Click here to Skip to main content
Click here to Skip to main content
Add your own
alternative version

Tokenizer and analyzer package supporting precedence prioritized rules

, 1 Jan 2002
A library allowing you to conveniently build a custom tokenizer and analyzer supporting precedence priorized rules
cxtpackagetut_win32vc.zip
cxTokenizer
cxTokenizer.dsp
cxTokenizer.plg
cxtPackage
cxtPackage.plg
cxtPackage.dsp
mathTok
mathTok.plg
mathTok.dsp
simpleCalc
simpleCalc.bmp
simpleCalc.dsp
simpleCalc.plg
tkCommon
cxAnalyzer
cxAnalyzer.dsp
cxAnalyzer.plg
cxtpackage_win32vc.zip
cxTokenizer.dsp
cxTokenizer.plg
Debug
cxAnalyzer.dsp
cxAnalyzer.plg
cxtPackage.plg
cxtPackage.dsp
grammaride.zip
pkgcomplete.zip
cxTokenizerMatchTokenRule.inl
cxTokenizer.dsp
cxtPackage.dsp
emptyTestApp
emptyTestApp.clw
res
emptyTestApp.ico
emptyTestApp.dsp
grammarIDE
grammarIDE.clw
res
grammarIDEDoc.ico
icon1.ico
zoomable.ico
Toolbar.bmp
grammarIDE.ico
vssver.scc
grammarIDE.dsp
simpleCalc.bmp
simpleCalc.dsp
vssver.scc
cxaToken.inl
cxAnalyzer.dsp
pkgsrconly.zip
cxTokenizerMatchTokenRule.inl
cxTokenizer.dsp
cxtPackage.dsp
emptyTestApp.clw
emptyTestApp.ico
emptyTestApp.dsp
vssver.scc
cxaToken.inl
cxAnalyzer.dsp
/*********************************************************************
	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.
    ---------------------------------------------------------------

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

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

#include "stdafx.h"

#include "cxTokenizerMapData.h"
#include "cxTokenizerTokenRule.h"
#include "cxTokenizerCharTokenRule.h"
#include "cxTokenizerMap.h"
#include "cxTokenizerContextCookie.h"
#include "cxTokenizerContext.h"
#include "cxTokenizerStringTokenRule.h"
#include "cxTokenizerNumberTokenRule.h"
#include "cxTokenizerCommentTokenRule.h"
//#include "cxTokenizerPreprocessorTokenRules.h"

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

#include "cxTokenizerMapDiags.cpp"

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

    cxTokenizerMap::cxTokenizerMap()
	    {
		m_fInitialized	=false;
	    }

    cxTokenizerMap::cxTokenizerMap(std::basic_istream<TCHAR>& input)
	    {
		m_fInitialized	=false;
        vLoadFromStream(input);
	    }

    cxTokenizerMap::~cxTokenizerMap()
	    {
	    ttrdel_vec_type::iterator	it;

	    for(it=m_vecRulesToDelete.begin();it!=m_vecRulesToDelete.end();it++)
		    delete (*it);
	    m_vecRulesToDelete.clear();
	    }

//////////////////////////////////////////////////////////////////////
// Protected operations
//////////////////////////////////////////////////////////////////////

    /*********************************************************************
	    FUNCTION:	cxTokenizerMap::pttrGetRuleForID
	    PURPOSE:	Searches the rule with the given ID
	    RETURNS:	cxTokenizerTokenRule*, if successful. Otherwise NULL
    *********************************************************************/
	const cxTokenizerTokenRule* cxTokenizerMap::pttrGetRuleForID(int nIDValue) const
		{
	    ttrdel_vec_type::const_iterator	it;

	    for(it=m_vecRulesToDelete.begin();it!=m_vecRulesToDelete.end();it++)
			{
			if( (*it)->nGetIDValue()==nIDValue )
				return (*it);
			}
		return NULL;
		}

    /*********************************************************************
	    FUNCTION:	cxTokenizerMap::pttrGetRuleForString
	    PURPOSE:	Searches the rule with the given token string
	    RETURNS:	cxTokenizerTokenRule*, if successful. Otherwise NULL
    *********************************************************************/
	const cxTokenizerTokenRule* cxTokenizerMap::pttrGetRuleForString(const std::tstring& strToken) const
		{
	    ttrdel_vec_type::const_iterator	it;

	    for(it=m_vecRulesToDelete.begin();it!=m_vecRulesToDelete.end();it++)
			{
			if( (*it)->strGetTokenString()==strToken )
				return (*it);
			}
		return NULL;
		}

    /*********************************************************************
	    FUNCTION:	cxTokenizerMap::fRegisterCharRule
	    PURPOSE:	Registers the given rule in the map
	    RETURNS:	'true' on success.
    *********************************************************************/
    bool	cxTokenizerMap::fRegisterCharRule(
				cxTokenizerMapData& tmdRules, 
				cxTokenizerCharTokenRule* pRule,
				cxTokenizerMapData **pptmdEnd)
	    {
	    if(NULL == pRule)
		    throw cxTokenizerException(ERR_UNEXPECTED_NULL_PARAMETER);

	    cxTokenizerMapData	*ptmdRulesCur = &tmdRules, *ptmdTemp = NULL;
	    std::tstring		strToken = pRule->strGetTokenString();
	    int					i,len;
	    bool				fReturn = true;

	    len			=strToken.length();
	    for(i=0;i<len;i++)
		    {
		    ptmdTemp	=ptmdRulesCur->ptmdInsert(
						    strToken[i],
						    (i==(len-1))?pRule:NULL);
		    if(NULL == ptmdTemp)
			    throw cxTokenizerException(ERR_UNEXPECTED_NULL_PARAMETER);

		    ptmdRulesCur=ptmdTemp;
		    }

		if(pptmdEnd!=NULL) (*pptmdEnd)=ptmdRulesCur;
	    return fReturn;
	    }

    /*********************************************************************
	    FUNCTION:	cxTokenizerMap::fRegisterComputedRule
	    PURPOSE:	Registers the given rule in the map
	    RETURNS:	'true' on success.
    *********************************************************************/
    bool	cxTokenizerMap::fRegisterComputedRule(
				cxTokenizerMapData& tmdRules, 
				cxTokenizerTokenRule* pRule)
	    {
	    if(NULL == pRule)
		    throw cxTokenizerException(ERR_UNEXPECTED_NULL_PARAMETER);

	    cxTokenizerMapData	*ptmdNewRule = new cxTokenizerMapData;
	    ptmdNewRule->m_pRule=pRule;
	    ptmdNewRule->m_fComputed=true;
	    tmdRules.insert(cxTokenizerMapData::value_type(_T('\0'),ptmdNewRule));

	    return true;
	    }

//////////////////////////////////////////////////////////////////////
// Operations
//////////////////////////////////////////////////////////////////////

    /*********************************************************************
	    FUNCTION:	cxTokenizerMap::vInitNotify
	    PURPOSE:	Broadcasts initialization messages to the contained rules
	    RETURNS:	- void -
    *********************************************************************/
    void	cxTokenizerMap::vInitNotify(bool fInit, cxTokenizer *pxTokenizer)
	    {
		m_tmdWIRules.vInitNotify(fInit,pxTokenizer);
		m_tmdFPRules.vInitNotify(fInit,pxTokenizer);
		}

    /*********************************************************************
	    FUNCTION:	cxTokenizerMap::fRegisterRule
	    PURPOSE:	Registers the given rule in the map
	    RETURNS:	'true' on success.
    *********************************************************************/
    bool	cxTokenizerMap::fRegisterRule(cxTokenizerTokenRule* pRule)
	    {
	    if(NULL == pRule)
		    throw cxTokenizerException(ERR_UNEXPECTED_NULL_PARAMETER);

	    cxTokenizerMapData* ptmdRules = NULL;

	    if(pRule->fIsFlagSet(ttrf_within))
		    ptmdRules	=&m_tmdWIRules;
	    else
		    ptmdRules	=&m_tmdFPRules;

	    if(pRule->fIsFlagSet(ttrf_character_rule))
		    return cxTokenizerMap::fRegisterCharRule(
				    *ptmdRules,
				    reinterpret_cast<cxTokenizerCharTokenRule*>(pRule));
	    else
		    return cxTokenizerMap::fRegisterComputedRule(
				    *ptmdRules,
				    pRule);
	    }

    /*********************************************************************
	    FUNCTION:	cxTokenizerMap::fBuildRule
	    PURPOSE:	Creates a path in the 'map' - tree (...) for
                    a character token using the text 'strToken'
	    RETURNS:	'true' on success.
    *********************************************************************/
    bool	cxTokenizerMap::fBuildRule(int nIDValue, const std::tstring strToken, const std::tstring& strInitString, bool fSeperator)
	    {
	    cxTokenizerCharTokenRule	*ptctrRule = NULL;
	    
	    if(fSeperator)
		    ptctrRule	=new cxTokenizerCharTokenRule(
                                nIDValue,
							    ((xttr_flags)(ttrf_character_rule | ttrf_within | ttrf_intermediate)),
							    strToken.data(), strInitString);
	    else
		    ptctrRule	=new cxTokenizerCharTokenRule(
                                nIDValue,
							    ((xttr_flags)(ttrf_character_rule | ttrf_seperate | ttrf_not_intermediate)),
							    strToken.data(), strInitString);

	    m_vecRulesToDelete.push_back(ptctrRule);

	    if(!fRegisterRule(ptctrRule))
		    return false;

	    return true;
	    }

    /*********************************************************************
	    FUNCTION:	cxTokenizerMap::fBuildHybridRule
	    PURPOSE:	Creates a path in the 'map' - tree (...) for
                    a character token using the text 'strToken'
	    RETURNS:	'true' on success.
    *********************************************************************/
    bool	cxTokenizerMap::fBuildHybridRule(int nIDValue, const std::tstring strToken, const std::tstring& strInitString, bool fSeperator, cxTokenizerTokenRule *pRule)
	    {
	    cxTokenizerCharTokenRule	*ptctrRule = NULL;
	    cxTokenizerMapData* ptmdRules = NULL;
	    cxTokenizerMapData* ptmdEnd = NULL;
	    cxTokenizerMapData* ptmdTemp = NULL;

	    if(fSeperator)
		    ptmdRules	=&m_tmdWIRules,
		    ptctrRule	=new cxTokenizerCharTokenRule(
                                0,
							    ((xttr_flags)(ttrf_character_rule | ttrf_within | ttrf_intermediate)),
							    strToken.data(), strInitString);
	    else
		    ptmdRules	=&m_tmdFPRules,
		    ptctrRule	=new cxTokenizerCharTokenRule(
                                0,
							    ((xttr_flags)(ttrf_character_rule | ttrf_seperate | ttrf_not_intermediate)),
							    strToken.data(), strInitString);

		m_vecRulesToDelete.push_back(ptctrRule);

		if(!cxTokenizerMap::fRegisterCharRule(
				*ptmdRules,
				reinterpret_cast<cxTokenizerCharTokenRule*>(ptctrRule),
				&ptmdEnd))
			return false;

		ASSERT(ptmdEnd!=NULL);
		ptmdEnd->m_fComputed=true;
		ptmdEnd->m_nHybridLength=strToken.size();
		ptmdEnd->m_pRule=pRule;

	    return true;
	    }

    /*********************************************************************
	    FUNCTION:	cxTokenizerMap::vLoadFromStream
	    PURPOSE:	Initializes the map from the text stream
	    RETURNS:	- void -
    *********************************************************************/
    void	cxTokenizerMap::vLoadFromStream(std::basic_istream<TCHAR>& input)
	    {
		ASSERT(m_fInitialized==false);

	    enum	mode_type {
		    mode_invalid,
		    mode_seperators,
		    mode_tokens,
		    mode_rules
		    };

	    std::tstring	strLine,strLine0;
	    mode_type		mode = mode_invalid;

	    while(!input.eof())
		    {
		    bool		fValid = false;
		    std::getline(input,strLine);

		    if(strLine.length()==0)
			    continue;

			if(strLine[0]==_T('\''))
				continue;

			strLine0	=strLine;
		    if(!fValid && _tcsicmp(strLine.data(),_T("[seperators]"))==0)
			    mode=mode_seperators, fValid=true;
		    if(!fValid && _tcsicmp(strLine.data(),_T("[tokens]"))==0)
			    mode=mode_tokens, fValid=true;
		    if(!fValid && _tcsicmp(strLine.data(),_T("[rules]"))==0)
			    mode=mode_rules, fValid=true;
			if(!fValid && _tcsicmp(strLine.data(),_T("[ends]"))==0)
				break;
			if(!fValid && _tcsicmp(strLine.data(),_T("[grammar]"))==0)
				break;

		    if(!fValid)
			    {
                std::string::size_type nTemp = strLine.find(':');
                int         nIDValue = 0;
                if(nTemp!=std::string::npos)
                    {
                    nIDValue    =_tcstoul(strLine.substr(0,nTemp).data(),NULL,10);
                    strLine     =ctkMisc::strParseEscapeCharacters(strLine.substr(nTemp+1));

					try {
						if(mode==mode_seperators)
							fValid	=fBuildRule(nIDValue,strLine,strLine0,true);
						if(mode==mode_tokens)
							fValid	=fBuildRule(nIDValue,strLine,strLine0,false);
						if(mode==mode_rules)
							{
							cxTokenizerTokenRule	*pNewRule = NULL;
							bool					fNoRegister = false;
							std::tstring			strRuleName, strArgs;
							std::tstring::size_type	pos = strLine.find(',');

							// extract arguments (if given)
							if(pos!=std::tstring::npos)
								strRuleName = strLine.substr(0,pos), strArgs = strLine.substr(pos), strArgs+=',';
							else
								strRuleName = strLine;

							try {
								if(_tcsicmp(strRuleName.data(),_T("strings"))==0)
									pNewRule = new cxTokenizerStringTokenRule(nIDValue,((xttr_flags)(ttrf_computed_rule | ttrf_within | ttrf_intermediate)), strLine0);
								if(_tcsicmp(strRuleName.data(),_T("numbers"))==0)
									pNewRule = new cxTokenizerNumberTokenRule(nIDValue,((xttr_flags)(ttrf_computed_rule | ttrf_within | ttrf_intermediate)), strLine0);
								if(_tcsicmp(strRuleName.data(),_T("cppmultilinecomments"))==0)
									{
									if(strArgs.find(",collect,")!=std::tstring::npos)
										pNewRule = new cxTokenizerMultiLineCommentTokenRule<true>(nIDValue,((xttr_flags)(ttrf_computed_rule | ttrf_within | ttrf_intermediate)), strLine0);
									else
										pNewRule = new cxTokenizerMultiLineCommentTokenRule<false>(nIDValue,((xttr_flags)(ttrf_computed_rule | ttrf_within | ttrf_intermediate)), strLine0);
									fBuildHybridRule(0,"/*",strLine0,true,pNewRule);
									fNoRegister = true;
									}
								if(_tcsicmp(strRuleName.data(),_T("cppsinglelinecomments"))==0)
									{
									if(strArgs.find(",collect,")!=std::tstring::npos)
										pNewRule = new cxTokenizerSingleLineCommentTokenRule<true>(nIDValue,((xttr_flags)(ttrf_computed_rule | ttrf_within | ttrf_intermediate)), strLine0);
									else
										pNewRule = new cxTokenizerSingleLineCommentTokenRule<false>(nIDValue,((xttr_flags)(ttrf_computed_rule | ttrf_within | ttrf_intermediate)), strLine0);
									fBuildHybridRule(0,"//",strLine0,true,pNewRule);
									fNoRegister = true;
									}
/*								if(_tcsicmp(strRuleName.data(),_T("cpppreprocessor"))==0)
									pNewRule = new cxTokenizerPreprocessorTokenRule(nIDValue,((xttr_flags)(ttrf_computed_rule | ttrf_within | ttrf_intermediate)), strLine0);*/
								if(pNewRule==NULL)
									pNewRule = new cxDummyTokenizerTokenRule(nIDValue,strLine.data());

								pNewRule->vSetArguments(strArgs);
								}
							catch(cxTokenizerException& e)
								{
								if(pNewRule) delete pNewRule;
								pNewRule = NULL;
								throw e;
								}
							catch(...)
								{
								ASSERT(FALSE);
								AfxMessageBox("Unhandled Exception in cxTokenizerMap::vLoadFromStream.");
								delete pNewRule; pNewRule=NULL;
								}

							if(pNewRule!=NULL)
								{
								m_vecRulesToDelete.push_back(pNewRule);
								if(!fNoRegister)
									{
									if(fRegisterRule(pNewRule))
										fValid = true;
									}
								else
									fValid = true;
								}
							}
						}
					catch(cxTokenizerException& e)
						{
						if(e.ErrorString()==NULL)
							e.SetErrorString(strLine.c_str());
						throw e;
						}
					}
				}

//		    ASSERT(fValid);
			if(!fValid)
				throw cxTokenizerException(ERR_INVALID_RULE,strLine.c_str());
		    }

		m_tmdFPRules.vSetQueryStage();
		m_tmdWIRules.vSetQueryStage();
	    }

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

Share

About the Author

Alexander Berthold
Web Developer
Germany Germany
No Biography provided

| Advertise | Privacy | Mobile
Web03 | 2.8.140821.2 | Last Updated 2 Jan 2002
Article Copyright 2001 by Alexander Berthold
Everything else Copyright © CodeProject, 1999-2014
Terms of Service
Layout: fixed | fluid