corrected typo in the creation date

[wxWidgets.git] / docs / latex / wx / regex.tex

diff --git a/docs/latex/wx/regex.tex b/docs/latex/wx/regex.tex
index 91ac1c63745c1f88002c25ba2f27ab5d8abcb68b..27c4928c74d152d105b4abda00e724f9f1fe5021 100644 (file)
--- a/docs/latex/wx/regex.tex
+++ b/docs/latex/wx/regex.tex
@@ -11,14 +11,29 @@
 
 \section{\class{wxRegEx}}\label{wxregex}
 
-wxRegEx represents a regular expression. The regular expressions syntax
-supported is the POSIX one. Both basic and extended regular expressions are
-supported but, unlike POSIX C API, the extended ones are used by default.
-
-This class provides support for regular expressions matching and also
-replacement. It is built on top of either the system library (if it has support
-for POSIX regular expressions - which is the case of the most modern Unices) or
-uses the built-in Henry Spencer's library from tcl.
+wxRegEx represents a regular expression.  This class provides support
+for regular expressions matching and also replacement.
+
+It is built on top of either the system library (if it has support
+for POSIX regular expressions - which is the case of the most modern
+Unices) or uses the built in Henry Spencer's library.  Henry Spencer
+would appreciate being given credit in the documentation of software
+which uses his library, but that is not a requirement.
+
+Regular expressions, as defined by POSIX, come in two flavours: {\it extended}
+and {\it basic}.  The builtin library also adds a third flavour
+of expression \helpref{advanced}{wxresyn}, which is not available
+when using the system library.
+
+Unicode is fully supported only when using the builtin library.
+When using the system library in Unicode mode, the expressions and data
+are translated to the default 8-bit encoding before being passed to
+the library.
+
+On platforms where a system library is available, the default is to use
+the builtin library for Unicode builds, and the system library otherwise.
+It is possible to use the other if preferred by selecting it when building
+the wxWidgets.
 
 \wxheading{Derived from}
 
@@ -31,8 +46,13 @@ Flags for regex compilation to be used with \helpref{Compile()}{wxregexcompile}:
 \begin{verbatim}
 enum
 {
-    // use extended regex syntax (default)
+    // use extended regex syntax
     wxRE_EXTENDED = 0,
+    
+    // use advanced RE syntax (built-in regex only)
+#ifdef wxHAS_REGEX_ADVANCED
+    wxRE_ADVANCED = 1,
+#endif
 
     // use basic RE syntax
     wxRE_BASIC    = 2,
@@ -78,22 +98,26 @@ is bad because the real email addresses can have more complicated form than
 \begin{verbatim}
 wxString text;
 ...
-wxRegEx reEmail = "([^@]+)@([[:alnum:].-_].)+([[:alnum:]]+)";
+wxRegEx reEmail = wxT("([^@]+)@([[:alnum:].-_].)+([[:alnum:]]+)");
 if ( reEmail.Matches(text) )
 {
     wxString text = reEmail.GetMatch(email);
     wxString username = reEmail.GetMatch(email, 1);
-    if ( reEmail.GetMatch(email, 3) == "com" ) // .com TLD?
+    if ( reEmail.GetMatch(email, 3) == wxT("com") ) // .com TLD?
     {
         ...
     }
 }
 
 // or we could do this to hide the email address
-size_t count = reEmail.ReplaceAll(text, "HIDDEN@\\2\\3");
+size_t count = reEmail.ReplaceAll(text, wxT("HIDDEN@\\2\\3"));
 printf("text now contains %u hidden addresses", count);
 \end{verbatim}
 
+\wxheading{Include files}
+
+<wx/regex.h>
+
 \latexignore{\rtfignore{\wxheading{Members}}}
 
 \membersection{wxRegEx::wxRegEx}\label{wxregexwxregex}
@@ -139,7 +163,7 @@ May only be called after successful call to \helpref{Matches()}{wxregexmatches}
 and only if {\tt wxRE\_NOSUB} was {\bf not} used in 
 \helpref{Compile()}{wxregexcompile}.
 
-Returns {\tt false} if no match or if an error occured.
+Returns {\tt false} if no match or if an error occurred.
 
 \constfunc{wxString}{GetMatch}{\param{const wxString\& }{text}, \param{size\_t }{index = 0}}
 
@@ -150,14 +174,38 @@ May only be called after successful call to \helpref{Matches()}{wxregexmatches}
 and only if {\tt wxRE\_NOSUB} was {\bf not} used in 
 \helpref{Compile()}{wxregexcompile}.
 
+\membersection{wxRegEx::GetMatchCount}\label{wxregexgetmatchcount}
+
+\constfunc{size\_t}{GetMatchCount}{\void}
+
+Returns the size of the array of matches, i.e. the number of bracketed
+subexpressions plus one for the expression itself, or $0$ on error.
+
+May only be called after successful call to \helpref{Compile()}{wxregexcompile}.
+and only if {\tt wxRE\_NOSUB} was {\bf not} used.
+
 \membersection{wxRegEx::Matches}\label{wxregexmatches}
 
 \constfunc{bool}{Matches}{\param{const wxChar* }{text}, \param{int }{flags = 0}}
 
+\constfunc{bool}{Matches}{\param{const wxChar* }{text}, \param{int }{flags}, \param{size\_t }{len}}
+
+\constfunc{bool}{Matches}{\param{const wxString\& }{text}, \param{int }{flags = 0}}
+
 Matches the precompiled regular expression against the string {\it text},
 returns {\tt true} if matches and {\tt false} otherwise.
 
-Flags may be combination of {\tt wxRE\_NOTBOL} and {\tt wxRE\_NOTEOL}.
+{\it Flags} may be combination of {\tt wxRE\_NOTBOL} and {\tt wxRE\_NOTEOL}.
+
+Some regex libraries assume that the text given is null terminated, while
+others require the length be given as a separate parameter. Therefore for
+maximum portability assume that {\it text} cannot contain embedded nulls.
+
+When the {\it Matches(const wxChar *text, int flags = 0)} form is used,
+a {\it wxStrlen()} will be done internally if the regex library requires the
+length. When using {\it Matches()} in a loop
+the {\it Matches(text, flags, len)} form can be used instead, making it
+possible to avoid a {\it wxStrlen()} inside the loop.
 
 May only be called after successful call to \helpref{Compile()}{wxregexcompile}.