summaryrefslogtreecommitdiff
path: root/libgo/go/compress/zlib/reader.go
blob: 78ea7043bcee353987e41b8ca210634247b75ad9 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

/*
Package zlib implements reading and writing of zlib format compressed data,
as specified in RFC 1950.

The implementation provides filters that uncompress during reading
and compress during writing.  For example, to write compressed data
to a buffer:

	var b bytes.Buffer
	w := zlib.NewWriter(&b)
	w.Write([]byte("hello, world\n"))
	w.Close()

and to read that data back:

	r, err := zlib.NewReader(&b)
	io.Copy(os.Stdout, r)
	r.Close()
*/
package zlib

import (
	"bufio"
	"compress/flate"
	"errors"
	"hash"
	"hash/adler32"
	"io"
)

const zlibDeflate = 8

var (
	// ErrChecksum is returned when reading ZLIB data that has an invalid checksum.
	ErrChecksum = errors.New("zlib: invalid checksum")
	// ErrDictionary is returned when reading ZLIB data that has an invalid dictionary.
	ErrDictionary = errors.New("zlib: invalid dictionary")
	// ErrHeader is returned when reading ZLIB data that has an invalid header.
	ErrHeader = errors.New("zlib: invalid header")
)

type reader struct {
	r            flate.Reader
	decompressor io.ReadCloser
	digest       hash.Hash32
	err          error
	scratch      [4]byte
}

// Resetter resets a ReadCloser returned by NewReader or NewReaderDict to
// to switch to a new underlying Reader. This permits reusing a ReadCloser
// instead of allocating a new one.
type Resetter interface {
	// Reset discards any buffered data and resets the Resetter as if it was
	// newly initialized with the given reader.
	Reset(r io.Reader, dict []byte) error
}

// NewReader creates a new ReadCloser.
// Reads from the returned ReadCloser read and decompress data from r.
// The implementation buffers input and may read more data than necessary from r.
// It is the caller's responsibility to call Close on the ReadCloser when done.
//
// The ReadCloser returned by NewReader also implements Resetter.
func NewReader(r io.Reader) (io.ReadCloser, error) {
	return NewReaderDict(r, nil)
}

// NewReaderDict is like NewReader but uses a preset dictionary.
// NewReaderDict ignores the dictionary if the compressed data does not refer to it.
// If the compressed data refers to a different dictionary, NewReaderDict returns ErrDictionary.
//
// The ReadCloser returned by NewReaderDict also implements Resetter.
func NewReaderDict(r io.Reader, dict []byte) (io.ReadCloser, error) {
	z := new(reader)
	err := z.Reset(r, dict)
	if err != nil {
		return nil, err
	}
	return z, nil
}

func (z *reader) Read(p []byte) (n int, err error) {
	if z.err != nil {
		return 0, z.err
	}
	if len(p) == 0 {
		return 0, nil
	}

	n, err = z.decompressor.Read(p)
	z.digest.Write(p[0:n])
	if n != 0 || err != io.EOF {
		z.err = err
		return
	}

	// Finished file; check checksum.
	if _, err := io.ReadFull(z.r, z.scratch[0:4]); err != nil {
		if err == io.EOF {
			err = io.ErrUnexpectedEOF
		}
		z.err = err
		return 0, err
	}
	// ZLIB (RFC 1950) is big-endian, unlike GZIP (RFC 1952).
	checksum := uint32(z.scratch[0])<<24 | uint32(z.scratch[1])<<16 | uint32(z.scratch[2])<<8 | uint32(z.scratch[3])
	if checksum != z.digest.Sum32() {
		z.err = ErrChecksum
		return 0, z.err
	}
	return
}

// Calling Close does not close the wrapped io.Reader originally passed to NewReader.
func (z *reader) Close() error {
	if z.err != nil {
		return z.err
	}
	z.err = z.decompressor.Close()
	return z.err
}

func (z *reader) Reset(r io.Reader, dict []byte) error {
	if fr, ok := r.(flate.Reader); ok {
		z.r = fr
	} else {
		z.r = bufio.NewReader(r)
	}
	_, err := io.ReadFull(z.r, z.scratch[0:2])
	if err != nil {
		if err == io.EOF {
			err = io.ErrUnexpectedEOF
		}
		return err
	}
	h := uint(z.scratch[0])<<8 | uint(z.scratch[1])
	if (z.scratch[0]&0x0f != zlibDeflate) || (h%31 != 0) {
		return ErrHeader
	}
	haveDict := z.scratch[1]&0x20 != 0
	if haveDict {
		_, err = io.ReadFull(z.r, z.scratch[0:4])
		if err != nil {
			if err == io.EOF {
				err = io.ErrUnexpectedEOF
			}
			return err
		}
		checksum := uint32(z.scratch[0])<<24 | uint32(z.scratch[1])<<16 | uint32(z.scratch[2])<<8 | uint32(z.scratch[3])
		if checksum != adler32.Checksum(dict) {
			return ErrDictionary
		}
	}
	if z.decompressor == nil {
		if haveDict {
			z.decompressor = flate.NewReaderDict(z.r, dict)
		} else {
			z.decompressor = flate.NewReader(z.r)
		}
	} else {
		z.decompressor.(flate.Resetter).Reset(z.r, dict)
	}
	z.digest = adler32.New()
	return nil
}