mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-21 00:00:13 +02:00
fed26f33a8
to support the new time parser and search functions in YaCy a high precision detection of date and time on the day is necessary. That requires that the time zone of the document content and the time zone of the user, doing a search, is detected. The time zone of the search request is done automatically using the browsers time zone offset which is delivered to the search request automatically and invisible to the user. The time zone for the content of web pages cannot be detected automatically and must be an attribute of crawl starts. The advanced crawl start now provides an input field to set the time zone in minutes as an offset number. All parsers must get a time zone offset passed, so this required the change of the parser java api. A lot of other changes had been made which corrects the wrong handling of dates in YaCy which was to add a correction based on the time zone of the server. Now no correction is added and all dates in YaCy are UTC/GMT time zone, a normalized time zone for all peers.
79 lines
3.0 KiB
Java
79 lines
3.0 KiB
Java
|
|
|
|
import java.io.IOException;
|
|
import java.text.ParseException;
|
|
import java.util.Date;
|
|
import java.util.List;
|
|
|
|
import net.yacy.cora.date.ISO8601Formatter;
|
|
import net.yacy.cora.order.Digest;
|
|
import net.yacy.cora.protocol.RequestHeader;
|
|
import net.yacy.data.BookmarksDB;
|
|
import net.yacy.search.Switchboard;
|
|
import net.yacy.server.serverObjects;
|
|
import net.yacy.server.serverSwitch;
|
|
|
|
public class get {
|
|
public static serverObjects respond(final RequestHeader header, final serverObjects post, final serverSwitch env) {
|
|
// return variable that accumulates replacements
|
|
final Switchboard switchboard = (Switchboard) env;
|
|
final boolean isAdmin=switchboard.verifyAuthentication(header);
|
|
final serverObjects prop = new serverObjects();
|
|
String tag = null;
|
|
final String date;
|
|
//String url=""; //urlfilter not yet implemented
|
|
|
|
if (post != null && post.containsKey("tag")) {
|
|
tag = post.get("tag");
|
|
}
|
|
if (post != null && post.containsKey("date")) {
|
|
date = post.get("date");
|
|
} else {
|
|
date = ISO8601Formatter.FORMATTER.format();
|
|
}
|
|
|
|
// if an extended xml should be used
|
|
final boolean extendedXML = (post != null && post.containsKey("extendedXML"));
|
|
|
|
int count=0;
|
|
|
|
Date parsedDate = null;
|
|
try {
|
|
parsedDate = ISO8601Formatter.FORMATTER.parse(date, 0).getTime();
|
|
} catch (final ParseException e) {
|
|
parsedDate = new Date();
|
|
}
|
|
|
|
final List<String> bookmark_hashes = switchboard.bookmarksDB.getDate(Long.toString(parsedDate.getTime())).getBookmarkList();
|
|
BookmarksDB.Bookmark bookmark = null;
|
|
for (final String bookmark_hash : bookmark_hashes){
|
|
try {
|
|
bookmark=switchboard.bookmarksDB.getBookmark(bookmark_hash);
|
|
if (ISO8601Formatter.FORMATTER.format(new Date(bookmark.getTimeStamp())).equals(date) &&
|
|
tag==null || bookmark.getTags().contains(tag) &&
|
|
isAdmin || bookmark.getPublic()){
|
|
prop.putHTML("posts_"+count+"_url", bookmark.getUrl());
|
|
prop.putHTML("posts_"+count+"_title", bookmark.getTitle());
|
|
prop.putHTML("posts_"+count+"_description", bookmark.getDescription());
|
|
prop.put("posts_"+count+"_md5", Digest.encodeMD5Hex(bookmark.getUrl()));
|
|
prop.put("posts_"+count+"_time", date);
|
|
prop.putHTML("posts_"+count+"_tags", bookmark.getTagsString().replaceAll(","," "));
|
|
|
|
// additional XML tags
|
|
prop.put("posts_"+count+"_isExtended",extendedXML ? "1" : "0");
|
|
if (extendedXML) {
|
|
prop.put("posts_"+count+"_isExtended_private", Boolean.toString(!bookmark.getPublic()));
|
|
}
|
|
count++;
|
|
}
|
|
} catch (final IOException e) {
|
|
}
|
|
}
|
|
prop.put("posts", count);
|
|
|
|
// return rewrite properties
|
|
return prop;
|
|
}
|
|
|
|
}
|