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.
151 lines
7.2 KiB
Java
151 lines
7.2 KiB
Java
// timeline.java
|
|
// (C) 2009 by Michael Peter Christen; mc@yacy.net, Frankfurt a. M., Germany
|
|
// first published 27.02.2009 on http://yacy.net
|
|
//
|
|
// This is a part of YaCy, a peer-to-peer based web search engine
|
|
//
|
|
// $LastChangedDate: 2009-02-10 01:06:59 +0100 (Di, 10 Feb 2009) $
|
|
// $LastChangedRevision: 5586 $
|
|
// $LastChangedBy: orbiter $
|
|
//
|
|
// LICENSE
|
|
//
|
|
// This program is free software; you can redistribute it and/or modify
|
|
// it under the terms of the GNU General Public License as published by
|
|
// the Free Software Foundation; either version 2 of the License, or
|
|
// (at your option) any later version.
|
|
//
|
|
// This program is distributed in the hope that it will be useful,
|
|
// but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
// GNU General Public License for more details.
|
|
//
|
|
// You should have received a copy of the GNU General Public License
|
|
// along with this program; if not, write to the Free Software
|
|
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
|
|
|
import java.text.ParseException;
|
|
import java.util.ArrayList;
|
|
import java.util.Date;
|
|
import java.util.HashMap;
|
|
import java.util.Iterator;
|
|
import java.util.List;
|
|
import java.util.Map;
|
|
import java.util.TreeMap;
|
|
|
|
import net.yacy.cora.date.AbstractFormatter;
|
|
import net.yacy.cora.date.GenericFormatter;
|
|
import net.yacy.cora.protocol.RequestHeader;
|
|
import net.yacy.cora.sorting.OrderedScoreMap;
|
|
import net.yacy.cora.util.CommonPattern;
|
|
import net.yacy.search.EventTracker.Event;
|
|
import net.yacy.search.EventTracker;
|
|
import net.yacy.search.query.AccessTracker;
|
|
import net.yacy.server.serverObjects;
|
|
import net.yacy.server.serverSwitch;
|
|
|
|
public final class timeline_p {
|
|
|
|
// example:
|
|
// http://localhost:8090/api/timeline_p.xml?from=20140601000000&to=20140629000000&data=queries&head=2&period=6h
|
|
|
|
public static serverObjects respond(@SuppressWarnings("unused") final RequestHeader header, final serverObjects post, final serverSwitch env) {
|
|
final serverObjects prop = new serverObjects();
|
|
if ((post == null) || (env == null)) return prop;
|
|
|
|
// get type of data to be listed in the timeline
|
|
int maxeventsperperiod = post.getInt("head", 1); // the maximum number of events per period
|
|
String period = post.get("period", ""); // must be an integer with a character c at the end, c = Y|M|d|h|m|s
|
|
long periodlength = 0;
|
|
if (period.length() > 0) {
|
|
char c = period.charAt(period.length() - 1);
|
|
long p = Long.parseLong(period.substring(0, period.length() - 1));
|
|
if (c == 's') periodlength = p * AbstractFormatter.secondMillis;
|
|
else if (c == 'm') periodlength = p * AbstractFormatter.minuteMillis;
|
|
else if (c == 'h') periodlength = p * AbstractFormatter.hourMillis;
|
|
else if (c == 'd') periodlength = p * AbstractFormatter.dayMillis;
|
|
else if (c == 'M') periodlength = p * AbstractFormatter.monthAverageMillis;
|
|
else if (c == 'Y' || c == 'y') periodlength = p * AbstractFormatter.normalyearMillis;
|
|
else periodlength = 0;
|
|
}
|
|
final String[] data = CommonPattern.COMMA.split(post.get("data", "")); // a string of word hashes that shall be searched and combined
|
|
Map<String, List<EventTracker.Event>> proc = new HashMap<>();
|
|
for (String s: data) if (s.length() > 0) proc.put(s, null);
|
|
|
|
// get a time period
|
|
Date fromDate = new Date(0);
|
|
Date toDate = new Date();
|
|
try {fromDate = GenericFormatter.SHORT_SECOND_FORMATTER.parse(post.get("from", "20031215182700"), 0).getTime();} catch (ParseException e) {}
|
|
try {toDate = GenericFormatter.SHORT_SECOND_FORMATTER.parse(post.get("to", GenericFormatter.SHORT_SECOND_FORMATTER.format(new Date())), 0).getTime();} catch (ParseException e) {}
|
|
|
|
// get latest dump;
|
|
AccessTracker.dumpLog();
|
|
|
|
// fill proc with events from the given data and time period
|
|
if (proc.containsKey("queries")) {
|
|
List<EventTracker.Event> events = AccessTracker.readLog(AccessTracker.getDumpFile(), fromDate, toDate);
|
|
proc.put("queries", events);
|
|
}
|
|
|
|
// mix all events into one event list
|
|
TreeMap<String, EventTracker.Event> eax = new TreeMap<>();
|
|
for (List<EventTracker.Event> events: proc.values()) if (events != null) {
|
|
for (EventTracker.Event event: events) eax.put(event.getFormattedDate(), event);
|
|
}
|
|
proc.clear(); // we don't need that here any more
|
|
List<EventTracker.Event> ea = new ArrayList<>();
|
|
for (Event event: eax.values()) ea.add(event);
|
|
|
|
if (periodlength > 0 && ea.size() > 0) {
|
|
// create a statistical analysis; step by chunks of periodlength entries
|
|
Event firstEvent = ea.iterator().next();
|
|
long startDate = fromDate.getTime();
|
|
//TreeMap<Date, EventTracker.Event>
|
|
OrderedScoreMap<String> accumulation = new OrderedScoreMap<>(null);
|
|
List<EventTracker.Event> eap = new ArrayList<>();
|
|
String limit = GenericFormatter.SHORT_SECOND_FORMATTER.format(new Date(startDate + periodlength));
|
|
for (Event event: ea) {
|
|
if (event.getFormattedDate().compareTo(limit) >= 0) {
|
|
// write accumulation of the score map into eap
|
|
stats(accumulation, eap, startDate, periodlength, maxeventsperperiod, firstEvent.type);
|
|
firstEvent = event;
|
|
startDate += periodlength;
|
|
limit = GenericFormatter.SHORT_SECOND_FORMATTER.format(new Date(startDate + periodlength));
|
|
}
|
|
accumulation.inc(event.payload.toString());
|
|
}
|
|
stats(accumulation, eap, startDate, periodlength, maxeventsperperiod, firstEvent.type);
|
|
|
|
// overwrite the old table for out
|
|
ea = eap;
|
|
}
|
|
|
|
// create a list of these events
|
|
int count = 0;
|
|
for (Event event: ea) {
|
|
prop.put("event_" + count + "_time", event.getFormattedDate());
|
|
prop.put("event_" + count + "_isPeriod", event.duration == 0 ? 0 : 1);
|
|
prop.put("event_" + count + "_isPeriod_duration", event.duration);
|
|
prop.put("event_" + count + "_isPeriod_count", event.count);
|
|
prop.putHTML("event_" + count + "_type", event.type);
|
|
prop.putXML("event_" + count + "_description", event.payload.toString());
|
|
count++;
|
|
}
|
|
prop.put("event", count);
|
|
prop.put("count", count);
|
|
return prop;
|
|
}
|
|
|
|
private static void stats(OrderedScoreMap<String> accumulation, List<EventTracker.Event> eap, long startDate, long periodlength, int head, String type) {
|
|
// write accumulation of the score map into eap
|
|
Iterator<String> si = accumulation.keys(false);
|
|
int c = 0;
|
|
while (si.hasNext() && c++ < head) {
|
|
String key = si.next();
|
|
eap.add(new Event(startDate, periodlength, type, key, accumulation.get(key)));
|
|
}
|
|
accumulation.clear();
|
|
}
|
|
|
|
}
|