artifact-parser 1.0.0__tar.gz

artifact_parser-1.0.0/.gitignore

@@ -0,0 +1,218 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.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
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.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/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+.task/checksum/codegen-check

artifact_parser-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Dat Nguyen
+
+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.

artifact_parser-1.0.0/PKG-INFO

@@ -0,0 +1,171 @@
+Metadata-Version: 2.4
+Name: artifact-parser
+Version: 1.0.0
+Summary: A pluggable framework for parsing data tool artifacts into typed Python models — dbt-core first.
+Project-URL: Homepage, https://github.com/datnguye/artifact-parser
+Project-URL: Repository, https://github.com/datnguye/artifact-parser
+Author-email: Dat Nguyen <datnguyen.it09@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: artifacts,catalog,dbt,manifest,parser,pydantic
+Classifier: Environment :: Console
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Requires-Dist: pydantic>=2.0
+Provides-Extra: codegen
+Requires-Dist: datamodel-code-generator>=0.63.0; extra == 'codegen'
+Requires-Dist: jinja2>=3.1; extra == 'codegen'
+Requires-Dist: typer>=0.26.7; extra == 'codegen'
+Provides-Extra: dbt
+Description-Content-Type: text/markdown
+
+# artifact-parser
+
+A small, pluggable framework for turning the JSON artifacts that data tools spit
+out into typed, validated Python objects. Point it at a blob, get back a pydantic
+model — no manual key-spelunking, no guessing which schema version you're holding.
+
+The framework is deliberately source-agnostic. Each **plugin** owns one family of
+artifacts and registers itself with a shared registry. The first one ships in the
+box: a full **dbt-core** parser (catalog, manifest, run-results, sources).
+
+## Install
+
+```bash
+uv add artifact-parser     # or: pip install artifact-parser
+```
+
+## Quick start
+
+The headline entry point sniffs any supported artifact and routes it to the right
+plugin — you don't have to know what you're holding:
+
+```python
+import json
+from artifact_parser import parse
+
+artifact = json.loads(open("target/manifest.json").read())
+model = parse(artifact)          # -> a ManifestV12 (or whatever version it is)
+print(model.metadata.dbt_schema_version)
+```
+
+When you *do* know the artifact family, the dbt plugin's typed helpers are more
+precise (and give better editor autocomplete):
+
+```python
+from artifact_parser.dbt import parse_manifest, parse_catalog
+
+manifest = parse_manifest(json.loads(open("target/manifest.json").read()))
+catalog = parse_catalog(json.loads(open("target/catalog.json").read()))
+```
+
+Hand it something it doesn't recognise and it tells you so, loudly, instead of
+returning a half-populated object:
+
+```python
+from artifact_parser import parse, UnknownArtifactError
+
+try:
+    parse({"metadata": {"dbt_schema_version": "made-up/v99.json"}})
+except UnknownArtifactError as exc:
+    print(exc)   # No registered parser recognises this artifact. Tried: dbt.
+```
+
+## Supported dbt artifacts
+
+| Artifact      | Versions | Generic parser        | Version-pinned parsers                |
+|---------------|----------|-----------------------|---------------------------------------|
+| `catalog`     | v1       | `parse_catalog`       | `parse_catalog_v1`                    |
+| `manifest`    | v1–v12   | `parse_manifest`      | `parse_manifest_v1` … `_v12`          |
+| `run-results` | v1–v6    | `parse_run_results`   | `parse_run_results_v1` … `_v6`        |
+| `sources`     | v1–v3    | `parse_sources`       | `parse_sources_v1` … `_v3`            |
+
+## Architecture
+
+```
+src/artifact_parser/
+├── core/                 # the framework — no knowledge of any specific tool
+│   ├── base.py           #   BaseArtifactModel (shared pydantic root)
+│   ├── parser.py         #   ArtifactParser (the plugin contract)
+│   ├── registry.py       #   ParserRegistry + the shared `registry` instance
+│   └── exceptions.py     #   ArtifactParserError + friends
+└── dbt/                  # the first plugin: dbt-core artifacts
+    ├── plugin.py         #   DbtArtifactParser (implements ArtifactParser)
+    ├── utils.py          #   schema-version sniffing
+    ├── resources/        #   committed dbt-core JSON schemas (codegen input)
+    └── generated/        #   droppable, rebuilt by `codegen dbt`
+        ├── parser.py     #     parse_<artifact>[_vN] public API
+        ├── version_map.py#     schema-version URL -> model class
+        └── models/       #     typed pydantic models, one module per version
+```
+
+The generated code is walled off in `generated/`. You can `rm -rf` that whole
+directory and rebuild it with `codegen dbt` (the package still imports while it's
+gone — the dbt plugin just sits out until you regenerate).
+
+The flow: a plugin answers *"is this mine?"* (`can_parse`) and *"make it typed"*
+(`parse`). The registry tries plugins in registration order and returns the first
+match. dbt registers itself on import, so `parse(...)` works out of the box.
+
+## Adding a new parser
+
+The whole point of the `core/` framework is that the second parser is cheap.
+By hand:
+
+1. Create `src/artifact_parser/<tool>/`.
+2. Define your models on `BaseArtifactModel`.
+3. Implement `ArtifactParser` (`name`, `can_parse`, `parse`) in `plugin.py`.
+4. Register it in the package `__init__.py`: `registry.register(MyParser())`.
+5. Import your plugin from the top-level `artifact_parser/__init__.py`.
+
+That's it — `parse()` now routes matching artifacts to your plugin.
+
+## Development
+
+This project uses [uv](https://docs.astral.sh/uv/) and
+[Task](https://taskfile.dev/). Common targets:
+
+| Goal                            | Task           |
+|---------------------------------|----------------|
+| Sync the environment            | `task install` |
+| Format + autofix                | `task format`  |
+| Lint (format-check + ruff)      | `task lint`    |
+| Run tests at 100% coverage      | `task test`    |
+
+`task --list` shows everything. The test suite enforces **100% coverage** of the
+framework and dbt dispatch code (the generated dbt models are excluded — they're
+schema, not logic). Beyond the synthetic fixtures, real artifacts from a live dbt
+build live in `tests/data/` and round-trip through the public `parse()` in
+`tests/artifact_parser/dbt/test_roundtrip.py` — the only tests that exercise
+populated nodes end to end.
+
+One non-obvious rule the generator enforces: the generated models are relaxed to
+pydantic `extra="ignore"` (not the `extra="forbid"` dbt's schemas imply), because
+real artifacts carry fields the published schema omits. A strict model would
+reject a perfectly good `manifest.json`. See `CLAUDE.md` for the why.
+
+### CI
+
+GitHub Actions back the same gates:
+
+| Workflow            | What it does                                                                 |
+|---------------------|-----------------------------------------------------------------------------|
+| `ci.yml`            | Lint + 100%-coverage tests on Python 3.10–3.13, plus a **codegen-in-sync** job that fails if the committed `generated/` drifts from a fresh regen. |
+| `schema-watch.yml`  | Weekly (and on demand): probes dbt's published schemas, regenerates, and opens a PR if a new version appeared. |
+| `release.yml`       | Build + coverage gate, then PyPI Trusted Publishing on a published Release (or TestPyPI via manual dispatch). |
+
+Action versions and Python deps are kept current by Dependabot.
+
+## Agentic setup
+
+This repo is wired for [Claude Code](https://claude.com/claude-code): a project
+`CLAUDE.md`, a `parser-author` subagent that owns `src/`, slash commands
+(`/test`, `/codegen`), secret-blocking and post-edit lint hooks, and the
+[context7](https://github.com/upstash/context7) MCP for pulling fresh library
+docs. See `CLAUDE.md` for the full tour. It will not write your code for you, but
+it tries hard to keep you from shipping a failing coverage gate.

artifact_parser-1.0.0/README.md

@@ -0,0 +1,145 @@
+# artifact-parser
+
+A small, pluggable framework for turning the JSON artifacts that data tools spit
+out into typed, validated Python objects. Point it at a blob, get back a pydantic
+model — no manual key-spelunking, no guessing which schema version you're holding.
+
+The framework is deliberately source-agnostic. Each **plugin** owns one family of
+artifacts and registers itself with a shared registry. The first one ships in the
+box: a full **dbt-core** parser (catalog, manifest, run-results, sources).
+
+## Install
+
+```bash
+uv add artifact-parser     # or: pip install artifact-parser
+```
+
+## Quick start
+
+The headline entry point sniffs any supported artifact and routes it to the right
+plugin — you don't have to know what you're holding:
+
+```python
+import json
+from artifact_parser import parse
+
+artifact = json.loads(open("target/manifest.json").read())
+model = parse(artifact)          # -> a ManifestV12 (or whatever version it is)
+print(model.metadata.dbt_schema_version)
+```
+
+When you *do* know the artifact family, the dbt plugin's typed helpers are more
+precise (and give better editor autocomplete):
+
+```python
+from artifact_parser.dbt import parse_manifest, parse_catalog
+
+manifest = parse_manifest(json.loads(open("target/manifest.json").read()))
+catalog = parse_catalog(json.loads(open("target/catalog.json").read()))
+```
+
+Hand it something it doesn't recognise and it tells you so, loudly, instead of
+returning a half-populated object:
+
+```python
+from artifact_parser import parse, UnknownArtifactError
+
+try:
+    parse({"metadata": {"dbt_schema_version": "made-up/v99.json"}})
+except UnknownArtifactError as exc:
+    print(exc)   # No registered parser recognises this artifact. Tried: dbt.
+```
+
+## Supported dbt artifacts
+
+| Artifact      | Versions | Generic parser        | Version-pinned parsers                |
+|---------------|----------|-----------------------|---------------------------------------|
+| `catalog`     | v1       | `parse_catalog`       | `parse_catalog_v1`                    |
+| `manifest`    | v1–v12   | `parse_manifest`      | `parse_manifest_v1` … `_v12`          |
+| `run-results` | v1–v6    | `parse_run_results`   | `parse_run_results_v1` … `_v6`        |
+| `sources`     | v1–v3    | `parse_sources`       | `parse_sources_v1` … `_v3`            |
+
+## Architecture
+
+```
+src/artifact_parser/
+├── core/                 # the framework — no knowledge of any specific tool
+│   ├── base.py           #   BaseArtifactModel (shared pydantic root)
+│   ├── parser.py         #   ArtifactParser (the plugin contract)
+│   ├── registry.py       #   ParserRegistry + the shared `registry` instance
+│   └── exceptions.py     #   ArtifactParserError + friends
+└── dbt/                  # the first plugin: dbt-core artifacts
+    ├── plugin.py         #   DbtArtifactParser (implements ArtifactParser)
+    ├── utils.py          #   schema-version sniffing
+    ├── resources/        #   committed dbt-core JSON schemas (codegen input)
+    └── generated/        #   droppable, rebuilt by `codegen dbt`
+        ├── parser.py     #     parse_<artifact>[_vN] public API
+        ├── version_map.py#     schema-version URL -> model class
+        └── models/       #     typed pydantic models, one module per version
+```
+
+The generated code is walled off in `generated/`. You can `rm -rf` that whole
+directory and rebuild it with `codegen dbt` (the package still imports while it's
+gone — the dbt plugin just sits out until you regenerate).
+
+The flow: a plugin answers *"is this mine?"* (`can_parse`) and *"make it typed"*
+(`parse`). The registry tries plugins in registration order and returns the first
+match. dbt registers itself on import, so `parse(...)` works out of the box.
+
+## Adding a new parser
+
+The whole point of the `core/` framework is that the second parser is cheap.
+By hand:
+
+1. Create `src/artifact_parser/<tool>/`.
+2. Define your models on `BaseArtifactModel`.
+3. Implement `ArtifactParser` (`name`, `can_parse`, `parse`) in `plugin.py`.
+4. Register it in the package `__init__.py`: `registry.register(MyParser())`.
+5. Import your plugin from the top-level `artifact_parser/__init__.py`.
+
+That's it — `parse()` now routes matching artifacts to your plugin.
+
+## Development
+
+This project uses [uv](https://docs.astral.sh/uv/) and
+[Task](https://taskfile.dev/). Common targets:
+
+| Goal                            | Task           |
+|---------------------------------|----------------|
+| Sync the environment            | `task install` |
+| Format + autofix                | `task format`  |
+| Lint (format-check + ruff)      | `task lint`    |
+| Run tests at 100% coverage      | `task test`    |
+
+`task --list` shows everything. The test suite enforces **100% coverage** of the
+framework and dbt dispatch code (the generated dbt models are excluded — they're
+schema, not logic). Beyond the synthetic fixtures, real artifacts from a live dbt
+build live in `tests/data/` and round-trip through the public `parse()` in
+`tests/artifact_parser/dbt/test_roundtrip.py` — the only tests that exercise
+populated nodes end to end.
+
+One non-obvious rule the generator enforces: the generated models are relaxed to
+pydantic `extra="ignore"` (not the `extra="forbid"` dbt's schemas imply), because
+real artifacts carry fields the published schema omits. A strict model would
+reject a perfectly good `manifest.json`. See `CLAUDE.md` for the why.
+
+### CI
+
+GitHub Actions back the same gates:
+
+| Workflow            | What it does                                                                 |
+|---------------------|-----------------------------------------------------------------------------|
+| `ci.yml`            | Lint + 100%-coverage tests on Python 3.10–3.13, plus a **codegen-in-sync** job that fails if the committed `generated/` drifts from a fresh regen. |
+| `schema-watch.yml`  | Weekly (and on demand): probes dbt's published schemas, regenerates, and opens a PR if a new version appeared. |
+| `release.yml`       | Build + coverage gate, then PyPI Trusted Publishing on a published Release (or TestPyPI via manual dispatch). |
+
+Action versions and Python deps are kept current by Dependabot.
+
+## Agentic setup
+
+This repo is wired for [Claude Code](https://claude.com/claude-code): a project
+`CLAUDE.md`, a `parser-author` subagent that owns `src/`, slash commands
+(`/test`, `/codegen`), secret-blocking and post-edit lint hooks, and the
+[context7](https://github.com/upstash/context7) MCP for pulling fresh library
+docs. See `CLAUDE.md` for the full tour. It will not write your code for you, but
+it tries hard to keep you from shipping a failing coverage gate.

artifact_parser-1.0.0/pyproject.toml

@@ -0,0 +1,106 @@
+[project]
+name = "artifact-parser"
+dynamic = ["version"]
+description = "A pluggable framework for parsing data tool artifacts into typed Python models — dbt-core first."
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.10"
+authors = [{ name = "Dat Nguyen", email = "datnguyen.it09@gmail.com" }]
+keywords = ["dbt", "artifacts", "manifest", "catalog", "parser", "pydantic"]
+classifiers = [
+  "Environment :: Console",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Software Development :: Libraries :: Python Modules",
+]
+dependencies = [
+  "pydantic>=2.0",
+]
+
+[project.optional-dependencies]
+dbt = []
+codegen = [
+  "datamodel-code-generator>=0.63.0",
+  "jinja2>=3.1",
+  "typer>=0.26.7",
+]
+
+[project.scripts]
+codegen = "codegen.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/datnguye/artifact-parser"
+Repository = "https://github.com/datnguye/artifact-parser"
+
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[tool.hatch.version]
+source = "vcs"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/artifact_parser", "src/codegen"]
+artifacts = [
+  "src/artifact_parser/py.typed",
+  "src/artifact_parser/dbt/resources/**/*.json",
+  "src/codegen/dbt/templates/*.jinja",
+]
+
+[tool.hatch.build.targets.sdist]
+include = [
+  "src/artifact_parser",
+  "src/codegen",
+  "README.md",
+  "LICENSE",
+]
+
+[dependency-groups]
+dev = [
+  "artifact-parser[codegen,dbt]",
+  "pre-commit>=4.6.0",
+  "pytest>=8.0",
+  "pytest-cov>=5.0",
+  "ruff>=0.4",
+]
+
+[tool.ruff]
+line-length = 88
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "SIM", "PLC0415"]
+
+[tool.ruff.lint.isort]
+force-single-line = true
+known-first-party = ["artifact_parser", "codegen"]
+
+[tool.ruff.lint.per-file-ignores]
+"src/artifact_parser/dbt/generated/**/*.py" = ["E501", "I", "UP", "B", "SIM"]
+"src/codegen/cli.py" = ["B008"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-ra --strict-markers --strict-config"
+
+[tool.coverage.run]
+source = ["artifact_parser", "codegen"]
+branch = true
+omit = [
+  "src/artifact_parser/dbt/generated/*.py",
+  "src/artifact_parser/dbt/generated/models/*/*.py",
+  "src/codegen/__main__.py",
+]
+
+[tool.coverage.report]
+fail_under = 100
+show_missing = true
+exclude_also = [
+  "if __name__ == .__main__.:",
+  "if TYPE_CHECKING:",
+  "\\.\\.\\.",
+  "pragma: no cover",
+]