code:`"true"` / :code:`"t"`
|
||||
- :code:`"yes"` / :code:`"y"`
|
||||
- :code:`"on"`
|
||||
- :code:`"1"`
|
||||
- :code:`1`
|
||||
|
||||
Values mapping to :code:`False`:
|
||||
|
||||
- :code:`False`
|
||||
- :code:`"false"` / :code:`"f"`
|
||||
- :code:`"no"` / :code:`"n"`
|
||||
- :code:`"off"`
|
||||
- :code:`"0"`
|
||||
- :code:`0`
|
||||
|
||||
:raises ValueError: for any other value.
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
if isinstance(val, str):
|
||||
val = val.lower()
|
||||
truthy = {True, "true", "t", "yes", "y", "on", "1", 1}
|
||||
falsy = {False, "false", "f", "no", "n", "off", "0", 0}
|
||||
try:
|
||||
if val in truthy:
|
||||
return True
|
||||
if val in falsy:
|
||||
return False
|
||||
except TypeError:
|
||||
# Raised when "val" is not hashable (e.g., lists)
|
||||
pass
|
||||
raise ValueError("Cannot convert value to bool: {}".format(val))
|
||||
|
|
@ -0,0 +1,92 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
|
||||
class FrozenError(AttributeError):
|
||||
"""
|
||||
A frozen/immutable instance or attribute have been attempted to be
|
||||
modified.
|
||||
|
||||
It mirrors the behavior of ``namedtuples`` by using the same error message
|
||||
and subclassing `AttributeError`.
|
||||
|
||||
.. versionadded:: 20.1.0
|
||||
"""
|
||||
|
||||
msg = "can't set attribute"
|
||||
args = [msg]
|
||||
|
||||
|
||||
class FrozenInstanceError(FrozenError):
|
||||
"""
|
||||
A frozen instance has been attempted to be modified.
|
||||
|
||||
.. versionadded:: 16.1.0
|
||||
"""
|
||||
|
||||
|
||||
class FrozenAttributeError(FrozenError):
|
||||
"""
|
||||
A frozen attribute has been attempted to be modified.
|
||||
|
||||
.. versionadded:: 20.1.0
|
||||
"""
|
||||
|
||||
|
||||
class AttrsAttributeNotFoundError(ValueError):
|
||||
"""
|
||||
An ``attrs`` function couldn't find an attribute that the user asked for.
|
||||
|
||||
.. versionadded:: 16.2.0
|
||||
"""
|
||||
|
||||
|
||||
class NotAnAttrsClassError(ValueError):
|
||||
"""
|
||||
A non-``attrs`` class has been passed into an ``attrs`` function.
|
||||
|
||||
.. versionadded:: 16.2.0
|
||||
"""
|
||||
|
||||
|
||||
class DefaultAlreadySetError(RuntimeError):
|
||||
"""
|
||||
A default has been set using ``attr.ib()`` and is attempted to be reset
|
||||
using the decorator.
|
||||
|
||||
.. versionadded:: 17.1.0
|
||||
"""
|
||||
|
||||
|
||||
class UnannotatedAttributeError(RuntimeError):
|
||||
"""
|
||||
A class with ``auto_attribs=True`` has an ``attr.ib()`` without a type
|
||||
annotation.
|
||||
|
||||
.. versionadded:: 17.3.0
|
||||
"""
|
||||
|
||||
|
||||
class PythonTooOldError(RuntimeError):
|
||||
"""
|
||||
It was attempted to use an ``attrs`` feature that requires a newer Python
|
||||
version.
|
||||
|
||||
.. versionadded:: 18.2.0
|
||||
"""
|
||||
|
||||
|
||||
class NotCallableError(TypeError):
|
||||
"""
|
||||
A ``attr.ib()`` requiring a callable has been set with a value
|
||||
that is not callable.
|
||||
|
||||
.. versionadded:: 19.2.0
|
||||
"""
|
||||
|
||||
def __init__(self, msg, value):
|
||||
super(TypeError, self).__init__(msg, value)
|
||||
self.msg = msg
|
||||
self.value = value
|
||||
|
||||
def __str__(self):
|
||||
return str(self.msg)
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
"""
|
||||
Commonly useful filters for `attr.asdict`.
|
||||
"""
|
||||
|
||||
from ._make import Attribute
|
||||
|
||||
|
||||
def _split_what(what):
|
||||
"""
|
||||
Returns a tuple of `frozenset`s of classes and attributes.
|
||||
"""
|
||||
return (
|
||||
frozenset(cls for cls in what if isinstance(cls, type)),
|
||||
frozenset(cls for cls in what if isinstance(cls, Attribute)),
|
||||
)
|
||||
|
||||
|
||||
def include(*what):
|
||||
"""
|
||||
Include *what*.
|
||||
|
||||
:param what: What to include.
|
||||
:type what: `list` of `type` or `attrs.Attribute`\\ s
|
||||
|
||||
:rtype: `callable`
|
||||
"""
|
||||
cls, attrs = _split_what(what)
|
||||
|
||||
def include_(attribute, value):
|
||||
return value.__class__ in cls or attribute in attrs
|
||||
|
||||
return include_
|
||||
|
||||
|
||||
def exclude(*what):
|
||||
"""
|
||||
Exclude *what*.
|
||||
|
||||
:param what: What to exclude.
|
||||
:type what: `list` of classes or `attrs.Attribute`\\ s.
|
||||
|
||||
:rtype: `callable`
|
||||
"""
|
||||
cls, attrs = _split_what(what)
|
||||
|
||||
def exclude_(attribute, value):
|
||||
return value.__class__ not in cls and attribute not in attrs
|
||||
|
||||
return exclude_
|
||||
|
|
@ -0,0 +1,73 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
"""
|
||||
Commonly used hooks for on_setattr.
|
||||
"""
|
||||
|
||||
|
||||
from . import _config
|
||||
from .exceptions import FrozenAttributeError
|
||||
|
||||
|
||||
def pipe(*setters):
|
||||
"""
|
||||
Run all *setters* and return the return value of the last one.
|
||||
|
||||
.. versionadded:: 20.1.0
|
||||
"""
|
||||
|
||||
def wrapped_pipe(instance, attrib, new_value):
|
||||
rv = new_value
|
||||
|
||||
for setter in setters:
|
||||
rv = setter(instance, attrib, rv)
|
||||
|
||||
return rv
|
||||
|
||||
return wrapped_pipe
|
||||
|
||||
|
||||
def frozen(_, __, ___):
|
||||
"""
|
||||
Prevent an attribute to be modified.
|
||||
|
||||
.. versionadded:: 20.1.0
|
||||
"""
|
||||
raise FrozenAttributeError()
|
||||
|
||||
|
||||
def validate(instance, attrib, new_value):
|
||||
"""
|
||||
Run *attrib*'s validator on *new_value* if it has one.
|
||||
|
||||
.. versionadded:: 20.1.0
|
||||
"""
|
||||
if _config._run_validators is False:
|
||||
return new_value
|
||||
|
||||
v = attrib.validator
|
||||
if not v:
|
||||
return new_value
|
||||
|
||||
v(instance, attrib, new_value)
|
||||
|
||||
return new_value
|
||||
|
||||
|
||||
def convert(instance, attrib, new_value):
|
||||
"""
|
||||
Run *attrib*'s converter -- if it has one -- on *new_value* and return the
|
||||
result.
|
||||
|
||||
.. versionadded:: 20.1.0
|
||||
"""
|
||||
c = attrib.converter
|
||||
if c:
|
||||
return c(new_value)
|
||||
|
||||
return new_value
|
||||
|
||||
|
||||
# Sentinel for disabling class-wide *on_setattr* hooks for certain attributes.
|
||||
# autodata stopped working, so the docstring is inlined in the API docs.
|
||||
NO_OP = object()
|
||||
|
|
@ -0,0 +1,594 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
"""
|
||||
Commonly useful validators.
|
||||
"""
|
||||
|
||||
|
||||
import operator
|
||||
import re
|
||||
|
||||
from contextlib import contextmanager
|
||||
|
||||
from ._config import get_run_validators, set_run_validators
|
||||
from ._make import _AndValidator, and_, attrib, attrs
|
||||
from .exceptions import NotCallableError
|
||||
|
||||
|
||||
try:
|
||||
Pattern = re.Pattern
|
||||
except AttributeError: # Python <3.7 lacks a Pattern type.
|
||||
Pattern = type(re.compile(""))
|
||||
|
||||
|
||||
__all__ = [
|
||||
"and_",
|
||||
"deep_iterable",
|
||||
"deep_mapping",
|
||||
"disabled",
|
||||
"ge",
|
||||
"get_disabled",
|
||||
"gt",
|
||||
"in_",
|
||||
"instance_of",
|
||||
"is_callable",
|
||||
"le",
|
||||
"lt",
|
||||
"matches_re",
|
||||
"max_len",
|
||||
"min_len",
|
||||
"optional",
|
||||
"provides",
|
||||
"set_disabled",
|
||||
]
|
||||
|
||||
|
||||
def set_disabled(disabled):
|
||||
"""
|
||||
Globally disable or enable running validators.
|
||||
|
||||
By default, they are run.
|
||||
|
||||
:param disabled: If ``True``, disable running all validators.
|
||||
:type disabled: bool
|
||||
|
||||
.. warning::
|
||||
|
||||
This function is not thread-safe!
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
set_run_validators(not disabled)
|
||||
|
||||
|
||||
def get_disabled():
|
||||
"""
|
||||
Return a bool indicating whether validators are currently disabled or not.
|
||||
|
||||
:return: ``True`` if validators are currently disabled.
|
||||
:rtype: bool
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
return not get_run_validators()
|
||||
|
||||
|
||||
@contextmanager
|
||||
def disabled():
|
||||
"""
|
||||
Context manager that disables running validators within its context.
|
||||
|
||||
.. warning::
|
||||
|
||||
This context manager is not thread-safe!
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
set_run_validators(False)
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
set_run_validators(True)
|
||||
|
||||
|
||||
@attrs(repr=False, slots=True, hash=True)
|
||||
class _InstanceOfValidator:
|
||||
type = attrib()
|
||||
|
||||
def __call__(self, inst, attr, value):
|
||||
"""
|
||||
We use a callable class to be able to change the ``__repr__``.
|
||||
"""
|
||||
if not isinstance(value, self.type):
|
||||
raise TypeError(
|
||||
"'{name}' must be {type!r} (got {value!r} that is a "
|
||||
"{actual!r}).".format(
|
||||
name=attr.name,
|
||||
type=self.type,
|
||||
actual=value.__class__,
|
||||
value=value,
|
||||
),
|
||||
attr,
|
||||
self.type,
|
||||
value,
|
||||
)
|
||||
|
||||
def __repr__(self):
|
||||
return "<instance_of validator for type {type!r}>".format(
|
||||
type=self.type
|
||||
)
|
||||
|
||||
|
||||
def instance_of(type):
|
||||
"""
|
||||
A validator that raises a `TypeError` if the initializer is called
|
||||
with a wrong type for this particular attribute (checks are performed using
|
||||
`isinstance` therefore it's also valid to pass a tuple of types).
|
||||
|
||||
:param type: The type to check for.
|
||||
:type type: type or tuple of types
|
||||
|
||||
:raises TypeError: With a human readable error message, the attribute
|
||||
(of type `attrs.Attribute`), the expected type, and the value it
|
||||
got.
|
||||
"""
|
||||
return _InstanceOfValidator(type)
|
||||
|
||||
|
||||
@attrs(repr=False, frozen=True, slots=True)
|
||||
class _MatchesReValidator:
|
||||
pattern = attrib()
|
||||
match_func = attrib()
|
||||
|
||||
def __call__(self, inst, attr, value):
|
||||
"""
|
||||
We use a callable class to be able to change the ``__repr__``.
|
||||
"""
|
||||
if not self.match_func(value):
|
||||
raise ValueError(
|
||||
"'{name}' must match regex {pattern!r}"
|
||||
" ({value!r} doesn't)".format(
|
||||
name=attr.name, pattern=self.pattern.pattern, value=value
|
||||
),
|
||||
attr,
|
||||
self.pattern,
|
||||
value,
|
||||
)
|
||||
|
||||
def __repr__(self):
|
||||
return "<matches_re validator for pattern {pattern!r}>".format(
|
||||
pattern=self.pattern
|
||||
)
|
||||
|
||||
|
||||
def matches_re(regex, flags=0, func=None):
|
||||
r"""
|
||||
A validator that raises `ValueError` if the initializer is called
|
||||
with a string that doesn't match *regex*.
|
||||
|
||||
:param regex: a regex string or precompiled pattern to match against
|
||||
:param int flags: flags that will be passed to the underlying re function
|
||||
(default 0)
|
||||
:param callable func: which underlying `re` function to call. Valid options
|
||||
are `re.fullmatch`, `re.search`, and `re.match`; the default ``None``
|
||||
means `re.fullmatch`. For performance reasons, the pattern is always
|
||||
precompiled using `re.compile`.
|
||||
|
||||
.. versionadded:: 19.2.0
|
||||
.. versionchanged:: 21.3.0 *regex* can be a pre-compiled pattern.
|
||||
"""
|
||||
valid_funcs = (re.fullmatch, None, re.search, re.match)
|
||||
if func not in valid_funcs:
|
||||
raise ValueError(
|
||||
"'func' must be one of {}.".format(
|
||||
", ".join(
|
||||
sorted(
|
||||
e and e.__name__ or "None" for e in set(valid_funcs)
|
||||
)
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
if isinstance(regex, Pattern):
|
||||
if flags:
|
||||
raise TypeError(
|
||||
"'flags' can only be used with a string pattern; "
|
||||
"pass flags to re.compile() instead"
|
||||
)
|
||||
pattern = regex
|
||||
else:
|
||||
pattern = re.compile(regex, flags)
|
||||
|
||||
if func is re.match:
|
||||
match_func = pattern.match
|
||||
elif func is re.search:
|
||||
match_func = pattern.search
|
||||
else:
|
||||
match_func = pattern.fullmatch
|
||||
|
||||
return _MatchesReValidator(pattern, match_func)
|
||||
|
||||
|
||||
@attrs(repr=False, slots=True, hash=True)
|
||||
class _ProvidesValidator:
|
||||
interface = attrib()
|
||||
|
||||
def __call__(self, inst, attr, value):
|
||||
"""
|
||||
We use a callable class to be able to change the ``__repr__``.
|
||||
"""
|
||||
if not self.interface.providedBy(value):
|
||||
raise TypeError(
|
||||
"'{name}' must provide {interface!r} which {value!r} "
|
||||
"doesn't.".format(
|
||||
name=attr.name, interface=self.interface, value=value
|
||||
),
|
||||
attr,
|
||||
self.interface,
|
||||
value,
|
||||
)
|
||||
|
||||
def __repr__(self):
|
||||
return "<provides validator for interface {interface!r}>".format(
|
||||
interface=self.interface
|
||||
)
|
||||
|
||||
|
||||
def provides(interface):
|
||||
"""
|
||||
A validator that raises a `TypeError` if the initializer is called
|
||||
with an object that does not provide the requested *interface* (checks are
|
||||
performed using ``interface.providedBy(value)`` (see `zope.interface
|
||||
<https://zopeinterface.readthedocs.io/en/latest/>`_).
|
||||
|
||||
:param interface: The interface to check for.
|
||||
:type interface: ``zope.interface.Interface``
|
||||
|
||||
:raises TypeError: With a human readable error message, the attribute
|
||||
(of type `attrs.Attribute`), the expected interface, and the
|
||||
value it got.
|
||||
"""
|
||||
return _ProvidesValidator(interface)
|
||||
|
||||
|
||||
@attrs(repr=False, slots=True, hash=True)
|
||||
class _OptionalValidator:
|
||||
validator = attrib()
|
||||
|
||||
def __call__(self, inst, attr, value):
|
||||
if value is None:
|
||||
return
|
||||
|
||||
self.validator(inst, attr, value)
|
||||
|
||||
def __repr__(self):
|
||||
return "<optional validator for {what} or None>".format(
|
||||
what=repr(self.validator)
|
||||
)
|
||||
|
||||
|
||||
def optional(validator):
|
||||
"""
|
||||
A validator that makes an attribute optional. An optional attribute is one
|
||||
which can be set to ``None`` in addition to satisfying the requirements of
|
||||
the sub-validator.
|
||||
|
||||
:param validator: A validator (or a list of validators) that is used for
|
||||
non-``None`` values.
|
||||
:type validator: callable or `list` of callables.
|
||||
|
||||
.. versionadded:: 15.1.0
|
||||
.. versionchanged:: 17.1.0 *validator* can be a list of validators.
|
||||
"""
|
||||
if isinstance(validator, list):
|
||||
return _OptionalValidator(_AndValidator(validator))
|
||||
return _OptionalValidator(validator)
|
||||
|
||||
|
||||
@attrs(repr=False, slots=True, hash=True)
|
||||
class _InValidator:
|
||||
options = attrib()
|
||||
|
||||
def __call__(self, inst, attr, value):
|
||||
try:
|
||||
in_options = value in self.options
|
||||
except TypeError: # e.g. `1 in "abc"`
|
||||
in_options = False
|
||||
|
||||
if not in_options:
|
||||
raise ValueError(
|
||||
"'{name}' must be in {options!r} (got {value!r})".format(
|
||||
name=attr.name, options=self.options, value=value
|
||||
),
|
||||
attr,
|
||||
self.options,
|
||||
value,
|
||||
)
|
||||
|
||||
def __repr__(self):
|
||||
return "<in_ validator with options {options!r}>".format(
|
||||
options=self.options
|
||||
)
|
||||
|
||||
|
||||
def in_(options):
|
||||
"""
|
||||
A validator that raises a `ValueError` if the initializer is called
|
||||
with a value that does not belong in the options provided. The check is
|
||||
performed using ``value in options``.
|
||||
|
||||
:param options: Allowed options.
|
||||
:type options: list, tuple, `enum.Enum`, ...
|
||||
|
||||
:raises ValueError: With a human readable error message, the attribute (of
|
||||
type `attrs.Attribute`), the expected options, and the value it
|
||||
got.
|
||||
|
||||
.. versionadded:: 17.1.0
|
||||
.. versionchanged:: 22.1.0
|
||||
The ValueError was incomplete until now and only contained the human
|
||||
readable error message. Now it contains all the information that has
|
||||
been promised since 17.1.0.
|
||||
"""
|
||||
return _InValidator(options)
|
||||
|
||||
|
||||
@attrs(repr=False, slots=False, hash=True)
|
||||
class _IsCallableValidator:
|
||||
def __call__(self, inst, attr, value):
|
||||
"""
|
||||
We use a callable class to be able to change the ``__repr__``.
|
||||
"""
|
||||
if not callable(value):
|
||||
message = (
|
||||
"'{name}' must be callable "
|
||||
"(got {value!r} that is a {actual!r})."
|
||||
)
|
||||
raise NotCallableError(
|
||||
msg=message.format(
|
||||
name=attr.name, value=value, actual=value.__class__
|
||||
),
|
||||
value=value,
|
||||
)
|
||||
|
||||
def __repr__(self):
|
||||
return "<is_callable validator>"
|
||||
|
||||
|
||||
def is_callable():
|
||||
"""
|
||||
A validator that raises a `attr.exceptions.NotCallableError` if the
|
||||
initializer is called with a value for this particular attribute
|
||||
that is not callable.
|
||||
|
||||
.. versionadded:: 19.1.0
|
||||
|
||||
:raises `attr.exceptions.NotCallableError`: With a human readable error
|
||||
message containing the attribute (`attrs.Attribute`) name,
|
||||
and the value it got.
|
||||
"""
|
||||
return _IsCallableValidator()
|
||||
|
||||
|
||||
@attrs(repr=False, slots=True, hash=True)
|
||||
class _DeepIterable:
|
||||
member_validator = attrib(validator=is_callable())
|
||||
iterable_validator = attrib(
|
||||
default=None, validator=optional(is_callable())
|
||||
)
|
||||
|
||||
def __call__(self, inst, attr, value):
|
||||
"""
|
||||
We use a callable class to be able to change the ``__repr__``.
|
||||
"""
|
||||
if self.iterable_validator is not None:
|
||||
self.iterable_validator(inst, attr, value)
|
||||
|
||||
for member in value:
|
||||
self.member_validator(inst, attr, member)
|
||||
|
||||
def __repr__(self):
|
||||
iterable_identifier = (
|
||||
""
|
||||
if self.iterable_validator is None
|
||||
else " {iterable!r}".format(iterable=self.iterable_validator)
|
||||
)
|
||||
return (
|
||||
"<deep_iterable validator for{iterable_identifier}"
|
||||
" iterables of {member!r}>"
|
||||
).format(
|
||||
iterable_identifier=iterable_identifier,
|
||||
member=self.member_validator,
|
||||
)
|
||||
|
||||
|
||||
def deep_iterable(member_validator, iterable_validator=None):
|
||||
"""
|
||||
A validator that performs deep validation of an iterable.
|
||||
|
||||
:param member_validator: Validator(s) to apply to iterable members
|
||||
:param iterable_validator: Validator to apply to iterable itself
|
||||
(optional)
|
||||
|
||||
.. versionadded:: 19.1.0
|
||||
|
||||
:raises TypeError: if any sub-validators fail
|
||||
"""
|
||||
if isinstance(member_validator, (list, tuple)):
|
||||
member_validator = and_(*member_validator)
|
||||
return _DeepIterable(member_validator, iterable_validator)
|
||||
|
||||
|
||||
@attrs(repr=False, slots=True, hash=True)
|
||||
class _DeepMapping:
|
||||
key_validator = attrib(validator=is_callable())
|
||||
value_validator = attrib(validator=is_callable())
|
||||
mapping_validator = attrib(default=None, validator=optional(is_callable()))
|
||||
|
||||
def __call__(self, inst, attr, value):
|
||||
"""
|
||||
We use a callable class to be able to change the ``__repr__``.
|
||||
"""
|
||||
if self.mapping_validator is not None:
|
||||
self.mapping_validator(inst, attr, value)
|
||||
|
||||
for key in value:
|
||||
self.key_validator(inst, attr, key)
|
||||
self.value_validator(inst, attr, value[key])
|
||||
|
||||
def __repr__(self):
|
||||
return (
|
||||
"<deep_mapping validator for objects mapping {key!r} to {value!r}>"
|
||||
).format(key=self.key_validator, value=self.value_validator)
|
||||
|
||||
|
||||
def deep_mapping(key_validator, value_validator, mapping_validator=None):
|
||||
"""
|
||||
A validator that performs deep validation of a dictionary.
|
||||
|
||||
:param key_validator: Validator to apply to dictionary keys
|
||||
:param value_validator: Validator to apply to dictionary values
|
||||
:param mapping_validator: Validator to apply to top-level mapping
|
||||
attribute (optional)
|
||||
|
||||
.. versionadded:: 19.1.0
|
||||
|
||||
:raises TypeError: if any sub-validators fail
|
||||
"""
|
||||
return _DeepMapping(key_validator, value_validator, mapping_validator)
|
||||
|
||||
|
||||
@attrs(repr=False, frozen=True, slots=True)
|
||||
class _NumberValidator:
|
||||
bound = attrib()
|
||||
compare_op = attrib()
|
||||
compare_func = attrib()
|
||||
|
||||
def __call__(self, inst, attr, value):
|
||||
"""
|
||||
We use a callable class to be able to change the ``__repr__``.
|
||||
"""
|
||||
if not self.compare_func(value, self.bound):
|
||||
raise ValueError(
|
||||
"'{name}' must be {op} {bound}: {value}".format(
|
||||
name=attr.name,
|
||||
op=self.compare_op,
|
||||
bound=self.bound,
|
||||
value=value,
|
||||
)
|
||||
)
|
||||
|
||||
def __repr__(self):
|
||||
return "<Validator for x {op} {bound}>".format(
|
||||
op=self.compare_op, bound=self.bound
|
||||
)
|
||||
|
||||
|
||||
def lt(val):
|
||||
"""
|
||||
A validator that raises `ValueError` if the initializer is called
|
||||
with a number larger or equal to *val*.
|
||||
|
||||
:param val: Exclusive upper bound for values
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
return _NumberValidator(val, "<", operator.lt)
|
||||
|
||||
|
||||
def le(val):
|
||||
"""
|
||||
A validator that raises `ValueError` if the initializer is called
|
||||
with a number greater than *val*.
|
||||
|
||||
:param val: Inclusive upper bound for values
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
return _NumberValidator(val, "<=", operator.le)
|
||||
|
||||
|
||||
def ge(val):
|
||||
"""
|
||||
A validator that raises `ValueError` if the initializer is called
|
||||
with a number smaller than *val*.
|
||||
|
||||
:param val: Inclusive lower bound for values
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
return _NumberValidator(val, ">=", operator.ge)
|
||||
|
||||
|
||||
def gt(val):
|
||||
"""
|
||||
A validator that raises `ValueError` if the initializer is called
|
||||
with a number smaller or equal to *val*.
|
||||
|
||||
:param val: Exclusive lower bound for values
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
return _NumberValidator(val, ">", operator.gt)
|
||||
|
||||
|
||||
@attrs(repr=False, frozen=True, slots=True)
|
||||
class _MaxLengthValidator:
|
||||
max_length = attrib()
|
||||
|
||||
def __call__(self, inst, attr, value):
|
||||
"""
|
||||
We use a callable class to be able to change the ``__repr__``.
|
||||
"""
|
||||
if len(value) > self.max_length:
|
||||
raise ValueError(
|
||||
"Length of '{name}' must be <= {max}: {len}".format(
|
||||
name=attr.name, max=self.max_length, len=len(value)
|
||||
)
|
||||
)
|
||||
|
||||
def __repr__(self):
|
||||
return "<max_len validator for {max}>".format(max=self.max_length)
|
||||
|
||||
|
||||
def max_len(length):
|
||||
"""
|
||||
A validator that raises `ValueError` if the initializer is called
|
||||
with a string or iterable that is longer than *length*.
|
||||
|
||||
:param int length: Maximum length of the string or iterable
|
||||
|
||||
.. versionadded:: 21.3.0
|
||||
"""
|
||||
return _MaxLengthValidator(length)
|
||||
|
||||
|
||||
@attrs(repr=False, frozen=True, slots=True)
|
||||
class _MinLengthValidator:
|
||||
min_length = attrib()
|
||||
|
||||
def __call__(self, inst, attr, value):
|
||||
"""
|
||||
We use a callable class to be able to change the ``__repr__``.
|
||||
"""
|
||||
if len(value) < self.min_length:
|
||||
raise ValueError(
|
||||
"Length of '{name}' must be => {min}: {len}".format(
|
||||
name=attr.name, min=self.min_length, len=len(value)
|
||||
)
|
||||
)
|
||||
|
||||
def __repr__(self):
|
||||
return "<min_len validator for {min}>".format(min=self.min_length)
|
||||
|
||||
|
||||
def min_len(length):
|
||||
"""
|
||||
A validator that raises `ValueError` if the initializer is called
|
||||
with a string or iterable that is shorter than *length*.
|
||||
|
||||
:param int length: Minimum length of the string or iterable
|
||||
|
||||
.. versionadded:: 22.1.0
|
||||
"""
|
||||
return _MinLengthValidator(length)
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
The MIT License (MIT)
|
||||
|
||||
Copyright (c) 2015 Hynek Schlawack and the attrs contributors
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
|
@ -0,0 +1,70 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
from attr import (
|
||||
NOTHING,
|
||||
Attribute,
|
||||
Factory,
|
||||
__author__,
|
||||
__copyright__,
|
||||
__description__,
|
||||
__doc__,
|
||||
__email__,
|
||||
__license__,
|
||||
__title__,
|
||||
__url__,
|
||||
__version__,
|
||||
__version_info__,
|
||||
assoc,
|
||||
cmp_using,
|
||||
define,
|
||||
evolve,
|
||||
field,
|
||||
fields,
|
||||
fields_dict,
|
||||
frozen,
|
||||
has,
|
||||
make_class,
|
||||
mutable,
|
||||
resolve_types,
|
||||
validate,
|
||||
)
|
||||
from attr._next_gen import asdict, astuple
|
||||
|
||||
from . import converters, exceptions, filters, setters, validators
|
||||
|
||||
|
||||
__all__ = [
|
||||
"__author__",
|
||||
"__copyright__",
|
||||
"__description__",
|
||||
"__doc__",
|
||||
"__email__",
|
||||
"__license__",
|
||||
"__title__",
|
||||
"__url__",
|
||||
"__version__",
|
||||
"__version_info__",
|
||||
"asdict",
|
||||
"assoc",
|
||||
"astuple",
|
||||
"Attribute",
|
||||
"cmp_using",
|
||||
"converters",
|
||||
"define",
|
||||
"evolve",
|
||||
"exceptions",
|
||||
"Factory",
|
||||
"field",
|
||||
"fields_dict",
|
||||
"fields",
|
||||
"filters",
|
||||
"frozen",
|
||||
"has",
|
||||
"make_class",
|
||||
"mutable",
|
||||
"NOTHING",
|
||||
"resolve_types",
|
||||
"setters",
|
||||
"validate",
|
||||
"validators",
|
||||
]
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
from attr.converters import * # noqa
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
from attr.exceptions import * # noqa
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
from attr.filters import * # noqa
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
from attr.setters import * # noqa
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
# SPDX-License-Identifier: MIT
|
||||
|
||||
from attr.validators import * # noqa
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
Copyright (c) 2013 Julian Berman
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in
|
||||
all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
||||
THE SOFTWARE.
|
||||
|
|
@ -0,0 +1,71 @@
|
|||
"""
|
||||
An implementation of JSON Schema for Python
|
||||
|
||||
The main functionality is provided by the validator classes for each of the
|
||||
supported JSON Schema versions.
|
||||
|
||||
Most commonly, `jsonschema.validators.validate` is the quickest way to simply
|
||||
validate a given instance under a schema, and will create a validator
|
||||
for you.
|
||||
"""
|
||||
import warnings
|
||||
|
||||
from jsonschema._format import FormatChecker
|
||||
from jsonschema._types import TypeChecker
|
||||
from jsonschema.exceptions import (
|
||||
ErrorTree,
|
||||
FormatError,
|
||||
RefResolutionError,
|
||||
SchemaError,
|
||||
ValidationError,
|
||||
)
|
||||
from jsonschema.protocols import Validator
|
||||
from jsonschema.validators import (
|
||||
Draft3Validator,
|
||||
Draft4Validator,
|
||||
Draft6Validator,
|
||||
Draft7Validator,
|
||||
Draft201909Validator,
|
||||
Draft202012Validator,
|
||||
RefResolver,
|
||||
validate,
|
||||
)
|
||||
|
||||
|
||||
def __getattr__(name):
|
||||
if name == "__version__":
|
||||
warnings.warn(
|
||||
"Accessing jsonschema.__version__ is deprecated and will be "
|
||||
"removed in a future release. Use importlib.metadata directly "
|
||||
"to query for jsonschema's version.",
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
|
||||
try:
|
||||
from importlib import metadata
|
||||
except ImportError:
|
||||
import importlib_metadata as metadata
|
||||
|
||||
return metadata.version("jsonschema")
|
||||
|
||||
format_checkers = {
|
||||
"draft3_format_checker": Draft3Validator,
|
||||
"draft4_format_checker": Draft4Validator,
|
||||
"draft6_format_checker": Draft6Validator,
|
||||
"draft7_format_checker": Draft7Validator,
|
||||
"draft201909_format_checker": Draft201909Validator,
|
||||
"draft202012_format_checker": Draft202012Validator,
|
||||
}
|
||||
ValidatorForFormat = format_checkers.get(name)
|
||||
if ValidatorForFormat is not None:
|
||||
warnings.warn(
|
||||
f"Accessing jsonschema.{name} is deprecated and will be "
|
||||
"removed in a future release. Instead, use the FORMAT_CHECKER "
|
||||
"attribute on the corresponding Validator.",
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
return ValidatorForFormat.FORMAT_CHECKER
|
||||
|
||||
raise AttributeError(f"module {__name__} has no attribute {name}")
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
from jsonschema.cli import main
|
||||
|
||||
main()
|
||||
|
|
@ -0,0 +1,513 @@
|
|||
from __future__ import annotations
|
||||
|
||||
from contextlib import suppress
|
||||
from uuid import UUID
|
||||
import datetime
|
||||
import ipaddress
|
||||
import re
|
||||
import typing
|
||||
import warnings
|
||||
|
||||
from jsonschema.exceptions import FormatError
|
||||
|
||||
_FormatCheckCallable = typing.Callable[[object], bool]
|
||||
_F = typing.TypeVar("_F", bound=_FormatCheckCallable)
|
||||
_RaisesType = typing.Union[
|
||||
typing.Type[Exception], typing.Tuple[typing.Type[Exception], ...],
|
||||
]
|
||||
|
||||
|
||||
class FormatChecker:
|
||||
"""
|
||||
A ``format`` property checker.
|
||||
|
||||
JSON Schema does not mandate that the ``format`` property actually do any
|
||||
validation. If validation is desired however, instances of this class can
|
||||
be hooked into validators to enable format validation.
|
||||
|
||||
`FormatChecker` objects always return ``True`` when asked about
|
||||
formats that they do not know how to validate.
|
||||
|
||||
To add a check for a custom format use the `FormatChecker.checks`
|
||||
decorator.
|
||||
|
||||
Arguments:
|
||||
|
||||
formats:
|
||||
|
||||
The known formats to validate. This argument can be used to
|
||||
limit which formats will be used during validation.
|
||||
"""
|
||||
|
||||
checkers: dict[
|
||||
str,
|
||||
tuple[_FormatCheckCallable, _RaisesType],
|
||||
] = {}
|
||||
|
||||
def __init__(self, formats: typing.Iterable[str] = None):
|
||||
if formats is None:
|
||||
formats = self.checkers.keys()
|
||||
self.checkers = {k: self.checkers[k] for k in formats}
|
||||
|
||||
def __repr__(self):
|
||||
return "<FormatChecker checkers={}>".format(sorted(self.checkers))
|
||||
|
||||
def checks(
|
||||
self, format: str, raises: _RaisesType = (),
|
||||
) -> typing.Callable[[_F], _F]:
|
||||
"""
|
||||
Register a decorated function as validating a new format.
|
||||
|
||||
Arguments:
|
||||
|
||||
format:
|
||||
|
||||
The format that the decorated function will check.
|
||||
|
||||
raises:
|
||||
|
||||
The exception(s) raised by the decorated function when an
|
||||
invalid instance is found.
|
||||
|
||||
The exception object will be accessible as the
|
||||
`jsonschema.exceptions.ValidationError.cause` attribute of the
|
||||
resulting validation error.
|
||||
"""
|
||||
|
||||
def _checks(func: _F) -> _F:
|
||||
self.checkers[format] = (func, raises)
|
||||
return func
|
||||
|
||||
return _checks
|
||||
|
||||
@classmethod
|
||||
def cls_checks(
|
||||
cls, format: str, raises: _RaisesType = (),
|
||||
) -> typing.Callable[[_F], _F]:
|
||||
warnings.warn(
|
||||
(
|
||||
"FormatChecker.cls_checks is deprecated. Call "
|
||||
"FormatChecker.checks on a specific FormatChecker instance "
|
||||
"instead."
|
||||
),
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
return cls._cls_checks(format=format, raises=raises)
|
||||
|
||||
@classmethod
|
||||
def _cls_checks(
|
||||
cls, format: str, raises: _RaisesType = (),
|
||||
) -> typing.Callable[[_F], _F]:
|
||||
def _checks(func: _F) -> _F:
|
||||
cls.checkers[format] = (func, raises)
|
||||
return func
|
||||
|
||||
return _checks
|
||||
|
||||
def check(self, instance: object, format: str) -> None:
|
||||
"""
|
||||
Check whether the instance conforms to the given format.
|
||||
|
||||
Arguments:
|
||||
|
||||
instance (*any primitive type*, i.e. str, number, bool):
|
||||
|
||||
The instance to check
|
||||
|
||||
format:
|
||||
|
||||
The format that instance should conform to
|
||||
|
||||
Raises:
|
||||
|
||||
FormatError:
|
||||
|
||||
if the instance does not conform to ``format``
|
||||
"""
|
||||
|
||||
if format not in self.checkers:
|
||||
return
|
||||
|
||||
func, raises = self.checkers[format]
|
||||
result, cause = None, None
|
||||
try:
|
||||
result = func(instance)
|
||||
except raises as e:
|
||||
cause = e
|
||||
if not result:
|
||||
raise FormatError(f"{instance!r} is not a {format!r}", cause=cause)
|
||||
|
||||
def conforms(self, instance: object, format: str) -> bool:
|
||||
"""
|
||||
Check whether the instance conforms to the given format.
|
||||
|
||||
Arguments:
|
||||
|
||||
instance (*any primitive type*, i.e. str, number, bool):
|
||||
|
||||
The instance to check
|
||||
|
||||
format:
|
||||
|
||||
The format that instance should conform to
|
||||
|
||||
Returns:
|
||||
|
||||
bool: whether it conformed
|
||||
"""
|
||||
|
||||
try:
|
||||
self.check(instance, format)
|
||||
except FormatError:
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
|
||||
draft3_format_checker = FormatChecker()
|
||||
draft4_format_checker = FormatChecker()
|
||||
draft6_format_checker = FormatChecker()
|
||||
draft7_format_checker = FormatChecker()
|
||||
draft201909_format_checker = FormatChecker()
|
||||
draft202012_format_checker = FormatChecker()
|
||||
|
||||
_draft_checkers: dict[str, FormatChecker] = dict(
|
||||
draft3=draft3_format_checker,
|
||||
draft4=draft4_format_checker,
|
||||
draft6=draft6_format_checker,
|
||||
draft7=draft7_format_checker,
|
||||
draft201909=draft201909_format_checker,
|
||||
draft202012=draft202012_format_checker,
|
||||
)
|
||||
|
||||
|
||||
def _checks_drafts(
|
||||
name=None,
|
||||
draft3=None,
|
||||
draft4=None,
|
||||
draft6=None,
|
||||
draft7=None,
|
||||
draft201909=None,
|
||||
draft202012=None,
|
||||
raises=(),
|
||||
) -> typing.Callable[[_F], _F]:
|
||||
draft3 = draft3 or name
|
||||
draft4 = draft4 or name
|
||||
draft6 = draft6 or name
|
||||
draft7 = draft7 or name
|
||||
draft201909 = draft201909 or name
|
||||
draft202012 = draft202012 or name
|
||||
|
||||
def wrap(func: _F) -> _F:
|
||||
if draft3:
|
||||
func = _draft_checkers["draft3"].checks(draft3, raises)(func)
|
||||
if draft4:
|
||||
func = _draft_checkers["draft4"].checks(draft4, raises)(func)
|
||||
if draft6:
|
||||
func = _draft_checkers["draft6"].checks(draft6, raises)(func)
|
||||
if draft7:
|
||||
func = _draft_checkers["draft7"].checks(draft7, raises)(func)
|
||||
if draft201909:
|
||||
func = _draft_checkers["draft201909"].checks(draft201909, raises)(
|
||||
func,
|
||||
)
|
||||
if draft202012:
|
||||
func = _draft_checkers["draft202012"].checks(draft202012, raises)(
|
||||
func,
|
||||
)
|
||||
|
||||
# Oy. This is bad global state, but relied upon for now, until
|
||||
# deprecation. See #519 and test_format_checkers_come_with_defaults
|
||||
FormatChecker._cls_checks(
|
||||
draft202012 or draft201909 or draft7 or draft6 or draft4 or draft3,
|
||||
raises,
|
||||
)(func)
|
||||
return func
|
||||
|
||||
return wrap
|
||||
|
||||
|
||||
@_checks_drafts(name="idn-email")
|
||||
@_checks_drafts(name="email")
|
||||
def is_email(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return "@" in instance
|
||||
|
||||
|
||||
@_checks_drafts(
|
||||
draft3="ip-address",
|
||||
draft4="ipv4",
|
||||
draft6="ipv4",
|
||||
draft7="ipv4",
|
||||
draft201909="ipv4",
|
||||
draft202012="ipv4",
|
||||
raises=ipaddress.AddressValueError,
|
||||
)
|
||||
def is_ipv4(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return bool(ipaddress.IPv4Address(instance))
|
||||
|
||||
|
||||
@_checks_drafts(name="ipv6", raises=ipaddress.AddressValueError)
|
||||
def is_ipv6(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
address = ipaddress.IPv6Address(instance)
|
||||
return not getattr(address, "scope_id", "")
|
||||
|
||||
|
||||
with suppress(ImportError):
|
||||
from fqdn import FQDN
|
||||
|
||||
@_checks_drafts(
|
||||
draft3="host-name",
|
||||
draft4="hostname",
|
||||
draft6="hostname",
|
||||
draft7="hostname",
|
||||
draft201909="hostname",
|
||||
draft202012="hostname",
|
||||
)
|
||||
def is_host_name(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return FQDN(instance).is_valid
|
||||
|
||||
|
||||
with suppress(ImportError):
|
||||
# The built-in `idna` codec only implements RFC 3890, so we go elsewhere.
|
||||
import idna
|
||||
|
||||
@_checks_drafts(
|
||||
draft7="idn-hostname",
|
||||
draft201909="idn-hostname",
|
||||
draft202012="idn-hostname",
|
||||
raises=(idna.IDNAError, UnicodeError),
|
||||
)
|
||||
def is_idn_host_name(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
idna.encode(instance)
|
||||
return True
|
||||
|
||||
|
||||
try:
|
||||
import rfc3987
|
||||
except ImportError:
|
||||
with suppress(ImportError):
|
||||
from rfc3986_validator import validate_rfc3986
|
||||
|
||||
@_checks_drafts(name="uri")
|
||||
def is_uri(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return validate_rfc3986(instance, rule="URI")
|
||||
|
||||
@_checks_drafts(
|
||||
draft6="uri-reference",
|
||||
draft7="uri-reference",
|
||||
draft201909="uri-reference",
|
||||
draft202012="uri-reference",
|
||||
raises=ValueError,
|
||||
)
|
||||
def is_uri_reference(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return validate_rfc3986(instance, rule="URI_reference")
|
||||
|
||||
else:
|
||||
|
||||
@_checks_drafts(
|
||||
draft7="iri",
|
||||
draft201909="iri",
|
||||
draft202012="iri",
|
||||
raises=ValueError,
|
||||
)
|
||||
def is_iri(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return rfc3987.parse(instance, rule="IRI")
|
||||
|
||||
@_checks_drafts(
|
||||
draft7="iri-reference",
|
||||
draft201909="iri-reference",
|
||||
draft202012="iri-reference",
|
||||
raises=ValueError,
|
||||
)
|
||||
def is_iri_reference(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return rfc3987.parse(instance, rule="IRI_reference")
|
||||
|
||||
@_checks_drafts(name="uri", raises=ValueError)
|
||||
def is_uri(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return rfc3987.parse(instance, rule="URI")
|
||||
|
||||
@_checks_drafts(
|
||||
draft6="uri-reference",
|
||||
draft7="uri-reference",
|
||||
draft201909="uri-reference",
|
||||
draft202012="uri-reference",
|
||||
raises=ValueError,
|
||||
)
|
||||
def is_uri_reference(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return rfc3987.parse(instance, rule="URI_reference")
|
||||
|
||||
|
||||
with suppress(ImportError):
|
||||
from rfc3339_validator import validate_rfc3339
|
||||
|
||||
@_checks_drafts(name="date-time")
|
||||
def is_datetime(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return validate_rfc3339(instance.upper())
|
||||
|
||||
@_checks_drafts(
|
||||
draft7="time",
|
||||
draft201909="time",
|
||||
draft202012="time",
|
||||
)
|
||||
def is_time(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return is_datetime("1970-01-01T" + instance)
|
||||
|
||||
|
||||
@_checks_drafts(name="regex", raises=re.error)
|
||||
def is_regex(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return bool(re.compile(instance))
|
||||
|
||||
|
||||
@_checks_drafts(
|
||||
draft3="date",
|
||||
draft7="date",
|
||||
draft201909="date",
|
||||
draft202012="date",
|
||||
raises=ValueError,
|
||||
)
|
||||
def is_date(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return bool(instance.isascii() and datetime.date.fromisoformat(instance))
|
||||
|
||||
|
||||
@_checks_drafts(draft3="time", raises=ValueError)
|
||||
def is_draft3_time(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return bool(datetime.datetime.strptime(instance, "%H:%M:%S"))
|
||||
|
||||
|
||||
with suppress(ImportError):
|
||||
from webcolors import CSS21_NAMES_TO_HEX
|
||||
import webcolors
|
||||
|
||||
def is_css_color_code(instance: object) -> bool:
|
||||
return webcolors.normalize_hex(instance)
|
||||
|
||||
@_checks_drafts(draft3="color", raises=(ValueError, TypeError))
|
||||
def is_css21_color(instance: object) -> bool:
|
||||
if (
|
||||
not isinstance(instance, str)
|
||||
or instance.lower() in CSS21_NAMES_TO_HEX
|
||||
):
|
||||
return True
|
||||
return is_css_color_code(instance)
|
||||
|
||||
|
||||
with suppress(ImportError):
|
||||
import jsonpointer
|
||||
|
||||
@_checks_drafts(
|
||||
draft6="json-pointer",
|
||||
draft7="json-pointer",
|
||||
draft201909="json-pointer",
|
||||
draft202012="json-pointer",
|
||||
raises=jsonpointer.JsonPointerException,
|
||||
)
|
||||
def is_json_pointer(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return bool(jsonpointer.JsonPointer(instance))
|
||||
|
||||
# TODO: I don't want to maintain this, so it
|
||||
# needs to go either into jsonpointer (pending
|
||||
# https://github.com/stefankoegl/python-json-pointer/issues/34) or
|
||||
# into a new external library.
|
||||
@_checks_drafts(
|
||||
draft7="relative-json-pointer",
|
||||
draft201909="relative-json-pointer",
|
||||
draft202012="relative-json-pointer",
|
||||
raises=jsonpointer.JsonPointerException,
|
||||
)
|
||||
def is_relative_json_pointer(instance: object) -> bool:
|
||||
# Definition taken from:
|
||||
# https://tools.ietf.org/html/draft-handrews-relative-json-pointer-01#section-3
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
non_negative_integer, rest = [], ""
|
||||
for i, character in enumerate(instance):
|
||||
if character.isdigit():
|
||||
# digits with a leading "0" are not allowed
|
||||
if i > 0 and int(instance[i - 1]) == 0:
|
||||
return False
|
||||
|
||||
non_negative_integer.append(character)
|
||||
continue
|
||||
|
||||
if not non_negative_integer:
|
||||
return False
|
||||
|
||||
rest = instance[i:]
|
||||
break
|
||||
return (rest == "#") or bool(jsonpointer.JsonPointer(rest))
|
||||
|
||||
|
||||
with suppress(ImportError):
|
||||
import uri_template
|
||||
|
||||
@_checks_drafts(
|
||||
draft6="uri-template",
|
||||
draft7="uri-template",
|
||||
draft201909="uri-template",
|
||||
draft202012="uri-template",
|
||||
)
|
||||
def is_uri_template(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return uri_template.validate(instance)
|
||||
|
||||
|
||||
with suppress(ImportError):
|
||||
import isoduration
|
||||
|
||||
@_checks_drafts(
|
||||
draft201909="duration",
|
||||
draft202012="duration",
|
||||
raises=isoduration.DurationParsingException,
|
||||
)
|
||||
def is_duration(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
return bool(isoduration.parse_duration(instance))
|
||||
|
||||
|
||||
@_checks_drafts(
|
||||
draft201909="uuid",
|
||||
draft202012="uuid",
|
||||
raises=ValueError,
|
||||
)
|
||||
def is_uuid(instance: object) -> bool:
|
||||
if not isinstance(instance, str):
|
||||
return True
|
||||
UUID(instance)
|
||||
return all(instance[position] == "-" for position in (8, 13, 18, 23))
|
||||
|
|
@ -0,0 +1,319 @@
|
|||
from jsonschema import _utils
|
||||
from jsonschema.exceptions import ValidationError
|
||||
|
||||
|
||||
def id_of_ignore_ref(property="$id"):
|
||||
def id_of(schema):
|
||||
"""
|
||||
Ignore an ``$id`` sibling of ``$ref`` if it is present.
|
||||
|
||||
Otherwise, return the ID of the given schema.
|
||||
"""
|
||||
if schema is True or schema is False or "$ref" in schema:
|
||||
return ""
|
||||
return schema.get(property, "")
|
||||
return id_of
|
||||
|
||||
|
||||
def ignore_ref_siblings(schema):
|
||||
"""
|
||||
Ignore siblings of ``$ref`` if it is present.
|
||||
|
||||
Otherwise, return all keywords.
|
||||
|
||||
Suitable for use with `create`'s ``applicable_validators`` argument.
|
||||
"""
|
||||
ref = schema.get("$ref")
|
||||
if ref is not None:
|
||||
return [("$ref", ref)]
|
||||
else:
|
||||
return schema.items()
|
||||
|
||||
|
||||
def dependencies_draft3(validator, dependencies, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
|
||||
for property, dependency in dependencies.items():
|
||||
if property not in instance:
|
||||
continue
|
||||
|
||||
if validator.is_type(dependency, "object"):
|
||||
yield from validator.descend(
|
||||
instance, dependency, schema_path=property,
|
||||
)
|
||||
elif validator.is_type(dependency, "string"):
|
||||
if dependency not in instance:
|
||||
message = f"{dependency!r} is a dependency of {property!r}"
|
||||
yield ValidationError(message)
|
||||
else:
|
||||
for each in dependency:
|
||||
if each not in instance:
|
||||
message = f"{each!r} is a dependency of {property!r}"
|
||||
yield ValidationError(message)
|
||||
|
||||
|
||||
def dependencies_draft4_draft6_draft7(
|
||||
validator,
|
||||
dependencies,
|
||||
instance,
|
||||
schema,
|
||||
):
|
||||
"""
|
||||
Support for the ``dependencies`` keyword from pre-draft 2019-09.
|
||||
|
||||
In later drafts, the keyword was split into separate
|
||||
``dependentRequired`` and ``dependentSchemas`` validators.
|
||||
"""
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
|
||||
for property, dependency in dependencies.items():
|
||||
if property not in instance:
|
||||
continue
|
||||
|
||||
if validator.is_type(dependency, "array"):
|
||||
for each in dependency:
|
||||
if each not in instance:
|
||||
message = f"{each!r} is a dependency of {property!r}"
|
||||
yield ValidationError(message)
|
||||
else:
|
||||
yield from validator.descend(
|
||||
instance, dependency, schema_path=property,
|
||||
)
|
||||
|
||||
|
||||
def disallow_draft3(validator, disallow, instance, schema):
|
||||
for disallowed in _utils.ensure_list(disallow):
|
||||
if validator.evolve(schema={"type": [disallowed]}).is_valid(instance):
|
||||
message = f"{disallowed!r} is disallowed for {instance!r}"
|
||||
yield ValidationError(message)
|
||||
|
||||
|
||||
def extends_draft3(validator, extends, instance, schema):
|
||||
if validator.is_type(extends, "object"):
|
||||
yield from validator.descend(instance, extends)
|
||||
return
|
||||
for index, subschema in enumerate(extends):
|
||||
yield from validator.descend(instance, subschema, schema_path=index)
|
||||
|
||||
|
||||
def items_draft3_draft4(validator, items, instance, schema):
|
||||
if not validator.is_type(instance, "array"):
|
||||
return
|
||||
|
||||
if validator.is_type(items, "object"):
|
||||
for index, item in enumerate(instance):
|
||||
yield from validator.descend(item, items, path=index)
|
||||
else:
|
||||
for (index, item), subschema in zip(enumerate(instance), items):
|
||||
yield from validator.descend(
|
||||
item, subschema, path=index, schema_path=index,
|
||||
)
|
||||
|
||||
|
||||
def items_draft6_draft7_draft201909(validator, items, instance, schema):
|
||||
if not validator.is_type(instance, "array"):
|
||||
return
|
||||
|
||||
if validator.is_type(items, "array"):
|
||||
for (index, item), subschema in zip(enumerate(instance), items):
|
||||
yield from validator.descend(
|
||||
item, subschema, path=index, schema_path=index,
|
||||
)
|
||||
else:
|
||||
for index, item in enumerate(instance):
|
||||
yield from validator.descend(item, items, path=index)
|
||||
|
||||
|
||||
def minimum_draft3_draft4(validator, minimum, instance, schema):
|
||||
if not validator.is_type(instance, "number"):
|
||||
return
|
||||
|
||||
if schema.get("exclusiveMinimum", False):
|
||||
failed = instance <= minimum
|
||||
cmp = "less than or equal to"
|
||||
else:
|
||||
failed = instance < minimum
|
||||
cmp = "less than"
|
||||
|
||||
if failed:
|
||||
message = f"{instance!r} is {cmp} the minimum of {minimum!r}"
|
||||
yield ValidationError(message)
|
||||
|
||||
|
||||
def maximum_draft3_draft4(validator, maximum, instance, schema):
|
||||
if not validator.is_type(instance, "number"):
|
||||
return
|
||||
|
||||
if schema.get("exclusiveMaximum", False):
|
||||
failed = instance >= maximum
|
||||
cmp = "greater than or equal to"
|
||||
else:
|
||||
failed = instance > maximum
|
||||
cmp = "greater than"
|
||||
|
||||
if failed:
|
||||
message = f"{instance!r} is {cmp} the maximum of {maximum!r}"
|
||||
yield ValidationError(message)
|
||||
|
||||
|
||||
def properties_draft3(validator, properties, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
|
||||
for property, subschema in properties.items():
|
||||
if property in instance:
|
||||
yield from validator.descend(
|
||||
instance[property],
|
||||
subschema,
|
||||
path=property,
|
||||
schema_path=property,
|
||||
)
|
||||
elif subschema.get("required", False):
|
||||
error = ValidationError(f"{property!r} is a required property")
|
||||
error._set(
|
||||
validator="required",
|
||||
validator_value=subschema["required"],
|
||||
instance=instance,
|
||||
schema=schema,
|
||||
)
|
||||
error.path.appendleft(property)
|
||||
error.schema_path.extend([property, "required"])
|
||||
yield error
|
||||
|
||||
|
||||
def type_draft3(validator, types, instance, schema):
|
||||
types = _utils.ensure_list(types)
|
||||
|
||||
all_errors = []
|
||||
for index, type in enumerate(types):
|
||||
if validator.is_type(type, "object"):
|
||||
errors = list(validator.descend(instance, type, schema_path=index))
|
||||
if not errors:
|
||||
return
|
||||
all_errors.extend(errors)
|
||||
else:
|
||||
if validator.is_type(instance, type):
|
||||
return
|
||||
else:
|
||||
reprs = []
|
||||
for type in types:
|
||||
try:
|
||||
reprs.append(repr(type["name"]))
|
||||
except Exception:
|
||||
reprs.append(repr(type))
|
||||
yield ValidationError(
|
||||
f"{instance!r} is not of type {', '.join(reprs)}",
|
||||
context=all_errors,
|
||||
)
|
||||
|
||||
|
||||
def contains_draft6_draft7(validator, contains, instance, schema):
|
||||
if not validator.is_type(instance, "array"):
|
||||
return
|
||||
|
||||
if not any(
|
||||
validator.evolve(schema=contains).is_valid(element)
|
||||
for element in instance
|
||||
):
|
||||
yield ValidationError(
|
||||
f"None of {instance!r} are valid under the given schema",
|
||||
)
|
||||
|
||||
|
||||
def recursiveRef(validator, recursiveRef, instance, schema):
|
||||
lookup_url, target = validator.resolver.resolution_scope, validator.schema
|
||||
|
||||
for each in reversed(validator.resolver._scopes_stack[1:]):
|
||||
lookup_url, next_target = validator.resolver.resolve(each)
|
||||
if next_target.get("$recursiveAnchor"):
|
||||
target = next_target
|
||||
else:
|
||||
break
|
||||
|
||||
fragment = recursiveRef.lstrip("#")
|
||||
subschema = validator.resolver.resolve_fragment(target, fragment)
|
||||
# FIXME: This is gutted (and not calling .descend) because it can trigger
|
||||
# recursion errors, so there's a bug here. Re-enable the tests to
|
||||
# see it.
|
||||
subschema
|
||||
return []
|
||||
|
||||
|
||||
def find_evaluated_item_indexes_by_schema(validator, instance, schema):
|
||||
"""
|
||||
Get all indexes of items that get evaluated under the current schema
|
||||
|
||||
Covers all keywords related to unevaluatedItems: items, prefixItems, if,
|
||||
then, else, contains, unevaluatedItems, allOf, oneOf, anyOf
|
||||
"""
|
||||
if validator.is_type(schema, "boolean"):
|
||||
return []
|
||||
evaluated_indexes = []
|
||||
|
||||
if "additionalItems" in schema:
|
||||
return list(range(0, len(instance)))
|
||||
|
||||
if "$ref" in schema:
|
||||
scope, resolved = validator.resolver.resolve(schema["$ref"])
|
||||
validator.resolver.push_scope(scope)
|
||||
|
||||
try:
|
||||
evaluated_indexes += find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, resolved,
|
||||
)
|
||||
finally:
|
||||
validator.resolver.pop_scope()
|
||||
|
||||
if "items" in schema:
|
||||
if validator.is_type(schema["items"], "object"):
|
||||
return list(range(0, len(instance)))
|
||||
evaluated_indexes += list(range(0, len(schema["items"])))
|
||||
|
||||
if "if" in schema:
|
||||
if validator.evolve(schema=schema["if"]).is_valid(instance):
|
||||
evaluated_indexes += find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, schema["if"],
|
||||
)
|
||||
if "then" in schema:
|
||||
evaluated_indexes += find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, schema["then"],
|
||||
)
|
||||
else:
|
||||
if "else" in schema:
|
||||
evaluated_indexes += find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, schema["else"],
|
||||
)
|
||||
|
||||
for keyword in ["contains", "unevaluatedItems"]:
|
||||
if keyword in schema:
|
||||
for k, v in enumerate(instance):
|
||||
if validator.evolve(schema=schema[keyword]).is_valid(v):
|
||||
evaluated_indexes.append(k)
|
||||
|
||||
for keyword in ["allOf", "oneOf", "anyOf"]:
|
||||
if keyword in schema:
|
||||
for subschema in schema[keyword]:
|
||||
errs = list(validator.descend(instance, subschema))
|
||||
if not errs:
|
||||
evaluated_indexes += find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, subschema,
|
||||
)
|
||||
|
||||
return evaluated_indexes
|
||||
|
||||
|
||||
def unevaluatedItems_draft2019(validator, unevaluatedItems, instance, schema):
|
||||
if not validator.is_type(instance, "array"):
|
||||
return
|
||||
evaluated_item_indexes = find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, schema,
|
||||
)
|
||||
unevaluated_items = [
|
||||
item for index, item in enumerate(instance)
|
||||
if index not in evaluated_item_indexes
|
||||
]
|
||||
if unevaluated_items:
|
||||
error = "Unevaluated items are not allowed (%s %s unexpected)"
|
||||
yield ValidationError(error % _utils.extras_msg(unevaluated_items))
|
||||
|
|
@ -0,0 +1,203 @@
|
|||
from __future__ import annotations
|
||||
|
||||
import numbers
|
||||
import typing
|
||||
|
||||
from pyrsistent import pmap
|
||||
from pyrsistent.typing import PMap
|
||||
import attr
|
||||
|
||||
from jsonschema.exceptions import UndefinedTypeCheck
|
||||
|
||||
|
||||
# unfortunately, the type of pmap is generic, and if used as the attr.ib
|
||||
# converter, the generic type is presented to mypy, which then fails to match
|
||||
# the concrete type of a type checker mapping
|
||||
# this "do nothing" wrapper presents the correct information to mypy
|
||||
def _typed_pmap_converter(
|
||||
init_val: typing.Mapping[
|
||||
str,
|
||||
typing.Callable[["TypeChecker", typing.Any], bool],
|
||||
],
|
||||
) -> PMap[str, typing.Callable[["TypeChecker", typing.Any], bool]]:
|
||||
return pmap(init_val)
|
||||
|
||||
|
||||
def is_array(checker, instance):
|
||||
return isinstance(instance, list)
|
||||
|
||||
|
||||
def is_bool(checker, instance):
|
||||
return isinstance(instance, bool)
|
||||
|
||||
|
||||
def is_integer(checker, instance):
|
||||
# bool inherits from int, so ensure bools aren't reported as ints
|
||||
if isinstance(instance, bool):
|
||||
return False
|
||||
return isinstance(instance, int)
|
||||
|
||||
|
||||
def is_null(checker, instance):
|
||||
return instance is None
|
||||
|
||||
|
||||
def is_number(checker, instance):
|
||||
# bool inherits from int, so ensure bools aren't reported as ints
|
||||
if isinstance(instance, bool):
|
||||
return False
|
||||
return isinstance(instance, numbers.Number)
|
||||
|
||||
|
||||
def is_object(checker, instance):
|
||||
return isinstance(instance, dict)
|
||||
|
||||
|
||||
def is_string(checker, instance):
|
||||
return isinstance(instance, str)
|
||||
|
||||
|
||||
def is_any(checker, instance):
|
||||
return True
|
||||
|
||||
|
||||
@attr.s(frozen=True, repr=False)
|
||||
class TypeChecker:
|
||||
"""
|
||||
A :kw:`type` property checker.
|
||||
|
||||
A `TypeChecker` performs type checking for a `Validator`, converting
|
||||
between the defined JSON Schema types and some associated Python types or
|
||||
objects.
|
||||
|
||||
Modifying the behavior just mentioned by redefining which Python objects
|
||||
are considered to be of which JSON Schema types can be done using
|
||||
`TypeChecker.redefine` or `TypeChecker.redefine_many`, and types can be
|
||||
removed via `TypeChecker.remove`. Each of these return a new `TypeChecker`.
|
||||
|
||||
Arguments:
|
||||
|
||||
type_checkers:
|
||||
|
||||
The initial mapping of types to their checking functions.
|
||||
"""
|
||||
|
||||
_type_checkers: PMap[
|
||||
str, typing.Callable[["TypeChecker", typing.Any], bool],
|
||||
] = attr.ib(
|
||||
default=pmap(),
|
||||
converter=_typed_pmap_converter,
|
||||
)
|
||||
|
||||
def __repr__(self):
|
||||
types = ", ".join(repr(k) for k in sorted(self._type_checkers))
|
||||
return f"<{self.__class__.__name__} types={{{types}}}>"
|
||||
|
||||
def is_type(self, instance, type: str) -> bool:
|
||||
"""
|
||||
Check if the instance is of the appropriate type.
|
||||
|
||||
Arguments:
|
||||
|
||||
instance:
|
||||
|
||||
The instance to check
|
||||
|
||||
type:
|
||||
|
||||
The name of the type that is expected.
|
||||
|
||||
Raises:
|
||||
|
||||
`jsonschema.exceptions.UndefinedTypeCheck`:
|
||||
|
||||
if ``type`` is unknown to this object.
|
||||
"""
|
||||
try:
|
||||
fn = self._type_checkers[type]
|
||||
except KeyError:
|
||||
raise UndefinedTypeCheck(type) from None
|
||||
|
||||
return fn(self, instance)
|
||||
|
||||
def redefine(self, type: str, fn) -> "TypeChecker":
|
||||
"""
|
||||
Produce a new checker with the given type redefined.
|
||||
|
||||
Arguments:
|
||||
|
||||
type:
|
||||
|
||||
The name of the type to check.
|
||||
|
||||
fn (collections.abc.Callable):
|
||||
|
||||
A callable taking exactly two parameters - the type
|
||||
checker calling the function and the instance to check.
|
||||
The function should return true if instance is of this
|
||||
type and false otherwise.
|
||||
"""
|
||||
return self.redefine_many({type: fn})
|
||||
|
||||
def redefine_many(self, definitions=()) -> "TypeChecker":
|
||||
"""
|
||||
Produce a new checker with the given types redefined.
|
||||
|
||||
Arguments:
|
||||
|
||||
definitions (dict):
|
||||
|
||||
A dictionary mapping types to their checking functions.
|
||||
"""
|
||||
type_checkers = self._type_checkers.update(definitions)
|
||||
return attr.evolve(self, type_checkers=type_checkers)
|
||||
|
||||
def remove(self, *types) -> "TypeChecker":
|
||||
"""
|
||||
Produce a new checker with the given types forgotten.
|
||||
|
||||
Arguments:
|
||||
|
||||
types:
|
||||
|
||||
the names of the types to remove.
|
||||
|
||||
Raises:
|
||||
|
||||
`jsonschema.exceptions.UndefinedTypeCheck`:
|
||||
|
||||
if any given type is unknown to this object
|
||||
"""
|
||||
|
||||
type_checkers = self._type_checkers
|
||||
for each in types:
|
||||
try:
|
||||
type_checkers = type_checkers.remove(each)
|
||||
except KeyError:
|
||||
raise UndefinedTypeCheck(each)
|
||||
return attr.evolve(self, type_checkers=type_checkers)
|
||||
|
||||
|
||||
draft3_type_checker = TypeChecker(
|
||||
{
|
||||
"any": is_any,
|
||||
"array": is_array,
|
||||
"boolean": is_bool,
|
||||
"integer": is_integer,
|
||||
"object": is_object,
|
||||
"null": is_null,
|
||||
"number": is_number,
|
||||
"string": is_string,
|
||||
},
|
||||
)
|
||||
draft4_type_checker = draft3_type_checker.remove("any")
|
||||
draft6_type_checker = draft4_type_checker.redefine(
|
||||
"integer",
|
||||
lambda checker, instance: (
|
||||
is_integer(checker, instance)
|
||||
or isinstance(instance, float) and instance.is_integer()
|
||||
),
|
||||
)
|
||||
draft7_type_checker = draft6_type_checker
|
||||
draft201909_type_checker = draft7_type_checker
|
||||
draft202012_type_checker = draft201909_type_checker
|
||||
|
|
@ -0,0 +1,345 @@
|
|||
from collections.abc import Mapping, MutableMapping, Sequence
|
||||
from urllib.parse import urlsplit
|
||||
import itertools
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
|
||||
class URIDict(MutableMapping):
|
||||
"""
|
||||
Dictionary which uses normalized URIs as keys.
|
||||
"""
|
||||
|
||||
def normalize(self, uri):
|
||||
return urlsplit(uri).geturl()
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
self.store = dict()
|
||||
self.store.update(*args, **kwargs)
|
||||
|
||||
def __getitem__(self, uri):
|
||||
return self.store[self.normalize(uri)]
|
||||
|
||||
def __setitem__(self, uri, value):
|
||||
self.store[self.normalize(uri)] = value
|
||||
|
||||
def __delitem__(self, uri):
|
||||
del self.store[self.normalize(uri)]
|
||||
|
||||
def __iter__(self):
|
||||
return iter(self.store)
|
||||
|
||||
def __len__(self):
|
||||
return len(self.store)
|
||||
|
||||
def __repr__(self):
|
||||
return repr(self.store)
|
||||
|
||||
|
||||
class Unset:
|
||||
"""
|
||||
An as-of-yet unset attribute or unprovided default parameter.
|
||||
"""
|
||||
|
||||
def __repr__(self):
|
||||
return "<unset>"
|
||||
|
||||
|
||||
def load_schema(name):
|
||||
"""
|
||||
Load a schema from ./schemas/``name``.json and return it.
|
||||
"""
|
||||
with open(
|
||||
os.path.join(os.path.dirname(__file__), "schemas", "{0}.json".format(name)),
|
||||
encoding="utf-8"
|
||||
) as f:
|
||||
data = f.read()
|
||||
|
||||
return json.loads(data)
|
||||
|
||||
|
||||
def format_as_index(container, indices):
|
||||
"""
|
||||
Construct a single string containing indexing operations for the indices.
|
||||
|
||||
For example for a container ``bar``, [1, 2, "foo"] -> bar[1][2]["foo"]
|
||||
|
||||
Arguments:
|
||||
|
||||
container (str):
|
||||
|
||||
A word to use for the thing being indexed
|
||||
|
||||
indices (sequence):
|
||||
|
||||
The indices to format.
|
||||
"""
|
||||
|
||||
if not indices:
|
||||
return container
|
||||
return f"{container}[{']['.join(repr(index) for index in indices)}]"
|
||||
|
||||
|
||||
def find_additional_properties(instance, schema):
|
||||
"""
|
||||
Return the set of additional properties for the given ``instance``.
|
||||
|
||||
Weeds out properties that should have been validated by ``properties`` and
|
||||
/ or ``patternProperties``.
|
||||
|
||||
Assumes ``instance`` is dict-like already.
|
||||
"""
|
||||
|
||||
properties = schema.get("properties", {})
|
||||
patterns = "|".join(schema.get("patternProperties", {}))
|
||||
for property in instance:
|
||||
if property not in properties:
|
||||
if patterns and re.search(patterns, property):
|
||||
continue
|
||||
yield property
|
||||
|
||||
|
||||
def extras_msg(extras):
|
||||
"""
|
||||
Create an error message for extra items or properties.
|
||||
"""
|
||||
|
||||
if len(extras) == 1:
|
||||
verb = "was"
|
||||
else:
|
||||
verb = "were"
|
||||
return ", ".join(repr(extra) for extra in sorted(extras)), verb
|
||||
|
||||
|
||||
def ensure_list(thing):
|
||||
"""
|
||||
Wrap ``thing`` in a list if it's a single str.
|
||||
|
||||
Otherwise, return it unchanged.
|
||||
"""
|
||||
|
||||
if isinstance(thing, str):
|
||||
return [thing]
|
||||
return thing
|
||||
|
||||
|
||||
def _mapping_equal(one, two):
|
||||
"""
|
||||
Check if two mappings are equal using the semantics of `equal`.
|
||||
"""
|
||||
if len(one) != len(two):
|
||||
return False
|
||||
return all(
|
||||
key in two and equal(value, two[key])
|
||||
for key, value in one.items()
|
||||
)
|
||||
|
||||
|
||||
def _sequence_equal(one, two):
|
||||
"""
|
||||
Check if two sequences are equal using the semantics of `equal`.
|
||||
"""
|
||||
if len(one) != len(two):
|
||||
return False
|
||||
return all(equal(i, j) for i, j in zip(one, two))
|
||||
|
||||
|
||||
def equal(one, two):
|
||||
"""
|
||||
Check if two things are equal evading some Python type hierarchy semantics.
|
||||
|
||||
Specifically in JSON Schema, evade `bool` inheriting from `int`,
|
||||
recursing into sequences to do the same.
|
||||
"""
|
||||
if isinstance(one, str) or isinstance(two, str):
|
||||
return one == two
|
||||
if isinstance(one, Sequence) and isinstance(two, Sequence):
|
||||
return _sequence_equal(one, two)
|
||||
if isinstance(one, Mapping) and isinstance(two, Mapping):
|
||||
return _mapping_equal(one, two)
|
||||
return unbool(one) == unbool(two)
|
||||
|
||||
|
||||
def unbool(element, true=object(), false=object()):
|
||||
"""
|
||||
A hack to make True and 1 and False and 0 unique for ``uniq``.
|
||||
"""
|
||||
|
||||
if element is True:
|
||||
return true
|
||||
elif element is False:
|
||||
return false
|
||||
return element
|
||||
|
||||
|
||||
def uniq(container):
|
||||
"""
|
||||
Check if all of a container's elements are unique.
|
||||
|
||||
Tries to rely on the container being recursively sortable, or otherwise
|
||||
falls back on (slow) brute force.
|
||||
"""
|
||||
try:
|
||||
sort = sorted(unbool(i) for i in container)
|
||||
sliced = itertools.islice(sort, 1, None)
|
||||
|
||||
for i, j in zip(sort, sliced):
|
||||
if equal(i, j):
|
||||
return False
|
||||
|
||||
except (NotImplementedError, TypeError):
|
||||
seen = []
|
||||
for e in container:
|
||||
e = unbool(e)
|
||||
|
||||
for i in seen:
|
||||
if equal(i, e):
|
||||
return False
|
||||
|
||||
seen.append(e)
|
||||
return True
|
||||
|
||||
|
||||
def find_evaluated_item_indexes_by_schema(validator, instance, schema):
|
||||
"""
|
||||
Get all indexes of items that get evaluated under the current schema
|
||||
|
||||
Covers all keywords related to unevaluatedItems: items, prefixItems, if,
|
||||
then, else, contains, unevaluatedItems, allOf, oneOf, anyOf
|
||||
"""
|
||||
if validator.is_type(schema, "boolean"):
|
||||
return []
|
||||
evaluated_indexes = []
|
||||
|
||||
if "items" in schema:
|
||||
return list(range(0, len(instance)))
|
||||
|
||||
if "$ref" in schema:
|
||||
scope, resolved = validator.resolver.resolve(schema["$ref"])
|
||||
validator.resolver.push_scope(scope)
|
||||
|
||||
try:
|
||||
evaluated_indexes += find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, resolved,
|
||||
)
|
||||
finally:
|
||||
validator.resolver.pop_scope()
|
||||
|
||||
if "prefixItems" in schema:
|
||||
evaluated_indexes += list(range(0, len(schema["prefixItems"])))
|
||||
|
||||
if "if" in schema:
|
||||
if validator.evolve(schema=schema["if"]).is_valid(instance):
|
||||
evaluated_indexes += find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, schema["if"],
|
||||
)
|
||||
if "then" in schema:
|
||||
evaluated_indexes += find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, schema["then"],
|
||||
)
|
||||
else:
|
||||
if "else" in schema:
|
||||
evaluated_indexes += find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, schema["else"],
|
||||
)
|
||||
|
||||
for keyword in ["contains", "unevaluatedItems"]:
|
||||
if keyword in schema:
|
||||
for k, v in enumerate(instance):
|
||||
if validator.evolve(schema=schema[keyword]).is_valid(v):
|
||||
evaluated_indexes.append(k)
|
||||
|
||||
for keyword in ["allOf", "oneOf", "anyOf"]:
|
||||
if keyword in schema:
|
||||
for subschema in schema[keyword]:
|
||||
errs = list(validator.descend(instance, subschema))
|
||||
if not errs:
|
||||
evaluated_indexes += find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, subschema,
|
||||
)
|
||||
|
||||
return evaluated_indexes
|
||||
|
||||
|
||||
def find_evaluated_property_keys_by_schema(validator, instance, schema):
|
||||
"""
|
||||
Get all keys of items that get evaluated under the current schema
|
||||
|
||||
Covers all keywords related to unevaluatedProperties: properties,
|
||||
additionalProperties, unevaluatedProperties, patternProperties,
|
||||
dependentSchemas, allOf, oneOf, anyOf, if, then, else
|
||||
"""
|
||||
if validator.is_type(schema, "boolean"):
|
||||
return []
|
||||
evaluated_keys = []
|
||||
|
||||
if "$ref" in schema:
|
||||
scope, resolved = validator.resolver.resolve(schema["$ref"])
|
||||
validator.resolver.push_scope(scope)
|
||||
|
||||
try:
|
||||
evaluated_keys += find_evaluated_property_keys_by_schema(
|
||||
validator, instance, resolved,
|
||||
)
|
||||
finally:
|
||||
validator.resolver.pop_scope()
|
||||
|
||||
for keyword in [
|
||||
"properties", "additionalProperties", "unevaluatedProperties",
|
||||
]:
|
||||
if keyword in schema:
|
||||
if validator.is_type(schema[keyword], "boolean"):
|
||||
for property, value in instance.items():
|
||||
if validator.evolve(schema=schema[keyword]).is_valid(
|
||||
{property: value},
|
||||
):
|
||||
evaluated_keys.append(property)
|
||||
|
||||
if validator.is_type(schema[keyword], "object"):
|
||||
for property, subschema in schema[keyword].items():
|
||||
if property in instance and validator.evolve(
|
||||
schema=subschema,
|
||||
).is_valid(instance[property]):
|
||||
evaluated_keys.append(property)
|
||||
|
||||
if "patternProperties" in schema:
|
||||
for property, value in instance.items():
|
||||
for pattern, _ in schema["patternProperties"].items():
|
||||
if re.search(pattern, property) and validator.evolve(
|
||||
schema=schema["patternProperties"],
|
||||
).is_valid({property: value}):
|
||||
evaluated_keys.append(property)
|
||||
|
||||
if "dependentSchemas" in schema:
|
||||
for property, subschema in schema["dependentSchemas"].items():
|
||||
if property not in instance:
|
||||
continue
|
||||
evaluated_keys += find_evaluated_property_keys_by_schema(
|
||||
validator, instance, subschema,
|
||||
)
|
||||
|
||||
for keyword in ["allOf", "oneOf", "anyOf"]:
|
||||
if keyword in schema:
|
||||
for subschema in schema[keyword]:
|
||||
errs = list(validator.descend(instance, subschema))
|
||||
if not errs:
|
||||
evaluated_keys += find_evaluated_property_keys_by_schema(
|
||||
validator, instance, subschema,
|
||||
)
|
||||
|
||||
if "if" in schema:
|
||||
if validator.evolve(schema=schema["if"]).is_valid(instance):
|
||||
evaluated_keys += find_evaluated_property_keys_by_schema(
|
||||
validator, instance, schema["if"],
|
||||
)
|
||||
if "then" in schema:
|
||||
evaluated_keys += find_evaluated_property_keys_by_schema(
|
||||
validator, instance, schema["then"],
|
||||
)
|
||||
else:
|
||||
if "else" in schema:
|
||||
evaluated_keys += find_evaluated_property_keys_by_schema(
|
||||
validator, instance, schema["else"],
|
||||
)
|
||||
|
||||
return evaluated_keys
|
||||
|
|
@ -0,0 +1,467 @@
|
|||
from fractions import Fraction
|
||||
from urllib.parse import urldefrag, urljoin
|
||||
import re
|
||||
|
||||
from jsonschema._utils import (
|
||||
ensure_list,
|
||||
equal,
|
||||
extras_msg,
|
||||
find_additional_properties,
|
||||
find_evaluated_item_indexes_by_schema,
|
||||
find_evaluated_property_keys_by_schema,
|
||||
unbool,
|
||||
uniq,
|
||||
)
|
||||
from jsonschema.exceptions import FormatError, ValidationError
|
||||
|
||||
|
||||
def patternProperties(validator, patternProperties, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
|
||||
for pattern, subschema in patternProperties.items():
|
||||
for k, v in instance.items():
|
||||
if re.search(pattern, k):
|
||||
yield from validator.descend(
|
||||
v, subschema, path=k, schema_path=pattern,
|
||||
)
|
||||
|
||||
|
||||
def propertyNames(validator, propertyNames, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
|
||||
for property in instance:
|
||||
yield from validator.descend(instance=property, schema=propertyNames)
|
||||
|
||||
|
||||
def additionalProperties(validator, aP, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
|
||||
extras = set(find_additional_properties(instance, schema))
|
||||
|
||||
if validator.is_type(aP, "object"):
|
||||
for extra in extras:
|
||||
yield from validator.descend(instance[extra], aP, path=extra)
|
||||
elif not aP and extras:
|
||||
if "patternProperties" in schema:
|
||||
if len(extras) == 1:
|
||||
verb = "does"
|
||||
else:
|
||||
verb = "do"
|
||||
|
||||
joined = ", ".join(repr(each) for each in sorted(extras))
|
||||
patterns = ", ".join(
|
||||
repr(each) for each in sorted(schema["patternProperties"])
|
||||
)
|
||||
error = f"{joined} {verb} not match any of the regexes: {patterns}"
|
||||
yield ValidationError(error)
|
||||
else:
|
||||
error = "Additional properties are not allowed (%s %s unexpected)"
|
||||
yield ValidationError(error % extras_msg(extras))
|
||||
|
||||
|
||||
def items(validator, items, instance, schema):
|
||||
if not validator.is_type(instance, "array"):
|
||||
return
|
||||
|
||||
prefix = len(schema.get("prefixItems", []))
|
||||
total = len(instance)
|
||||
if items is False and total > prefix:
|
||||
message = f"Expected at most {prefix} items, but found {total}"
|
||||
yield ValidationError(message)
|
||||
else:
|
||||
for index in range(prefix, total):
|
||||
yield from validator.descend(
|
||||
instance=instance[index],
|
||||
schema=items,
|
||||
path=index,
|
||||
)
|
||||
|
||||
|
||||
def additionalItems(validator, aI, instance, schema):
|
||||
if (
|
||||
not validator.is_type(instance, "array")
|
||||
or validator.is_type(schema.get("items", {}), "object")
|
||||
):
|
||||
return
|
||||
|
||||
len_items = len(schema.get("items", []))
|
||||
if validator.is_type(aI, "object"):
|
||||
for index, item in enumerate(instance[len_items:], start=len_items):
|
||||
yield from validator.descend(item, aI, path=index)
|
||||
elif not aI and len(instance) > len(schema.get("items", [])):
|
||||
error = "Additional items are not allowed (%s %s unexpected)"
|
||||
yield ValidationError(
|
||||
error % extras_msg(instance[len(schema.get("items", [])):]),
|
||||
)
|
||||
|
||||
|
||||
def const(validator, const, instance, schema):
|
||||
if not equal(instance, const):
|
||||
yield ValidationError(f"{const!r} was expected")
|
||||
|
||||
|
||||
def contains(validator, contains, instance, schema):
|
||||
if not validator.is_type(instance, "array"):
|
||||
return
|
||||
|
||||
matches = 0
|
||||
min_contains = schema.get("minContains", 1)
|
||||
max_contains = schema.get("maxContains", len(instance))
|
||||
|
||||
for each in instance:
|
||||
if validator.evolve(schema=contains).is_valid(each):
|
||||
matches += 1
|
||||
if matches > max_contains:
|
||||
yield ValidationError(
|
||||
"Too many items match the given schema "
|
||||
f"(expected at most {max_contains})",
|
||||
validator="maxContains",
|
||||
validator_value=max_contains,
|
||||
)
|
||||
return
|
||||
|
||||
if matches < min_contains:
|
||||
if not matches:
|
||||
yield ValidationError(
|
||||
f"{instance!r} does not contain items "
|
||||
"matching the given schema",
|
||||
)
|
||||
else:
|
||||
yield ValidationError(
|
||||
"Too few items match the given schema (expected at least "
|
||||
f"{min_contains} but only {matches} matched)",
|
||||
validator="minContains",
|
||||
validator_value=min_contains,
|
||||
)
|
||||
|
||||
|
||||
def exclusiveMinimum(validator, minimum, instance, schema):
|
||||
if not validator.is_type(instance, "number"):
|
||||
return
|
||||
|
||||
if instance <= minimum:
|
||||
yield ValidationError(
|
||||
f"{instance!r} is less than or equal to "
|
||||
f"the minimum of {minimum!r}",
|
||||
)
|
||||
|
||||
|
||||
def exclusiveMaximum(validator, maximum, instance, schema):
|
||||
if not validator.is_type(instance, "number"):
|
||||
return
|
||||
|
||||
if instance >= maximum:
|
||||
yield ValidationError(
|
||||
f"{instance!r} is greater than or equal "
|
||||
f"to the maximum of {maximum!r}",
|
||||
)
|
||||
|
||||
|
||||
def minimum(validator, minimum, instance, schema):
|
||||
if not validator.is_type(instance, "number"):
|
||||
return
|
||||
|
||||
if instance < minimum:
|
||||
message = f"{instance!r} is less than the minimum of {minimum!r}"
|
||||
yield ValidationError(message)
|
||||
|
||||
|
||||
def maximum(validator, maximum, instance, schema):
|
||||
if not validator.is_type(instance, "number"):
|
||||
return
|
||||
|
||||
if instance > maximum:
|
||||
message = f"{instance!r} is greater than the maximum of {maximum!r}"
|
||||
yield ValidationError(message)
|
||||
|
||||
|
||||
def multipleOf(validator, dB, instance, schema):
|
||||
if not validator.is_type(instance, "number"):
|
||||
return
|
||||
|
||||
if isinstance(dB, float):
|
||||
quotient = instance / dB
|
||||
try:
|
||||
failed = int(quotient) != quotient
|
||||
except OverflowError:
|
||||
# When `instance` is large and `dB` is less than one,
|
||||
# quotient can overflow to infinity; and then casting to int
|
||||
# raises an error.
|
||||
#
|
||||
# In this case we fall back to Fraction logic, which is
|
||||
# exact and cannot overflow. The performance is also
|
||||
# acceptable: we try the fast all-float option first, and
|
||||
# we know that fraction(dB) can have at most a few hundred
|
||||
# digits in each part. The worst-case slowdown is therefore
|
||||
# for already-slow enormous integers or Decimals.
|
||||
failed = (Fraction(instance) / Fraction(dB)).denominator != 1
|
||||
else:
|
||||
failed = instance % dB
|
||||
|
||||
if failed:
|
||||
yield ValidationError(f"{instance!r} is not a multiple of {dB}")
|
||||
|
||||
|
||||
def minItems(validator, mI, instance, schema):
|
||||
if validator.is_type(instance, "array") and len(instance) < mI:
|
||||
yield ValidationError(f"{instance!r} is too short")
|
||||
|
||||
|
||||
def maxItems(validator, mI, instance, schema):
|
||||
if validator.is_type(instance, "array") and len(instance) > mI:
|
||||
yield ValidationError(f"{instance!r} is too long")
|
||||
|
||||
|
||||
def uniqueItems(validator, uI, instance, schema):
|
||||
if (
|
||||
uI
|
||||
and validator.is_type(instance, "array")
|
||||
and not uniq(instance)
|
||||
):
|
||||
yield ValidationError(f"{instance!r} has non-unique elements")
|
||||
|
||||
|
||||
def pattern(validator, patrn, instance, schema):
|
||||
if (
|
||||
validator.is_type(instance, "string")
|
||||
and not re.search(patrn, instance)
|
||||
):
|
||||
yield ValidationError(f"{instance!r} does not match {patrn!r}")
|
||||
|
||||
|
||||
def format(validator, format, instance, schema):
|
||||
if validator.format_checker is not None:
|
||||
try:
|
||||
validator.format_checker.check(instance, format)
|
||||
except FormatError as error:
|
||||
yield ValidationError(error.message, cause=error.cause)
|
||||
|
||||
|
||||
def minLength(validator, mL, instance, schema):
|
||||
if validator.is_type(instance, "string") and len(instance) < mL:
|
||||
yield ValidationError(f"{instance!r} is too short")
|
||||
|
||||
|
||||
def maxLength(validator, mL, instance, schema):
|
||||
if validator.is_type(instance, "string") and len(instance) > mL:
|
||||
yield ValidationError(f"{instance!r} is too long")
|
||||
|
||||
|
||||
def dependentRequired(validator, dependentRequired, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
|
||||
for property, dependency in dependentRequired.items():
|
||||
if property not in instance:
|
||||
continue
|
||||
|
||||
for each in dependency:
|
||||
if each not in instance:
|
||||
message = f"{each!r} is a dependency of {property!r}"
|
||||
yield ValidationError(message)
|
||||
|
||||
|
||||
def dependentSchemas(validator, dependentSchemas, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
|
||||
for property, dependency in dependentSchemas.items():
|
||||
if property not in instance:
|
||||
continue
|
||||
yield from validator.descend(
|
||||
instance, dependency, schema_path=property,
|
||||
)
|
||||
|
||||
|
||||
def enum(validator, enums, instance, schema):
|
||||
if instance == 0 or instance == 1:
|
||||
unbooled = unbool(instance)
|
||||
if all(unbooled != unbool(each) for each in enums):
|
||||
yield ValidationError(f"{instance!r} is not one of {enums!r}")
|
||||
elif instance not in enums:
|
||||
yield ValidationError(f"{instance!r} is not one of {enums!r}")
|
||||
|
||||
|
||||
def ref(validator, ref, instance, schema):
|
||||
resolve = getattr(validator.resolver, "resolve", None)
|
||||
if resolve is None:
|
||||
with validator.resolver.resolving(ref) as resolved:
|
||||
yield from validator.descend(instance, resolved)
|
||||
else:
|
||||
scope, resolved = validator.resolver.resolve(ref)
|
||||
validator.resolver.push_scope(scope)
|
||||
|
||||
try:
|
||||
yield from validator.descend(instance, resolved)
|
||||
finally:
|
||||
validator.resolver.pop_scope()
|
||||
|
||||
|
||||
def dynamicRef(validator, dynamicRef, instance, schema):
|
||||
_, fragment = urldefrag(dynamicRef)
|
||||
|
||||
for url in validator.resolver._scopes_stack:
|
||||
lookup_url = urljoin(url, dynamicRef)
|
||||
with validator.resolver.resolving(lookup_url) as subschema:
|
||||
if ("$dynamicAnchor" in subschema
|
||||
and fragment == subschema["$dynamicAnchor"]):
|
||||
yield from validator.descend(instance, subschema)
|
||||
break
|
||||
else:
|
||||
with validator.resolver.resolving(dynamicRef) as subschema:
|
||||
yield from validator.descend(instance, subschema)
|
||||
|
||||
|
||||
def type(validator, types, instance, schema):
|
||||
types = ensure_list(types)
|
||||
|
||||
if not any(validator.is_type(instance, type) for type in types):
|
||||
reprs = ", ".join(repr(type) for type in types)
|
||||
yield ValidationError(f"{instance!r} is not of type {reprs}")
|
||||
|
||||
|
||||
def properties(validator, properties, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
|
||||
for property, subschema in properties.items():
|
||||
if property in instance:
|
||||
yield from validator.descend(
|
||||
instance[property],
|
||||
subschema,
|
||||
path=property,
|
||||
schema_path=property,
|
||||
)
|
||||
|
||||
|
||||
def required(validator, required, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
for property in required:
|
||||
if property not in instance:
|
||||
yield ValidationError(f"{property!r} is a required property")
|
||||
|
||||
|
||||
def minProperties(validator, mP, instance, schema):
|
||||
if validator.is_type(instance, "object") and len(instance) < mP:
|
||||
yield ValidationError(f"{instance!r} does not have enough properties")
|
||||
|
||||
|
||||
def maxProperties(validator, mP, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
if validator.is_type(instance, "object") and len(instance) > mP:
|
||||
yield ValidationError(f"{instance!r} has too many properties")
|
||||
|
||||
|
||||
def allOf(validator, allOf, instance, schema):
|
||||
for index, subschema in enumerate(allOf):
|
||||
yield from validator.descend(instance, subschema, schema_path=index)
|
||||
|
||||
|
||||
def anyOf(validator, anyOf, instance, schema):
|
||||
all_errors = []
|
||||
for index, subschema in enumerate(anyOf):
|
||||
errs = list(validator.descend(instance, subschema, schema_path=index))
|
||||
if not errs:
|
||||
break
|
||||
all_errors.extend(errs)
|
||||
else:
|
||||
yield ValidationError(
|
||||
f"{instance!r} is not valid under any of the given schemas",
|
||||
context=all_errors,
|
||||
)
|
||||
|
||||
|
||||
def oneOf(validator, oneOf, instance, schema):
|
||||
subschemas = enumerate(oneOf)
|
||||
all_errors = []
|
||||
for index, subschema in subschemas:
|
||||
errs = list(validator.descend(instance, subschema, schema_path=index))
|
||||
if not errs:
|
||||
first_valid = subschema
|
||||
break
|
||||
all_errors.extend(errs)
|
||||
else:
|
||||
yield ValidationError(
|
||||
f"{instance!r} is not valid under any of the given schemas",
|
||||
context=all_errors,
|
||||
)
|
||||
|
||||
more_valid = [
|
||||
each for _, each in subschemas
|
||||
if validator.evolve(schema=each).is_valid(instance)
|
||||
]
|
||||
if more_valid:
|
||||
more_valid.append(first_valid)
|
||||
reprs = ", ".join(repr(schema) for schema in more_valid)
|
||||
yield ValidationError(f"{instance!r} is valid under each of {reprs}")
|
||||
|
||||
|
||||
def not_(validator, not_schema, instance, schema):
|
||||
if validator.evolve(schema=not_schema).is_valid(instance):
|
||||
message = f"{instance!r} should not be valid under {not_schema!r}"
|
||||
yield ValidationError(message)
|
||||
|
||||
|
||||
def if_(validator, if_schema, instance, schema):
|
||||
if validator.evolve(schema=if_schema).is_valid(instance):
|
||||
if "then" in schema:
|
||||
then = schema["then"]
|
||||
yield from validator.descend(instance, then, schema_path="then")
|
||||
elif "else" in schema:
|
||||
else_ = schema["else"]
|
||||
yield from validator.descend(instance, else_, schema_path="else")
|
||||
|
||||
|
||||
def unevaluatedItems(validator, unevaluatedItems, instance, schema):
|
||||
if not validator.is_type(instance, "array"):
|
||||
return
|
||||
evaluated_item_indexes = find_evaluated_item_indexes_by_schema(
|
||||
validator, instance, schema,
|
||||
)
|
||||
unevaluated_items = [
|
||||
item for index, item in enumerate(instance)
|
||||
if index not in evaluated_item_indexes
|
||||
]
|
||||
if unevaluated_items:
|
||||
error = "Unevaluated items are not allowed (%s %s unexpected)"
|
||||
yield ValidationError(error % extras_msg(unevaluated_items))
|
||||
|
||||
|
||||
def unevaluatedProperties(validator, unevaluatedProperties, instance, schema):
|
||||
if not validator.is_type(instance, "object"):
|
||||
return
|
||||
evaluated_property_keys = find_evaluated_property_keys_by_schema(
|
||||
validator, instance, schema,
|
||||
)
|
||||
unevaluated_property_keys = []
|
||||
for property in instance:
|
||||
if property not in evaluated_property_keys:
|
||||
for _ in validator.descend(
|
||||
instance[property],
|
||||
unevaluatedProperties,
|
||||
path=property,
|
||||
schema_path=property,
|
||||
):
|
||||
unevaluated_property_keys.append(property)
|
||||
|
||||
if unevaluated_property_keys:
|
||||
error = "Unevaluated properties are not allowed (%s %s unexpected)"
|
||||
yield ValidationError(error % extras_msg(unevaluated_property_keys))
|
||||
|
||||
|
||||
def prefixItems(validator, prefixItems, instance, schema):
|
||||
if not validator.is_type(instance, "array"):
|
||||
return
|
||||
|
||||
for (index, item), subschema in zip(enumerate(instance), prefixItems):
|
||||
yield from validator.descend(
|
||||
instance=item,
|
||||
schema=subschema,
|
||||
schema_path=index,
|
||||
path=index,
|
||||
)
|
||||
|
|
@ -0,0 +1,5 @@
|
|||
"""
|
||||
Benchmarks for validation.
|
||||
|
||||
This package is *not* public API.
|
||||
"""
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
"""
|
||||
A performance benchmark using the example from issue #232.
|
||||
|
||||
See https://github.com/python-jsonschema/jsonschema/pull/232.
|
||||
"""
|
||||
from pathlib import Path
|
||||
|
||||
from pyperf import Runner
|
||||
from pyrsistent import m
|
||||
|
||||
from jsonschema.tests._suite import Version
|
||||
import jsonschema
|
||||
|
||||
issue232 = Version(
|
||||
path=Path(__file__).parent / "issue232",
|
||||
remotes=m(),
|
||||
name="issue232",
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
issue232.benchmark(
|
||||
runner=Runner(),
|
||||
Validator=jsonschema.Draft4Validator,
|
||||
)
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,12 @@
|
|||
"""
|
||||
A performance benchmark using the official test suite.
|
||||
|
||||
This benchmarks jsonschema using every valid example in the
|
||||
JSON-Schema-Test-Suite. It will take some time to complete.
|
||||
"""
|
||||
from pyperf import Runner
|
||||
|
||||
from jsonschema.tests._suite import Suite
|
||||
|
||||
if __name__ == "__main__":
|
||||
Suite().benchmark(runner=Runner())
|
||||
|
|
@ -0,0 +1,299 @@
|
|||
"""
|
||||
The ``jsonschema`` command line.
|
||||
"""
|
||||
|
||||
from json import JSONDecodeError
|
||||
from textwrap import dedent
|
||||
import argparse
|
||||
import json
|
||||
import sys
|
||||
import traceback
|
||||
import warnings
|
||||
|
||||
try:
|
||||
from importlib import metadata
|
||||
except ImportError:
|
||||
import importlib_metadata as metadata # type: ignore
|
||||
|
||||
try:
|
||||
from pkgutil import resolve_name
|
||||
except ImportError:
|
||||
from pkgutil_resolve_name import resolve_name # type: ignore
|
||||
|
||||
import attr
|
||||
|
||||
from jsonschema.exceptions import SchemaError
|
||||
from jsonschema.validators import RefResolver, validator_for
|
||||
|
||||
warnings.warn(
|
||||
(
|
||||
"The jsonschema CLI is deprecated and will be removed in a future "
|
||||
"version. Please use check-jsonschema instead, which can be installed "
|
||||
"from https://pypi.org/project/check-jsonschema/"
|
||||
),
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
|
||||
|
||||
class _CannotLoadFile(Exception):
|
||||
pass
|
||||
|
||||
|
||||
@attr.s
|
||||
class _Outputter:
|
||||
|
||||
_formatter = attr.ib()
|
||||
_stdout = attr.ib()
|
||||
_stderr = attr.ib()
|
||||
|
||||
@classmethod
|
||||
def from_arguments(cls, arguments, stdout, stderr):
|
||||
if arguments["output"] == "plain":
|
||||
formatter = _PlainFormatter(arguments["error_format"])
|
||||
elif arguments["output"] == "pretty":
|
||||
formatter = _PrettyFormatter()
|
||||
return cls(formatter=formatter, stdout=stdout, stderr=stderr)
|
||||
|
||||
def load(self, path):
|
||||
try:
|
||||
file = open(path)
|
||||
except FileNotFoundError:
|
||||
self.filenotfound_error(path=path, exc_info=sys.exc_info())
|
||||
raise _CannotLoadFile()
|
||||
|
||||
with file:
|
||||
try:
|
||||
return json.load(file)
|
||||
except JSONDecodeError:
|
||||
self.parsing_error(path=path, exc_info=sys.exc_info())
|
||||
raise _CannotLoadFile()
|
||||
|
||||
def filenotfound_error(self, **kwargs):
|
||||
self._stderr.write(self._formatter.filenotfound_error(**kwargs))
|
||||
|
||||
def parsing_error(self, **kwargs):
|
||||
self._stderr.write(self._formatter.parsing_error(**kwargs))
|
||||
|
||||
def validation_error(self, **kwargs):
|
||||
self._stderr.write(self._formatter.validation_error(**kwargs))
|
||||
|
||||
def validation_success(self, **kwargs):
|
||||
self._stdout.write(self._formatter.validation_success(**kwargs))
|
||||
|
||||
|
||||
@attr.s
|
||||
class _PrettyFormatter:
|
||||
|
||||
_ERROR_MSG = dedent(
|
||||
"""\
|
||||
===[{type}]===({path})===
|
||||
|
||||
{body}
|
||||
-----------------------------
|
||||
""",
|
||||
)
|
||||
_SUCCESS_MSG = "===[SUCCESS]===({path})===\n"
|
||||
|
||||
def filenotfound_error(self, path, exc_info):
|
||||
return self._ERROR_MSG.format(
|
||||
path=path,
|
||||
type="FileNotFoundError",
|
||||
body="{!r} does not exist.".format(path),
|
||||
)
|
||||
|
||||
def parsing_error(self, path, exc_info):
|
||||
exc_type, exc_value, exc_traceback = exc_info
|
||||
exc_lines = "".join(
|
||||
traceback.format_exception(exc_type, exc_value, exc_traceback),
|
||||
)
|
||||
return self._ERROR_MSG.format(
|
||||
path=path,
|
||||
type=exc_type.__name__,
|
||||
body=exc_lines,
|
||||
)
|
||||
|
||||
def validation_error(self, instance_path, error):
|
||||
return self._ERROR_MSG.format(
|
||||
path=instance_path,
|
||||
type=error.__class__.__name__,
|
||||
body=error,
|
||||
)
|
||||
|
||||
def validation_success(self, instance_path):
|
||||
return self._SUCCESS_MSG.format(path=instance_path)
|
||||
|
||||
|
||||
@attr.s
|
||||
class _PlainFormatter:
|
||||
|
||||
_error_format = attr.ib()
|
||||
|
||||
def filenotfound_error(self, path, exc_info):
|
||||
return "{!r} does not exist.\n".format(path)
|
||||
|
||||
def parsing_error(self, path, exc_info):
|
||||
return "Failed to parse {}: {}\n".format(
|
||||
"<stdin>" if path == "<stdin>" else repr(path),
|
||||
exc_info[1],
|
||||
)
|
||||
|
||||
def validation_error(self, instance_path, error):
|
||||
return self._error_format.format(file_name=instance_path, error=error)
|
||||
|
||||
def validation_success(self, instance_path):
|
||||
return ""
|
||||
|
||||
|
||||
def _resolve_name_with_default(name):
|
||||
if "." not in name:
|
||||
name = "jsonschema." + name
|
||||
return resolve_name(name)
|
||||
|
||||
|
||||
parser = argparse.ArgumentParser(
|
||||
description="JSON Schema Validation CLI",
|
||||
)
|
||||
parser.add_argument(
|
||||
"-i", "--instance",
|
||||
action="append",
|
||||
dest="instances",
|
||||
help="""
|
||||
a path to a JSON instance (i.e. filename.json) to validate (may
|
||||
be specified multiple times). If no instances are provided via this
|
||||
option, one will be expected on standard input.
|
||||
""",
|
||||
)
|
||||
parser.add_argument(
|
||||
"-F", "--error-format",
|
||||
help="""
|
||||
the format to use for each validation error message, specified
|
||||
in a form suitable for str.format. This string will be passed
|
||||
one formatted object named 'error' for each ValidationError.
|
||||
Only provide this option when using --output=plain, which is the
|
||||
default. If this argument is unprovided and --output=plain is
|
||||
used, a simple default representation will be used.
|
||||
""",
|
||||
)
|
||||
parser.add_argument(
|
||||
"-o", "--output",
|
||||
choices=["plain", "pretty"],
|
||||
default="plain",
|
||||
help="""
|
||||
an output format to use. 'plain' (default) will produce minimal
|
||||
text with one line for each error, while 'pretty' will produce
|
||||
more detailed human-readable output on multiple lines.
|
||||
""",
|
||||
)
|
||||
parser.add_argument(
|
||||
"-V", "--validator",
|
||||
type=_resolve_name_with_default,
|
||||
help="""
|
||||
the fully qualified object name of a validator to use, or, for
|
||||
validators that are registered with jsonschema, simply the name
|
||||
of the class.
|
||||
""",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--base-uri",
|
||||
help="""
|
||||
a base URI to assign to the provided schema, even if it does not
|
||||
declare one (via e.g. $id). This option can be used if you wish to
|
||||
resolve relative references to a particular URI (or local path)
|
||||
""",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--version",
|
||||
action="version",
|
||||
version=metadata.version("jsonschema"),
|
||||
)
|
||||
parser.add_argument(
|
||||
"schema",
|
||||
help="the path to a JSON Schema to validate with (i.e. schema.json)",
|
||||
)
|
||||
|
||||
|
||||
def parse_args(args):
|
||||
arguments = vars(parser.parse_args(args=args or ["--help"]))
|
||||
if arguments["output"] != "plain" and arguments["error_format"]:
|
||||
raise parser.error(
|
||||
"--error-format can only be used with --output plain",
|
||||
)
|
||||
if arguments["output"] == "plain" and arguments["error_format"] is None:
|
||||
arguments["error_format"] = "{error.instance}: {error.message}\n"
|
||||
return arguments
|
||||
|
||||
|
||||
def _validate_instance(instance_path, instance, validator, outputter):
|
||||
invalid = False
|
||||
for error in validator.iter_errors(instance):
|
||||
invalid = True
|
||||
outputter.validation_error(instance_path=instance_path, error=error)
|
||||
|
||||
if not invalid:
|
||||
outputter.validation_success(instance_path=instance_path)
|
||||
return invalid
|
||||
|
||||
|
||||
def main(args=sys.argv[1:]):
|
||||
sys.exit(run(arguments=parse_args(args=args)))
|
||||
|
||||
|
||||
def run(arguments, stdout=sys.stdout, stderr=sys.stderr, stdin=sys.stdin):
|
||||
outputter = _Outputter.from_arguments(
|
||||
arguments=arguments,
|
||||
stdout=stdout,
|
||||
stderr=stderr,
|
||||
)
|
||||
|
||||
try:
|
||||
schema = outputter.load(arguments["schema"])
|
||||
except _CannotLoadFile:
|
||||
return 1
|
||||
|
||||
if arguments["validator"] is None:
|
||||
arguments["validator"] = validator_for(schema)
|
||||
|
||||
try:
|
||||
arguments["validator"].check_schema(schema)
|
||||
except SchemaError as error:
|
||||
outputter.validation_error(
|
||||
instance_path=arguments["schema"],
|
||||
error=error,
|
||||
)
|
||||
return 1
|
||||
|
||||
if arguments["instances"]:
|
||||
load, instances = outputter.load, arguments["instances"]
|
||||
else:
|
||||
def load(_):
|
||||
try:
|
||||
return json.load(stdin)
|
||||
except JSONDecodeError:
|
||||
outputter.parsing_error(
|
||||
path="<stdin>", exc_info=sys.exc_info(),
|
||||
)
|
||||
raise _CannotLoadFile()
|
||||
instances = ["<stdin>"]
|
||||
|
||||
resolver = RefResolver(
|
||||
base_uri=arguments["base_uri"],
|
||||
referrer=schema,
|
||||
) if arguments["base_uri"] is not None else None
|
||||
|
||||
validator = arguments["validator"](schema, resolver=resolver)
|
||||
exit_code = 0
|
||||
for each in instances:
|
||||
try:
|
||||
instance = load(each)
|
||||
except _CannotLoadFile:
|
||||
exit_code = 1
|
||||
else:
|
||||
exit_code |= _validate_instance(
|
||||
instance_path=each,
|
||||
instance=instance,
|
||||
validator=validator,
|
||||
outputter=outputter,
|
||||
)
|
||||
|
||||
return exit_code
|
||||
|
|
@ -0,0 +1,396 @@
|
|||
"""
|
||||
Validation errors, and some surrounding helpers.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from collections import defaultdict, deque
|
||||
from pprint import pformat
|
||||
from textwrap import dedent, indent
|
||||
import heapq
|
||||
import itertools
|
||||
|
||||
import attr
|
||||
|
||||
from jsonschema import _utils
|
||||
|
||||
WEAK_MATCHES: frozenset[str] = frozenset(["anyOf", "oneOf"])
|
||||
STRONG_MATCHES: frozenset[str] = frozenset()
|
||||
|
||||
_unset = _utils.Unset()
|
||||
|
||||
|
||||
class _Error(Exception):
|
||||
def __init__(
|
||||
self,
|
||||
message,
|
||||
validator=_unset,
|
||||
path=(),
|
||||
cause=None,
|
||||
context=(),
|
||||
validator_value=_unset,
|
||||
instance=_unset,
|
||||
schema=_unset,
|
||||
schema_path=(),
|
||||
parent=None,
|
||||
type_checker=_unset,
|
||||
):
|
||||
super(_Error, self).__init__(
|
||||
message,
|
||||
validator,
|
||||
path,
|
||||
cause,
|
||||
context,
|
||||
validator_value,
|
||||
instance,
|
||||
schema,
|
||||
schema_path,
|
||||
parent,
|
||||
)
|
||||
self.message = message
|
||||
self.path = self.relative_path = deque(path)
|
||||
self.schema_path = self.relative_schema_path = deque(schema_path)
|
||||
self.context = list(context)
|
||||
self.cause = self.__cause__ = cause
|
||||
self.validator = validator
|
||||
self.validator_value = validator_value
|
||||
self.instance = instance
|
||||
self.schema = schema
|
||||
self.parent = parent
|
||||
self._type_checker = type_checker
|
||||
|
||||
for error in context:
|
||||
error.parent = self
|
||||
|
||||
def __repr__(self):
|
||||
return f"<{self.__class__.__name__}: {self.message!r}>"
|
||||
|
||||
def __str__(self):
|
||||
essential_for_verbose = (
|
||||
self.validator, self.validator_value, self.instance, self.schema,
|
||||
)
|
||||
if any(m is _unset for m in essential_for_verbose):
|
||||
return self.message
|
||||
|
||||
schema_path = _utils.format_as_index(
|
||||
container=self._word_for_schema_in_error_message,
|
||||
indices=list(self.relative_schema_path)[:-1],
|
||||
)
|
||||
instance_path = _utils.format_as_index(
|
||||
container=self._word_for_instance_in_error_message,
|
||||
indices=self.relative_path,
|
||||
)
|
||||
prefix = 16 * " "
|
||||
|
||||
return dedent(
|
||||
f"""\
|
||||
{self.message}
|
||||
|
||||
Failed validating {self.validator!r} in {schema_path}:
|
||||
{indent(pformat(self.schema, width=72), prefix).lstrip()}
|
||||
|
||||
On {instance_path}:
|
||||
{indent(pformat(self.instance, width=72), prefix).lstrip()}
|
||||
""".rstrip(),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def create_from(cls, other):
|
||||
return cls(**other._contents())
|
||||
|
||||
@property
|
||||
def absolute_path(self):
|
||||
parent = self.parent
|
||||
if parent is None:
|
||||
return self.relative_path
|
||||
|
||||
path = deque(self.relative_path)
|
||||
path.extendleft(reversed(parent.absolute_path))
|
||||
return path
|
||||
|
||||
@property
|
||||
def absolute_schema_path(self):
|
||||
parent = self.parent
|
||||
if parent is None:
|
||||
return self.relative_schema_path
|
||||
|
||||
path = deque(self.relative_schema_path)
|
||||
path.extendleft(reversed(parent.absolute_schema_path))
|
||||
return path
|
||||
|
||||
@property
|
||||
def json_path(self):
|
||||
path = "$"
|
||||
for elem in self.absolute_path:
|
||||
if isinstance(elem, int):
|
||||
path += "[" + str(elem) + "]"
|
||||
else:
|
||||
path += "." + elem
|
||||
return path
|
||||
|
||||
def _set(self, type_checker=None, **kwargs):
|
||||
if type_checker is not None and self._type_checker is _unset:
|
||||
self._type_checker = type_checker
|
||||
|
||||
for k, v in kwargs.items():
|
||||
if getattr(self, k) is _unset:
|
||||
setattr(self, k, v)
|
||||
|
||||
def _contents(self):
|
||||
attrs = (
|
||||
"message", "cause", "context", "validator", "validator_value",
|
||||
"path", "schema_path", "instance", "schema", "parent",
|
||||
)
|
||||
return dict((attr, getattr(self, attr)) for attr in attrs)
|
||||
|
||||
def _matches_type(self):
|
||||
try:
|
||||
expected = self.schema["type"]
|
||||
except (KeyError, TypeError):
|
||||
return False
|
||||
|
||||
if isinstance(expected, str):
|
||||
return self._type_checker.is_type(self.instance, expected)
|
||||
|
||||
return any(
|
||||
self._type_checker.is_type(self.instance, expected_type)
|
||||
for expected_type in expected
|
||||
)
|
||||
|
||||
|
||||
class ValidationError(_Error):
|
||||
"""
|
||||
An instance was invalid under a provided schema.
|
||||
"""
|
||||
|
||||
_word_for_schema_in_error_message = "schema"
|
||||
_word_for_instance_in_error_message = "instance"
|
||||
|
||||
|
||||
class SchemaError(_Error):
|
||||
"""
|
||||
A schema was invalid under its corresponding metaschema.
|
||||
"""
|
||||
|
||||
_word_for_schema_in_error_message = "metaschema"
|
||||
_word_for_instance_in_error_message = "schema"
|
||||
|
||||
|
||||
@attr.s(hash=True)
|
||||
class RefResolutionError(Exception):
|
||||
"""
|
||||
A ref could not be resolved.
|
||||
"""
|
||||
|
||||
_cause = attr.ib()
|
||||
|
||||
def __str__(self):
|
||||
return str(self._cause)
|
||||
|
||||
|
||||
class UndefinedTypeCheck(Exception):
|
||||
"""
|
||||
A type checker was asked to check a type it did not have registered.
|
||||
"""
|
||||
|
||||
def __init__(self, type):
|
||||
self.type = type
|
||||
|
||||
def __str__(self):
|
||||
return f"Type {self.type!r} is unknown to this type checker"
|
||||
|
||||
|
||||
class UnknownType(Exception):
|
||||
"""
|
||||
A validator was asked to validate an instance against an unknown type.
|
||||
"""
|
||||
|
||||
def __init__(self, type, instance, schema):
|
||||
self.type = type
|
||||
self.instance = instance
|
||||
self.schema = schema
|
||||
|
||||
def __str__(self):
|
||||
prefix = 16 * " "
|
||||
|
||||
return dedent(
|
||||
f"""\
|
||||
Unknown type {self.type!r} for validator with schema:
|
||||
{indent(pformat(self.schema, width=72), prefix).lstrip()}
|
||||
|
||||
While checking instance:
|
||||
{indent(pformat(self.instance, width=72), prefix).lstrip()}
|
||||
""".rstrip(),
|
||||
)
|
||||
|
||||
|
||||
class FormatError(Exception):
|
||||
"""
|
||||
Validating a format failed.
|
||||
"""
|
||||
|
||||
def __init__(self, message, cause=None):
|
||||
super(FormatError, self).__init__(message, cause)
|
||||
self.message = message
|
||||
self.cause = self.__cause__ = cause
|
||||
|
||||
def __str__(self):
|
||||
return self.message
|
||||
|
||||
|
||||
class ErrorTree:
|
||||
"""
|
||||
ErrorTrees make it easier to check which validations failed.
|
||||
"""
|
||||
|
||||
_instance = _unset
|
||||
|
||||
def __init__(self, errors=()):
|
||||
self.errors = {}
|
||||
self._contents = defaultdict(self.__class__)
|
||||
|
||||
for error in errors:
|
||||
container = self
|
||||
for element in error.path:
|
||||
container = container[element]
|
||||
container.errors[error.validator] = error
|
||||
|
||||
container._instance = error.instance
|
||||
|
||||
def __contains__(self, index):
|
||||
"""
|
||||
Check whether ``instance[index]`` has any errors.
|
||||
"""
|
||||
|
||||
return index in self._contents
|
||||
|
||||
def __getitem__(self, index):
|
||||
"""
|
||||
Retrieve the child tree one level down at the given ``index``.
|
||||
|
||||
If the index is not in the instance that this tree corresponds
|
||||
to and is not known by this tree, whatever error would be raised
|
||||
by ``instance.__getitem__`` will be propagated (usually this is
|
||||
some subclass of `LookupError`.
|
||||
"""
|
||||
|
||||
if self._instance is not _unset and index not in self:
|
||||
self._instance[index]
|
||||
return self._contents[index]
|
||||
|
||||
def __setitem__(self, index, value):
|
||||
"""
|
||||
Add an error to the tree at the given ``index``.
|
||||
"""
|
||||
self._contents[index] = value
|
||||
|
||||
def __iter__(self):
|
||||
"""
|
||||
Iterate (non-recursively) over the indices in the instance with errors.
|
||||
"""
|
||||
|
||||
return iter(self._contents)
|
||||
|
||||
def __len__(self):
|
||||
"""
|
||||
Return the `total_errors`.
|
||||
"""
|
||||
return self.total_errors
|
||||
|
||||
def __repr__(self):
|
||||
total = len(self)
|
||||
errors = "error" if total == 1 else "errors"
|
||||
return f"<{self.__class__.__name__} ({total} total {errors})>"
|
||||
|
||||
@property
|
||||
def total_errors(self):
|
||||
"""
|
||||
The total number of errors in the entire tree, including children.
|
||||
"""
|
||||
|
||||
child_errors = sum(len(tree) for _, tree in self._contents.items())
|
||||
return len(self.errors) + child_errors
|
||||
|
||||
|
||||
def by_relevance(weak=WEAK_MATCHES, strong=STRONG_MATCHES):
|
||||
"""
|
||||
Create a key function that can be used to sort errors by relevance.
|
||||
|
||||
Arguments:
|
||||
weak (set):
|
||||
a collection of validation keywords to consider to be
|
||||
"weak". If there are two errors at the same level of the
|
||||
instance and one is in the set of weak validation keywords,
|
||||
the other error will take priority. By default, :kw:`anyOf`
|
||||
and :kw:`oneOf` are considered weak keywords and will be
|
||||
superseded by other same-level validation errors.
|
||||
|
||||
strong (set):
|
||||
a collection of validation keywords to consider to be
|
||||
"strong"
|
||||
"""
|
||||
def relevance(error):
|
||||
validator = error.validator
|
||||
return (
|
||||
-len(error.path),
|
||||
validator not in weak,
|
||||
validator in strong,
|
||||
not error._matches_type(),
|
||||
)
|
||||
return relevance
|
||||
|
||||
|
||||
relevance = by_relevance()
|
||||
|
||||
|
||||
def best_match(errors, key=relevance):
|
||||
"""
|
||||
Try to find an error that appears to be the best match among given errors.
|
||||
|
||||
In general, errors that are higher up in the instance (i.e. for which
|
||||
`ValidationError.path` is shorter) are considered better matches,
|
||||
since they indicate "more" is wrong with the instance.
|
||||
|
||||
If the resulting match is either :kw:`oneOf` or :kw:`anyOf`, the
|
||||
*opposite* assumption is made -- i.e. the deepest error is picked,
|
||||
since these keywords only need to match once, and any other errors
|
||||
may not be relevant.
|
||||
|
||||
Arguments:
|
||||
errors (collections.abc.Iterable):
|
||||
|
||||
the errors to select from. Do not provide a mixture of
|
||||
errors from different validation attempts (i.e. from
|
||||
different instances or schemas), since it won't produce
|
||||
sensical output.
|
||||
|
||||
key (collections.abc.Callable):
|
||||
|
||||
the key to use when sorting errors. See `relevance` and
|
||||
transitively `by_relevance` for more details (the default is
|
||||
to sort with the defaults of that function). Changing the
|
||||
default is only useful if you want to change the function
|
||||
that rates errors but still want the error context descent
|
||||
done by this function.
|
||||
|
||||
Returns:
|
||||
the best matching error, or ``None`` if the iterable was empty
|
||||
|
||||
.. note::
|
||||
|
||||
This function is a heuristic. Its return value may change for a given
|
||||
set of inputs from version to version if better heuristics are added.
|
||||
"""
|
||||
errors = iter(errors)
|
||||
best = next(errors, None)
|
||||
if best is None:
|
||||
return
|
||||
best = max(itertools.chain([best], errors), key=key)
|
||||
|
||||
while best.context:
|
||||
# Calculate the minimum via nsmallest, because we don't recurse if
|
||||
# all nested errors have the same relevance (i.e. if min == max == all)
|
||||
smallest = heapq.nsmallest(2, best.context, key=key)
|
||||
if len(smallest) == 2 and key(smallest[0]) == key(smallest[1]):
|
||||
return best
|
||||
best = smallest[0]
|
||||
return best
|
||||
|
|
@ -0,0 +1,224 @@
|
|||
"""
|
||||
typing.Protocol classes for jsonschema interfaces.
|
||||
"""
|
||||
|
||||
# for reference material on Protocols, see
|
||||
# https://www.python.org/dev/peps/pep-0544/
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Callable, Mapping
|
||||
from typing import TYPE_CHECKING, Any, ClassVar, Iterable
|
||||
import sys
|
||||
|
||||
# doing these imports with `try ... except ImportError` doesn't pass mypy
|
||||
# checking because mypy sees `typing._SpecialForm` and
|
||||
# `typing_extensions._SpecialForm` as incompatible
|
||||
#
|
||||
# see:
|
||||
# https://mypy.readthedocs.io/en/stable/runtime_troubles.html#using-new-additions-to-the-typing-module
|
||||
# https://github.com/python/mypy/issues/4427
|
||||
if sys.version_info >= (3, 8):
|
||||
from typing import Protocol, runtime_checkable
|
||||
else:
|
||||
from typing_extensions import Protocol, runtime_checkable
|
||||
|
||||
# in order for Sphinx to resolve references accurately from type annotations,
|
||||
# it needs to see names like `jsonschema.TypeChecker`
|
||||
# therefore, only import at type-checking time (to avoid circular references),
|
||||
# but use `jsonschema` for any types which will otherwise not be resolvable
|
||||
if TYPE_CHECKING:
|
||||
import jsonschema
|
||||
|
||||
from jsonschema.exceptions import ValidationError
|
||||
|
||||
# For code authors working on the validator protocol, these are the three
|
||||
# use-cases which should be kept in mind:
|
||||
#
|
||||
# 1. As a protocol class, it can be used in type annotations to describe the
|
||||
# available methods and attributes of a validator
|
||||
# 2. It is the source of autodoc for the validator documentation
|
||||
# 3. It is runtime_checkable, meaning that it can be used in isinstance()
|
||||
# checks.
|
||||
#
|
||||
# Since protocols are not base classes, isinstance() checking is limited in
|
||||
# its capabilities. See docs on runtime_checkable for detail
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class Validator(Protocol):
|
||||
"""
|
||||
The protocol to which all validator classes adhere.
|
||||
|
||||
Arguments:
|
||||
|
||||
schema:
|
||||
|
||||
The schema that the validator object will validate with.
|
||||
It is assumed to be valid, and providing
|
||||
an invalid schema can lead to undefined behavior. See
|
||||
`Validator.check_schema` to validate a schema first.
|
||||
|
||||
resolver:
|
||||
|
||||
a resolver that will be used to resolve :kw:`$ref`
|
||||
properties (JSON references). If unprovided, one will be created.
|
||||
|
||||
format_checker:
|
||||
|
||||
if provided, a checker which will be used to assert about
|
||||
:kw:`format` properties present in the schema. If unprovided,
|
||||
*no* format validation is done, and the presence of format
|
||||
within schemas is strictly informational. Certain formats
|
||||
require additional packages to be installed in order to assert
|
||||
against instances. Ensure you've installed `jsonschema` with
|
||||
its `extra (optional) dependencies <index:extras>` when
|
||||
invoking ``pip``.
|
||||
|
||||
.. deprecated:: v4.12.0
|
||||
|
||||
Subclassing validator classes now explicitly warns this is not part of
|
||||
their public API.
|
||||
"""
|
||||
|
||||
#: An object representing the validator's meta schema (the schema that
|
||||
#: describes valid schemas in the given version).
|
||||
META_SCHEMA: ClassVar[Mapping]
|
||||
|
||||
#: A mapping of validation keywords (`str`\s) to functions that
|
||||
#: validate the keyword with that name. For more information see
|
||||
#: `creating-validators`.
|
||||
VALIDATORS: ClassVar[Mapping]
|
||||
|
||||
#: A `jsonschema.TypeChecker` that will be used when validating
|
||||
#: :kw:`type` keywords in JSON schemas.
|
||||
TYPE_CHECKER: ClassVar[jsonschema.TypeChecker]
|
||||
|
||||
#: A `jsonschema.FormatChecker` that will be used when validating
|
||||
#: :kw:`format` keywords in JSON schemas.
|
||||
FORMAT_CHECKER: ClassVar[jsonschema.FormatChecker]
|
||||
|
||||
#: A function which given a schema returns its ID.
|
||||
ID_OF: Callable[[Any], str | None]
|
||||
|
||||
#: The schema that will be used to validate instances
|
||||
schema: Mapping | bool
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
schema: Mapping | bool,
|
||||
resolver: jsonschema.RefResolver | None = None,
|
||||
format_checker: jsonschema.FormatChecker | None = None,
|
||||
) -> None:
|
||||
...
|
||||
|
||||
@classmethod
|
||||
def check_schema(cls, schema: Mapping | bool) -> None:
|
||||
"""
|
||||
Validate the given schema against the validator's `META_SCHEMA`.
|
||||
|
||||
Raises:
|
||||
|
||||
`jsonschema.exceptions.SchemaError`:
|
||||
|
||||
if the schema is invalid
|
||||
"""
|
||||
|
||||
def is_type(self, instance: Any, type: str) -> bool:
|
||||
"""
|
||||
Check if the instance is of the given (JSON Schema) type.
|
||||
|
||||
Arguments:
|
||||
|
||||
instance:
|
||||
|
||||
the value to check
|
||||
|
||||
type:
|
||||
|
||||
the name of a known (JSON Schema) type
|
||||
|
||||
Returns:
|
||||
|
||||
whether the instance is of the given type
|
||||
|
||||
Raises:
|
||||
|
||||
`jsonschema.exceptions.UnknownType`:
|
||||
|
||||
if ``type`` is not a known type
|
||||
"""
|
||||
|
||||
def is_valid(self, instance: Any) -> bool:
|
||||
"""
|
||||
Check if the instance is valid under the current `schema`.
|
||||
|
||||
Returns:
|
||||
|
||||
whether the instance is valid or not
|
||||
|
||||
>>> schema = {"maxItems" : 2}
|
||||
>>> Draft202012Validator(schema).is_valid([2, 3, 4])
|
||||
False
|
||||
"""
|
||||
|
||||
def iter_errors(self, instance: Any) -> Iterable[ValidationError]:
|
||||
r"""
|
||||
Lazily yield each of the validation errors in the given instance.
|
||||
|
||||
>>> schema = {
|
||||
... "type" : "array",
|
||||
... "items" : {"enum" : [1, 2, 3]},
|
||||
... "maxItems" : 2,
|
||||
... }
|
||||
>>> v = Draft202012Validator(schema)
|
||||
>>> for error in sorted(v.iter_errors([2, 3, 4]), key=str):
|
||||
... print(error.message)
|
||||
4 is not one of [1, 2, 3]
|
||||
[2, 3, 4] is too long
|
||||
|
||||
.. deprecated:: v4.0.0
|
||||
|
||||
Calling this function with a second schema argument is deprecated.
|
||||
Use `Validator.evolve` instead.
|
||||
"""
|
||||
|
||||
def validate(self, instance: Any) -> None:
|
||||
"""
|
||||
Check if the instance is valid under the current `schema`.
|
||||
|
||||
Raises:
|
||||
|
||||
`jsonschema.exceptions.ValidationError`:
|
||||
|
||||
if the instance is invalid
|
||||
|
||||
>>> schema = {"maxItems" : 2}
|
||||
>>> Draft202012Validator(schema).validate([2, 3, 4])
|
||||
Traceback (most recent call last):
|
||||
...
|
||||
ValidationError: [2, 3, 4] is too long
|
||||
"""
|
||||
|
||||
def evolve(self, **kwargs) -> "Validator":
|
||||
"""
|
||||
Create a new validator like this one, but with given changes.
|
||||
|
||||
Preserves all other attributes, so can be used to e.g. create a
|
||||
validator with a different schema but with the same :kw:`$ref`
|
||||
resolution behavior.
|
||||
|
||||
>>> validator = Draft202012Validator({})
|
||||
>>> validator.evolve(schema={"type": "number"})
|
||||
Draft202012Validator(schema={'type': 'number'}, format_checker=None)
|
||||
|
||||
The returned object satisfies the validator protocol, but may not
|
||||
be of the same concrete class! In particular this occurs
|
||||
when a :kw:`$ref` occurs to a schema with a different
|
||||
:kw:`$schema` than this one (i.e. for a different draft).
|
||||
|
||||
>>> validator.evolve(
|
||||
... schema={"$schema": Draft7Validator.META_SCHEMA["$id"]}
|
||||
... )
|
||||
Draft7Validator(schema=..., format_checker=None)
|
||||
"""
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
{
|
||||
"$schema": "https://json-schema.org/draft/2019-09/schema",
|
||||
"$id": "https://json-schema.org/draft/2019-09/schema",
|
||||
"$vocabulary": {
|
||||
"https://json-schema.org/draft/2019-09/vocab/core": true,
|
||||
"https://json-schema.org/draft/2019-09/vocab/applicator": true,
|
||||
"https://json-schema.org/draft/2019-09/vocab/validation": true,
|
||||
"https://json-schema.org/draft/2019-09/vocab/meta-data": true,
|
||||
"https://json-schema.org/draft/2019-09/vocab/format": false,
|
||||
"https://json-schema.org/draft/2019-09/vocab/content": true
|
||||
},
|
||||
"$recursiveAnchor": true,
|
||||
|
||||
"title": "Core and Validation specifications meta-schema",
|
||||
"allOf": [
|
||||
{"$ref": "meta/core"},
|
||||
{"$ref": "meta/applicator"},
|
||||
{"$ref": "meta/validation"},
|
||||
{"$ref": "meta/meta-data"},
|
||||
{"$ref": "meta/format"},
|
||||
{"$ref": "meta/content"}
|
||||
],
|
||||
"type": ["object", "boolean"],
|
||||
"properties": {
|
||||
"definitions": {
|
||||
"$comment": "While no longer an official keyword as it is replaced by $defs, this keyword is retained in the meta-schema to prevent incompatible extensions as it remains in common use.",
|
||||
"type": "object",
|
||||
"additionalProperties": { "$recursiveRef": "#" },
|
||||
"default": {}
|
||||
},
|
||||
"dependencies": {
|
||||
"$comment": "\"dependencies\" is no longer a keyword, but schema authors should avoid redefining it to facilitate a smooth transition to \"dependentSchemas\" and \"dependentRequired\"",
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"anyOf": [
|
||||
{ "$recursiveRef": "#" },
|
||||
{ "$ref": "meta/validation#/$defs/stringArray" }
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,58 @@
|
|||
{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"$id": "https://json-schema.org/draft/2020-12/schema",
|
||||
"$vocabulary": {
|
||||
"https://json-schema.org/draft/2020-12/vocab/core": true,
|
||||
"https://json-schema.org/draft/2020-12/vocab/applicator": true,
|
||||
"https://json-schema.org/draft/2020-12/vocab/unevaluated": true,
|
||||
"https://json-schema.org/draft/2020-12/vocab/validation": true,
|
||||
"https://json-schema.org/draft/2020-12/vocab/meta-data": true,
|
||||
"https://json-schema.org/draft/2020-12/vocab/format-annotation": true,
|
||||
"https://json-schema.org/draft/2020-12/vocab/content": true
|
||||
},
|
||||
"$dynamicAnchor": "meta",
|
||||
|
||||
"title": "Core and Validation specifications meta-schema",
|
||||
"allOf": [
|
||||
{"$ref": "meta/core"},
|
||||
{"$ref": "meta/applicator"},
|
||||
{"$ref": "meta/unevaluated"},
|
||||
{"$ref": "meta/validation"},
|
||||
{"$ref": "meta/meta-data"},
|
||||
{"$ref": "meta/format-annotation"},
|
||||
{"$ref": "meta/content"}
|
||||
],
|
||||
"type": ["object", "boolean"],
|
||||
"$comment": "This meta-schema also defines keywords that have appeared in previous drafts in order to prevent incompatible extensions as they remain in common use.",
|
||||
"properties": {
|
||||
"definitions": {
|
||||
"$comment": "\"definitions\" has been replaced by \"$defs\".",
|
||||
"type": "object",
|
||||
"additionalProperties": { "$dynamicRef": "#meta" },
|
||||
"deprecated": true,
|
||||
"default": {}
|
||||
},
|
||||
"dependencies": {
|
||||
"$comment": "\"dependencies\" has been split and replaced by \"dependentSchemas\" and \"dependentRequired\" in order to serve their differing semantics.",
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"anyOf": [
|
||||
{ "$dynamicRef": "#meta" },
|
||||
{ "$ref": "meta/validation#/$defs/stringArray" }
|
||||
]
|
||||
},
|
||||
"deprecated": true,
|
||||
"default": {}
|
||||
},
|
||||
"$recursiveAnchor": {
|
||||
"$comment": "\"$recursiveAnchor\" has been replaced by \"$dynamicAnchor\".",
|
||||
"$ref": "meta/core#/$defs/anchorString",
|
||||
"deprecated": true
|
||||
},
|
||||
"$recursiveRef": {
|
||||
"$comment": "\"$recursiveRef\" has been replaced by \"$dynamicRef\".",
|
||||
"$ref": "meta/core#/$defs/uriReferenceString",
|
||||
"deprecated": true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,172 @@
|
|||
{
|
||||
"$schema" : "http://json-schema.org/draft-03/schema#",
|
||||
"id" : "http://json-schema.org/draft-03/schema#",
|
||||
"type" : "object",
|
||||
|
||||
"properties" : {
|
||||
"type" : {
|
||||
"type" : ["string", "array"],
|
||||
"items" : {
|
||||
"type" : ["string", {"$ref" : "#"}]
|
||||
},
|
||||
"uniqueItems" : true,
|
||||
"default" : "any"
|
||||
},
|
||||
|
||||
"properties" : {
|
||||
"type" : "object",
|
||||
"additionalProperties" : {"$ref" : "#"},
|
||||
"default" : {}
|
||||
},
|
||||
|
||||
"patternProperties" : {
|
||||
"type" : "object",
|
||||
"additionalProperties" : {"$ref" : "#"},
|
||||
"default" : {}
|
||||
},
|
||||
|
||||
"additionalProperties" : {
|
||||
"type" : [{"$ref" : "#"}, "boolean"],
|
||||
"default" : {}
|
||||
},
|
||||
|
||||
"items" : {
|
||||
"type" : [{"$ref" : "#"}, "array"],
|
||||
"items" : {"$ref" : "#"},
|
||||
"default" : {}
|
||||
},
|
||||
|
||||
"additionalItems" : {
|
||||
"type" : [{"$ref" : "#"}, "boolean"],
|
||||
"default" : {}
|
||||
},
|
||||
|
||||
"required" : {
|
||||
"type" : "boolean",
|
||||
"default" : false
|
||||
},
|
||||
|
||||
"dependencies" : {
|
||||
"type" : "object",
|
||||
"additionalProperties" : {
|
||||
"type" : ["string", "array", {"$ref" : "#"}],
|
||||
"items" : {
|
||||
"type" : "string"
|
||||
}
|
||||
},
|
||||
"default" : {}
|
||||
},
|
||||
|
||||
"minimum" : {
|
||||
"type" : "number"
|
||||
},
|
||||
|
||||
"maximum" : {
|
||||
"type" : "number"
|
||||
},
|
||||
|
||||
"exclusiveMinimum" : {
|
||||
"type" : "boolean",
|
||||
"default" : false
|
||||
},
|
||||
|
||||
"exclusiveMaximum" : {
|
||||
"type" : "boolean",
|
||||
"default" : false
|
||||
},
|
||||
|
||||
"minItems" : {
|
||||
"type" : "integer",
|
||||
"minimum" : 0,
|
||||
"default" : 0
|
||||
},
|
||||
|
||||
"maxItems" : {
|
||||
"type" : "integer",
|
||||
"minimum" : 0
|
||||
},
|
||||
|
||||
"uniqueItems" : {
|
||||
"type" : "boolean",
|
||||
"default" : false
|
||||
},
|
||||
|
||||
"pattern" : {
|
||||
"type" : "string",
|
||||
"format" : "regex"
|
||||
},
|
||||
|
||||
"minLength" : {
|
||||
"type" : "integer",
|
||||
"minimum" : 0,
|
||||
"default" : 0
|
||||
},
|
||||
|
||||
"maxLength" : {
|
||||
"type" : "integer"
|
||||
},
|
||||
|
||||
"enum" : {
|
||||
"type" : "array",
|
||||
"minItems" : 1,
|
||||
"uniqueItems" : true
|
||||
},
|
||||
|
||||
"default" : {
|
||||
"type" : "any"
|
||||
},
|
||||
|
||||
"title" : {
|
||||
"type" : "string"
|
||||
},
|
||||
|
||||
"description" : {
|
||||
"type" : "string"
|
||||
},
|
||||
|
||||
"format" : {
|
||||
"type" : "string"
|
||||
},
|
||||
|
||||
"divisibleBy" : {
|
||||
"type" : "number",
|
||||
"minimum" : 0,
|
||||
"exclusiveMinimum" : true,
|
||||
"default" : 1
|
||||
},
|
||||
|
||||
"disallow" : {
|
||||
"type" : ["string", "array"],
|
||||
"items" : {
|
||||
"type" : ["string", {"$ref" : "#"}]
|
||||
},
|
||||
"uniqueItems" : true
|
||||
},
|
||||
|
||||
"extends" : {
|
||||
"type" : [{"$ref" : "#"}, "array"],
|
||||
"items" : {"$ref" : "#"},
|
||||
"default" : {}
|
||||
},
|
||||
|
||||
"id" : {
|
||||
"type" : "string"
|
||||
},
|
||||
|
||||
"$ref" : {
|
||||
"type" : "string"
|
||||
},
|
||||
|
||||
"$schema" : {
|
||||
"type" : "string",
|
||||
"format" : "uri"
|
||||
}
|
||||
},
|
||||
|
||||
"dependencies" : {
|
||||
"exclusiveMinimum" : "minimum",
|
||||
"exclusiveMaximum" : "maximum"
|
||||
},
|
||||
|
||||
"default" : {}
|
||||
}
|
||||
|
|
@ -0,0 +1,149 @@
|
|||
{
|
||||
"id": "http://json-schema.org/draft-04/schema#",
|
||||
"$schema": "http://json-schema.org/draft-04/schema#",
|
||||
"description": "Core schema meta-schema",
|
||||
"definitions": {
|
||||
"schemaArray": {
|
||||
"type": "array",
|
||||
"minItems": 1,
|
||||
"items": { "$ref": "#" }
|
||||
},
|
||||
"positiveInteger": {
|
||||
"type": "integer",
|
||||
"minimum": 0
|
||||
},
|
||||
"positiveIntegerDefault0": {
|
||||
"allOf": [ { "$ref": "#/definitions/positiveInteger" }, { "default": 0 } ]
|
||||
},
|
||||
"simpleTypes": {
|
||||
"enum": [ "array", "boolean", "integer", "null", "number", "object", "string" ]
|
||||
},
|
||||
"stringArray": {
|
||||
"type": "array",
|
||||
"items": { "type": "string" },
|
||||
"minItems": 1,
|
||||
"uniqueItems": true
|
||||
}
|
||||
},
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string"
|
||||
},
|
||||
"$schema": {
|
||||
"type": "string"
|
||||
},
|
||||
"title": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": {
|
||||
"type": "string"
|
||||
},
|
||||
"default": {},
|
||||
"multipleOf": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"exclusiveMinimum": true
|
||||
},
|
||||
"maximum": {
|
||||
"type": "number"
|
||||
},
|
||||
"exclusiveMaximum": {
|
||||
"type": "boolean",
|
||||
"default": false
|
||||
},
|
||||
"minimum": {
|
||||
"type": "number"
|
||||
},
|
||||
"exclusiveMinimum": {
|
||||
"type": "boolean",
|
||||
"default": false
|
||||
},
|
||||
"maxLength": { "$ref": "#/definitions/positiveInteger" },
|
||||
"minLength": { "$ref": "#/definitions/positiveIntegerDefault0" },
|
||||
"pattern": {
|
||||
"type": "string",
|
||||
"format": "regex"
|
||||
},
|
||||
"additionalItems": {
|
||||
"anyOf": [
|
||||
{ "type": "boolean" },
|
||||
{ "$ref": "#" }
|
||||
],
|
||||
"default": {}
|
||||
},
|
||||
"items": {
|
||||
"anyOf": [
|
||||
{ "$ref": "#" },
|
||||
{ "$ref": "#/definitions/schemaArray" }
|
||||
],
|
||||
"default": {}
|
||||
},
|
||||
"maxItems": { "$ref": "#/definitions/positiveInteger" },
|
||||
"minItems": { "$ref": "#/definitions/positiveIntegerDefault0" },
|
||||
"uniqueItems": {
|
||||
"type": "boolean",
|
||||
"default": false
|
||||
},
|
||||
"maxProperties": { "$ref": "#/definitions/positiveInteger" },
|
||||
"minProperties": { "$ref": "#/definitions/positiveIntegerDefault0" },
|
||||
"required": { "$ref": "#/definitions/stringArray" },
|
||||
"additionalProperties": {
|
||||
"anyOf": [
|
||||
{ "type": "boolean" },
|
||||
{ "$ref": "#" }
|
||||
],
|
||||
"default": {}
|
||||
},
|
||||
"definitions": {
|
||||
"type": "object",
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"default": {}
|
||||
},
|
||||
"properties": {
|
||||
"type": "object",
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"default": {}
|
||||
},
|
||||
"patternProperties": {
|
||||
"type": "object",
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"default": {}
|
||||
},
|
||||
"dependencies": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"anyOf": [
|
||||
{ "$ref": "#" },
|
||||
{ "$ref": "#/definitions/stringArray" }
|
||||
]
|
||||
}
|
||||
},
|
||||
"enum": {
|
||||
"type": "array",
|
||||
"minItems": 1,
|
||||
"uniqueItems": true
|
||||
},
|
||||
"type": {
|
||||
"anyOf": [
|
||||
{ "$ref": "#/definitions/simpleTypes" },
|
||||
{
|
||||
"type": "array",
|
||||
"items": { "$ref": "#/definitions/simpleTypes" },
|
||||
"minItems": 1,
|
||||
"uniqueItems": true
|
||||
}
|
||||
]
|
||||
},
|
||||
"format": { "type": "string" },
|
||||
"allOf": { "$ref": "#/definitions/schemaArray" },
|
||||
"anyOf": { "$ref": "#/definitions/schemaArray" },
|
||||
"oneOf": { "$ref": "#/definitions/schemaArray" },
|
||||
"not": { "$ref": "#" }
|
||||
},
|
||||
"dependencies": {
|
||||
"exclusiveMaximum": [ "maximum" ],
|
||||
"exclusiveMinimum": [ "minimum" ]
|
||||
},
|
||||
"default": {}
|
||||
}
|
||||
|
|
@ -0,0 +1,153 @@
|
|||
{
|
||||
"$schema": "http://json-schema.org/draft-06/schema#",
|
||||
"$id": "http://json-schema.org/draft-06/schema#",
|
||||
"title": "Core schema meta-schema",
|
||||
"definitions": {
|
||||
"schemaArray": {
|
||||
"type": "array",
|
||||
"minItems": 1,
|
||||
"items": { "$ref": "#" }
|
||||
},
|
||||
"nonNegativeInteger": {
|
||||
"type": "integer",
|
||||
"minimum": 0
|
||||
},
|
||||
"nonNegativeIntegerDefault0": {
|
||||
"allOf": [
|
||||
{ "$ref": "#/definitions/nonNegativeInteger" },
|
||||
{ "default": 0 }
|
||||
]
|
||||
},
|
||||
"simpleTypes": {
|
||||
"enum": [
|
||||
"array",
|
||||
"boolean",
|
||||
"integer",
|
||||
"null",
|
||||
"number",
|
||||
"object",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"stringArray": {
|
||||
"type": "array",
|
||||
"items": { "type": "string" },
|
||||
"uniqueItems": true,
|
||||
"default": []
|
||||
}
|
||||
},
|
||||
"type": ["object", "boolean"],
|
||||
"properties": {
|
||||
"$id": {
|
||||
"type": "string",
|
||||
"format": "uri-reference"
|
||||
},
|
||||
"$schema": {
|
||||
"type": "string",
|
||||
"format": "uri"
|
||||
},
|
||||
"$ref": {
|
||||
"type": "string",
|
||||
"format": "uri-reference"
|
||||
},
|
||||
"title": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": {
|
||||
"type": "string"
|
||||
},
|
||||
"default": {},
|
||||
"examples": {
|
||||
"type": "array",
|
||||
"items": {}
|
||||
},
|
||||
"multipleOf": {
|
||||
"type": "number",
|
||||
"exclusiveMinimum": 0
|
||||
},
|
||||
"maximum": {
|
||||
"type": "number"
|
||||
},
|
||||
"exclusiveMaximum": {
|
||||
"type": "number"
|
||||
},
|
||||
"minimum": {
|
||||
"type": "number"
|
||||
},
|
||||
"exclusiveMinimum": {
|
||||
"type": "number"
|
||||
},
|
||||
"maxLength": { "$ref": "#/definitions/nonNegativeInteger" },
|
||||
"minLength": { "$ref": "#/definitions/nonNegativeIntegerDefault0" },
|
||||
"pattern": {
|
||||
"type": "string",
|
||||
"format": "regex"
|
||||
},
|
||||
"additionalItems": { "$ref": "#" },
|
||||
"items": {
|
||||
"anyOf": [
|
||||
{ "$ref": "#" },
|
||||
{ "$ref": "#/definitions/schemaArray" }
|
||||
],
|
||||
"default": {}
|
||||
},
|
||||
"maxItems": { "$ref": "#/definitions/nonNegativeInteger" },
|
||||
"minItems": { "$ref": "#/definitions/nonNegativeIntegerDefault0" },
|
||||
"uniqueItems": {
|
||||
"type": "boolean",
|
||||
"default": false
|
||||
},
|
||||
"contains": { "$ref": "#" },
|
||||
"maxProperties": { "$ref": "#/definitions/nonNegativeInteger" },
|
||||
"minProperties": { "$ref": "#/definitions/nonNegativeIntegerDefault0" },
|
||||
"required": { "$ref": "#/definitions/stringArray" },
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"definitions": {
|
||||
"type": "object",
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"default": {}
|
||||
},
|
||||
"properties": {
|
||||
"type": "object",
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"default": {}
|
||||
},
|
||||
"patternProperties": {
|
||||
"type": "object",
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"propertyNames": { "format": "regex" },
|
||||
"default": {}
|
||||
},
|
||||
"dependencies": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"anyOf": [
|
||||
{ "$ref": "#" },
|
||||
{ "$ref": "#/definitions/stringArray" }
|
||||
]
|
||||
}
|
||||
},
|
||||
"propertyNames": { "$ref": "#" },
|
||||
"const": {},
|
||||
"enum": {
|
||||
"type": "array"
|
||||
},
|
||||
"type": {
|
||||
"anyOf": [
|
||||
{ "$ref": "#/definitions/simpleTypes" },
|
||||
{
|
||||
"type": "array",
|
||||
"items": { "$ref": "#/definitions/simpleTypes" },
|
||||
"minItems": 1,
|
||||
"uniqueItems": true
|
||||
}
|
||||
]
|
||||
},
|
||||
"format": { "type": "string" },
|
||||
"allOf": { "$ref": "#/definitions/schemaArray" },
|
||||
"anyOf": { "$ref": "#/definitions/schemaArray" },
|
||||
"oneOf": { "$ref": "#/definitions/schemaArray" },
|
||||
"not": { "$ref": "#" }
|
||||
},
|
||||
"default": {}
|
||||
}
|
||||
|
|
@ -0,0 +1,166 @@
|
|||
{
|
||||
"$schema": "http://json-schema.org/draft-07/schema#",
|
||||
"$id": "http://json-schema.org/draft-07/schema#",
|
||||
"title": "Core schema meta-schema",
|
||||
"definitions": {
|
||||
"schemaArray": {
|
||||
"type": "array",
|
||||
"minItems": 1,
|
||||
"items": { "$ref": "#" }
|
||||
},
|
||||
"nonNegativeInteger": {
|
||||
"type": "integer",
|
||||
"minimum": 0
|
||||
},
|
||||
"nonNegativeIntegerDefault0": {
|
||||
"allOf": [
|
||||
{ "$ref": "#/definitions/nonNegativeInteger" },
|
||||
{ "default": 0 }
|
||||
]
|
||||
},
|
||||
"simpleTypes": {
|
||||
"enum": [
|
||||
"array",
|
||||
"boolean",
|
||||
"integer",
|
||||
"null",
|
||||
"number",
|
||||
"object",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"stringArray": {
|
||||
"type": "array",
|
||||
"items": { "type": "string" },
|
||||
"uniqueItems": true,
|
||||
"default": []
|
||||
}
|
||||
},
|
||||
"type": ["object", "boolean"],
|
||||
"properties": {
|
||||
"$id": {
|
||||
"type": "string",
|
||||
"format": "uri-reference"
|
||||
},
|
||||
"$schema": {
|
||||
"type": "string",
|
||||
"format": "uri"
|
||||
},
|
||||
"$ref": {
|
||||
"type": "string",
|
||||
"format": "uri-reference"
|
||||
},
|
||||
"$comment": {
|
||||
"type": "string"
|
||||
},
|
||||
"title": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": {
|
||||
"type": "string"
|
||||
},
|
||||
"default": true,
|
||||
"readOnly": {
|
||||
"type": "boolean",
|
||||
"default": false
|
||||
},
|
||||
"examples": {
|
||||
"type": "array",
|
||||
"items": true
|
||||
},
|
||||
"multipleOf": {
|
||||
"type": "number",
|
||||
"exclusiveMinimum": 0
|
||||
},
|
||||
"maximum": {
|
||||
"type": "number"
|
||||
},
|
||||
"exclusiveMaximum": {
|
||||
"type": "number"
|
||||
},
|
||||
"minimum": {
|
||||
"type": "number"
|
||||
},
|
||||
"exclusiveMinimum": {
|
||||
"type": "number"
|
||||
},
|
||||
"maxLength": { "$ref": "#/definitions/nonNegativeInteger" },
|
||||
"minLength": { "$ref": "#/definitions/nonNegativeIntegerDefault0" },
|
||||
"pattern": {
|
||||
"type": "string",
|
||||
"format": "regex"
|
||||
},
|
||||
"additionalItems": { "$ref": "#" },
|
||||
"items": {
|
||||
"anyOf": [
|
||||
{ "$ref": "#" },
|
||||
{ "$ref": "#/definitions/schemaArray" }
|
||||
],
|
||||
"default": true
|
||||
},
|
||||
"maxItems": { "$ref": "#/definitions/nonNegativeInteger" },
|
||||
"minItems": { "$ref": "#/definitions/nonNegativeIntegerDefault0" },
|
||||
"uniqueItems": {
|
||||
"type": "boolean",
|
||||
"default": false
|
||||
},
|
||||
"contains": { "$ref": "#" },
|
||||
"maxProperties": { "$ref": "#/definitions/nonNegativeInteger" },
|
||||
"minProperties": { "$ref": "#/definitions/nonNegativeIntegerDefault0" },
|
||||
"required": { "$ref": "#/definitions/stringArray" },
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"definitions": {
|
||||
"type": "object",
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"default": {}
|
||||
},
|
||||
"properties": {
|
||||
"type": "object",
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"default": {}
|
||||
},
|
||||
"patternProperties": {
|
||||
"type": "object",
|
||||
"additionalProperties": { "$ref": "#" },
|
||||
"propertyNames": { "format": "regex" },
|
||||
"default": {}
|
||||
},
|
||||
"dependencies": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"anyOf": [
|
||||
{ "$ref": "#" },
|
||||
{ "$ref": "#/definitions/stringArray" }
|
||||
]
|
||||
}
|
||||
},
|
||||
"propertyNames": { "$ref": "#" },
|
||||
"const": true,
|
||||
"enum": {
|
||||
"type": "array",
|
||||
"items": true
|
||||
},
|
||||
"type": {
|
||||
"anyOf": [
|
||||
{ "$ref": "#/definitions/simpleTypes" },
|
||||
{
|
||||
"type": "array",
|
||||
"items": { "$ref": "#/definitions/simpleTypes" },
|
||||
"minItems": 1,
|
||||
"uniqueItems": true
|
||||
}
|
||||
]
|
||||
},
|
||||
"format": { "type": "string" },
|
||||
"contentMediaType": { "type": "string" },
|
||||
"contentEncoding": { "type": "string" },
|
||||
"if": {"$ref": "#"},
|
||||
"then": {"$ref": "#"},
|
||||
"else": {"$ref": "#"},
|
||||
"allOf": { "$ref": "#/definitions/schemaArray" },
|
||||
"anyOf": { "$ref": "#/definitions/schemaArray" },
|
||||
"oneOf": { "$ref": "#/definitions/schemaArray" },
|
||||
"not": { "$ref": "#" }
|
||||
},
|
||||
"default": true
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,18 @@
|
|||
Copyright © 2017 Erez Shinan
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy of
|
||||
this software and associated documentation files (the "Software"), to deal in
|
||||
the Software without restriction, including without limitation the rights to
|
||||
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
|
||||
the Software, and to permit persons to whom the Software is furnished to do so,
|
||||
subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
|
||||
FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
|
||||
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
|
||||
IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
|
|
@ -0,0 +1,38 @@
|
|||
from .exceptions import (
|
||||
GrammarError,
|
||||
LarkError,
|
||||
LexError,
|
||||
ParseError,
|
||||
UnexpectedCharacters,
|
||||
UnexpectedEOF,
|
||||
UnexpectedInput,
|
||||
UnexpectedToken,
|
||||
)
|
||||
from .lark import Lark
|
||||
from .lexer import Token
|
||||
from .tree import ParseTree, Tree
|
||||
from .utils import logger
|
||||
from .visitors import Discard, Transformer, Transformer_NonRecursive, Visitor, v_args
|
||||
|
||||
__version__: str = "1.1.4"
|
||||
|
||||
__all__ = (
|
||||
"GrammarError",
|
||||
"LarkError",
|
||||
"LexError",
|
||||
"ParseError",
|
||||
"UnexpectedCharacters",
|
||||
"UnexpectedEOF",
|
||||
"UnexpectedInput",
|
||||
"UnexpectedToken",
|
||||
"Lark",
|
||||
"Token",
|
||||
"ParseTree",
|
||||
"Tree",
|
||||
"logger",
|
||||
"Discard",
|
||||
"Transformer",
|
||||
"Transformer_NonRecursive",
|
||||
"Visitor",
|
||||
"v_args",
|
||||
)
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
# For usage of lark with PyInstaller. See https://pyinstaller-sample-hook.readthedocs.io/en/latest/index.html
|
||||
|
||||
import os
|
||||
|
||||
def get_hook_dirs():
|
||||
return [os.path.dirname(__file__)]
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
#-----------------------------------------------------------------------------
|
||||
# Copyright (c) 2017-2020, PyInstaller Development Team.
|
||||
#
|
||||
# Distributed under the terms of the GNU General Public License (version 2
|
||||
# or later) with exception for distributing the bootloader.
|
||||
#
|
||||
# The full license is in the file COPYING.txt, distributed with this software.
|
||||
#
|
||||
# SPDX-License-Identifier: (GPL-2.0-or-later WITH Bootloader-exception)
|
||||
#-----------------------------------------------------------------------------
|
||||
|
||||
from PyInstaller.utils.hooks import collect_data_files
|
||||
|
||||
datas = collect_data_files('lark')
|
||||
|
|
@ -0,0 +1,59 @@
|
|||
"""
|
||||
Module of utilities for transforming a lark.Tree into a custom Abstract Syntax Tree
|
||||
"""
|
||||
|
||||
import inspect, re
|
||||
import types
|
||||
from typing import Optional, Callable
|
||||
|
||||
from lark import Transformer, v_args
|
||||
|
||||
class Ast:
|
||||
"""Abstract class
|
||||
|
||||
Subclasses will be collected by `create_transformer()`
|
||||
"""
|
||||
pass
|
||||
|
||||
class AsList:
|
||||
"""Abstract class
|
||||
|
||||
Subclasses will be instantiated with the parse results as a single list, instead of as arguments.
|
||||
"""
|
||||
|
||||
class WithMeta:
|
||||
"""Abstract class
|
||||
|
||||
Subclasses will be instantiated with the Meta instance of the tree. (see ``v_args`` for more detail)
|
||||
"""
|
||||
pass
|
||||
|
||||
def camel_to_snake(name):
|
||||
return re.sub(r'(?<!^)(?=[A-Z])', '_', name).lower()
|
||||
|
||||
def create_transformer(ast_module: types.ModuleType,
|
||||
transformer: Optional[Transformer]=None,
|
||||
decorator_factory: Callable=v_args) -> Transformer:
|
||||
"""Collects `Ast` subclasses from the given module, and creates a Lark transformer that builds the AST.
|
||||
|
||||
For each class, we create a corresponding rule in the transformer, with a matching name.
|
||||
CamelCase names will be converted into snake_case. Example: "CodeBlock" -> "code_block".
|
||||
|
||||
Classes starting with an underscore (`_`) will be skipped.
|
||||
|
||||
Parameters:
|
||||
ast_module: A Python module containing all the subclasses of ``ast_utils.Ast``
|
||||
transformer (Optional[Transformer]): An initial transformer. Its attributes may be overwritten.
|
||||
decorator_factory (Callable): An optional callable accepting two booleans, inline, and meta,
|
||||
and returning a decorator for the methods of ``transformer``. (default: ``v_args``).
|
||||
"""
|
||||
t = transformer or Transformer()
|
||||
|
||||
for name, obj in inspect.getmembers(ast_module):
|
||||
if not name.startswith('_') and inspect.isclass(obj):
|
||||
if issubclass(obj, Ast):
|
||||
wrapper = decorator_factory(inline=not issubclass(obj, AsList), meta=issubclass(obj, WithMeta))
|
||||
obj = wrapper(obj).__get__(t)
|
||||
setattr(t, camel_to_snake(name), obj)
|
||||
|
||||
return t
|
||||
|
|
@ -0,0 +1,82 @@
|
|||
from copy import deepcopy
|
||||
import sys
|
||||
from types import ModuleType
|
||||
from typing import Callable, Collection, Dict, Optional, TYPE_CHECKING
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .lark import PostLex
|
||||
from .lexer import Lexer
|
||||
from typing import Union, Type
|
||||
if sys.version_info >= (3, 8):
|
||||
from typing import Literal
|
||||
else:
|
||||
from typing_extensions import Literal
|
||||
if sys.version_info >= (3, 10):
|
||||
from typing import TypeAlias
|
||||
else:
|
||||
from typing_extensions import TypeAlias
|
||||
|
||||
from .utils import Serialize
|
||||
from .lexer import TerminalDef, Token
|
||||
|
||||
###{standalone
|
||||
|
||||
_ParserArgType: 'TypeAlias' = 'Literal["earley", "lalr", "cyk", "auto"]'
|
||||
_LexerArgType: 'TypeAlias' = 'Union[Literal["auto", "basic", "contextual", "dynamic", "dynamic_complete"], Type[Lexer]]'
|
||||
_Callback = Callable[[Token], Token]
|
||||
|
||||
class LexerConf(Serialize):
|
||||
__serialize_fields__ = 'terminals', 'ignore', 'g_regex_flags', 'use_bytes', 'lexer_type'
|
||||
__serialize_namespace__ = TerminalDef,
|
||||
|
||||
terminals: Collection[TerminalDef]
|
||||
re_module: ModuleType
|
||||
ignore: Collection[str]
|
||||
postlex: 'Optional[PostLex]'
|
||||
callbacks: Dict[str, _Callback]
|
||||
g_regex_flags: int
|
||||
skip_validation: bool
|
||||
use_bytes: bool
|
||||
lexer_type: Optional[_LexerArgType]
|
||||
|
||||
def __init__(self, terminals: Collection[TerminalDef], re_module: ModuleType, ignore: Collection[str]=(), postlex: 'Optional[PostLex]'=None, callbacks: Optional[Dict[str, _Callback]]=None, g_regex_flags: int=0, skip_validation: bool=False, use_bytes: bool=False):
|
||||
self.terminals = terminals
|
||||
self.terminals_by_name = {t.name: t for t in self.terminals}
|
||||
assert len(self.terminals) == len(self.terminals_by_name)
|
||||
self.ignore = ignore
|
||||
self.postlex = postlex
|
||||
self.callbacks = callbacks or {}
|
||||
self.g_regex_flags = g_regex_flags
|
||||
self.re_module = re_module
|
||||
self.skip_validation = skip_validation
|
||||
self.use_bytes = use_bytes
|
||||
self.lexer_type = None
|
||||
|
||||
def _deserialize(self):
|
||||
self.terminals_by_name = {t.name: t for t in self.terminals}
|
||||
|
||||
def __deepcopy__(self, memo=None):
|
||||
return type(self)(
|
||||
deepcopy(self.terminals, memo),
|
||||
self.re_module,
|
||||
deepcopy(self.ignore, memo),
|
||||
deepcopy(self.postlex, memo),
|
||||
deepcopy(self.callbacks, memo),
|
||||
deepcopy(self.g_regex_flags, memo),
|
||||
deepcopy(self.skip_validation, memo),
|
||||
deepcopy(self.use_bytes, memo),
|
||||
)
|
||||
|
||||
|
||||
class ParserConf(Serialize):
|
||||
__serialize_fields__ = 'rules', 'start', 'parser_type'
|
||||
|
||||
def __init__(self, rules, callbacks, start):
|
||||
assert isinstance(start, list)
|
||||
self.rules = rules
|
||||
self.callbacks = callbacks
|
||||
self.start = start
|
||||
|
||||
self.parser_type = None
|
||||
|
||||
###}
|
||||
|
|
@ -0,0 +1,292 @@
|
|||
from .utils import logger, NO_VALUE
|
||||
from typing import Mapping, Iterable, Callable, Union, TypeVar, Tuple, Any, List, Set, Optional, Collection, TYPE_CHECKING
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .lexer import Token
|
||||
from .parsers.lalr_interactive_parser import InteractiveParser
|
||||
from .tree import Tree
|
||||
|
||||
###{standalone
|
||||
|
||||
class LarkError(Exception):
|
||||
pass
|
||||
|
||||
|
||||
class ConfigurationError(LarkError, ValueError):
|
||||
pass
|
||||
|
||||
|
||||
def assert_config(value, options: Collection, msg='Got %r, expected one of %s'):
|
||||
if value not in options:
|
||||
raise ConfigurationError(msg % (value, options))
|
||||
|
||||
|
||||
class GrammarError(LarkError):
|
||||
pass
|
||||
|
||||
|
||||
class ParseError(LarkError):
|
||||
pass
|
||||
|
||||
|
||||
class LexError(LarkError):
|
||||
pass
|
||||
|
||||
T = TypeVar('T')
|
||||
|
||||
class UnexpectedInput(LarkError):
|
||||
"""UnexpectedInput Error.
|
||||
|
||||
Used as a base class for the following exceptions:
|
||||
|
||||
- ``UnexpectedCharacters``: The lexer encountered an unexpected string
|
||||
- ``UnexpectedToken``: The parser received an unexpected token
|
||||
- ``UnexpectedEOF``: The parser expected a token, but the input ended
|
||||
|
||||
After catching one of these exceptions, you may call the following helper methods to create a nicer error message.
|
||||
"""
|
||||
line: int
|
||||
column: int
|
||||
pos_in_stream = None
|
||||
state: Any
|
||||
_terminals_by_name = None
|
||||
|
||||
def get_context(self, text: str, span: int=40) -> str:
|
||||
"""Returns a pretty string pinpointing the error in the text,
|
||||
with span amount of context characters around it.
|
||||
|
||||
Note:
|
||||
The parser doesn't hold a copy of the text it has to parse,
|
||||
so you have to provide it again
|
||||
"""
|
||||
assert self.pos_in_stream is not None, self
|
||||
pos = self.pos_in_stream
|
||||
start = max(pos - span, 0)
|
||||
end = pos + span
|
||||
if not isinstance(text, bytes):
|
||||
before = text[start:pos].rsplit('\n', 1)[-1]
|
||||
after = text[pos:end].split('\n', 1)[0]
|
||||
return before + after + '\n' + ' ' * len(before.expandtabs()) + '^\n'
|
||||
else:
|
||||
before = text[start:pos].rsplit(b'\n', 1)[-1]
|
||||
after = text[pos:end].split(b'\n', 1)[0]
|
||||
return (before + after + b'\n' + b' ' * len(before.expandtabs()) + b'^\n').decode("ascii", "backslashreplace")
|
||||
|
||||
def match_examples(self, parse_fn: 'Callable[[str], Tree]',
|
||||
examples: Union[Mapping[T, Iterable[str]], Iterable[Tuple[T, Iterable[str]]]],
|
||||
token_type_match_fallback: bool=False,
|
||||
use_accepts: bool=True
|
||||
) -> Optional[T]:
|
||||
"""Allows you to detect what's wrong in the input text by matching
|
||||
against example errors.
|
||||
|
||||
Given a parser instance and a dictionary mapping some label with
|
||||
some malformed syntax examples, it'll return the label for the
|
||||
example that bests matches the current error. The function will
|
||||
iterate the dictionary until it finds a matching error, and
|
||||
return the corresponding value.
|
||||
|
||||
For an example usage, see `examples/error_reporting_lalr.py`
|
||||
|
||||
Parameters:
|
||||
parse_fn: parse function (usually ``lark_instance.parse``)
|
||||
examples: dictionary of ``{'example_string': value}``.
|
||||
use_accepts: Recommended to keep this as ``use_accepts=True``.
|
||||
"""
|
||||
assert self.state is not None, "Not supported for this exception"
|
||||
|
||||
if isinstance(examples, Mapping):
|
||||
examples = examples.items()
|
||||
|
||||
candidate = (None, False)
|
||||
for i, (label, example) in enumerate(examples):
|
||||
assert not isinstance(example, str), "Expecting a list"
|
||||
|
||||
for j, malformed in enumerate(example):
|
||||
try:
|
||||
parse_fn(malformed)
|
||||
except UnexpectedInput as ut:
|
||||
if ut.state == self.state:
|
||||
if (
|
||||
use_accepts
|
||||
and isinstance(self, UnexpectedToken)
|
||||
and isinstance(ut, UnexpectedToken)
|
||||
and ut.accepts != self.accepts
|
||||
):
|
||||
logger.debug("Different accepts with same state[%d]: %s != %s at example [%s][%s]" %
|
||||
(self.state, self.accepts, ut.accepts, i, j))
|
||||
continue
|
||||
if (
|
||||
isinstance(self, (UnexpectedToken, UnexpectedEOF))
|
||||
and isinstance(ut, (UnexpectedToken, UnexpectedEOF))
|
||||
):
|
||||
if ut.token == self.token: # Try exact match first
|
||||
logger.debug("Exact Match at example [%s][%s]" % (i, j))
|
||||
return label
|
||||
|
||||
if token_type_match_fallback:
|
||||
# Fallback to token types match
|
||||
if (ut.token.type == self.token.type) and not candidate[-1]:
|
||||
logger.debug("Token Type Fallback at example [%s][%s]" % (i, j))
|
||||
candidate = label, True
|
||||
|
||||
if candidate[0] is None:
|
||||
logger.debug("Same State match at example [%s][%s]" % (i, j))
|
||||
candidate = label, False
|
||||
|
||||
return candidate[0]
|
||||
|
||||
def _format_expected(self, expected):
|
||||
if self._terminals_by_name:
|
||||
d = self._terminals_by_name
|
||||
expected = [d[t_name].user_repr() if t_name in d else t_name for t_name in expected]
|
||||
return "Expected one of: \n\t* %s\n" % '\n\t* '.join(expected)
|
||||
|
||||
|
||||
class UnexpectedEOF(ParseError, UnexpectedInput):
|
||||
"""An exception that is raised by the parser, when the input ends while it still expects a token.
|
||||
"""
|
||||
expected: 'List[Token]'
|
||||
|
||||
def __init__(self, expected, state=None, terminals_by_name=None):
|
||||
super(UnexpectedEOF, self).__init__()
|
||||
|
||||
self.expected = expected
|
||||
self.state = state
|
||||
from .lexer import Token
|
||||
self.token = Token("<EOF>", "") # , line=-1, column=-1, pos_in_stream=-1)
|
||||
self.pos_in_stream = -1
|
||||
self.line = -1
|
||||
self.column = -1
|
||||
self._terminals_by_name = terminals_by_name
|
||||
|
||||
|
||||
def __str__(self):
|
||||
message = "Unexpected end-of-input. "
|
||||
message += self._format_expected(self.expected)
|
||||
return message
|
||||
|
||||
|
||||
class UnexpectedCharacters(LexError, UnexpectedInput):
|
||||
"""An exception that is raised by the lexer, when it cannot match the next
|
||||
string of characters to any of its terminals.
|
||||
"""
|
||||
|
||||
allowed: Set[str]
|
||||
considered_tokens: Set[Any]
|
||||
|
||||
def __init__(self, seq, lex_pos, line, column, allowed=None, considered_tokens=None, state=None, token_history=None,
|
||||
terminals_by_name=None, considered_rules=None):
|
||||
super(UnexpectedCharacters, self).__init__()
|
||||
|
||||
# TODO considered_tokens and allowed can be figured out using state
|
||||
self.line = line
|
||||
self.column = column
|
||||
self.pos_in_stream = lex_pos
|
||||
self.state = state
|
||||
self._terminals_by_name = terminals_by_name
|
||||
|
||||
self.allowed = allowed
|
||||
self.considered_tokens = considered_tokens
|
||||
self.considered_rules = considered_rules
|
||||
self.token_history = token_history
|
||||
|
||||
if isinstance(seq, bytes):
|
||||
self.char = seq[lex_pos:lex_pos + 1].decode("ascii", "backslashreplace")
|
||||
else:
|
||||
self.char = seq[lex_pos]
|
||||
self._context = self.get_context(seq)
|
||||
|
||||
|
||||
def __str__(self):
|
||||
message = "No terminal matches '%s' in the current parser context, at line %d col %d" % (self.char, self.line, self.column)
|
||||
message += '\n\n' + self._context
|
||||
if self.allowed:
|
||||
message += self._format_expected(self.allowed)
|
||||
if self.token_history:
|
||||
message += '\nPrevious tokens: %s\n' % ', '.join(repr(t) for t in self.token_history)
|
||||
return message
|
||||
|
||||
|
||||
class UnexpectedToken(ParseError, UnexpectedInput):
|
||||
"""An exception that is raised by the parser, when the token it received
|
||||
doesn't match any valid step forward.
|
||||
|
||||
Parameters:
|
||||
token: The mismatched token
|
||||
expected: The set of expected tokens
|
||||
considered_rules: Which rules were considered, to deduce the expected tokens
|
||||
state: A value representing the parser state. Do not rely on its value or type.
|
||||
interactive_parser: An instance of ``InteractiveParser``, that is initialized to the point of failture,
|
||||
and can be used for debugging and error handling.
|
||||
|
||||
Note: These parameters are available as attributes of the instance.
|
||||
"""
|
||||
|
||||
expected: Set[str]
|
||||
considered_rules: Set[str]
|
||||
interactive_parser: 'InteractiveParser'
|
||||
|
||||
def __init__(self, token, expected, considered_rules=None, state=None, interactive_parser=None, terminals_by_name=None, token_history=None):
|
||||
super(UnexpectedToken, self).__init__()
|
||||
|
||||
# TODO considered_rules and expected can be figured out using state
|
||||
self.line = getattr(token, 'line', '?')
|
||||
self.column = getattr(token, 'column', '?')
|
||||
self.pos_in_stream = getattr(token, 'start_pos', None)
|
||||
self.state = state
|
||||
|
||||
self.token = token
|
||||
self.expected = expected # XXX deprecate? `accepts` is better
|
||||
self._accepts = NO_VALUE
|
||||
self.considered_rules = considered_rules
|
||||
self.interactive_parser = interactive_parser
|
||||
self._terminals_by_name = terminals_by_name
|
||||
self.token_history = token_history
|
||||
|
||||
|
||||
@property
|
||||
def accepts(self) -> Set[str]:
|
||||
if self._accepts is NO_VALUE:
|
||||
self._accepts = self.interactive_parser and self.interactive_parser.accepts()
|
||||
return self._accepts
|
||||
|
||||
def __str__(self):
|
||||
message = ("Unexpected token %r at line %s, column %s.\n%s"
|
||||
% (self.token, self.line, self.column, self._format_expected(self.accepts or self.expected)))
|
||||
if self.token_history:
|
||||
message += "Previous tokens: %r\n" % self.token_history
|
||||
|
||||
return message
|
||||
|
||||
|
||||
|
||||
class VisitError(LarkError):
|
||||
"""VisitError is raised when visitors are interrupted by an exception
|
||||
|
||||
It provides the following attributes for inspection:
|
||||
|
||||
Parameters:
|
||||
rule: the name of the visit rule that failed
|
||||
obj: the tree-node or token that was being processed
|
||||
orig_exc: the exception that cause it to fail
|
||||
|
||||
Note: These parameters are available as attributes
|
||||
"""
|
||||
|
||||
obj: 'Union[Tree, Token]'
|
||||
orig_exc: Exception
|
||||
|
||||
def __init__(self, rule, obj, orig_exc):
|
||||
message = 'Error trying to process rule "%s":\n\n%s' % (rule, orig_exc)
|
||||
super(VisitError, self).__init__(message)
|
||||
|
||||
self.rule = rule
|
||||
self.obj = obj
|
||||
self.orig_exc = orig_exc
|
||||
|
||||
|
||||
class MissingVariableError(LarkError):
|
||||
pass
|
||||
|
||||
###}
|
||||
|
|
@ -0,0 +1,122 @@
|
|||
from typing import Optional, Tuple, ClassVar
|
||||
|
||||
from .utils import Serialize
|
||||
|
||||
###{standalone
|
||||
TOKEN_DEFAULT_PRIORITY = 0
|
||||
|
||||
|
||||
class Symbol(Serialize):
|
||||
__slots__ = ('name',)
|
||||
|
||||
name: str
|
||||
is_term: ClassVar[bool] = NotImplemented
|
||||
|
||||
def __init__(self, name: str) -> None:
|
||||
self.name = name
|
||||
|
||||
def __eq__(self, other):
|
||||
assert isinstance(other, Symbol), other
|
||||
return self.is_term == other.is_term and self.name == other.name
|
||||
|
||||
def __ne__(self, other):
|
||||
return not (self == other)
|
||||
|
||||
def __hash__(self):
|
||||
return hash(self.name)
|
||||
|
||||
def __repr__(self):
|
||||
return '%s(%r)' % (type(self).__name__, self.name)
|
||||
|
||||
fullrepr = property(__repr__)
|
||||
|
||||
def renamed(self, f):
|
||||
return type(self)(f(self.name))
|
||||
|
||||
|
||||
class Terminal(Symbol):
|
||||
__serialize_fields__ = 'name', 'filter_out'
|
||||
|
||||
is_term: ClassVar[bool] = True
|
||||
|
||||
def __init__(self, name, filter_out=False):
|
||||
self.name = name
|
||||
self.filter_out = filter_out
|
||||
|
||||
@property
|
||||
def fullrepr(self):
|
||||
return '%s(%r, %r)' % (type(self).__name__, self.name, self.filter_out)
|
||||
|
||||
def renamed(self, f):
|
||||
return type(self)(f(self.name), self.filter_out)
|
||||
|
||||
|
||||
class NonTerminal(Symbol):
|
||||
__serialize_fields__ = 'name',
|
||||
|
||||
is_term: ClassVar[bool] = False
|
||||
|
||||
|
||||
class RuleOptions(Serialize):
|
||||
__serialize_fields__ = 'keep_all_tokens', 'expand1', 'priority', 'template_source', 'empty_indices'
|
||||
|
||||
keep_all_tokens: bool
|
||||
expand1: bool
|
||||
priority: Optional[int]
|
||||
template_source: Optional[str]
|
||||
empty_indices: Tuple[bool, ...]
|
||||
|
||||
def __init__(self, keep_all_tokens: bool=False, expand1: bool=False, priority: Optional[int]=None, template_source: Optional[str]=None, empty_indices: Tuple[bool, ...]=()) -> None:
|
||||
self.keep_all_tokens = keep_all_tokens
|
||||
self.expand1 = expand1
|
||||
self.priority = priority
|
||||
self.template_source = template_source
|
||||
self.empty_indices = empty_indices
|
||||
|
||||
def __repr__(self):
|
||||
return 'RuleOptions(%r, %r, %r, %r)' % (
|
||||
self.keep_all_tokens,
|
||||
self.expand1,
|
||||
self.priority,
|
||||
self.template_source
|
||||
)
|
||||
|
||||
|
||||
class Rule(Serialize):
|
||||
"""
|
||||
origin : a symbol
|
||||
expansion : a list of symbols
|
||||
order : index of this expansion amongst all rules of the same name
|
||||
"""
|
||||
__slots__ = ('origin', 'expansion', 'alias', 'options', 'order', '_hash')
|
||||
|
||||
__serialize_fields__ = 'origin', 'expansion', 'order', 'alias', 'options'
|
||||
__serialize_namespace__ = Terminal, NonTerminal, RuleOptions
|
||||
|
||||
def __init__(self, origin, expansion, order=0, alias=None, options=None):
|
||||
self.origin = origin
|
||||
self.expansion = expansion
|
||||
self.alias = alias
|
||||
self.order = order
|
||||
self.options = options or RuleOptions()
|
||||
self._hash = hash((self.origin, tuple(self.expansion)))
|
||||
|
||||
def _deserialize(self):
|
||||
self._hash = hash((self.origin, tuple(self.expansion)))
|
||||
|
||||
def __str__(self):
|
||||
return '<%s : %s>' % (self.origin.name, ' '.join(x.name for x in self.expansion))
|
||||
|
||||
def __repr__(self):
|
||||
return 'Rule(%r, %r, %r, %r)' % (self.origin, self.expansion, self.alias, self.options)
|
||||
|
||||
def __hash__(self):
|
||||
return self._hash
|
||||
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, Rule):
|
||||
return False
|
||||
return self.origin == other.origin and self.expansion == other.expansion
|
||||
|
||||
|
||||
###}
|
||||
|
|
@ -0,0 +1,59 @@
|
|||
// Basic terminals for common use
|
||||
|
||||
|
||||
//
|
||||
// Numbers
|
||||
//
|
||||
|
||||
DIGIT: "0".."9"
|
||||
HEXDIGIT: "a".."f"|"A".."F"|DIGIT
|
||||
|
||||
INT: DIGIT+
|
||||
SIGNED_INT: ["+"|"-"] INT
|
||||
DECIMAL: INT "." INT? | "." INT
|
||||
|
||||
// float = /-?\d+(\.\d+)?([eE][+-]?\d+)?/
|
||||
_EXP: ("e"|"E") SIGNED_INT
|
||||
FLOAT: INT _EXP | DECIMAL _EXP?
|
||||
SIGNED_FLOAT: ["+"|"-"] FLOAT
|
||||
|
||||
NUMBER: FLOAT | INT
|
||||
SIGNED_NUMBER: ["+"|"-"] NUMBER
|
||||
|
||||
//
|
||||
// Strings
|
||||
//
|
||||
_STRING_INNER: /.*?/
|
||||
_STRING_ESC_INNER: _STRING_INNER /(?<!\\)(\\\\)*?/
|
||||
|
||||
ESCAPED_STRING : "\"" _STRING_ESC_INNER "\""
|
||||
|
||||
|
||||
//
|
||||
// Names (Variables)
|
||||
//
|
||||
LCASE_LETTER: "a".."z"
|
||||
UCASE_LETTER: "A".."Z"
|
||||
|
||||
LETTER: UCASE_LETTER | LCASE_LETTER
|
||||
WORD: LETTER+
|
||||
|
||||
CNAME: ("_"|LETTER) ("_"|LETTER|DIGIT)*
|
||||
|
||||
|
||||
//
|
||||
// Whitespace
|
||||
//
|
||||
WS_INLINE: (" "|/\t/)+
|
||||
WS: /[ \t\f\r\n]/+
|
||||
|
||||
CR : /\r/
|
||||
LF : /\n/
|
||||
NEWLINE: (CR? LF)+
|
||||
|
||||
|
||||
// Comments
|
||||
SH_COMMENT: /#[^\n]*/
|
||||
CPP_COMMENT: /\/\/[^\n]*/
|
||||
C_COMMENT: "/*" /(.|\n)*?/ "*/"
|
||||
SQL_COMMENT: /--[^\n]*/
|
||||
|
|
@ -0,0 +1,59 @@
|
|||
start: (_item? _NL)* _item?
|
||||
|
||||
_item: rule
|
||||
| token
|
||||
| statement
|
||||
|
||||
rule: RULE rule_params priority? ":" expansions
|
||||
token: TOKEN token_params priority? ":" expansions
|
||||
|
||||
rule_params: ["{" RULE ("," RULE)* "}"]
|
||||
token_params: ["{" TOKEN ("," TOKEN)* "}"]
|
||||
|
||||
priority: "." NUMBER
|
||||
|
||||
statement: "%ignore" expansions -> ignore
|
||||
| "%import" import_path ["->" name] -> import
|
||||
| "%import" import_path name_list -> multi_import
|
||||
| "%override" rule -> override_rule
|
||||
| "%declare" name+ -> declare
|
||||
|
||||
!import_path: "."? name ("." name)*
|
||||
name_list: "(" name ("," name)* ")"
|
||||
|
||||
?expansions: alias (_VBAR alias)*
|
||||
|
||||
?alias: expansion ["->" RULE]
|
||||
|
||||
?expansion: expr*
|
||||
|
||||
?expr: atom [OP | "~" NUMBER [".." NUMBER]]
|
||||
|
||||
?atom: "(" expansions ")"
|
||||
| "[" expansions "]" -> maybe
|
||||
| value
|
||||
|
||||
?value: STRING ".." STRING -> literal_range
|
||||
| name
|
||||
| (REGEXP | STRING) -> literal
|
||||
| name "{" value ("," value)* "}" -> template_usage
|
||||
|
||||
name: RULE
|
||||
| TOKEN
|
||||
|
||||
_VBAR: _NL? "|"
|
||||
OP: /[+*]|[?](?![a-z])/
|
||||
RULE: /!?[_?]?[a-z][_a-z0-9]*/
|
||||
TOKEN: /_?[A-Z][_A-Z0-9]*/
|
||||
STRING: _STRING "i"?
|
||||
REGEXP: /\/(?!\/)(\\\/|\\\\|[^\/])*?\/[imslux]*/
|
||||
_NL: /(\r?\n)+\s*/
|
||||
|
||||
%import common.ESCAPED_STRING -> _STRING
|
||||
%import common.SIGNED_INT -> NUMBER
|
||||
%import common.WS_INLINE
|
||||
|
||||
COMMENT: /\s*/ "//" /[^\n]/*
|
||||
|
||||
%ignore WS_INLINE
|
||||
%ignore COMMENT
|
||||
|
|
@ -0,0 +1,304 @@
|
|||
// Python 3 grammar for Lark
|
||||
|
||||
// This grammar should parse all python 3.x code successfully.
|
||||
|
||||
// Adapted from: https://docs.python.org/3/reference/grammar.html
|
||||
|
||||
// Start symbols for the grammar:
|
||||
// single_input is a single interactive statement;
|
||||
// file_input is a module or sequence of commands read from an input file;
|
||||
// eval_input is the input for the eval() functions.
|
||||
// NB: compound_stmt in single_input is followed by extra NEWLINE!
|
||||
//
|
||||
|
||||
single_input: _NEWLINE | simple_stmt | compound_stmt _NEWLINE
|
||||
file_input: (_NEWLINE | stmt)*
|
||||
eval_input: testlist _NEWLINE*
|
||||
|
||||
decorator: "@" dotted_name [ "(" [arguments] ")" ] _NEWLINE
|
||||
decorators: decorator+
|
||||
decorated: decorators (classdef | funcdef | async_funcdef)
|
||||
|
||||
async_funcdef: "async" funcdef
|
||||
funcdef: "def" name "(" [parameters] ")" ["->" test] ":" suite
|
||||
|
||||
parameters: paramvalue ("," paramvalue)* ["," SLASH ("," paramvalue)*] ["," [starparams | kwparams]]
|
||||
| starparams
|
||||
| kwparams
|
||||
|
||||
SLASH: "/" // Otherwise the it will completely disappear and it will be undisguisable in the result
|
||||
starparams: (starparam | starguard) poststarparams
|
||||
starparam: "*" typedparam
|
||||
starguard: "*"
|
||||
poststarparams: ("," paramvalue)* ["," kwparams]
|
||||
kwparams: "**" typedparam ","?
|
||||
|
||||
?paramvalue: typedparam ("=" test)?
|
||||
?typedparam: name (":" test)?
|
||||
|
||||
|
||||
lambdef: "lambda" [lambda_params] ":" test
|
||||
lambdef_nocond: "lambda" [lambda_params] ":" test_nocond
|
||||
lambda_params: lambda_paramvalue ("," lambda_paramvalue)* ["," [lambda_starparams | lambda_kwparams]]
|
||||
| lambda_starparams
|
||||
| lambda_kwparams
|
||||
?lambda_paramvalue: name ("=" test)?
|
||||
lambda_starparams: "*" [name] ("," lambda_paramvalue)* ["," [lambda_kwparams]]
|
||||
lambda_kwparams: "**" name ","?
|
||||
|
||||
|
||||
?stmt: simple_stmt | compound_stmt
|
||||
?simple_stmt: small_stmt (";" small_stmt)* [";"] _NEWLINE
|
||||
?small_stmt: (expr_stmt | assign_stmt | del_stmt | pass_stmt | flow_stmt | import_stmt | global_stmt | nonlocal_stmt | assert_stmt)
|
||||
expr_stmt: testlist_star_expr
|
||||
assign_stmt: annassign | augassign | assign
|
||||
|
||||
annassign: testlist_star_expr ":" test ["=" test]
|
||||
assign: testlist_star_expr ("=" (yield_expr|testlist_star_expr))+
|
||||
augassign: testlist_star_expr augassign_op (yield_expr|testlist)
|
||||
!augassign_op: "+=" | "-=" | "*=" | "@=" | "/=" | "%=" | "&=" | "|=" | "^=" | "<<=" | ">>=" | "**=" | "//="
|
||||
?testlist_star_expr: test_or_star_expr
|
||||
| test_or_star_expr ("," test_or_star_expr)+ ","? -> tuple
|
||||
| test_or_star_expr "," -> tuple
|
||||
|
||||
// For normal and annotated assignments, additional restrictions enforced by the interpreter
|
||||
del_stmt: "del" exprlist
|
||||
pass_stmt: "pass"
|
||||
?flow_stmt: break_stmt | continue_stmt | return_stmt | raise_stmt | yield_stmt
|
||||
break_stmt: "break"
|
||||
continue_stmt: "continue"
|
||||
return_stmt: "return" [testlist]
|
||||
yield_stmt: yield_expr
|
||||
raise_stmt: "raise" [test ["from" test]]
|
||||
import_stmt: import_name | import_from
|
||||
import_name: "import" dotted_as_names
|
||||
// note below: the ("." | "...") is necessary because "..." is tokenized as ELLIPSIS
|
||||
import_from: "from" (dots? dotted_name | dots) "import" ("*" | "(" import_as_names ")" | import_as_names)
|
||||
!dots: "."+
|
||||
import_as_name: name ["as" name]
|
||||
dotted_as_name: dotted_name ["as" name]
|
||||
import_as_names: import_as_name ("," import_as_name)* [","]
|
||||
dotted_as_names: dotted_as_name ("," dotted_as_name)*
|
||||
dotted_name: name ("." name)*
|
||||
global_stmt: "global" name ("," name)*
|
||||
nonlocal_stmt: "nonlocal" name ("," name)*
|
||||
assert_stmt: "assert" test ["," test]
|
||||
|
||||
?compound_stmt: if_stmt | while_stmt | for_stmt | try_stmt | match_stmt
|
||||
| with_stmt | funcdef | classdef | decorated | async_stmt
|
||||
async_stmt: "async" (funcdef | with_stmt | for_stmt)
|
||||
if_stmt: "if" test ":" suite elifs ["else" ":" suite]
|
||||
elifs: elif_*
|
||||
elif_: "elif" test ":" suite
|
||||
while_stmt: "while" test ":" suite ["else" ":" suite]
|
||||
for_stmt: "for" exprlist "in" testlist ":" suite ["else" ":" suite]
|
||||
try_stmt: "try" ":" suite except_clauses ["else" ":" suite] [finally]
|
||||
| "try" ":" suite finally -> try_finally
|
||||
finally: "finally" ":" suite
|
||||
except_clauses: except_clause+
|
||||
except_clause: "except" [test ["as" name]] ":" suite
|
||||
// NB compile.c makes sure that the default except clause is last
|
||||
|
||||
|
||||
with_stmt: "with" with_items ":" suite
|
||||
with_items: with_item ("," with_item)*
|
||||
with_item: test ["as" name]
|
||||
|
||||
match_stmt: "match" test ":" _NEWLINE _INDENT case+ _DEDENT
|
||||
|
||||
case: "case" pattern ["if" test] ":" suite
|
||||
|
||||
?pattern: sequence_item_pattern "," _sequence_pattern -> sequence_pattern
|
||||
| as_pattern
|
||||
?as_pattern: or_pattern ("as" NAME)?
|
||||
?or_pattern: closed_pattern ("|" closed_pattern)*
|
||||
?closed_pattern: literal_pattern
|
||||
| NAME -> capture_pattern
|
||||
| "_" -> any_pattern
|
||||
| attr_pattern
|
||||
| "(" as_pattern ")"
|
||||
| "[" _sequence_pattern "]" -> sequence_pattern
|
||||
| "(" (sequence_item_pattern "," _sequence_pattern)? ")" -> sequence_pattern
|
||||
| "{" (mapping_item_pattern ("," mapping_item_pattern)* ","?)?"}" -> mapping_pattern
|
||||
| "{" (mapping_item_pattern ("," mapping_item_pattern)* ",")? "**" NAME ","? "}" -> mapping_star_pattern
|
||||
| class_pattern
|
||||
|
||||
literal_pattern: inner_literal_pattern
|
||||
|
||||
?inner_literal_pattern: "None" -> const_none
|
||||
| "True" -> const_true
|
||||
| "False" -> const_false
|
||||
| STRING -> string
|
||||
| number
|
||||
|
||||
attr_pattern: NAME ("." NAME)+ -> value
|
||||
|
||||
name_or_attr_pattern: NAME ("." NAME)* -> value
|
||||
|
||||
mapping_item_pattern: (literal_pattern|attr_pattern) ":" as_pattern
|
||||
|
||||
_sequence_pattern: (sequence_item_pattern ("," sequence_item_pattern)* ","?)?
|
||||
?sequence_item_pattern: as_pattern
|
||||
| "*" NAME -> star_pattern
|
||||
|
||||
class_pattern: name_or_attr_pattern "(" [arguments_pattern ","?] ")"
|
||||
arguments_pattern: pos_arg_pattern ["," keyws_arg_pattern]
|
||||
| keyws_arg_pattern -> no_pos_arguments
|
||||
|
||||
pos_arg_pattern: as_pattern ("," as_pattern)*
|
||||
keyws_arg_pattern: keyw_arg_pattern ("," keyw_arg_pattern)*
|
||||
keyw_arg_pattern: NAME "=" as_pattern
|
||||
|
||||
|
||||
|
||||
suite: simple_stmt | _NEWLINE _INDENT stmt+ _DEDENT
|
||||
|
||||
?test: or_test ("if" or_test "else" test)?
|
||||
| lambdef
|
||||
| assign_expr
|
||||
|
||||
assign_expr: name ":=" test
|
||||
|
||||
?test_nocond: or_test | lambdef_nocond
|
||||
|
||||
?or_test: and_test ("or" and_test)*
|
||||
?and_test: not_test_ ("and" not_test_)*
|
||||
?not_test_: "not" not_test_ -> not_test
|
||||
| comparison
|
||||
?comparison: expr (comp_op expr)*
|
||||
star_expr: "*" expr
|
||||
|
||||
?expr: or_expr
|
||||
?or_expr: xor_expr ("|" xor_expr)*
|
||||
?xor_expr: and_expr ("^" and_expr)*
|
||||
?and_expr: shift_expr ("&" shift_expr)*
|
||||
?shift_expr: arith_expr (_shift_op arith_expr)*
|
||||
?arith_expr: term (_add_op term)*
|
||||
?term: factor (_mul_op factor)*
|
||||
?factor: _unary_op factor | power
|
||||
|
||||
!_unary_op: "+"|"-"|"~"
|
||||
!_add_op: "+"|"-"
|
||||
!_shift_op: "<<"|">>"
|
||||
!_mul_op: "*"|"@"|"/"|"%"|"//"
|
||||
// <> isn't actually a valid comparison operator in Python. It's here for the
|
||||
// sake of a __future__ import described in PEP 401 (which really works :-)
|
||||
!comp_op: "<"|">"|"=="|">="|"<="|"<>"|"!="|"in"|"not" "in"|"is"|"is" "not"
|
||||
|
||||
?power: await_expr ("**" factor)?
|
||||
?await_expr: AWAIT? atom_expr
|
||||
AWAIT: "await"
|
||||
|
||||
?atom_expr: atom_expr "(" [arguments] ")" -> funccall
|
||||
| atom_expr "[" subscriptlist "]" -> getitem
|
||||
| atom_expr "." name -> getattr
|
||||
| atom
|
||||
|
||||
?atom: "(" yield_expr ")"
|
||||
| "(" _tuple_inner? ")" -> tuple
|
||||
| "(" comprehension{test_or_star_expr} ")" -> tuple_comprehension
|
||||
| "[" _testlist_comp? "]" -> list
|
||||
| "[" comprehension{test_or_star_expr} "]" -> list_comprehension
|
||||
| "{" _dict_exprlist? "}" -> dict
|
||||
| "{" comprehension{key_value} "}" -> dict_comprehension
|
||||
| "{" _set_exprlist "}" -> set
|
||||
| "{" comprehension{test} "}" -> set_comprehension
|
||||
| name -> var
|
||||
| number
|
||||
| string_concat
|
||||
| "(" test ")"
|
||||
| "..." -> ellipsis
|
||||
| "None" -> const_none
|
||||
| "True" -> const_true
|
||||
| "False" -> const_false
|
||||
|
||||
|
||||
?string_concat: string+
|
||||
|
||||
_testlist_comp: test | _tuple_inner
|
||||
_tuple_inner: test_or_star_expr (("," test_or_star_expr)+ [","] | ",")
|
||||
|
||||
|
||||
?test_or_star_expr: test
|
||||
| star_expr
|
||||
|
||||
?subscriptlist: subscript
|
||||
| subscript (("," subscript)+ [","] | ",") -> subscript_tuple
|
||||
?subscript: test | ([test] ":" [test] [sliceop]) -> slice
|
||||
sliceop: ":" [test]
|
||||
?exprlist: (expr|star_expr)
|
||||
| (expr|star_expr) (("," (expr|star_expr))+ [","]|",")
|
||||
?testlist: test | testlist_tuple
|
||||
testlist_tuple: test (("," test)+ [","] | ",")
|
||||
_dict_exprlist: (key_value | "**" expr) ("," (key_value | "**" expr))* [","]
|
||||
|
||||
key_value: test ":" test
|
||||
|
||||
_set_exprlist: test_or_star_expr ("," test_or_star_expr)* [","]
|
||||
|
||||
classdef: "class" name ["(" [arguments] ")"] ":" suite
|
||||
|
||||
|
||||
|
||||
arguments: argvalue ("," argvalue)* ("," [ starargs | kwargs])?
|
||||
| starargs
|
||||
| kwargs
|
||||
| comprehension{test}
|
||||
|
||||
starargs: stararg ("," stararg)* ("," argvalue)* ["," kwargs]
|
||||
stararg: "*" test
|
||||
kwargs: "**" test ("," argvalue)*
|
||||
|
||||
?argvalue: test ("=" test)?
|
||||
|
||||
|
||||
comprehension{comp_result}: comp_result comp_fors [comp_if]
|
||||
comp_fors: comp_for+
|
||||
comp_for: [ASYNC] "for" exprlist "in" or_test
|
||||
ASYNC: "async"
|
||||
?comp_if: "if" test_nocond
|
||||
|
||||
// not used in grammar, but may appear in "node" passed from Parser to Compiler
|
||||
encoding_decl: name
|
||||
|
||||
yield_expr: "yield" [testlist]
|
||||
| "yield" "from" test -> yield_from
|
||||
|
||||
number: DEC_NUMBER | HEX_NUMBER | BIN_NUMBER | OCT_NUMBER | FLOAT_NUMBER | IMAG_NUMBER
|
||||
string: STRING | LONG_STRING
|
||||
|
||||
// Other terminals
|
||||
|
||||
_NEWLINE: ( /\r?\n[\t ]*/ | COMMENT )+
|
||||
|
||||
%ignore /[\t \f]+/ // WS
|
||||
%ignore /\\[\t \f]*\r?\n/ // LINE_CONT
|
||||
%ignore COMMENT
|
||||
%declare _INDENT _DEDENT
|
||||
|
||||
|
||||
// Python terminals
|
||||
|
||||
!name: NAME | "match" | "case"
|
||||
NAME: /[^\W\d]\w*/
|
||||
COMMENT: /#[^\n]*/
|
||||
|
||||
STRING: /([ubf]?r?|r[ubf])("(?!"").*?(?<!\\)(\\\\)*?"|'(?!'').*?(?<!\\)(\\\\)*?')/i
|
||||
LONG_STRING: /([ubf]?r?|r[ubf])(""".*?(?<!\\)(\\\\)*?"""|'''.*?(?<!\\)(\\\\)*?''')/is
|
||||
|
||||
_SPECIAL_DEC: "0".."9" ("_"? "0".."9" )*
|
||||
DEC_NUMBER: "1".."9" ("_"? "0".."9" )*
|
||||
| "0" ("_"? "0" )* /(?![1-9])/
|
||||
HEX_NUMBER.2: "0" ("x" | "X") ("_"? ("0".."9" | "a".."f" | "A".."F"))+
|
||||
OCT_NUMBER.2: "0" ("o" | "O") ("_"? "0".."7" )+
|
||||
BIN_NUMBER.2: "0" ("b" | "B") ("_"? "0".."1" )+
|
||||
|
||||
_EXP: ("e"|"E") ["+" | "-"] _SPECIAL_DEC
|
||||
DECIMAL: "." _SPECIAL_DEC | _SPECIAL_DEC "." _SPECIAL_DEC?
|
||||
FLOAT_NUMBER.2: _SPECIAL_DEC _EXP | DECIMAL _EXP?
|
||||
IMAG_NUMBER.2: (_SPECIAL_DEC | FLOAT_NUMBER) ("J" | "j")
|
||||
|
||||
|
||||
// Comma-separated list (with an optional trailing comma)
|
||||
cs_list{item}: item ("," item)* ","?
|
||||
_cs_list{item}: item ("," item)* ","?
|
||||
|
|
@ -0,0 +1,7 @@
|
|||
// TODO: LETTER, WORD, etc.
|
||||
|
||||
//
|
||||
// Whitespace
|
||||
//
|
||||
WS_INLINE: /[ \t\xa0]/+
|
||||
WS: /[ \t\xa0\f\r\n]/+
|
||||
|
|
@ -0,0 +1,112 @@
|
|||
"Provides Indentation services for languages with indentation similar to Python"
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import List, Iterator
|
||||
|
||||
from .exceptions import LarkError
|
||||
from .lark import PostLex
|
||||
from .lexer import Token
|
||||
|
||||
###{standalone
|
||||
|
||||
class DedentError(LarkError):
|
||||
pass
|
||||
|
||||
class Indenter(PostLex, ABC):
|
||||
paren_level: int
|
||||
indent_level: List[int]
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.paren_level = 0
|
||||
self.indent_level = [0]
|
||||
assert self.tab_len > 0
|
||||
|
||||
def handle_NL(self, token: Token) -> Iterator[Token]:
|
||||
if self.paren_level > 0:
|
||||
return
|
||||
|
||||
yield token
|
||||
|
||||
indent_str = token.rsplit('\n', 1)[1] # Tabs and spaces
|
||||
indent = indent_str.count(' ') + indent_str.count('\t') * self.tab_len
|
||||
|
||||
if indent > self.indent_level[-1]:
|
||||
self.indent_level.append(indent)
|
||||
yield Token.new_borrow_pos(self.INDENT_type, indent_str, token)
|
||||
else:
|
||||
while indent < self.indent_level[-1]:
|
||||
self.indent_level.pop()
|
||||
yield Token.new_borrow_pos(self.DEDENT_type, indent_str, token)
|
||||
|
||||
if indent != self.indent_level[-1]:
|
||||
raise DedentError('Unexpected dedent to column %s. Expected dedent to %s' % (indent, self.indent_level[-1]))
|
||||
|
||||
def _process(self, stream):
|
||||
for token in stream:
|
||||
if token.type == self.NL_type:
|
||||
yield from self.handle_NL(token)
|
||||
else:
|
||||
yield token
|
||||
|
||||
if token.type in self.OPEN_PAREN_types:
|
||||
self.paren_level += 1
|
||||
elif token.type in self.CLOSE_PAREN_types:
|
||||
self.paren_level -= 1
|
||||
assert self.paren_level >= 0
|
||||
|
||||
while len(self.indent_level) > 1:
|
||||
self.indent_level.pop()
|
||||
yield Token(self.DEDENT_type, '')
|
||||
|
||||
assert self.indent_level == [0], self.indent_level
|
||||
|
||||
def process(self, stream):
|
||||
self.paren_level = 0
|
||||
self.indent_level = [0]
|
||||
return self._process(stream)
|
||||
|
||||
# XXX Hack for ContextualLexer. Maybe there's a more elegant solution?
|
||||
@property
|
||||
def always_accept(self):
|
||||
return (self.NL_type,)
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def NL_type(self) -> str:
|
||||
raise NotImplementedError()
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def OPEN_PAREN_types(self) -> List[str]:
|
||||
raise NotImplementedError()
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def CLOSE_PAREN_types(self) -> List[str]:
|
||||
raise NotImplementedError()
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def INDENT_type(self) -> str:
|
||||
raise NotImplementedError()
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def DEDENT_type(self) -> str:
|
||||
raise NotImplementedError()
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def tab_len(self) -> int:
|
||||
raise NotImplementedError()
|
||||
|
||||
|
||||
class PythonIndenter(Indenter):
|
||||
NL_type = '_NEWLINE'
|
||||
OPEN_PAREN_types = ['LPAR', 'LSQB', 'LBRACE']
|
||||
CLOSE_PAREN_types = ['RPAR', 'RSQB', 'RBRACE']
|
||||
INDENT_type = '_INDENT'
|
||||
DEDENT_type = '_DEDENT'
|
||||
tab_len = 8
|
||||
|
||||
###}
|
||||
|
|
@ -0,0 +1,648 @@
|
|||
from abc import ABC, abstractmethod
|
||||
import getpass
|
||||
import sys, os, pickle
|
||||
import tempfile
|
||||
import types
|
||||
import re
|
||||
from typing import (
|
||||
TypeVar, Type, List, Dict, Iterator, Callable, Union, Optional, Sequence,
|
||||
Tuple, Iterable, IO, Any, TYPE_CHECKING, Collection
|
||||
)
|
||||
if TYPE_CHECKING:
|
||||
from .parsers.lalr_interactive_parser import InteractiveParser
|
||||
from .tree import ParseTree
|
||||
from .visitors import Transformer
|
||||
if sys.version_info >= (3, 8):
|
||||
from typing import Literal
|
||||
else:
|
||||
from typing_extensions import Literal
|
||||
from .parser_frontends import ParsingFrontend
|
||||
|
||||
from .exceptions import ConfigurationError, assert_config, UnexpectedInput
|
||||
from .utils import Serialize, SerializeMemoizer, FS, isascii, logger
|
||||
from .load_grammar import load_grammar, FromPackageLoader, Grammar, verify_used_files, PackageResource, md5_digest
|
||||
from .tree import Tree
|
||||
from .common import LexerConf, ParserConf, _ParserArgType, _LexerArgType
|
||||
|
||||
from .lexer import Lexer, BasicLexer, TerminalDef, LexerThread, Token
|
||||
from .parse_tree_builder import ParseTreeBuilder
|
||||
from .parser_frontends import _validate_frontend_args, _get_lexer_callbacks, _deserialize_parsing_frontend, _construct_parsing_frontend
|
||||
from .grammar import Rule
|
||||
|
||||
|
||||
try:
|
||||
import regex
|
||||
_has_regex = True
|
||||
except ImportError:
|
||||
_has_regex = False
|
||||
|
||||
|
||||
###{standalone
|
||||
|
||||
|
||||
class PostLex(ABC):
|
||||
@abstractmethod
|
||||
def process(self, stream: Iterator[Token]) -> Iterator[Token]:
|
||||
return stream
|
||||
|
||||
always_accept: Iterable[str] = ()
|
||||
|
||||
class LarkOptions(Serialize):
|
||||
"""Specifies the options for Lark
|
||||
|
||||
"""
|
||||
|
||||
start: List[str]
|
||||
debug: bool
|
||||
transformer: 'Optional[Transformer]'
|
||||
propagate_positions: Union[bool, str]
|
||||
maybe_placeholders: bool
|
||||
cache: Union[bool, str]
|
||||
regex: bool
|
||||
g_regex_flags: int
|
||||
keep_all_tokens: bool
|
||||
tree_class: Any
|
||||
parser: _ParserArgType
|
||||
lexer: _LexerArgType
|
||||
ambiguity: 'Literal["auto", "resolve", "explicit", "forest"]'
|
||||
postlex: Optional[PostLex]
|
||||
priority: 'Optional[Literal["auto", "normal", "invert"]]'
|
||||
lexer_callbacks: Dict[str, Callable[[Token], Token]]
|
||||
use_bytes: bool
|
||||
edit_terminals: Optional[Callable[[TerminalDef], TerminalDef]]
|
||||
import_paths: 'List[Union[str, Callable[[Union[None, str, PackageResource], str], Tuple[str, str]]]]'
|
||||
source_path: Optional[str]
|
||||
|
||||
OPTIONS_DOC = """
|
||||
**=== General Options ===**
|
||||
|
||||
start
|
||||
The start symbol. Either a string, or a list of strings for multiple possible starts (Default: "start")
|
||||
debug
|
||||
Display debug information and extra warnings. Use only when debugging (Default: ``False``)
|
||||
When used with Earley, it generates a forest graph as "sppf.png", if 'dot' is installed.
|
||||
transformer
|
||||
Applies the transformer to every parse tree (equivalent to applying it after the parse, but faster)
|
||||
propagate_positions
|
||||
Propagates (line, column, end_line, end_column) attributes into all tree branches.
|
||||
Accepts ``False``, ``True``, or a callable, which will filter which nodes to ignore when propagating.
|
||||
maybe_placeholders
|
||||
When ``True``, the ``[]`` operator returns ``None`` when not matched.
|
||||
When ``False``, ``[]`` behaves like the ``?`` operator, and returns no value at all.
|
||||
(default= ``True``)
|
||||
cache
|
||||
Cache the results of the Lark grammar analysis, for x2 to x3 faster loading. LALR only for now.
|
||||
|
||||
- When ``False``, does nothing (default)
|
||||
- When ``True``, caches to a temporary file in the local directory
|
||||
- When given a string, caches to the path pointed by the string
|
||||
regex
|
||||
When True, uses the ``regex`` module instead of the stdlib ``re``.
|
||||
g_regex_flags
|
||||
Flags that are applied to all terminals (both regex and strings)
|
||||
keep_all_tokens
|
||||
Prevent the tree builder from automagically removing "punctuation" tokens (Default: ``False``)
|
||||
tree_class
|
||||
Lark will produce trees comprised of instances of this class instead of the default ``lark.Tree``.
|
||||
|
||||
**=== Algorithm Options ===**
|
||||
|
||||
parser
|
||||
Decides which parser engine to use. Accepts "earley" or "lalr". (Default: "earley").
|
||||
(there is also a "cyk" option for legacy)
|
||||
lexer
|
||||
Decides whether or not to use a lexer stage
|
||||
|
||||
- "auto" (default): Choose for me based on the parser
|
||||
- "basic": Use a basic lexer
|
||||
- "contextual": Stronger lexer (only works with parser="lalr")
|
||||
- "dynamic": Flexible and powerful (only with parser="earley")
|
||||
- "dynamic_complete": Same as dynamic, but tries *every* variation of tokenizing possible.
|
||||
ambiguity
|
||||
Decides how to handle ambiguity in the parse. Only relevant if parser="earley"
|
||||
|
||||
- "resolve": The parser will automatically choose the simplest derivation
|
||||
(it chooses consistently: greedy for tokens, non-greedy for rules)
|
||||
- "explicit": The parser will return all derivations wrapped in "_ambig" tree nodes (i.e. a forest).
|
||||
- "forest": The parser will return the root of the shared packed parse forest.
|
||||
|
||||
**=== Misc. / Domain Specific Options ===**
|
||||
|
||||
postlex
|
||||
Lexer post-processing (Default: ``None``) Only works with the basic and contextual lexers.
|
||||
priority
|
||||
How priorities should be evaluated - "auto", ``None``, "normal", "invert" (Default: "auto")
|
||||
lexer_callbacks
|
||||
Dictionary of callbacks for the lexer. May alter tokens during lexing. Use with caution.
|
||||
use_bytes
|
||||
Accept an input of type ``bytes`` instead of ``str``.
|
||||
edit_terminals
|
||||
A callback for editing the terminals before parse.
|
||||
import_paths
|
||||
A List of either paths or loader functions to specify from where grammars are imported
|
||||
source_path
|
||||
Override the source of from where the grammar was loaded. Useful for relative imports and unconventional grammar loading
|
||||
**=== End of Options ===**
|
||||
"""
|
||||
if __doc__:
|
||||
__doc__ += OPTIONS_DOC
|
||||
|
||||
|
||||
# Adding a new option needs to be done in multiple places:
|
||||
# - In the dictionary below. This is the primary truth of which options `Lark.__init__` accepts
|
||||
# - In the docstring above. It is used both for the docstring of `LarkOptions` and `Lark`, and in readthedocs
|
||||
# - As an attribute of `LarkOptions` above
|
||||
# - Potentially in `_LOAD_ALLOWED_OPTIONS` below this class, when the option doesn't change how the grammar is loaded
|
||||
# - Potentially in `lark.tools.__init__`, if it makes sense, and it can easily be passed as a cmd argument
|
||||
_defaults: Dict[str, Any] = {
|
||||
'debug': False,
|
||||
'keep_all_tokens': False,
|
||||
'tree_class': None,
|
||||
'cache': False,
|
||||
'postlex': None,
|
||||
'parser': 'earley',
|
||||
'lexer': 'auto',
|
||||
'transformer': None,
|
||||
'start': 'start',
|
||||
'priority': 'auto',
|
||||
'ambiguity': 'auto',
|
||||
'regex': False,
|
||||
'propagate_positions': False,
|
||||
'lexer_callbacks': {},
|
||||
'maybe_placeholders': True,
|
||||
'edit_terminals': None,
|
||||
'g_regex_flags': 0,
|
||||
'use_bytes': False,
|
||||
'import_paths': [],
|
||||
'source_path': None,
|
||||
'_plugins': {},
|
||||
}
|
||||
|
||||
def __init__(self, options_dict: Dict[str, Any]) -> None:
|
||||
o = dict(options_dict)
|
||||
|
||||
options = {}
|
||||
for name, default in self._defaults.items():
|
||||
if name in o:
|
||||
value = o.pop(name)
|
||||
if isinstance(default, bool) and name not in ('cache', 'use_bytes', 'propagate_positions'):
|
||||
value = bool(value)
|
||||
else:
|
||||
value = default
|
||||
|
||||
options[name] = value
|
||||
|
||||
if isinstance(options['start'], str):
|
||||
options['start'] = [options['start']]
|
||||
|
||||
self.__dict__['options'] = options
|
||||
|
||||
|
||||
assert_config(self.parser, ('earley', 'lalr', 'cyk', None))
|
||||
|
||||
if self.parser == 'earley' and self.transformer:
|
||||
raise ConfigurationError('Cannot specify an embedded transformer when using the Earley algorithm. '
|
||||
'Please use your transformer on the resulting parse tree, or use a different algorithm (i.e. LALR)')
|
||||
|
||||
if o:
|
||||
raise ConfigurationError("Unknown options: %s" % o.keys())
|
||||
|
||||
def __getattr__(self, name: str) -> Any:
|
||||
try:
|
||||
return self.__dict__['options'][name]
|
||||
except KeyError as e:
|
||||
raise AttributeError(e)
|
||||
|
||||
def __setattr__(self, name: str, value: str) -> None:
|
||||
assert_config(name, self.options.keys(), "%r isn't a valid option. Expected one of: %s")
|
||||
self.options[name] = value
|
||||
|
||||
def serialize(self, memo = None) -> Dict[str, Any]:
|
||||
return self.options
|
||||
|
||||
@classmethod
|
||||
def deserialize(cls, data: Dict[str, Any], memo: Dict[int, Union[TerminalDef, Rule]]) -> "LarkOptions":
|
||||
return cls(data)
|
||||
|
||||
|
||||
# Options that can be passed to the Lark parser, even when it was loaded from cache/standalone.
|
||||
# These options are only used outside of `load_grammar`.
|
||||
_LOAD_ALLOWED_OPTIONS = {'postlex', 'transformer', 'lexer_callbacks', 'use_bytes', 'debug', 'g_regex_flags', 'regex', 'propagate_positions', 'tree_class', '_plugins'}
|
||||
|
||||
_VALID_PRIORITY_OPTIONS = ('auto', 'normal', 'invert', None)
|
||||
_VALID_AMBIGUITY_OPTIONS = ('auto', 'resolve', 'explicit', 'forest')
|
||||
|
||||
|
||||
_T = TypeVar('_T', bound="Lark")
|
||||
|
||||
class Lark(Serialize):
|
||||
"""Main interface for the library.
|
||||
|
||||
It's mostly a thin wrapper for the many different parsers, and for the tree constructor.
|
||||
|
||||
Parameters:
|
||||
grammar: a string or file-object containing the grammar spec (using Lark's ebnf syntax)
|
||||
options: a dictionary controlling various aspects of Lark.
|
||||
|
||||
Example:
|
||||
>>> Lark(r'''start: "foo" ''')
|
||||
Lark(...)
|
||||
"""
|
||||
|
||||
source_path: str
|
||||
source_grammar: str
|
||||
grammar: 'Grammar'
|
||||
options: LarkOptions
|
||||
lexer: Lexer
|
||||
terminals: Collection[TerminalDef]
|
||||
|
||||
def __init__(self, grammar: 'Union[Grammar, str, IO[str]]', **options) -> None:
|
||||
self.options = LarkOptions(options)
|
||||
re_module: types.ModuleType
|
||||
|
||||
# Set regex or re module
|
||||
use_regex = self.options.regex
|
||||
if use_regex:
|
||||
if _has_regex:
|
||||
re_module = regex
|
||||
else:
|
||||
raise ImportError('`regex` module must be installed if calling `Lark(regex=True)`.')
|
||||
else:
|
||||
re_module = re
|
||||
|
||||
# Some, but not all file-like objects have a 'name' attribute
|
||||
if self.options.source_path is None:
|
||||
try:
|
||||
self.source_path = grammar.name # type: ignore[union-attr]
|
||||
except AttributeError:
|
||||
self.source_path = '<string>'
|
||||
else:
|
||||
self.source_path = self.options.source_path
|
||||
|
||||
# Drain file-like objects to get their contents
|
||||
try:
|
||||
read = grammar.read # type: ignore[union-attr]
|
||||
except AttributeError:
|
||||
pass
|
||||
else:
|
||||
grammar = read()
|
||||
|
||||
cache_fn = None
|
||||
cache_md5 = None
|
||||
if isinstance(grammar, str):
|
||||
self.source_grammar = grammar
|
||||
if self.options.use_bytes:
|
||||
if not isascii(grammar):
|
||||
raise ConfigurationError("Grammar must be ascii only, when use_bytes=True")
|
||||
|
||||
if self.options.cache:
|
||||
if self.options.parser != 'lalr':
|
||||
raise ConfigurationError("cache only works with parser='lalr' for now")
|
||||
|
||||
unhashable = ('transformer', 'postlex', 'lexer_callbacks', 'edit_terminals', '_plugins')
|
||||
options_str = ''.join(k+str(v) for k, v in options.items() if k not in unhashable)
|
||||
from . import __version__
|
||||
s = grammar + options_str + __version__ + str(sys.version_info[:2])
|
||||
cache_md5 = md5_digest(s)
|
||||
|
||||
if isinstance(self.options.cache, str):
|
||||
cache_fn = self.options.cache
|
||||
else:
|
||||
if self.options.cache is not True:
|
||||
raise ConfigurationError("cache argument must be bool or str")
|
||||
|
||||
try:
|
||||
username = getpass.getuser()
|
||||
except Exception:
|
||||
# The exception raised may be ImportError or OSError in
|
||||
# the future. For the cache, we don't care about the
|
||||
# specific reason - we just want a username.
|
||||
username = "unknown"
|
||||
|
||||
cache_fn = tempfile.gettempdir() + "/.lark_cache_%s_%s_%s_%s.tmp" % (username, cache_md5, *sys.version_info[:2])
|
||||
|
||||
old_options = self.options
|
||||
try:
|
||||
with FS.open(cache_fn, 'rb') as f:
|
||||
logger.debug('Loading grammar from cache: %s', cache_fn)
|
||||
# Remove options that aren't relevant for loading from cache
|
||||
for name in (set(options) - _LOAD_ALLOWED_OPTIONS):
|
||||
del options[name]
|
||||
file_md5 = f.readline().rstrip(b'\n')
|
||||
cached_used_files = pickle.load(f)
|
||||
if file_md5 == cache_md5.encode('utf8') and verify_used_files(cached_used_files):
|
||||
cached_parser_data = pickle.load(f)
|
||||
self._load(cached_parser_data, **options)
|
||||
return
|
||||
except FileNotFoundError:
|
||||
# The cache file doesn't exist; parse and compose the grammar as normal
|
||||
pass
|
||||
except Exception: # We should probably narrow done which errors we catch here.
|
||||
logger.exception("Failed to load Lark from cache: %r. We will try to carry on.", cache_fn)
|
||||
|
||||
# In theory, the Lark instance might have been messed up by the call to `_load`.
|
||||
# In practice the only relevant thing that might have been overwritten should be `options`
|
||||
self.options = old_options
|
||||
|
||||
|
||||
# Parse the grammar file and compose the grammars
|
||||
self.grammar, used_files = load_grammar(grammar, self.source_path, self.options.import_paths, self.options.keep_all_tokens)
|
||||
else:
|
||||
assert isinstance(grammar, Grammar)
|
||||
self.grammar = grammar
|
||||
|
||||
|
||||
if self.options.lexer == 'auto':
|
||||
if self.options.parser == 'lalr':
|
||||
self.options.lexer = 'contextual'
|
||||
elif self.options.parser == 'earley':
|
||||
if self.options.postlex is not None:
|
||||
logger.info("postlex can't be used with the dynamic lexer, so we use 'basic' instead. "
|
||||
"Consider using lalr with contextual instead of earley")
|
||||
self.options.lexer = 'basic'
|
||||
else:
|
||||
self.options.lexer = 'dynamic'
|
||||
elif self.options.parser == 'cyk':
|
||||
self.options.lexer = 'basic'
|
||||
else:
|
||||
assert False, self.options.parser
|
||||
lexer = self.options.lexer
|
||||
if isinstance(lexer, type):
|
||||
assert issubclass(lexer, Lexer) # XXX Is this really important? Maybe just ensure interface compliance
|
||||
else:
|
||||
assert_config(lexer, ('basic', 'contextual', 'dynamic', 'dynamic_complete'))
|
||||
if self.options.postlex is not None and 'dynamic' in lexer:
|
||||
raise ConfigurationError("Can't use postlex with a dynamic lexer. Use basic or contextual instead")
|
||||
|
||||
if self.options.ambiguity == 'auto':
|
||||
if self.options.parser == 'earley':
|
||||
self.options.ambiguity = 'resolve'
|
||||
else:
|
||||
assert_config(self.options.parser, ('earley', 'cyk'), "%r doesn't support disambiguation. Use one of these parsers instead: %s")
|
||||
|
||||
if self.options.priority == 'auto':
|
||||
self.options.priority = 'normal'
|
||||
|
||||
if self.options.priority not in _VALID_PRIORITY_OPTIONS:
|
||||
raise ConfigurationError("invalid priority option: %r. Must be one of %r" % (self.options.priority, _VALID_PRIORITY_OPTIONS))
|
||||
if self.options.ambiguity not in _VALID_AMBIGUITY_OPTIONS:
|
||||
raise ConfigurationError("invalid ambiguity option: %r. Must be one of %r" % (self.options.ambiguity, _VALID_AMBIGUITY_OPTIONS))
|
||||
|
||||
if self.options.parser is None:
|
||||
terminals_to_keep = '*'
|
||||
elif self.options.postlex is not None:
|
||||
terminals_to_keep = set(self.options.postlex.always_accept)
|
||||
else:
|
||||
terminals_to_keep = set()
|
||||
|
||||
# Compile the EBNF grammar into BNF
|
||||
self.terminals, self.rules, self.ignore_tokens = self.grammar.compile(self.options.start, terminals_to_keep)
|
||||
|
||||
if self.options.edit_terminals:
|
||||
for t in self.terminals:
|
||||
self.options.edit_terminals(t)
|
||||
|
||||
self._terminals_dict = {t.name: t for t in self.terminals}
|
||||
|
||||
# If the user asked to invert the priorities, negate them all here.
|
||||
if self.options.priority == 'invert':
|
||||
for rule in self.rules:
|
||||
if rule.options.priority is not None:
|
||||
rule.options.priority = -rule.options.priority
|
||||
for term in self.terminals:
|
||||
term.priority = -term.priority
|
||||
# Else, if the user asked to disable priorities, strip them from the
|
||||
# rules and terminals. This allows the Earley parsers to skip an extra forest walk
|
||||
# for improved performance, if you don't need them (or didn't specify any).
|
||||
elif self.options.priority is None:
|
||||
for rule in self.rules:
|
||||
if rule.options.priority is not None:
|
||||
rule.options.priority = None
|
||||
for term in self.terminals:
|
||||
term.priority = 0
|
||||
|
||||
# TODO Deprecate lexer_callbacks?
|
||||
self.lexer_conf = LexerConf(
|
||||
self.terminals, re_module, self.ignore_tokens, self.options.postlex,
|
||||
self.options.lexer_callbacks, self.options.g_regex_flags, use_bytes=self.options.use_bytes
|
||||
)
|
||||
|
||||
if self.options.parser:
|
||||
self.parser = self._build_parser()
|
||||
elif lexer:
|
||||
self.lexer = self._build_lexer()
|
||||
|
||||
if cache_fn:
|
||||
logger.debug('Saving grammar to cache: %s', cache_fn)
|
||||
try:
|
||||
with FS.open(cache_fn, 'wb') as f:
|
||||
assert cache_md5 is not None
|
||||
f.write(cache_md5.encode('utf8') + b'\n')
|
||||
pickle.dump(used_files, f)
|
||||
self.save(f, _LOAD_ALLOWED_OPTIONS)
|
||||
except IOError as e:
|
||||
logger.exception("Failed to save Lark to cache: %r.", cache_fn, e)
|
||||
|
||||
if __doc__:
|
||||
__doc__ += "\n\n" + LarkOptions.OPTIONS_DOC
|
||||
|
||||
__serialize_fields__ = 'parser', 'rules', 'options'
|
||||
|
||||
def _build_lexer(self, dont_ignore: bool=False) -> BasicLexer:
|
||||
lexer_conf = self.lexer_conf
|
||||
if dont_ignore:
|
||||
from copy import copy
|
||||
lexer_conf = copy(lexer_conf)
|
||||
lexer_conf.ignore = ()
|
||||
return BasicLexer(lexer_conf)
|
||||
|
||||
def _prepare_callbacks(self) -> None:
|
||||
self._callbacks = {}
|
||||
# we don't need these callbacks if we aren't building a tree
|
||||
if self.options.ambiguity != 'forest':
|
||||
self._parse_tree_builder = ParseTreeBuilder(
|
||||
self.rules,
|
||||
self.options.tree_class or Tree,
|
||||
self.options.propagate_positions,
|
||||
self.options.parser != 'lalr' and self.options.ambiguity == 'explicit',
|
||||
self.options.maybe_placeholders
|
||||
)
|
||||
self._callbacks = self._parse_tree_builder.create_callback(self.options.transformer)
|
||||
self._callbacks.update(_get_lexer_callbacks(self.options.transformer, self.terminals))
|
||||
|
||||
def _build_parser(self) -> "ParsingFrontend":
|
||||
self._prepare_callbacks()
|
||||
_validate_frontend_args(self.options.parser, self.options.lexer)
|
||||
parser_conf = ParserConf(self.rules, self._callbacks, self.options.start)
|
||||
return _construct_parsing_frontend(
|
||||
self.options.parser,
|
||||
self.options.lexer,
|
||||
self.lexer_conf,
|
||||
parser_conf,
|
||||
options=self.options
|
||||
)
|
||||
|
||||
def save(self, f, exclude_options: Collection[str] = ()) -> None:
|
||||
"""Saves the instance into the given file object
|
||||
|
||||
Useful for caching and multiprocessing.
|
||||
"""
|
||||
data, m = self.memo_serialize([TerminalDef, Rule])
|
||||
if exclude_options:
|
||||
data["options"] = {n: v for n, v in data["options"].items() if n not in exclude_options}
|
||||
pickle.dump({'data': data, 'memo': m}, f, protocol=pickle.HIGHEST_PROTOCOL)
|
||||
|
||||
@classmethod
|
||||
def load(cls: Type[_T], f) -> _T:
|
||||
"""Loads an instance from the given file object
|
||||
|
||||
Useful for caching and multiprocessing.
|
||||
"""
|
||||
inst = cls.__new__(cls)
|
||||
return inst._load(f)
|
||||
|
||||
def _deserialize_lexer_conf(self, data: Dict[str, Any], memo: Dict[int, Union[TerminalDef, Rule]], options: LarkOptions) -> LexerConf:
|
||||
lexer_conf = LexerConf.deserialize(data['lexer_conf'], memo)
|
||||
lexer_conf.callbacks = options.lexer_callbacks or {}
|
||||
lexer_conf.re_module = regex if options.regex else re
|
||||
lexer_conf.use_bytes = options.use_bytes
|
||||
lexer_conf.g_regex_flags = options.g_regex_flags
|
||||
lexer_conf.skip_validation = True
|
||||
lexer_conf.postlex = options.postlex
|
||||
return lexer_conf
|
||||
|
||||
def _load(self: _T, f: Any, **kwargs) -> _T:
|
||||
if isinstance(f, dict):
|
||||
d = f
|
||||
else:
|
||||
d = pickle.load(f)
|
||||
memo_json = d['memo']
|
||||
data = d['data']
|
||||
|
||||
assert memo_json
|
||||
memo = SerializeMemoizer.deserialize(memo_json, {'Rule': Rule, 'TerminalDef': TerminalDef}, {})
|
||||
options = dict(data['options'])
|
||||
if (set(kwargs) - _LOAD_ALLOWED_OPTIONS) & set(LarkOptions._defaults):
|
||||
raise ConfigurationError("Some options are not allowed when loading a Parser: {}"
|
||||
.format(set(kwargs) - _LOAD_ALLOWED_OPTIONS))
|
||||
options.update(kwargs)
|
||||
self.options = LarkOptions.deserialize(options, memo)
|
||||
self.rules = [Rule.deserialize(r, memo) for r in data['rules']]
|
||||
self.source_path = '<deserialized>'
|
||||
_validate_frontend_args(self.options.parser, self.options.lexer)
|
||||
self.lexer_conf = self._deserialize_lexer_conf(data['parser'], memo, self.options)
|
||||
self.terminals = self.lexer_conf.terminals
|
||||
self._prepare_callbacks()
|
||||
self._terminals_dict = {t.name: t for t in self.terminals}
|
||||
self.parser = _deserialize_parsing_frontend(
|
||||
data['parser'],
|
||||
memo,
|
||||
self.lexer_conf,
|
||||
self._callbacks,
|
||||
self.options, # Not all, but multiple attributes are used
|
||||
)
|
||||
return self
|
||||
|
||||
@classmethod
|
||||
def _load_from_dict(cls, data, memo, **kwargs):
|
||||
inst = cls.__new__(cls)
|
||||
return inst._load({'data': data, 'memo': memo}, **kwargs)
|
||||
|
||||
@classmethod
|
||||
def open(cls: Type[_T], grammar_filename: str, rel_to: Optional[str]=None, **options) -> _T:
|
||||
"""Create an instance of Lark with the grammar given by its filename
|
||||
|
||||
If ``rel_to`` is provided, the function will find the grammar filename in relation to it.
|
||||
|
||||
Example:
|
||||
|
||||
>>> Lark.open("grammar_file.lark", rel_to=__file__, parser="lalr")
|
||||
Lark(...)
|
||||
|
||||
"""
|
||||
if rel_to:
|
||||
basepath = os.path.dirname(rel_to)
|
||||
grammar_filename = os.path.join(basepath, grammar_filename)
|
||||
with open(grammar_filename, encoding='utf8') as f:
|
||||
return cls(f, **options)
|
||||
|
||||
@classmethod
|
||||
def open_from_package(cls: Type[_T], package: str, grammar_path: str, search_paths: 'Sequence[str]'=[""], **options) -> _T:
|
||||
"""Create an instance of Lark with the grammar loaded from within the package `package`.
|
||||
This allows grammar loading from zipapps.
|
||||
|
||||
Imports in the grammar will use the `package` and `search_paths` provided, through `FromPackageLoader`
|
||||
|
||||
Example:
|
||||
|
||||
Lark.open_from_package(__name__, "example.lark", ("grammars",), parser=...)
|
||||
"""
|
||||
package_loader = FromPackageLoader(package, search_paths)
|
||||
full_path, text = package_loader(None, grammar_path)
|
||||
options.setdefault('source_path', full_path)
|
||||
options.setdefault('import_paths', [])
|
||||
options['import_paths'].append(package_loader)
|
||||
return cls(text, **options)
|
||||
|
||||
def __repr__(self):
|
||||
return 'Lark(open(%r), parser=%r, lexer=%r, ...)' % (self.source_path, self.options.parser, self.options.lexer)
|
||||
|
||||
|
||||
def lex(self, text: str, dont_ignore: bool=False) -> Iterator[Token]:
|
||||
"""Only lex (and postlex) the text, without parsing it. Only relevant when lexer='basic'
|
||||
|
||||
When dont_ignore=True, the lexer will return all tokens, even those marked for %ignore.
|
||||
|
||||
:raises UnexpectedCharacters: In case the lexer cannot find a suitable match.
|
||||
"""
|
||||
lexer: Lexer
|
||||
if not hasattr(self, 'lexer') or dont_ignore:
|
||||
lexer = self._build_lexer(dont_ignore)
|
||||
else:
|
||||
lexer = self.lexer
|
||||
lexer_thread = LexerThread.from_text(lexer, text)
|
||||
stream = lexer_thread.lex(None)
|
||||
if self.options.postlex:
|
||||
return self.options.postlex.process(stream)
|
||||
return stream
|
||||
|
||||
def get_terminal(self, name: str) -> TerminalDef:
|
||||
"""Get information about a terminal"""
|
||||
return self._terminals_dict[name]
|
||||
|
||||
def parse_interactive(self, text: Optional[str]=None, start: Optional[str]=None) -> 'InteractiveParser':
|
||||
"""Start an interactive parsing session.
|
||||
|
||||
Parameters:
|
||||
text (str, optional): Text to be parsed. Required for ``resume_parse()``.
|
||||
start (str, optional): Start symbol
|
||||
|
||||
Returns:
|
||||
A new InteractiveParser instance.
|
||||
|
||||
See Also: ``Lark.parse()``
|
||||
"""
|
||||
return self.parser.parse_interactive(text, start=start)
|
||||
|
||||
def parse(self, text: str, start: Optional[str]=None, on_error: 'Optional[Callable[[UnexpectedInput], bool]]'=None) -> 'ParseTree':
|
||||
"""Parse the given text, according to the options provided.
|
||||
|
||||
Parameters:
|
||||
text (str): Text to be parsed.
|
||||
start (str, optional): Required if Lark was given multiple possible start symbols (using the start option).
|
||||
on_error (function, optional): if provided, will be called on UnexpectedToken error. Return true to resume parsing.
|
||||
LALR only. See examples/advanced/error_handling.py for an example of how to use on_error.
|
||||
|
||||
Returns:
|
||||
If a transformer is supplied to ``__init__``, returns whatever is the
|
||||
result of the transformation. Otherwise, returns a Tree instance.
|
||||
|
||||
:raises UnexpectedInput: On a parse error, one of these sub-exceptions will rise:
|
||||
``UnexpectedCharacters``, ``UnexpectedToken``, or ``UnexpectedEOF``.
|
||||
For convenience, these sub-exceptions also inherit from ``ParserError`` and ``LexerError``.
|
||||
|
||||
"""
|
||||
return self.parser.parse(text, start=start, on_error=on_error)
|
||||
|
||||
|
||||
###}
|
||||
|
|
@ -0,0 +1,603 @@
|
|||
# Lexer Implementation
|
||||
|
||||
from abc import abstractmethod, ABC
|
||||
import re
|
||||
from contextlib import suppress
|
||||
from typing import (
|
||||
TypeVar, Type, List, Dict, Iterator, Collection, Callable, Optional, FrozenSet, Any,
|
||||
Pattern as REPattern, ClassVar, TYPE_CHECKING, overload
|
||||
)
|
||||
from types import ModuleType
|
||||
import warnings
|
||||
if TYPE_CHECKING:
|
||||
from .common import LexerConf
|
||||
|
||||
from .utils import classify, get_regexp_width, Serialize
|
||||
from .exceptions import UnexpectedCharacters, LexError, UnexpectedToken
|
||||
from .grammar import TOKEN_DEFAULT_PRIORITY
|
||||
|
||||
###{standalone
|
||||
from copy import copy
|
||||
|
||||
|
||||
class Pattern(Serialize, ABC):
|
||||
|
||||
value: str
|
||||
flags: Collection[str]
|
||||
raw: Optional[str]
|
||||
type: ClassVar[str]
|
||||
|
||||
def __init__(self, value: str, flags: Collection[str]=(), raw: Optional[str]=None) -> None:
|
||||
self.value = value
|
||||
self.flags = frozenset(flags)
|
||||
self.raw = raw
|
||||
|
||||
def __repr__(self):
|
||||
return repr(self.to_regexp())
|
||||
|
||||
# Pattern Hashing assumes all subclasses have a different priority!
|
||||
def __hash__(self):
|
||||
return hash((type(self), self.value, self.flags))
|
||||
|
||||
def __eq__(self, other):
|
||||
return type(self) == type(other) and self.value == other.value and self.flags == other.flags
|
||||
|
||||
@abstractmethod
|
||||
def to_regexp(self) -> str:
|
||||
raise NotImplementedError()
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def min_width(self) -> int:
|
||||
raise NotImplementedError()
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def max_width(self) -> int:
|
||||
raise NotImplementedError()
|
||||
|
||||
def _get_flags(self, value):
|
||||
for f in self.flags:
|
||||
value = ('(?%s:%s)' % (f, value))
|
||||
return value
|
||||
|
||||
|
||||
class PatternStr(Pattern):
|
||||
__serialize_fields__ = 'value', 'flags'
|
||||
|
||||
type: ClassVar[str] = "str"
|
||||
|
||||
def to_regexp(self) -> str:
|
||||
return self._get_flags(re.escape(self.value))
|
||||
|
||||
@property
|
||||
def min_width(self) -> int:
|
||||
return len(self.value)
|
||||
|
||||
@property
|
||||
def max_width(self) -> int:
|
||||
return len(self.value)
|
||||
|
||||
|
||||
class PatternRE(Pattern):
|
||||
__serialize_fields__ = 'value', 'flags', '_width'
|
||||
|
||||
type: ClassVar[str] = "re"
|
||||
|
||||
def to_regexp(self) -> str:
|
||||
return self._get_flags(self.value)
|
||||
|
||||
_width = None
|
||||
def _get_width(self):
|
||||
if self._width is None:
|
||||
self._width = get_regexp_width(self.to_regexp())
|
||||
return self._width
|
||||
|
||||
@property
|
||||
def min_width(self) -> int:
|
||||
return self._get_width()[0]
|
||||
|
||||
@property
|
||||
def max_width(self) -> int:
|
||||
return self._get_width()[1]
|
||||
|
||||
|
||||
class TerminalDef(Serialize):
|
||||
__serialize_fields__ = 'name', 'pattern', 'priority'
|
||||
__serialize_namespace__ = PatternStr, PatternRE
|
||||
|
||||
name: str
|
||||
pattern: Pattern
|
||||
priority: int
|
||||
|
||||
def __init__(self, name: str, pattern: Pattern, priority: int=TOKEN_DEFAULT_PRIORITY) -> None:
|
||||
assert isinstance(pattern, Pattern), pattern
|
||||
self.name = name
|
||||
self.pattern = pattern
|
||||
self.priority = priority
|
||||
|
||||
def __repr__(self):
|
||||
return '%s(%r, %r)' % (type(self).__name__, self.name, self.pattern)
|
||||
|
||||
def user_repr(self) -> str:
|
||||
if self.name.startswith('__'): # We represent a generated terminal
|
||||
return self.pattern.raw or self.name
|
||||
else:
|
||||
return self.name
|
||||
|
||||
_T = TypeVar('_T', bound="Token")
|
||||
|
||||
class Token(str):
|
||||
"""A string with meta-information, that is produced by the lexer.
|
||||
|
||||
When parsing text, the resulting chunks of the input that haven't been discarded,
|
||||
will end up in the tree as Token instances. The Token class inherits from Python's ``str``,
|
||||
so normal string comparisons and operations will work as expected.
|
||||
|
||||
Attributes:
|
||||
type: Name of the token (as specified in grammar)
|
||||
value: Value of the token (redundant, as ``token.value == token`` will always be true)
|
||||
start_pos: The index of the token in the text
|
||||
line: The line of the token in the text (starting with 1)
|
||||
column: The column of the token in the text (starting with 1)
|
||||
end_line: The line where the token ends
|
||||
end_column: The next column after the end of the token. For example,
|
||||
if the token is a single character with a column value of 4,
|
||||
end_column will be 5.
|
||||
end_pos: the index where the token ends (basically ``start_pos + len(token)``)
|
||||
"""
|
||||
__slots__ = ('type', 'start_pos', 'value', 'line', 'column', 'end_line', 'end_column', 'end_pos')
|
||||
|
||||
__match_args__ = ('type', 'value')
|
||||
|
||||
type: str
|
||||
start_pos: Optional[int]
|
||||
value: Any
|
||||
line: Optional[int]
|
||||
column: Optional[int]
|
||||
end_line: Optional[int]
|
||||
end_column: Optional[int]
|
||||
end_pos: Optional[int]
|
||||
|
||||
|
||||
@overload
|
||||
def __new__(
|
||||
cls,
|
||||
type: str,
|
||||
value: Any,
|
||||
start_pos: Optional[int]=None,
|
||||
line: Optional[int]=None,
|
||||
column: Optional[int]=None,
|
||||
end_line: Optional[int]=None,
|
||||
end_column: Optional[int]=None,
|
||||
end_pos: Optional[int]=None
|
||||
) -> 'Token':
|
||||
...
|
||||
|
||||
@overload
|
||||
def __new__(
|
||||
cls,
|
||||
type_: str,
|
||||
value: Any,
|
||||
start_pos: Optional[int]=None,
|
||||
line: Optional[int]=None,
|
||||
column: Optional[int]=None,
|
||||
end_line: Optional[int]=None,
|
||||
end_column: Optional[int]=None,
|
||||
end_pos: Optional[int]=None
|
||||
) -> 'Token': ...
|
||||
|
||||
def __new__(cls, *args, **kwargs):
|
||||
if "type_" in kwargs:
|
||||
warnings.warn("`type_` is deprecated use `type` instead", DeprecationWarning)
|
||||
|
||||
if "type" in kwargs:
|
||||
raise TypeError("Error: using both 'type' and the deprecated 'type_' as arguments.")
|
||||
kwargs["type"] = kwargs.pop("type_")
|
||||
|
||||
return cls._future_new(*args, **kwargs)
|
||||
|
||||
|
||||
@classmethod
|
||||
def _future_new(cls, type, value, start_pos=None, line=None, column=None, end_line=None, end_column=None, end_pos=None):
|
||||
inst = super(Token, cls).__new__(cls, value)
|
||||
|
||||
inst.type = type
|
||||
inst.start_pos = start_pos
|
||||
inst.value = value
|
||||
inst.line = line
|
||||
inst.column = column
|
||||
inst.end_line = end_line
|
||||
inst.end_column = end_column
|
||||
inst.end_pos = end_pos
|
||||
return inst
|
||||
|
||||
@overload
|
||||
def update(self, type: Optional[str]=None, value: Optional[Any]=None) -> 'Token':
|
||||
...
|
||||
|
||||
@overload
|
||||
def update(self, type_: Optional[str]=None, value: Optional[Any]=None) -> 'Token':
|
||||
...
|
||||
|
||||
def update(self, *args, **kwargs):
|
||||
if "type_" in kwargs:
|
||||
warnings.warn("`type_` is deprecated use `type` instead", DeprecationWarning)
|
||||
|
||||
if "type" in kwargs:
|
||||
raise TypeError("Error: using both 'type' and the deprecated 'type_' as arguments.")
|
||||
kwargs["type"] = kwargs.pop("type_")
|
||||
|
||||
return self._future_update(*args, **kwargs)
|
||||
|
||||
def _future_update(self, type: Optional[str]=None, value: Optional[Any]=None) -> 'Token':
|
||||
return Token.new_borrow_pos(
|
||||
type if type is not None else self.type,
|
||||
value if value is not None else self.value,
|
||||
self
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def new_borrow_pos(cls: Type[_T], type_: str, value: Any, borrow_t: 'Token') -> _T:
|
||||
return cls(type_, value, borrow_t.start_pos, borrow_t.line, borrow_t.column, borrow_t.end_line, borrow_t.end_column, borrow_t.end_pos)
|
||||
|
||||
def __reduce__(self):
|
||||
return (self.__class__, (self.type, self.value, self.start_pos, self.line, self.column))
|
||||
|
||||
def __repr__(self):
|
||||
return 'Token(%r, %r)' % (self.type, self.value)
|
||||
|
||||
def __deepcopy__(self, memo):
|
||||
return Token(self.type, self.value, self.start_pos, self.line, self.column)
|
||||
|
||||
def __eq__(self, other):
|
||||
if isinstance(other, Token) and self.type != other.type:
|
||||
return False
|
||||
|
||||
return str.__eq__(self, other)
|
||||
|
||||
__hash__ = str.__hash__
|
||||
|
||||
|
||||
class LineCounter:
|
||||
__slots__ = 'char_pos', 'line', 'column', 'line_start_pos', 'newline_char'
|
||||
|
||||
def __init__(self, newline_char):
|
||||
self.newline_char = newline_char
|
||||
self.char_pos = 0
|
||||
self.line = 1
|
||||
self.column = 1
|
||||
self.line_start_pos = 0
|
||||
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, LineCounter):
|
||||
return NotImplemented
|
||||
|
||||
return self.char_pos == other.char_pos and self.newline_char == other.newline_char
|
||||
|
||||
def feed(self, token: Token, test_newline=True):
|
||||
"""Consume a token and calculate the new line & column.
|
||||
|
||||
As an optional optimization, set test_newline=False if token doesn't contain a newline.
|
||||
"""
|
||||
if test_newline:
|
||||
newlines = token.count(self.newline_char)
|
||||
if newlines:
|
||||
self.line += newlines
|
||||
self.line_start_pos = self.char_pos + token.rindex(self.newline_char) + 1
|
||||
|
||||
self.char_pos += len(token)
|
||||
self.column = self.char_pos - self.line_start_pos + 1
|
||||
|
||||
|
||||
class UnlessCallback:
|
||||
def __init__(self, scanner):
|
||||
self.scanner = scanner
|
||||
|
||||
def __call__(self, t):
|
||||
res = self.scanner.match(t.value, 0)
|
||||
if res:
|
||||
_value, t.type = res
|
||||
return t
|
||||
|
||||
|
||||
class CallChain:
|
||||
def __init__(self, callback1, callback2, cond):
|
||||
self.callback1 = callback1
|
||||
self.callback2 = callback2
|
||||
self.cond = cond
|
||||
|
||||
def __call__(self, t):
|
||||
t2 = self.callback1(t)
|
||||
return self.callback2(t) if self.cond(t2) else t2
|
||||
|
||||
|
||||
def _get_match(re_, regexp, s, flags):
|
||||
m = re_.match(regexp, s, flags)
|
||||
if m:
|
||||
return m.group(0)
|
||||
|
||||
def _create_unless(terminals, g_regex_flags, re_, use_bytes):
|
||||
tokens_by_type = classify(terminals, lambda t: type(t.pattern))
|
||||
assert len(tokens_by_type) <= 2, tokens_by_type.keys()
|
||||
embedded_strs = set()
|
||||
callback = {}
|
||||
for retok in tokens_by_type.get(PatternRE, []):
|
||||
unless = []
|
||||
for strtok in tokens_by_type.get(PatternStr, []):
|
||||
if strtok.priority != retok.priority:
|
||||
continue
|
||||
s = strtok.pattern.value
|
||||
if s == _get_match(re_, retok.pattern.to_regexp(), s, g_regex_flags):
|
||||
unless.append(strtok)
|
||||
if strtok.pattern.flags <= retok.pattern.flags:
|
||||
embedded_strs.add(strtok)
|
||||
if unless:
|
||||
callback[retok.name] = UnlessCallback(Scanner(unless, g_regex_flags, re_, match_whole=True, use_bytes=use_bytes))
|
||||
|
||||
new_terminals = [t for t in terminals if t not in embedded_strs]
|
||||
return new_terminals, callback
|
||||
|
||||
|
||||
class Scanner:
|
||||
def __init__(self, terminals, g_regex_flags, re_, use_bytes, match_whole=False):
|
||||
self.terminals = terminals
|
||||
self.g_regex_flags = g_regex_flags
|
||||
self.re_ = re_
|
||||
self.use_bytes = use_bytes
|
||||
self.match_whole = match_whole
|
||||
|
||||
self.allowed_types = {t.name for t in self.terminals}
|
||||
|
||||
self._mres = self._build_mres(terminals, len(terminals))
|
||||
|
||||
def _build_mres(self, terminals, max_size):
|
||||
# Python sets an unreasonable group limit (currently 100) in its re module
|
||||
# Worse, the only way to know we reached it is by catching an AssertionError!
|
||||
# This function recursively tries less and less groups until it's successful.
|
||||
postfix = '$' if self.match_whole else ''
|
||||
mres = []
|
||||
while terminals:
|
||||
pattern = u'|'.join(u'(?P<%s>%s)' % (t.name, t.pattern.to_regexp() + postfix) for t in terminals[:max_size])
|
||||
if self.use_bytes:
|
||||
pattern = pattern.encode('latin-1')
|
||||
try:
|
||||
mre = self.re_.compile(pattern, self.g_regex_flags)
|
||||
except AssertionError: # Yes, this is what Python provides us.. :/
|
||||
return self._build_mres(terminals, max_size//2)
|
||||
|
||||
mres.append(mre)
|
||||
terminals = terminals[max_size:]
|
||||
return mres
|
||||
|
||||
def match(self, text, pos):
|
||||
for mre in self._mres:
|
||||
m = mre.match(text, pos)
|
||||
if m:
|
||||
return m.group(0), m.lastgroup
|
||||
|
||||
|
||||
def _regexp_has_newline(r: str):
|
||||
r"""Expressions that may indicate newlines in a regexp:
|
||||
- newlines (\n)
|
||||
- escaped newline (\\n)
|
||||
- anything but ([^...])
|
||||
- any-char (.) when the flag (?s) exists
|
||||
- spaces (\s)
|
||||
"""
|
||||
return '\n' in r or '\\n' in r or '\\s' in r or '[^' in r or ('(?s' in r and '.' in r)
|
||||
|
||||
|
||||
class LexerState:
|
||||
"""Represents the current state of the lexer as it scans the text
|
||||
(Lexer objects are only instanciated per grammar, not per text)
|
||||
"""
|
||||
|
||||
__slots__ = 'text', 'line_ctr', 'last_token'
|
||||
|
||||
def __init__(self, text, line_ctr=None, last_token=None):
|
||||
self.text = text
|
||||
self.line_ctr = line_ctr or LineCounter(b'\n' if isinstance(text, bytes) else '\n')
|
||||
self.last_token = last_token
|
||||
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, LexerState):
|
||||
return NotImplemented
|
||||
|
||||
return self.text is other.text and self.line_ctr == other.line_ctr and self.last_token == other.last_token
|
||||
|
||||
def __copy__(self):
|
||||
return type(self)(self.text, copy(self.line_ctr), self.last_token)
|
||||
|
||||
|
||||
class LexerThread:
|
||||
"""A thread that ties a lexer instance and a lexer state, to be used by the parser
|
||||
"""
|
||||
|
||||
def __init__(self, lexer: 'Lexer', lexer_state: LexerState):
|
||||
self.lexer = lexer
|
||||
self.state = lexer_state
|
||||
|
||||
@classmethod
|
||||
def from_text(cls, lexer: 'Lexer', text: str):
|
||||
return cls(lexer, LexerState(text))
|
||||
|
||||
def lex(self, parser_state):
|
||||
return self.lexer.lex(self.state, parser_state)
|
||||
|
||||
def __copy__(self):
|
||||
return type(self)(self.lexer, copy(self.state))
|
||||
|
||||
_Token = Token
|
||||
|
||||
|
||||
_Callback = Callable[[Token], Token]
|
||||
|
||||
class Lexer(ABC):
|
||||
"""Lexer interface
|
||||
|
||||
Method Signatures:
|
||||
lex(self, lexer_state, parser_state) -> Iterator[Token]
|
||||
"""
|
||||
@abstractmethod
|
||||
def lex(self, lexer_state: LexerState, parser_state: Any) -> Iterator[Token]:
|
||||
return NotImplemented
|
||||
|
||||
def make_lexer_state(self, text):
|
||||
"Deprecated"
|
||||
return LexerState(text)
|
||||
|
||||
|
||||
class BasicLexer(Lexer):
|
||||
|
||||
terminals: Collection[TerminalDef]
|
||||
ignore_types: FrozenSet[str]
|
||||
newline_types: FrozenSet[str]
|
||||
user_callbacks: Dict[str, _Callback]
|
||||
callback: Dict[str, _Callback]
|
||||
re: ModuleType
|
||||
|
||||
def __init__(self, conf: 'LexerConf') -> None:
|
||||
terminals = list(conf.terminals)
|
||||
assert all(isinstance(t, TerminalDef) for t in terminals), terminals
|
||||
|
||||
self.re = conf.re_module
|
||||
|
||||
if not conf.skip_validation:
|
||||
# Sanitization
|
||||
for t in terminals:
|
||||
try:
|
||||
self.re.compile(t.pattern.to_regexp(), conf.g_regex_flags)
|
||||
except self.re.error:
|
||||
raise LexError("Cannot compile token %s: %s" % (t.name, t.pattern))
|
||||
|
||||
if t.pattern.min_width == 0:
|
||||
raise LexError("Lexer does not allow zero-width terminals. (%s: %s)" % (t.name, t.pattern))
|
||||
|
||||
if not (set(conf.ignore) <= {t.name for t in terminals}):
|
||||
raise LexError("Ignore terminals are not defined: %s" % (set(conf.ignore) - {t.name for t in terminals}))
|
||||
|
||||
# Init
|
||||
self.newline_types = frozenset(t.name for t in terminals if _regexp_has_newline(t.pattern.to_regexp()))
|
||||
self.ignore_types = frozenset(conf.ignore)
|
||||
|
||||
terminals.sort(key=lambda x: (-x.priority, -x.pattern.max_width, -len(x.pattern.value), x.name))
|
||||
self.terminals = terminals
|
||||
self.user_callbacks = conf.callbacks
|
||||
self.g_regex_flags = conf.g_regex_flags
|
||||
self.use_bytes = conf.use_bytes
|
||||
self.terminals_by_name = conf.terminals_by_name
|
||||
|
||||
self._scanner = None
|
||||
|
||||
def _build_scanner(self):
|
||||
terminals, self.callback = _create_unless(self.terminals, self.g_regex_flags, self.re, self.use_bytes)
|
||||
assert all(self.callback.values())
|
||||
|
||||
for type_, f in self.user_callbacks.items():
|
||||
if type_ in self.callback:
|
||||
# Already a callback there, probably UnlessCallback
|
||||
self.callback[type_] = CallChain(self.callback[type_], f, lambda t: t.type == type_)
|
||||
else:
|
||||
self.callback[type_] = f
|
||||
|
||||
self._scanner = Scanner(terminals, self.g_regex_flags, self.re, self.use_bytes)
|
||||
|
||||
@property
|
||||
def scanner(self):
|
||||
if self._scanner is None:
|
||||
self._build_scanner()
|
||||
return self._scanner
|
||||
|
||||
def match(self, text, pos):
|
||||
return self.scanner.match(text, pos)
|
||||
|
||||
def lex(self, state: LexerState, parser_state: Any) -> Iterator[Token]:
|
||||
with suppress(EOFError):
|
||||
while True:
|
||||
yield self.next_token(state, parser_state)
|
||||
|
||||
def next_token(self, lex_state: LexerState, parser_state: Any=None) -> Token:
|
||||
line_ctr = lex_state.line_ctr
|
||||
while line_ctr.char_pos < len(lex_state.text):
|
||||
res = self.match(lex_state.text, line_ctr.char_pos)
|
||||
if not res:
|
||||
allowed = self.scanner.allowed_types - self.ignore_types
|
||||
if not allowed:
|
||||
allowed = {"<END-OF-FILE>"}
|
||||
raise UnexpectedCharacters(lex_state.text, line_ctr.char_pos, line_ctr.line, line_ctr.column,
|
||||
allowed=allowed, token_history=lex_state.last_token and [lex_state.last_token],
|
||||
state=parser_state, terminals_by_name=self.terminals_by_name)
|
||||
|
||||
value, type_ = res
|
||||
|
||||
if type_ not in self.ignore_types:
|
||||
t = Token(type_, value, line_ctr.char_pos, line_ctr.line, line_ctr.column)
|
||||
line_ctr.feed(value, type_ in self.newline_types)
|
||||
t.end_line = line_ctr.line
|
||||
t.end_column = line_ctr.column
|
||||
t.end_pos = line_ctr.char_pos
|
||||
if t.type in self.callback:
|
||||
t = self.callback[t.type](t)
|
||||
if not isinstance(t, Token):
|
||||
raise LexError("Callbacks must return a token (returned %r)" % t)
|
||||
lex_state.last_token = t
|
||||
return t
|
||||
else:
|
||||
if type_ in self.callback:
|
||||
t2 = Token(type_, value, line_ctr.char_pos, line_ctr.line, line_ctr.column)
|
||||
self.callback[type_](t2)
|
||||
line_ctr.feed(value, type_ in self.newline_types)
|
||||
|
||||
# EOF
|
||||
raise EOFError(self)
|
||||
|
||||
|
||||
class ContextualLexer(Lexer):
|
||||
|
||||
lexers: Dict[str, BasicLexer]
|
||||
root_lexer: BasicLexer
|
||||
|
||||
def __init__(self, conf: 'LexerConf', states: Dict[str, Collection[str]], always_accept: Collection[str]=()) -> None:
|
||||
terminals = list(conf.terminals)
|
||||
terminals_by_name = conf.terminals_by_name
|
||||
|
||||
trad_conf = copy(conf)
|
||||
trad_conf.terminals = terminals
|
||||
|
||||
lexer_by_tokens: Dict[FrozenSet[str], BasicLexer] = {}
|
||||
self.lexers = {}
|
||||
for state, accepts in states.items():
|
||||
key = frozenset(accepts)
|
||||
try:
|
||||
lexer = lexer_by_tokens[key]
|
||||
except KeyError:
|
||||
accepts = set(accepts) | set(conf.ignore) | set(always_accept)
|
||||
lexer_conf = copy(trad_conf)
|
||||
lexer_conf.terminals = [terminals_by_name[n] for n in accepts if n in terminals_by_name]
|
||||
lexer = BasicLexer(lexer_conf)
|
||||
lexer_by_tokens[key] = lexer
|
||||
|
||||
self.lexers[state] = lexer
|
||||
|
||||
assert trad_conf.terminals is terminals
|
||||
self.root_lexer = BasicLexer(trad_conf)
|
||||
|
||||
def lex(self, lexer_state: LexerState, parser_state: Any) -> Iterator[Token]:
|
||||
try:
|
||||
while True:
|
||||
lexer = self.lexers[parser_state.position]
|
||||
yield lexer.next_token(lexer_state, parser_state)
|
||||
except EOFError:
|
||||
pass
|
||||
except UnexpectedCharacters as e:
|
||||
# In the contextual lexer, UnexpectedCharacters can mean that the terminal is defined, but not in the current context.
|
||||
# This tests the input against the global context, to provide a nicer error.
|
||||
try:
|
||||
last_token = lexer_state.last_token # Save last_token. Calling root_lexer.next_token will change this to the wrong token
|
||||
token = self.root_lexer.next_token(lexer_state, parser_state)
|
||||
raise UnexpectedToken(token, e.allowed, state=parser_state, token_history=[last_token], terminals_by_name=self.root_lexer.terminals_by_name)
|
||||
except UnexpectedCharacters:
|
||||
raise e # Raise the original UnexpectedCharacters. The root lexer raises it with the wrong expected set.
|
||||
|
||||
###}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,387 @@
|
|||
from typing import List
|
||||
|
||||
from .exceptions import GrammarError, ConfigurationError
|
||||
from .lexer import Token
|
||||
from .tree import Tree
|
||||
from .visitors import Transformer_InPlace
|
||||
from .visitors import _vargs_meta, _vargs_meta_inline
|
||||
|
||||
###{standalone
|
||||
from functools import partial, wraps
|
||||
from itertools import repeat, product
|
||||
|
||||
|
||||
class ExpandSingleChild:
|
||||
def __init__(self, node_builder):
|
||||
self.node_builder = node_builder
|
||||
|
||||
def __call__(self, children):
|
||||
if len(children) == 1:
|
||||
return children[0]
|
||||
else:
|
||||
return self.node_builder(children)
|
||||
|
||||
|
||||
|
||||
class PropagatePositions:
|
||||
def __init__(self, node_builder, node_filter=None):
|
||||
self.node_builder = node_builder
|
||||
self.node_filter = node_filter
|
||||
|
||||
def __call__(self, children):
|
||||
res = self.node_builder(children)
|
||||
|
||||
if isinstance(res, Tree):
|
||||
# Calculate positions while the tree is streaming, according to the rule:
|
||||
# - nodes start at the start of their first child's container,
|
||||
# and end at the end of their last child's container.
|
||||
# Containers are nodes that take up space in text, but have been inlined in the tree.
|
||||
|
||||
res_meta = res.meta
|
||||
|
||||
first_meta = self._pp_get_meta(children)
|
||||
if first_meta is not None:
|
||||
if not hasattr(res_meta, 'line'):
|
||||
# meta was already set, probably because the rule has been inlined (e.g. `?rule`)
|
||||
res_meta.line = getattr(first_meta, 'container_line', first_meta.line)
|
||||
res_meta.column = getattr(first_meta, 'container_column', first_meta.column)
|
||||
res_meta.start_pos = getattr(first_meta, 'container_start_pos', first_meta.start_pos)
|
||||
res_meta.empty = False
|
||||
|
||||
res_meta.container_line = getattr(first_meta, 'container_line', first_meta.line)
|
||||
res_meta.container_column = getattr(first_meta, 'container_column', first_meta.column)
|
||||
|
||||
last_meta = self._pp_get_meta(reversed(children))
|
||||
if last_meta is not None:
|
||||
if not hasattr(res_meta, 'end_line'):
|
||||
res_meta.end_line = getattr(last_meta, 'container_end_line', last_meta.end_line)
|
||||
res_meta.end_column = getattr(last_meta, 'container_end_column', last_meta.end_column)
|
||||
res_meta.end_pos = getattr(last_meta, 'container_end_pos', last_meta.end_pos)
|
||||
res_meta.empty = False
|
||||
|
||||
res_meta.container_end_line = getattr(last_meta, 'container_end_line', last_meta.end_line)
|
||||
res_meta.container_end_column = getattr(last_meta, 'container_end_column', last_meta.end_column)
|
||||
|
||||
return res
|
||||
|
||||
def _pp_get_meta(self, children):
|
||||
for c in children:
|
||||
if self.node_filter is not None and not self.node_filter(c):
|
||||
continue
|
||||
if isinstance(c, Tree):
|
||||
if not c.meta.empty:
|
||||
return c.meta
|
||||
elif isinstance(c, Token):
|
||||
return c
|
||||
elif hasattr(c, '__lark_meta__'):
|
||||
return c.__lark_meta__()
|
||||
|
||||
def make_propagate_positions(option):
|
||||
if callable(option):
|
||||
return partial(PropagatePositions, node_filter=option)
|
||||
elif option is True:
|
||||
return PropagatePositions
|
||||
elif option is False:
|
||||
return None
|
||||
|
||||
raise ConfigurationError('Invalid option for propagate_positions: %r' % option)
|
||||
|
||||
|
||||
class ChildFilter:
|
||||
def __init__(self, to_include, append_none, node_builder):
|
||||
self.node_builder = node_builder
|
||||
self.to_include = to_include
|
||||
self.append_none = append_none
|
||||
|
||||
def __call__(self, children):
|
||||
filtered = []
|
||||
|
||||
for i, to_expand, add_none in self.to_include:
|
||||
if add_none:
|
||||
filtered += [None] * add_none
|
||||
if to_expand:
|
||||
filtered += children[i].children
|
||||
else:
|
||||
filtered.append(children[i])
|
||||
|
||||
if self.append_none:
|
||||
filtered += [None] * self.append_none
|
||||
|
||||
return self.node_builder(filtered)
|
||||
|
||||
|
||||
class ChildFilterLALR(ChildFilter):
|
||||
"""Optimized childfilter for LALR (assumes no duplication in parse tree, so it's safe to change it)"""
|
||||
|
||||
def __call__(self, children):
|
||||
filtered = []
|
||||
for i, to_expand, add_none in self.to_include:
|
||||
if add_none:
|
||||
filtered += [None] * add_none
|
||||
if to_expand:
|
||||
if filtered:
|
||||
filtered += children[i].children
|
||||
else: # Optimize for left-recursion
|
||||
filtered = children[i].children
|
||||
else:
|
||||
filtered.append(children[i])
|
||||
|
||||
if self.append_none:
|
||||
filtered += [None] * self.append_none
|
||||
|
||||
return self.node_builder(filtered)
|
||||
|
||||
|
||||
class ChildFilterLALR_NoPlaceholders(ChildFilter):
|
||||
"Optimized childfilter for LALR (assumes no duplication in parse tree, so it's safe to change it)"
|
||||
def __init__(self, to_include, node_builder):
|
||||
self.node_builder = node_builder
|
||||
self.to_include = to_include
|
||||
|
||||
def __call__(self, children):
|
||||
filtered = []
|
||||
for i, to_expand in self.to_include:
|
||||
if to_expand:
|
||||
if filtered:
|
||||
filtered += children[i].children
|
||||
else: # Optimize for left-recursion
|
||||
filtered = children[i].children
|
||||
else:
|
||||
filtered.append(children[i])
|
||||
return self.node_builder(filtered)
|
||||
|
||||
|
||||
def _should_expand(sym):
|
||||
return not sym.is_term and sym.name.startswith('_')
|
||||
|
||||
|
||||
def maybe_create_child_filter(expansion, keep_all_tokens, ambiguous, _empty_indices: List[bool]):
|
||||
# Prepare empty_indices as: How many Nones to insert at each index?
|
||||
if _empty_indices:
|
||||
assert _empty_indices.count(False) == len(expansion)
|
||||
s = ''.join(str(int(b)) for b in _empty_indices)
|
||||
empty_indices = [len(ones) for ones in s.split('0')]
|
||||
assert len(empty_indices) == len(expansion)+1, (empty_indices, len(expansion))
|
||||
else:
|
||||
empty_indices = [0] * (len(expansion)+1)
|
||||
|
||||
to_include = []
|
||||
nones_to_add = 0
|
||||
for i, sym in enumerate(expansion):
|
||||
nones_to_add += empty_indices[i]
|
||||
if keep_all_tokens or not (sym.is_term and sym.filter_out):
|
||||
to_include.append((i, _should_expand(sym), nones_to_add))
|
||||
nones_to_add = 0
|
||||
|
||||
nones_to_add += empty_indices[len(expansion)]
|
||||
|
||||
if _empty_indices or len(to_include) < len(expansion) or any(to_expand for i, to_expand,_ in to_include):
|
||||
if _empty_indices or ambiguous:
|
||||
return partial(ChildFilter if ambiguous else ChildFilterLALR, to_include, nones_to_add)
|
||||
else:
|
||||
# LALR without placeholders
|
||||
return partial(ChildFilterLALR_NoPlaceholders, [(i, x) for i,x,_ in to_include])
|
||||
|
||||
|
||||
class AmbiguousExpander:
|
||||
"""Deal with the case where we're expanding children ('_rule') into a parent but the children
|
||||
are ambiguous. i.e. (parent->_ambig->_expand_this_rule). In this case, make the parent itself
|
||||
ambiguous with as many copies as their are ambiguous children, and then copy the ambiguous children
|
||||
into the right parents in the right places, essentially shifting the ambiguity up the tree."""
|
||||
def __init__(self, to_expand, tree_class, node_builder):
|
||||
self.node_builder = node_builder
|
||||
self.tree_class = tree_class
|
||||
self.to_expand = to_expand
|
||||
|
||||
def __call__(self, children):
|
||||
def _is_ambig_tree(t):
|
||||
return hasattr(t, 'data') and t.data == '_ambig'
|
||||
|
||||
# -- When we're repeatedly expanding ambiguities we can end up with nested ambiguities.
|
||||
# All children of an _ambig node should be a derivation of that ambig node, hence
|
||||
# it is safe to assume that if we see an _ambig node nested within an ambig node
|
||||
# it is safe to simply expand it into the parent _ambig node as an alternative derivation.
|
||||
ambiguous = []
|
||||
for i, child in enumerate(children):
|
||||
if _is_ambig_tree(child):
|
||||
if i in self.to_expand:
|
||||
ambiguous.append(i)
|
||||
|
||||
child.expand_kids_by_data('_ambig')
|
||||
|
||||
if not ambiguous:
|
||||
return self.node_builder(children)
|
||||
|
||||
expand = [iter(child.children) if i in ambiguous else repeat(child) for i, child in enumerate(children)]
|
||||
return self.tree_class('_ambig', [self.node_builder(list(f[0])) for f in product(zip(*expand))])
|
||||
|
||||
|
||||
def maybe_create_ambiguous_expander(tree_class, expansion, keep_all_tokens):
|
||||
to_expand = [i for i, sym in enumerate(expansion)
|
||||
if keep_all_tokens or ((not (sym.is_term and sym.filter_out)) and _should_expand(sym))]
|
||||
if to_expand:
|
||||
return partial(AmbiguousExpander, to_expand, tree_class)
|
||||
|
||||
|
||||
class AmbiguousIntermediateExpander:
|
||||
"""
|
||||
Propagate ambiguous intermediate nodes and their derivations up to the
|
||||
current rule.
|
||||
|
||||
In general, converts
|
||||
|
||||
rule
|
||||
_iambig
|
||||
_inter
|
||||
someChildren1
|
||||
...
|
||||
_inter
|
||||
someChildren2
|
||||
...
|
||||
someChildren3
|
||||
...
|
||||
|
||||
to
|
||||
|
||||
_ambig
|
||||
rule
|
||||
someChildren1
|
||||
...
|
||||
someChildren3
|
||||
...
|
||||
rule
|
||||
someChildren2
|
||||
...
|
||||
someChildren3
|
||||
...
|
||||
rule
|
||||
childrenFromNestedIambigs
|
||||
...
|
||||
someChildren3
|
||||
...
|
||||
...
|
||||
|
||||
propagating up any nested '_iambig' nodes along the way.
|
||||
"""
|
||||
|
||||
def __init__(self, tree_class, node_builder):
|
||||
self.node_builder = node_builder
|
||||
self.tree_class = tree_class
|
||||
|
||||
def __call__(self, children):
|
||||
def _is_iambig_tree(child):
|
||||
return hasattr(child, 'data') and child.data == '_iambig'
|
||||
|
||||
def _collapse_iambig(children):
|
||||
"""
|
||||
Recursively flatten the derivations of the parent of an '_iambig'
|
||||
node. Returns a list of '_inter' nodes guaranteed not
|
||||
to contain any nested '_iambig' nodes, or None if children does
|
||||
not contain an '_iambig' node.
|
||||
"""
|
||||
|
||||
# Due to the structure of the SPPF,
|
||||
# an '_iambig' node can only appear as the first child
|
||||
if children and _is_iambig_tree(children[0]):
|
||||
iambig_node = children[0]
|
||||
result = []
|
||||
for grandchild in iambig_node.children:
|
||||
collapsed = _collapse_iambig(grandchild.children)
|
||||
if collapsed:
|
||||
for child in collapsed:
|
||||
child.children += children[1:]
|
||||
result += collapsed
|
||||
else:
|
||||
new_tree = self.tree_class('_inter', grandchild.children + children[1:])
|
||||
result.append(new_tree)
|
||||
return result
|
||||
|
||||
collapsed = _collapse_iambig(children)
|
||||
if collapsed:
|
||||
processed_nodes = [self.node_builder(c.children) for c in collapsed]
|
||||
return self.tree_class('_ambig', processed_nodes)
|
||||
|
||||
return self.node_builder(children)
|
||||
|
||||
|
||||
|
||||
def inplace_transformer(func):
|
||||
@wraps(func)
|
||||
def f(children):
|
||||
# function name in a Transformer is a rule name.
|
||||
tree = Tree(func.__name__, children)
|
||||
return func(tree)
|
||||
return f
|
||||
|
||||
|
||||
def apply_visit_wrapper(func, name, wrapper):
|
||||
if wrapper is _vargs_meta or wrapper is _vargs_meta_inline:
|
||||
raise NotImplementedError("Meta args not supported for internal transformer")
|
||||
|
||||
@wraps(func)
|
||||
def f(children):
|
||||
return wrapper(func, name, children, None)
|
||||
return f
|
||||
|
||||
|
||||
class ParseTreeBuilder:
|
||||
def __init__(self, rules, tree_class, propagate_positions=False, ambiguous=False, maybe_placeholders=False):
|
||||
self.tree_class = tree_class
|
||||
self.propagate_positions = propagate_positions
|
||||
self.ambiguous = ambiguous
|
||||
self.maybe_placeholders = maybe_placeholders
|
||||
|
||||
self.rule_builders = list(self._init_builders(rules))
|
||||
|
||||
def _init_builders(self, rules):
|
||||
propagate_positions = make_propagate_positions(self.propagate_positions)
|
||||
|
||||
for rule in rules:
|
||||
options = rule.options
|
||||
keep_all_tokens = options.keep_all_tokens
|
||||
expand_single_child = options.expand1
|
||||
|
||||
wrapper_chain = list(filter(None, [
|
||||
(expand_single_child and not rule.alias) and ExpandSingleChild,
|
||||
maybe_create_child_filter(rule.expansion, keep_all_tokens, self.ambiguous, options.empty_indices if self.maybe_placeholders else None),
|
||||
propagate_positions,
|
||||
self.ambiguous and maybe_create_ambiguous_expander(self.tree_class, rule.expansion, keep_all_tokens),
|
||||
self.ambiguous and partial(AmbiguousIntermediateExpander, self.tree_class)
|
||||
]))
|
||||
|
||||
yield rule, wrapper_chain
|
||||
|
||||
def create_callback(self, transformer=None):
|
||||
callbacks = {}
|
||||
|
||||
default_handler = getattr(transformer, '__default__', None)
|
||||
if default_handler:
|
||||
def default_callback(data, children):
|
||||
return default_handler(data, children, None)
|
||||
else:
|
||||
default_callback = self.tree_class
|
||||
|
||||
for rule, wrapper_chain in self.rule_builders:
|
||||
|
||||
user_callback_name = rule.alias or rule.options.template_source or rule.origin.name
|
||||
try:
|
||||
f = getattr(transformer, user_callback_name)
|
||||
wrapper = getattr(f, 'visit_wrapper', None)
|
||||
if wrapper is not None:
|
||||
f = apply_visit_wrapper(f, user_callback_name, wrapper)
|
||||
elif isinstance(transformer, Transformer_InPlace):
|
||||
f = inplace_transformer(f)
|
||||
except AttributeError:
|
||||
f = partial(default_callback, user_callback_name)
|
||||
|
||||
for w in wrapper_chain:
|
||||
f = w(f)
|
||||
|
||||
if rule in callbacks:
|
||||
raise GrammarError("Rule '%s' already exists" % (rule,))
|
||||
|
||||
callbacks[rule] = f
|
||||
|
||||
return callbacks
|
||||
|
||||
###}
|
||||
|
|
@ -0,0 +1,245 @@
|
|||
from typing import Any, Callable, Dict, Tuple
|
||||
|
||||
from .exceptions import ConfigurationError, GrammarError, assert_config
|
||||
from .utils import get_regexp_width, Serialize
|
||||
from .parsers.grammar_analysis import GrammarAnalyzer
|
||||
from .lexer import LexerThread, BasicLexer, ContextualLexer, Lexer
|
||||
from .parsers import earley, xearley, cyk
|
||||
from .parsers.lalr_parser import LALR_Parser
|
||||
from .tree import Tree
|
||||
from .common import LexerConf, ParserConf, _ParserArgType, _LexerArgType
|
||||
|
||||
###{standalone
|
||||
|
||||
def _wrap_lexer(lexer_class):
|
||||
future_interface = getattr(lexer_class, '__future_interface__', False)
|
||||
if future_interface:
|
||||
return lexer_class
|
||||
else:
|
||||
class CustomLexerWrapper(Lexer):
|
||||
def __init__(self, lexer_conf):
|
||||
self.lexer = lexer_class(lexer_conf)
|
||||
def lex(self, lexer_state, parser_state):
|
||||
return self.lexer.lex(lexer_state.text)
|
||||
return CustomLexerWrapper
|
||||
|
||||
|
||||
def _deserialize_parsing_frontend(data, memo, lexer_conf, callbacks, options):
|
||||
parser_conf = ParserConf.deserialize(data['parser_conf'], memo)
|
||||
cls = (options and options._plugins.get('LALR_Parser')) or LALR_Parser
|
||||
parser = cls.deserialize(data['parser'], memo, callbacks, options.debug)
|
||||
parser_conf.callbacks = callbacks
|
||||
return ParsingFrontend(lexer_conf, parser_conf, options, parser=parser)
|
||||
|
||||
|
||||
_parser_creators: 'Dict[str, Callable[[LexerConf, Any, Any], Any]]' = {}
|
||||
|
||||
|
||||
class ParsingFrontend(Serialize):
|
||||
__serialize_fields__ = 'lexer_conf', 'parser_conf', 'parser'
|
||||
|
||||
def __init__(self, lexer_conf, parser_conf, options, parser=None):
|
||||
self.parser_conf = parser_conf
|
||||
self.lexer_conf = lexer_conf
|
||||
self.options = options
|
||||
|
||||
# Set-up parser
|
||||
if parser: # From cache
|
||||
self.parser = parser
|
||||
else:
|
||||
create_parser = _parser_creators.get(parser_conf.parser_type)
|
||||
assert create_parser is not None, "{} is not supported in standalone mode".format(
|
||||
parser_conf.parser_type
|
||||
)
|
||||
self.parser = create_parser(lexer_conf, parser_conf, options)
|
||||
|
||||
# Set-up lexer
|
||||
lexer_type = lexer_conf.lexer_type
|
||||
self.skip_lexer = False
|
||||
if lexer_type in ('dynamic', 'dynamic_complete'):
|
||||
assert lexer_conf.postlex is None
|
||||
self.skip_lexer = True
|
||||
return
|
||||
|
||||
try:
|
||||
create_lexer = {
|
||||
'basic': create_basic_lexer,
|
||||
'contextual': create_contextual_lexer,
|
||||
}[lexer_type]
|
||||
except KeyError:
|
||||
assert issubclass(lexer_type, Lexer), lexer_type
|
||||
self.lexer = _wrap_lexer(lexer_type)(lexer_conf)
|
||||
else:
|
||||
self.lexer = create_lexer(lexer_conf, self.parser, lexer_conf.postlex, options)
|
||||
|
||||
if lexer_conf.postlex:
|
||||
self.lexer = PostLexConnector(self.lexer, lexer_conf.postlex)
|
||||
|
||||
def _verify_start(self, start=None):
|
||||
if start is None:
|
||||
start_decls = self.parser_conf.start
|
||||
if len(start_decls) > 1:
|
||||
raise ConfigurationError("Lark initialized with more than 1 possible start rule. Must specify which start rule to parse", start_decls)
|
||||
start ,= start_decls
|
||||
elif start not in self.parser_conf.start:
|
||||
raise ConfigurationError("Unknown start rule %s. Must be one of %r" % (start, self.parser_conf.start))
|
||||
return start
|
||||
|
||||
def _make_lexer_thread(self, text):
|
||||
cls = (self.options and self.options._plugins.get('LexerThread')) or LexerThread
|
||||
return text if self.skip_lexer else cls.from_text(self.lexer, text)
|
||||
|
||||
def parse(self, text, start=None, on_error=None):
|
||||
chosen_start = self._verify_start(start)
|
||||
kw = {} if on_error is None else {'on_error': on_error}
|
||||
stream = self._make_lexer_thread(text)
|
||||
return self.parser.parse(stream, chosen_start, **kw)
|
||||
|
||||
def parse_interactive(self, text=None, start=None):
|
||||
chosen_start = self._verify_start(start)
|
||||
if self.parser_conf.parser_type != 'lalr':
|
||||
raise ConfigurationError("parse_interactive() currently only works with parser='lalr' ")
|
||||
stream = self._make_lexer_thread(text)
|
||||
return self.parser.parse_interactive(stream, chosen_start)
|
||||
|
||||
|
||||
def _validate_frontend_args(parser, lexer) -> None:
|
||||
assert_config(parser, ('lalr', 'earley', 'cyk'))
|
||||
if not isinstance(lexer, type): # not custom lexer?
|
||||
expected = {
|
||||
'lalr': ('basic', 'contextual'),
|
||||
'earley': ('basic', 'dynamic', 'dynamic_complete'),
|
||||
'cyk': ('basic', ),
|
||||
}[parser]
|
||||
assert_config(lexer, expected, 'Parser %r does not support lexer %%r, expected one of %%s' % parser)
|
||||
|
||||
|
||||
def _get_lexer_callbacks(transformer, terminals):
|
||||
result = {}
|
||||
for terminal in terminals:
|
||||
callback = getattr(transformer, terminal.name, None)
|
||||
if callback is not None:
|
||||
result[terminal.name] = callback
|
||||
return result
|
||||
|
||||
class PostLexConnector:
|
||||
def __init__(self, lexer, postlexer):
|
||||
self.lexer = lexer
|
||||
self.postlexer = postlexer
|
||||
|
||||
def lex(self, lexer_state, parser_state):
|
||||
i = self.lexer.lex(lexer_state, parser_state)
|
||||
return self.postlexer.process(i)
|
||||
|
||||
|
||||
|
||||
def create_basic_lexer(lexer_conf, parser, postlex, options):
|
||||
cls = (options and options._plugins.get('BasicLexer')) or BasicLexer
|
||||
return cls(lexer_conf)
|
||||
|
||||
def create_contextual_lexer(lexer_conf, parser, postlex, options):
|
||||
cls = (options and options._plugins.get('ContextualLexer')) or ContextualLexer
|
||||
states = {idx:list(t.keys()) for idx, t in parser._parse_table.states.items()}
|
||||
always_accept = postlex.always_accept if postlex else ()
|
||||
return cls(lexer_conf, states, always_accept=always_accept)
|
||||
|
||||
def create_lalr_parser(lexer_conf, parser_conf, options=None):
|
||||
debug = options.debug if options else False
|
||||
cls = (options and options._plugins.get('LALR_Parser')) or LALR_Parser
|
||||
return cls(parser_conf, debug=debug)
|
||||
|
||||
_parser_creators['lalr'] = create_lalr_parser
|
||||
|
||||
###}
|
||||
|
||||
class EarleyRegexpMatcher:
|
||||
def __init__(self, lexer_conf):
|
||||
self.regexps = {}
|
||||
for t in lexer_conf.terminals:
|
||||
regexp = t.pattern.to_regexp()
|
||||
try:
|
||||
width = get_regexp_width(regexp)[0]
|
||||
except ValueError:
|
||||
raise GrammarError("Bad regexp in token %s: %s" % (t.name, regexp))
|
||||
else:
|
||||
if width == 0:
|
||||
raise GrammarError("Dynamic Earley doesn't allow zero-width regexps", t)
|
||||
if lexer_conf.use_bytes:
|
||||
regexp = regexp.encode('utf-8')
|
||||
|
||||
self.regexps[t.name] = lexer_conf.re_module.compile(regexp, lexer_conf.g_regex_flags)
|
||||
|
||||
def match(self, term, text, index=0):
|
||||
return self.regexps[term.name].match(text, index)
|
||||
|
||||
|
||||
def create_earley_parser__dynamic(lexer_conf, parser_conf, options=None, **kw):
|
||||
if lexer_conf.callbacks:
|
||||
raise GrammarError("Earley's dynamic lexer doesn't support lexer_callbacks.")
|
||||
|
||||
earley_matcher = EarleyRegexpMatcher(lexer_conf)
|
||||
return xearley.Parser(lexer_conf, parser_conf, earley_matcher.match, **kw)
|
||||
|
||||
def _match_earley_basic(term, token):
|
||||
return term.name == token.type
|
||||
|
||||
def create_earley_parser__basic(lexer_conf, parser_conf, options, **kw):
|
||||
return earley.Parser(lexer_conf, parser_conf, _match_earley_basic, **kw)
|
||||
|
||||
def create_earley_parser(lexer_conf, parser_conf, options):
|
||||
resolve_ambiguity = options.ambiguity == 'resolve'
|
||||
debug = options.debug if options else False
|
||||
tree_class = options.tree_class or Tree if options.ambiguity != 'forest' else None
|
||||
|
||||
extra = {}
|
||||
if lexer_conf.lexer_type == 'dynamic':
|
||||
f = create_earley_parser__dynamic
|
||||
elif lexer_conf.lexer_type == 'dynamic_complete':
|
||||
extra['complete_lex'] =True
|
||||
f = create_earley_parser__dynamic
|
||||
else:
|
||||
f = create_earley_parser__basic
|
||||
|
||||
return f(lexer_conf, parser_conf, options, resolve_ambiguity=resolve_ambiguity, debug=debug, tree_class=tree_class, **extra)
|
||||
|
||||
|
||||
|
||||
class CYK_FrontEnd:
|
||||
def __init__(self, lexer_conf, parser_conf, options=None):
|
||||
self._analysis = GrammarAnalyzer(parser_conf)
|
||||
self.parser = cyk.Parser(parser_conf.rules)
|
||||
|
||||
self.callbacks = parser_conf.callbacks
|
||||
|
||||
def parse(self, lexer_thread, start):
|
||||
tokens = list(lexer_thread.lex(None))
|
||||
tree = self.parser.parse(tokens, start)
|
||||
return self._transform(tree)
|
||||
|
||||
def _transform(self, tree):
|
||||
subtrees = list(tree.iter_subtrees())
|
||||
for subtree in subtrees:
|
||||
subtree.children = [self._apply_callback(c) if isinstance(c, Tree) else c for c in subtree.children]
|
||||
|
||||
return self._apply_callback(tree)
|
||||
|
||||
def _apply_callback(self, tree):
|
||||
return self.callbacks[tree.rule](tree.children)
|
||||
|
||||
|
||||
_parser_creators['earley'] = create_earley_parser
|
||||
_parser_creators['cyk'] = CYK_FrontEnd
|
||||
|
||||
|
||||
def _construct_parsing_frontend(
|
||||
parser_type: _ParserArgType,
|
||||
lexer_type: _LexerArgType,
|
||||
lexer_conf,
|
||||
parser_conf,
|
||||
options
|
||||
):
|
||||
assert isinstance(lexer_conf, LexerConf)
|
||||
assert isinstance(parser_conf, ParserConf)
|
||||
parser_conf.parser_type = parser_type
|
||||
lexer_conf.lexer_type = lexer_type
|
||||
return ParsingFrontend(lexer_conf, parser_conf, options)
|
||||
|
|
@ -0,0 +1,345 @@
|
|||
"""This module implements a CYK parser."""
|
||||
|
||||
# Author: https://github.com/ehudt (2018)
|
||||
#
|
||||
# Adapted by Erez
|
||||
|
||||
|
||||
from collections import defaultdict
|
||||
import itertools
|
||||
|
||||
from ..exceptions import ParseError
|
||||
from ..lexer import Token
|
||||
from ..tree import Tree
|
||||
from ..grammar import Terminal as T, NonTerminal as NT, Symbol
|
||||
|
||||
try:
|
||||
xrange
|
||||
except NameError:
|
||||
xrange = range
|
||||
|
||||
def match(t, s):
|
||||
assert isinstance(t, T)
|
||||
return t.name == s.type
|
||||
|
||||
|
||||
class Rule:
|
||||
"""Context-free grammar rule."""
|
||||
|
||||
def __init__(self, lhs, rhs, weight, alias):
|
||||
super(Rule, self).__init__()
|
||||
assert isinstance(lhs, NT), lhs
|
||||
assert all(isinstance(x, NT) or isinstance(x, T) for x in rhs), rhs
|
||||
self.lhs = lhs
|
||||
self.rhs = rhs
|
||||
self.weight = weight
|
||||
self.alias = alias
|
||||
|
||||
def __str__(self):
|
||||
return '%s -> %s' % (str(self.lhs), ' '.join(str(x) for x in self.rhs))
|
||||
|
||||
def __repr__(self):
|
||||
return str(self)
|
||||
|
||||
def __hash__(self):
|
||||
return hash((self.lhs, tuple(self.rhs)))
|
||||
|
||||
def __eq__(self, other):
|
||||
return self.lhs == other.lhs and self.rhs == other.rhs
|
||||
|
||||
def __ne__(self, other):
|
||||
return not (self == other)
|
||||
|
||||
|
||||
class Grammar:
|
||||
"""Context-free grammar."""
|
||||
|
||||
def __init__(self, rules):
|
||||
self.rules = frozenset(rules)
|
||||
|
||||
def __eq__(self, other):
|
||||
return self.rules == other.rules
|
||||
|
||||
def __str__(self):
|
||||
return '\n' + '\n'.join(sorted(repr(x) for x in self.rules)) + '\n'
|
||||
|
||||
def __repr__(self):
|
||||
return str(self)
|
||||
|
||||
|
||||
# Parse tree data structures
|
||||
class RuleNode:
|
||||
"""A node in the parse tree, which also contains the full rhs rule."""
|
||||
|
||||
def __init__(self, rule, children, weight=0):
|
||||
self.rule = rule
|
||||
self.children = children
|
||||
self.weight = weight
|
||||
|
||||
def __repr__(self):
|
||||
return 'RuleNode(%s, [%s])' % (repr(self.rule.lhs), ', '.join(str(x) for x in self.children))
|
||||
|
||||
|
||||
|
||||
class Parser:
|
||||
"""Parser wrapper."""
|
||||
|
||||
def __init__(self, rules):
|
||||
super(Parser, self).__init__()
|
||||
self.orig_rules = {rule: rule for rule in rules}
|
||||
rules = [self._to_rule(rule) for rule in rules]
|
||||
self.grammar = to_cnf(Grammar(rules))
|
||||
|
||||
def _to_rule(self, lark_rule):
|
||||
"""Converts a lark rule, (lhs, rhs, callback, options), to a Rule."""
|
||||
assert isinstance(lark_rule.origin, NT)
|
||||
assert all(isinstance(x, Symbol) for x in lark_rule.expansion)
|
||||
return Rule(
|
||||
lark_rule.origin, lark_rule.expansion,
|
||||
weight=lark_rule.options.priority if lark_rule.options.priority else 0,
|
||||
alias=lark_rule)
|
||||
|
||||
def parse(self, tokenized, start): # pylint: disable=invalid-name
|
||||
"""Parses input, which is a list of tokens."""
|
||||
assert start
|
||||
start = NT(start)
|
||||
|
||||
table, trees = _parse(tokenized, self.grammar)
|
||||
# Check if the parse succeeded.
|
||||
if all(r.lhs != start for r in table[(0, len(tokenized) - 1)]):
|
||||
raise ParseError('Parsing failed.')
|
||||
parse = trees[(0, len(tokenized) - 1)][start]
|
||||
return self._to_tree(revert_cnf(parse))
|
||||
|
||||
def _to_tree(self, rule_node):
|
||||
"""Converts a RuleNode parse tree to a lark Tree."""
|
||||
orig_rule = self.orig_rules[rule_node.rule.alias]
|
||||
children = []
|
||||
for child in rule_node.children:
|
||||
if isinstance(child, RuleNode):
|
||||
children.append(self._to_tree(child))
|
||||
else:
|
||||
assert isinstance(child.name, Token)
|
||||
children.append(child.name)
|
||||
t = Tree(orig_rule.origin, children)
|
||||
t.rule=orig_rule
|
||||
return t
|
||||
|
||||
|
||||
def print_parse(node, indent=0):
|
||||
if isinstance(node, RuleNode):
|
||||
print(' ' * (indent * 2) + str(node.rule.lhs))
|
||||
for child in node.children:
|
||||
print_parse(child, indent + 1)
|
||||
else:
|
||||
print(' ' * (indent * 2) + str(node.s))
|
||||
|
||||
|
||||
def _parse(s, g):
|
||||
"""Parses sentence 's' using CNF grammar 'g'."""
|
||||
# The CYK table. Indexed with a 2-tuple: (start pos, end pos)
|
||||
table = defaultdict(set)
|
||||
# Top-level structure is similar to the CYK table. Each cell is a dict from
|
||||
# rule name to the best (lightest) tree for that rule.
|
||||
trees = defaultdict(dict)
|
||||
# Populate base case with existing terminal production rules
|
||||
for i, w in enumerate(s):
|
||||
for terminal, rules in g.terminal_rules.items():
|
||||
if match(terminal, w):
|
||||
for rule in rules:
|
||||
table[(i, i)].add(rule)
|
||||
if (rule.lhs not in trees[(i, i)] or
|
||||
rule.weight < trees[(i, i)][rule.lhs].weight):
|
||||
trees[(i, i)][rule.lhs] = RuleNode(rule, [T(w)], weight=rule.weight)
|
||||
|
||||
# Iterate over lengths of sub-sentences
|
||||
for l in xrange(2, len(s) + 1):
|
||||
# Iterate over sub-sentences with the given length
|
||||
for i in xrange(len(s) - l + 1):
|
||||
# Choose partition of the sub-sentence in [1, l)
|
||||
for p in xrange(i + 1, i + l):
|
||||
span1 = (i, p - 1)
|
||||
span2 = (p, i + l - 1)
|
||||
for r1, r2 in itertools.product(table[span1], table[span2]):
|
||||
for rule in g.nonterminal_rules.get((r1.lhs, r2.lhs), []):
|
||||
table[(i, i + l - 1)].add(rule)
|
||||
r1_tree = trees[span1][r1.lhs]
|
||||
r2_tree = trees[span2][r2.lhs]
|
||||
rule_total_weight = rule.weight + r1_tree.weight + r2_tree.weight
|
||||
if (rule.lhs not in trees[(i, i + l - 1)]
|
||||
or rule_total_weight < trees[(i, i + l - 1)][rule.lhs].weight):
|
||||
trees[(i, i + l - 1)][rule.lhs] = RuleNode(rule, [r1_tree, r2_tree], weight=rule_total_weight)
|
||||
return table, trees
|
||||
|
||||
|
||||
# This section implements context-free grammar converter to Chomsky normal form.
|
||||
# It also implements a conversion of parse trees from its CNF to the original
|
||||
# grammar.
|
||||
# Overview:
|
||||
# Applies the following operations in this order:
|
||||
# * TERM: Eliminates non-solitary terminals from all rules
|
||||
# * BIN: Eliminates rules with more than 2 symbols on their right-hand-side.
|
||||
# * UNIT: Eliminates non-terminal unit rules
|
||||
#
|
||||
# The following grammar characteristics aren't featured:
|
||||
# * Start symbol appears on RHS
|
||||
# * Empty rules (epsilon rules)
|
||||
|
||||
|
||||
class CnfWrapper:
|
||||
"""CNF wrapper for grammar.
|
||||
|
||||
Validates that the input grammar is CNF and provides helper data structures.
|
||||
"""
|
||||
|
||||
def __init__(self, grammar):
|
||||
super(CnfWrapper, self).__init__()
|
||||
self.grammar = grammar
|
||||
self.rules = grammar.rules
|
||||
self.terminal_rules = defaultdict(list)
|
||||
self.nonterminal_rules = defaultdict(list)
|
||||
for r in self.rules:
|
||||
# Validate that the grammar is CNF and populate auxiliary data structures.
|
||||
assert isinstance(r.lhs, NT), r
|
||||
if len(r.rhs) not in [1, 2]:
|
||||
raise ParseError("CYK doesn't support empty rules")
|
||||
if len(r.rhs) == 1 and isinstance(r.rhs[0], T):
|
||||
self.terminal_rules[r.rhs[0]].append(r)
|
||||
elif len(r.rhs) == 2 and all(isinstance(x, NT) for x in r.rhs):
|
||||
self.nonterminal_rules[tuple(r.rhs)].append(r)
|
||||
else:
|
||||
assert False, r
|
||||
|
||||
def __eq__(self, other):
|
||||
return self.grammar == other.grammar
|
||||
|
||||
def __repr__(self):
|
||||
return repr(self.grammar)
|
||||
|
||||
|
||||
class UnitSkipRule(Rule):
|
||||
"""A rule that records NTs that were skipped during transformation."""
|
||||
|
||||
def __init__(self, lhs, rhs, skipped_rules, weight, alias):
|
||||
super(UnitSkipRule, self).__init__(lhs, rhs, weight, alias)
|
||||
self.skipped_rules = skipped_rules
|
||||
|
||||
def __eq__(self, other):
|
||||
return isinstance(other, type(self)) and self.skipped_rules == other.skipped_rules
|
||||
|
||||
__hash__ = Rule.__hash__
|
||||
|
||||
|
||||
def build_unit_skiprule(unit_rule, target_rule):
|
||||
skipped_rules = []
|
||||
if isinstance(unit_rule, UnitSkipRule):
|
||||
skipped_rules += unit_rule.skipped_rules
|
||||
skipped_rules.append(target_rule)
|
||||
if isinstance(target_rule, UnitSkipRule):
|
||||
skipped_rules += target_rule.skipped_rules
|
||||
return UnitSkipRule(unit_rule.lhs, target_rule.rhs, skipped_rules,
|
||||
weight=unit_rule.weight + target_rule.weight, alias=unit_rule.alias)
|
||||
|
||||
|
||||
def get_any_nt_unit_rule(g):
|
||||
"""Returns a non-terminal unit rule from 'g', or None if there is none."""
|
||||
for rule in g.rules:
|
||||
if len(rule.rhs) == 1 and isinstance(rule.rhs[0], NT):
|
||||
return rule
|
||||
return None
|
||||
|
||||
|
||||
def _remove_unit_rule(g, rule):
|
||||
"""Removes 'rule' from 'g' without changing the langugage produced by 'g'."""
|
||||
new_rules = [x for x in g.rules if x != rule]
|
||||
refs = [x for x in g.rules if x.lhs == rule.rhs[0]]
|
||||
new_rules += [build_unit_skiprule(rule, ref) for ref in refs]
|
||||
return Grammar(new_rules)
|
||||
|
||||
|
||||
def _split(rule):
|
||||
"""Splits a rule whose len(rhs) > 2 into shorter rules."""
|
||||
rule_str = str(rule.lhs) + '__' + '_'.join(str(x) for x in rule.rhs)
|
||||
rule_name = '__SP_%s' % (rule_str) + '_%d'
|
||||
yield Rule(rule.lhs, [rule.rhs[0], NT(rule_name % 1)], weight=rule.weight, alias=rule.alias)
|
||||
for i in xrange(1, len(rule.rhs) - 2):
|
||||
yield Rule(NT(rule_name % i), [rule.rhs[i], NT(rule_name % (i + 1))], weight=0, alias='Split')
|
||||
yield Rule(NT(rule_name % (len(rule.rhs) - 2)), rule.rhs[-2:], weight=0, alias='Split')
|
||||
|
||||
|
||||
def _term(g):
|
||||
"""Applies the TERM rule on 'g' (see top comment)."""
|
||||
all_t = {x for rule in g.rules for x in rule.rhs if isinstance(x, T)}
|
||||
t_rules = {t: Rule(NT('__T_%s' % str(t)), [t], weight=0, alias='Term') for t in all_t}
|
||||
new_rules = []
|
||||
for rule in g.rules:
|
||||
if len(rule.rhs) > 1 and any(isinstance(x, T) for x in rule.rhs):
|
||||
new_rhs = [t_rules[x].lhs if isinstance(x, T) else x for x in rule.rhs]
|
||||
new_rules.append(Rule(rule.lhs, new_rhs, weight=rule.weight, alias=rule.alias))
|
||||
new_rules.extend(v for k, v in t_rules.items() if k in rule.rhs)
|
||||
else:
|
||||
new_rules.append(rule)
|
||||
return Grammar(new_rules)
|
||||
|
||||
|
||||
def _bin(g):
|
||||
"""Applies the BIN rule to 'g' (see top comment)."""
|
||||
new_rules = []
|
||||
for rule in g.rules:
|
||||
if len(rule.rhs) > 2:
|
||||
new_rules += _split(rule)
|
||||
else:
|
||||
new_rules.append(rule)
|
||||
return Grammar(new_rules)
|
||||
|
||||
|
||||
def _unit(g):
|
||||
"""Applies the UNIT rule to 'g' (see top comment)."""
|
||||
nt_unit_rule = get_any_nt_unit_rule(g)
|
||||
while nt_unit_rule:
|
||||
g = _remove_unit_rule(g, nt_unit_rule)
|
||||
nt_unit_rule = get_any_nt_unit_rule(g)
|
||||
return g
|
||||
|
||||
|
||||
def to_cnf(g):
|
||||
"""Creates a CNF grammar from a general context-free grammar 'g'."""
|
||||
g = _unit(_bin(_term(g)))
|
||||
return CnfWrapper(g)
|
||||
|
||||
|
||||
def unroll_unit_skiprule(lhs, orig_rhs, skipped_rules, children, weight, alias):
|
||||
if not skipped_rules:
|
||||
return RuleNode(Rule(lhs, orig_rhs, weight=weight, alias=alias), children, weight=weight)
|
||||
else:
|
||||
weight = weight - skipped_rules[0].weight
|
||||
return RuleNode(
|
||||
Rule(lhs, [skipped_rules[0].lhs], weight=weight, alias=alias), [
|
||||
unroll_unit_skiprule(skipped_rules[0].lhs, orig_rhs,
|
||||
skipped_rules[1:], children,
|
||||
skipped_rules[0].weight, skipped_rules[0].alias)
|
||||
], weight=weight)
|
||||
|
||||
|
||||
def revert_cnf(node):
|
||||
"""Reverts a parse tree (RuleNode) to its original non-CNF form (Node)."""
|
||||
if isinstance(node, T):
|
||||
return node
|
||||
# Reverts TERM rule.
|
||||
if node.rule.lhs.name.startswith('__T_'):
|
||||
return node.children[0]
|
||||
else:
|
||||
children = []
|
||||
for child in map(revert_cnf, node.children):
|
||||
# Reverts BIN rule.
|
||||
if isinstance(child, RuleNode) and child.rule.lhs.name.startswith('__SP_'):
|
||||
children += child.children
|
||||
else:
|
||||
children.append(child)
|
||||
# Reverts UNIT rule.
|
||||
if isinstance(node.rule, UnitSkipRule):
|
||||
return unroll_unit_skiprule(node.rule.lhs, node.rule.rhs,
|
||||
node.rule.skipped_rules, children,
|
||||
node.rule.weight, node.rule.alias)
|
||||
else:
|
||||
return RuleNode(node.rule, children)
|
||||
|
|
@ -0,0 +1,295 @@
|
|||
"""This module implements an Earley parser.
|
||||
|
||||
The core Earley algorithm used here is based on Elizabeth Scott's implementation, here:
|
||||
https://www.sciencedirect.com/science/article/pii/S1571066108001497
|
||||
|
||||
That is probably the best reference for understanding the algorithm here.
|
||||
|
||||
The Earley parser outputs an SPPF-tree as per that document. The SPPF tree format
|
||||
is explained here: https://lark-parser.readthedocs.io/en/latest/_static/sppf/sppf.html
|
||||
"""
|
||||
|
||||
from collections import deque
|
||||
|
||||
from ..lexer import Token
|
||||
from ..tree import Tree
|
||||
from ..exceptions import UnexpectedEOF, UnexpectedToken
|
||||
from ..utils import logger
|
||||
from .grammar_analysis import GrammarAnalyzer
|
||||
from ..grammar import NonTerminal
|
||||
from .earley_common import Item
|
||||
from .earley_forest import ForestSumVisitor, SymbolNode, TokenNode, ForestToParseTree
|
||||
|
||||
class Parser:
|
||||
def __init__(self, lexer_conf, parser_conf, term_matcher, resolve_ambiguity=True, debug=False, tree_class=Tree):
|
||||
analysis = GrammarAnalyzer(parser_conf)
|
||||
self.lexer_conf = lexer_conf
|
||||
self.parser_conf = parser_conf
|
||||
self.resolve_ambiguity = resolve_ambiguity
|
||||
self.debug = debug
|
||||
self.tree_class = tree_class
|
||||
|
||||
self.FIRST = analysis.FIRST
|
||||
self.NULLABLE = analysis.NULLABLE
|
||||
self.callbacks = parser_conf.callbacks
|
||||
self.predictions = {}
|
||||
|
||||
## These could be moved to the grammar analyzer. Pre-computing these is *much* faster than
|
||||
# the slow 'isupper' in is_terminal.
|
||||
self.TERMINALS = { sym for r in parser_conf.rules for sym in r.expansion if sym.is_term }
|
||||
self.NON_TERMINALS = { sym for r in parser_conf.rules for sym in r.expansion if not sym.is_term }
|
||||
|
||||
self.forest_sum_visitor = None
|
||||
for rule in parser_conf.rules:
|
||||
if rule.origin not in self.predictions:
|
||||
self.predictions[rule.origin] = [x.rule for x in analysis.expand_rule(rule.origin)]
|
||||
|
||||
## Detect if any rules/terminals have priorities set. If the user specified priority = None, then
|
||||
# the priorities will be stripped from all rules/terminals before they reach us, allowing us to
|
||||
# skip the extra tree walk. We'll also skip this if the user just didn't specify priorities
|
||||
# on any rules/terminals.
|
||||
if self.forest_sum_visitor is None and rule.options.priority is not None:
|
||||
self.forest_sum_visitor = ForestSumVisitor
|
||||
|
||||
# Check terminals for priorities
|
||||
# Ignore terminal priorities if the basic lexer is used
|
||||
if self.lexer_conf.lexer_type != 'basic' and self.forest_sum_visitor is None:
|
||||
for term in self.lexer_conf.terminals:
|
||||
if term.priority:
|
||||
self.forest_sum_visitor = ForestSumVisitor
|
||||
break
|
||||
|
||||
self.term_matcher = term_matcher
|
||||
|
||||
|
||||
def predict_and_complete(self, i, to_scan, columns, transitives):
|
||||
"""The core Earley Predictor and Completer.
|
||||
|
||||
At each stage of the input, we handling any completed items (things
|
||||
that matched on the last cycle) and use those to predict what should
|
||||
come next in the input stream. The completions and any predicted
|
||||
non-terminals are recursively processed until we reach a set of,
|
||||
which can be added to the scan list for the next scanner cycle."""
|
||||
# Held Completions (H in E.Scotts paper).
|
||||
node_cache = {}
|
||||
held_completions = {}
|
||||
|
||||
column = columns[i]
|
||||
# R (items) = Ei (column.items)
|
||||
items = deque(column)
|
||||
while items:
|
||||
item = items.pop() # remove an element, A say, from R
|
||||
|
||||
### The Earley completer
|
||||
if item.is_complete: ### (item.s == string)
|
||||
if item.node is None:
|
||||
label = (item.s, item.start, i)
|
||||
item.node = node_cache[label] if label in node_cache else node_cache.setdefault(label, SymbolNode(*label))
|
||||
item.node.add_family(item.s, item.rule, item.start, None, None)
|
||||
|
||||
# create_leo_transitives(item.rule.origin, item.start)
|
||||
|
||||
###R Joop Leo right recursion Completer
|
||||
if item.rule.origin in transitives[item.start]:
|
||||
transitive = transitives[item.start][item.s]
|
||||
if transitive.previous in transitives[transitive.column]:
|
||||
root_transitive = transitives[transitive.column][transitive.previous]
|
||||
else:
|
||||
root_transitive = transitive
|
||||
|
||||
new_item = Item(transitive.rule, transitive.ptr, transitive.start)
|
||||
label = (root_transitive.s, root_transitive.start, i)
|
||||
new_item.node = node_cache[label] if label in node_cache else node_cache.setdefault(label, SymbolNode(*label))
|
||||
new_item.node.add_path(root_transitive, item.node)
|
||||
if new_item.expect in self.TERMINALS:
|
||||
# Add (B :: aC.B, h, y) to Q
|
||||
to_scan.add(new_item)
|
||||
elif new_item not in column:
|
||||
# Add (B :: aC.B, h, y) to Ei and R
|
||||
column.add(new_item)
|
||||
items.append(new_item)
|
||||
###R Regular Earley completer
|
||||
else:
|
||||
# Empty has 0 length. If we complete an empty symbol in a particular
|
||||
# parse step, we need to be able to use that same empty symbol to complete
|
||||
# any predictions that result, that themselves require empty. Avoids
|
||||
# infinite recursion on empty symbols.
|
||||
# held_completions is 'H' in E.Scott's paper.
|
||||
is_empty_item = item.start == i
|
||||
if is_empty_item:
|
||||
held_completions[item.rule.origin] = item.node
|
||||
|
||||
originators = [originator for originator in columns[item.start] if originator.expect is not None and originator.expect == item.s]
|
||||
for originator in originators:
|
||||
new_item = originator.advance()
|
||||
label = (new_item.s, originator.start, i)
|
||||
new_item.node = node_cache[label] if label in node_cache else node_cache.setdefault(label, SymbolNode(*label))
|
||||
new_item.node.add_family(new_item.s, new_item.rule, i, originator.node, item.node)
|
||||
if new_item.expect in self.TERMINALS:
|
||||
# Add (B :: aC.B, h, y) to Q
|
||||
to_scan.add(new_item)
|
||||
elif new_item not in column:
|
||||
# Add (B :: aC.B, h, y) to Ei and R
|
||||
column.add(new_item)
|
||||
items.append(new_item)
|
||||
|
||||
### The Earley predictor
|
||||
elif item.expect in self.NON_TERMINALS: ### (item.s == lr0)
|
||||
new_items = []
|
||||
for rule in self.predictions[item.expect]:
|
||||
new_item = Item(rule, 0, i)
|
||||
new_items.append(new_item)
|
||||
|
||||
# Process any held completions (H).
|
||||
if item.expect in held_completions:
|
||||
new_item = item.advance()
|
||||
label = (new_item.s, item.start, i)
|
||||
new_item.node = node_cache[label] if label in node_cache else node_cache.setdefault(label, SymbolNode(*label))
|
||||
new_item.node.add_family(new_item.s, new_item.rule, new_item.start, item.node, held_completions[item.expect])
|
||||
new_items.append(new_item)
|
||||
|
||||
for new_item in new_items:
|
||||
if new_item.expect in self.TERMINALS:
|
||||
to_scan.add(new_item)
|
||||
elif new_item not in column:
|
||||
column.add(new_item)
|
||||
items.append(new_item)
|
||||
|
||||
def _parse(self, lexer, columns, to_scan, start_symbol=None):
|
||||
def is_quasi_complete(item):
|
||||
if item.is_complete:
|
||||
return True
|
||||
|
||||
quasi = item.advance()
|
||||
while not quasi.is_complete:
|
||||
if quasi.expect not in self.NULLABLE:
|
||||
return False
|
||||
if quasi.rule.origin == start_symbol and quasi.expect == start_symbol:
|
||||
return False
|
||||
quasi = quasi.advance()
|
||||
return True
|
||||
|
||||
# def create_leo_transitives(origin, start):
|
||||
# ... # removed at commit 4c1cfb2faf24e8f8bff7112627a00b94d261b420
|
||||
|
||||
def scan(i, token, to_scan):
|
||||
"""The core Earley Scanner.
|
||||
|
||||
This is a custom implementation of the scanner that uses the
|
||||
Lark lexer to match tokens. The scan list is built by the
|
||||
Earley predictor, based on the previously completed tokens.
|
||||
This ensures that at each phase of the parse we have a custom
|
||||
lexer context, allowing for more complex ambiguities."""
|
||||
next_to_scan = set()
|
||||
next_set = set()
|
||||
columns.append(next_set)
|
||||
transitives.append({})
|
||||
node_cache = {}
|
||||
|
||||
for item in set(to_scan):
|
||||
if match(item.expect, token):
|
||||
new_item = item.advance()
|
||||
label = (new_item.s, new_item.start, i)
|
||||
# 'terminals' may not contain token.type when using %declare
|
||||
# Additionally, token is not always a Token
|
||||
# For example, it can be a Tree when using TreeMatcher
|
||||
term = terminals.get(token.type) if isinstance(token, Token) else None
|
||||
# Set the priority of the token node to 0 so that the
|
||||
# terminal priorities do not affect the Tree chosen by
|
||||
# ForestSumVisitor after the basic lexer has already
|
||||
# "used up" the terminal priorities
|
||||
token_node = TokenNode(token, term, priority=0)
|
||||
new_item.node = node_cache[label] if label in node_cache else node_cache.setdefault(label, SymbolNode(*label))
|
||||
new_item.node.add_family(new_item.s, item.rule, new_item.start, item.node, token_node)
|
||||
|
||||
if new_item.expect in self.TERMINALS:
|
||||
# add (B ::= Aai+1.B, h, y) to Q'
|
||||
next_to_scan.add(new_item)
|
||||
else:
|
||||
# add (B ::= Aa+1.B, h, y) to Ei+1
|
||||
next_set.add(new_item)
|
||||
|
||||
if not next_set and not next_to_scan:
|
||||
expect = {i.expect.name for i in to_scan}
|
||||
raise UnexpectedToken(token, expect, considered_rules=set(to_scan), state=frozenset(i.s for i in to_scan))
|
||||
|
||||
return next_to_scan
|
||||
|
||||
|
||||
# Define parser functions
|
||||
match = self.term_matcher
|
||||
|
||||
terminals = self.lexer_conf.terminals_by_name
|
||||
|
||||
# Cache for nodes & tokens created in a particular parse step.
|
||||
transitives = [{}]
|
||||
|
||||
## The main Earley loop.
|
||||
# Run the Prediction/Completion cycle for any Items in the current Earley set.
|
||||
# Completions will be added to the SPPF tree, and predictions will be recursively
|
||||
# processed down to terminals/empty nodes to be added to the scanner for the next
|
||||
# step.
|
||||
expects = {i.expect for i in to_scan}
|
||||
i = 0
|
||||
for token in lexer.lex(expects):
|
||||
self.predict_and_complete(i, to_scan, columns, transitives)
|
||||
|
||||
to_scan = scan(i, token, to_scan)
|
||||
i += 1
|
||||
|
||||
expects.clear()
|
||||
expects |= {i.expect for i in to_scan}
|
||||
|
||||
self.predict_and_complete(i, to_scan, columns, transitives)
|
||||
|
||||
## Column is now the final column in the parse.
|
||||
assert i == len(columns)-1
|
||||
return to_scan
|
||||
|
||||
def parse(self, lexer, start):
|
||||
assert start, start
|
||||
start_symbol = NonTerminal(start)
|
||||
|
||||
columns = [set()]
|
||||
to_scan = set() # The scan buffer. 'Q' in E.Scott's paper.
|
||||
|
||||
## Predict for the start_symbol.
|
||||
# Add predicted items to the first Earley set (for the predictor) if they
|
||||
# result in a non-terminal, or the scanner if they result in a terminal.
|
||||
for rule in self.predictions[start_symbol]:
|
||||
item = Item(rule, 0, 0)
|
||||
if item.expect in self.TERMINALS:
|
||||
to_scan.add(item)
|
||||
else:
|
||||
columns[0].add(item)
|
||||
|
||||
to_scan = self._parse(lexer, columns, to_scan, start_symbol)
|
||||
|
||||
# If the parse was successful, the start
|
||||
# symbol should have been completed in the last step of the Earley cycle, and will be in
|
||||
# this column. Find the item for the start_symbol, which is the root of the SPPF tree.
|
||||
solutions = [n.node for n in columns[-1] if n.is_complete and n.node is not None and n.s == start_symbol and n.start == 0]
|
||||
if not solutions:
|
||||
expected_terminals = [t.expect.name for t in to_scan]
|
||||
raise UnexpectedEOF(expected_terminals, state=frozenset(i.s for i in to_scan))
|
||||
|
||||
if self.debug:
|
||||
from .earley_forest import ForestToPyDotVisitor
|
||||
try:
|
||||
debug_walker = ForestToPyDotVisitor()
|
||||
except ImportError:
|
||||
logger.warning("Cannot find dependency 'pydot', will not generate sppf debug image")
|
||||
else:
|
||||
debug_walker.visit(solutions[0], "sppf.png")
|
||||
|
||||
|
||||
if len(solutions) > 1:
|
||||
assert False, 'Earley should not generate multiple start symbol items!'
|
||||
|
||||
if self.tree_class is not None:
|
||||
# Perform our SPPF -> AST conversion
|
||||
transformer = ForestToParseTree(self.tree_class, self.callbacks, self.forest_sum_visitor and self.forest_sum_visitor(), self.resolve_ambiguity)
|
||||
return transformer.transform(solutions[0])
|
||||
|
||||
# return the root of the SPPF
|
||||
return solutions[0]
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
"""This module implements useful building blocks for the Earley parser
|
||||
"""
|
||||
|
||||
|
||||
class Item:
|
||||
"An Earley Item, the atom of the algorithm."
|
||||
|
||||
__slots__ = ('s', 'rule', 'ptr', 'start', 'is_complete', 'expect', 'previous', 'node', '_hash')
|
||||
def __init__(self, rule, ptr, start):
|
||||
self.is_complete = len(rule.expansion) == ptr
|
||||
self.rule = rule # rule
|
||||
self.ptr = ptr # ptr
|
||||
self.start = start # j
|
||||
self.node = None # w
|
||||
if self.is_complete:
|
||||
self.s = rule.origin
|
||||
self.expect = None
|
||||
self.previous = rule.expansion[ptr - 1] if ptr > 0 and len(rule.expansion) else None
|
||||
else:
|
||||
self.s = (rule, ptr)
|
||||
self.expect = rule.expansion[ptr]
|
||||
self.previous = rule.expansion[ptr - 1] if ptr > 0 and len(rule.expansion) else None
|
||||
self._hash = hash((self.s, self.start))
|
||||
|
||||
def advance(self):
|
||||
return Item(self.rule, self.ptr + 1, self.start)
|
||||
|
||||
def __eq__(self, other):
|
||||
return self is other or (self.s == other.s and self.start == other.start)
|
||||
|
||||
def __hash__(self):
|
||||
return self._hash
|
||||
|
||||
def __repr__(self):
|
||||
before = ( expansion.name for expansion in self.rule.expansion[:self.ptr] )
|
||||
after = ( expansion.name for expansion in self.rule.expansion[self.ptr:] )
|
||||
symbol = "{} ::= {}* {}".format(self.rule.origin.name, ' '.join(before), ' '.join(after))
|
||||
return '%s (%d)' % (symbol, self.start)
|
||||
|
||||
|
||||
# class TransitiveItem(Item):
|
||||
# ... # removed at commit 4c1cfb2faf24e8f8bff7112627a00b94d261b420
|
||||
|
|
@ -0,0 +1,804 @@
|
|||
""""This module implements an SPPF implementation
|
||||
|
||||
This is used as the primary output mechanism for the Earley parser
|
||||
in order to store complex ambiguities.
|
||||
|
||||
Full reference and more details is here:
|
||||
https://web.archive.org/web/20190616123959/http://www.bramvandersanden.com/post/2014/06/shared-packed-parse-forest/
|
||||
"""
|
||||
|
||||
from random import randint
|
||||
from collections import deque
|
||||
from operator import attrgetter
|
||||
from importlib import import_module
|
||||
from functools import partial
|
||||
|
||||
from ..parse_tree_builder import AmbiguousIntermediateExpander
|
||||
from ..visitors import Discard
|
||||
from ..lexer import Token
|
||||
from ..utils import logger
|
||||
from ..tree import Tree
|
||||
|
||||
class ForestNode:
|
||||
pass
|
||||
|
||||
class SymbolNode(ForestNode):
|
||||
"""
|
||||
A Symbol Node represents a symbol (or Intermediate LR0).
|
||||
|
||||
Symbol nodes are keyed by the symbol (s). For intermediate nodes
|
||||
s will be an LR0, stored as a tuple of (rule, ptr). For completed symbol
|
||||
nodes, s will be a string representing the non-terminal origin (i.e.
|
||||
the left hand side of the rule).
|
||||
|
||||
The children of a Symbol or Intermediate Node will always be Packed Nodes;
|
||||
with each Packed Node child representing a single derivation of a production.
|
||||
|
||||
Hence a Symbol Node with a single child is unambiguous.
|
||||
|
||||
Parameters:
|
||||
s: A Symbol, or a tuple of (rule, ptr) for an intermediate node.
|
||||
start: The index of the start of the substring matched by this symbol (inclusive).
|
||||
end: The index of the end of the substring matched by this symbol (exclusive).
|
||||
|
||||
Properties:
|
||||
is_intermediate: True if this node is an intermediate node.
|
||||
priority: The priority of the node's symbol.
|
||||
"""
|
||||
__slots__ = ('s', 'start', 'end', '_children', 'paths', 'paths_loaded', 'priority', 'is_intermediate', '_hash')
|
||||
def __init__(self, s, start, end):
|
||||
self.s = s
|
||||
self.start = start
|
||||
self.end = end
|
||||
self._children = set()
|
||||
self.paths = set()
|
||||
self.paths_loaded = False
|
||||
|
||||
### We use inf here as it can be safely negated without resorting to conditionals,
|
||||
# unlike None or float('NaN'), and sorts appropriately.
|
||||
self.priority = float('-inf')
|
||||
self.is_intermediate = isinstance(s, tuple)
|
||||
self._hash = hash((self.s, self.start, self.end))
|
||||
|
||||
def add_family(self, lr0, rule, start, left, right):
|
||||
self._children.add(PackedNode(self, lr0, rule, start, left, right))
|
||||
|
||||
def add_path(self, transitive, node):
|
||||
self.paths.add((transitive, node))
|
||||
|
||||
def load_paths(self):
|
||||
for transitive, node in self.paths:
|
||||
if transitive.next_titem is not None:
|
||||
vn = SymbolNode(transitive.next_titem.s, transitive.next_titem.start, self.end)
|
||||
vn.add_path(transitive.next_titem, node)
|
||||
self.add_family(transitive.reduction.rule.origin, transitive.reduction.rule, transitive.reduction.start, transitive.reduction.node, vn)
|
||||
else:
|
||||
self.add_family(transitive.reduction.rule.origin, transitive.reduction.rule, transitive.reduction.start, transitive.reduction.node, node)
|
||||
self.paths_loaded = True
|
||||
|
||||
@property
|
||||
def is_ambiguous(self):
|
||||
"""Returns True if this node is ambiguous."""
|
||||
return len(self.children) > 1
|
||||
|
||||
@property
|
||||
def children(self):
|
||||
"""Returns a list of this node's children sorted from greatest to
|
||||
least priority."""
|
||||
if not self.paths_loaded: self.load_paths()
|
||||
return sorted(self._children, key=attrgetter('sort_key'))
|
||||
|
||||
def __iter__(self):
|
||||
return iter(self._children)
|
||||
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, SymbolNode):
|
||||
return False
|
||||
return self is other or (type(self.s) == type(other.s) and self.s == other.s and self.start == other.start and self.end is other.end)
|
||||
|
||||
def __hash__(self):
|
||||
return self._hash
|
||||
|
||||
def __repr__(self):
|
||||
if self.is_intermediate:
|
||||
rule = self.s[0]
|
||||
ptr = self.s[1]
|
||||
before = ( expansion.name for expansion in rule.expansion[:ptr] )
|
||||
after = ( expansion.name for expansion in rule.expansion[ptr:] )
|
||||
symbol = "{} ::= {}* {}".format(rule.origin.name, ' '.join(before), ' '.join(after))
|
||||
else:
|
||||
symbol = self.s.name
|
||||
return "({}, {}, {}, {})".format(symbol, self.start, self.end, self.priority)
|
||||
|
||||
class PackedNode(ForestNode):
|
||||
"""
|
||||
A Packed Node represents a single derivation in a symbol node.
|
||||
|
||||
Parameters:
|
||||
rule: The rule associated with this node.
|
||||
parent: The parent of this node.
|
||||
left: The left child of this node. ``None`` if one does not exist.
|
||||
right: The right child of this node. ``None`` if one does not exist.
|
||||
priority: The priority of this node.
|
||||
"""
|
||||
__slots__ = ('parent', 's', 'rule', 'start', 'left', 'right', 'priority', '_hash')
|
||||
def __init__(self, parent, s, rule, start, left, right):
|
||||
self.parent = parent
|
||||
self.s = s
|
||||
self.start = start
|
||||
self.rule = rule
|
||||
self.left = left
|
||||
self.right = right
|
||||
self.priority = float('-inf')
|
||||
self._hash = hash((self.left, self.right))
|
||||
|
||||
@property
|
||||
def is_empty(self):
|
||||
return self.left is None and self.right is None
|
||||
|
||||
@property
|
||||
def sort_key(self):
|
||||
"""
|
||||
Used to sort PackedNode children of SymbolNodes.
|
||||
A SymbolNode has multiple PackedNodes if it matched
|
||||
ambiguously. Hence, we use the sort order to identify
|
||||
the order in which ambiguous children should be considered.
|
||||
"""
|
||||
return self.is_empty, -self.priority, self.rule.order
|
||||
|
||||
@property
|
||||
def children(self):
|
||||
"""Returns a list of this node's children."""
|
||||
return [x for x in [self.left, self.right] if x is not None]
|
||||
|
||||
def __iter__(self):
|
||||
yield self.left
|
||||
yield self.right
|
||||
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, PackedNode):
|
||||
return False
|
||||
return self is other or (self.left == other.left and self.right == other.right)
|
||||
|
||||
def __hash__(self):
|
||||
return self._hash
|
||||
|
||||
def __repr__(self):
|
||||
if isinstance(self.s, tuple):
|
||||
rule = self.s[0]
|
||||
ptr = self.s[1]
|
||||
before = ( expansion.name for expansion in rule.expansion[:ptr] )
|
||||
after = ( expansion.name for expansion in rule.expansion[ptr:] )
|
||||
symbol = "{} ::= {}* {}".format(rule.origin.name, ' '.join(before), ' '.join(after))
|
||||
else:
|
||||
symbol = self.s.name
|
||||
return "({}, {}, {}, {})".format(symbol, self.start, self.priority, self.rule.order)
|
||||
|
||||
class TokenNode(ForestNode):
|
||||
"""
|
||||
A Token Node represents a matched terminal and is always a leaf node.
|
||||
|
||||
Parameters:
|
||||
token: The Token associated with this node.
|
||||
term: The TerminalDef matched by the token.
|
||||
priority: The priority of this node.
|
||||
"""
|
||||
__slots__ = ('token', 'term', 'priority', '_hash')
|
||||
def __init__(self, token, term, priority=None):
|
||||
self.token = token
|
||||
self.term = term
|
||||
if priority is not None:
|
||||
self.priority = priority
|
||||
else:
|
||||
self.priority = term.priority if term is not None else 0
|
||||
self._hash = hash(token)
|
||||
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, TokenNode):
|
||||
return False
|
||||
return self is other or (self.token == other.token)
|
||||
|
||||
def __hash__(self):
|
||||
return self._hash
|
||||
|
||||
def __repr__(self):
|
||||
return repr(self.token)
|
||||
|
||||
class ForestVisitor:
|
||||
"""
|
||||
An abstract base class for building forest visitors.
|
||||
|
||||
This class performs a controllable depth-first walk of an SPPF.
|
||||
The visitor will not enter cycles and will backtrack if one is encountered.
|
||||
Subclasses are notified of cycles through the ``on_cycle`` method.
|
||||
|
||||
Behavior for visit events is defined by overriding the
|
||||
``visit*node*`` functions.
|
||||
|
||||
The walk is controlled by the return values of the ``visit*node_in``
|
||||
methods. Returning a node(s) will schedule them to be visited. The visitor
|
||||
will begin to backtrack if no nodes are returned.
|
||||
|
||||
Parameters:
|
||||
single_visit: If ``True``, non-Token nodes will only be visited once.
|
||||
"""
|
||||
|
||||
def __init__(self, single_visit=False):
|
||||
self.single_visit = single_visit
|
||||
|
||||
def visit_token_node(self, node):
|
||||
"""Called when a ``Token`` is visited. ``Token`` nodes are always leaves."""
|
||||
pass
|
||||
|
||||
def visit_symbol_node_in(self, node):
|
||||
"""Called when a symbol node is visited. Nodes that are returned
|
||||
will be scheduled to be visited. If ``visit_intermediate_node_in``
|
||||
is not implemented, this function will be called for intermediate
|
||||
nodes as well."""
|
||||
pass
|
||||
|
||||
def visit_symbol_node_out(self, node):
|
||||
"""Called after all nodes returned from a corresponding ``visit_symbol_node_in``
|
||||
call have been visited. If ``visit_intermediate_node_out``
|
||||
is not implemented, this function will be called for intermediate
|
||||
nodes as well."""
|
||||
pass
|
||||
|
||||
def visit_packed_node_in(self, node):
|
||||
"""Called when a packed node is visited. Nodes that are returned
|
||||
will be scheduled to be visited. """
|
||||
pass
|
||||
|
||||
def visit_packed_node_out(self, node):
|
||||
"""Called after all nodes returned from a corresponding ``visit_packed_node_in``
|
||||
call have been visited."""
|
||||
pass
|
||||
|
||||
def on_cycle(self, node, path):
|
||||
"""Called when a cycle is encountered.
|
||||
|
||||
Parameters:
|
||||
node: The node that causes a cycle.
|
||||
path: The list of nodes being visited: nodes that have been
|
||||
entered but not exited. The first element is the root in a forest
|
||||
visit, and the last element is the node visited most recently.
|
||||
``path`` should be treated as read-only.
|
||||
"""
|
||||
pass
|
||||
|
||||
def get_cycle_in_path(self, node, path):
|
||||
"""A utility function for use in ``on_cycle`` to obtain a slice of
|
||||
``path`` that only contains the nodes that make up the cycle."""
|
||||
index = len(path) - 1
|
||||
while id(path[index]) != id(node):
|
||||
index -= 1
|
||||
return path[index:]
|
||||
|
||||
def visit(self, root):
|
||||
# Visiting is a list of IDs of all symbol/intermediate nodes currently in
|
||||
# the stack. It serves two purposes: to detect when we 'recurse' in and out
|
||||
# of a symbol/intermediate so that we can process both up and down. Also,
|
||||
# since the SPPF can have cycles it allows us to detect if we're trying
|
||||
# to recurse into a node that's already on the stack (infinite recursion).
|
||||
visiting = set()
|
||||
|
||||
# set of all nodes that have been visited
|
||||
visited = set()
|
||||
|
||||
# a list of nodes that are currently being visited
|
||||
# used for the `on_cycle` callback
|
||||
path = []
|
||||
|
||||
# We do not use recursion here to walk the Forest due to the limited
|
||||
# stack size in python. Therefore input_stack is essentially our stack.
|
||||
input_stack = deque([root])
|
||||
|
||||
# It is much faster to cache these as locals since they are called
|
||||
# many times in large parses.
|
||||
vpno = getattr(self, 'visit_packed_node_out')
|
||||
vpni = getattr(self, 'visit_packed_node_in')
|
||||
vsno = getattr(self, 'visit_symbol_node_out')
|
||||
vsni = getattr(self, 'visit_symbol_node_in')
|
||||
vino = getattr(self, 'visit_intermediate_node_out', vsno)
|
||||
vini = getattr(self, 'visit_intermediate_node_in', vsni)
|
||||
vtn = getattr(self, 'visit_token_node')
|
||||
oc = getattr(self, 'on_cycle')
|
||||
|
||||
while input_stack:
|
||||
current = next(reversed(input_stack))
|
||||
try:
|
||||
next_node = next(current)
|
||||
except StopIteration:
|
||||
input_stack.pop()
|
||||
continue
|
||||
except TypeError:
|
||||
### If the current object is not an iterator, pass through to Token/SymbolNode
|
||||
pass
|
||||
else:
|
||||
if next_node is None:
|
||||
continue
|
||||
|
||||
if id(next_node) in visiting:
|
||||
oc(next_node, path)
|
||||
continue
|
||||
|
||||
input_stack.append(next_node)
|
||||
continue
|
||||
|
||||
if isinstance(current, TokenNode):
|
||||
vtn(current.token)
|
||||
input_stack.pop()
|
||||
continue
|
||||
|
||||
current_id = id(current)
|
||||
if current_id in visiting:
|
||||
if isinstance(current, PackedNode):
|
||||
vpno(current)
|
||||
elif current.is_intermediate:
|
||||
vino(current)
|
||||
else:
|
||||
vsno(current)
|
||||
input_stack.pop()
|
||||
path.pop()
|
||||
visiting.remove(current_id)
|
||||
visited.add(current_id)
|
||||
elif self.single_visit and current_id in visited:
|
||||
input_stack.pop()
|
||||
else:
|
||||
visiting.add(current_id)
|
||||
path.append(current)
|
||||
if isinstance(current, PackedNode):
|
||||
next_node = vpni(current)
|
||||
elif current.is_intermediate:
|
||||
next_node = vini(current)
|
||||
else:
|
||||
next_node = vsni(current)
|
||||
if next_node is None:
|
||||
continue
|
||||
|
||||
if not isinstance(next_node, ForestNode):
|
||||
next_node = iter(next_node)
|
||||
elif id(next_node) in visiting:
|
||||
oc(next_node, path)
|
||||
continue
|
||||
|
||||
input_stack.append(next_node)
|
||||
|
||||
class ForestTransformer(ForestVisitor):
|
||||
"""The base class for a bottom-up forest transformation. Most users will
|
||||
want to use ``TreeForestTransformer`` instead as it has a friendlier
|
||||
interface and covers most use cases.
|
||||
|
||||
Transformations are applied via inheritance and overriding of the
|
||||
``transform*node`` methods.
|
||||
|
||||
``transform_token_node`` receives a ``Token`` as an argument.
|
||||
All other methods receive the node that is being transformed and
|
||||
a list of the results of the transformations of that node's children.
|
||||
The return value of these methods are the resulting transformations.
|
||||
|
||||
If ``Discard`` is raised in a node's transformation, no data from that node
|
||||
will be passed to its parent's transformation.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
super(ForestTransformer, self).__init__()
|
||||
# results of transformations
|
||||
self.data = dict()
|
||||
# used to track parent nodes
|
||||
self.node_stack = deque()
|
||||
|
||||
def transform(self, root):
|
||||
"""Perform a transformation on an SPPF."""
|
||||
self.node_stack.append('result')
|
||||
self.data['result'] = []
|
||||
self.visit(root)
|
||||
assert len(self.data['result']) <= 1
|
||||
if self.data['result']:
|
||||
return self.data['result'][0]
|
||||
|
||||
def transform_symbol_node(self, node, data):
|
||||
"""Transform a symbol node."""
|
||||
return node
|
||||
|
||||
def transform_intermediate_node(self, node, data):
|
||||
"""Transform an intermediate node."""
|
||||
return node
|
||||
|
||||
def transform_packed_node(self, node, data):
|
||||
"""Transform a packed node."""
|
||||
return node
|
||||
|
||||
def transform_token_node(self, node):
|
||||
"""Transform a ``Token``."""
|
||||
return node
|
||||
|
||||
def visit_symbol_node_in(self, node):
|
||||
self.node_stack.append(id(node))
|
||||
self.data[id(node)] = []
|
||||
return node.children
|
||||
|
||||
def visit_packed_node_in(self, node):
|
||||
self.node_stack.append(id(node))
|
||||
self.data[id(node)] = []
|
||||
return node.children
|
||||
|
||||
def visit_token_node(self, node):
|
||||
transformed = self.transform_token_node(node)
|
||||
if transformed is not Discard:
|
||||
self.data[self.node_stack[-1]].append(transformed)
|
||||
|
||||
def _visit_node_out_helper(self, node, method):
|
||||
self.node_stack.pop()
|
||||
transformed = method(node, self.data[id(node)])
|
||||
if transformed is not Discard:
|
||||
self.data[self.node_stack[-1]].append(transformed)
|
||||
del self.data[id(node)]
|
||||
|
||||
def visit_symbol_node_out(self, node):
|
||||
self._visit_node_out_helper(node, self.transform_symbol_node)
|
||||
|
||||
def visit_intermediate_node_out(self, node):
|
||||
self._visit_node_out_helper(node, self.transform_intermediate_node)
|
||||
|
||||
def visit_packed_node_out(self, node):
|
||||
self._visit_node_out_helper(node, self.transform_packed_node)
|
||||
|
||||
|
||||
class ForestSumVisitor(ForestVisitor):
|
||||
"""
|
||||
A visitor for prioritizing ambiguous parts of the Forest.
|
||||
|
||||
This visitor is used when support for explicit priorities on
|
||||
rules is requested (whether normal, or invert). It walks the
|
||||
forest (or subsets thereof) and cascades properties upwards
|
||||
from the leaves.
|
||||
|
||||
It would be ideal to do this during parsing, however this would
|
||||
require processing each Earley item multiple times. That's
|
||||
a big performance drawback; so running a forest walk is the
|
||||
lesser of two evils: there can be significantly more Earley
|
||||
items created during parsing than there are SPPF nodes in the
|
||||
final tree.
|
||||
"""
|
||||
def __init__(self):
|
||||
super(ForestSumVisitor, self).__init__(single_visit=True)
|
||||
|
||||
def visit_packed_node_in(self, node):
|
||||
yield node.left
|
||||
yield node.right
|
||||
|
||||
def visit_symbol_node_in(self, node):
|
||||
return iter(node.children)
|
||||
|
||||
def visit_packed_node_out(self, node):
|
||||
priority = node.rule.options.priority if not node.parent.is_intermediate and node.rule.options.priority else 0
|
||||
priority += getattr(node.right, 'priority', 0)
|
||||
priority += getattr(node.left, 'priority', 0)
|
||||
node.priority = priority
|
||||
|
||||
def visit_symbol_node_out(self, node):
|
||||
node.priority = max(child.priority for child in node.children)
|
||||
|
||||
class PackedData():
|
||||
"""Used in transformationss of packed nodes to distinguish the data
|
||||
that comes from the left child and the right child.
|
||||
"""
|
||||
|
||||
class _NoData():
|
||||
pass
|
||||
|
||||
NO_DATA = _NoData()
|
||||
|
||||
def __init__(self, node, data):
|
||||
self.left = self.NO_DATA
|
||||
self.right = self.NO_DATA
|
||||
if data:
|
||||
if node.left is not None:
|
||||
self.left = data[0]
|
||||
if len(data) > 1:
|
||||
self.right = data[1]
|
||||
else:
|
||||
self.right = data[0]
|
||||
|
||||
class ForestToParseTree(ForestTransformer):
|
||||
"""Used by the earley parser when ambiguity equals 'resolve' or
|
||||
'explicit'. Transforms an SPPF into an (ambiguous) parse tree.
|
||||
|
||||
Parameters:
|
||||
tree_class: The tree class to use for construction
|
||||
callbacks: A dictionary of rules to functions that output a tree
|
||||
prioritizer: A ``ForestVisitor`` that manipulates the priorities of ForestNodes
|
||||
resolve_ambiguity: If True, ambiguities will be resolved based on
|
||||
priorities. Otherwise, `_ambig` nodes will be in the resulting tree.
|
||||
use_cache: If True, the results of packed node transformations will be cached.
|
||||
"""
|
||||
|
||||
def __init__(self, tree_class=Tree, callbacks=dict(), prioritizer=ForestSumVisitor(), resolve_ambiguity=True, use_cache=True):
|
||||
super(ForestToParseTree, self).__init__()
|
||||
self.tree_class = tree_class
|
||||
self.callbacks = callbacks
|
||||
self.prioritizer = prioritizer
|
||||
self.resolve_ambiguity = resolve_ambiguity
|
||||
self._use_cache = use_cache
|
||||
self._cache = {}
|
||||
self._on_cycle_retreat = False
|
||||
self._cycle_node = None
|
||||
self._successful_visits = set()
|
||||
|
||||
def visit(self, root):
|
||||
if self.prioritizer:
|
||||
self.prioritizer.visit(root)
|
||||
super(ForestToParseTree, self).visit(root)
|
||||
self._cache = {}
|
||||
|
||||
def on_cycle(self, node, path):
|
||||
logger.debug("Cycle encountered in the SPPF at node: %s. "
|
||||
"As infinite ambiguities cannot be represented in a tree, "
|
||||
"this family of derivations will be discarded.", node)
|
||||
self._cycle_node = node
|
||||
self._on_cycle_retreat = True
|
||||
|
||||
def _check_cycle(self, node):
|
||||
if self._on_cycle_retreat:
|
||||
if id(node) == id(self._cycle_node) or id(node) in self._successful_visits:
|
||||
self._cycle_node = None
|
||||
self._on_cycle_retreat = False
|
||||
else:
|
||||
return Discard
|
||||
|
||||
def _collapse_ambig(self, children):
|
||||
new_children = []
|
||||
for child in children:
|
||||
if hasattr(child, 'data') and child.data == '_ambig':
|
||||
new_children += child.children
|
||||
else:
|
||||
new_children.append(child)
|
||||
return new_children
|
||||
|
||||
def _call_rule_func(self, node, data):
|
||||
# called when transforming children of symbol nodes
|
||||
# data is a list of trees or tokens that correspond to the
|
||||
# symbol's rule expansion
|
||||
return self.callbacks[node.rule](data)
|
||||
|
||||
def _call_ambig_func(self, node, data):
|
||||
# called when transforming a symbol node
|
||||
# data is a list of trees where each tree's data is
|
||||
# equal to the name of the symbol or one of its aliases.
|
||||
if len(data) > 1:
|
||||
return self.tree_class('_ambig', data)
|
||||
elif data:
|
||||
return data[0]
|
||||
return Discard
|
||||
|
||||
def transform_symbol_node(self, node, data):
|
||||
if id(node) not in self._successful_visits:
|
||||
return Discard
|
||||
r = self._check_cycle(node)
|
||||
if r is Discard:
|
||||
return r
|
||||
self._successful_visits.remove(id(node))
|
||||
data = self._collapse_ambig(data)
|
||||
return self._call_ambig_func(node, data)
|
||||
|
||||
def transform_intermediate_node(self, node, data):
|
||||
if id(node) not in self._successful_visits:
|
||||
return Discard
|
||||
r = self._check_cycle(node)
|
||||
if r is Discard:
|
||||
return r
|
||||
self._successful_visits.remove(id(node))
|
||||
if len(data) > 1:
|
||||
children = [self.tree_class('_inter', c) for c in data]
|
||||
return self.tree_class('_iambig', children)
|
||||
return data[0]
|
||||
|
||||
def transform_packed_node(self, node, data):
|
||||
r = self._check_cycle(node)
|
||||
if r is Discard:
|
||||
return r
|
||||
if self.resolve_ambiguity and id(node.parent) in self._successful_visits:
|
||||
return Discard
|
||||
if self._use_cache and id(node) in self._cache:
|
||||
return self._cache[id(node)]
|
||||
children = []
|
||||
assert len(data) <= 2
|
||||
data = PackedData(node, data)
|
||||
if data.left is not PackedData.NO_DATA:
|
||||
if node.left.is_intermediate and isinstance(data.left, list):
|
||||
children += data.left
|
||||
else:
|
||||
children.append(data.left)
|
||||
if data.right is not PackedData.NO_DATA:
|
||||
children.append(data.right)
|
||||
if node.parent.is_intermediate:
|
||||
return self._cache.setdefault(id(node), children)
|
||||
return self._cache.setdefault(id(node), self._call_rule_func(node, children))
|
||||
|
||||
def visit_symbol_node_in(self, node):
|
||||
super(ForestToParseTree, self).visit_symbol_node_in(node)
|
||||
if self._on_cycle_retreat:
|
||||
return
|
||||
return node.children
|
||||
|
||||
def visit_packed_node_in(self, node):
|
||||
self._on_cycle_retreat = False
|
||||
to_visit = super(ForestToParseTree, self).visit_packed_node_in(node)
|
||||
if not self.resolve_ambiguity or id(node.parent) not in self._successful_visits:
|
||||
if not self._use_cache or id(node) not in self._cache:
|
||||
return to_visit
|
||||
|
||||
def visit_packed_node_out(self, node):
|
||||
super(ForestToParseTree, self).visit_packed_node_out(node)
|
||||
if not self._on_cycle_retreat:
|
||||
self._successful_visits.add(id(node.parent))
|
||||
|
||||
def handles_ambiguity(func):
|
||||
"""Decorator for methods of subclasses of ``TreeForestTransformer``.
|
||||
Denotes that the method should receive a list of transformed derivations."""
|
||||
func.handles_ambiguity = True
|
||||
return func
|
||||
|
||||
class TreeForestTransformer(ForestToParseTree):
|
||||
"""A ``ForestTransformer`` with a tree ``Transformer``-like interface.
|
||||
By default, it will construct a tree.
|
||||
|
||||
Methods provided via inheritance are called based on the rule/symbol
|
||||
names of nodes in the forest.
|
||||
|
||||
Methods that act on rules will receive a list of the results of the
|
||||
transformations of the rule's children. By default, trees and tokens.
|
||||
|
||||
Methods that act on tokens will receive a token.
|
||||
|
||||
Alternatively, methods that act on rules may be annotated with
|
||||
``handles_ambiguity``. In this case, the function will receive a list
|
||||
of all the transformations of all the derivations of the rule.
|
||||
By default, a list of trees where each tree.data is equal to the
|
||||
rule name or one of its aliases.
|
||||
|
||||
Non-tree transformations are made possible by override of
|
||||
``__default__``, ``__default_token__``, and ``__default_ambig__``.
|
||||
|
||||
Note:
|
||||
Tree shaping features such as inlined rules and token filtering are
|
||||
not built into the transformation. Positions are also not propagated.
|
||||
|
||||
Parameters:
|
||||
tree_class: The tree class to use for construction
|
||||
prioritizer: A ``ForestVisitor`` that manipulates the priorities of nodes in the SPPF.
|
||||
resolve_ambiguity: If True, ambiguities will be resolved based on priorities.
|
||||
use_cache (bool): If True, caches the results of some transformations,
|
||||
potentially improving performance when ``resolve_ambiguity==False``.
|
||||
Only use if you know what you are doing: i.e. All transformation
|
||||
functions are pure and referentially transparent.
|
||||
"""
|
||||
|
||||
def __init__(self, tree_class=Tree, prioritizer=ForestSumVisitor(), resolve_ambiguity=True, use_cache=False):
|
||||
super(TreeForestTransformer, self).__init__(tree_class, dict(), prioritizer, resolve_ambiguity, use_cache)
|
||||
|
||||
def __default__(self, name, data):
|
||||
"""Default operation on tree (for override).
|
||||
|
||||
Returns a tree with name with data as children.
|
||||
"""
|
||||
return self.tree_class(name, data)
|
||||
|
||||
def __default_ambig__(self, name, data):
|
||||
"""Default operation on ambiguous rule (for override).
|
||||
|
||||
Wraps data in an '_ambig_' node if it contains more than
|
||||
one element.
|
||||
"""
|
||||
if len(data) > 1:
|
||||
return self.tree_class('_ambig', data)
|
||||
elif data:
|
||||
return data[0]
|
||||
return Discard
|
||||
|
||||
def __default_token__(self, node):
|
||||
"""Default operation on ``Token`` (for override).
|
||||
|
||||
Returns ``node``.
|
||||
"""
|
||||
return node
|
||||
|
||||
def transform_token_node(self, node):
|
||||
return getattr(self, node.type, self.__default_token__)(node)
|
||||
|
||||
def _call_rule_func(self, node, data):
|
||||
name = node.rule.alias or node.rule.options.template_source or node.rule.origin.name
|
||||
user_func = getattr(self, name, self.__default__)
|
||||
if user_func == self.__default__ or hasattr(user_func, 'handles_ambiguity'):
|
||||
user_func = partial(self.__default__, name)
|
||||
if not self.resolve_ambiguity:
|
||||
wrapper = partial(AmbiguousIntermediateExpander, self.tree_class)
|
||||
user_func = wrapper(user_func)
|
||||
return user_func(data)
|
||||
|
||||
def _call_ambig_func(self, node, data):
|
||||
name = node.s.name
|
||||
user_func = getattr(self, name, self.__default_ambig__)
|
||||
if user_func == self.__default_ambig__ or not hasattr(user_func, 'handles_ambiguity'):
|
||||
user_func = partial(self.__default_ambig__, name)
|
||||
return user_func(data)
|
||||
|
||||
class ForestToPyDotVisitor(ForestVisitor):
|
||||
"""
|
||||
A Forest visitor which writes the SPPF to a PNG.
|
||||
|
||||
The SPPF can get really large, really quickly because
|
||||
of the amount of meta-data it stores, so this is probably
|
||||
only useful for trivial trees and learning how the SPPF
|
||||
is structured.
|
||||
"""
|
||||
def __init__(self, rankdir="TB"):
|
||||
super(ForestToPyDotVisitor, self).__init__(single_visit=True)
|
||||
self.pydot = import_module('pydot')
|
||||
self.graph = self.pydot.Dot(graph_type='digraph', rankdir=rankdir)
|
||||
|
||||
def visit(self, root, filename):
|
||||
super(ForestToPyDotVisitor, self).visit(root)
|
||||
try:
|
||||
self.graph.write_png(filename)
|
||||
except FileNotFoundError as e:
|
||||
logger.error("Could not write png: ", e)
|
||||
|
||||
def visit_token_node(self, node):
|
||||
graph_node_id = str(id(node))
|
||||
graph_node_label = "\"{}\"".format(node.value.replace('"', '\\"'))
|
||||
graph_node_color = 0x808080
|
||||
graph_node_style = "\"filled,rounded\""
|
||||
graph_node_shape = "diamond"
|
||||
graph_node = self.pydot.Node(graph_node_id, style=graph_node_style, fillcolor="#{:06x}".format(graph_node_color), shape=graph_node_shape, label=graph_node_label)
|
||||
self.graph.add_node(graph_node)
|
||||
|
||||
def visit_packed_node_in(self, node):
|
||||
graph_node_id = str(id(node))
|
||||
graph_node_label = repr(node)
|
||||
graph_node_color = 0x808080
|
||||
graph_node_style = "filled"
|
||||
graph_node_shape = "diamond"
|
||||
graph_node = self.pydot.Node(graph_node_id, style=graph_node_style, fillcolor="#{:06x}".format(graph_node_color), shape=graph_node_shape, label=graph_node_label)
|
||||
self.graph.add_node(graph_node)
|
||||
yield node.left
|
||||
yield node.right
|
||||
|
||||
def visit_packed_node_out(self, node):
|
||||
graph_node_id = str(id(node))
|
||||
graph_node = self.graph.get_node(graph_node_id)[0]
|
||||
for child in [node.left, node.right]:
|
||||
if child is not None:
|
||||
child_graph_node_id = str(id(child.token if isinstance(child, TokenNode) else child))
|
||||
child_graph_node = self.graph.get_node(child_graph_node_id)[0]
|
||||
self.graph.add_edge(self.pydot.Edge(graph_node, child_graph_node))
|
||||
else:
|
||||
#### Try and be above the Python object ID range; probably impl. specific, but maybe this is okay.
|
||||
child_graph_node_id = str(randint(100000000000000000000000000000,123456789012345678901234567890))
|
||||
child_graph_node_style = "invis"
|
||||
child_graph_node = self.pydot.Node(child_graph_node_id, style=child_graph_node_style, label="None")
|
||||
child_edge_style = "invis"
|
||||
self.graph.add_node(child_graph_node)
|
||||
self.graph.add_edge(self.pydot.Edge(graph_node, child_graph_node, style=child_edge_style))
|
||||
|
||||
def visit_symbol_node_in(self, node):
|
||||
graph_node_id = str(id(node))
|
||||
graph_node_label = repr(node)
|
||||
graph_node_color = 0x808080
|
||||
graph_node_style = "\"filled\""
|
||||
if node.is_intermediate:
|
||||
graph_node_shape = "ellipse"
|
||||
else:
|
||||
graph_node_shape = "rectangle"
|
||||
graph_node = self.pydot.Node(graph_node_id, style=graph_node_style, fillcolor="#{:06x}".format(graph_node_color), shape=graph_node_shape, label=graph_node_label)
|
||||
self.graph.add_node(graph_node)
|
||||
return iter(node.children)
|
||||
|
||||
def visit_symbol_node_out(self, node):
|
||||
graph_node_id = str(id(node))
|
||||
graph_node = self.graph.get_node(graph_node_id)[0]
|
||||
for child in node.children:
|
||||
child_graph_node_id = str(id(child))
|
||||
child_graph_node = self.graph.get_node(child_graph_node_id)[0]
|
||||
self.graph.add_edge(self.pydot.Edge(graph_node, child_graph_node))
|
||||
|
|
@ -0,0 +1,185 @@
|
|||
from collections import Counter, defaultdict
|
||||
|
||||
from ..utils import bfs, fzset, classify
|
||||
from ..exceptions import GrammarError
|
||||
from ..grammar import Rule, Terminal, NonTerminal
|
||||
|
||||
|
||||
class RulePtr:
|
||||
__slots__ = ('rule', 'index')
|
||||
|
||||
def __init__(self, rule, index):
|
||||
assert isinstance(rule, Rule)
|
||||
assert index <= len(rule.expansion)
|
||||
self.rule = rule
|
||||
self.index = index
|
||||
|
||||
def __repr__(self):
|
||||
before = [x.name for x in self.rule.expansion[:self.index]]
|
||||
after = [x.name for x in self.rule.expansion[self.index:]]
|
||||
return '<%s : %s * %s>' % (self.rule.origin.name, ' '.join(before), ' '.join(after))
|
||||
|
||||
@property
|
||||
def next(self):
|
||||
return self.rule.expansion[self.index]
|
||||
|
||||
def advance(self, sym):
|
||||
assert self.next == sym
|
||||
return RulePtr(self.rule, self.index+1)
|
||||
|
||||
@property
|
||||
def is_satisfied(self):
|
||||
return self.index == len(self.rule.expansion)
|
||||
|
||||
def __eq__(self, other):
|
||||
return self.rule == other.rule and self.index == other.index
|
||||
def __hash__(self):
|
||||
return hash((self.rule, self.index))
|
||||
|
||||
|
||||
# state generation ensures no duplicate LR0ItemSets
|
||||
class LR0ItemSet:
|
||||
__slots__ = ('kernel', 'closure', 'transitions', 'lookaheads')
|
||||
|
||||
def __init__(self, kernel, closure):
|
||||
self.kernel = fzset(kernel)
|
||||
self.closure = fzset(closure)
|
||||
self.transitions = {}
|
||||
self.lookaheads = defaultdict(set)
|
||||
|
||||
def __repr__(self):
|
||||
return '{%s | %s}' % (', '.join([repr(r) for r in self.kernel]), ', '.join([repr(r) for r in self.closure]))
|
||||
|
||||
|
||||
def update_set(set1, set2):
|
||||
if not set2 or set1 > set2:
|
||||
return False
|
||||
|
||||
copy = set(set1)
|
||||
set1 |= set2
|
||||
return set1 != copy
|
||||
|
||||
def calculate_sets(rules):
|
||||
"""Calculate FOLLOW sets.
|
||||
|
||||
Adapted from: http://lara.epfl.ch/w/cc09:algorithm_for_first_and_follow_sets"""
|
||||
symbols = {sym for rule in rules for sym in rule.expansion} | {rule.origin for rule in rules}
|
||||
|
||||
# foreach grammar rule X ::= Y(1) ... Y(k)
|
||||
# if k=0 or {Y(1),...,Y(k)} subset of NULLABLE then
|
||||
# NULLABLE = NULLABLE union {X}
|
||||
# for i = 1 to k
|
||||
# if i=1 or {Y(1),...,Y(i-1)} subset of NULLABLE then
|
||||
# FIRST(X) = FIRST(X) union FIRST(Y(i))
|
||||
# for j = i+1 to k
|
||||
# if i=k or {Y(i+1),...Y(k)} subset of NULLABLE then
|
||||
# FOLLOW(Y(i)) = FOLLOW(Y(i)) union FOLLOW(X)
|
||||
# if i+1=j or {Y(i+1),...,Y(j-1)} subset of NULLABLE then
|
||||
# FOLLOW(Y(i)) = FOLLOW(Y(i)) union FIRST(Y(j))
|
||||
# until none of NULLABLE,FIRST,FOLLOW changed in last iteration
|
||||
|
||||
NULLABLE = set()
|
||||
FIRST = {}
|
||||
FOLLOW = {}
|
||||
for sym in symbols:
|
||||
FIRST[sym]={sym} if sym.is_term else set()
|
||||
FOLLOW[sym]=set()
|
||||
|
||||
# Calculate NULLABLE and FIRST
|
||||
changed = True
|
||||
while changed:
|
||||
changed = False
|
||||
|
||||
for rule in rules:
|
||||
if set(rule.expansion) <= NULLABLE:
|
||||
if update_set(NULLABLE, {rule.origin}):
|
||||
changed = True
|
||||
|
||||
for i, sym in enumerate(rule.expansion):
|
||||
if set(rule.expansion[:i]) <= NULLABLE:
|
||||
if update_set(FIRST[rule.origin], FIRST[sym]):
|
||||
changed = True
|
||||
else:
|
||||
break
|
||||
|
||||
# Calculate FOLLOW
|
||||
changed = True
|
||||
while changed:
|
||||
changed = False
|
||||
|
||||
for rule in rules:
|
||||
for i, sym in enumerate(rule.expansion):
|
||||
if i==len(rule.expansion)-1 or set(rule.expansion[i+1:]) <= NULLABLE:
|
||||
if update_set(FOLLOW[sym], FOLLOW[rule.origin]):
|
||||
changed = True
|
||||
|
||||
for j in range(i+1, len(rule.expansion)):
|
||||
if set(rule.expansion[i+1:j]) <= NULLABLE:
|
||||
if update_set(FOLLOW[sym], FIRST[rule.expansion[j]]):
|
||||
changed = True
|
||||
|
||||
return FIRST, FOLLOW, NULLABLE
|
||||
|
||||
|
||||
class GrammarAnalyzer:
|
||||
def __init__(self, parser_conf, debug=False):
|
||||
self.debug = debug
|
||||
|
||||
root_rules = {start: Rule(NonTerminal('$root_' + start), [NonTerminal(start), Terminal('$END')])
|
||||
for start in parser_conf.start}
|
||||
|
||||
rules = parser_conf.rules + list(root_rules.values())
|
||||
self.rules_by_origin = classify(rules, lambda r: r.origin)
|
||||
|
||||
if len(rules) != len(set(rules)):
|
||||
duplicates = [item for item, count in Counter(rules).items() if count > 1]
|
||||
raise GrammarError("Rules defined twice: %s" % ', '.join(str(i) for i in duplicates))
|
||||
|
||||
for r in rules:
|
||||
for sym in r.expansion:
|
||||
if not (sym.is_term or sym in self.rules_by_origin):
|
||||
raise GrammarError("Using an undefined rule: %s" % sym)
|
||||
|
||||
self.start_states = {start: self.expand_rule(root_rule.origin)
|
||||
for start, root_rule in root_rules.items()}
|
||||
|
||||
self.end_states = {start: fzset({RulePtr(root_rule, len(root_rule.expansion))})
|
||||
for start, root_rule in root_rules.items()}
|
||||
|
||||
lr0_root_rules = {start: Rule(NonTerminal('$root_' + start), [NonTerminal(start)])
|
||||
for start in parser_conf.start}
|
||||
|
||||
lr0_rules = parser_conf.rules + list(lr0_root_rules.values())
|
||||
assert(len(lr0_rules) == len(set(lr0_rules)))
|
||||
|
||||
self.lr0_rules_by_origin = classify(lr0_rules, lambda r: r.origin)
|
||||
|
||||
# cache RulePtr(r, 0) in r (no duplicate RulePtr objects)
|
||||
self.lr0_start_states = {start: LR0ItemSet([RulePtr(root_rule, 0)], self.expand_rule(root_rule.origin, self.lr0_rules_by_origin))
|
||||
for start, root_rule in lr0_root_rules.items()}
|
||||
|
||||
self.FIRST, self.FOLLOW, self.NULLABLE = calculate_sets(rules)
|
||||
|
||||
def expand_rule(self, source_rule, rules_by_origin=None):
|
||||
"Returns all init_ptrs accessible by rule (recursive)"
|
||||
|
||||
if rules_by_origin is None:
|
||||
rules_by_origin = self.rules_by_origin
|
||||
|
||||
init_ptrs = set()
|
||||
def _expand_rule(rule):
|
||||
assert not rule.is_term, rule
|
||||
|
||||
for r in rules_by_origin[rule]:
|
||||
init_ptr = RulePtr(r, 0)
|
||||
init_ptrs.add(init_ptr)
|
||||
|
||||
if r.expansion: # if not empty rule
|
||||
new_r = init_ptr.next
|
||||
if not new_r.is_term:
|
||||
yield new_r
|
||||
|
||||
for _ in bfs([source_rule], _expand_rule):
|
||||
pass
|
||||
|
||||
return fzset(init_ptrs)
|
||||
|
|
@ -0,0 +1,303 @@
|
|||
"""This module builds a LALR(1) transition-table for lalr_parser.py
|
||||
|
||||
For now, shift/reduce conflicts are automatically resolved as shifts.
|
||||
"""
|
||||
|
||||
# Author: Erez Shinan (2017)
|
||||
# Email : erezshin@gmail.com
|
||||
|
||||
from collections import defaultdict
|
||||
|
||||
from ..utils import classify, classify_bool, bfs, fzset, Enumerator, logger
|
||||
from ..exceptions import GrammarError
|
||||
|
||||
from .grammar_analysis import GrammarAnalyzer, Terminal, LR0ItemSet
|
||||
from ..grammar import Rule
|
||||
|
||||
###{standalone
|
||||
|
||||
class Action:
|
||||
def __init__(self, name):
|
||||
self.name = name
|
||||
def __str__(self):
|
||||
return self.name
|
||||
def __repr__(self):
|
||||
return str(self)
|
||||
|
||||
Shift = Action('Shift')
|
||||
Reduce = Action('Reduce')
|
||||
|
||||
|
||||
class ParseTable:
|
||||
def __init__(self, states, start_states, end_states):
|
||||
self.states = states
|
||||
self.start_states = start_states
|
||||
self.end_states = end_states
|
||||
|
||||
def serialize(self, memo):
|
||||
tokens = Enumerator()
|
||||
|
||||
states = {
|
||||
state: {tokens.get(token): ((1, arg.serialize(memo)) if action is Reduce else (0, arg))
|
||||
for token, (action, arg) in actions.items()}
|
||||
for state, actions in self.states.items()
|
||||
}
|
||||
|
||||
return {
|
||||
'tokens': tokens.reversed(),
|
||||
'states': states,
|
||||
'start_states': self.start_states,
|
||||
'end_states': self.end_states,
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def deserialize(cls, data, memo):
|
||||
tokens = data['tokens']
|
||||
states = {
|
||||
state: {tokens[token]: ((Reduce, Rule.deserialize(arg, memo)) if action==1 else (Shift, arg))
|
||||
for token, (action, arg) in actions.items()}
|
||||
for state, actions in data['states'].items()
|
||||
}
|
||||
return cls(states, data['start_states'], data['end_states'])
|
||||
|
||||
|
||||
class IntParseTable(ParseTable):
|
||||
|
||||
@classmethod
|
||||
def from_ParseTable(cls, parse_table):
|
||||
enum = list(parse_table.states)
|
||||
state_to_idx = {s:i for i,s in enumerate(enum)}
|
||||
int_states = {}
|
||||
|
||||
for s, la in parse_table.states.items():
|
||||
la = {k:(v[0], state_to_idx[v[1]]) if v[0] is Shift else v
|
||||
for k,v in la.items()}
|
||||
int_states[ state_to_idx[s] ] = la
|
||||
|
||||
|
||||
start_states = {start:state_to_idx[s] for start, s in parse_table.start_states.items()}
|
||||
end_states = {start:state_to_idx[s] for start, s in parse_table.end_states.items()}
|
||||
return cls(int_states, start_states, end_states)
|
||||
|
||||
###}
|
||||
|
||||
|
||||
# digraph and traverse, see The Theory and Practice of Compiler Writing
|
||||
|
||||
# computes F(x) = G(x) union (union { G(y) | x R y })
|
||||
# X: nodes
|
||||
# R: relation (function mapping node -> list of nodes that satisfy the relation)
|
||||
# G: set valued function
|
||||
def digraph(X, R, G):
|
||||
F = {}
|
||||
S = []
|
||||
N = {}
|
||||
for x in X:
|
||||
N[x] = 0
|
||||
for x in X:
|
||||
# this is always true for the first iteration, but N[x] may be updated in traverse below
|
||||
if N[x] == 0:
|
||||
traverse(x, S, N, X, R, G, F)
|
||||
return F
|
||||
|
||||
# x: single node
|
||||
# S: stack
|
||||
# N: weights
|
||||
# X: nodes
|
||||
# R: relation (see above)
|
||||
# G: set valued function
|
||||
# F: set valued function we are computing (map of input -> output)
|
||||
def traverse(x, S, N, X, R, G, F):
|
||||
S.append(x)
|
||||
d = len(S)
|
||||
N[x] = d
|
||||
F[x] = G[x]
|
||||
for y in R[x]:
|
||||
if N[y] == 0:
|
||||
traverse(y, S, N, X, R, G, F)
|
||||
n_x = N[x]
|
||||
assert(n_x > 0)
|
||||
n_y = N[y]
|
||||
assert(n_y != 0)
|
||||
if (n_y > 0) and (n_y < n_x):
|
||||
N[x] = n_y
|
||||
F[x].update(F[y])
|
||||
if N[x] == d:
|
||||
f_x = F[x]
|
||||
while True:
|
||||
z = S.pop()
|
||||
N[z] = -1
|
||||
F[z] = f_x
|
||||
if z == x:
|
||||
break
|
||||
|
||||
|
||||
class LALR_Analyzer(GrammarAnalyzer):
|
||||
def __init__(self, parser_conf, debug=False):
|
||||
GrammarAnalyzer.__init__(self, parser_conf, debug)
|
||||
self.nonterminal_transitions = []
|
||||
self.directly_reads = defaultdict(set)
|
||||
self.reads = defaultdict(set)
|
||||
self.includes = defaultdict(set)
|
||||
self.lookback = defaultdict(set)
|
||||
|
||||
|
||||
def compute_lr0_states(self):
|
||||
self.lr0_states = set()
|
||||
# map of kernels to LR0ItemSets
|
||||
cache = {}
|
||||
|
||||
def step(state):
|
||||
_, unsat = classify_bool(state.closure, lambda rp: rp.is_satisfied)
|
||||
|
||||
d = classify(unsat, lambda rp: rp.next)
|
||||
for sym, rps in d.items():
|
||||
kernel = fzset({rp.advance(sym) for rp in rps})
|
||||
new_state = cache.get(kernel, None)
|
||||
if new_state is None:
|
||||
closure = set(kernel)
|
||||
for rp in kernel:
|
||||
if not rp.is_satisfied and not rp.next.is_term:
|
||||
closure |= self.expand_rule(rp.next, self.lr0_rules_by_origin)
|
||||
new_state = LR0ItemSet(kernel, closure)
|
||||
cache[kernel] = new_state
|
||||
|
||||
state.transitions[sym] = new_state
|
||||
yield new_state
|
||||
|
||||
self.lr0_states.add(state)
|
||||
|
||||
for _ in bfs(self.lr0_start_states.values(), step):
|
||||
pass
|
||||
|
||||
def compute_reads_relations(self):
|
||||
# handle start state
|
||||
for root in self.lr0_start_states.values():
|
||||
assert(len(root.kernel) == 1)
|
||||
for rp in root.kernel:
|
||||
assert(rp.index == 0)
|
||||
self.directly_reads[(root, rp.next)] = set([ Terminal('$END') ])
|
||||
|
||||
for state in self.lr0_states:
|
||||
seen = set()
|
||||
for rp in state.closure:
|
||||
if rp.is_satisfied:
|
||||
continue
|
||||
s = rp.next
|
||||
# if s is a not a nonterminal
|
||||
if s not in self.lr0_rules_by_origin:
|
||||
continue
|
||||
if s in seen:
|
||||
continue
|
||||
seen.add(s)
|
||||
nt = (state, s)
|
||||
self.nonterminal_transitions.append(nt)
|
||||
dr = self.directly_reads[nt]
|
||||
r = self.reads[nt]
|
||||
next_state = state.transitions[s]
|
||||
for rp2 in next_state.closure:
|
||||
if rp2.is_satisfied:
|
||||
continue
|
||||
s2 = rp2.next
|
||||
# if s2 is a terminal
|
||||
if s2 not in self.lr0_rules_by_origin:
|
||||
dr.add(s2)
|
||||
if s2 in self.NULLABLE:
|
||||
r.add((next_state, s2))
|
||||
|
||||
def compute_includes_lookback(self):
|
||||
for nt in self.nonterminal_transitions:
|
||||
state, nonterminal = nt
|
||||
includes = []
|
||||
lookback = self.lookback[nt]
|
||||
for rp in state.closure:
|
||||
if rp.rule.origin != nonterminal:
|
||||
continue
|
||||
# traverse the states for rp(.rule)
|
||||
state2 = state
|
||||
for i in range(rp.index, len(rp.rule.expansion)):
|
||||
s = rp.rule.expansion[i]
|
||||
nt2 = (state2, s)
|
||||
state2 = state2.transitions[s]
|
||||
if nt2 not in self.reads:
|
||||
continue
|
||||
for j in range(i + 1, len(rp.rule.expansion)):
|
||||
if not rp.rule.expansion[j] in self.NULLABLE:
|
||||
break
|
||||
else:
|
||||
includes.append(nt2)
|
||||
# state2 is at the final state for rp.rule
|
||||
if rp.index == 0:
|
||||
for rp2 in state2.closure:
|
||||
if (rp2.rule == rp.rule) and rp2.is_satisfied:
|
||||
lookback.add((state2, rp2.rule))
|
||||
for nt2 in includes:
|
||||
self.includes[nt2].add(nt)
|
||||
|
||||
def compute_lookaheads(self):
|
||||
read_sets = digraph(self.nonterminal_transitions, self.reads, self.directly_reads)
|
||||
follow_sets = digraph(self.nonterminal_transitions, self.includes, read_sets)
|
||||
|
||||
for nt, lookbacks in self.lookback.items():
|
||||
for state, rule in lookbacks:
|
||||
for s in follow_sets[nt]:
|
||||
state.lookaheads[s].add(rule)
|
||||
|
||||
def compute_lalr1_states(self):
|
||||
m = {}
|
||||
reduce_reduce = []
|
||||
for state in self.lr0_states:
|
||||
actions = {}
|
||||
for la, next_state in state.transitions.items():
|
||||
actions[la] = (Shift, next_state.closure)
|
||||
for la, rules in state.lookaheads.items():
|
||||
if len(rules) > 1:
|
||||
# Try to resolve conflict based on priority
|
||||
p = [(r.options.priority or 0, r) for r in rules]
|
||||
p.sort(key=lambda r: r[0], reverse=True)
|
||||
best, second_best = p[:2]
|
||||
if best[0] > second_best[0]:
|
||||
rules = [best[1]]
|
||||
else:
|
||||
reduce_reduce.append((state, la, rules))
|
||||
if la in actions:
|
||||
if self.debug:
|
||||
logger.warning('Shift/Reduce conflict for terminal %s: (resolving as shift)', la.name)
|
||||
logger.warning(' * %s', list(rules)[0])
|
||||
else:
|
||||
actions[la] = (Reduce, list(rules)[0])
|
||||
m[state] = { k.name: v for k, v in actions.items() }
|
||||
|
||||
if reduce_reduce:
|
||||
msgs = []
|
||||
for state, la, rules in reduce_reduce:
|
||||
msg = 'Reduce/Reduce collision in %s between the following rules: %s' % (la, ''.join([ '\n\t- ' + str(r) for r in rules ]))
|
||||
if self.debug:
|
||||
msg += '\n collision occurred in state: {%s\n }' % ''.join(['\n\t' + str(x) for x in state.closure])
|
||||
msgs.append(msg)
|
||||
raise GrammarError('\n\n'.join(msgs))
|
||||
|
||||
states = { k.closure: v for k, v in m.items() }
|
||||
|
||||
# compute end states
|
||||
end_states = {}
|
||||
for state in states:
|
||||
for rp in state:
|
||||
for start in self.lr0_start_states:
|
||||
if rp.rule.origin.name == ('$root_' + start) and rp.is_satisfied:
|
||||
assert(start not in end_states)
|
||||
end_states[start] = state
|
||||
|
||||
_parse_table = ParseTable(states, { start: state.closure for start, state in self.lr0_start_states.items() }, end_states)
|
||||
|
||||
if self.debug:
|
||||
self.parse_table = _parse_table
|
||||
else:
|
||||
self.parse_table = IntParseTable.from_ParseTable(_parse_table)
|
||||
|
||||
def compute_lalr(self):
|
||||
self.compute_lr0_states()
|
||||
self.compute_reads_relations()
|
||||
self.compute_includes_lookback()
|
||||
self.compute_lookaheads()
|
||||
self.compute_lalr1_states()
|
||||
|
|
@ -0,0 +1,148 @@
|
|||
# This module provides a LALR interactive parser, which is used for debugging and error handling
|
||||
|
||||
from typing import Iterator, List
|
||||
from copy import copy
|
||||
import warnings
|
||||
|
||||
from lark.exceptions import UnexpectedToken
|
||||
from lark.lexer import Token, LexerThread
|
||||
|
||||
|
||||
class InteractiveParser:
|
||||
"""InteractiveParser gives you advanced control over parsing and error handling when parsing with LALR.
|
||||
|
||||
For a simpler interface, see the ``on_error`` argument to ``Lark.parse()``.
|
||||
"""
|
||||
def __init__(self, parser, parser_state, lexer_thread: LexerThread):
|
||||
self.parser = parser
|
||||
self.parser_state = parser_state
|
||||
self.lexer_thread = lexer_thread
|
||||
self.result = None
|
||||
|
||||
@property
|
||||
def lexer_state(self) -> LexerThread:
|
||||
warnings.warn("lexer_state will be removed in subsequent releases. Use lexer_thread instead.", DeprecationWarning)
|
||||
return self.lexer_thread
|
||||
|
||||
def feed_token(self, token: Token):
|
||||
"""Feed the parser with a token, and advance it to the next state, as if it received it from the lexer.
|
||||
|
||||
Note that ``token`` has to be an instance of ``Token``.
|
||||
"""
|
||||
return self.parser_state.feed_token(token, token.type == '$END')
|
||||
|
||||
def iter_parse(self) -> Iterator[Token]:
|
||||
"""Step through the different stages of the parse, by reading tokens from the lexer
|
||||
and feeding them to the parser, one per iteration.
|
||||
|
||||
Returns an iterator of the tokens it encounters.
|
||||
|
||||
When the parse is over, the resulting tree can be found in ``InteractiveParser.result``.
|
||||
"""
|
||||
for token in self.lexer_thread.lex(self.parser_state):
|
||||
yield token
|
||||
self.result = self.feed_token(token)
|
||||
|
||||
def exhaust_lexer(self) -> List[Token]:
|
||||
"""Try to feed the rest of the lexer state into the interactive parser.
|
||||
|
||||
Note that this modifies the instance in place and does not feed an '$END' Token
|
||||
"""
|
||||
return list(self.iter_parse())
|
||||
|
||||
|
||||
def feed_eof(self, last_token=None):
|
||||
"""Feed a '$END' Token. Borrows from 'last_token' if given."""
|
||||
eof = Token.new_borrow_pos('$END', '', last_token) if last_token is not None else self.lexer_thread._Token('$END', '', 0, 1, 1)
|
||||
return self.feed_token(eof)
|
||||
|
||||
|
||||
def __copy__(self):
|
||||
"""Create a new interactive parser with a separate state.
|
||||
|
||||
Calls to feed_token() won't affect the old instance, and vice-versa.
|
||||
"""
|
||||
return type(self)(
|
||||
self.parser,
|
||||
copy(self.parser_state),
|
||||
copy(self.lexer_thread),
|
||||
)
|
||||
|
||||
def copy(self):
|
||||
return copy(self)
|
||||
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, InteractiveParser):
|
||||
return False
|
||||
|
||||
return self.parser_state == other.parser_state and self.lexer_thread == other.lexer_thread
|
||||
|
||||
def as_immutable(self):
|
||||
"""Convert to an ``ImmutableInteractiveParser``."""
|
||||
p = copy(self)
|
||||
return ImmutableInteractiveParser(p.parser, p.parser_state, p.lexer_thread)
|
||||
|
||||
def pretty(self):
|
||||
"""Print the output of ``choices()`` in a way that's easier to read."""
|
||||
out = ["Parser choices:"]
|
||||
for k, v in self.choices().items():
|
||||
out.append('\t- %s -> %r' % (k, v))
|
||||
out.append('stack size: %s' % len(self.parser_state.state_stack))
|
||||
return '\n'.join(out)
|
||||
|
||||
def choices(self):
|
||||
"""Returns a dictionary of token types, matched to their action in the parser.
|
||||
|
||||
Only returns token types that are accepted by the current state.
|
||||
|
||||
Updated by ``feed_token()``.
|
||||
"""
|
||||
return self.parser_state.parse_conf.parse_table.states[self.parser_state.position]
|
||||
|
||||
def accepts(self):
|
||||
"""Returns the set of possible tokens that will advance the parser into a new valid state."""
|
||||
accepts = set()
|
||||
for t in self.choices():
|
||||
if t.isupper(): # is terminal?
|
||||
new_cursor = copy(self)
|
||||
try:
|
||||
new_cursor.feed_token(self.lexer_thread._Token(t, ''))
|
||||
except UnexpectedToken:
|
||||
pass
|
||||
else:
|
||||
accepts.add(t)
|
||||
return accepts
|
||||
|
||||
def resume_parse(self):
|
||||
"""Resume automated parsing from the current state."""
|
||||
return self.parser.parse_from_state(self.parser_state)
|
||||
|
||||
|
||||
|
||||
class ImmutableInteractiveParser(InteractiveParser):
|
||||
"""Same as ``InteractiveParser``, but operations create a new instance instead
|
||||
of changing it in-place.
|
||||
"""
|
||||
|
||||
result = None
|
||||
|
||||
def __hash__(self):
|
||||
return hash((self.parser_state, self.lexer_thread))
|
||||
|
||||
def feed_token(self, token):
|
||||
c = copy(self)
|
||||
c.result = InteractiveParser.feed_token(c, token)
|
||||
return c
|
||||
|
||||
def exhaust_lexer(self):
|
||||
"""Try to feed the rest of the lexer state into the parser.
|
||||
|
||||
Note that this returns a new ImmutableInteractiveParser and does not feed an '$END' Token"""
|
||||
cursor = self.as_mutable()
|
||||
cursor.exhaust_lexer()
|
||||
return cursor.as_immutable()
|
||||
|
||||
def as_mutable(self):
|
||||
"""Convert to an ``InteractiveParser``."""
|
||||
p = copy(self)
|
||||
return InteractiveParser(p.parser, p.parser_state, p.lexer_thread)
|
||||
|
|
@ -0,0 +1,199 @@
|
|||
"""This module implements a LALR(1) Parser
|
||||
"""
|
||||
# Author: Erez Shinan (2017)
|
||||
# Email : erezshin@gmail.com
|
||||
from copy import deepcopy, copy
|
||||
from typing import Dict, Any
|
||||
from ..lexer import Token
|
||||
from ..utils import Serialize
|
||||
|
||||
from .lalr_analysis import LALR_Analyzer, Shift, Reduce, IntParseTable
|
||||
from .lalr_interactive_parser import InteractiveParser
|
||||
from lark.exceptions import UnexpectedCharacters, UnexpectedInput, UnexpectedToken
|
||||
|
||||
###{standalone
|
||||
|
||||
class LALR_Parser(Serialize):
|
||||
def __init__(self, parser_conf, debug=False):
|
||||
analysis = LALR_Analyzer(parser_conf, debug=debug)
|
||||
analysis.compute_lalr()
|
||||
callbacks = parser_conf.callbacks
|
||||
|
||||
self._parse_table = analysis.parse_table
|
||||
self.parser_conf = parser_conf
|
||||
self.parser = _Parser(analysis.parse_table, callbacks, debug)
|
||||
|
||||
@classmethod
|
||||
def deserialize(cls, data, memo, callbacks, debug=False):
|
||||
inst = cls.__new__(cls)
|
||||
inst._parse_table = IntParseTable.deserialize(data, memo)
|
||||
inst.parser = _Parser(inst._parse_table, callbacks, debug)
|
||||
return inst
|
||||
|
||||
def serialize(self, memo: Any = None) -> Dict[str, Any]:
|
||||
return self._parse_table.serialize(memo)
|
||||
|
||||
def parse_interactive(self, lexer, start):
|
||||
return self.parser.parse(lexer, start, start_interactive=True)
|
||||
|
||||
def parse(self, lexer, start, on_error=None):
|
||||
try:
|
||||
return self.parser.parse(lexer, start)
|
||||
except UnexpectedInput as e:
|
||||
if on_error is None:
|
||||
raise
|
||||
|
||||
while True:
|
||||
if isinstance(e, UnexpectedCharacters):
|
||||
s = e.interactive_parser.lexer_thread.state
|
||||
p = s.line_ctr.char_pos
|
||||
|
||||
if not on_error(e):
|
||||
raise e
|
||||
|
||||
if isinstance(e, UnexpectedCharacters):
|
||||
# If user didn't change the character position, then we should
|
||||
if p == s.line_ctr.char_pos:
|
||||
s.line_ctr.feed(s.text[p:p+1])
|
||||
|
||||
try:
|
||||
return e.interactive_parser.resume_parse()
|
||||
except UnexpectedToken as e2:
|
||||
if (isinstance(e, UnexpectedToken)
|
||||
and e.token.type == e2.token.type == '$END'
|
||||
and e.interactive_parser == e2.interactive_parser):
|
||||
# Prevent infinite loop
|
||||
raise e2
|
||||
e = e2
|
||||
except UnexpectedCharacters as e2:
|
||||
e = e2
|
||||
|
||||
|
||||
class ParseConf:
|
||||
__slots__ = 'parse_table', 'callbacks', 'start', 'start_state', 'end_state', 'states'
|
||||
|
||||
def __init__(self, parse_table, callbacks, start):
|
||||
self.parse_table = parse_table
|
||||
|
||||
self.start_state = self.parse_table.start_states[start]
|
||||
self.end_state = self.parse_table.end_states[start]
|
||||
self.states = self.parse_table.states
|
||||
|
||||
self.callbacks = callbacks
|
||||
self.start = start
|
||||
|
||||
|
||||
class ParserState:
|
||||
__slots__ = 'parse_conf', 'lexer', 'state_stack', 'value_stack'
|
||||
|
||||
def __init__(self, parse_conf, lexer, state_stack=None, value_stack=None):
|
||||
self.parse_conf = parse_conf
|
||||
self.lexer = lexer
|
||||
self.state_stack = state_stack or [self.parse_conf.start_state]
|
||||
self.value_stack = value_stack or []
|
||||
|
||||
@property
|
||||
def position(self):
|
||||
return self.state_stack[-1]
|
||||
|
||||
# Necessary for match_examples() to work
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, ParserState):
|
||||
return NotImplemented
|
||||
return len(self.state_stack) == len(other.state_stack) and self.position == other.position
|
||||
|
||||
def __copy__(self):
|
||||
return type(self)(
|
||||
self.parse_conf,
|
||||
self.lexer, # XXX copy
|
||||
copy(self.state_stack),
|
||||
deepcopy(self.value_stack),
|
||||
)
|
||||
|
||||
def copy(self):
|
||||
return copy(self)
|
||||
|
||||
def feed_token(self, token, is_end=False):
|
||||
state_stack = self.state_stack
|
||||
value_stack = self.value_stack
|
||||
states = self.parse_conf.states
|
||||
end_state = self.parse_conf.end_state
|
||||
callbacks = self.parse_conf.callbacks
|
||||
|
||||
while True:
|
||||
state = state_stack[-1]
|
||||
try:
|
||||
action, arg = states[state][token.type]
|
||||
except KeyError:
|
||||
expected = {s for s in states[state].keys() if s.isupper()}
|
||||
raise UnexpectedToken(token, expected, state=self, interactive_parser=None)
|
||||
|
||||
assert arg != end_state
|
||||
|
||||
if action is Shift:
|
||||
# shift once and return
|
||||
assert not is_end
|
||||
state_stack.append(arg)
|
||||
value_stack.append(token if token.type not in callbacks else callbacks[token.type](token))
|
||||
return
|
||||
else:
|
||||
# reduce+shift as many times as necessary
|
||||
rule = arg
|
||||
size = len(rule.expansion)
|
||||
if size:
|
||||
s = value_stack[-size:]
|
||||
del state_stack[-size:]
|
||||
del value_stack[-size:]
|
||||
else:
|
||||
s = []
|
||||
|
||||
value = callbacks[rule](s)
|
||||
|
||||
_action, new_state = states[state_stack[-1]][rule.origin.name]
|
||||
assert _action is Shift
|
||||
state_stack.append(new_state)
|
||||
value_stack.append(value)
|
||||
|
||||
if is_end and state_stack[-1] == end_state:
|
||||
return value_stack[-1]
|
||||
|
||||
class _Parser:
|
||||
def __init__(self, parse_table, callbacks, debug=False):
|
||||
self.parse_table = parse_table
|
||||
self.callbacks = callbacks
|
||||
self.debug = debug
|
||||
|
||||
def parse(self, lexer, start, value_stack=None, state_stack=None, start_interactive=False):
|
||||
parse_conf = ParseConf(self.parse_table, self.callbacks, start)
|
||||
parser_state = ParserState(parse_conf, lexer, state_stack, value_stack)
|
||||
if start_interactive:
|
||||
return InteractiveParser(self, parser_state, parser_state.lexer)
|
||||
return self.parse_from_state(parser_state)
|
||||
|
||||
|
||||
def parse_from_state(self, state):
|
||||
# Main LALR-parser loop
|
||||
try:
|
||||
token = None
|
||||
for token in state.lexer.lex(state):
|
||||
state.feed_token(token)
|
||||
|
||||
end_token = Token.new_borrow_pos('$END', '', token) if token else Token('$END', '', 0, 1, 1)
|
||||
return state.feed_token(end_token, True)
|
||||
except UnexpectedInput as e:
|
||||
try:
|
||||
e.interactive_parser = InteractiveParser(self, state, state.lexer)
|
||||
except NameError:
|
||||
pass
|
||||
raise e
|
||||
except Exception as e:
|
||||
if self.debug:
|
||||
print("")
|
||||
print("STATE STACK DUMP")
|
||||
print("----------------")
|
||||
for i, s in enumerate(state.state_stack):
|
||||
print('%d)' % i , s)
|
||||
print("")
|
||||
|
||||
raise
|
||||
###}
|
||||
|
|
@ -0,0 +1,109 @@
|
|||
from ..utils import compare
|
||||
from functools import cmp_to_key
|
||||
|
||||
from ..tree import Tree
|
||||
|
||||
|
||||
# Standard ambiguity resolver (uses comparison)
|
||||
#
|
||||
# Author: Erez Sh
|
||||
|
||||
def _compare_rules(rule1, rule2):
|
||||
return -compare( len(rule1.expansion), len(rule2.expansion))
|
||||
|
||||
def _sum_priority(tree):
|
||||
p = 0
|
||||
|
||||
for n in tree.iter_subtrees():
|
||||
try:
|
||||
p += n.meta.rule.options.priority or 0
|
||||
except AttributeError:
|
||||
pass
|
||||
|
||||
return p
|
||||
|
||||
def _compare_priority(tree1, tree2):
|
||||
tree1.iter_subtrees()
|
||||
|
||||
def _compare_drv(tree1, tree2):
|
||||
try:
|
||||
rule1 = tree1.meta.rule
|
||||
except AttributeError:
|
||||
rule1 = None
|
||||
|
||||
try:
|
||||
rule2 = tree2.meta.rule
|
||||
except AttributeError:
|
||||
rule2 = None
|
||||
|
||||
if None == rule1 == rule2:
|
||||
return compare(tree1, tree2)
|
||||
elif rule1 is None:
|
||||
return -1
|
||||
elif rule2 is None:
|
||||
return 1
|
||||
|
||||
assert tree1.data != '_ambig'
|
||||
assert tree2.data != '_ambig'
|
||||
|
||||
p1 = _sum_priority(tree1)
|
||||
p2 = _sum_priority(tree2)
|
||||
c = (p1 or p2) and compare(p1, p2)
|
||||
if c:
|
||||
return c
|
||||
|
||||
c = _compare_rules(tree1.meta.rule, tree2.meta.rule)
|
||||
if c:
|
||||
return c
|
||||
|
||||
# rules are "equal", so compare trees
|
||||
if len(tree1.children) == len(tree2.children):
|
||||
for t1, t2 in zip(tree1.children, tree2.children):
|
||||
c = _compare_drv(t1, t2)
|
||||
if c:
|
||||
return c
|
||||
|
||||
return compare(len(tree1.children), len(tree2.children))
|
||||
|
||||
|
||||
def _standard_resolve_ambig(tree):
|
||||
assert tree.data == '_ambig'
|
||||
key_f = cmp_to_key(_compare_drv)
|
||||
best = max(tree.children, key=key_f)
|
||||
assert best.data == 'drv'
|
||||
tree.set('drv', best.children)
|
||||
tree.meta.rule = best.meta.rule # needed for applying callbacks
|
||||
|
||||
def standard_resolve_ambig(tree):
|
||||
for ambig in tree.find_data('_ambig'):
|
||||
_standard_resolve_ambig(ambig)
|
||||
|
||||
return tree
|
||||
|
||||
|
||||
|
||||
|
||||
# Anti-score Sum
|
||||
#
|
||||
# Author: Uriva (https://github.com/uriva)
|
||||
|
||||
def _antiscore_sum_drv(tree):
|
||||
if not isinstance(tree, Tree):
|
||||
return 0
|
||||
|
||||
assert tree.data != '_ambig'
|
||||
|
||||
return _sum_priority(tree)
|
||||
|
||||
def _antiscore_sum_resolve_ambig(tree):
|
||||
assert tree.data == '_ambig'
|
||||
best = min(tree.children, key=_antiscore_sum_drv)
|
||||
assert best.data == 'drv'
|
||||
tree.set('drv', best.children)
|
||||
tree.meta.rule = best.meta.rule # needed for applying callbacks
|
||||
|
||||
def antiscore_sum_resolve_ambig(tree):
|
||||
for ambig in tree.find_data('_ambig'):
|
||||
_antiscore_sum_resolve_ambig(ambig)
|
||||
|
||||
return tree
|
||||
|
|
@ -0,0 +1,159 @@
|
|||
"""This module implements an experimental Earley parser with a dynamic lexer
|
||||
|
||||
The core Earley algorithm used here is based on Elizabeth Scott's implementation, here:
|
||||
https://www.sciencedirect.com/science/article/pii/S1571066108001497
|
||||
|
||||
That is probably the best reference for understanding the algorithm here.
|
||||
|
||||
The Earley parser outputs an SPPF-tree as per that document. The SPPF tree format
|
||||
is better documented here:
|
||||
http://www.bramvandersanden.com/post/2014/06/shared-packed-parse-forest/
|
||||
|
||||
Instead of running a lexer beforehand, or using a costy char-by-char method, this parser
|
||||
uses regular expressions by necessity, achieving high-performance while maintaining all of
|
||||
Earley's power in parsing any CFG.
|
||||
"""
|
||||
|
||||
from collections import defaultdict
|
||||
|
||||
from ..tree import Tree
|
||||
from ..exceptions import UnexpectedCharacters
|
||||
from ..lexer import Token
|
||||
from ..grammar import Terminal
|
||||
from .earley import Parser as BaseParser
|
||||
from .earley_forest import SymbolNode, TokenNode
|
||||
|
||||
|
||||
class Parser(BaseParser):
|
||||
def __init__(self, lexer_conf, parser_conf, term_matcher, resolve_ambiguity=True, complete_lex = False, debug=False, tree_class=Tree):
|
||||
BaseParser.__init__(self, lexer_conf, parser_conf, term_matcher, resolve_ambiguity, debug, tree_class)
|
||||
self.ignore = [Terminal(t) for t in lexer_conf.ignore]
|
||||
self.complete_lex = complete_lex
|
||||
|
||||
def _parse(self, stream, columns, to_scan, start_symbol=None):
|
||||
|
||||
def scan(i, to_scan):
|
||||
"""The core Earley Scanner.
|
||||
|
||||
This is a custom implementation of the scanner that uses the
|
||||
Lark lexer to match tokens. The scan list is built by the
|
||||
Earley predictor, based on the previously completed tokens.
|
||||
This ensures that at each phase of the parse we have a custom
|
||||
lexer context, allowing for more complex ambiguities."""
|
||||
|
||||
node_cache = {}
|
||||
|
||||
# 1) Loop the expectations and ask the lexer to match.
|
||||
# Since regexp is forward looking on the input stream, and we only
|
||||
# want to process tokens when we hit the point in the stream at which
|
||||
# they complete, we push all tokens into a buffer (delayed_matches), to
|
||||
# be held possibly for a later parse step when we reach the point in the
|
||||
# input stream at which they complete.
|
||||
for item in set(to_scan):
|
||||
m = match(item.expect, stream, i)
|
||||
if m:
|
||||
t = Token(item.expect.name, m.group(0), i, text_line, text_column)
|
||||
delayed_matches[m.end()].append( (item, i, t) )
|
||||
|
||||
if self.complete_lex:
|
||||
s = m.group(0)
|
||||
for j in range(1, len(s)):
|
||||
m = match(item.expect, s[:-j])
|
||||
if m:
|
||||
t = Token(item.expect.name, m.group(0), i, text_line, text_column)
|
||||
delayed_matches[i+m.end()].append( (item, i, t) )
|
||||
|
||||
# XXX The following 3 lines were commented out for causing a bug. See issue #768
|
||||
# # Remove any items that successfully matched in this pass from the to_scan buffer.
|
||||
# # This ensures we don't carry over tokens that already matched, if we're ignoring below.
|
||||
# to_scan.remove(item)
|
||||
|
||||
# 3) Process any ignores. This is typically used for e.g. whitespace.
|
||||
# We carry over any unmatched items from the to_scan buffer to be matched again after
|
||||
# the ignore. This should allow us to use ignored symbols in non-terminals to implement
|
||||
# e.g. mandatory spacing.
|
||||
for x in self.ignore:
|
||||
m = match(x, stream, i)
|
||||
if m:
|
||||
# Carry over any items still in the scan buffer, to past the end of the ignored items.
|
||||
delayed_matches[m.end()].extend([(item, i, None) for item in to_scan ])
|
||||
|
||||
# If we're ignoring up to the end of the file, # carry over the start symbol if it already completed.
|
||||
delayed_matches[m.end()].extend([(item, i, None) for item in columns[i] if item.is_complete and item.s == start_symbol])
|
||||
|
||||
next_to_scan = set()
|
||||
next_set = set()
|
||||
columns.append(next_set)
|
||||
transitives.append({})
|
||||
|
||||
## 4) Process Tokens from delayed_matches.
|
||||
# This is the core of the Earley scanner. Create an SPPF node for each Token,
|
||||
# and create the symbol node in the SPPF tree. Advance the item that completed,
|
||||
# and add the resulting new item to either the Earley set (for processing by the
|
||||
# completer/predictor) or the to_scan buffer for the next parse step.
|
||||
for item, start, token in delayed_matches[i+1]:
|
||||
if token is not None:
|
||||
token.end_line = text_line
|
||||
token.end_column = text_column + 1
|
||||
token.end_pos = i + 1
|
||||
|
||||
new_item = item.advance()
|
||||
label = (new_item.s, new_item.start, i)
|
||||
token_node = TokenNode(token, terminals[token.type])
|
||||
new_item.node = node_cache[label] if label in node_cache else node_cache.setdefault(label, SymbolNode(*label))
|
||||
new_item.node.add_family(new_item.s, item.rule, new_item.start, item.node, token_node)
|
||||
else:
|
||||
new_item = item
|
||||
|
||||
if new_item.expect in self.TERMINALS:
|
||||
# add (B ::= Aai+1.B, h, y) to Q'
|
||||
next_to_scan.add(new_item)
|
||||
else:
|
||||
# add (B ::= Aa+1.B, h, y) to Ei+1
|
||||
next_set.add(new_item)
|
||||
|
||||
del delayed_matches[i+1] # No longer needed, so unburden memory
|
||||
|
||||
if not next_set and not delayed_matches and not next_to_scan:
|
||||
considered_rules = list(sorted(to_scan, key=lambda key: key.rule.origin.name))
|
||||
raise UnexpectedCharacters(stream, i, text_line, text_column, {item.expect.name for item in to_scan},
|
||||
set(to_scan), state=frozenset(i.s for i in to_scan),
|
||||
considered_rules=considered_rules
|
||||
)
|
||||
|
||||
return next_to_scan
|
||||
|
||||
|
||||
delayed_matches = defaultdict(list)
|
||||
match = self.term_matcher
|
||||
terminals = self.lexer_conf.terminals_by_name
|
||||
|
||||
# Cache for nodes & tokens created in a particular parse step.
|
||||
transitives = [{}]
|
||||
|
||||
text_line = 1
|
||||
text_column = 1
|
||||
|
||||
## The main Earley loop.
|
||||
# Run the Prediction/Completion cycle for any Items in the current Earley set.
|
||||
# Completions will be added to the SPPF tree, and predictions will be recursively
|
||||
# processed down to terminals/empty nodes to be added to the scanner for the next
|
||||
# step.
|
||||
i = 0
|
||||
for token in stream:
|
||||
self.predict_and_complete(i, to_scan, columns, transitives)
|
||||
|
||||
to_scan = scan(i, to_scan)
|
||||
|
||||
if token == '\n':
|
||||
text_line += 1
|
||||
text_column = 1
|
||||
else:
|
||||
text_column += 1
|
||||
i += 1
|
||||
|
||||
self.predict_and_complete(i, to_scan, columns, transitives)
|
||||
|
||||
## Column is now the final column in the parse.
|
||||
assert i == len(columns)-1
|
||||
return to_scan
|
||||
|
|
@ -0,0 +1,106 @@
|
|||
"""Reconstruct text from a tree, based on Lark grammar"""
|
||||
|
||||
from typing import List, Dict, Union, Callable, Iterable, Optional
|
||||
|
||||
from .lark import Lark
|
||||
from .tree import Tree, ParseTree
|
||||
from .visitors import Transformer_InPlace
|
||||
from .lexer import Token, PatternStr, TerminalDef
|
||||
from .grammar import Terminal, NonTerminal, Symbol
|
||||
|
||||
from .tree_matcher import TreeMatcher, is_discarded_terminal
|
||||
from .utils import is_id_continue
|
||||
|
||||
def is_iter_empty(i):
|
||||
try:
|
||||
_ = next(i)
|
||||
return False
|
||||
except StopIteration:
|
||||
return True
|
||||
|
||||
|
||||
class WriteTokensTransformer(Transformer_InPlace):
|
||||
"Inserts discarded tokens into their correct place, according to the rules of grammar"
|
||||
|
||||
tokens: Dict[str, TerminalDef]
|
||||
term_subs: Dict[str, Callable[[Symbol], str]]
|
||||
|
||||
def __init__(self, tokens: Dict[str, TerminalDef], term_subs: Dict[str, Callable[[Symbol], str]]) -> None:
|
||||
self.tokens = tokens
|
||||
self.term_subs = term_subs
|
||||
|
||||
def __default__(self, data, children, meta):
|
||||
if not getattr(meta, 'match_tree', False):
|
||||
return Tree(data, children)
|
||||
|
||||
iter_args = iter(children)
|
||||
to_write = []
|
||||
for sym in meta.orig_expansion:
|
||||
if is_discarded_terminal(sym):
|
||||
try:
|
||||
v = self.term_subs[sym.name](sym)
|
||||
except KeyError:
|
||||
t = self.tokens[sym.name]
|
||||
if not isinstance(t.pattern, PatternStr):
|
||||
raise NotImplementedError("Reconstructing regexps not supported yet: %s" % t)
|
||||
|
||||
v = t.pattern.value
|
||||
to_write.append(v)
|
||||
else:
|
||||
x = next(iter_args)
|
||||
if isinstance(x, list):
|
||||
to_write += x
|
||||
else:
|
||||
if isinstance(x, Token):
|
||||
assert Terminal(x.type) == sym, x
|
||||
else:
|
||||
assert NonTerminal(x.data) == sym, (sym, x)
|
||||
to_write.append(x)
|
||||
|
||||
assert is_iter_empty(iter_args)
|
||||
return to_write
|
||||
|
||||
|
||||
class Reconstructor(TreeMatcher):
|
||||
"""
|
||||
A Reconstructor that will, given a full parse Tree, generate source code.
|
||||
|
||||
Note:
|
||||
The reconstructor cannot generate values from regexps. If you need to produce discarded
|
||||
regexes, such as newlines, use `term_subs` and provide default values for them.
|
||||
|
||||
Paramters:
|
||||
parser: a Lark instance
|
||||
term_subs: a dictionary of [Terminal name as str] to [output text as str]
|
||||
"""
|
||||
|
||||
write_tokens: WriteTokensTransformer
|
||||
|
||||
def __init__(self, parser: Lark, term_subs: Optional[Dict[str, Callable[[Symbol], str]]]=None) -> None:
|
||||
TreeMatcher.__init__(self, parser)
|
||||
|
||||
self.write_tokens = WriteTokensTransformer({t.name:t for t in self.tokens}, term_subs or {})
|
||||
|
||||
def _reconstruct(self, tree):
|
||||
unreduced_tree = self.match_tree(tree, tree.data)
|
||||
|
||||
res = self.write_tokens.transform(unreduced_tree)
|
||||
for item in res:
|
||||
if isinstance(item, Tree):
|
||||
# TODO use orig_expansion.rulename to support templates
|
||||
yield from self._reconstruct(item)
|
||||
else:
|
||||
yield item
|
||||
|
||||
def reconstruct(self, tree: ParseTree, postproc: Optional[Callable[[Iterable[str]], Iterable[str]]]=None, insert_spaces: bool=True) -> str:
|
||||
x = self._reconstruct(tree)
|
||||
if postproc:
|
||||
x = postproc(x)
|
||||
y = []
|
||||
prev_item = ''
|
||||
for item in x:
|
||||
if insert_spaces and prev_item and item and is_id_continue(prev_item[-1]) and is_id_continue(item[0]):
|
||||
y.append(' ')
|
||||
y.append(item)
|
||||
prev_item = item
|
||||
return ''.join(y)
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
import sys
|
||||
from argparse import ArgumentParser, FileType
|
||||
from textwrap import indent
|
||||
from logging import DEBUG, INFO, WARN, ERROR
|
||||
from typing import Optional
|
||||
import warnings
|
||||
|
||||
from lark import Lark, logger
|
||||
|
||||
lalr_argparser = ArgumentParser(add_help=False, epilog='Look at the Lark documentation for more info on the options')
|
||||
|
||||
flags = [
|
||||
('d', 'debug'),
|
||||
'keep_all_tokens',
|
||||
'regex',
|
||||
'propagate_positions',
|
||||
'maybe_placeholders',
|
||||
'use_bytes'
|
||||
]
|
||||
|
||||
options = ['start', 'lexer']
|
||||
|
||||
lalr_argparser.add_argument('-v', '--verbose', action='count', default=0, help="Increase Logger output level, up to three times")
|
||||
lalr_argparser.add_argument('-s', '--start', action='append', default=[])
|
||||
lalr_argparser.add_argument('-l', '--lexer', default='contextual', choices=('basic', 'contextual'))
|
||||
encoding: Optional[str] = 'utf-8' if sys.version_info > (3, 4) else None
|
||||
lalr_argparser.add_argument('-o', '--out', type=FileType('w', encoding=encoding), default=sys.stdout, help='the output file (default=stdout)')
|
||||
lalr_argparser.add_argument('grammar_file', type=FileType('r', encoding=encoding), help='A valid .lark file')
|
||||
|
||||
for flag in flags:
|
||||
if isinstance(flag, tuple):
|
||||
options.append(flag[1])
|
||||
lalr_argparser.add_argument('-' + flag[0], '--' + flag[1], action='store_true')
|
||||
elif isinstance(flag, str):
|
||||
options.append(flag)
|
||||
lalr_argparser.add_argument('--' + flag, action='store_true')
|
||||
else:
|
||||
raise NotImplementedError("flags must only contain strings or tuples of strings")
|
||||
|
||||
|
||||
def build_lalr(namespace):
|
||||
logger.setLevel((ERROR, WARN, INFO, DEBUG)[min(namespace.verbose, 3)])
|
||||
if len(namespace.start) == 0:
|
||||
namespace.start.append('start')
|
||||
kwargs = {n: getattr(namespace, n) for n in options}
|
||||
return Lark(namespace.grammar_file, parser='lalr', **kwargs), namespace.out
|
||||
|
||||
|
||||
def showwarning_as_comment(message, category, filename, lineno, file=None, line=None):
|
||||
# Based on warnings._showwarnmsg_impl
|
||||
text = warnings.formatwarning(message, category, filename, lineno, line)
|
||||
text = indent(text, '# ')
|
||||
if file is None:
|
||||
file = sys.stderr
|
||||
if file is None:
|
||||
return
|
||||
try:
|
||||
file.write(text)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
|
||||
def make_warnings_comments():
|
||||
warnings.showwarning = showwarning_as_comment
|
||||
|
|
@ -0,0 +1,202 @@
|
|||
"Converts Nearley grammars to Lark"
|
||||
|
||||
import os.path
|
||||
import sys
|
||||
import codecs
|
||||
import argparse
|
||||
|
||||
|
||||
from lark import Lark, Transformer, v_args
|
||||
|
||||
nearley_grammar = r"""
|
||||
start: (ruledef|directive)+
|
||||
|
||||
directive: "@" NAME (STRING|NAME)
|
||||
| "@" JS -> js_code
|
||||
ruledef: NAME "->" expansions
|
||||
| NAME REGEXP "->" expansions -> macro
|
||||
expansions: expansion ("|" expansion)*
|
||||
|
||||
expansion: expr+ js
|
||||
|
||||
?expr: item (":" /[+*?]/)?
|
||||
|
||||
?item: rule|string|regexp|null
|
||||
| "(" expansions ")"
|
||||
|
||||
rule: NAME
|
||||
string: STRING
|
||||
regexp: REGEXP
|
||||
null: "null"
|
||||
JS: /{%.*?%}/s
|
||||
js: JS?
|
||||
|
||||
NAME: /[a-zA-Z_$]\w*/
|
||||
COMMENT: /#[^\n]*/
|
||||
REGEXP: /\[.*?\]/
|
||||
|
||||
STRING: _STRING "i"?
|
||||
|
||||
%import common.ESCAPED_STRING -> _STRING
|
||||
%import common.WS
|
||||
%ignore WS
|
||||
%ignore COMMENT
|
||||
|
||||
"""
|
||||
|
||||
nearley_grammar_parser = Lark(nearley_grammar, parser='earley', lexer='basic')
|
||||
|
||||
def _get_rulename(name):
|
||||
name = {'_': '_ws_maybe', '__': '_ws'}.get(name, name)
|
||||
return 'n_' + name.replace('$', '__DOLLAR__').lower()
|
||||
|
||||
@v_args(inline=True)
|
||||
class NearleyToLark(Transformer):
|
||||
def __init__(self):
|
||||
self._count = 0
|
||||
self.extra_rules = {}
|
||||
self.extra_rules_rev = {}
|
||||
self.alias_js_code = {}
|
||||
|
||||
def _new_function(self, code):
|
||||
name = 'alias_%d' % self._count
|
||||
self._count += 1
|
||||
|
||||
self.alias_js_code[name] = code
|
||||
return name
|
||||
|
||||
def _extra_rule(self, rule):
|
||||
if rule in self.extra_rules_rev:
|
||||
return self.extra_rules_rev[rule]
|
||||
|
||||
name = 'xrule_%d' % len(self.extra_rules)
|
||||
assert name not in self.extra_rules
|
||||
self.extra_rules[name] = rule
|
||||
self.extra_rules_rev[rule] = name
|
||||
return name
|
||||
|
||||
def rule(self, name):
|
||||
return _get_rulename(name)
|
||||
|
||||
def ruledef(self, name, exps):
|
||||
return '!%s: %s' % (_get_rulename(name), exps)
|
||||
|
||||
def expr(self, item, op):
|
||||
rule = '(%s)%s' % (item, op)
|
||||
return self._extra_rule(rule)
|
||||
|
||||
def regexp(self, r):
|
||||
return '/%s/' % r
|
||||
|
||||
def null(self):
|
||||
return ''
|
||||
|
||||
def string(self, s):
|
||||
return self._extra_rule(s)
|
||||
|
||||
def expansion(self, *x):
|
||||
x, js = x[:-1], x[-1]
|
||||
if js.children:
|
||||
js_code ,= js.children
|
||||
js_code = js_code[2:-2]
|
||||
alias = '-> ' + self._new_function(js_code)
|
||||
else:
|
||||
alias = ''
|
||||
return ' '.join(x) + alias
|
||||
|
||||
def expansions(self, *x):
|
||||
return '%s' % ('\n |'.join(x))
|
||||
|
||||
def start(self, *rules):
|
||||
return '\n'.join(filter(None, rules))
|
||||
|
||||
def _nearley_to_lark(g, builtin_path, n2l, js_code, folder_path, includes):
|
||||
rule_defs = []
|
||||
|
||||
tree = nearley_grammar_parser.parse(g)
|
||||
for statement in tree.children:
|
||||
if statement.data == 'directive':
|
||||
directive, arg = statement.children
|
||||
if directive in ('builtin', 'include'):
|
||||
folder = builtin_path if directive == 'builtin' else folder_path
|
||||
path = os.path.join(folder, arg[1:-1])
|
||||
if path not in includes:
|
||||
includes.add(path)
|
||||
with codecs.open(path, encoding='utf8') as f:
|
||||
text = f.read()
|
||||
rule_defs += _nearley_to_lark(text, builtin_path, n2l, js_code, os.path.abspath(os.path.dirname(path)), includes)
|
||||
else:
|
||||
assert False, directive
|
||||
elif statement.data == 'js_code':
|
||||
code ,= statement.children
|
||||
code = code[2:-2]
|
||||
js_code.append(code)
|
||||
elif statement.data == 'macro':
|
||||
pass # TODO Add support for macros!
|
||||
elif statement.data == 'ruledef':
|
||||
rule_defs.append(n2l.transform(statement))
|
||||
else:
|
||||
raise Exception("Unknown statement: %s" % statement)
|
||||
|
||||
return rule_defs
|
||||
|
||||
|
||||
def create_code_for_nearley_grammar(g, start, builtin_path, folder_path, es6=False):
|
||||
import js2py
|
||||
|
||||
emit_code = []
|
||||
def emit(x=None):
|
||||
if x:
|
||||
emit_code.append(x)
|
||||
emit_code.append('\n')
|
||||
|
||||
js_code = ['function id(x) {return x[0];}']
|
||||
n2l = NearleyToLark()
|
||||
rule_defs = _nearley_to_lark(g, builtin_path, n2l, js_code, folder_path, set())
|
||||
lark_g = '\n'.join(rule_defs)
|
||||
lark_g += '\n'+'\n'.join('!%s: %s' % item for item in n2l.extra_rules.items())
|
||||
|
||||
emit('from lark import Lark, Transformer')
|
||||
emit()
|
||||
emit('grammar = ' + repr(lark_g))
|
||||
emit()
|
||||
|
||||
for alias, code in n2l.alias_js_code.items():
|
||||
js_code.append('%s = (%s);' % (alias, code))
|
||||
|
||||
if es6:
|
||||
emit(js2py.translate_js6('\n'.join(js_code)))
|
||||
else:
|
||||
emit(js2py.translate_js('\n'.join(js_code)))
|
||||
emit('class TransformNearley(Transformer):')
|
||||
for alias in n2l.alias_js_code:
|
||||
emit(" %s = var.get('%s').to_python()" % (alias, alias))
|
||||
emit(" __default__ = lambda self, n, c, m: c if c else None")
|
||||
|
||||
emit()
|
||||
emit('parser = Lark(grammar, start="n_%s", maybe_placeholders=False)' % start)
|
||||
emit('def parse(text):')
|
||||
emit(' return TransformNearley().transform(parser.parse(text))')
|
||||
|
||||
return ''.join(emit_code)
|
||||
|
||||
def main(fn, start, nearley_lib, es6=False):
|
||||
with codecs.open(fn, encoding='utf8') as f:
|
||||
grammar = f.read()
|
||||
return create_code_for_nearley_grammar(grammar, start, os.path.join(nearley_lib, 'builtin'), os.path.abspath(os.path.dirname(fn)), es6=es6)
|
||||
|
||||
def get_arg_parser():
|
||||
parser = argparse.ArgumentParser(description='Reads a Nearley grammar (with js functions), and outputs an equivalent lark parser.')
|
||||
parser.add_argument('nearley_grammar', help='Path to the file containing the nearley grammar')
|
||||
parser.add_argument('start_rule', help='Rule within the nearley grammar to make the base rule')
|
||||
parser.add_argument('nearley_lib', help='Path to root directory of nearley codebase (used for including builtins)')
|
||||
parser.add_argument('--es6', help='Enable experimental ES6 support', action='store_true')
|
||||
return parser
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = get_arg_parser()
|
||||
if len(sys.argv) == 1:
|
||||
parser.print_help(sys.stderr)
|
||||
sys.exit(1)
|
||||
args = parser.parse_args()
|
||||
print(main(fn=args.nearley_grammar, start=args.start_rule, nearley_lib=args.nearley_lib, es6=args.es6))
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
import codecs
|
||||
import sys
|
||||
import json
|
||||
|
||||
from lark import Lark
|
||||
from lark.grammar import RuleOptions, Rule
|
||||
from lark.lexer import TerminalDef
|
||||
from lark.tools import lalr_argparser, build_lalr
|
||||
|
||||
import argparse
|
||||
|
||||
argparser = argparse.ArgumentParser(prog='python -m lark.tools.serialize', parents=[lalr_argparser],
|
||||
description="Lark Serialization Tool - Stores Lark's internal state & LALR analysis as a JSON file",
|
||||
epilog='Look at the Lark documentation for more info on the options')
|
||||
|
||||
|
||||
def serialize(lark_inst, outfile):
|
||||
data, memo = lark_inst.memo_serialize([TerminalDef, Rule])
|
||||
outfile.write('{\n')
|
||||
outfile.write(' "data": %s,\n' % json.dumps(data))
|
||||
outfile.write(' "memo": %s\n' % json.dumps(memo))
|
||||
outfile.write('}\n')
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv)==1:
|
||||
argparser.print_help(sys.stderr)
|
||||
sys.exit(1)
|
||||
ns = argparser.parse_args()
|
||||
serialize(*build_lalr(ns))
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
|
@ -0,0 +1,194 @@
|
|||
###{standalone
|
||||
#
|
||||
#
|
||||
# Lark Stand-alone Generator Tool
|
||||
# ----------------------------------
|
||||
# Generates a stand-alone LALR(1) parser
|
||||
#
|
||||
# Git: https://github.com/erezsh/lark
|
||||
# Author: Erez Shinan (erezshin@gmail.com)
|
||||
#
|
||||
#
|
||||
# >>> LICENSE
|
||||
#
|
||||
# This tool and its generated code use a separate license from Lark,
|
||||
# and are subject to the terms of the Mozilla Public License, v. 2.0.
|
||||
# If a copy of the MPL was not distributed with this
|
||||
# file, You can obtain one at https://mozilla.org/MPL/2.0/.
|
||||
#
|
||||
# If you wish to purchase a commercial license for this tool and its
|
||||
# generated code, you may contact me via email or otherwise.
|
||||
#
|
||||
# If MPL2 is incompatible with your free or open-source project,
|
||||
# contact me and we'll work it out.
|
||||
#
|
||||
#
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
from collections.abc import Sequence
|
||||
from types import ModuleType
|
||||
from typing import (
|
||||
TypeVar, Generic, Type, Tuple, List, Dict, Iterator, Collection, Callable, Optional, FrozenSet, Any,
|
||||
Union, Iterable, IO, TYPE_CHECKING, overload,
|
||||
Pattern as REPattern, ClassVar, Set, Mapping
|
||||
)
|
||||
###}
|
||||
|
||||
import sys
|
||||
import token, tokenize
|
||||
import os
|
||||
from os import path
|
||||
from collections import defaultdict
|
||||
from functools import partial
|
||||
from argparse import ArgumentParser
|
||||
|
||||
import lark
|
||||
from lark.tools import lalr_argparser, build_lalr, make_warnings_comments
|
||||
|
||||
|
||||
from lark.grammar import Rule
|
||||
from lark.lexer import TerminalDef
|
||||
|
||||
_dir = path.dirname(__file__)
|
||||
_larkdir = path.join(_dir, path.pardir)
|
||||
|
||||
|
||||
EXTRACT_STANDALONE_FILES = [
|
||||
'tools/standalone.py',
|
||||
'exceptions.py',
|
||||
'utils.py',
|
||||
'tree.py',
|
||||
'visitors.py',
|
||||
'grammar.py',
|
||||
'lexer.py',
|
||||
'common.py',
|
||||
'parse_tree_builder.py',
|
||||
'parsers/lalr_parser.py',
|
||||
'parsers/lalr_analysis.py',
|
||||
'parser_frontends.py',
|
||||
'lark.py',
|
||||
'indenter.py',
|
||||
]
|
||||
|
||||
def extract_sections(lines):
|
||||
section = None
|
||||
text = []
|
||||
sections = defaultdict(list)
|
||||
for line in lines:
|
||||
if line.startswith('###'):
|
||||
if line[3] == '{':
|
||||
section = line[4:].strip()
|
||||
elif line[3] == '}':
|
||||
sections[section] += text
|
||||
section = None
|
||||
text = []
|
||||
else:
|
||||
raise ValueError(line)
|
||||
elif section:
|
||||
text.append(line)
|
||||
|
||||
return {name: ''.join(text) for name, text in sections.items()}
|
||||
|
||||
|
||||
def strip_docstrings(line_gen):
|
||||
""" Strip comments and docstrings from a file.
|
||||
Based on code from: https://stackoverflow.com/questions/1769332/script-to-remove-python-comments-docstrings
|
||||
"""
|
||||
res = []
|
||||
|
||||
prev_toktype = token.INDENT
|
||||
last_lineno = -1
|
||||
last_col = 0
|
||||
|
||||
tokgen = tokenize.generate_tokens(line_gen)
|
||||
for toktype, ttext, (slineno, scol), (elineno, ecol), ltext in tokgen:
|
||||
if slineno > last_lineno:
|
||||
last_col = 0
|
||||
if scol > last_col:
|
||||
res.append(" " * (scol - last_col))
|
||||
if toktype == token.STRING and prev_toktype == token.INDENT:
|
||||
# Docstring
|
||||
res.append("#--")
|
||||
elif toktype == tokenize.COMMENT:
|
||||
# Comment
|
||||
res.append("##\n")
|
||||
else:
|
||||
res.append(ttext)
|
||||
prev_toktype = toktype
|
||||
last_col = ecol
|
||||
last_lineno = elineno
|
||||
|
||||
return ''.join(res)
|
||||
|
||||
|
||||
def gen_standalone(lark_inst, output=None, out=sys.stdout, compress=False):
|
||||
if output is None:
|
||||
output = partial(print, file=out)
|
||||
|
||||
import pickle, zlib, base64
|
||||
def compressed_output(obj):
|
||||
s = pickle.dumps(obj, pickle.HIGHEST_PROTOCOL)
|
||||
c = zlib.compress(s)
|
||||
output(repr(base64.b64encode(c)))
|
||||
|
||||
def output_decompress(name):
|
||||
output('%(name)s = pickle.loads(zlib.decompress(base64.b64decode(%(name)s)))' % locals())
|
||||
|
||||
output('# The file was automatically generated by Lark v%s' % lark.__version__)
|
||||
output('__version__ = "%s"' % lark.__version__)
|
||||
output()
|
||||
|
||||
for i, pyfile in enumerate(EXTRACT_STANDALONE_FILES):
|
||||
with open(os.path.join(_larkdir, pyfile)) as f:
|
||||
code = extract_sections(f)['standalone']
|
||||
if i: # if not this file
|
||||
code = strip_docstrings(partial(next, iter(code.splitlines(True))))
|
||||
output(code)
|
||||
|
||||
data, m = lark_inst.memo_serialize([TerminalDef, Rule])
|
||||
output('import pickle, zlib, base64')
|
||||
if compress:
|
||||
output('DATA = (')
|
||||
compressed_output(data)
|
||||
output(')')
|
||||
output_decompress('DATA')
|
||||
output('MEMO = (')
|
||||
compressed_output(m)
|
||||
output(')')
|
||||
output_decompress('MEMO')
|
||||
else:
|
||||
output('DATA = (')
|
||||
output(data)
|
||||
output(')')
|
||||
output('MEMO = (')
|
||||
output(m)
|
||||
output(')')
|
||||
|
||||
|
||||
output('Shift = 0')
|
||||
output('Reduce = 1')
|
||||
output("def Lark_StandAlone(**kwargs):")
|
||||
output(" return Lark._load_from_dict(DATA, MEMO, **kwargs)")
|
||||
|
||||
|
||||
|
||||
|
||||
def main():
|
||||
make_warnings_comments()
|
||||
parser = ArgumentParser(prog="prog='python -m lark.tools.standalone'", description="Lark Stand-alone Generator Tool",
|
||||
parents=[lalr_argparser], epilog='Look at the Lark documentation for more info on the options')
|
||||
parser.add_argument('-c', '--compress', action='store_true', default=0, help="Enable compression")
|
||||
if len(sys.argv) == 1:
|
||||
parser.print_help(sys.stderr)
|
||||
sys.exit(1)
|
||||
ns = parser.parse_args()
|
||||
|
||||
lark_inst, out = build_lalr(ns)
|
||||
gen_standalone(lark_inst, out=out, compress=ns.compress)
|
||||
|
||||
ns.out.close()
|
||||
ns.grammar_file.close()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
|
@ -0,0 +1,263 @@
|
|||
import sys
|
||||
from copy import deepcopy
|
||||
|
||||
from typing import List, Callable, Iterator, Union, Optional, Generic, TypeVar, Any, TYPE_CHECKING
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .lexer import TerminalDef, Token
|
||||
import rich
|
||||
if sys.version_info >= (3, 8):
|
||||
from typing import Literal
|
||||
else:
|
||||
from typing_extensions import Literal
|
||||
|
||||
###{standalone
|
||||
from collections import OrderedDict
|
||||
|
||||
class Meta:
|
||||
|
||||
empty: bool
|
||||
line: int
|
||||
column: int
|
||||
start_pos: int
|
||||
end_line: int
|
||||
end_column: int
|
||||
end_pos: int
|
||||
orig_expansion: 'List[TerminalDef]'
|
||||
match_tree: bool
|
||||
|
||||
def __init__(self):
|
||||
self.empty = True
|
||||
|
||||
|
||||
_Leaf_T = TypeVar("_Leaf_T")
|
||||
Branch = Union[_Leaf_T, 'Tree[_Leaf_T]']
|
||||
|
||||
|
||||
class Tree(Generic[_Leaf_T]):
|
||||
"""The main tree class.
|
||||
|
||||
Creates a new tree, and stores "data" and "children" in attributes of the same name.
|
||||
Trees can be hashed and compared.
|
||||
|
||||
Parameters:
|
||||
data: The name of the rule or alias
|
||||
children: List of matched sub-rules and terminals
|
||||
meta: Line & Column numbers (if ``propagate_positions`` is enabled).
|
||||
meta attributes: line, column, start_pos, end_line, end_column, end_pos
|
||||
"""
|
||||
|
||||
data: str
|
||||
children: 'List[Branch[_Leaf_T]]'
|
||||
|
||||
def __init__(self, data: str, children: 'List[Branch[_Leaf_T]]', meta: Optional[Meta]=None) -> None:
|
||||
self.data = data
|
||||
self.children = children
|
||||
self._meta = meta
|
||||
|
||||
@property
|
||||
def meta(self) -> Meta:
|
||||
if self._meta is None:
|
||||
self._meta = Meta()
|
||||
return self._meta
|
||||
|
||||
def __repr__(self):
|
||||
return 'Tree(%r, %r)' % (self.data, self.children)
|
||||
|
||||
def _pretty_label(self):
|
||||
return self.data
|
||||
|
||||
def _pretty(self, level, indent_str):
|
||||
if len(self.children) == 1 and not isinstance(self.children[0], Tree):
|
||||
return [indent_str*level, self._pretty_label(), '\t', '%s' % (self.children[0],), '\n']
|
||||
|
||||
l = [indent_str*level, self._pretty_label(), '\n']
|
||||
for n in self.children:
|
||||
if isinstance(n, Tree):
|
||||
l += n._pretty(level+1, indent_str)
|
||||
else:
|
||||
l += [indent_str*(level+1), '%s' % (n,), '\n']
|
||||
|
||||
return l
|
||||
|
||||
def pretty(self, indent_str: str=' ') -> str:
|
||||
"""Returns an indented string representation of the tree.
|
||||
|
||||
Great for debugging.
|
||||
"""
|
||||
return ''.join(self._pretty(0, indent_str))
|
||||
|
||||
def __rich__(self, parent:'rich.tree.Tree'=None) -> 'rich.tree.Tree':
|
||||
"""Returns a tree widget for the 'rich' library.
|
||||
|
||||
Example:
|
||||
::
|
||||
from rich import print
|
||||
from lark import Tree
|
||||
|
||||
tree = Tree('root', ['node1', 'node2'])
|
||||
print(tree)
|
||||
"""
|
||||
return self._rich(parent)
|
||||
|
||||
def _rich(self, parent):
|
||||
if parent:
|
||||
tree = parent.add(f'[bold]{self.data}[/bold]')
|
||||
else:
|
||||
import rich.tree
|
||||
tree = rich.tree.Tree(self.data)
|
||||
|
||||
for c in self.children:
|
||||
if isinstance(c, Tree):
|
||||
c._rich(tree)
|
||||
else:
|
||||
tree.add(f'[green]{c}[/green]')
|
||||
|
||||
return tree
|
||||
|
||||
def __eq__(self, other):
|
||||
try:
|
||||
return self.data == other.data and self.children == other.children
|
||||
except AttributeError:
|
||||
return False
|
||||
|
||||
def __ne__(self, other):
|
||||
return not (self == other)
|
||||
|
||||
def __hash__(self) -> int:
|
||||
return hash((self.data, tuple(self.children)))
|
||||
|
||||
def iter_subtrees(self) -> 'Iterator[Tree[_Leaf_T]]':
|
||||
"""Depth-first iteration.
|
||||
|
||||
Iterates over all the subtrees, never returning to the same node twice (Lark's parse-tree is actually a DAG).
|
||||
"""
|
||||
queue = [self]
|
||||
subtrees = OrderedDict()
|
||||
for subtree in queue:
|
||||
subtrees[id(subtree)] = subtree
|
||||
# Reason for type ignore https://github.com/python/mypy/issues/10999
|
||||
queue += [c for c in reversed(subtree.children) # type: ignore[misc]
|
||||
if isinstance(c, Tree) and id(c) not in subtrees]
|
||||
|
||||
del queue
|
||||
return reversed(list(subtrees.values()))
|
||||
|
||||
def iter_subtrees_topdown(self):
|
||||
"""Breadth-first iteration.
|
||||
|
||||
Iterates over all the subtrees, return nodes in order like pretty() does.
|
||||
"""
|
||||
stack = [self]
|
||||
while stack:
|
||||
node = stack.pop()
|
||||
if not isinstance(node, Tree):
|
||||
continue
|
||||
yield node
|
||||
for child in reversed(node.children):
|
||||
stack.append(child)
|
||||
|
||||
def find_pred(self, pred: 'Callable[[Tree[_Leaf_T]], bool]') -> 'Iterator[Tree[_Leaf_T]]':
|
||||
"""Returns all nodes of the tree that evaluate pred(node) as true."""
|
||||
return filter(pred, self.iter_subtrees())
|
||||
|
||||
def find_data(self, data: str) -> 'Iterator[Tree[_Leaf_T]]':
|
||||
"""Returns all nodes of the tree whose data equals the given data."""
|
||||
return self.find_pred(lambda t: t.data == data)
|
||||
|
||||
###}
|
||||
|
||||
def expand_kids_by_data(self, *data_values):
|
||||
"""Expand (inline) children with any of the given data values. Returns True if anything changed"""
|
||||
changed = False
|
||||
for i in range(len(self.children)-1, -1, -1):
|
||||
child = self.children[i]
|
||||
if isinstance(child, Tree) and child.data in data_values:
|
||||
self.children[i:i+1] = child.children
|
||||
changed = True
|
||||
return changed
|
||||
|
||||
|
||||
def scan_values(self, pred: 'Callable[[Branch[_Leaf_T]], bool]') -> Iterator[_Leaf_T]:
|
||||
"""Return all values in the tree that evaluate pred(value) as true.
|
||||
|
||||
This can be used to find all the tokens in the tree.
|
||||
|
||||
Example:
|
||||
>>> all_tokens = tree.scan_values(lambda v: isinstance(v, Token))
|
||||
"""
|
||||
for c in self.children:
|
||||
if isinstance(c, Tree):
|
||||
for t in c.scan_values(pred):
|
||||
yield t
|
||||
else:
|
||||
if pred(c):
|
||||
yield c
|
||||
|
||||
def __deepcopy__(self, memo):
|
||||
return type(self)(self.data, deepcopy(self.children, memo), meta=self._meta)
|
||||
|
||||
def copy(self) -> 'Tree[_Leaf_T]':
|
||||
return type(self)(self.data, self.children)
|
||||
|
||||
def set(self, data: str, children: 'List[Branch[_Leaf_T]]') -> None:
|
||||
self.data = data
|
||||
self.children = children
|
||||
|
||||
|
||||
ParseTree = Tree['Token']
|
||||
|
||||
|
||||
class SlottedTree(Tree):
|
||||
__slots__ = 'data', 'children', 'rule', '_meta'
|
||||
|
||||
|
||||
def pydot__tree_to_png(tree: Tree, filename: str, rankdir: 'Literal["TB", "LR", "BT", "RL"]'="LR", **kwargs) -> None:
|
||||
graph = pydot__tree_to_graph(tree, rankdir, **kwargs)
|
||||
graph.write_png(filename)
|
||||
|
||||
|
||||
def pydot__tree_to_dot(tree: Tree, filename, rankdir="LR", **kwargs):
|
||||
graph = pydot__tree_to_graph(tree, rankdir, **kwargs)
|
||||
graph.write(filename)
|
||||
|
||||
|
||||
def pydot__tree_to_graph(tree: Tree, rankdir="LR", **kwargs):
|
||||
"""Creates a colorful image that represents the tree (data+children, without meta)
|
||||
|
||||
Possible values for `rankdir` are "TB", "LR", "BT", "RL", corresponding to
|
||||
directed graphs drawn from top to bottom, from left to right, from bottom to
|
||||
top, and from right to left, respectively.
|
||||
|
||||
`kwargs` can be any graph attribute (e. g. `dpi=200`). For a list of
|
||||
possible attributes, see https://www.graphviz.org/doc/info/attrs.html.
|
||||
"""
|
||||
|
||||
import pydot # type: ignore[import]
|
||||
graph = pydot.Dot(graph_type='digraph', rankdir=rankdir, **kwargs)
|
||||
|
||||
i = [0]
|
||||
|
||||
def new_leaf(leaf):
|
||||
node = pydot.Node(i[0], label=repr(leaf))
|
||||
i[0] += 1
|
||||
graph.add_node(node)
|
||||
return node
|
||||
|
||||
def _to_pydot(subtree):
|
||||
color = hash(subtree.data) & 0xffffff
|
||||
color |= 0x808080
|
||||
|
||||
subnodes = [_to_pydot(child) if isinstance(child, Tree) else new_leaf(child)
|
||||
for child in subtree.children]
|
||||
node = pydot.Node(i[0], style="filled", fillcolor="#%x" % color, label=subtree.data)
|
||||
i[0] += 1
|
||||
graph.add_node(node)
|
||||
|
||||
for subnode in subnodes:
|
||||
graph.add_edge(pydot.Edge(node, subnode))
|
||||
|
||||
return node
|
||||
|
||||
_to_pydot(tree)
|
||||
return graph
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue