archive/tar: convert Reader.Next to be loop based

Motivation for change:
* Recursive logic is hard to follow, since it tends to apply
things in reverse. On the other hand, the tar formats tend to
describe meta headers as affecting the next entry.
* Recursion also applies changes in the wrong order. Two test
files are attached that use multiple headers. The previous Go
behavior differs from what GNU and BSD tar do.

Change-Id: Ic1557256fc1363c5cb26570e5d0b9f65a9e57341
Reviewed-on: https://go-review.googlesource.com/14624
Run-TryBot: Joe Tsai <joetsai@digital-static.net>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>

archive/tar/reader.go

@@ -138,8 +138,6 @@ func NewReader(r io.Reader) *Reader { return &Reader{r: r} }
 //
 // io.EOF is returned at the end of the input.
 func (tr *Reader) Next() (*Header, error) {
-	var p parser
-	var hdr *Header
 	if tr.RawAccounting {
 		if tr.rawBytes == nil {
 			tr.rawBytes = bytes.NewBuffer(nil)
@@ -147,50 +145,77 @@ func (tr *Reader) Next() (*Header, error) {
 			tr.rawBytes.Reset()
 		}
 	}
-	if tr.err == nil {
-		tr.skipUnread()
-	}
+
 	if tr.err != nil {
-		return hdr, tr.err
+		return nil, tr.err
 	}
+
+	var hdr *Header
+	var extHdrs map[string]string
+
+	// Externally, Next iterates through the tar archive as if it is a series of
+	// files. Internally, the tar format often uses fake "files" to add meta
+	// data that describes the next file. These meta data "files" should not
+	// normally be visible to the outside. As such, this loop iterates through
+	// one or more "header files" until it finds a "normal file".
+loop:
+	for {
+		tr.err = tr.skipUnread()
+		if tr.err != nil {
+			return nil, tr.err
+		}
+
 		hdr = tr.readHeader()
-	if hdr == nil {
-		return hdr, tr.err
+		if tr.err != nil {
+			return nil, tr.err
 		}
-	// Check for PAX/GNU header.
+		// Check for PAX/GNU special headers and files.
 		switch hdr.Typeflag {
 		case TypeXHeader:
-		//  PAX extended header
-		headers, err := parsePAX(tr)
-		if err != nil {
-			return nil, err
-		}
-		// We actually read the whole file,
-		// but this skips alignment padding
-		tr.skipUnread()
+			extHdrs, tr.err = parsePAX(tr)
 			if tr.err != nil {
 				return nil, tr.err
 			}
-		hdr = tr.readHeader()
-		if hdr == nil {
+			continue loop // This is a meta header affecting the next header
+		case TypeGNULongName, TypeGNULongLink:
+			var realname []byte
+			realname, tr.err = ioutil.ReadAll(tr)
+			if tr.err != nil {
 				return nil, tr.err
 			}
-		mergePAX(hdr, headers)
+
+			if tr.RawAccounting {
+				if _, tr.err = tr.rawBytes.Write(realname); tr.err != nil {
+					return nil, tr.err
+				}
+			}
+
+			// Convert GNU extensions to use PAX headers.
+			if extHdrs == nil {
+				extHdrs = make(map[string]string)
+			}
+			var p parser
+			switch hdr.Typeflag {
+			case TypeGNULongName:
+				extHdrs[paxPath] = p.parseString(realname)
+			case TypeGNULongLink:
+				extHdrs[paxLinkpath] = p.parseString(realname)
+			}
+			if p.err != nil {
+				tr.err = p.err
+				return nil, tr.err
+			}
+			continue loop // This is a meta header affecting the next header
+		default:
+			mergePAX(hdr, extHdrs)
 
 			// Check for a PAX format sparse file
-		sp, err := tr.checkForGNUSparsePAXHeaders(hdr, headers)
+			sp, err := tr.checkForGNUSparsePAXHeaders(hdr, extHdrs)
 			if err != nil {
 				tr.err = err
 				return nil, err
 			}
 			if sp != nil {
-			// Sparse files do not make sense when applied to the special header
-			// types that never have a data section.
-			if isHeaderOnlyType(hdr.Typeflag) {
-				tr.err = ErrHeader
-				return nil, tr.err
-			}
-
 				// Current file is a PAX format GNU sparse file.
 				// Set the current file reader to a sparse file reader.
 				tr.curr, tr.err = newSparseFileReader(tr.curr, sp, hdr.Size)
@@ -198,63 +223,10 @@ func (tr *Reader) Next() (*Header, error) {
 					return nil, tr.err
 				}
 			}
-		return hdr, nil
-	case TypeGNULongName:
-		// We have a GNU long name header. Its contents are the real file name.
-		realname, err := ioutil.ReadAll(tr)
-		if err != nil {
-			return nil, err
+			break loop // This is a file, so stop
 		}
-		var buf []byte
-		if tr.RawAccounting {
-			if _, err = tr.rawBytes.Write(realname); err != nil {
-				return nil, err
-			}
-			buf = make([]byte, tr.rawBytes.Len())
-			copy(buf[:], tr.RawBytes())
-		}
-		hdr, err := tr.Next()
-		// since the above call to Next() resets the buffer, we need to throw the bytes over
-		if tr.RawAccounting {
-			buf = append(buf, tr.RawBytes()...)
-			if _, err = tr.rawBytes.Write(buf); err != nil {
-				return nil, err
-			}
-		}
-		hdr.Name = p.parseString(realname)
-		if p.err != nil {
-			return nil, p.err
 	}
 	return hdr, nil
-	case TypeGNULongLink:
-		// We have a GNU long link header.
-		realname, err := ioutil.ReadAll(tr)
-		if err != nil {
-			return nil, err
-		}
-		var buf []byte
-		if tr.RawAccounting {
-			if _, err = tr.rawBytes.Write(realname); err != nil {
-				return nil, err
-			}
-			buf = make([]byte, tr.rawBytes.Len())
-			copy(buf[:], tr.RawBytes())
-		}
-		hdr, err := tr.Next()
-		// since the above call to Next() resets the buffer, we need to throw the bytes over
-		if tr.RawAccounting {
-			buf = append(buf, tr.RawBytes()...)
-			if _, err = tr.rawBytes.Write(buf); err != nil {
-				return nil, err
-			}
-		}
-		hdr.Name = p.parseString(realname)
-		if p.err != nil {
-			return nil, p.err
-		}
-		return hdr, nil
-	}
-	return hdr, tr.err
 }
 
 // checkForGNUSparsePAXHeaders checks the PAX headers for GNU sparse headers. If they are found, then

archive/tar/reader_test.go

@@ -288,6 +288,30 @@ var untarTests = []*untarTest{
 			},
 		},
 	},
+	{
+		// Matches the behavior of GNU, BSD, and STAR tar utilities.
+		file: "testdata/gnu-multi-hdrs.tar",
+		headers: []*Header{
+			{
+				Name:     "GNU2/GNU2/long-path-name",
+				Linkname: "GNU4/GNU4/long-linkpath-name",
+				ModTime:  time.Unix(0, 0),
+				Typeflag: '2',
+			},
+		},
+	},
+	{
+		// Matches the behavior of GNU and BSD tar utilities.
+		file: "testdata/pax-multi-hdrs.tar",
+		headers: []*Header{
+			{
+				Name:     "bar",
+				Linkname: "PAX4/PAX4/long-linkpath-name",
+				ModTime:  time.Unix(0, 0),
+				Typeflag: '2',
+			},
+		},
+	},
 	{
 		file: "testdata/neg-size.tar",
 		err:  ErrHeader,