feat(cli): accept an archive of dranzer reports as one material

app/controlplane/api/workflowcontract/v1/crafting_schema.proto

@@ -178,7 +178,9 @@ message CraftingSchema {
       SYSINTERNALS_SIGCHECK = 34;
       // Sysinternals AccessChk text output https://learn.microsoft.com/en-us/sysinternals/downloads/accesschk
       SYSINTERNALS_ACCESSCHK = 35;
-      // CERT/CC dranzer ActiveX/COM control test report (plain text) https://github.com/CERTCC/dranzer
+      // CERT/CC dranzer ActiveX/COM control test report (plain text): a single
+      // report or an archive (zip or tar.gz) holding the per-mode reports of one
+      // run (-b, -p, -s, -t) https://github.com/CERTCC/dranzer
       CERTCC_DRANZER = 36;
       // OpenSSF Scorecard result in JSON format
       // https://github.com/ossf/scorecard

pkg/attestation/crafter/api/attestation/v1/crafting_state.go

@@ -240,11 +240,16 @@ func (m *Attestation_Material) ingestMaterialToJSON(rawMaterial []byte, value st
 		// dranzer emits plain text; project it to JSON so the policy engine,
 		// which only consumes JSON, can evaluate it. The raw text is preserved
 		// in the projection's "raw" field for string-matching fallbacks.
-		report, err := dranzer.Parse(rawMaterial)
+		//
+		// The material may also be an archive of the per-mode reports of one run
+		// (-b/-p/-s/-t), so the projection aggregates its entries. Parsing the
+		// archive bytes as text instead would yield an empty report, and the
+		// policy would then skip rather than evaluate — a false pass.
+		bundle, err := dranzer.ParseBundle(rawMaterial)
 		if err != nil {
 			return nil, fmt.Errorf("invalid dranzer material: %w", err)
 		}
-		return json.Marshal(report)
+		return json.Marshal(bundle)
 	}
 
 	return rawMaterial, nil

pkg/attestation/crafter/api/attestation/v1/crafting_state_test.go

@@ -331,6 +331,42 @@ func TestGetEvaluableContentWithMetadata(t *testing.T) {
 	}
 }
 
+// TestDranzerBundleIsEvaluable guards that a CERTCC_DRANZER material holding an
+// archive of per-mode reports projects to an aggregate the existing
+// activex-controls-fuzzed policy can evaluate. Recording the archive whole
+// without aggregating would hand the policy engine zip bytes, which parse to an
+// empty report and make the policy *skip* — a clean-looking false pass.
+func TestDranzerBundleIsEvaluable(t *testing.T) {
+	m := &Attestation_Material{
+		MaterialType: schemaapi.CraftingSchema_Material_CERTCC_DRANZER,
+		M: &Attestation_Material_Artifact_{
+			Artifact: &Attestation_Material_Artifact{Name: "dranzer-report", Digest: "sha256:deadbeef"},
+		},
+	}
+
+	content, err := m.GetEvaluableContent("testdata/dranzer-bundle.zip")
+	require.NoError(t, err)
+
+	var decoded map[string]any
+	require.NoError(t, json.NewDecoder(bytes.NewReader(content)).Decode(&decoded))
+
+	// The policy reads tool.name and needs run evidence to avoid skipping.
+	assert.Equal(t, "dranzer", decoded["tool"].(map[string]any)["name"])
+	assert.Equal(t, "96", decoded["tool"].(map[string]any)["version"])
+
+	// failed_count sums across the bundle, so the -t mode's single failure is
+	// what makes the gate fire.
+	summary := decoded["summary"].(map[string]any)
+	assert.EqualValues(t, 1, summary["failed_count"])
+	assert.EqualValues(t, 0, summary["hung_count"])
+	assert.EqualValues(t, 16, summary["object_count"])
+
+	assert.Len(t, decoded["findings"], 1, "the -t report's crash finding must survive aggregation")
+
+	// The CSV companion is not a report, so only the four modes are listed.
+	assert.Len(t, decoded["reports"], 4)
+}
+
 // TestCoberturaEmptyReportIsEvaluable guards the requirement that a legitimate
 // empty coverage report (line-rate="NaN", no packages) projects to valid JSON
 // the policy engine can evaluate — instead of failing with a NaN marshal error,

pkg/attestation/crafter/materials/archive.go

@@ -16,262 +16,82 @@
 package materials
 
 import (
-	"archive/tar"
-	"archive/zip"
-	"bytes"
-	"compress/gzip"
-	"errors"
 	"fmt"
 	"io"
-	"io/fs"
-	"os"
 	"path"
 	"strings"
-	"syscall"
 
 	schemaapi "github.com/chainloop-dev/chainloop/app/controlplane/api/workflowcontract/v1"
+	"github.com/chainloop-dev/chainloop/pkg/attestation/crafter/materials/archiveio"
 )
 
+// The archive container primitives live in the archiveio leaf package so the
+// policy-input projections can share them without importing this package (which
+// would be an import cycle). The names below are kept as aliases so existing
+// callers and their tests are unaffected.
+
 // ArchiveFormat identifies a supported archive container.
-type ArchiveFormat int
+type ArchiveFormat = archiveio.Format
 
 const (
-	ArchiveNone ArchiveFormat = iota
-	ArchiveZip
-	ArchiveTar
-	ArchiveTarGz
+	ArchiveNone  = archiveio.None
+	ArchiveZip   = archiveio.Zip
+	ArchiveTar   = archiveio.Tar
+	ArchiveTarGz = archiveio.TarGz
 )
 
-// DetectArchive reports whether path is a supported archive and, if so, its
-// format. Detection is by extension first; for files whose extension does not
-// match, magic bytes are used as a backstop so renamed archives are still
-// caught. A non-archive returns (ArchiveNone, nil).
-func DetectArchive(path string) (ArchiveFormat, error) {
-	lower := strings.ToLower(path)
-	switch {
-	case strings.HasSuffix(lower, ".zip"):
-		return ArchiveZip, nil
-	case strings.HasSuffix(lower, ".tar.gz"), strings.HasSuffix(lower, ".tgz"):
-		return ArchiveTarGz, nil
-	case strings.HasSuffix(lower, ".tar"):
-		return ArchiveTar, nil
-	}
-
-	return detectByMagic(path)
-}
-
-func detectByMagic(path string) (ArchiveFormat, error) {
-	f, err := os.Open(path)
-	if err != nil {
-		// These errors mean the value is not a file path at all (e.g. "hello
-		// world" for STRING, or "registry/app:v1" for CONTAINER_IMAGE where
-		// "registry" happens to be a regular file in the working directory, which
-		// yields ENOTDIR); treat them as a non-archive so callers passing non-file
-		// values are not surprised. Any other error (permissions, I/O) is real and
-		// must surface.
-		if errors.Is(err, fs.ErrNotExist) || errors.Is(err, syscall.ENOTDIR) {
-			return ArchiveNone, nil
-		}
-		return ArchiveNone, fmt.Errorf("opening %q: %w", path, err)
-	}
-	defer f.Close()
-
-	// 512 bytes is enough for the gzip/zip magic and the tar "ustar" marker at
-	// offset 257.
-	header := make([]byte, 512)
-	n, _ := f.Read(header)
-	header = header[:n]
-
-	switch {
-	case bytes.HasPrefix(header, []byte("PK\x03\x04")), bytes.HasPrefix(header, []byte("PK\x05\x06")):
-		return ArchiveZip, nil
-	case bytes.HasPrefix(header, []byte{0x1f, 0x8b}):
-		return ArchiveTarGz, nil
-	case len(header) >= 262 && bytes.Equal(header[257:262], []byte("ustar")):
-		return ArchiveTar, nil
-	}
-
-	return ArchiveNone, nil
-}
+// ArchiveLimits bounds archive expansion to guard against zip bombs.
+type ArchiveLimits = archiveio.Limits
 
 var (
 	// ErrTooManyEntries is returned when an archive has more qualifying entries
 	// than the configured maximum.
-	ErrTooManyEntries = errors.New("archive exceeds the maximum number of entries")
+	ErrTooManyEntries = archiveio.ErrTooManyEntries
 	// ErrArchiveTooLarge is returned when the running uncompressed size of an
 	// archive exceeds the configured maximum.
-	ErrArchiveTooLarge = errors.New("archive exceeds the maximum uncompressed size")
+	ErrArchiveTooLarge = archiveio.ErrArchiveTooLarge
 	// ErrUnsafeEntry is returned when an archive entry's path is absolute or escapes the extraction root.
-	ErrUnsafeEntry = errors.New("unsafe entry path in archive")
+	ErrUnsafeEntry = archiveio.ErrUnsafeEntry
 )
 
-// ArchiveLimits bounds archive expansion to guard against zip bombs.
-type ArchiveLimits struct {
-	MaxEntries   int
-	MaxTotalSize int64
+// DetectArchive reports whether path is a supported archive and, if so, its
+// format. A non-archive returns (ArchiveNone, nil).
+func DetectArchive(path string) (ArchiveFormat, error) {
+	return archiveio.DetectPath(path)
 }
 
 // DefaultArchiveLimits returns the safe defaults: 10000 entries and 1 GiB
 // total uncompressed size.
 func DefaultArchiveLimits() ArchiveLimits {
-	return ArchiveLimits{MaxEntries: 10000, MaxTotalSize: 1 << 30}
-}
-
-// capReader wraps a reader and fails once the shared running total exceeds max,
-// so we never trust an archive's declared sizes.
-type capReader struct {
-	r     io.Reader
-	total *int64
-	max   int64
-}
-
-func (c *capReader) Read(p []byte) (int, error) {
-	n, err := c.r.Read(p)
-	*c.total += int64(n)
-	if *c.total > c.max {
-		return n, ErrArchiveTooLarge
-	}
-	return n, err
+	return archiveio.DefaultLimits()
 }
 
 // WalkArchiveEntries calls yield for every regular file in the archive,
 // enforcing the limits and skipping directories, symlinks, hardlinks, empty
 // entries, and path-traversal entries.
 func WalkArchiveEntries(path string, format ArchiveFormat, limits ArchiveLimits, yield func(name string, r io.Reader) error) error {
-	var total int64
-	count := 0
-	visit := func(name string, r io.Reader) error {
-		if !safeArchivePath(name) {
-			return fmt.Errorf("%w: %q", ErrUnsafeEntry, name)
-		}
-		count++
-		if count > limits.MaxEntries {
-			return ErrTooManyEntries
-		}
-		if err := yield(name, &capReader{r: r, total: &total, max: limits.MaxTotalSize}); err != nil {
-			return fmt.Errorf("processing entry %q: %w", name, err)
-		}
-		return nil
-	}
-
-	switch format {
-	case ArchiveZip:
-		return walkZip(path, visit)
-	case ArchiveTar:
-		return walkTar(path, false, visit)
-	case ArchiveTarGz:
-		return walkTar(path, true, visit)
-	default:
-		return fmt.Errorf("unsupported archive format")
-	}
-}
-
-// safeArchivePath rejects absolute paths and any path that escapes the
-// extraction root via ".." path components. A filename that merely contains
-// ".." as a substring (e.g. "foo..bar.json") is accepted; only actual path
-// components equal to ".." are rejected.
-func safeArchivePath(name string) bool {
-	normalized := strings.ReplaceAll(name, "\\", "/")
-	// Reject absolute paths, including Windows drive-letter (e.g. "C:/x") and
-	// UNC paths (which normalize to a leading "/").
-	if strings.HasPrefix(normalized, "/") || hasWindowsDriveLetter(normalized) {
-		return false
-	}
-	// Canonicalise against a virtual root and check that the result stays
-	// within it. path.Clean will resolve ".." components so a path like
-	// "a/../../etc/passwd" becomes "/etc/passwd" which does not start with
-	// the virtual prefix "/root/"; a safe path like "a/b.txt" becomes
-	// "/root/a/b.txt" which does.
-	const root = "/root"
-	clean := path.Clean(root + "/" + normalized)
-	return strings.HasPrefix(clean, root+"/") || clean == root
-}
-
-// hasWindowsDriveLetter reports whether name begins with a Windows drive-letter
-// prefix such as "C:" or "c:/", which denotes an absolute path on Windows.
-func hasWindowsDriveLetter(name string) bool {
-	if len(name) < 2 || name[1] != ':' {
-		return false
-	}
-	c := name[0]
-	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z')
-}
-
-func walkZip(p string, visit func(name string, r io.Reader) error) error {
-	zr, err := zip.OpenReader(p)
-	if err != nil {
-		return fmt.Errorf("opening zip: %w", err)
-	}
-	defer zr.Close()
-
-	for _, f := range zr.File {
-		// Skip directories, symlinks, and empty entries: they carry no file
-		// content worth recording as a material. Empty-entry skipping is
-		// intentional per the explode design (an empty evidence file produces
-		// no material). Note: symlink detection relies on Unix mode bits stored
-		// in the zip; archives written without Unix metadata won't carry the
-		// symlink bit, so such a symlink would be treated as a regular file
-		// (its content being the stored target path). Tar symlinks are detected
-		// reliably via the typeflag below.
-		if f.FileInfo().IsDir() || f.Mode()&os.ModeSymlink != 0 || f.UncompressedSize64 == 0 {
-			continue
-		}
-		rc, err := f.Open()
-		if err != nil {
-			return fmt.Errorf("opening entry %q: %w", f.Name, err)
-		}
-		err = visit(f.Name, rc)
-		rc.Close()
-		if err != nil {
-			return err
-		}
-	}
-	return nil
-}
-
-func walkTar(p string, gzipped bool, visit func(name string, r io.Reader) error) error {
-	f, err := os.Open(p)
-	if err != nil {
-		return fmt.Errorf("opening tar: %w", err)
-	}
-	defer f.Close()
-
-	var src io.Reader = f
-	if gzipped {
-		gz, err := gzip.NewReader(f)
-		if err != nil {
-			return fmt.Errorf("opening gzip: %w", err)
-		}
-		defer gz.Close()
-		src = gz
-	}
-
-	tr := tar.NewReader(src)
-	for {
-		hdr, err := tr.Next()
-		if errors.Is(err, io.EOF) {
-			return nil
-		}
-		if err != nil {
-			return fmt.Errorf("reading tar: %w", err)
-		}
-		// Only regular files become materials; directories, symlinks, hardlinks
-		// and other special entries are skipped via the typeflag. Empty entries
-		// are skipped intentionally (an empty evidence file produces no material).
-		if hdr.Typeflag != tar.TypeReg || hdr.Size == 0 {
-			continue
-		}
-		if err := visit(hdr.Name, tr); err != nil {
-			return err
-		}
-	}
+	return archiveio.WalkPath(path, format, limits, yield)
 }
 
 // explodableKinds is the allowlist of material kinds whose archive value is
 // expanded into one material per entry. Every other kind (ARTIFACT, EVIDENCE,
 // ZAP_DAST_ZIP, …) records the archive whole, so a customer can still provide a
-// regular zip as a single material. Extend this set as more kinds gain a
-// meaningful "bundle of the same kind" archive form.
+// regular zip as a single material.
+//
+// A kind that accepts an archive has two strategies available, and this set
+// selects the first:
+//
+//   - Explode (this set): each entry is independent evidence that stands on its
+//     own, so each becomes its own material bound to policies by type.
+//   - Record whole plus an aggregating projection: the entries are one artifact
+//     whose parts only mean something together, so the archive fills a single
+//     contract slot and the projection folds the entries for the policy engine.
+//     CERTCC_DRANZER works this way — see dranzer.ParseBundle and the projection
+//     in Attestation_Material.ingestMaterialToJSON — because one run's per-mode
+//     reports are facets of a single result, not interchangeable evidence.
+//
+// Adding a kind here changes its contract-slot semantics from one material to N,
+// so choose the strategy before extending the set.
 var explodableKinds = map[string]struct{}{
 	schemaapi.CraftingSchema_Material_SBOM_CYCLONEDX_JSON.String(): {},
 	schemaapi.CraftingSchema_Material_SBOM_SPDX_JSON.String():      {},