% htmlparser.tex at 14/Mar/99 20:13:37
%
-
\section{\class{wxHtmlParser}}\label{wxhtmlparser}
-This class handles {\bf generic} parsing of HTML document : it scans
+This class handles the {\bf generic} parsing of HTML document: it scans
the document and divide it into blocks of tags (where one block
-consists of begining and ending tag and of text between these
-2 tags).
+consists of beginning and ending tag and of text between these
+two tags).
It is independent from wxHtmlWindow and can be used as stand-alone parser
(Julian Smart's idea of speech-only HTML viewer or wget-like utility -
-see InetGet sample for example).
+see InetGet sample for example).
It uses system of tag handlers to parse the HTML document. Tag handlers
-are not staticaly shared by all instances but are created for each
+are not statically shared by all instances but are created for each
wxHtmlParser instance. The reason is that the handler may contain
document-specific temporary data used during parsing (e.g. complicated
-structures like tables)
+structures like tables).
-Typically the user calls only \helpref{Parse}{wxhtmlparserparse} method.
+Typically the user calls only the \helpref{Parse}{wxhtmlparserparse} method.
\wxheading{Derived from}
wxObject
+\wxheading{Include files}
+
+<wx/html/htmlpars.h>
+
\wxheading{See also}
\helpref{Cells Overview}{cells},
\latexignore{\rtfignore{\wxheading{Members}}}
-
\membersection{wxHtmlParser::wxHtmlParser}\label{wxhtmlparserwxhtmlparser}
\func{}{wxHtmlParser}{\void}
-Constructor.
+Constructor.
+\membersection{wxHtmlParser::AddTag}\label{wxhtmlparseraddtag}
-\membersection{wxHtmlParser::SetFS}\label{wxhtmlparsersetfs}
+\func{void}{AddTag}{\param{const wxHtmlTag\& }{tag}}
-\func{void}{SetFS}{\param{wxFileSystem }{*fs}}
+This may (and may not) be overwritten in derived class.
-Sets the virtual file system that will be used to request additional
-files. (For example {\tt <IMG>} tag handler requests wxFSFile with the
-image data.)
+This method is called each time new tag is about to be added.
+{\it tag} contains information about the tag. (See \helpref{wxHtmlTag}{wxhtmltag}
+for details.)
+
+Default (wxHtmlParser) behaviour is this:
+First it finds a handler capable of handling this tag and then it calls
+handler's HandleTag method.
+
+\membersection{wxHtmlParser::AddTagHandler}\label{wxhtmlparseraddtaghandler}
+
+\func{virtual void}{AddTagHandler}{\param{wxHtmlTagHandler }{*handler}}
+
+Adds handler to the internal list (\& hash table) of handlers. This
+method should not be called directly by user but rather by derived class'
+constructor.
+
+This adds the handler to this {\bf instance} of wxHtmlParser, not to
+all objects of this class! (Static front-end to AddTagHandler is provided
+by wxHtmlWinParser).
+
+All handlers are deleted on object deletion.
+
+\membersection{wxHtmlParser::AddText}\label{wxhtmlparseraddword}
+
+\func{virtual void}{AddWord}{\param{const char* }{txt}}
+
+Must be overwritten in derived class.
+
+This method is called by \helpref{DoParsing}{wxhtmlparserdoparsing}
+each time a part of text is parsed. {\it txt} is NOT only one word, it is
+substring of input. It is not formatted or preprocessed (so white spaces are
+unmodified).
+
+\membersection{wxHtmlParser::DoParsing}\label{wxhtmlparserdoparsing}
+
+\func{void}{DoParsing}{\param{int }{begin\_pos}, \param{int }{end\_pos}}
+
+\func{void}{DoParsing}{\void}
+
+Parses the m\_Source from begin\_pos to end\_pos-1.
+(in noparams version it parses whole m\_Source)
+
+\membersection{wxHtmlParser::DoneParser}\label{wxhtmlparserdoneparser}
+
+\func{virtual void}{DoneParser}{\void}
+
+This must be called after DoParsing().
\membersection{wxHtmlParser::GetFS}\label{wxhtmlparsergetfs}
\constfunc{wxFileSystem*}{GetFS}{\void}
Returns pointer to the file system. Because each tag handler has
-reference to it's parent parser it can easily request the file by
+reference to it is parent parser it can easily request the file by
calling
\begin{verbatim}
wxFSFile *f = m_Parser -> GetFS() -> OpenFile("image.jpg");
\end{verbatim}
+\membersection{wxHtmlParser::GetProduct}\label{wxhtmlparsergetproduct}
-\membersection{wxHtmlParser::Parse}\label{wxhtmlparserparse}
+\func{virtual wxObject*}{GetProduct}{\void}
-\func{wxObject*}{Parse}{\param{const wxString\& }{source}}
+Returns product of parsing. Returned value is result of parsing
+of the document. The type of this result depends on internal
+representation in derived parser (but it must be derived from wxObject!).
-Proceeds parsing of the document. This is end-user method. You can simply
-call it when you need to obtain parsed output (which is parser-specific)
+See wxHtmlWinParser for details.
-The method does these things:
+\membersection{wxHtmlParser::GetSource}\label{wxhtmlparsergetsource}
-\begin{enumerate}
-\item calls \helpref{InitParser(source)}{wxhtmlparserinitparser}
-\item calls \helpref{DoParsing}{wxhtmlparserdoparsing}
-\item calls \helpref{GetProduct}{wxhtmlparsergetproduct}
-\item calls \helpref{DoneParser}{wxhtmlparserdoneparser}
-\item returns value returned by GetProduct
-\end{enumerate}
+\func{wxString*}{GetSource}{\void}
+
+Returns pointer to the source being parsed.
-You shouldn't use InitParser, DoParsing, GetProduct or DoneParser directly.
\membersection{wxHtmlParser::InitParser}\label{wxhtmlparserinitparser}
\func{virtual void}{InitParser}{\param{const wxString\& }{source}}
-Setups the parser for parsing the {\it source} string. (Should be overriden
+Setups the parser for parsing the {\it source} string. (Should be overridden
in derived class)
+\membersection{wxHtmlParser::OpenURL}\label{wxhtmlparseropenurl}
-\membersection{wxHtmlParser::DoneParser}\label{wxhtmlparserdoneparser}
+\func{virtual wxFSFile*}{OpenURL}{\param{wxHtmlURLType }{type}, \param{const wxString\& }{url}}
-\func{virtual void}{DoneParser}{\void}
+Opens given URL and returns {\tt wxFSFile} object that can be used to read data
+from it. This method may return NULL in one of two cases: either the URL doesn't
+point to any valid resource or the URL is blocked by overridden implementation
+of {\it OpenURL} in derived class.
-This must be called after DoParsing().
+\wxheading{Parameters}
+\docparam{type}{Indicates type of the resource. Is one of:
-\membersection{wxHtmlParser::DoParsing}\label{wxhtmlparserdoparsing}
+\begin{twocollist}\itemsep=0pt
+\twocolitem{{\bf wxHTML\_URL\_PAGE}}{Opening a HTML page.}
+\twocolitem{{\bf wxHTML\_URL\_IMAGE}}{Opening an image.}
+\twocolitem{{\bf wxHTML\_URL\_OTHER}}{Opening a resource that doesn't fall into
+any other category.}
+\end{twocollist}}
-\func{void}{DoParsing}{\param{int }{begin\_pos}, \param{int }{end\_pos}}
+\docparam{url}{URL being opened.}
-\func{void}{DoParsing}{\void}
+\wxheading{Notes}
-Parses the m\_Source from begin\_pos to end\_pos-1.
-(in noparams version it parses whole m\_Source)
+Always use this method in tag handlers instead of {\tt GetFS()->OpenFile()}
+because it can block the URL and is thus more secure.
-\membersection{wxHtmlParser::GetProduct}\label{wxhtmlparsergetproduct}
+Default behaviour is to call \helpref{wxHtmlWindow::OnOpeningURL}{wxhtmlwindowonopeningurl}
+of the associated wxHtmlWindow object (which may decide to block the URL or
+redirect it to another one),if there's any, and always open the URL if the
+parser is not used with wxHtmlWindow.
-\func{virtual wxObject*}{GetProduct}{\void}
+Returned {\tt wxFSFile} object is not guaranteed to point to {\it url}, it might
+have been redirected!
-Returns product of parsing. Returned value is result of parsing
-of the document. The type of this result depends on internal
-representation in derived parser (but it must be derived from wxObject!).
+\membersection{wxHtmlParser::Parse}\label{wxhtmlparserparse}
-See wxHtmlWinParser for details.
+\func{wxObject*}{Parse}{\param{const wxString\& }{source}}
+Proceeds parsing of the document. This is end-user method. You can simply
+call it when you need to obtain parsed output (which is parser-specific)
-\membersection{wxHtmlParser::AddTagHandler}\label{wxhtmlparseraddtaghandler}
+The method does these things:
-\func{virtual void}{AddTagHandler}{\param{wxHtmlTagHandler }{*handler}}
+\begin{enumerate}\itemsep=0pt
+\item calls \helpref{InitParser(source)}{wxhtmlparserinitparser}
+\item calls \helpref{DoParsing}{wxhtmlparserdoparsing}
+\item calls \helpref{GetProduct}{wxhtmlparsergetproduct}
+\item calls \helpref{DoneParser}{wxhtmlparserdoneparser}
+\item returns value returned by GetProduct
+\end{enumerate}
-Adds handler to the internal list (\& hash table) of handlers. This
-method should not be called directly by user but rather by derived class'
-constructor.
+You shouldn't use InitParser, DoParsing, GetProduct or DoneParser directly.
-This adds the handler to this {\bf instance} of wxHtmlParser not to
-all objects of this class!!! (Static front-end to AddTagHandler is provided
-by wxHtmlWinParser)
+\membersection{wxHtmlParser::PushTagHandler}\label{wxhtmlparserpushtaghandler}
-All handlers are deleted on object deletion.
+\func{void}{PushTagHandler}{\param{wxHtmlTagHandler* }{handler}, \param{wxString }{tags}}
-\membersection{wxHtmlParser::GetSource}\label{wxhtmlparsergetsource}
+Forces the handler to handle additional tags
+(not returned by \helpref{GetSupportedTags}{wxhtmltaghandlergetsupportedtags}).
+The handler should already be added to this parser.
-\func{wxString*}{GetSource}{\void}
+\wxheading{Parameters}
-Returns pointer to the source being parsed.
+\docparam{handler}{the handler}
+\docparam{tags}{List of tags (in same format as GetSupportedTags's return value). The parser
+will redirect these tags to {\it handler} (until call to \helpref{PopTagHandler}{wxhtmlparserpoptaghandler}). }
+\wxheading{Example}
-\membersection{wxHtmlParser::GetTempData}\label{wxhtmlparsergettempdata}
+Imagine you want to parse following pseudo-html structure:
-\func{virtual wxList*}{GetTempData}{\void}
+\begin{verbatim}
+<myitems>
+ <param name="one" value="1">
+ <param name="two" value="2">
+</myitems>
+
+<execute>
+ <param program="text.exe">
+</execute>
+\end{verbatim}
+
+It is obvious that you cannot use only one tag handler for <param> tag.
+Instead you must use context-sensitive handlers for <param> inside <myitems>
+and <param> inside <execute>.
-This method returns list of wxObjects that represents
-all data allocated by the parser. These can't be freeded
-by destructor because they must be valid as long as
-GetProduct's return value is valid - the caller must
-explicitly call
+This is the preferred solution:
\begin{verbatim}
-delete (MyParser -> GetTempData());
+TAG_HANDLER_BEGIN(MYITEM, "MYITEMS")
+ TAG_HANDLER_PROC(tag)
+ {
+ // ...something...
+
+ m_Parser -> PushTagHandler(this, "PARAM");
+ ParseInner(tag);
+ m_Parser -> PopTagHandler();
+
+ // ...something...
+ }
+TAG_HANDLER_END(MYITEM)
\end{verbatim}
-to free the memory (this method always sets the list to delete its contents)
-
-\wxheading{Example}
-Why is this neccessary? Imagine wxHtmlWinParser : when handling
-FONT tag it creates some fonts. These fonts are then used by wxHtmlWindow
-to display the text. But wxHtmWinParser object is needed only when parsing
-the document - it may be deleted then. But fonts CAN'T be deleted - they
-must exist as long as the window is displaying text.
+\membersection{wxHtmlParser::PopTagHandler}\label{wxhtmlparserpoptaghandler}
-GetTempData() solves the problem.
+\func{void}{PopTagHandler}{\void}
-\membersection{wxHtmlParser::AddText}\label{wxhtmlparseraddword}
+Restores parser's state before last call to
+\helpref{PushTagHandler}{wxhtmlparserpushtaghandler}.
-\func{virtual void}{AddWord}{\param{const char* }{txt}}
-Must be overwriten in derived class.
+\membersection{wxHtmlParser::SetFS}\label{wxhtmlparsersetfs}
-This method is called by \helpref{DoParsing}{wxhtmlparserdoparsing}
-each time a part of text is parsed. {\it txt} is NOT only one word, it is
-substring of input. It is not formatted or preprocessed (so white spaces are
-unmodified)
+\func{void}{SetFS}{\param{wxFileSystem }{*fs}}
-\membersection{wxHtmlParser::AddTag}\label{wxhtmlparseraddtag}
+Sets the virtual file system that will be used to request additional
+files. (For example {\tt <IMG>} tag handler requests wxFSFile with the
+image data.)
-\func{void}{AddTag}{\param{const wxHtmlTag\& }{tag}
+\membersection{wxHtmlParser::StopParsing}\label{wxhtmlparserstopparsing}
-This may (and may not) be overwriten in derived class.
+\func{void}{StopParsing}{\void}
-This method is called each time new tag is about to be added.
-{\it tag} contains information about the tag. (See \helpref{wxHtmlTag}{wxhtmltag}
-for details.)
+Call this function to interrupt parsing from a tag handler. No more tags
+will be parsed afterward. This function may only be called from
+\helpref{wxHtmlParser::Parse}{wxhtmlparserparse} or any function called
+by it (i.e. from tag handlers).
-Default (wxHtmlParser) behaviour is this :
-First it finds a handler capable of handling this tag and then it calls
-handler's HandleTag method.
projects / wxWidgets.git / blobdiff