ka.tika-eval.1.24.1.source-code.tika-eval-comparison-config.xml Maven / Gradle / Ivy
<?xml version="1.0" encoding="UTF-8" standalone="no" ?>
<!--
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.
-->
<tika-batch-config
maxAliveTimeSeconds="-1"
pauseOnEarlyTerminationMillis="500"
timeoutCheckPulseMillis="1000"
maxQueueSize="10000"
numConsumers="5"
timeoutThresholdMillis="300000"
>
<commandline>
<option opt="bc" longOpt="batch-config" hasArg="true"
description="xml batch config file" required="true"/>
<option opt="inputDir" hasArg="true"
description="dir to start crawling"/>
<option opt="numConsumers" hasArg="true"
description="number of fileConsumers threads"/>
<option opt="extractsA" hasArg="true"
description="this dir for analysis" required="false"/>
<option opt="extractsB" hasArg="true"
description="thatDir for analysis"/>
<option opt="db" hasArg="true"
description="name of db directory or file to which to write results"/>
<option opt="alterExtract" hasArg="true"
description="for json-formatted extract files
process full metadata list ('as_is'=default),
take just the first/container document ('first_only'),
concatenate all content into the first metadata item ('concatenate_content')"/>
<option opt="minExtractLength" hasArg="true"
description="minimum extract length to process"/>
<option opt="maxExtractLength" hasArg="true"
description="maximum extract length to process"/>
<option opt="jdbc" hasArg="true"
description="full jdbc connection string"/>
<option opt="jdbcDriver" hasArg="true"
description="canonical class name for jdbc driver"/>
<option opt="tablePrefixA" hasArg="true"
description="EXPERT: prefix for table names for A"/>
<option opt="tablePrefixB" hasArg="true"
description="EXPERT: prefix for table names for B"/>
<option opt="drop" hasArg="false" description="drop tables if they exist"/>
<option opt="maxFilesToAdd" hasArg="true" description="maximum number of files to add to the crawler"/>
<option opt="maxTokens" hasArg="true" description="maximum tokens to process, default=200000"/>
<option opt="maxContentLength" hasArg="true"
description="truncate content beyond this length for calculating 'contents' stats, default=1000000"/>
<option opt="maxContentLengthForLangId" hasArg="true"
description="truncate content beyond this length for language id, default=50000"/>
<option opt="defaultLangCode" hasArg="true"
description="which language to use for common words if no 'common words' file exists for the langid result"/>
</commandline>
<!--
Can also add startDir: this tells the crawler to start indexing a
child directory of the srcDir directory.
-->
<crawler builderClass="org.apache.tika.batch.fs.builders.FSCrawlerBuilder"
crawlOrder="sorted"
maxConsecWaitMillis="30000"
maxFilesToAdd="-1"
maxFilesToConsider="-1"
includeFilePat=""
excludeFilePat=""
/>
<consumers builderClass="org.apache.tika.eval.batch.EvalConsumersBuilder"
consumerBuilderClass="org.apache.tika.eval.batch.ExtractComparerBuilder"
dbAppend="false"
crawlingInputDir="false"
minExtractLength="-1"
maxExtractLength="2000000"
commonTokens="resources/common_tokens"
/>
<!-- langModelDir="resources/langmodels" -->
<!-- reporter and interrupter are optional -->
<reporter builderClass="org.apache.tika.batch.builders.SimpleLogReporterBuilder" sleepMillis="1000"
staleThresholdMillis="500000"/>
</tika-batch-config>