Kickstart the schemas revamp (WIP)

.github/workflows/precommit.yml

@@ -0,0 +1,14 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - uses: actions/setup-python@v3
+    - uses: pre-commit/[email protected]

.gitignore

@@ -0,0 +1,165 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+.ruff_cache
+
+# vscode
+.vscode/

.pre-commit-config.yaml

@@ -0,0 +1,34 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev:  v4.4.0
+    hooks:
+      - id: check-added-large-files
+      - id: pretty-format-json
+        exclude: archive|examples
+      - id: check-json
+      - id: check-docstring-first
+      - id: trailing-whitespace
+        exclude: archive|examples
+      - id: end-of-file-fixer
+        exclude: archive|examples
+-   repo: https://github.com/psf/black
+    rev: 23.3.0
+    hooks:
+    - id: black
+      pass_filenames: true
+      exclude: _vendor|vendored|examples|archive
+-   repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.0.265
+    hooks:
+      - id: ruff
+-   repo: https://github.com/python-jsonschema/check-jsonschema
+    rev: 0.23.0
+    hooks:
+      - id: check-github-workflows
+-   repo: https://github.com/econchick/interrogate
+    rev: 1.5.0
+    hooks:
+      - id: interrogate
+        types: [python]
+        # exclude: ^(docs/conf.py|setup.py|tests/functional/sample)
+        args: [--config=pyproject.toml]

generate-index.py → archive/generate-index.py

@@ -93,10 +93,10 @@
 
 """
 
-files=sorted(p for p in os.listdir(".") if p.endswith(".schema.json"))
+files = sorted(p for p in os.listdir(".") if p.endswith(".schema.json"))
 rendered = Template(_TEMPLATE).render(files=files)
 
 print(rendered, file=sys.stderr)
 
 with open(join(dirname(__file__), "index.html"), "w") as fh:
-    fh.write(rendered)
+    fh.write(rendered)

conda_models/_base.py

@@ -0,0 +1,27 @@
+from functools import lru_cache
+from typing import Optional, Type
+
+from pydantic import BaseModel, Extra, create_model
+
+
+class ExtrasForbiddenModel(BaseModel):
+    class Config:
+        extra = Extra.forbid
+
+
+@lru_cache(maxsize=None)
+def make_optional(baseclass: Type[BaseModel]) -> Type[BaseModel]:
+    """Extracts the fields and validators from the baseclass and make fields optional"""
+    fields = baseclass.__fields__
+    validators = {"__validators__": baseclass.__validators__}
+    optional_fields = {key: (Optional[item.type_], None) for key, item in fields.items()}
+    return create_model(
+        f"Optional{baseclass.__name__}",
+        **optional_fields,
+        __validators__=validators,
+    )
+
+
+def export_to_json(model, path):
+    with open(path, "w") as f:
+        f.write(model.json(indent=2))

conda_models/channeldata.py

@@ -0,0 +1,67 @@
+from typing import Iterable, Optional
+
+from pydantic import AnyUrl, Field
+
+from ._base import ExtrasForbiddenModel
+from .run_exports import RunExports
+from .types import PackageNameStr, VersionStr
+
+
+class ChannelDataPackage(ExtrasForbiddenModel):
+    has_activate_scripts: bool = Field(..., alias="activate.d")
+    "Whether the package contains activation scripts"
+    has_deactivate_scripts: bool = Field(..., alias="deactivate.d")
+    "Whether the package contains deactivation scripts"
+    binary_prefix: bool
+    "Whether the package contains binary files that hardcode the installation prefix"
+    description: Optional[str] = None
+    "The description of the package"
+    dev_url: Optional[Iterable[AnyUrl]] = None
+    "The URL to the development page of the package"
+    doc_url: Optional[Iterable[AnyUrl]] = None
+    "The URL to the documentation page of the package"
+    home: Optional[Iterable[AnyUrl]] = None
+    "The URL to the homepage of the package"
+    source_url: Optional[Iterable[AnyUrl]] = None
+    "The URL to the latest source code of the package"
+    license: Optional[str] = None
+    "The license of the package"
+    has_post_link_scripts: bool
+    "Whether the package contains post-link scripts"
+    has_pre_link_scripts: bool
+    "Whether the package contains pre-link scripts"
+    has_pre_unlink_scripts: bool
+    "Whether the package contains pre-unlink scripts"
+    run_exports: dict[VersionStr, RunExports]
+    "The run exports of the package, per package version (not build!)"
+    subdirs: Iterable[str]
+    "Which subdirs the package is available in"
+    summary: Optional[str] = None
+    "The summary of the package. Shorter than description."
+    text_prefix: bool
+    "Whether the package contains text files that hardcode the installation prefix"
+    timestamp: Optional[int] = None
+    "Last update time for artifacts of this package"
+    version: Optional[VersionStr] = None
+    "The latest version of the package"
+
+
+class ChannelData(ExtrasForbiddenModel):
+    """
+    Data structures that are present in a `channeldata.json` file. Some channels on anaconda.org
+    contain a `channeldata.json` file which describes the subdirs the channel contains, the
+    packages stored in the channel and additional data about them like their latest version.
+
+    The `ChannelData` struct represents the data found within the `channeldata.json` file. The
+    `ChannelDataPackage` contains information about a package.
+
+    Note that certain aspects of `ChannelData` are broken (e.g. run_exports is only available for a
+    single package variant) and therefore the `ChannelData` struct is not really used much more.
+    """
+
+    channeldata_version: int
+    "The version of the channeldata format"
+    packages: dict[PackageNameStr, ChannelDataPackage]
+    "The packages available in the channel, grouped by name"
+    subdirs: Iterable[str]
+    "The subdirs available in the channel"

conda_models/conda_build_config.py

@@ -0,0 +1,3 @@
+"""
+WIP
+"""

conda_models/conda_lock.py

@@ -0,0 +1,3 @@
+"""
+WIP
+"""