0.8.1-rc1/pge/src/main/resources/examples/Crawler/mime-extractor-map.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.
-->
<cas:mimetypemap xmlns:cas="http://oodt.jpl.nassa.gov/1.0/cas" magic="false"
    mimeRepo="mime-types.xml">

  <!-- This will be the default extractor used if product doesn't match any
    of the mime-types defined in mime-types.xml file (this element is optional) -->
  <default>
    <!-- you can put a default NamingConvention here too.
    <namingConvention id="PDFNamingConv" />
    -->
    <!-- You can add multiple extractors here if there are more than one,
      however extractor is optional, so below extractor can be removed -->
    <extractor class="org.apache.oodt.cas.metadata.extractors.MetReaderExtractor" />
  </default>

  <mime type="all/products">
    <extractor class="org.apache.oodt.cas.metadata.extractors.MetReaderExtractor" />
  </mime>

  <!-- Example type where PGE generates a metadata file for the product, but
    the product also needs additional metadata extraction from it... in the
    mime-types.xml file txt/product has super type all/products, which means
    that for any product that is a txt/product then all/products extractors
    will be first be run on it (which, in this case, is just one extractor
    which reads in the existing metadata file) followed by txt/product
    extractors which is a filename based extractor. -->
  <mime type="txt/product">
    <extractor class="org.apache.oodt.cas.metadata.extractors.FilenameTokenMetExtractor">
      <config file="filename.extractor.config.xml" />
    </extractor>
  </mime>

  <!-- This is an example of a type where only one extractor is run on
    product, this is because pdf/product only specifies one extractor and
    in mime-types.xml file pdf/product has no super type. -->
  <mime type="pdf/product">
    <namingConvention id="PDFNamingConv" />
    <extractor class="org.apache.oodt.cas.metadata.extractors.FilenameTokenMetExtractor">
      <config file="filename.extractor.config.xml" />
    </extractor>
  </mime>

  <!-- This is an example of a type where two extractors get run... this case
    is an alternative way of handling txt/product... txt/product will run
    the same 2 extractors which this type will run but for different reasons...
    doc/product doesn't have any super type, it instead defines both extractors
    directly to itself. -->
  <mime type="doc/product">
    <extractor class="org.apache.oodt.cas.metadata.extractors.MetReaderExtractor" />
    <extractor class="org.apache.oodt.cas.metadata.extractors.FilenameTokenMetExtractor">
      <config file="filename.extractor.config.xml" />
    </extractor>
  </mime>
</cas:mimetypemap>