]> git.saurik.com Git - wxWidgets.git/blob - docs/latex/wx/htparser.tex
Large parts rewritten and reorganized
[wxWidgets.git] / 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 begining 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 staticaly 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{See also}
30
31 \helpref{Cells Overview}{cells},
32 \helpref{Tag Handlers Overview}{handlers},
33 \helpref{wxHtmlTag}{wxhtmltag}
34
35 \latexignore{\rtfignore{\wxheading{Members}}}
36
37 \membersection{wxHtmlParser::wxHtmlParser}\label{wxhtmlparserwxhtmlparser}
38
39 \func{}{wxHtmlParser}{\void}
40
41 Constructor.
42
43 \membersection{wxHtmlParser::AddTag}\label{wxhtmlparseraddtag}
44
45 \func{void}{AddTag}{\param{const wxHtmlTag\& }{tag}}
46
47 This may (and may not) be overwriten in derived class.
48
49 This method is called each time new tag is about to be added.
50 {\it tag} contains information about the tag. (See \helpref{wxHtmlTag}{wxhtmltag}
51 for details.)
52
53 Default (wxHtmlParser) behaviour is this:
54 First it finds a handler capable of handling this tag and then it calls
55 handler's HandleTag method.
56
57 \membersection{wxHtmlParser::AddTagHandler}\label{wxhtmlparseraddtaghandler}
58
59 \func{virtual void}{AddTagHandler}{\param{wxHtmlTagHandler }{*handler}}
60
61 Adds handler to the internal list (\& hash table) of handlers. This
62 method should not be called directly by user but rather by derived class'
63 constructor.
64
65 This adds the handler to this {\bf instance} of wxHtmlParser, not to
66 all objects of this class! (Static front-end to AddTagHandler is provided
67 by wxHtmlWinParser).
68
69 All handlers are deleted on object deletion.
70
71 \membersection{wxHtmlParser::AddText}\label{wxhtmlparseraddword}
72
73 \func{virtual void}{AddWord}{\param{const char* }{txt}}
74
75 Must be overwriten in derived class.
76
77 This method is called by \helpref{DoParsing}{wxhtmlparserdoparsing}
78 each time a part of text is parsed. {\it txt} is NOT only one word, it is
79 substring of input. It is not formatted or preprocessed (so white spaces are
80 unmodified).
81
82 \membersection{wxHtmlParser::DoParsing}\label{wxhtmlparserdoparsing}
83
84 \func{void}{DoParsing}{\param{int }{begin\_pos}, \param{int }{end\_pos}}
85
86 \func{void}{DoParsing}{\void}
87
88 Parses the m\_Source from begin\_pos to end\_pos-1.
89 (in noparams version it parses whole m\_Source)
90
91 \membersection{wxHtmlParser::DoneParser}\label{wxhtmlparserdoneparser}
92
93 \func{virtual void}{DoneParser}{\void}
94
95 This must be called after DoParsing().
96
97 \membersection{wxHtmlParser::GetFS}\label{wxhtmlparsergetfs}
98
99 \constfunc{wxFileSystem*}{GetFS}{\void}
100
101 Returns pointer to the file system. Because each tag handler has
102 reference to it's parent parser it can easily request the file by
103 calling
104
105 \begin{verbatim}
106 wxFSFile *f = m_Parser -> GetFS() -> OpenFile("image.jpg");
107 \end{verbatim}
108
109 \membersection{wxHtmlParser::GetProduct}\label{wxhtmlparsergetproduct}
110
111 \func{virtual wxObject*}{GetProduct}{\void}
112
113 Returns product of parsing. Returned value is result of parsing
114 of the document. The type of this result depends on internal
115 representation in derived parser (but it must be derived from wxObject!).
116
117 See wxHtmlWinParser for details.
118
119 \membersection{wxHtmlParser::GetSource}\label{wxhtmlparsergetsource}
120
121 \func{wxString*}{GetSource}{\void}
122
123 Returns pointer to the source being parsed.
124
125
126 \membersection{wxHtmlParser::InitParser}\label{wxhtmlparserinitparser}
127
128 \func{virtual void}{InitParser}{\param{const wxString\& }{source}}
129
130 Setups the parser for parsing the {\it source} string. (Should be overriden
131 in derived class)
132
133 \membersection{wxHtmlParser::Parse}\label{wxhtmlparserparse}
134
135 \func{wxObject*}{Parse}{\param{const wxString\& }{source}}
136
137 Proceeds parsing of the document. This is end-user method. You can simply
138 call it when you need to obtain parsed output (which is parser-specific)
139
140 The method does these things:
141
142 \begin{enumerate}\itemsep=0pt
143 \item calls \helpref{InitParser(source)}{wxhtmlparserinitparser}
144 \item calls \helpref{DoParsing}{wxhtmlparserdoparsing}
145 \item calls \helpref{GetProduct}{wxhtmlparsergetproduct}
146 \item calls \helpref{DoneParser}{wxhtmlparserdoneparser}
147 \item returns value returned by GetProduct
148 \end{enumerate}
149
150 You shouldn't use InitParser, DoParsing, GetProduct or DoneParser directly.
151
152
153
154 \membersection{wxHtmlParser::PushTagHandler}\label{wxhtmlparserpushtaghandler}
155
156 \func{void}{PushTagHandler}{\param{wxHtmlTagHandler* }{handler}, \param{wxString }{tags}}
157
158 Forces the handler to handle additional tags
159 (not returned by \helpref{GetSupportedTags}{wxhtmltaghandlergetsupportedtags}).
160 The handler should already be added to this parser.
161
162 \wxheading{Parameters}
163
164 \docparam{handler}{the handler}
165 \docparam{tags}{List of tags (in same format as GetSupportedTags's return value). The parser
166 will redirect these tags to {\it handler} (until call to \helpref{PopTagHandler}{wxhtmlparserpoptaghandler}). }
167
168 \wxheading{Example}
169
170 Imagine you want to parse following pseudo-html structure:
171
172 \begin{verbatim}
173 <myitems>
174 <param name="one" value="1">
175 <param name="two" value="2">
176 </myitems>
177
178 <execute>
179 <param program="text.exe">
180 </execute>
181 \end{verbatim}
182
183 It is obvious that you cannot use only one tag handler for <param> tag.
184 Instead you must use context-sensitive handlers for <param> inside <myitems>
185 and <param> inside <execute>.
186
187 This is the prefered solution:
188
189 \begin{verbatim}
190 TAG_HANDLER_BEGIN(MYITEM, "MYITEMS")
191 TAG_HANDLER_PROC(tag)
192 {
193 // ...something...
194
195 m_Parser -> PushTagHandler(this, "PARAM");
196 ParseInner(tag);
197 m_Parser -> PopTagHandler();
198
199 // ...something...
200 }
201 TAG_HANDLER_END(MYITEM)
202 \end{verbatim}
203
204
205 \membersection{wxHtmlParser::PopTagHandler}\label{wxhtmlparserpoptaghandler}
206
207 \func{void}{PopTagHandler}{\void}
208
209 Restores parser's state before last call to
210 \helpref{PushTagHandler}{wxhtmlparserpushtaghandler}.
211
212
213 \membersection{wxHtmlParser::SetFS}\label{wxhtmlparsersetfs}
214
215 \func{void}{SetFS}{\param{wxFileSystem }{*fs}}
216
217 Sets the virtual file system that will be used to request additional
218 files. (For example {\tt <IMG>} tag handler requests wxFSFile with the
219 image data.)
220