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

*
* Parameters:   unicode_array - the array containing unicode character numbers
*
* Returns:      output - the UTF-8 encoded string representing the data
*
******************************************************************************/

function unicode_array_to_UTF8( $unicode_array )
{

        // Create a string to receive the UTF-8 output
        $output = "";

        // Cycle through each Unicode character number
        foreach( $unicode_array as $unicode_char )
        {
                // Check which range the current unicode character lies in
                if ( ( $unicode_char >= 0x00 ) && ( $unicode_char <= 0x7F ) )
                {
                        // 1 Byte UTF-8 Unicode (7-Bit ASCII) Character

                        $output .= chr($unicode_char);          // Output is equal to input for 7-bit ASCII
                }
                else if ( ( $unicode_char >= 0x80 ) && ( $unicode_char <= 0x7FF ) )
                {
                        // 2 Byte UTF-8 Unicode - binary encode data as : 110xxxxx 10xxxxxx

                        $output .= chr(0xC0 + ($unicode_char/0x40));
                        $output .= chr(0x80 + ($unicode_char & 0x3F));
                }
                else if ( ( $unicode_char >= 0x800 ) && ( $unicode_char <= 0xFFFF ) )
                {
                        // 3 Byte UTF-8 Unicode - binary encode data as : 1110xxxx 10xxxxxx 10xxxxxx

                        $output .= chr(0xE0 + ($unicode_char/0x1000));
                        $output .= chr(0x80 + (($unicode_char/0x40) & 0x3F));
                        $output .= chr(0x80 + ($unicode_char & 0x3F));
                }
                else if ( ( $unicode_char >= 0x10000 ) && ( $unicode_char <= 0x1FFFFF ) )
                {
                        // 4 Byte UTF-8 Unicode - binary encode data as : 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx

                        $output .= chr(0xF0 + ($unicode_char/0x40000));
                        $output .= chr(0x80 + (($unicode_char/0x1000) & 0x3F));
                        $output .= chr(0x80 + (($unicode_char/0x40) & 0x3F));
                        $output .= chr(0x80 + ($unicode_char & 0x3F));
                }
                else if ( ( $unicode_char >= 0x200000 ) && ( $unicode_char <= 0x3FFFFFF ) )
                {
                        // 5 Byte UTF-8 Unicode - binary encode data as : 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx

                        $output .= chr(0xF8 + ($unicode_char/0x1000000));
                        $output .= chr(0x80 + (($unicode_char/0x40000) & 0x3F));
                        $output .= chr(0x80 + (($unicode_char/0x1000) & 0x3F));
                        $output .= chr(0x80 + (($unicode_char/0x40) & 0x3F));
                        $output .= chr(0x80 + ($unicode_char & 0x3F));
                }
                else if ( ( $unicode_char >= 0x4000000 ) && ( $unicode_char <= 0x7FFFFFFF ) )
                {
                        // 6 Byte UTF-8 Unicode - binary encode data as : 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx

                        $output .= chr(0xFC + ($unicode_char/0x40000000));
                        $output .= chr(0x80 + (($unicode_char/0x1000000) & 0x3F));
                        $output .= chr(0x80 + (($unicode_char/0x40000) & 0x3F));
                        $output .= chr(0x80 + (($unicode_char/0x1000) & 0x3F));
                        $output .= chr(0x80 + (($unicode_char/0x40) & 0x3F));
                        $output .= chr(0x80 + ($unicode_char & 0x3F));
                }
                else
                {
                        // Invalid Code - do nothing
                }

        }

        // Return resulting UTF-8 String
        return $output;
}

/******************************************************************************
* End of Function:     unicode_array_to_UTF8
******************************************************************************/









/******************************************************************************
*
* Function:     unicode_array_to_UTF16
*
* Description:  Converts an array of unicode character numbers to a string
*               encoded by UTF-16
*
* Parameters:   unicode_array - the array containing unicode character numbers
*               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:      output - the UTF-16 encoded string representing the data
*
******************************************************************************/

function unicode_array_to_UTF16( $unicode_array, $MSB_first )
{

        // Create a string to receive the UTF-16 output
        $output = "";

        // Cycle through each Unicode character number
        foreach( $unicode_array as $unicode_char )
        {
                // Check which range the current unicode character lies in
                if ( ( ( $unicode_char >= 0x0000 ) && ( $unicode_char <= 0xD7FF ) ) ||
                     ( ( $unicode_char >= 0xE000 ) && ( $unicode_char <= 0xFFFF ) ) )
                {
                        // Normal 16 Bit Character  (Not a Surrogate Pair)

                        // Check what byte order should be used
                        if ( $MSB_first )
                        {
                                // Big Endian
                                $output .= chr( $unicode_char / 0x100 ) . chr( $unicode_char % 0x100 ) ;
                        }
                        else
                        {
                                // Little Endian
                                $output .= chr( $unicode_char % 0x100 ) . chr( $unicode_char / 0x100 ) ;
                        }

                }
                else if ( ( $unicode_char >= 0x10000 ) && ( $unicode_char <= 0x10FFFF ) )
                {
                        // Surrogate Pair required

                        // Calculate Surrogates
                        $High_Surrogate = ( ( $unicode_char - 0x10000 ) / 0x400 ) + 0xD800;
                        $Low_Surrogate = ( ( $unicode_char - 0x10000 ) % 0x400 ) + 0xDC00;

                        // Check what byte order should be used
                        if ( $MSB_first )
                        {
                                // Big Endian
                                $output .= chr( $High_Surrogate / 0x100 ) . chr( $High_Surrogate % 0x100 );
                                $output .= chr( $Low_Surrogate / 0x100 ) . chr( $Low_Surrogate % 0x100 );
                        }
                        else
                        {
                                // Little Endian
                                $output .= chr( $High_Surrogate % 0x100 ) . chr( $High_Surrogate / 0x100 );
                                $output .= chr( $Low_Surrogate % 0x100 ) . chr( $Low_Surrogate / 0x100 );
                        }
                }
                else
                {
                        // Invalid UTF-16 codepoint
                        // Unicode value should never be between 0xD800 and 0xDFFF
                        // Do not output this point - there is no way to encode it in UTF-16
                }

        }

        // Return resulting UTF-16 String
        return $output;
}

/******************************************************************************
* End of Function:     unicode_array_to_UTF16
******************************************************************************/





/******************************************************************************
*
* Function:     xml_UTF8_clean
*
* Description:  XML has specific requirements about the characters that are
*               allowed, and characters that must be escaped.
*               This function ensures that all characters in the given string
*               are valid, and that characters such as Quotes, Greater than,
*               Less than and Ampersand are properly escaped. Newlines and Tabs
*               are also escaped.
*               Note - Do not use this on constructed XML which includes tags,
*                      as it will escape the tags. It is designed to be used
*                      on the tag and attribute names, attribute values, and text.
*
* Parameters:   utf8_text - a string containing the UTF-8 data
*
* Returns:      output - the array containing the unicode character numbers
*
******************************************************************************/

function xml_UTF8_clean( $UTF8_text )
{
        // Ensure that the Unicode UTF8 encoding is valid.

        $UTF8_text = UTF8_fix( $UTF8_text );


        // XML only allows characters in the following unicode ranges
        // #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
        // Hence we need to delete any characters that dont fit this

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

        // Create a new array to receive the valid unicode character numbers
        $new_unicode_array = array( );

        // Cycle through the unicode character numbers
        foreach( $unicode_array as  $unichar )
        {
                // Check if the unicode character number is valid for XML
                if ( ( $unichar == 0x09 ) ||
                     ( $unichar == 0x0A ) ||
                     ( $unichar == 0x0D ) ||
                     ( ( $unichar >= 0x20 ) && ( $unichar <= 0xD7FF ) ) ||
                     ( ( $unichar >= 0xE000 ) && ( $unichar <= 0xFFFD ) ) ||
                     ( ( $unichar >= 0x10000 ) && ( $unichar <= 0x10FFFF ) ) )
                {
                       // Unicode character is valid for XML - add it to the valid characters array
                       $new_unicode_array[] = $unichar;
                }

        }

        // Convert the array of valid unicode character numbers back to UTF-8 encoded text
        $UTF8_text = unicode_array_to_UTF8( $new_unicode_array );

        // Escape any special HTML characters present
        $UTF8_text =  htmlspecialchars ( $UTF8_text, ENT_QUOTES );

        // Escape CR, LF and TAB characters, so that they are kept and not treated as expendable white space
        $trans = array( "\x09" => "&#x09;", "\x0A" => "&#x0A;", "\x0D" => "&#x0D;" );
        $UTF8_text = strtr( $UTF8_text, $trans );

        // Return the resulting XML valid string
        return $UTF8_text;
}

/******************************************************************************
* End of Function:     xml_UTF8_clean
******************************************************************************/









/******************************************************************************
*
* Function:     xml_UTF16_clean
*
* Description:  XML has specific requirements about the characters that are
*               allowed, and characters that must be escaped.
*               This function ensures that all characters in the given string
*               are valid, and that characters such as Quotes, Greater than,
*               Less than and Ampersand are properly escaped. Newlines and Tabs
*               are also escaped.
*               Note - Do not use this on constructed XML which includes tags,
*                      as it will escape the tags. It is designed to be used
*                      on the tag and attribute names, attribute values, and text.
*
* 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:      output - the array containing the unicode character numbers
*
******************************************************************************/

function xml_UTF16_clean( $UTF16_text, $MSB_first )
{
        // Ensure that the Unicode UTF16 encoding is valid.

        $UTF16_text = UTF16_fix( $UTF16_text, $MSB_first );


        // XML only allows characters in the following unicode ranges
        // #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
        // Hence we need to delete any characters that dont fit this

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

        // Create a new array to receive the valid unicode character numbers
        $new_unicode_array = array( );

        // Cycle through the unicode character numbers
        foreach( $unicode_array as  $unichar )
        {
                // Check if the unicode character number is valid for XML
                if ( ( $unichar == 0x09 ) ||
                     ( $unichar == 0x0A ) ||
                     ( $unichar == 0x0D ) ||
                     ( ( $unichar >= 0x20 ) && ( $unichar <= 0xD7FF ) ) ||
                     ( ( $unichar >= 0xE000 ) && ( $unichar <= 0xFFFD ) ) ||
                     ( ( $unichar >= 0x10000 ) && ( $unichar <= 0x10FFFF ) ) )
                {
                       // Unicode character is valid for XML - add it to the valid characters array
                       $new_unicode_array[] = $unichar;
                }