initial commit

tests/ubuntu_vm/snapshot.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+"""Create a bounded source/PDFium snapshot, excluding results, builds and VM keys."""
+import argparse
+import hashlib
+import json
+import os
+from pathlib import Path
+import re
+import tarfile
+
+ROOT = Path(__file__).resolve().parents[2]
+parser = argparse.ArgumentParser(description=__doc__)
+parser.add_argument('--name', required=True)
+args = parser.parse_args()
+if not re.fullmatch(r'[a-z0-9][a-z0-9-]{0,63}', args.name):
+    parser.error('Use a short lowercase snapshot name')
+work = Path(os.environ.get('DOCVIEW_VM_WORK', ROOT / 'build-ubuntu-vm')).resolve()
+archive = work / (args.name + '.tar.gz')
+manifest = work / 'metadata' / (args.name + '.json')
+if archive.exists() or manifest.exists():
+    parser.error('Choose a new name to preserve previous source evidence')
+files = [ROOT / name for name in ('CMakeLists.txt', 'resources.qrc', 'README.md')]
+for name in ('src', 'qml', 'cmake', 'resources', 'tools', 'tests', 'docs', '.deps/pdfium'):
+    directory = ROOT / name
+    for base, directories, leaves in os.walk(directory, followlinks=False):
+        directories[:] = [d for d in directories if d not in ('results', '__pycache__', '.git')
+                          and not (Path(base) / d).is_symlink()]
+        files.extend(Path(base) / leaf for leaf in leaves if leaf != 'validation-record.json')
+rows, total = [], 0
+for path in sorted(set(files)):
+    if path.is_symlink() or not path.is_file() or not path.resolve().is_relative_to(ROOT):
+        raise SystemExit('Unexpected non-regular source input')
+    size = path.stat().st_size
+    total += size
+    if len(rows) >= 10000 or size > 256 * 1024 * 1024 or total > 512 * 1024 * 1024:
+        raise SystemExit('Source snapshot exceeds finite limits')
+    with path.open('rb') as stream:
+        digest = hashlib.file_digest(stream, 'sha256').hexdigest()
+    rows.append({'path': str(path.relative_to(ROOT)), 'size': size, 'sha256': digest})
+work.mkdir(parents=True, exist_ok=True)
+manifest.parent.mkdir(parents=True, exist_ok=True)
+with tarfile.open(archive, 'x:gz') as stream:
+    for row in rows:
+        stream.add(ROOT / row['path'], arcname=row['path'], recursive=False)
+with archive.open('rb') as stream:
+    digest = hashlib.file_digest(stream, 'sha256').hexdigest()
+manifest.write_text(json.dumps({'archiveSha256': digest, 'files': rows}, indent=2) + '\n')
+print(json.dumps({'files': len(rows), 'sourceBytes': total, 'archiveSha256': digest}))