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
|
/*
* This code is copyrighted work by Daniel Luz <dev at mernen dot com>.
*
* Distributed under the Ruby license: https://www.ruby-lang.org/en/about/license.txt
*/
package json.ext;
import org.jruby.exceptions.RaiseException;
import org.jruby.runtime.ThreadContext;
import org.jruby.util.ByteList;
/**
* A decoder that reads a JSON-encoded string from the given sources and
* returns its decoded form on a new ByteList. Escaped Unicode characters
* are encoded as UTF-8.
*/
final class StringDecoder extends ByteListTranscoder {
/**
* Stores the offset of the high surrogate when reading a surrogate pair,
* or -1 when not.
*/
private int surrogatePairStart = -1;
// Array used for writing multi-byte characters into the buffer at once
private final byte[] aux = new byte[4];
StringDecoder(ThreadContext context) {
super(context);
}
ByteList decode(ByteList src, int start, int end) {
ByteList out = new ByteList(end - start);
out.setEncoding(src.getEncoding());
init(src, start, end, out);
while (hasNext()) {
handleChar(readUtf8Char());
}
quoteStop(pos);
return out;
}
private void handleChar(int c) {
if (c == '\\') {
quoteStop(charStart);
handleEscapeSequence();
} else {
quoteStart();
}
}
private void handleEscapeSequence() {
ensureMin(1);
switch (readUtf8Char()) {
case 'b':
append('\b');
break;
case 'f':
append('\f');
break;
case 'n':
append('\n');
break;
case 'r':
append('\r');
break;
case 't':
append('\t');
break;
case 'u':
ensureMin(4);
int cp = readHex();
if (Character.isHighSurrogate((char)cp)) {
handleLowSurrogate((char)cp);
} else if (Character.isLowSurrogate((char)cp)) {
// low surrogate with no high surrogate
throw invalidUtf8();
} else {
writeUtf8Char(cp);
}
break;
default: // '\\', '"', '/'...
quoteStart();
}
}
private void handleLowSurrogate(char highSurrogate) {
surrogatePairStart = charStart;
ensureMin(1);
int lowSurrogate = readUtf8Char();
if (lowSurrogate == '\\') {
ensureMin(5);
if (readUtf8Char() != 'u') throw invalidUtf8();
lowSurrogate = readHex();
}
if (Character.isLowSurrogate((char)lowSurrogate)) {
writeUtf8Char(Character.toCodePoint(highSurrogate,
(char)lowSurrogate));
surrogatePairStart = -1;
} else {
throw invalidUtf8();
}
}
private void writeUtf8Char(int codePoint) {
if (codePoint < 0x80) {
append(codePoint);
} else if (codePoint < 0x800) {
aux[0] = (byte)(0xc0 | (codePoint >>> 6));
aux[1] = tailByte(codePoint & 0x3f);
append(aux, 0, 2);
} else if (codePoint < 0x10000) {
aux[0] = (byte)(0xe0 | (codePoint >>> 12));
aux[1] = tailByte(codePoint >>> 6);
aux[2] = tailByte(codePoint);
append(aux, 0, 3);
} else {
aux[0] = (byte)(0xf0 | codePoint >>> 18);
aux[1] = tailByte(codePoint >>> 12);
aux[2] = tailByte(codePoint >>> 6);
aux[3] = tailByte(codePoint);
append(aux, 0, 4);
}
}
private byte tailByte(int value) {
return (byte)(0x80 | (value & 0x3f));
}
/**
* Reads a 4-digit unsigned hexadecimal number from the source.
*/
private int readHex() {
int numberStart = pos;
int result = 0;
int length = 4;
for (int i = 0; i < length; i++) {
int digit = readUtf8Char();
int digitValue;
if (digit >= '0' && digit <= '9') {
digitValue = digit - '0';
} else if (digit >= 'a' && digit <= 'f') {
digitValue = 10 + digit - 'a';
} else if (digit >= 'A' && digit <= 'F') {
digitValue = 10 + digit - 'A';
} else {
throw new NumberFormatException("Invalid base 16 number "
+ src.subSequence(numberStart, numberStart + length));
}
result = result * 16 + digitValue;
}
return result;
}
@Override
protected RaiseException invalidUtf8() {
ByteList message = new ByteList(
ByteList.plain("partial character in source, " +
"but hit end near "));
int start = surrogatePairStart != -1 ? surrogatePairStart : charStart;
message.append(src, start, srcEnd - start);
return Utils.newException(context, Utils.M_PARSER_ERROR,
context.getRuntime().newString(message));
}
}
|
