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

<?php

/******************************************************************************
*
* Filename:     Unicode.php
*
* Description:  Provides functions for handling Unicode strings in PHP without
*               needing to configure the non-default mbstring extension
*
* Author:       Evan Hunter
*
* Date:         27/7/2004
*
* Project:      JPEG Metadata
*
* Revision:     1.10
*
* Changes:      1.00 -> 1.10 : Added the following functions:
*                              smart_HTML_Entities
*                              smart_htmlspecialchars
*                              HTML_UTF16_UnEscape
*                              HTML_UTF8_UnEscape
*                              changed HTML_UTF8_Escape and HTML_UTF16_Escape to
*                              use smart_htmlspecialchars, so that characters which
*                              were already escaped would remain intact
*
*
* URL:          http://electronics.ozhiker.com
*
* License:      This file is part of the PHP JPEG Metadata Toolkit.
*
*               The PHP JPEG Metadata Toolkit 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.
*
*               The PHP JPEG Metadata Toolkit 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 General Public License
*               for more details.
*
*               You should have received a copy of the GNU General Public
*               License along with the PHP JPEG Metadata Toolkit; if not,
*               write to the Free Software Foundation, Inc., 59 Temple
*               Place, Suite 330, Boston, MA  02111-1307  USA
*
*               If you require a different license for commercial or other
*               purposes, please contact the author: [e-mail]
*
******************************************************************************/


// TODO: UTF-16 functions have not been tested fully



/******************************************************************************
*
* Unicode UTF-8 Encoding Functions
*
* Description:  UTF-8 is a Unicode encoding system in which extended characters
*               use only the upper half (128 values) of the byte range, thus it
*               allows the use of normal 7-bit ASCII text.
*               7-Bit ASCII will pass straight through UTF-8 encoding/decoding without change
*
*
* The encoding is as follows:
* Unicode Value          :  Binary representation (x=data bit)
*--------------------------------------------------------------------------------
* U-00000000 - U-0000007F:  0xxxxxxx                      <- This is 7-bit ASCII
* U-00000080 - U-000007FF:  110xxxxx 10xxxxxx
* U-00000800 - U-0000FFFF:  1110xxxx 10xxxxxx 10xxxxxx
* U-00010000 - U-001FFFFF:  11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
* U-00200000 - U-03FFFFFF:  111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
* U-04000000 - U-7FFFFFFF:  1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
*--------------------------------------------------------------------------------
*
******************************************************************************/




/******************************************************************************
*
* Unicode UTF-16 Encoding Functions
*
* Description:  UTF-16 is a Unicode encoding system uses 16 bit values for representing
*               characters.
*               It also has an extended set of characters available by the use
*               of surrogate pairs, which are a pair of 16 bit values, giving a
*               total data length of 20 useful bits.
*
*
* The encoding is as follows:
* Unicode Value          :  Binary representation (x=data bit)
*--------------------------------------------------------------------------------
* U-000000 - U-00D7FF:  xxxxxxxx xxxxxxxx
* U-00D800 - U-00DBFF:  Not available - used for high surrogate pairs
* U-00DC00 - U-00DFFF:  Not available - used for low surrogate pairs
  U-00E000 - U-00FFFF:  xxxxxxxx xxxxxxxx
* U-010000 - U-10FFFF:  110110ww wwxxxxxx  110111xx xxxxxxxx      ( wwww = (uni-0x10000)/0x10000 )
*--------------------------------------------------------------------------------
*
*  Surrogate pair Calculations
*
*  $hi = ($uni - 0x10000) / 0x400 + 0xD800;
*  $lo = ($uni - 0x10000) % 0x400 + 0xDC00;
*
*
*  $uni = 0x10000 + ($hi - 0xD800) * 0x400 + ($lo - 0xDC00);
*
*
******************************************************************************/






/******************************************************************************
*
* Function:     UTF8_fix
*
* Description:  Checks a string for badly formed Unicode UTF-8 coding and
*               returns the same string containing only the parts which
*               were properly formed UTF-8 data.
*
* Parameters:   utf8_text - a string with possibly badly formed UTF-8 data
*
* Returns:      output - the well formed UTF-8 version of the string
*
******************************************************************************/

function UTF8_fix( $utf8_text )
{
        // Initialise the current position in the string
        $pos = 0;

        // Create a string to accept the well formed output
        $output = "" ;

        // Cycle through each group of bytes, ensuring the coding is correct
        while ( $pos < strlen( $utf8_text ) )
        {
                // Retreive the current numerical character value
                $chval = ord($utf8_text{$pos});

                // Check what the first character is - it will tell us how many bytes the
                // Unicode value covers

                if ( ( $chval >= 0x00 ) && ( $chval <= 0x7F ) )
                {
                        // 1 Byte UTF-8 Unicode (7-Bit ASCII) Character
                        $bytes = 1;
                }
                else if ( ( $chval >= 0xC0 ) && ( $chval <= 0xDF ) )
                {
                        // 2 Byte UTF-8 Unicode Character
                        $bytes = 2;
                }
                else if ( ( $chval >= 0xE0 ) && ( $chval <= 0xEF ) )
                {
                        // 3 Byte UTF-8 Unicode Character
                        $bytes = 3;
                }
                else if ( ( $chval >= 0xF0 ) && ( $chval <= 0xF7 ) )
                {
                        // 4 Byte UTF-8 Unicode Character
                        $bytes = 4;
                }
                else if ( ( $chval >= 0xF8 ) && ( $chval <= 0xFB ) )
                {
                        // 5 Byte UTF-8 Unicode Character
                        $bytes = 5;
                }
                else if ( ( $chval >= 0xFC ) && ( $chval <= 0xFD ) )
                {
                        // 6 Byte UTF-8 Unicode Character
                        $bytes = 6;
                }
                else
                {
                        // Invalid Code - skip character and do nothing
                        $bytes = 0;
                        $pos++;
                }


                // check that there is enough data remaining to read
                if (($pos + $bytes - 1) < strlen( $utf8_text ) )
                {
                        // Cycle through the number of bytes specified,
                        // copying them to the output string
                        while ( $bytes > 0 )
                        {
                                $output .= $utf8_text{$pos};
                                $pos++;
                                $bytes--;
                        }
                }
                else
                {
                        break;
                }
        }

        // Return the result
        return $output;
}

/******************************************************************************
* End of Function:     UTF8_fix
******************************************************************************/









/******************************************************************************
*
* Function:     UTF16_fix
*
* Description:  Checks a string for badly formed Unicode UTF-16 coding and
*               returns the same string containing only the parts which
*               were properly formed UTF-16 data.
*
* Parameters:   utf16_text - a string with possibly badly formed 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 well formed UTF-16 version of the string
*
******************************************************************************/

function UTF16_fix( $utf16_text, $MSB_first )
{
        // Initialise the current position in the string
        $pos = 0;

        // Create a string to accept the well formed output
        $output = "" ;

        // Cycle through each group of bytes, ensuring the coding is correct
        while ( $pos < strlen( $utf16_text ) )
        {
                // Retreive the current numerical character value
                $chval1 = ord($utf16_text{$pos});

                // Skip over character just read
                $pos++;

                // Check if there is another character available
                if ( $pos  < strlen( $utf16_text ) )
                {
                        // Another character is available - get it for the second half of the UTF-16 value
                        $chval2 = ord( $utf16_text{$pos} );
                }
                else
                {
                        // Error - no second byte to this UTF-16 value - end processing
                        continue 1;
                }

                // Skip over character just read
                $pos++;

                // Calculate the 16 bit unicode value
                if ( $MSB_first )
                {
                        // Big Endian
                        $UTF16_val = $chval1 * 0x100 + $chval2;
                }
                else
                {
                        // Little Endian
                        $UTF16_val = $chval2 * 0x100 + $chval1;
                }



                if ( ( ( $UTF16_val >= 0x0000 ) && ( $UTF16_val <= 0xD7FF ) ) ||
                     ( ( $UTF16_val >= 0xE000 ) && ( $UTF16_val <= 0xFFFF ) ) )
                {
                        // Normal Character (Non Surrogate pair)
                        // Add it to the output
                        $output .= chr( $chval1 ) . chr ( $chval2 );
                }
                else if ( ( $UTF16_val >= 0xD800 ) && ( $UTF16_val <= 0xDBFF ) )
                {
                        // High surrogate of a surrogate pair
                        // Now we need to read the low surrogate
                        // Check if there is another 2 characters available
                        if ( ( $pos + 3 ) < strlen( $utf16_text ) )
                        {
                                // Another 2 characters are available - get them
                                $chval3 = ord( $utf16_text{$pos} );
                                $chval4 = ord( $utf16_text{$pos+1} );

                                // Calculate the second 16 bit unicode value
                                if ( $MSB_first )
                                {
                                        // Big Endian
                                        $UTF16_val2 = $chval3 * 0x100 + $chval4;
                                }
                                else