src/selection/SelectionCompiler.hpp

/*
 * Copyright (c) 2005 The University of Notre Dame. All Rights Reserved.
 *
 * The University of Notre Dame grants you ("Licensee") a
 * non-exclusive, royalty free, license to use, modify and
 * redistribute this software in source and binary code form, provided
 * that the following conditions are met:
 *
 * 1. Acknowledgement of the program authors must be made in any
 *    publication of scientific results based in part on use of the
 *    program.  An acceptable form of acknowledgement is citation of
 *    the article in which the program was described (Matthew
 *    A. Meineke, Charles F. Vardeman II, Teng Lin, Christopher
 *    J. Fennell and J. Daniel Gezelter, "OOPSE: An Object-Oriented
 *    Parallel Simulation Engine for Molecular Dynamics,"
 *    J. Comput. Chem. 26, pp. 252-271 (2005))
 *
 * 2. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 3. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the
 *    distribution.
 *
 * This software is provided "AS IS," without a warranty of any
 * kind. All express or implied conditions, representations and
 * warranties, including any implied warranty of merchantability,
 * fitness for a particular purpose or non-infringement, are hereby
 * excluded.  The University of Notre Dame and its licensors shall not
 * be liable for any damages suffered by licensee as a result of
 * using, modifying or distributing the software or its
 * derivatives. In no event will the University of Notre Dame or its
 * licensors be liable for any lost revenue, profit or data, or for
 * direct, indirect, special, consequential, incidental or punitive
 * damages, however caused and regardless of the theory of liability,
 * arising out of the use of or inability to use software, even if the
 * University of Notre Dame has been advised of the possibility of
 * such damages.
 */

#ifndef SELECTION_SELECTIONCOMPILER_HPP
#define SELECTION_SELECTIONCOMPILER_HPP
#include <iostream>
#include <string>
#include <vector>

#include "selection/Token.hpp"
#include "selection/TokenMap.hpp"
namespace oopse {


/**
 * @class SelectionCompiler SelectionCompiler.hpp "selection/SelectionCompiler.hpp"
 * @brief compile a selection script to tokens
 * @todo document
 * <pre>

    expression       :: = clauseOr

    clauseOr         ::= clauseAnd {OR clauseAnd}*

    clauseAnd        ::= clauseNot {AND clauseNot}*

    clauseNot        ::= NOT clauseNot | clausePrimitive

    clausePrimitive  ::= clauseComparator |
                         clauseWithin |
                         clauseChemObject |
                         none | all |
                         ( clauseOr )

    clauseComparator ::= atomproperty comparatorop integer

    clauseWithin     ::= WITHIN ( clauseDistance , expression )

    clauseDistance   ::= integer | decimal
    
    clauseChemObject::= {clauseMolecule} | {clauseStuntDouble}

    clauseMolecule ::= {clauseMolName} | {clauseMolIndex}

    clauseMolName ::= molname clauseName
    
    clauseName::= *|string

    clauseMolIndex ::= molindex clauseIndex
    
    clauseIndex ::= integer {- integer }
    
    clauseStuntDouble ::= {clauseStuntDoubleName} | {clauseStuntDoubleIndex}

    clauseStuntDoubleName ::= name clauseName

    clauseStuntDoubleIndex ::= index clauseIndex

 * </pre>
 */
class SelectionCompiler{
    public:
        bool compile(const std::string& filename, const std::string& script );
        

        std::vector<int> getLineNumbers() {
            return lineNumbers;
        }

        std::vector<int> getLineIndices() {
            return lineIndices;
        }

        std::vector<std::vector<Token> > getAatokenCompiled() {
            return aatokenCompiled;
        }

        std::string getErrorMessage() {
            std::string strError = errorMessage;
            strError += " : " + errorLine + "\n";

            if (!filename.empty()) {
                strError += filename;
            }

            strError += " line#" + lineCurrent;
            return strError;
        }

        
    private:

        bool internalCompile();


        bool lookingAtLeadingWhitespace();
        bool lookingAtComment();
        bool lookingAtEndOfLine();
        bool lookingAtEndOfStatement();
        bool lookingAtString();
        bool lookingAtDecimal(bool allowNegative);
        bool lookingAtInteger(bool allowNegative);
        bool lookingAtLookupToken();
        bool lookingAtSpecialString();

        std::string getUnescapedStringLiteral();
        int getHexitValue(char ch);        

        bool compileCommand(const std::vector<Token>& ltoken);
        bool compileExpression();        
        bool compileExpression(int itoken);        
        
        bool clauseOr();
        bool clauseAnd();
        bool clauseNot();
        bool clausePrimitive();
        bool clauseWithin();
        bool clauseComparator();
        bool clauseName(int tok);
        bool clauseIndex(int tok);

        Token tokenNext();
        boost::any valuePeek();
        int tokPeek();

        bool addTokenToPostfix(const Token& token);


        bool compileError(const std::string& errorMessage) {
            std::cerr << "SelectionCompiler Error: " << errorMessage << std::endl;
            error = true;
            this->errorMessage = errorMessage;
            return false;
        }
        
        bool commandExpected() {
            return compileError("command expected");
        }

        bool invalidExpressionToken(const std::string& ident) {
            return compileError("invalid expression token:" + ident);
        }

        bool unrecognizedToken() {
            return compileError("unrecognized token");
        }

        bool badArgumentCount() {
            return compileError("bad argument count");
        }

        bool endOfExpressionExpected() {
            return compileError("end of expression expected");
        }

        bool leftParenthesisExpected() {
            return compileError("left parenthesis expected");
        }

        bool rightParenthesisExpected() {
            return compileError("right parenthesis expected");
        }

        bool commaExpected() {
            return compileError("comma expected");
        }

        bool unrecognizedExpressionToken() {
            boost::any tmp = valuePeek();
            std::string tokenStr;

            try {
                tokenStr = boost::any_cast<std::string>(tmp);                
            } catch(const boost::bad_any_cast &) {
                return compileError("any_cast error");
            }
            
            return compileError("unrecognized expression token:" + tokenStr);
        }

        bool comparisonOperatorExpected() {
            return compileError("comparison operator expected");
        }

        bool integerExpected() {
            return compileError("integer expected");
        }        
        
        bool numberOrKeywordExpected() {
            return compileError("number or keyword expected");
        }        
        
        std::string filename;
        std::string script;

        std::vector<int> lineNumbers;
        std::vector<int> lineIndices;
        std::vector<std::vector<Token> >aatokenCompiled;

        bool error;
        std::string errorMessage;
        std::string errorLine;

        int cchScript;
        short lineCurrent;

        int ichToken;
        int cchToken;
        std::vector<Token> atokenCommand;

        int ichCurrentCommand;

        std::vector<Token> ltokenPostfix;
        std::vector<Token> atokenInfix;
        int itokenInfix;

        //std::vector<Token> compiledTokens_;
};

}
#endif

Revision:	1965
Committed:	Wed Feb 2 23:13:11 2005 UTC (19 years, 5 months ago) by tim
File size:	7868 byte(s)
Log Message:	selection library in progress, except SelectionEvaluator, other files are compiled
#	User	Rev	Content
1	tim	1961	/*
2			* Copyright (c) 2005 The University of Notre Dame. All Rights Reserved.
3			*
4			* The University of Notre Dame grants you ("Licensee") a
5			* non-exclusive, royalty free, license to use, modify and
6			* redistribute this software in source and binary code form, provided
7			* that the following conditions are met:
8			*
9			* 1. Acknowledgement of the program authors must be made in any
10			* publication of scientific results based in part on use of the
11			* program. An acceptable form of acknowledgement is citation of
12			* the article in which the program was described (Matthew
13			* A. Meineke, Charles F. Vardeman II, Teng Lin, Christopher
14			* J. Fennell and J. Daniel Gezelter, "OOPSE: An Object-Oriented
15			* Parallel Simulation Engine for Molecular Dynamics,"
16			* J. Comput. Chem. 26, pp. 252-271 (2005))
17			*
18			* 2. Redistributions of source code must retain the above copyright
19			* notice, this list of conditions and the following disclaimer.
20			*
21			* 3. Redistributions in binary form must reproduce the above copyright
22			* notice, this list of conditions and the following disclaimer in the
23			* documentation and/or other materials provided with the
24			* distribution.
25			*
26			* This software is provided "AS IS," without a warranty of any
27			* kind. All express or implied conditions, representations and
28			* warranties, including any implied warranty of merchantability,
29			* fitness for a particular purpose or non-infringement, are hereby
30			* excluded. The University of Notre Dame and its licensors shall not
31			* be liable for any damages suffered by licensee as a result of
32			* using, modifying or distributing the software or its
33			* derivatives. In no event will the University of Notre Dame or its
34			* licensors be liable for any lost revenue, profit or data, or for
35			* direct, indirect, special, consequential, incidental or punitive
36			* damages, however caused and regardless of the theory of liability,
37			* arising out of the use of or inability to use software, even if the
38			* University of Notre Dame has been advised of the possibility of
39			* such damages.
40			*/
41
42			#ifndef SELECTION_SELECTIONCOMPILER_HPP
43			#define SELECTION_SELECTIONCOMPILER_HPP
44	tim	1965	#include <iostream>
45	tim	1962	#include <string>
46	tim	1961	#include <vector>
47	tim	1965
48			#include "selection/Token.hpp"
49			#include "selection/TokenMap.hpp"
50	tim	1961	namespace oopse {
51
52
53			/**
54			* @class SelectionCompiler SelectionCompiler.hpp "selection/SelectionCompiler.hpp"
55			* @brief compile a selection script to tokens
56	tim	1962	* @todo document
57	tim	1961	* <pre>
58
59			expression :: = clauseOr
60
61			clauseOr ::= clauseAnd {OR clauseAnd}*
62
63			clauseAnd ::= clauseNot {AND clauseNot}*
64
65			clauseNot ::= NOT clauseNot \| clausePrimitive
66
67			clausePrimitive ::= clauseComparator \|
68			clauseWithin \|
69	tim	1962	clauseChemObject \|
70	tim	1961	none \| all \|
71			( clauseOr )
72
73			clauseComparator ::= atomproperty comparatorop integer
74
75			clauseWithin ::= WITHIN ( clauseDistance , expression )
76
77			clauseDistance ::= integer \| decimal
78	tim	1962
79			clauseChemObject::= {clauseMolecule} \| {clauseStuntDouble}
80	tim	1961
81	tim	1962	clauseMolecule ::= {clauseMolName} \| {clauseMolIndex}
82
83			clauseMolName ::= molname clauseName
84	tim	1961
85	tim	1962	clauseName::= *\|string
86	tim	1961
87	tim	1962	clauseMolIndex ::= molindex clauseIndex
88
89			clauseIndex ::= integer {- integer }
90
91			clauseStuntDouble ::= {clauseStuntDoubleName} \| {clauseStuntDoubleIndex}
92	tim	1961
93	tim	1962	clauseStuntDoubleName ::= name clauseName
94	tim	1961
95	tim	1962	clauseStuntDoubleIndex ::= index clauseIndex
96	tim	1961
97	tim	1962	* </pre>
98			*/
99			class SelectionCompiler{
100			public:
101			bool compile(const std::string& filename, const std::string& script );
102
103	tim	1961
104	tim	1962	std::vector<int> getLineNumbers() {
105			return lineNumbers;
106			}
107	tim	1961
108	tim	1962	std::vector<int> getLineIndices() {
109			return lineIndices;
110			}
111	tim	1961
112	tim	1962	std::vector<std::vector<Token> > getAatokenCompiled() {
113			return aatokenCompiled;
114			}
115	tim	1961
116	tim	1962	std::string getErrorMessage() {
117			std::string strError = errorMessage;
118			strError += " : " + errorLine + "\n";
119	tim	1961
120	tim	1962	if (!filename.empty()) {
121			strError += filename;
122			}
123	tim	1961
124	tim	1962	strError += " line#" + lineCurrent;
125			return strError;
126			}
127	tim	1961
128	tim	1962
129	tim	1961	private:
130
131	tim	1965	bool internalCompile();
132	tim	1962
133
134			bool lookingAtLeadingWhitespace();
135			bool lookingAtComment();
136			bool lookingAtEndOfLine();
137			bool lookingAtEndOfStatement();
138			bool lookingAtString();
139	tim	1965	bool lookingAtDecimal(bool allowNegative);
140			bool lookingAtInteger(bool allowNegative);
141			bool lookingAtLookupToken();
142			bool lookingAtSpecialString();
143	tim	1962
144	tim	1965	std::string getUnescapedStringLiteral();
145			int getHexitValue(char ch);
146	tim	1962
147	tim	1965	bool compileCommand(const std::vector<Token>& ltoken);
148			bool compileExpression();
149			bool compileExpression(int itoken);
150	tim	1962
151	tim	1961	bool clauseOr();
152			bool clauseAnd();
153			bool clauseNot();
154			bool clausePrimitive();
155			bool clauseWithin();
156			bool clauseComparator();
157	tim	1965	bool clauseName(int tok);
158			bool clauseIndex(int tok);
159	tim	1962
160	tim	1965	Token tokenNext();
161			boost::any valuePeek();
162			int tokPeek();
163
164			bool addTokenToPostfix(const Token& token);
165
166
167	tim	1962	bool compileError(const std::string& errorMessage) {
168	tim	1965	std::cerr << "SelectionCompiler Error: " << errorMessage << std::endl;
169	tim	1962	error = true;
170	tim	1965	this->errorMessage = errorMessage;
171	tim	1962	return false;
172			}
173	tim	1961
174	tim	1962	bool commandExpected() {
175			return compileError("command expected");
176			}
177	tim	1961
178	tim	1962	bool invalidExpressionToken(const std::string& ident) {
179			return compileError("invalid expression token:" + ident);
180			}
181
182			bool unrecognizedToken() {
183			return compileError("unrecognized token");
184			}
185
186			bool badArgumentCount() {
187			return compileError("bad argument count");
188			}
189
190			bool endOfExpressionExpected() {
191			return compileError("end of expression expected");
192			}
193
194			bool leftParenthesisExpected() {
195			return compileError("left parenthesis expected");
196			}
197
198			bool rightParenthesisExpected() {
199			return compileError("right parenthesis expected");
200			}
201
202			bool commaExpected() {
203			return compileError("comma expected");
204			}
205
206			bool unrecognizedExpressionToken() {
207	tim	1965	boost::any tmp = valuePeek();
208			std::string tokenStr;
209
210			try {
211			tokenStr = boost::any_cast<std::string>(tmp);
212			} catch(const boost::bad_any_cast &) {
213			return compileError("any_cast error");
214			}
215
216			return compileError("unrecognized expression token:" + tokenStr);
217	tim	1962	}
218
219			bool comparisonOperatorExpected() {
220			return compileError("comparison operator expected");
221			}
222
223			bool integerExpected() {
224			return compileError("integer expected");
225			}
226
227	tim	1965	bool numberOrKeywordExpected() {
228			return compileError("number or keyword expected");
229			}
230	tim	1962
231			std::string filename;
232			std::string script;
233
234			std::vector<int> lineNumbers;
235			std::vector<int> lineIndices;
236			std::vector<std::vector<Token> >aatokenCompiled;
237
238			bool error;
239			std::string errorMessage;
240			std::string errorLine;
241
242			int cchScript;
243			short lineCurrent;
244
245			int ichToken;
246			int cchToken;
247			std::vector<Token> atokenCommand;
248
249			int ichCurrentCommand;
250
251			std::vector<Token> ltokenPostfix;
252			std::vector<Token> atokenInfix;
253			int itokenInfix;
254
255			//std::vector<Token> compiledTokens_;
256	tim	1961	};
257
258			}
259			#endif
260	tim	1962