You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
yacy_search_server/htroot/robots.java

76 lines
4.0 KiB

import java.io.File;
import java.util.ArrayList;
import de.anomic.http.httpRequestHeader;
import de.anomic.http.httpdRobotsTxtConfig;
import de.anomic.plasma.plasmaSwitchboard;
import de.anomic.plasma.plasmaSwitchboardConstants;
import de.anomic.server.serverObjects;
import de.anomic.server.serverSwitch;
import de.anomic.server.servletProperties;
public class robots {
public static servletProperties respond(final httpRequestHeader header, final serverObjects post, final serverSwitch<?> env) {
final servletProperties prop = new servletProperties();
final httpdRobotsTxtConfig rbc = ((plasmaSwitchboard)env).robotstxtConfig;
if (rbc.isAllDisallowed()) {
prop.put(httpdRobotsTxtConfig.ALL, 1);
} else {
* Complete number localization and provide a more reasonable interface to serverObjects: - put(key, value) methods are now used if a value added to the map should be kept as it is. Numbers are transformed (but not formatted) to an equivalent String representation. - putASIS(...) have been removed, now done with simple put(...) (see above). - puNum(...) can be used for number values which should be stored in a formatted way, either depending on the current locale setting for yacy (default) or in a "none" locale (see javadocs and setLocalize()). - putHTML(...) escapes special characters into corresponding HTML enities ('<' => '&lt;') which was done with put(...) before and so was called too often, becauses it is necessary only for very few cases. Additionally there is a "forXML" mode which only replaces < > & ". In short: Use put(...) for almost everything, use putXY(...) if you need some special transformation of the value. A few bugs have been fixed as well, and there should be a small performance improvement for complex pages with a lot of values. * added additional Sum/Avg rows to access tracker pages, see http://forum.yacy-websuche.de/viewtopic.php?f=5&t=456 * removed duplicate code (mostly related to the big changes above). TODO: - make sure, number formats work as expected _everywhere_, report overseen stuff http://forum.yacy-websuche.de/viewtopic.php?f=5&t=437 - probably a good idea to add special putDate() methods as they are used in many pages and create duplicated formatting code + maybe some centralized handling for memory value formatting. - further improve the speed of page creation for the WatchCrawler. git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4178 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
if (rbc.isBlogDisallowed()) prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.BLOG, "1");
if (rbc.isBookmarksDisallowed()) prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.BOOKMARKS, "1");
if (rbc.isFileshareDisallowed()) prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.FILESHARE, "1");
if (rbc.isHomepageDisallowed()) prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.HOMEPAGE, "1");
if (rbc.isNetworkDisallowed()) prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.NETWORK, "1");
if (rbc.isNewsDisallowed()) prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.NEWS, "1");
if (rbc.isStatusDisallowed()) prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.STATUS, "1");
if (rbc.isSurftipsDisallowed()) prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.SURFTIPS, "1");
if (rbc.isWikiDisallowed()) prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.WIKI, "1");
if (rbc.isProfileDisallowed()) prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.PROFILE, "1");
if (rbc.isLockedDisallowed() || rbc.isDirsDisallowed()) {
final ArrayList<String>[] p = getFiles(env.getConfig(plasmaSwitchboardConstants.HTROOT_PATH, plasmaSwitchboardConstants.HTROOT_PATH_DEFAULT));
if (rbc.isLockedDisallowed()) {
prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.LOCKED, p[0].size());
for (int i=0; i<p[0].size(); i++)
prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.LOCKED + "_" + i + "_page", p[0].get(i));
}
if (rbc.isDirsDisallowed()) {
prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.DIRS, p[1].size());
for (int i=0; i<p[1].size(); i++)
prop.put(httpdRobotsTxtConfig.ALL + "_" + httpdRobotsTxtConfig.DIRS + "_" + i + "_dir", p[1].get(i));
}
}
}
return prop;
}
@SuppressWarnings("unchecked")
private static ArrayList<String>[] getFiles(final String htrootPath) {
final File htroot = new File(htrootPath);
if (!htroot.exists()) return null;
final ArrayList<String> htrootFiles = new ArrayList<String>();
final ArrayList<String> htrootDirs = new ArrayList<String>();
final String[] htroots = htroot.list();
File file;
for (int i=0, dot; i<htroots.length; i++) {
if (htroots[i].equals("www")) continue;
file = new File(htroot, htroots[i]);
if (file.isDirectory()) {
htrootDirs.add(htroots[i]);
} else if (
((dot = htroots[i].lastIndexOf('.')) < 2 ||
htroots[i].charAt(dot - 2) == '_' && htroots[i].charAt(dot - 1) == 'p') &&
!(htroots[i].endsWith("java") || htroots[i].endsWith("class"))
) {
htrootFiles.add(htroots[i]);
}
}
return new ArrayList[] { htrootFiles, htrootDirs };
}
}