]> git.saurik.com Git - wxWidgets.git/blob - docs/latex/wx/htparser.tex
Small fixes for Tex2RTF but alas, we still get memory problems.
[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{Include files}
30
31 <wx/html/htmlpars.h>
32
33
34 \wxheading{See also}
35
36 \helpref{Cells Overview}{cells},
37 \helpref{Tag Handlers Overview}{handlers},
38 \helpref{wxHtmlTag}{wxhtmltag}
39
40 \latexignore{\rtfignore{\wxheading{Members}}}
41
42 \membersection{wxHtmlParser::wxHtmlParser}\label{wxhtmlparserwxhtmlparser}
43
44 \func{}{wxHtmlParser}{\void}
45
46 Constructor.
47
48 \membersection{wxHtmlParser::AddTag}\label{wxhtmlparseraddtag}
49
50 \func{void}{AddTag}{\param{const wxHtmlTag\& }{tag}}
51
52 This may (and may not) be overwriten in derived class.
53
54 This method is called each time new tag is about to be added.
55 {\it tag} contains information about the tag. (See \helpref{wxHtmlTag}{wxhtmltag}
56 for details.)
57
58 Default (wxHtmlParser) behaviour is this:
59 First it finds a handler capable of handling this tag and then it calls
60 handler's HandleTag method.
61
62 \membersection{wxHtmlParser::AddTagHandler}\label{wxhtmlparseraddtaghandler}
63
64 \func{virtual void}{AddTagHandler}{\param{wxHtmlTagHandler }{*handler}}
65
66 Adds handler to the internal list (\& hash table) of handlers. This
67 method should not be called directly by user but rather by derived class'
68 constructor.
69
70 This adds the handler to this {\bf instance} of wxHtmlParser, not to
71 all objects of this class! (Static front-end to AddTagHandler is provided
72 by wxHtmlWinParser).
73
74 All handlers are deleted on object deletion.
75
76 \membersection{wxHtmlParser::AddText}\label{wxhtmlparseraddword}
77
78 \func{virtual void}{AddWord}{\param{const char* }{txt}}
79
80 Must be overwriten in derived class.
81
82 This method is called by \helpref{DoParsing}{wxhtmlparserdoparsing}
83 each time a part of text is parsed. {\it txt} is NOT only one word, it is
84 substring of input. It is not formatted or preprocessed (so white spaces are
85 unmodified).
86
87 \membersection{wxHtmlParser::DoParsing}\label{wxhtmlparserdoparsing}
88
89 \func{void}{DoParsing}{\param{int }{begin\_pos}, \param{int }{end\_pos}}
90
91 \func{void}{DoParsing}{\void}
92
93 Parses the m\_Source from begin\_pos to end\_pos-1.
94 (in noparams version it parses whole m\_Source)
95
96 \membersection{wxHtmlParser::DoneParser}\label{wxhtmlparserdoneparser}
97
98 \func{virtual void}{DoneParser}{\void}
99
100 This must be called after DoParsing().
101
102 \membersection{wxHtmlParser::GetFS}\label{wxhtmlparsergetfs}
103
104 \constfunc{wxFileSystem*}{GetFS}{\void}
105
106 Returns pointer to the file system. Because each tag handler has
107 reference to it's parent parser it can easily request the file by
108 calling
109
110 \begin{verbatim}
111 wxFSFile *f = m_Parser -> GetFS() -> OpenFile("image.jpg");
112 \end{verbatim}
113
114 \membersection{wxHtmlParser::GetProduct}\label{wxhtmlparsergetproduct}
115
116 \func{virtual wxObject*}{GetProduct}{\void}
117
118 Returns product of parsing. Returned value is result of parsing
119 of the document. The type of this result depends on internal
120 representation in derived parser (but it must be derived from wxObject!).
121
122 See wxHtmlWinParser for details.
123
124 \membersection{wxHtmlParser::GetSource}\label{wxhtmlparsergetsource}
125
126 \func{wxString*}{GetSource}{\void}
127
128 Returns pointer to the source being parsed.
129
130
131 \membersection{wxHtmlParser::InitParser}\label{wxhtmlparserinitparser}
132
133 \func{virtual void}{InitParser}{\param{const wxString\& }{source}}
134
135 Setups the parser for parsing the {\it source} string. (Should be overriden
136 in derived class)
137
138 \membersection{wxHtmlParser::Parse}\label{wxhtmlparserparse}
139
140 \func{wxObject*}{Parse}{\param{const wxString\& }{source}}
141
142 Proceeds parsing of the document. This is end-user method. You can simply
143 call it when you need to obtain parsed output (which is parser-specific)
144
145 The method does these things:
146
147 \begin{enumerate}\itemsep=0pt
148 \item calls \helpref{InitParser(source)}{wxhtmlparserinitparser}
149 \item calls \helpref{DoParsing}{wxhtmlparserdoparsing}
150 \item calls \helpref{GetProduct}{wxhtmlparsergetproduct}
151 \item calls \helpref{DoneParser}{wxhtmlparserdoneparser}
152 \item returns value returned by GetProduct
153 \end{enumerate}
154
155 You shouldn't use InitParser, DoParsing, GetProduct or DoneParser directly.
156
157
158
159 \membersection{wxHtmlParser::PushTagHandler}\label{wxhtmlparserpushtaghandler}
160
161 \func{void}{PushTagHandler}{\param{wxHtmlTagHandler* }{handler}, \param{wxString }{tags}}
162
163 Forces the handler to handle additional tags
164 (not returned by \helpref{GetSupportedTags}{wxhtmltaghandlergetsupportedtags}).
165 The handler should already be added to this parser.
166
167 \wxheading{Parameters}
168
169 \docparam{handler}{the handler}
170 \docparam{tags}{List of tags (in same format as GetSupportedTags's return value). The parser
171 will redirect these tags to {\it handler} (until call to \helpref{PopTagHandler}{wxhtmlparserpoptaghandler}). }
172
173 \wxheading{Example}
174
175 Imagine you want to parse following pseudo-html structure:
176
177 \begin{verbatim}
178 <myitems>
179 <param name="one" value="1">
180 <param name="two" value="2">
181 </myitems>
182
183 <execute>
184 <param program="text.exe">
185 </execute>
186 \end{verbatim}
187
188 It is obvious that you cannot use only one tag handler for <param> tag.
189 Instead you must use context-sensitive handlers for <param> inside <myitems>
190 and <param> inside <execute>.
191
192 This is the prefered solution:
193
194 \begin{verbatim}
195 TAG_HANDLER_BEGIN(MYITEM, "MYITEMS")
196 TAG_HANDLER_PROC(tag)
197 {
198 // ...something...
199
200 m_Parser -> PushTagHandler(this, "PARAM");
201 ParseInner(tag);
202 m_Parser -> PopTagHandler();
203
204 // ...something...
205 }
206 TAG_HANDLER_END(MYITEM)
207 \end{verbatim}
208
209
210 \membersection{wxHtmlParser::PopTagHandler}\label{wxhtmlparserpoptaghandler}
211
212 \func{void}{PopTagHandler}{\void}
213
214 Restores parser's state before last call to
215 \helpref{PushTagHandler}{wxhtmlparserpushtaghandler}.
216
217
218 \membersection{wxHtmlParser::SetFS}\label{wxhtmlparsersetfs}
219
220 \func{void}{SetFS}{\param{wxFileSystem }{*fs}}
221
222 Sets the virtual file system that will be used to request additional
223 files. (For example {\tt <IMG>} tag handler requests wxFSFile with the
224 image data.)
225