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

                                {
                                        // Little Endian
                                        $UTF16_val2 = $chval4 * 0x100 + $chval3;
                                }

                                // Check that this is a low surrogate
                                if ( ( $UTF16_val2 >= 0xDC00 ) && ( $UTF16_val2 <= 0xDFFF ) )
                                {
                                        // Low surrogate found following high surrogate
                                        // Add both to the output
                                        $output .= chr( $chval1 ) . chr ( $chval2 ) . chr( $chval3 ) . chr ( $chval4 );

                                        // Skip over the low surrogate
                                        $pos += 2;
                                }
                                else
                                {
                                        // Low surrogate not found after high surrogate
                                        // Don't add either to the output
                                        // Only the High surrogate is skipped and processing continues after it
                                }

                        }
                        else
                        {
                                // Error - not enough data for low surrogate - end processing
                                continue 1;
                        }

                }
                else
                {
                        // Low surrogate of a surrogate pair
                        // This should not happen - it means this is a lone low surrogate
                        // Dont add it to the output
                }

        }

        // Return the result
        return $output;
}

/******************************************************************************
* End of Function:     UTF16_fix
******************************************************************************/





/******************************************************************************
*
* Function:     UTF8_to_unicode_array
*
* Description:  Converts a string encoded with Unicode UTF-8, to an array of
*               numbers which represent unicode character numbers
*
* Parameters:   utf8_text - a string containing the UTF-8 data
*
* Returns:      output - the array containing the unicode character numbers
*
******************************************************************************/

function UTF8_to_unicode_array( $utf8_text )
{
        // Create an array to receive the unicode character numbers output
        $output = array( );

        // Cycle through the characters in the UTF-8 string
        for ( $pos = 0; $pos < strlen( $utf8_text ); $pos++ )
        {
                // 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;
                        $outputval = $chval;    // Since 7-bit ASCII is unaffected, the output equals the input
                }
                else if ( ( $chval >= 0xC0 ) && ( $chval <= 0xDF ) )
                {
                        // 2 Byte UTF-8 Unicode
                        $bytes = 2;
                        $outputval = $chval & 0x1F;     // The first byte is bitwise ANDed with 0x1F to remove the leading 110b
                }
                else if ( ( $chval >= 0xE0 ) && ( $chval <= 0xEF ) )
                {
                        // 3 Byte UTF-8 Unicode
                        $bytes = 3;
                        $outputval = $chval & 0x0F;     // The first byte is bitwise ANDed with 0x0F to remove the leading 1110b
                }
                else if ( ( $chval >= 0xF0 ) && ( $chval <= 0xF7 ) )
                {
                        // 4 Byte UTF-8 Unicode
                        $bytes = 4;
                        $outputval = $chval & 0x07;     // The first byte is bitwise ANDed with 0x07 to remove the leading 11110b
                }
                else if ( ( $chval >= 0xF8 ) && ( $chval <= 0xFB ) )
                {
                        // 5 Byte UTF-8 Unicode
                        $bytes = 5;
                        $outputval = $chval & 0x03;     // The first byte is bitwise ANDed with 0x03 to remove the leading 111110b
                }
                else if ( ( $chval >= 0xFC ) && ( $chval <= 0xFD ) )
                {
                        // 6 Byte UTF-8 Unicode
                        $bytes = 6;
                        $outputval = $chval & 0x01;     // The first byte is bitwise ANDed with 0x01 to remove the leading 1111110b
                }
                else
                {
                        // Invalid Code - do nothing
                        $bytes = 0;
                }

                // Check if the byte was valid
                if ( $bytes !== 0 )
                {
                        // The byte was valid

                        // Check if there is enough data left in the UTF-8 string to allow the
                        // retrieval of the remainder of this unicode character
                        if ( $pos + $bytes - 1 < strlen( $utf8_text ) )
                        {
                                // The UTF-8 string is long enough

                                // Cycle through the number of bytes required,
                                // minus the first one which has already been done
                                while ( $bytes > 1 )
                                {
                                        $pos++;
                                        $bytes--;

                                        // Each remaining byte is coded with 6 bits of data and 10b on the high
                                        // order bits. Hence we need to shift left by 6 bits (0x40) then add the
                                        // current characer after it has been bitwise ANDed with 0x3F to remove the
                                        // highest two bits.
                                        $outputval = $outputval*0x40 + ( (ord($utf8_text{$pos})) & 0x3F );
                                }

                                // Add the calculated Unicode number to the output array
                                $output[] = $outputval;
                        }
                }

        }

        // Return the resulting array
        return $output;
}

/******************************************************************************
* End of Function:     UTF8_to_unicode_array
******************************************************************************/





/******************************************************************************
*
* Function:     UTF16_to_unicode_array
*
* Description:  Converts a string encoded with Unicode UTF-16, to an array of
*               numbers which represent unicode character numbers
*
* 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 UTF16_to_unicode_array( $utf16_text, $MSB_first )
{
        // Create an array to receive the unicode character numbers output
        $output = array( );


        // Initialise the current position in the string
        $pos = 0;

        // 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[] = $UTF16_val;
                }
                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
                                {
                                        // Little Endian
                                        $UTF16_val2 = $chval4 * 0x100 + $chval3;
                                }

                                // Check that this is a low surrogate
                                if ( ( $UTF16_val2 >= 0xDC00 ) && ( $UTF16_val2 <= 0xDFFF ) )
                                {
                                        // Low surrogate found following high surrogate
                                        // Add both to the output
                                        $output[] = 0x10000 + ( ( $UTF16_val - 0xD800 ) * 0x400 ) + ( $UTF16_val2 - 0xDC00 );

                                        // Skip over the low surrogate
                                        $pos += 2;
                                }
                                else
                                {
                                        // Low surrogate not found after high surrogate
                                        // Don't add either to the output
                                        // The high surrogate is skipped and processing continued
                                }

                        }
                        else
                        {
                                // Error - not enough data for low surrogate - end processing
                                continue 1;
                        }

                }
                else
                {
                        // Low surrogate of a surrogate pair
                        // This should not happen - it means this is a lone low surrogate
                        // Don't add it to the output
                }

        }

        // Return the result
        return $output;


}

/******************************************************************************
* End of Function:     UTF16_to_unicode_array
******************************************************************************/







/******************************************************************************
*
* Function:     unicode_array_to_UTF8
*
* Description:  Converts an array of unicode character numbers to a string
*               encoded by UTF-8