Re: [Archive-access-discuss] Wayback question

[Natalia T. <nt...@ce...>]

Hi Mathew
I review web.xml and both paths are the same directory...

The incoming path in resourceIndex

         <param-name>resourceindex.incomingpath</param-name>
         <param-value>/wayback/index-data/incoming</param-value>

and the target in resourceStore
         <param-name>resourcestore.indextarget</param-name>
         <param-value>/wayback/index-data/incoming</param-value>


Any others ideas?
Here is the full web.xml

<?xml version="1.0"?>
<!DOCTYPE web-app PUBLIC "-//Sun Microsystems, Inc.//DTD Web Application 
2.3//EN"
	"http://java.sun.com/dtd/web-app_2_3.dtd">
<web-app>

	<!-- General Installation information
	 -->

     <context-param>
         <param-name>installationname</param-name>
         <param-value>General Configuration</param-value>
         <description>
             This text will appear on the Wayback Configuration and 
Status page
             and may assist in determining which installation users are 
viewing
             via their web browser in environments with multiple Wayback
             installations.
         </description>
     </context-param>

     <listener>
 
<listener-class>org.archive.wayback.core.WaybackContextListener</listener-class>
     </listener>
<!-- START OF  Timeline UI  OPTIONS
This section contains configuration for using the wayback machine in 
timeline
access mode, similar to the WERA application.

These options are not used by default.
-->
     <servlet>
         <servlet-name>XMLQueryServlet</servlet-name>
 
<servlet-class>org.archive.wayback.query.QueryServlet</servlet-class>
         <init-param>
             <param-name>queryui.jsppath</param-name>
             <param-value>jsp/QueryXMLUI</param-value>
         </init-param>
     </servlet>
     <servlet-mapping>
         <servlet-name>XMLQueryServlet</servlet-name>
         <url-pattern>/xmlquery</url-pattern>
     </servlet-mapping>
	
     <servlet>
         <servlet-name>QueryServlet</servlet-name>
     	<servlet-class>org.archive.wayback.query.QueryServlet</servlet-class>
         <init-param>
             <param-name>queryui.jsppath</param-name>
             <param-value>jsp/QueryUI</param-value>
         </init-param>
     </servlet>
     <servlet-mapping>
	<servlet-name>QueryServlet</servlet-name>
	<url-pattern>/query</url-pattern>
     </servlet-mapping>

     <servlet>
	<servlet-name>TimelineQueryServlet</servlet-name>
     	<servlet-class>org.archive.wayback.query.QueryServlet</servlet-class>
         <init-param>
             <param-name>queryui.jsppath</param-name>
             <param-value>jsp/TimelineUI</param-value>
         </init-param>
     </servlet>
     <servlet-mapping>
	<servlet-name>TimelineQueryServlet</servlet-name>
	<url-pattern>/timeline</url-pattern>
     </servlet-mapping>

     <servlet>
	<servlet-name>FramesetReplayServlet</servlet-name>
 
<servlet-class>org.archive.wayback.replay.ReplayServlet</servlet-class>
     	<init-param>
	    <param-name>replayrenderer.classname</param-name>
 
<param-value>org.archive.wayback.timeline.FramesetReplayRenderer</param-value>
             <description>Implementation responsible for drawing 
replayed resources and replay error messages</description>
         </init-param>
     </servlet>
     <servlet-mapping>
         <servlet-name>FramesetReplayServlet</servlet-name>
         <url-pattern>/frameset</url-pattern>
     </servlet-mapping>

     <servlet>
	<servlet-name>InlineReplayServlet</servlet-name>
 
<servlet-class>org.archive.wayback.replay.ReplayServlet</servlet-class>
         <init-param>
             <param-name>replayrenderer.classname</param-name>
 
<param-value>org.archive.wayback.timeline.TimelineReplayRenderer</param-value>
             <description>Implementation responsible for drawing 
replayed resources and replay error messages</description>
         </init-param>
     </servlet>
     <servlet-mapping>
         <servlet-name>InlineReplayServlet</servlet-name>
         <url-pattern>/replay</url-pattern>
     </servlet-mapping>

     <servlet>
         <servlet-name>MetaReplayServlet</servlet-name>
 
<servlet-class>org.archive.wayback.replay.ReplayServlet</servlet-class>
         <init-param>
             <param-name>replayrenderer.classname</param-name>
 
<param-value>org.archive.wayback.timeline.MetaReplayRenderer</param-value>
             <description>Implementation responsible for drawing 
replayed resources and replay error messages</description>
         </init-param>
     </servlet>
     <servlet-mapping>
         <servlet-name>MetaReplayServlet</servlet-name>
         <url-pattern>/meta</url-pattern>
     </servlet-mapping>


     <context-param>
         <param-name>replayui.jsppath</param-name>
         <param-value>jsp/ReplayUI</param-value>
         <description>ReplayUI specific path to jsp pages. relative to 
webapp/</description>
     </context-param>

     <context-param>
	<param-name>queryrenderer.classname</param-name>
	<param-value>org.archive.wayback.timeline.TimelineQueryRenderer</param-value>
	<description>Implementation responsible for drawing Index Query 
results</description>
     </context-param>

     <context-param>
         <param-name>replayuriconverter.classname</param-name>
 
<param-value>org.archive.wayback.timeline.TimelineReplayResultURIConverter</param-value>
         <description>Class that implements translation of index results 
to Replayable URIs for this Wayback</description>
     </context-param>



     <context-param>
         <param-name>jsuri</param-name>
 
<param-value>http://recercat.test.cesca.es/wayback/jsp/TimelineUI/wm-timeline-text.js,http://recercat.test.cesca.es/wayback/jsp/TimelineUI/wm-timeline.js</param-value>
         <description>HTTP URI to javascript files</description>
     </context-param>
	

     <context-param>
         <param-name>replayuriprefix</param-name>
 
<param-value>http://recercat.test.cesca.es/wayback/replay</param-value>
         <description>HTTP URI prefix for the replay servlet</description>
     </context-param>

     <context-param>
         <param-name>metauriprefix</param-name>
 
<param-value>http://recercat.test.cesca.es/wayback/meta</param-value>
         <description>HTTP URI prefix for the meta replay 
servlet</description>
     </context-param>

     <context-param>
         <param-name>timelineuriprefix</param-name>
 
<param-value>http://recercat.test.cesca.es/wayback/timeline</param-value>
         <description>HTTP URI prefix for the timeline servlet</description>
     </context-param>

     <context-param>
         <param-name>frameseturiprefix</param-name>
 
<param-value>http://recercat.test.cesca.es/wayback/frameset</param-value>
         <description>HTTP URI prefix for the frameset servlet</description>
     </context-param>
<!-- END OF  Timeline UI  OPTIONS -->

<!-- START OF  Local-ARC ResourceStore  OPTIONS
This section contains configuration for accessing ARC files from a single
directory on a local filesystem. If ARC files are spread across multiple
local directories, a single directory be created, and populated with 
symbolic
links to the various locations of the ARC files. This configuration 
section also
contains specific configuration for an indexing thread, which can optionally
notice new ARC files, generate CDX flat files for new ARCs, and hand off 
these
CDX files to a BDB resource index for merging.
-->
	
     <context-param>
         <param-name>resourcestore.classname</param-name>
 
<param-value>org.archive.wayback.resourcestore.LocalARCResourceStore</param-value>
         <description>Class that implements ResourceStore for this 
Wayback</description>
     </context-param>

     <context-param>
         <param-name>resourcestore.arcpath</param-name>
         <param-value>/dades/arcs</param-value>
         <description>
             Directory where ARC files are found (possibly where 
Heritrix writes them.)
             This directory must exist.
         </description>
     </context-param>

     <context-param>
         <param-name>resourcestore.autoindex</param-name>
         <param-value>1</param-value>
         <description>
             If this is set to '1', then a background thread is launched 
that
             detects new ARC files appearing in arcpath. New ARCs are 
indexed,
             and a CDX flat file, with one line per ARC Record is 
created, one
             CDX file per ARC. These CDX files are then handed off to 
the index
             for incorporation into the index.
         </description>
     </context-param>

     <context-param>
         <param-name>resourcestore.tmppath</param-name>
         <param-value>/wayback/arc-indexer/tmp</param-value>
         <description>
             Directory where CDX files are created temporarily. This is a
             scratch space directory, which must exist.
         </description>
     </context-param>

     <context-param>
         <param-name>resourcestore.workpath</param-name>
         <param-value>/wayback/arc-indexer/work</param-value>
         <description>
             Directory which holds empty flag files indicating that ARC 
files
             are waiting to be indexed.
             This directory must exist.
         </description>
     </context-param>

     <context-param>
         <param-name>resourcestore.queuedpath</param-name>
         <param-value>/wayback/arc-indexer/queued</param-value>
         <description>
             Directory which holds empty flag files indicating that ARC 
files
             have already been seen and queued for indexing.
             This directory must exist.
         </description>
     </context-param>

     <context-param>
         <param-name>resourcestore.indextarget</param-name>
         <param-value>/wayback/index-data/incoming</param-value>
         <description>
             Directory or URL where CDX files are sent after they are 
created. If
             the value of this parameter begins with http://, then the 
value is
             assumed to be a URL where CDX files are PUT, on a possibly 
remote
             resourceindex node. If the value does not begin with 
http://, then
             the value is assumed to be a local directory, which must 
exist,
             where completed CDX files are moved for incorporation into the
             index.
         </description>
     </context-param>

     <context-param>
         <param-name>resourcestore.indexinterval</param-name>
         <param-value>1000</param-value>
         <description>
             Millisecond interval between checks for new ARCs that need 
to be
             processed. This is only the initial time slept when first 
starting
             up, and after any new files are found. Each interval that 
no new
             ARCs are detected, the duration slept increases by this amount.
         </description>
     </context-param>

<!-- END OF  Local-ARC ResourceStore  OPTIONS -->


<!-- START OF  Local-BDB ResourceIndex  OPTIONS
This section contains configuration for using a BDB JE to hold the document
index on the local filesystem. This section also contains configuration for
an optional index update thread, which will scan a directory for new 
index data,
in CDX format, and will automatically add new index records to the 
index.This
is the default index storage implementation.
-->
	
     <filter>
         <filter-name>RemoteSubmitFilter</filter-name>
 
<filter-class>org.archive.wayback.resourceindex.indexer.RemoteSubmitFilter</filter-class>
         <init-param>
             <param-name>pipeline.statusjsp</param-name>
             <param-value>jsp/PipelineUI/PipelineStatus.jsp</param-value>
         </init-param>
     </filter>
     <filter-mapping>
         <filter-name>RemoteSubmitFilter</filter-name>
         <url-pattern>/index-incoming/*</url-pattern>
     </filter-mapping>

     <context-param>
         <param-name>resourceindex.classname</param-name>
 
<param-value>org.archive.wayback.resourceindex.LocalResourceIndex</param-value>
         <description>Class that implements ResourceIndex for this 
Wayback</description>
     </context-param>

     <context-param>
         <param-name>resourceindex.sourceclass</param-name>
         <param-value>BDB</param-value>
         <description>Class that implements ResultSource for this Wayback,
         currently: BDB|CDX</description>
     </context-param>

     <context-param>
         <param-name>resourceindex.indexpath</param-name>
         <param-value>/wayback/index</param-value>
         <description>
             LocalBDBResourceIndex specific directory to store the BDB 
files.
             Directory must exists.
         </description>
     </context-param>

     <context-param>
         <param-name>resourceindex.dbname</param-name>
         <param-value>DB1</param-value>
         <description>
             LocalBDBResourceIndex specific name for BDB database
         </description>
     </context-param>

     <context-param>
         <param-name>resourceindex.incomingpath</param-name>
         <param-value>/wayback/index-data/incoming</param-value>
         <description>
             BDB index-specific configuration that indicates new CDX 
format flat
             files will appear in the directory named in the value of 
this param.
             If this configuration is present and non-empty, a 
background thread
             will be started that monitors this directory, and adds CDX 
records
             in files found in this directory to the index.
         </description>
     </context-param>

     <context-param>
         <param-name>resourceindex.mergedpath</param-name>
         <param-value>/wayback/index-data/merged</param-value>
         <description>
             If this value is present and non-empty, then CDX files that are
             successfully processed from incoming are moved to this 
directory
             after merging. If this option is missing or blank, CDX 
files are
             deleted after merging.
         </description>
     </context-param>

     <context-param>
         <param-name>resourceindex.failedpath</param-name>
         <param-value>/wayback/index-data/failed</param-value>
         <description>
             If this value is present and non-empty, then CDX files that 
fail to
             parse successfully are moved to this directory after a single
             attempt. If this option is missing or blank, malformed CDX 
files are
             left in the incoming directory and repeatedly re-attempted 
until
             some other process moves them out of the way or fixes them.
         </description>
     </context-param>

     <context-param>
         <param-name>resourceindex.mergeinterval</param-name>
         <param-value>10000</param-value>
         <description>
             Millisecond interval between checks for new files in the 
incoming
             directory. This is only the starting number, when no new 
files are
             found in the directory. Each subsequent interval will 
increase by
             this number of ms, until a file is found, at which point the
             interval will revert to the initial level.
         </description>
     </context-param>

     <context-param>
         <param-name>maxresults</param-name>
         <param-value>1000</param-value>
         <description>
         	Maximum number of results to return from the ResourceIndex.
         </description>
     </context-param>

<!-- END OF  Local-BDB ResourceIndex  OPTIONS -->


</web-app>

Thanks,

Natalia