wip major changes

2026-04-05 07:17:52 +10:00 · 2025-12-24 20:09:51 -08:00
parent c1335fed37
commit 1915333b81
450 changed files with 35814 additions and 19015 deletions
--- a/archivebox/plugins/git/on_Crawl__00_validate_git.py
+++ b/archivebox/plugins/git/on_Crawl__00_validate_git.py
@@ -0,0 +1,126 @@
+#!/usr/bin/env python3
+"""
+Validation hook for git binary.
+
+Runs at crawl start to verify git is available.
+Outputs JSONL for InstalledBinary and Machine config updates.
+"""
+
+import os
+import sys
+import json
+import shutil
+import hashlib
+import subprocess
+from pathlib import Path
+
+
+def get_binary_version(abspath: str) -> str | None:
+    """Get version string from binary."""
+    try:
+        result = subprocess.run(
+            [abspath, '--version'],
+            capture_output=True,
+            text=True,
+            timeout=5,
+        )
+        if result.returncode == 0 and result.stdout:
+            # git version string: "git version 2.43.0"
+            first_line = result.stdout.strip().split('\n')[0]
+            parts = first_line.split()
+            if len(parts) >= 3 and parts[0] == 'git':
+                return parts[2]
+            return first_line[:32]
+    except Exception:
+        pass
+    return None
+
+
+def get_binary_hash(abspath: str) -> str | None:
+    """Get SHA256 hash of binary."""
+    try:
+        with open(abspath, 'rb') as f:
+            return hashlib.sha256(f.read()).hexdigest()
+    except Exception:
+        return None
+
+
+def find_git() -> dict | None:
+    """Find git binary."""
+    try:
+        from abx_pkg import Binary, EnvProvider
+
+        class GitBinary(Binary):
+            name: str = 'git'
+            binproviders_supported = [EnvProvider()]
+
+        binary = GitBinary()
+        loaded = binary.load()
+        if loaded and loaded.abspath:
+            return {
+                'name': 'git',
+                'abspath': str(loaded.abspath),
+                'version': str(loaded.version) if loaded.version else None,
+                'sha256': loaded.sha256 if hasattr(loaded, 'sha256') else None,
+                'binprovider': loaded.binprovider.name if loaded.binprovider else 'env',
+            }
+    except ImportError:
+        pass
+    except Exception:
+        pass
+
+    # Fallback to shutil.which
+    abspath = shutil.which('git') or os.environ.get('GIT_BINARY', '')
+    if abspath and Path(abspath).is_file():
+        return {
+            'name': 'git',
+            'abspath': abspath,
+            'version': get_binary_version(abspath),
+            'sha256': get_binary_hash(abspath),
+            'binprovider': 'env',
+        }
+
+    return None
+
+
+def main():
+    result = find_git()
+
+    if result and result.get('abspath'):
+        print(json.dumps({
+            'type': 'InstalledBinary',
+            'name': result['name'],
+            'abspath': result['abspath'],
+            'version': result['version'],
+            'sha256': result['sha256'],
+            'binprovider': result['binprovider'],
+        }))
+
+        print(json.dumps({
+            'type': 'Machine',
+            '_method': 'update',
+            'key': 'config/GIT_BINARY',
+            'value': result['abspath'],
+        }))
+
+        if result['version']:
+            print(json.dumps({
+                'type': 'Machine',
+                '_method': 'update',
+                'key': 'config/GIT_VERSION',
+                'value': result['version'],
+            }))
+
+        sys.exit(0)
+    else:
+        print(json.dumps({
+            'type': 'Dependency',
+            'bin_name': 'git',
+            'bin_providers': 'apt,brew,env',
+        }))
+        print(f"git binary not found", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()