lucene/benchmark/conf/wstok.alg

# 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.
#
# This alg compares the performance of the original Character.isWhitespace()-based

content.source=org.apache.lucene.benchmark.byTask.feeds.ReutersContentSource
doc.tokenized=false
doc.body.tokenized=true
docs.dir=reuters-out

-AnalyzerFactory(name:WhitespaceTokenizer, WhitespaceTokenizer(rule:java))

-AnalyzerFactory(name:UnicodeWhitespaceTokenizer, WhitespaceTokenizer(rule:unicode))

{ "Rounds"

    -NewAnalyzer(WhitespaceTokenizer)
    -ResetInputs
    { "[Character.isWhitespace()] WhitespaceTokenizer" { ReadTokens > : 20000 }

    -NewAnalyzer(UnicodeWhitespaceTokenizer)
    -ResetInputs
    { "[UnicodeProps.WHITESPACE.get()] UnicodeWhitespaceTokenizer" { ReadTokens > : 20000 }

    NewRound
} : 5
RepSumByNameRound