]>
Commit | Line | Data |
---|---|---|
5526e819 | 1 | ///////////////////////////////////////////////////////////////////////////// |
69941f05 | 2 | // Name: htmlfilt.cpp |
5526e819 VS |
3 | // Purpose: wxHtmlFilter - input filter for translating into HTML format |
4 | // Author: Vaclav Slavik | |
69941f05 | 5 | // RCS-ID: $Id$ |
5526e819 | 6 | // Copyright: (c) 1999 Vaclav Slavik |
65571936 | 7 | // Licence: wxWindows licence |
5526e819 VS |
8 | ///////////////////////////////////////////////////////////////////////////// |
9 | ||
10 | ||
14f355c2 | 11 | #if defined(__GNUG__) && !defined(NO_GCC_PRAGMA) |
1aedb1dd | 12 | #pragma implementation "htmlfilt.h" |
5526e819 VS |
13 | #endif |
14 | ||
4dcaf11a | 15 | #include "wx/wxprec.h" |
5526e819 | 16 | |
314260fb | 17 | #include "wx/defs.h" |
f6bcfd97 | 18 | #if wxUSE_HTML && wxUSE_STREAMS |
5526e819 | 19 | |
2b5f62a0 | 20 | #ifdef __BORLANDC__ |
5526e819 VS |
21 | #pragma hdrstop |
22 | #endif | |
23 | ||
24 | #ifndef WXPRECOMP | |
04dbb646 VZ |
25 | #include "wx/log.h" |
26 | #include "wx/intl.h" | |
5526e819 VS |
27 | #endif |
28 | ||
2b5f62a0 | 29 | #include "wx/strconv.h" |
69941f05 | 30 | #include "wx/html/htmlfilt.h" |
4dcaf11a | 31 | #include "wx/html/htmlwin.h" |
5526e819 | 32 | |
eb37e1d2 | 33 | // utility function: read a wxString from a wxInputStream |
2b5f62a0 | 34 | static void ReadString(wxString& str, wxInputStream* s, wxMBConv& conv) |
eb37e1d2 MB |
35 | { |
36 | size_t streamSize = s->GetSize(); | |
37 | ||
2b5f62a0 | 38 | if (streamSize == ~(size_t)0) |
eb37e1d2 MB |
39 | { |
40 | const size_t bufSize = 4095; | |
41 | char buffer[bufSize+1]; | |
42 | size_t lastRead; | |
43 | ||
44 | do | |
45 | { | |
46 | s->Read(buffer, bufSize); | |
47 | lastRead = s->LastRead(); | |
48 | buffer[lastRead] = 0; | |
2b5f62a0 | 49 | str.Append(wxString(buffer, conv)); |
eb37e1d2 | 50 | } |
2b5f62a0 | 51 | while (lastRead == bufSize); |
eb37e1d2 MB |
52 | } |
53 | else | |
54 | { | |
55 | char* src = new char[streamSize+1]; | |
56 | s->Read(src, streamSize); | |
57 | src[streamSize] = 0; | |
2b5f62a0 VZ |
58 | str = wxString(src, conv); |
59 | delete[] src; | |
eb37e1d2 MB |
60 | } |
61 | } | |
5526e819 VS |
62 | |
63 | /* | |
64 | ||
65 | There is code for several default filters: | |
66 | ||
67 | */ | |
68 | ||
69 | IMPLEMENT_ABSTRACT_CLASS(wxHtmlFilter, wxObject) | |
70 | ||
71 | //-------------------------------------------------------------------------------- | |
72 | // wxHtmlFilterPlainText | |
73 | // filter for text/plain or uknown | |
74 | //-------------------------------------------------------------------------------- | |
75 | ||
76 | IMPLEMENT_DYNAMIC_CLASS(wxHtmlFilterPlainText, wxHtmlFilter) | |
77 | ||
a4c97004 | 78 | bool wxHtmlFilterPlainText::CanRead(const wxFSFile& WXUNUSED(file)) const |
5526e819 | 79 | { |
d1da8872 | 80 | return true; |
5526e819 VS |
81 | } |
82 | ||
83 | ||
84 | ||
420ec58a | 85 | wxString wxHtmlFilterPlainText::ReadFile(const wxFSFile& file) const |
5526e819 VS |
86 | { |
87 | wxInputStream *s = file.GetStream(); | |
5526e819 VS |
88 | wxString doc, doc2; |
89 | ||
90 | if (s == NULL) return wxEmptyString; | |
2b5f62a0 | 91 | ReadString(doc, s, wxConvISO8859_1); |
5526e819 | 92 | |
d1da8872 WS |
93 | doc.Replace(wxT("&"), wxT("&"), true); |
94 | doc.Replace(wxT("<"), wxT("<"), true); | |
95 | doc.Replace(wxT(">"), wxT(">"), true); | |
2b5f62a0 | 96 | doc2 = wxT("<HTML><BODY><PRE>\n") + doc + wxT("\n</PRE></BODY></HTML>"); |
5526e819 VS |
97 | return doc2; |
98 | } | |
99 | ||
100 | ||
101 | ||
102 | ||
103 | ||
104 | //-------------------------------------------------------------------------------- | |
105 | // wxHtmlFilterImage | |
106 | // filter for image/* | |
107 | //-------------------------------------------------------------------------------- | |
108 | ||
109 | class wxHtmlFilterImage : public wxHtmlFilter | |
110 | { | |
111 | DECLARE_DYNAMIC_CLASS(wxHtmlFilterImage) | |
112 | ||
113 | public: | |
420ec58a VS |
114 | virtual bool CanRead(const wxFSFile& file) const; |
115 | virtual wxString ReadFile(const wxFSFile& file) const; | |
5526e819 VS |
116 | }; |
117 | ||
118 | IMPLEMENT_DYNAMIC_CLASS(wxHtmlFilterImage, wxHtmlFilter) | |
119 | ||
120 | ||
121 | ||
420ec58a | 122 | bool wxHtmlFilterImage::CanRead(const wxFSFile& file) const |
5526e819 | 123 | { |
0413cec5 | 124 | return (file.GetMimeType().Left(6) == wxT("image/")); |
5526e819 VS |
125 | } |
126 | ||
127 | ||
128 | ||
420ec58a | 129 | wxString wxHtmlFilterImage::ReadFile(const wxFSFile& file) const |
5526e819 | 130 | { |
2b5f62a0 VZ |
131 | wxString res = wxT("<HTML><BODY><IMG SRC=\"") + file.GetLocation() + wxT("\"></BODY></HTML>"); |
132 | return res; | |
5526e819 VS |
133 | } |
134 | ||
135 | ||
136 | ||
137 | ||
138 | //-------------------------------------------------------------------------------- | |
2b5f62a0 VZ |
139 | // wxHtmlFilterHTML |
140 | // filter for text/html | |
5526e819 VS |
141 | //-------------------------------------------------------------------------------- |
142 | ||
5526e819 VS |
143 | |
144 | IMPLEMENT_DYNAMIC_CLASS(wxHtmlFilterHTML, wxHtmlFilter) | |
145 | ||
420ec58a | 146 | bool wxHtmlFilterHTML::CanRead(const wxFSFile& file) const |
5526e819 | 147 | { |
f61815af GL |
148 | // return (file.GetMimeType() == "text/html"); |
149 | // This is true in most case but some page can return: | |
150 | // "text/html; char-encoding=...." | |
151 | // So we use Find instead | |
77611ad4 | 152 | return (file.GetMimeType().Find(wxT("text/html")) == 0); |
5526e819 VS |
153 | } |
154 | ||
155 | ||
156 | ||
420ec58a | 157 | wxString wxHtmlFilterHTML::ReadFile(const wxFSFile& file) const |
5526e819 VS |
158 | { |
159 | wxInputStream *s = file.GetStream(); | |
5526e819 VS |
160 | wxString doc; |
161 | ||
04dbb646 | 162 | if (s == NULL) |
f3c82859 | 163 | { |
f6bcfd97 | 164 | wxLogError(_("Cannot open HTML document: %s"), file.GetLocation().c_str()); |
f3c82859 VS |
165 | return wxEmptyString; |
166 | } | |
5526e819 | 167 | |
d1da8872 | 168 | // NB: We convert input file to wchar_t here in Unicode mode, based on |
2b5f62a0 VZ |
169 | // either Content-Type header or <meta> tags. In ANSI mode, we don't |
170 | // do it as it is done by wxHtmlParser (for this reason, we add <meta> | |
171 | // tag if we used Content-Type header). | |
172 | #if wxUSE_UNICODE | |
d1da8872 | 173 | int charsetPos; |
2b5f62a0 VZ |
174 | if ((charsetPos = file.GetMimeType().Find(_T("; charset="))) != wxNOT_FOUND) |
175 | { | |
176 | wxString charset = file.GetMimeType().Mid(charsetPos + 10); | |
177 | wxCSConv conv(charset); | |
178 | ReadString(doc, s, conv); | |
179 | } | |
180 | else | |
181 | { | |
182 | wxString tmpdoc; | |
183 | ReadString(tmpdoc, s, wxConvISO8859_1); | |
184 | wxString charset = wxHtmlParser::ExtractCharsetInformation(tmpdoc); | |
185 | if (charset.empty()) | |
186 | doc = tmpdoc; | |
187 | else | |
188 | { | |
189 | wxCSConv conv(charset); | |
190 | doc = wxString(tmpdoc.mb_str(wxConvISO8859_1), conv); | |
191 | } | |
192 | } | |
193 | #else // !wxUSE_UNICODE | |
194 | ReadString(doc, s, wxConvLibc); | |
04dbb646 | 195 | // add meta tag if we obtained this through http: |
2b5f62a0 | 196 | if (!file.GetMimeType().empty()) |
981e62aa | 197 | { |
2b5f62a0 VZ |
198 | wxString hdr; |
199 | wxString mime = file.GetMimeType(); | |
200 | hdr.Printf(_T("<meta http-equiv=\"Content-Type\" content=\"%s\">"), mime.c_str()); | |
201 | return hdr+doc; | |
981e62aa | 202 | } |
2b5f62a0 | 203 | #endif |
981e62aa | 204 | |
3ca6a5f0 | 205 | return doc; |
5526e819 VS |
206 | } |
207 | ||
208 | ||
209 | ||
210 | ||
211 | ///// Module: | |
212 | ||
213 | class wxHtmlFilterModule : public wxModule | |
214 | { | |
215 | DECLARE_DYNAMIC_CLASS(wxHtmlFilterModule) | |
216 | ||
217 | public: | |
218 | virtual bool OnInit() | |
219 | { | |
220 | wxHtmlWindow::AddFilter(new wxHtmlFilterHTML); | |
221 | wxHtmlWindow::AddFilter(new wxHtmlFilterImage); | |
d1da8872 | 222 | return true; |
5526e819 VS |
223 | } |
224 | virtual void OnExit() {} | |
225 | }; | |
226 | ||
227 | IMPLEMENT_DYNAMIC_CLASS(wxHtmlFilterModule, wxModule) | |
228 | ||
8dd71e2b | 229 | #endif |