Lucene example source code file (sample.alg)

This example Lucene source code file (sample.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

asf, asf, createindex, license, license, optimize, populatelong, populateshort, resetsystemerase, see, the, the, you, you

The Lucene sample.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.
# */
# --------------------------------------------------------
# 
# Sample: what is the effect of doc size on indexing time?
#
# There are two parts in this test:
# - PopulateShort adds 2N documents of length  L
# - PopulateLong  adds  N documents of length 2L
# Which one would be faster?
# The comparison is done twice.
#
# --------------------------------------------------------

# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.

merge.factor=mrg:10:20
max.buffered=buf:100:1000
compound=true

analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory

doc.stored=true
doc.tokenized=true
doc.term.vector=false
log.step=500

docs.dir=reuters-out
#docs.dir=reuters-111

content.source=org.apache.lucene.benchmark.byTask.feeds.SingleDocSource
#content.source=org.apache.lucene.benchmark.byTask.feeds.ReutersContentSource

query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker

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

log.queries=false
# -------------------------------------------------------------------------------------

{

    { "PopulateShort"
        CreateIndex
        { AddDoc(4000) > : 20000
        Optimize
        CloseIndex
    >

    ResetSystemErase
    
    { "PopulateLong"
        CreateIndex
        { AddDoc(8000) > : 10000
        Optimize
        CloseIndex
    >

    ResetSystemErase

    NewRound

} : 2

RepSumByName
RepSelectByPref Populate