looseprs.cpp

linux下的一款播放器

/* ***** BEGIN LICENSE BLOCK *****
 * Source last modified: $Id: looseprs.cpp,v 1.6.28.3 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 "hxcom.h"
#include "hxtypes.h"
#include "hxstrutl.h"
#include "hxmap.h"
#include "xmlencod.h"
#include "looseprs.h"
#include <ctype.h>

#include "hxheap.h"
#ifdef _DEBUG
#undef HX_THIS_FILE		
static const char HX_THIS_FILE[] = __FILE__;
#endif

static const int MAX_ERROR_LEN = 80;

XMLParser::XMLParser(BOOL bStrictCompliance, const char* pEncoding,
		     BOOL bAllowNonXMLComments):
    m_bStrictCompliance(bStrictCompliance),
    m_bAllowNonXMLComments(bAllowNonXMLComments),
    m_bCommentWasFound(FALSE),
    m_bXMLandSMIL10FullCompliance(FALSE),
    m_ulCurrentLine(1),
    m_ulCurrentCol(1),
    m_ulTagStartLine(1),
    m_ulTagStartCol(1),
    m_pLastError(0)
    , m_bStoreErrors(FALSE)
{
    m_pCurrentFrame = new XMLFrame;
    m_comment_state = 0;
    m_comment_get_arg = 0;
    m_comment_pos = 0;
    if(pEncoding)
    {
	m_pEncoding = new_string(pEncoding);
    }
    else
    {
	m_pEncoding = new_string("US-ASCII");	// default encoding
    }
}

XMLParser::~XMLParser()
{
    HX_DELETE(m_pLastError);
    HX_VECTOR_DELETE(m_pEncoding);
    delete m_pCurrentFrame;
}

void
XMLParser::Reset(void)
{
    if (m_pCurrentFrame != NULL) delete m_pCurrentFrame;
    m_pCurrentFrame = NULL;
}

// class function to get version/encoding of XML content
HX_RESULT
XMLParser::GetPrologInfo(const char* pBuf,
			 UINT32 ulBufLen,
			 char*& pVersion,
			 char*& pEncoding)
{
    HX_RESULT rc = HXR_FAIL;

    const char* pCh = pBuf;
    enum { VERSION, ENCODING } nPrologAttribute = VERSION;
    char quoteType = '"';

    BOOL bDone = FALSE;
    BOOL bInComment = FALSE;
    int state = 0;
    const char* pValueStart = NULL;

    while(!bDone &&
        pCh < pBuf + ulBufLen)
    {
        switch(state)
        {
            case 0: // looking for either a comment open
                    // or a prolog
            {
                if(*pCh == '<')
                {
                    if(*(pCh + 1) == '!' &&
                       *(pCh + 2) == '-' &&
                       *(pCh + 3) == '-')
                    {
                        if(bInComment)
                        {
                            bDone = TRUE;   // no nested comments
                        }
                        pCh += 4;   // skip over
                        bInComment = TRUE;
                        state = 1;
                    }
                    else if(*(pCh + 1) == '?' &&
                            *(pCh + 2) == 'x' &&
                            *(pCh + 3) == 'm' &&
                            *(pCh + 4) == 'l')
                    {
                        pCh += 5;   // skip over 
                        state = 2;
                    }
                    else
                    {
                        bDone = TRUE;   // no prolog
                    }
                }
                else if(isspace(*pCh))
                {
                    pCh++;
                }
                else
                {
                    bDone = TRUE;   // can't find prolog
                }
            }
            break;

            case 1: // comment end
            {
                if(*pCh == '-' &&
                   *(pCh + 1) == '-' &&
                   *(pCh + 2) == '>')
                {
                    pCh += 3;
                    bInComment = FALSE;
                    state = 0;
                }
                else
                {
                    pCh++;
                }
            }
            break;

            case 2: // known attribute in prolog
            {
                if(strncmp(pCh, "version", 7) == 0)
                {
                    pCh += 7;
                    nPrologAttribute = VERSION;
                    state = 3;
                }
                else if(strncmp(pCh, "encoding", 8) == 0)
                {
                    pCh += 8;
                    nPrologAttribute = ENCODING;
                    state = 3;
                }
                else
                {
                    pCh++;
                }
            }
            break;

            case 3: // '='
            {
                if(*pCh == '=')
                {
                    state = 4;
                }
                pCh++;
            }
            break;

            case 4: // quote type
            {
                if(*pCh == '"')
                {
                    quoteType = '"';
                    pValueStart = pCh + 1;
                    state = 5;
                }
                else if(*pCh == '\'')
                {
                    quoteType = '\'';
                    pValueStart = pCh + 1;
                    state = 5;
                }
                else
                {
                    bDone = TRUE;   // badly formed
                }
                pCh++;
            }
            break;

            case 5: // get value
            {
                if(*pCh == quoteType)
                {
                    if (pValueStart)
                    {
                        INT32 lValLen = pCh - pValueStart;
                        if (lValLen > 0)
                        {
                            char* pTmp = new char [lValLen + 1];
                            if (pTmp)
                            {
                                strncpy(pTmp, pValueStart, lValLen);
                                pTmp[lValLen] = '\0';
                                if(nPrologAttribute == VERSION)
                                {
                                    pVersion = pTmp;
                                }
                                else if(nPrologAttribute == ENCODING)
                                {
                                    pEncoding = pTmp;
                                }
                                rc = HXR_OK;    // got one!
                                // reset for next string
                                state = 2;
                            }
                        }
                    }
                }
                pCh++;
            }
            break;
        }
    }
    return rc;
}

char
XMLParser::GetEscapeMacro(const char*& ptr, const char* end)
{
    char returnCh;
    if(*ptr != '&')
    {
	returnCh = *ptr;
    }
    else
    {
	int maxLen = end - ptr;
	if((maxLen > 5) && strncmp(ptr, "&apos;", 6) == 0)
	{
	    returnCh = '\'';
	    ptr += 6;
	}
	else if((maxLen > 5) && strncmp(ptr, "&quot;", 6) == 0)
	{
	    returnCh = '"';
	    ptr += 6;
	}
	else if((maxLen > 3) && strncmp(ptr, "&lt;", 4) == 0)
	{
	    returnCh = '<';
	    ptr += 4;
	}
	else if((maxLen > 3) && strncmp(ptr, "&gt;", 4) == 0)
	{
	    returnCh = '>';
	    ptr += 4;
	}
	else if((maxLen > 4) && strncmp(ptr, "&amp;", 5) == 0)
	{
	    returnCh = '&';
	    ptr += 5;
	}
	else
	{
	    returnCh = '&';
	    ptr++;
	}
    }
    return returnCh;
}

GetStringResult
XMLParser::GetString(const char*& ptr, const char* end, 
		      char*& val, UINT32 type)
{
    GetStringResult retval = GSInvalid;

    CHXXMLEncode xmlStr(m_pEncoding, (BYTE*)ptr, end - ptr);
    UINT16 uLen = 0;
    ptr = (const char*)xmlStr.GetNextChar(uLen);
    while(isspace(*ptr) && ptr < end)
    {
	ptr = (const char*)xmlStr.GetNextChar(uLen);
    }
    if((const char*)ptr >= end)
    {
	return GSNoValue;
    }
    if(*ptr == '>')
    {
	ptr = (const char*)xmlStr.GetNextChar(uLen);
	return GSNoValue;
    }
    if(*ptr == '/' && *(ptr + 1) == '>')
    {
	xmlStr += 2;
	ptr = (const char*)xmlStr++;
	return GSNoValue;
    }

    // temp buffer to copy string value
    char* pVal = new char[end - ptr + 1];
    char* pValPtr = pVal;
    char* pValStartPtr = pVal;

    switch(type)
    {
	case TagType:
	{
	    // The main tag name, delimited by space
	    if(*ptr == '/')
	    {
		retval = GSEndTag;
		pValStartPtr++;
	    }
	    while(!isspace(*ptr) && *ptr != '>' && ptr < end)
	    {
		*pValPtr++ = *ptr;
		if(uLen == 2)
		{
		    *pValPtr++ = *(ptr + 1);
		}
		ptr = (const char*)xmlStr.GetNextChar(uLen);
	    }
	    break;
	}
	case AttributeName:
	{
	    // Delimited by whitespace or =
	    while(!isspace(*ptr) && *ptr != '=' && *ptr != '>' && ptr < end)
	    {
		*pValPtr++ = *ptr;
		if(uLen == 2)
		{
		    *pValPtr++ = *(ptr + 1);
		}
		ptr = (const char*)xmlStr.GetNextChar(uLen);
	    }
	    BOOL foundequals = FALSE;
	    if(ptr < end)
	    {
		// Set the ptr to past the =
		while((isspace(*ptr) || *ptr == '=') && ptr < end)
		{
		    if(*ptr == '=')
			foundequals=TRUE;
		    ptr = (const char*)xmlStr.GetNextChar(uLen);
		}
	    }
	    if(!foundequals)
	    {
		retval = GSValueOnly;
	    }
	    break;
	}
	case AttributeValue:
	case AttributeValueNoQuote:
	case AttributeValueDirective:
	{
	    if(*ptr == '"')
	    {
		ptr = (const char*)xmlStr.GetNextChar(uLen);
		while(ptr<end && *ptr != '"')
		{
		    if(*ptr == '&')
		    {
			*pValPtr = GetEscapeMacro(ptr, end);
			pValPtr++;
			xmlStr.SetCurrent((BYTE*)ptr);
		    }
		    else
		    {
			*pValPtr++ = *ptr;
			if(uLen == 2)
			{
			    *pValPtr++ = *(ptr + 1);
			}
		    }
		    ptr = (const char*)xmlStr.GetNextChar(uLen);
		}
		if(*ptr != '"')
		{
		    return GSMissingQuote;
		}
		/* Skip the quote */
		ptr = (const char*)xmlStr.GetNextChar(uLen);
		//Fixes 28799 (which is really an XML authoring error)
		// if m_bXMLandSMIL10FullCompliance is FALSE:
		if (m_bXMLandSMIL10FullCompliance  &&
			!isspace(*ptr)  &&  '>' != *ptr  &&
			(('/' != *ptr  &&  '?' != *ptr)
			||  '>' != *(ptr+1)) )
		{
		    //[SMIL 1.0 Compliance] Fixes PR 23995.  Junk following a
		    // name="value" construct should be treated as an error,
		    // e.g., the comma should be treated as an error in the
		    // following: <region height="10", width="20"/>
		    return GSInvalid;
		}
	    }
	    else if(*ptr == '\'')
	    {
		ptr = (const char*)xmlStr.GetNextChar(uLen);
		while(*ptr != '\'' && ptr < end)
		{
		    if(*ptr == '&')
		    {
			*pValPtr = GetEscapeMacro(ptr, end);
			pValPtr++;
			xmlStr.SetCurrent((BYTE*)ptr);
		    }
		    else
		    {
			*pValPtr++ = *ptr;
			if(uLen == 2)
			{
			    *pValPtr++ = *(ptr + 1);
			}
		    }
		    ptr = (const char*)xmlStr.GetNextChar(uLen);
		}
		if(*ptr != '\'')
		{
		    delete [] pVal;
		    return GSMissingQuote;
		}
		/* Skip the quote */
		ptr = (const char*)xmlStr.GetNextChar(uLen);
	    }
	    else if(*ptr == '[' && type == AttributeValueDirective)
	    {
		ptr = (const char*)xmlStr.GetNextChar(uLen);
		while(*ptr != ']' && ptr < end)
		{
		    *pValPtr++ = *ptr;
		    if(uLen == 2)
		    {
			*pValPtr++ = *(ptr + 1);
		    }
		    ptr = (const char*)xmlStr.GetNextChar(uLen);
		}
		if(*ptr != ']')
		{
		    delete[] pVal;
		    return GSMissingQuote;
		}
		/* skip the ']' */
		ptr = (const char*)xmlStr.GetNextChar(uLen);
	    }
	    else
	    {
		if(m_bStrictCompliance && 
		   type != AttributeValueNoQuote &&
		   type != AttributeValueDirective)
		{
		    /* error - value must be quoted */
		    delete [] pVal;
		    return GSMissingQuote;
		}
		else
		{
		    /* don't care!!! */
		    while(!isspace(*ptr) && *ptr != '>' && ptr < end)
		    {
			*pValPtr++ = *ptr;
			if(uLen == 2)
			{
			    *pValPtr++ = *(ptr + 1);
			}
			ptr = (const char*)xmlStr.GetNextChar(uLen);
		    }
		}
	    }
	    break;
	}
    }

    *pValPtr = '\0';

    val = new_string(pValStartPtr);
    delete [] pVal;

    if(retval == GSInvalid)
	return GSFoundExpected;
    else
	return retval;
}

void
XMLParser::FindCommentClose(const char*& buf, const char* start,
			    const char* end)
{
    BOOL   bResult	 = FALSE;
    UINT16 nCommentDepth = 1;

    CHXXMLEncode xmlStr(m_pEncoding, (BYTE*)start, end - start);
    UINT16 uLen = 0;

    const char* pos = (const char*)xmlStr.GetNextChar(uLen);
    while(pos < end && m_comment_state > 0)
    {
	switch(m_comment_state)
	{
	    case 1:
		if(*pos == '-')
		    m_comment_state = 2;
		else if (*pos == '<')
		    m_comment_state = 4;
		else if (*pos == '>' && m_bAllowNonXMLComments)
		{
		    nCommentDepth--;
		    if (nCommentDepth == 0)
		    {
			m_comment_state = 0;
			buf = (const char*)xmlStr.GetNextChar(uLen);
		    }
		    else
			m_comment_state = 1;
		}
		else if(m_comment_start)
		{
		    if(*pos == '#')