0.10/metadata/src/main/resources/examples/extern-config.xml

<?xml version="1.0" encoding="UTF-8"?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more contributor
license agreements.  See the NOTICE.txt 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.
-->
<!-- FIXME: change namespace URI? -->
<cas:externextractor xmlns:cas="http://oodt.jpl.nasa.gov/1.0/cas">

	<!--  
	    workingDir: specifies the directory that the external command line met extractor will
	    be run in. 
	    
	    if workingDir is not specified, and if the external command line met extractor honors
	    the workingDir contract (generating .met file in directory that it is called from), then 
	    the .met file will be generated in /path/to/file's parent directory. Otherwise, if the
	    external command let met extractor doesn't honor working dir, then all bets
	    are off.
	    
	    metFileExt: specifies the file extension for the extern met extractor to look for when 
	    reading the generated met file into Java as an in-memory CAS metadata object. The met 
	    file extension is appended to the full file path of the original data file. If not specified, 
	    then the met file extension defaults to &quot;.met&quot;.
	-->
	<exec workingDir="" metFileExt="">
		<!--  this path can be absolute or relative -->
		<!--  you can optionally specify envReplace tag (=true) 
		      to turn on environment variable replacement
		-->
		<extractorBinPath envReplace="true">[PWD]/src/test/gov/nasa/jpl/oodt/cas/metadata/extractors/testExtractor</extractorBinPath>

		<!--  make sure to use character entities if there are any weird
			parameters here that would screw up the XML.
			
			args come after providing the file to this met extractor. So, in other
			words, we assume that extractorBinPath &gt;file&lt; &lt;args...&gt;
			
			where the first parameter is always the file to extract metadata from,
			and the remaining parameters are optional to provide to the underlying
			met extractor.
		-->
		<args>
			<arg isDataFile="true"/>
			<arg isMetFile="true"/>
			<arg>-Dtrue=always</arg>
			<arg>foo</arg>
			<arg>bar</arg>
			<!--  you can optionally specify that you would like environment 
			      variable replacement on a particular argument
			      
			      You can also optionally specify that the argument is a path
			      and that you would like it to be treated as such using the
			      isPath="true". If not specified, the path is treated as if
			      isPath was specified as "false", and String.replaceAll("\\s", "\\\\ ")
			      is not called. If called, all white spaces are replaced from the path
			      (using the above regex), and replaced with the literal string
			      "\ ".
			      
			      The appendExt parameter is used to augment an existing argument 
			      with some specified extension. This is typically used on paths 
			      to add another extension to an argument that's a path. For instance, 
			      you could append the .cas metadata file extension to an existing 
			      path, e.g., the data file path.
			-->
			<arg envReplace="true" isPath="true">[HOME]/test boo</arg>
			<arg appendExt="cas">/full/path/to/somefile.txt</arg>
		</args>
	</exec>

</cas:externextractor>