File: decode.go

package info (click to toggle)
golang-github-golang-snappy 0.0+git20160529.d9eb7a3-3
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, buster, buster-backports, experimental, sid
  • size: 272 kB
  • sloc: asm: 587; cpp: 59; makefile: 11
file content (237 lines) | stat: -rw-r--r-- 6,013 bytes parent folder | download | duplicates (11)
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
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
// Copyright 2011 The Snappy-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 snappy

import (
	"encoding/binary"
	"errors"
	"io"
)

var (
	// ErrCorrupt reports that the input is invalid.
	ErrCorrupt = errors.New("snappy: corrupt input")
	// ErrTooLarge reports that the uncompressed length is too large.
	ErrTooLarge = errors.New("snappy: decoded block is too large")
	// ErrUnsupported reports that the input isn't supported.
	ErrUnsupported = errors.New("snappy: unsupported input")

	errUnsupportedLiteralLength = errors.New("snappy: unsupported literal length")
)

// DecodedLen returns the length of the decoded block.
func DecodedLen(src []byte) (int, error) {
	v, _, err := decodedLen(src)
	return v, err
}

// decodedLen returns the length of the decoded block and the number of bytes
// that the length header occupied.
func decodedLen(src []byte) (blockLen, headerLen int, err error) {
	v, n := binary.Uvarint(src)
	if n <= 0 || v > 0xffffffff {
		return 0, 0, ErrCorrupt
	}

	const wordSize = 32 << (^uint(0) >> 32 & 1)
	if wordSize == 32 && v > 0x7fffffff {
		return 0, 0, ErrTooLarge
	}
	return int(v), n, nil
}

const (
	decodeErrCodeCorrupt                  = 1
	decodeErrCodeUnsupportedLiteralLength = 2
)

// Decode returns the decoded form of src. The returned slice may be a sub-
// slice of dst if dst was large enough to hold the entire decoded block.
// Otherwise, a newly allocated slice will be returned.
//
// The dst and src must not overlap. It is valid to pass a nil dst.
func Decode(dst, src []byte) ([]byte, error) {
	dLen, s, err := decodedLen(src)
	if err != nil {
		return nil, err
	}
	if dLen <= len(dst) {
		dst = dst[:dLen]
	} else {
		dst = make([]byte, dLen)
	}
	switch decode(dst, src[s:]) {
	case 0:
		return dst, nil
	case decodeErrCodeUnsupportedLiteralLength:
		return nil, errUnsupportedLiteralLength
	}
	return nil, ErrCorrupt
}

// NewReader returns a new Reader that decompresses from r, using the framing
// format described at
// https://github.com/google/snappy/blob/master/framing_format.txt
func NewReader(r io.Reader) *Reader {
	return &Reader{
		r:       r,
		decoded: make([]byte, maxBlockSize),
		buf:     make([]byte, maxEncodedLenOfMaxBlockSize+checksumSize),
	}
}

// Reader is an io.Reader that can read Snappy-compressed bytes.
type Reader struct {
	r       io.Reader
	err     error
	decoded []byte
	buf     []byte
	// decoded[i:j] contains decoded bytes that have not yet been passed on.
	i, j       int
	readHeader bool
}

// Reset discards any buffered data, resets all state, and switches the Snappy
// reader to read from r. This permits reusing a Reader rather than allocating
// a new one.
func (r *Reader) Reset(reader io.Reader) {
	r.r = reader
	r.err = nil
	r.i = 0
	r.j = 0
	r.readHeader = false
}

func (r *Reader) readFull(p []byte, allowEOF bool) (ok bool) {
	if _, r.err = io.ReadFull(r.r, p); r.err != nil {
		if r.err == io.ErrUnexpectedEOF || (r.err == io.EOF && !allowEOF) {
			r.err = ErrCorrupt
		}
		return false
	}
	return true
}

// Read satisfies the io.Reader interface.
func (r *Reader) Read(p []byte) (int, error) {
	if r.err != nil {
		return 0, r.err
	}
	for {
		if r.i < r.j {
			n := copy(p, r.decoded[r.i:r.j])
			r.i += n
			return n, nil
		}
		if !r.readFull(r.buf[:4], true) {
			return 0, r.err
		}
		chunkType := r.buf[0]
		if !r.readHeader {
			if chunkType != chunkTypeStreamIdentifier {
				r.err = ErrCorrupt
				return 0, r.err
			}
			r.readHeader = true
		}
		chunkLen := int(r.buf[1]) | int(r.buf[2])<<8 | int(r.buf[3])<<16
		if chunkLen > len(r.buf) {
			r.err = ErrUnsupported
			return 0, r.err
		}

		// The chunk types are specified at
		// https://github.com/google/snappy/blob/master/framing_format.txt
		switch chunkType {
		case chunkTypeCompressedData:
			// Section 4.2. Compressed data (chunk type 0x00).
			if chunkLen < checksumSize {
				r.err = ErrCorrupt
				return 0, r.err
			}
			buf := r.buf[:chunkLen]
			if !r.readFull(buf, false) {
				return 0, r.err
			}
			checksum := uint32(buf[0]) | uint32(buf[1])<<8 | uint32(buf[2])<<16 | uint32(buf[3])<<24
			buf = buf[checksumSize:]

			n, err := DecodedLen(buf)
			if err != nil {
				r.err = err
				return 0, r.err
			}
			if n > len(r.decoded) {
				r.err = ErrCorrupt
				return 0, r.err
			}
			if _, err := Decode(r.decoded, buf); err != nil {
				r.err = err
				return 0, r.err
			}
			if crc(r.decoded[:n]) != checksum {
				r.err = ErrCorrupt
				return 0, r.err
			}
			r.i, r.j = 0, n
			continue

		case chunkTypeUncompressedData:
			// Section 4.3. Uncompressed data (chunk type 0x01).
			if chunkLen < checksumSize {
				r.err = ErrCorrupt
				return 0, r.err
			}
			buf := r.buf[:checksumSize]
			if !r.readFull(buf, false) {
				return 0, r.err
			}
			checksum := uint32(buf[0]) | uint32(buf[1])<<8 | uint32(buf[2])<<16 | uint32(buf[3])<<24
			// Read directly into r.decoded instead of via r.buf.
			n := chunkLen - checksumSize
			if n > len(r.decoded) {
				r.err = ErrCorrupt
				return 0, r.err
			}
			if !r.readFull(r.decoded[:n], false) {
				return 0, r.err
			}
			if crc(r.decoded[:n]) != checksum {
				r.err = ErrCorrupt
				return 0, r.err
			}
			r.i, r.j = 0, n
			continue

		case chunkTypeStreamIdentifier:
			// Section 4.1. Stream identifier (chunk type 0xff).
			if chunkLen != len(magicBody) {
				r.err = ErrCorrupt
				return 0, r.err
			}
			if !r.readFull(r.buf[:len(magicBody)], false) {
				return 0, r.err
			}
			for i := 0; i < len(magicBody); i++ {
				if r.buf[i] != magicBody[i] {
					r.err = ErrCorrupt
					return 0, r.err
				}
			}
			continue
		}

		if chunkType <= 0x7f {
			// Section 4.5. Reserved unskippable chunks (chunk types 0x02-0x7f).
			r.err = ErrUnsupported
			return 0, r.err
		}
		// Section 4.4 Padding (chunk type 0xfe).
		// Section 4.6. Reserved skippable chunks (chunk types 0x80-0xfd).
		if !r.readFull(r.buf[:chunkLen], false) {
			return 0, r.err
		}
	}
}