File: tokenizer.h

package info (click to toggle)
votca-tools 1.2.4-1
  • links: PTS, VCS
  • area: main
  • in suites: jessie, jessie-kfreebsd
  • size: 13,352 kB
  • ctags: 64,112
  • sloc: cpp: 176,559; ansic: 42; sh: 11; makefile: 7
file content (113 lines) | stat: -rw-r--r-- 3,254 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
/* 
 * Copyright 2009-2011 The VOTCA Development Team (http://www.votca.org)
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 *
 */

#ifndef _tools_H
#define	_tools_H

#include <string>
#include <vector>
#include <boost/tokenizer.hpp>
#include <boost/lexical_cast.hpp>

namespace votca { namespace tools {


/**
 * \brief break string into words
 *
 * This class wraps boost::tokenizer to break a string into words. A list of
 * delimeters can be freely choosen.
 */
class Tokenizer 
{                        
public:
    typedef boost::tokenizer<boost::char_separator<char> >::iterator
        iterator;
    
    /**
     * \brief startup tokenization
     * @param str string to break up
     * @param separators list of separators
     *
     * After initialization,the words can be accessed using the iterator
     * interface or directly transferred to a vector ToVector of ConvertToVector.
     */
    Tokenizer(const std::string &str, const char *separators) {
        _str = str;
        boost::char_separator<char> sep(separators);
        tok = new boost::tokenizer<boost::char_separator<char> >(_str, sep);
        //boost::escaped_list_separator<char> sep(" ", separators, "\"");
        //tok = new boost::tokenizer<boost::escaped_list_separator<char> >(str, sep);
        
    }
    
    ~Tokenizer() {
        delete tok;
    }
    
    /**
     * \brief iterator to first element
     * @return begin iterator
     */
    iterator begin() { return tok->begin(); }
    /**
     * \brief end iterator
     * @return end iterator
     */
    iterator end() { return tok->end(); }
    
    /**
     * \brief store all words in a vector of strings.
     * @param v storage vector
     *
     * This class appends all words to a vector of strings.
     */
    void ToVector(std::vector<std::string> &v) {
        for(iterator iter=begin(); iter!=end(); ++iter)
            v.push_back(*iter);
    }

    /**
     * \brief store all words in a vector with type conversion.
     * @param v storage vector
     *
     * This class appends all words to a vector of arbitrary type (e.g. double)
     * and also does type conversion.
     */
    template < typename T >
    void ConvertToVector(std::vector<T> &v){
        std::vector<std::string> tmp;
        ToVector(tmp);
        v.resize(tmp.size());
        typename std::vector<T>::iterator viter = v.begin();
        typename std::vector<std::string>::iterator iter;
        for(iter = tmp.begin(); iter!=tmp.end(); ++iter, ++viter)
            *viter = boost::lexical_cast<T, std::string>(*iter);
    }
    
private:
    boost::tokenizer< boost::char_separator<char> > *tok;
    std::string _str;
};


int wildcmp(const char *wild, const char *string);

}}

#endif	/* _tools_H */