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 |
                         clauseName |
                         none | all |
                         ( clauseOr )

    clauseComparator ::= atomproperty comparatorop integer

    clauseWithin     ::= WITHIN ( clauseDistance , expression )

    clauseDistance   ::= integer | decimal
        
    clauseName::= *|string{.string{.string}}


 * </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;
            }

            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 clauseChemObjName();        
        bool clauseIndex();
        Token tokenNext();
        boost::any valuePeek();
        int tokPeek();

        bool addTokenToPostfix(const Token& token);
        bool isNameValid(const std::string& name);

        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 numberExpected() {
            return compileError("number 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:	2147
Committed:	Tue Apr 5 23:09:48 2005 UTC (19 years, 3 months ago) by tim
File size:	7448 byte(s)
Log Message:	support '+' and '-' in atom type name;clean the code a little bit
#	Content
1	/*
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	#include <iostream>
45	#include <string>
46	#include <vector>
47
48	#include "selection/Token.hpp"
49	#include "selection/TokenMap.hpp"
50	namespace oopse {
51
52
53	/**
54	* @class SelectionCompiler SelectionCompiler.hpp "selection/SelectionCompiler.hpp"
55	* @brief compile a selection script to tokens
56	* @todo document
57	* <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	clauseName \|
70	none \| all \|
71	( clauseOr )
72
73	clauseComparator ::= atomproperty comparatorop integer
74
75	clauseWithin ::= WITHIN ( clauseDistance , expression )
76
77	clauseDistance ::= integer \| decimal
78
79	clauseName::= *\|string{.string{.string}}
80
81
82	* </pre>
83	*/
84	class SelectionCompiler{
85	public:
86	bool compile(const std::string& filename, const std::string& script );
87
88
89	std::vector<int> getLineNumbers() {
90	return lineNumbers;
91	}
92
93	std::vector<int> getLineIndices() {
94	return lineIndices;
95	}
96
97	std::vector<std::vector<Token> > getAatokenCompiled() {
98	return aatokenCompiled;
99	}
100
101	std::string getErrorMessage() {
102	std::string strError = errorMessage;
103	strError += " : " + errorLine + "\n";
104
105	if (!filename.empty()) {
106	strError += filename;
107	}
108
109	return strError;
110	}
111
112
113	private:
114
115	bool internalCompile();
116
117
118	bool lookingAtLeadingWhitespace();
119	//bool lookingAtComment();
120	bool lookingAtEndOfLine();
121	bool lookingAtEndOfStatement();
122	bool lookingAtString();
123	bool lookingAtDecimal(bool allowNegative);
124	bool lookingAtInteger(bool allowNegative);
125	bool lookingAtLookupToken();
126	bool lookingAtSpecialString();
127
128	std::string getUnescapedStringLiteral();
129	int getHexitValue(char ch);
130
131	bool compileCommand(const std::vector<Token>& ltoken);
132	bool compileExpression();
133	bool compileExpression(int itoken);
134
135	bool clauseOr();
136	bool clauseAnd();
137	bool clauseNot();
138	bool clausePrimitive();
139	bool clauseWithin();
140	bool clauseComparator();
141	bool clauseChemObjName();
142	bool clauseIndex();
143	Token tokenNext();
144	boost::any valuePeek();
145	int tokPeek();
146
147	bool addTokenToPostfix(const Token& token);
148	bool isNameValid(const std::string& name);
149
150	bool compileError(const std::string& errorMessage) {
151	std::cerr << "SelectionCompiler Error: " << errorMessage << std::endl;
152	error = true;
153	this->errorMessage = errorMessage;
154	return false;
155	}
156
157	bool commandExpected() {
158	return compileError("command expected");
159	}
160
161	bool invalidExpressionToken(const std::string& ident) {
162	return compileError("invalid expression token:" + ident);
163	}
164
165	bool unrecognizedToken() {
166	return compileError("unrecognized token");
167	}
168
169	bool badArgumentCount() {
170	return compileError("bad argument count");
171	}
172
173	bool endOfExpressionExpected() {
174	return compileError("end of expression expected");
175	}
176
177	bool leftParenthesisExpected() {
178	return compileError("left parenthesis expected");
179	}
180
181	bool rightParenthesisExpected() {
182	return compileError("right parenthesis expected");
183	}
184
185	bool commaExpected() {
186	return compileError("comma expected");
187	}
188
189	bool unrecognizedExpressionToken() {
190	boost::any tmp = valuePeek();
191	std::string tokenStr;
192
193	try {
194	tokenStr = boost::any_cast<std::string>(tmp);
195	} catch(const boost::bad_any_cast &) {
196	return compileError("any_cast error");
197	}
198
199	return compileError("unrecognized expression token:" + tokenStr);
200	}
201
202	bool comparisonOperatorExpected() {
203	return compileError("comparison operator expected");
204	}
205
206	bool numberExpected() {
207	return compileError("number expected");
208	}
209
210	bool numberOrKeywordExpected() {
211	return compileError("number or keyword expected");
212	}
213
214	std::string filename;
215	std::string script;
216
217	std::vector<int> lineNumbers;
218	std::vector<int> lineIndices;
219	std::vector<std::vector<Token> >aatokenCompiled;
220
221	bool error;
222	std::string errorMessage;
223	std::string errorLine;
224
225	int cchScript;
226	short lineCurrent;
227
228	int ichToken;
229	int cchToken;
230	std::vector<Token> atokenCommand;
231
232	int ichCurrentCommand;
233
234	std::vector<Token> ltokenPostfix;
235	std::vector<Token> atokenInfix;
236	int itokenInfix;
237
238	//std::vector<Token> compiledTokens_;
239	};
240
241	}
242	#endif
243