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. 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.
 */
 
/**
 * @file StringTokenizer.hpp
 * @author tlin
 * @date 09/20/2004
 * @time 11:30am
 * @version 1.0
 */

#ifndef UTIL_STRINGTOKENIZER_HPP
#define UTIL_STRINGTOKENIZER_HPP

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

  /**
   * @class StringTokenizer.hpp "util/StringTokenizer.hpp"
   * @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();
  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 oopse

#endif                          //UTIL_STRINGTOKENIZER_HPP
Revision:	3437
Committed:	Wed Jul 30 18:11:19 2008 UTC (16 years, 1 month ago) by gezelter
File size:	7893 byte(s)
Log Message:	Many fixes
#	User	Rev	Content
1	gezelter	2204	/*
2	gezelter	1930	* Copyright (c) 2005 The University of Notre Dame. All Rights Reserved.
3	tim	1594	*
4	gezelter	1930	* 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	tim	1594	*/
41	gezelter	1930
42			/**
43			* @file StringTokenizer.hpp
44			* @author tlin
45			* @date 09/20/2004
46			* @time 11:30am
47			* @version 1.0
48			*/
49	tim	1594
50			#ifndef UTIL_STRINGTOKENIZER_HPP
51			#define UTIL_STRINGTOKENIZER_HPP
52
53	gezelter	1930	#include <string>
54	gezelter	3437	#include <stdlib.h>
55	tim	2469	#include <vector>
56	tim	2759	#include "config.h"
57	gezelter	1930	namespace oopse {
58	tim	1594
59	gezelter	2204	/**
60			* @class StringTokenizer.hpp "util/StringTokenizer.hpp"
61			* @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	1594
70	gezelter	2204	/**
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	1594
82	gezelter	2204	/**
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			StringTokenizer(std::string::const_iterator& first, std::string::const_iterator& last,
93			const std::string & delim = " ;\t\n\r");
94	tim	1594
95	gezelter	2204	/**
96			* Constructs a string tokenizer for the specified string. The characters in the delim argument
97			* are the delimiters for separating tokens.
98			* If the returnTokens flag is true, then the delimiter characters are also returned as tokens.
99			* Each delimiter is returned as a string of length one. If the flag is false, the delimiter
100			* characters are skipped and only serve as separators between tokens.
101			* @param str a string to be parsed.
102			* @param delim the delimiters.
103			* @param returnTokens flag indicating whether to return the delimiters as tokens.
104			*/
105			StringTokenizer(const std::string&str, const std::string&delim,
106			bool returnTokens);
107	tim	1594
108	gezelter	2204	/**
109			* Calculates the number of times that this tokenizer's nextToken method can be called
110			* before it generates an exception.
111			* @return the number of tokens remaining in the string using the current delimiter set.
112			*/
113			int countTokens();
114	tim	1594
115	gezelter	2204	/**
116			* Tests if there are more tokens available from this tokenizer's string.
117			* @return true if there are more tokens available from this tokenizer's string, false otherwise
118			*/
119			bool hasMoreTokens();
120	tim	1594
121	gezelter	2204	/**
122			* Returns the next token from this string tokenizer.
123			* @return the next token from this string tokenizer.
124			* @exception NoSuchElementException if there are no more tokens in this tokenizer's string
125			*/
126			std::string nextToken();
127	tim	1594
128	gezelter	2204	//actually, nextToken Can be template function
129			//template <typename ReturnType>
130			//ReturnType nextToken();
131	gezelter	1930
132	gezelter	2204	/**
133			* Returns the next token from this string tokenizer as a bool.
134			* @return the next token from this string tokenizer as a bool.
135			*/
136			bool nextTokenAsBool();
137	tim	1594
138	gezelter	2204	/**
139			* Returns the next token from this string tokenizer as an integer.
140			* @return the next token from this string tokenizer as an integer.
141			*/
142			int nextTokenAsInt();
143	tim	1594
144	gezelter	2204	/**
145			* Returns the next token from this string tokenizer as a float.
146			* @return the next token from this string tokenizer as a float.
147			*/
148			float nextTokenAsFloat();
149	tim	1594
150	gezelter	2204	/**
151	tim	2759	* Returns the next token from this string tokenizer as a RealType.
152			* @return the next token from this string tokenizer as a RealType.
153	gezelter	2204	*/
154	tim	2759	RealType nextTokenAsDouble();
155	tim	1594
156	gezelter	2204	/**
157			* Returns the next token without advancing the position of the StringTokenizer.
158			* @return the next token
159			*/
160			std::string peekNextToken();
161	gezelter	1930
162	gezelter	2204	/**
163			* Returns the current delimiter set of this string tokenizer
164			* @return the current delimiter set
165			*/
166			const std::string& getDelimiters() {
167			return delim_;
168			}
169	gezelter	1930
170	gezelter	2204	/**
171			* Returns the original string before tokenizing.
172			* @return the original string before tokenizing
173			*/
174			const std::string& getOriginal() {
175			return tokenString_;
176			}
177	gezelter	1930
178	tim	2469	/**
179			* Returns all of the tokens
180			* @return all of the tokens
181			*/
182			std::vector<std::string> getAllTokens();
183	gezelter	2204	private:
184	gezelter	1930
185	gezelter	2204	/**
186			* Test if character is in current delimiter set.
187			* @param c character to be tested
188			* @return true if character is in current delimiter set, flase otherwise.
189			*/
190			bool isDelimiter(const char c);
191	gezelter	1930
192	gezelter	2204	/** convert a fortran number to a c/c++ number */
193			void convertFortranNumber(std::string& fortranNumber);
194	tim	1945
195
196	gezelter	2204	std::string tokenString_;
197	gezelter	1930
198	gezelter	2204	std::string delim_; /*< current delimiter set of this string tokenizer /
199	gezelter	1930
200	gezelter	2204	bool returnTokens_; /*< flag indicating whether to return the delimiters as tokens /
201	gezelter	1930
202	gezelter	2204	std::string::const_iterator currentPos_;
203			std::string::const_iterator end_;
204			};
205	gezelter	1930
206			} //namespace oopse
207
208			#endif //UTIL_STRINGTOKENIZER_HPP