summaryrefslogtreecommitdiffstats
path: root/tdecore/kregexp.h
blob: 0bb2b04caafdcd045d96dd6527e77394bd64c9d6 (plain)
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
/* This file is part of the KDE libraries
   Copyright (c) 1999 Torben Weis <weis@kde.org>

   This library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Library General Public
   License version 2 as published by the Free Software Foundation.

   This library 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
   Library General Public License for more details.

   You should have received a copy of the GNU Library General Public License
   along with this library; see the file COPYING.LIB.  If not, write to
   the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
   Boston, MA 02110-1301, USA.
*/
#ifndef __kregexp_h__
#define __kregexp_h__

#include "tdelibs_export.h"

class KRegExpPrivate;

/**
 * @deprecated
 * Please use TQRegExp instead.
 *
 * Regular expression (regexp) matching with back-references.
 *
 * This was implemented
 * because TQRegExp did not support back-references. It now does and
 * is recommended over KRegExp because of the unicode support and the
 * more powerful API.
 *
 * Back-references are parts of a regexp grouped with parentheses. If a
 * string matches the regexp, you can access the text that matched each
 * group with the group method. This is similar to regular expressions 
 * in Perl.
 *
 * Example:
 * \code
 *  KRegExp ex( "([A-Za-z]+) (.+)" );
 *  ex.match( "42 Torben Weis" );
 *  kdDebug() << ex.group(0) << endl;
 *  kdDebug() << ex.group(1) << endl;
 *  kdDebug() << ex.group(2) << endl;
 * \endcode
 * Output:
 * \code
 *  Torben Weis
 *  Torben
 *  Weis
 * \endcode
 *
 * Please notice that KRegExp does @em not support unicode.
 *
 * @author Torben Weis <weis@kde.org>
 */
class TDECORE_EXPORT TDE_DEPRECATED KRegExp
{
public:

  /**
   * Creates a KRegExp object without a default pattern.
   */
  KRegExp();

  /**
   * Creates a KRegExp object.
   * @param _pattern	The regular expression to use for matches.
   * @param _mode	If this is "i", case-insensitive matches will be
   * 			performed.
   */
  KRegExp( const char *_pattern, const char *_mode = "" );
  ~KRegExp();

  /**
   * Prepare a regular expression for subsequent matches.
   * @param _pattern	The regular expression to use for matches.
   * @param _mode	If this is "i", case-insensitive matches will be
   * 			performed.
   * @return bool if successful.
   */
  bool compile( const char *_pattern, const char *_mode = "" );

  /**
   * Match a string to the last supplied regexp.
   * @param _string the string to match
   * @return @p true on match, false otherwise.
   */
  bool match( const char *_string );


  /**
   * Returns a group from the match.
   *
   * @param _grp May be in the range [0..9]. If @p _grp is 0 then the complete
   *             matched string is returned.
   * @return a grouped substring. A substring may be empty.
   *         In this case 0 is returned. Otherwise you may @em not
   *         delete or modify the returned value. In addition the
   *         returned value becomes invalid after the KRegExp instance
   *         is deleted or after match() was called again.
   */
  const char *group( int _grp );

  /**
   * The offset of the given group in the string.
   * @param _grp May be in the range [0..9]. If @p _grp is 0 then the start offset
   *             of the complete matched string is returned.
   * @return The start offset of the grouped substring.
   */
  int groupStart( int _grp );
  /**
   * The offset of the given group's end in the string.
   * @param _grp May be in the range [0..9]. If @p _grp is 0 then the end offset
   *             of the complete matched string is returned.
   * @return The end offset of the grouped substring. The "end offset" is the first
   *         character after the string.
   */
  int groupEnd( int _grp );

private:
  KRegExpPrivate *m_pPrivate;
};


#endif