blob: f1e04b172c579922f19c0cf5e0ec4e10e29420f6 [file] [log] [blame]
Scott Baker2c1c4822019-10-16 11:02:41 -07001// Copyright 2011 The Snappy-Go Authors. All rights reserved.
2// Use of this source code is governed by a BSD-style
3// license that can be found in the LICENSE file.
4
5package snappy
6
7import (
8 "encoding/binary"
9 "errors"
10 "io"
11)
12
13var (
14 // ErrCorrupt reports that the input is invalid.
15 ErrCorrupt = errors.New("snappy: corrupt input")
16 // ErrTooLarge reports that the uncompressed length is too large.
17 ErrTooLarge = errors.New("snappy: decoded block is too large")
18 // ErrUnsupported reports that the input isn't supported.
19 ErrUnsupported = errors.New("snappy: unsupported input")
20
21 errUnsupportedLiteralLength = errors.New("snappy: unsupported literal length")
22)
23
24// DecodedLen returns the length of the decoded block.
25func DecodedLen(src []byte) (int, error) {
26 v, _, err := decodedLen(src)
27 return v, err
28}
29
30// decodedLen returns the length of the decoded block and the number of bytes
31// that the length header occupied.
32func decodedLen(src []byte) (blockLen, headerLen int, err error) {
33 v, n := binary.Uvarint(src)
34 if n <= 0 || v > 0xffffffff {
35 return 0, 0, ErrCorrupt
36 }
37
38 const wordSize = 32 << (^uint(0) >> 32 & 1)
39 if wordSize == 32 && v > 0x7fffffff {
40 return 0, 0, ErrTooLarge
41 }
42 return int(v), n, nil
43}
44
45const (
46 decodeErrCodeCorrupt = 1
47 decodeErrCodeUnsupportedLiteralLength = 2
48)
49
50// Decode returns the decoded form of src. The returned slice may be a sub-
51// slice of dst if dst was large enough to hold the entire decoded block.
52// Otherwise, a newly allocated slice will be returned.
53//
54// The dst and src must not overlap. It is valid to pass a nil dst.
khenaidoo26721882021-08-11 17:42:52 -040055//
56// Decode handles the Snappy block format, not the Snappy stream format.
Scott Baker2c1c4822019-10-16 11:02:41 -070057func Decode(dst, src []byte) ([]byte, error) {
58 dLen, s, err := decodedLen(src)
59 if err != nil {
60 return nil, err
61 }
62 if dLen <= len(dst) {
63 dst = dst[:dLen]
64 } else {
65 dst = make([]byte, dLen)
66 }
67 switch decode(dst, src[s:]) {
68 case 0:
69 return dst, nil
70 case decodeErrCodeUnsupportedLiteralLength:
71 return nil, errUnsupportedLiteralLength
72 }
73 return nil, ErrCorrupt
74}
75
76// NewReader returns a new Reader that decompresses from r, using the framing
77// format described at
78// https://github.com/google/snappy/blob/master/framing_format.txt
79func NewReader(r io.Reader) *Reader {
80 return &Reader{
81 r: r,
82 decoded: make([]byte, maxBlockSize),
83 buf: make([]byte, maxEncodedLenOfMaxBlockSize+checksumSize),
84 }
85}
86
87// Reader is an io.Reader that can read Snappy-compressed bytes.
khenaidoo26721882021-08-11 17:42:52 -040088//
89// Reader handles the Snappy stream format, not the Snappy block format.
Scott Baker2c1c4822019-10-16 11:02:41 -070090type Reader struct {
91 r io.Reader
92 err error
93 decoded []byte
94 buf []byte
95 // decoded[i:j] contains decoded bytes that have not yet been passed on.
96 i, j int
97 readHeader bool
98}
99
100// Reset discards any buffered data, resets all state, and switches the Snappy
101// reader to read from r. This permits reusing a Reader rather than allocating
102// a new one.
103func (r *Reader) Reset(reader io.Reader) {
104 r.r = reader
105 r.err = nil
106 r.i = 0
107 r.j = 0
108 r.readHeader = false
109}
110
111func (r *Reader) readFull(p []byte, allowEOF bool) (ok bool) {
112 if _, r.err = io.ReadFull(r.r, p); r.err != nil {
113 if r.err == io.ErrUnexpectedEOF || (r.err == io.EOF && !allowEOF) {
114 r.err = ErrCorrupt
115 }
116 return false
117 }
118 return true
119}
120
121// Read satisfies the io.Reader interface.
122func (r *Reader) Read(p []byte) (int, error) {
123 if r.err != nil {
124 return 0, r.err
125 }
126 for {
127 if r.i < r.j {
128 n := copy(p, r.decoded[r.i:r.j])
129 r.i += n
130 return n, nil
131 }
132 if !r.readFull(r.buf[:4], true) {
133 return 0, r.err
134 }
135 chunkType := r.buf[0]
136 if !r.readHeader {
137 if chunkType != chunkTypeStreamIdentifier {
138 r.err = ErrCorrupt
139 return 0, r.err
140 }
141 r.readHeader = true
142 }
143 chunkLen := int(r.buf[1]) | int(r.buf[2])<<8 | int(r.buf[3])<<16
144 if chunkLen > len(r.buf) {
145 r.err = ErrUnsupported
146 return 0, r.err
147 }
148
149 // The chunk types are specified at
150 // https://github.com/google/snappy/blob/master/framing_format.txt
151 switch chunkType {
152 case chunkTypeCompressedData:
153 // Section 4.2. Compressed data (chunk type 0x00).
154 if chunkLen < checksumSize {
155 r.err = ErrCorrupt
156 return 0, r.err
157 }
158 buf := r.buf[:chunkLen]
159 if !r.readFull(buf, false) {
160 return 0, r.err
161 }
162 checksum := uint32(buf[0]) | uint32(buf[1])<<8 | uint32(buf[2])<<16 | uint32(buf[3])<<24
163 buf = buf[checksumSize:]
164
165 n, err := DecodedLen(buf)
166 if err != nil {
167 r.err = err
168 return 0, r.err
169 }
170 if n > len(r.decoded) {
171 r.err = ErrCorrupt
172 return 0, r.err
173 }
174 if _, err := Decode(r.decoded, buf); err != nil {
175 r.err = err
176 return 0, r.err
177 }
178 if crc(r.decoded[:n]) != checksum {
179 r.err = ErrCorrupt
180 return 0, r.err
181 }
182 r.i, r.j = 0, n
183 continue
184
185 case chunkTypeUncompressedData:
186 // Section 4.3. Uncompressed data (chunk type 0x01).
187 if chunkLen < checksumSize {
188 r.err = ErrCorrupt
189 return 0, r.err
190 }
191 buf := r.buf[:checksumSize]
192 if !r.readFull(buf, false) {
193 return 0, r.err
194 }
195 checksum := uint32(buf[0]) | uint32(buf[1])<<8 | uint32(buf[2])<<16 | uint32(buf[3])<<24
196 // Read directly into r.decoded instead of via r.buf.
197 n := chunkLen - checksumSize
198 if n > len(r.decoded) {
199 r.err = ErrCorrupt
200 return 0, r.err
201 }
202 if !r.readFull(r.decoded[:n], false) {
203 return 0, r.err
204 }
205 if crc(r.decoded[:n]) != checksum {
206 r.err = ErrCorrupt
207 return 0, r.err
208 }
209 r.i, r.j = 0, n
210 continue
211
212 case chunkTypeStreamIdentifier:
213 // Section 4.1. Stream identifier (chunk type 0xff).
214 if chunkLen != len(magicBody) {
215 r.err = ErrCorrupt
216 return 0, r.err
217 }
218 if !r.readFull(r.buf[:len(magicBody)], false) {
219 return 0, r.err
220 }
221 for i := 0; i < len(magicBody); i++ {
222 if r.buf[i] != magicBody[i] {
223 r.err = ErrCorrupt
224 return 0, r.err
225 }
226 }
227 continue
228 }
229
230 if chunkType <= 0x7f {
231 // Section 4.5. Reserved unskippable chunks (chunk types 0x02-0x7f).
232 r.err = ErrUnsupported
233 return 0, r.err
234 }
235 // Section 4.4 Padding (chunk type 0xfe).
236 // Section 4.6. Reserved skippable chunks (chunk types 0x80-0xfd).
237 if !r.readFull(r.buf[:chunkLen], false) {
238 return 0, r.err
239 }
240 }
241}