mstoeck3/autopsy-flatpak
1
0
Fork 0
mirror of https://github.com/overcuriousity/autopsy-flatpak.git synced 2025-07-06 21:00:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use internal Solr w/ configs, get dependencies from Ivy

Browse Source
This commit is contained in:
Peter J. Martel 2011-12-06 15:35:12 -05:00
parent 2bcc877ce5
commit f02341c739
18 changed files with 7150 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
.gitignore vendored
View File

@ -16,8 +16,11 @@
/DataModel/release/modules/lib/zlib1.dll
/KeywordSearch/build/
/KeywordSearch/release/
/KeywordSearch/release/modules/ext/
/KeywordSearch/release/solr/lib/
/KeywordSearch/release/solr/solr/lib/
/KeywordSearch/release/solr/start.jar
/KeywordSearch/release/solr/webapps/solr.war
*/nbproject/private/*
/nbproject/private/*

8
KeywordSearch/build.xml
View File

@ -34,9 +34,13 @@
<target name="init" depends="basic-init,files-init,build-init,-javac-init">
<ivy:resolve/>
<ivy:retrieve sync="true" pattern="/release/modules/ext/[artifact]-[revision](-[classifier]).[ext]" />
<ivy:retrieve conf="autopsy" sync="true" pattern="/release/modules/ext/[artifact]-[revision](-[classifier]).[ext]" />
<ivy:retrieve conf="solr-war" sync="true" pattern="/release/solr/webapps/solr.war" />
<ivy:retrieve conf="start-solr" sync="true" pattern="/release/solr/start.jar" />
<ivy:retrieve conf="jetty-libs" sync="true" pattern="/release/solr/lib/[artifact]-[revision](-[classifier]).[ext]" />
<ivy:retrieve conf="solr-libs" sync="true" pattern="/release/solr/solr/lib/[artifact]-[revision](-[classifier]).[ext]" />
</target>
</project>

20
KeywordSearch/ivy.xml
View File

@ -1,12 +1,20 @@
<ivy-module version="2.0">
<info organisation="org.sleuthkit.autopsy" module="keywordsearch"/>
<configurations >
<conf name="autopsy"/>
<conf name="solr-libs"/>
<conf name="solr-war"/>
<conf name="start-solr"/>
<conf name="jetty-libs"/>
</configurations>
<dependencies>
<dependency org="org.apache.solr" name="solr-cell" rev="3.5.0"/>
<dependency org="org.apache.solr" name="solr-solrj" rev="3.5.0"/>
<dependency org="org.apache.solr" name="solr" rev="3.5.0"/>
<dependency org="org.apache.solr" name="solr" rev="3.5.0"/>
<dependency org="org.mortbay.jetty" name="start" rev="6.1.26"/>
<dependency org="commons-lang" name="commons-lang" rev="2.4"/>
<dependency conf="solr-libs->default" org="org.apache.solr" name="solr-cell" rev="3.5.0"/>
<dependency conf="solr-war->default" org="org.apache.solr" name="solr" rev="3.5.0" transitive="false" /> <!-- the war file -->
<dependency conf="autopsy->*" org="org.apache.solr" name="solr-solrj" rev="3.5.0"/>
<dependency conf="autopsy->*" org="commons-lang" name="commons-lang" rev="2.4"/>
<dependency conf="start-solr->default" org="org.mortbay.jetty" name="start" rev="6.1.26"/>
<dependency conf="jetty-libs->default" org="org.mortbay.jetty" name="jetty" rev="6.1.26"/>
<dependency conf="jetty-libs->default" org="org.mortbay.jetty" name="jsp-2.1" rev="6.1.14"/>
</dependencies>
</ivy-module>

227
KeywordSearch/release/solr/etc/jetty.xml Normal file
View File

@ -0,0 +1,227 @@
<?xml version="1.0"?>
<!DOCTYPE Configure PUBLIC "-//Mort Bay Consulting//DTD Configure//EN" "http://jetty.mortbay.org/configure.dtd">
<!-- =============================================================== -->
<!-- Configure the Jetty Server -->
<!-- -->
<!-- Documentation of this file format can be found at: -->
<!-- http://docs.codehaus.org/display/JETTY/jetty.xml -->
<!-- -->
<!-- =============================================================== -->
<Configure id="Server" class="org.mortbay.jetty.Server">
<!-- Increase the maximum POST size to 1 MB to be able to handle large shard requests -->
<Call class="java.lang.System" name="setProperty">
<Arg>org.mortbay.jetty.Request.maxFormContentSize</Arg>
<Arg>1000000</Arg>
</Call>
<!-- =========================================================== -->
<!-- Server Thread Pool -->
<!-- =========================================================== -->
<Set name="ThreadPool">
<New class="org.mortbay.thread.QueuedThreadPool">
<Set name="minThreads">10</Set>
<Set name="maxThreads">10000</Set>
<Set name="lowThreads">20</Set>
</New>
<!-- Optional Java 5 bounded threadpool with job queue
<New class="org.mortbay.thread.concurrent.ThreadPool">
<Set name="corePoolSize">50</Set>
<Set name="maximumPoolSize">50</Set>
</New>
-->
</Set>
<!-- =========================================================== -->
<!-- Set connectors -->
<!-- =========================================================== -->
<!-- One of each type! -->
<!-- =========================================================== -->
<!-- Use this connector for many frequently idle connections
and for threadless continuations.
-->
<!--
<Call name="addConnector">
<Arg>
<New class="org.mortbay.jetty.nio.SelectChannelConnector">
<Set name="host"><SystemProperty name="jetty.host" /></Set>
<Set name="port"><SystemProperty name="jetty.port" default="8983"/></Set>
<Set name="maxIdleTime">30000</Set>
<Set name="Acceptors">2</Set>
<Set name="statsOn">false</Set>
<Set name="confidentialPort">8443</Set>
<Set name="lowResourcesConnections">5000</Set>
<Set name="lowResourcesMaxIdleTime">5000</Set>
</New>
</Arg>
</Call>
-->
<!-- This connector is currently being used for Solr because it
showed better performance than nio.SelectChannelConnector
for typical Solr requests. -->
<Call name="addConnector">
<Arg>
<New class="org.mortbay.jetty.bio.SocketConnector">
<Set name="host"><SystemProperty name="jetty.host" /></Set>
<Set name="port"><SystemProperty name="jetty.port" default="8983"/></Set>
<Set name="maxIdleTime">50000</Set>
<Set name="lowResourceMaxIdleTime">1500</Set>
<Set name="statsOn">false</Set>
</New>
</Arg>
</Call>
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<!-- To add a HTTPS SSL listener -->
<!-- see jetty-ssl.xml to add an ssl connector. use -->
<!-- java -jar start.jar etc/jetty.xml etc/jetty-ssl.xml -->
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<!-- To allow Jetty to be started from xinetd -->
<!-- mixin jetty-xinetd.xml: -->
<!-- java -jar start.jar etc/jetty.xml etc/jetty-xinetd.xml -->
<!-- -->
<!-- See jetty-xinetd.xml for further instructions. -->
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<!-- =========================================================== -->
<!-- Set up global session ID manager -->
<!-- =========================================================== -->
<!--
<Set name="sessionIdManager">
<New class="org.mortbay.jetty.servlet.HashSessionIdManager">
<Set name="workerName">node1</Set>
</New>
</Set>
-->
<!-- =========================================================== -->
<!-- Set handler Collection Structure -->
<!-- =========================================================== -->
<Set name="handler">
<New id="Handlers" class="org.mortbay.jetty.handler.HandlerCollection">
<Set name="handlers">
<Array type="org.mortbay.jetty.Handler">
<Item>
<New id="Contexts" class="org.mortbay.jetty.handler.ContextHandlerCollection"/>
</Item>
<Item>
<New id="DefaultHandler" class="org.mortbay.jetty.handler.DefaultHandler"/>
</Item>
<Item>
<New id="RequestLog" class="org.mortbay.jetty.handler.RequestLogHandler"/>
</Item>
</Array>
</Set>
</New>
</Set>
<!-- =========================================================== -->
<!-- Configure the context deployer -->
<!-- A context deployer will deploy contexts described in -->
<!-- configuration files discovered in a directory. -->
<!-- The configuration directory can be scanned for hot -->
<!-- deployments at the configured scanInterval. -->
<!-- -->
<!-- This deployer is configured to deploy contexts configured -->
<!-- in the $JETTY_HOME/contexts directory -->
<!-- -->
<!-- =========================================================== -->
<Call name="addLifeCycle">
<Arg>
<New class="org.mortbay.jetty.deployer.ContextDeployer">
<Set name="contexts"><Ref id="Contexts"/></Set>
<Set name="configurationDir"><SystemProperty name="jetty.home" default="."/>/contexts</Set>
<Set name="scanInterval">5</Set>
</New>
</Arg>
</Call>
<!-- =========================================================== -->
<!-- Configure the webapp deployer. -->
<!-- A webapp deployer will deploy standard webapps discovered -->
<!-- in a directory at startup, without the need for additional -->
<!-- configuration files. It does not support hot deploy or -->
<!-- non standard contexts (see ContextDeployer above). -->
<!-- -->
<!-- This deployer is configured to deploy webapps from the -->
<!-- $JETTY_HOME/webapps directory -->
<!-- -->
<!-- Normally only one type of deployer need be used. -->
<!-- -->
<!-- =========================================================== -->
<Call name="addLifeCycle">
<Arg>
<New class="org.mortbay.jetty.deployer.WebAppDeployer">
<Set name="contexts"><Ref id="Contexts"/></Set>
<Set name="webAppDir"><SystemProperty name="jetty.home" default="."/>/webapps</Set>
<Set name="parentLoaderPriority">false</Set>
<Set name="extract">true</Set>
<Set name="allowDuplicates">false</Set>
<Set name="defaultsDescriptor"><SystemProperty name="jetty.home" default="."/>/etc/webdefault.xml</Set>
</New>
</Arg>
</Call>
<!-- =========================================================== -->
<!-- Configure Authentication Realms -->
<!-- Realms may be configured for the entire server here, or -->
<!-- they can be configured for a specific web app in a context -->
<!-- configuration (see $(jetty.home)/contexts/test.xml for an -->
<!-- example). -->
<!-- =========================================================== -->
<!--
<Set name="UserRealms">
<Array type="org.mortbay.jetty.security.UserRealm">
<Item>
<New class="org.mortbay.jetty.security.HashUserRealm">
<Set name="name">Test Realm</Set>
<Set name="config"><SystemProperty name="jetty.home" default="."/>/etc/realm.properties</Set>
<Set name="refreshInterval">0</Set>
</New>
</Item>
</Array>
</Set>
-->
<!-- =========================================================== -->
<!-- Configure Request Log -->
<!-- Request logs may be configured for the entire server here, -->
<!-- or they can be configured for a specific web app in a -->
<!-- contexts configuration (see $(jetty.home)/contexts/test.xml -->
<!-- for an example). -->
<!-- =========================================================== -->
<!--
<Ref id="RequestLog">
<Set name="requestLog">
<New id="RequestLogImpl" class="org.mortbay.jetty.NCSARequestLog">
<Set name="filename"><SystemProperty name="jetty.logs" default="./logs"/>/yyyy_mm_dd.request.log</Set>
<Set name="filenameDateFormat">yyyy_MM_dd</Set>
<Set name="retainDays">90</Set>
<Set name="append">true</Set>
<Set name="extended">false</Set>
<Set name="logCookies">false</Set>
<Set name="LogTimeZone">GMT</Set>
</New>
</Set>
</Ref>
-->
<!-- =========================================================== -->
<!-- extra options -->
<!-- =========================================================== -->
<Set name="stopAtShutdown">true</Set>
<Set name="sendServerVersion">false</Set>
<Set name="sendDateHeader">false</Set>
<Set name="gracefulShutdown">1000</Set>
</Configure>

410
KeywordSearch/release/solr/etc/webdefault.xml Normal file
View File

@ -0,0 +1,410 @@
<?xml version="1.0" encoding="ISO-8859-1"?>
<!-- ===================================================================== -->
<!-- This file contains the default descriptor for web applications. -->
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<!-- The intent of this descriptor is to include jetty specific or common -->
<!-- configuration for all webapps. If a context has a webdefault.xml -->
<!-- descriptor, it is applied before the contexts own web.xml file -->
<!-- -->
<!-- A context may be assigned a default descriptor by: -->
<!-- + Calling WebApplicationContext.setDefaultsDescriptor -->
<!-- + Passed an arg to addWebApplications -->
<!-- -->
<!-- This file is used both as the resource within the jetty.jar (which is -->
<!-- used as the default if no explicit defaults descriptor is set) and it -->
<!-- is copied to the etc directory of the Jetty distro and explicitly -->
<!-- by the jetty.xml file. -->
<!-- -->
<!-- ===================================================================== -->
<web-app
xmlns="http://java.sun.com/xml/ns/javaee"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://java.sun.com/xml/ns/javaee http://java.sun.com/xml/ns/javaee/web-app_2_5.xsd"
metadata-complete="true"
version="2.5">
<description>
Default web.xml file.
This file is applied to a Web application before it's own WEB_INF/web.xml file
</description>
<!-- ==================================================================== -->
<!-- Context params to control Session Cookies -->
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<!-- UNCOMMENT TO ACTIVATE
<context-param>
<param-name>org.mortbay.jetty.servlet.SessionDomain</param-name>
<param-value>127.0.0.1</param-value>
</context-param>
<context-param>
<param-name>org.mortbay.jetty.servlet.SessionPath</param-name>
<param-value>/</param-value>
</context-param>
<context-param>
<param-name>org.mortbay.jetty.servlet.MaxAge</param-name>
<param-value>-1</param-value>
</context-param>
-->
<context-param>
<param-name>org.mortbay.jetty.webapp.NoTLDJarPattern</param-name>
<param-value>start.jar|ant-.*\.jar|dojo-.*\.jar|jetty-.*\.jar|jsp-api-.*\.jar|junit-.*\.jar|servlet-api-.*\.jar|dnsns\.jar|rt\.jar|jsse\.jar|tools\.jar|sunpkcs11\.jar|sunjce_provider\.jar|xerces.*\.jar</param-value>
</context-param>
<!-- ==================================================================== -->
<!-- The default servlet. -->
<!-- This servlet, normally mapped to /, provides the handling for static -->
<!-- content, OPTIONS and TRACE methods for the context. -->
<!-- The following initParameters are supported: -->
<!-- -->
<!-- acceptRanges If true, range requests and responses are -->
<!-- supported -->
<!-- -->
<!-- dirAllowed If true, directory listings are returned if no -->
<!-- welcome file is found. Else 403 Forbidden. -->
<!-- -->
<!-- welcomeServlets If true, attempt to dispatch to welcome files -->
<!-- that are servlets, if no matching static -->
<!-- resources can be found. -->
<!-- -->
<!-- redirectWelcome If true, redirect welcome file requests -->
<!-- else use request dispatcher forwards -->
<!-- -->
<!-- gzip If set to true, then static content will be served-->
<!-- as gzip content encoded if a matching resource is -->
<!-- found ending with ".gz" -->
<!-- -->
<!-- resoureBase Can be set to replace the context resource base -->
<!-- -->
<!-- relativeResourceBase -->
<!-- Set with a pathname relative to the base of the -->
<!-- servlet context root. Useful for only serving -->
<!-- static content from only specific subdirectories. -->
<!-- -->
<!-- useFileMappedBuffer -->
<!-- If set to true (the default), a memory mapped -->
<!-- file buffer will be used to serve static content -->
<!-- when using an NIO connector. Setting this value -->
<!-- to false means that a direct buffer will be used -->
<!-- instead. If you are having trouble with Windows -->
<!-- file locking, set this to false. -->
<!-- -->
<!-- cacheControl If set, all static content will have this value -->
<!-- set as the cache-control header. -->
<!-- -->
<!-- maxCacheSize Maximum size of the static resource cache -->
<!-- -->
<!-- maxCachedFileSize Maximum size of any single file in the cache -->
<!-- -->
<!-- maxCachedFiles Maximum number of files in the cache -->
<!-- -->
<!-- cacheType "nio", "bio" or "both" to determine the type(s) -->
<!-- of resource cache. A bio cached buffer may be used-->
<!-- by nio but is not as efficient as a nio buffer. -->
<!-- An nio cached buffer may not be used by bio. -->
<!-- -->
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<servlet>
<servlet-name>default</servlet-name>
<servlet-class>org.mortbay.jetty.servlet.DefaultServlet</servlet-class>
<init-param>
<param-name>acceptRanges</param-name>
<param-value>true</param-value>
</init-param>
<init-param>
<param-name>dirAllowed</param-name>
<param-value>true</param-value>
</init-param>
<init-param>
<param-name>welcomeServlets</param-name>
<param-value>false</param-value>
</init-param>
<init-param>
<param-name>redirectWelcome</param-name>
<param-value>false</param-value>
</init-param>
<init-param>
<param-name>maxCacheSize</param-name>
<param-value>256000000</param-value>
</init-param>
<init-param>
<param-name>maxCachedFileSize</param-name>
<param-value>10000000</param-value>
</init-param>
<init-param>
<param-name>maxCachedFiles</param-name>
<param-value>1000</param-value>
</init-param>
<init-param>
<param-name>cacheType</param-name>
<param-value>both</param-value>
</init-param>
<init-param>
<param-name>gzip</param-name>
<param-value>true</param-value>
</init-param>
<init-param>
<param-name>useFileMappedBuffer</param-name>
<param-value>true</param-value>
</init-param>
<!--
<init-param>
<param-name>cacheControl</param-name>
<param-value>max-age=3600,public</param-value>
</init-param>
-->
<load-on-startup>0</load-on-startup>
</servlet>
<servlet-mapping> <servlet-name>default</servlet-name> <url-pattern>/</url-pattern> </servlet-mapping>
<!-- ==================================================================== -->
<!-- JSP Servlet -->
<!-- This is the jasper JSP servlet from the jakarta project -->
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<!-- The JSP page compiler and execution servlet, which is the mechanism -->
<!-- used by Glassfish to support JSP pages. Traditionally, this servlet -->
<!-- is mapped to URL patterh "*.jsp". This servlet supports the -->
<!-- following initialization parameters (default values are in square -->
<!-- brackets): -->
<!-- -->
<!-- checkInterval If development is false and reloading is true, -->
<!-- background compiles are enabled. checkInterval -->
<!-- is the time in seconds between checks to see -->
<!-- if a JSP page needs to be recompiled. [300] -->
<!-- -->
<!-- compiler Which compiler Ant should use to compile JSP -->
<!-- pages. See the Ant documenation for more -->
<!-- information. [javac] -->
<!-- -->
<!-- classdebuginfo Should the class file be compiled with -->
<!-- debugging information? [true] -->
<!-- -->
<!-- classpath What class path should I use while compiling -->
<!-- generated servlets? [Created dynamically -->
<!-- based on the current web application] -->
<!-- Set to ? to make the container explicitly set -->
<!-- this parameter. -->
<!-- -->
<!-- development Is Jasper used in development mode (will check -->
<!-- for JSP modification on every access)? [true] -->
<!-- -->
<!-- enablePooling Determines whether tag handler pooling is -->
<!-- enabled [true] -->
<!-- -->
<!-- fork Tell Ant to fork compiles of JSP pages so that -->
<!-- a separate JVM is used for JSP page compiles -->
<!-- from the one Tomcat is running in. [true] -->
<!-- -->
<!-- ieClassId The class-id value to be sent to Internet -->
<!-- Explorer when using <jsp:plugin> tags. -->
<!-- [clsid:8AD9C840-044E-11D1-B3E9-00805F499D93] -->
<!-- -->
<!-- javaEncoding Java file encoding to use for generating java -->
<!-- source files. [UTF-8] -->
<!-- -->
<!-- keepgenerated Should we keep the generated Java source code -->
<!-- for each page instead of deleting it? [true] -->
<!-- -->
<!-- logVerbosityLevel The level of detailed messages to be produced -->
<!-- by this servlet. Increasing levels cause the -->
<!-- generation of more messages. Valid values are -->
<!-- FATAL, ERROR, WARNING, INFORMATION, and DEBUG. -->
<!-- [WARNING] -->
<!-- -->
<!-- mappedfile Should we generate static content with one -->
<!-- print statement per input line, to ease -->
<!-- debugging? [false] -->
<!-- -->
<!-- -->
<!-- reloading Should Jasper check for modified JSPs? [true] -->
<!-- -->
<!-- suppressSmap Should the generation of SMAP info for JSR45 -->
<!-- debugging be suppressed? [false] -->
<!-- -->
<!-- dumpSmap Should the SMAP info for JSR45 debugging be -->
<!-- dumped to a file? [false] -->
<!-- False if suppressSmap is true -->
<!-- -->
<!-- scratchdir What scratch directory should we use when -->
<!-- compiling JSP pages? [default work directory -->
<!-- for the current web application] -->
<!-- -->
<!-- tagpoolMaxSize The maximum tag handler pool size [5] -->
<!-- -->
<!-- xpoweredBy Determines whether X-Powered-By response -->
<!-- header is added by generated servlet [false] -->
<!-- -->
<!-- If you wish to use Jikes to compile JSP pages: -->
<!-- Set the init parameter "compiler" to "jikes". Define -->
<!-- the property "-Dbuild.compiler.emacs=true" when starting Jetty -->
<!-- to cause Jikes to emit error messages in a format compatible with -->
<!-- Jasper. -->
<!-- If you get an error reporting that jikes can't use UTF-8 encoding, -->
<!-- try setting the init parameter "javaEncoding" to "ISO-8859-1". -->
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<servlet id="jsp">
<servlet-name>jsp</servlet-name>
<servlet-class>org.apache.jasper.servlet.JspServlet</servlet-class>
<init-param>
<param-name>logVerbosityLevel</param-name>
<param-value>DEBUG</param-value>
</init-param>
<init-param>
<param-name>fork</param-name>
<param-value>false</param-value>
</init-param>
<init-param>
<param-name>xpoweredBy</param-name>
<param-value>false</param-value>
</init-param>
<!--
<init-param>
<param-name>classpath</param-name>
<param-value>?</param-value>
</init-param>
-->
<load-on-startup>0</load-on-startup>
</servlet>
<servlet-mapping>
<servlet-name>jsp</servlet-name>
<url-pattern>*.jsp</url-pattern>
<url-pattern>*.jspf</url-pattern>
<url-pattern>*.jspx</url-pattern>
<url-pattern>*.xsp</url-pattern>
<url-pattern>*.JSP</url-pattern>
<url-pattern>*.JSPF</url-pattern>
<url-pattern>*.JSPX</url-pattern>
<url-pattern>*.XSP</url-pattern>
</servlet-mapping>
<!-- ==================================================================== -->
<!-- Dynamic Servlet Invoker. -->
<!-- This servlet invokes anonymous servlets that have not been defined -->
<!-- in the web.xml or by other means. The first element of the pathInfo -->
<!-- of a request passed to the envoker is treated as a servlet name for -->
<!-- an existing servlet, or as a class name of a new servlet. -->
<!-- This servlet is normally mapped to /servlet/* -->
<!-- This servlet support the following initParams: -->
<!-- -->
<!-- nonContextServlets If false, the invoker can only load -->
<!-- servlets from the contexts classloader. -->
<!-- This is false by default and setting this -->
<!-- to true may have security implications. -->
<!-- -->
<!-- verbose If true, log dynamic loads -->
<!-- -->
<!-- * All other parameters are copied to the -->
<!-- each dynamic servlet as init parameters -->
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<!-- Uncomment for dynamic invocation
<servlet>
<servlet-name>invoker</servlet-name>
<servlet-class>org.mortbay.jetty.servlet.Invoker</servlet-class>
<init-param>
<param-name>verbose</param-name>
<param-value>false</param-value>
</init-param>
<init-param>
<param-name>nonContextServlets</param-name>
<param-value>false</param-value>
</init-param>
<init-param>
<param-name>dynamicParam</param-name>
<param-value>anyValue</param-value>
</init-param>
<load-on-startup>0</load-on-startup>
</servlet>
<servlet-mapping> <servlet-name>invoker</servlet-name> <url-pattern>/servlet/*</url-pattern> </servlet-mapping>
-->
<!-- ==================================================================== -->
<session-config>
<session-timeout>30</session-timeout>
</session-config>
<!-- ==================================================================== -->
<!-- Default MIME mappings -->
<!-- The default MIME mappings are provided by the mime.properties -->
<!-- resource in the org.mortbay.jetty.jar file. Additional or modified -->
<!-- mappings may be specified here -->
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<!-- UNCOMMENT TO ACTIVATE
<mime-mapping>
<extension>mysuffix</extension>
<mime-type>mymime/type</mime-type>
</mime-mapping>
-->
<!-- ==================================================================== -->
<welcome-file-list>
<welcome-file>index.html</welcome-file>
<welcome-file>index.htm</welcome-file>
<welcome-file>index.jsp</welcome-file>
</welcome-file-list>
<!-- ==================================================================== -->
<locale-encoding-mapping-list>
<locale-encoding-mapping><locale>ar</locale><encoding>ISO-8859-6</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>be</locale><encoding>ISO-8859-5</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>bg</locale><encoding>ISO-8859-5</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>ca</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>cs</locale><encoding>ISO-8859-2</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>da</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>de</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>el</locale><encoding>ISO-8859-7</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>en</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>es</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>et</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>fi</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>fr</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>hr</locale><encoding>ISO-8859-2</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>hu</locale><encoding>ISO-8859-2</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>is</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>it</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>iw</locale><encoding>ISO-8859-8</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>ja</locale><encoding>Shift_JIS</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>ko</locale><encoding>EUC-KR</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>lt</locale><encoding>ISO-8859-2</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>lv</locale><encoding>ISO-8859-2</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>mk</locale><encoding>ISO-8859-5</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>nl</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>no</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>pl</locale><encoding>ISO-8859-2</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>pt</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>ro</locale><encoding>ISO-8859-2</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>ru</locale><encoding>ISO-8859-5</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>sh</locale><encoding>ISO-8859-5</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>sk</locale><encoding>ISO-8859-2</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>sl</locale><encoding>ISO-8859-2</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>sq</locale><encoding>ISO-8859-2</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>sr</locale><encoding>ISO-8859-5</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>sv</locale><encoding>ISO-8859-1</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>tr</locale><encoding>ISO-8859-9</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>uk</locale><encoding>ISO-8859-5</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>zh</locale><encoding>GB2312</encoding></locale-encoding-mapping>
<locale-encoding-mapping><locale>zh_TW</locale><encoding>Big5</encoding></locale-encoding-mapping>
</locale-encoding-mapping-list>
<security-constraint>
<web-resource-collection>
<web-resource-name>Disable TRACE</web-resource-name>
<url-pattern>/</url-pattern>
<http-method>TRACE</http-method>
</web-resource-collection>
<auth-constraint/>
</security-constraint>
</web-app>

31
KeywordSearch/release/solr/solr/conf/admin-extra.html Normal file
View File

@ -0,0 +1,31 @@
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
<!-- The content of this page will be statically included into the top
of the admin page. Uncomment this as an example to see there the content
will show up.
<hr>
<i>This line will appear before the first table</i>
<tr>
<td colspan="2">
This row will be appended to the end of the first table
</td>
</tr>
<hr>
-->

36
KeywordSearch/release/solr/solr/conf/elevate.xml Normal file
View File

@ -0,0 +1,36 @@
<?xml version="1.0" encoding="UTF-8" ?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
<!-- If this file is found in the config directory, it will only be
loaded once at startup. If it is found in Solr's data
directory, it will be re-loaded every commit.
-->
<elevate>
<query text="foo bar">
<doc id="1" />
<doc id="2" />
<doc id="3" />
</query>
<query text="ipod">
<doc id="MA147LL/A" /> <!-- put the actual ipod at the top -->
<doc id="IW-02" exclude="true" /> <!-- exclude this cable -->
</query>
</elevate>

3813
KeywordSearch/release/solr/solr/conf/mapping-FoldToASCII.txt Normal file
View File

File diff suppressed because it is too large Load Diff

246
KeywordSearch/release/solr/solr/conf/mapping-ISOLatin1Accent.txt Normal file
View File

@ -0,0 +1,246 @@
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Syntax:
# "source" => "target"
# "source".length() > 0 (source cannot be empty.)
# "target".length() >= 0 (target can be empty.)
# example:
# "À" => "A"
# "\u00C0" => "A"
# "\u00C0" => "\u0041"
# "ß" => "ss"
# "\t" => " "
# "\n" => ""
# À => A
"\u00C0" => "A"
# Á => A
"\u00C1" => "A"
# Â => A
"\u00C2" => "A"
# Ã => A
"\u00C3" => "A"
# Ä => A
"\u00C4" => "A"
# Å => A
"\u00C5" => "A"
# Æ => AE
"\u00C6" => "AE"
# Ç => C
"\u00C7" => "C"
# È => E
"\u00C8" => "E"
# É => E
"\u00C9" => "E"
# Ê => E
"\u00CA" => "E"
# Ë => E
"\u00CB" => "E"
# Ì => I
"\u00CC" => "I"
# Í => I
"\u00CD" => "I"
# Î => I
"\u00CE" => "I"
# Ï => I
"\u00CF" => "I"
# IJ => IJ
"\u0132" => "IJ"
# Ð => D
"\u00D0" => "D"
# Ñ => N
"\u00D1" => "N"
# Ò => O
"\u00D2" => "O"
# Ó => O
"\u00D3" => "O"
# Ô => O
"\u00D4" => "O"
# Õ => O
"\u00D5" => "O"
# Ö => O
"\u00D6" => "O"
# Ø => O
"\u00D8" => "O"
# Π=> OE
"\u0152" => "OE"
# Þ
"\u00DE" => "TH"
# Ù => U
"\u00D9" => "U"
# Ú => U
"\u00DA" => "U"
# Û => U
"\u00DB" => "U"
# Ü => U
"\u00DC" => "U"
# Ý => Y
"\u00DD" => "Y"
# Ÿ => Y
"\u0178" => "Y"
# à => a
"\u00E0" => "a"
# á => a
"\u00E1" => "a"
# â => a
"\u00E2" => "a"
# ã => a
"\u00E3" => "a"
# ä => a
"\u00E4" => "a"
# å => a
"\u00E5" => "a"
# æ => ae
"\u00E6" => "ae"
# ç => c
"\u00E7" => "c"
# è => e
"\u00E8" => "e"
# é => e
"\u00E9" => "e"
# ê => e
"\u00EA" => "e"
# ë => e
"\u00EB" => "e"
# ì => i
"\u00EC" => "i"
# í => i
"\u00ED" => "i"
# î => i
"\u00EE" => "i"
# ï => i
"\u00EF" => "i"
# ij => ij
"\u0133" => "ij"
# ð => d
"\u00F0" => "d"
# ñ => n
"\u00F1" => "n"
# ò => o
"\u00F2" => "o"
# ó => o
"\u00F3" => "o"
# ô => o
"\u00F4" => "o"
# õ => o
"\u00F5" => "o"
# ö => o
"\u00F6" => "o"
# ø => o
"\u00F8" => "o"
# œ => oe
"\u0153" => "oe"
# ß => ss
"\u00DF" => "ss"
# þ => th
"\u00FE" => "th"
# ù => u
"\u00F9" => "u"
# ú => u
"\u00FA" => "u"
# û => u
"\u00FB" => "u"
# ü => u
"\u00FC" => "u"
# ý => y
"\u00FD" => "y"
# ÿ => y
"\u00FF" => "y"
# ff => ff
"\uFB00" => "ff"
# fi => fi
"\uFB01" => "fi"
# fl => fl
"\uFB02" => "fl"
# ffi => ffi
"\uFB03" => "ffi"
# ffl => ffl
"\uFB04" => "ffl"
# ſt => ft
"\uFB05" => "ft"
# st => st
"\uFB06" => "st"

21
KeywordSearch/release/solr/solr/conf/protwords.txt Normal file
View File

@ -0,0 +1,21 @@
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#-----------------------------------------------------------------------
# Use a protected word file to protect against the stemmer reducing two
# unrelated words to the same base word.
# Some non-words that normally won't be encountered,
# just to test that they won't be stemmed.
dontstems
zwhacky

633
KeywordSearch/release/solr/solr/conf/schema.xml Normal file
View File

@ -0,0 +1,633 @@
<?xml version="1.0" encoding="UTF-8" ?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
<!--
This is the Solr schema file. This file should be named "schema.xml" and
should be in the conf directory under the solr home
(i.e. ./solr/conf/schema.xml by default)
or located where the classloader for the Solr webapp can find it.
This example schema is the recommended starting point for users.
It should be kept correct and concise, usable out-of-the-box.
For more information, on how to customize this file, please see
http://wiki.apache.org/solr/SchemaXml
PERFORMANCE NOTE: this schema includes many optional features and should not
be used for benchmarking. To improve performance one could
- set stored="false" for all fields possible (esp large fields) when you
only need to search on the field but don't need to return the original
value.
- set indexed="false" if you don't need to search on the field, but only
return the field as a result of searching on other indexed fields.
- remove all unneeded copyField statements
- for best index size and searching performance, set "index" to false
for all general text fields, use copyField to copy them to the
catchall "text" field, and use that for searching.
- For maximum indexing performance, use the StreamingUpdateSolrServer
java client.
- Remember to run the JVM in server mode, and use a higher logging level
that avoids logging every request
-->
<schema name="Maytag Keyword Search" version="1.4">
<!-- attribute "name" is the name of this schema and is only used for display purposes.
Applications should change this to reflect the nature of the search collection.
version="1.4" is Solr's version number for the schema syntax and semantics. It should
not normally be changed by applications.
1.0: multiValued attribute did not exist, all fields are multiValued by nature
1.1: multiValued attribute introduced, false by default
1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
1.3: removed optional field compress feature
1.4: default auto-phrase (QueryParser feature) to off
-->
<types>
<!-- field type definitions. The "name" attribute is
just a label to be used by field definitions. The "class"
attribute and any other attributes determine the real
behavior of the fieldType.
Class names starting with "solr" refer to java classes in the
org.apache.solr.analysis package.
-->
<!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
<fieldtype name="binary" class="solr.BinaryField"/>
<!-- The optional sortMissingLast and sortMissingFirst attributes are
currently supported on types that are sorted internally as strings.
This includes "string","boolean","sint","slong","sfloat","sdouble","pdate"
- If sortMissingLast="true", then a sort on this field will cause documents
without the field to come after documents with the field,
regardless of the requested sort order (asc or desc).
- If sortMissingFirst="true", then a sort on this field will cause documents
without the field to come before documents with the field,
regardless of the requested sort order.
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the
field first in an ascending sort and last in a descending sort.
-->
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-->
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<!--
Numeric field types that index each value at various levels of precision
to accelerate range queries when the number of values between the range
endpoints is large. See the javadoc for NumericRangeQuery for internal
implementation details.
Smaller precisionStep values (specified in bits) will lead to more tokens
indexed per value, slightly larger index size, and faster range queries.
A precisionStep of 0 disables indexing at different precision levels.
-->
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory.
Expressions can also be used to denote calculations that should be
performed relative to "NOW" to determine the value, ie...
NOW/HOUR
... Round to the start of the current hour
NOW-1DAY
... Exactly 1 day prior to now
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
Consult the DateField javadocs for more information.
Note: For faster range queries, consider the tdate type
-->
<fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
<!-- A Trie based date field for faster date range queries and date faceting. -->
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
<!--
Note:
These should only be used for compatibility with existing indexes (created with older Solr versions)
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
Plain numeric field types that store and index the text
value verbatim (and hence don't support range queries, since the
lexicographic ordering isn't equal to the numeric ordering)
-->
<fieldType name="pint" class="solr.IntField" omitNorms="true"/>
<fieldType name="plong" class="solr.LongField" omitNorms="true"/>
<fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
<fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/>
<fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
<!--
Note:
These should only be used for compatibility with existing indexes (created with older Solr versions)
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
Numeric field types that manipulate the value into
a string value that isn't human-readable in its internal form,
but with a lexicographic ordering the same as the numeric ordering,
so that range queries work correctly.
-->
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
<!-- The "RandomSortField" is not used to store or search any
data. You can declare fields of this type it in your schema
to generate pseudo-random orderings of your docs for sorting
purposes. The ordering is generated based on the field name
and the version of the index, As long as the index version
remains unchanged, and the same field name is reused,
the ordering of the docs will be consistent.
If you want different psuedo-random orderings of documents,
for the same version of the index, use a dynamicField and
change the name
-->
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<!-- solr.TextField allows the specification of custom text analyzers
specified as a tokenizer and a list of token filters. Different
analyzers may be specified for indexing and querying.
The optional positionIncrementGap puts space between multiple fields of
this type on the same document, with the purpose of preventing false phrase
matching across fields.
For more info on customizing your analyzer chain, please see
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-->
<!-- One can also specify an existing Analyzer class that has a
default constructor via the class attribute on the analyzer element
<fieldType name="text_greek" class="solr.TextField">
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
</fieldType>
-->
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- A general text field that has reasonable, generic
cross-language defaults: it tokenizes with StandardTokenizer,
removes stop words from case-insensitive "stopwords.txt"
(empty by default), and down cases. At query time only, it
also applies synonyms. -->
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English: it
tokenizes with StandardTokenizer, removes English stop words
(stopwords_en.txt), down cases, protects words from protwords.txt, and
finally applies Porter's stemming. The query time analyzer
also applies synonyms from synonyms.txt. -->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
add enablePositionIncrements=true in both the index and query
analyzers to leave a 'gap' for more accurate phrase queries.
-->
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords_en.txt"
enablePositionIncrements="true"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords_en.txt"
enablePositionIncrements="true"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English, plus
aggressive word-splitting and autophrase features enabled.
This field is just like text_en, except it adds
WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and
non-alphanumeric chars. This means certain compound word
cases will work, for example query "wi fi" will match
document "WiFi" or "wi-fi". However, other cases will still
not match, for example if the query is "wifi" and the
document is "wi fi" or if the query is "wi-fi" and the
document is "wifi".
-->
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
add enablePositionIncrements=true in both the index and query
analyzers to leave a 'gap' for more accurate phrase queries.
-->
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords_en.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords_en.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!-- Just like text_general except it reverses the characters of
each token, to enable more efficient leading wildcard queries. -->
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- charFilter + WhitespaceTokenizer -->
<!--
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
-->
<!-- This is an example of using the KeywordTokenizer along
With various TokenFilterFactories to produce a sortable field
that does not include some properties of the source text
-->
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
which may include back references to portions of the original
string matched by the pattern.
See the Java Regular Expression documentation for more
information on pattern and replacement string syntax.
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
</fieldType>
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldtype>
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
Attributes of the DelimitedPayloadTokenFilterFactory :
"delimiter" - a one character delimiter. Default is | (pipe)
"encoder" - how to encode the following value into a playload
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
integer -> o.a.l.a.p.IntegerEncoder
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
</analyzer>
</fieldtype>
<!-- lowercases the entire field value, keeping it as a single token. -->
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.PathHierarchyTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- since fields of this type are by default not stored or indexed,
any data added to them will be ignored outright. -->
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
<!-- This point type indexes the coordinates as separate fields (subFields)
If subFieldType is defined, it references a type, and a dynamic field
definition is created matching *___<typename>. Alternately, if
subFieldSuffix is defined, that is used to create the subFields.
Example: if subFieldType="double", then the coordinates would be
indexed in fields myloc_0___double,myloc_1___double.
Example: if subFieldSuffix="_d" then the coordinates would be indexed
in fields myloc_0_d,myloc_1_d
The subFields are an implementation detail of the fieldType, and end
users normally should not need to know about them.
-->
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
<!--
A Geohash is a compact representation of a latitude longitude pair in a single field.
See http://wiki.apache.org/solr/SpatialSearch
-->
<fieldtype name="geohash" class="solr.GeoHashField"/>
</types>
<fields>
<!-- Valid attributes for fields:
name: mandatory - the name for the field
type: mandatory - the name of a previously defined type from the
<types> section
indexed: true if this field should be indexed (searchable or sortable)
stored: true if this field should be retrievable
multiValued: true if this field may contain multiple values per document
omitNorms: (expert) set to true to omit the norms associated with
this field (this disables length normalization and index-time
boosting for the field, and saves some memory). Only full-text
fields or fields that need an index-time boost need norms.
termVectors: [false] set to true to store the term vector for a
given field.
When using MoreLikeThis, fields used for similarity should be
stored for best performance.
termPositions: Store position information with the term vector.
This will increase storage costs.
termOffsets: Store offset information with the term vector. This
will increase storage costs.
default: a value that should be used if no value is specified
when adding a document.
-->
<field name="id" type="string" indexed="true" stored="true" required="true" />
<!-- The content field holds the text extracted by SolrCell -->
<field name="content" type="text_general" indexed="true" stored="true"/>
<!-- The strings field holds strings extracted from files that SolrCell doesn't support -->
<field name="strings" type="text_general" indexed="true" stored="true"/>
<field name="file_name" type="text_general" indexed="true" stored="true"/>
<field name="ctime" type="tdate" indexed="true" stored="true"/>
<field name="atime" type="tdate" indexed="true" stored="true"/>
<field name="mtime" type="tdate" indexed="true" stored="true"/>
<field name="crtime" type="tdate" indexed="true" stored="true"/>
<!-- Common metadata fields, named specifically to match up with
SolrCell metadata when parsing rich documents such as Word, PDF.
Some fields are multiValued only because Tika currently may return
multiple values for them.
-->
<field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
<field name="subject" type="text_general" indexed="true" stored="true"/>
<field name="description" type="text_general" indexed="true" stored="true"/>
<field name="comments" type="text_general" indexed="true" stored="true"/>
<field name="author" type="text_general" indexed="true" stored="true"/>
<field name="keywords" type="text_general" indexed="true" stored="true"/>
<field name="category" type="text_general" indexed="true" stored="true"/>
<field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="last_modified" type="date" indexed="true" stored="true"/>
<field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
<!-- Tika places all metadata into a multivalued field named "meta" -->
<field name="meta" type="text_general" indexed="true" stored="true" multiValued="true"/>
<!-- catchall field, containing all other searchable text fields (implemented
via copyField further on in this schema -->
<field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
<!-- catchall text field that indexes tokens both normally and in reverse for efficient
leading wildcard queries. -->
<field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/>
<!-- Uncommenting the following will create a "timestamp" field using
a default value of "NOW" to indicate when each document was indexed.
-->
<!--
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
-->
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
will be used if the name matches any of the patterns.
RESTRICTION: the glob-like pattern in the name attribute must have
a "*" only at the start or the end.
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
Longer patterns will be matched first. if equal size patterns
both match, the first appearing in the schema will be used. -->
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
<dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
<!-- Type used to index the lat and lon components for the "location" FieldType -->
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
<dynamicField name="*_p" type="location" indexed="true" stored="true"/>
<!-- some trie-coded dynamic fields for faster range queries -->
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
<dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="random_*" type="random" />
<!-- uncomment the following to ignore any fields that don't already match an existing
field name or dynamic field, rather than reporting them as an error.
alternately, change the type="ignored" to some other type e.g. "text" if you want
unknown fields indexed and/or stored by default -->
<!--dynamicField name="*" type="ignored" multiValued="true" /-->
</fields>
<!-- Field to use to determine and enforce document uniqueness.
Unless this field is marked with required="false", it will be a required field
-->
<uniqueKey>id</uniqueKey>
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
<defaultSearchField>text</defaultSearchField>
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
<solrQueryParser defaultOperator="OR"/>
<!-- copyField commands copy one field to another at the time a document
is added to the index. It's used either to index the same field differently,
or to add multiple fields to the same field for easier/faster searching. -->
<copyField source="content" dest="text"/>
<copyField source="file_name" dest="text"/>
<copyField source="meta" dest="text"/>
<copyField source="strings" dest="text"/>
<!-- Above, multiple source fields are copied to the [text] field.
Another way to map multiple source fields to the same
destination field is to use the dynamic field syntax.
copyField also supports a maxChars to copy setting. -->
<!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
<!-- copy name to alphaNameSort, a field designed for sorting by name -->
<!-- <copyField source="name" dest="alphaNameSort"/> -->
<!-- Similarity is the scoring routine for each document vs. a query.
A custom similarity may be specified here, but the default is fine
for most applications. -->
<!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
<!-- ... OR ...
Specify a SimilarityFactory class name implementation
allowing parameters to be used.
-->
<!--
<similarity class="com.example.solr.CustomSimilarityFactory">
<str name="paramkey">param value</str>
</similarity>
-->
</schema>

24
KeywordSearch/release/solr/solr/conf/scripts.conf Normal file
View File

@ -0,0 +1,24 @@
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
user=
solr_hostname=localhost
solr_port=8983
rsyncd_port=18983
data_dir=
webapp_name=solr
master_host=
master_data_dir=
master_status_dir=

1550
KeywordSearch/release/solr/solr/conf/solrconfig.xml Normal file
View File

File diff suppressed because it is too large Load Diff

2
KeywordSearch/release/solr/solr/conf/spellings.txt Normal file
View File

@ -0,0 +1,2 @@
pizza
history

14
KeywordSearch/release/solr/solr/conf/stopwords.txt Normal file
View File

@ -0,0 +1,14 @@
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

54
KeywordSearch/release/solr/solr/conf/stopwords_en.txt Normal file
View File

@ -0,0 +1,54 @@
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# a couple of test stopwords to test that the words are really being
# configured from this file:
stopworda
stopwordb
# Standard english stop words taken from Lucene's StopAnalyzer
a
an
and
are
as
at
be
but
by
for
if
in
into
is
it
no
not
of
on
or
such
that
the
their
then
there
these
they
this
to
was
will
with

31
KeywordSearch/release/solr/solr/conf/synonyms.txt Normal file
View File

@ -0,0 +1,31 @@
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#-----------------------------------------------------------------------
#some test synonym mappings unlikely to appear in real input text
aaafoo => aaabar
bbbfoo => bbbfoo bbbbar
cccfoo => cccbar cccbaz
fooaaa,baraaa,bazaaa
# Some synonym groups specific to this example
GB,gib,gigabyte,gigabytes
MB,mib,megabyte,megabytes
Television, Televisions, TV, TVs
#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
#after us won't split it into two words.
# Synonym mappings can be used for spelling correction too
pixima => pixma
a\,a => b\,b

33
KeywordSearch/release/solr/solr/solr.xml Normal file
View File

@ -0,0 +1,33 @@
<?xml version="1.0" encoding="UTF-8" ?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
<!--
All (relative) paths are relative to the installation path
persistent: Save changes made via the API to this file
sharedLib: path to a lib directory that will be shared across all cores
-->
<solr persistent="false">
<!--
adminPath: RequestHandler path to manage cores.
If 'null' (or absent), cores will not be manageable via request handler
-->
<cores adminPath="/admin/cores" shareSchema="true">
</cores>
</solr>