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
|
package helpers
import "unicode/utf8"
const hexChars = "0123456789ABCDEF"
const firstASCII = 0x20
const lastASCII = 0x7E
const firstHighSurrogate = 0xD800
const firstLowSurrogate = 0xDC00
const lastLowSurrogate = 0xDFFF
func canPrintWithoutEscape(c rune, asciiOnly bool) bool {
if c <= lastASCII {
return c >= firstASCII && c != '\\' && c != '"'
} else {
return !asciiOnly && c != '\uFEFF' && (c < firstHighSurrogate || c > lastLowSurrogate)
}
}
func QuoteSingle(text string, asciiOnly bool) []byte {
return internalQuote(text, asciiOnly, '\'')
}
func QuoteForJSON(text string, asciiOnly bool) []byte {
return internalQuote(text, asciiOnly, '"')
}
func internalQuote(text string, asciiOnly bool, quoteChar byte) []byte {
// Estimate the required length
lenEstimate := 2
for _, c := range text {
if canPrintWithoutEscape(c, asciiOnly) {
lenEstimate += utf8.RuneLen(c)
} else {
switch c {
case '\b', '\f', '\n', '\r', '\t', '\\':
lenEstimate += 2
case '"':
if quoteChar == '"' {
lenEstimate += 2
}
case '\'':
if quoteChar == '\'' {
lenEstimate += 2
}
default:
if c <= 0xFFFF {
lenEstimate += 6
} else {
lenEstimate += 12
}
}
}
}
// Preallocate the array
bytes := make([]byte, 0, lenEstimate)
i := 0
n := len(text)
bytes = append(bytes, quoteChar)
for i < n {
c, width := DecodeWTF8Rune(text[i:])
// Fast path: a run of characters that don't need escaping
if canPrintWithoutEscape(c, asciiOnly) {
start := i
i += width
for i < n {
c, width = DecodeWTF8Rune(text[i:])
if !canPrintWithoutEscape(c, asciiOnly) {
break
}
i += width
}
bytes = append(bytes, text[start:i]...)
continue
}
switch c {
case '\b':
bytes = append(bytes, "\\b"...)
i++
case '\f':
bytes = append(bytes, "\\f"...)
i++
case '\n':
bytes = append(bytes, "\\n"...)
i++
case '\r':
bytes = append(bytes, "\\r"...)
i++
case '\t':
bytes = append(bytes, "\\t"...)
i++
case '\\':
bytes = append(bytes, "\\\\"...)
i++
case '"':
if quoteChar == '"' {
bytes = append(bytes, "\\\""...)
} else {
bytes = append(bytes, '"')
}
i++
case '\'':
if quoteChar == '\'' {
bytes = append(bytes, "\\'"...)
} else {
bytes = append(bytes, '\'')
}
i++
default:
i += width
if c <= 0xFFFF {
bytes = append(
bytes,
'\\', 'u', hexChars[c>>12], hexChars[(c>>8)&15], hexChars[(c>>4)&15], hexChars[c&15],
)
} else {
c -= 0x10000
lo := firstHighSurrogate + ((c >> 10) & 0x3FF)
hi := firstLowSurrogate + (c & 0x3FF)
bytes = append(
bytes,
'\\', 'u', hexChars[lo>>12], hexChars[(lo>>8)&15], hexChars[(lo>>4)&15], hexChars[lo&15],
'\\', 'u', hexChars[hi>>12], hexChars[(hi>>8)&15], hexChars[(hi>>4)&15], hexChars[hi&15],
)
}
}
}
return append(bytes, quoteChar)
}
|
