src/utils/StringTokenizer.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, 234107 (2008).          
 * [4]  Kuang & Gezelter,  J. Chem. Phys. 133, 164101 (2010).
 * [5]  Vardeman, Stocker & Gezelter, J. Chem. Theory Comput. 7, 834 (2011).
 */
 
/**
 * @file StringTokenizer.hpp
 * @author tlin
 * @date 09/20/2004
 * @version 1.0
 */

#ifndef UTIL_STRINGTOKENIZER_HPP
#define UTIL_STRINGTOKENIZER_HPP

#include <string>
#include <stdlib.h>
#include <vector>
#include "config.h"
namespace OpenMD {

  /**
   * @class StringTokenizer
   * @brief The string tokenizer class allows an application to break a string into tokens
   * The set of delimiters (the characters that separate tokens) may be specified either 
   * at creation time or on a per-token basis. 
   * An instance of StringTokenizer behaves in one of two ways, depending on whether it was 
   * created with the returnTokens flag having the value true or false.
   */
  class StringTokenizer {
  public:

    /**
     * Constructs a string tokenizer for the specified string. The characters in the delim argument
     * are the delimiters for separating tokens. characters are skipped and only serve as 
     * separators between tokens.
     * @param str a string to be parsed.
     * @param delim the delimiters, default value is " ;\t\n\r".
     * @note this is still a little bit java like implementation. Pure c++ one should use TokenIterator.
     * Boost's tokenizer class is one of them 
     */
    StringTokenizer(const std::string & str,
                    const std::string & delim = " ;\t\n\r");

    /**
     * Constructs a string tokenizer for an iterator range [first, last). The characters in the delim argument
     * are the delimiters for separating tokens. characters are skipped and only serve as 
     * separators between tokens.
     * @param first begin iterator
     * @param last end iterator
     * @param delim the delimiters, default value is " ;\t\n\r".
     * @note this is still a little bit java like implementation. Pure c++ one should use TokenIterator.
     * Boost's tokenizer class is one of them 
     */
    StringTokenizer(std::string::const_iterator& first,
                    std::string::const_iterator& last,
                    const std::string & delim = " ;\t\n\r");

    /**
     * Constructs a string tokenizer for the specified string. The characters in the delim argument
     * are the delimiters for separating tokens. 
     * If the returnTokens flag is true, then the delimiter characters are also returned as tokens. 
     * Each delimiter is returned as a string of length one. If the flag is false, the delimiter 
     * characters are skipped and only serve as separators between tokens.
     * @param str a string to be parsed. 
     * @param delim the delimiters. 
     * @param returnTokens flag indicating whether to return the delimiters as tokens.
     */
    StringTokenizer(const std::string&str, const std::string&delim,
                    bool returnTokens);

    /**
     * Calculates the number of times that this tokenizer's nextToken method can be called 
     * before it generates an exception.
     * @return the number of tokens remaining in the string using the current delimiter set.
     */
    int countTokens();

    /**
     * Tests if there are more tokens available from this tokenizer's string.
     * @return true if there are more tokens available from this tokenizer's string, false otherwise
     */
    bool hasMoreTokens();

    /**
     * Returns the next token from this string tokenizer.
     * @return the next token from this string tokenizer.
     * @exception NoSuchElementException if there are no more tokens in this tokenizer's string
     */
    std::string nextToken();

    //actually, nextToken Can be template function
    //template <typename ReturnType>
    //ReturnType nextToken();
        
    /**
     * Returns the next token from this string tokenizer as a bool.
     * @return the next token from this string tokenizer  as a bool.
     */
    bool nextTokenAsBool();

    /**
     * Returns the next token from this string tokenizer as an integer.
     * @return the next token from this string tokenizer  as an integer.
     */
    int nextTokenAsInt();

    /**
     * Returns the next token from this string tokenizer as a float.
     * @return the next token from this string tokenizer as a float.
     */
    float nextTokenAsFloat();

    /**
     * Returns the next token from this string tokenizer as a RealType.
     * @return the next token from this string tokenizer as a RealType.
     */
    RealType nextTokenAsDouble();

    /**
     * Returns the next token without advancing the position of the StringTokenizer.
     * @return the next token
     */
    std::string  peekNextToken();

    /**
     * Returns the current delimiter set of this string tokenizer
     * @return the current delimiter set
     */
    const std::string& getDelimiters() {
      return delim_;
    }

    /** 
     * Returns the original string before tokenizing.
     * @return the original string before tokenizing 
     */
    const std::string& getOriginal() {
      return tokenString_;
    }

    /** 
     * Returns all of the tokens
     * @return all of the tokens
     */
    std::vector<std::string> getAllTokens();
    /** 
     * Returns the remaining unparsed string
     * @return the remaining unparsed string
     */
    std::string getRemainingString();
  private:

    /**
     * Test if character is in current delimiter set.
     * @param c character to be tested
     * @return true if character is in current delimiter set, flase otherwise.
     */
    bool isDelimiter(const char c);

    /** convert a fortran number to a c/c++ number */
    void convertFortranNumber(std::string& fortranNumber);
         

    std::string tokenString_;

    std::string delim_;         /**< current delimiter set of this string tokenizer */

    bool returnTokens_; /**< flag indicating whether to return the delimiters as tokens */

    std::string::const_iterator currentPos_;
    std::string::const_iterator end_;
  };

}                               //namespace OpenMD

#endif                          //UTIL_STRINGTOKENIZER_HPP
Revision:	2045
Committed:	Fri Nov 28 20:10:17 2014 UTC (10 years, 5 months ago) by gezelter
File size:	8120 byte(s)
Log Message:	Starting to get ready for 2.3 release. Separating type parsers from io routines. Fixing old samples to use newer syntax.
#	User	Rev	Content
1	gezelter	507	/*
2	gezelter	246	* Copyright (c) 2005 The University of Notre Dame. All Rights Reserved.
3	tim	101	*
4	gezelter	246	* 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	gezelter	246	* notice, this list of conditions and the following disclaimer.
11			*
12	gezelter	1390	* 2. Redistributions in binary form must reproduce the above copyright
13	gezelter	246	* 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	gezelter	1879	* [3] Sun, Lin & Gezelter, J. Chem. Phys. 128, 234107 (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	101	*/
42	gezelter	246
43			/**
44			* @file StringTokenizer.hpp
45			* @author tlin
46			* @date 09/20/2004
47			* @version 1.0
48			*/
49	tim	101
50			#ifndef UTIL_STRINGTOKENIZER_HPP
51			#define UTIL_STRINGTOKENIZER_HPP
52
53	gezelter	246	#include <string>
54	gezelter	1282	#include <stdlib.h>
55	tim	770	#include <vector>
56	tim	963	#include "config.h"
57	gezelter	1390	namespace OpenMD {
58	tim	101
59	gezelter	507	/**
60	gezelter	1879	* @class StringTokenizer
61	gezelter	507	* @brief The string tokenizer class allows an application to break a string into tokens
62			* The set of delimiters (the characters that separate tokens) may be specified either
63			* at creation time or on a per-token basis.
64			* An instance of StringTokenizer behaves in one of two ways, depending on whether it was
65			* created with the returnTokens flag having the value true or false.
66			*/
67			class StringTokenizer {
68			public:
69	tim	101
70	gezelter	507	/**
71			* Constructs a string tokenizer for the specified string. The characters in the delim argument
72			* are the delimiters for separating tokens. characters are skipped and only serve as
73			* separators between tokens.
74			* @param str a string to be parsed.
75			* @param delim the delimiters, default value is " ;\t\n\r".
76			* @note this is still a little bit java like implementation. Pure c++ one should use TokenIterator.
77			* Boost's tokenizer class is one of them
78			*/
79			StringTokenizer(const std::string & str,
80			const std::string & delim = " ;\t\n\r");
81	tim	101
82	gezelter	507	/**
83			* Constructs a string tokenizer for an iterator range [first, last). The characters in the delim argument
84			* are the delimiters for separating tokens. characters are skipped and only serve as
85			* separators between tokens.
86			* @param first begin iterator
87			* @param last end iterator
88			* @param delim the delimiters, default value is " ;\t\n\r".
89			* @note this is still a little bit java like implementation. Pure c++ one should use TokenIterator.
90			* Boost's tokenizer class is one of them
91			*/
92	gezelter	2045	StringTokenizer(std::string::const_iterator& first,
93			std::string::const_iterator& last,
94	gezelter	507	const std::string & delim = " ;\t\n\r");
95	tim	101
96	gezelter	507	/**
97			* Constructs a string tokenizer for the specified string. The characters in the delim argument
98			* are the delimiters for separating tokens.
99			* If the returnTokens flag is true, then the delimiter characters are also returned as tokens.
100			* Each delimiter is returned as a string of length one. If the flag is false, the delimiter
101			* characters are skipped and only serve as separators between tokens.
102			* @param str a string to be parsed.
103			* @param delim the delimiters.
104			* @param returnTokens flag indicating whether to return the delimiters as tokens.
105			*/
106			StringTokenizer(const std::string&str, const std::string&delim,
107			bool returnTokens);
108	tim	101
109	gezelter	507	/**
110			* Calculates the number of times that this tokenizer's nextToken method can be called
111			* before it generates an exception.
112			* @return the number of tokens remaining in the string using the current delimiter set.
113			*/
114			int countTokens();
115	tim	101
116	gezelter	507	/**
117			* Tests if there are more tokens available from this tokenizer's string.
118			* @return true if there are more tokens available from this tokenizer's string, false otherwise
119			*/
120			bool hasMoreTokens();
121	tim	101
122	gezelter	507	/**
123			* Returns the next token from this string tokenizer.
124			* @return the next token from this string tokenizer.
125			* @exception NoSuchElementException if there are no more tokens in this tokenizer's string
126			*/
127			std::string nextToken();
128	tim	101
129	gezelter	507	//actually, nextToken Can be template function
130			//template <typename ReturnType>
131			//ReturnType nextToken();
132	gezelter	246
133	gezelter	507	/**
134			* Returns the next token from this string tokenizer as a bool.
135			* @return the next token from this string tokenizer as a bool.
136			*/
137			bool nextTokenAsBool();
138	tim	101
139	gezelter	507	/**
140			* Returns the next token from this string tokenizer as an integer.
141			* @return the next token from this string tokenizer as an integer.
142			*/
143			int nextTokenAsInt();
144	tim	101
145	gezelter	507	/**
146			* Returns the next token from this string tokenizer as a float.
147			* @return the next token from this string tokenizer as a float.
148			*/
149			float nextTokenAsFloat();
150	tim	101
151	gezelter	507	/**
152	tim	963	* Returns the next token from this string tokenizer as a RealType.
153			* @return the next token from this string tokenizer as a RealType.
154	gezelter	507	*/
155	tim	963	RealType nextTokenAsDouble();
156	tim	101
157	gezelter	507	/**
158			* Returns the next token without advancing the position of the StringTokenizer.
159			* @return the next token
160			*/
161			std::string peekNextToken();
162	gezelter	246
163	gezelter	507	/**
164			* Returns the current delimiter set of this string tokenizer
165			* @return the current delimiter set
166			*/
167			const std::string& getDelimiters() {
168			return delim_;
169			}
170	gezelter	246
171	gezelter	507	/**
172			* Returns the original string before tokenizing.
173			* @return the original string before tokenizing
174			*/
175			const std::string& getOriginal() {
176			return tokenString_;
177			}
178	gezelter	246
179	tim	770	/**
180			* Returns all of the tokens
181			* @return all of the tokens
182			*/
183			std::vector<std::string> getAllTokens();
184	gezelter	2045	/**
185			* Returns the remaining unparsed string
186			* @return the remaining unparsed string
187			*/
188			std::string getRemainingString();
189	gezelter	507	private:
190	gezelter	246
191	gezelter	507	/**
192			* Test if character is in current delimiter set.
193			* @param c character to be tested
194			* @return true if character is in current delimiter set, flase otherwise.
195			*/
196			bool isDelimiter(const char c);
197	gezelter	246
198	gezelter	507	/** convert a fortran number to a c/c++ number */
199			void convertFortranNumber(std::string& fortranNumber);
200	tim	261
201
202	gezelter	507	std::string tokenString_;
203	gezelter	246
204	gezelter	507	std::string delim_; /*< current delimiter set of this string tokenizer /
205	gezelter	246
206	gezelter	507	bool returnTokens_; /*< flag indicating whether to return the delimiters as tokens /
207	gezelter	246
208	gezelter	507	std::string::const_iterator currentPos_;
209			std::string::const_iterator end_;
210			};
211	gezelter	246
212	gezelter	1390	} //namespace OpenMD
213	gezelter	246
214			#endif //UTIL_STRINGTOKENIZER_HPP