package packfile import ( "bytes" "compress/zlib" "encoding/binary" "fmt" "io" "io/ioutil" "gopkg.in/src-d/go-git.v4/core" ) var ( // ErrEmptyPackfile is returned by ReadHeader when no data is found in the packfile ErrEmptyPackfile = NewError("empty packfile") // ErrBadSignature is returned by ReadHeader when the signature in the packfile is incorrect. ErrBadSignature = NewError("malformed pack file signature") // ErrUnsupportedVersion is returned by ReadHeader when the packfile version is // different than VersionSupported. ErrUnsupportedVersion = NewError("unsupported packfile version") // ErrSeekNotSupported returned if seek is not support ErrSeekNotSupported = NewError("not seek support") ) const ( // VersionSupported is the packfile version supported by this parser. VersionSupported uint32 = 2 ) // ObjectHeader contains the information related to the object, this information // is collected from the previous bytes to the content of the object. type ObjectHeader struct { Type core.ObjectType Offset int64 Length int64 Reference core.Hash OffsetReference int64 } // A Parser is a collection of functions to read and process data form a packfile. // Values from this type are not zero-value safe. See the NewParser function bellow. type Scanner struct { r *byteReadSeeker // pendingObject is used to detect if an object has been read, or still // is waiting to be read pendingObject *ObjectHeader } // NewParser returns a new Parser that reads from the packfile represented by r. func NewScannerFromReader(r io.Reader) *Scanner { s := &trackableReader{Reader: r} return NewScanner(s) } func NewScanner(r io.ReadSeeker) *Scanner { s := &byteReadSeeker{r} return &Scanner{r: s} } // Header reads the whole packfile header (signature, version and object count). // It returns the version and the object count and performs checks on the // validity of the signature and the version fields. func (s *Scanner) Header() (version, objects uint32, err error) { sig, err := s.readSignature() if err != nil { if err == io.EOF { err = ErrEmptyPackfile } return } if !s.isValidSignature(sig) { err = ErrBadSignature return } version, err = s.readVersion() if err != nil { return } if !s.isSupportedVersion(version) { err = ErrUnsupportedVersion.AddDetails("%d", version) return } objects, err = s.readCount() return } // readSignature reads an returns the signature field in the packfile. func (s *Scanner) readSignature() ([]byte, error) { var sig = make([]byte, 4) if _, err := io.ReadFull(s.r, sig); err != nil { return []byte{}, err } return sig, nil } // isValidSignature returns if sig is a valid packfile signature. func (s *Scanner) isValidSignature(sig []byte) bool { return bytes.Equal(sig, []byte{'P', 'A', 'C', 'K'}) } // readVersion reads and returns the version field of a packfile. func (s *Scanner) readVersion() (uint32, error) { return s.readInt32() } // isSupportedVersion returns whether version v is supported by the parser. // The current supported version is VersionSupported, defined above. func (s *Scanner) isSupportedVersion(v uint32) bool { return v == VersionSupported } // readCount reads and returns the count of objects field of a packfile. func (s *Scanner) readCount() (uint32, error) { return s.readInt32() } // ReadInt32 reads 4 bytes and returns them as a Big Endian int32. func (s *Scanner) readInt32() (uint32, error) { var v uint32 if err := binary.Read(s.r, binary.BigEndian, &v); err != nil { return 0, err } return v, nil } // NextObjectHeader returns the ObjectHeader for the next object in the reader func (s *Scanner) NextObjectHeader() (*ObjectHeader, error) { if err := s.discardObjectIfNeeded(); err != nil { return nil, err } h := &ObjectHeader{} s.pendingObject = h var err error h.Offset, err = s.r.Seek(0, io.SeekCurrent) if err != nil { return nil, err } h.Type, h.Length, err = s.readObjectTypeAndLength() if err != nil { return nil, err } switch h.Type { case core.OFSDeltaObject: no, err := s.readNegativeOffset() if err != nil { return nil, err } h.OffsetReference = h.Offset + no case core.REFDeltaObject: var err error h.Reference, err = s.readHash() if err != nil { return nil, err } } return h, nil } func (s *Scanner) discardObjectIfNeeded() error { if s.pendingObject == nil { return nil } h := s.pendingObject n, err := s.NextObject(ioutil.Discard) if err != nil { return err } if n != h.Length { return fmt.Errorf( "error discarding object, discarded %d, expected %d", n, h.Length, ) } return nil } // ReadObjectTypeAndLength reads and returns the object type and the // length field from an object entry in a packfile. func (s *Scanner) readObjectTypeAndLength() (core.ObjectType, int64, error) { t, c, err := s.readType() if err != nil { return t, 0, err } l, err := s.readLength(c) return t, l, err } func (s *Scanner) readType() (core.ObjectType, byte, error) { var c byte var err error if c, err = s.r.ReadByte(); err != nil { return core.ObjectType(0), 0, err } typ := parseType(c) return typ, c, nil } // the length is codified in the last 4 bits of the first byte and in // the last 7 bits of subsequent bytes. Last byte has a 0 MSB. func (s *Scanner) readLength(first byte) (int64, error) { length := int64(first & maskFirstLength) c := first shift := firstLengthBits var err error for moreBytesInLength(c) { if c, err = s.r.ReadByte(); err != nil { return 0, err } length += int64(c&maskLength) << shift shift += lengthBits } return length, nil } func (s *Scanner) NextObject(w io.Writer) (written int64, err error) { s.pendingObject = nil return s.copyObject(w) } // ReadRegularObject reads and write a non-deltified object // from it zlib stream in an object entry in the packfile. func (s *Scanner) copyObject(w io.Writer) (int64, error) { zr, err := zlib.NewReader(s.r) if err != nil { if err != zlib.ErrHeader { return -1, fmt.Errorf("zlib reading error: %s", err) } } defer func() { closeErr := zr.Close() if err == nil { err = closeErr } }() return io.Copy(w, zr) } func (s *Scanner) IsSeekable() bool { _, ok := s.r.ReadSeeker.(*trackableReader) return !ok } // Seek sets a new offset from start, returns the old position before the change func (s *Scanner) Seek(offset int64) (previous int64, err error) { previous, err = s.r.Seek(0, io.SeekCurrent) if err != nil { return -1, err } _, err = s.r.Seek(offset, io.SeekStart) return previous, err } func (s *Scanner) Checksum() (core.Hash, error) { err := s.discardObjectIfNeeded() if err != nil { return core.ZeroHash, err } return s.readHash() } // ReadHash reads a hash. func (s *Scanner) readHash() (core.Hash, error) { var h core.Hash if _, err := io.ReadFull(s.r, h[:]); err != nil { return core.ZeroHash, err } return h, nil } // ReadNegativeOffset reads and returns an offset from a OFS DELTA // object entry in a packfile. OFS DELTA offsets are specified in Git // VLQ special format: // // Ordinary VLQ has some redundancies, example: the number 358 can be // encoded as the 2-octet VLQ 0x8166 or the 3-octet VLQ 0x808166 or the // 4-octet VLQ 0x80808166 and so forth. // // To avoid these redundancies, the VLQ format used in Git removes this // prepending redundancy and extends the representable range of shorter // VLQs by adding an offset to VLQs of 2 or more octets in such a way // that the lowest possible value for such an (N+1)-octet VLQ becomes // exactly one more than the maximum possible value for an N-octet VLQ. // In particular, since a 1-octet VLQ can store a maximum value of 127, // the minimum 2-octet VLQ (0x8000) is assigned the value 128 instead of // 0. Conversely, the maximum value of such a 2-octet VLQ (0xff7f) is // 16511 instead of just 16383. Similarly, the minimum 3-octet VLQ // (0x808000) has a value of 16512 instead of zero, which means // that the maximum 3-octet VLQ (0xffff7f) is 2113663 instead of // just 2097151. And so forth. // // This is how the offset is saved in C: // // dheader[pos] = ofs & 127; // while (ofs >>= 7) // dheader[--pos] = 128 | (--ofs & 127); // func (s *Scanner) readNegativeOffset() (int64, error) { var c byte var err error if c, err = s.r.ReadByte(); err != nil { return 0, err } var offset = int64(c & maskLength) for moreBytesInLength(c) { offset++ if c, err = s.r.ReadByte(); err != nil { return 0, err } offset = (offset << lengthBits) + int64(c&maskLength) } return -offset, nil } func (s *Scanner) Close() error { _, err := io.Copy(ioutil.Discard, s.r) return err } func moreBytesInLength(c byte) bool { return c&maskContinue > 0 } var ( maskContinue = uint8(128) // 1000 0000 maskType = uint8(112) // 0111 0000 maskFirstLength = uint8(15) // 0000 1111 firstLengthBits = uint8(4) // the first byte has 4 bits to store the length maskLength = uint8(127) // 0111 1111 lengthBits = uint8(7) // subsequent bytes has 7 bits to store the length ) func parseType(b byte) core.ObjectType { return core.ObjectType((b & maskType) >> firstLengthBits) } type trackableReader struct { io.Reader count int64 } // Read reads up to len(p) bytes into p. func (r *trackableReader) Read(p []byte) (n int, err error) { n, err = r.Reader.Read(p) r.count += int64(n) return } // Seek only supports io.SeekCurrent, any other operation fails func (r *trackableReader) Seek(offset int64, whence int) (int64, error) { if whence != io.SeekCurrent { return -1, ErrSeekNotSupported } return r.count, nil } type byteReadSeeker struct { io.ReadSeeker } // ReadByte reads a byte. func (r *byteReadSeeker) ReadByte() (byte, error) { var p [1]byte _, err := r.ReadSeeker.Read(p[:]) return p[0], err }