source: nutchez-0.1/conf/nutch-site.xml @ 220

<configuration>
<property>
  <name>http.agent.name</name>
  <value>user</value>
  <description>HTTP 'User-Agent' request header. </description> 
</property>
<property>
  <name>http.agent.description</name>
  <value>MyTest</value>
  <description>Further description</description> 
</property>
<property>
  <name>http.agent.url</name> 
  <value>localhost</value> 
  <description>A URL to advertise in the User-Agent header. </description> 
</property>
<property>
  <name>http.agent.email</name>
  <value>you@yous</value> 
  <description>An email address 
  </description> 
</property>
<property>
  <name>plugin.folders</name>
  <value>/opt/nutchez/nutch/plugins</value>
  <description>Directories where nutch plugins are located. </description>
</property>
<property>
  <name>plugin.includes</name>
  <value>protocol-http|urlfilter-regex|parse-(text|html|ext|msexcel|mspowerpoint|msword|oo|pdf|rss|zip)|index-(more|basic|anchor)|query-(more|basic|site|url)|response-(json|xml)|summary-basic|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
  <description> Regular expression naming plugin directory names</description>
 </property>
 <property>
  <name>parse.plugin.file</name>
  <value>parse-plugins.xml</value>
  <description>The name of the file that defines the associations between
  content-types and parsers.</description>
 </property>
 <property>
   <name>db.max.outlinks.per.page</name>
   <value>-1</value>
   <description> </description>
 </property> 
 <property>
   <name>http.content.limit</name> 
   <value>-1</value>
 </property>
<property>
  <name>indexer.mergeFactor</name>
  <value>500</value>
  <description>The factor that determines the frequency of Lucene segment
  merges. This must not be less than 2, higher values increase indexing
  speed but lead to increased RAM usage, and increase the number of
  open file handles (which may lead to "Too many open files" errors).
  NOTE: the "segments" here have nothing to do with Nutch segments, they
  are a low-level data unit used by Lucene.
  </description>
</property>

<property>
  <name>indexer.minMergeDocs</name>
  <value>500</value>
  <description>This number determines the minimum number of Lucene
  Documents buffered in memory between Lucene segment merges. Larger
  values increase indexing speed and increase RAM usage.
  </description>
</property>
<property>
  <name>db.ignore.external.links</name>
  <value>false</value>
  <description>If true, outlinks leading from a page to external hosts
  will be ignored. This is an effective way to limit the crawl to include
  only initially injected hosts, without creating complex URLFilters.
  </description>
</property>
<property>
  <name>file.content.limit</name>
  <value>1000000</value>
  <description>The length limit for downloaded content, in bytes.
  If this value is nonnegative (>=0), content longer than it will be truncated;
  otherwise, no truncation at all.
  </description>
</property>
</configuration>