]> git.saurik.com Git - wxWidgets.git/blob - src/html/htmlpars.cpp
Unicode overview added
[wxWidgets.git] / src / html / htmlpars.cpp
1 /////////////////////////////////////////////////////////////////////////////
2 // Name: htmlpars.cpp
3 // Purpose: wxHtmlParser class (generic parser)
4 // Author: Vaclav Slavik
5 // RCS-ID: $Id$
6 // Copyright: (c) 1999 Vaclav Slavik
7 // Licence: wxWindows Licence
8 /////////////////////////////////////////////////////////////////////////////
9
10
11 #ifdef __GNUG__
12 #pragma implementation
13 #endif
14
15 #include <wx/wxprec.h>
16
17 #include "wx/defs.h"
18 #if wxUSE_HTML
19
20 #ifdef __BORDLANDC__
21 #pragma hdrstop
22 #endif
23
24 #ifndef WXPRECOMP
25 #include <wx/wx.h>
26 #endif
27
28 #include "wx/tokenzr.h"
29 #include "wx/wfstream.h"
30 #include "wx/url.h"
31 #include "wx/html/htmldefs.h"
32 #include "wx/html/htmlpars.h"
33
34
35
36 //-----------------------------------------------------------------------------
37 // wxHtmlParser
38 //-----------------------------------------------------------------------------
39
40 IMPLEMENT_ABSTRACT_CLASS(wxHtmlParser,wxObject)
41
42
43 wxObject* wxHtmlParser::Parse(const wxString& source)
44 {
45 wxObject *result;
46
47 InitParser(source);
48 DoParsing();
49 result = GetProduct();
50 DoneParser();
51 return result;
52 }
53
54
55
56 void wxHtmlParser::InitParser(const wxString& source)
57 {
58 m_Source = source;
59 m_Cache = new wxHtmlTagsCache(m_Source);
60 }
61
62
63
64 void wxHtmlParser::DoneParser()
65 {
66 delete m_Cache;
67 m_Cache = NULL;
68 }
69
70
71
72 #define HTML_MAX_BUFLEN 1024
73
74 void wxHtmlParser::DoParsing(int begin_pos, int end_pos)
75 {
76 char temp[HTML_BUFLEN], c;
77 int i;
78 int templen;
79
80 templen = 0;
81 i = begin_pos;
82
83 while (i < end_pos) {
84 c = m_Source[i];
85
86 // continue building word:
87 if (c != '<') {
88 temp[templen++] = c;
89 if (templen == HTML_BUFLEN-1) {
90 temp[templen] = 0;
91 AddText(temp);
92 templen = 0;
93 }
94 i++;
95 }
96
97 else if (c == '<') {
98 wxHtmlTag tag(m_Source, i, end_pos, m_Cache);
99
100 if (templen) {
101 temp[templen] = 0;
102 AddText(temp);
103 templen = 0;
104 }
105 AddTag(tag);
106 if (tag.HasEnding()) i = tag.GetEndPos2();
107 else i = tag.GetBeginPos();
108 }
109 }
110
111 if (templen) { // last word of block :-(
112 temp[templen] = 0;
113 AddText(temp);
114 }
115 }
116
117
118
119 void wxHtmlParser::AddTag(const wxHtmlTag& tag)
120 {
121 wxHtmlTagHandler *h;
122 bool inner = FALSE;
123
124 h = (wxHtmlTagHandler*) m_HandlersHash.Get(tag.GetName());
125 if (h)
126 inner = h -> HandleTag(tag);
127 if (!inner) {
128 if (tag.HasEnding())
129 DoParsing(tag.GetBeginPos(), tag.GetEndPos1());
130 }
131 }
132
133
134
135 void wxHtmlParser::AddTagHandler(wxHtmlTagHandler *handler)
136 {
137 wxString s(handler -> GetSupportedTags());
138 wxStringTokenizer tokenizer(s, ", ");
139
140 #if (wxVERSION_NUMBER < 2100)
141 while (tokenizer.HasMoreToken())
142 #else
143 while (tokenizer.HasMoreTokens())
144 #endif
145 m_HandlersHash.Put(tokenizer.NextToken(), handler);
146
147 if (m_HandlersList.IndexOf(handler) == wxNOT_FOUND)
148 m_HandlersList.Append(handler);
149
150 handler -> SetParser(this);
151 }
152
153
154
155 wxHtmlParser::~wxHtmlParser()
156 {
157 m_HandlersHash.Clear();
158 m_HandlersList.DeleteContents(TRUE);
159 m_HandlersList.Clear();
160 }
161
162
163
164 //-----------------------------------------------------------------------------
165 // wxHtmlTagHandler
166 //-----------------------------------------------------------------------------
167
168 IMPLEMENT_ABSTRACT_CLASS(wxHtmlTagHandler,wxObject)
169
170 #endif