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
|
// +build !amd64,!arm64 go1.26 !go1.17 arm64,!go1.20
/*
* Copyright 2021 ByteDance Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package unquote
import (
"unicode"
"unicode/utf16"
"unicode/utf8"
"github.com/bytedance/sonic/internal/rt"
"github.com/bytedance/sonic/internal/native/types"
)
// getu4 decodes \uXXXX from the beginning of s, returning the hex value,
// or it returns -1.
func getu4(s []byte) rune {
if len(s) < 6 || s[0] != '\\' || s[1] != 'u' {
return -1
}
var r rune
for _, c := range s[2:6] {
switch {
case '0' <= c && c <= '9':
c = c - '0'
case 'a' <= c && c <= 'f':
c = c - 'a' + 10
case 'A' <= c && c <= 'F':
c = c - 'A' + 10
default:
return -1
}
r = r*16 + rune(c)
}
return r
}
// unquoteBytes is a fallback implementation copied from Go standard library
// encoding/json/decode.go. This is used when native unquote is not available.
func unquoteBytes(s []byte) (t []byte, ok bool) {
// Check for unusual characters. If there are none,
// then no unquoting is needed, so return a slice of the
// original bytes.
r := 0
for r < len(s) {
c := s[r]
if c == '\\' || c == '"' || c < ' ' {
break
}
if c < utf8.RuneSelf {
r++
continue
}
rr, size := utf8.DecodeRune(s[r:])
if rr == utf8.RuneError && size == 1 {
break
}
r += size
}
if r == len(s) {
return s, true
}
b := make([]byte, len(s)+2*utf8.UTFMax)
w := copy(b, s[0:r])
for r < len(s) {
// Out of room? Can only happen if s is full of
// malformed UTF-8 and we're replacing each
// byte with RuneError.
if w >= len(b)-2*utf8.UTFMax {
nb := make([]byte, (len(b)+utf8.UTFMax)*2)
copy(nb, b[0:w])
b = nb
}
switch c := s[r]; {
case c == '\\':
r++
if r >= len(s) {
return
}
switch s[r] {
default:
return
case '"', '\\', '/', '\'':
b[w] = s[r]
r++
w++
case 'b':
b[w] = '\b'
r++
w++
case 'f':
b[w] = '\f'
r++
w++
case 'n':
b[w] = '\n'
r++
w++
case 'r':
b[w] = '\r'
r++
w++
case 't':
b[w] = '\t'
r++
w++
case 'u':
r--
rr := getu4(s[r:])
if rr < 0 {
return
}
r += 6
if utf16.IsSurrogate(rr) {
rr1 := getu4(s[r:])
if dec := utf16.DecodeRune(rr, rr1); dec != unicode.ReplacementChar {
// A valid pair; consume.
r += 6
w += utf8.EncodeRune(b[w:], dec)
break
}
// Invalid surrogate; fall back to replacement rune.
rr = unicode.ReplacementChar
}
w += utf8.EncodeRune(b[w:], rr)
}
// Quote, control characters are invalid.
case c == '"', c < ' ':
return
// ASCII
case c < utf8.RuneSelf:
b[w] = c
r++
w++
// Coerce to well-formed UTF-8.
default:
rr, size := utf8.DecodeRune(s[r:])
r += size
w += utf8.EncodeRune(b[w:], rr)
}
}
return b[0:w], true
}
// getu4Fallback decodes a 4-byte hex sequence from the beginning of s.
// It is copied from Go standard library encoding/json.decode.go.
func getu4Fallback(s []byte) rune {
if len(s) < 6 || s[0] != '\\' || s[1] != 'u' {
return -1
}
var r rune
for _, c := range s[2:6] {
switch {
case '0' <= c && c <= '9':
c = c - '0'
case 'a' <= c && c <= 'f':
c = c - 'a' + 10
case 'A' <= c && c <= 'F':
c = c - 'A' + 10
default:
return -1
}
r = r*16 + rune(c)
}
return r
}
// String unescapes an escaped string (not including `"` at beginning and end)
// It validates invalid UTF8 and replace with `\ufffd`
func String(s string) (ret string, err types.ParsingError) {
// Convert string to []byte and use fallback implementation
sBytes := rt.Str2Mem(s)
result, ok := unquoteBytes(sBytes)
if !ok {
return "", types.ERR_INVALID_ESCAPE
}
return string(result), 0
}
// String unescapes an escaped string (not including `"` at beginning and end)
// - replace enables replacing invalid utf8 escaped char with `\uffd`
func _String(s string, _replace bool) (ret string, err error) {
return String(s)
}
|
