summaryrefslogtreecommitdiff
path: root/vendor/github.com/containerd
diff options
context:
space:
mode:
Diffstat (limited to 'vendor/github.com/containerd')
-rw-r--r--vendor/github.com/containerd/stargz-snapshotter/estargz/LICENSE202
-rw-r--r--vendor/github.com/containerd/stargz-snapshotter/estargz/build.go628
-rw-r--r--vendor/github.com/containerd/stargz-snapshotter/estargz/errorutil/errors.go40
-rw-r--r--vendor/github.com/containerd/stargz-snapshotter/estargz/estargz.go933
-rw-r--r--vendor/github.com/containerd/stargz-snapshotter/estargz/go.mod10
-rw-r--r--vendor/github.com/containerd/stargz-snapshotter/estargz/go.sum8
-rw-r--r--vendor/github.com/containerd/stargz-snapshotter/estargz/gzip.go216
-rw-r--r--vendor/github.com/containerd/stargz-snapshotter/estargz/testutil.go1933
-rw-r--r--vendor/github.com/containerd/stargz-snapshotter/estargz/types.go314
9 files changed, 4284 insertions, 0 deletions
diff --git a/vendor/github.com/containerd/stargz-snapshotter/estargz/LICENSE b/vendor/github.com/containerd/stargz-snapshotter/estargz/LICENSE
new file mode 100644
index 000000000..d64569567
--- /dev/null
+++ b/vendor/github.com/containerd/stargz-snapshotter/estargz/LICENSE
@@ -0,0 +1,202 @@
+
+ Apache License
+ Version 2.0, January 2004
+ http://www.apache.org/licenses/
+
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+ 1. Definitions.
+
+ "License" shall mean the terms and conditions for use, reproduction,
+ and distribution as defined by Sections 1 through 9 of this document.
+
+ "Licensor" shall mean the copyright owner or entity authorized by
+ the copyright owner that is granting the License.
+
+ "Legal Entity" shall mean the union of the acting entity and all
+ other entities that control, are controlled by, or are under common
+ control with that entity. For the purposes of this definition,
+ "control" means (i) the power, direct or indirect, to cause the
+ direction or management of such entity, whether by contract or
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
+ outstanding shares, or (iii) beneficial ownership of such entity.
+
+ "You" (or "Your") shall mean an individual or Legal Entity
+ exercising permissions granted by this License.
+
+ "Source" form shall mean the preferred form for making modifications,
+ including but not limited to software source code, documentation
+ source, and configuration files.
+
+ "Object" form shall mean any form resulting from mechanical
+ transformation or translation of a Source form, including but
+ not limited to compiled object code, generated documentation,
+ and conversions to other media types.
+
+ "Work" shall mean the work of authorship, whether in Source or
+ Object form, made available under the License, as indicated by a
+ copyright notice that is included in or attached to the work
+ (an example is provided in the Appendix below).
+
+ "Derivative Works" shall mean any work, whether in Source or Object
+ form, that is based on (or derived from) the Work and for which the
+ editorial revisions, annotations, elaborations, or other modifications
+ represent, as a whole, an original work of authorship. For the purposes
+ of this License, Derivative Works shall not include works that remain
+ separable from, or merely link (or bind by name) to the interfaces of,
+ the Work and Derivative Works thereof.
+
+ "Contribution" shall mean any work of authorship, including
+ the original version of the Work and any modifications or additions
+ to that Work or Derivative Works thereof, that is intentionally
+ submitted to Licensor for inclusion in the Work by the copyright owner
+ or by an individual or Legal Entity authorized to submit on behalf of
+ the copyright owner. For the purposes of this definition, "submitted"
+ means any form of electronic, verbal, or written communication sent
+ to the Licensor or its representatives, including but not limited to
+ communication on electronic mailing lists, source code control systems,
+ and issue tracking systems that are managed by, or on behalf of, the
+ Licensor for the purpose of discussing and improving the Work, but
+ excluding communication that is conspicuously marked or otherwise
+ designated in writing by the copyright owner as "Not a Contribution."
+
+ "Contributor" shall mean Licensor and any individual or Legal Entity
+ on behalf of whom a Contribution has been received by Licensor and
+ subsequently incorporated within the Work.
+
+ 2. Grant of Copyright License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ copyright license to reproduce, prepare Derivative Works of,
+ publicly display, publicly perform, sublicense, and distribute the
+ Work and such Derivative Works in Source or Object form.
+
+ 3. Grant of Patent License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ (except as stated in this section) patent license to make, have made,
+ use, offer to sell, sell, import, and otherwise transfer the Work,
+ where such license applies only to those patent claims licensable
+ by such Contributor that are necessarily infringed by their
+ Contribution(s) alone or by combination of their Contribution(s)
+ with the Work to which such Contribution(s) was submitted. If You
+ institute patent litigation against any entity (including a
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
+ or a Contribution incorporated within the Work constitutes direct
+ or contributory patent infringement, then any patent licenses
+ granted to You under this License for that Work shall terminate
+ as of the date such litigation is filed.
+
+ 4. Redistribution. You may reproduce and distribute copies of the
+ Work or Derivative Works thereof in any medium, with or without
+ modifications, and in Source or Object form, provided that You
+ meet the following conditions:
+
+ (a) You must give any other recipients of the Work or
+ Derivative Works a copy of this License; and
+
+ (b) You must cause any modified files to carry prominent notices
+ stating that You changed the files; and
+
+ (c) You must retain, in the Source form of any Derivative Works
+ that You distribute, all copyright, patent, trademark, and
+ attribution notices from the Source form of the Work,
+ excluding those notices that do not pertain to any part of
+ the Derivative Works; and
+
+ (d) If the Work includes a "NOTICE" text file as part of its
+ distribution, then any Derivative Works that You distribute must
+ include a readable copy of the attribution notices contained
+ within such NOTICE file, excluding those notices that do not
+ pertain to any part of the Derivative Works, in at least one
+ of the following places: within a NOTICE text file distributed
+ as part of the Derivative Works; within the Source form or
+ documentation, if provided along with the Derivative Works; or,
+ within a display generated by the Derivative Works, if and
+ wherever such third-party notices normally appear. The contents
+ of the NOTICE file are for informational purposes only and
+ do not modify the License. You may add Your own attribution
+ notices within Derivative Works that You distribute, alongside
+ or as an addendum to the NOTICE text from the Work, provided
+ that such additional attribution notices cannot be construed
+ as modifying the License.
+
+ You may add Your own copyright statement to Your modifications and
+ may provide additional or different license terms and conditions
+ for use, reproduction, or distribution of Your modifications, or
+ for any such Derivative Works as a whole, provided Your use,
+ reproduction, and distribution of the Work otherwise complies with
+ the conditions stated in this License.
+
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
+ any Contribution intentionally submitted for inclusion in the Work
+ by You to the Licensor shall be under the terms and conditions of
+ this License, without any additional terms or conditions.
+ Notwithstanding the above, nothing herein shall supersede or modify
+ the terms of any separate license agreement you may have executed
+ with Licensor regarding such Contributions.
+
+ 6. Trademarks. This License does not grant permission to use the trade
+ names, trademarks, service marks, or product names of the Licensor,
+ except as required for reasonable and customary use in describing the
+ origin of the Work and reproducing the content of the NOTICE file.
+
+ 7. Disclaimer of Warranty. Unless required by applicable law or
+ agreed to in writing, Licensor provides the Work (and each
+ Contributor provides its Contributions) on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+ implied, including, without limitation, any warranties or conditions
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+ PARTICULAR PURPOSE. You are solely responsible for determining the
+ appropriateness of using or redistributing the Work and assume any
+ risks associated with Your exercise of permissions under this License.
+
+ 8. Limitation of Liability. In no event and under no legal theory,
+ whether in tort (including negligence), contract, or otherwise,
+ unless required by applicable law (such as deliberate and grossly
+ negligent acts) or agreed to in writing, shall any Contributor be
+ liable to You for damages, including any direct, indirect, special,
+ incidental, or consequential damages of any character arising as a
+ result of this License or out of the use or inability to use the
+ Work (including but not limited to damages for loss of goodwill,
+ work stoppage, computer failure or malfunction, or any and all
+ other commercial damages or losses), even if such Contributor
+ has been advised of the possibility of such damages.
+
+ 9. Accepting Warranty or Additional Liability. While redistributing
+ the Work or Derivative Works thereof, You may choose to offer,
+ and charge a fee for, acceptance of support, warranty, indemnity,
+ or other liability obligations and/or rights consistent with this
+ License. However, in accepting such obligations, You may act only
+ on Your own behalf and on Your sole responsibility, not on behalf
+ of any other Contributor, and only if You agree to indemnify,
+ defend, and hold each Contributor harmless for any liability
+ incurred by, or claims asserted against, such Contributor by reason
+ of your accepting any such warranty or additional liability.
+
+ END OF TERMS AND CONDITIONS
+
+ APPENDIX: How to apply the Apache License to your work.
+
+ To apply the Apache License to your work, attach the following
+ boilerplate notice, with the fields enclosed by brackets "[]"
+ replaced with your own identifying information. (Don't include
+ the brackets!) The text should be enclosed in the appropriate
+ comment syntax for the file format. We also recommend that a
+ file or class name and description of purpose be included on the
+ same "printed page" as the copyright notice for easier
+ identification within third-party archives.
+
+ Copyright [yyyy] [name of copyright owner]
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
diff --git a/vendor/github.com/containerd/stargz-snapshotter/estargz/build.go b/vendor/github.com/containerd/stargz-snapshotter/estargz/build.go
new file mode 100644
index 000000000..708b26689
--- /dev/null
+++ b/vendor/github.com/containerd/stargz-snapshotter/estargz/build.go
@@ -0,0 +1,628 @@
+/*
+ Copyright The containerd Authors.
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+*/
+
+/*
+ Copyright 2019 The Go Authors. All rights reserved.
+ Use of this source code is governed by a BSD-style
+ license that can be found in the LICENSE file.
+*/
+
+package estargz
+
+import (
+ "archive/tar"
+ "bytes"
+ "compress/gzip"
+ "fmt"
+ "io"
+ "io/ioutil"
+ "os"
+ "path"
+ "runtime"
+ "strings"
+ "sync"
+
+ "github.com/containerd/stargz-snapshotter/estargz/errorutil"
+ "github.com/klauspost/compress/zstd"
+ digest "github.com/opencontainers/go-digest"
+ "github.com/pkg/errors"
+ "golang.org/x/sync/errgroup"
+)
+
+type options struct {
+ chunkSize int
+ compressionLevel int
+ prioritizedFiles []string
+ missedPrioritizedFiles *[]string
+ compression Compression
+}
+
+type Option func(o *options) error
+
+// WithChunkSize option specifies the chunk size of eStargz blob to build.
+func WithChunkSize(chunkSize int) Option {
+ return func(o *options) error {
+ o.chunkSize = chunkSize
+ return nil
+ }
+}
+
+// WithCompressionLevel option specifies the gzip compression level.
+// The default is gzip.BestCompression.
+// See also: https://godoc.org/compress/gzip#pkg-constants
+func WithCompressionLevel(level int) Option {
+ return func(o *options) error {
+ o.compressionLevel = level
+ return nil
+ }
+}
+
+// WithPrioritizedFiles option specifies the list of prioritized files.
+// These files must be complete paths that are absolute or relative to "/"
+// For example, all of "foo/bar", "/foo/bar", "./foo/bar" and "../foo/bar"
+// are treated as "/foo/bar".
+func WithPrioritizedFiles(files []string) Option {
+ return func(o *options) error {
+ o.prioritizedFiles = files
+ return nil
+ }
+}
+
+// WithAllowPrioritizeNotFound makes Build continue the execution even if some
+// of prioritized files specified by WithPrioritizedFiles option aren't found
+// in the input tar. Instead, this records all missed file names to the passed
+// slice.
+func WithAllowPrioritizeNotFound(missedFiles *[]string) Option {
+ return func(o *options) error {
+ if missedFiles == nil {
+ return fmt.Errorf("WithAllowPrioritizeNotFound: slice must be passed")
+ }
+ o.missedPrioritizedFiles = missedFiles
+ return nil
+ }
+}
+
+// WithCompression specifies compression algorithm to be used.
+// Default is gzip.
+func WithCompression(compression Compression) Option {
+ return func(o *options) error {
+ o.compression = compression
+ return nil
+ }
+}
+
+// Blob is an eStargz blob.
+type Blob struct {
+ io.ReadCloser
+ diffID digest.Digester
+ tocDigest digest.Digest
+}
+
+// DiffID returns the digest of uncompressed blob.
+// It is only valid to call DiffID after Close.
+func (b *Blob) DiffID() digest.Digest {
+ return b.diffID.Digest()
+}
+
+// TOCDigest returns the digest of uncompressed TOC JSON.
+func (b *Blob) TOCDigest() digest.Digest {
+ return b.tocDigest
+}
+
+// Build builds an eStargz blob which is an extended version of stargz, from a blob (gzip, zstd
+// or plain tar) passed through the argument. If there are some prioritized files are listed in
+// the option, these files are grouped as "prioritized" and can be used for runtime optimization
+// (e.g. prefetch). This function builds a blob in parallel, with dividing that blob into several
+// (at least the number of runtime.GOMAXPROCS(0)) sub-blobs.
+func Build(tarBlob *io.SectionReader, opt ...Option) (_ *Blob, rErr error) {
+ var opts options
+ opts.compressionLevel = gzip.BestCompression // BestCompression by default
+ for _, o := range opt {
+ if err := o(&opts); err != nil {
+ return nil, err
+ }
+ }
+ if opts.compression == nil {
+ opts.compression = newGzipCompressionWithLevel(opts.compressionLevel)
+ }
+ layerFiles := newTempFiles()
+ defer func() {
+ if rErr != nil {
+ if err := layerFiles.CleanupAll(); err != nil {
+ rErr = errors.Wrapf(rErr, "failed to cleanup tmp files: %v", err)
+ }
+ }
+ }()
+ tarBlob, err := decompressBlob(tarBlob, layerFiles)
+ if err != nil {
+ return nil, err
+ }
+ entries, err := sortEntries(tarBlob, opts.prioritizedFiles, opts.missedPrioritizedFiles)
+ if err != nil {
+ return nil, err
+ }
+ tarParts := divideEntries(entries, runtime.GOMAXPROCS(0))
+ writers := make([]*Writer, len(tarParts))
+ payloads := make([]*os.File, len(tarParts))
+ var mu sync.Mutex
+ var eg errgroup.Group
+ for i, parts := range tarParts {
+ i, parts := i, parts
+ // builds verifiable stargz sub-blobs
+ eg.Go(func() error {
+ esgzFile, err := layerFiles.TempFile("", "esgzdata")
+ if err != nil {
+ return err
+ }
+ sw := NewWriterWithCompressor(esgzFile, opts.compression)
+ sw.ChunkSize = opts.chunkSize
+ if err := sw.AppendTar(readerFromEntries(parts...)); err != nil {
+ return err
+ }
+ mu.Lock()
+ writers[i] = sw
+ payloads[i] = esgzFile
+ mu.Unlock()
+ return nil
+ })
+ }
+ if err := eg.Wait(); err != nil {
+ rErr = err
+ return nil, err
+ }
+ tocAndFooter, tocDgst, err := closeWithCombine(opts.compressionLevel, writers...)
+ if err != nil {
+ rErr = err
+ return nil, err
+ }
+ var rs []io.Reader
+ for _, p := range payloads {
+ fs, err := fileSectionReader(p)
+ if err != nil {
+ return nil, err
+ }
+ rs = append(rs, fs)
+ }
+ diffID := digest.Canonical.Digester()
+ pr, pw := io.Pipe()
+ go func() {
+ r, err := opts.compression.Reader(io.TeeReader(io.MultiReader(append(rs, tocAndFooter)...), pw))
+ if err != nil {
+ pw.CloseWithError(err)
+ return
+ }
+ defer r.Close()
+ if _, err := io.Copy(diffID.Hash(), r); err != nil {
+ pw.CloseWithError(err)
+ return
+ }
+ pw.Close()
+ }()
+ return &Blob{
+ ReadCloser: readCloser{
+ Reader: pr,
+ closeFunc: layerFiles.CleanupAll,
+ },
+ tocDigest: tocDgst,
+ diffID: diffID,
+ }, nil
+}
+
+// closeWithCombine takes unclosed Writers and close them. This also returns the
+// toc that combined all Writers into.
+// Writers doesn't write TOC and footer to the underlying writers so they can be
+// combined into a single eStargz and tocAndFooter returned by this function can
+// be appended at the tail of that combined blob.
+func closeWithCombine(compressionLevel int, ws ...*Writer) (tocAndFooterR io.Reader, tocDgst digest.Digest, err error) {
+ if len(ws) == 0 {
+ return nil, "", fmt.Errorf("at least one writer must be passed")
+ }
+ for _, w := range ws {
+ if w.closed {
+ return nil, "", fmt.Errorf("writer must be unclosed")
+ }
+ defer func(w *Writer) { w.closed = true }(w)
+ if err := w.closeGz(); err != nil {
+ return nil, "", err
+ }
+ if err := w.bw.Flush(); err != nil {
+ return nil, "", err
+ }
+ }
+ var (
+ mtoc = new(JTOC)
+ currentOffset int64
+ )
+ mtoc.Version = ws[0].toc.Version
+ for _, w := range ws {
+ for _, e := range w.toc.Entries {
+ // Recalculate Offset of non-empty files/chunks
+ if (e.Type == "reg" && e.Size > 0) || e.Type == "chunk" {
+ e.Offset += currentOffset
+ }
+ mtoc.Entries = append(mtoc.Entries, e)
+ }
+ if w.toc.Version > mtoc.Version {
+ mtoc.Version = w.toc.Version
+ }
+ currentOffset += w.cw.n
+ }
+
+ return tocAndFooter(ws[0].compressor, mtoc, currentOffset)
+}
+
+func tocAndFooter(compressor Compressor, toc *JTOC, offset int64) (io.Reader, digest.Digest, error) {
+ buf := new(bytes.Buffer)
+ tocDigest, err := compressor.WriteTOCAndFooter(buf, offset, toc, nil)
+ if err != nil {
+ return nil, "", err
+ }
+ return buf, tocDigest, nil
+}
+
+// divideEntries divides passed entries to the parts at least the number specified by the
+// argument.
+func divideEntries(entries []*entry, minPartsNum int) (set [][]*entry) {
+ var estimatedSize int64
+ for _, e := range entries {
+ estimatedSize += e.header.Size
+ }
+ unitSize := estimatedSize / int64(minPartsNum)
+ var (
+ nextEnd = unitSize
+ offset int64
+ )
+ set = append(set, []*entry{})
+ for _, e := range entries {
+ set[len(set)-1] = append(set[len(set)-1], e)
+ offset += e.header.Size
+ if offset > nextEnd {
+ set = append(set, []*entry{})
+ nextEnd += unitSize
+ }
+ }
+ return
+}
+
+var errNotFound = errors.New("not found")
+
+// sortEntries reads the specified tar blob and returns a list of tar entries.
+// If some of prioritized files are specified, the list starts from these
+// files with keeping the order specified by the argument.
+func sortEntries(in io.ReaderAt, prioritized []string, missedPrioritized *[]string) ([]*entry, error) {
+
+ // Import tar file.
+ intar, err := importTar(in)
+ if err != nil {
+ return nil, errors.Wrap(err, "failed to sort")
+ }
+
+ // Sort the tar file respecting to the prioritized files list.
+ sorted := &tarFile{}
+ for _, l := range prioritized {
+ if err := moveRec(l, intar, sorted); err != nil {
+ if errors.Is(err, errNotFound) && missedPrioritized != nil {
+ *missedPrioritized = append(*missedPrioritized, l)
+ continue // allow not found
+ }
+ return nil, errors.Wrap(err, "failed to sort tar entries")
+ }
+ }
+ if len(prioritized) == 0 {
+ sorted.add(&entry{
+ header: &tar.Header{
+ Name: NoPrefetchLandmark,
+ Typeflag: tar.TypeReg,
+ Size: int64(len([]byte{landmarkContents})),
+ },
+ payload: bytes.NewReader([]byte{landmarkContents}),
+ })
+ } else {
+ sorted.add(&entry{
+ header: &tar.Header{
+ Name: PrefetchLandmark,
+ Typeflag: tar.TypeReg,
+ Size: int64(len([]byte{landmarkContents})),
+ },
+ payload: bytes.NewReader([]byte{landmarkContents}),
+ })
+ }
+
+ // Dump all entry and concatinate them.
+ return append(sorted.dump(), intar.dump()...), nil
+}
+
+// readerFromEntries returns a reader of tar archive that contains entries passed
+// through the arguments.
+func readerFromEntries(entries ...*entry) io.Reader {
+ pr, pw := io.Pipe()
+ go func() {
+ tw := tar.NewWriter(pw)
+ defer tw.Close()
+ for _, entry := range entries {
+ if err := tw.WriteHeader(entry.header); err != nil {
+ pw.CloseWithError(fmt.Errorf("Failed to write tar header: %v", err))
+ return
+ }
+ if _, err := io.Copy(tw, entry.payload); err != nil {
+ pw.CloseWithError(fmt.Errorf("Failed to write tar payload: %v", err))
+ return
+ }
+ }
+ pw.Close()
+ }()
+ return pr
+}
+
+func importTar(in io.ReaderAt) (*tarFile, error) {
+ tf := &tarFile{}
+ pw, err := newCountReader(in)
+ if err != nil {
+ return nil, errors.Wrap(err, "failed to make position watcher")
+ }
+ tr := tar.NewReader(pw)
+
+ // Walk through all nodes.
+ for {
+ // Fetch and parse next header.
+ h, err := tr.Next()
+ if err != nil {
+ if err == io.EOF {
+ break
+ } else {
+ return nil, errors.Wrap(err, "failed to parse tar file")
+ }
+ }
+ switch cleanEntryName(h.Name) {
+ case PrefetchLandmark, NoPrefetchLandmark:
+ // Ignore existing landmark
+ continue
+ }
+
+ // Add entry. If it already exists, replace it.
+ if _, ok := tf.get(h.Name); ok {
+ tf.remove(h.Name)
+ }
+ tf.add(&entry{
+ header: h,
+ payload: io.NewSectionReader(in, pw.currentPos(), h.Size),
+ })
+ }
+
+ return tf, nil
+}
+
+func moveRec(name string, in *tarFile, out *tarFile) error {
+ name = cleanEntryName(name)
+ if name == "" { // root directory. stop recursion.
+ if e, ok := in.get(name); ok {
+ // entry of the root directory exists. we should move it as well.
+ // this case will occur if tar entries are prefixed with "./", "/", etc.
+ out.add(e)
+ in.remove(name)
+ }
+ return nil
+ }
+
+ _, okIn := in.get(name)
+ _, okOut := out.get(name)
+ if !okIn && !okOut {
+ return errors.Wrapf(errNotFound, "file: %q", name)
+ }
+
+ parent, _ := path.Split(strings.TrimSuffix(name, "/"))
+ if err := moveRec(parent, in, out); err != nil {
+ return err
+ }
+ if e, ok := in.get(name); ok && e.header.Typeflag == tar.TypeLink {
+ if err := moveRec(e.header.Linkname, in, out); err != nil {
+ return err
+ }
+ }
+ if e, ok := in.get(name); ok {
+ out.add(e)
+ in.remove(name)
+ }
+ return nil
+}
+
+type entry struct {
+ header *tar.Header
+ payload io.ReadSeeker
+}
+
+type tarFile struct {
+ index map[string]*entry
+ stream []*entry
+}
+
+func (f *tarFile) add(e *entry) {
+ if f.index == nil {
+ f.index = make(map[string]*entry)
+ }
+ f.index[cleanEntryName(e.header.Name)] = e
+ f.stream = append(f.stream, e)
+}
+
+func (f *tarFile) remove(name string) {
+ name = cleanEntryName(name)
+ if f.index != nil {
+ delete(f.index, name)
+ }
+ var filtered []*entry
+ for _, e := range f.stream {
+ if cleanEntryName(e.header.Name) == name {
+ continue
+ }
+ filtered = append(filtered, e)
+ }
+ f.stream = filtered
+}
+
+func (f *tarFile) get(name string) (e *entry, ok bool) {
+ if f.index == nil {
+ return nil, false
+ }
+ e, ok = f.index[cleanEntryName(name)]
+ return
+}
+
+func (f *tarFile) dump() []*entry {
+ return f.stream
+}
+
+type readCloser struct {
+ io.Reader
+ closeFunc func() error
+}
+
+func (rc readCloser) Close() error {
+ return rc.closeFunc()
+}
+
+func fileSectionReader(file *os.File) (*io.SectionReader, error) {
+ info, err := file.Stat()
+ if err != nil {
+ return nil, err
+ }
+ return io.NewSectionReader(file, 0, info.Size()), nil
+}
+
+func newTempFiles() *tempFiles {
+ return &tempFiles{}
+}
+
+type tempFiles struct {
+ files []*os.File
+ filesMu sync.Mutex
+}
+
+func (tf *tempFiles) TempFile(dir, pattern string) (*os.File, error) {
+ f, err := ioutil.TempFile(dir, pattern)
+ if err != nil {
+ return nil, err
+ }
+ tf.filesMu.Lock()
+ tf.files = append(tf.files, f)
+ tf.filesMu.Unlock()
+ return f, nil
+}
+
+func (tf *tempFiles) CleanupAll() error {
+ tf.filesMu.Lock()
+ defer tf.filesMu.Unlock()
+ var allErr []error
+ for _, f := range tf.files {
+ if err := f.Close(); err != nil {
+ allErr = append(allErr, err)
+ }
+ if err := os.Remove(f.Name()); err != nil {
+ allErr = append(allErr, err)
+ }
+ }
+ tf.files = nil
+ return errorutil.Aggregate(allErr)
+}
+
+func newCountReader(r io.ReaderAt) (*countReader, error) {
+ pos := int64(0)
+ return &countReader{r: r, cPos: &pos}, nil
+}
+
+type countReader struct {
+ r io.ReaderAt
+ cPos *int64
+
+ mu sync.Mutex
+}
+
+func (cr *countReader) Read(p []byte) (int, error) {
+ cr.mu.Lock()
+ defer cr.mu.Unlock()
+
+ n, err := cr.r.ReadAt(p, *cr.cPos)
+ if err == nil {
+ *cr.cPos += int64(n)
+ }
+ return n, err
+}
+
+func (cr *countReader) Seek(offset int64, whence int) (int64, error) {
+ cr.mu.Lock()
+ defer cr.mu.Unlock()
+
+ switch whence {
+ default:
+ return 0, fmt.Errorf("Unknown whence: %v", whence)
+ case io.SeekStart:
+ case io.SeekCurrent:
+ offset += *cr.cPos
+ case io.SeekEnd:
+ return 0, fmt.Errorf("Unsupported whence: %v", whence)
+ }
+
+ if offset < 0 {
+ return 0, fmt.Errorf("invalid offset")
+ }
+ *cr.cPos = offset
+ return offset, nil
+}
+
+func (cr *countReader) currentPos() int64 {
+ cr.mu.Lock()
+ defer cr.mu.Unlock()
+
+ return *cr.cPos
+}
+
+func decompressBlob(org *io.SectionReader, tmp *tempFiles) (*io.SectionReader, error) {
+ if org.Size() < 4 {
+ return org, nil
+ }
+ src := make([]byte, 4)
+ if _, err := org.Read(src); err != nil && err != io.EOF {
+ return nil, err
+ }
+ var dR io.Reader
+ if bytes.Equal([]byte{0x1F, 0x8B, 0x08}, src[:3]) {
+ // gzip
+ dgR, err := gzip.NewReader(io.NewSectionReader(org, 0, org.Size()))
+ if err != nil {
+ return nil, err
+ }
+ defer dgR.Close()
+ dR = io.Reader(dgR)
+ } else if bytes.Equal([]byte{0x28, 0xb5, 0x2f, 0xfd}, src[:4]) {
+ // zstd
+ dzR, err := zstd.NewReader(io.NewSectionReader(org, 0, org.Size()))
+ if err != nil {
+ return nil, err
+ }
+ defer dzR.Close()
+ dR = io.Reader(dzR)
+ } else {
+ // uncompressed
+ return io.NewSectionReader(org, 0, org.Size()), nil
+ }
+ b, err := tmp.TempFile("", "uncompresseddata")
+ if err != nil {
+ return nil, err
+ }
+ if _, err := io.Copy(b, dR); err != nil {
+ return nil, err
+ }
+ return fileSectionReader(b)
+}
diff --git a/vendor/github.com/containerd/stargz-snapshotter/estargz/errorutil/errors.go b/vendor/github.com/containerd/stargz-snapshotter/estargz/errorutil/errors.go
new file mode 100644
index 000000000..6de78b02d
--- /dev/null
+++ b/vendor/github.com/containerd/stargz-snapshotter/estargz/errorutil/errors.go
@@ -0,0 +1,40 @@
+/*
+ Copyright The containerd Authors.
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+*/
+
+package errorutil
+
+import (
+ "errors"
+ "fmt"
+ "strings"
+)
+
+// Aggregate combines a list of errors into a single new error.
+func Aggregate(errs []error) error {
+ switch len(errs) {
+ case 0:
+ return nil
+ case 1:
+ return errs[0]
+ default:
+ points := make([]string, len(errs)+1)
+ points[0] = fmt.Sprintf("%d error(s) occurred:", len(errs))
+ for i, err := range errs {
+ points[i+1] = fmt.Sprintf("* %s", err)
+ }
+ return errors.New(strings.Join(points, "\n\t"))
+ }
+}
diff --git a/vendor/github.com/containerd/stargz-snapshotter/estargz/estargz.go b/vendor/github.com/containerd/stargz-snapshotter/estargz/estargz.go
new file mode 100644
index 000000000..e997d9cce
--- /dev/null
+++ b/vendor/github.com/containerd/stargz-snapshotter/estargz/estargz.go
@@ -0,0 +1,933 @@
+/*
+ Copyright The containerd Authors.
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+*/
+
+/*
+ Copyright 2019 The Go Authors. All rights reserved.
+ Use of this source code is governed by a BSD-style
+ license that can be found in the LICENSE file.
+*/
+
+package estargz
+
+import (
+ "archive/tar"
+ "bufio"
+ "bytes"
+ "compress/gzip"
+ "crypto/sha256"
+ "fmt"
+ "hash"
+ "io"
+ "io/ioutil"
+ "os"
+ "path"
+ "sort"
+ "strings"
+ "sync"
+ "time"
+
+ "github.com/containerd/stargz-snapshotter/estargz/errorutil"
+ digest "github.com/opencontainers/go-digest"
+ "github.com/pkg/errors"
+)
+
+// A Reader permits random access reads from a stargz file.
+type Reader struct {
+ sr *io.SectionReader
+ toc *JTOC
+ tocDigest digest.Digest
+
+ // m stores all non-chunk entries, keyed by name.
+ m map[string]*TOCEntry
+
+ // chunks stores all TOCEntry values for regular files that
+ // are split up. For a file with a single chunk, it's only
+ // stored in m.
+ chunks map[string][]*TOCEntry
+
+ decompressor Decompressor
+}
+
+type openOpts struct {
+ tocOffset int64
+ decompressors []Decompressor
+ telemetry *Telemetry
+}
+
+// OpenOption is an option used during opening the layer
+type OpenOption func(o *openOpts) error
+
+// WithTOCOffset option specifies the offset of TOC
+func WithTOCOffset(tocOffset int64) OpenOption {
+ return func(o *openOpts) error {
+ o.tocOffset = tocOffset
+ return nil
+ }
+}
+
+// WithDecompressors option specifies decompressors to use.
+// Default is gzip-based decompressor.
+func WithDecompressors(decompressors ...Decompressor) OpenOption {
+ return func(o *openOpts) error {
+ o.decompressors = decompressors
+ return nil
+ }
+}
+
+// WithTelemetry option specifies the telemetry hooks
+func WithTelemetry(telemetry *Telemetry) OpenOption {
+ return func(o *openOpts) error {
+ o.telemetry = telemetry
+ return nil
+ }
+}
+
+// A func which takes start time and records the diff
+type MeasureLatencyHook func(time.Time)
+
+// A struct which defines telemetry hooks. By implementing these hooks you should be able to record
+// the latency metrics of the respective steps of estargz open operation. To be used with estargz.OpenWithTelemetry(...)
+type Telemetry struct {
+ GetFooterLatency MeasureLatencyHook // measure time to get stargz footer (in milliseconds)
+ GetTocLatency MeasureLatencyHook // measure time to GET TOC JSON (in milliseconds)
+ DeserializeTocLatency MeasureLatencyHook // measure time to deserialize TOC JSON (in milliseconds)
+}
+
+// Open opens a stargz file for reading.
+// The behaviour is configurable using options.
+//
+// Note that each entry name is normalized as the path that is relative to root.
+func Open(sr *io.SectionReader, opt ...OpenOption) (*Reader, error) {
+ var opts openOpts
+ for _, o := range opt {
+ if err := o(&opts); err != nil {
+ return nil, err
+ }
+ }
+
+ gzipCompressors := []Decompressor{new(GzipDecompressor), new(legacyGzipDecompressor)}
+ decompressors := append(gzipCompressors, opts.decompressors...)
+
+ // Determine the size to fetch. Try to fetch as many bytes as possible.
+ fetchSize := maxFooterSize(sr.Size(), decompressors...)
+ if maybeTocOffset := opts.tocOffset; maybeTocOffset > fetchSize {
+ if maybeTocOffset > sr.Size() {
+ return nil, fmt.Errorf("blob size %d is smaller than the toc offset", sr.Size())
+ }
+ fetchSize = sr.Size() - maybeTocOffset
+ }
+
+ start := time.Now() // before getting layer footer
+ footer := make([]byte, fetchSize)
+ if _, err := sr.ReadAt(footer, sr.Size()-fetchSize); err != nil {
+ return nil, fmt.Errorf("error reading footer: %v", err)
+ }
+ if opts.telemetry != nil && opts.telemetry.GetFooterLatency != nil {
+ opts.telemetry.GetFooterLatency(start)
+ }
+
+ var allErr []error
+ var found bool
+ var r *Reader
+ for _, d := range decompressors {
+ fSize := d.FooterSize()
+ fOffset := positive(int64(len(footer)) - fSize)
+ maybeTocBytes := footer[:fOffset]
+ tocOffset, tocSize, err := d.ParseFooter(footer[fOffset:])
+ if err != nil {
+ allErr = append(allErr, err)
+ continue
+ }
+ if tocSize <= 0 {
+ tocSize = sr.Size() - tocOffset - fSize
+ }
+ if tocSize < int64(len(maybeTocBytes)) {
+ maybeTocBytes = maybeTocBytes[:tocSize]
+ }
+ r, err = parseTOC(d, sr, tocOffset, tocSize, maybeTocBytes, opts)
+ if err == nil {
+ found = true
+ break
+ }
+ allErr = append(allErr, err)
+ }
+ if !found {
+ return nil, errorutil.Aggregate(allErr)
+ }
+ if err := r.initFields(); err != nil {
+ return nil, fmt.Errorf("failed to initialize fields of entries: %v", err)
+ }
+ return r, nil
+}
+
+// OpenFooter extracts and parses footer from the given blob.
+// only supports gzip-based eStargz.
+func OpenFooter(sr *io.SectionReader) (tocOffset int64, footerSize int64, rErr error) {
+ if sr.Size() < FooterSize && sr.Size() < legacyFooterSize {
+ return 0, 0, fmt.Errorf("blob size %d is smaller than the footer size", sr.Size())
+ }
+ var footer [FooterSize]byte
+ if _, err := sr.ReadAt(footer[:], sr.Size()-FooterSize); err != nil {
+ return 0, 0, fmt.Errorf("error reading footer: %v", err)
+ }
+ var allErr []error
+ for _, d := range []Decompressor{new(GzipDecompressor), new(legacyGzipDecompressor)} {
+ fSize := d.FooterSize()
+ fOffset := positive(int64(len(footer)) - fSize)
+ tocOffset, _, err := d.ParseFooter(footer[fOffset:])
+ if err == nil {
+ return tocOffset, fSize, err
+ }
+ allErr = append(allErr, err)
+ }
+ return 0, 0, errorutil.Aggregate(allErr)
+}
+
+// initFields populates the Reader from r.toc after decoding it from
+// JSON.
+//
+// Unexported fields are populated and TOCEntry fields that were
+// implicit in the JSON are populated.
+func (r *Reader) initFields() error {
+ r.m = make(map[string]*TOCEntry, len(r.toc.Entries))
+ r.chunks = make(map[string][]*TOCEntry)
+ var lastPath string
+ uname := map[int]string{}
+ gname := map[int]string{}
+ var lastRegEnt *TOCEntry
+ for _, ent := range r.toc.Entries {
+ ent.Name = cleanEntryName(ent.Name)
+ if ent.Type == "reg" {
+ lastRegEnt = ent
+ }
+ if ent.Type == "chunk" {
+ ent.Name = lastPath
+ r.chunks[ent.Name] = append(r.chunks[ent.Name], ent)
+ if ent.ChunkSize == 0 && lastRegEnt != nil {
+ ent.ChunkSize = lastRegEnt.Size - ent.ChunkOffset
+ }
+ } else {
+ lastPath = ent.Name
+
+ if ent.Uname != "" {
+ uname[ent.UID] = ent.Uname
+ } else {
+ ent.Uname = uname[ent.UID]
+ }
+ if ent.Gname != "" {
+ gname[ent.GID] = ent.Gname
+ } else {
+ ent.Gname = uname[ent.GID]
+ }
+
+ ent.modTime, _ = time.Parse(time.RFC3339, ent.ModTime3339)
+
+ if ent.Type == "dir" {
+ ent.NumLink++ // Parent dir links to this directory
+ }
+ r.m[ent.Name] = ent
+ }
+ if ent.Type == "reg" && ent.ChunkSize > 0 && ent.ChunkSize < ent.Size {
+ r.chunks[ent.Name] = make([]*TOCEntry, 0, ent.Size/ent.ChunkSize+1)
+ r.chunks[ent.Name] = append(r.chunks[ent.Name], ent)
+ }
+ if ent.ChunkSize == 0 && ent.Size != 0 {
+ ent.ChunkSize = ent.Size
+ }
+ }
+
+ // Populate children, add implicit directories:
+ for _, ent := range r.toc.Entries {
+ if ent.Type == "chunk" {
+ continue
+ }
+ // add "foo/":
+ // add "foo" child to "" (creating "" if necessary)
+ //
+ // add "foo/bar/":
+ // add "bar" child to "foo" (creating "foo" if necessary)
+ //
+ // add "foo/bar.txt":
+ // add "bar.txt" child to "foo" (creating "foo" if necessary)
+ //
+ // add "a/b/c/d/e/f.txt":
+ // create "a/b/c/d/e" node
+ // add "f.txt" child to "e"
+
+ name := ent.Name
+ pdirName := parentDir(name)
+ if name == pdirName {
+ // This entry and its parent are the same.
+ // Ignore this for avoiding infinite loop of the reference.
+ // The example case where this can occur is when tar contains the root
+ // directory itself (e.g. "./", "/").
+ continue
+ }
+ pdir := r.getOrCreateDir(pdirName)
+ ent.NumLink++ // at least one name(ent.Name) references this entry.
+ if ent.Type == "hardlink" {
+ if org, ok := r.m[cleanEntryName(ent.LinkName)]; ok {
+ org.NumLink++ // original entry is referenced by this ent.Name.
+ ent = org
+ } else {
+ return fmt.Errorf("%q is a hardlink but the linkname %q isn't found", ent.Name, ent.LinkName)
+ }
+ }
+ pdir.addChild(path.Base(name), ent)
+ }
+
+ lastOffset := r.sr.Size()
+ for i := len(r.toc.Entries) - 1; i >= 0; i-- {
+ e := r.toc.Entries[i]
+ if e.isDataType() {
+ e.nextOffset = lastOffset
+ }
+ if e.Offset != 0 {
+ lastOffset = e.Offset
+ }
+ }
+
+ return nil
+}
+
+func parentDir(p string) string {
+ dir, _ := path.Split(p)
+ return strings.TrimSuffix(dir, "/")
+}
+
+func (r *Reader) getOrCreateDir(d string) *TOCEntry {
+ e, ok := r.m[d]
+ if !ok {
+ e = &TOCEntry{
+ Name: d,
+ Type: "dir",
+ Mode: 0755,
+ NumLink: 2, // The directory itself(.) and the parent link to this directory.
+ }
+ r.m[d] = e
+ if d != "" {
+ pdir := r.getOrCreateDir(parentDir(d))
+ pdir.addChild(path.Base(d), e)
+ }
+ }
+ return e
+}
+
+// VerifyTOC checks that the TOC JSON in the passed blob matches the
+// passed digests and that the TOC JSON contains digests for all chunks
+// contained in the blob. If the verification succceeds, this function
+// returns TOCEntryVerifier which holds all chunk digests in the stargz blob.
+func (r *Reader) VerifyTOC(tocDigest digest.Digest) (TOCEntryVerifier, error) {
+ // Verify the digest of TOC JSON
+ if r.tocDigest != tocDigest {
+ return nil, fmt.Errorf("invalid TOC JSON %q; want %q", r.tocDigest, tocDigest)
+ }
+
+ chunkDigestMap := make(map[int64]digest.Digest) // map from chunk offset to the chunk digest
+ regDigestMap := make(map[int64]digest.Digest) // map from chunk offset to the reg file digest
+ var chunkDigestMapIncomplete bool
+ var regDigestMapIncomplete bool
+ var containsChunk bool
+ for _, e := range r.toc.Entries {
+ if e.Type != "reg" && e.Type != "chunk" {
+ continue
+ }
+
+ // offset must be unique in stargz blob
+ _, dOK := chunkDigestMap[e.Offset]
+ _, rOK := regDigestMap[e.Offset]
+ if dOK || rOK {
+ return nil, fmt.Errorf("offset %d found twice", e.Offset)
+ }
+
+ if e.Type == "reg" {
+ if e.Size == 0 {
+ continue // ignores empty file
+ }
+
+ // record the digest of regular file payload
+ if e.Digest != "" {
+ d, err := digest.Parse(e.Digest)
+ if err != nil {
+ return nil, errors.Wrapf(err,
+ "failed to parse regular file digest %q", e.Digest)
+ }
+ regDigestMap[e.Offset] = d
+ } else {
+ regDigestMapIncomplete = true
+ }
+ } else {
+ containsChunk = true // this layer contains "chunk" entries.
+ }
+
+ // "reg" also can contain ChunkDigest (e.g. when "reg" is the first entry of
+ // chunked file)
+ if e.ChunkDigest != "" {
+ d, err := digest.Parse(e.ChunkDigest)
+ if err != nil {
+ return nil, errors.Wrapf(err,
+ "failed to parse chunk digest %q", e.ChunkDigest)
+ }
+ chunkDigestMap[e.Offset] = d
+ } else {
+ chunkDigestMapIncomplete = true
+ }
+ }
+
+ if chunkDigestMapIncomplete {
+ // Though some chunk digests are not found, if this layer doesn't contain
+ // "chunk"s and all digest of "reg" files are recorded, we can use them instead.
+ if !containsChunk && !regDigestMapIncomplete {
+ return &verifier{digestMap: regDigestMap}, nil
+ }
+ return nil, fmt.Errorf("some ChunkDigest not found in TOC JSON")
+ }
+
+ return &verifier{digestMap: chunkDigestMap}, nil
+}
+
+// verifier is an implementation of TOCEntryVerifier which holds verifiers keyed by
+// offset of the chunk.
+type verifier struct {
+ digestMap map[int64]digest.Digest
+ digestMapMu sync.Mutex
+}
+
+// Verifier returns a content verifier specified by TOCEntry.
+func (v *verifier) Verifier(ce *TOCEntry) (digest.Verifier, error) {
+ v.digestMapMu.Lock()
+ defer v.digestMapMu.Unlock()
+ d, ok := v.digestMap[ce.Offset]
+ if !ok {
+ return nil, fmt.Errorf("verifier for offset=%d,size=%d hasn't been registered",
+ ce.Offset, ce.ChunkSize)
+ }
+ return d.Verifier(), nil
+}
+
+// ChunkEntryForOffset returns the TOCEntry containing the byte of the
+// named file at the given offset within the file.
+// Name must be absolute path or one that is relative to root.
+func (r *Reader) ChunkEntryForOffset(name string, offset int64) (e *TOCEntry, ok bool) {
+ name = cleanEntryName(name)
+ e, ok = r.Lookup(name)
+ if !ok || !e.isDataType() {
+ return nil, false
+ }
+ ents := r.chunks[name]
+ if len(ents) < 2 {
+ if offset >= e.ChunkSize {
+ return nil, false
+ }
+ return e, true
+ }
+ i := sort.Search(len(ents), func(i int) bool {
+ e := ents[i]
+ return e.ChunkOffset >= offset || (offset > e.ChunkOffset && offset < e.ChunkOffset+e.ChunkSize)
+ })
+ if i == len(ents) {
+ return nil, false
+ }
+ return ents[i], true
+}
+
+// Lookup returns the Table of Contents entry for the given path.
+//
+// To get the root directory, use the empty string.
+// Path must be absolute path or one that is relative to root.
+func (r *Reader) Lookup(path string) (e *TOCEntry, ok bool) {
+ path = cleanEntryName(path)
+ if r == nil {
+ return
+ }
+ e, ok = r.m[path]
+ if ok && e.Type == "hardlink" {
+ e, ok = r.m[e.LinkName]
+ }
+ return
+}
+
+// OpenFile returns the reader of the specified file payload.
+//
+// Name must be absolute path or one that is relative to root.
+func (r *Reader) OpenFile(name string) (*io.SectionReader, error) {
+ name = cleanEntryName(name)
+ ent, ok := r.Lookup(name)
+ if !ok {
+ // TODO: come up with some error plan. This is lazy:
+ return nil, &os.PathError{
+ Path: name,
+ Op: "OpenFile",
+ Err: os.ErrNotExist,
+ }
+ }
+ if ent.Type != "reg" {
+ return nil, &os.PathError{
+ Path: name,
+ Op: "OpenFile",
+ Err: errors.New("not a regular file"),
+ }
+ }
+ fr := &fileReader{
+ r: r,
+ size: ent.Size,
+ ents: r.getChunks(ent),
+ }
+ return io.NewSectionReader(fr, 0, fr.size), nil
+}
+
+func (r *Reader) getChunks(ent *TOCEntry) []*TOCEntry {
+ if ents, ok := r.chunks[ent.Name]; ok {
+ return ents
+ }
+ return []*TOCEntry{ent}
+}
+
+type fileReader struct {
+ r *Reader
+ size int64
+ ents []*TOCEntry // 1 or more reg/chunk entries
+}
+
+func (fr *fileReader) ReadAt(p []byte, off int64) (n int, err error) {
+ if off >= fr.size {
+ return 0, io.EOF
+ }
+ if off < 0 {
+ return 0, errors.New("invalid offset")
+ }
+ var i int
+ if len(fr.ents) > 1 {
+ i = sort.Search(len(fr.ents), func(i int) bool {
+ return fr.ents[i].ChunkOffset >= off
+ })
+ if i == len(fr.ents) {
+ i = len(fr.ents) - 1
+ }
+ }
+ ent := fr.ents[i]
+ if ent.ChunkOffset > off {
+ if i == 0 {
+ return 0, errors.New("internal error; first chunk offset is non-zero")
+ }
+ ent = fr.ents[i-1]
+ }
+
+ // If ent is a chunk of a large file, adjust the ReadAt
+ // offset by the chunk's offset.
+ off -= ent.ChunkOffset
+
+ finalEnt := fr.ents[len(fr.ents)-1]
+ compressedOff := ent.Offset
+ // compressedBytesRemain is the number of compressed bytes in this
+ // file remaining, over 1+ chunks.
+ compressedBytesRemain := finalEnt.NextOffset() - compressedOff
+
+ sr := io.NewSectionReader(fr.r.sr, compressedOff, compressedBytesRemain)
+
+ const maxRead = 2 << 20
+ var bufSize = maxRead
+ if compressedBytesRemain < maxRead {
+ bufSize = int(compressedBytesRemain)
+ }
+
+ br := bufio.NewReaderSize(sr, bufSize)
+ if _, err := br.Peek(bufSize); err != nil {
+ return 0, fmt.Errorf("fileReader.ReadAt.peek: %v", err)
+ }
+
+ dr, err := fr.r.decompressor.Reader(br)
+ if err != nil {
+ return 0, fmt.Errorf("fileReader.ReadAt.decompressor.Reader: %v", err)
+ }
+ defer dr.Close()
+ if n, err := io.CopyN(ioutil.Discard, dr, off); n != off || err != nil {
+ return 0, fmt.Errorf("discard of %d bytes = %v, %v", off, n, err)
+ }
+ return io.ReadFull(dr, p)
+}
+
+// A Writer writes stargz files.
+//
+// Use NewWriter to create a new Writer.
+type Writer struct {
+ bw *bufio.Writer
+ cw *countWriter
+ toc *JTOC
+ diffHash hash.Hash // SHA-256 of uncompressed tar
+
+ closed bool
+ gz io.WriteCloser
+ lastUsername map[int]string
+ lastGroupname map[int]string
+ compressor Compressor
+
+ // ChunkSize optionally controls the maximum number of bytes
+ // of data of a regular file that can be written in one gzip
+ // stream before a new gzip stream is started.
+ // Zero means to use a default, currently 4 MiB.
+ ChunkSize int
+}
+
+// currentCompressionWriter writes to the current w.gz field, which can
+// change throughout writing a tar entry.
+//
+// Additionally, it updates w's SHA-256 of the uncompressed bytes
+// of the tar file.
+type currentCompressionWriter struct{ w *Writer }
+
+func (ccw currentCompressionWriter) Write(p []byte) (int, error) {
+ ccw.w.diffHash.Write(p)
+ return ccw.w.gz.Write(p)
+}
+
+func (w *Writer) chunkSize() int {
+ if w.ChunkSize <= 0 {
+ return 4 << 20
+ }
+ return w.ChunkSize
+}
+
+// NewWriter returns a new stargz writer (gzip-based) writing to w.
+//
+// The writer must be closed to write its trailing table of contents.
+func NewWriter(w io.Writer) *Writer {
+ return NewWriterLevel(w, gzip.BestCompression)
+}
+
+// NewWriterLevel returns a new stargz writer (gzip-based) writing to w.
+// The compression level is configurable.
+//
+// The writer must be closed to write its trailing table of contents.
+func NewWriterLevel(w io.Writer, compressionLevel int) *Writer {
+ return NewWriterWithCompressor(w, NewGzipCompressorWithLevel(compressionLevel))
+}
+
+// NewWriterLevel returns a new stargz writer writing to w.
+// The compression method is configurable.
+//
+// The writer must be closed to write its trailing table of contents.
+func NewWriterWithCompressor(w io.Writer, c Compressor) *Writer {
+ bw := bufio.NewWriter(w)
+ cw := &countWriter{w: bw}
+ return &Writer{
+ bw: bw,
+ cw: cw,
+ toc: &JTOC{Version: 1},
+ diffHash: sha256.New(),
+ compressor: c,
+ }
+}
+
+// Close writes the stargz's table of contents and flushes all the
+// buffers, returning any error.
+func (w *Writer) Close() (digest.Digest, error) {
+ if w.closed {
+ return "", nil
+ }
+ defer func() { w.closed = true }()
+
+ if err := w.closeGz(); err != nil {
+ return "", err
+ }
+
+ // Write the TOC index and footer.
+ tocDigest, err := w.compressor.WriteTOCAndFooter(w.cw, w.cw.n, w.toc, w.diffHash)
+ if err != nil {
+ return "", err
+ }
+ if err := w.bw.Flush(); err != nil {
+ return "", err
+ }
+
+ return tocDigest, nil
+}
+
+func (w *Writer) closeGz() error {
+ if w.closed {
+ return errors.New("write on closed Writer")
+ }
+ if w.gz != nil {
+ if err := w.gz.Close(); err != nil {
+ return err
+ }
+ w.gz = nil
+ }
+ return nil
+}
+
+// nameIfChanged returns name, unless it was the already the value of (*mp)[id],
+// in which case it returns the empty string.
+func (w *Writer) nameIfChanged(mp *map[int]string, id int, name string) string {
+ if name == "" {
+ return ""
+ }
+ if *mp == nil {
+ *mp = make(map[int]string)
+ }
+ if (*mp)[id] == name {
+ return ""
+ }
+ (*mp)[id] = name
+ return name
+}
+
+func (w *Writer) condOpenGz() (err error) {
+ if w.gz == nil {
+ w.gz, err = w.compressor.Writer(w.cw)
+ }
+ return
+}
+
+// AppendTar reads the tar or tar.gz file from r and appends
+// each of its contents to w.
+//
+// The input r can optionally be gzip compressed but the output will
+// always be gzip compressed.
+func (w *Writer) AppendTar(r io.Reader) error {
+ br := bufio.NewReader(r)
+ var tr *tar.Reader
+ if isGzip(br) {
+ // NewReader can't fail if isGzip returned true.
+ zr, _ := gzip.NewReader(br)
+ tr = tar.NewReader(zr)
+ } else {
+ tr = tar.NewReader(br)
+ }
+ for {
+ h, err := tr.Next()
+ if err == io.EOF {
+ break
+ }
+ if err != nil {
+ return fmt.Errorf("error reading from source tar: tar.Reader.Next: %v", err)
+ }
+ if h.Name == TOCTarName {
+ // It is possible for a layer to be "stargzified" twice during the
+ // distribution lifecycle. So we reserve "TOCTarName" here to avoid
+ // duplicated entries in the resulting layer.
+ continue
+ }
+
+ xattrs := make(map[string][]byte)
+ const xattrPAXRecordsPrefix = "SCHILY.xattr."
+ if h.PAXRecords != nil {
+ for k, v := range h.PAXRecords {
+ if strings.HasPrefix(k, xattrPAXRecordsPrefix) {
+ xattrs[k[len(xattrPAXRecordsPrefix):]] = []byte(v)
+ }
+ }
+ }
+ ent := &TOCEntry{
+ Name: h.Name,
+ Mode: h.Mode,
+ UID: h.Uid,
+ GID: h.Gid,
+ Uname: w.nameIfChanged(&w.lastUsername, h.Uid, h.Uname),
+ Gname: w.nameIfChanged(&w.lastGroupname, h.Gid, h.Gname),
+ ModTime3339: formatModtime(h.ModTime),
+ Xattrs: xattrs,
+ }
+ if err := w.condOpenGz(); err != nil {
+ return err
+ }
+ tw := tar.NewWriter(currentCompressionWriter{w})
+ if err := tw.WriteHeader(h); err != nil {
+ return err
+ }
+ switch h.Typeflag {
+ case tar.TypeLink:
+ ent.Type = "hardlink"
+ ent.LinkName = h.Linkname
+ case tar.TypeSymlink:
+ ent.Type = "symlink"
+ ent.LinkName = h.Linkname
+ case tar.TypeDir:
+ ent.Type = "dir"
+ case tar.TypeReg:
+ ent.Type = "reg"
+ ent.Size = h.Size
+ case tar.TypeChar:
+ ent.Type = "char"
+ ent.DevMajor = int(h.Devmajor)
+ ent.DevMinor = int(h.Devminor)
+ case tar.TypeBlock:
+ ent.Type = "block"
+ ent.DevMajor = int(h.Devmajor)
+ ent.DevMinor = int(h.Devminor)
+ case tar.TypeFifo:
+ ent.Type = "fifo"
+ default:
+ return fmt.Errorf("unsupported input tar entry %q", h.Typeflag)
+ }
+
+ // We need to keep a reference to the TOC entry for regular files, so that we
+ // can fill the digest later.
+ var regFileEntry *TOCEntry
+ var payloadDigest digest.Digester
+ if h.Typeflag == tar.TypeReg {
+ regFileEntry = ent
+ payloadDigest = digest.Canonical.Digester()
+ }
+
+ if h.Typeflag == tar.TypeReg && ent.Size > 0 {
+ var written int64
+ totalSize := ent.Size // save it before we destroy ent
+ tee := io.TeeReader(tr, payloadDigest.Hash())
+ for written < totalSize {
+ if err := w.closeGz(); err != nil {
+ return err
+ }
+
+ chunkSize := int64(w.chunkSize())
+ remain := totalSize - written
+ if remain < chunkSize {
+ chunkSize = remain
+ } else {
+ ent.ChunkSize = chunkSize
+ }
+ ent.Offset = w.cw.n
+ ent.ChunkOffset = written
+ chunkDigest := digest.Canonical.Digester()
+
+ if err := w.condOpenGz(); err != nil {
+ return err
+ }
+
+ teeChunk := io.TeeReader(tee, chunkDigest.Hash())
+ if _, err := io.CopyN(tw, teeChunk, chunkSize); err != nil {
+ return fmt.Errorf("error copying %q: %v", h.Name, err)
+ }
+ ent.ChunkDigest = chunkDigest.Digest().String()
+ w.toc.Entries = append(w.toc.Entries, ent)
+ written += chunkSize
+ ent = &TOCEntry{
+ Name: h.Name,
+ Type: "chunk",
+ }
+ }
+ } else {
+ w.toc.Entries = append(w.toc.Entries, ent)
+ }
+ if payloadDigest != nil {
+ regFileEntry.Digest = payloadDigest.Digest().String()
+ }
+ if err := tw.Flush(); err != nil {
+ return err
+ }
+ }
+ return nil
+}
+
+// DiffID returns the SHA-256 of the uncompressed tar bytes.
+// It is only valid to call DiffID after Close.
+func (w *Writer) DiffID() string {
+ return fmt.Sprintf("sha256:%x", w.diffHash.Sum(nil))
+}
+
+func maxFooterSize(blobSize int64, decompressors ...Decompressor) (res int64) {
+ for _, d := range decompressors {
+ if s := d.FooterSize(); res < s && s <= blobSize {
+ res = s
+ }
+ }
+ return
+}
+
+func parseTOC(d Decompressor, sr *io.SectionReader, tocOff, tocSize int64, tocBytes []byte, opts openOpts) (*Reader, error) {
+ if len(tocBytes) > 0 {
+ start := time.Now()
+ toc, tocDgst, err := d.ParseTOC(bytes.NewReader(tocBytes))
+ if err == nil {
+ if opts.telemetry != nil && opts.telemetry.DeserializeTocLatency != nil {
+ opts.telemetry.DeserializeTocLatency(start)
+ }
+ return &Reader{
+ sr: sr,
+ toc: toc,
+ tocDigest: tocDgst,
+ decompressor: d,
+ }, nil
+ }
+ }
+
+ start := time.Now()
+ tocBytes = make([]byte, tocSize)
+ if _, err := sr.ReadAt(tocBytes, tocOff); err != nil {
+ return nil, fmt.Errorf("error reading %d byte TOC targz: %v", len(tocBytes), err)
+ }
+ if opts.telemetry != nil && opts.telemetry.GetTocLatency != nil {
+ opts.telemetry.GetTocLatency(start)
+ }
+ start = time.Now()
+ toc, tocDgst, err := d.ParseTOC(bytes.NewReader(tocBytes))
+ if err != nil {
+ return nil, err
+ }
+ if opts.telemetry != nil && opts.telemetry.DeserializeTocLatency != nil {
+ opts.telemetry.DeserializeTocLatency(start)
+ }
+ return &Reader{
+ sr: sr,
+ toc: toc,
+ tocDigest: tocDgst,
+ decompressor: d,
+ }, nil
+}
+
+func formatModtime(t time.Time) string {
+ if t.IsZero() || t.Unix() == 0 {
+ return ""
+ }
+ return t.UTC().Round(time.Second).Format(time.RFC3339)
+}
+
+func cleanEntryName(name string) string {
+ // Use path.Clean to consistently deal with path separators across platforms.
+ return strings.TrimPrefix(path.Clean("/"+name), "/")
+}
+
+// countWriter counts how many bytes have been written to its wrapped
+// io.Writer.
+type countWriter struct {
+ w io.Writer
+ n int64
+}
+
+func (cw *countWriter) Write(p []byte) (n int, err error) {
+ n, err = cw.w.Write(p)
+ cw.n += int64(n)
+ return
+}
+
+// isGzip reports whether br is positioned right before an upcoming gzip stream.
+// It does not consume any bytes from br.
+func isGzip(br *bufio.Reader) bool {
+ const (
+ gzipID1 = 0x1f
+ gzipID2 = 0x8b
+ gzipDeflate = 8
+ )
+ peek, _ := br.Peek(3)
+ return len(peek) >= 3 && peek[0] == gzipID1 && peek[1] == gzipID2 && peek[2] == gzipDeflate
+}
+
+func positive(n int64) int64 {
+ if n < 0 {
+ return 0
+ }
+ return n
+}
diff --git a/vendor/github.com/containerd/stargz-snapshotter/estargz/go.mod b/vendor/github.com/containerd/stargz-snapshotter/estargz/go.mod
new file mode 100644
index 000000000..ee6b2e17f
--- /dev/null
+++ b/vendor/github.com/containerd/stargz-snapshotter/estargz/go.mod
@@ -0,0 +1,10 @@
+module github.com/containerd/stargz-snapshotter/estargz
+
+go 1.16
+
+require (
+ github.com/klauspost/compress v1.13.5
+ github.com/opencontainers/go-digest v1.0.0
+ github.com/pkg/errors v0.9.1
+ golang.org/x/sync v0.0.0-20201207232520-09787c993a3a
+)
diff --git a/vendor/github.com/containerd/stargz-snapshotter/estargz/go.sum b/vendor/github.com/containerd/stargz-snapshotter/estargz/go.sum
new file mode 100644
index 000000000..66cd2d69c
--- /dev/null
+++ b/vendor/github.com/containerd/stargz-snapshotter/estargz/go.sum
@@ -0,0 +1,8 @@
+github.com/klauspost/compress v1.13.5 h1:9O69jUPDcsT9fEm74W92rZL9FQY7rCdaXVneq+yyzl4=
+github.com/klauspost/compress v1.13.5/go.mod h1:/3/Vjq9QcHkK5uEr5lBEmyoZ1iFhe47etQ6QUkpK6sk=
+github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
+github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM=
+github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
+github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
+golang.org/x/sync v0.0.0-20201207232520-09787c993a3a h1:DcqTD9SDLc+1P/r1EmRBwnVsrOwW+kk2vWf9n+1sGhs=
+golang.org/x/sync v0.0.0-20201207232520-09787c993a3a/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
diff --git a/vendor/github.com/containerd/stargz-snapshotter/estargz/gzip.go b/vendor/github.com/containerd/stargz-snapshotter/estargz/gzip.go
new file mode 100644
index 000000000..efc435e09
--- /dev/null
+++ b/vendor/github.com/containerd/stargz-snapshotter/estargz/gzip.go
@@ -0,0 +1,216 @@
+/*
+ Copyright The containerd Authors.
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+*/
+
+/*
+ Copyright 2019 The Go Authors. All rights reserved.
+ Use of this source code is governed by a BSD-style
+ license that can be found in the LICENSE file.
+*/
+
+package estargz
+
+import (
+ "archive/tar"
+ "bytes"
+ "compress/gzip"
+ "encoding/binary"
+ "encoding/json"
+ "fmt"
+ "hash"
+ "io"
+ "strconv"
+
+ digest "github.com/opencontainers/go-digest"
+ "github.com/pkg/errors"
+)
+
+type gzipCompression struct {
+ *gzipCompressor
+ *GzipDecompressor
+}
+
+func newGzipCompressionWithLevel(level int) Compression {
+ return &gzipCompression{
+ &gzipCompressor{level},
+ &GzipDecompressor{},
+ }
+}
+
+func NewGzipCompressorWithLevel(level int) Compressor {
+ return &gzipCompressor{level}
+}
+
+type gzipCompressor struct {
+ compressionLevel int
+}
+
+func (gc *gzipCompressor) Writer(w io.Writer) (io.WriteCloser, error) {
+ return gzip.NewWriterLevel(w, gc.compressionLevel)
+}
+
+func (gc *gzipCompressor) WriteTOCAndFooter(w io.Writer, off int64, toc *JTOC, diffHash hash.Hash) (digest.Digest, error) {
+ tocJSON, err := json.MarshalIndent(toc, "", "\t")
+ if err != nil {
+ return "", err
+ }
+ gz, _ := gzip.NewWriterLevel(w, gc.compressionLevel)
+ gw := io.Writer(gz)
+ if diffHash != nil {
+ gw = io.MultiWriter(gz, diffHash)
+ }
+ tw := tar.NewWriter(gw)
+ if err := tw.WriteHeader(&tar.Header{
+ Typeflag: tar.TypeReg,
+ Name: TOCTarName,
+ Size: int64(len(tocJSON)),
+ }); err != nil {
+ return "", err
+ }
+ if _, err := tw.Write(tocJSON); err != nil {
+ return "", err
+ }
+
+ if err := tw.Close(); err != nil {
+ return "", err
+ }
+ if err := gz.Close(); err != nil {
+ return "", err
+ }
+ if _, err := w.Write(gzipFooterBytes(off)); err != nil {
+ return "", err
+ }
+ return digest.FromBytes(tocJSON), nil
+}
+
+// gzipFooterBytes returns the 51 bytes footer.
+func gzipFooterBytes(tocOff int64) []byte {
+ buf := bytes.NewBuffer(make([]byte, 0, FooterSize))
+ gz, _ := gzip.NewWriterLevel(buf, gzip.NoCompression) // MUST be NoCompression to keep 51 bytes
+
+ // Extra header indicating the offset of TOCJSON
+ // https://tools.ietf.org/html/rfc1952#section-2.3.1.1
+ header := make([]byte, 4)
+ header[0], header[1] = 'S', 'G'
+ subfield := fmt.Sprintf("%016xSTARGZ", tocOff)
+ binary.LittleEndian.PutUint16(header[2:4], uint16(len(subfield))) // little-endian per RFC1952
+ gz.Header.Extra = append(header, []byte(subfield)...)
+ gz.Close()
+ if buf.Len() != FooterSize {
+ panic(fmt.Sprintf("footer buffer = %d, not %d", buf.Len(), FooterSize))
+ }
+ return buf.Bytes()
+}
+
+type GzipDecompressor struct{}
+
+func (gz *GzipDecompressor) Reader(r io.Reader) (io.ReadCloser, error) {
+ return gzip.NewReader(r)
+}
+
+func (gz *GzipDecompressor) ParseTOC(r io.Reader) (toc *JTOC, tocDgst digest.Digest, err error) {
+ return parseTOCEStargz(r)
+}
+
+func (gz *GzipDecompressor) ParseFooter(p []byte) (tocOffset, tocSize int64, err error) {
+ if len(p) != FooterSize {
+ return 0, 0, fmt.Errorf("invalid length %d cannot be parsed", len(p))
+ }
+ zr, err := gzip.NewReader(bytes.NewReader(p))
+ if err != nil {
+ return 0, 0, err
+ }
+ defer zr.Close()
+ extra := zr.Header.Extra
+ si1, si2, subfieldlen, subfield := extra[0], extra[1], extra[2:4], extra[4:]
+ if si1 != 'S' || si2 != 'G' {
+ return 0, 0, fmt.Errorf("invalid subfield IDs: %q, %q; want E, S", si1, si2)
+ }
+ if slen := binary.LittleEndian.Uint16(subfieldlen); slen != uint16(16+len("STARGZ")) {
+ return 0, 0, fmt.Errorf("invalid length of subfield %d; want %d", slen, 16+len("STARGZ"))
+ }
+ if string(subfield[16:]) != "STARGZ" {
+ return 0, 0, fmt.Errorf("STARGZ magic string must be included in the footer subfield")
+ }
+ tocOffset, err = strconv.ParseInt(string(subfield[:16]), 16, 64)
+ if err != nil {
+ return 0, 0, errors.Wrapf(err, "legacy: failed to parse toc offset")
+ }
+ return tocOffset, 0, nil
+}
+
+func (gz *GzipDecompressor) FooterSize() int64 {
+ return FooterSize
+}
+
+type legacyGzipDecompressor struct{}
+
+func (gz *legacyGzipDecompressor) Reader(r io.Reader) (io.ReadCloser, error) {
+ return gzip.NewReader(r)
+}
+
+func (gz *legacyGzipDecompressor) ParseTOC(r io.Reader) (toc *JTOC, tocDgst digest.Digest, err error) {
+ return parseTOCEStargz(r)
+}
+
+func (gz *legacyGzipDecompressor) ParseFooter(p []byte) (tocOffset, tocSize int64, err error) {
+ if len(p) != legacyFooterSize {
+ return 0, 0, fmt.Errorf("legacy: invalid length %d cannot be parsed", len(p))
+ }
+ zr, err := gzip.NewReader(bytes.NewReader(p))
+ if err != nil {
+ return 0, 0, errors.Wrapf(err, "legacy: failed to get footer gzip reader")
+ }
+ defer zr.Close()
+ extra := zr.Header.Extra
+ if len(extra) != 16+len("STARGZ") {
+ return 0, 0, fmt.Errorf("legacy: invalid stargz's extra field size")
+ }
+ if string(extra[16:]) != "STARGZ" {
+ return 0, 0, fmt.Errorf("legacy: magic string STARGZ not found")
+ }
+ tocOffset, err = strconv.ParseInt(string(extra[:16]), 16, 64)
+ if err != nil {
+ return 0, 0, errors.Wrapf(err, "legacy: failed to parse toc offset")
+ }
+ return tocOffset, 0, nil
+}
+
+func (gz *legacyGzipDecompressor) FooterSize() int64 {
+ return legacyFooterSize
+}
+
+func parseTOCEStargz(r io.Reader) (toc *JTOC, tocDgst digest.Digest, err error) {
+ zr, err := gzip.NewReader(r)
+ if err != nil {
+ return nil, "", fmt.Errorf("malformed TOC gzip header: %v", err)
+ }
+ defer zr.Close()
+ zr.Multistream(false)
+ tr := tar.NewReader(zr)
+ h, err := tr.Next()
+ if err != nil {
+ return nil, "", fmt.Errorf("failed to find tar header in TOC gzip stream: %v", err)
+ }
+ if h.Name != TOCTarName {
+ return nil, "", fmt.Errorf("TOC tar entry had name %q; expected %q", h.Name, TOCTarName)
+ }
+ dgstr := digest.Canonical.Digester()
+ toc = new(JTOC)
+ if err := json.NewDecoder(io.TeeReader(tr, dgstr.Hash())).Decode(&toc); err != nil {
+ return nil, "", fmt.Errorf("error decoding TOC JSON: %v", err)
+ }
+ return toc, dgstr.Digest(), nil
+}
diff --git a/vendor/github.com/containerd/stargz-snapshotter/estargz/testutil.go b/vendor/github.com/containerd/stargz-snapshotter/estargz/testutil.go
new file mode 100644
index 000000000..020729b7e
--- /dev/null
+++ b/vendor/github.com/containerd/stargz-snapshotter/estargz/testutil.go
@@ -0,0 +1,1933 @@
+/*
+ Copyright The containerd Authors.
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+*/
+
+/*
+ Copyright 2019 The Go Authors. All rights reserved.
+ Use of this source code is governed by a BSD-style
+ license that can be found in the LICENSE file.
+*/
+
+package estargz
+
+import (
+ "archive/tar"
+ "bytes"
+ "compress/gzip"
+ "crypto/sha256"
+ "encoding/json"
+ "fmt"
+ "io"
+ "io/ioutil"
+ "os"
+ "reflect"
+ "sort"
+ "strings"
+ "testing"
+ "time"
+
+ "github.com/containerd/stargz-snapshotter/estargz/errorutil"
+ "github.com/klauspost/compress/zstd"
+ digest "github.com/opencontainers/go-digest"
+ "github.com/pkg/errors"
+)
+
+// TestingController is Compression with some helper methods necessary for testing.
+type TestingController interface {
+ Compression
+ CountStreams(*testing.T, []byte) int
+ DiffIDOf(*testing.T, []byte) string
+ String() string
+}
+
+// CompressionTestSuite tests this pkg with controllers can build valid eStargz blobs and parse them.
+func CompressionTestSuite(t *testing.T, controllers ...TestingController) {
+ t.Run("testBuild", func(t *testing.T) { t.Parallel(); testBuild(t, controllers...) })
+ t.Run("testDigestAndVerify", func(t *testing.T) { t.Parallel(); testDigestAndVerify(t, controllers...) })
+ t.Run("testWriteAndOpen", func(t *testing.T) { t.Parallel(); testWriteAndOpen(t, controllers...) })
+}
+
+const (
+ uncompressedType int = iota
+ gzipType
+ zstdType
+)
+
+var srcCompressions = []int{
+ uncompressedType,
+ gzipType,
+ zstdType,
+}
+
+var allowedPrefix = [4]string{"", "./", "/", "../"}
+
+// testBuild tests the resulting stargz blob built by this pkg has the same
+// contents as the normal stargz blob.
+func testBuild(t *testing.T, controllers ...TestingController) {
+ tests := []struct {
+ name string
+ chunkSize int
+ in []tarEntry
+ }{
+ {
+ name: "regfiles and directories",
+ chunkSize: 4,
+ in: tarOf(
+ file("foo", "test1"),
+ dir("foo2/"),
+ file("foo2/bar", "test2", xAttr(map[string]string{"test": "sample"})),
+ ),
+ },
+ {
+ name: "empty files",
+ chunkSize: 4,
+ in: tarOf(
+ file("foo", "tttttt"),
+ file("foo_empty", ""),
+ file("foo2", "tttttt"),
+ file("foo_empty2", ""),
+ file("foo3", "tttttt"),
+ file("foo_empty3", ""),
+ file("foo4", "tttttt"),
+ file("foo_empty4", ""),
+ file("foo5", "tttttt"),
+ file("foo_empty5", ""),
+ file("foo6", "tttttt"),
+ ),
+ },
+ {
+ name: "various files",
+ chunkSize: 4,
+ in: tarOf(
+ file("baz.txt", "bazbazbazbazbazbazbaz"),
+ file("foo.txt", "a"),
+ symlink("barlink", "test/bar.txt"),
+ dir("test/"),
+ dir("dev/"),
+ blockdev("dev/testblock", 3, 4),
+ fifo("dev/testfifo"),
+ chardev("dev/testchar1", 5, 6),
+ file("test/bar.txt", "testbartestbar", xAttr(map[string]string{"test2": "sample2"})),
+ dir("test2/"),
+ link("test2/bazlink", "baz.txt"),
+ chardev("dev/testchar2", 1, 2),
+ ),
+ },
+ {
+ name: "no contents",
+ chunkSize: 4,
+ in: tarOf(
+ file("baz.txt", ""),
+ symlink("barlink", "test/bar.txt"),
+ dir("test/"),
+ dir("dev/"),
+ blockdev("dev/testblock", 3, 4),
+ fifo("dev/testfifo"),
+ chardev("dev/testchar1", 5, 6),
+ file("test/bar.txt", "", xAttr(map[string]string{"test2": "sample2"})),
+ dir("test2/"),
+ link("test2/bazlink", "baz.txt"),
+ chardev("dev/testchar2", 1, 2),
+ ),
+ },
+ }
+ for _, tt := range tests {
+ for _, srcCompression := range srcCompressions {
+ srcCompression := srcCompression
+ for _, cl := range controllers {
+ cl := cl
+ for _, prefix := range allowedPrefix {
+ prefix := prefix
+ t.Run(tt.name+"-"+fmt.Sprintf("compression=%v-prefix=%q-src=%d", cl, prefix, srcCompression), func(t *testing.T) {
+ tarBlob := buildTarStatic(t, tt.in, prefix)
+ // Test divideEntries()
+ entries, err := sortEntries(tarBlob, nil, nil) // identical order
+ if err != nil {
+ t.Fatalf("faield to parse tar: %v", err)
+ }
+ var merged []*entry
+ for _, part := range divideEntries(entries, 4) {
+ merged = append(merged, part...)
+ }
+ if !reflect.DeepEqual(entries, merged) {
+ for _, e := range entries {
+ t.Logf("Original: %v", e.header)
+ }
+ for _, e := range merged {
+ t.Logf("Merged: %v", e.header)
+ }
+ t.Errorf("divided entries couldn't be merged")
+ return
+ }
+
+ // Prepare sample data
+ wantBuf := new(bytes.Buffer)
+ sw := NewWriterWithCompressor(wantBuf, cl)
+ sw.ChunkSize = tt.chunkSize
+ if err := sw.AppendTar(tarBlob); err != nil {
+ t.Fatalf("faield to append tar to want stargz: %v", err)
+ }
+ if _, err := sw.Close(); err != nil {
+ t.Fatalf("faield to prepare want stargz: %v", err)
+ }
+ wantData := wantBuf.Bytes()
+ want, err := Open(io.NewSectionReader(
+ bytes.NewReader(wantData), 0, int64(len(wantData))),
+ WithDecompressors(cl),
+ )
+ if err != nil {
+ t.Fatalf("failed to parse the want stargz: %v", err)
+ }
+
+ // Prepare testing data
+ rc, err := Build(compressBlob(t, tarBlob, srcCompression),
+ WithChunkSize(tt.chunkSize), WithCompression(cl))
+ if err != nil {
+ t.Fatalf("faield to build stargz: %v", err)
+ }
+ defer rc.Close()
+ gotBuf := new(bytes.Buffer)
+ if _, err := io.Copy(gotBuf, rc); err != nil {
+ t.Fatalf("failed to copy built stargz blob: %v", err)
+ }
+ gotData := gotBuf.Bytes()
+ got, err := Open(io.NewSectionReader(
+ bytes.NewReader(gotBuf.Bytes()), 0, int64(len(gotData))),
+ WithDecompressors(cl),
+ )
+ if err != nil {
+ t.Fatalf("failed to parse the got stargz: %v", err)
+ }
+
+ // Check DiffID is properly calculated
+ rc.Close()
+ diffID := rc.DiffID()
+ wantDiffID := cl.DiffIDOf(t, gotData)
+ if diffID.String() != wantDiffID {
+ t.Errorf("DiffID = %q; want %q", diffID, wantDiffID)
+ }
+
+ // Compare as stargz
+ if !isSameVersion(t, cl, wantData, gotData) {
+ t.Errorf("built stargz hasn't same json")
+ return
+ }
+ if !isSameEntries(t, want, got) {
+ t.Errorf("built stargz isn't same as the original")
+ return
+ }
+
+ // Compare as tar.gz
+ if !isSameTarGz(t, cl, wantData, gotData) {
+ t.Errorf("built stargz isn't same tar.gz")
+ return
+ }
+ })
+ }
+ }
+ }
+ }
+}
+
+func isSameTarGz(t *testing.T, controller TestingController, a, b []byte) bool {
+ aGz, err := controller.Reader(bytes.NewReader(a))
+ if err != nil {
+ t.Fatalf("failed to read A")
+ }
+ defer aGz.Close()
+ bGz, err := controller.Reader(bytes.NewReader(b))
+ if err != nil {
+ t.Fatalf("failed to read B")
+ }
+ defer bGz.Close()
+
+ // Same as tar's Next() method but ignores landmarks and TOCJSON file
+ next := func(r *tar.Reader) (h *tar.Header, err error) {
+ for {
+ if h, err = r.Next(); err != nil {
+ return
+ }
+ if h.Name != PrefetchLandmark &&
+ h.Name != NoPrefetchLandmark &&
+ h.Name != TOCTarName {
+ return
+ }
+ }
+ }
+
+ aTar := tar.NewReader(aGz)
+ bTar := tar.NewReader(bGz)
+ for {
+ // Fetch and parse next header.
+ aH, aErr := next(aTar)
+ bH, bErr := next(bTar)
+ if aErr != nil || bErr != nil {
+ if aErr == io.EOF && bErr == io.EOF {
+ break
+ }
+ t.Fatalf("Failed to parse tar file: A: %v, B: %v", aErr, bErr)
+ }
+ if !reflect.DeepEqual(aH, bH) {
+ t.Logf("different header (A = %v; B = %v)", aH, bH)
+ return false
+
+ }
+ aFile, err := ioutil.ReadAll(aTar)
+ if err != nil {
+ t.Fatal("failed to read tar payload of A")
+ }
+ bFile, err := ioutil.ReadAll(bTar)
+ if err != nil {
+ t.Fatal("failed to read tar payload of B")
+ }
+ if !bytes.Equal(aFile, bFile) {
+ t.Logf("different tar payload (A = %q; B = %q)", string(a), string(b))
+ return false
+ }
+ }
+
+ return true
+}
+
+func isSameVersion(t *testing.T, controller TestingController, a, b []byte) bool {
+ aJTOC, _, err := parseStargz(io.NewSectionReader(bytes.NewReader(a), 0, int64(len(a))), controller)
+ if err != nil {
+ t.Fatalf("failed to parse A: %v", err)
+ }
+ bJTOC, _, err := parseStargz(io.NewSectionReader(bytes.NewReader(b), 0, int64(len(b))), controller)
+ if err != nil {
+ t.Fatalf("failed to parse B: %v", err)
+ }
+ t.Logf("A: TOCJSON: %v", dumpTOCJSON(t, aJTOC))
+ t.Logf("B: TOCJSON: %v", dumpTOCJSON(t, bJTOC))
+ return aJTOC.Version == bJTOC.Version
+}
+
+func isSameEntries(t *testing.T, a, b *Reader) bool {
+ aroot, ok := a.Lookup("")
+ if !ok {
+ t.Fatalf("failed to get root of A")
+ }
+ broot, ok := b.Lookup("")
+ if !ok {
+ t.Fatalf("failed to get root of B")
+ }
+ aEntry := stargzEntry{aroot, a}
+ bEntry := stargzEntry{broot, b}
+ return contains(t, aEntry, bEntry) && contains(t, bEntry, aEntry)
+}
+
+func compressBlob(t *testing.T, src *io.SectionReader, srcCompression int) *io.SectionReader {
+ buf := new(bytes.Buffer)
+ var w io.WriteCloser
+ var err error
+ if srcCompression == gzipType {
+ w = gzip.NewWriter(buf)
+ } else if srcCompression == zstdType {
+ w, err = zstd.NewWriter(buf)
+ if err != nil {
+ t.Fatalf("failed to init zstd writer: %v", err)
+ }
+ } else {
+ return src
+ }
+ src.Seek(0, io.SeekStart)
+ if _, err := io.Copy(w, src); err != nil {
+ t.Fatalf("failed to compress source")
+ }
+ if err := w.Close(); err != nil {
+ t.Fatalf("failed to finalize compress source")
+ }
+ data := buf.Bytes()
+ return io.NewSectionReader(bytes.NewReader(data), 0, int64(len(data)))
+
+}
+
+type stargzEntry struct {
+ e *TOCEntry
+ r *Reader
+}
+
+// contains checks if all child entries in "b" are also contained in "a".
+// This function also checks if the files/chunks contain the same contents among "a" and "b".
+func contains(t *testing.T, a, b stargzEntry) bool {
+ ae, ar := a.e, a.r
+ be, br := b.e, b.r
+ t.Logf("Comparing: %q vs %q", ae.Name, be.Name)
+ if !equalEntry(ae, be) {
+ t.Logf("%q != %q: entry: a: %v, b: %v", ae.Name, be.Name, ae, be)
+ return false
+ }
+ if ae.Type == "dir" {
+ t.Logf("Directory: %q vs %q: %v vs %v", ae.Name, be.Name,
+ allChildrenName(ae), allChildrenName(be))
+ iscontain := true
+ ae.ForeachChild(func(aBaseName string, aChild *TOCEntry) bool {
+ // Walk through all files on this stargz file.
+
+ if aChild.Name == PrefetchLandmark ||
+ aChild.Name == NoPrefetchLandmark {
+ return true // Ignore landmarks
+ }
+
+ // Ignore a TOCEntry of "./" (formated as "" by stargz lib) on root directory
+ // because this points to the root directory itself.
+ if aChild.Name == "" && ae.Name == "" {
+ return true
+ }
+
+ bChild, ok := be.LookupChild(aBaseName)
+ if !ok {
+ t.Logf("%q (base: %q): not found in b: %v",
+ ae.Name, aBaseName, allChildrenName(be))
+ iscontain = false
+ return false
+ }
+
+ childcontain := contains(t, stargzEntry{aChild, a.r}, stargzEntry{bChild, b.r})
+ if !childcontain {
+ t.Logf("%q != %q: non-equal dir", ae.Name, be.Name)
+ iscontain = false
+ return false
+ }
+ return true
+ })
+ return iscontain
+ } else if ae.Type == "reg" {
+ af, err := ar.OpenFile(ae.Name)
+ if err != nil {
+ t.Fatalf("failed to open file %q on A: %v", ae.Name, err)
+ }
+ bf, err := br.OpenFile(be.Name)
+ if err != nil {
+ t.Fatalf("failed to open file %q on B: %v", be.Name, err)
+ }
+
+ var nr int64
+ for nr < ae.Size {
+ abytes, anext, aok := readOffset(t, af, nr, a)
+ bbytes, bnext, bok := readOffset(t, bf, nr, b)
+ if !aok && !bok {
+ break
+ } else if !(aok && bok) || anext != bnext {
+ t.Logf("%q != %q (offset=%d): chunk existence a=%v vs b=%v, anext=%v vs bnext=%v",
+ ae.Name, be.Name, nr, aok, bok, anext, bnext)
+ return false
+ }
+ nr = anext
+ if !bytes.Equal(abytes, bbytes) {
+ t.Logf("%q != %q: different contents %v vs %v",
+ ae.Name, be.Name, string(abytes), string(bbytes))
+ return false
+ }
+ }
+ return true
+ }
+
+ return true
+}
+
+func allChildrenName(e *TOCEntry) (children []string) {
+ e.ForeachChild(func(baseName string, _ *TOCEntry) bool {
+ children = append(children, baseName)
+ return true
+ })
+ return
+}
+
+func equalEntry(a, b *TOCEntry) bool {
+ // Here, we selectively compare fileds that we are interested in.
+ return a.Name == b.Name &&
+ a.Type == b.Type &&
+ a.Size == b.Size &&
+ a.ModTime3339 == b.ModTime3339 &&
+ a.Stat().ModTime().Equal(b.Stat().ModTime()) && // modTime time.Time
+ a.LinkName == b.LinkName &&
+ a.Mode == b.Mode &&
+ a.UID == b.UID &&
+ a.GID == b.GID &&
+ a.Uname == b.Uname &&
+ a.Gname == b.Gname &&
+ (a.Offset > 0) == (b.Offset > 0) &&
+ (a.NextOffset() > 0) == (b.NextOffset() > 0) &&
+ a.DevMajor == b.DevMajor &&
+ a.DevMinor == b.DevMinor &&
+ a.NumLink == b.NumLink &&
+ reflect.DeepEqual(a.Xattrs, b.Xattrs) &&
+ // chunk-related infomations aren't compared in this function.
+ // ChunkOffset int64 `json:"chunkOffset,omitempty"`
+ // ChunkSize int64 `json:"chunkSize,omitempty"`
+ // children map[string]*TOCEntry
+ a.Digest == b.Digest
+}
+
+func readOffset(t *testing.T, r *io.SectionReader, offset int64, e stargzEntry) ([]byte, int64, bool) {
+ ce, ok := e.r.ChunkEntryForOffset(e.e.Name, offset)
+ if !ok {
+ return nil, 0, false
+ }
+ data := make([]byte, ce.ChunkSize)
+ t.Logf("Offset: %v, NextOffset: %v", ce.Offset, ce.NextOffset())
+ n, err := r.ReadAt(data, ce.ChunkOffset)
+ if err != nil {
+ t.Fatalf("failed to read file payload of %q (offset:%d,size:%d): %v",
+ e.e.Name, ce.ChunkOffset, ce.ChunkSize, err)
+ }
+ if int64(n) != ce.ChunkSize {
+ t.Fatalf("unexpected copied data size %d; want %d",
+ n, ce.ChunkSize)
+ }
+ return data[:n], offset + ce.ChunkSize, true
+}
+
+func dumpTOCJSON(t *testing.T, tocJSON *JTOC) string {
+ jtocData, err := json.Marshal(*tocJSON)
+ if err != nil {
+ t.Fatalf("failed to marshal TOC JSON: %v", err)
+ }
+ buf := new(bytes.Buffer)
+ if _, err := io.Copy(buf, bytes.NewReader(jtocData)); err != nil {
+ t.Fatalf("failed to read toc json blob: %v", err)
+ }
+ return buf.String()
+}
+
+const chunkSize = 3
+
+// type check func(t *testing.T, sgzData []byte, tocDigest digest.Digest, dgstMap map[string]digest.Digest, compressionLevel int)
+type check func(t *testing.T, sgzData []byte, tocDigest digest.Digest, dgstMap map[string]digest.Digest, controller TestingController)
+
+// testDigestAndVerify runs specified checks against sample stargz blobs.
+func testDigestAndVerify(t *testing.T, controllers ...TestingController) {
+ tests := []struct {
+ name string
+ tarInit func(t *testing.T, dgstMap map[string]digest.Digest) (blob []tarEntry)
+ checks []check
+ }{
+ {
+ name: "no-regfile",
+ tarInit: func(t *testing.T, dgstMap map[string]digest.Digest) (blob []tarEntry) {
+ return tarOf(
+ dir("test/"),
+ )
+ },
+ checks: []check{
+ checkStargzTOC,
+ checkVerifyTOC,
+ checkVerifyInvalidStargzFail(buildTarStatic(t, tarOf(
+ dir("test2/"), // modified
+ ), allowedPrefix[0])),
+ },
+ },
+ {
+ name: "small-files",
+ tarInit: func(t *testing.T, dgstMap map[string]digest.Digest) (blob []tarEntry) {
+ return tarOf(
+ regDigest(t, "baz.txt", "", dgstMap),
+ regDigest(t, "foo.txt", "a", dgstMap),
+ dir("test/"),
+ regDigest(t, "test/bar.txt", "bbb", dgstMap),
+ )
+ },
+ checks: []check{
+ checkStargzTOC,
+ checkVerifyTOC,
+ checkVerifyInvalidStargzFail(buildTarStatic(t, tarOf(
+ file("baz.txt", ""),
+ file("foo.txt", "M"), // modified
+ dir("test/"),
+ file("test/bar.txt", "bbb"),
+ ), allowedPrefix[0])),
+ // checkVerifyInvalidTOCEntryFail("foo.txt"), // TODO
+ checkVerifyBrokenContentFail("foo.txt"),
+ },
+ },
+ {
+ name: "big-files",
+ tarInit: func(t *testing.T, dgstMap map[string]digest.Digest) (blob []tarEntry) {
+ return tarOf(
+ regDigest(t, "baz.txt", "bazbazbazbazbazbazbaz", dgstMap),
+ regDigest(t, "foo.txt", "a", dgstMap),
+ dir("test/"),
+ regDigest(t, "test/bar.txt", "testbartestbar", dgstMap),
+ )
+ },
+ checks: []check{
+ checkStargzTOC,
+ checkVerifyTOC,
+ checkVerifyInvalidStargzFail(buildTarStatic(t, tarOf(
+ file("baz.txt", "bazbazbazMMMbazbazbaz"), // modified
+ file("foo.txt", "a"),
+ dir("test/"),
+ file("test/bar.txt", "testbartestbar"),
+ ), allowedPrefix[0])),
+ checkVerifyInvalidTOCEntryFail("test/bar.txt"),
+ checkVerifyBrokenContentFail("test/bar.txt"),
+ },
+ },
+ {
+ name: "with-non-regfiles",
+ tarInit: func(t *testing.T, dgstMap map[string]digest.Digest) (blob []tarEntry) {
+ return tarOf(
+ regDigest(t, "baz.txt", "bazbazbazbazbazbazbaz", dgstMap),
+ regDigest(t, "foo.txt", "a", dgstMap),
+ symlink("barlink", "test/bar.txt"),
+ dir("test/"),
+ regDigest(t, "test/bar.txt", "testbartestbar", dgstMap),
+ dir("test2/"),
+ link("test2/bazlink", "baz.txt"),
+ )
+ },
+ checks: []check{
+ checkStargzTOC,
+ checkVerifyTOC,
+ checkVerifyInvalidStargzFail(buildTarStatic(t, tarOf(
+ file("baz.txt", "bazbazbazbazbazbazbaz"),
+ file("foo.txt", "a"),
+ symlink("barlink", "test/bar.txt"),
+ dir("test/"),
+ file("test/bar.txt", "testbartestbar"),
+ dir("test2/"),
+ link("test2/bazlink", "foo.txt"), // modified
+ ), allowedPrefix[0])),
+ checkVerifyInvalidTOCEntryFail("test/bar.txt"),
+ checkVerifyBrokenContentFail("test/bar.txt"),
+ },
+ },
+ }
+
+ for _, tt := range tests {
+ for _, srcCompression := range srcCompressions {
+ srcCompression := srcCompression
+ for _, cl := range controllers {
+ cl := cl
+ for _, prefix := range allowedPrefix {
+ prefix := prefix
+ t.Run(tt.name+"-"+fmt.Sprintf("compression=%v-prefix=%q", cl, prefix), func(t *testing.T) {
+ // Get original tar file and chunk digests
+ dgstMap := make(map[string]digest.Digest)
+ tarBlob := buildTarStatic(t, tt.tarInit(t, dgstMap), prefix)
+
+ rc, err := Build(compressBlob(t, tarBlob, srcCompression),
+ WithChunkSize(chunkSize), WithCompression(cl))
+ if err != nil {
+ t.Fatalf("failed to convert stargz: %v", err)
+ }
+ tocDigest := rc.TOCDigest()
+ defer rc.Close()
+ buf := new(bytes.Buffer)
+ if _, err := io.Copy(buf, rc); err != nil {
+ t.Fatalf("failed to copy built stargz blob: %v", err)
+ }
+ newStargz := buf.Bytes()
+ // NoPrefetchLandmark is added during `Bulid`, which is expected behaviour.
+ dgstMap[chunkID(NoPrefetchLandmark, 0, int64(len([]byte{landmarkContents})))] = digest.FromBytes([]byte{landmarkContents})
+
+ for _, check := range tt.checks {
+ check(t, newStargz, tocDigest, dgstMap, cl)
+ }
+ })
+ }
+ }
+ }
+ }
+}
+
+// checkStargzTOC checks the TOC JSON of the passed stargz has the expected
+// digest and contains valid chunks. It walks all entries in the stargz and
+// checks all chunk digests stored to the TOC JSON match the actual contents.
+func checkStargzTOC(t *testing.T, sgzData []byte, tocDigest digest.Digest, dgstMap map[string]digest.Digest, controller TestingController) {
+ sgz, err := Open(
+ io.NewSectionReader(bytes.NewReader(sgzData), 0, int64(len(sgzData))),
+ WithDecompressors(controller),
+ )
+ if err != nil {
+ t.Errorf("failed to parse converted stargz: %v", err)
+ return
+ }
+ digestMapTOC, err := listDigests(io.NewSectionReader(
+ bytes.NewReader(sgzData), 0, int64(len(sgzData))),
+ controller,
+ )
+ if err != nil {
+ t.Fatalf("failed to list digest: %v", err)
+ }
+ found := make(map[string]bool)
+ for id := range dgstMap {
+ found[id] = false
+ }
+ zr, err := controller.Reader(bytes.NewReader(sgzData))
+ if err != nil {
+ t.Fatalf("failed to decompress converted stargz: %v", err)
+ }
+ defer zr.Close()
+ tr := tar.NewReader(zr)
+ for {
+ h, err := tr.Next()
+ if err != nil {
+ if err != io.EOF {
+ t.Errorf("failed to read tar entry: %v", err)
+ return
+ }
+ break
+ }
+ if h.Name == TOCTarName {
+ // Check the digest of TOC JSON based on the actual contents
+ // It's sure that TOC JSON exists in this archive because
+ // Open succeeded.
+ dgstr := digest.Canonical.Digester()
+ if _, err := io.Copy(dgstr.Hash(), tr); err != nil {
+ t.Fatalf("failed to calculate digest of TOC JSON: %v",
+ err)
+ }
+ if dgstr.Digest() != tocDigest {
+ t.Errorf("invalid TOC JSON %q; want %q", tocDigest, dgstr.Digest())
+ }
+ continue
+ }
+ if _, ok := sgz.Lookup(h.Name); !ok {
+ t.Errorf("lost stargz entry %q in the converted TOC", h.Name)
+ return
+ }
+ var n int64
+ for n < h.Size {
+ ce, ok := sgz.ChunkEntryForOffset(h.Name, n)
+ if !ok {
+ t.Errorf("lost chunk %q(offset=%d) in the converted TOC",
+ h.Name, n)
+ return
+ }
+
+ // Get the original digest to make sure the file contents are kept unchanged
+ // from the original tar, during the whole conversion steps.
+ id := chunkID(h.Name, n, ce.ChunkSize)
+ want, ok := dgstMap[id]
+ if !ok {
+ t.Errorf("Unexpected chunk %q(offset=%d,size=%d): %v",
+ h.Name, n, ce.ChunkSize, dgstMap)
+ return
+ }
+ found[id] = true
+
+ // Check the file contents
+ dgstr := digest.Canonical.Digester()
+ if _, err := io.CopyN(dgstr.Hash(), tr, ce.ChunkSize); err != nil {
+ t.Fatalf("failed to calculate digest of %q (offset=%d,size=%d)",
+ h.Name, n, ce.ChunkSize)
+ }
+ if want != dgstr.Digest() {
+ t.Errorf("Invalid contents in converted stargz %q: %q; want %q",
+ h.Name, dgstr.Digest(), want)
+ return
+ }
+
+ // Check the digest stored in TOC JSON
+ dgstTOC, ok := digestMapTOC[ce.Offset]
+ if !ok {
+ t.Errorf("digest of %q(offset=%d,size=%d,chunkOffset=%d) isn't registered",
+ h.Name, ce.Offset, ce.ChunkSize, ce.ChunkOffset)
+ }
+ if want != dgstTOC {
+ t.Errorf("Invalid digest in TOCEntry %q: %q; want %q",
+ h.Name, dgstTOC, want)
+ return
+ }
+
+ n += ce.ChunkSize
+ }
+ }
+
+ for id, ok := range found {
+ if !ok {
+ t.Errorf("required chunk %q not found in the converted stargz: %v", id, found)
+ }
+ }
+}
+
+// checkVerifyTOC checks the verification works for the TOC JSON of the passed
+// stargz. It walks all entries in the stargz and checks the verifications for
+// all chunks work.
+func checkVerifyTOC(t *testing.T, sgzData []byte, tocDigest digest.Digest, dgstMap map[string]digest.Digest, controller TestingController) {
+ sgz, err := Open(
+ io.NewSectionReader(bytes.NewReader(sgzData), 0, int64(len(sgzData))),
+ WithDecompressors(controller),
+ )
+ if err != nil {
+ t.Errorf("failed to parse converted stargz: %v", err)
+ return
+ }
+ ev, err := sgz.VerifyTOC(tocDigest)
+ if err != nil {
+ t.Errorf("failed to verify stargz: %v", err)
+ return
+ }
+
+ found := make(map[string]bool)
+ for id := range dgstMap {
+ found[id] = false
+ }
+ zr, err := controller.Reader(bytes.NewReader(sgzData))
+ if err != nil {
+ t.Fatalf("failed to decompress converted stargz: %v", err)
+ }
+ defer zr.Close()
+ tr := tar.NewReader(zr)
+ for {
+ h, err := tr.Next()
+ if err != nil {
+ if err != io.EOF {
+ t.Errorf("failed to read tar entry: %v", err)
+ return
+ }
+ break
+ }
+ if h.Name == TOCTarName {
+ continue
+ }
+ if _, ok := sgz.Lookup(h.Name); !ok {
+ t.Errorf("lost stargz entry %q in the converted TOC", h.Name)
+ return
+ }
+ var n int64
+ for n < h.Size {
+ ce, ok := sgz.ChunkEntryForOffset(h.Name, n)
+ if !ok {
+ t.Errorf("lost chunk %q(offset=%d) in the converted TOC",
+ h.Name, n)
+ return
+ }
+
+ v, err := ev.Verifier(ce)
+ if err != nil {
+ t.Errorf("failed to get verifier for %q(offset=%d)", h.Name, n)
+ }
+
+ found[chunkID(h.Name, n, ce.ChunkSize)] = true
+
+ // Check the file contents
+ if _, err := io.CopyN(v, tr, ce.ChunkSize); err != nil {
+ t.Fatalf("failed to get chunk of %q (offset=%d,size=%d)",
+ h.Name, n, ce.ChunkSize)
+ }
+ if !v.Verified() {
+ t.Errorf("Invalid contents in converted stargz %q (should be succeeded)",
+ h.Name)
+ return
+ }
+ n += ce.ChunkSize
+ }
+ }
+
+ for id, ok := range found {
+ if !ok {
+ t.Errorf("required chunk %q not found in the converted stargz: %v", id, found)
+ }
+ }
+}
+
+// checkVerifyInvalidTOCEntryFail checks if misconfigured TOC JSON can be
+// detected during the verification and the verification returns an error.
+func checkVerifyInvalidTOCEntryFail(filename string) check {
+ return func(t *testing.T, sgzData []byte, tocDigest digest.Digest, dgstMap map[string]digest.Digest, controller TestingController) {
+ funcs := map[string]rewriteFunc{
+ "lost digest in a entry": func(t *testing.T, toc *JTOC, sgz *io.SectionReader) {
+ var found bool
+ for _, e := range toc.Entries {
+ if cleanEntryName(e.Name) == filename {
+ if e.Type != "reg" && e.Type != "chunk" {
+ t.Fatalf("entry %q to break must be regfile or chunk", filename)
+ }
+ if e.ChunkDigest == "" {
+ t.Fatalf("entry %q is already invalid", filename)
+ }
+ e.ChunkDigest = ""
+ found = true
+ }
+ }
+ if !found {
+ t.Fatalf("rewrite target not found")
+ }
+ },
+ "duplicated entry offset": func(t *testing.T, toc *JTOC, sgz *io.SectionReader) {
+ var (
+ sampleEntry *TOCEntry
+ targetEntry *TOCEntry
+ )
+ for _, e := range toc.Entries {
+ if e.Type == "reg" || e.Type == "chunk" {
+ if cleanEntryName(e.Name) == filename {
+ targetEntry = e
+ } else {
+ sampleEntry = e
+ }
+ }
+ }
+ if sampleEntry == nil {
+ t.Fatalf("TOC must contain at least one regfile or chunk entry other than the rewrite target")
+ }
+ if targetEntry == nil {
+ t.Fatalf("rewrite target not found")
+ }
+ targetEntry.Offset = sampleEntry.Offset
+ },
+ }
+
+ for name, rFunc := range funcs {
+ t.Run(name, func(t *testing.T) {
+ newSgz, newTocDigest := rewriteTOCJSON(t, io.NewSectionReader(bytes.NewReader(sgzData), 0, int64(len(sgzData))), rFunc, controller)
+ buf := new(bytes.Buffer)
+ if _, err := io.Copy(buf, newSgz); err != nil {
+ t.Fatalf("failed to get converted stargz")
+ }
+ isgz := buf.Bytes()
+
+ sgz, err := Open(
+ io.NewSectionReader(bytes.NewReader(isgz), 0, int64(len(isgz))),
+ WithDecompressors(controller),
+ )
+ if err != nil {
+ t.Fatalf("failed to parse converted stargz: %v", err)
+ return
+ }
+ _, err = sgz.VerifyTOC(newTocDigest)
+ if err == nil {
+ t.Errorf("must fail for invalid TOC")
+ return
+ }
+ })
+ }
+ }
+}
+
+// checkVerifyInvalidStargzFail checks if the verification detects that the
+// given stargz file doesn't match to the expected digest and returns error.
+func checkVerifyInvalidStargzFail(invalid *io.SectionReader) check {
+ return func(t *testing.T, sgzData []byte, tocDigest digest.Digest, dgstMap map[string]digest.Digest, controller TestingController) {
+ rc, err := Build(invalid, WithChunkSize(chunkSize), WithCompression(controller))
+ if err != nil {
+ t.Fatalf("failed to convert stargz: %v", err)
+ }
+ defer rc.Close()
+ buf := new(bytes.Buffer)
+ if _, err := io.Copy(buf, rc); err != nil {
+ t.Fatalf("failed to copy built stargz blob: %v", err)
+ }
+ mStargz := buf.Bytes()
+
+ sgz, err := Open(
+ io.NewSectionReader(bytes.NewReader(mStargz), 0, int64(len(mStargz))),
+ WithDecompressors(controller),
+ )
+ if err != nil {
+ t.Fatalf("failed to parse converted stargz: %v", err)
+ return
+ }
+ _, err = sgz.VerifyTOC(tocDigest)
+ if err == nil {
+ t.Errorf("must fail for invalid TOC")
+ return
+ }
+ }
+}
+
+// checkVerifyBrokenContentFail checks if the verifier detects broken contents
+// that doesn't match to the expected digest and returns error.
+func checkVerifyBrokenContentFail(filename string) check {
+ return func(t *testing.T, sgzData []byte, tocDigest digest.Digest, dgstMap map[string]digest.Digest, controller TestingController) {
+ // Parse stargz file
+ sgz, err := Open(
+ io.NewSectionReader(bytes.NewReader(sgzData), 0, int64(len(sgzData))),
+ WithDecompressors(controller),
+ )
+ if err != nil {
+ t.Fatalf("failed to parse converted stargz: %v", err)
+ return
+ }
+ ev, err := sgz.VerifyTOC(tocDigest)
+ if err != nil {
+ t.Fatalf("failed to verify stargz: %v", err)
+ return
+ }
+
+ // Open the target file
+ sr, err := sgz.OpenFile(filename)
+ if err != nil {
+ t.Fatalf("failed to open file %q", filename)
+ }
+ ce, ok := sgz.ChunkEntryForOffset(filename, 0)
+ if !ok {
+ t.Fatalf("lost chunk %q(offset=%d) in the converted TOC", filename, 0)
+ return
+ }
+ if ce.ChunkSize == 0 {
+ t.Fatalf("file mustn't be empty")
+ return
+ }
+ data := make([]byte, ce.ChunkSize)
+ if _, err := sr.ReadAt(data, ce.ChunkOffset); err != nil {
+ t.Errorf("failed to get data of a chunk of %q(offset=%q)",
+ filename, ce.ChunkOffset)
+ }
+
+ // Check the broken chunk (must fail)
+ v, err := ev.Verifier(ce)
+ if err != nil {
+ t.Fatalf("failed to get verifier for %q", filename)
+ }
+ broken := append([]byte{^data[0]}, data[1:]...)
+ if _, err := io.CopyN(v, bytes.NewReader(broken), ce.ChunkSize); err != nil {
+ t.Fatalf("failed to get chunk of %q (offset=%d,size=%d)",
+ filename, ce.ChunkOffset, ce.ChunkSize)
+ }
+ if v.Verified() {
+ t.Errorf("verification must fail for broken file chunk %q(org:%q,broken:%q)",
+ filename, data, broken)
+ }
+ }
+}
+
+func chunkID(name string, offset, size int64) string {
+ return fmt.Sprintf("%s-%d-%d", cleanEntryName(name), offset, size)
+}
+
+type rewriteFunc func(t *testing.T, toc *JTOC, sgz *io.SectionReader)
+
+func rewriteTOCJSON(t *testing.T, sgz *io.SectionReader, rewrite rewriteFunc, controller TestingController) (newSgz io.Reader, tocDigest digest.Digest) {
+ decodedJTOC, jtocOffset, err := parseStargz(sgz, controller)
+ if err != nil {
+ t.Fatalf("failed to extract TOC JSON: %v", err)
+ }
+
+ rewrite(t, decodedJTOC, sgz)
+
+ tocFooter, tocDigest, err := tocAndFooter(controller, decodedJTOC, jtocOffset)
+ if err != nil {
+ t.Fatalf("failed to create toc and footer: %v", err)
+ }
+
+ // Reconstruct stargz file with the modified TOC JSON
+ if _, err := sgz.Seek(0, io.SeekStart); err != nil {
+ t.Fatalf("failed to reset the seek position of stargz: %v", err)
+ }
+ return io.MultiReader(
+ io.LimitReader(sgz, jtocOffset), // Original stargz (before TOC JSON)
+ tocFooter, // Rewritten TOC and footer
+ ), tocDigest
+}
+
+func listDigests(sgz *io.SectionReader, controller TestingController) (map[int64]digest.Digest, error) {
+ decodedJTOC, _, err := parseStargz(sgz, controller)
+ if err != nil {
+ return nil, err
+ }
+ digestMap := make(map[int64]digest.Digest)
+ for _, e := range decodedJTOC.Entries {
+ if e.Type == "reg" || e.Type == "chunk" {
+ if e.Type == "reg" && e.Size == 0 {
+ continue // ignores empty file
+ }
+ if e.ChunkDigest == "" {
+ return nil, fmt.Errorf("ChunkDigest of %q(off=%d) not found in TOC JSON",
+ e.Name, e.Offset)
+ }
+ d, err := digest.Parse(e.ChunkDigest)
+ if err != nil {
+ return nil, err
+ }
+ digestMap[e.Offset] = d
+ }
+ }
+ return digestMap, nil
+}
+
+func parseStargz(sgz *io.SectionReader, controller TestingController) (decodedJTOC *JTOC, jtocOffset int64, err error) {
+ fSize := controller.FooterSize()
+ footer := make([]byte, fSize)
+ if _, err := sgz.ReadAt(footer, sgz.Size()-fSize); err != nil {
+ return nil, 0, errors.Wrap(err, "error reading footer")
+ }
+ tocOffset, _, err := controller.ParseFooter(footer[positive(int64(len(footer))-fSize):])
+ if err != nil {
+ return nil, 0, errors.Wrapf(err, "failed to parse footer")
+ }
+
+ // Decode the TOC JSON
+ tocReader := io.NewSectionReader(sgz, tocOffset, sgz.Size()-tocOffset-fSize)
+ decodedJTOC, _, err = controller.ParseTOC(tocReader)
+ if err != nil {
+ return nil, 0, errors.Wrap(err, "failed to parse TOC")
+ }
+ return decodedJTOC, tocOffset, nil
+}
+
+func testWriteAndOpen(t *testing.T, controllers ...TestingController) {
+ const content = "Some contents"
+ invalidUtf8 := "\xff\xfe\xfd"
+
+ xAttrFile := xAttr{"foo": "bar", "invalid-utf8": invalidUtf8}
+ sampleOwner := owner{uid: 50, gid: 100}
+
+ tests := []struct {
+ name string
+ chunkSize int
+ in []tarEntry
+ want []stargzCheck
+ wantNumGz int // expected number of streams
+ }{
+ {
+ name: "empty",
+ in: tarOf(),
+ wantNumGz: 2, // TOC + footer
+ want: checks(
+ numTOCEntries(0),
+ ),
+ },
+ {
+ name: "1dir_1empty_file",
+ in: tarOf(
+ dir("foo/"),
+ file("foo/bar.txt", ""),
+ ),
+ wantNumGz: 3, // dir, TOC, footer
+ want: checks(
+ numTOCEntries(2),
+ hasDir("foo/"),
+ hasFileLen("foo/bar.txt", 0),
+ entryHasChildren("foo", "bar.txt"),
+ hasFileDigest("foo/bar.txt", digestFor("")),
+ ),
+ },
+ {
+ name: "1dir_1file",
+ in: tarOf(
+ dir("foo/"),
+ file("foo/bar.txt", content, xAttrFile),
+ ),
+ wantNumGz: 4, // var dir, foo.txt alone, TOC, footer
+ want: checks(
+ numTOCEntries(2),
+ hasDir("foo/"),
+ hasFileLen("foo/bar.txt", len(content)),
+ hasFileDigest("foo/bar.txt", digestFor(content)),
+ hasFileContentsRange("foo/bar.txt", 0, content),
+ hasFileContentsRange("foo/bar.txt", 1, content[1:]),
+ entryHasChildren("", "foo"),
+ entryHasChildren("foo", "bar.txt"),
+ hasFileXattrs("foo/bar.txt", "foo", "bar"),
+ hasFileXattrs("foo/bar.txt", "invalid-utf8", invalidUtf8),
+ ),
+ },
+ {
+ name: "2meta_2file",
+ in: tarOf(
+ dir("bar/", sampleOwner),
+ dir("foo/", sampleOwner),
+ file("foo/bar.txt", content, sampleOwner),
+ ),
+ wantNumGz: 4, // both dirs, foo.txt alone, TOC, footer
+ want: checks(
+ numTOCEntries(3),
+ hasDir("bar/"),
+ hasDir("foo/"),
+ hasFileLen("foo/bar.txt", len(content)),
+ entryHasChildren("", "bar", "foo"),
+ entryHasChildren("foo", "bar.txt"),
+ hasChunkEntries("foo/bar.txt", 1),
+ hasEntryOwner("bar/", sampleOwner),
+ hasEntryOwner("foo/", sampleOwner),
+ hasEntryOwner("foo/bar.txt", sampleOwner),
+ ),
+ },
+ {
+ name: "3dir",
+ in: tarOf(
+ dir("bar/"),
+ dir("foo/"),
+ dir("foo/bar/"),
+ ),
+ wantNumGz: 3, // 3 dirs, TOC, footer
+ want: checks(
+ hasDirLinkCount("bar/", 2),
+ hasDirLinkCount("foo/", 3),
+ hasDirLinkCount("foo/bar/", 2),
+ ),
+ },
+ {
+ name: "symlink",
+ in: tarOf(
+ dir("foo/"),
+ symlink("foo/bar", "../../x"),
+ ),
+ wantNumGz: 3, // metas + TOC + footer
+ want: checks(
+ numTOCEntries(2),
+ hasSymlink("foo/bar", "../../x"),
+ entryHasChildren("", "foo"),
+ entryHasChildren("foo", "bar"),
+ ),
+ },
+ {
+ name: "chunked_file",
+ chunkSize: 4,
+ in: tarOf(
+ dir("foo/"),
+ file("foo/big.txt", "This "+"is s"+"uch "+"a bi"+"g fi"+"le"),
+ ),
+ wantNumGz: 9,
+ want: checks(
+ numTOCEntries(7), // 1 for foo dir, 6 for the foo/big.txt file
+ hasDir("foo/"),
+ hasFileLen("foo/big.txt", len("This is such a big file")),
+ hasFileDigest("foo/big.txt", digestFor("This is such a big file")),
+ hasFileContentsRange("foo/big.txt", 0, "This is such a big file"),
+ hasFileContentsRange("foo/big.txt", 1, "his is such a big file"),
+ hasFileContentsRange("foo/big.txt", 2, "is is such a big file"),
+ hasFileContentsRange("foo/big.txt", 3, "s is such a big file"),
+ hasFileContentsRange("foo/big.txt", 4, " is such a big file"),
+ hasFileContentsRange("foo/big.txt", 5, "is such a big file"),
+ hasFileContentsRange("foo/big.txt", 6, "s such a big file"),
+ hasFileContentsRange("foo/big.txt", 7, " such a big file"),
+ hasFileContentsRange("foo/big.txt", 8, "such a big file"),
+ hasFileContentsRange("foo/big.txt", 9, "uch a big file"),
+ hasFileContentsRange("foo/big.txt", 10, "ch a big file"),
+ hasFileContentsRange("foo/big.txt", 11, "h a big file"),
+ hasFileContentsRange("foo/big.txt", 12, " a big file"),
+ hasFileContentsRange("foo/big.txt", len("This is such a big file")-1, ""),
+ hasChunkEntries("foo/big.txt", 6),
+ ),
+ },
+ {
+ name: "recursive",
+ in: tarOf(
+ dir("/", sampleOwner),
+ dir("bar/", sampleOwner),
+ dir("foo/", sampleOwner),
+ file("foo/bar.txt", content, sampleOwner),
+ ),
+ wantNumGz: 4, // dirs, bar.txt alone, TOC, footer
+ want: checks(
+ maxDepth(2), // 0: root directory, 1: "foo/", 2: "bar.txt"
+ ),
+ },
+ {
+ name: "block_char_fifo",
+ in: tarOf(
+ tarEntryFunc(func(w *tar.Writer, prefix string) error {
+ return w.WriteHeader(&tar.Header{
+ Name: prefix + "b",
+ Typeflag: tar.TypeBlock,
+ Devmajor: 123,
+ Devminor: 456,
+ })
+ }),
+ tarEntryFunc(func(w *tar.Writer, prefix string) error {
+ return w.WriteHeader(&tar.Header{
+ Name: prefix + "c",
+ Typeflag: tar.TypeChar,
+ Devmajor: 111,
+ Devminor: 222,
+ })
+ }),
+ tarEntryFunc(func(w *tar.Writer, prefix string) error {
+ return w.WriteHeader(&tar.Header{
+ Name: prefix + "f",
+ Typeflag: tar.TypeFifo,
+ })
+ }),
+ ),
+ wantNumGz: 3,
+ want: checks(
+ lookupMatch("b", &TOCEntry{Name: "b", Type: "block", DevMajor: 123, DevMinor: 456, NumLink: 1}),
+ lookupMatch("c", &TOCEntry{Name: "c", Type: "char", DevMajor: 111, DevMinor: 222, NumLink: 1}),
+ lookupMatch("f", &TOCEntry{Name: "f", Type: "fifo", NumLink: 1}),
+ ),
+ },
+ {
+ name: "modes",
+ in: tarOf(
+ dir("foo1/", 0755|os.ModeDir|os.ModeSetgid),
+ file("foo1/bar1", content, 0700|os.ModeSetuid),
+ file("foo1/bar2", content, 0755|os.ModeSetgid),
+ dir("foo2/", 0755|os.ModeDir|os.ModeSticky),
+ file("foo2/bar3", content, 0755|os.ModeSticky),
+ dir("foo3/", 0755|os.ModeDir),
+ file("foo3/bar4", content, os.FileMode(0700)),
+ file("foo3/bar5", content, os.FileMode(0755)),
+ ),
+ wantNumGz: 8, // dir, bar1 alone, bar2 alone + dir, bar3 alone + dir, bar4 alone, bar5 alone, TOC, footer
+ want: checks(
+ hasMode("foo1/", 0755|os.ModeDir|os.ModeSetgid),
+ hasMode("foo1/bar1", 0700|os.ModeSetuid),
+ hasMode("foo1/bar2", 0755|os.ModeSetgid),
+ hasMode("foo2/", 0755|os.ModeDir|os.ModeSticky),
+ hasMode("foo2/bar3", 0755|os.ModeSticky),
+ hasMode("foo3/", 0755|os.ModeDir),
+ hasMode("foo3/bar4", os.FileMode(0700)),
+ hasMode("foo3/bar5", os.FileMode(0755)),
+ ),
+ },
+ }
+
+ for _, tt := range tests {
+ for _, cl := range controllers {
+ cl := cl
+ for _, prefix := range allowedPrefix {
+ prefix := prefix
+ t.Run(tt.name+"-"+fmt.Sprintf("compression=%v-prefix=%q", cl, prefix), func(t *testing.T) {
+ tr, cancel := buildTar(t, tt.in, prefix)
+ defer cancel()
+ var stargzBuf bytes.Buffer
+ w := NewWriterWithCompressor(&stargzBuf, cl)
+ w.ChunkSize = tt.chunkSize
+ if err := w.AppendTar(tr); err != nil {
+ t.Fatalf("Append: %v", err)
+ }
+ if _, err := w.Close(); err != nil {
+ t.Fatalf("Writer.Close: %v", err)
+ }
+ b := stargzBuf.Bytes()
+
+ diffID := w.DiffID()
+ wantDiffID := cl.DiffIDOf(t, b)
+ if diffID != wantDiffID {
+ t.Errorf("DiffID = %q; want %q", diffID, wantDiffID)
+ }
+
+ got := cl.CountStreams(t, b)
+ if got != tt.wantNumGz {
+ t.Errorf("number of streams = %d; want %d", got, tt.wantNumGz)
+ }
+
+ telemetry, checkCalled := newCalledTelemetry()
+ r, err := Open(
+ io.NewSectionReader(bytes.NewReader(b), 0, int64(len(b))),
+ WithDecompressors(cl),
+ WithTelemetry(telemetry),
+ )
+ if err != nil {
+ t.Fatalf("stargz.Open: %v", err)
+ }
+ if err := checkCalled(); err != nil {
+ t.Errorf("telemetry failure: %v", err)
+ }
+ for _, want := range tt.want {
+ want.check(t, r)
+ }
+ })
+ }
+ }
+ }
+}
+
+func newCalledTelemetry() (telemetry *Telemetry, check func() error) {
+ var getFooterLatencyCalled bool
+ var getTocLatencyCalled bool
+ var deserializeTocLatencyCalled bool
+ return &Telemetry{
+ func(time.Time) { getFooterLatencyCalled = true },
+ func(time.Time) { getTocLatencyCalled = true },
+ func(time.Time) { deserializeTocLatencyCalled = true },
+ }, func() error {
+ var allErr []error
+ if !getFooterLatencyCalled {
+ allErr = append(allErr, fmt.Errorf("metrics GetFooterLatency isn't called"))
+ }
+ if !getTocLatencyCalled {
+ allErr = append(allErr, fmt.Errorf("metrics GetTocLatency isn't called"))
+ }
+ if !deserializeTocLatencyCalled {
+ allErr = append(allErr, fmt.Errorf("metrics DeserializeTocLatency isn't called"))
+ }
+ return errorutil.Aggregate(allErr)
+ }
+}
+
+func digestFor(content string) string {
+ sum := sha256.Sum256([]byte(content))
+ return fmt.Sprintf("sha256:%x", sum)
+}
+
+type numTOCEntries int
+
+func (n numTOCEntries) check(t *testing.T, r *Reader) {
+ if r.toc == nil {
+ t.Fatal("nil TOC")
+ }
+ if got, want := len(r.toc.Entries), int(n); got != want {
+ t.Errorf("got %d TOC entries; want %d", got, want)
+ }
+ t.Logf("got TOC entries:")
+ for i, ent := range r.toc.Entries {
+ entj, _ := json.Marshal(ent)
+ t.Logf(" [%d]: %s\n", i, entj)
+ }
+ if t.Failed() {
+ t.FailNow()
+ }
+}
+
+func checks(s ...stargzCheck) []stargzCheck { return s }
+
+type stargzCheck interface {
+ check(t *testing.T, r *Reader)
+}
+
+type stargzCheckFn func(*testing.T, *Reader)
+
+func (f stargzCheckFn) check(t *testing.T, r *Reader) { f(t, r) }
+
+func maxDepth(max int) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ e, ok := r.Lookup("")
+ if !ok {
+ t.Fatal("root directory not found")
+ }
+ d, err := getMaxDepth(t, e, 0, 10*max)
+ if err != nil {
+ t.Errorf("failed to get max depth (wanted %d): %v", max, err)
+ return
+ }
+ if d != max {
+ t.Errorf("invalid depth %d; want %d", d, max)
+ return
+ }
+ })
+}
+
+func getMaxDepth(t *testing.T, e *TOCEntry, current, limit int) (max int, rErr error) {
+ if current > limit {
+ return -1, fmt.Errorf("walkMaxDepth: exceeds limit: current:%d > limit:%d",
+ current, limit)
+ }
+ max = current
+ e.ForeachChild(func(baseName string, ent *TOCEntry) bool {
+ t.Logf("%q(basename:%q) is child of %q\n", ent.Name, baseName, e.Name)
+ d, err := getMaxDepth(t, ent, current+1, limit)
+ if err != nil {
+ rErr = err
+ return false
+ }
+ if d > max {
+ max = d
+ }
+ return true
+ })
+ return
+}
+
+func hasFileLen(file string, wantLen int) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ for _, ent := range r.toc.Entries {
+ if ent.Name == file {
+ if ent.Type != "reg" {
+ t.Errorf("file type of %q is %q; want \"reg\"", file, ent.Type)
+ } else if ent.Size != int64(wantLen) {
+ t.Errorf("file size of %q = %d; want %d", file, ent.Size, wantLen)
+ }
+ return
+ }
+ }
+ t.Errorf("file %q not found", file)
+ })
+}
+
+func hasFileXattrs(file, name, value string) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ for _, ent := range r.toc.Entries {
+ if ent.Name == file {
+ if ent.Type != "reg" {
+ t.Errorf("file type of %q is %q; want \"reg\"", file, ent.Type)
+ }
+ if ent.Xattrs == nil {
+ t.Errorf("file %q has no xattrs", file)
+ return
+ }
+ valueFound, found := ent.Xattrs[name]
+ if !found {
+ t.Errorf("file %q has no xattr %q", file, name)
+ return
+ }
+ if string(valueFound) != value {
+ t.Errorf("file %q has xattr %q with value %q instead of %q", file, name, valueFound, value)
+ }
+
+ return
+ }
+ }
+ t.Errorf("file %q not found", file)
+ })
+}
+
+func hasFileDigest(file string, digest string) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ ent, ok := r.Lookup(file)
+ if !ok {
+ t.Fatalf("didn't find TOCEntry for file %q", file)
+ }
+ if ent.Digest != digest {
+ t.Fatalf("Digest(%q) = %q, want %q", file, ent.Digest, digest)
+ }
+ })
+}
+
+func hasFileContentsRange(file string, offset int, want string) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ f, err := r.OpenFile(file)
+ if err != nil {
+ t.Fatal(err)
+ }
+ got := make([]byte, len(want))
+ n, err := f.ReadAt(got, int64(offset))
+ if err != nil {
+ t.Fatalf("ReadAt(len %d, offset %d) = %v, %v", len(got), offset, n, err)
+ }
+ if string(got) != want {
+ t.Fatalf("ReadAt(len %d, offset %d) = %q, want %q", len(got), offset, got, want)
+ }
+ })
+}
+
+func hasChunkEntries(file string, wantChunks int) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ ent, ok := r.Lookup(file)
+ if !ok {
+ t.Fatalf("no file for %q", file)
+ }
+ if ent.Type != "reg" {
+ t.Fatalf("file %q has unexpected type %q; want reg", file, ent.Type)
+ }
+ chunks := r.getChunks(ent)
+ if len(chunks) != wantChunks {
+ t.Errorf("len(r.getChunks(%q)) = %d; want %d", file, len(chunks), wantChunks)
+ return
+ }
+ f := chunks[0]
+
+ var gotChunks []*TOCEntry
+ var last *TOCEntry
+ for off := int64(0); off < f.Size; off++ {
+ e, ok := r.ChunkEntryForOffset(file, off)
+ if !ok {
+ t.Errorf("no ChunkEntryForOffset at %d", off)
+ return
+ }
+ if last != e {
+ gotChunks = append(gotChunks, e)
+ last = e
+ }
+ }
+ if !reflect.DeepEqual(chunks, gotChunks) {
+ t.Errorf("gotChunks=%d, want=%d; contents mismatch", len(gotChunks), wantChunks)
+ }
+
+ // And verify the NextOffset
+ for i := 0; i < len(gotChunks)-1; i++ {
+ ci := gotChunks[i]
+ cnext := gotChunks[i+1]
+ if ci.NextOffset() != cnext.Offset {
+ t.Errorf("chunk %d NextOffset %d != next chunk's Offset of %d", i, ci.NextOffset(), cnext.Offset)
+ }
+ }
+ })
+}
+
+func entryHasChildren(dir string, want ...string) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ want := append([]string(nil), want...)
+ var got []string
+ ent, ok := r.Lookup(dir)
+ if !ok {
+ t.Fatalf("didn't find TOCEntry for dir node %q", dir)
+ }
+ for baseName := range ent.children {
+ got = append(got, baseName)
+ }
+ sort.Strings(got)
+ sort.Strings(want)
+ if !reflect.DeepEqual(got, want) {
+ t.Errorf("children of %q = %q; want %q", dir, got, want)
+ }
+ })
+}
+
+func hasDir(file string) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ for _, ent := range r.toc.Entries {
+ if ent.Name == cleanEntryName(file) {
+ if ent.Type != "dir" {
+ t.Errorf("file type of %q is %q; want \"dir\"", file, ent.Type)
+ }
+ return
+ }
+ }
+ t.Errorf("directory %q not found", file)
+ })
+}
+
+func hasDirLinkCount(file string, count int) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ for _, ent := range r.toc.Entries {
+ if ent.Name == cleanEntryName(file) {
+ if ent.Type != "dir" {
+ t.Errorf("file type of %q is %q; want \"dir\"", file, ent.Type)
+ return
+ }
+ if ent.NumLink != count {
+ t.Errorf("link count of %q = %d; want %d", file, ent.NumLink, count)
+ }
+ return
+ }
+ }
+ t.Errorf("directory %q not found", file)
+ })
+}
+
+func hasMode(file string, mode os.FileMode) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ for _, ent := range r.toc.Entries {
+ if ent.Name == cleanEntryName(file) {
+ if ent.Stat().Mode() != mode {
+ t.Errorf("invalid mode: got %v; want %v", ent.Stat().Mode(), mode)
+ return
+ }
+ return
+ }
+ }
+ t.Errorf("file %q not found", file)
+ })
+}
+
+func hasSymlink(file, target string) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ for _, ent := range r.toc.Entries {
+ if ent.Name == file {
+ if ent.Type != "symlink" {
+ t.Errorf("file type of %q is %q; want \"symlink\"", file, ent.Type)
+ } else if ent.LinkName != target {
+ t.Errorf("link target of symlink %q is %q; want %q", file, ent.LinkName, target)
+ }
+ return
+ }
+ }
+ t.Errorf("symlink %q not found", file)
+ })
+}
+
+func lookupMatch(name string, want *TOCEntry) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ e, ok := r.Lookup(name)
+ if !ok {
+ t.Fatalf("failed to Lookup entry %q", name)
+ }
+ if !reflect.DeepEqual(e, want) {
+ t.Errorf("entry %q mismatch.\n got: %+v\nwant: %+v\n", name, e, want)
+ }
+
+ })
+}
+
+func hasEntryOwner(entry string, owner owner) stargzCheck {
+ return stargzCheckFn(func(t *testing.T, r *Reader) {
+ ent, ok := r.Lookup(strings.TrimSuffix(entry, "/"))
+ if !ok {
+ t.Errorf("entry %q not found", entry)
+ return
+ }
+ if ent.UID != owner.uid || ent.GID != owner.gid {
+ t.Errorf("entry %q has invalid owner (uid:%d, gid:%d) instead of (uid:%d, gid:%d)", entry, ent.UID, ent.GID, owner.uid, owner.gid)
+ return
+ }
+ })
+}
+
+func tarOf(s ...tarEntry) []tarEntry { return s }
+
+type tarEntry interface {
+ appendTar(tw *tar.Writer, prefix string) error
+}
+
+type tarEntryFunc func(*tar.Writer, string) error
+
+func (f tarEntryFunc) appendTar(tw *tar.Writer, prefix string) error { return f(tw, prefix) }
+
+func buildTar(t *testing.T, ents []tarEntry, prefix string) (r io.Reader, cancel func()) {
+ pr, pw := io.Pipe()
+ go func() {
+ tw := tar.NewWriter(pw)
+ for _, ent := range ents {
+ if err := ent.appendTar(tw, prefix); err != nil {
+ t.Errorf("building input tar: %v", err)
+ pw.Close()
+ return
+ }
+ }
+ if err := tw.Close(); err != nil {
+ t.Errorf("closing write of input tar: %v", err)
+ }
+ pw.Close()
+ }()
+ return pr, func() { go pr.Close(); go pw.Close() }
+}
+
+func buildTarStatic(t *testing.T, ents []tarEntry, prefix string) *io.SectionReader {
+ buf := new(bytes.Buffer)
+ tw := tar.NewWriter(buf)
+ for _, ent := range ents {
+ if err := ent.appendTar(tw, prefix); err != nil {
+ t.Fatalf("building input tar: %v", err)
+ }
+ }
+ if err := tw.Close(); err != nil {
+ t.Errorf("closing write of input tar: %v", err)
+ }
+ data := buf.Bytes()
+ return io.NewSectionReader(bytes.NewReader(data), 0, int64(len(data)))
+}
+
+func dir(name string, opts ...interface{}) tarEntry {
+ return tarEntryFunc(func(tw *tar.Writer, prefix string) error {
+ var o owner
+ mode := os.FileMode(0755)
+ for _, opt := range opts {
+ switch v := opt.(type) {
+ case owner:
+ o = v
+ case os.FileMode:
+ mode = v
+ default:
+ return errors.New("unsupported opt")
+ }
+ }
+ if !strings.HasSuffix(name, "/") {
+ panic(fmt.Sprintf("missing trailing slash in dir %q ", name))
+ }
+ tm, err := fileModeToTarMode(mode)
+ if err != nil {
+ return err
+ }
+ return tw.WriteHeader(&tar.Header{
+ Typeflag: tar.TypeDir,
+ Name: prefix + name,
+ Mode: tm,
+ Uid: o.uid,
+ Gid: o.gid,
+ })
+ })
+}
+
+// xAttr are extended attributes to set on test files created with the file func.
+type xAttr map[string]string
+
+// owner is owner ot set on test files and directories with the file and dir functions.
+type owner struct {
+ uid int
+ gid int
+}
+
+func file(name, contents string, opts ...interface{}) tarEntry {
+ return tarEntryFunc(func(tw *tar.Writer, prefix string) error {
+ var xattrs xAttr
+ var o owner
+ mode := os.FileMode(0644)
+ for _, opt := range opts {
+ switch v := opt.(type) {
+ case xAttr:
+ xattrs = v
+ case owner:
+ o = v
+ case os.FileMode:
+ mode = v
+ default:
+ return errors.New("unsupported opt")
+ }
+ }
+ if strings.HasSuffix(name, "/") {
+ return fmt.Errorf("bogus trailing slash in file %q", name)
+ }
+ tm, err := fileModeToTarMode(mode)
+ if err != nil {
+ return err
+ }
+ if err := tw.WriteHeader(&tar.Header{
+ Typeflag: tar.TypeReg,
+ Name: prefix + name,
+ Mode: tm,
+ Xattrs: xattrs,
+ Size: int64(len(contents)),
+ Uid: o.uid,
+ Gid: o.gid,
+ }); err != nil {
+ return err
+ }
+ _, err = io.WriteString(tw, contents)
+ return err
+ })
+}
+
+func symlink(name, target string) tarEntry {
+ return tarEntryFunc(func(tw *tar.Writer, prefix string) error {
+ return tw.WriteHeader(&tar.Header{
+ Typeflag: tar.TypeSymlink,
+ Name: prefix + name,
+ Linkname: target,
+ Mode: 0644,
+ })
+ })
+}
+
+func link(name string, linkname string) tarEntry {
+ now := time.Now()
+ return tarEntryFunc(func(w *tar.Writer, prefix string) error {
+ return w.WriteHeader(&tar.Header{
+ Typeflag: tar.TypeLink,
+ Name: prefix + name,
+ Linkname: linkname,
+ ModTime: now,
+ AccessTime: now,
+ ChangeTime: now,
+ })
+ })
+}
+
+func chardev(name string, major, minor int64) tarEntry {
+ now := time.Now()
+ return tarEntryFunc(func(w *tar.Writer, prefix string) error {
+ return w.WriteHeader(&tar.Header{
+ Typeflag: tar.TypeChar,
+ Name: prefix + name,
+ Devmajor: major,
+ Devminor: minor,
+ ModTime: now,
+ AccessTime: now,
+ ChangeTime: now,
+ })
+ })
+}
+
+func blockdev(name string, major, minor int64) tarEntry {
+ now := time.Now()
+ return tarEntryFunc(func(w *tar.Writer, prefix string) error {
+ return w.WriteHeader(&tar.Header{
+ Typeflag: tar.TypeBlock,
+ Name: prefix + name,
+ Devmajor: major,
+ Devminor: minor,
+ ModTime: now,
+ AccessTime: now,
+ ChangeTime: now,
+ })
+ })
+}
+func fifo(name string) tarEntry {
+ now := time.Now()
+ return tarEntryFunc(func(w *tar.Writer, prefix string) error {
+ return w.WriteHeader(&tar.Header{
+ Typeflag: tar.TypeFifo,
+ Name: prefix + name,
+ ModTime: now,
+ AccessTime: now,
+ ChangeTime: now,
+ })
+ })
+}
+
+func prefetchLandmark() tarEntry {
+ return tarEntryFunc(func(w *tar.Writer, prefix string) error {
+ if err := w.WriteHeader(&tar.Header{
+ Name: PrefetchLandmark,
+ Typeflag: tar.TypeReg,
+ Size: int64(len([]byte{landmarkContents})),
+ }); err != nil {
+ return err
+ }
+ contents := []byte{landmarkContents}
+ if _, err := io.CopyN(w, bytes.NewReader(contents), int64(len(contents))); err != nil {
+ return err
+ }
+ return nil
+ })
+}
+
+func noPrefetchLandmark() tarEntry {
+ return tarEntryFunc(func(w *tar.Writer, prefix string) error {
+ if err := w.WriteHeader(&tar.Header{
+ Name: NoPrefetchLandmark,
+ Typeflag: tar.TypeReg,
+ Size: int64(len([]byte{landmarkContents})),
+ }); err != nil {
+ return err
+ }
+ contents := []byte{landmarkContents}
+ if _, err := io.CopyN(w, bytes.NewReader(contents), int64(len(contents))); err != nil {
+ return err
+ }
+ return nil
+ })
+}
+
+func regDigest(t *testing.T, name string, contentStr string, digestMap map[string]digest.Digest) tarEntry {
+ if digestMap == nil {
+ t.Fatalf("digest map mustn't be nil")
+ }
+ content := []byte(contentStr)
+
+ var n int64
+ for n < int64(len(content)) {
+ size := int64(chunkSize)
+ remain := int64(len(content)) - n
+ if remain < size {
+ size = remain
+ }
+ dgstr := digest.Canonical.Digester()
+ if _, err := io.CopyN(dgstr.Hash(), bytes.NewReader(content[n:n+size]), size); err != nil {
+ t.Fatalf("failed to calculate digest of %q (name=%q,offset=%d,size=%d)",
+ string(content[n:n+size]), name, n, size)
+ }
+ digestMap[chunkID(name, n, size)] = dgstr.Digest()
+ n += size
+ }
+
+ return tarEntryFunc(func(w *tar.Writer, prefix string) error {
+ if err := w.WriteHeader(&tar.Header{
+ Typeflag: tar.TypeReg,
+ Name: prefix + name,
+ Size: int64(len(content)),
+ }); err != nil {
+ return err
+ }
+ if _, err := io.CopyN(w, bytes.NewReader(content), int64(len(content))); err != nil {
+ return err
+ }
+ return nil
+ })
+}
+
+func fileModeToTarMode(mode os.FileMode) (int64, error) {
+ h, err := tar.FileInfoHeader(fileInfoOnlyMode(mode), "")
+ if err != nil {
+ return 0, err
+ }
+ return h.Mode, nil
+}
+
+// fileInfoOnlyMode is os.FileMode that populates only file mode.
+type fileInfoOnlyMode os.FileMode
+
+func (f fileInfoOnlyMode) Name() string { return "" }
+func (f fileInfoOnlyMode) Size() int64 { return 0 }
+func (f fileInfoOnlyMode) Mode() os.FileMode { return os.FileMode(f) }
+func (f fileInfoOnlyMode) ModTime() time.Time { return time.Now() }
+func (f fileInfoOnlyMode) IsDir() bool { return os.FileMode(f).IsDir() }
+func (f fileInfoOnlyMode) Sys() interface{} { return nil }
diff --git a/vendor/github.com/containerd/stargz-snapshotter/estargz/types.go b/vendor/github.com/containerd/stargz-snapshotter/estargz/types.go
new file mode 100644
index 000000000..1b1075a64
--- /dev/null
+++ b/vendor/github.com/containerd/stargz-snapshotter/estargz/types.go
@@ -0,0 +1,314 @@
+/*
+ Copyright The containerd Authors.
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+*/
+
+/*
+ Copyright 2019 The Go Authors. All rights reserved.
+ Use of this source code is governed by a BSD-style
+ license that can be found in the LICENSE file.
+*/
+
+package estargz
+
+import (
+ "archive/tar"
+ "hash"
+ "io"
+ "os"
+ "path"
+ "time"
+
+ digest "github.com/opencontainers/go-digest"
+)
+
+const (
+ // TOCTarName is the name of the JSON file in the tar archive in the
+ // table of contents gzip stream.
+ TOCTarName = "stargz.index.json"
+
+ // FooterSize is the number of bytes in the footer
+ //
+ // The footer is an empty gzip stream with no compression and an Extra
+ // header of the form "%016xSTARGZ", where the 64 bit hex-encoded
+ // number is the offset to the gzip stream of JSON TOC.
+ //
+ // 51 comes from:
+ //
+ // 10 bytes gzip header
+ // 2 bytes XLEN (length of Extra field) = 26 (4 bytes header + 16 hex digits + len("STARGZ"))
+ // 2 bytes Extra: SI1 = 'S', SI2 = 'G'
+ // 2 bytes Extra: LEN = 22 (16 hex digits + len("STARGZ"))
+ // 22 bytes Extra: subfield = fmt.Sprintf("%016xSTARGZ", offsetOfTOC)
+ // 5 bytes flate header
+ // 8 bytes gzip footer
+ // (End of the eStargz blob)
+ //
+ // NOTE: For Extra fields, subfield IDs SI1='S' SI2='G' is used for eStargz.
+ FooterSize = 51
+
+ // legacyFooterSize is the number of bytes in the legacy stargz footer.
+ //
+ // 47 comes from:
+ //
+ // 10 byte gzip header +
+ // 2 byte (LE16) length of extra, encoding 22 (16 hex digits + len("STARGZ")) == "\x16\x00" +
+ // 22 bytes of extra (fmt.Sprintf("%016xSTARGZ", tocGzipOffset))
+ // 5 byte flate header
+ // 8 byte gzip footer (two little endian uint32s: digest, size)
+ legacyFooterSize = 47
+
+ // TOCJSONDigestAnnotation is an annotation for an image layer. This stores the
+ // digest of the TOC JSON.
+ // This annotation is valid only when it is specified in `.[]layers.annotations`
+ // of an image manifest.
+ TOCJSONDigestAnnotation = "containerd.io/snapshot/stargz/toc.digest"
+
+ // StoreUncompressedSizeAnnotation is an additional annotation key for eStargz to enable lazy
+ // pulling on containers/storage. Stargz Store is required to expose the layer's uncompressed size
+ // to the runtime but current OCI image doesn't ship this information by default. So we store this
+ // to the special annotation.
+ StoreUncompressedSizeAnnotation = "io.containers.estargz.uncompressed-size"
+
+ // PrefetchLandmark is a file entry which indicates the end position of
+ // prefetch in the stargz file.
+ PrefetchLandmark = ".prefetch.landmark"
+
+ // NoPrefetchLandmark is a file entry which indicates that no prefetch should
+ // occur in the stargz file.
+ NoPrefetchLandmark = ".no.prefetch.landmark"
+
+ landmarkContents = 0xf
+)
+
+// JTOC is the JSON-serialized table of contents index of the files in the stargz file.
+type JTOC struct {
+ Version int `json:"version"`
+ Entries []*TOCEntry `json:"entries"`
+}
+
+// TOCEntry is an entry in the stargz file's TOC (Table of Contents).
+type TOCEntry struct {
+ // Name is the tar entry's name. It is the complete path
+ // stored in the tar file, not just the base name.
+ Name string `json:"name"`
+
+ // Type is one of "dir", "reg", "symlink", "hardlink", "char",
+ // "block", "fifo", or "chunk".
+ // The "chunk" type is used for regular file data chunks past the first
+ // TOCEntry; the 2nd chunk and on have only Type ("chunk"), Offset,
+ // ChunkOffset, and ChunkSize populated.
+ Type string `json:"type"`
+
+ // Size, for regular files, is the logical size of the file.
+ Size int64 `json:"size,omitempty"`
+
+ // ModTime3339 is the modification time of the tar entry. Empty
+ // means zero or unknown. Otherwise it's in UTC RFC3339
+ // format. Use the ModTime method to access the time.Time value.
+ ModTime3339 string `json:"modtime,omitempty"`
+ modTime time.Time
+
+ // LinkName, for symlinks and hardlinks, is the link target.
+ LinkName string `json:"linkName,omitempty"`
+
+ // Mode is the permission and mode bits.
+ Mode int64 `json:"mode,omitempty"`
+
+ // UID is the user ID of the owner.
+ UID int `json:"uid,omitempty"`
+
+ // GID is the group ID of the owner.
+ GID int `json:"gid,omitempty"`
+
+ // Uname is the username of the owner.
+ //
+ // In the serialized JSON, this field may only be present for
+ // the first entry with the same UID.
+ Uname string `json:"userName,omitempty"`
+
+ // Gname is the group name of the owner.
+ //
+ // In the serialized JSON, this field may only be present for
+ // the first entry with the same GID.
+ Gname string `json:"groupName,omitempty"`
+
+ // Offset, for regular files, provides the offset in the
+ // stargz file to the file's data bytes. See ChunkOffset and
+ // ChunkSize.
+ Offset int64 `json:"offset,omitempty"`
+
+ nextOffset int64 // the Offset of the next entry with a non-zero Offset
+
+ // DevMajor is the major device number for "char" and "block" types.
+ DevMajor int `json:"devMajor,omitempty"`
+
+ // DevMinor is the major device number for "char" and "block" types.
+ DevMinor int `json:"devMinor,omitempty"`
+
+ // NumLink is the number of entry names pointing to this entry.
+ // Zero means one name references this entry.
+ NumLink int
+
+ // Xattrs are the extended attribute for the entry.
+ Xattrs map[string][]byte `json:"xattrs,omitempty"`
+
+ // Digest stores the OCI checksum for regular files payload.
+ // It has the form "sha256:abcdef01234....".
+ Digest string `json:"digest,omitempty"`
+
+ // ChunkOffset is non-zero if this is a chunk of a large,
+ // regular file. If so, the Offset is where the gzip header of
+ // ChunkSize bytes at ChunkOffset in Name begin.
+ //
+ // In serialized form, a "chunkSize" JSON field of zero means
+ // that the chunk goes to the end of the file. After reading
+ // from the stargz TOC, though, the ChunkSize is initialized
+ // to a non-zero file for when Type is either "reg" or
+ // "chunk".
+ ChunkOffset int64 `json:"chunkOffset,omitempty"`
+ ChunkSize int64 `json:"chunkSize,omitempty"`
+
+ // ChunkDigest stores an OCI digest of the chunk. This must be formed
+ // as "sha256:0123abcd...".
+ ChunkDigest string `json:"chunkDigest,omitempty"`
+
+ children map[string]*TOCEntry
+}
+
+// ModTime returns the entry's modification time.
+func (e *TOCEntry) ModTime() time.Time { return e.modTime }
+
+// NextOffset returns the position (relative to the start of the
+// stargz file) of the next gzip boundary after e.Offset.
+func (e *TOCEntry) NextOffset() int64 { return e.nextOffset }
+
+func (e *TOCEntry) addChild(baseName string, child *TOCEntry) {
+ if e.children == nil {
+ e.children = make(map[string]*TOCEntry)
+ }
+ if child.Type == "dir" {
+ e.NumLink++ // Entry ".." in the subdirectory links to this directory
+ }
+ e.children[baseName] = child
+}
+
+// isDataType reports whether TOCEntry is a regular file or chunk (something that
+// contains regular file data).
+func (e *TOCEntry) isDataType() bool { return e.Type == "reg" || e.Type == "chunk" }
+
+// Stat returns a FileInfo value representing e.
+func (e *TOCEntry) Stat() os.FileInfo { return fileInfo{e} }
+
+// ForeachChild calls f for each child item. If f returns false, iteration ends.
+// If e is not a directory, f is not called.
+func (e *TOCEntry) ForeachChild(f func(baseName string, ent *TOCEntry) bool) {
+ for name, ent := range e.children {
+ if !f(name, ent) {
+ return
+ }
+ }
+}
+
+// LookupChild returns the directory e's child by its base name.
+func (e *TOCEntry) LookupChild(baseName string) (child *TOCEntry, ok bool) {
+ child, ok = e.children[baseName]
+ return
+}
+
+// fileInfo implements os.FileInfo using the wrapped *TOCEntry.
+type fileInfo struct{ e *TOCEntry }
+
+var _ os.FileInfo = fileInfo{}
+
+func (fi fileInfo) Name() string { return path.Base(fi.e.Name) }
+func (fi fileInfo) IsDir() bool { return fi.e.Type == "dir" }
+func (fi fileInfo) Size() int64 { return fi.e.Size }
+func (fi fileInfo) ModTime() time.Time { return fi.e.ModTime() }
+func (fi fileInfo) Sys() interface{} { return fi.e }
+func (fi fileInfo) Mode() (m os.FileMode) {
+ // TOCEntry.Mode is tar.Header.Mode so we can understand the these bits using `tar` pkg.
+ m = (&tar.Header{Mode: fi.e.Mode}).FileInfo().Mode() &
+ (os.ModePerm | os.ModeSetuid | os.ModeSetgid | os.ModeSticky)
+ switch fi.e.Type {
+ case "dir":
+ m |= os.ModeDir
+ case "symlink":
+ m |= os.ModeSymlink
+ case "char":
+ m |= os.ModeDevice | os.ModeCharDevice
+ case "block":
+ m |= os.ModeDevice
+ case "fifo":
+ m |= os.ModeNamedPipe
+ }
+ return m
+}
+
+// TOCEntryVerifier holds verifiers that are usable for verifying chunks contained
+// in a eStargz blob.
+type TOCEntryVerifier interface {
+
+ // Verifier provides a content verifier that can be used for verifying the
+ // contents of the specified TOCEntry.
+ Verifier(ce *TOCEntry) (digest.Verifier, error)
+}
+
+// Compression provides the compression helper to be used creating and parsing eStargz.
+// This package provides gzip-based Compression by default, but any compression
+// algorithm (e.g. zstd) can be used as long as it implements Compression.
+type Compression interface {
+ Compressor
+ Decompressor
+}
+
+// Compressor represents the helper mothods to be used for creating eStargz.
+type Compressor interface {
+ // Writer returns WriteCloser to be used for writing a chunk to eStargz.
+ // Everytime a chunk is written, the WriteCloser is closed and Writer is
+ // called again for writing the next chunk.
+ Writer(w io.Writer) (io.WriteCloser, error)
+
+ // WriteTOCAndFooter is called to write JTOC to the passed Writer.
+ // diffHash calculates the DiffID (uncompressed sha256 hash) of the blob
+ // WriteTOCAndFooter can optionally write anything that affects DiffID calculation
+ // (e.g. uncompressed TOC JSON).
+ //
+ // This function returns tocDgst that represents the digest of TOC that will be used
+ // to verify this blob when it's parsed.
+ WriteTOCAndFooter(w io.Writer, off int64, toc *JTOC, diffHash hash.Hash) (tocDgst digest.Digest, err error)
+}
+
+// Deompressor represents the helper mothods to be used for parsing eStargz.
+type Decompressor interface {
+ // Reader returns ReadCloser to be used for decompressing file payload.
+ Reader(r io.Reader) (io.ReadCloser, error)
+
+ // FooterSize returns the size of the footer of this blob.
+ FooterSize() int64
+
+ // ParseFooter parses the footer and returns the offset and (compressed) size of TOC.
+ //
+ // Here, tocSize is optional. If tocSize <= 0, it's by default the size of the range
+ // from tocOffset until the beginning of the footer (blob size - tocOff - FooterSize).
+ ParseFooter(p []byte) (tocOffset, tocSize int64, err error)
+
+ // ParseTOC parses TOC from the passed reader. The reader provides the partial contents
+ // of the underlying blob that has the range specified by ParseFooter method.
+ //
+ // This function returns tocDgst that represents the digest of TOC that will be used
+ // to verify this blob. This must match to the value returned from
+ // Compressor.WriteTOCAndFooter that is used when creating this blob.
+ ParseTOC(r io.Reader) (toc *JTOC, tocDgst digest.Digest, err error)
+}