Basic support for reading 7z archives

Close mholt#53

7z.go

@@ -0,0 +1,119 @@
+package archiver
+
+import (
+	"bytes"
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"io/fs"
+	"log"
+	"path"
+	"strings"
+
+	"github.com/bodgit/sevenzip"
+)
+
+func init() {
+	RegisterFormat(SevenZip{})
+
+	// looks like the sevenzip package registers a lot of decompressors for us automatically:
+	// https://github.com/bodgit/sevenzip/blob/46c5197162c784318b98b9a3f80289a9aa1ca51a/register.go#L38-L61
+}
+
+type SevenZip struct {
+	// If true, errors encountered during reading or writing
+	// a file within an archive will be logged and the
+	// operation will continue on remaining files.
+	ContinueOnError bool
+
+	// The password, if dealing with an encrypted archive.
+	Password string
+}
+
+func (z SevenZip) Name() string { return ".7z" }
+
+func (z SevenZip) Match(filename string, stream io.Reader) (MatchResult, error) {
+	var mr MatchResult
+
+	// match filename
+	if strings.Contains(strings.ToLower(filename), z.Name()) {
+		mr.ByName = true
+	}
+
+	// match file header
+	buf, err := readAtMost(stream, len(sevenZipHeader))
+	if err != nil {
+		return mr, err
+	}
+	mr.ByStream = bytes.Equal(buf, sevenZipHeader)
+
+	return mr, nil
+}
+
+// Extract extracts files from z, implementing the Extractor interface. Uniquely, however,
+// sourceArchive must be an io.ReaderAt and io.Seeker, which are oddly disjoint interfaces
+// from io.Reader which is what the method signature requires. We chose this signature for
+// the interface because we figure you can Read() from anything you can ReadAt() or Seek()
+// with. Due to the nature of the zip archive format, if sourceArchive is not an io.Seeker
+// and io.ReaderAt, an error is returned.
+func (z SevenZip) Extract(ctx context.Context, sourceArchive io.Reader, pathsInArchive []string, handleFile FileHandler) error {
+	sra, ok := sourceArchive.(seekReaderAt)
+	if !ok {
+		return fmt.Errorf("input type must be an io.ReaderAt and io.Seeker because of zip format constraints")
+	}
+
+	size, err := streamSizeBySeeking(sra)
+	if err != nil {
+		return fmt.Errorf("determining stream size: %w", err)
+	}
+
+	zr, err := sevenzip.NewReaderWithPassword(sra, size, z.Password)
+	if err != nil {
+		return err
+	}
+
+	// important to initialize to non-nil, empty value due to how fileIsIncluded works
+	skipDirs := skipList{}
+
+	for i, f := range zr.File {
+		if err := ctx.Err(); err != nil {
+			return err // honor context cancellation
+		}
+
+		if !fileIsIncluded(pathsInArchive, f.Name) {
+			continue
+		}
+		if fileIsIncluded(skipDirs, f.Name) {
+			continue
+		}
+
+		file := File{
+			FileInfo:      f.FileInfo(),
+			Header:        f.FileHeader,
+			NameInArchive: f.Name,
+			Open:          func() (io.ReadCloser, error) { return f.Open() },
+		}
+
+		err := handleFile(ctx, file)
+		if errors.Is(err, fs.SkipDir) {
+			// if a directory, skip this path; if a file, skip the folder path
+			dirPath := f.Name
+			if !file.IsDir() {
+				dirPath = path.Dir(f.Name) + "/"
+			}
+			skipDirs.add(dirPath)
+		} else if err != nil {
+			if z.ContinueOnError {
+				log.Printf("[ERROR] %s: %v", f.Name, err)
+				continue
+			}
+			return fmt.Errorf("handling file %d: %s: %w", i, f.Name, err)
+		}
+	}
+
+	return nil
+}
+
+// https://py7zr.readthedocs.io/en/latest/archive_format.html#signature
+var sevenZipHeader = []byte("7z\xBC\xAF\x27\x1C")

README.md

@@ -19,6 +19,7 @@ Introducing **Archiver 4.0** - a cross-platform, multi-format archive utility an
 - Walk or traverse into archive files
 - Extract only specific files from archives
 - Insert (append) into .tar files
+- Read from password-protected 7-Zip files
 - Numerous archive and compression formats supported
 - Extensible (add more formats just by registering them)
 - Cross-platform, static binary
@@ -45,6 +46,7 @@ Introducing **Archiver 4.0** - a cross-platform, multi-format archive utility an
 - .zip
 - .tar (including any compressed variants like .tar.gz)
 - .rar (read-only)
+- .7z (read-only)
 
 Tar files can optionally be compressed using any compression format.
 

go.mod

@@ -5,15 +5,25 @@ go 1.18
 require (
 	github.com/andybalholm/brotli v1.0.4
 	github.com/dsnet/compress v0.0.1
-	github.com/klauspost/compress v1.15.5
+	github.com/klauspost/compress v1.15.9
 	github.com/klauspost/pgzip v1.2.5
 	github.com/nwaples/rardecode/v2 v2.0.0-beta.2
 	github.com/therootcompany/xz v1.0.1
 	github.com/ulikunitz/xz v0.5.10
 )
 
 require (
+	github.com/bodgit/sevenzip v1.3.0
 	github.com/golang/snappy v0.0.4
-	github.com/pierrec/lz4/v4 v4.1.14
+	github.com/pierrec/lz4/v4 v4.1.15
 	golang.org/x/text v0.3.7
 )
+
+require (
+	github.com/bodgit/plumbing v1.2.0 // indirect
+	github.com/bodgit/windows v1.0.0 // indirect
+	github.com/connesc/cipherio v0.2.1 // indirect
+	github.com/hashicorp/errwrap v1.0.0 // indirect
+	github.com/hashicorp/go-multierror v1.1.1 // indirect
+	go4.org v0.0.0-20200411211856-f5505b9728dd // indirect
+)