src/utils/StringTokenizer.cpp

/*
 * Copyright (C) 2000-2004  Object Oriented Parallel Simulation Engine (OOPSE) project
 * 
 * Contact: oopse@oopse.org
 * 
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public License
 * as published by the Free Software Foundation; either version 2.1
 * of the License, or (at your option) any later version.
 * All we ask is that proper credit is given for our work, which includes
 * - but is not limited to - adding the above copyright notice to the beginning
 * of your source code files, and to any copyright notice that you may distribute
 * with programs based on this work.
 * 
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Lesser General Public License for more details.
 * 
 * You should have received a copy of the GNU Lesser General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
 *
 */

#include <iostream>
#include <sstream>
#include "utils/StringTokenizer.hpp"

namespace oopse {


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;
            }
        }

        //encount a token here
        while ( tmpIter != end_ && !isDelimiter(*tmpIter) ) {
            ++tmpIter;
        }

         if (tmpIter != end_) {
            ++numToken;
        } else {
            break;
        }

    }

    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;
    }
}

int StringTokenizer::nextTokenAsInt() {
    std::string token = nextToken();
    std::istringstream iss(token);
    int result;
    
    if (iss >> result) {
        return result;
    } else {
        std::cerr << "unable to convert " << token << "to an integer" << std::endl;
        return 0;
    }
}

float StringTokenizer::nextTokenAsFloat() {
    std::string token = nextToken();
    std::istringstream iss(token);
    float result;
    
    if (iss >> result) {
        return result;
    } else {
        std::cerr << "unable to convert " << token << "to a float" << std::endl;
        return 0.0;
    }
}

double StringTokenizer::nextTokenAsDouble() {
    std::string token = nextToken();
    std::istringstream iss(token);
    double result;
    
    if (iss >> result) {
        return result;
    } else {
        std::cerr << "unable to convert " << token << "to a double" << std::endl;
        return 0.0;
    }
}

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;    
}

}//end namespace oopse

Revision:	1780
Committed:	Wed Nov 24 19:49:07 2004 UTC (19 years, 9 months ago) by tim
File size:	5901 byte(s)
Log Message:	StringTokenizer passes unit test
#	User	Rev	Content
1	tim	1736	/*
2			* Copyright (C) 2000-2004 Object Oriented Parallel Simulation Engine (OOPSE) project
3			*
4			* Contact: oopse@oopse.org
5			*
6			* This program is free software; you can redistribute it and/or
7			* modify it under the terms of the GNU Lesser General Public License
8			* as published by the Free Software Foundation; either version 2.1
9			* of the License, or (at your option) any later version.
10			* All we ask is that proper credit is given for our work, which includes
11			* - but is not limited to - adding the above copyright notice to the beginning
12			* of your source code files, and to any copyright notice that you may distribute
13			* with programs based on this work.
14			*
15			* This program is distributed in the hope that it will be useful,
16			* but WITHOUT ANY WARRANTY; without even the implied warranty of
17			* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18			* GNU Lesser General Public License for more details.
19			*
20			* You should have received a copy of the GNU Lesser General Public License
21			* along with this program; if not, write to the Free Software
22			* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
23			*
24			*/
25
26	tim	1780	#include <iostream>
27			#include <sstream>
28	tim	1736	#include "utils/StringTokenizer.hpp"
29
30			namespace oopse {
31
32
33			StringTokenizer::StringTokenizer(const std::string & str, const std::string & delim)
34			: tokenString_(str), delim_(delim), returnTokens_(false),
35			currentPos_(tokenString_.begin()), end_(tokenString_.end()){
36
37			}
38
39			StringTokenizer::StringTokenizer(std::string::const_iterator& first, std::string::const_iterator& last,
40			const std::string & delim)
41	tim	1780	: tokenString_(first, last) , delim_(delim), returnTokens_(false),
42	tim	1736	currentPos_(tokenString_.begin()), end_(tokenString_.end()) {
43
44			}
45
46			StringTokenizer::StringTokenizer(const std::string&str, const std::string&delim,
47			bool returnTokens)
48			: tokenString_(str), delim_(delim), returnTokens_(returnTokens),
49			currentPos_(tokenString_.begin()), end_(tokenString_.end()) {
50
51			}
52
53	tim	1780	bool StringTokenizer::isDelimiter(const char c) {
54			return delim_.find(c) == std::string::npos ? false : true;
55			}
56
57	tim	1736	int StringTokenizer::countTokens() {
58
59	tim	1780	std::string::const_iterator tmpIter = currentPos_;
60	tim	1736	int numToken = 0;
61
62			while (true) {
63
64			//skip delimiter first
65			while( tmpIter != end_ && isDelimiter(*tmpIter)) {
66			++tmpIter;
67
68			if (returnTokens_) {
69			//if delimiter is consider as token
70			++numToken;
71			}
72			}
73
74			//encount a token here
75			while ( tmpIter != end_ && !isDelimiter(*tmpIter) ) {
76			++tmpIter;
77			}
78
79			if (tmpIter != end_) {
80			++numToken;
81			} else {
82			break;
83			}
84
85			}
86
87			return numToken;
88			}
89
90			bool StringTokenizer::hasMoreTokens() {
91	tim	1737
92			if (currentPos_ == end_) {
93			return false;
94			} else if (returnTokens_) {
95			return true;
96			} else {
97	tim	1780	std::string::const_iterator i = currentPos_;
98	tim	1736
99	tim	1737	//walk through the remaining string to check whether it contains non-delimeter or not
100			while(i != end_ && isDelimiter(*i)) {
101			++i;
102			}
103
104			return i != end_ ? true : false;
105			}
106	tim	1736	}
107
108			std::string StringTokenizer::nextToken() {
109	tim	1741	std::string result;
110	tim	1736
111			if(currentPos_ != end_) {
112	tim	1780	std::insert_iterator<std::string> insertIter(result, result.begin());
113	tim	1736
114			while( currentPos_ != end_ && isDelimiter(*currentPos_)) {
115
116			if (returnTokens_) {
117			insertIter++ = currentPos_++;
118			return result;
119			}
120
121			++currentPos_;
122			}
123
124			while (currentPos_ != end_ && !isDelimiter(*currentPos_)) {
125			insertIter++ = currentPos_++;
126			}
127
128			}
129
130			return result;
131			}
132
133	tim	1758	bool StringTokenizer::nextTokenAsBool() {
134			std::string token = nextToken();
135			std::istringstream iss(token);
136			bool result;
137
138			if (iss >> result) {
139			return result;
140			} else {
141	tim	1780	std::cerr << "unable to convert " << token << "to a bool" << std::endl;
142	tim	1758	return false;
143			}
144			}
145
146	tim	1736	int StringTokenizer::nextTokenAsInt() {
147	tim	1741	std::string token = nextToken();
148			std::istringstream iss(token);
149			int result;
150
151			if (iss >> result) {
152			return result;
153			} else {
154	tim	1780	std::cerr << "unable to convert " << token << "to an integer" << std::endl;
155	tim	1741	return 0;
156			}
157	tim	1736	}
158
159			float StringTokenizer::nextTokenAsFloat() {
160	tim	1741	std::string token = nextToken();
161			std::istringstream iss(token);
162			float result;
163
164			if (iss >> result) {
165			return result;
166			} else {
167	tim	1780	std::cerr << "unable to convert " << token << "to a float" << std::endl;
168	tim	1741	return 0.0;
169			}
170	tim	1736	}
171
172	tim	1741	double StringTokenizer::nextTokenAsDouble() {
173			std::string token = nextToken();
174			std::istringstream iss(token);
175			double result;
176
177			if (iss >> result) {
178			return result;
179			} else {
180	tim	1780	std::cerr << "unable to convert " << token << "to a double" << std::endl;
181	tim	1741	return 0.0;
182			}
183			}
184
185	tim	1736	std::string StringTokenizer::peekNextToken() {
186	tim	1780	std::string result;
187	tim	1736	std::string::const_iterator tmpIter = currentPos_;
188
189			if(tmpIter != end_) {
190	tim	1780	std::insert_iterator<std::string> insertIter(result, result.begin());
191	tim	1736
192			while(tmpIter != end_ && isDelimiter(*tmpIter)) {
193
194			if (returnTokens_) {
195			insertIter++ = tmpIter++;
196			return result;
197			}
198
199			++tmpIter;
200			}
201
202			while (tmpIter != end_ && !isDelimiter(*tmpIter)) {
203			insertIter++ = tmpIter++;
204			}
205			}
206
207			return result;
208			}
209
210	tim	1780	}//end namespace oopse
211	tim	1736