[Archive-access-cvs] archive-access/projects/nutch/conf nutch-site.xml,1.24.2.3,1.24.2.4

[Doug C. <cu...@us...>]

Update of /cvsroot/archive-access/archive-access/projects/nutch/conf
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv27408/conf

Modified Files:
      Tag: mapred
	nutch-site.xml 
Log Message:
Pre-au fixes.

Index: nutch-site.xml
===================================================================
RCS file: /cvsroot/archive-access/archive-access/projects/nutch/conf/nutch-site.xml,v
retrieving revision 1.24.2.3
retrieving revision 1.24.2.4
diff -C2 -d -r1.24.2.3 -r1.24.2.4
*** nutch-site.xml	1 Sep 2005 18:45:29 -0000	1.24.2.3
--- nutch-site.xml	20 Oct 2005 23:30:48 -0000	1.24.2.4
***************
*** 9,83 ****
  <!-- <property> -->
  <!--   <name>fs.default.name</name> -->
! <!--   <value>ia109102:8009</value> -->
  <!-- </property> -->
  
- <property>
-   <name>ndfs.name.dir</name>
-   <value>/0/nutch/ndfs/names</value>
- </property>
- 
- <property>
-   <name>ndfs.data.dir</name>
-   <value>/0/nutch/ndfs/doug,/1/nutch/ndfs/doug</value>
- </property>
- 
- <property>
-   <name>ndfs.replication</name>
-   <value>2</value>
- </property>
- 
  <!-- MapReduce -->
  
  <!-- <property> -->
  <!--   <name>mapred.job.tracker</name> -->
! <!--   <value>ia109102:8010</value> -->
! <!-- </property> -->
! 
! <!-- <property> -->
! <!--   <name>mapred.job.tracker.info.port</name> -->
! <!--   <value>7846</value> -->
! <!-- </property> -->
! 
! <!-- <property> -->
! <!--   <name>mapred.local.dir</name> -->
! <!--   <value>/0/nutch/mapred/local</value> -->
! <!-- </property> -->
! 
! <!-- <property> -->
! <!--   <name>mapred.system.dir</name> -->
! <!--   <value>/mapred/system</value> -->
! <!-- </property> -->
! 
! <!-- <property> -->
! <!--   <name>mapred.task.timeout</name> -->
! <!--   <value>3600000</value> -->
  <!-- </property> -->
  
  <!-- Override a few Nutch defaults -->
  
- 
- <!-- Enable parse-ext (parse-ext is a parser that calls the 'ext'ernal program
- xpdf to parse pdf files. Also enable parse-default and the ia plugins.
- -->
  <property>
!   <name>plugin.includes</name>
!   <value>urlfilter-regex|parse-(text|html|ext|default)|index-(basic|ia)|query-(basic|site|url|ia)</value>
  </property>
  
! <!-- keep all links, not just inter-host -->
! <!-- db updates will be FASTER if set to true.
!     Downside is that link text from same site won't be included.
!     (More valuable to take anchor text from other hosts).  Use this
!     if wide variety of sites to index.
! -->
  <property>
!   <name>db.ignore.internal.links</name>
!   <value>false</value>
  </property>
  
- <!-- use in-degree as poor-man's link analysis -->
  <property>
!   <name>indexer.boost.by.link.count</name>
!   <value>true</value>
  </property>
  
--- 9,38 ----
  <!-- <property> -->
  <!--   <name>fs.default.name</name> -->
! <!--   <value>ia109102.archive.org:8009</value> -->
  <!-- </property> -->
  
  <!-- MapReduce -->
  
  <!-- <property> -->
  <!--   <name>mapred.job.tracker</name> -->
! <!--   <value>ia109102.archive.org:8010</value> -->
  <!-- </property> -->
  
  <!-- Override a few Nutch defaults -->
  
  <property>
!   <name>archive.collection</name>
!   <value>au</value>
  </property>
  
! <!-- the name of the archive server hosting this archive -->
  <property>
!   <name>archive.host</name>
!   <value>crawls.archive.org</value>
  </property>
  
  <property>
!   <name>plugin.includes</name>
!   <value>urlfilter-regex|parse-(text|html|js|ext)|index-(basic|ia)|query-(basic|site|url|ia)</value>
  </property>
  
***************
*** 132,160 ****
  </property>
  
- <!-- the name of the archive server hosting this archive -->
- <property>
-   <name>archive.host</name>
-   <value>crawls.archive.org</value>
- </property>
- 
- <!-- The name of this archive collection.
-     DEPRECATED.  Now search.jsp uses the 'collection' returned by the search
-     result drawing up the wayback URL and at index time, use the
-     command-line 'collection' option.
- 
- <property>
-   <name>archive.collection</name>
-   <value>be05</value>
- </property>
- -->
- 
- <!--Optionally, hardcode the nutch datadir location rather
-     than rely on tomcat startup location.
- <property>
-     <name>searcher.dir</name>
-     <value>/home/stack/workspace/nutch-datadir</value>
- </property>
-  -->
- 
   <!--If set to true, all contenttypes are indexed.  Otherwise we only
       index text/* and application/*
--- 87,90 ----
***************
*** 164,166 ****
--- 94,97 ----
    <value>false</value>
  </property>
+ 
  </nutch-conf>