Project

General

Profile

1
lod_baseURI=http://lod.openaire.eu/data/
2
lod_dataPath=/user/giorgos.alexiou/rdfData
3
lod_delim=,
4
lod_enclosing='
5
lod_output=/tmp/lod_dump/
6
#Config for DM
7
#--------DM Cluster configuration-------
8
#zookeeperQuorum=namenode1.hadoop.dm.openaire.eu,namenode2.hadoop.dm.openaire.eu,jobtracker1.hadoop.dm.openaire.eu,jobtracker2.hadoop.dm.openaire.eu,hbase-master1.hadoop.dm.openaire.eu
9
#zookeeperZnode=root-region-server
10
#zookeepeClientPort=2181
11
#jobTracker=dm-cluster-jt
12
#nameNode=hdfs://dm-cluster-nn
13
#oozie.wf.application.path=hdfs://dm-cluster-nn/user/eri.katsari/lodinter/oozie_app
14
#oozie.wf.application.path=hdfs://dm-cluster-nn/user/giorgos.alexiou/lod/oozie_app
15
#oozieServiceLoc=http://oozie.hadoop.dm.openaire.eu:11000/oozie
16
#----OCEAN CLUSTER CONFIG-------------
17
zookeeperQuorum=localhost:2181
18
zookeeperZnode=localhost:2181
19
zookeepeClientPort=2181
20
jobTracker=master:8032
21
nameNode=hdfs://master:8020/
22
oozie.wf.application.path=hdfs://master:8020/user/eri/inter/oozie_app
23
oozieServiceLoc=http://83.212.110.197:11000/oozie/
24
numReducers=10
25
sourceInput=/tmp/lod_zenodo/source/*
26
targetInput=/tmp/lod_zenodo/target/*
27
lod_block_output=/tmp/lod_blocks/
28
queueName=default
29
#user.name=giorgos.alexiou
30
#workingDir=/user/giorgos.alexiou/core/javamapreduce/lodexport/working_dir
31
user.name=eri.katsari
32
workingDir=/user/eri.katsari/core/javamapreduce/lodinter/working_dir
33
out1=datasource
34
out2=result
35
out3=project
36
out4=person
37
out5=organization
38
buildOut1=blocks
39
buildOut2=stats
40
sourceBuildInput=/tmp/lod_dump/OA/
41
targetBuildInput=/tmp/lod_dump/TARGET/
42
lod_redisHost=10.0.0.4
43
lod_redisPort=16897
44
statsInputPath=/tmp/lod_blocks/stats/
45
groundTruthPath=/tmp/lodfinal/groundTruth
46
linkageOutputPath=/tmp/lodfinal/source
47
statsOutputPath=/tmp/lod_blocks/stats/
48
lod_sourceMappings={"result":["http://www.w3.org/1999/02/22-rdf-syntax-ns#type","http://purl.org/dc/terms/identifier","http://lod.openaire.eu/vocab/dateOfTransformation","http://lod.openair
49
e.eu/vocab/dateOfCollection","http://purl.org/dc/terms/identifier","http://www.eurocris.org/ontologies/cerif/1.3#name","http://purl.org/dc/terms/dateAccepted","http://purl.org/dc/terms/publ
50
isher","http://purl.org/dc/terms/identifier","http://purl.org/dc/terms/language","http://purl.org/dc/terms/date","http://lod.openaire.eu/vocab/resultSubject","http://lod.openaire.eu/vocab/e
51
xternalReference","http://purl.org/dc/terms/source","http://purl.org/dc/terms/format","http://lod.openaire.eu/vocab/context","http://dbpedia.org/ontology/country","http://purl.org/dc/terms/
52
accessRights","http://purl.org/dc/terms/description","http://lsdis.cs.uga.edu/projects/semdis/opus#journal_name","http://lod.openaire.eu/vocab/dataSourceType","http://lod.openaire.eu/vocab/
53
device","http://lod.openaire.eu/vocab/size","http://lod.openaire.eu/vocab/version","http://lod.openaire.eu/vocab/lastMetadataUpdate","http://lod.openaire.eu/vocab/metadataVersion","http://l
54
od.openaire.eu/vocab/year","http://lod.openaire.eu/vocab/resultType"],"project": ["http://www.w3.org/1999/02/22-rdf-syntax-ns#type","http://purl.org/dc/terms/identifier","http://lod.openaire.eu/vocab/dateOfTransformation","http://lod.openaire.eu/vocab/dateOfCollection","http://purl.org/dc/terms/identifier","http://lod.openaire.eu/vocab/projectCode","http://schema.org/url","http://www.eurocris.org/ontologies/cerif/1.3#acronym","http://www.eurocris.org/ontologies/cerif/1.3#name","http://www.eurocris.org/ontologies/cerif/1.3#startDate","http://www.eurocris.org/ontologies/cerif/1.3#endDate","http://purl.org/cerif/frapo/hasCallIdentifier","http://www.eurocris.org/ontologies/cerif/1.3#keyword","http://www.w3.org/2006/time#hasDurationDescription","http://lod.openaire.eu/vocab/ec_SC39","http://lod.openaire.eu/vocab/contractType","http://lod.openaire.eu/vocab/oaMandatePublications","http://lod.openaire.eu/vocab/projectSubjects","http://od.openaire.eu/vocab/ec_article29-3","http://lod.openaire.eu/vocab/funder","http://lod.openaire.eu/vocab/fundingLevel0","http://lod.openaire.eu/vocab/fundingLevel1","http://lod.openaire.eu/vocab/fundingLevel2","http://lod.openaire.eu/vocab/fundingLevel3"],"person": ["http://www.w3.org/1999/02/22-rdf-syntax-ns#type","http://purl.org/dc/terms/identifier","http://lod.openaire.eu/vocab/dateOfTransformation","http://lod.openaire.eu/vocab/dateOfCollection","http://purl.org/dc/terms/identifier", "http://xmlns.com/foaf/0.1/firstName","http://xmlns.com/foaf/0.1/lastName", "http://xmlns.com/foaf/0.1/name","http://schema.org/faxNumber","http://xmlns.com/foaf/0.1/mbox","http://xmlns.com/foaf/0.1/phone", "http://schema.org/nationality","http://purl.org/dc/terms/identifier", "http://lod.openaire.eu/vocab/trust"],"organization": ["http://www.w3.org/1999/02/22-rdf-syntax-ns#type","http://purl.org/dc/terms/identifier","http://lod.openaire.eu/vocab/dateOfTransformation","http://lod.openaire.eu/vocab/dateOfCollection","http://purl.org/dc/terms/identifier","http://www.w3.org/2004/02/skos/core#altLabel","http://www.w3.org/2004/02/skos/core#prefLabel","http://lod.openaire.eu/vocab/webSiteUrl","http://xmlns.com/foaf/0.1/logo","http://dbpedia.org/ontology/country","http://lod.openaire.eu/vocab/entityType" ],"datasource":["http://www.w3.org/1999/02/22-rdf-syntax-ns#type","http://purl.org/dc/terms/identifier","http://lod.openaire.eu/vocab/dateOfTransformation","http://lod.openaire.eu/vocab/dateOfCollection","http://purl.org/dc/terms/identifier","http://lod.openaire.eu/vocab/datasourceType","http://lod.openaire.eu/vocab/openAIRECompatibility","http://dbpedia.org/ontology/officialName","http://lod.openaire.eu/vocab/englishName","http://schema.org/url","http://xmlns.com/foaf/0.1/logo","http://xmlns.com/foaf/0.1/mbox","http://purl.org/vocab/vann/preferredNamespacePrefix","http://www.w3.org/2003/01/geo/wgs84_pos#lat","http://www.w3.org/2003/01/geo/wgs84_pos#long","http://lod.openaire.eu/vocab/dateOfValidity","http://purl.org/dc/terms/description","http://lod.openaire.eu/vocab/subjectList","http://lod.openaire.eu/numberOfItems","http://purl.org/dc/terms/date","http://lod.openaire.eu/vocab/policies","http://lod.openaire.eu/vocab/languages","http://lod.openaire.eu/vocab/contentType","http://lod.openaire.eu/vocab/accessInfoPackage","http://lod.openaire.eu/vocab/releaseStartDate","http://lod.openaire.eu/vocab/releaseEndDate","http://lod.openaire.eu/vocab/missionStatementUrl","http://www.europeana.eu/schemas/edm/dataProvider","http://lod.openaire.eu/vocab/serviceProvider","http://lod.openaire.eu/vocab/databaseAccessType","http://lod.openaire.eu/vocab/dataUploadType","http://lod.openaire.eu/vocab/dataUploadRestrictions","http://lod.openaire.eu/vocab/versioning","http://lod.openaire.eu/vocab/citationGuidelineUrl","http://lod.openaire.eu/vocab/qualityManagementKind","http://lod.openaire.eu/vocab/pidSystems","http://lod.openaire.eu/vocab/certificates","http://purl.org/dc/terms/accessRights"]}
55
lod.configXML=lod_configXML=<?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE LIMES SYSTEM "limes.dtd"> <LIMES> <PREFIX> <NAMESPACE>http://www.w3.org/1999/02/22-rdf-syntax-ns#</NAMESPACE> <LABEL>rdf</LABEL> </PREFIX> <PREFIX> <NAMESPACE>http://www.w3.org/2000/01/rdf-schema#</NAMESPACE> <LABEL>rdfs</LABEL> </PREFIX> <SOURCE> <ID>source1</ID> <ENDPOINT>/user/kanakakis/groundTruth/sourceNT</ENDPOINT> <VAR>?x</VAR> <PAGESIZE>100</PAGESIZE> <RESTRICTION>?x rdf:type http://www.eurocris.org/ontologies/cerif/1.3#ResultEntity</RESTRICTION> <PROPERTY>http://lod.openaire.eu/vocab/year RENAME Year</PROPERTY> <PROPERTY>http://www.w3.org/1999/02/22-rdf-syntax-ns# RENAME type</PROPERTY> <PROPERTY>http://purl.org/dc/terms/identifier RENAME id</PROPERTY> <PROPERTY>http://www.eurocris.org/ontologies/cerif/1.3#name AS lowercase->regexreplace("[^A-Za-z0-9]"," ") RENAME publicationName</PROPERTY> </SOURCE> <TARGET> <ID>source2</ID> <ENDPOINT>/user/kanakakis/groundTruth/targetNT</ENDPOINT> <VAR>?y</VAR> <PAGESIZE>100</PAGESIZE> <RESTRICTION>?y rdf:type http://swrc.ontoware.org/ontology#Article</RESTRICTION> <PROPERTY>http://www.w3.org/1999/02/22-rdf-syntax-ns# RENAME type</PROPERTY> <PROPERTY>http://purl.org/dc/terms/issued RENAME Year</PROPERTY> <PROPERTY>http://purl.org/dc/terms/identifier RENAME id</PROPERTY> <PROPERTY>http://www.w3.org/2000/01/rdf-schema#label AS lowercase->regexreplace("[^A-Za-z0-9]"," ") RENAME articleName</PROPERTY> </TARGET> <METRIC>AND(jaro(x.publicationName,y.articleName)|0.8,jaro(x.Year,y.Year)|1.0)</METRIC> <!-- <METRIC>jaro(x.publicatioName,y.articleName)|0.7</METRIC> --> <ACCEPTANCE> <THRESHOLD>0.8</THRESHOLD> <FILE>/user/kanakakis/groundTruth/accepted_links_0.8_no_purge</FILE> <RELATION>owl:sameAs</RELATION> </ACCEPTANCE> <REVIEW> <THRESHOLD>0.8</THRESHOLD> <FILE>/user/kanakakis/groundTruth/verified_links_0.8</FILE> <RELATION>owl:sameAs</RELATION> </REVIEW> <EXECUTION>Default</EXECUTION> <OUTPUT>TTL</OUTPUT> </LIMES>
56
lod.limesDTD=<?xml version="1.0" encoding="utf-8"?> <!ELEMENT LIMES (PREFIX*, SOURCE, TARGET, METRIC, ACCEPTANCE, REVIEW, EXECUTION*, GRANULARITY*, OUTPUT*)> <!ELEMENT PREFIX (NAMESPACE, LABEL)> <!ELEMENT NAMESPACE (#PCDATA)> <!ELEMENT LABEL (#PCDATA)> <!ELEMENT SOURCE (ID, ENDPOINT, GRAPH*, VAR, PAGESIZE, RESTRICTION+, PROPERTY+, TYPE*)> <!ELEMENT TARGET (ID, ENDPOINT, GRAPH*, VAR, PAGESIZE, RESTRICTION+, PROPERTY+, TYPE*)> <!ELEMENT ID (#PCDATA)> <!ELEMENT RESTRICTION (#PCDATA)> <!ELEMENT METRIC (#PCDATA)> <!ELEMENT ACCEPTANCE (THRESHOLD, FILE, RELATION)> <!ELEMENT REVIEW (THRESHOLD, FILE, RELATION)> <!ELEMENT RELATION (#PCDATA)> <!ELEMENT ENDPOINT (#PCDATA)> <!ELEMENT GRAPH (#PCDATA)> <!ELEMENT VAR (#PCDATA)> <!ELEMENT CLASS (#PCDATA)> <!ELEMENT PROPERTY (#PCDATA)> <!ELEMENT TYPE (#PCDATA)> <!ELEMENT THRESHOLD (#PCDATA)> <!ELEMENT FILE (#PCDATA)> <!ELEMENT PAGESIZE (#PCDATA)> <!ELEMENT EXECUTION (#PCDATA)> <!ELEMENT GRANULARITY (#PCDATA)> <!ELEMENT OUTPUT (#PCDATA)>
57
lod_final_output=/tmp/lodfinal/
58
lodSourceEntityType=result
59
lodTargetEntityType=result
60
stopwordsReducers=1
61
lodBlocksInput=/tmp/lod_dump/
62
lodBlocksOutput=/tmp/lod_dump/stopwords
63
lod_createCompositekey=true
64
lod_distanceAlgorithm=HAMMING
65
lod_similarityThreshold=0.8
66
lodPrefix=http://lod.openaire.eu/data/result/
67
lodStopwords=a,able,about,above,abst,accordance,according,accordingly,across,act,actually,added,adj,affected,affecting,affects,after,afterwards,again,against,ah,all,almost,alone,along,already,also,although,always,am,among,amongst,an,and,announce,another,any,anybody,anyhow,anymore,anyone,anything,anyway,anyways,anywhere,apparently,approximately,are,aren,arent,arise,around,as,aside,ask,asking,at,auth,available,away,awfully,b,back,be,became,because,become,becomes,becoming,been,before,beforehand,begin,beginning,beginnings,begins,behind,being,believe,below,beside,besides,between,beyond,biol,both,brief,briefly,but,by,c,ca,came,can,cannot,cant,cause,causes,certain,certainly,co,com,come,comes,contain,containing,contains,could,couldnt,d,date,did,didnt,different,do,does,doesnt,doing,done,dont,down,downwards,due,during,e,each,ed,edu,effect,eg,eight,eighty,either,else,elsewhere,end,ending,enough,especially,et,et-al,etc,even,ever,every,everybody,everyone,everything,everywhere,ex,except,f,far,few,ff,fifth,first,five,fix,followed,following,follows,for,former,formerly,forth,found,four,from,further,furthermore,g,gave,get,gets,getting,give,given,gives,giving,go,goes,gone,got,gotten,h,had,happens,hardly,has,hasnt,have,havent,having,he,hed,hence,her,here,hereafter,hereby,herein,heres,hereupon,hers,herself,hes,hi,hid,him,himself,his,hither,home,how,howbeit,however,hundred,i,id,ie,if,ill,im,immediate,immediately,importance,important,in,inc,indeed,index,information,instead,into,invention,inward,is,isnt,it,itd,itll,its,itself,ive,j,just,k,keep,	keeps,kept,kg,km,know,known,knows,l,largely,last,lately,later,latter,latterly,least,less,lest,let,lets,like,liked,likely,line,little,ll,look,looking,looks,ltd,m,made,mainly,make,makes,many,may,maybe,me,mean,means,meantime,meanwhile,merely,mg,might,million,miss,ml,more,moreover,most,mostly,mr,mrs,much,mug,must,my,myself,n,na,name,namely,nay,nd,near,nearly,necessarily,necessary,need,needs,neither,never,nevertheless,new,next,nine,ninety,no,nobody,non,none,nonetheless,noone,nor,normally,nos,not,noted,nothing,now,nowhere,o,obtain,obtained,obviously,of,off,often,oh,ok,okay,old,omitted,on,once,one,ones,only,onto,or,ord,other,others,otherwise,ought,our,ours,ourselves,out,outside,over,overall,owing,own,p,page,pages,part,particular,particularly,past,per,perhaps,placed,please,plus,poorly,possible,possibly,potentially,pp,predominantly,present,previously,primarily,probably,promptly,proud,provides,put,q,que,quickly,quite,qv,r,ran,rather,rd,re,readily,really,recent,recently,ref,refs,regarding,regardless,regards,related,relatively,research,respectively,resulted,resulting,results,right,run,s,said,same,saw,say,saying,says,sec,section,see,seeing,seem,seemed,seeming,seems,seen,self,selves,sent,seven,several,shall,she,shed,shell,shes,should,shouldnt,show,showed,shown,showns,shows,significant,significantly,similar,similarly,since,six,slightly,so,some,somebody,somehow,someone,somethan,something,sometime,sometimes,somewhat,somewhere,soon,sorry,specifically,specified,specify,specifying,still,stop,strongly,sub,substantially,successfully,such,sufficiently,suggest,sup,sure,t,take,taken,taking,tell,tends,th,than,thank,thanks,thanx,that,thatll,thats,thatve,the,their,theirs,them,themselves,then,thence,there,thereafter,thereby,thered,therefore,therein,therell,thereof,therere,theres,thereto,thereupon,thereve,these,they,theyd,theyll,theyre,theyve,think,this,those,thou,though,thoughh,thousand,throug,through,throughout,thru,thus,til,tip,to,together,too,took,toward,towards,tried,tries,truly,try,trying,ts,twice,two,u,un,under,unfortunately,unless,unlike,unlikely,until,unto,up,upon,ups,us,use,used,useful,usefully,usefulness,uses,using,usually,v,value,various,ve,very,via,viz,vol,vols,vs,w,want,wants,was,wasnt,way,we,wed,welcome,well,went,were,werent,weve,what,whatever,whatll,whats,when,whence,whenever,where,whereafter,whereas,whereby,wherein,wheres,whereupon,wherever,whether,which,while,whim,whither,who,whod,whoever,whole,wholl,whom,whomever,whos,whose,why,widely,willing,wish,with,within,without,wont,words,world,would,wouldnt,www,x,y,yes,yet,you,youd,youll,your,youre,yours,yourself,yourselves,youve,z,zero
68
lod_configXML=<?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE LIMES SYSTEM "limes.dtd"> <LIMES> <PREFIX> <NAMESPACE>http://www.w3.org/1999/02/22-rdf-syntax-ns#</NAMESPACE> <LABEL>rdf</LABEL> </PREFIX> <PREFIX> <NAMESPACE>http://www.w3.org/2000/01/rdf-schema#</NAMESPACE> <LABEL>rdfs</LABEL> </PREFIX> <SOURCE> <ID>source1</ID> <ENDPOINT>/user/kanakakis/groundTruth/sourceNT</ENDPOINT> <VAR>?x</VAR> <PAGESIZE>100</PAGESIZE> <RESTRICTION>?x rdf:type http://www.eurocris.org/ontologies/cerif/1.3#ResultEntity</RESTRICTION> <PROPERTY>http://lod.openaire.eu/vocab/year RENAME Year</PROPERTY> <PROPERTY>http://www.w3.org/1999/02/22-rdf-syntax-ns# RENAME type</PROPERTY> <PROPERTY>http://purl.org/dc/terms/identifier RENAME id</PROPERTY> <PROPERTY>http://www.eurocris.org/ontologies/cerif/1.3#name AS lowercase->regexreplace("[^A-Za-z0-9]"," ") RENAME publicationName</PROPERTY> </SOURCE> <TARGET> <ID>source2</ID> <ENDPOINT>/user/kanakakis/groundTruth/targetNT</ENDPOINT> <VAR>?y</VAR> <PAGESIZE>100</PAGESIZE> <RESTRICTION>?y rdf:type http://swrc.ontoware.org/ontology#Article</RESTRICTION> <PROPERTY>http://www.w3.org/1999/02/22-rdf-syntax-ns# RENAME type</PROPERTY> <PROPERTY>http://purl.org/dc/terms/issued RENAME Year</PROPERTY> <PROPERTY>http://purl.org/dc/terms/identifier RENAME id</PROPERTY> <PROPERTY>http://www.w3.org/2000/01/rdf-schema#label AS lowercase->regexreplace("[^A-Za-z0-9]"," ") RENAME articleName</PROPERTY> </TARGET> <METRIC>AND(jaro(x.publicationName,y.articleName)|0.8,jaro(x.Year,y.Year)|1.0)</METRIC> <!-- <METRIC>jaro(x.publicatioName,y.articleName)|0.7</METRIC> --> <ACCEPTANCE> <THRESHOLD>0.8</THRESHOLD> <FILE>/user/kanakakis/groundTruth/accepted_links_0.8_no_purge</FILE> <RELATION>owl:sameAs</RELATION> </ACCEPTANCE> <REVIEW> <THRESHOLD>0.8</THRESHOLD> <FILE>/user/kanakakis/groundTruth/verified_links_0.8</FILE> <RELATION>owl:sameAs</RELATION> </REVIEW> <EXECUTION>Default</EXECUTION> <OUTPUT>TTL</OUTPUT> </LIMES>
69
lod_limesDTD=<?xml version="1.0" encoding="utf-8"?> <!ELEMENT LIMES (PREFIX*, SOURCE, TARGET, METRIC, ACCEPTANCE, REVIEW, EXECUTION*, GRANULARITY*, OUTPUT*)> <!ELEMENT PREFIX (NAMESPACE, LABEL)> <!ELEMENT NAMESPACE (#PCDATA)> <!ELEMENT LABEL (#PCDATA)> <!ELEMENT SOURCE (ID, ENDPOINT, GRAPH*, VAR, PAGESIZE, RESTRICTION+, PROPERTY+, TYPE*)> <!ELEMENT TARGET (ID, ENDPOINT, GRAPH*, VAR, PAGESIZE, RESTRICTION+, PROPERTY+, TYPE*)> <!ELEMENT ID (#PCDATA)> <!ELEMENT RESTRICTION (#PCDATA)> <!ELEMENT METRIC (#PCDATA)> <!ELEMENT ACCEPTANCE (THRESHOLD, FILE, RELATION)> <!ELEMENT REVIEW (THRESHOLD, FILE, RELATION)> <!ELEMENT RELATION (#PCDATA)> <!ELEMENT ENDPOINT (#PCDATA)> <!ELEMENT GRAPH (#PCDATA)> <!ELEMENT VAR (#PCDATA)> <!ELEMENT CLASS (#PCDATA)> <!ELEMENT PROPERTY (#PCDATA)> <!ELEMENT TYPE (#PCDATA)> <!ELEMENT THRESHOLD (#PCDATA)> <!ELEMENT FILE (#PCDATA)> <!ELEMENT PAGESIZE (#PCDATA)> <!ELEMENT EXECUTION (#PCDATA)> <!ELEMENT GRANULARITY (#PCDATA)> <!ELEMENT OUTPUT (#PCDATA)>
(2-2/2)