X-Git-Url: https://git.saurik.com/wxWidgets.git/blobdiff_plain/dbdb39b2d0b8c3359eab1693fd1fc786499f62d7..bf7945cef10c0844a32e95695c544d829da9293a:/docs/latex/wx/tokenizr.tex

diff --git a/docs/latex/wx/tokenizr.tex b/docs/latex/wx/tokenizr.tex
index 750bd8cb35..0b8490ce1d 100644
--- a/docs/latex/wx/tokenizr.tex
+++ b/docs/latex/wx/tokenizr.tex
@@ -1,6 +1,60 @@
 \section{\class{wxStringTokenizer}}\label{wxstringtokenizer}
 
-wxStringTokenizer helps you to break a string up into a number of tokens.
+wxStringTokenizer helps you to break a string up into a number of tokens. It
+replaces the standard C function {\tt strtok()} and also extends it in a
+number of ways.
+
+To use this class, you should create a wxStringTokenizer object, give it the
+string to tokenize and also the delimiters which separate tokens in the string
+(by default, white space characters will be used).
+
+Then \helpref{GetNextToken}{wxstringtokenizergetnexttoken} may be called
+repeatedly until it \helpref{HasMoreTokens}{wxstringtokenizerhasmoretokens} 
+returns FALSE.
+
+For example:
+
+\begin{verbatim}
+
+wxStringTokenizer tkz("first:second:third:fourth", ":");
+while ( tkz.HasMoreTokens() )
+{
+    wxString token = tkz.GetNextToken();
+
+    // process token here
+}
+\end{verbatim}
+
+By default, wxStringTokenizer will behave in the same way as {\tt strtok()} if
+the delimiters string only contains white space characters but, unlike the
+standard function, it will return empty tokens if this is not the case. This
+is helpful for parsing strictly formatted data where the number of fields is
+fixed but some of them may be empty (i.e. {\tt TAB} or comma delimited text
+files).
+
+The behaviour is governed by the last 
+\helpref{constructor}{wxstringtokenizerwxstringtokenizer}/\helpref{SetString}{wxstringtokenizersetstring} 
+parameter {\tt mode} which may be one of the following:
+
+\twocolwidtha{5cm}%
+\begin{twocollist}\itemsep=0pt
+\twocolitem{{\tt wxTOKEN\_DEFAULT}}{Default behaviour (as described above):
+same as {\tt wxTOKEN\_STRTOK} if the delimiter string contains only
+whitespaces, same as {\tt wxTOKEN\_RET\_EMPTY} otherwise}
+\twocolitem{{\tt wxTOKEN\_RET\_EMPTY}}{In this mode, the empty tokens in the
+middle of the string will be returned, i.e. {\tt "a::b:"} will be tokenized in
+three tokens `a', `' and `b'.}
+\twocolitem{{\tt wxTOKEN\_RET\_EMPTY\_ALL}}{In this mode, empty trailing token
+(after the last delimiter character) will be returned as well. The string as
+above will contain four tokens: the already mentioned ones and another empty
+one as the last one.}
+\twocolitem{{\tt wxTOKEN\_RET\_DELIMS}}{In this mode, the delimiter character
+after the end of the current token (there may be none if this is the last
+token) is returned appended to the token. Otherwise, it is the same mode as 
+{\tt wxTOKEN\_RET\_EMPTY}.}
+\twocolitem{{\tt wxTOKEN\_STRTOK}}{In this mode the class behaves exactly like
+the standard {\tt strtok()} function. The empty tokens are never returned.}
+\end{twocollist}
 
 \wxheading{Derived from}
 
@@ -16,49 +70,53 @@ wxStringTokenizer helps you to break a string up into a number of tokens.
 
 \func{}{wxStringTokenizer}{\void}
 
-Default constructor.
+Default constructor. You must call 
+\helpref{SetString}{wxstringtokenizersetstring} before calling any other
+methods.
 
-\func{}{wxStringTokenizer}{\param{const wxString\& }{to\_tokenize}, \param{const wxString\& }{delims = " $\backslash$t$\backslash$r$\backslash$n"}, \param{bool }{ret\_delim = FALSE}}
+\func{}{wxStringTokenizer}{\param{const wxString\& }{str}, \param{const wxString\& }{delims = " $\backslash$t$\backslash$r$\backslash$n"}, \param{wxStringTokenizerMode }{mode = wxTOKEN\_DEFAULT}}
 
-Constructor. Pass the string to tokenize, a string containing delimiters,
-a flag specifying whether delimiters are retained.
+Constructor. Pass the string to tokenize, a string containing delimiters
+and the mode specifying how the string should be tokenized.
 
-\membersection{wxStringTokenizer::\destruct{wxStringTokenizer}}\label{wxstringtokenizerdtor}
+\membersection{wxStringTokenizer::CountTokens}\label{wxstringtokenizercounttokens}
 
-\func{}{\destruct{wxStringTokenizer}}{\void}
+\constfunc{int}{CountTokens}{\void}
 
-Destructor.
+Returns the number of tokens in the input string.
 
-\membersection{wxStringTokenizer::CountTokens}\label{wxstringtokenizercounttokens}
+\membersection{wxStringTokenizer::HasMoreTokens}\label{wxstringtokenizerhasmoretokens}
 
-\constfunc{virtual int}{CountTokens}{\void}
+\constfunc{bool}{HasMoreTokens}{\void}
 
-Returns the number of tokens in the input string.
+Returns TRUE if the tokenizer has further tokens, FALSE if none are left.
 
-\membersection{wxStringTokenizer::HasMoreToken}\label{wxstringtokenizerhasmoretoken}
+\membersection{wxStringTokenizer::GetNextToken}\label{wxstringtokenizergetnexttoken}
 
-\constfunc{virtual bool}{HasMoreToken}{\void}
+\func{wxString}{GetNextToken}{\void}
 
-Returns TRUE if the tokenizer has further tokens.
+Returns the next token or empty string if the end of string was reached.
 
-\membersection{wxStringTokenizer::NextToken}\label{wxstringtokenizernexttoken}
+\membersection{wxStringTokenizer::GetPosition}\label{wxstringtokenizergetposition}
 
-\constfunc{virtual wxString}{NextToken}{\void}
+\constfunc{size\_t}{GetPosition}{\void}
 
-Returns the next token.
+Returns the current position (i.e. one index after the last returned
+token or 0 if GetNextToken() has never been called) in the original
+string.
 
 \membersection{wxStringTokenizer::GetString}\label{wxstringtokenizergetstring}
 
-\constfunc{virtual wxString}{GetString}{\void}
+\constfunc{wxString}{GetString}{\void}
 
-Returns the input string.
+Returns the part of the starting string without all token already extracted.
 
 \membersection{wxStringTokenizer::SetString}\label{wxstringtokenizersetstring}
 
-\func{void}{SetString}{\param{const wxString\& }{to\_tokenize}, \param{const wxString\& }{delims = " $\backslash$t$\backslash$r$\backslash$n"}, \param{bool }{ret\_delim = FALSE}}
+\func{void}{SetString}{\param{const wxString\& }{to\_tokenize}, \param{const wxString\& }{delims = " $\backslash$t$\backslash$r$\backslash$n"}, \param{wxStringTokenizerMode }{mode = wxTOKEN\_DEFAULT}}
 
 Initializes the tokenizer.
 
 Pass the string to tokenize, a string containing delimiters,
-a flag specifying whether delimiters are retained.
+and the mode specifying how the string should be tokenized.