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
|
/*
* Copyright 2008 Fabrice Colin
*
* 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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Library General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#include <errno.h>
#include <iostream>
#include <glibmm/convert.h>
#include <glibmm/ustring.h>
#include "StringManip.h"
#include "TextConverter.h"
using std::cout;
using std::endl;
using std::string;
using namespace Glib;
TextConverter::TextConverter(unsigned int maxErrors) :
m_utf8Locale(false),
m_maxErrors(maxErrors),
m_conversionErrors(0)
{
// Get the locale charset
m_utf8Locale = get_charset(m_localeCharset);
}
TextConverter::~TextConverter()
{
}
string TextConverter::toUTF8(const string &text, const string &charset)
{
unsigned int textLen = (unsigned int)text.length();
// Call overload
return toUTF8(text.c_str(), textLen, charset);
}
string TextConverter::toUTF8(const char *pText, unsigned int textLen, const string &charset)
{
string textCharset(StringManip::toLowerCase(charset));
char outputBuffer[8192];
char *pInput = const_cast<char *>(pText);
m_conversionErrors = 0;
if ((pText == NULL) ||
(textLen == 0) ||
(textCharset == "utf-8"))
{
// No conversion necessary
return string(pText, textLen);
}
if (textCharset.empty() == true)
{
if (m_utf8Locale == true)
{
// The current locale uses UTF-8
return string(pText, textLen);
}
textCharset = m_localeCharset;
}
IConv converter("UTF-8", textCharset);
string outputText;
gsize inputSize = (gsize)textLen;
bool invalidSequence = false;
while (inputSize > 0)
{
char *pOutput = outputBuffer;
gsize outputSize = 8192;
size_t conversions = converter.iconv(&pInput, &inputSize, &pOutput, &outputSize);
int errorCode = errno;
if (conversions == -1)
{
if (errorCode == EILSEQ)
{
// Conversion was only partially successful
++m_conversionErrors;
#ifdef DEBUG
cout << "TextConverter::toUTF8: invalid sequence at " << pInput - pText << endl;
#endif
if (m_conversionErrors >= m_maxErrors)
{
// Give up
return string(pText, textLen);
}
converter.reset();
outputText.append(outputBuffer, 8192 - outputSize);
if (invalidSequence == false)
{
outputText += "?";
invalidSequence = true;
}
// Skip that
++pInput;
--inputSize;
continue;
}
else if (errorCode != E2BIG)
{
#ifdef DEBUG
cout << "TextConverter::toUTF8: unknown error " << errorCode << endl;
#endif
return string(pText, textLen);
}
}
else
{
invalidSequence = false;
}
// Append what was successfully converted
outputText.append(outputBuffer, 8192 - outputSize);
}
#ifdef DEBUG
cout << "TextConverter::toUTF8: " << m_conversionErrors << " conversion errors" << endl;
#endif
return outputText;
}
unsigned int TextConverter::getErrorsCount(void) const
{
return m_conversionErrors;
}
string TextConverter::fromUTF8(const string &text)
{
try
{
return locale_from_utf8(text);
}
catch (ConvertError &ce)
{
#ifdef DEBUG
cout << "TextConverter::fromUTF8: " << ce.what() << endl;
#endif
}
return "";
}
|
