unicode.php

CMS系统 提供学习研究修改最好了 比流行的一些CMS简单 但是更容易理解 是帮助你学习PHPCMS系统的好东东哦

        }

        // Convert the array of valid unicode character numbers back to UTF-16 encoded text
        $UTF16_text = unicode_array_to_UTF16( $new_unicode_array, $MSB_first );

        // Escape any special HTML characters present
        $UTF16_text =  htmlspecialchars ( $UTF16_text, ENT_QUOTES );

        // Escape CR, LF and TAB characters, so that they are kept and not treated as expendable white space
        $trans = array( "\x09" => "	", "\x0A" => "
", "\x0D" => "
" );
        $UTF16_text = strtr( $UTF16_text, $trans );

        // Return the resulting XML valid string
        return $UTF16_text;
}

/******************************************************************************
* End of Function:     xml_UTF16_clean
******************************************************************************/






/******************************************************************************
*
* Function:     HTML_UTF8_Escape
*
* Description:  A HTML page can display UTF-8 data properly if it has a
*               META http-equiv="Content-Type" tag with the content attribute
*               including the value: "charset=utf-8".
*               Otherwise the ISO-8859-1 character set is usually assumed, and
*               Unicode values above 0x7F must be escaped.
*               This function takes a UTF-8 encoded string and escapes the
*               characters above 0x7F as well as reserved HTML characters such
*               as Quotes, Greater than, Less than and Ampersand.
*
* Parameters:   utf8_text - a string containing the UTF-8 data
*
* Returns:      htmloutput - a string containing the HTML equivalent
*
******************************************************************************/

function HTML_UTF8_Escape( $UTF8_text )
{

        // Ensure that the Unicode UTF8 encoding is valid.
        $UTF8_text = UTF8_fix( $UTF8_text );

        // Change: changed to use smart_htmlspecialchars, so that characters which were already escaped would remain intact, as of revision 1.10
        // Escape any special HTML characters present
        $UTF8_text =  smart_htmlspecialchars( $UTF8_text, ENT_QUOTES );

        // Convert the UTF-8 string to an array of unicode character numbers
        $unicode_array = UTF8_to_unicode_array( $UTF8_text );

        // Create a string to receive the escaped HTML
        $htmloutput = "";

        // Cycle through the unicode character numbers
        foreach( $unicode_array as  $unichar )
        {
                // Check if the character needs to be escaped
                if ( ( $unichar >= 0x00 ) && ( $unichar <= 0x7F ) )
                {
                        // Character is less than 0x7F - add it to the html as is
                        $htmloutput .= chr( $unichar );
                }
                else
                {
                        // Character is greater than 0x7F - escape it and add it to the html
                        $htmloutput .= "&#x" . dechex($unichar) . ";";
                }
        }

        // Return the resulting escaped HTML
        return $htmloutput;
}

/******************************************************************************
* End of Function:     HTML_UTF8_Escape
******************************************************************************/



/******************************************************************************
*
* Function:     HTML_UTF8_UnEscape
*
* Description:  Converts HTML which contains escaped decimal or hex characters
*               into UTF-8 text
*
* Parameters:   HTML_text - a string containing the HTML text to convert
*
* Returns:      utfoutput - a string containing the UTF-8 equivalent
*
******************************************************************************/

function HTML_UTF8_UnEscape( $HTML_text )
{
        preg_match_all( "/\&\#(\d+);/", $HTML_text, $matches);
        preg_match_all( "/\&\#[x|X]([A|B|C|D|E|F|a|b|c|d|e|f|0-9]+);/", $HTML_text, $hexmatches);
        foreach( $hexmatches[1] as $index => $match )
        {
                $matches[0][] = $hexmatches[0][$index];
                $matches[1][] = hexdec( $match );
        }

        for ( $i = 0; $i < count( $matches[ 0 ] ); $i++ )
        {
                $trans = array( $matches[0][$i] => unicode_array_to_UTF8( array( $matches[1][$i] ) ) );

                $HTML_text = strtr( $HTML_text , $trans );
        }
        return $HTML_text;
}

/******************************************************************************
* End of Function:     HTML_UTF8_UnEscape
******************************************************************************/






/******************************************************************************
*
* Function:     HTML_UTF16_Escape
*
* Description:  A HTML page can display UTF-16 data properly if it has a
*               META http-equiv="Content-Type" tag with the content attribute
*               including the value: "charset=utf-16".
*               Otherwise the ISO-8859-1 character set is usually assumed, and
*               Unicode values above 0x7F must be escaped.
*               This function takes a UTF-16 encoded string and escapes the
*               characters above 0x7F as well as reserved HTML characters such
*               as Quotes, Greater than, Less than and Ampersand.
*
* Parameters:   utf16_text - a string containing the UTF-16 data
*               MSB_first - True will cause processing as Big Endian UTF-16 (Motorola, MSB first)
*                           False will cause processing as Little Endian UTF-16 (Intel, LSB first)
*
* Returns:      htmloutput - a string containing the HTML equivalent
*
******************************************************************************/

function HTML_UTF16_Escape( $UTF16_text, $MSB_first )
{

        // Ensure that the Unicode UTF16 encoding is valid.
        $UTF16_text = UTF16_fix( $UTF16_text, $MSB_first );

        // Change: changed to use smart_htmlspecialchars, so that characters which were already escaped would remain intact, as of revision 1.10
        // Escape any special HTML characters present
        $UTF16_text =  smart_htmlspecialchars( $UTF16_text );

        // Convert the UTF-16 string to an array of unicode character numbers
        $unicode_array = UTF16_to_unicode_array( $UTF16_text, $MSB_first );

        // Create a string to receive the escaped HTML
        $htmloutput = "";

        // Cycle through the unicode character numbers
        foreach( $unicode_array as  $unichar )
        {
                // Check if the character needs to be escaped
                if ( ( $unichar >= 0x00 ) && ( $unichar <= 0x7F ) )
                {
                        // Character is less than 0x7F - add it to the html as is
                        $htmloutput .= chr( $unichar );
                }
                else
                {
                        // Character is greater than 0x7F - escape it and add it to the html
                        $htmloutput .= "&#x" . dechex($unichar) . ";";
                }
        }

        // Return the resulting escaped HTML
        return $htmloutput;
}

/******************************************************************************
* End of Function:     HTML_UTF16_Escape
******************************************************************************/


/******************************************************************************
*
* Function:     HTML_UTF16_UnEscape
*
* Description:  Converts HTML which contains escaped decimal or hex characters
*               into UTF-16 text
*
* Parameters:   HTML_text - a string containing the HTML text to be converted
*               MSB_first - True will cause processing as Big Endian UTF-16 (Motorola, MSB first)
*                           False will cause processing as Little Endian UTF-16 (Intel, LSB first)
*
* Returns:      utfoutput - a string containing the UTF-16 equivalent
*
******************************************************************************/

function HTML_UTF16_UnEscape( $HTML_text, $MSB_first )
{
        $utf8_text = HTML_UTF8_UnEscape( $HTML_text );

        return unicode_array_to_UTF16( UTF8_to_unicode_array( $utf8_text ), $MSB_first );
}

/******************************************************************************
* End of Function:     HTML_UTF16_UnEscape
******************************************************************************/




/******************************************************************************
*
* Function:     smart_HTML_Entities
*
* Description:  Performs the same function as HTML_Entities, but leaves entities
*               that are already escaped intact.
*
* Parameters:   HTML_text - a string containing the HTML text to be escaped
*
* Returns:      HTML_text_out - a string containing the escaped HTML text
*
******************************************************************************/

function smart_HTML_Entities( $HTML_text )
{
        // Get a table containing the HTML entities translations
        $translation_table = get_html_translation_table( HTML_ENTITIES );

        // Change the ampersand to translate to itself, to avoid getting &amp;
        $translation_table[ chr(38) ] = '&';

        // Perform replacements
        // Regular expression says: find an ampersand, check the text after it,
        // if the text after it is not one of the following, then replace the ampersand
        // with &amp;
        // a) any combination of up to 4 letters (upper or lower case) with at least 2 or 3 non whitespace characters, then a semicolon
        // b) a hash symbol, then between 2 and 7 digits
        // c) a hash symbol, an 'x' character, then between 2 and 7 digits
        // d) a hash symbol, an 'X' character, then between 2 and 7 digits
        return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,7}|#x[0-9]{2,7}|#X[0-9]{2,7};)/","&amp;" , strtr( $HTML_text, $translation_table ) );
}

/******************************************************************************
* End of Function:     smart_HTML_Entities
******************************************************************************/



/******************************************************************************
*
* Function:     smart_htmlspecialchars
*
* Description:  Performs the same function as htmlspecialchars, but leaves characters
*               that are already escaped intact.
*
* Parameters:   HTML_text - a string containing the HTML text to be escaped
*
* Returns:      HTML_text_out - a string containing the escaped HTML text
*
******************************************************************************/

function smart_htmlspecialchars( $HTML_text , $quotes=ENT_COMPAT)
{
        // Get a table containing the HTML special characters translations
        $translation_table=get_html_translation_table (HTML_SPECIALCHARS);

        // Change the ampersand to translate to itself, to avoid getting &amp;
        $translation_table[ chr(38) ] = '&';

        // Perform replacements
        // Regular expression says: find an ampersand, check the text after it,
        // if the text after it is not one of the following, then replace the ampersand
        // with &amp;
        // a) any combination of up to 4 letters (upper or lower case) with at least 2 or 3 non whitespace characters, then a semicolon
        // b) a hash symbol, then between 2 and 7 digits
        // c) a hash symbol, an 'x' character, then between 2 and 7 digits
        // d) a hash symbol, an 'X' character, then between 2 and 7 digits
        $str = preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,7}|#x[0-9]{2,7}|#X[0-9]{2,7};)/","&amp;" , strtr( $HTML_text, $translation_table ) );
        
        switch($quotes)
        {
        	case 0;	// ENT_NOQUOTES
        	break;
        	case 2:	// ENT_COMPAT
        		$str = str_replace('"','&quot;',$str);
        	break;
        	case 3: // ENT_QUOTES
        		$str = str_replace('"','&quot;',$str);
        		$str = str_replace("'",'&#039;',$str);
        	break;
        }
        
        return $str;
}

/******************************************************************************
* End of Function:     smart_htmlspecialchars
******************************************************************************/


?>