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
|
/*
* 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;
/**
* An encoder that reads from the given source and outputs its representation
* to another ByteList. The source string is fully checked for UTF-8 validity,
* and throws a GeneratorError if any problem is found.
*/
final class StringEncoder extends ByteListTranscoder {
private final boolean asciiOnly;
// Escaped characters will reuse this array, to avoid new allocations
// or appending them byte-by-byte
private final byte[] aux =
new byte[] {/* First unicode character */
'\\', 'u', 0, 0, 0, 0,
/* Second unicode character (for surrogate pairs) */
'\\', 'u', 0, 0, 0, 0,
/* "\X" characters */
'\\', 0};
// offsets on the array above
private static final int ESCAPE_UNI1_OFFSET = 0;
private static final int ESCAPE_UNI2_OFFSET = ESCAPE_UNI1_OFFSET + 6;
private static final int ESCAPE_CHAR_OFFSET = ESCAPE_UNI2_OFFSET + 6;
/** Array used for code point decomposition in surrogates */
private final char[] utf16 = new char[2];
private static final byte[] HEX =
new byte[] {'0', '1', '2', '3', '4', '5', '6', '7',
'8', '9', 'a', 'b', 'c', 'd', 'e', 'f'};
StringEncoder(ThreadContext context, boolean asciiOnly) {
super(context);
this.asciiOnly = asciiOnly;
}
void encode(ByteList src, ByteList out) {
init(src, out);
append('"');
while (hasNext()) {
handleChar(readUtf8Char());
}
quoteStop(pos);
append('"');
}
private void handleChar(int c) {
switch (c) {
case '"':
case '\\':
escapeChar((char)c);
break;
case '\n':
escapeChar('n');
break;
case '\r':
escapeChar('r');
break;
case '\t':
escapeChar('t');
break;
case '\f':
escapeChar('f');
break;
case '\b':
escapeChar('b');
break;
default:
if (c >= 0x20 && c <= 0x7f ||
(c >= 0x80 && !asciiOnly)) {
quoteStart();
} else {
quoteStop(charStart);
escapeUtf8Char(c);
}
}
}
private void escapeChar(char c) {
quoteStop(charStart);
aux[ESCAPE_CHAR_OFFSET + 1] = (byte)c;
append(aux, ESCAPE_CHAR_OFFSET, 2);
}
private void escapeUtf8Char(int codePoint) {
int numChars = Character.toChars(codePoint, utf16, 0);
escapeCodeUnit(utf16[0], ESCAPE_UNI1_OFFSET + 2);
if (numChars > 1) escapeCodeUnit(utf16[1], ESCAPE_UNI2_OFFSET + 2);
append(aux, ESCAPE_UNI1_OFFSET, 6 * numChars);
}
private void escapeCodeUnit(char c, int auxOffset) {
for (int i = 0; i < 4; i++) {
aux[auxOffset + i] = HEX[(c >>> (12 - 4 * i)) & 0xf];
}
}
@Override
protected RaiseException invalidUtf8() {
return Utils.newException(context, Utils.M_GENERATOR_ERROR,
"source sequence is illegal/malformed utf-8");
}
}
|
