aboutsummaryrefslogtreecommitdiffstats
path: root/vendor/github.com/klauspost/compress/internal/fuzz/helpers.go
blob: eb49d66bf6d14c6241c35c8660ce39e2ed9ed2d9 (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
//go:build go1.18
// +build go1.18

package fuzz

import (
	"archive/zip"
	"bytes"
	"encoding/binary"
	"fmt"
	"go/ast"
	"go/parser"
	"go/token"
	"io"
	"os"
	"strconv"
	"testing"
)

type InputType uint8

const (
	// TypeRaw indicates that files are raw bytes.
	TypeRaw InputType = iota
	// TypeGoFuzz indicates files are from Go Fuzzer.
	TypeGoFuzz
	// TypeOSSFuzz indicates that files are from OSS fuzzer with size before data.
	TypeOSSFuzz
)

// AddFromZip will read the supplied zip and add all as corpus for f.
// Byte slices only.
func AddFromZip(f *testing.F, filename string, t InputType, short bool) {
	file, err := os.Open(filename)
	if err != nil {
		f.Fatal(err)
	}
	fi, err := file.Stat()
	if err != nil {
		f.Fatal(err)
	}
	zr, err := zip.NewReader(file, fi.Size())
	if err != nil {
		f.Fatal(err)
	}
	for i, file := range zr.File {
		if short && i%10 != 0 {
			continue
		}
		rc, err := file.Open()
		if err != nil {
			f.Fatal(err)
		}

		b, err := io.ReadAll(rc)
		if err != nil {
			f.Fatal(err)
		}
		rc.Close()
		t := t
		if t == TypeOSSFuzz {
			t = TypeRaw // Fallback
			if len(b) >= 4 {
				sz := binary.BigEndian.Uint32(b)
				if sz <= uint32(len(b))-4 {
					f.Add(b[4 : 4+sz])
					continue
				}
			}
		}

		if bytes.HasPrefix(b, []byte("go test fuzz")) {
			t = TypeGoFuzz
		} else {
			t = TypeRaw
		}

		if t == TypeRaw {
			f.Add(b)
			continue
		}
		vals, err := unmarshalCorpusFile(b)
		if err != nil {
			f.Fatal(err)
		}
		for _, v := range vals {
			f.Add(v)
		}
	}
}

// unmarshalCorpusFile decodes corpus bytes into their respective values.
func unmarshalCorpusFile(b []byte) ([][]byte, error) {
	if len(b) == 0 {
		return nil, fmt.Errorf("cannot unmarshal empty string")
	}
	lines := bytes.Split(b, []byte("\n"))
	if len(lines) < 2 {
		return nil, fmt.Errorf("must include version and at least one value")
	}
	var vals = make([][]byte, 0, len(lines)-1)
	for _, line := range lines[1:] {
		line = bytes.TrimSpace(line)
		if len(line) == 0 {
			continue
		}
		v, err := parseCorpusValue(line)
		if err != nil {
			return nil, fmt.Errorf("malformed line %q: %v", line, err)
		}
		vals = append(vals, v)
	}
	return vals, nil
}

// parseCorpusValue
func parseCorpusValue(line []byte) ([]byte, error) {
	fs := token.NewFileSet()
	expr, err := parser.ParseExprFrom(fs, "(test)", line, 0)
	if err != nil {
		return nil, err
	}
	call, ok := expr.(*ast.CallExpr)
	if !ok {
		return nil, fmt.Errorf("expected call expression")
	}
	if len(call.Args) != 1 {
		return nil, fmt.Errorf("expected call expression with 1 argument; got %d", len(call.Args))
	}
	arg := call.Args[0]

	if arrayType, ok := call.Fun.(*ast.ArrayType); ok {
		if arrayType.Len != nil {
			return nil, fmt.Errorf("expected []byte or primitive type")
		}
		elt, ok := arrayType.Elt.(*ast.Ident)
		if !ok || elt.Name != "byte" {
			return nil, fmt.Errorf("expected []byte")
		}
		lit, ok := arg.(*ast.BasicLit)
		if !ok || lit.Kind != token.STRING {
			return nil, fmt.Errorf("string literal required for type []byte")
		}
		s, err := strconv.Unquote(lit.Value)
		if err != nil {
			return nil, err
		}
		return []byte(s), nil
	}
	return nil, fmt.Errorf("expected []byte")
}