Ensure leading directories always exist in manifest

When extracting from an archive it is possible the leading directories
are not part of the archive. Add them to the manifest as otherwise the
behaviour of "index.html" varies depending how the archive was created.

src/extract.go

@@ -145,6 +145,9 @@ func ExtractTar(ctx context.Context, reader io.Reader, oldManifest *Manifest) (*
 		return nil, UnresolvedRefError{missing}
 	}
 
+	// Ensure parent directories exist for all entries.
+	EnsureLeadingDirectories(manifest)
+
 	logc.Printf(ctx,
 		"reuse: %s recycled, %s transferred\n",
 		datasize.ByteSize(dataBytesRecycled).HR(),
@@ -226,6 +229,9 @@ func ExtractZip(ctx context.Context, reader io.Reader, oldManifest *Manifest) (*
 		return nil, UnresolvedRefError{missing}
 	}
 
+	// Ensure parent directories exist for all entries.
+	EnsureLeadingDirectories(manifest)
+
 	logc.Printf(ctx,
 		"reuse: %s recycled, %s transferred\n",
 		datasize.ByteSize(dataBytesRecycled).HR(),
@@ -234,3 +240,4 @@ func ExtractZip(ctx context.Context, reader io.Reader, oldManifest *Manifest) (*
 
 	return manifest, nil
 }
+

src/manifest.go

@@ -144,6 +144,20 @@ func AddProblem(manifest *Manifest, pathName, format string, args ...any) error
 	return fmt.Errorf("%s: %s", pathName, cause)
 }
 
+// EnsureLeadingDirectories adds directory entries for any parent directories
+// that are implicitly referenced by files in the manifest but don't have
+// explicit directory entries. (This can be the case if an archive is created
+// via globs rather than including a whole directory.)
+func EnsureLeadingDirectories(manifest *Manifest) {
+	for name := range manifest.Contents {
+		for dir := path.Dir(name); dir != "." && dir != ""; dir = path.Dir(dir) {
+			if _, exists := manifest.Contents[dir]; !exists {
+				AddDirectory(manifest, dir)
+			}
+		}
+	}
+}
+
 func GetProblemReport(manifest *Manifest) []string {
 	var report []string
 	for _, problem := range manifest.Problems {