From: <bra...@us...> - 2009-11-06 03:16:00
|
Revision: 2902 http://archive-access.svn.sourceforge.net/archive-access/?rev=2902&view=rev Author: bradtofel Date: 2009-11-06 03:15:50 +0000 (Fri, 06 Nov 2009) Log Message: ----------- Updated comments and provided additional deployment examples. Modified Paths: -------------- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/wayback.xml Modified: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/wayback.xml =================================================================== --- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/wayback.xml 2009-11-06 02:56:35 UTC (rev 2901) +++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/wayback.xml 2009-11-06 03:15:50 UTC (rev 2902) @@ -24,7 +24,6 @@ The ResourceFileLocationDB implementation to use for mapping ARC/WARC names to absolute paths/URLs via a BDBJE database. --> - <bean id="resourcefilelocationdb" class="org.archive.wayback.resourcestore.locationdb.BDBResourceFileLocationDB"> <property name="bdbPath" value="${wayback.basedir}/file-db/db/" /> <property name="bdbName" value="DB1" /> @@ -32,6 +31,15 @@ </bean> <!-- + The following bean provides an alternate flat-file based LocationDB + implementation. +--> +<!-- + <bean id="resourcefilelocationdb" class="org.archive.wayback.resourcestore.locationdb.FlatFileResourceFileLocationDB"> + <property name="path" value="${wayback.basedir}/path-index.txt" /> + </bean> +--> +<!-- To enable manual management of, or remote access to the above locationDB, uncomment the following bean. --> @@ -47,11 +55,10 @@ Required when using the SimpleResourceStore to access distributed ARC/WARC files over HTTP through a single reverse proxy. --> -<!-- + <bean name="8080:fileproxy" class="org.archive.wayback.resourcestore.locationdb.FileProxyServlet"> <property name="locationDB" ref="resourcefilelocationdb" /> </bean> ---> <!-- @@ -61,11 +68,21 @@ --> <import resource="BDBCollection.xml"/> <!-- - <import resource="NutchCollection.xml"/> <import resource="CDXCollection.xml"/> <import resource="RemoteCollection.xml"/> + <import resource="NutchCollection.xml"/> --> +<!-- + LiveWeb.xml contains beans that enable fetching content from the live + web, and caching those results in ARC files. This import is needed if you + use the "excluder-factory-robot" exclusionFactory property of the + AccessPoints, which will cause live robots.txt files to be consulted + retroactively before showing archived content. +--> +<!-- + <import resource="LiveWeb.xml"/> +--> <!-- This is the only AccessPoint defined by default within this wayback.xml @@ -80,14 +97,26 @@ --> <import resource="ArchivalUrlReplay.xml"/> <bean name="8080:wayback" class="org.archive.wayback.webapp.AccessPoint"> + <property name="collection" ref="localbdbcollection" /> +<!-- + An example of a text file CDX collection, with a text file path index. + <property name="collection" ref="localcdxcollection" /> +--> <property name="replay" ref="archivalurlreplay" /> <property name="query"> <bean class="org.archive.wayback.query.Renderer"> <property name="captureJsp" value="/WEB-INF/query/CalendarResults.jsp" /> +<!-- + This .jsp provides a "search engine" style listing of results vertically + <property name="captureJsp" value="/WEB-INF/query/HTMLCaptureResults.jsp" /> +--> </bean> </property> +<!-- See the LiveWeb.xml import above. + <property name="exclusionFactory" ref="excluder-factory-robot" /> +--> <property name="uriConverter"> <bean class="org.archive.wayback.archivalurl.ArchivalUrlResultURIConverter"> <property name="replayURIPrefix" value="http://localhost.archive.org:8080/wayback/"/> @@ -97,15 +126,64 @@ <property name="parser"> <bean class="org.archive.wayback.archivalurl.ArchivalUrlRequestParser"> <property name="maxRecords" value="1000" /> - <property name="earliestTimestamp" value="1996" /> + <!-- + <property name="earliestTimestamp" value="1999" /> + <property name="latestTimestamp" value="2004" /> + --> </bean> </property> - + <!-- + The following property will cause only results matching the exact host + the user requested to be displayed. URLs matching other versions of the + same host will be stored in the closeMatches list of the SearchResults, + and can be displayed by query .jsp files. + --> + <!-- + <property name="exactHostMatch" value="true" /> + --> </bean> + <!-- + + All beans defined below here represent examples of alternate + AccessPoint definitions and implementations. + +--> + + + + + + +<!-- The following AccessPoint inherits all configuration from the 8080:wayback + AccessPoint, but provides a OpenSearch format query results. + + Note: the links generated by this AccessPoint drive to the parent + 8080:wayback AccessPoint: presumably users following links from here + will prefer the HTML interface. + --> + <bean name="8080:opensearch" parent="8080:wayback"> + <property name="urlRoot" value="http://localhost.archive.org:8080/wayback/" /> + <property name="query"> + <bean class="org.archive.wayback.query.Renderer"> + <property name="captureJsp" value="/WEB-INF/query/OpenSearchCaptureResults.jsp" /> + <property name="urlJsp" value="/WEB-INF/query/OpenSearchUrlResults.jsp" /> + </bean> + </property> + <property name="exception"> + <bean class="org.archive.wayback.exception.BaseExceptionRenderer"> + <property name="xmlErrorJsp" value="/WEB-INF/exception/OpenSearchError.jsp" /> + <property name="errorJsp" value="/WEB-INF/exception/OpenSearchError.jsp" /> + </bean> + </property> + </bean> + + +<!-- + The following AccessPoint inherits all configuration from the 8080:wayback AccessPoint, but provides a DomainPrefix Replay UI to the same collection. These two access points can be used simultaneously on the same Tomcat installation. @@ -144,7 +222,6 @@ Note: using this AccessPoint requires adding a "Connector" on port 8090 in your Tomcat's server.xml file. --> - <!-- <import resource="ProxyReplay.xml"/> <bean name="8090" parent="8080:wayback"> <property name="urlRoot" value="http://localhost.archive.org:8090/" /> @@ -155,7 +232,7 @@ </bean> </property> <property name="parser"> - <bean class="org.archive.wayback.proxy.ProxyRequestParser"> + <bean class="org.archive.wayback.proxy.ProxyArchivalRequestParser"> <property name="localhostNames"> <list> <value>localhost.archive.org</value> @@ -165,7 +242,31 @@ </bean> </property> </bean> + + <bean name="8091" parent="8080:wayback"> + <property name="urlRoot" value="http://localhost.archive.org/" /> + <property name="replay" ref="proxyreplay" /> + <property name="uriConverter"> + <bean class="org.archive.wayback.archivalurl.ArchivalUrlResultURIConverter"> + <property name="replayURIPrefix" value="http://localhost.archive.org/"/> + </bean> +<!-- + <bean class="org.archive.wayback.proxy.RedirectResultURIConverter"> + <property name="redirectURI" value="http://localhost.archive.org:8090/jsp/QueryUI/Redirect.jsp" /> + </bean> --> + </property> + <property name="parser"> + <bean class="org.archive.wayback.proxy.ProxyArchivalRequestParser"> + <property name="localhostNames"> + <list> + <value>localhost.archive.org</value> + </list> + </property> + <property name="maxRecords" value="1000" /> + </bean> + </property> + </bean> <!-- The following AccessPoint inherits all configuration from the 8080:wayback This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site. |