1. 1
2. 2
3. 3
4. 4
5. 5
6. 6
7. 7
8. 8
9. 9
10. 10
11. 11
12. 12
13. 13
14. 14
15. 15
16. 16
17. 17
18. 18
19. 19
20. 20
21. 21
22. 22
23. 23
24. 24
25. 25
26. 26
27. 27
28. 28
29. 29
30. 30
31. 31
32. 32
33. 33
34. 34
35. 35
36. 36
37. 37
38. 38
39. 39
40. 40
41. 41
42. 42
43. 43
44. 44
45. 45
46. 46
47. 47
48. 48
49. 49
50. 50
51. 51
52. 52
53. 53
54. 54
55. 55
56. 56
57. 57
58. 58
59. 59
60. 60
61. 61
62. 62
63. 63
64. 64
65. 65
66. 66
67. 67
68. 68
69. 69
70. 70
71. 71
72. 72
73. 73
74. 74
75. 75
76. 76
77. 77
78. 78
79. 79
80. 80
81. 81
82. 82
83. 83
84. 84
85. 85
86. 86
87. 87
88. 88
89. 89
90. 90
91. 91
92. 92
93. 93
94. 94
95. 95
96. 96
97. 97
98. 98
99. 99
100. 100
101. 101
102. 102
103. 103
104. 104
105. 105
106. 106
107. 107
108. 108
109. 109
110. 110
111. 111
112. 112
113. 113
114. 114
115. 115
116. 116
117. 117
118. 118
119. 119
120. 120
121. 121
122. 122

package zstd

import (
	"bytes"
	"encoding/binary"
	"errors"
	"fmt"
	"io"

	"github.com/klauspost/compress/huff0"
)

type dict struct {
	id uint32

	litEnc              *huff0.Scratch
	llDec, ofDec, mlDec sequenceDec
	//llEnc, ofEnc, mlEnc []*fseEncoder
	offsets [3]int
	content []byte
}

var dictMagic = [4]byte{0x37, 0xa4, 0x30, 0xec}

// ID returns the dictionary id or 0 if d is nil.
func (d *dict) ID() uint32 {
	if d == nil {
		return 0
	}
	return d.id
}

// DictContentSize returns the dictionary content size or 0 if d is nil.
func (d *dict) DictContentSize() int {
	if d == nil {
		return 0
	}
	return len(d.content)
}

// Load a dictionary as described in
// https://github.com/facebook/zstd/blob/master/doc/zstd_compression_format.md#dictionary-format
func loadDict(b []byte) (*dict, error) {
	// Check static field size.
	if len(b) <= 8+(3*4) {
		return nil, io.ErrUnexpectedEOF
	}
	d := dict{
		llDec: sequenceDec{fse: &fseDecoder{}},
		ofDec: sequenceDec{fse: &fseDecoder{}},
		mlDec: sequenceDec{fse: &fseDecoder{}},
	}
	if !bytes.Equal(b[:4], dictMagic[:]) {
		return nil, ErrMagicMismatch
	}
	d.id = binary.LittleEndian.Uint32(b[4:8])
	if d.id == 0 {
		return nil, errors.New("dictionaries cannot have ID 0")
	}

	// Read literal table
	var err error
	d.litEnc, b, err = huff0.ReadTable(b[8:], nil)
	if err != nil {
		return nil, err
	}
	d.litEnc.Reuse = huff0.ReusePolicyMust

	br := byteReader{
		b:   b,
		off: 0,
	}
	readDec := func(i tableIndex, dec *fseDecoder) error {
		if err := dec.readNCount(&br, uint16(maxTableSymbol[i])); err != nil {
			return err
		}
		if br.overread() {
			return io.ErrUnexpectedEOF
		}
		err = dec.transform(symbolTableX[i])
		if err != nil {
			println("Transform table error:", err)
			return err
		}
		if debugDecoder || debugEncoder {
			println("Read table ok", "symbolLen:", dec.symbolLen)
		}
		// Set decoders as predefined so they aren't reused.
		dec.preDefined = true
		return nil
	}

	if err := readDec(tableOffsets, d.ofDec.fse); err != nil {
		return nil, err
	}
	if err := readDec(tableMatchLengths, d.mlDec.fse); err != nil {
		return nil, err
	}
	if err := readDec(tableLiteralLengths, d.llDec.fse); err != nil {
		return nil, err
	}
	if br.remain() < 12 {
		return nil, io.ErrUnexpectedEOF
	}

	d.offsets[0] = int(br.Uint32())
	br.advance(4)
	d.offsets[1] = int(br.Uint32())
	br.advance(4)
	d.offsets[2] = int(br.Uint32())
	br.advance(4)
	if d.offsets[0] <= 0 || d.offsets[1] <= 0 || d.offsets[2] <= 0 {
		return nil, errors.New("invalid offset in dictionary")
	}
	d.content = make([]byte, br.remain())
	copy(d.content, br.unread())
	if d.offsets[0] > len(d.content) || d.offsets[1] > len(d.content) || d.offsets[2] > len(d.content) {
		return nil, fmt.Errorf("initial offset bigger than dictionary content size %d, offsets: %v", len(d.content), d.offsets)
	}

	return &d, nil
}