docs/latex/wx/htparser.tex

   1 %
   2 % automatically generated by HelpGen from
   3 % htmlparser.tex at 14/Mar/99 20:13:37
   4 %
   5
   6 \section{\class{wxHtmlParser}}\label{wxhtmlparser}
   7
   8 This class handles the {\bf generic} parsing of HTML document: it scans
   9 the document and divide it into blocks of tags (where one block
  10 consists of beginning and ending tag and of text between these
  11 two tags).
  12
  13 It is independent from wxHtmlWindow and can be used as stand-alone parser
  14 (Julian Smart's idea of speech-only HTML viewer or wget-like utility -
  15 see InetGet sample for example).
  16
  17 It uses system of tag handlers to parse the HTML document. Tag handlers
  18 are not statically shared by all instances but are created for each
  19 wxHtmlParser instance. The reason is that the handler may contain
  20 document-specific temporary data used during parsing (e.g. complicated
  21 structures like tables).
  22
  23 Typically the user calls only the \helpref{Parse}{wxhtmlparserparse} method.
  24
  25 \wxheading{Derived from}
  26
  27 wxObject
  28
  29 \wxheading{Include files}
  30
  31 <wx/html/htmlpars.h>
  32
  33 \wxheading{See also}
  34
  35 \helpref{Cells Overview}{cells},
  36 \helpref{Tag Handlers Overview}{handlers},
  37 \helpref{wxHtmlTag}{wxhtmltag}
  38
  39 \latexignore{\rtfignore{\wxheading{Members}}}
  40
  41 \membersection{wxHtmlParser::wxHtmlParser}\label{wxhtmlparserwxhtmlparser}
  42
  43 \func{}{wxHtmlParser}{\void}
  44
  45 Constructor.
  46
  47 \membersection{wxHtmlParser::AddTag}\label{wxhtmlparseraddtag}
  48
  49 \func{void}{AddTag}{\param{const wxHtmlTag\& }{tag}}
  50
  51 This may (and may not) be overwritten in derived class.
  52
  53 This method is called each time new tag is about to be added.
  54 {\it tag} contains information about the tag. (See \helpref{wxHtmlTag}{wxhtmltag}
  55 for details.)
  56
  57 Default (wxHtmlParser) behaviour is this:
  58 First it finds a handler capable of handling this tag and then it calls
  59 handler's HandleTag method.
  60
  61 \membersection{wxHtmlParser::AddTagHandler}\label{wxhtmlparseraddtaghandler}
  62
  63 \func{virtual void}{AddTagHandler}{\param{wxHtmlTagHandler }{*handler}}
  64
  65 Adds handler to the internal list (\& hash table) of handlers. This
  66 method should not be called directly by user but rather by derived class'
  67 constructor.
  68
  69 This adds the handler to this {\bf instance} of wxHtmlParser, not to
  70 all objects of this class! (Static front-end to AddTagHandler is provided
  71 by wxHtmlWinParser).
  72
  73 All handlers are deleted on object deletion.
  74
  75 \membersection{wxHtmlParser::AddText}\label{wxhtmlparseraddword}
  76
  77 \func{virtual void}{AddWord}{\param{const char* }{txt}}
  78
  79 Must be overwritten in derived class.
  80
  81 This method is called by \helpref{DoParsing}{wxhtmlparserdoparsing}
  82 each time a part of text is parsed. {\it txt} is NOT only one word, it is
  83 substring of input. It is not formatted or preprocessed (so white spaces are
  84 unmodified).
  85
  86 \membersection{wxHtmlParser::DoParsing}\label{wxhtmlparserdoparsing}
  87
  88 \func{void}{DoParsing}{\param{int }{begin\_pos}, \param{int }{end\_pos}}
  89
  90 \func{void}{DoParsing}{\void}
  91
  92 Parses the m\_Source from begin\_pos to end\_pos-1.
  93 (in noparams version it parses whole m\_Source)
  94
  95 \membersection{wxHtmlParser::DoneParser}\label{wxhtmlparserdoneparser}
  96
  97 \func{virtual void}{DoneParser}{\void}
  98
  99 This must be called after DoParsing().
 100
 101 \membersection{wxHtmlParser::GetFS}\label{wxhtmlparsergetfs}
 102
 103 \constfunc{wxFileSystem*}{GetFS}{\void}
 104
 105 Returns pointer to the file system. Because each tag handler has
 106 reference to it is parent parser it can easily request the file by
 107 calling
 108
 109 \begin{verbatim}
 110 wxFSFile *f = m_Parser -> GetFS() -> OpenFile("image.jpg");
 111 \end{verbatim}
 112
 113 \membersection{wxHtmlParser::GetProduct}\label{wxhtmlparsergetproduct}
 114
 115 \func{virtual wxObject*}{GetProduct}{\void}
 116
 117 Returns product of parsing. Returned value is result of parsing
 118 of the document. The type of this result depends on internal
 119 representation in derived parser (but it must be derived from wxObject!).
 120
 121 See wxHtmlWinParser for details.
 122
 123 \membersection{wxHtmlParser::GetSource}\label{wxhtmlparsergetsource}
 124
 125 \func{wxString*}{GetSource}{\void}
 126
 127 Returns pointer to the source being parsed.
 128
 129
 130 \membersection{wxHtmlParser::InitParser}\label{wxhtmlparserinitparser}
 131
 132 \func{virtual void}{InitParser}{\param{const wxString\& }{source}}
 133
 134 Setups the parser for parsing the {\it source} string. (Should be overridden
 135 in derived class)
 136
 137 \membersection{wxHtmlParser::OpenURL}\label{wxhtmlparseropenurl}
 138
 139 \func{virtual wxFSFile*}{OpenURL}{\param{wxHtmlURLType }{type}, \param{const wxString\& }{url}}
 140
 141 Opens given URL and returns {\tt wxFSFile} object that can be used to read data
 142 from it. This method may return NULL in one of two cases: either the URL doesn't
 143 point to any valid resource or the URL is blocked by overridden implementation
 144 of {\it OpenURL} in derived class.
 145
 146 \wxheading{Parameters}
 147
 148 \docparam{type}{Indicates type of the resource. Is one of:
 149
 150 \begin{twocollist}\itemsep=0pt
 151 \twocolitem{{\bf wxHTML\_URL\_PAGE}}{Opening a HTML page.}
 152 \twocolitem{{\bf wxHTML\_URL\_IMAGE}}{Opening an image.}
 153 \twocolitem{{\bf wxHTML\_URL\_OTHER}}{Opening a resource that doesn't fall into
 154 any other category.}
 155 \end{twocollist}}
 156
 157 \docparam{url}{URL being opened.}
 158
 159 \wxheading{Notes}
 160
 161 Always use this method in tag handlers instead of {\tt GetFS()->OpenFile()}
 162 because it can block the URL and is thus more secure.
 163
 164 Default behaviour is to call \helpref{wxHtmlWindow::OnOpeningURL}{wxhtmlwindowonopeningurl}
 165 of the associated wxHtmlWindow object (which may decide to block the URL or
 166 redirect it to another one),if there's any, and always open the URL if the
 167 parser is not used with wxHtmlWindow.
 168
 169 Returned {\tt wxFSFile} object is not guaranteed to point to {\it url}, it might
 170 have been redirected!
 171
 172 \membersection{wxHtmlParser::Parse}\label{wxhtmlparserparse}
 173
 174 \func{wxObject*}{Parse}{\param{const wxString\& }{source}}
 175
 176 Proceeds parsing of the document. This is end-user method. You can simply
 177 call it when you need to obtain parsed output (which is parser-specific)
 178
 179 The method does these things:
 180
 181 \begin{enumerate}\itemsep=0pt
 182 \item calls \helpref{InitParser(source)}{wxhtmlparserinitparser}
 183 \item calls \helpref{DoParsing}{wxhtmlparserdoparsing}
 184 \item calls \helpref{GetProduct}{wxhtmlparsergetproduct}
 185 \item calls \helpref{DoneParser}{wxhtmlparserdoneparser}
 186 \item returns value returned by GetProduct
 187 \end{enumerate}
 188
 189 You shouldn't use InitParser, DoParsing, GetProduct or DoneParser directly.
 190
 191 \membersection{wxHtmlParser::PushTagHandler}\label{wxhtmlparserpushtaghandler}
 192
 193 \func{void}{PushTagHandler}{\param{wxHtmlTagHandler* }{handler}, \param{wxString }{tags}}
 194
 195 Forces the handler to handle additional tags
 196 (not returned by \helpref{GetSupportedTags}{wxhtmltaghandlergetsupportedtags}).
 197 The handler should already be added to this parser.
 198
 199 \wxheading{Parameters}
 200
 201 \docparam{handler}{the handler}
 202 \docparam{tags}{List of tags (in same format as GetSupportedTags's return value). The parser
 203 will redirect these tags to {\it handler} (until call to \helpref{PopTagHandler}{wxhtmlparserpoptaghandler}). }
 204
 205 \wxheading{Example}
 206
 207 Imagine you want to parse following pseudo-html structure:
 208
 209 \begin{verbatim}
 210 <myitems>
 211     <param name="one" value="1">
 212     <param name="two" value="2">
 213 </myitems>
 214
 215 <execute>
 216     <param program="text.exe">
 217 </execute>
 218 \end{verbatim}
 219
 220 It is obvious that you cannot use only one tag handler for <param> tag.
 221 Instead you must use context-sensitive handlers for <param> inside <myitems>
 222 and <param> inside <execute>.
 223
 224 This is the preferred solution:
 225
 226 \begin{verbatim}
 227 TAG_HANDLER_BEGIN(MYITEM, "MYITEMS")
 228     TAG_HANDLER_PROC(tag)
 229     {
 230         // ...something...
 231
 232         m_Parser -> PushTagHandler(this, "PARAM");
 233         ParseInner(tag);
 234         m_Parser -> PopTagHandler();
 235
 236         // ...something...
 237      }
 238 TAG_HANDLER_END(MYITEM)
 239 \end{verbatim}
 240
 241
 242 \membersection{wxHtmlParser::PopTagHandler}\label{wxhtmlparserpoptaghandler}
 243
 244 \func{void}{PopTagHandler}{\void}
 245
 246 Restores parser's state before last call to
 247 \helpref{PushTagHandler}{wxhtmlparserpushtaghandler}.
 248
 249
 250 \membersection{wxHtmlParser::SetFS}\label{wxhtmlparsersetfs}
 251
 252 \func{void}{SetFS}{\param{wxFileSystem }{*fs}}
 253
 254 Sets the virtual file system that will be used to request additional
 255 files. (For example {\tt <IMG>} tag handler requests wxFSFile with the
 256 image data.)
 257
 258 \membersection{wxHtmlParser::StopParsing}\label{wxhtmlparserstopparsing}
 259
 260 \func{void}{StopParsing}{\void}
 261
 262 Call this function to interrupt parsing from a tag handler. No more tags
 263 will be parsed afterward. This function may only be called from
 264 \helpref{wxHtmlParser::Parse}{wxhtmlparserparse} or any function called
 265 by it (i.e. from tag handlers).
 266