xmlesc.cpp

来自「symbian 下的helix player源代码」· C++ 代码 · 共 1,586 行 · 第 1/4 页

/* ***** BEGIN LICENSE BLOCK *****
 * Source last modified: $Id: xmlesc.cpp,v 1.8.2.1 2004/07/19 21:04:07 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 ***** */

//   $Id: xmlesc.cpp,v 1.8.2.1 2004/07/19 21:04:07 hubbe Exp $

/*******************************************************************
 *
 *  NAME:	xmlesc.cpp
 *
 *  CLASS
 *	CEscapeXMLtoHTML
 *
 *  DESCRIPTION:
 *	The implmentation for a class that escapes all the XML characters
 *	that are not printable in HTML.  A IHXBuffer is passed into the
 *	class on throgh the Convert Method. This is a pure virtual class.
 *	The CheckTag, and OnTag functions must be implemented in a child
 *	class.
 *
 *  NOTES:
 *	Started with Mozilla's ColorHTML function
 *		
 *******************************************************************/

#include "hxcom.h"     /* IUnknown */
#include "hxtypes.h" 
#include "hxbuffer.h"
#include "hxiids.h"
#include "hxstrutl.h"
#include "hxstring.h"
#include "perplex.h"
#include "rtsputil.h"

#include "growingq.h"
#include "xmlesc.h"
#include "vsrcinfo.h"

#include "hlxclib/string.h"

/*___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 * Static variable declarations
 *___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~*/
const char* const
CEscapeXMLtoHTML::m_pDefaultTags[20] = 
{
     tag_BEGIN_TAG
    ,tag_END_TAG
    ,tag_BEGIN_TAG_NAME
    ,tag_END_TAG_NAME
    ,tag_BEGIN_ATTRIBUTE
    ,tag_END_ATTRIBUTE
    ,tag_BEGIN_BROKEN_ATT
    ,tag_END_BROKEN_ATT
    ,tag_BEGIN_COMMENT
    ,tag_END_COMMENT
    ,tag_BEGIN_AMPERSAND
    ,tag_END_AMPERSAND
    ,tag_BEGIN_HREF
    ,tag_END_HREF
    ,tag_PROCESSING_INSTRUCTIONS
    ,tag_END_PI
    ,tag_BEGIN_CDATA
    ,tag_END_CDATA
    ,tag_BEGIN_DTD
    ,tag_END_DTD
};

const char* const
CEscapeXMLtoHTML::m_pStyleTags[20] =
{
     style_BEGIN_TAG
    ,style_END_TAG
    ,style_BEGIN_TAG_NAME
    ,style_END_TAG_NAME
    ,style_BEGIN_ATTRIBUTE
    ,style_END_ATTRIBUTE
    ,style_BEGIN_BROKEN_ATT
    ,style_END_BROKEN_ATT
    ,style_BEGIN_COMMENT
    ,style_END_COMMENT
    ,style_BEGIN_AMPERSAND
    ,style_END_AMPERSAND
    ,style_BEGIN_HREF
    ,style_END_HREF
    ,style_PROCESSING_INSTRUCTIONS
    ,style_END_PI
    ,style_BEGIN_CDATA
    ,style_END_CDATA
    ,style_BEGIN_DTD
    ,style_END_DTD
};

/*___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 * Public Methods
 *___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~*/
/*___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *  CEscapeXMLtoHTML(pServerUrl, pOurPath)
 *
 *  PARAMETERS:
 *	pServerUrl  Full url to the server including the template file. 
 *	pOurPath    The Relative path of the file currently being parsed
 *		    no trailing "/"
 *	bMangleLinks    - to mangle or not
 *	bUseStyles	- output in styles or regular HTML
 *	pHotTags	- The tags that we will call OnTag For.
 *	pDefaultView    - The default viewsource to use for remote rstp
 *			  links ":port/viewmount/viewfile"
 *  DESCRIPTION:
 *	Constructor.
 *	This is the primary means of creating an instance of CEscapeXMLtoHTML.
 *___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~*/
CEscapeXMLtoHTML::CEscapeXMLtoHTML(IHXValues* pOptions, const char** pHotTags) 
: m_pEscapeStrings(NULL)
, m_pServerUrl(NULL)
, m_pOurPath(NULL)
, m_pHotTags(NULL)
, m_pDefaultView(NULL)
, m_pFileName(NULL)
, m_pRamGen(NULL)
, m_ulModDate(0)
, m_ulFileSize(0)
{
    m_pHotTags = pHotTags;

    IHXBuffer* pViewURL = NULL;
    IHXBuffer* pCurrentPath = NULL;
    IHXBuffer* pRemoteView = NULL;
    IHXBuffer* pFileName = NULL;
    UINT32 ulMangle = 0;
    UINT32 ulStyles = 0;
    if ( FAILED(pOptions->GetPropertyCString("ViewSourceURL", pViewURL)) ||
	 FAILED(pOptions->GetPropertyCString("CurrentPath", pCurrentPath)) ||
	 FAILED(pOptions->GetPropertyULONG32("HidePaths", ulMangle)) ||
	 FAILED(pOptions->GetPropertyULONG32("UseStyles", ulStyles)) ||
	 FAILED(pOptions->GetPropertyCString("RemoteViewSourceURL", pRemoteView)) ||
	 FAILED(pOptions->GetPropertyCString("FileName", pFileName)) ||
	 FAILED(pOptions->GetPropertyULONG32("ModificationTime", m_ulModDate)) ||
	 FAILED(pOptions->GetPropertyULONG32("FileSize", m_ulFileSize)) )
    {
	HX_ASSERT(FALSE);
	// return HXR_INVALID_PARAMETER;
    }

    m_bMangleLinks = ulMangle ? TRUE : FALSE;
    BOOL bUseStyles = ulStyles ? TRUE : FALSE;

    m_pServerUrl = new char[pViewURL->GetSize()+1];
    strcpy(m_pServerUrl, (char*)pViewURL->GetBuffer()); /* Flawfinder: ignore */

    m_pOurPath = new char[pCurrentPath->GetSize()+1];
    strcpy(m_pOurPath, (char*)pCurrentPath->GetBuffer()); /* Flawfinder: ignore */

    m_pDefaultView = new char[pRemoteView->GetSize()+1];
    strcpy(m_pDefaultView, (char*)pRemoteView->GetBuffer()); /* Flawfinder: ignore */

    m_pFileName = new char[pFileName->GetSize()+1];
    strcpy(m_pFileName, (char*)pFileName->GetBuffer()); /* Flawfinder: ignore */

    IHXBuffer* pRamGen = NULL;
    if ( SUCCEEDED(pOptions->GetPropertyCString("RamGenURL", pRamGen)) )
    {
	m_pRamGen = new char[pRamGen->GetSize()+1];
	strcpy(m_pRamGen, (char*)pRamGen->GetBuffer()); /* Flawfinder: ignore */
    }

    HX_RELEASE(pRamGen);
    HX_RELEASE(pRemoteView);
    HX_RELEASE(pViewURL);
    HX_RELEASE(pCurrentPath);
    HX_RELEASE(pFileName);

    if ( bUseStyles )
    {
	m_pEscapeStrings = (const char**) m_pStyleTags;
    }
    else
    {
	m_pEscapeStrings = (const char**) m_pDefaultTags;
    }
}

/*___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *  ~CEscapeXMLtoHTML()
 *
 *  PARAMETERS:
 *		none
 *
 *  DESCRIPTION:
 *		Destructor.
 *
 *___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~*/
CEscapeXMLtoHTML::~CEscapeXMLtoHTML()
{
    HX_VECTOR_DELETE(m_pRamGen);
    HX_VECTOR_DELETE(m_pServerUrl);
    HX_VECTOR_DELETE(m_pOurPath);
    HX_VECTOR_DELETE(m_pDefaultView);
    HX_VECTOR_DELETE(m_pFileName);
}

/*___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *  Convert(pXMLsrc, pOutBuffer)
 *
 *  PARAMETERS:
 *	pXMLsrc		Pointer to a IHXBuffer containing the src of xml to 
 *			be converted
 *	pOutBuffer	A new IHXBuffer containing the parsed XML data ready
 *			to be displayed in an HTML browser.
 *
 *  DESCRIPTION:
 *	Creates a growing queue, copies the buffers to a cstring, then calls 
 *	the Parse(...) function to parse the string.  Next the outputed is 
 *	dequeued Off the growing queue and put in a new IHXBuffer and 
 *	returned
 *
 *  RETURNS
 *	
 *___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~*/
STDMETHODIMP CEscapeXMLtoHTML::Convert(IHXBuffer* pXMLsrc,
				       REF(IHXBuffer*) pOutBuffer)
{
    // TODO: UTF-16
    UCHAR* pIn = NULL;
    UINT32 ulLen;
    
    HX_ASSERT(pXMLsrc != NULL);
    pXMLsrc->Get(pIn, ulLen);
    
    CBigByteGrowingQueue* pQueue = NULL;
    
    if ( ulLen )
    {
	pQueue = new CBigByteGrowingQueue(ulLen*4);
	if ( !pQueue )
	{
	    // panic
	    HX_RELEASE(pXMLsrc);
	    return HXR_OUTOFMEMORY;
	}

	DataObject StateObj;
	StateObj.state = IN_CONTENT;
	StateObj.bPushChar = TRUE;
    
	PushHeader(pQueue);
	pQueue->EnQueue("<pre><!--  Begin Source  -->\n");
	Parse(pIn, ulLen, pQueue, &StateObj);
	pQueue->EnQueue("\n<!--  End Source  --></pre>\n");
	UINT32 ulOutLen;
	ulOutLen =  pQueue->GetQueuedItemCount();

	HX_RELEASE(pOutBuffer);
	pOutBuffer = new CHXBuffer();
	pOutBuffer->AddRef();
	if ( pOutBuffer->SetSize(ulOutLen) != HXR_OK )
	{
	    HX_RELEASE(pXMLsrc);
	    return HXR_OUTOFMEMORY;
	}
	UCHAR* pOut = pOutBuffer->GetBuffer();
	pQueue->DeQueue(pOut, ulOutLen);
    }
    else
    { // just return an empty buffer.
	HX_RELEASE(pOutBuffer);
	pOutBuffer = new CHXBuffer();
	pOutBuffer->AddRef();
    }
    HX_DELETE(pQueue);
    return HXR_OK;
}

/*___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *  PushCommonHeader(queue)
 *
 *  PARAMETERS:
 *
 *  queue	The queue to push the output to.
 *
 *  DESCRIPTION:
 *
 *	Pushes the common information onto the queue.
 *
 *  RETURNS
 *	
 *___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~*/
void CEscapeXMLtoHTML::PushCommonHeader(CBigByteGrowingQueue* queue)
{
    queue->EnQueue(z_pFileName);
    queue->EnQueue(m_pFileName);
    queue->EnQueue(z_pEndLine);
    
    QueueModificationTime(queue, m_ulModDate);

    QueueFileSize(queue, m_ulFileSize);

    if ( m_pRamGen )
    {
	queue->EnQueue(z_pRamLink);
	queue->EnQueue("<a href=\"");
	queue->EnQueue(m_pRamGen);
	const char* p = m_pOurPath;
	if ( *p == '/' )
	{
	    p++;
	}
	queue->EnQueue(p);
	queue->EnQueue("/");
	queue->EnQueue(m_pFileName);
	queue->EnQueue("\">");
	queue->EnQueue(m_pRamGen);
	queue->EnQueue(p);
	queue->EnQueue("/");
	queue->EnQueue(m_pFileName);
	queue->EnQueue("</a>");
	queue->EnQueue(z_pEndLine);
    }
}

/*___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 * Protected Methods
 *___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~*/
/*___________________________________________________________________________
 *~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *  WrapAttributeWithHREF (pPositionPointer, ulLen, pObj, pQueue, pAttribute)
 *
 *  PARAMETERS:
 *
 *  pPositionPointer		Pointer to a character string.  It points to the first
 *		whitespace after the tagname
 *  ulLen	Length to end of pPositionPointer so we don't overrun the buffer
 *  pObj	The current state of the Parse Function, this can be used
 *		to continue parsing.
 *  queue	The queue to push the output to.
 *  pAttribute	The attribute we want to wrap.
 *
 *  DESCRIPTION: