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
123. 123
124. 124
125. 125
126. 126
127. 127
128. 128
129. 129
130. 130
131. 131
132. 132
133. 133
134. 134
135. 135
136. 136
137. 137
138. 138
139. 139
140. 140
141. 141
142. 142
143. 143
144. 144
145. 145
146. 146
147. 147
148. 148
149. 149
150. 150
151. 151
152. 152
153. 153
154. 154
155. 155
156. 156
157. 157
158. 158
159. 159
160. 160
161. 161

// Copyright 2018 The 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 text

import (
	"bytes"
	"strconv"
	"strings"
	"unicode"
	"unicode/utf16"
	"unicode/utf8"

	"google.golang.org/protobuf/internal/strs"
)

// parseStringValue parses string field token.
// This differs from parseString since the text format allows
// multiple back-to-back string literals where they are semantically treated
// as a single large string with all values concatenated.
//
// E.g., `"foo" "bar" "baz"` => "foobarbaz"
func (d *Decoder) parseStringValue() (Token, error) {
	// Note that the ending quote is sufficient to unambiguously mark the end
	// of a string. Thus, the text grammar does not require intervening
	// whitespace or control characters in-between strings.
	// Thus, the following is valid:
	//	`"foo"'bar'"baz"` => "foobarbaz"
	in0 := d.in
	var ss []string
	for len(d.in) > 0 && (d.in[0] == '"' || d.in[0] == '\'') {
		s, err := d.parseString()
		if err != nil {
			return Token{}, err
		}
		ss = append(ss, s)
	}
	// d.in already points to the end of the value at this point.
	return Token{
		kind:  Scalar,
		attrs: stringValue,
		pos:   len(d.orig) - len(in0),
		raw:   in0[:len(in0)-len(d.in)],
		str:   strings.Join(ss, ""),
	}, nil
}

// parseString parses a string value enclosed in " or '.
func (d *Decoder) parseString() (string, error) {
	in := d.in
	if len(in) == 0 {
		return "", ErrUnexpectedEOF
	}
	quote := in[0]
	in = in[1:]
	i := indexNeedEscapeInBytes(in)
	in, out := in[i:], in[:i:i] // set cap to prevent mutations
	for len(in) > 0 {
		switch r, n := utf8.DecodeRune(in); {
		case r == utf8.RuneError && n == 1:
			return "", d.newSyntaxError("invalid UTF-8 detected")
		case r == 0 || r == '\n':
			return "", d.newSyntaxError("invalid character %q in string", r)
		case r == rune(quote):
			in = in[1:]
			d.consume(len(d.in) - len(in))
			return string(out), nil
		case r == '\\':
			if len(in) < 2 {
				return "", ErrUnexpectedEOF
			}
			switch r := in[1]; r {
			case '"', '\'', '\\', '?':
				in, out = in[2:], append(out, r)
			case 'a':
				in, out = in[2:], append(out, '\a')
			case 'b':
				in, out = in[2:], append(out, '\b')
			case 'n':
				in, out = in[2:], append(out, '\n')
			case 'r':
				in, out = in[2:], append(out, '\r')
			case 't':
				in, out = in[2:], append(out, '\t')
			case 'v':
				in, out = in[2:], append(out, '\v')
			case 'f':
				in, out = in[2:], append(out, '\f')
			case '0', '1', '2', '3', '4', '5', '6', '7':
				// One, two, or three octal characters.
				n := len(in[1:]) - len(bytes.TrimLeft(in[1:], "01234567"))
				if n > 3 {
					n = 3
				}
				v, err := strconv.ParseUint(string(in[1:1+n]), 8, 8)
				if err != nil {
					return "", d.newSyntaxError("invalid octal escape code %q in string", in[:1+n])
				}
				in, out = in[1+n:], append(out, byte(v))
			case 'x':
				// One or two hexadecimal characters.
				n := len(in[2:]) - len(bytes.TrimLeft(in[2:], "0123456789abcdefABCDEF"))
				if n > 2 {
					n = 2
				}
				v, err := strconv.ParseUint(string(in[2:2+n]), 16, 8)
				if err != nil {
					return "", d.newSyntaxError("invalid hex escape code %q in string", in[:2+n])
				}
				in, out = in[2+n:], append(out, byte(v))
			case 'u', 'U':
				// Four or eight hexadecimal characters
				n := 6
				if r == 'U' {
					n = 10
				}
				if len(in) < n {
					return "", ErrUnexpectedEOF
				}
				v, err := strconv.ParseUint(string(in[2:n]), 16, 32)
				if utf8.MaxRune < v || err != nil {
					return "", d.newSyntaxError("invalid Unicode escape code %q in string", in[:n])
				}
				in = in[n:]

				r := rune(v)
				if utf16.IsSurrogate(r) {
					if len(in) < 6 {
						return "", ErrUnexpectedEOF
					}
					v, err := strconv.ParseUint(string(in[2:6]), 16, 16)
					r = utf16.DecodeRune(r, rune(v))
					if in[0] != '\\' || in[1] != 'u' || r == unicode.ReplacementChar || err != nil {
						return "", d.newSyntaxError("invalid Unicode escape code %q in string", in[:6])
					}
					in = in[6:]
				}
				out = append(out, string(r)...)
			default:
				return "", d.newSyntaxError("invalid escape code %q in string", in[:2])
			}
		default:
			i := indexNeedEscapeInBytes(in[n:])
			in, out = in[n+i:], append(out, in[:n+i]...)
		}
	}
	return "", ErrUnexpectedEOF
}

// indexNeedEscapeInString returns the index of the character that needs
// escaping. If no characters need escaping, this returns the input length.
func indexNeedEscapeInBytes(b []byte) int { return indexNeedEscapeInString(strs.UnsafeString(b)) }

// UnmarshalString returns an unescaped string given a textproto string value.
// String value needs to contain single or double quotes. This is only used by
// internal/encoding/defval package for unmarshaling bytes.
func UnmarshalString(s string) (string, error) {
	d := NewDecoder([]byte(s))
	return d.parseString()
}