archive/tar: automatically promote TypeRegA

Change Reader to promote TypeRegA to TypeReg in headers, unless their
name have a trailing slash which is already promoted to TypeDir. This
will allow client code to handle just TypeReg instead both TypeReg and
TypeRegA.

Change Writer to promote TypeRegA to TypeReg or TypeDir in the headers
depending on whether the name has a trailing slash. This normalization
is motivated by the specification (in pax(1)):

   0 represents a regular file. For backwards-compatibility, a
   typeflag value of binary zero ( '\0' ) should be recognized as
   meaning a regular file when extracting files from the
   archive. Archives written with this version of the archive file
   format create regular files with a typeflag value of the
   ISO/IEC 646:1991 standard IRV '0'.

Fixes #22768.

Change-Id: I149ec55824580d446cdde5a0d7a0457ad7b03466
Reviewed-on: https://go-review.googlesource.com/85656
Reviewed-by: Joe Tsai <thebrokentoaster@gmail.com>
Run-TryBot: Joe Tsai <thebrokentoaster@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>

src/archive/tar/common.go

@@ -56,7 +56,7 @@ func (he headerError) Error() string {
 const (
 	// Type '0' indicates a regular file.
 	TypeReg  = '0'
-	TypeRegA = '\x00' // For legacy support; use TypeReg instead
+	TypeRegA = '\x00' // Deprecated: Use TypeReg instead.
 
 	// Type '1' to '6' are header-only flags and may not have a data body.
 	TypeLink    = '1' // Hard link
@@ -138,7 +138,10 @@ var basicKeys = map[string]bool{
 // should do so by creating a new Header and copying the fields
 // that they are interested in preserving.
 type Header struct {
-	Typeflag byte // Type of header entry (should be TypeReg for most files)
+	// Typeflag is the type of header entry.
+	// The zero value is automatically promoted to either TypeReg or TypeDir
+	// depending on the presence of a trailing slash in Name.
+	Typeflag byte
 
 	Name     string // Name of file entry
 	Linkname string // Target name of link (valid for TypeLink or TypeSymlink)

src/archive/tar/reader.go

@@ -131,8 +131,12 @@ loop:
 			if gnuLongLink != "" {
 				hdr.Linkname = gnuLongLink
 			}
-			if hdr.Typeflag == TypeRegA && strings.HasSuffix(hdr.Name, "/") {
-				hdr.Typeflag = TypeDir // Legacy archives use trailing slash for directories
+			if hdr.Typeflag == TypeRegA {
+				if strings.HasSuffix(hdr.Name, "/") {
+					hdr.Typeflag = TypeDir // Legacy archives use trailing slash for directories
+				} else {
+					hdr.Typeflag = TypeReg
+				}
 			}
 
 			// The extended headers may have updated the size.

src/archive/tar/reader_test.go

@@ -189,7 +189,7 @@ func TestReader(t *testing.T) {
 			Gid:      5000,
 			Size:     5,
 			ModTime:  time.Unix(1244593104, 0),
-			Typeflag: '\x00',
+			Typeflag: '0',
 		}, {
 			Name:     "small2.txt",
 			Mode:     0444,
@@ -197,7 +197,7 @@ func TestReader(t *testing.T) {
 			Gid:      5000,
 			Size:     11,
 			ModTime:  time.Unix(1244593104, 0),
-			Typeflag: '\x00',
+			Typeflag: '0',
 		}},
 	}, {
 		file: "testdata/pax.tar",
@@ -534,9 +534,10 @@ func TestReader(t *testing.T) {
 		// a buggy pre-Go1.8 tar.Writer.
 		file: "testdata/invalid-go17.tar",
 		headers: []*Header{{
-			Name:    "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/foo",
-			Uid:     010000000,
-			ModTime: time.Unix(0, 0),
+			Name:     "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/foo",
+			Uid:      010000000,
+			ModTime:  time.Unix(0, 0),
+			Typeflag: '0',
 		}},
 	}, {
 		// USTAR archive with a regular entry with non-zero device numbers.

src/archive/tar/tar_test.go

@@ -306,6 +306,7 @@ func TestRoundTrip(t *testing.T) {
 		ModTime:    time.Now().Round(time.Second),
 		PAXRecords: map[string]string{"uid": "2097152"},
 		Format:     FormatPAX,
+		Typeflag:   TypeReg,
 	}
 	if err := tw.WriteHeader(hdr); err != nil {
 		t.Fatalf("tw.WriteHeader: %v", err)

src/archive/tar/writer.go

@@ -71,6 +71,16 @@ func (tw *Writer) WriteHeader(hdr *Header) error {
 	}
 	tw.hdr = *hdr // Shallow copy of Header
 
+	// Avoid usage of the legacy TypeRegA flag, and automatically promote
+	// it to use TypeReg or TypeDir.
+	if tw.hdr.Typeflag == TypeRegA {
+		if strings.HasSuffix(tw.hdr.Name, "/") {
+			tw.hdr.Typeflag = TypeDir
+		} else {
+			tw.hdr.Typeflag = TypeReg
+		}
+	}
+
 	// Round ModTime and ignore AccessTime and ChangeTime unless
 	// the format is explicitly chosen.
 	// This ensures nominal usage of WriteHeader (without specifying the format)

src/archive/tar/writer_test.go

@@ -461,6 +461,15 @@ func TestWriter(t *testing.T) {
 			testHeader{Header{Name: strings.Repeat("123456789/", 30)}, nil},
 			testClose{nil},
 		},
+	}, {
+		// Automatically promote zero value of Typeflag depending on the name.
+		file: "testdata/file-and-dir.tar",
+		tests: []testFnc{
+			testHeader{Header{Name: "small.txt", Size: 5}, nil},
+			testWrite{"Kilts", 5, nil},
+			testHeader{Header{Name: "dir/"}, nil},
+			testClose{nil},
+		},
 	}}
 
 	equalError := func(x, y error) bool {
@@ -809,8 +818,8 @@ func TestValidTypeflagWithPAXHeader(t *testing.T) {
 		if err != nil {
 			t.Fatalf("Failed to read header: %s", err)
 		}
-		if header.Typeflag != 0 {
-			t.Fatalf("Typeflag should've been 0, found %d", header.Typeflag)
+		if header.Typeflag != TypeReg {
+			t.Fatalf("Typeflag should've been %d, found %d", TypeReg, header.Typeflag)
 		}
 	}
 }