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>

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 double.
     * @return the next token from this string tokenizer as a double.
     */
    double 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_;
    }

  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:	2204
Committed:	Fri Apr 15 22:04:00 2005 UTC (20 years, 6 months ago) by gezelter
File size:	7702 byte(s)
Log Message:	xemacs has been drafted to perform our indentation services
#	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	1594
55	gezelter	1930	namespace oopse {
56	tim	1594
57	gezelter	2204	/**
58			* @class StringTokenizer.hpp "util/StringTokenizer.hpp"
59			* @brief The string tokenizer class allows an application to break a string into tokens
60			* The set of delimiters (the characters that separate tokens) may be specified either
61			* at creation time or on a per-token basis.
62			* An instance of StringTokenizer behaves in one of two ways, depending on whether it was
63			* created with the returnTokens flag having the value true or false.
64			*/
65			class StringTokenizer {
66			public:
67	tim	1594
68	gezelter	2204	/**
69			* Constructs a string tokenizer for the specified string. The characters in the delim argument
70			* are the delimiters for separating tokens. characters are skipped and only serve as
71			* separators between tokens.
72			* @param str a string to be parsed.
73			* @param delim the delimiters, default value is " ;\t\n\r".
74			* @note this is still a little bit java like implementation. Pure c++ one should use TokenIterator.
75			* Boost's tokenizer class is one of them
76			*/
77			StringTokenizer(const std::string & str,
78			const std::string & delim = " ;\t\n\r");
79	tim	1594
80	gezelter	2204	/**
81			* Constructs a string tokenizer for an iterator range [first, last). The characters in the delim argument
82			* are the delimiters for separating tokens. characters are skipped and only serve as
83			* separators between tokens.
84			* @param first begin iterator
85			* @param last end iterator
86			* @param delim the delimiters, default value is " ;\t\n\r".
87			* @note this is still a little bit java like implementation. Pure c++ one should use TokenIterator.
88			* Boost's tokenizer class is one of them
89			*/
90			StringTokenizer(std::string::const_iterator& first, std::string::const_iterator& last,
91			const std::string & delim = " ;\t\n\r");
92	tim	1594
93	gezelter	2204	/**
94			* Constructs a string tokenizer for the specified string. The characters in the delim argument
95			* are the delimiters for separating tokens.
96			* If the returnTokens flag is true, then the delimiter characters are also returned as tokens.
97			* Each delimiter is returned as a string of length one. If the flag is false, the delimiter
98			* characters are skipped and only serve as separators between tokens.
99			* @param str a string to be parsed.
100			* @param delim the delimiters.
101			* @param returnTokens flag indicating whether to return the delimiters as tokens.
102			*/
103			StringTokenizer(const std::string&str, const std::string&delim,
104			bool returnTokens);
105	tim	1594
106	gezelter	2204	/**
107			* Calculates the number of times that this tokenizer's nextToken method can be called
108			* before it generates an exception.
109			* @return the number of tokens remaining in the string using the current delimiter set.
110			*/
111			int countTokens();
112	tim	1594
113	gezelter	2204	/**
114			* Tests if there are more tokens available from this tokenizer's string.
115			* @return true if there are more tokens available from this tokenizer's string, false otherwise
116			*/
117			bool hasMoreTokens();
118	tim	1594
119	gezelter	2204	/**
120			* Returns the next token from this string tokenizer.
121			* @return the next token from this string tokenizer.
122			* @exception NoSuchElementException if there are no more tokens in this tokenizer's string
123			*/
124			std::string nextToken();
125	tim	1594
126	gezelter	2204	//actually, nextToken Can be template function
127			//template <typename ReturnType>
128			//ReturnType nextToken();
129	gezelter	1930
130	gezelter	2204	/**
131			* Returns the next token from this string tokenizer as a bool.
132			* @return the next token from this string tokenizer as a bool.
133			*/
134			bool nextTokenAsBool();
135	tim	1594
136	gezelter	2204	/**
137			* Returns the next token from this string tokenizer as an integer.
138			* @return the next token from this string tokenizer as an integer.
139			*/
140			int nextTokenAsInt();
141	tim	1594
142	gezelter	2204	/**
143			* Returns the next token from this string tokenizer as a float.
144			* @return the next token from this string tokenizer as a float.
145			*/
146			float nextTokenAsFloat();
147	tim	1594
148	gezelter	2204	/**
149			* Returns the next token from this string tokenizer as a double.
150			* @return the next token from this string tokenizer as a double.
151			*/
152			double nextTokenAsDouble();
153	tim	1594
154	gezelter	2204	/**
155			* Returns the next token without advancing the position of the StringTokenizer.
156			* @return the next token
157			*/
158			std::string peekNextToken();
159	gezelter	1930
160	gezelter	2204	/**
161			* Returns the current delimiter set of this string tokenizer
162			* @return the current delimiter set
163			*/
164			const std::string& getDelimiters() {
165			return delim_;
166			}
167	gezelter	1930
168	gezelter	2204	/**
169			* Returns the original string before tokenizing.
170			* @return the original string before tokenizing
171			*/
172			const std::string& getOriginal() {
173			return tokenString_;
174			}
175	gezelter	1930
176	gezelter	2204	private:
177	gezelter	1930
178	gezelter	2204	/**
179			* Test if character is in current delimiter set.
180			* @param c character to be tested
181			* @return true if character is in current delimiter set, flase otherwise.
182			*/
183			bool isDelimiter(const char c);
184	gezelter	1930
185	gezelter	2204	/** convert a fortran number to a c/c++ number */
186			void convertFortranNumber(std::string& fortranNumber);
187	tim	1945
188
189	gezelter	2204	std::string tokenString_;
190	gezelter	1930
191	gezelter	2204	std::string delim_; /*< current delimiter set of this string tokenizer /
192	gezelter	1930
193	gezelter	2204	bool returnTokens_; /*< flag indicating whether to return the delimiters as tokens /
194	gezelter	1930
195	gezelter	2204	std::string::const_iterator currentPos_;
196			std::string::const_iterator end_;
197			};
198	gezelter	1930
199			} //namespace oopse
200
201			#endif //UTIL_STRINGTOKENIZER_HPP