src/utils/StringTokenizer.cpp

/*
 * 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]  Vardeman & Gezelter, in progress (2009).                        
 */
 
#include <iostream>
#include <iterator>
#include <sstream>
#include "utils/StringTokenizer.hpp"

namespace OpenMD {


  StringTokenizer::StringTokenizer(const std::string & str, const std::string & delim) 
    : tokenString_(str), delim_(delim), returnTokens_(false),
      currentPos_(tokenString_.begin()), end_(tokenString_.end()){

    }

  StringTokenizer::StringTokenizer(std::string::const_iterator& first, std::string::const_iterator& last,
                                   const std::string & delim)  
    : tokenString_(first, last) , delim_(delim), returnTokens_(false),
      currentPos_(tokenString_.begin()), end_(tokenString_.end()) {

    }

  StringTokenizer::StringTokenizer(const std::string&str, const std::string&delim,
                                   bool returnTokens)
    : tokenString_(str), delim_(delim), returnTokens_(returnTokens),
      currentPos_(tokenString_.begin()), end_(tokenString_.end()) {

    }

  bool StringTokenizer::isDelimiter(const char c) {
    return delim_.find(c) == std::string::npos ? false : true;
  }

  int StringTokenizer::countTokens() {
    
    std::string::const_iterator tmpIter = currentPos_;    
    int numToken = 0;

    while (true) {

      //skip delimiter first
      while( tmpIter != end_ && isDelimiter(*tmpIter)) {
        ++tmpIter;

        if (returnTokens_) {
          //if delimiter is consider as token
          ++numToken;
        }
      }
        
      if (tmpIter == end_) {
        break;
      }
        
      //encount a token here
      while ( tmpIter != end_ && !isDelimiter(*tmpIter) ) {
        ++tmpIter;
      }

      ++numToken;

    }

    return numToken;
  }

  bool StringTokenizer::hasMoreTokens() {
    
    if (currentPos_ == end_) {
      return false;
    } else if (returnTokens_) {
      return true;
    } else {
      std::string::const_iterator i = currentPos_;

      //walk through the remaining string to check whether it contains non-delimeter or not
      while(i != end_ && isDelimiter(*i)) {
        ++i;
      }

      return i != end_ ? true : false;
    }
  }

  std::string StringTokenizer::nextToken() {
    std::string result;
    
    if(currentPos_ != end_) {
      std::insert_iterator<std::string> insertIter(result, result.begin());

      while( currentPos_ != end_ && isDelimiter(*currentPos_)) {

        if (returnTokens_) {
          *insertIter++ = *currentPos_++;
          return result;
        }
            
        ++currentPos_;
      }

      while (currentPos_ != end_ && !isDelimiter(*currentPos_)) {
        *insertIter++ = *currentPos_++;
      }
        
    }
    
    return result;
  }

  bool StringTokenizer::nextTokenAsBool() {
    std::string token = nextToken();
    std::istringstream iss(token);
    bool result;
    
    if (iss >> result) {
      return result;
    } else {
      std::cerr << "unable to convert " << token << " to a bool" << std::endl;
      return false;
    }
  }
 
  //Since libstdc++(GCC 3.2) has an i/ostream::operator>>/<<(streambuf*) bug (Bug 9318)
  //Instead of using iostream facility, we use C library
  int StringTokenizer::nextTokenAsInt() {
    std::string token = nextToken();
   
    return atoi(token.c_str());
  }

  float StringTokenizer::nextTokenAsFloat() {
    std::string token = nextToken();
    convertFortranNumber(token);
    return (float) (atof(token.c_str()));
  }

  RealType StringTokenizer::nextTokenAsDouble() {
    std::string token = nextToken();
    convertFortranNumber(token);
    return atof(token.c_str());
  }

  std::string  StringTokenizer::peekNextToken() {
    std::string result;
    std::string::const_iterator tmpIter = currentPos_;
    
    if(tmpIter != end_) {
      std::insert_iterator<std::string> insertIter(result, result.begin());

      while(tmpIter != end_ && isDelimiter(*tmpIter)) {

        if (returnTokens_) {
          *insertIter++ = *tmpIter++;
          return result;
        }
            
        ++tmpIter;
      }

      while (tmpIter != end_ && !isDelimiter(*tmpIter)) {
        *insertIter++ = *tmpIter++;
      }
    }
    
    return result;    
  }

 std::vector<std::string>  StringTokenizer::getAllTokens() {
    std::vector<std::string> tokens;
    while (hasMoreTokens()) {
        tokens.push_back(nextToken());
    }
    return tokens;
 }
  void StringTokenizer::convertFortranNumber(std::string& fortranNumber) {
    std::string::iterator i;
    for(i = fortranNumber.begin(); i != fortranNumber.end(); ++i) {
      if (*i == 'd' || *i == 'D') {
        *i = 'E';
      }
    }
  }

}//end namespace OpenMD

Revision:	1390
Committed:	Wed Nov 25 20:02:06 2009 UTC (15 years, 5 months ago) by gezelter
File size:	6496 byte(s)
Log Message:	Almost all of the changes necessary to create OpenMD out of our old project (OOPSE-4)
#	User	Rev	Content
1	gezelter	507	/*
2	gezelter	246	* 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	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			* [3] Sun, Lin & Gezelter, J. Chem. Phys. 128, 24107 (2008).
39			* [4] Vardeman & Gezelter, in progress (2009).
40	gezelter	246	*/
41
42			#include <iostream>
43			#include <iterator>
44			#include <sstream>
45			#include "utils/StringTokenizer.hpp"
46
47	gezelter	1390	namespace OpenMD {
48	gezelter	246
49
50	gezelter	507	StringTokenizer::StringTokenizer(const std::string & str, const std::string & delim)
51			: tokenString_(str), delim_(delim), returnTokens_(false),
52			currentPos_(tokenString_.begin()), end_(tokenString_.end()){
53	gezelter	246
54	gezelter	507	}
55	gezelter	246
56	gezelter	507	StringTokenizer::StringTokenizer(std::string::const_iterator& first, std::string::const_iterator& last,
57			const std::string & delim)
58			: tokenString_(first, last) , delim_(delim), returnTokens_(false),
59			currentPos_(tokenString_.begin()), end_(tokenString_.end()) {
60	gezelter	246
61	gezelter	507	}
62	gezelter	246
63	gezelter	507	StringTokenizer::StringTokenizer(const std::string&str, const std::string&delim,
64			bool returnTokens)
65			: tokenString_(str), delim_(delim), returnTokens_(returnTokens),
66			currentPos_(tokenString_.begin()), end_(tokenString_.end()) {
67	gezelter	246
68	gezelter	507	}
69	gezelter	246
70	gezelter	507	bool StringTokenizer::isDelimiter(const char c) {
71	gezelter	246	return delim_.find(c) == std::string::npos ? false : true;
72	gezelter	507	}
73	gezelter	246
74	gezelter	507	int StringTokenizer::countTokens() {
75	gezelter	246
76			std::string::const_iterator tmpIter = currentPos_;
77			int numToken = 0;
78
79			while (true) {
80
81	gezelter	507	//skip delimiter first
82			while( tmpIter != end_ && isDelimiter(*tmpIter)) {
83			++tmpIter;
84	gezelter	246
85	gezelter	507	if (returnTokens_) {
86			//if delimiter is consider as token
87			++numToken;
88			}
89			}
90	gezelter	246
91	gezelter	507	if (tmpIter == end_) {
92			break;
93			}
94	gezelter	246
95	gezelter	507	//encount a token here
96			while ( tmpIter != end_ && !isDelimiter(*tmpIter) ) {
97			++tmpIter;
98			}
99	gezelter	246
100	gezelter	507	++numToken;
101	gezelter	246
102			}
103
104			return numToken;
105	gezelter	507	}
106	gezelter	246
107	gezelter	507	bool StringTokenizer::hasMoreTokens() {
108	gezelter	246
109			if (currentPos_ == end_) {
110	gezelter	507	return false;
111	gezelter	246	} else if (returnTokens_) {
112	gezelter	507	return true;
113	gezelter	246	} else {
114	gezelter	507	std::string::const_iterator i = currentPos_;
115	gezelter	246
116	gezelter	507	//walk through the remaining string to check whether it contains non-delimeter or not
117			while(i != end_ && isDelimiter(*i)) {
118			++i;
119			}
120	gezelter	246
121	gezelter	507	return i != end_ ? true : false;
122	gezelter	246	}
123	gezelter	507	}
124	gezelter	246
125	gezelter	507	std::string StringTokenizer::nextToken() {
126	gezelter	246	std::string result;
127
128			if(currentPos_ != end_) {
129	gezelter	507	std::insert_iterator<std::string> insertIter(result, result.begin());
130	gezelter	246
131	gezelter	507	while( currentPos_ != end_ && isDelimiter(*currentPos_)) {
132	gezelter	246
133	gezelter	507	if (returnTokens_) {
134			insertIter++ = currentPos_++;
135			return result;
136			}
137	gezelter	246
138	gezelter	507	++currentPos_;
139			}
140	gezelter	246
141	gezelter	507	while (currentPos_ != end_ && !isDelimiter(*currentPos_)) {
142			insertIter++ = currentPos_++;
143			}
144	gezelter	246
145			}
146
147			return result;
148	gezelter	507	}
149	gezelter	246
150	gezelter	507	bool StringTokenizer::nextTokenAsBool() {
151	gezelter	246	std::string token = nextToken();
152			std::istringstream iss(token);
153			bool result;
154
155			if (iss >> result) {
156	gezelter	507	return result;
157	gezelter	246	} else {
158	gezelter	507	std::cerr << "unable to convert " << token << " to a bool" << std::endl;
159			return false;
160	gezelter	246	}
161	gezelter	507	}
162	tim	261
163	gezelter	507	//Since libstdc++(GCC 3.2) has an i/ostream::operator>>/<<(streambuf*) bug (Bug 9318)
164			//Instead of using iostream facility, we use C library
165			int StringTokenizer::nextTokenAsInt() {
166	gezelter	246	std::string token = nextToken();
167	tim	261
168			return atoi(token.c_str());
169	gezelter	507	}
170	gezelter	246
171	gezelter	507	float StringTokenizer::nextTokenAsFloat() {
172	gezelter	246	std::string token = nextToken();
173	tim	261	convertFortranNumber(token);
174			return (float) (atof(token.c_str()));
175	gezelter	507	}
176	gezelter	246
177	tim	963	RealType StringTokenizer::nextTokenAsDouble() {
178	gezelter	246	std::string token = nextToken();
179	tim	261	convertFortranNumber(token);
180			return atof(token.c_str());
181	gezelter	507	}
182	gezelter	246
183	gezelter	507	std::string StringTokenizer::peekNextToken() {
184	gezelter	246	std::string result;
185			std::string::const_iterator tmpIter = currentPos_;
186
187			if(tmpIter != end_) {
188	gezelter	507	std::insert_iterator<std::string> insertIter(result, result.begin());
189	gezelter	246
190	gezelter	507	while(tmpIter != end_ && isDelimiter(*tmpIter)) {
191	gezelter	246
192	gezelter	507	if (returnTokens_) {
193			insertIter++ = tmpIter++;
194			return result;
195			}
196	gezelter	246
197	gezelter	507	++tmpIter;
198			}
199	gezelter	246
200	gezelter	507	while (tmpIter != end_ && !isDelimiter(*tmpIter)) {
201			insertIter++ = tmpIter++;
202			}
203	gezelter	246	}
204
205			return result;
206	gezelter	507	}
207	gezelter	246
208	tim	770	std::vector<std::string> StringTokenizer::getAllTokens() {
209			std::vector<std::string> tokens;
210			while (hasMoreTokens()) {
211			tokens.push_back(nextToken());
212			}
213			return tokens;
214			}
215	gezelter	507	void StringTokenizer::convertFortranNumber(std::string& fortranNumber) {
216	tim	261	std::string::iterator i;
217			for(i = fortranNumber.begin(); i != fortranNumber.end(); ++i) {
218	gezelter	507	if (i == 'd' \|\| i == 'D') {
219			*i = 'E';
220			}
221	tim	261	}
222	gezelter	507	}
223	tim	261
224	gezelter	1390	}//end namespace OpenMD
225	gezelter	246