# $Id: index.properties $ fgsindex.indexName = INDEXNAME fgsindex.operationsImpl = dk.defxws.fgslucene.OperationsImpl fgsindex.defaultUpdateIndexDocXslt = INDEXINGDOCXSLT fgsindex.defaultUpdateIndexResultXslt = updateIndexToResultPage fgsindex.defaultGfindObjectsResultXslt = gfindObjectsToResultPage fgsindex.defaultBrowseIndexResultXslt = browseIndexToResultPage fgsindex.defaultGetIndexInfoResultXslt = copyXml #fgsindex.indexDir = <...> fgsindex.indexDir = INDEXDIR fgsindex.analyzer = org.apache.lucene.analysis.standard.StandardAnalyzer fgsindex.fieldAnalyzers = dc.title::org.apache.lucene.analysis.standard.StandardAnalyzer dc.creator::org.apache.lucene.analysis.standard.StandardAnalyzer # used to index and query TOKENIZED index fields # for UN_TOKENIZED index fields see fgsindex.untokenizedFields further down #Stopwords file for the analyzer, comment the line if no stopwords #fgsindex.stopwordsLocation = /stopwords.txt fgsindex.defaultQueryFields = dc.description dc.title # setting of org.apache.lucene.queryParser.QueryParser setAllowLeadingWildcard() # Set to true to allow leading wildcard characters, * or ? # Default: false. fgsindex.allowLeadingWildcard = false # setting of org.apache.lucene.queryParser.QueryParser setLowercaseExpandedTerms() # Whether terms of wildcard, prefix, fuzzy and range queries are to be automatically lower-cased or not. # Default: true. fgsindex.lowercaseExpandedTerms = true #sortFields may be given as parameter to gfindObjects, or as config default. ########### # as parameter: ?operation=gfindObjects&sortFields=[sortFieldsValue]&... # as config default: #fgsindex.defaultSortFields = sortFieldsValue #examples: #fgsindex.defaultSortFields = PID,STRING,true #fgsindex.defaultSortFields = sf1,SCORE;sf2,cy-GB-var,true # sortFieldsValue ::= [sortField[';'sortField]*] # sortField ::= sortFieldName[','(sortType | locale | comparatorClass)[','reverse]]]] # sortFieldName ::= #the name of an index field, which is UN_TOKENIZED and contains a single term per document # sortType ::= 'BYTE' | 'DOC' | 'DOUBLE' | 'FLOAT' | 'INT' | 'LONG' | 'SCORE' | 'SHORT' | 'STRING' | 'STRING_VAL' # locale ::= language['-'country['-'variant]] # comparatorClass ::= package-path'.'className['('param['-'param]*')'] # reverse ::= 'false' (default) | 'true' | 'reverse' # sortType 'AUTO' is removed in Lucene 3.x # The test class dk.defxws.fedoragsearch.test.ComparatorSourceTest has been removed in GSearch 2.3, # because the interface org.apache.lucene.search.SortComparatorSource is deprecated in Lucene 3.x # Briefly, one or more sortFields will determine the sequence of search results, # as defined either by sortType or by locale, and it may be in reverse. # If no sortFieldsValue is given, then this code from GSearch is run # TopDocs hits = searcher.search(query, numHits); // in dk.defxws.fgslucene.Statement.java # where the sequence is by default. # If a sortFieldsValue is given, then this code is run # TopDocs hits = searcher.search(query, numHits, sort); # where sort is an instance of org.apache.lucene.search.Sort, see # http://lucene.apache.org/java/3_3_0/api/index.html # See org.apache.lucene.search.SortField for more about sortType, locale and reverse values. #fgsindex.untokenizedFields = list of index fields created as UN_TOKENIZED ########################### # Effect: during search the KeywordAnalyzer is used for untokenized fields, # while the fgsindex.analyzer is used for other fields. # Only untokenized fields, which do not occur in every index document, # need be listed here. # example: #fgsindex.untokenizedFields = fgs.contentModel uf1 uf2 fgsindex.untokenizedFields = PID # snippets ########## #fgsindex.snippetBegin = fgsindex.snippetBegin = ## this value is default if not specified #fgsindex.snippetEnd = fgsindex.snippetEnd = ## this value is default if not specified # optimization see e.g. http://www.onjava.com/pub/a/onjava/2003/03/05/lucene.html ############## # fgsindex.mergeFactor = 10 fgsindex.mergeFactor = 100 ## 10 is default if not specified # fgsindex.maxBufferedDocs = 10 fgsindex.maxBufferedDocs = 100 ## 10 is default if not specified # fgsindex.defaultWriteLockTimeout = 1000 #fgsindex.defaultWriteLockTimeout = 0 fgsindex.defaultWriteLockTimeout = @indexwritelocktimeout@ ## 0 is default if not specified # from http://lucene.apache.org/java/2_3_0/api/IndexWriter.html : ## mergeFactor ## determines how often segment indices are merged by addDocument(). ## With smaller values, less RAM is used while indexing, and searches on unoptimized indices are faster, ## but indexing speed is slower. With larger values, more RAM is used during indexing, ## and while searches on unoptimized indices are slower, indexing is faster. ## Thus larger values (> 10) are best for batch index creation, ## and smaller values (< 10) for indices that are interactively maintained. ## maxBufferedDocs ## determines the minimal number of documents required ## before the buffered in-memory documents are merged and a new Segment is created. ## Since Documents are merged in a RAMDirectory, large value gives faster indexing. ## At the same time, mergeFactor limits the number of files open in a FSDirectory. ## defaultWriteLockTimeout ## sets the default maximum time to wait for a write lock (in milliseconds). # ...?operation=updateIndex&action=optimize ## will perform IndexWriter.optimize() ## which merges all segments together into a single segment, optimizing an index for search. # custom URIResolver #################### #fgsindex.uriResolver = dk.defxws.fedoragsearch.server.URIResolverImpl