summaryrefslogtreecommitdiffstats
path: root/vendor/github.com/klauspost/compress/zstd/decodeheader.go
blob: f6a240970d467c2755d12fca02db67eae73d4bfb (plain) (blame)
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
// Copyright 2020+ Klaus Post. All rights reserved.
// License information can be found in the LICENSE file.

package zstd

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

// HeaderMaxSize is the maximum size of a Frame and Block Header.
// If less is sent to Header.Decode it *may* still contain enough information.
const HeaderMaxSize = 14 + 3

// Header contains information about the first frame and block within that.
type Header struct {
	// SingleSegment specifies whether the data is to be decompressed into a
	// single contiguous memory segment.
	// It implies that WindowSize is invalid and that FrameContentSize is valid.
	SingleSegment bool

	// WindowSize is the window of data to keep while decoding.
	// Will only be set if SingleSegment is false.
	WindowSize uint64

	// Dictionary ID.
	// If 0, no dictionary.
	DictionaryID uint32

	// HasFCS specifies whether FrameContentSize has a valid value.
	HasFCS bool

	// FrameContentSize is the expected uncompressed size of the entire frame.
	FrameContentSize uint64

	// Skippable will be true if the frame is meant to be skipped.
	// This implies that FirstBlock.OK is false.
	Skippable bool

	// SkippableID is the user-specific ID for the skippable frame.
	// Valid values are between 0 to 15, inclusive.
	SkippableID int

	// SkippableSize is the length of the user data to skip following
	// the header.
	SkippableSize uint32

	// HeaderSize is the raw size of the frame header.
	//
	// For normal frames, it includes the size of the magic number and
	// the size of the header (per section 3.1.1.1).
	// It does not include the size for any data blocks (section 3.1.1.2) nor
	// the size for the trailing content checksum.
	//
	// For skippable frames, this counts the size of the magic number
	// along with the size of the size field of the payload.
	// It does not include the size of the skippable payload itself.
	// The total frame size is the HeaderSize plus the SkippableSize.
	HeaderSize int

	// First block information.
	FirstBlock struct {
		// OK will be set if first block could be decoded.
		OK bool

		// Is this the last block of a frame?
		Last bool

		// Is the data compressed?
		// If true CompressedSize will be populated.
		// Unfortunately DecompressedSize cannot be determined
		// without decoding the blocks.
		Compressed bool

		// DecompressedSize is the expected decompressed size of the block.
		// Will be 0 if it cannot be determined.
		DecompressedSize int

		// CompressedSize of the data in the block.
		// Does not include the block header.
		// Will be equal to DecompressedSize if not Compressed.
		CompressedSize int
	}

	// If set there is a checksum present for the block content.
	// The checksum field at the end is always 4 bytes long.
	HasCheckSum bool
}

// Decode the header from the beginning of the stream.
// This will decode the frame header and the first block header if enough bytes are provided.
// It is recommended to provide at least HeaderMaxSize bytes.
// If the frame header cannot be read an error will be returned.
// If there isn't enough input, io.ErrUnexpectedEOF is returned.
// The FirstBlock.OK will indicate if enough information was available to decode the first block header.
func (h *Header) Decode(in []byte) error {
	*h = Header{}
	if len(in) < 4 {
		return io.ErrUnexpectedEOF
	}
	h.HeaderSize += 4
	b, in := in[:4], in[4:]
	if string(b) != frameMagic {
		if string(b[1:4]) != skippableFrameMagic || b[0]&0xf0 != 0x50 {
			return ErrMagicMismatch
		}
		if len(in) < 4 {
			return io.ErrUnexpectedEOF
		}
		h.HeaderSize += 4
		h.Skippable = true
		h.SkippableID = int(b[0] & 0xf)
		h.SkippableSize = binary.LittleEndian.Uint32(in)
		return nil
	}

	// Read Window_Descriptor
	// https://github.com/facebook/zstd/blob/dev/doc/zstd_compression_format.md#window_descriptor
	if len(in) < 1 {
		return io.ErrUnexpectedEOF
	}
	fhd, in := in[0], in[1:]
	h.HeaderSize++
	h.SingleSegment = fhd&(1<<5) != 0
	h.HasCheckSum = fhd&(1<<2) != 0
	if fhd&(1<<3) != 0 {
		return errors.New("reserved bit set on frame header")
	}

	if !h.SingleSegment {
		if len(in) < 1 {
			return io.ErrUnexpectedEOF
		}
		var wd byte
		wd, in = in[0], in[1:]
		h.HeaderSize++
		windowLog := 10 + (wd >> 3)
		windowBase := uint64(1) << windowLog
		windowAdd := (windowBase / 8) * uint64(wd&0x7)
		h.WindowSize = windowBase + windowAdd
	}

	// Read Dictionary_ID
	// https://github.com/facebook/zstd/blob/dev/doc/zstd_compression_format.md#dictionary_id
	if size := fhd & 3; size != 0 {
		if size == 3 {
			size = 4
		}
		if len(in) < int(size) {
			return io.ErrUnexpectedEOF
		}
		b, in = in[:size], in[size:]
		h.HeaderSize += int(size)
		switch len(b) {
		case 1:
			h.DictionaryID = uint32(b[0])
		case 2:
			h.DictionaryID = uint32(b[0]) | (uint32(b[1]) << 8)
		case 4:
			h.DictionaryID = uint32(b[0]) | (uint32(b[1]) << 8) | (uint32(b[2]) << 16) | (uint32(b[3]) << 24)
		}
	}

	// Read Frame_Content_Size
	// https://github.com/facebook/zstd/blob/dev/doc/zstd_compression_format.md#frame_content_size
	var fcsSize int
	v := fhd >> 6
	switch v {
	case 0:
		if h.SingleSegment {
			fcsSize = 1
		}
	default:
		fcsSize = 1 << v
	}

	if fcsSize > 0 {
		h.HasFCS = true
		if len(in) < fcsSize {
			return io.ErrUnexpectedEOF
		}
		b, in = in[:fcsSize], in[fcsSize:]
		h.HeaderSize += int(fcsSize)
		switch len(b) {
		case 1:
			h.FrameContentSize = uint64(b[0])
		case 2:
			// When FCS_Field_Size is 2, the offset of 256 is added.
			h.FrameContentSize = uint64(b[0]) | (uint64(b[1]) << 8) + 256
		case 4:
			h.FrameContentSize = uint64(b[0]) | (uint64(b[1]) << 8) | (uint64(b[2]) << 16) | (uint64(b[3]) << 24)
		case 8:
			d1 := uint32(b[0]) | (uint32(b[1]) << 8) | (uint32(b[2]) << 16) | (uint32(b[3]) << 24)
			d2 := uint32(b[4]) | (uint32(b[5]) << 8) | (uint32(b[6]) << 16) | (uint32(b[7]) << 24)
			h.FrameContentSize = uint64(d1) | (uint64(d2) << 32)
		}
	}

	// Frame Header done, we will not fail from now on.
	if len(in) < 3 {
		return nil
	}
	tmp := in[:3]
	bh := uint32(tmp[0]) | (uint32(tmp[1]) << 8) | (uint32(tmp[2]) << 16)
	h.FirstBlock.Last = bh&1 != 0
	blockType := blockType((bh >> 1) & 3)
	// find size.
	cSize := int(bh >> 3)
	switch blockType {
	case blockTypeReserved:
		return nil
	case blockTypeRLE:
		h.FirstBlock.Compressed = true
		h.FirstBlock.DecompressedSize = cSize
		h.FirstBlock.CompressedSize = 1
	case blockTypeCompressed:
		h.FirstBlock.Compressed = true
		h.FirstBlock.CompressedSize = cSize
	case blockTypeRaw:
		h.FirstBlock.DecompressedSize = cSize
		h.FirstBlock.CompressedSize = cSize
	default:
		panic("Invalid block type")
	}

	h.FirstBlock.OK = true
	return nil
}