File: tokenizer.cc

package info (click to toggle)
din 5.2.1-3
  • links: PTS, VCS
  • area: main
  • in suites: jessie-kfreebsd
  • size: 2,152 kB
  • ctags: 2,490
  • sloc: cpp: 9,369; sh: 6,563; ansic: 2,977; tcl: 1,770; makefile: 285
file content (133 lines) | stat: -rw-r--r-- 3,140 bytes parent folder | download | duplicates (3)
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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
/*
 * This file is part of din.
 *
 * din is copyright (c) 2006 - 2012 S Jagannathan <jag@dinisnoise.org>
 * For more information, please visit http://dinisnoise.org
 *
 * din is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 2 of the License, or
 * (at your option) any later version.
 *
 * din 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 General Public License
 * for more details.
 *
 * You should have received a copy of the GNU General Public License along
 * with din.  If not, see <http://www.gnu.org/licenses/>.
 *
*/
// string tokenizer
// based on initial code by Song Ho Ahn (song.ahn@gmail.com)

#include "tokenizer.h"
#include <cstdlib>

#include <iostream>
using namespace std;

tokenizer::tokenizer() {
  str ("");
  del (DEFAULT_DELIMITER);
}

tokenizer::tokenizer(const std::string& s, const std::string& d) {
  str (s);
  del (d);
}

tokenizer::tokenizer (const std::vector<std::string>& t) {
  vec (t);
}

void tokenizer::set (const std::string& s, const std::string& d) {
  str (s);
  del (d);
}

void tokenizer::str (const std::string& s) {
  buffer = s;
  blen = buffer.length ();
  init_cur ();
  tokens_available = 0;
}

void tokenizer::del (const std::string& d) {
  delimiter = d;
  dlen = delimiter.length ();
}

void tokenizer::vec (const std::vector<std::string>& t) {
  tokens = t;
  tokens_available = 1;
  tokid = 0;
}

void tokenizer::init_cur () {
  if (blen) cur = 0; else cur = -1;
}

tokenizer& tokenizer::operator>> (std::string& s) {
  if (tokens_available) {
    if (tokid < tokens.size()) s = tokens[tokid++]; else {
      s = "";
      cur = blen;
    }
  } else {
    token = "";
    if (blen < 1) {
      s = token;
    } else {
      skip_ws ();
      while ((cur < blen) && !isdelim (buffer[cur])) {
        token += buffer[cur];
        ++cur;
      }
      s = token;
    }
  }
  return *this;
}

tokenizer& tokenizer::operator>> (float& f) {
  string s; *this >> s;
  f = atof (s.c_str());
  return *this;
}

tokenizer& tokenizer::operator>> (int& i) {
  string s; *this >> s;
  i = atoi (s.c_str());
  return *this;
}

tokenizer& tokenizer::operator>> (char& c) {
  string s; *this >> s;
  if (s.length()) c = s[0];
  return *this;
}

void tokenizer::skip_ws () {
  while (cur < blen) if (!isdelim (buffer[cur])) break; else ++cur;
}

bool tokenizer::isdelim (char c) {
  for (int i = 0; i < dlen; ++i) {
    if (delimiter[i] == c) return true;
  }
  return false;
}

string tokenizer::cur2end () {
  if (tokens_available) {
    string result;
    static const char spc = ' ';
    for (int i = tokid, j = tokens.size(); i < j; ++i) result = result + tokens[i] + spc;
    return result;
  } else {
    if (cur > -1) {
      return buffer.substr (cur, blen - 1);
    } else return "";
  }
}