X-Git-Url: https://git.saurik.com/wxWidgets.git/blobdiff_plain/ad813b00d5956f35f2b1585a276095e24ce8ad5a..0ff2a74d0cc65f081aafcff79bcd3fd14638814f:/docs/latex/wx/tokenizr.tex?ds=sidebyside diff --git a/docs/latex/wx/tokenizr.tex b/docs/latex/wx/tokenizr.tex index ffc8d5dfe7..75f8ab9e8a 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(wxT("first:second:third:fourth"), wxT(":")); +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} @@ -12,53 +66,68 @@ wxStringTokenizer helps you to break a string up into a number of tokens. \latexignore{\rtfignore{\wxheading{Members}}} + \membersection{wxStringTokenizer::wxStringTokenizer}\label{wxstringtokenizerwxstringtokenizer} \func{}{wxStringTokenizer}{\void} -Default constructor. - -\func{}{wxStringTokenizer}{\param{const wxString\& }{to\_tokenize}, \param{const wxString\& }{delims = " $\backslash$t$\backslash$r$\backslash$n"}, \param{bool }{ret\_delim = FALSE}} - -Constructor. Pass the string to tokenize, a string containing delimiters, -a flag specifying whether delimiters are retained. +Default constructor. You must call +\helpref{SetString}{wxstringtokenizersetstring} before calling any other +methods. -\membersection{wxStringTokenizer::\destruct{wxStringTokenizer}}\label{wxstringtokenizerdtor} +\func{}{wxStringTokenizer}{\param{const wxString\& }{str}, \param{const wxString\& }{delims = " $\backslash$t$\backslash$r$\backslash$n"}, \param{wxStringTokenizerMode }{mode = wxTOKEN\_DEFAULT}} -\func{}{\destruct{wxStringTokenizer}}{\void} +Constructor. Pass the string to tokenize, a string containing delimiters +and the mode specifying how the string should be tokenized. -Destructor. \membersection{wxStringTokenizer::CountTokens}\label{wxstringtokenizercounttokens} \constfunc{int}{CountTokens}{\void} -Returns the number of tokens in the input string. +Returns the number of tokens remaining in the input string. The number of +tokens returned by this function is decremented each time +\helpref{GetNextToken}{wxstringtokenizergetnexttoken} is called and when it +reaches $0$ \helpref{HasMoreTokens}{wxstringtokenizerhasmoretokens} returns +\false. + \membersection{wxStringTokenizer::HasMoreTokens}\label{wxstringtokenizerhasmoretokens} \constfunc{bool}{HasMoreTokens}{\void} -Returns TRUE if the tokenizer has further tokens. +Returns \true if the tokenizer has further tokens, \false if none are left. + \membersection{wxStringTokenizer::GetNextToken}\label{wxstringtokenizergetnexttoken} -\constfunc{wxString}{GetNextToken}{\void} +\func{wxString}{GetNextToken}{\void} + +Returns the next token or empty string if the end of string was reached. + + +\membersection{wxStringTokenizer::GetPosition}\label{wxstringtokenizergetposition} + +\constfunc{size\_t}{GetPosition}{\void} + +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. -Returns the next token. \membersection{wxStringTokenizer::GetString}\label{wxstringtokenizergetstring} \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.