wip 2

archivebox/plugins/git/on_Crawl__00_install_git.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+"""
+Install git if not already available.
+
+Runs at crawl start to ensure git is installed.
+Outputs JSONL for InstalledBinary.
+"""
+
+import json
+import sys
+from pathlib import Path
+
+
+def main():
+    try:
+        from abx_pkg import Binary, AptProvider, BrewProvider, EnvProvider, BinProviderOverrides
+
+        AptProvider.model_rebuild()
+        BrewProvider.model_rebuild()
+        EnvProvider.model_rebuild()
+
+        # git binary and package have same name
+        git_binary = Binary(
+            name='git',
+            binproviders=[AptProvider(), BrewProvider(), EnvProvider()]
+        )
+
+        # Try to load, install if not found
+        try:
+            loaded = git_binary.load()
+            if not loaded or not loaded.abspath:
+                raise Exception("Not loaded")
+        except Exception:
+            # Install via system package manager
+            loaded = git_binary.install()
+
+        if loaded and loaded.abspath:
+            # Output InstalledBinary JSONL
+            print(json.dumps({
+                'type': 'InstalledBinary',
+                'name': 'git',
+                'abspath': str(loaded.abspath),
+                'version': str(loaded.version) if loaded.version else None,
+                'sha256': loaded.sha256,
+                'binprovider': loaded.loaded_binprovider.name if loaded.loaded_binprovider else 'unknown',
+            }))
+            sys.exit(0)
+        else:
+            print(json.dumps({
+                'type': 'Dependency',
+                'bin_name': 'git',
+                'bin_providers': 'apt,brew,env',
+            }))
+            print("Failed to install git", file=sys.stderr)
+            sys.exit(1)
+
+    except Exception as e:
+        print(json.dumps({
+            'type': 'Dependency',
+            'bin_name': 'git',
+            'bin_providers': 'apt,brew,env',
+        }))
+        print(f"Error installing git: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

archivebox/plugins/git/tests/test_git.py

@@ -0,0 +1,90 @@
+"""
+Integration tests for git plugin
+
+Tests verify:
+1. Install hook installs git via abx-pkg
+2. Verify deps with abx-pkg
+3. Standalone git extractor execution
+"""
+
+import json
+import shutil
+import subprocess
+import sys
+import tempfile
+from pathlib import Path
+import pytest
+
+PLUGIN_DIR = Path(__file__).parent.parent
+GIT_HOOK = PLUGIN_DIR / 'on_Snapshot__12_git.py'
+GIT_INSTALL_HOOK = PLUGIN_DIR / 'on_Crawl__00_install_git.py'
+TEST_URL = 'https://github.com/example/repo.git'
+
+def test_hook_script_exists():
+    assert GIT_HOOK.exists()
+
+def test_git_install_hook():
+    """Test git install hook to install git if needed."""
+    result = subprocess.run(
+        [sys.executable, str(GIT_INSTALL_HOOK)],
+        capture_output=True,
+        text=True,
+        timeout=600
+    )
+
+    assert result.returncode == 0, f"Install hook failed: {result.stderr}"
+
+    # Verify InstalledBinary JSONL output
+    found_binary = False
+    for line in result.stdout.strip().split('\n'):
+        if line.strip():
+            try:
+                record = json.loads(line)
+                if record.get('type') == 'InstalledBinary':
+                    assert record['name'] == 'git'
+                    assert record['abspath']
+                    found_binary = True
+                    break
+            except json.JSONDecodeError:
+                pass
+
+    assert found_binary, "Should output InstalledBinary record"
+
+def test_verify_deps_with_abx_pkg():
+    """Verify git is available via abx-pkg after hook installation."""
+    from abx_pkg import Binary, AptProvider, BrewProvider, EnvProvider
+
+    AptProvider.model_rebuild()
+    BrewProvider.model_rebuild()
+    EnvProvider.model_rebuild()
+
+    git_binary = Binary(name='git', binproviders=[AptProvider(), BrewProvider(), EnvProvider()])
+    git_loaded = git_binary.load()
+    assert git_loaded and git_loaded.abspath, "git should be available after install hook"
+
+def test_reports_missing_git():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        env = {'PATH': '/nonexistent'}
+        result = subprocess.run(
+            [sys.executable, str(GIT_HOOK), '--url', TEST_URL, '--snapshot-id', 'test123'],
+            cwd=tmpdir, capture_output=True, text=True, env=env
+        )
+        if result.returncode != 0:
+            combined = result.stdout + result.stderr
+            assert 'DEPENDENCY_NEEDED' in combined or 'git' in combined.lower() or 'ERROR=' in combined
+
+def test_handles_non_git_url():
+    if not shutil.which('git'):
+        pytest.skip("git not installed")
+    
+    with tempfile.TemporaryDirectory() as tmpdir:
+        result = subprocess.run(
+            [sys.executable, str(GIT_HOOK), '--url', 'https://example.com', '--snapshot-id', 'test789'],
+            cwd=tmpdir, capture_output=True, text=True, timeout=30
+        )
+        # Should fail or skip for non-git URL
+        assert result.returncode in (0, 1)
+        assert 'STATUS=' in result.stdout
+
+if __name__ == '__main__':
+    pytest.main([__file__, '-v'])