docs/latex/wx/regex.tex

   1 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
   2 %% Name:        regex.tex
   3 %% Purpose:     wxRegEx documentation
   4 %% Author:      Vadim Zeitlin
   5 %% Modified by:
   6 %% Created:     14.07.01
   7 %% RCS-ID:      $Id$
   8 %% Copyright:   (c) 2001 Vadim Zeitlin
   9 %% License:     wxWidgets license
  10 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  11
  12 \section{\class{wxRegEx}}\label{wxregex}
  13
  14 wxRegEx represents a regular expression.  This class provides support
  15 for regular expressions matching and also replacement.
  16
  17 It is built on top of either the system library (if it has support
  18 for POSIX regular expressions - which is the case of the most modern
  19 Unices) or uses the built in Henry Spencer's library.  Henry Spencer
  20 would appreciate being given credit in the documentation of software
  21 which uses his library, but that is not a requirement.
  22
  23 Regular expressions, as defined by POSIX, come in two flavours: {\it extended}
  24 and {\it basic}.  The builtin library also adds a third flavour
  25 of expression \helpref{advanced}{wxresyn}, which is not available
  26 when using the system library.
  27
  28 Unicode is fully supported only when using the builtin library.
  29 When using the system library in Unicode mode, the expressions and data
  30 are translated to the default 8-bit encoding before being passed to
  31 the library.
  32
  33 On platforms where a system library is available, the default is to use
  34 the builtin library for Unicode builds, and the system library otherwise.
  35 It is possible to use the other if preferred by selecting it when building
  36 the wxWidgets.
  37
  38 \wxheading{Derived from}
  39
  40 No base class
  41
  42 \wxheading{Data structures}
  43
  44 Flags for regex compilation to be used with \helpref{Compile()}{wxregexcompile}:
  45
  46 \begin{verbatim}
  47 enum
  48 {
  49     // use extended regex syntax
  50     wxRE_EXTENDED = 0,
  51
  52     // use advanced RE syntax (built-in regex only)
  53 #ifdef wxHAS_REGEX_ADVANCED
  54     wxRE_ADVANCED = 1,
  55 #endif
  56
  57     // use basic RE syntax
  58     wxRE_BASIC    = 2,
  59
  60     // ignore case in match
  61     wxRE_ICASE    = 4,
  62
  63     // only check match, don't set back references
  64     wxRE_NOSUB    = 8,
  65
  66     // if not set, treat '\n' as an ordinary character, otherwise it is
  67     // special: it is not matched by '.' and '^' and '$' always match
  68     // after/before it regardless of the setting of wxRE_NOT[BE]OL
  69     wxRE_NEWLINE  = 16,
  70
  71     // default flags
  72     wxRE_DEFAULT  = wxRE_EXTENDED
  73 }
  74 \end{verbatim}
  75
  76 Flags for regex matching to be used with \helpref{Matches()}{wxregexmatches}.
  77
  78 These flags are mainly useful when doing several matches in a long string
  79 to prevent erroneous matches for {\tt '\textasciicircum'} and {\tt '\$'}:
  80
  81 \begin{verbatim}
  82 enum
  83 {
  84     // '^' doesn't match at the start of line
  85     wxRE_NOTBOL = 32,
  86
  87     // '$' doesn't match at the end of line
  88     wxRE_NOTEOL = 64
  89 }
  90 \end{verbatim}
  91
  92 \wxheading{Examples}
  93
  94 A bad example of processing some text containing email addresses (the example
  95 is bad because the real email addresses can have more complicated form than
  96 {\tt user@host.net}):
  97
  98 \begin{verbatim}
  99 wxString text;
 100 ...
 101 wxRegEx reEmail = wxT("([^@]+)@([[:alnum:].-_].)+([[:alnum:]]+)");
 102 if ( reEmail.Matches(text) )
 103 {
 104     wxString text = reEmail.GetMatch(email);
 105     wxString username = reEmail.GetMatch(email, 1);
 106     if ( reEmail.GetMatch(email, 3) == wxT("com") ) // .com TLD?
 107     {
 108         ...
 109     }
 110 }
 111
 112 // or we could do this to hide the email address
 113 size_t count = reEmail.ReplaceAll(text, wxT("HIDDEN@\\2\\3"));
 114 printf("text now contains %u hidden addresses", count);
 115 \end{verbatim}
 116
 117 \latexignore{\rtfignore{\wxheading{Members}}}
 118
 119 \membersection{wxRegEx::wxRegEx}\label{wxregexwxregex}
 120
 121 \func{}{wxRegEx}{\void}
 122
 123 Default ctor: use \helpref{Compile()}{wxregexcompile} later.
 124
 125 \func{}{wxRegEx}{\param{const wxString\& }{expr}, \param{int }{flags = wxRE\_DEFAULT}}
 126
 127 Create and compile the regular expression, use
 128 \helpref{IsValid}{wxregexisvalid} to test for compilation errors.
 129
 130 \membersection{wxRegEx::\destruct{wxRegEx}}\label{wxregexdtor}
 131
 132 \func{}{\destruct{wxRegEx}}{\void}
 133
 134 dtor not virtual, don't derive from this class
 135
 136 \membersection{wxRegEx::Compile}\label{wxregexcompile}
 137
 138 \func{bool}{Compile}{\param{const wxString\& }{pattern}, \param{int }{flags = wxRE\_DEFAULT}}
 139
 140 Compile the string into regular expression, return {\tt true} if ok or {\tt false}
 141 if string has a syntax error.
 142
 143 \membersection{wxRegEx::IsValid}\label{wxregexisvalid}
 144
 145 \constfunc{bool}{IsValid}{\void}
 146
 147 Return {\tt true} if this is a valid compiled regular expression, {\tt false}
 148 otherwise.
 149
 150 \membersection{wxRegEx::GetMatch}\label{wxregexgetmatch}
 151
 152 \constfunc{bool}{GetMatch}{\param{size\_t* }{start}, \param{size\_t* }{len}, \param{size\_t }{index = 0}}
 153
 154 Get the start index and the length of the match of the expression
 155 (if {\it index} is $0$) or a bracketed subexpression ({\it index} different
 156 from $0$).
 157
 158 May only be called after successful call to \helpref{Matches()}{wxregexmatches}
 159 and only if {\tt wxRE\_NOSUB} was {\bf not} used in
 160 \helpref{Compile()}{wxregexcompile}.
 161
 162 Returns {\tt false} if no match or if an error occured.
 163
 164 \constfunc{wxString}{GetMatch}{\param{const wxString\& }{text}, \param{size\_t }{index = 0}}
 165
 166 Returns the part of string corresponding to the match where {\it index} is
 167 interpreted as above. Empty string is returned if match failed
 168
 169 May only be called after successful call to \helpref{Matches()}{wxregexmatches}
 170 and only if {\tt wxRE\_NOSUB} was {\bf not} used in
 171 \helpref{Compile()}{wxregexcompile}.
 172
 173 \membersection{wxRegEx::GetMatchCount}\label{wxregexgetmatchcount}
 174
 175 \constfunc{size\_t}{GetMatchCount}{\void}
 176
 177 Returns the size of the array of matches, i.e. the number of bracketed
 178 subexpressions plus one for the expression itself, or $0$ on error.
 179
 180 May only be called after successful call to \helpref{Compile()}{wxregexcompile}.
 181 and only if {\tt wxRE\_NOSUB} was {\bf not} used.
 182
 183 \membersection{wxRegEx::Matches}\label{wxregexmatches}
 184
 185 \constfunc{bool}{Matches}{\param{const wxChar* }{text}, \param{int }{flags = 0}}
 186
 187 Matches the precompiled regular expression against the string {\it text},
 188 returns {\tt true} if matches and {\tt false} otherwise.
 189
 190 Flags may be combination of {\tt wxRE\_NOTBOL} and {\tt wxRE\_NOTEOL}.
 191
 192 May only be called after successful call to \helpref{Compile()}{wxregexcompile}.
 193
 194 \membersection{wxRegEx::Replace}\label{wxregexreplace}
 195
 196 \constfunc{int}{Replace}{\param{wxString* }{text}, \param{const wxString\& }{replacement}, \param{size\_t }{maxMatches = 0}}
 197
 198 Replaces the current regular expression in the string pointed to by
 199 {\it text}, with the text in {\it replacement} and return number of matches
 200 replaced (maybe $0$ if none found) or $-1$ on error.
 201
 202 The replacement text may contain back references {\tt $\backslash$number} which will be
 203 replaced with the value of the corresponding subexpression in the
 204 pattern match. {\tt $\backslash$0} corresponds to the entire match and {\tt \&} is a
 205 synonym for it. Backslash may be used to quote itself or {\tt \&} character.
 206
 207 {\it maxMatches} may be used to limit the number of replacements made, setting
 208 it to $1$, for example, will only replace first occurrence (if any) of the
 209 pattern in the text while default value of $0$ means replace all.
 210
 211 \membersection{wxRegEx::ReplaceAll}\label{wxregexreplaceall}
 212
 213 \constfunc{int}{ReplaceAll}{\param{wxString* }{text}, \param{const wxString\& }{replacement}}
 214
 215 Replace all occurrences: this is actually a synonym for
 216 \helpref{Replace()}{wxregexreplace}.
 217
 218 \wxheading{See also}
 219
 220 \helpref{ReplaceFirst}{wxregexreplacefirst}
 221
 222 \membersection{wxRegEx::ReplaceFirst}\label{wxregexreplacefirst}
 223
 224 \constfunc{int}{ReplaceFirst}{\param{wxString* }{text}, \param{const wxString\& }{replacement}}
 225
 226 Replace the first occurrence.
 227
 228 \wxheading{See also}
 229
 230 \helpref{Replace}{wxregexreplace}
 231