### ### YaCy Init File ### # These properties will be loaded upon installation. # They are used only once for set-up. # If you make changes to this file and want these to make any effect, # you must delete the yacy.conf file in DATA/SETTINGS # ---------------------------------------------------------------------------- # the HTTP service configurations # port number where the server should bind to # e.g. 8080 # #eth0:8080 # 192.168.0.1:8080 port = 8080 # use UPnP [true/false] upnp.enabled = # remote host on UPnP device upnp.remoteHost = #sometimes you may want yacy to bind to another port, than the one reachable from outside. #then set bindPort to the port yacy should bind on, and port to the port, visible from outside #to run yacy on port 8080, reachable from port 80, set bindPort=8080, port=80 and use #iptables -t nat -A PREROUTING -p tcp -s 192.168.24.0/16 --dport 80 -j DNAT --to 192.168.24.1:8080 #(of course you need to customize the ips) bindPort = # SSL support: # # For a German manual see http://yacy-websuche.de/wiki/index.php/De:Interface%C3%9CberHTTPS # # English speaking user read below: # # With this you can access your peer using https://localhost:8080 # # There are two possibilities to specify which certificate should # be used by YaCy. # # 1) Create a new certificate: # # *) For testing purposes, you can create a keystore with a self-signed certificate, # using the following command: # C:\> keytool -keystore mySrvKeystore -genkey -keyalg RSA -alias mycert # # *) Then configure the keyStoreXXXX properties accordingly, e.g. # keyStore = c:/yacy/DATA/SETTINGS/mySrvKeystore # keyStorePassword = mypwd # # 2) Import an existing certificate: # # Alternatively you can import an existing certificate in pkcs12 format into # the keystore. # # This can be done by setting the pkcs12XXX properties accordingly, e.g. # pkcs12ImportFile = c:/temp/keystore.pkcs12 # pkcs12ImportPwd = test # # If the property keyStore is not specified, then a new keystore file # DATA/SETTINGS/myPeerKeystore will be created. keyStore = keyStorePassword = pkcs12ImportFile = pkcs12ImportPwd = # server tracking: maximum time a track entry is hold in the internal cache # value is in milliseconds, default is one hour server.maxTrackingTime = 3600000 # maximum number of tracks per host server.maxTrackingCount = 1000 # maximum number of hosts that are tracked server.maxTrackingHostCount = 100 # maximum file sizes: since some users experience problems with too large files # the file size of database files can be limited. Larger files can be used to get a # better IO performance and to use less RAM; however, if the size must be limited # because of limitations of the file system, the maximum size can be set here filesize.max.win = 2147483647 filesize.max.other = 8589934591 # Network Definition # There can be separate YaCy networks, and managed sub-groups of the general network. # The essentials of the network definition are attached in separate property files. # The property here can also be a url where the definition can be loaded. # In case of privately managed networks, this configuration must be changed BEFORE it is released # to the members of the separated network peers. network.unit.definition = defaults/yacy.network.freeworld.unit #network.unit.definition = defaults/yacy.network.intranet.unit network.group.definition = defaults/yacy.network.group # Update process properties # The update server location is given in the network.unit.definition, # but the settings for update processing and cycles are individual. # the update process can be either 'manual' (no automatic lookup for new versions), # 'guided' (automatic lookup, but user is asked before update is performed', # or 'auto' (whenever an update is available, the update is loaded and installed) update.process = manual # the cycle value applies only if the process is automatic or guided. The value means hours. # There is currently a fixed minimum number of hours of 24 hours for updates update.cycle = 168 # a version number blacklist can restrict automatic or guided updates to a specific # range of version numbers. The restriction is done with a blacklist (standard regexpr) # It is recommended to set this list to low developer version numbers update.blacklist = ...[123] # a update can also restricted with a concept property, which can decide if an # update is only valid if it either is a main release or any svn release including new development releases # Valid keywords are 'main' and 'any' update.concept = any # the following values are set automatically: # the lookup time when the last time a lookup to the network update server(s) where done update.time.lookup = 0 # the download time when the last time a release was downloaded update.time.download = 0 # the deploy time when the last update was done; milliseconds since epoch update.time.deploy = 0 # delete old downloaded files after this amount of days to free disk space # the latest release is always kept update.deleteOld = 30 # only install sign files update.onlySignedFiles = 1 # restart-option # a peer can be re-started periodically # restart.process can be either 'off' (no automatic restart) or 'time' (time- rule-based, see below) restart.process = off # the restart.cycle is the number of hours that must pass before a restart is done restart.cycle = 20 # the restart.hour is a pattern that must match with the hour string (two-digit, 24h) # when the restart should be performed restart.hour = 03 # the following values are set automatically restart.time = 0 # clusters within a network: # every network can have an unlimited number of clusters. Clusters may be also completely # sealed and have no connection to other peers. When a cluster does not use the # p2p protocol and the bootstraping mechanism to contact other peers, we call them # Robinson peers. They can appear in different 'visibilities': # - privatepeer: no connection and no data exchange to any other peer # - privatecluster: connections only to self-defined addresses (other peers in same mode) # - publiccluster: like privatecluster, but visible and searcheable by public p2p nodes # - publicpeer: a single peer without cluster connection, but visible for p2p nodes # all public robinson peers should use a peer tag string to be searcheable if in the # search request these tags appear cluster.mode=publicpeer cluster.peers.yacydomain=localpeer.yacy cluster.peers.ipport=localhost:8080 # bootstrapLoadTimeout # this is the time-out for loading of the seedlist files during bootstraping # the time should not be too long, since loading of the seedlist is not parallelized # and a not successful loading of a seed file may prevent a peer from becoming # a (at least) junior status. If the time-out is too short, there is the danger # that the peer stays in virgin mode bootstrapLoadTimeout = 6000 # time-out of client control socket in milliseconds # since this applies only to the client-proxy connection, # it can be rather short # milliseconds clientTimeout = 10000 # maximal number of httpd sessions # a client may open several connections at once, and the httpdMaxBusySessions value sets # a limit on the number of concurrent connections httpdMaxBusySessions = 200 # default root path for the file server # may be overridden by the htdocs parameter # users shall be encouraged to use the htdocs path for individual content, # not this path defined here htRootPath = htroot htTemplatePath = htroot/env/templates # the htroot path # root path for the httpd file server htDefaultPath=htroot # individual htroot folder # every user may publicize her/his own web pages # these pages shall be placed in the path defined here # the htdocs path shares its content with the htroot path htDocsPath = DATA/HTDOCS # alternative path for the repository path of the web server: the URL # http://localhost:8080/repository # points to DATA/HTDOCS/repository, but can be altered with this repository path # hint: the repository path is the default path for intranet indexing. The easiest ways # to do a indexing of the local storage system is to set a path here for the repository # that points to the root path of the files that shall be indexed repositoryPath=DATA/HTDOCS/repository # the default files (typically index.html), if no file name is given # The complete path to this file is created by combination with the rootPath # you can set a list of defaults, separated by comma # the first one is preferred defaultFiles = ConfigBasic.html,index.html,index.htm,default.html,search.html,console.html,control.html,welcome.html,wiki.html,forum.html,blog.html,email.html,content.html,monitor.html,share.html,dir.html,readme.txt # locale-options: YaCy supports localization. # Web pages for special languages are located in the htLocalePath # The htLocaleLang defines a list of language options as / # the must exist as sub-path to htLocalePath # the htLocaleSelection selects from the given locales, value=one-of- locale.source=locales locale.work=DATA/LOCALE/locales locale.translated_html=DATA/LOCALE/htroot locale.lang=default/English,de/Deutsch,fr/Français,nl/Nederlands,it/Italiano,es/Español,pt/Portugês,fi/Suomi,se/Svenska,dk/Dansk,gr/Eλληvικα,sk/Slovensky locale.language=default # virtual host for httpdFileServlet access # for example http:/// shall access the file servlet and # return the defaultFile at rootPath # either way, http:/// denotes the same as http://localhost:/ # for the preconfigured value 'localpeer', the URL is: # http://localpeer/ fileHost = localpeer # specify the path to the MIME matching file table mimeTable = defaults/httpd.mime # specify the path to the sessionid name file sessionidNamesFile = defaults/sessionid.names # a path to the file cache, used for the internal proxy and as crawl buffer # This will be used if the server is addressed as a proxy proxyCache = DATA/HTCACHE # the maximum disc cache size for files in Cache in megabytes # default: 32 Gigabyte proxyCacheSize = 32768 # a path to the surrogate input directory surrogates.in = DATA/SURROGATES/in # a path to the surrogate output directory surrogates.out = DATA/SURROGATES/out # a path to the dictionaries directory # this directory also contains subdirectories for input sources, the did-you-mean function and other dictionaries = DATA/DICTIONARIES # storage place for new releases releases = DATA/RELEASE # time limits for the crawler: # these times (milliseconds) are the shortest times for an access of the crawler to the same domain # the crawler may read files faster than that, but never from the same domain faster than these time intervals # a delta of 500 milliseconds means that no more than two files are taken from the same server # there is a hard-coded limit which prevents that the used time is shorter that these default times # the time-limits are distinguished for local and global crawls: there is no limit for an intranet-crawl. minimumLocalDelta = 0 minimumGlobalDelta = 500 # the following mime-types are a blacklist for indexing: # parser.mime.deny: specifies mime-types that shall not be indexed parser.mime.deny= parser.extensions.deny= # Promotion Strings # These strings appear in the Web Mask of the YACY search client # Set these Strings to cusomize your peer and give any message to # other peer users promoteSearchPageGreeting = P2P Web Search # if the following property is set to true, the network name is used as greeting promoteSearchPageGreeting.useNetworkName = false # the following attributes can be used to define a custom image and home page on the search page promoteSearchPageGreeting.homepage = http://yacy.net promoteSearchPageGreeting.largeImage = /env/grafics/YaCyLogo_120ppi.png promoteSearchPageGreeting.smallImage = /env/grafics/YaCyLogo_60ppi.png # the path to the public reverse word index for text files (web pages) # the primary path is relative to the data root, the secondary path is an absolute path # when the secondary path should be equal to the primary, it must be declared empty indexPrimaryPath=DATA/INDEX # the commons are words that appear in the index more than 64k times in references. # Since indexes with such size cannot be handled efficiently, they are sorted in such a way that references with high ranking # are stored back into the index, and references with bad ranking are sorted out. Such sorted-out references can be stored # for later use (but there is no at this time). If the sorted-out references should be stored, the following property should be # set to true. If set to false, they are abandoned (deleted), and previously stored commons are removed. index.storeCommons=false # the path to the LISTS files. Most lists are used to filter web content listsPath=DATA/LISTS # path to additional databases, like messages, blog data and bookmarks workPath=DATA/WORK # the path to the SKINS files. skinPath=DATA/SKINS # the yellow-list; URL's elements # (the core of an URL; like 'yahoo' in 'de.yahoo.com') # appearing in this list will not get a manipulated user agent string proxyYellowList=yacy.yellow # the black-list; URLs appearing in this list will not be loaded; # instead always a 404 is returned # all these files will be placed in the listsPath BlackLists.Shared=url.default.black BlackLists.DefaultList=url.default.black #these are not needed as default. they just keep the values from beeing deleted ... proxy.BlackLists=url.default.black crawler.BlackLists=url.default.black dht.BlackLists=url.default.black search.BlackLists=url.default.black surftips.BlackLists=url.default.black news.BlackLists=url.default.black proxyCookieBlackList=cookie.default.black proxyCookieWhiteList=cookie.default.black # the blue-list; # no search result is locally presented that has any word of the bluelist # in the search words, the URL or the URL's description plasmaBlueList=yacy.blue # this proxy may in turn again access another proxy # if you wish to do that, specify it here # if you want to switch on the proxy use, set remoteProxyUse=true # remoteProxyNoProxy is a no-proxy pattern list for the remote proxy remoteProxyUse=false remoteProxyUse4Yacy=true remoteProxyUse4SSL=true remoteProxyHost=192.168.2.2 remoteProxyPort=4239 remoteProxyUser= remoteProxyPwd= remoteProxyNoProxy=10\..*,127.*,172.(1[6-9]|2[0-9]|3[0-1])\..*,169.254.*,192.168.*,localhost # the proxy may filter the content of transferred web pages # the bluelist removes specific keywords from web pages proxyBlueList=yacy.blue # security settigns # we provide proxy and server security through a 2-stage security gate: # 1st stage: firewall-like access control trough ip filter for clients # 2nd stage: password settings for proxy, server and server administrators # by default, these settings are weak to simplify set-up and testing # every user/adiministrator shall be encouraged to change these settings # your can change them also online during run-time on # http://localhost:8080/ # proxyClient: client-ip's that may connect the proxy for proxy service # if several ip's are allowed then they must be separated by a ',' # any ip may contain the wildcard-sign '*' #proxyClient=192.168.0.4 proxyClient=localhost,127.0.0.1,192.168.*,10\..* # YaCyHop: allow public usage of proxy for yacy-protocol # this enables usage of the internal http proxy for everyone, # if the file path starts with /yacy/ # This is used to enable anonymization of yacy protocol requests # Instead of asking a remote peer directly, a peer in between is asked # to prevent that the asked peer knows which peer asks. YaCyHop=true # serverClient: client-ip's that may connect to the web server, # thus are allowed to use the search service # if you set this to another value, search requst from others # are blocked, but you will also be blocked from using others # search services. serverClient=* # use_proxyAccounts: set to true to restrict proxy-access to some identified users. #use User_p.html to create some Users. use_proxyAccounts=false # adminAccount: a user:password - pair for administration of # settings through the web interface # should be set to a secret. By default it is without a password # but you are encouraged to set it to another value on the page # http://localhost:8080/ConfigBasic.html #adminAccount=admin:mysecretpassword adminAccount= adminAccountBase64MD5= # special access handling for users from localhost: # access from localhost may be granted with administration authority # if this flag is set. It is set to true by default to make usage of YaCy easy # if you use YaCy on a headless server, you should set this to false # or configure this on http://localhost:8080/ConfigBasic.html # during the first 10 minutes of operation of YaCy; # if the admin account password is still empty after 10 minutes a random # password is generated an access is then ONLY from localhost, which will cause # inaccessibility for installations on headless servers. adminAccountForLocalhost=true # if you are running a principal peer, you must update the following variables # The upload method that should be used to upload the seed-list file to # a public accessible webserver where it can be loaded by other peers. # # You can set the seedUploadMethod-Property to # - None # - Ftp # - File # - Scp (only if you have installed the optional addon) # seedUploadMethod=none # This is the most common method to upload the seed-list # # This is an ftp account with all relevant information. # The update is only made if there had been changes in between. seedFTPServer= seedFTPAccount= seedFTPPassword= seedFTPPath= # alternatively to an FTP account, a peer can also become a principal peer # if the seed-list can be generated as a file and that file is also accessible from # the internet. In this case, omit any ftp settings and set this path here. # if this path stays empty, an ftp account is considered # however, you must always set a seedURL because it is used to check if the # file is actually accessible from the internet seedFilePath= # Settings needed to upload the seed-list file via scp # # Please note that this upload method can only be used if you have installed # this optional upload method. seedScpServer= seedScpServerPort= seedScpAccount= seedScpPassword= seedScpPath= # every peer should have a name. inded, we try to give every peer an unique ID, # which is necessary for internal organization of the index sharing, but the # peer's name is purely informal. No function but information is applied. # please change this at your pleasure peerName=anomic # every peer periodically scans for other peers. you can set the time # of the period here (minutes) peerCycle=2 # Debug mode for YACY network: this will trigger that also local ip's are # accepted as peer addresses yacyDebugMode=false #staticIP if you have a static IP, you can use this setting staticIP= # each time YaCy starts up, it can trigger the local browser to show the # status page. This is active by default, to make it easier for first-time # users to understand what this application does. You can disable browser # pop-up here or set a different start page, like the search page # the browser type is optional and works only under certain conditions browserPopUpTrigger=true browserPopUpPage=ConfigBasic.html browserPopUpApplication=firefox # defines if the YaCy icon appears in the system tray on supported platforms trayIcon=true trayIcon.force=false tray.label=YaCy # index sharing attributes: by default, sharing is on. # If you want to use YaCy only for local indexing (robinson mode), # you may switch this off allowDistributeIndex=true allowDistributeIndexWhileCrawling=false allowDistributeIndexWhileIndexing=true allowReceiveIndex=true allowUnlimitedReceiveIndexFrom= indexReceiveBlockBlacklist=true # the frequency is the number of links per minute, that the peer allowes # _every_ other peer to send to this peer defaultWordReceiveFrequency=100 defaultLinkReceiveFrequency=30 # the default may be overridden for each peer individually, these # settings are only available through the online interface # prefetch parameters # the prefetch depth assigns a specific depth to the prefetch mechanism # prefetch of 0 means no prefetch; a prefetch of 1 means to prefetch all # embedded URLs, but since embedded image links are loaded by the browser # this means that only embedded anchors are prefetched additionally # a prefetch of 2 would result in loading of all images and anchor pages # of all embedded anchors. Be careful with this value, since even a prefetch # of 2 would result in hundreds of prefetched URLs for each single proxy fill. proxyPrefetchDepth=0 proxyStoreHTCache=true proxyIndexingRemote=false proxyIndexingLocalText=true proxyIndexingLocalMedia=true # proxy usage only for .yacy-Domains for autoconfig proxyYacyOnly=false # From the 'IndexCreate' menu point you can also define a crawling start point. # The crawling works the same way as the prefetch, but it is possible to # assign a different crawling depth. # Be careful with this number. Consider a branching factor of average 20; # A prefetch-depth of 8 would index 25.600.000.000 pages, maybe the whole WWW. crawlingDepth=3 crawlingIfOlder=-1 crawlingDomFilterDepth=-1 crawlingDomMaxPages=-1 indexText=true indexMedia=true # Filter for crawlinig; may be used to restrict a crawl to a specific domain # URLs are only indexed and further crawled if they match this filter crawlingFilter=.* crawlingQ=false storeHTCache=false storeTXCache=true # peers may initiate remote crawling tasks. # every peer may allow or disallow to be used as crawling-peer; # you can also set a maximum crawl depth that can be requested or accepted # order=parameters for requester; response=parameters for responder # these values apply only for senior-senior - communication # The delay value is number of seconds bewteen two separate orders crawlOrder=true crawlOrderDepth=0 crawlOrderDelay=8 crawlResponse=true crawlResponseDepth=0 # indexing-exclusion - rules # There rules are important to reduce the number of words that are indexed # We distinguish three different sets of stop-words: # static - excludes all words given in the file yacy.stopwords from indexing, # dynamic - excludes all words from indexing which are listed by statistic rules, # parental - excludes all words from indexing which had been indexed in the parent web page. xsstopw=true xdstopw=true xpstopw=true # Topwords filtering # If set to true, all stopwords (stopwords.yacy) are filtered from the topwords # Change to false if requesting hits from peers with modified stopwords-file and using the unchanged client-version filterOutStopwordsFromTopwords=true # performance-settings # delay-times for permanent loops (milliseconds) # the idlesleep is the pause that an proces sleeps if the last call to the # process job was without execution of anything; # the busysleep is the pause after a full job execution # the prereq-value is a memory pre-requisite: that much bytes must # be available/free in the heap; othervise the loop is not executed # and another idlesleep is performed 20_dhtdistribution_idlesleep=15000 20_dhtdistribution_busysleep=10000 20_dhtdistribution_memprereq=12582912 30_peerping_idlesleep=120000 30_peerping_busysleep=120000 30_peerping_memprereq=2097152 40_peerseedcycle_idlesleep=1800000 40_peerseedcycle_busysleep=1200000 40_peerseedcycle_memprereq=4194304 50_localcrawl_idlesleep=2000 50_localcrawl_busysleep=20 50_localcrawl_memprereq=12582912 50_localcrawl_isPaused=false 60_remotecrawlloader_idlesleep=60000 60_remotecrawlloader_busysleep=10000 60_remotecrawlloader_memprereq=12582912 60_remotecrawlloader_isPaused=false 62_remotetriggeredcrawl_idlesleep=10000 62_remotetriggeredcrawl_busysleep=1000 62_remotetriggeredcrawl_memprereq=12582912 62_remotetriggeredcrawl_isPaused=false 70_surrogates_idlesleep=10000 70_surrogates_busysleep=0 70_surrogates_memprereq=12582912 90_cleanup_idlesleep=300000 90_cleanup_busysleep=300000 90_cleanup_memprereq=0 # autoReCrawl Options autoReCrawl_idlesleep = 3600000 autoReCrawl_busysleep = 3600000 autoReCrawl_memprereq = -1 # additional attributes: # performanceIO is a percent-value. a value of 10 means, that 10% of the busysleep time # is used to flush the RAM cache, which is the major part of the IO in YaCy performanceProfile=defaults/yacy.init performanceSpeed=100 performanceIO=10 # cleanup-process: # properties for tasks that are performed during cleanup cleanup.deletionProcessedNews = true cleanup.deletionPublishedNews = true # default memory settings for startup of yacy # is valid in unix/shell and windows environments but # not for first startup of YaCy # -Xmx and -Xms maximum/init Java heap size # both values should be equal, # othervise the YaCy-internal memory supervision does not work javastart_Xmx=Xmx180m javastart_Xms=Xms180m # YaCy is able to use RAM copies of database tables. This needs a lot of RAM # To switch copying of file tables int RAM on, use this property # this value is automatically set to true, if more than one gigabyte RAM is available ramcopy=false # some java versions may be limited to a specific array size # of 134217727 entries. To prevent that tables of that size are generated, # set this property to false # If you want to have better performance and switch ramcopy on, try also to # set this property to true # this value is automatically set to true, if more than two gigabyte is available exceed134217727=false # priority of the yacy-process # is valid in unix/shell and windows environments but # not for first startup of YaCy # UNIX: corresponds to the nice-level # WIN: -20=realtime;-15=high;-10=above;0=normal;10=below;20=low javastart_priority=10 # performance properties for the word index cache # wordCacheMaxLow/High is the number of word indexes that shall be held in the # ram cache during indexing. If you want to increase indexing speed, increase this # value i.e. up to one million, but increase also the memory limit to a minimum of 2GB wordCacheMaxCount = 100000 # Specifies if yacy can be used as transparent http proxy. # # Please note that you also have to reconfigure your firewall # before you can use yacy as transparent proxy. On linux this # can be done like this: # iptables -t nat -A PREROUTING -p tcp -s 192.168.0.0/16 \ # --dport 80 -j DNAT --to 192.168.0.1:8080 # # With this iptables filter listed above all http traffic that # comes from your private network (in this case 192.168.0.0) # and goes to any webserver listening on port 80 will be forwarded # by the firewall to yacy running on port 8080 (192.168.0.1:8080) isTransparentProxy=false # Specifies if yacy should use the http connection keep-alive feature connectionKeepAliveSupport=true # Specifies the timeout the proxy sould use proxy.clientTimeout = 30000 # Specifies if the proxy should send the via header according to RFC proxy.sendViaHeader=true # Specifies if the proxy should send the X-Forwarded-For header proxy.sendXForwardedForHeader=true # Enable cookie monitoring proxy.monitorCookies=false # msgForwarding: Specifies if yacy should forward received messages via # email to the configured email address msgForwardingEnabled=false msgForwardingCmd=/usr/sbin/sendmail msgForwardingTo=root@localhost #crawlPause: delay time after specific functions before crawling is resumed crawlPause.proxy=15000 crawlPause.localsearch=9000 crawlPause.remotesearch=3000 # Some configuration values for the crawler crawler.clientTimeout=9000 # http crawler specific settings; size in bytes crawler.http.acceptEncoding=gzip crawler.http.acceptLanguage=en-us,en;q=0.5 crawler.http.acceptCharset=ISO-8859-1,utf-8;q=0.7,*;q=0.7 crawler.http.maxFileSize=1048576 # ftp crawler specific settings; size in bytes crawler.ftp.maxFileSize=1048576 # smb crawler specific settings: maximum size crawler.smb.maxFileSize=50000000 # maximum number of crawler threads crawler.MaxActiveThreads = 200 # maximum size of indexing queue indexer.slots = 100 # maximum size of stacker queue stacker.slots = 2000 # search domains. If set to false then that search is not available search.text = true search.images = true search.audio = true search.video = true search.app = true # number of search results displayed by default search.items = 10 # specifies if yacy should set it's own referer if no referer URL # was set by the client. useYacyReferer = false # allow only 443(https-port) for https-proxy? # if you want to tunnel other protocols, set to false secureHttps = true # specifies if the httpdFileHandler should cache # the template-files from the htroot directory enableTemplateCache = true # specifies if the http post body should be transfered # using content-encoding gzip during index transfer # a) indexDistribution: which is done periodically if you have enabled # Index Distribution via IndexControl_p.html # b) indexTransfer: which can be used to transfer the whole index of a peer # this can be started via IndexTransfer_p.html # c) indexControl: which can be triggered manually via IndexControl_p.html to # transfer a chosen subset of the peer index indexDistribution.gzipBody = true indexTransfer.gzipBody = true indexControl.gzipBody = true # defining timeouts for index- transfer/distribution/control indexControl.timeout = 60000 indexDistribution.timeout = 60000 indexTransfer.timeout = 120000 # defining max. allowed amount of open files during index- transfer/distribution indexDistribution.maxOpenFiles = 800 indexTransfer.maxOpenFiles = 800 # sizes for index distribution indexDistribution.minChunkSize = 10 indexDistribution.maxChunkSize = 1000 indexDistribution.startChunkSize = 200 indexDistribution.maxChunkFails = 1 # Distribution of Citation-Reference (CR-) files # The distribution is done in two steps: # first step to anonymize the records # second step to forward to a collecting peer # to anonymize the data even against the intermediate peer # a specific precentage is also sent again to other peers. # for key-numbers please see de.anomic.plasma.plasmaRankingDistribution CRDistOn = true CRDist0Path = GLOBAL/010_owncr CRDist0Method = 1 CRDist0Percent = 0 CRDist0Target = CRDist1Path = GLOBAL/014_othercr CRDist1Method = 9 CRDist1Percent = 30 CRDist1Target = kaskelix.de:8080,yacy.dyndns.org:8000 # Search sequence settings # collection: # time = time to get a RWI out of RAM cache, assortments and WORDS files # count = maximum number of RWI-entries that shall be collected # # join: # time = time to perform the join between all collected RWIs # count = maximum number of entries that shall be joined # # presort: # time = time to do a sort of the joined URL-records # count = maximum number of entries that shall be pre-sorted # # urlfetch: # time = time to fetch the real URLs from the LURL database # count = maximum number of urls that shall be fetched # # postsort: # time = time for final sort of URLs # count = maximum number oof URLs that shall be retrieved during sort # # filter: # time = time to filter out unwanted urls (like redundant urls) # count = maximum number of urls that shall be filtered # # snippetfetch: # time = time to fetch snippets for selected URLs # count = maximum number of snipptes to be fetched # # all values are percent # time-percent is the percent of total search time # count-percent is the percent of total wanted urls in result # we distinguish local and remote search times searchProcessLocalTime_c = 44 searchProcessLocalCount_c = 10000000 searchProcessLocalTime_j = 8 searchProcessLocalCount_j = 1000000 searchProcessLocalTime_r = 8 searchProcessLocalCount_r =100000 searchProcessLocalTime_u = 20 searchProcessLocalCount_u = 10000 searchProcessLocalTime_o = 10 searchProcessLocalCount_o = 100 searchProcessLocalTime_f = 5 searchProcessLocalCount_f = 100 searchProcessLocalTime_s = 5 searchProcessLocalCount_s = 30 searchProcessRemoteTime_c = 44 searchProcessRemoteCount_c = 1000000 searchProcessRemoteTime_j = 8 searchProcessRemoteCount_j = 1000000 searchProcessRemoteTime_r = 8 searchProcessRemoteCount_r = 1000 searchProcessRemoteTime_u = 20 searchProcessRemoteCount_u = 1000 searchProcessRemoteTime_o = 10 searchProcessRemoteCount_o = 1000 searchProcessRemoteTime_f = 5 searchProcessRemoteCount_f = 100 searchProcessRemoteTime_s = 5 searchProcessRemoteCount_s = 10 # timeouts for snippet fetching in ms # timeout_text is for text-snippets, timeout_media for media, e.g. images timeout_text = 10000 timeout_media = 15000 # path to ranking directory containing ranking reference files rankingPath = DATA/RANKING # a list of domain name patterns that should not be cached by the httpc dns cache httpc.nameCacheNoCachingPatterns = .*.ath.cx,.*.blogdns.*,.*.boldlygoingnowhere.org,.*.dnsalias.*,.*.dnsdojo.*,.*.dvrdns.org,.*.dyn-o-saur.com,.*.dynalias.*,.*.dyndns.*,.*.ftpaccess.cc,.*.game-host.org,.*.game-server.cc,.*.getmyip.com,.*.gotdns.*,.*.ham-radio-op.net,.*.hobby-site.com,.*.homedns.org,.*.homeftp.*,.*.homeip.net,.*.homelinux.*,.*.homeunix.*,.*.is-a-chef.*,.*.is-a-geek.*,.*.kicks-ass.*,.*.merseine.nu,.*.mine.nu,.*.myphotos.cc,.*.podzone.*,.*.scrapping.cc,.*.selfip.*,.*.servebbs.*,.*.serveftp.*,.*.servegame.org,.*.shacknet.nu #externalRedirectors #squid Redirector compatible externalRedirector= svnRevision=0 currentSkin=pdblue # flag to show if pages shall be usable for non-admin users # this can be applied to the Surftips.html and yacysearch.html page publicSurftips = true publicSearchpage = true # Wiki access rights # the built-in wiki system allows by default only that the administrator is allowed to make changes # this can be changed. There are three options: # admin - only the admin has write right # all - everybody has write right # user - the admin and every user registered in the user db has write right WikiAccess = admin # Search Profiles # we will support different search profiles # this is currently only a single default profile # If this profile setting is empty, a hard-coded profile from plasmaSearchRanking is used rankingProfile = #optional extern thumbnail program. #the program must accept the invocation PROGRAM http://url /path/to/filename thumbnailProgram = # settings for the peer's local robots.txt # the following restrictions are possible (comma-separated): # - all : entire domain is disallowed # - blog : the blog-pages # - bookmarks : the bookmark-page # - dirs : all directories in htroot (standard setting, as there is no usable information in) # - fileshare : all files in the peer's file share (DATA/HTDOCS/share) # - homepage : all files on the peer's home page (DATA/HTDOCS/www) # - locked : all servlets ending on '_p.*' (standard setting, as robots would need a password to access them anyways) # - news : the news-page # - network : the network-pages # - status : peer's status page # - surftips : the surftips-page # - wiki : the wiki-page httpd.robots.txt = locked,dirs # class to use for parsing wikicode wikiParser.class = de.anomic.data.wikiCode # settings for automatic deletion of old entries in passive and potential seed-db # time means max time (in days) a peer may not have been seen before it is deleted routing.deleteOldSeeds.permission = true routing.deleteOldSeeds.time = 30 # options to remember the default search engines when using the search compare features compare_yacy.left = YaCy compare_yacy.right = YaCy # minimum free disk space for crawling (MiB) disk.free = 3000 # minimum for DHT disk.free.hardlimit = 1000 # minimum memory to accept dht-in (KB) memory.acceptDHT = 50000 memory.disabledDHT = false # setting if execution of CGI files is allowed or not cgi.allow = false cgi.suffixes = cgi,pl # whether this is a version for a web browser browserintegration = false # content integration settings content.phpbb3.urlstub = http:/// content.phpbb3.dbtype = mysql content.phpbb3.dbhost = localhost content.phpbb3.dbport = 3306 content.phpbb3.dbname = forum content.phpbb3.tableprefix = phpbb_ content.phpbb3.dbuser = notroot content.phpbb3.dbpw = joshua content.phpbb3.ppf = 1000 content.phpbb3.dumpfile = # segment assignment for index storage processes in YaCy: # each process can store its index result in it's own index segment segment.process.receipts_tmp = default segment.process.queries_tmp = default segment.process.dhtin_tmp = default segment.process.dhtout_tmp = default segment.process.proxy_tmp = default segment.process.localcrawling_tmp = default segment.process.remotecrawling_tmp = default segment.process.default_tmp = default # search engine teaser: an about box in search results # this is only shown, if the about.body is filled about.headline = about.body =