Click here to Skip to main content
15,885,216 members
Articles / Programming Languages / C++

Tokenizer and analyzer package supporting precedence prioritized rules

Rate me:
Please Sign up or sign in to vote.
5.00/5 (4 votes)
1 Jan 20023 min read 181.4K   2.8K   54  
A library allowing you to conveniently build a custom tokenizer and analyzer supporting precedence priorized rules
/*********************************************************************
	Copyright (C) 2001 by

		Alexander Berthold, alexander-berthold@web.de.
		Hoegestr. 54
		79108 Freiburg i. Breisgau
		Germany

    -- This file is part of cxTokenizer --

    "cxTokenizer" is free software; you can redistribute it and/or 
	modify it under the terms of the GNU Lesser General Public 
	License as published by the Free Software Foundation; either 
	version 2 of the License, or any later version.

    "cxTokenizer" is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU Lesser General Public License for more details.

    You should have received a copy of the GNU Lesser General Public
	License along with "cxTokenizer"; if not, write to the Free 
	Software  Foundation, Inc., 59 Temple Place, Suite 330, 
	Boston, MA  02111-1307  USA

    ---------------------------------------------------------------
      If you find any bugs or if you make other corrections/
	  enhancements, i'd appreciate if you'd let me know about 
	  that. My email is
  
       alexander-berthold@web.de
  
      If you share this code, do not remove this text.
    ---------------------------------------------------------------

*********************************************************************/

// cxTokenizerContext.cpp: implementation of the cxTokenizerContext class.
//
//////////////////////////////////////////////////////////////////////

#include "stdafx.h"

#include "cxTokenizerMapData.h"
#include "cxTokenizerTokenRule.h"
#include "cxTokenizerContextCookie.h"
#include "cxTokenizerContext.h"
#include "cxTokenizer.h"
#include "cxTokenizerInputStream.h"

#ifdef _DEBUG
#undef THIS_FILE
static char THIS_FILE[]=__FILE__;
#define new DEBUG_NEW
#endif

#include "cxTokenizerContextDiags.cpp"

//////////////////////////////////////////////////////////////////////
// Construction/Destruction
//////////////////////////////////////////////////////////////////////

    cxTokenizerContext::cxTokenizerContext()
	    {
	    ctkFlagsMixin<xtctx_flags>::vClearAllFlags();
		m_pxtTokenizer=NULL;
	    }

    cxTokenizerContext::~cxTokenizerContext()
	    {
		vReset();
	    }

	void cxTokenizerContext::vReset()
		{
		tc_cookiemap_type::iterator it;
		for(it=m_mapCookies.begin();it!=m_mapCookies.end();it++)
			delete it->second;
		for(it=m_mapGlobalCookies.begin();it!=m_mapGlobalCookies.end();it++)
			delete it->second;
	    m_mapCookies.clear();
		m_mapGlobalCookies.clear();
	    m_lstTokenRules.clear();
		}

//////////////////////////////////////////////////////////////////////
// Cookie operations
//////////////////////////////////////////////////////////////////////

    /*********************************************************************
	    FUNCTION:	cxTokenizerContext::ptccGetCookie
	    PURPOSE:	Returns the cookie for the ID 'dwCookieID'
	    RETURNS:	cxTokenizerContextCookie*
    *********************************************************************/
    cxTokenizerContextCookie
		    *cxTokenizerContext::ptccGetCookie(const tc_cookiemap_type& map, DWORD dwCookieID) const
	    {
	    ASSERT(dwCookieID!=0);

	    const_cookiemap_iterator	it;
	    it					=map.find(dwCookieID);
	    if(it==map.end() || it->second->fIsDeleted())
		    return NULL;

	    ASSERT(it->second->fCheckValid());

	    return it->second;
	    }

    /*********************************************************************
	    FUNCTION:	cxTokenizerContext::fDeleteCookie
	    PURPOSE:	Deletes the cookie for the cookie ID 'dwCookieID'
	    RETURNS:	'true' if deleted
                    'false' if cookie did not exist
    *********************************************************************/
    bool	cxTokenizerContext::fDeleteCookie(DWORD dwCookieID)
	    {
	    ASSERT(dwCookieID!=0);

	    cookiemap_iterator	it;
	    it					=m_mapCookies.find(dwCookieID);
	    if(it==m_mapCookies.end())
		    return false;

		it->second->~cxTokenizerContextCookie();
		it->second->m_fDeleted = true;

	    return true;
	    }

    /*********************************************************************
	    FUNCTION:	cxTokenizerContext::fDeleteCookie
	    PURPOSE:	Deletes the cookie for the rule 'pltrRule'
	    RETURNS:	'true' if deleted
                    'false' if cookie did not exist
    *********************************************************************/
    bool	cxTokenizerContext::fDeleteCookie(cxTokenizerTokenRule *pttrRule)
	    {
	    ASSERT(pttrRule!=NULL);
	    ASSERT(pttrRule->fCheckValid());

	    // TODO: find better solution
	    DWORD	dwCookieID = (DWORD)pttrRule;

	    return fDeleteCookie(dwCookieID);
	    }

    /*********************************************************************
	    FUNCTION:	cxTokenizerContext::fDeleteCookie
	    PURPOSE:	Deletes the cookie for the cookie ID 'dwCookieID'
	    RETURNS:	'true' if deleted
                    'false' if cookie did not exist
    *********************************************************************/
    bool	cxTokenizerContext::fDeleteGlobalCookie(DWORD dwCookieID)
	    {
	    ASSERT(dwCookieID!=0);

	    cookiemap_iterator	it;
	    it					=m_mapGlobalCookies.find(dwCookieID);
	    if(it==m_mapGlobalCookies.end())
		    return false;

		delete (*it).second;
		m_mapGlobalCookies.erase(it);

	    return true;
	    }

    /*********************************************************************
	    FUNCTION:	cxTokenizerContext::fDeleteCookie
	    PURPOSE:	Deletes the cookie for the rule 'pltrRule'
	    RETURNS:	'true' if deleted
                    'false' if cookie did not exist
    *********************************************************************/
    bool	cxTokenizerContext::fDeleteGlobalCookie(cxTokenizerTokenRule *pttrRule)
	    {
	    ASSERT(pttrRule!=NULL);
	    ASSERT(pttrRule->fCheckValid());

	    // TODO: find better solution
	    DWORD	dwCookieID = (DWORD)pttrRule;

	    return fDeleteGlobalCookie(dwCookieID);
	    }

//////////////////////////////////////////////////////////////////////
// Data access operations
//////////////////////////////////////////////////////////////////////

	namespace utility
		{
		class	rule_is_deleted : public std::unary_function<cxTokenizerContext::cxListEntry*, bool>
			{
			public:
				bool operator() (const cxTokenizerContext::cxListEntry*& pEntry) const
					{
					return pEntry->fIsMarkedForDeletion();
					}
			};
		}

    /*********************************************************************
	    FUNCTION:	cxTokenizerContext::nDeleteMarkedListEntries
	    PURPOSE:	Removes all rules with 'fMarkedForDeletion' - flag
                    set from the list of the currently active rules
	    RETURNS:	int; count of removed rules
    *********************************************************************/
    int		cxTokenizerContext::nDeleteMarkedListEntries()
	    {
		ASSERT(fCheckValid());
		m_lstTokenRules.remove_if( utility::rule_is_deleted() );
		return 1;
	    }

    /*********************************************************************
	    FUNCTION:	cxTokenizerContext::vIncludeStream
	    PURPOSE:	"Pushes" a input stream which will be processed
					until EOS is reached, then input goes on with
					previous input stream
	    RETURNS:	- void -
    *********************************************************************/
    void	cxTokenizerContext::vIncludeStream(cxTokenizerInputStream *ptisInclude)
	    {
		ASSERT(fCheckValid());
		ASSERT(ptisInclude!=NULL);
		ASSERT(ptisInclude->fCheckValid());
		ASSERT(m_pxtTokenizer->fCheckValid());
		m_pxtTokenizer->vPushInputStream(ptisInclude);
	    }

    /*********************************************************************
	    FUNCTION:	cxTokenizerContext::vCleanUpAfterTokenRecognition
	    PURPOSE:	Is being called after a (delimeting!) token has 
                    been recognized (cxTokenizer::vDelimTokenRecognized).
                    Resets the lexxer context.
	    RETURNS:	- void -
    *********************************************************************/
    void	cxTokenizerContext::vCleanUpAfterTokenRecognition()
	    {
	    // delete cookies
	    cookiemap_iterator	cit;
	    for(cit=m_mapCookies.begin();cit!=m_mapCookies.end();cit++)
			{
			if(!cit->second->fIsDeleted())
				{
				cit->second->~cxTokenizerContextCookie();
				cit->second->m_fDeleted = true;
				}
			}

	    // delete token list
	    rulelist_iterator	it;
	    for(it=m_lstTokenRules.begin();it!=m_lstTokenRules.end();it++)
		    (*it)->vMarkForDeletion();
	    nDeleteMarkedListEntries();

	    // delete current text
	    m_strCurrentText	=_T("");
	    }

	TCHAR	cxTokenizerContext::tcPeekNextCharacter() const
		{
		ASSERT(m_pxtTokenizer!=NULL);
		ASSERT(m_pxtTokenizer->ptiGetInputStream()!=NULL);
		return m_pxtTokenizer->ptiGetInputStream()->tcPeekNextCharacter();
		}

	bool	cxTokenizerContext::fIsLastCharacter() const
		{
		ASSERT(m_pxtTokenizer!=NULL);
		ASSERT(m_pxtTokenizer->ptiGetInputStream()!=NULL);
		return m_pxtTokenizer->ptiGetInputStream()->fIsEofReached();
		}

By viewing downloads associated with this article you agree to the Terms of Service and the article's licence.

If a file you wish to view isn't highlighted, and is a text file (not binary), please let us know and we'll add colourisation support for it.

License

This article has no explicit license attached to it but may contain usage terms in the article text or the download files themselves. If in doubt please contact the author via the discussion board below.

A list of licenses authors might use can be found here


Written By
Web Developer
Germany Germany
This member has not yet provided a Biography. Assume it's interesting and varied, and probably something to do with programming.

Comments and Discussions