Facebook: Replace #&... html codes to chars (fixes #32)

git-svn-id: http://svn.miranda-ng.org/main/trunk@2208 1316c22d-e87f-b044-9b9b-93d7a3e3ba9c

2 files changed, 167 insertions, 140 deletions

diff --git a/protocols/FacebookRM/src/utils.cpp b/protocols/FacebookRM/src/utils.cpp
index 8e33b26e01..999cb69c56 100644
--- a/protocols/FacebookRM/src/utils.cpp
+++ b/protocols/FacebookRM/src/utils.cpp
@@ -24,10 +24,9 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 

 std::string utils::url::encode(const std::string &s)

 {

-	char *encoded = reinterpret_cast<char*>(CallService( MS_NETLIB_URLENCODE,

-		0,reinterpret_cast<LPARAM>(s.c_str())));

+	char *encoded = reinterpret_cast<char*>(CallService(MS_NETLIB_URLENCODE, 0, reinterpret_cast<LPARAM>(s.c_str())));

 	std::string ret = encoded;

-	HeapFree(GetProcessHeap(),0,encoded);

+	HeapFree(GetProcessHeap(), 0, encoded);

 

 	return ret;

 }

@@ -35,30 +34,30 @@ std::string utils::url::encode(const std::string &s)
 std::string utils::url::decode(std::string data)

 {

 	// TODO: Better and universal method?

-	utils::text::replace_all( &data, "%2F", "/" );

-	utils::text::replace_all( &data, "%3F", "?" );

-	utils::text::replace_all( &data, "%3D", "=" );

-	utils::text::replace_all( &data, "%26", "&" );

+	utils::text::replace_all(&data, "%2F", "/");

+	utils::text::replace_all(&data, "%3F", "?");

+	utils::text::replace_all(&data, "%3D", "=");

+	utils::text::replace_all(&data, "%26", "&");

 

 	return data;

 }

 

-std::string utils::time::unix_timestamp( )

+std::string utils::time::unix_timestamp()

 {

-	time_t in = ::time( NULL );

-	return utils::conversion::to_string( ( void* )&in, UTILS_CONV_TIME_T );

+	time_t in = ::time(NULL);

+	return utils::conversion::to_string((void*)&in, UTILS_CONV_TIME_T);

 }

 

-std::string utils::time::mili_timestamp( )

+std::string utils::time::mili_timestamp()

 {

 	SYSTEMTIME st;

 	std::string timestamp = utils::time::unix_timestamp();

 	GetSystemTime(&st);

-	timestamp.append(utils::conversion::to_string( ( void* )&st.wMilliseconds, UTILS_CONV_UNSIGNED_NUMBER ));

+	timestamp.append(utils::conversion::to_string((void*)&st.wMilliseconds, UTILS_CONV_UNSIGNED_NUMBER));

 	return timestamp;

 }

 

-DWORD utils::time::fix_timestamp( double mili_timestamp )

+DWORD utils::time::fix_timestamp(double mili_timestamp)

 {

 	// If it is really mili_timestamp

 	if (mili_timestamp > 100000000000) {

@@ -67,7 +66,7 @@ DWORD utils::time::fix_timestamp( double mili_timestamp )
 	return (DWORD) mili_timestamp;

 }

 

-DWORD utils::conversion::to_timestamp( std::string data )

+DWORD utils::conversion::to_timestamp(std::string data)

 {

 	DWORD timestamp = NULL;

 	if (!utils::conversion::from_string<DWORD>(timestamp, data, std::dec)) {

@@ -76,57 +75,57 @@ DWORD utils::conversion::to_timestamp( std::string data )
 	return timestamp;

 }

 

-std::string utils::conversion::to_string( void* data, WORD type )

+std::string utils::conversion::to_string(void* data, WORD type)

 {

 	std::stringstream out;

 

-	switch ( type )

+	switch (type)

 	{

   	case UTILS_CONV_BOOLEAN:

 		out << (data ? "true" : "false");

 

     case UTILS_CONV_TIME_T:

-		out << (*( time_t* )data);

+		out << (*(time_t*)data);

 		break;

 

 	case UTILS_CONV_SIGNED_NUMBER:

-  		out << (*( signed int* )data);

+  		out << (*(signed int*)data);

 		break;

 

 	case UTILS_CONV_UNSIGNED_NUMBER:

-		out << (*( unsigned int* )data);

+		out << (*(unsigned int*)data);

 		break;

 	}

 

-	return out.str( );

+	return out.str();

 }

 

-void utils::text::replace_first( std::string* data, std::string from, std::string to )

+void utils::text::replace_first(std::string* data, std::string from, std::string to)

 {

 	std::string::size_type position = data->find(from);

-	if ( position != std::string::npos )

+	if (position != std::string::npos)

 	{

-		data->replace( position, from.size(), to );

+		data->replace(position, from.size(), to);

 	}

 }

 

-void utils::text::replace_all( std::string* data, std::string from, std::string to )

+void utils::text::replace_all(std::string* data, std::string from, std::string to)

 {

 	std::string::size_type position = 0;

 

-	while ( ( position = data->find( from, position )) != std::string::npos )

+	while ((position = data->find(from, position)) != std::string::npos)

 	{

-		data->replace( position, from.size(), to );

+		data->replace(position, from.size(), to);

 		position++;

 	}

 }

 

-unsigned int utils::text::count_all( std::string* data, std::string term )

+unsigned int utils::text::count_all(std::string* data, std::string term)

 {

 	unsigned int count = 0;

 	std::string::size_type position = 0;

 

-	while ( ( position = data->find( term, position )) != std::string::npos )

+	while ((position = data->find(term, position)) != std::string::npos)

 	{

 		count++;

 		position++;

@@ -135,20 +134,37 @@ unsigned int utils::text::count_all( std::string* data, std::string term )
 	return count;

 }

 

-std::string utils::text::special_expressions_decode( std::string data )

+void utils::text::append_ordinal(unsigned int value, std::string* data)

 {

-	utils::text::replace_all( &data, "&amp;", "&" );

-	utils::text::replace_all( &data, "&quot;", "\"" );

-	utils::text::replace_all( &data, "&#039;", "'" );

-	utils::text::replace_all( &data, "&#64;", "@" );

-	utils::text::replace_all( &data, "&lt;", "<" );

-	utils::text::replace_all( &data, "&gt;", ">" );

+	if (value >= 128 && value <= 2047)

+	{ // U+0080 .. U+07FF

+		*data += (char)(192 + (value / 64));

+		*data += (char)(128 + (value % 64));

+	} 

+	else if (value >= 2048 && value <= 65535)

+	{ // U+0800 .. U+FFFF

+		*data += (char)(224 + (value / 4096));

+		*data += (char)(128 + ((value / 64) % 64));

+		*data += (char)(128 + (value % 64));

+	}

+	else if (value <= 127)

+	{ // U+0000 .. U+007F

+		*data += (char)value;

+	}

+}

 

-	utils::text::replace_all( &data, "&hearts;", "\xE2\x99\xA5" ); // direct byte replacement

-//	utils::text::replace_all( &data, "&hearts;", "\\u2665" );      // indirect slashu replacement

+std::string utils::text::special_expressions_decode(std::string data)

+{

+	utils::text::replace_all(&data, "&amp;", "&");

+	utils::text::replace_all(&data, "&quot;", "\"");

+	utils::text::replace_all(&data, "&lt;", "<");

+	utils::text::replace_all(&data, "&gt;", ">");

+

+	utils::text::replace_all(&data, "&hearts;", "\xE2\x99\xA5"); // direct byte replacement

+//	utils::text::replace_all(&data, "&hearts;", "\\u2665");      // indirect slashu replacement

 

-	utils::text::replace_all( &data, "\\/", "/" );

-	utils::text::replace_all( &data, "\\\\", "\\" );

+	utils::text::replace_all(&data, "\\/", "/");

+	utils::text::replace_all(&data, "\\\\", "\\");

 

 	// TODO: Add more to comply general usage

 	// http://www.utexas.edu/learn/html/spchar.html

@@ -158,25 +174,51 @@ std::string utils::text::special_expressions_decode( std::string data )
 	// http://www.w3schools.com/tags/ref_entities.asp

 	// http://www.natural-innovations.com/wa/doc-charset.html

 	// http://webdesign.about.com/library/bl_htmlcodes.htm

-	

-	return data;

+

+	std::string new_string = "";

+	for (std::string::size_type i = 0; i < data.length(); i++)

+	{

+		if (data.at(i) == '&' && (i+1) < data.length() && data.at(i+1) == '#')

+		{

+			unsigned int udn;

+			std::string::size_type comma = data.find(";", i);

+			if (comma != std::string::npos) {

+				bool hexa = false;

+				if ((i+2) < data.length() && data.at(i+2) == 'x') {

+					hexa = true;

+					i += 3;

+				} else {

+					i += 2;

+				}

+				udn = strtol(data.substr(i, comma-i).c_str(), NULL, hexa ? 16 : 10);

+				i = comma;

+			}

+			

+			utils::text::append_ordinal(udn, &new_string);

+			continue;

+		}

+

+		new_string += data.at(i);

+	}

+

+	return new_string;

 }

 

-std::string utils::text::edit_html( std::string data )

+std::string utils::text::edit_html(std::string data)

 {

 	std::string::size_type end = 0;

 	std::string::size_type start = 0;

 	std::string new_string = "";

   

-	while ( end != std::string::npos )

+	while (end != std::string::npos)

 	{

-		end = data.find( "<span class=\\\"text_exposed_hide", start );

-		if ( end != std::string::npos )

+		end = data.find("<span class=\\\"text_exposed_hide", start);

+		if (end != std::string::npos)

 		{

-			new_string += data.substr( start, end - start );

-			start = data.find( "<\\/span", end );

+			new_string += data.substr(start, end - start);

+			start = data.find("<\\/span", end);

 		} else {

-			new_string += data.substr( start, data.length() - start );

+			new_string += data.substr(start, data.length() - start);

 		}

 	}

 

@@ -184,15 +226,15 @@ std::string utils::text::edit_html( std::string data )
 	data = new_string;

 	new_string = "";

 

-	while ( end != std::string::npos )

+	while (end != std::string::npos)

 	{

-		end = data.find( "<span class=\\\"uiTooltipText", start );

-		if ( end != std::string::npos )

+		end = data.find("<span class=\\\"uiTooltipText", start);

+		if (end != std::string::npos)

 		{

-			new_string += data.substr( start, end - start );

-			start = data.find( "<\\/span", end );

+			new_string += data.substr(start, end - start);

+			start = data.find("<\\/span", end);

 		} else {

-			new_string += data.substr( start, data.length() - start );

+			new_string += data.substr(start, data.length() - start);

 		}

 	}

 

@@ -200,64 +242,64 @@ std::string utils::text::edit_html( std::string data )
 	start = end = 0;

 	data = new_string;

 	new_string = "";

-	while ( end != std::string::npos )

+	while (end != std::string::npos)

 	{

-		end = data.find( "translate_story_link\\\">", start );

-		if ( end != std::string::npos )

+		end = data.find("translate_story_link\\\">", start);

+		if (end != std::string::npos)

 		{

-			new_string += data.substr( start, end - start );

-			start = data.find( "<\\/div", end );

+			new_string += data.substr(start, end - start);

+			start = data.find("<\\/div", end);

 		} else {

-			new_string += data.substr( start, data.length() - start );

+			new_string += data.substr(start, data.length() - start);

 		}

 	}

 

 	// Append newline after attachement title

-	start = new_string.find( "class=\\\"uiAttachmentTitle", 0 );

-	if ( start != std::string::npos )

+	start = new_string.find("class=\\\"uiAttachmentTitle", 0);

+	if (start != std::string::npos)

 	{

-		data = new_string.substr( 0, start );

-		data = utils::text::trim( data );

+		data = new_string.substr(0, start);

+		data = utils::text::trim(data);

 

-		start = new_string.find( ">", start );

-		if ( start != std::string::npos )

+		start = new_string.find(">", start);

+		if (start != std::string::npos)

 			new_string.insert(start+1, "\n\n");

 

-		start = new_string.find( "<\\/div>", start );

-		if ( start != std::string::npos )

+		start = new_string.find("<\\/div>", start);

+		if (start != std::string::npos)

 			new_string.insert(start, "\n");

 	}

 

 	// Append newline between attachement link and description

-	start = new_string.find( "uiAttachmentDesc", 0 );

-	if ( start != std::string::npos )

+	start = new_string.find("uiAttachmentDesc", 0);

+	if (start != std::string::npos)

 	{

-		start = new_string.find( ">", start );

-		if ( start != std::string::npos )

+		start = new_string.find(">", start);

+		if (start != std::string::npos)

 			new_string.insert(start+1, "\n");

 

-		start = new_string.find( "<\\/div>", start );

-		if ( start != std::string::npos )

+		start = new_string.find("<\\/div>", start);

+		if (start != std::string::npos)

 			new_string.insert(start, "\n");

 	}

   

-	utils::text::replace_all( &new_string, "<br \\/>", "\n" );

-	utils::text::replace_all( &new_string, "\n\n\n", "\n\n" );

-	//utils::text::replace_all( &new_string, "\\t", "" );

-	//utils::text::replace_all( &new_string, "\\n", "" );

+	utils::text::replace_all(&new_string, "<br \\/>", "\n");

+	utils::text::replace_all(&new_string, "\n\n\n", "\n\n");

+	//utils::text::replace_all(&new_string, "\\t", "");

+	//utils::text::replace_all(&new_string, "\\n", "");

 	return new_string;

 }

 

 

-std::string utils::text::remove_html( std::string data )

+std::string utils::text::remove_html(std::string data)

 {

 	std::string new_string = "";

 

-	for ( std::string::size_type i = 0; i < data.length( ); i++ )

+	for (std::string::size_type i = 0; i < data.length(); i++)

 	{

-		if ( data.at(i) == '<' && data.at(i+1) != ' ' )

+		if (data.at(i) == '<' && data.at(i+1) != ' ')

 		{

-			i = data.find( ">", i );

+			i = data.find(">", i);

 			if (i == std::string::npos)

 				break;

 

@@ -270,32 +312,16 @@ std::string utils::text::remove_html( std::string data )
 	return new_string;

 }

 

-std::string utils::text::slashu_to_utf8( std::string data )

+std::string utils::text::slashu_to_utf8(std::string data)

 {

 	std::string new_string = "";

 

-	for ( std::string::size_type i = 0; i < data.length( ); i++ )

+	for (std::string::size_type i = 0; i < data.length(); i++)

 	{

-		if ( data.at(i) == '\\' && (i+1) < data.length( ) && data.at(i+1) == 'u' )

+		if (data.at(i) == '\\' && (i+1) < data.length() && data.at(i+1) == 'u')

 		{

-			unsigned int udn = strtol( data.substr( i + 2, 4 ).c_str(), NULL, 16 );

-

-			if ( udn >= 128 && udn <= 2047 )

-			{ // U+0080 .. U+07FF

-				new_string += ( char )( 192 + ( udn / 64 ));

-				new_string += ( char )( 128 + ( udn % 64 ));

-			} 

-			else if ( udn >= 2048 && udn <= 65535 )

-			{ // U+0800 .. U+FFFF

-				new_string += ( char )( 224 + ( udn / 4096 ));

-				new_string += ( char )( 128 + ( ( udn / 64 ) % 64 ));

-				new_string += ( char )( 128 + ( udn % 64  ));

-			}

-			else if ( udn <= 127 )

-			{ // U+0000 .. U+007F (should not appear)

-				new_string += ( char )udn;

-			}

-

+			unsigned int udn = strtol(data.substr(i + 2, 4).c_str(), NULL, 16);

+			append_ordinal(udn, &new_string);

 			i += 5;

 			continue;

 		}

@@ -306,13 +332,13 @@ std::string utils::text::slashu_to_utf8( std::string data )
 	return new_string;

 }

 

-std::string utils::text::trim( std::string data )

+std::string utils::text::trim(std::string data)

 {

 	std::string spaces = " \t\r\n"; // TODO: include "nbsp"?

-	std::string::size_type begin = data.find_first_not_of( spaces );

-	std::string::size_type end = data.find_last_not_of( spaces ) + 1;

+	std::string::size_type begin = data.find_first_not_of(spaces);

+	std::string::size_type end = data.find_last_not_of(spaces) + 1;

 

-	return (begin != std::string::npos) ? data.substr( begin, end - begin ) : "";

+	return (begin != std::string::npos) ? data.substr(begin, end - begin) : "";

 }

 

 void utils::text::explode(std::string str, std::string separator, std::vector<std::string>* results)

@@ -331,36 +357,36 @@ void utils::text::explode(std::string str, std::string separator, std::vector<st
 	}

 }

 

-std::string utils::text::source_get_value( std::string* data, unsigned int argument_count, ... )

+std::string utils::text::source_get_value(std::string* data, unsigned int argument_count, ...)

 {

 	va_list arg;

 	std::string ret;

 	std::string::size_type start = 0, end = 0;

 	

-	va_start( arg, argument_count );

+	va_start(arg, argument_count);

 	

-	for ( unsigned int i = argument_count; i > 0; i-- )

+	for (unsigned int i = argument_count; i > 0; i--)

 	{

-		if ( i == 1 )

+		if (i == 1)

 		{

-			end = data->find( va_arg( arg, char* ), start );

-			if ( start == std::string::npos || end == std::string::npos )

+			end = data->find(va_arg(arg, char*), start);

+			if (start == std::string::npos || end == std::string::npos)

 				break;

-			ret = data->substr( start, end - start );

+			ret = data->substr(start, end - start);

 		} else {

-			std::string term = va_arg( arg, char* );

-			start = data->find( term, start );

-			if ( start == std::string::npos )

+			std::string term = va_arg(arg, char*);

+			start = data->find(term, start);

+			if (start == std::string::npos)

 				break;

 			start += term.length();

 		}

 	}

 	

-	va_end( arg );	

+	va_end(arg);	

 	return ret;

 }

 

-std::string utils::text::source_get_value2( std::string* data, const char *term, const char *endings)

+std::string utils::text::source_get_value2(std::string* data, const char *term, const char *endings)

 {

 	std::string::size_type start = 0, end = 0;

 	std::string ret;

@@ -371,17 +397,17 @@ std::string utils::text::source_get_value2( std::string* data, const char *term,
 

 		end = data->find_first_of(endings, start);

 		if (end != std::string::npos) {

-			ret = data->substr( start, end - start );

+			ret = data->substr(start, end - start);

 		}

 	}

 

 	return ret;

 }

 

-int utils::number::random( )

+int utils::number::random()

 {

-	srand( ::time( NULL ));

-	return rand( );

+	srand(::time(NULL));

+	return rand();

 }

 

 int utils::debug::log(std::string file_name, std::string text)

@@ -389,23 +415,23 @@ int utils::debug::log(std::string file_name, std::string text)
 	char szFile[MAX_PATH];

 	GetModuleFileNameA(g_hInstance, szFile, SIZEOF(szFile));

 	std::string path = szFile;

-	path = path.substr( 0, path.rfind( "\\" ));

-	path = path.substr( 0, path.rfind( "\\" ) + 1 );

+	path = path.substr(0, path.rfind("\\"));

+	path = path.substr(0, path.rfind("\\") + 1);

 	path = path + file_name.c_str() + ".txt";

 

 	SYSTEMTIME time;

-	GetLocalTime( &time );

+	GetLocalTime(&time);

 

-	std::ofstream out( path.c_str(), std::ios_base::out | std::ios_base::app | std::ios_base::ate );

+	std::ofstream out(path.c_str(), std::ios_base::out | std::ios_base::app | std::ios_base::ate);

 	out << "[" << (time.wHour < 10 ? "0" : "") << time.wHour << ":" << (time.wMinute < 10 ? "0" : "") << time.wMinute << ":" << (time.wSecond < 10 ? "0" : "") << time.wSecond << "] " << text << std::endl;

-	out.close( );

+	out.close();

 

 	return EXIT_SUCCESS;

 }

 

-void __fastcall utils::mem::detract(char** str )

+void __fastcall utils::mem::detract(char** str)

 {

-	utils::mem::detract( ( void** )str );

+	utils::mem::detract((void**)str);

 }

 

 void __fastcall utils::mem::detract(void** p)

diff --git a/protocols/FacebookRM/src/utils.h b/protocols/FacebookRM/src/utils.h
index 75712d6a2d..b9cb11a369 100644
--- a/protocols/FacebookRM/src/utils.h
+++ b/protocols/FacebookRM/src/utils.h
@@ -82,17 +82,18 @@ namespace utils
 

 	namespace text

 	{

-		void replace_first( std::string* data, std::string from, std::string to );

-		void replace_all( std::string* data, std::string from, std::string to );

-		unsigned int count_all( std::string* data, std::string term );

-		std::string special_expressions_decode( std::string data );

-		std::string edit_html( std::string data );

-		std::string remove_html( std::string data );

-		std::string slashu_to_utf8( std::string data );

-		std::string trim( std::string data );

-		std::string source_get_value( std::string* data, unsigned int argument_count, ... );

-		std::string source_get_value2( std::string* data, const char *term, const char *endings);

+		void replace_first(std::string* data, std::string from, std::string to);

+		void replace_all(std::string* data, std::string from, std::string to);

+		unsigned int count_all(std::string* data, std::string term);

+		std::string special_expressions_decode( std::string data);

+		std::string edit_html(std::string data);

+		std::string remove_html(std::string data);

+		std::string slashu_to_utf8(std::string data);

+		std::string trim(std::string data);

+		std::string source_get_value(std::string* data, unsigned int argument_count, ...);

+		std::string source_get_value2(std::string* data, const char *term, const char *endings);

 		void explode(std::string str, std::string separator, std::vector<std::string>* results);

+		void append_ordinal(unsigned int value, std::string* data);

 	};

 

 	namespace conversion