2 * Rhynodge - HtmlFilter.java - Copyright © 2013 David Roden
4 * This program is free software: you can redistribute it and/or modify
5 * it under the terms of the GNU General Public License as published by
6 * the Free Software Foundation, either version 3 of the License, or
7 * (at your option) any later version.
9 * This program is distributed in the hope that it will be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 * GNU General Public License for more details.
14 * You should have received a copy of the GNU General Public License
15 * along with this program. If not, see <http://www.gnu.org/licenses/>.
18 package net.pterodactylus.rhynodge.filters;
20 import static com.google.common.base.Preconditions.checkState;
22 import net.pterodactylus.rhynodge.Filter;
23 import net.pterodactylus.rhynodge.State;
24 import net.pterodactylus.rhynodge.states.FailedState;
25 import net.pterodactylus.rhynodge.states.HtmlState;
26 import net.pterodactylus.rhynodge.states.HttpState;
28 import org.apache.log4j.Logger;
29 import org.jsoup.Jsoup;
30 import org.jsoup.nodes.Document;
33 * {@link Filter} that converts a {@link HttpState} into an {@link HtmlState}.
35 * @author <a href="mailto:bombe@pterodactylus.net">David ‘Bombe’ Roden</a>
37 public class HtmlFilter implements Filter {
39 private static final Logger logger = Logger.getLogger(HtmlFilter.class);
45 public State filter(State state) {
46 if (!state.success()) {
47 return FailedState.from(state);
49 checkState(state instanceof HttpState, "state is not a HttpState but a %s", state.getClass().getName());
50 logger.trace(String.format("Got HTML: %s, %s", ((HttpState) state).contentType(), ((HttpState) state).content()));
51 Document document = Jsoup.parse(((HttpState) state).content(), ((HttpState) state).uri());
52 return new HtmlState(((HttpState) state).uri(), document);