beam: add sha256_manifest gen/verify CLI with tests

wizard-work/beam/sha256_manifest.py

@@ -0,0 +1,94 @@
+#!/usr/bin/env python3
+"""Generate and verify a SHA-256 manifest for a directory of files."""
+import argparse
+import hashlib
+import os
+import sys
+
+
+def sha256_file(path):
+    h = hashlib.sha256()
+    with open(path, "rb") as f:
+        for chunk in iter(lambda: f.read(65536), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def collect(root):
+    out = []
+    for dirpath, _, files in os.walk(root):
+        for name in files:
+            full = os.path.join(dirpath, name)
+            rel = os.path.relpath(full, root)
+            out.append((rel, sha256_file(full)))
+    out.sort(key=lambda x: x[0])
+    return out
+
+
+def cmd_gen(root, out_path):
+    rows = collect(root)
+    lines = [f"{digest}  {rel}" for rel, digest in rows]
+    text = "\n".join(lines) + ("\n" if lines else "")
+    if out_path:
+        with open(out_path, "w", encoding="utf-8") as f:
+            f.write(text)
+    else:
+        sys.stdout.write(text)
+    return 0
+
+
+def parse_manifest(path):
+    entries = []
+    with open(path, "r", encoding="utf-8") as f:
+        for lineno, raw in enumerate(f, 1):
+            line = raw.rstrip("\n")
+            if not line.strip():
+                continue
+            parts = line.split("  ", 1)
+            if len(parts) != 2:
+                raise ValueError(f"bad manifest line {lineno}: {line!r}")
+            digest, rel = parts
+            if len(digest) != 64:
+                raise ValueError(f"bad digest on line {lineno}")
+            entries.append((rel, digest))
+    return entries
+
+
+def cmd_verify(root, manifest_path):
+    expected = dict(parse_manifest(manifest_path))
+    failures = []
+    for rel, digest in expected.items():
+        full = os.path.join(root, rel)
+        if not os.path.isfile(full):
+            failures.append(f"MISSING  {rel}")
+            continue
+        got = sha256_file(full)
+        if got != digest:
+            failures.append(f"MISMATCH {rel}\n  expected {digest}\n  got      {got}")
+    for rel, _ in collect(root):
+        if rel not in expected:
+            failures.append(f"EXTRA    {rel}")
+    if failures:
+        sys.stderr.write("verification FAILED:\n" + "\n".join(failures) + "\n")
+        return 1
+    print(f"OK: {len(expected)} files verified")
+    return 0
+
+
+def main(argv=None):
+    p = argparse.ArgumentParser()
+    sub = p.add_subparsers(dest="cmd", required=True)
+    g = sub.add_parser("gen")
+    g.add_argument("root")
+    g.add_argument("--out", default=None)
+    v = sub.add_parser("verify")
+    v.add_argument("root")
+    v.add_argument("manifest")
+    args = p.parse_args(argv)
+    if args.cmd == "gen":
+        return cmd_gen(args.root, args.out)
+    return cmd_verify(args.root, args.manifest)
+
+
+if __name__ == "__main__":
+    sys.exit(main())