ka.tika-eval.1.26.source-code.tika-eval-file-profiler-config.xml Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of tika-eval Show documentation
There is a newer version: 3.0.0
<?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="60000"
        timeoutCheckPulseMillis="1000"
        maxQueueSize="50000"
        numConsumers="5"
        timeoutThresholdMillis="900000">

    <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="extracts" hasArg="true"
                description="this dir for analysis" required="false"/>
        <option opt="db" hasArg="true"
                description="name of db directory or file to which to write results"/>
        <option opt="jdbc" hasArg="true"
                description="full jdbc connection string"/>
        <option opt="jdbcDriver" hasArg="true"
                description="canonical class name for jdbc driver"/>
        <option opt="tablePrefix" hasArg="true"
                description="EXPERT: prefix for table names"/>
        <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="timeoutThresholdMillis" hasArg="true" description="timeout per file in milliseconds"/>
        <option opt="maxConsecWaitMillis" hasArg="true" description="max wait for crawler to add file to queue"/>

    </commandline>


    <!--
        Can also add startDir: this tells the crawler to start indexing a
        child directory of the inputDir directory.
    -->
    <crawler builderClass="org.apache.tika.batch.fs.builders.FSCrawlerBuilder"

             crawlOrder="sorted"
             maxConsecWaitMillis="1800000"
             maxFilesToAdd="-1"
             maxFilesToConsider="-1"
             includeFilePat=""
             excludeFilePat=""
             maxFileSizeBytes="-1"
    />

    <consumers builderClass="org.apache.tika.eval.batch.EvalConsumersBuilder"
               consumerBuilderClass="org.apache.tika.eval.batch.FileProfilerBuilder"/>


    <!-- reporter and interrupter are optional -->
    <reporter builderClass="org.apache.tika.batch.builders.SimpleLogReporterBuilder" sleepMillis="1000"
              staleThresholdMillis="500000"/>
</tika-batch-config>