698730c4ebbetter utf-8 support everywhere using a default utf-8 encoding for all string conversions. todo: add this also for debian start script (how do I do that?)
orbiter
2010-09-03 22:18:10 +00:00
ca0a03e9ea... migrating to HttpComponents-Client-4.x ... ssl-stuff: accept almost everything
sixcooler
2010-09-03 16:02:52 +00:00
d8f52c5b9cadded a changelog url to download
orbiter
2010-09-03 12:55:36 +00:00
1da5241c2ddo not block server session if maximum number of sessions is reached, just try to clean up once
orbiter
2010-09-03 12:05:37 +00:00
3988a95fb5added ability in rss reader to parse atom feeds
orbiter
2010-09-03 08:53:24 +00:00
5de70c3d7cchanged way of storage for search requests: - the search request cache can now get as large as 1000 entries - if more entries arrive, unused are deleted - the elements may stay in the cache up to 10 minutes and longer if they are used - the elements are deleted earlier that 10 minutes if the memory gets low This commit was mainly done for metager-feeding peers that have a query load of 50000 queries each day. Also added: - a monitor for cache hit/cache miss in PerformanceMemory_p.html (see at bottom of page)
orbiter
2010-09-02 21:52:45 +00:00
9d080f387echange in handling of the all-visible home path for storage in YaCy: the home path can now be distinguished between - data home; the path where the DATA directory is created - application home; everything else This will make it possible to store application data on Mac releases within the ~/Library/YaCy directory; a place where Mac applications write their data. Similar techniques will be possible for debian and windows. To use the new data path, YaCy can be started with -start <data path> or -gui <data path>
orbiter
2010-09-02 19:24:22 +00:00
fa5683adfecreate a mac dmg file (a disc image) for mac releases in ant
orbiter
2010-09-02 19:11:49 +00:00
091281c9f2Mac app ant task building a ready-to-distribute zip file extending r7080
lotus
2010-09-02 08:01:01 +00:00
65eaf30f77redesign of crawl profiles data structure. target will be: - permanent storage of auto-dom statistics in profile - storage of profiles in WorkTable data structure not finished yet. No functional change yet.
orbiter
2010-08-31 15:47:47 +00:00
3f1d5a061fby default store crawled pages to HTCache to support verify=false snippet generation
orbiter
2010-08-31 09:28:01 +00:00
2009999162show landing page after installation finished
lotus
2010-08-30 20:04:19 +00:00
938676265ffix shutdown command, close HttpClient connection pool
f1ori
2010-08-30 17:48:20 +00:00
55da979291disable revision detection for git
f1ori
2010-08-30 17:11:19 +00:00
6d2e0f5fb4always kill shutdown java instance, even if yacy succeeded, in future, the TERM-signal should be used, but currently not all threads are joined during shutdown
f1ori
2010-08-29 23:26:03 +00:00
be0abd92cdalways use kill command in initscript, after timeout elapsed and yacy didn't finished
f1ori
2010-08-29 18:15:22 +00:00
e9160ea1e5Mac ant task according to r7023
lotus
2010-08-27 18:40:32 +00:00
93d2c22e60adapted memory for first run to current standard values
lotus
2010-08-27 18:38:02 +00:00
104318d58a- added nice colors to feed indexing state messages - added a 'remove all' button for new and scheduled rss feed list - made adding of new rss feeds concurrent so interface is more responsible
orbiter
2010-08-27 11:56:51 +00:00
23ba107834UPnP port forwarding default on now. This also displays a message on the entry settings page if not successful, so the user gets an extra hint to open his ports.
lotus
2010-08-27 08:45:00 +00:00
d5ccbb99f9the Windows installer now always requires admin level for installation (Vista/7) unfortunately some users seem to forget to manually install the downloaded Java runtime and therefore could not start YaCy - added concept to always distribute the latest Java version via external php script
lotus
2010-08-26 16:53:20 +00:00
4f22e2df41bugfixes for - next-execution-time in scheduler - deletion of scheduled rss feed loading (now deletes also the scheduling entry)
orbiter
2010-08-26 16:42:00 +00:00
42414a6ae3added two more tables in rss reader interface: - fresh recorded rss feeds (not yet loaded or in scheduler) - rss feeds in scheduler The first list has a button that can be used to place rss feeds into the scheduler The second list has a button to delete rss feeds from the scheduler
orbiter
2010-08-26 16:01:45 +00:00
0f276dd63f- MapHeap now implements Map<byte[], Map<String, String>> - refactoring of method names to comply with Map method names
orbiter
2010-08-24 12:36:56 +00:00
cf07b34c2dimplemented the Map interface in the ARC classes so it will be possible to instantiate ARCs as Map<byte[], Map<String, byte[]>> Because such Maps with byte[] keys cannot be stored in hash maps (bad hashing on byte[]) another ARC with comparable Maps has been added
orbiter
2010-08-23 23:38:03 +00:00
c60d0282fdmore abstraction for tables stored in heaps: the BEncodedHeap now implements Map<byte[], Map<String, byte[]>> This will make it possible that also different database storage types may be added that implement also the same Map<byte[], Map<String, byte[]>> interface.
orbiter
2010-08-23 21:27:58 +00:00
3197ca42edpreparations to move the HTCache into cora: - move the header framework classes to cora - move the ARC caching classes to cora - refactoring of code to call these classes from cora
orbiter
2010-08-23 12:32:02 +00:00
844f158686- removed dependencies in header framework: moved http date methods from DateFormatter to HeaderFramework changed logging to log4j - added ftp load access to MultiProtocolURI - ensured termination of RSS feed iteration
orbiter
2010-08-23 11:41:12 +00:00
80ba543d4csvn fix for uppercase problem
orbiter
2010-08-23 01:16:17 +00:00
5e7081cd19refactoring towards a unified loading mechanism for MultiProtocolURIs
orbiter
2010-08-23 01:08:56 +00:00
caece04f26removed System.err and System.out usage from FTPClient; changed logging to log4j (preferred in yacy.cora)
orbiter
2010-08-22 22:51:31 +00:00
90531f78ffrefactoring of the cora package to get subpackages for http and ftp (smb to come)
orbiter
2010-08-22 22:32:39 +00:00
d0fb6bc2bccleaned up superfluous classes after sixcoolers migration to HttpComponents-Client-4.x
orbiter
2010-08-22 22:04:31 +00:00
dcd9065c84next try to fix loading of network picture
orbiter
2010-08-22 22:02:54 +00:00
661867923a... migrating to HttpComponents-Client-4.x ... The Client is dead, long live the Client! (no references to the old client)
sixcooler
2010-08-22 17:38:27 +00:00
6e4d2f0800fix for the network image sync bug
orbiter
2010-08-21 10:59:21 +00:00
7aa860c505- more logging - more stability for database heap in case of buffer failure
orbiter
2010-08-21 10:16:05 +00:00
dfd416e3fbremoved a mysterious image buffer
orbiter
2010-08-20 23:13:59 +00:00
e10cd115a9- added a new RSS reader interface. This is not finished but you can now load and look at RSS feeds. It will be used to index RSS feeds in a way that is appropriate for such kind of data. - refactoring of Mediawiki and PHPBB3 loader interface names (just renamed) - removed two old not used RSS loader interfaces - fixed a bug in RSS parser library of cora - added a new RSS parser component to the set of yacy document parsers
orbiter
2010-08-20 11:30:02 +00:00
933dc1a600removed old rss parser (will be replaced with parser from cora package)
orbiter
2010-08-20 07:42:38 +00:00
70dd26ec95added the new crawl scheduling function to the crawl start menu: - the scheduler extends the option for re-crawl timing. Many people misunderstood the re-crawl timing feature because that was just a criteria for the url double-check and not a scheduler. Now the scheduler setting is combined with the re-crawl setting and people will have the choice between no re-crawl, re-crawl as was possible so far and a scheduled re-crawl. The 'classic' re-crawl time is set automatically when the scheduling function is selected - removed the bookmark-based scheduler. This scheduler was not able to transport all attributes of a crawl start and did therefore not support special crawling starts i.e. for forums and wikis - since the old scheduler was not aber to crawl special forums and wikis, the must-not-match filter was statically fixed to all bad pages for these special use cases. Since the new scheduler can handle these filters, it is possible to remove the default settings for the filters - removed the busy thread that was used to trigger the bookmark-based scheduler - removed the crontab for the bookmark-based scheduler
orbiter
2010-08-19 23:52:38 +00:00
5a994c9796added a scheduler based on API actions - every process that is monitored with the API Steering interface can now be scheduled! - added input methods in Steering interface to set a scheduling time - added a view on the steering api that shows only crawl jobs inside the Crawl Profile servlet - added a scheduling call process in the cleanup process handler that triggers the scheduled processes This causes that the cleanup now also looks for scheduled processes. Such processes are therefore not executed at the same time as given in the target execution time but they will be executed within the cleanup process time window.
orbiter
2010-08-19 12:13:54 +00:00
189a986ebd- modified api-call interface to record api calls with references to api-call database (carries pk) - added recording date, last execution date and next execution date for a scheduler (scheduler to be implemented next) - extended database access methods for more data formats, especially for date insert/retrieval - extended 'Steering' interface to show new database fields - migrated Steering to new http client - extended cora http client to transmit authentication and also added some convenience methods (http response code) - simplified database back-end (not so much specialized methods for multiple properties) - extended date formatter to produce a special format to show dates in html ( in spaces of date format)
orbiter
2010-08-18 15:56:38 +00:00
1bc08e1416support debconf in debian package * now you are ask some questions to preconfigure yacy after installing the debian package
f1ori
2010-08-18 13:30:57 +00:00
f616cdfce4better resistance of NetworkImage generation against heavy load this is needed for the network image on the yacy.net home page
orbiter
2010-08-18 09:51:00 +00:00
2f8ff8ec02de.lng: Added some German translation for Config* pages that I have found untranslated ConfigNetwork_p.html: Updated Javascript for P2P <-> Robinson selection to use the new ID values - sorry for breaking this in 6996 (undoing id -> name changes again in 7041 and 7042 because the name tag is not allowed in XHMTL Strict 1.0)
mikeworks
2010-08-18 05:55:11 +00:00
86d7f8a989- the web visualization can now be generated in custom color - added input fields in WatchWebStructure_p.html - introduced enum classes for Draw Mode and Filter Mode
orbiter
2010-08-17 10:44:00 +00:00
64d4204f44fix for NPE in network image computation
orbiter
2010-08-17 08:18:17 +00:00
7fdb17bb96redirect uncaught exceptions to logging + small other changes
orbiter
2010-08-16 12:33:06 +00:00
237cfc44b0fixed auto-set values for robinson selection; this reverts a single line from SVN 6996
orbiter
2010-08-15 18:23:47 +00:00
85501414e9Amending and supplementing de. Translation of the network.html
suessthomas
2010-08-14 20:11:23 +00:00
87b1684211additional double-check in balancer
orbiter
2010-08-12 17:18:15 +00:00
653e617a1f* fix debian package dependencies for recent ubuntu and debian testing
f1ori
2010-08-12 15:05:10 +00:00
0d81731e88fixed crawler bug caused by NPE in logging
orbiter
2010-08-12 01:29:56 +00:00
a82a93f2fc- better url double check in crawler - more logging for error urls
orbiter
2010-08-11 09:54:18 +00:00
a6ed6e8cb9... migrating to HttpComponents-Client-4.x ... make the occurrence of multiple header-keys possible
sixcooler
2010-08-10 21:22:30 +00:00
171f2bd84e- removed unused network oanet - added new network definition 'allip' which can be used in networks where intranet and internet-addresses shall be indexed - added a auto-switch-off for global search if there are no global peers
orbiter
2010-08-09 23:41:17 +00:00
b480b7a4d0fix for bug in last commit
orbiter
2010-08-09 00:13:32 +00:00
b12bfe1f91better usage of OSM tile cache and YaCy cache by usage of better tile server computation based on a coordinate hash
orbiter
2010-08-08 23:51:37 +00:00
388aa021c2- concurrent loading of OSM tiles - added a 4-time re-try in case that tile server does not respond
orbiter
2010-08-08 23:14:08 +00:00
670c746dc5dual-licensed HttpConnectionInfo for LGPL original GPL license holder granted dual-licensing by email
orbiter
2010-08-07 23:03:10 +00:00
838e8a1cb7added a Macintosh OSX application wrapper. You can now create a YaCy Mac application like this: - build a new version of YaCy - take everything that is in the yacy home directory (from the fresh build) and move it into a copy of the YaCy.app directory under YaCy.app/Contents/Resources/Java/ - ready: double-click the YaCy.app icon and the new YaCy gui starts, then the browsers is also opened. - if the Mac application is terminated, also the YaCy demon should be stopped automatically and vice versa. This is currently not really good working and needs some more care. A build script for this is missing. Does anyone know how to do that in ant?
orbiter
2010-08-05 11:11:15 +00:00
301a59e07fmoved browser access method from kelondro/util/OS to gui/framework/Browser
orbiter
2010-08-05 10:49:58 +00:00
ec72387165added a very early test version of a YaCy gui component. The gui currently does nothing else than providing a search window that sends the search string to the browser The gui is started when YaCy is started with the option -g or --gui, like ./startYACY.sh -g The gui will primary be used to provide a 'real' macintosh version that can be started and operated like any other macintosh application. A special mac application wrapper will follow.
orbiter
2010-08-05 10:43:03 +00:00
6388a58fc7better memory management and slightly less (in total and temporary) RAM allocation: - confirm that database objects that are not supposed to grow do not have a index memory management that is designed for growth - changed index sorting method in such a way that it allocates less objects during quicksort - database classes classes renaming (shorter, naming addresses that objects hold in RAM) - added a large number of asserts to check if objects actually take the RAM that they should have
orbiter
2010-08-04 13:33:12 +00:00
5924a0d851- enhanced concurrency in database index access for multicore - added statistics about database index caches in PerformanceMemory_p.html - adoped many classes to use the new statistics - added missing close statements
orbiter
2010-08-03 04:58:48 +00:00
55a2536bcfenhancement in drawing speed and reduction of object allocation during drawing
orbiter
2010-08-03 02:44:08 +00:00
610855e362do not use network graph cache if called from authorized account
orbiter
2010-08-03 02:43:15 +00:00
9ab06bc333enhancement in sorting efficiency (database root operation): less object allocation
orbiter
2010-08-03 02:42:28 +00:00
a55af783bfhealing for color blindness
orbiter
2010-07-26 22:54:06 +00:00
710e7bb700de.lng: Added German translation for http://localhost:8080/Ranking_p.html without the actual values (hardcoded in HashMap in Ranking_p.java)
mikeworks
2010-07-26 20:57:54 +00:00