|
|
@ -121,69 +121,112 @@ namespace NLGUI
|
|
|
|
|
|
|
|
|
|
|
|
// ***************************************************************************
|
|
|
|
// ***************************************************************************
|
|
|
|
// http://stackoverflow.com/a/18335183
|
|
|
|
// http://stackoverflow.com/a/18335183
|
|
|
|
static std::string correct_non_utf_8(const std::string &str)
|
|
|
|
static std::string correctNonUtf8(const std::string &str)
|
|
|
|
{
|
|
|
|
{
|
|
|
|
int i, f_size=str.size();
|
|
|
|
int i, f_size=str.size();
|
|
|
|
unsigned char c,c2,c3,c4;
|
|
|
|
unsigned char c,c2,c3,c4;
|
|
|
|
std::string to;
|
|
|
|
std::string to;
|
|
|
|
to.reserve(f_size);
|
|
|
|
to.reserve(f_size);
|
|
|
|
|
|
|
|
|
|
|
|
for(i=0 ; i<f_size ; i++){
|
|
|
|
for(i=0 ; i<f_size ; i++)
|
|
|
|
|
|
|
|
{
|
|
|
|
c=(unsigned char)(str[i]);
|
|
|
|
c=(unsigned char)(str[i]);
|
|
|
|
if(c<32){//control char
|
|
|
|
if (c<32)
|
|
|
|
if(c==9 || c==10 || c==13){//allow only \t \n \r
|
|
|
|
{
|
|
|
|
|
|
|
|
//control char
|
|
|
|
|
|
|
|
if(c==9 || c==10 || c==13)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//allow only \t \n \r
|
|
|
|
to.append(1,c);
|
|
|
|
to.append(1,c);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
continue;
|
|
|
|
}else if(c<127){//normal ASCII
|
|
|
|
}
|
|
|
|
|
|
|
|
else if (c<127)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//normal ASCII
|
|
|
|
to.append(1,c);
|
|
|
|
to.append(1,c);
|
|
|
|
continue;
|
|
|
|
continue;
|
|
|
|
}else if(c<160){//control char (nothing should be defined here either ASCI, ISO_8859-1 or UTF8, so skipping)
|
|
|
|
}
|
|
|
|
if(c==128){//fix microsoft mess, add euro
|
|
|
|
else if (c < 160)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//control char (nothing should be defined here either ASCI, ISO_8859-1 or UTF8, so skipping)
|
|
|
|
|
|
|
|
if (c == 128)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//fix microsoft mess, add euro
|
|
|
|
to.append(1,226);
|
|
|
|
to.append(1,226);
|
|
|
|
to.append(1,130);
|
|
|
|
to.append(1,130);
|
|
|
|
to.append(1,172);
|
|
|
|
to.append(1,172);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if(c==133){//fix IBM mess, add NEL = \n\r
|
|
|
|
|
|
|
|
|
|
|
|
if (c == 133)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//fix IBM mess, add NEL = \n\r
|
|
|
|
to.append(1,10);
|
|
|
|
to.append(1,10);
|
|
|
|
to.append(1,13);
|
|
|
|
to.append(1,13);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
continue;
|
|
|
|
}else if(c<192){//invalid for UTF8, converting ASCII
|
|
|
|
}
|
|
|
|
|
|
|
|
else if (c < 192)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//invalid for UTF8, converting ASCII
|
|
|
|
to.append(1,(unsigned char)194);
|
|
|
|
to.append(1,(unsigned char)194);
|
|
|
|
to.append(1,c);
|
|
|
|
to.append(1,c);
|
|
|
|
continue;
|
|
|
|
continue;
|
|
|
|
}else if(c<194){//invalid for UTF8, converting ASCII
|
|
|
|
}
|
|
|
|
|
|
|
|
else if (c < 194)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//invalid for UTF8, converting ASCII
|
|
|
|
to.append(1,(unsigned char)195);
|
|
|
|
to.append(1,(unsigned char)195);
|
|
|
|
to.append(1,c-64);
|
|
|
|
to.append(1,c-64);
|
|
|
|
continue;
|
|
|
|
continue;
|
|
|
|
}else if(c<224 && i+1<f_size){//possibly 2byte UTF8
|
|
|
|
}
|
|
|
|
|
|
|
|
else if (c < 224 && i + 1 < f_size)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//possibly 2byte UTF8
|
|
|
|
c2 = (unsigned char)(str[i+1]);
|
|
|
|
c2 = (unsigned char)(str[i+1]);
|
|
|
|
if(c2>127 && c2<192){//valid 2byte UTF8
|
|
|
|
|
|
|
|
if(c==194 && c2<160){//control char, skipping
|
|
|
|
if (c2 > 127 && c2 < 192)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//valid 2byte UTF8
|
|
|
|
|
|
|
|
if (c == 194 && c2 < 160)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//control char, skipping
|
|
|
|
;
|
|
|
|
;
|
|
|
|
}else{
|
|
|
|
}
|
|
|
|
|
|
|
|
else
|
|
|
|
|
|
|
|
{
|
|
|
|
to.append(1,c);
|
|
|
|
to.append(1,c);
|
|
|
|
to.append(1,c2);
|
|
|
|
to.append(1,c2);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
i++;
|
|
|
|
i++;
|
|
|
|
continue;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}else if(c<240 && i+2<f_size){//possibly 3byte UTF8
|
|
|
|
}
|
|
|
|
|
|
|
|
else if (c < 240 && i + 2 < f_size)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
// possibly 3byte UTF8
|
|
|
|
c2 = (unsigned char)(str[i+1]);
|
|
|
|
c2 = (unsigned char)(str[i+1]);
|
|
|
|
c3 = (unsigned char)(str[i+2]);
|
|
|
|
c3 = (unsigned char)(str[i+2]);
|
|
|
|
if(c2>127 && c2<192 && c3>127 && c3<192){//valid 3byte UTF8
|
|
|
|
|
|
|
|
|
|
|
|
if (c2 > 127 && c2 < 192 && c3 > 127 && c3 < 192)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
// valid 3byte UTF8
|
|
|
|
to.append(1,c);
|
|
|
|
to.append(1,c);
|
|
|
|
to.append(1,c2);
|
|
|
|
to.append(1,c2);
|
|
|
|
to.append(1,c3);
|
|
|
|
to.append(1,c3);
|
|
|
|
i+=2;
|
|
|
|
i+=2;
|
|
|
|
continue;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}else if(c<245 && i+3<f_size){//possibly 4byte UTF8
|
|
|
|
}
|
|
|
|
|
|
|
|
else if (c < 245 && i + 3 < f_size)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//possibly 4byte UTF8
|
|
|
|
c2 = (unsigned char)(str[i+1]);
|
|
|
|
c2 = (unsigned char)(str[i+1]);
|
|
|
|
c3 = (unsigned char)(str[i+2]);
|
|
|
|
c3 = (unsigned char)(str[i+2]);
|
|
|
|
c4 = (unsigned char)(str[i+3]);
|
|
|
|
c4 = (unsigned char)(str[i+3]);
|
|
|
|
if(c2>127 && c2<192 && c3>127 && c3<192 && c4>127 && c4<192){//valid 4byte UTF8
|
|
|
|
if (c2 > 127 && c2 < 192 && c3 > 127 && c3 < 192 && c4 > 127 && c4 < 192)
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
//valid 4byte UTF8
|
|
|
|
to.append(1,c);
|
|
|
|
to.append(1,c);
|
|
|
|
to.append(1,c2);
|
|
|
|
to.append(1,c2);
|
|
|
|
to.append(1,c3);
|
|
|
|
to.append(1,c3);
|
|
|
@ -192,6 +235,7 @@ namespace NLGUI
|
|
|
|
continue;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
//invalid UTF8, converting ASCII (c>245 || string too short for multi-byte))
|
|
|
|
//invalid UTF8, converting ASCII (c>245 || string too short for multi-byte))
|
|
|
|
to.append(1,(unsigned char)195);
|
|
|
|
to.append(1,(unsigned char)195);
|
|
|
|
to.append(1,c-64);
|
|
|
|
to.append(1,c-64);
|
|
|
@ -250,7 +294,7 @@ namespace NLGUI
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
// if there is invalid utf-8 chars, then libxml will break everything after first it finds.
|
|
|
|
// if there is invalid utf-8 chars, then libxml will break everything after first it finds.
|
|
|
|
htmlString = correct_non_utf_8(htmlString);
|
|
|
|
htmlString = correctNonUtf8(htmlString);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
// ***************************************************************************
|
|
|
|
// ***************************************************************************
|
|
|
|