P04-01: 同時発生の更新規約

tools/check_p04_order_evidence.py

@@ -141,6 +141,44 @@ def git_bytes(*args):
     return subprocess.check_output(['git', '--no-replace-objects', *args], cwd=ROOT, env=env)
 
 
+def parse_blob_batch(stdout, oids):
+    """Decode length-framed output without splitting binary payloads into lines."""
+    result = {}
+    offset = 0
+    for oid in oids:
+        end = stdout.find(b'\n', offset)
+        require(end >= 0, 'truncated blob batch header')
+        header = stdout[offset:end].split(b' ')
+        require(len(header) == 3 and header[0] == oid.encode('ascii')
+                and header[1] == b'blob' and re.fullmatch(rb'[0-9]+', header[2]) is not None,
+                'invalid blob batch header: ' + oid)
+        size = int(header[2])
+        start = end + 1
+        end = start + size
+        require(end < len(stdout) and stdout[end:end + 1] == b'\n',
+                'truncated blob batch payload or missing LF: ' + oid)
+        result[oid] = stdout[start:end]
+        offset = end + 1
+    require(offset == len(stdout), 'extra blob batch output')
+    return result
+
+
+def read_blobs(oids):
+    """One process per request; no cache can cross object namespaces."""
+    requested = list(oids)
+    require(all(isinstance(oid, str) and re.fullmatch('[0-9a-f]{40}', oid) is not None
+                for oid in requested), 'invalid full blob OID')
+    requested = sorted(set(requested))
+    if not requested:
+        return {}
+    env = _GIT_ENV if _GIT_ENV is not None else git_environment()
+    # Inherit stderr and raise on nonzero status, exactly as git_bytes does.
+    stdout = subprocess.check_output(['git', '--no-replace-objects', 'cat-file', '--batch'],
+                                    input=('\n'.join(requested) + '\n').encode('ascii'),
+                                    cwd=ROOT, env=env)
+    return parse_blob_batch(stdout, requested)
+
+
 def git_environment():
     env = {k: v for k, v in os.environ.items() if not k.startswith('GIT_')}
     env.update(GIT_OPTIONAL_LOCKS='0', GIT_NO_REPLACE_OBJECTS='1', GIT_CONFIG_NOSYSTEM='1',
@@ -197,9 +235,11 @@ def allowed_path(path):
 
 def product_manifest(entries):
     result = {}
+    blobs = read_blobs(oid for path, (_, oid) in entries.items()
+                       if selected_path(path) and path != CHECKER_PATH)
     for path, (_, oid) in sorted(entries.items()):
         if selected_path(path) and path != CHECKER_PATH:
-            data = git_bytes('cat-file', 'blob', oid)
+            data = blobs[oid]
             result[path] = {'bytes': len(data), 'sha256': hashlib.sha256(data).hexdigest()}
     return result
 
@@ -337,9 +377,10 @@ def actual_checkout():
     require(not git_bytes('status', '--porcelain=v1', '--untracked-files=all',
                           '--ignore-submodules=none'), 'checkout is not clean')
     require(not git_bytes('ls-files', '--others', '-z'), 'untracked/ignored substitution')
+    blobs = read_blobs(oid for _, oid in entries.values())
     for path, (mode, oid) in entries.items():
         actual = safe(ROOT, path)
-        require(actual.read_bytes() == git_bytes('cat-file', 'blob', oid), 'HEAD/tree/FS bytes: ' + path)
+        require(actual.read_bytes() == blobs[oid], 'HEAD/tree/FS bytes: ' + path)
         require(('100755' if actual.stat().st_mode & 0o111 else '100644') == mode,
                 'HEAD/tree/FS mode: ' + path)
     # Also reject untracked directory symlinks, including ones ignored by Git.