feat/add python car library

README.md

@@ -68,9 +68,10 @@ Fixtures are tested against the [libipld](https://github.com/ipld/libipld) stack
 ### Python
 
 Fixtures are tested against the [ipld-dag-pb](https://github.com/storacha/py-ipld-dag-pb)
-library:
+and [ipld-car](https://github.com/storacha/py-ipld-car) library:
 
 * DAG-PB: [ipld-dag-pb](https://pypi.org/project/ipld-dag-pb/)
+* CAR: [ipld-car](https://pypi.org/project/ipld-car)
 
 ## Running tests
 

js/make-car.js

@@ -10,13 +10,20 @@ const outStream = createWriteStream(outFile)
 const { writer, out } = await CarWriter.create([])
 const pipe = pipeline(out, outStream)
 
+const blocks = []
 for (const { name, url } of fixtureDirectories()) {
   const data = await loadFixture(url)
   for (const { cid, bytes } of Object.values(data)) {
-    await writer.put({ cid: CID.parse(cid), bytes })
+    blocks.push({ cid, bytes })
   }
 }
 
+blocks.sort((a, b) => a.cid < b.cid ? -1 : a.cid > b.cid ? 1 : 0)
+
+for (const { cid, bytes } of blocks) {
+  await writer.put({ cid: CID.parse(cid), bytes })
+}
+
 await writer.close()
 await pipe
-console.log(`Wrote fixtures to ${outFile}`)
+console.log(`Wrote fixtures to ${outFile}`)

python/.gitignore

@@ -0,0 +1,162 @@
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/

python/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 
 [project]
-name = "py-ipld-dag-pb-test"
+name = "python"
 version = "0.0.1"
 requires-python = ">=3.10"
 classifiers = [
@@ -13,5 +13,8 @@ classifiers = [
 dependencies = [
     "multiformats",
     "ipld-dag-pb",
-    "pytest"
+    "pytest",
+    "ipld-car",
 ]
+[tool.hatch.build.targets.wheel]
+packages = ["python"]

python/requirements.txt

@@ -8,6 +8,8 @@ bases==0.3.0
     # via multiformats
 iniconfig==2.1.0
     # via pytest
+ipld-car==0.0.1
+    # via py-ipld-dag-pb-test (pyproject.toml)
 ipld-dag-pb==0.0.1
     # via py-ipld-dag-pb-test (pyproject.toml)
 multiformats==0.3.1.post4

python/tests/test_car.py

@@ -0,0 +1,47 @@
+import pytest
+from pathlib import Path
+from multiformats import CID
+import ipld_car
+
+FIXTURES_DIR = Path(__file__).parents[2] / "fixtures"
+REPO_ROOT = FIXTURES_DIR.parent
+
+
+def load_all_fixtures() -> list[ipld_car.Block]:
+    """Load all non-negative fixtures CID and data"""
+    fixture_blocks: list[ipld_car.Block] = []
+
+    for dir in sorted(FIXTURES_DIR.iterdir()):
+        if dir.is_dir():  # skip .gitattributes file
+            for file in dir.iterdir():
+                fixture_cid = file.stem
+                with file.open(mode="rb") as file_obj:
+                    fixture_data = file_obj.read()
+                fixture_blocks.append((CID.decode(fixture_cid), fixture_data,))
+
+    return fixture_blocks
+
+
+@pytest.fixture
+def car_fixture_data() -> bytes:
+    """Load CAR fixture data from CAR file: `fixtures.car`"""
+    with open(REPO_ROOT / "fixtures.car", mode="rb") as f:
+        return f.read()
+
+
+def test_car_decode(car_fixture_data):
+    decoded_roots, decoded_blocks = ipld_car.decode(car_fixture_data)
+    assert decoded_roots == []
+    assert (
+        sorted([(block[0].encode(), block[1],) for block in load_all_fixtures()]) ==
+        sorted([(block[0].encode(), block[1],) for block in decoded_blocks])
+    )
+
+
+def test_car_encode(car_fixture_data):
+    # encoded blocks from the fixtures dir into CAR
+    fixture_blocks = sorted(load_all_fixtures(), key=lambda block: block[0].encode())
+    encoded_fixture_blocks_car = ipld_car.encode(roots=[], blocks=fixture_blocks)
+    assert encoded_fixture_blocks_car == car_fixture_data
+    # verify same blocks are present in encoded-then-decoded-fixture-blocks
+    # and decoded car fixture file