bigindex-solr 1.2.0 → 1.3.0

data/solr/solr/bin/backup

@@ -74,7 +74,7 @@ fi
 
 fixUser "$@"
 
-start=`date +"%s"`
+setStartTime
 
 logMessage started by $oldwhoami
 logMessage command: $0 $@
@@ -101,7 +101,16 @@ logMessage making backup ${data_dir}/${name}
 
 # make a backup using hard links into temporary location
 # then move it into place atomically
-cp -lr ${data_dir}/index ${data_dir}/${temp}
+if [[ "${OS}" == "SunOS" || "${OS}" == "Darwin" || "${OS}" == "FreeBSD" ]]
+then
+  orig_dir=$(pwd)
+  mkdir ${data_dir}/${temp}
+  cd ${data_dir}/index
+  find . -print|cpio -pdlmu ${data_dir}/${temp} 1>/dev/null 2>&1
+  cd ${orig_dir}
+else
+  cp -lr ${data_dir}/index ${data_dir}/${temp}
+fi
 mv ${data_dir}/${temp} ${data_dir}/${name}
 
 logExit ended 0

data/solr/solr/bin/backupcleaner

@@ -95,7 +95,7 @@ function remove
     /bin/rm -rf $1
 }
 
-start=`date +"%s"`
+setStartTime
 
 logMessage started by $oldwhoami
 logMessage command: $0 $@

data/solr/solr/bin/commit

@@ -103,7 +103,7 @@ fi
 
 fixUser "$@"
 
-start=`date +"%s"`
+setStartTime
 
 logMessage started by $oldwhoami
 logMessage command: $0 $@
@@ -116,13 +116,18 @@ then
   logExit failed 1
 fi
 
-# check status of commit request
+# check status of commit request - original format
 echo $rs | grep '<result.*status="0"' > /dev/null 2>&1
 if [[ $? != 0 ]]
 then
-  logMessage commit request to Solr at ${curl_url} failed:
-  logMessage $rs
-  logExit failed 2
+# check status of commit request - new format
+  echo $rs | grep '<lst name="responseHeader"><int name="status">0</int>' > /dev/null 2>&1
+  if [[ $? != 0 ]]
+  then
+    logMessage commit request to Solr at ${curl_url} failed:
+    logMessage $rs
+    logExit failed 2
+  fi
 fi
 
 logExit ended 0

data/solr/solr/bin/optimize

@@ -104,7 +104,7 @@ fi
 
 fixUser "$@"
 
-start=`date +"%s"`
+setStartTime
 
 logMessage started by $oldwhoami
 logMessage command: $0 $@
@@ -117,13 +117,18 @@ then
   logExit failed 1
 fi
 
-# check status of optimize request
+# check status of optimize request - original format
 rc=`echo $rs|cut -f2 -d'"'`
 if [[ $? != 0 ]]
 then
-  logMessage optimize request to Solr at ${curl_url} failed:
-  logMessage $rs
-  logExit failed 2
+# check status of optimize request - new format
+  echo $rs | grep '<lst name="responseHeader"><int name="status">0</int>' > /dev/null 2>&1
+  if [[ $? != 0 ]]
+  then
+    logMessage optimize request to Solr at ${curl_url} failed:
+    logMessage $rs
+    logExit failed 2
+  fi
 fi
 
 logExit ended 0

data/solr/solr/bin/readercycle

@@ -104,7 +104,7 @@ fi
 
 fixUser "$@"
 
-start=`date +"%s"`
+setStartTime
 
 logMessage started by $oldwhoami
 logMessage command: $0 $@

data/solr/solr/bin/rsyncd-disable

@@ -60,7 +60,7 @@ done
 
 fixUser "$@"
 
-start=`date +"%s"`
+setStartTime
 
 logMessage disabled by $oldwhoami
 logMessage command: $0 $@

data/solr/solr/bin/rsyncd-enable

@@ -59,7 +59,7 @@ done
 
 fixUser "$@"
 
-start=`date +"%s"`
+setStartTime
 
 logMessage enabled by $oldwhoami
 logMessage command: $0 $@

data/solr/solr/bin/rsyncd-start

@@ -98,7 +98,7 @@ logMessage command: $0 $@
 if [[ ! -f ${solr_root}/logs/rsyncd-enabled ]]
 then
     logMessage rsyncd disabled
-    exit 1
+    exit 2
 fi
 
 if \

data/solr/solr/bin/scripts-util

@@ -21,6 +21,7 @@ export PATH=/sbin:/usr/sbin:/bin:/usr/bin:$PATH
 
 # set up variables
 prog=${0##*/}
+OS=`uname`
 
 # source the config file if present
 confFile=${solr_root}/conf/scripts.conf
@@ -48,7 +49,17 @@ function fixUser
 
     if [[ "${oldwhoami}" == "" ]]
     then
-        oldwhoami=`ps h -Hfp $(pgrep -g0 ${0##*/}) | tail -1|cut -f1 -d" "`
+        oldwhoami=`ps h -Hfp $(pgrep -f -g0 $0) | tail -1|cut -f1 -d" "`
+    fi
+}
+
+function setStartTime
+{
+    if [[ "${OS}" == "SunOS" ]]
+    then
+        start=`perl -e "print time;"`
+    else
+        start=`date +"%s"`
     fi
 }
 
@@ -68,7 +79,12 @@ function logMessage
 
 function logExit
 {
-    end=`date +"%s"`
+    if [[ "${OS}" == "SunOS" ]]
+    then
+        end=`perl -e "print time;"`
+    else
+        end=`date +"%s"`
+    fi
     diff=`expr $end - $start`
     echo "$(timeStamp) $1 (elapsed time: $diff sec)">>$log
     exit $2

data/solr/solr/bin/snapcleaner

@@ -91,7 +91,13 @@ fi
 
 function remove
 {
-    syncing=`ps -fwwwu ${user}|grep -w rsync|grep -v grep|grep -w $1`
+    if [[ "${OS}" == "Darwin" || "${OS}" == "FreeBSD" ]]
+    then
+     syncing=`ps -www -U ${user} |grep -w rsync|grep -v grep|grep -w $1`
+    else
+     syncing=`ps -fwwwu ${user}|grep -w rsync|grep -v grep|grep -w $1`
+    fi
+
     if [[ -n $syncing ]]
     then
 	logMessage $1 not removed - rsync in progress
@@ -101,7 +107,7 @@ function remove
     fi
 }
 
-start=`date +"%s"`
+setStartTime
 
 logMessage started by $oldwhoami
 logMessage command: $0 $@

data/solr/solr/bin/snapinstaller

@@ -104,7 +104,7 @@ then
     master_status_dir=${solr_root}/${master_status_dir}
 fi
 
-start=`date +"%s"`
+setStartTime
 
 logMessage started by $oldwhoami
 logMessage command: $0 $@
@@ -141,9 +141,20 @@ fi
 # install using hard links into temporary directory
 # remove original index and then atomically copy new one into place
 logMessage installing snapshot ${name}
-cp -lr ${name}/ ${data_dir}/index.tmp$$
-/bin/rm -rf ${data_dir}/index
-mv -f ${data_dir}/index.tmp$$ ${data_dir}/index
+if [[ "${OS}" == "SunOS" || "${OS}" == "Darwin" || "${OS}" == "FreeBSD" ]]
+then
+  orig_dir=$(pwd)
+  mkdir ${data_dir}/index.tmp$$ && \
+  cd ${name} && \
+  find . -print|cpio -pdlmu ${data_dir}/index.tmp$$ 1>/dev/null 2>&1 && \
+  /bin/rm -rf ${data_dir}/index && \
+  mv -f ${data_dir}/index.tmp$$ ${data_dir}/index
+  cd ${orig_dir}
+else
+  cp -lr ${name}/ ${data_dir}/index.tmp$$ && \
+  /bin/rm -rf ${data_dir}/index && \
+  mv -f ${data_dir}/index.tmp$$ ${data_dir}/index
+fi
 
 # update distribution stats
 echo ${name} > ${solr_root}/logs/snapshot.current

data/solr/solr/bin/snappuller

@@ -156,7 +156,7 @@ function pushStatus
     scp -q -o StrictHostKeyChecking=no ${solr_root}/logs/snappuller.status ${master_host}:${master_status_dir}/snapshot.status.`uname -n`
 }
 
-start=`date +"%s"`
+setStartTime
 
 logMessage started by $oldwhoami
 logMessage command: $0 $@
@@ -164,7 +164,7 @@ logMessage command: $0 $@
 if [[ ! -f ${solr_root}/logs/snappuller-enabled ]]
 then
     logMessage snappuller disabled
-    exit 1
+    exit 2
 fi
 
 # make sure we can ssh to master
@@ -200,7 +200,16 @@ fi
 # take a snapshot of current index so that only modified files will be rsync-ed
 # put the snapshot in the 'work-in-progress" directory to prevent it from
 # being installed while the copying is still in progress
-cp -lr ${data_dir}/index ${data_dir}/${name}-wip
+if [[ "${OS}" == "SunOS" || "${OS}" == "Darwin" || "${OS}" == "FreeBSD"  ]]
+then
+  orig_dir=$(pwd)
+  mkdir ${data_dir}/${name}-wip
+  cd ${data_dir}/index
+  find . -print|cpio -pdlmu ${data_dir}/${name}-wip 1>/dev/null 2>&1
+  cd ${orig_dir}
+else
+  cp -lr ${data_dir}/index ${data_dir}/${name}-wip
+fi
 # force rsync of segments and .del files since we are doing size-only
 if [[ -n ${sizeonly} ]]
 then
@@ -214,9 +223,15 @@ logMessage pulling snapshot ${name}
 ssh -o StrictHostKeyChecking=no ${master_host} mkdir -p ${master_status_dir}
 
 # start new distribution stats
-rsyncStart=`date`
+rsyncStart=`date +'%Y-%m-%d %H:%M:%S'`
+if [[ "${OS}" == "Darwin" || "${OS}" == "FreeBSD"  ]]
+then
+  startTimestamp=`date -j -f '%Y-%m-%d %H:%M:%S' "$rsyncStart" +'%Y%m%d-%H%M%S'`
+  rsyncStartSec=`date -j -f '%Y-%m-%d %H:%M:%S' "$rsyncStart" +'%s'`
+else
 startTimestamp=`date -d "$rsyncStart" +'%Y%m%d-%H%M%S'`
 rsyncStartSec=`date -d "$rsyncStart" +'%s'`
+fi
 startStatus="rsync of `basename ${name}` started:$startTimestamp"
 echo ${startStatus} > ${solr_root}/logs/snappuller.status
 pushStatus
@@ -226,9 +241,15 @@ rsync -Wa${verbose}${compress} --delete ${sizeonly} \
 ${stats} rsync://${master_host}:${rsyncd_port}/solr/${name}/ ${data_dir}/${name}-wip
 
 rc=$?
-rsyncEnd=`date`
+rsyncEnd=`date +'%Y-%m-%d %H:%M:%S'`
+if [[ "${OS}" == "Darwin" || "${OS}" == "FreeBSD"  ]]
+then
+  endTimestamp=`date -j -f '%Y-%m-%d %H:%M:%S' "$rsyncEnd" +'%Y%m%d-%H%M%S'`
+  rsyncEndSec=`date -j -f '%Y-%m-%d %H:%M:%S' "$rsyncEnd" +'%s'`
+else
 endTimestamp=`date -d "$rsyncEnd" +'%Y%m%d-%H%M%S'`
 rsyncEndSec=`date -d "$rsyncEnd" +'%s'`
+fi
 elapsed=`expr $rsyncEndSec - $rsyncStartSec`
 if [[ $rc != 0 ]]
 then

data/solr/solr/bin/snappuller-disable

@@ -60,7 +60,7 @@ done
 
 fixUser "$@"
 
-start=`date +"%s"`
+setStartTime
 
 logMessage disabled by $oldwhoami
 logMessage command: $0 $@

data/solr/solr/bin/snappuller-enable

@@ -60,7 +60,7 @@ done
 
 fixUser "$@"
 
-start=`date +"%s"`
+setStartTime
 
 logMessage enabled by $oldwhoami
 logMessage command: $0 $@

data/solr/solr/bin/snapshooter

@@ -36,10 +36,11 @@ usage: $prog [-d dir] [-u username] [-v]
        -u          specify user to sudo to before running script
        -v          increase verbosity
        -V          output debugging info
+       -c          only take snapshot if different than previous
 "
 
 # parse args
-while getopts d:u:vV OPTION
+while getopts d:u:vVc OPTION
 do
     case $OPTION in
     d)
@@ -54,6 +55,9 @@ do
     V)
         debug="V"
         ;;
+    c)
+        check=1
+ 	;;
     *)
         echo "$USAGE"
         exit 1
@@ -74,7 +78,7 @@ then
     data_dir=${solr_root}/${data_dir}
 fi
 
-start=`date +"%s"`
+setStartTime
 
 logMessage started by $oldwhoami
 logMessage command: $0 $@
@@ -95,6 +99,20 @@ then
     logExit aborted 1
 fi
 
+if [[ ${check} ]]
+then
+   previous=`find ${data_dir} -name snapshot.\* | sort -r  | head -1` 
+   if [[ -d ${previous} ]]
+   then
+     differences=`diff -q ${data_dir}/index ${previous} | wc -l` 
+     if [[ ${differences} -lt 1 ]]
+     then 
+       logMessage Snap would be same as last, exiting
+       logExit aborted 1 
+     fi
+   fi
+fi
+
 # clean up after INT/TERM
 trap 'echo cleaning up, please wait ...;/bin/rm -rf ${name} ${temp};logExit aborted 13' INT TERM
 
@@ -102,7 +120,16 @@ logMessage taking snapshot ${name}
 
 # take a snapshot using hard links into temporary location
 # then move it into place atomically
-cp -lr ${data_dir}/index ${temp}
+if [[ "${OS}" == "SunOS" || "${OS}" == "Darwin"  || "${OS}" == "FreeBSD" ]]
+then
+  orig_dir=$(pwd)
+  mkdir ${temp}
+  cd ${data_dir}/index
+  find . -print|cpio -pdlmu ${temp} 1>/dev/null 2>&1
+  cd ${orig_dir}
+else
+  cp -lr ${data_dir}/index ${temp}
+fi
 mv ${temp} ${name}
 
 logExit ended 0

data/solr/solr/conf/elevate.xml

@@ -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>

data/solr/solr/conf/solrconfig.xml

@@ -29,34 +29,105 @@
   <!-- 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:./solr/data}</dataDir>
 
+
   <indexDefaults>
    <!-- Values here affect all index writers and act as a default unless overridden. -->
     <useCompoundFile>false</useCompoundFile>
+
     <mergeFactor>10</mergeFactor>
-    <maxBufferedDocs>1000</maxBufferedDocs>
+    <!--
+     If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
+
+     -->
+    <!--<maxBufferedDocs>1000</maxBufferedDocs>-->
+    <!-- Tell Lucene when to flush documents to disk.
+    Giving Lucene more memory for indexing means faster indexing at the cost of more RAM
+
+    If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
+
+    -->
+    <ramBufferSizeMB>32</ramBufferSizeMB>
     <maxMergeDocs>2147483647</maxMergeDocs>
     <maxFieldLength>10000</maxFieldLength>
     <writeLockTimeout>1000</writeLockTimeout>
     <commitLockTimeout>10000</commitLockTimeout>
+
+    <!--
+     Expert: Turn on Lucene's auto commit capability.
+     This causes intermediate segment flushes to write a new lucene
+     index descriptor, enabling it to be opened by an external
+     IndexReader.
+     NOTE: Despite the name, this value does not have any relation to Solr's autoCommit functionality
+     -->
+    <!--<luceneAutoCommit>false</luceneAutoCommit>-->
+    <!--
+     Expert:
+     The Merge Policy in Lucene controls how merging is handled by Lucene.  The default in 2.3 is the LogByteSizeMergePolicy, previous
+     versions used LogDocMergePolicy.
+
+     LogByteSizeMergePolicy chooses segments to merge based on their size.  The Lucene 2.2 default, LogDocMergePolicy chose when
+     to merge based on number of documents
+
+     Other implementations of MergePolicy must have a no-argument constructor
+     -->
+    <!--<mergePolicy>org.apache.lucene.index.LogByteSizeMergePolicy</mergePolicy>-->
+
+    <!--
+     Expert:
+     The Merge Scheduler in Lucene controls how merges are performed.  The ConcurrentMergeScheduler (Lucene 2.3 default)
+      can perform merges in the background using separate threads.  The SerialMergeScheduler (Lucene 2.2 default) does not.
+     -->
+    <!--<mergeScheduler>org.apache.lucene.index.ConcurrentMergeScheduler</mergeScheduler>-->
+
+    <!--
+      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
+      simple = SimpleFSLockFactory
+
+      (For backwards compatibility with Solr 1.2, 'simple' is the default
+       if not specified.)
+    -->
+    <lockType>single</lockType>
   </indexDefaults>
 
   <mainIndex>
     <!-- options specific to the main on-disk lucene index -->
     <useCompoundFile>false</useCompoundFile>
+    <ramBufferSizeMB>32</ramBufferSizeMB>
     <mergeFactor>10</mergeFactor>
-    <maxBufferedDocs>1000</maxBufferedDocs>
+    <!-- Deprecated -->
+    <!--<maxBufferedDocs>1000</maxBufferedDocs>-->
     <maxMergeDocs>2147483647</maxMergeDocs>
     <maxFieldLength>10000</maxFieldLength>
 
     <!-- If true, unlock any held write or commit locks on startup. 
          This defeats the locking mechanism that allows multiple
          processes to safely access a lucene index, and should be
-         used with care. -->
+         used with care.
+         This is not needed if lock type is 'none' or 'single'
+     -->
     <unlockOnStartup>false</unlockOnStartup>
   </mainIndex>
+  
+  <!--	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.
+  		
+		If you want to connect to a particular server, specify the agentId
+		e.g. <jmx agentId="myAgent" />
+		
+		If you want to start a new MBeanServer, specify the serviceUrl
+		e.g <jmx serviceurl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr" />
+		
+		For more details see http://wiki.apache.org/solr/SolrJmx
+  -->
+  <jmx />
 
   <!-- the default high-performance update handler -->
   <updateHandler class="solr.DirectUpdateHandler2">
@@ -66,10 +137,12 @@
          org.apache.solr.(search|update|request|core|analysis)
      -->
 
-    <!-- autocommit pending docs if certain criteria are met 
+    <!-- Perform a <commit/> automatically under certain conditions:
+         maxDocs - number of updates since last commit is greater than this
+         maxTime - oldest uncommited update (in ms) is this long ago
     <autoCommit> 
       <maxDocs>10000</maxDocs>
-      <maxTime>1000</maxTime>
+      <maxTime>1000</maxTime> 
     </autoCommit>
     -->
 
@@ -82,8 +155,8 @@
       -->
     <!-- A postCommit event is fired after every commit or optimize command
     <listener event="postCommit" class="solr.RunExecutableListener">
-      <str name="exe">snapshooter</str>
-      <str name="dir">solr/bin</str>
+      <str name="exe">solr/bin/snapshooter</str>
+      <str name="dir">.</str>
       <bool name="wait">true</bool>
       <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
       <arr name="env"> <str>MYVAR=val1</str> </arr>
@@ -126,7 +199,7 @@
       class="solr.LRUCache"
       size="512"
       initialSize="512"
-      autowarmCount="256"/>
+      autowarmCount="128"/>
 
    <!-- queryResultCache caches results of searches - ordered lists of
          document ids (DocList) based on a query, a sort, and the range
@@ -135,7 +208,7 @@
       class="solr.LRUCache"
       size="512"
       initialSize="512"
-      autowarmCount="256"/>
+      autowarmCount="32"/>
 
   <!-- documentCache caches Lucene Document objects (the stored fields for each document).
        Since Lucene internal document ids are transient, this cache will not be autowarmed.  -->
@@ -180,9 +253,13 @@
          is requested, a superset of the requested number of document ids
          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 50 will be collected and cached.  Any further
+         then documents 0 through 49 will be collected and cached.  Any further
          requests in that range can be satisfied via the cache.  -->
-    <queryResultWindowSize>10</queryResultWindowSize>
+    <queryResultWindowSize>50</queryResultWindowSize>
+    
+    <!-- Maximum number of documents to cache for any entry in the
+         queryResultCache. -->
+    <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
 
     <!-- This entry enables an int hash representation for filters (DocSets)
          when the number of items in the set is less than maxSize.  For smaller
@@ -190,36 +267,27 @@
          iterate over, and faster to take intersections.  -->
     <HashDocSet maxSize="3000" loadFactor="0.75"/>
 
-
-    <!-- boolToFilterOptimizer converts boolean clauses with zero boost
-         into cached filters if the number of docs selected by the clause exceeds
-         the threshold (represented as a fraction of the total index) -->
-    <boolTofilterOptimizer enabled="true" cacheSize="32" threshold=".05"/>
-
-
     <!-- a newSearcher event is fired whenever a new searcher is being prepared
          and there is a current searcher handling requests (aka registered). -->
     <!-- QuerySenderListener takes an array of NamedList and executes a
          local query request for each NamedList in sequence. -->
-    <!--
     <listener event="newSearcher" class="solr.QuerySenderListener">
       <arr name="queries">
         <lst> <str name="q">solr</str> <str name="start">0</str> <str name="rows">10</str> </lst>
         <lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
+        <lst><str name="q">static newSearcher warming query from solrconfig.xml</str></lst>
       </arr>
     </listener>
-    -->
 
     <!-- a firstSearcher event is fired whenever a new searcher is being
          prepared but there is no current registered searcher to handle
          requests or to gain autowarming data from. -->
-    <!--
     <listener event="firstSearcher" class="solr.QuerySenderListener">
       <arr name="queries">
         <lst> <str name="q">fast_warm</str> <str name="start">0</str> <str name="rows">10</str> </lst>
+        <lst><str name="q">static firstSearcher warming query from solrconfig.xml</str></lst>
       </arr>
     </listener>
-    -->
 
     <!-- If a search request comes in and there is no current registered searcher,
          then immediately register the still warming searcher and use it.  If
@@ -230,7 +298,7 @@
     <!-- Maximum number of searchers that may be warming in the background
       concurrently.  An error is returned if this limit is exceeded. Recommend
       1-2 for read-only slaves, higher for masters w/o cache warming. -->
-    <maxWarmingSearchers>4</maxWarmingSearchers>
+    <maxWarmingSearchers>2</maxWarmingSearchers>
 
   </query>
 
@@ -242,20 +310,57 @@
   <requestDispatcher handleSelect="true" >
     <!--Make sure your system has some authentication before enabling remote streaming!  -->
     <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+        
+    <!-- Set HTTP caching related parameters (for proxy caches and clients).
+          
+         To get the behaviour of Solr 1.2 (ie: no caching related headers)
+         use the never304="true" option and do not specify a value for
+         <cacheControl>
+    -->
+    <!-- <httpCaching never304="true"> -->
+    <httpCaching lastModifiedFrom="openTime"
+                 etagSeed="Solr">
+       <!-- lastModFrom="openTime" is the default, 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 corrispond 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
+            differnet 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.
+       -->
+       <!-- 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"
+       -->
+       <!-- <cacheControl>max-age=30, public</cacheControl> -->
+    </httpCaching>
   </requestDispatcher>
   
       
   <!-- requestHandler plugins... incoming queries will be dispatched to the
-     correct handler based on the qt (query type) param matching the
-     name of registered handlers.
-     The "standard" request handler is the default and will be used if qt
-     is not specified in the request.
+     correct handler based on the path or the qt (query type) param.
+     Names starting with a '/' are accessed with the a path equal to the 
+     registered name.  Names without a leading '/' are accessed with:
+      http://host/app/select?qt=name
+     If no qt is defined, the requestHandler that declares default="true"
+     will be used.
   -->
-  <requestHandler name="standard" class="solr.StandardRequestHandler">
+  <requestHandler name="standard" class="solr.SearchHandler" default="true">
     <!-- default values for query parameters -->
      <lst name="defaults">
        <str name="echoParams">explicit</str>
-	   <str name="json.nl">map</str>
        <!-- 
        <int name="rows">10</int>
        <str name="fl">*</str>
@@ -264,12 +369,16 @@
      </lst>
   </requestHandler>
 
+
   <!-- DisMaxRequestHandler allows easy searching across multiple fields
-       for simple user-entered phrases. 
+       for simple user-entered phrases.  It's implementation is now
+       just the standard SearchHandler with a default query type
+       of "dismax". 
        see http://wiki.apache.org/solr/DisMaxRequestHandler
    -->
-  <requestHandler name="dismax" class="solr.DisMaxRequestHandler" >
+  <requestHandler name="dismax" class="solr.SearchHandler" >
     <lst name="defaults">
+     <str name="defType">dismax</str>
      <str name="echoParams">explicit</str>
      <float name="tie">0.01</float>
      <str name="qf">
@@ -279,7 +388,7 @@
         text^0.2 features^1.1 name^1.5 manu^1.4 manu_exact^1.9
      </str>
      <str name="bf">
-        ord(poplarity)^0.5 recip(rord(price),1,1000,1000)^0.3
+        ord(popularity)^0.5 recip(rord(price),1,1000,1000)^0.3
      </str>
      <str name="fl">
         id,name,price,score
@@ -289,14 +398,23 @@
      </str>
      <int name="ps">100</int>
      <str name="q.alt">*:*</str>
+     <!-- example highlighter config, enable per-query with hl=true -->     
+     <str name="hl.fl">text features name</str>
+     <!-- for this field, we want no fragmenting, just highlighting -->
+     <str name="f.name.hl.fragsize">0</str>
+     <!-- instructs Solr to return the field itself if no query terms are
+          found -->
+     <str name="f.name.hl.alternateField">name</str>
+     <str name="f.text.hl.fragmenter">regex</str> <!-- defined below -->
     </lst>
   </requestHandler>
 
   <!-- Note how you can register the same handler multiple times with
        different names (and different init parameters)
     -->
-  <requestHandler name="partitioned" class="solr.DisMaxRequestHandler" >
+  <requestHandler name="partitioned" class="solr.SearchHandler" >
     <lst name="defaults">
+     <str name="defType">dismax</str>
      <str name="echoParams">explicit</str>
      <str name="qf">text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0</str>
      <str name="mm">2&lt;-1 5&lt;-2 6&lt;90%</str>
@@ -345,49 +463,103 @@
     </lst>
   </requestHandler>
   
-  <requestHandler name="instock" class="solr.DisMaxRequestHandler" >
-    <!-- for legacy reasons, DisMaxRequestHandler will assume all init
-         params are "defaults" if you don't explicitly specify any defaults.
-      -->
-     <str name="fq">
-        inStock:true
-     </str>
-     <str name="qf">
-        text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
-     </str>
-     <str name="mm">
-        2&lt;-1 5&lt;-2 6&lt;90%
-     </str>
-  </requestHandler>
-
 
-  <!-- SpellCheckerRequestHandler takes in a word (or several words) as the
-       value of the "q" parameter and returns a list of alternative spelling
-       suggestions.  If invoked with a ...&cmd=rebuild, it will rebuild the
-       spellchecker index.
+  <!--
+   Search components are registered to SolrCore and used by Search Handlers
+   
+   By default, the following components are avaliable:
+    
+   <searchComponent name="query"     class="org.apache.solr.handler.component.QueryComponent" />
+   <searchComponent name="facet"     class="org.apache.solr.handler.component.FacetComponent" />
+   <searchComponent name="mlt"       class="org.apache.solr.handler.component.MoreLikeThisComponent" />
+   <searchComponent name="highlight" class="org.apache.solr.handler.component.HighlightComponent" />
+   <searchComponent name="debug"     class="org.apache.solr.handler.component.DebugComponent" />
+
+   Default configuration in a requestHandler would look like:
+    <arr name="components">
+      <str>query</str>
+      <str>facet</str>
+      <str>mlt</str>
+      <str>highlight</str>
+      <str>debug</str>
+    </arr>
+
+    If you register a searchComponent to one of the standard names, that will be used instead.
+    To insert handlers before or after the 'standard' components, use:
+    
+    <arr name="first-components">
+      <str>myFirstComponentName</str>
+    </arr>
+    
+    <arr name="last-components">
+      <str>myLastComponentName</str>
+    </arr>
   -->
-  <requestHandler name="spellchecker" class="solr.SpellCheckerRequestHandler" startup="lazy">
-    <!-- default values for query parameters -->
-     <lst name="defaults">
-       <int name="suggestionCount">1</int>
-       <float name="accuracy">0.5</float>
-     </lst>
-     
-     <!-- Main init params for handler -->
-     
-     <!-- The directory where your SpellChecker Index should live.   -->
-     <!-- May be absolute, or relative to the Solr "dataDir" directory. -->
-     <!-- If this option is not specified, a RAM directory will be used -->
-     <str name="spellcheckerIndexDir">spell</str>
-     
-     <!-- the field in your schema that you want to be able to build -->
-     <!-- your spell index on. This should be a field that uses a very -->
-     <!-- simple FieldType without a lot of Analysis (ie: string) -->
-     <str name="termSourceField">word</str>
-     
-   </requestHandler>
 
+   <!-- The spell check component can return a list of alternative spelling
+  suggestions.  -->
+  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+    <str name="queryAnalyzerFieldType">textSpell</str>
+
+    <lst name="spellchecker">
+      <str name="name">default</str>
+      <str name="field">spell</str>
+      <str name="spellcheckIndexDir">./spellchecker1</str>
+
+    </lst>
+    <lst name="spellchecker">
+      <str name="name">jarowinkler</str>
+      <str name="field">spell</str>
+      <!-- Use a different Distance Measure -->
+      <str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str>
+      <str name="spellcheckIndexDir">./spellchecker2</str>
+
+    </lst>
+
+    <lst name="spellchecker">
+      <str name="classname">solr.FileBasedSpellChecker</str>
+      <str name="name">file</str>
+      <str name="sourceLocation">spellings.txt</str>
+      <str name="characterEncoding">UTF-8</str>
+      <str name="spellcheckIndexDir">./spellcheckerFile</str>
+    </lst>
+  </searchComponent>
+
+  <!-- a request handler utilizing the spellcheck component -->
+  <requestHandler name="/spellCheckCompRH" class="solr.SearchHandler">
+    <lst name="defaults">
+      <!-- omp = Only More Popular -->
+      <str name="spellcheck.onlyMorePopular">false</str>
+      <!-- exr = Extended Results -->
+      <str name="spellcheck.extendedResults">false</str>
+      <!--  The number of suggestions to return -->
+      <str name="spellcheck.count">1</str>
+    </lst>
+    <arr name="last-components">
+      <str>spellcheck</str>
+    </arr>
+  </requestHandler>
+ 
+  <!-- a search component that enables you to configure the top results for
+       a given query regardless of the normal lucene scoring.-->
+  <searchComponent name="elevator" class="solr.QueryElevationComponent" >
+    <!-- pick a fieldType to analyze queries -->
+    <str name="queryFieldType">string</str>
+    <str name="config-file">elevate.xml</str>
+  </searchComponent>
+ 
+  <!-- a request handler utilizing the elevator component -->
+  <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+    </lst>
+    <arr name="last-components">
+      <str>elevator</str>
+    </arr>
+  </requestHandler>
   
+
   <!-- Update request handler.  
   
        Note: Since solr1.1 requestHandlers requires a valid content type header if posted in 
@@ -398,17 +570,47 @@
     -->
   <requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
 
+  <!--
+   Analysis request handler.  Since Solr 1.3.  Use to returnhow a document is analyzed.  Useful
+   for debugging and as a token server for other types of applications
+   -->
+  <requestHandler name="/analysis" class="solr.AnalysisRequestHandler" />
+  
+
   <!-- CSV update handler, loaded on demand -->
   <requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy" />
 
 
-  <!-- Admin Handlers.  TODO? There could be a single handler that loads them all... -->
+  <!-- 
+   Admin Handlers - This will register all the standard admin RequestHandlers.  Adding 
+   this single handler is equivolent to registering:
+   
   <requestHandler name="/admin/luke"       class="org.apache.solr.handler.admin.LukeRequestHandler" />
   <requestHandler name="/admin/system"     class="org.apache.solr.handler.admin.SystemInfoHandler" />
   <requestHandler name="/admin/plugins"    class="org.apache.solr.handler.admin.PluginInfoHandler" />
   <requestHandler name="/admin/threads"    class="org.apache.solr.handler.admin.ThreadDumpHandler" />
   <requestHandler name="/admin/properties" class="org.apache.solr.handler.admin.PropertiesRequestHandler" />
+  <requestHandler name="/admin/file"       class="org.apache.solr.handler.admin.ShowFileRequestHandler" >
   
+  If you wish to hide files under ${solr.home}/conf, explicitly register the ShowFileRequestHandler using:
+  <requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" >
+    <lst name="invariants">
+     <str name="hidden">synonyms.txt</str> 
+     <str name="hidden">anotherfile.txt</str> 
+    </lst>
+  </requestHandler>
+  -->
+  <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
+  
+  <!-- ping/healthcheck -->
+  <requestHandler name="/admin/ping" class="PingRequestHandler">
+    <lst name="defaults">
+      <str name="qt">standard</str>
+      <str name="q">solrpingquery</str>
+      <str name="echoParams">all</str>
+    </lst>
+  </requestHandler>
+    
   <!-- Echo the request contents back to the client -->
   <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
     <lst name="defaults">
@@ -417,17 +619,50 @@
     </lst>
   </requestHandler>
   
+  <highlighting>
+   <!-- Configure the standard fragmenter -->
+   <!-- This could most likely be commented out in the "default" case -->
+   <fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
+    <lst name="defaults">
+     <int name="hl.fragsize">100</int>
+    </lst>
+   </fragmenter>
+
+   <!-- A regular-expression-based fragmenter (f.i., for sentence extraction) -->
+   <fragmenter name="regex" class="org.apache.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\"']{20,200}</str>
+    </lst>
+   </fragmenter>
+   
+   <!-- Configure the standard formatter -->
+   <formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
+    <lst name="defaults">
+     <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+     <str name="hl.simple.post"><![CDATA[</em>]]></str>
+    </lst>
+   </formatter>
+  </highlighting>
+  
+  
   <!-- queryResponseWriter plugins... query responses will be written using the
     writer specified by the 'wt' request parameter matching the name of a registered
     writer.
-    The "standard" writer is the default and will be used if 'wt' is not specified 
+    The "default" writer is the default and will be used if 'wt' is not specified 
     in the request. XMLResponseWriter will be used if nothing is specified here.
     The json, python, and ruby writers are also available by default.
 
-    <queryResponseWriter name="standard" class="org.apache.solr.request.XMLResponseWriter"/>
+    <queryResponseWriter name="xml" class="org.apache.solr.request.XMLResponseWriter" default="true"/>
     <queryResponseWriter name="json" class="org.apache.solr.request.JSONResponseWriter"/>
     <queryResponseWriter name="python" class="org.apache.solr.request.PythonResponseWriter"/>
     <queryResponseWriter name="ruby" class="org.apache.solr.request.RubyResponseWriter"/>
+    <queryResponseWriter name="php" class="org.apache.solr.request.PHPResponseWriter"/>
+    <queryResponseWriter name="phps" class="org.apache.solr.request.PHPSerializedResponseWriter"/>
 
     <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
   -->
@@ -439,17 +674,20 @@
   <queryResponseWriter name="xslt" class="org.apache.solr.request.XSLTResponseWriter">
     <int name="xsltCacheLifetimeSeconds">5</int>
   </queryResponseWriter> 
+
+
+  <!-- example of registering a query parser
+  <queryParser name="lucene" class="org.apache.solr.search.LuceneQParserPlugin"/>
+  -->
+
+  <!-- example of registering a custom function parser 
+  <valueSourceParser name="myfunc" class="com.mycompany.MyValueSourceParser" />
+  -->
     
   <!-- config for the admin interface --> 
   <admin>
     <defaultQuery>solr</defaultQuery>
-    <gettableFiles>solrconfig.xml schema.xml admin-extra.html</gettableFiles>
-    <!-- pingQuery should be "URLish" ...
-         &amp; separated key=val pairs ... but there shouldn't be any
-         URL escaping of the values -->
-    <pingQuery>
-     qt=standard&amp;q=solrpingquery
-    </pingQuery>
+    
     <!-- configure a healthcheck file for servers behind a loadbalancer
     <healthcheck type="file">server-enabled</healthcheck>
     -->