solr_makr 0.0.4 → 0.5.1

data/lib/{files → solr_makr/files/default-configset/conf}/solrconfig.xml

@@ -16,9 +16,9 @@
  limitations under the License.
 -->
 
-<!-- 
+<!--
      For more details about configurations options that may appear in
-     this file, see http://wiki.apache.org/solr/SolrConfigXml. 
+     this file, see http://wiki.apache.org/solr/SolrConfigXml.
 -->
 <config>
   <!-- In all configuration below, a prefix of "solr." for class names
@@ -35,33 +35,20 @@
        that you fully re-index after changing this setting as it can
        affect both how text is indexed and queried.
   -->
-  <luceneMatchVersion>LUCENE_41</luceneMatchVersion>
-
-  <!-- <lib/> directives can be used to instruct Solr to load an Jars
-       identified and use them to resolve any "plugins" specified in
-       your solrconfig.xml or schema.xml (ie: Analyzers, Request
-       Handlers, etc...).
-
-       All directories and paths are resolved relative to the
-       instanceDir.
-
-       Please note that <lib/> directives are processed in the order
-       that they appear in your solrconfig.xml file, and are "stacked" 
-       on top of each other when building a ClassLoader - so if you have 
-       plugin jars with dependencies on other jars, the "lower level" 
-       dependency jars should be loaded first.
-
-       If a "./lib" directory exists in your instanceDir, all files
-       found in it are included as if you had used the following
-       syntax...
-       
-              <lib dir="./lib" />
+  <luceneMatchVersion>5.0.0</luceneMatchVersion>
+
+  <!-- Data Directory
+
+       Used to specify an alternate directory to hold all index data
+       other than the default ./data under the Solr home.  If
+       replication is in use, this should match the replication
+       configuration.
     -->
   <dataDir>${solr.data.dir:}</dataDir>
 
 
   <!-- The DirectoryFactory to use for indexes.
-       
+
        solr.StandardDirectoryFactory is filesystem
        based and tries to pick the best implementation for the current
        JVM and platform.  solr.NRTCachingDirectoryFactory, the default,
@@ -74,57 +61,85 @@
        solr.RAMDirectoryFactory is memory based, not
        persistent, and doesn't work with replication.
     -->
-  <directoryFactory name="DirectoryFactory" 
-                    class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/> 
+  <directoryFactory name="DirectoryFactory"
+                    class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">
+  </directoryFactory>
+
+  <!-- The CodecFactory for defining the format of the inverted index.
+       The default implementation is SchemaCodecFactory, which is the official Lucene
+       index format, but hooks into the schema to provide per-field customization of
+       the postings lists and per-document values in the fieldType element
+       (postingsFormat/docValuesFormat). Note that most of the alternative implementations
+       are experimental, so if you choose to customize the index format, it's a good
+       idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
+       before upgrading to a newer version to avoid unnecessary reindexing.
+  -->
+  <codecFactory class="solr.SchemaCodecFactory"/>
+
+  <schemaFactory class="ClassicIndexSchemaFactory"/>
 
   <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
        Index Config - These settings control low-level behavior of indexing
        Most example settings here show the default value, but are commented
        out, to more easily see where customizations have been made.
-       
+
        Note: This replaces <indexDefaults> and <mainIndex> from older versions
        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
   <indexConfig>
-    <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a 
-         LimitTokenCountFilterFactory in your fieldType definition. E.g. 
-     <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+
+    <!-- LockFactory
+
+         This option specifies which Lucene LockFactory implementation
+         to use.
+
+         single = SingleInstanceLockFactory - suggested for a
+                  read-only index or when there is no possibility of
+                  another process trying to modify the index.
+         native = NativeFSLockFactory - uses OS native file locking.
+                  Do not use when multiple solr webapps in the same
+                  JVM are attempting to share a single index.
+         simple = SimpleFSLockFactory  - uses a plain file for locking
+
+         Defaults: 'native' is default for Solr3.6 and later, otherwise
+                   'simple' is the default
+
+         More details on the nuances of each LockFactory...
+         http://wiki.apache.org/lucene-java/AvailableLockFactories
     -->
-    <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
-    <!-- <writeLockTimeout>1000</writeLockTimeout>  -->
-
-    <!-- The maximum number of simultaneous threads that may be
-         indexing documents at once in IndexWriter; if more than this
-         many threads arrive they will wait for others to finish.
-         Default in Solr/Lucene is 8. -->
-    <maxIndexingThreads>2</maxIndexingThreads> 
-
-    <useCompoundFile>true</useCompoundFile>
-
-    <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
-         indexing for buffering added documents and deletions before they are
-         flushed to the Directory.
-         maxBufferedDocs sets a limit on the number of documents buffered
-         before flushing.
-         If both ramBufferSizeMB and maxBufferedDocs is set, then
-         Lucene will flush based on whichever limit is hit first.  -->
-    <ramBufferSizeMB>20</ramBufferSizeMB> -->
-    <maxBufferedDocs>10000</maxBufferedDocs>
-
-    <!-- Expert: Merge Policy 
-         The Merge Policy in Lucene controls how merging of segments is done.
-         The default since Solr/Lucene 3.3 is TieredMergePolicy.
-         The default since Lucene 2.3 was the LogByteSizeMergePolicy,
-         Even older versions of Lucene used LogDocMergePolicy.
+    <lockType>${solr.lock.type:native}</lockType>
+
+    <!-- Lucene Infostream
+
+         To aid in advanced debugging, Lucene provides an "InfoStream"
+         of detailed information when indexing.
+
+         Setting the value to true will instruct the underlying Lucene
+         IndexWriter to write its info stream to solr's log. By default,
+         this is enabled here, and controlled through log4j.properties.
       -->
-    <mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
-      <int name="maxMergeAtOnce">4</int>
-      <int name="segmentsPerTier">4</int>
-    </mergePolicy>
-    
-    <unlockOnStartup>true</unlockOnStartup>
-    
+     <infoStream>true</infoStream>
   </indexConfig>
 
+
+  <!-- JMX
+
+       This example enables JMX if and only if an existing MBeanServer
+       is found, use this if you want to configure JMX through JVM
+       parameters. Remove this to disable exposing Solr configuration
+       and statistics to JMX.
+
+       For more details see http://wiki.apache.org/solr/SolrJmx
+    -->
+  <jmx />
+  <!-- If you want to connect to a particular server, specify the
+       agentId
+    -->
+  <!-- <jmx agentId="myAgent" /> -->
+  <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+  <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+    -->
+
+  <!-- The default high-performance update handler -->
   <updateHandler class="solr.DirectUpdateHandler2">
 
     <!-- Enables a transaction log, used for real-time get, durability, and
@@ -132,22 +147,66 @@
          uncommitted changes to the index, so use of a hard autoCommit
          is recommended (see below).
          "dir" - the target directory for transaction logs, defaults to the
-                solr data directory.  --> 
+                solr data directory.  -->
     <updateLog>
       <str name="dir">${solr.ulog.dir:}</str>
     </updateLog>
 
-     <autoCommit> 
-       <maxTime>15000</maxTime> 
-       <openSearcher>false</openSearcher> 
+    <!-- AutoCommit
+
+         Perform a hard commit automatically under certain conditions.
+         Instead of enabling autoCommit, consider using "commitWithin"
+         when adding documents.
+
+         http://wiki.apache.org/solr/UpdateXmlMessages
+
+         maxDocs - Maximum number of documents to add since the last
+                   commit before automatically triggering a new commit.
+
+         maxTime - Maximum amount of time in ms that is allowed to pass
+                   since a document was added before automatically
+                   triggering a new commit.
+         openSearcher - if false, the commit causes recent index changes
+           to be flushed to stable storage, but does not cause a new
+           searcher to be opened to make those changes visible.
+
+         If the updateLog is enabled, then it's highly recommended to
+         have some sort of hard autoCommit to limit the log size.
+      -->
+     <autoCommit>
+       <maxTime>15000</maxTime>
+       <maxDocs>25</maxDocs>
+       <openSearcher>true</openSearcher>
      </autoCommit>
 
-     <autoSoftCommit> 
-       <maxTime>5000</maxTime> 
+    <!-- softAutoCommit is like autoCommit except it causes a
+         'soft' commit which only ensures that changes are visible
+         but does not ensure that data is synced to disk.  This is
+         faster and more near-realtime friendly than a hard commit.
+      -->
+     <autoSoftCommit>
+       <maxTime>1000</maxTime>
      </autoSoftCommit>
+
   </updateHandler>
 
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Query section - these settings control query time things like caches
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
   <query>
+    <!-- Max Boolean Clauses
+
+         Maximum number of clauses in each BooleanQuery,  an exception
+         is thrown if exceeded.
+
+         ** WARNING **
+
+         This option actually modifies a global Lucene property that
+         will affect all SolrCores.  If multiple solrconfig.xml files
+         disagree on this property, the value at any given moment will
+         be based on the last SolrCore to be initialized.
+
+      -->
     <maxBooleanClauses>1024</maxBooleanClauses>
 
 
@@ -155,7 +214,7 @@
 
          There are two implementations of cache available for Solr,
          LRUCache, based on a synchronized LinkedHashMap, and
-         FastLRUCache, based on a ConcurrentHashMap.  
+         FastLRUCache, based on a ConcurrentHashMap.
 
          FastLRUCache has faster gets and slower puts in single
          threaded operation and thus is generally faster than LRUCache
@@ -180,7 +239,7 @@
            initialSize - the initial capacity (number of entries) of
                the cache.  (see java.util.HashMap)
            autowarmCount - the number of entries to prepopulate from
-               and old cache.  
+               and old cache.
       -->
     <filterCache class="solr.FastLRUCache"
                  size="512"
@@ -188,26 +247,34 @@
                  autowarmCount="0"/>
 
     <!-- Query Result Cache
-         
+
          Caches results of searches - ordered lists of document ids
-         (DocList) based on a query, a sort, and the range of documents requested.  
+         (DocList) based on a query, a sort, and the range of documents requested.
       -->
     <queryResultCache class="solr.LRUCache"
                      size="512"
                      initialSize="512"
                      autowarmCount="0"/>
-   
+
     <!-- Document Cache
 
          Caches Lucene Document objects (the stored fields for each
          document).  Since Lucene internal document ids are transient,
-         this cache will not be autowarmed.  
+         this cache will not be autowarmed.
       -->
     <documentCache class="solr.LRUCache"
                    size="512"
                    initialSize="512"
                    autowarmCount="0"/>
 
+    <!-- custom cache currently used by block join -->
+    <cache name="perSegFilter"
+      class="solr.search.LRUCache"
+      size="10"
+      initialSize="0"
+      autowarmCount="10"
+      regenerator="solr.NoOpRegenerator" />
+
     <!-- Lazy Field Loading
 
          If true, stored fields that are not requested will be loaded
@@ -218,23 +285,6 @@
     -->
     <enableLazyFieldLoading>true</enableLazyFieldLoading>
 
-   <!-- Use Filter For Sorted Query
-
-        A possible optimization that attempts to use a filter to
-        satisfy a search.  If the requested sort does not include
-        score, then the filterCache will be checked for a filter
-        matching the query. If found, the filter will be used as the
-        source of document ids, and then the sort will be applied to
-        that.
-
-        For most situations, this will not be useful unless you
-        frequently get the same search repeatedly with different sort
-        options, and none of them ever use "score"
-     -->
-   <!--
-      <useFilterForSortedQuery>true</useFilterForSortedQuery>
-     -->
-
    <!-- Result Window Size
 
         An optimization for use with the queryResultCache.  When a search
@@ -242,32 +292,15 @@
         are collected.  For example, if a search for a particular query
         requests matching documents 10 through 19, and queryWindowSize is 50,
         then documents 0 through 49 will be collected and cached.  Any further
-        requests in that range can be satisfied via the cache.  
+        requests in that range can be satisfied via the cache.
      -->
    <queryResultWindowSize>20</queryResultWindowSize>
 
    <!-- Maximum number of documents to cache for any entry in the
-        queryResultCache. 
+        queryResultCache.
      -->
    <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
 
-   <!-- Query Related Event Listeners
-
-        Various IndexSearcher related events can trigger Listeners to
-        take actions.
-
-        newSearcher - fired whenever a new searcher is being prepared
-        and there is a current searcher handling requests (aka
-        registered).  It can be used to prime certain caches to
-        prevent long request times for certain requests.
-
-        firstSearcher - fired whenever a new searcher is being
-        prepared but there is no current registered searcher to handle
-        requests or to gain autowarming data from.
-
-        
-     -->
-
     <!-- Use Cold Searcher
 
          If a search request comes in and there is no current
@@ -278,7 +311,7 @@
     <useColdSearcher>false</useColdSearcher>
 
     <!-- Max Warming Searchers
-         
+
          Maximum number of searchers that may be warming in the
          background concurrently.  An error is returned if this limit
          is exceeded.
@@ -286,7 +319,7 @@
          Recommend values of 1-2 for read-only slaves, higher for
          masters w/o cache warming.
       -->
-    <maxWarmingSearchers>5</maxWarmingSearchers>
+    <maxWarmingSearchers>2</maxWarmingSearchers>
 
   </query>
 
@@ -300,7 +333,7 @@
        such as /select?qt=XXX
 
        handleSelect="true" will cause the SolrDispatchFilter to process
-       the request and dispatch the query to a handler specified by the 
+       the request and dispatch the query to a handler specified by the
        "qt" param, assuming "/select" isn't already registered.
 
        handleSelect="false" will cause the SolrDispatchFilter to
@@ -322,18 +355,29 @@
 
          multipartUploadLimitInKB - specifies the max size (in KiB) of
          Multipart File Uploads that Solr will allow in a Request.
-         
+
          formdataUploadLimitInKB - specifies the max size (in KiB) of
          form data (application/x-www-form-urlencoded) sent via
          POST. You can use POST to pass request parameters not
          fitting into the URL.
-         
+
+         addHttpRequestToContext - if set to true, it will instruct
+         the requestParsers to include the original HttpServletRequest
+         object in the context map of the SolrQueryRequest under the
+         key "httpRequest". It will not be used by any of the existing
+         Solr components, but may be useful when developing custom
+         plugins.
+
          *** WARNING ***
          The settings below authorize Solr to fetch remote files, You
          should make sure your system has some authentication before
          using enableRemoteStreaming="true"
 
-      --> 
+      -->
+    <requestParsers enableRemoteStreaming="true"
+                    multipartUploadLimitInKB="2048000"
+                    formdataUploadLimitInKB="2048"
+                    addHttpRequestToContext="false"/>
 
     <!-- HTTP Caching
 
@@ -343,54 +387,10 @@
          related headers
       -->
     <httpCaching never304="true" />
-    <!-- If you include a <cacheControl> directive, it will be used to
-         generate a Cache-Control header (as well as an Expires header
-         if the value contains "max-age=")
-         
-         By default, no Cache-Control header is generated.
-         
-         You can use the <cacheControl> option even if you have set
-         never304="true"
-      -->
-    <!--
-       <httpCaching never304="true" >
-         <cacheControl>max-age=30, public</cacheControl> 
-       </httpCaching>
-      -->
-    <!-- To enable Solr to respond with automatically generated HTTP
-         Caching headers, and to response to Cache Validation requests
-         correctly, set the value of never304="false"
-         
-         This will cause Solr to generate Last-Modified and ETag
-         headers based on the properties of the Index.
-
-         The following options can also be specified to affect the
-         values of these headers...
-
-         lastModFrom - the default value is "openTime" which means the
-         Last-Modified value (and validation against If-Modified-Since
-         requests) will all be relative to when the current Searcher
-         was opened.  You can change it to lastModFrom="dirLastMod" if
-         you want the value to exactly correspond to when the physical
-         index was last modified.
-
-         etagSeed="..." is an option you can change to force the ETag
-         header (and validation against If-None-Match requests) to be
-         different even if the index has not changed (ie: when making
-         significant changes to your config file)
-
-         (lastModifiedFrom and etagSeed are both ignored if you use
-         the never304="true" option)
-      -->
-    <!--
-       <httpCaching lastModifiedFrom="openTime"
-                    etagSeed="Solr">
-         <cacheControl>max-age=30, public</cacheControl> 
-       </httpCaching>
-      -->
+
   </requestDispatcher>
 
-  <!-- Request Handlers 
+  <!-- Request Handlers
 
        http://wiki.apache.org/solr/SolrRequestHandler
 
@@ -419,6 +419,11 @@
        queries across multiple shards
     -->
   <requestHandler name="/select" class="solr.SearchHandler">
+    <lst name="defaults">
+      <str name="spellcheck.dictionary">default</str>
+      <str name="spellcheck.extendedResults">true</str>
+      <str name="spellcheck.collate">true</str>
+    </lst>
     <arr name="last-components">
       <str>spellcheck</str>
     </arr>
@@ -434,78 +439,97 @@
      </lst>
      <arr name="last-components">
        <str>spellcheck</str>
-     </arr>     
+     </arr>
   </requestHandler>
 
+  <!--
+    The export request handler is used to export full sorted result sets.
+    Do not change these defaults.
+  -->
+  <requestHandler name="/export" class="solr.SearchHandler">
+    <lst name="invariants">
+      <str name="rq">{!xport}</str>
+      <str name="wt">xsort</str>
+      <str name="distrib">false</str>
+    </lst>
 
-  <!-- realtime get handler, guaranteed to return the latest stored fields of
-       any document, without the need to commit or open a new searcher.  The
-       current implementation relies on the updateLog feature being enabled. -->
-  <requestHandler name="/get" class="solr.RealTimeGetHandler">
-     <lst name="defaults">
-       <str name="omitHeader">true</str>
-       <str name="wt">json</str>
-       <str name="indent">true</str>
-     </lst>
-  </requestHandler>
-
-  <requestHandler name="/update" class="solr.UpdateRequestHandler">
-  </requestHandler>
-
-  <requestHandler name="/update/json" class="solr.JsonUpdateRequestHandler">
-        <lst name="defaults">
-         <str name="stream.contentType">application/json</str>
-       </lst>
+    <arr name="components">
+      <str>query</str>
+    </arr>
   </requestHandler>
 
-  <requestHandler name="/update/csv" class="solr.CSVRequestHandler">
-        <lst name="defaults">
-         <str name="stream.contentType">application/csv</str>
-       </lst>
-  </requestHandler>
 
-  <requestHandler name="/update/extract" 
-                  startup="lazy"
-                  class="solr.extraction.ExtractingRequestHandler" >
+  <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell">
     <lst name="defaults">
-      <str name="lowernames">true</str>
-      <str name="uprefix">ignored_</str>
-
-      <!-- capture link hrefs but ignore div attributes -->
-      <str name="captureAttr">true</str>
-      <str name="fmap.a">links</str>
-      <str name="fmap.div">ignored_</str>
+      <str name="df">text</str>
     </lst>
-  </requestHandler>
-
-  <requestHandler name="/analysis/field" 
+  </initParams>
+
+  <!-- Field Analysis Request Handler
+
+       RequestHandler that provides much the same functionality as
+       analysis.jsp. Provides the ability to specify multiple field
+       types and field names in the same request and outputs
+       index-time and query-time analysis for each of them.
+
+       Request parameters are:
+       analysis.fieldname - field name whose analyzers are to be used
+
+       analysis.fieldtype - field type whose analyzers are to be used
+       analysis.fieldvalue - text for index-time analysis
+       q (or analysis.q) - text for query time analysis
+       analysis.showmatch (true|false) - When set to true and when
+           query analysis is performed, the produced tokens of the
+           field value analysis will be marked as "matched" for every
+           token that is produces by the query analysis
+   -->
+  <requestHandler name="/analysis/field"
                   startup="lazy"
                   class="solr.FieldAnalysisRequestHandler" />
 
-  <requestHandler name="/analysis/document" 
-                  class="solr.DocumentAnalysisRequestHandler" 
-                  startup="lazy" />
 
-  <!-- ping/healthcheck -->
-  <requestHandler name="/admin/ping" class="solr.PingRequestHandler">
-    <lst name="invariants">
-      <str name="q">solrpingquery</str>
-    </lst>
-    <lst name="defaults">
-      <str name="echoParams">all</str>
-    </lst>
-  </requestHandler>
+  <!-- Document Analysis Handler
+
+       http://wiki.apache.org/solr/AnalysisRequestHandler
+
+       An analysis handler that provides a breakdown of the analysis
+       process of provided documents. This handler expects a (single)
+       content stream with the following format:
+
+       <docs>
+         <doc>
+           <field name="id">1</field>
+           <field name="name">The Name</field>
+           <field name="text">The Text Value</field>
+         </doc>
+         <doc>...</doc>
+         <doc>...</doc>
+         ...
+       </docs>
+
+    Note: Each document must contain a field which serves as the
+    unique key. This key is used in the returned response to associate
+    an analysis breakdown to the analyzed document.
 
+    Like the FieldAnalysisRequestHandler, this handler also supports
+    query analysis by sending either an "analysis.query" or "q"
+    request parameter that holds the query text to be analyzed. It
+    also supports the "analysis.showmatch" parameter which when set to
+    true, all field tokens that match the query tokens will be marked
+    as a "match".
+  -->
+  <requestHandler name="/analysis/document"
+                  class="solr.DocumentAnalysisRequestHandler"
+                  startup="lazy" />
+
+  <!-- Echo the request contents back to the client -->
   <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
     <lst name="defaults">
-     <str name="echoParams">explicit</str> 
+     <str name="echoParams">explicit</str>
      <str name="echoHandler">true</str>
     </lst>
   </requestHandler>
 
-  <requestHandler name="/replication" class="solr.ReplicationHandler" > 
-  </requestHandler>
-
   <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
 
     <str name="queryAnalyzerFieldType">textSpell</str>
@@ -513,11 +537,18 @@
     <!-- Multiple "Spell Checkers" can be declared and used by this
          component
       -->
-
-    <!-- a spellchecker built from a field of the main index -->
     <lst name="spellchecker">
       <str name="name">default</str>
-      <str name="field">name</str>
+      <!-- change field to textSpell and use copyField in schema.xml
+      to spellcheck multiple fields -->
+      <str name="field">textSpell</str>
+      <str name="buildOnCommit">true</str>
+    </lst>
+
+    <lst name="spellchecker">
+      <str name="name">example</str>
+      <str name="field">title_text</str>
+      <str name="buildOnCommit">true</str>
       <str name="classname">solr.DirectSolrSpellChecker</str>
       <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
       <str name="distanceMeasure">internal</str>
@@ -534,134 +565,69 @@
       <!-- maximum threshold of documents a query term can appear to be considered for correction -->
       <float name="maxQueryFrequency">0.01</float>
       <!-- uncomment this to require suggestions to occur in 1% of the documents
-      	<float name="thresholdTokenFrequency">.01</float>
+           <float name="thresholdTokenFrequency">.01</float>
       -->
     </lst>
-    
+
     <!-- a spellchecker that can break or combine words.  See "/spell" handler below for usage -->
     <lst name="spellchecker">
       <str name="name">wordbreak</str>
-      <str name="classname">solr.WordBreakSolrSpellChecker</str>      
+      <str name="classname">solr.WordBreakSolrSpellChecker</str>
       <str name="field">name</str>
       <str name="combineWords">true</str>
       <str name="breakWords">true</str>
       <int name="maxChanges">10</int>
     </lst>
+    -->
   </searchComponent>
 
-  <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
+  <!-- Search Components
+
+       Search components are registered to SolrCore and used by
+       instances of SearchHandler (which can access them by name)
+
+       By default, the following components are available:
+
+       <searchComponent name="query"     class="solr.QueryComponent" />
+       <searchComponent name="facet"     class="solr.FacetComponent" />
+       <searchComponent name="mlt"       class="solr.MoreLikeThisComponent" />
+       <searchComponent name="highlight" class="solr.HighlightComponent" />
+       <searchComponent name="stats"     class="solr.StatsComponent" />
+       <searchComponent name="debug"     class="solr.DebugComponent" />
 
+     -->
+
+  <!-- Terms Component
+
+       http://wiki.apache.org/solr/TermsComponent
+
+       A component to return terms and document frequency of those
+       terms
+    -->
   <searchComponent name="terms" class="solr.TermsComponent"/>
 
-  <searchComponent class="solr.HighlightComponent" name="highlight">
-    <highlighting>
-      <!-- Configure the standard fragmenter -->
-      <!-- This could most likely be commented out in the "default" case -->
-      <fragmenter name="gap" 
-                  default="true"
-                  class="solr.highlight.GapFragmenter">
-        <lst name="defaults">
-          <int name="hl.fragsize">100</int>
-        </lst>
-      </fragmenter>
-
-      <!-- A regular-expression-based fragmenter 
-           (for sentence extraction) 
-        -->
-      <fragmenter name="regex" 
-                  class="solr.highlight.RegexFragmenter">
-        <lst name="defaults">
-          <!-- slightly smaller fragsizes work better because of slop -->
-          <int name="hl.fragsize">70</int>
-          <!-- allow 50% slop on fragment sizes -->
-          <float name="hl.regex.slop">0.5</float>
-          <!-- a basic sentence pattern -->
-          <str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
-        </lst>
-      </fragmenter>
-
-      <!-- Configure the standard formatter -->
-      <formatter name="html" 
-                 default="true"
-                 class="solr.highlight.HtmlFormatter">
-        <lst name="defaults">
-          <str name="hl.simple.pre"><![CDATA[<em>]]></str>
-          <str name="hl.simple.post"><![CDATA[</em>]]></str>
-        </lst>
-      </formatter>
-
-      <!-- Configure the standard encoder -->
-      <encoder name="html" 
-               class="solr.highlight.HtmlEncoder" />
-
-      <!-- Configure the standard fragListBuilder -->
-      <fragListBuilder name="simple" 
-                       class="solr.highlight.SimpleFragListBuilder"/>
-      
-      <!-- Configure the single fragListBuilder -->
-      <fragListBuilder name="single" 
-                       class="solr.highlight.SingleFragListBuilder"/>
-      
-      <!-- Configure the weighted fragListBuilder -->
-      <fragListBuilder name="weighted" 
-                       default="true"
-                       class="solr.highlight.WeightedFragListBuilder"/>
-      
-      <!-- default tag FragmentsBuilder -->
-      <fragmentsBuilder name="default" 
-                        default="true"
-                        class="solr.highlight.ScoreOrderFragmentsBuilder">
-        <!-- 
-        <lst name="defaults">
-          <str name="hl.multiValuedSeparatorChar">/</str>
-        </lst>
-        -->
-      </fragmentsBuilder>
-
-      <!-- multi-colored tag FragmentsBuilder -->
-      <fragmentsBuilder name="colored" 
-                        class="solr.highlight.ScoreOrderFragmentsBuilder">
-        <lst name="defaults">
-          <str name="hl.tag.pre"><![CDATA[
-               <b style="background:yellow">,<b style="background:lawgreen">,
-               <b style="background:aquamarine">,<b style="background:magenta">,
-               <b style="background:palegreen">,<b style="background:coral">,
-               <b style="background:wheat">,<b style="background:khaki">,
-               <b style="background:lime">,<b style="background:deepskyblue">]]></str>
-          <str name="hl.tag.post"><![CDATA[</b>]]></str>
-        </lst>
-      </fragmentsBuilder>
-      
-      <boundaryScanner name="default" 
-                       default="true"
-                       class="solr.highlight.SimpleBoundaryScanner">
-        <lst name="defaults">
-          <str name="hl.bs.maxScan">10</str>
-          <str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
-        </lst>
-      </boundaryScanner>
-      
-      <boundaryScanner name="breakIterator" 
-                       class="solr.highlight.BreakIteratorBoundaryScanner">
-        <lst name="defaults">
-          <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
-          <str name="hl.bs.type">WORD</str>
-          <!-- language and country are used when constructing Locale object.  -->
-          <!-- And the Locale object will be used when getting instance of BreakIterator -->
-          <str name="hl.bs.language">en</str>
-          <str name="hl.bs.country">US</str>
-        </lst>
-      </boundaryScanner>
-    </highlighting>
-  </searchComponent>
-  
+  <!-- A request handler for demonstrating the terms component -->
+  <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
+     <lst name="defaults">
+      <bool name="terms">true</bool>
+      <bool name="distrib">false</bool>
+    </lst>
+    <arr name="components">
+      <str>terms</str>
+    </arr>
+  </requestHandler>
+
   <requestHandler class="solr.MoreLikeThisHandler" name="/mlt">
     <lst name="defaults">
       <str name="mlt.mintf">1</str>
       <str name="mlt.mindf">2</str>
     </lst>
   </requestHandler>
-  
-  <!-- Admin Handlers - This will register all the standard admin RequestHandlers. -->
-  <requestHandler name="/admin/" class="solr.admin.AdminHandlers" />
+
+  <!-- Legacy config for the admin interface -->
+  <admin>
+    <defaultQuery>*:*</defaultQuery>
+  </admin>
+
 </config>
+