1
/* This file is part of Strigi Desktop Search
3
* Copyright (C) 2007 Jos van den Oever <jos@vandenoever.info>
5
* This library is free software; you can redistribute it and/or
6
* modify it under the terms of the GNU Library General Public
7
* License as published by the Free Software Foundation; either
8
* version 2 of the License, or (at your option) any later version.
10
* This library is distributed in the hope that it will be useful,
11
* but WITHOUT ANY WARRANTY; without even the implied warranty of
12
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13
* Library General Public License for more details.
15
* You should have received a copy of the GNU Library General Public License
16
* along with this library; see the file COPYING.LIB. If not, write to
17
* the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
18
* Boston, MA 02110-1301, USA.
21
#ifndef STRIGI_HTMLSAXANALYZER
22
#define STRIGI_HTMLSAXANALYZER
24
#include <strigi/strigiconfig.h>
25
#include <strigi/streamsaxanalyzer.h>
29
class StreamSaxAnalyzer;
30
class HtmlSaxAnalyzer : public StreamSaxAnalyzer {
32
const char* name() const { return "HtmlSaxAnalyzer"; }
33
void startAnalysis(AnalysisResult*);
34
void endAnalysis(bool complete);
35
void startElement(const char* localname, const char* prefix,
36
const char* uri, int nb_namespaces, const char** namespaces,
37
int nb_attributes,int nb_defaulted,const char** attributes);
38
void endElement(const char* localname, const char* prefix,
40
void characters(const char* data, uint32_t length);
41
bool isReadyWithStream();
43
class HtmlSaxAnalyzerFactory : public StreamSaxAnalyzerFactory {
44
const char* name() const {
45
return "HtmlSaxAnalyzer";
47
void registerFields(Strigi::FieldRegister&) {
49
StreamSaxAnalyzer* newInstance() const {
50
return new HtmlSaxAnalyzer();