hxstringutils.c

linux下的一款播放器

/* ***** BEGIN LICENSE BLOCK *****
 * Source last modified: $Id: HXStringUtils.c,v 1.2.2.3 2004/07/09 01:49:35 hubbe Exp $
 * 
 * Portions Copyright (c) 1995-2004 RealNetworks, Inc. All Rights Reserved.
 * 
 * The contents of this file, and the files included with this file,
 * are subject to the current version of the RealNetworks Public
 * Source License (the "RPSL") available at
 * http://www.helixcommunity.org/content/rpsl unless you have licensed
 * the file under the current version of the RealNetworks Community
 * Source License (the "RCSL") available at
 * http://www.helixcommunity.org/content/rcsl, in which case the RCSL
 * will apply. You may also obtain the license terms directly from
 * RealNetworks.  You may not use this file except in compliance with
 * the RPSL or, if you have a valid RCSL with RealNetworks applicable
 * to this file, the RCSL.  Please see the applicable RPSL or RCSL for
 * the rights, obligations and limitations governing use of the
 * contents of the file.
 * 
 * Alternatively, the contents of this file may be used under the
 * terms of the GNU General Public License Version 2 or later (the
 * "GPL") in which case the provisions of the GPL are applicable
 * instead of those above. If you wish to allow use of your version of
 * this file only under the terms of the GPL, and not to allow others
 * to use your version of this file under the terms of either the RPSL
 * or RCSL, indicate your decision by deleting the provisions above
 * and replace them with the notice and other provisions required by
 * the GPL. If you do not delete the provisions above, a recipient may
 * use your version of this file under the terms of any one of the
 * RPSL, the RCSL or the GPL.
 * 
 * This file is part of the Helix DNA Technology. RealNetworks is the
 * developer of the Original Code and owns the copyrights in the
 * portions it created.
 * 
 * This file, and the files included with this file, is distributed
 * and made available on an 'AS IS' basis, WITHOUT WARRANTY OF ANY
 * KIND, EITHER EXPRESS OR IMPLIED, AND REALNETWORKS HEREBY DISCLAIMS
 * ALL SUCH WARRANTIES, INCLUDING WITHOUT LIMITATION, ANY WARRANTIES
 * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, QUIET
 * ENJOYMENT OR NON-INFRINGEMENT.
 * 
 * Technology Compatibility Kit Test Suite(s) Location:
 *    http://www.helixcommunity.org/content/tck
 * 
 * Contributor(s):
 * 
 * ***** END LICENSE BLOCK ***** */

#include "HXStringUtils.h"

/* UTF-8 should only contain octets with the top bit set in one of the
  patterns:
  - one octet 0xC2 to 0xDF, then one octet 0x80 to 0xBF
  - one octet 0xE0 to 0xEF, then two octets 0x80 to 0xBF
  - one octet 0xF0 to 0xF7, then three octets 0x80 to 0xBF
  - one octet 0xF8 to 0xFB, then four octets 0x80 to 0xBF
  - one octet 0xFC to 0xFD, then five octets 0x80 to 0xBF
*/

CFStringEncoding
GuessEncodingForCString( const unsigned char * pszChars )
{
	const unsigned char* pszCursor = pszChars;
	int groupSize;
	UInt8 testChar;
	int idx;

	while ( *pszCursor != 0 )
	{
		testChar = *pszCursor;

		if ( testChar < 0x80 )
		{
			// high bit not set, so it's fine for UTF-8
		}
		else
		{
			// high bit is set
			if      ( testChar >= 0xC2 && testChar <= 0xDF ) groupSize = 1;
			else if ( testChar >= 0xE0 && testChar <= 0xEF ) groupSize = 2;
			else if ( testChar >= 0xF0 && testChar <= 0xF7 ) groupSize = 3;
			else if ( testChar >= 0xF8 && testChar <= 0xFB ) groupSize = 4;
			else if ( testChar >= 0xFC && testChar <= 0xFD ) groupSize = 5;
			else
			{
				// high bit is set and it's lacking a UTF-8 group marker
				// XXXSEH: We're assuming most all content will be encoded either in UTF-8 or in Windows.
				return kCFStringEncodingWindowsLatin1; // CFStringGetSystemEncoding();
			}
			
			for ( idx = 0; idx < groupSize; idx++ )
			{
				++pszCursor;
				testChar = *pszCursor;

				if ( testChar < 0x80 || testChar > 0xBF )
				{
					return kCFStringEncodingWindowsLatin1; // CFStringGetSystemEncoding();
				}
			}
		}
		++pszCursor;
	}
	return kCFStringEncodingUTF8;
}