Lucene example source code file (collector.alg)

This example Lucene source code file (collector.alg) is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" ^TM.

Java - Lucene tags/keywords

apache, asf, closereader, license, license, openreader, repsumbypref, repsumbypref, repsumbyprefround, repsumbyprefround, searchwithpostsortcollector, searchwithpostsortcollector, see, you

The Lucene collector.alg source code

#/**
# * Licensed to the Apache Software Foundation (ASF) under one or more
# * contributor license agreements.  See the NOTICE file distributed with
# * this work for additional information regarding copyright ownership.
# * The ASF licenses this file to You under the Apache License, Version 2.0
# * (the "License"); you may not use this file except in compliance with
# * the License.  You may obtain a copy of the License at
# *
# *     http://www.apache.org/licenses/LICENSE-2.0
# *
# * Unless required by applicable law or agreed to in writing, software
# * distributed under the License is distributed on an "AS IS" BASIS,
# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# * See the License for the specific language governing permissions and
# * limitations under the License.
# */
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.

# collector.class can be:
#    Fully Qualified Class Name of a Collector with a empty constructor
#    topScoreDocOrdered - Creates a TopScoreDocCollector that requires in order docs
#    topScoreDocUnordered - Like above, but allows out of order
collector.class=coll:topScoreDocOrdered:topScoreDocUnordered:topScoreDocOrdered:topScoreDocUnordered

analyzer=org.apache.lucene.analysis.WhitespaceAnalyzer
directory=FSDirectory
#directory=RamDirectory

doc.stored=true
doc.tokenized=true
doc.term.vector=false
log.step=100000

search.num.hits=1000000

content.source=org.apache.lucene.benchmark.byTask.feeds.LongToEnglishContentSource


query.maker=org.apache.lucene.benchmark.byTask.feeds.LongToEnglishQueryMaker

# task at this depth or less would print when they start
task.max.depth.log=2

log.queries=true
# -------------------------------------------------------------------------------------

{ "Rounds"

    ResetSystemErase

    { "Populate"
        CreateIndex
        { "MAddDocs" AddDoc } : 2000000
        Optimize
        CloseIndex
    }

    OpenReader
    { "topDocs" SearchWithCollector > : 10
    CloseReader

#    OpenReader
#uses an array of search.num.hits size, but can also take in a parameter
#    { "psc" SearchWithPostSortCollector > : 10
#    { "psc100" SearchWithPostSortCollector(100) > : 10
#    { "psc1000" SearchWithPostSortCollector(1000) > : 10
#    { "psc10000" SearchWithPostSortCollector(10000) > : 10
#    { "psc50000" SearchWithPostSortCollector(50000) > : 10
#    CloseReader

    RepSumByPref topDocs
#    RepSumByPref psc
#    RepSumByPref psc100
#    RepSumByPref psc1000
#    RepSumByPref psc10000
#    RepSumByPref psc50000

    NewRound

} : 4

#RepSumByNameRound
#RepSumByName
#RepSumByPrefRound topDocs
#RepSumByPrefRound psc
#RepSumByPrefRound psc100
#RepSumByPrefRound psc1000
#RepSumByPrefRound psc10000
#RepSumByPrefRound psc50000