crawl-tests.xml

<?xml version="1.0"?>
<!--
 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.
-->

<!-- Configuration overrides used during unit tests. -->

<configuration>

<property>
  <name>plugin.includes</name>
  <value>parse-tika|protocol-http|urlfilter-suffix|scoring-opic</value>
  <description>Enable required plugins.</description>
</property>

<property>
  <name>content.server.port</name>
  <value>55000</value>
  <description>Port of http server serving content.</description>
</property>

<property>
  <name>fetcher.server.delay</name>
  <value>0.2</value>
  <description>The number of seconds the fetcher will delay between 
   successive requests to the same server.</description>
</property>

<property>
  <name>http.agent.name</name>
  <value>test-nutch</value>
</property>

<property>
  <name>http.robots.agents</name>
  <value>test-nutch,*</value>
</property>

<property>
  <name>http.agent.name.check</name>
  <value>true</value>
</property>

<property>                                                                                                                                                   
  <name>http.robots.agents</name>                                                                                                                            
  <value>test-nutch,*</value>                                                                                                                                
  <description>The agent strings we'll look for in robots.txt files,                                                                                         
  comma-separated, in decreasing order of precedence. You should                                                                                             
  put the value of http.agent.name as the first agent name, and keep the                                                                                     
  default * at the end of the list. E.g.: BlurflDev,Blurfl,*                                                                                                 
  </description>                                                                                                                                             
</property>

<property>
  <name>io.serializations</name>
  <value>org.apache.hadoop.io.serializer.WritableSerialization,org.apache.hadoop.io.serializer.JavaSerialization</value>
  <!-- org.apache.hadoop.io.serializer.avro.AvroSpecificSerialization,
  org.apache.hadoop.io.serializer.avro.AvroReflectSerialization,
  org.apache.hadoop.io.serializer.avro.AvroGenericSerialization, -->
  <description>A list of serialization classes that can be used for
  obtaining serializers and deserializers.</description>
</property>

</configuration>