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
|
/*
Rosegarden
A sequencer and musical notation editor.
This program is Copyright 2000-2008
Guillaume Laurent <[email protected]>,
Chris Cannam <[email protected]>,
Richard Bown <[email protected]>
The moral right of the authors to claim authorship of this work
has been asserted.
This program is free software; you can redistribute it and/or
modify it under the terms of the GNU General Public License as
published by the Free Software Foundation; either version 2 of the
License, or (at your option) any later version. See the file
COPYING included with this distribution for more information.
*/
#include "XmlExportable.h"
#include <iostream>
#include <cstdlib>
#include <cstring>
namespace Rosegarden
{
static std::string s1;
static std::string multibyte;
std::string XmlExportable::encode(const std::string &s0)
{
static char *buffer = 0;
static size_t bufsiz = 0;
size_t buflen = 0;
static char multibyte[20];
size_t mblen = 0;
size_t len = s0.length();
if (bufsiz < len * 2 + 10) {
bufsiz = len * 2 + 10;
buffer = (char *)malloc(bufsiz);
}
// Escape any xml special characters, and also make sure we have
// valid utf8 -- otherwise we won't be able to re-read the xml.
// Amazing how complicated this gets.
bool warned = false; // no point in warning forever for long bogus strings
for (size_t i = 0; i < len; ++i) {
unsigned char c = s0[i];
if (((c & 0xc0) == 0xc0) || !(c & 0x80)) {
// 11xxxxxx or 0xxxxxxx: first byte of a character sequence
if (mblen > 0) {
// does multibyte contain a valid sequence?
unsigned int length =
(!(multibyte[0] & 0x20)) ? 2 :
(!(multibyte[0] & 0x10)) ? 3 :
(!(multibyte[0] & 0x08)) ? 4 :
(!(multibyte[0] & 0x04)) ? 5 : 0;
if (length == 0 || mblen == length) {
if (bufsiz < buflen + mblen + 1) {
bufsiz = 2 * buflen + mblen + 1;
buffer = (char *)realloc(buffer, bufsiz);
}
strncpy(buffer + buflen, multibyte, mblen);
buflen += mblen;
} else {
if (!warned) {
std::cerr
<< "WARNING: Invalid utf8 char width in string \""
<< s0 << "\" at index " << i << " ("
<< mblen << " octet"
<< (mblen != 1 ? "s" : "")
<< ", expected " << length << ")" << std::endl;
warned = true;
}
// and drop the character
}
}
mblen = 0;
if (!(c & 0x80)) { // ascii
if (bufsiz < buflen + 10) {
bufsiz = 2 * buflen + 10;
buffer = (char *)realloc(buffer, bufsiz);
}
switch (c) {
case '&' : strncpy(buffer + buflen, "&", 5); buflen += 5; break;
case '<' : strncpy(buffer + buflen, "<", 4); buflen += 4; break;
case '>' : strncpy(buffer + buflen, ">", 4); buflen += 4; break;
case '"' : strncpy(buffer + buflen, """, 6); buflen += 6; break;
case '\'' : strncpy(buffer + buflen, "'", 6); buflen += 6; break;
case 0x9:
case 0xa:
case 0xd:
// convert these special cases to plain whitespace:
buffer[buflen++] = ' ';
break;
default:
if (c >= 32) buffer[buflen++] = c;
else {
if (!warned) {
std::cerr
<< "WARNING: Invalid utf8 octet in string \""
<< s0 << "\" at index " << i << " ("
<< (int)c << " < 32)" << std::endl;
}
warned = true;
}
}
} else {
// store in multibyte rather than straight to s1, so
// that we know we're in the middle of something
// (below). At this point we know mblen == 0.
multibyte[mblen++] = c;
}
} else {
// second or subsequent byte
if (mblen == 0) { // ... without a first byte!
if (!warned) {
std::cerr
<< "WARNING: Invalid utf8 octet sequence in string \""
<< s0 << "\" at index " << i << std::endl;
warned = true;
}
} else {
if (mblen >= sizeof(multibyte)-1) {
if (!warned) {
std::cerr
<< "WARNING: Character too wide in string \""
<< s0 << "\" at index " << i << " (reached width of "
<< mblen << ")" << std::endl;
}
warned = true;
mblen = 0;
} else {
multibyte[mblen++] = c;
}
}
}
}
if (mblen > 0) {
// does multibyte contain a valid sequence?
unsigned int length =
(!(multibyte[0] & 0x20)) ? 2 :
(!(multibyte[0] & 0x10)) ? 3 :
(!(multibyte[0] & 0x08)) ? 4 :
(!(multibyte[0] & 0x04)) ? 5 : 0;
if (length == 0 || mblen == length) {
if (bufsiz < buflen + mblen + 1) {
bufsiz = 2 * buflen + mblen + 1;
buffer = (char *)realloc(buffer, bufsiz);
}
strncpy(buffer + buflen, multibyte, mblen);
buflen += mblen;
} else {
if (!warned) {
std::cerr
<< "WARNING: Invalid utf8 char width in string \""
<< s0 << "\" at index " << len << " ("
<< mblen << " octet"
<< (mblen != 1 ? "s" : "")
<< ", expected " << length << ")" << std::endl;
warned = true;
}
// and drop the character
}
}
buffer[buflen] = '\0';
return buffer;
}
}
|