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 <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:	2759
Committed:	Wed May 17 21:51:42 2006 UTC (18 years, 2 months ago) by tim
File size:	7873 byte(s)
Log Message:	Adding single precision capabilities to c++ side
#	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	tim	2469	#include <vector>
55	tim	2759	#include "config.h"
56	gezelter	1930	namespace oopse {
57	tim	1594
58	gezelter	2204	/**
59			* @class StringTokenizer.hpp "util/StringTokenizer.hpp"
60			* @brief The string tokenizer class allows an application to break a string into tokens
61			* The set of delimiters (the characters that separate tokens) may be specified either
62			* at creation time or on a per-token basis.
63			* An instance of StringTokenizer behaves in one of two ways, depending on whether it was
64			* created with the returnTokens flag having the value true or false.
65			*/
66			class StringTokenizer {
67			public:
68	tim	1594
69	gezelter	2204	/**
70			* Constructs a string tokenizer for the specified string. The characters in the delim argument
71			* are the delimiters for separating tokens. characters are skipped and only serve as
72			* separators between tokens.
73			* @param str a string to be parsed.
74			* @param delim the delimiters, default value is " ;\t\n\r".
75			* @note this is still a little bit java like implementation. Pure c++ one should use TokenIterator.
76			* Boost's tokenizer class is one of them
77			*/
78			StringTokenizer(const std::string & str,
79			const std::string & delim = " ;\t\n\r");
80	tim	1594
81	gezelter	2204	/**
82			* Constructs a string tokenizer for an iterator range [first, last). The characters in the delim argument
83			* are the delimiters for separating tokens. characters are skipped and only serve as
84			* separators between tokens.
85			* @param first begin iterator
86			* @param last end iterator
87			* @param delim the delimiters, default value is " ;\t\n\r".
88			* @note this is still a little bit java like implementation. Pure c++ one should use TokenIterator.
89			* Boost's tokenizer class is one of them
90			*/
91			StringTokenizer(std::string::const_iterator& first, std::string::const_iterator& last,
92			const std::string & delim = " ;\t\n\r");
93	tim	1594
94	gezelter	2204	/**
95			* Constructs a string tokenizer for the specified string. The characters in the delim argument
96			* are the delimiters for separating tokens.
97			* If the returnTokens flag is true, then the delimiter characters are also returned as tokens.
98			* Each delimiter is returned as a string of length one. If the flag is false, the delimiter
99			* characters are skipped and only serve as separators between tokens.
100			* @param str a string to be parsed.
101			* @param delim the delimiters.
102			* @param returnTokens flag indicating whether to return the delimiters as tokens.
103			*/
104			StringTokenizer(const std::string&str, const std::string&delim,
105			bool returnTokens);
106	tim	1594
107	gezelter	2204	/**
108			* Calculates the number of times that this tokenizer's nextToken method can be called
109			* before it generates an exception.
110			* @return the number of tokens remaining in the string using the current delimiter set.
111			*/
112			int countTokens();
113	tim	1594
114	gezelter	2204	/**
115			* Tests if there are more tokens available from this tokenizer's string.
116			* @return true if there are more tokens available from this tokenizer's string, false otherwise
117			*/
118			bool hasMoreTokens();
119	tim	1594
120	gezelter	2204	/**
121			* Returns the next token from this string tokenizer.
122			* @return the next token from this string tokenizer.
123			* @exception NoSuchElementException if there are no more tokens in this tokenizer's string
124			*/
125			std::string nextToken();
126	tim	1594
127	gezelter	2204	//actually, nextToken Can be template function
128			//template <typename ReturnType>
129			//ReturnType nextToken();
130	gezelter	1930
131	gezelter	2204	/**
132			* Returns the next token from this string tokenizer as a bool.
133			* @return the next token from this string tokenizer as a bool.
134			*/
135			bool nextTokenAsBool();
136	tim	1594
137	gezelter	2204	/**
138			* Returns the next token from this string tokenizer as an integer.
139			* @return the next token from this string tokenizer as an integer.
140			*/
141			int nextTokenAsInt();
142	tim	1594
143	gezelter	2204	/**
144			* Returns the next token from this string tokenizer as a float.
145			* @return the next token from this string tokenizer as a float.
146			*/
147			float nextTokenAsFloat();
148	tim	1594
149	gezelter	2204	/**
150	tim	2759	* Returns the next token from this string tokenizer as a RealType.
151			* @return the next token from this string tokenizer as a RealType.
152	gezelter	2204	*/
153	tim	2759	RealType nextTokenAsDouble();
154	tim	1594
155	gezelter	2204	/**
156			* Returns the next token without advancing the position of the StringTokenizer.
157			* @return the next token
158			*/
159			std::string peekNextToken();
160	gezelter	1930
161	gezelter	2204	/**
162			* Returns the current delimiter set of this string tokenizer
163			* @return the current delimiter set
164			*/
165			const std::string& getDelimiters() {
166			return delim_;
167			}
168	gezelter	1930
169	gezelter	2204	/**
170			* Returns the original string before tokenizing.
171			* @return the original string before tokenizing
172			*/
173			const std::string& getOriginal() {
174			return tokenString_;
175			}
176	gezelter	1930
177	tim	2469	/**
178			* Returns all of the tokens
179			* @return all of the tokens
180			*/
181			std::vector<std::string> getAllTokens();
182	gezelter	2204	private:
183	gezelter	1930
184	gezelter	2204	/**
185			* Test if character is in current delimiter set.
186			* @param c character to be tested
187			* @return true if character is in current delimiter set, flase otherwise.
188			*/
189			bool isDelimiter(const char c);
190	gezelter	1930
191	gezelter	2204	/** convert a fortran number to a c/c++ number */
192			void convertFortranNumber(std::string& fortranNumber);
193	tim	1945
194
195	gezelter	2204	std::string tokenString_;
196	gezelter	1930
197	gezelter	2204	std::string delim_; /*< current delimiter set of this string tokenizer /
198	gezelter	1930
199	gezelter	2204	bool returnTokens_; /*< flag indicating whether to return the delimiters as tokens /
200	gezelter	1930
201	gezelter	2204	std::string::const_iterator currentPos_;
202			std::string::const_iterator end_;
203			};
204	gezelter	1930
205			} //namespace oopse
206
207			#endif //UTIL_STRINGTOKENIZER_HPP