Files
orchard/backend/tests/unit/test_metadata.py
2026-02-05 10:31:04 -06:00

244 lines
9.0 KiB
Python

"""Unit tests for metadata extraction functionality."""
import io
import gzip
import tarfile
import zipfile
import pytest
from app.metadata import (
extract_metadata,
extract_deb_metadata,
extract_wheel_metadata,
extract_tarball_metadata,
extract_jar_metadata,
parse_deb_control,
)
class TestDebMetadata:
"""Tests for Debian package metadata extraction."""
def test_parse_deb_control_basic(self):
"""Test parsing a basic control file."""
control = """Package: my-package
Version: 1.2.3
Architecture: amd64
Maintainer: Test <test@example.com>
Description: A test package
"""
result = parse_deb_control(control)
assert result["package_name"] == "my-package"
assert result["version"] == "1.2.3"
assert result["architecture"] == "amd64"
assert result["format"] == "deb"
def test_parse_deb_control_with_epoch(self):
"""Test parsing version with epoch."""
control = """Package: another-pkg
Version: 2:1.0.0-1
"""
result = parse_deb_control(control)
assert result["version"] == "2:1.0.0-1"
assert result["package_name"] == "another-pkg"
assert result["format"] == "deb"
def test_extract_deb_metadata_invalid_magic(self):
"""Test that invalid ar magic returns empty dict."""
file = io.BytesIO(b"not an ar archive")
result = extract_deb_metadata(file)
assert result == {}
def test_extract_deb_metadata_valid_ar_no_control(self):
"""Test ar archive without control.tar returns empty."""
# Create minimal ar archive with just debian-binary
ar_data = b"!<arch>\n"
ar_data += b"debian-binary/ 0 0 0 100644 4 `\n"
ar_data += b"2.0\n"
file = io.BytesIO(ar_data)
result = extract_deb_metadata(file)
# Should return empty since no control.tar found
assert result == {} or "version" not in result
class TestWheelMetadata:
"""Tests for Python wheel metadata extraction."""
def _create_wheel_with_metadata(self, metadata_content: str) -> io.BytesIO:
"""Helper to create a wheel file with given METADATA content."""
buf = io.BytesIO()
with zipfile.ZipFile(buf, 'w') as zf:
zf.writestr('package-1.0.0.dist-info/METADATA', metadata_content)
buf.seek(0)
return buf
def test_extract_wheel_version(self):
"""Test extracting version from wheel METADATA."""
metadata = """Metadata-Version: 2.1
Name: my-package
Version: 2.3.4
Summary: A test package
"""
file = self._create_wheel_with_metadata(metadata)
result = extract_wheel_metadata(file)
assert result.get("version") == "2.3.4"
assert result.get("package_name") == "my-package"
assert result.get("format") == "wheel"
def test_extract_wheel_no_version(self):
"""Test wheel without version field."""
metadata = """Metadata-Version: 2.1
Name: no-version-pkg
"""
file = self._create_wheel_with_metadata(metadata)
result = extract_wheel_metadata(file)
assert "version" not in result
assert result.get("package_name") == "no-version-pkg"
assert result.get("format") == "wheel"
def test_extract_wheel_invalid_zip(self):
"""Test that invalid zip returns format-only dict."""
file = io.BytesIO(b"not a zip file")
result = extract_wheel_metadata(file)
assert result == {"format": "wheel"}
def test_extract_wheel_no_metadata_file(self):
"""Test wheel without METADATA file returns format-only dict."""
buf = io.BytesIO()
with zipfile.ZipFile(buf, 'w') as zf:
zf.writestr('some_file.py', 'print("hello")')
buf.seek(0)
result = extract_wheel_metadata(buf)
assert result == {"format": "wheel"}
class TestTarballMetadata:
"""Tests for tarball metadata extraction from filename."""
def test_extract_version_from_filename_standard(self):
"""Test standard package-version.tar.gz format."""
file = io.BytesIO(b"") # Content doesn't matter for filename extraction
result = extract_tarball_metadata(file, "mypackage-1.2.3.tar.gz")
assert result.get("version") == "1.2.3"
assert result.get("package_name") == "mypackage"
assert result.get("format") == "tarball"
def test_extract_version_with_v_prefix(self):
"""Test version with v prefix."""
file = io.BytesIO(b"")
result = extract_tarball_metadata(file, "package-v2.0.0.tar.gz")
assert result.get("version") == "2.0.0"
assert result.get("package_name") == "package"
assert result.get("format") == "tarball"
def test_extract_version_underscore_separator(self):
"""Test package_version format."""
file = io.BytesIO(b"")
result = extract_tarball_metadata(file, "my_package_3.1.4.tar.gz")
assert result.get("version") == "3.1.4"
assert result.get("package_name") == "my_package"
assert result.get("format") == "tarball"
def test_extract_version_complex(self):
"""Test complex version string."""
file = io.BytesIO(b"")
result = extract_tarball_metadata(file, "package-1.0.0-beta.1.tar.gz")
# The regex handles versions with suffix like -beta_1
assert result.get("format") == "tarball"
# May or may not extract version depending on regex match
if "version" in result:
assert result.get("package_name") == "package"
def test_extract_no_version_in_filename(self):
"""Test filename without version returns format-only dict."""
file = io.BytesIO(b"")
result = extract_tarball_metadata(file, "package.tar.gz")
# Should return format but no version
assert result.get("version") is None
assert result.get("format") == "tarball"
class TestJarMetadata:
"""Tests for JAR/Java metadata extraction."""
def _create_jar_with_manifest(self, manifest_content: str) -> io.BytesIO:
"""Helper to create a JAR file with given MANIFEST.MF content."""
buf = io.BytesIO()
with zipfile.ZipFile(buf, 'w') as zf:
zf.writestr('META-INF/MANIFEST.MF', manifest_content)
buf.seek(0)
return buf
def test_extract_jar_version_from_manifest(self):
"""Test extracting version from MANIFEST.MF."""
manifest = """Manifest-Version: 1.0
Implementation-Title: my-library
Implementation-Version: 4.5.6
"""
file = self._create_jar_with_manifest(manifest)
result = extract_jar_metadata(file)
assert result.get("version") == "4.5.6"
assert result.get("package_name") == "my-library"
assert result.get("format") == "jar"
def test_extract_jar_bundle_version(self):
"""Test extracting OSGi Bundle-Version."""
manifest = """Manifest-Version: 1.0
Bundle-Version: 2.1.0
Bundle-Name: Test Bundle
"""
file = self._create_jar_with_manifest(manifest)
result = extract_jar_metadata(file)
# Bundle-Version is stored in bundle_version, not version
assert result.get("bundle_version") == "2.1.0"
assert result.get("bundle_name") == "Test Bundle"
assert result.get("format") == "jar"
def test_extract_jar_invalid_zip(self):
"""Test that invalid JAR returns format-only dict."""
file = io.BytesIO(b"not a jar file")
result = extract_jar_metadata(file)
assert result == {"format": "jar"}
class TestExtractMetadataDispatch:
"""Tests for the main extract_metadata dispatcher function."""
def test_dispatch_to_wheel(self):
"""Test that .whl files use wheel extractor."""
buf = io.BytesIO()
with zipfile.ZipFile(buf, 'w') as zf:
zf.writestr('pkg-1.0.dist-info/METADATA', 'Version: 1.0.0\nName: pkg')
buf.seek(0)
result = extract_metadata(buf, "package-1.0.0-py3-none-any.whl")
assert result.get("version") == "1.0.0"
assert result.get("package_name") == "pkg"
assert result.get("format") == "wheel"
def test_dispatch_to_tarball(self):
"""Test that .tar.gz files use tarball extractor."""
file = io.BytesIO(b"")
result = extract_metadata(file, "mypackage-2.3.4.tar.gz")
assert result.get("version") == "2.3.4"
assert result.get("package_name") == "mypackage"
assert result.get("format") == "tarball"
def test_dispatch_unknown_extension(self):
"""Test that unknown extensions return empty dict."""
file = io.BytesIO(b"some content")
result = extract_metadata(file, "unknown.xyz")
assert result == {}
def test_file_position_reset_after_extraction(self):
"""Test that file position is reset to start after extraction."""
buf = io.BytesIO()
with zipfile.ZipFile(buf, 'w') as zf:
zf.writestr('pkg-1.0.dist-info/METADATA', 'Version: 1.0.0\nName: pkg')
buf.seek(0)
extract_metadata(buf, "package.whl")
# File should be back at position 0
assert buf.tell() == 0