Menu
▾
▴
[Archive-access-cvs] SF.net SVN: archive-access: [2032] trunk/archive-access/projects/wayback/ wayback-webapp/src/main/webapp/WEB-INF/wayback.xml
|
From: <bra...@us...> - 2007-10-02 03:35:03
|
Revision: 2032
http://archive-access.svn.sourceforge.net/archive-access/?rev=2032&view=rev
Author: bradtofel
Date: 2007-10-01 20:35:05 -0700 (Mon, 01 Oct 2007)
Log Message:
-----------
UPDATE: major overhaul in prep for 1.0, setting default configuration, and leaving commonly used options present but commented out.
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 2007-10-02 03:33:49 UTC (rev 2031)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/wayback.xml 2007-10-02 03:35:05 UTC (rev 2032)
@@ -2,6 +2,12 @@
<!DOCTYPE beans PUBLIC "-//SPRING//DTD BEAN//EN" "http://www.springframework.org/dtd/spring-beans.dtd">
<beans>
+<!--
+ The following 3 beans are required when using the ArcProxy for providing
+ HTTP 1.1 remote access to ARC files distributed across multiple computers
+ or directories.
+-->
+<!--
<bean id="filelocationdb" class="org.archive.wayback.resourcestore.http.FileLocationDB"
init-method="init">
<property name="bdbPath" value="/tmp/wayback/arc-db" />
@@ -15,133 +21,160 @@
<bean name="8080:locationdb" class="org.archive.wayback.resourcestore.http.FileLocationDBServlet">
<property name="locationDB" ref="filelocationdb" />
</bean>
+-->
- <bean id="bdbsearchresultsource"
- class="org.archive.wayback.resourceindex.bdb.BDBIndex"
- init-method="init">
- <property name="bdbName" value="DB1" />
- <property name="bdbPath" value="/tmp/wayback/index/" />
- </bean>
- <bean id="cdxsearchresultsource" class="org.archive.wayback.resourceindex.cdx.CDXIndex">
- <property name="path" value="/tmp/wayback/cdx-index/index.cdx" />
- </bean>
+<!--
+ The following 2 beans are required when using exclusions based on live
+ robots.txt documents.
+-->
+<!--
+ <bean id="livewebcache" class="org.archive.wayback.liveweb.LiveWebCache">
- <bean id="compositecdxresultsource" class="org.archive.wayback.resourceindex.CompositeSearchResultSource">
- <property name="CDXSources">
- <list>
- <value>/tmp/wayback/cdx-index/index.cdx.1</value>
- <value>/tmp/wayback/cdx-index/index.cdx.2</value>
- </list>
- </property>
- </bean>
+ <property name="arcCacheDir">
+ <bean class="org.archive.wayback.liveweb.ARCCacheDirectory"
+ init-method="init">
+
+ <property name="arcDir" value="/tmp/wayback/liveweb/arcs/" />
+ <property name="arcPrefix" value="live" />
+ </bean>
+ </property>
- <bean id="localbdbindex" class="org.archive.wayback.resourceindex.LocalResourceIndex">
- <property name="source" ref="bdbsearchresultsource" />
- <property name="maxRecords" value="10000" />
- </bean>
- <bean id="localcdxindex" class="org.archive.wayback.resourceindex.LocalResourceIndex">
- <property name="source" ref="cdxsearchresultsource" />
- <property name="maxRecords" value="10000" />
- </bean>
+ <property name="cacher">
+ <bean class="org.archive.wayback.liveweb.URLCacher">
+ <property name="tmpDir" value="/tmp/wayback/liveweb/tmp/" />
+ </bean>
+ </property>
- <bean id="localstore" class="org.archive.wayback.resourcestore.LocalARCResourceStore">
- <property name="arcDir" value="/tmp/wayback/arcs/" />
- </bean>
+ <property name="index">
+ <bean class="org.archive.wayback.liveweb.LiveWebLocalResourceIndex">
- <bean id="standardquery" class="org.archive.wayback.query.Renderer">
- </bean>
- <bean id="calendarquery" class="org.archive.wayback.query.Renderer">
- </bean>
- <bean id="xmlquery" class="org.archive.wayback.query.Renderer">
- <property name="captureJsp" value="/jsp/XMLResults.jsp" />
- <property name="urlJsp" value="/jsp/XMLResults.jsp" />
- <property name="errorJsp" value="/jsp/XMLError.jsp" />
- </bean>
+ <property name="source">
+ <bean class="org.archive.wayback.resourceindex.bdb.BDBIndex"
+ init-method="init">
+ <property name="bdbName" value="DB1" />
+ <property name="bdbPath" value="/tmp/wayback/liveweb/db/" />
+ </bean>
+ </property>
+ </bean>
+ </property>
+ </bean>
+
+ <bean id="excluder-factory-robot" class="org.archive.wayback.accesscontrol.robotstxt.RobotExclusionFilterFactory">
+ <property name="maxCacheMS" value="86400000" />
+ <property name="userAgent" value="ia_archiver" />
+ <property name="webCache" ref="livewebcache" />
+ </bean>
+-->
- <bean id="archivalurlreplay" class="org.archive.wayback.archivalurl.ArchivalUrlReplayDispatcher">
- <property name="jsInserts">
- <list>
- <value>http://localhost:8080/wm.js</value>
- </list>
- </property>
- </bean>
- <bean id="archivalurluriconverter"
- class="org.archive.wayback.archivalurl.ArchivalUrlResultURIConverter">
- <property name="replayURIPrefix" value="http://localhost:8080/wayback/" />
- </bean>
- <bean id="archivalurlparser" class="org.archive.wayback.archivalurl.ArchivalUrlRequestParser" init-method="init">
- <property name="maxRecords" value="1000" />
- </bean>
+ <bean id="localbdbcollection" class="org.archive.wayback.webapp.WaybackCollection">
+ <property name="resourceStore">
+ <bean class="org.archive.wayback.resourcestore.LocalARCResourceStore"
+ init-method="init">
+ <property name="arcDir" value="/tmp/wayback/arcs/" />
+ <property name="queuedDir" value="/tmp/wayback/arc-indexer/queued" />
+ <property name="workDir" value="/tmp/wayback/arc-indexer/work" />
+ <property name="runInterval" value="10000" />
+ <property name="indexClient">
+ <bean class="org.archive.wayback.resourceindex.indexer.IndexClient">
+ <property name="tmpDir" value="/tmp/wayback/arc-indexer/tmp" />
+ <property name="target" value="/tmp/wayback/index-data/incoming" />
+ </bean>
+ </property>
+ </bean>
+ </property>
- <bean id="proxyreplay" class="org.archive.wayback.proxy.ProxyReplayDispatcher">
- </bean>
- <bean id="proxyuriconverter" class="org.archive.wayback.proxy.RedirectResultURIConverter">
- <property name="redirectURI" value="http://localhost:8090/jsp/QueryUI/Redirect.jsp" />
- </bean>
- <bean id="proxyparser" class="org.archive.wayback.proxy.ProxyRequestParser" init-method="init">
- <property name="maxRecords" value="1000" />
- </bean>
+ <property name="resourceIndex">
+ <bean class="org.archive.wayback.resourceindex.LocalResourceIndex">
+ <property name="source">
+ <bean class="org.archive.wayback.resourceindex.bdb.BDBIndex"
+ init-method="init">
+ <property name="bdbName" value="DB1" />
+ <property name="bdbPath" value="/tmp/wayback/index/" />
+ <property name="updater">
+ <bean class="org.archive.wayback.resourceindex.bdb.BDBIndexUpdater">
+ <property name="incoming" value="/tmp/wayback/index-data/incoming/" />
+ <property name="failed" value="/tmp/wayback/index-data/failed/" />
+ <property name="merged" value="/tmp/wayback/index-data/merged/" />
+ <property name="runInterval" value="10000" />
+ </bean>
+ </property>
+ </bean>
+ </property>
+ <property name="maxRecords" value="10000" />
+ </bean>
+ </property>
+ </bean>
+<!--
+ The following WaybackCollection bean template is required when using a
+ manually built local CDX index.
+-->
+<!--
+ <bean id="localcdxcollection" class="org.archive.wayback.webapp.WaybackCollection">
- <bean id="archivalcontext" abstract="true"
- class="org.archive.wayback.webapp.WaybackContext">
- <property name="index" ref="localbdbindex" />
- <property name="store" ref="localstore" />
- <property name="query" ref="standardquery" />
- <property name="replay" ref="archivalurlreplay" />
- <property name="parser" ref="archivalurlparser" />
- <property name="uriConverter" ref="archivalurluriconverter" />
- </bean>
+ <property name="resourceStore">
+ <bean class="org.archive.wayback.resourcestore.LocalARCResourceStore"
+ init-method="init">
+ <property name="arcDir" value="/tmp/wayback/arcs/" />
+ </bean>
+ </property>
- <bean name="8080:wayback" class="org.archive.wayback.webapp.WaybackContext">
- <property name="configs">
- <props>
- <prop key="key1">key1-value</prop>
- <prop key="key2">key2-value</prop>
- </props>
- </property>
+ <property name="resourceIndex">
+ <bean class="org.archive.wayback.resourceindex.LocalResourceIndex">
+ <property name="source">
+ <bean id="cdxsearchresultsource" class="org.archive.wayback.resourceindex.cdx.CDXIndex">
+ <property name="path" value="/tmp/wayback/cdx-index/index.cdx" />
+ </bean>
+ </property>
+ <property name="maxRecords" value="10000" />
+ </bean>
+ </property>
+ </bean>
+-->
+
+
<!--
- <property name="index" ref="localcdxindex" />
+ The following WaybackCollection bean template is required when using a
+ remote ResourceIndex and ResourceStore implementation. This will also
+ required setting up an arcproxy and locationdb on the host specified by
+ the resourceStore:urlPrefix configuration, and an addition AccessPoint
+ on the host specified by the resourceIndex:searchUrlBase configuration.
-->
- <property name="index">
- <bean class="org.archive.wayback.resourceindex.LocalResourceIndex">
- <property name="source">
- <bean class="org.archive.wayback.resourceindex.bdb.BDBIndex"
- init-method="init">
- <property name="bdbName" value="DB1" />
- <property name="bdbPath" value="/tmp/wayback/index/" />
- <property name="updater">
- <bean class="org.archive.wayback.resourceindex.bdb.BDBIndexUpdater">
- <property name="incoming" value="/tmp/wayback/index-data/incoming/" />
- <property name="failed" value="/tmp/wayback/index-data/failed/" />
- <property name="merged" value="/tmp/wayback/index-data/merged/" />
- <property name="runInterval" value="10000" />
- </bean>
- </property>
- </bean>
- </property>
- <property name="maxRecords" value="10000" />
- </bean>
- </property>
- <property name="store">
- <bean class="org.archive.wayback.resourcestore.LocalARCResourceStore"
- init-method="init">
- <property name="arcDir" value="/tmp/wayback/arcs/" />
- <property name="queuedDir" value="/tmp/wayback/arc-indexer/queued" />
- <property name="workDir" value="/tmp/wayback/arc-indexer/work" />
- <property name="runInterval" value="10000" />
- <property name="indexClient">
- <bean class="org.archive.wayback.resourceindex.indexer.IndexClient">
- <property name="tmpDir" value="/tmp/wayback/arc-indexer/tmp" />
- <property name="target" value="/tmp/wayback/index-data/incoming" />
- </bean>
- </property>
- </bean>
- </property>
-
+<!--
+ <bean id="remotecollection" class="org.archive.wayback.webapp.WaybackCollection">
+
+ <property name="resourceStore">
+ <bean class="org.archive.wayback.resourcestore.HttpARCResourceStore">
+ <property name="urlPrefix" value="http://localhost:8080/arcproxy/" />
+ </bean>
+ </property>
+
+ <property name="resourceIndex">
+ <bean class="org.archive.wayback.resourceindex.RemoteResourceIndex"
+ init-method="init">
+ <property name="searchUrlBase" value="http://indexhost:8080/index/xmlquery" />
+ </bean>
+ </property>
+ </bean>
+-->
+
+<!--
+ This is the only AccessPoint defined by default within this wayback.xml
+ Spring configuration file, providing an ArchivalURL Replay UI to the
+ "localbdbcollection" by providing ArchivalURL-specific implementations
+ of the replay, parser, and uriConverter.
+
+ This AccessPoint currently will provide access only from the machine
+ running Tomcat. To provide external access, replace "localhost" with your
+ fully qualified hostname of the computer running Tomcat.
+-->
+ <bean name="8080:wayback" class="org.archive.wayback.webapp.AccessPoint">
+
+ <property name="collection" ref="localbdbcollection" />
+
<property name="query">
<bean class="org.archive.wayback.query.Renderer">
<property name="captureJsp" value="/jsp/HTMLResults.jsp" />
@@ -178,27 +211,78 @@
</property>
</bean>
-
- <bean name="8081" parent="8080:wayback">
- <property name="useServerName" value="true" />
- <property name="replay">
- <bean class="org.archive.wayback.domainprefix.DomainPrefixReplayDispatcher" />
- </property>
-
- <property name="parser">
- <bean class="org.archive.wayback.domainprefix.DomainPrefixCompositeRequestParser"
- init-method="init">
- <property name="hostPort" value="localhost.archive.org:8081" />
- <property name="maxRecords" value="1000" />
- <property name="earliestTimestamp" value="1996" />
+<!--
+ The following AccessPoint inherits all configuration from the 8080:wayback
+ AccessPoint, but only allows access from the specified IP network.
+-->
+<!--
+ <bean name="8080:netsecure" parent="8080:wayback">
+ <property name="authentication">
+ <bean class="org.archive.wayback.authenticationcontrol.IPMatchesBooleanOperator">
+ <property name="allowedRanges">
+ <list>
+ <value>192.168.1.16/24</value>
+ </list>
+ </property>
</bean>
</property>
+ <property name="uriConverter">
+ <bean class="org.archive.wayback.archivalurl.ArchivalUrlResultURIConverter">
+ <property name="replayURIPrefix" value="http://192.168.1.16:8080/netsecure/" />
+ </bean>
+ </property>
+ </bean>
+-->
- <property name="uriConverter">
- <bean class="org.archive.wayback.domainprefix.DomainPrefixResultURIConverter">
- <property name="hostPort" value="localhost.archive.org:8081" />
- </bean>
+<!--
+ The following AccessPoint inherits all configuration from the 8080:wayback
+ AccessPoint, but checks live web robots.txt documents to determine if
+ archived content should be accessible.
+
+ Note: using this AccessPoint requires enabling the "livewebcache" and
+ "excluder-factory-robot" beans declared at the top of this file.
+-->
+<!--
+ <bean name="8080:robots" parent="8080:wayback">
+ <property name="exclusionFactory" ref="excluder-factory-robot" />
+ <property name="uriConverter">
+ <bean class="org.archive.wayback.archivalurl.ArchivalUrlResultURIConverter">
+ <property name="replayURIPrefix" value="http://localhost:8080/robots/" />
+ </bean>
+ </property>
+ </bean>
+-->
+
+
+<!--
+ The following AccessPoint inherits all configuration from the 8080:wayback
+ AccessPoint, but provides a Proxy Replay UI to the same collection. These
+ two access points can be used simultaneously on the same Tomcat
+ installation.
+
+ Note: using this AccessPoint requires adding a "Connector" on port 8090
+ in your Tomcat's server.xml file.
+ -->
+<!--
+ <bean name="8090" parent="8080:wayback">
+ <property name="replay">
+ <bean class="org.archive.wayback.proxy.ProxyReplayDispatcher" />
</property>
- </bean>
-
+ <property name="uriconverter">
+ <bean class="org.archive.wayback.proxy.RedirectResultURIConverter">
+ <property name="redirectURI" value="http://foo.archive.org:8090/jsp/Redirect.jsp" />
+ </bean>
+ </property>
+ <property name="parser">
+ <bean class="org.archive.wayback.proxy.ProxyRequestParser" init-method="init">
+ <property name="localhostNames">
+ <list>
+ <value>foo.archive.org</value>
+ </list>
+ </property>
+ <property name="maxRecords" value="1000" />
+ </bean>
+ </property>
+ </bean>
+-->
</beans>
\ No newline at end of file
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
