/
strconv.go
248 lines (233 loc) · 5.21 KB
/
strconv.go
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
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
// Copyright 2009 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 reflect
import (
"unicode/utf8"
)
// errSyntax indicates that a value does not have the right syntax for the target type.
var errSyntax = badSyntax{}
type badSyntax struct{}
func (badSyntax) Error() string {
return "invalid syntax"
}
func unhex(b byte) (v rune, ok bool) {
c := rune(b)
switch {
case '0' <= c && c <= '9':
return c - '0', true
case 'a' <= c && c <= 'f':
return c - 'a' + 10, true
case 'A' <= c && c <= 'F':
return c - 'A' + 10, true
}
return
}
// unquoteChar decodes the first character or byte in the escaped string
// or character literal represented by the string s.
// It returns four values:
//
// 1) value, the decoded Unicode code point or byte value;
// 2) multibyte, a boolean indicating whether the decoded character requires a multibyte UTF-8 representation;
// 3) tail, the remainder of the string after the character; and
// 4) an error that will be nil if the character is syntactically valid.
//
// The second argument, quote, specifies the type of literal being parsed
// and therefore which escaped quote character is permitted.
// If set to a single quote, it permits the sequence \' and disallows unescaped '.
// If set to a double quote, it permits \" and disallows unescaped ".
// If set to zero, it does not permit either escape and allows both quote characters to appear unescaped.
func unquoteChar(s string, quote byte) (value rune, multibyte bool, tail string, err error) {
// easy cases
if len(s) == 0 {
err = errSyntax
return
}
switch c := s[0]; {
case c == quote && (quote == '\'' || quote == '"'):
err = errSyntax
return
case c >= utf8.RuneSelf:
r, size := utf8.DecodeRuneInString(s)
return r, true, s[size:], nil
case c != '\\':
return rune(s[0]), false, s[1:], nil
}
// hard case: c is backslash
if len(s) <= 1 {
err = errSyntax
return
}
c := s[1]
s = s[2:]
switch c {
case 'a':
value = '\a'
case 'b':
value = '\b'
case 'f':
value = '\f'
case 'n':
value = '\n'
case 'r':
value = '\r'
case 't':
value = '\t'
case 'v':
value = '\v'
case 'x', 'u', 'U':
n := 0
switch c {
case 'x':
n = 2
case 'u':
n = 4
case 'U':
n = 8
}
var v rune
if len(s) < n {
err = errSyntax
return
}
for j := 0; j < n; j++ {
x, ok := unhex(s[j])
if !ok {
err = errSyntax
return
}
v = v<<4 | x
}
s = s[n:]
if c == 'x' {
// single-byte string, possibly not UTF-8
value = v
break
}
if v > utf8.MaxRune {
err = errSyntax
return
}
value = v
multibyte = true
case '0', '1', '2', '3', '4', '5', '6', '7':
v := rune(c) - '0'
if len(s) < 2 {
err = errSyntax
return
}
for j := 0; j < 2; j++ { // one digit already; two more
x := rune(s[j]) - '0'
if x < 0 || x > 7 {
err = errSyntax
return
}
v = (v << 3) | x
}
s = s[2:]
if v > 255 {
err = errSyntax
return
}
value = v
case '\\':
value = '\\'
case '\'', '"':
if c != quote {
err = errSyntax
return
}
value = rune(c)
default:
err = errSyntax
return
}
tail = s
return
}
// unquote interprets s as a single-quoted, double-quoted,
// or backquoted Go string literal, returning the string value
// that s quotes. (If s is single-quoted, it would be a Go
// character literal; unquote returns the corresponding
// one-character string.)
func unquote(s string) (string, error) {
n := len(s)
if n < 2 {
return "", errSyntax
}
quote := s[0]
if quote != s[n-1] {
return "", errSyntax
}
s = s[1 : n-1]
if quote == '`' {
if contains(s, '`') {
return "", errSyntax
}
if contains(s, '\r') {
// -1 because we know there is at least one \r to remove.
buf := make([]byte, 0, len(s)-1)
for i := 0; i < len(s); i++ {
if s[i] != '\r' {
buf = append(buf, s[i])
}
}
return string(buf), nil
}
return s, nil
}
if quote != '"' && quote != '\'' {
return "", errSyntax
}
if contains(s, '\n') {
return "", errSyntax
}
// Is it trivial? Avoid allocation.
if !contains(s, '\\') && !contains(s, quote) {
switch quote {
case '"':
if utf8.ValidString(s) {
return s, nil
}
case '\'':
r, size := utf8.DecodeRuneInString(s)
if size == len(s) && (r != utf8.RuneError || size != 1) {
return s, nil
}
}
}
var runeTmp [utf8.UTFMax]byte
buf := make([]byte, 0, 3*len(s)/2) // Try to avoid more allocations.
for len(s) > 0 {
c, multibyte, ss, err := unquoteChar(s, quote)
if err != nil {
return "", err
}
s = ss
if c < utf8.RuneSelf || !multibyte {
buf = append(buf, byte(c))
} else {
n := utf8.EncodeRune(runeTmp[:], c)
buf = append(buf, runeTmp[:n]...)
}
if quote == '\'' && len(s) != 0 {
// single-quoted must be single character
return "", errSyntax
}
}
return string(buf), nil
}
// contains reports whether the string contains the byte c.
func contains(s string, c byte) bool {
return indexByteString(s, c) != -1
}
// Index finds the index of the first instance of the specified byte in the string.
// If the byte is not found, this returns -1.
func indexByteString(s string, c byte) int {
for i := 0; i < len(s); i++ {
if s[i] == c {
return i
}
}
return -1
}