Make TarFilter more useful

There are a few changes:
* Callers can specify if they want recursive behaviour or not
* All file listings to tar are sent on stdin, to handle long lists better
* We can pass in a list of filenames which will be created as empty
  files in the tarball

This is exactly what we want for the creation of layer tarballs given
a container fs, a set of files to add and a set of whiteout files to create.

archive.go

@@ -80,21 +80,73 @@ func (compression *Compression) Extension() string {
 // Tar creates an archive from the directory at `path`, and returns it as a
 // stream of bytes.
 func Tar(path string, compression Compression) (io.Reader, error) {
-	return TarFilter(path, compression, nil)
+	return TarFilter(path, compression, nil, true, nil)
+}
+
+func escapeName(name string) string {
+	escaped := make([]byte,0)
+	for i, c := range []byte(name) {
+		if i == 0 && c == '/' {
+			continue
+		}
+		// all printable chars except "-" which is 0x2d
+		if (0x20 <= c && c <= 0x7E) && c != 0x2d  {
+			escaped = append(escaped, c)
+		} else {
+			escaped = append(escaped, fmt.Sprintf("\\%03o", c)...)
+		}
+	}
+	return string(escaped)
 }
 
 // Tar creates an archive from the directory at `path`, only including files whose relative
 // paths are included in `filter`. If `filter` is nil, then all files are included.
-func TarFilter(path string, compression Compression, filter []string) (io.Reader, error) {
+func TarFilter(path string, compression Compression, filter []string, recursive bool, createFiles []string) (io.Reader, error) {
-	args := []string{"tar", "--numeric-owner", "-f", "-", "-C", path}
+	args := []string{"tar", "--numeric-owner", "-f", "-", "-C", path, "-T", "-",}
 	if filter == nil {
 		filter = []string{"."}
 	}
 	args = append(args, "-c"+compression.Flag())
-	for _, f := range filter {
+
-		args = append(args, f)
+	if !recursive {
+		args = append(args, "--no-recursion")
 	}
-	return CmdStream(exec.Command(args[0], args[1:]...))
+
+	files := ""
+	for _, f := range filter {
+		files = files + escapeName(f) + "\n"
+	}
+
+	tmpDir := ""
+
+	if createFiles != nil {
+		tmpDir, err := ioutil.TempDir("", "docker-tar")
+		if err != nil {
+			return nil, err
+		}
+
+		files = files + "-C" + tmpDir + "\n"
+		for _, f := range createFiles {
+			path := filepath.Join(tmpDir, f)
+			err := os.MkdirAll(filepath.Dir(path), 0600)
+			if err != nil {
+				return nil, err
+			}
+
+			if file, err := os.OpenFile(path, os.O_CREATE, 0600); err != nil {
+				return nil, err
+			} else {
+				file.Close()
+			}
+			files = files + escapeName(f) + "\n"
+		}
+	}
+
+	return CmdStream(exec.Command(args[0], args[1:]...), &files, func () {
+		if tmpDir != "" {
+			_ = os.RemoveAll(tmpDir)
+		}
+	})
 }
 
 // Untar reads a stream of bytes from `archive`, parses it as a tar archive,
@@ -141,7 +193,7 @@ func Untar(archive io.Reader, path string) error {
 // TarUntar aborts and returns the error.
 func TarUntar(src string, filter []string, dst string) error {
 	utils.Debugf("TarUntar(%s %s %s)", src, filter, dst)
-	archive, err := TarFilter(src, Uncompressed, filter)
+	archive, err := TarFilter(src, Uncompressed, filter, true, nil)
 	if err != nil {
 		return err
 	}
@@ -228,7 +280,18 @@ func CopyFileWithTar(src, dst string) error {
 // CmdStream executes a command, and returns its stdout as a stream.
 // If the command fails to run or doesn't complete successfully, an error
 // will be returned, including anything written on stderr.
-func CmdStream(cmd *exec.Cmd) (io.Reader, error) {
+func CmdStream(cmd *exec.Cmd, input *string, atEnd func()) (io.Reader, error) {
+	if input != nil {
+		stdin, err := cmd.StdinPipe()
+		if err != nil {
+			return nil, err
+		}
+		// Write stdin if any
+		go func() {
+			_, _ = stdin.Write([]byte(*input))
+			stdin.Close()
+		}()
+	}
 	stdout, err := cmd.StdoutPipe()
 	if err != nil {
 		return nil, err
@@ -259,6 +322,9 @@ func CmdStream(cmd *exec.Cmd) (io.Reader, error) {
 		} else {
 			pipeW.Close()
 		}
+		if atEnd != nil {
+			atEnd()
+		}
 	}()
 	// Run the command and return the pipe
 	if err := cmd.Start(); err != nil {

archive_test.go

@@ -14,7 +14,7 @@ import (
 
 func TestCmdStreamLargeStderr(t *testing.T) {
 	cmd := exec.Command("/bin/sh", "-c", "dd if=/dev/zero bs=1k count=1000 of=/dev/stderr; echo hello")
-	out, err := CmdStream(cmd)
+	out, err := CmdStream(cmd, nil, nil)
 	if err != nil {
 		t.Fatalf("Failed to start command: %s", err)
 	}
@@ -35,7 +35,7 @@ func TestCmdStreamLargeStderr(t *testing.T) {
 
 func TestCmdStreamBad(t *testing.T) {
 	badCmd := exec.Command("/bin/sh", "-c", "echo hello; echo >&2 error couldn\\'t reverse the phase pulser; exit 1")
-	out, err := CmdStream(badCmd)
+	out, err := CmdStream(badCmd, nil, nil)
 	if err != nil {
 		t.Fatalf("Failed to start command: %s", err)
 	}
@@ -50,7 +50,7 @@ func TestCmdStreamBad(t *testing.T) {
 
 func TestCmdStreamGood(t *testing.T) {
 	cmd := exec.Command("/bin/sh", "-c", "echo hello; exit 0")
-	out, err := CmdStream(cmd)
+	out, err := CmdStream(cmd, nil, nil)
 	if err != nil {
 		t.Fatal(err)
 	}

container.go

@@ -1277,5 +1277,5 @@ func (container *Container) Copy(resource string) (Archive, error) {
 		filter = []string{path.Base(basePath)}
 		basePath = path.Dir(basePath)
 	}
-	return TarFilter(basePath, Uncompressed, filter)
+	return TarFilter(basePath, Uncompressed, filter, true, nil)
 }