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. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. 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.
 *
 * SUPPORT OPEN SCIENCE!  If you use OpenMD or its source code in your
 * research, please cite the appropriate papers when you publish your
 * work.  Good starting points are:
 *                                                                      
 * [1]  Meineke, et al., J. Comp. Chem. 26, 252-271 (2005).             
 * [2]  Fennell & Gezelter, J. Chem. Phys. 124, 234104 (2006).          
 * [3]  Sun, Lin & Gezelter, J. Chem. Phys. 128, 24107 (2008).          
 * [4]  Kuang & Gezelter,  J. Chem. Phys. 133, 164101 (2010).
 * [5]  Vardeman, Stocker & Gezelter, J. Chem. Theory Comput. 7, 834 (2011).
 */

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

#include "selection/SelectionToken.hpp"
#include "selection/TokenMap.hpp"
#include "brains/SimInfo.hpp"

namespace OpenMD {


  /**
   * @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& errorMsg) {

      sprintf( painCave.errMsg,
               "SelectionCompiler Error: %s\n", errorMsg.c_str());
      painCave.severity = OPENMD_ERROR;
      painCave.isFatal = 1;
      simError();

      error = true;
      this->errorMessage = errorMsg;
      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:	1782
Committed:	Wed Aug 22 02:28:28 2012 UTC (12 years, 8 months ago) by gezelter
File size:	7072 byte(s)
Log Message:	MERGE OpenMD development branch 1465:1781 into trunk
#	User	Rev	Content
1	tim	277	/*
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	gezelter	1390	* 1. Redistributions of source code must retain the above copyright
10	tim	277	* notice, this list of conditions and the following disclaimer.
11			*
12	gezelter	1390	* 2. Redistributions in binary form must reproduce the above copyright
13	tim	277	* notice, this list of conditions and the following disclaimer in the
14			* documentation and/or other materials provided with the
15			* distribution.
16			*
17			* This software is provided "AS IS," without a warranty of any
18			* kind. All express or implied conditions, representations and
19			* warranties, including any implied warranty of merchantability,
20			* fitness for a particular purpose or non-infringement, are hereby
21			* excluded. The University of Notre Dame and its licensors shall not
22			* be liable for any damages suffered by licensee as a result of
23			* using, modifying or distributing the software or its
24			* derivatives. In no event will the University of Notre Dame or its
25			* licensors be liable for any lost revenue, profit or data, or for
26			* direct, indirect, special, consequential, incidental or punitive
27			* damages, however caused and regardless of the theory of liability,
28			* arising out of the use of or inability to use software, even if the
29			* University of Notre Dame has been advised of the possibility of
30			* such damages.
31	gezelter	1390	*
32			* SUPPORT OPEN SCIENCE! If you use OpenMD or its source code in your
33			* research, please cite the appropriate papers when you publish your
34			* work. Good starting points are:
35			*
36			* [1] Meineke, et al., J. Comp. Chem. 26, 252-271 (2005).
37			* [2] Fennell & Gezelter, J. Chem. Phys. 124, 234104 (2006).
38			* [3] Sun, Lin & Gezelter, J. Chem. Phys. 128, 24107 (2008).
39	gezelter	1782	* [4] Kuang & Gezelter, J. Chem. Phys. 133, 164101 (2010).
40			* [5] Vardeman, Stocker & Gezelter, J. Chem. Theory Comput. 7, 834 (2011).
41	tim	277	*/
42
43			#ifndef SELECTION_SELECTIONCOMPILER_HPP
44			#define SELECTION_SELECTIONCOMPILER_HPP
45	tim	281	#include <iostream>
46	tim	278	#include <string>
47	tim	277	#include <vector>
48	tim	281
49	tim	770	#include "selection/SelectionToken.hpp"
50	tim	281	#include "selection/TokenMap.hpp"
51	cli2	1364	#include "brains/SimInfo.hpp"
52
53	gezelter	1390	namespace OpenMD {
54	tim	277
55
56	gezelter	507	/**
57			* @class SelectionCompiler SelectionCompiler.hpp "selection/SelectionCompiler.hpp"
58			* @brief compile a selection script to tokens
59			* @todo document
60			* <pre>
61	tim	277
62	gezelter	507	expression :: = clauseOr
63	tim	277
64	gezelter	507	clauseOr ::= clauseAnd {OR clauseAnd}*
65	tim	277
66	gezelter	507	clauseAnd ::= clauseNot {AND clauseNot}*
67	tim	277
68	gezelter	507	clauseNot ::= NOT clauseNot \| clausePrimitive
69	tim	277
70	gezelter	507	clausePrimitive ::= clauseComparator \|
71			clauseWithin \|
72			clauseName \|
73			none \| all \|
74			( clauseOr )
75	tim	277
76	gezelter	507	clauseComparator ::= atomproperty comparatorop integer
77	tim	277
78	gezelter	507	clauseWithin ::= WITHIN ( clauseDistance , expression )
79	tim	277
80	gezelter	507	clauseDistance ::= integer \| decimal
81	tim	283
82	gezelter	507	clauseName::= *\|string{.string{.string}}
83	tim	277
84	tim	278
85	gezelter	507	* </pre>
86			*/
87			class SelectionCompiler{
88			public:
89			bool compile(const std::string& filename, const std::string& script );
90	tim	278
91	tim	277
92	gezelter	507	std::vector<int> getLineNumbers() {
93			return lineNumbers;
94			}
95	tim	277
96	gezelter	507	std::vector<int> getLineIndices() {
97			return lineIndices;
98			}
99	tim	277
100	gezelter	507	std::vector<std::vector<Token> > getAatokenCompiled() {
101			return aatokenCompiled;
102			}
103	tim	277
104	gezelter	507	std::string getErrorMessage() {
105			std::string strError = errorMessage;
106			strError += " : " + errorLine + "\n";
107	tim	277
108	gezelter	507	if (!filename.empty()) {
109			strError += filename;
110			}
111	tim	277
112	gezelter	507	return strError;
113			}
114	tim	277
115	tim	278
116	gezelter	507	private:
117	tim	277
118	gezelter	507	bool internalCompile();
119	tim	278
120
121	gezelter	507	bool lookingAtLeadingWhitespace();
122			//bool lookingAtComment();
123			bool lookingAtEndOfLine();
124			bool lookingAtEndOfStatement();
125			bool lookingAtString();
126			bool lookingAtDecimal(bool allowNegative);
127			bool lookingAtInteger(bool allowNegative);
128			bool lookingAtLookupToken();
129			bool lookingAtSpecialString();
130	tim	278
131	gezelter	507	std::string getUnescapedStringLiteral();
132			int getHexitValue(char ch);
133	tim	278
134	gezelter	507	bool compileCommand(const std::vector<Token>& ltoken);
135			bool compileExpression();
136			bool compileExpression(int itoken);
137	tim	278
138	gezelter	507	bool clauseOr();
139			bool clauseAnd();
140			bool clauseNot();
141			bool clausePrimitive();
142			bool clauseWithin();
143			bool clauseComparator();
144			bool clauseChemObjName();
145			bool clauseIndex();
146			Token tokenNext();
147			boost::any valuePeek();
148			int tokPeek();
149	tim	281
150	gezelter	507	bool addTokenToPostfix(const Token& token);
151			bool isNameValid(const std::string& name);
152	tim	281
153	gezelter	507	bool compileError(const std::string& errorMsg) {
154	cli2	1364
155			sprintf( painCave.errMsg,
156			"SelectionCompiler Error: %s\n", errorMsg.c_str());
157	gezelter	1390	painCave.severity = OPENMD_ERROR;
158	cli2	1364	painCave.isFatal = 1;
159			simError();
160
161	gezelter	507	error = true;
162			this->errorMessage = errorMsg;
163			return false;
164			}
165	tim	277
166	gezelter	507	bool commandExpected() {
167			return compileError("command expected");
168			}
169	tim	277
170	gezelter	507	bool invalidExpressionToken(const std::string& ident) {
171			return compileError("invalid expression token:" + ident);
172			}
173	tim	278
174	gezelter	507	bool unrecognizedToken() {
175			return compileError("unrecognized token");
176			}
177	tim	278
178	gezelter	507	bool badArgumentCount() {
179			return compileError("bad argument count");
180			}
181	tim	278
182	gezelter	507	bool endOfExpressionExpected() {
183			return compileError("end of expression expected");
184			}
185	tim	278
186	gezelter	507	bool leftParenthesisExpected() {
187			return compileError("left parenthesis expected");
188			}
189	tim	278
190	gezelter	507	bool rightParenthesisExpected() {
191			return compileError("right parenthesis expected");
192			}
193	tim	278
194	gezelter	507	bool commaExpected() {
195			return compileError("comma expected");
196			}
197	tim	278
198	gezelter	507	bool unrecognizedExpressionToken() {
199			boost::any tmp = valuePeek();
200			std::string tokenStr;
201	tim	281
202	gezelter	507	try {
203			tokenStr = boost::any_cast<std::string>(tmp);
204			} catch(const boost::bad_any_cast &) {
205			return compileError("any_cast error");
206			}
207	tim	281
208	gezelter	507	return compileError("unrecognized expression token:" + tokenStr);
209			}
210	tim	278
211	gezelter	507	bool comparisonOperatorExpected() {
212			return compileError("comparison operator expected");
213			}
214	tim	278
215	gezelter	507	bool numberExpected() {
216			return compileError("number expected");
217			}
218	tim	278
219	gezelter	507	bool numberOrKeywordExpected() {
220			return compileError("number or keyword expected");
221			}
222	tim	278
223	gezelter	507	std::string filename;
224			std::string script;
225	tim	278
226	gezelter	507	std::vector<int> lineNumbers;
227			std::vector<int> lineIndices;
228			std::vector<std::vector<Token> >aatokenCompiled;
229	tim	278
230	gezelter	507	bool error;
231			std::string errorMessage;
232			std::string errorLine;
233	tim	278
234	gezelter	507	int cchScript;
235			short lineCurrent;
236	tim	278
237	gezelter	507	int ichToken;
238			int cchToken;
239			std::vector<Token> atokenCommand;
240	tim	278
241	gezelter	507	int ichCurrentCommand;
242	tim	278
243	gezelter	507	std::vector<Token> ltokenPostfix;
244			std::vector<Token> atokenInfix;
245			int itokenInfix;
246	tim	278
247	gezelter	507	//std::vector<Token> compiledTokens_;
248			};
249	tim	277
250			}
251			#endif
252	tim	278