xmlvalid.cpp

linux下的一款播放器

/* ***** BEGIN LICENSE BLOCK *****
 * Source last modified: $Id: xmlvalid.cpp,v 1.4.32.3 2004/07/09 01:44:10 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 "hxtypes.h"
#include "hxcom.h"
#include "hxassert.h"

#ifdef XXXJHUG
#include "hlxclib/stdio.h"
#endif /* XXXJHUG */
#include "hlxclib/stdlib.h"
#include "xmlvalid.h"
#include "hlxclib/string.h"

BOOL ISO8859Valid::IsNameValid(const BYTE* p, UINT32 len)
{
    BOOL bValid = IsLetter(*p) || IsDigit(*p) || *p == '_' || *p == ':';

    for (const BYTE* end = p + len; bValid && *p && p < end; ++p )
    {
	bValid = IsLetter(*p) || IsDigit(*p) || *p == '.' ||
	    *p == '-' || *p == '_' || *p == ':' || 
	    IsCombiningChar(*p);
    }

    return bValid;
}

BOOL ISO8859Valid::IsNmtokenValid(const BYTE* p, UINT32 len)
{
    BOOL bValid = TRUE;
    
    for (const BYTE* end = p + len; bValid && *p && p < end; ++p )
    {
	bValid = IsLetter(*p) || IsDigit(*p) || *p == '.' ||
	    *p == '-' || *p == '_' || *p == ':' || 
	    IsCombiningChar(*p);
    }

    return bValid;
}


// assume that string has allready been parsed for ' and "
//::=  '"' ([^%&"] | PEReference | Reference)* '"'  
//   |  "'" ([^%&'] | PEReference | Reference)* "'" 
BOOL ISO8859Valid::IsEntityValueValid(const BYTE* p, UINT32 len)
{
    BOOL bValid = TRUE;
    const BYTE* pBeginRef = NULL;
    
    for (const BYTE* end = p + len; bValid && *p && p < end; ++p )
    {
	if ( *p == '&' || *p == '%' )
	{
	    pBeginRef = p;
	}
	else if (pBeginRef && *p == ';')
	{
	    bValid = IsRefValid(pBeginRef + 1, p - pBeginRef - 1);
	    pBeginRef = NULL;
	}
    }
    return bValid;
}

BOOL ISO8859Valid::IsRefValid(const BYTE *p, UINT32 len)
{
    BOOL bValid = FALSE;
    HX_ASSERT(*(p -1) == '&');
    // ref - 0 - nothing, '&' - beginning of Refference
    //	     'n' - beginning of number
    //	     'h' - hex number
    //	     'd' - decimal number
    //	     'e' - entity reference
    BYTE ref = '&';
    const BYTE* pBeginRef = NULL;
    
    for (const BYTE* end = p + len; bValid && *p && p < end; ++p )
    {
	switch ( ref )
	{
	case '&':
	    if ( *p == '#' )
	    {
		ref = 'n';
	    }
	    else
	    {
		ref = 'e';
		pBeginRef = p;
	    }
	    break;
	case 'n':
	    if (*p == 'x' || *p == 'X')
	    {
		ref = 'h';
	    }
	    else
	    {
		ref = 'd';
		bValid = IsDigit(*p);
	    }
	    break;
	case 'd':
	    if ( *p == ';' )
	    {
		ref = '\0';
	    }
	    else 
	    {
		bValid = IsDigit(*p);
	    }
	    break;
	case 'h':
	    if ( *p == ';' )
	    {
		ref = '\0';
	    }
	    else
	    {
		bValid = IsDigit(*p) || BETWEEN(*p, 'a', 'f') 
		    || BETWEEN(*p, 'A', 'F');
	    }
	    break;
	case 'e':
	    if ( *p == ';' )
	    {
		// this could be checked as we go in a single pass.
		bValid = IsNameValid(pBeginRef, p - pBeginRef);
		pBeginRef = NULL;
		ref = '\0';
	    }
	    break;
	case '\0':
	    return bValid;
	}
    }
    return bValid;
}


// assume that string has allready been parsed for ' and "
// AttValue ::=  '"' ([^<&"] | Reference)* '"'  
//   |  "'" ([^<&'] | Reference)* "'" 
BOOL ISO8859Valid::IsAttValueValid(const BYTE* p, UINT32 len)
{
    BOOL bValid = TRUE;
    const BYTE* pBeginRef = NULL;
    
    for (const BYTE* end = p + len; bValid && *p && p < end; ++p )
    {
	if ( *p == '&' )
	{
	    bValid = FALSE;
	    pBeginRef = p;
	}
	else if (*p == '<')
	{
	    bValid = FALSE;
	}
	else if (pBeginRef && *p == ';')
	{
	    bValid = IsRefValid(pBeginRef + 1, p - pBeginRef - 1);
	    pBeginRef = NULL;
	}
    }
    return bValid;
}

//SystemLiteral ::=  ('"' [^"]* '"') | ("'" [^']* "'")  
// assuming that the deliminators have allready been parsed.
// there fore system literals should allways be valid.
BOOL ISO8859Valid::IsSystemLiteralValid(const BYTE* p, UINT32 len)
{
    return TRUE;
}

// Public ID Literal
//[12]  PubidLiteral ::=  '"' PubidChar* '"' | "'" (PubidChar - "'")* "'" 
//[13]  PubidChar ::=  #x20 | #xD | #xA | [a-zA-Z0-9] | [] 
BOOL ISO8859Valid::IsPubidLiteralValid(const BYTE* p, UINT32 len)
{
    BOOL bValid = TRUE;
    for (const BYTE* end = p + len; bValid && *p && p < end; ++p )
    {
	bValid = *p == 0x20 || *p == 0xD || *p == 0xA || BETWEEN(*p, 'a', 'z') || 
	    BETWEEN(*p, 'A', 'Z') || BETWEEN(*p, '0', '9') || strchr("-()+,./:=?;!*#@$_%", *p);
    }

    return bValid;
}


inline BOOL ISO8859Valid::IsLetter(const BYTE c)
{
    return IsBaseChar(c) || IsIdeographic(c);
}

inline BOOL ISO8859Valid::IsBaseChar(const BYTE c)
{
    return BETWEEN(c, 0x41, 0x5A) || BETWEEN(c, 0x61, 0x7A) || 
	   BETWEEN(c, 0xC0, 0xD6) || BETWEEN(c, 0xD8, 0xF6) ||
	   BETWEEN(c, 0xF8, 0xFF);
}

inline BOOL ISO8859Valid::IsIdeographic(const BYTE c)
{
    return FALSE;
}

inline BOOL ISO8859Valid::IsCombiningChar(const BYTE c)
{
    return FALSE;
}

inline BOOL ISO8859Valid::IsDigit(const BYTE c)
{
    return BETWEEN(c, 0x30, 0x39);
}

inline BOOL ISO8859Valid::IsExtender(const BYTE c)
{
    return c == 0xB7;
}



BOOL UTF16Valid::IsNameValid(const UINT16* p, UINT32 len)
{
    BOOL bValid = IsLetter(*p) || IsDigit(*p) || *p == '_' || *p == ':';

    for (const UINT16* end = p + len; bValid && *p && p < end; ++p )
    {
	bValid = IsLetter(*p) || IsDigit(*p) || *p == '.' ||
	    *p == '-' || *p == '_' || *p == ':' || 
	    IsCombiningChar(*p);
    }

    return bValid;
}

BOOL UTF16Valid::IsNmtokenValid(const UINT16* p, UINT32 len)
{
    BOOL bValid = TRUE;
    
    for (const UINT16* end = p + len; bValid && *p && p < end; ++p )
    {
	bValid = IsLetter(*p) || IsDigit(*p) || *p == '.' ||
	    *p == '-' || *p == '_' || *p == ':' || 
	    IsCombiningChar(*p);
    }