You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@bigtop.apache.org by rv...@apache.org on 2013/09/25 23:35:13 UTC
[1/5] BIGTOP-1079. bump version of Solr to 4.4.0
Updated Branches:
refs/heads/master 8ecc8e3a2 -> 3d5a79f9b
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/rpm/solr/SOURCES/solr-server.init
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/rpm/solr/SOURCES/solr-server.init b/bigtop-packages/src/rpm/solr/SOURCES/solr-server.init
index f2cd481..066ba8b 100644
--- a/bigtop-packages/src/rpm/solr/SOURCES/solr-server.init
+++ b/bigtop-packages/src/rpm/solr/SOURCES/solr-server.init
@@ -48,7 +48,12 @@ SOLR_LOCK_DIR="/var/lock/subsys/"
LOCKFILE="${SOLR_LOCK_DIR}/solr"
desc="Solr server daemon"
-EXEC_PATH=$SOLR_HOME/bin/solrd
+EXEC_PATH=". $SOLR_HOME/bin/solrd"
+
+BIGTOP_DEFAULTS_DIR=${BIGTOP_DEFAULTS_DIR-/etc/default}
+[ -n "${BIGTOP_DEFAULTS_DIR}" -a -r ${BIGTOP_DEFAULTS_DIR}/solr ] && \
+ EXEC_PATH=". ${BIGTOP_DEFAULTS_DIR}/solr ; ${EXEC_PATH}"
+
SOLR_PID_FILE=${SOLR_RUN_DIR}/solr.pid
# These directories may be tmpfs and may or may not exist
@@ -71,7 +76,7 @@ tomcat_deployment() {
start() {
[ -x $exec ] || exit $ERROR_PROGRAM_NOT_INSTALLED
- checkstatus
+ checkstatus > /dev/null 2>&1
status=$?
if [ "$status" -eq "$STATUS_RUNNING" ]; then
exit 0
@@ -87,8 +92,8 @@ start() {
stop() {
if [ ! -e $SOLR_PID_FILE ]; then
- log_failure_msg "$desc is not running"
- exit 0
+ log_success_msg "$desc is not running"
+ return 0
fi
log_success_msg "Stopping ${desc}: "
@@ -131,6 +136,10 @@ condrestart(){
[ -e ${LOCKFILE} ] && restart || :
}
+init(){
+ rm -rf /var/lib/solr/*
+}
+
case "$1" in
start)
start
@@ -147,8 +156,11 @@ case "$1" in
condrestart|try-restart)
condrestart
;;
+ init)
+ init
+ ;;
*)
- echo $"Usage: $0 {start|stop|status|restart|try-restart|condrestart}"
+ echo $"Usage: $0 {start|stop|status|restart|try-restart|condrestart|init}"
exit 1
esac
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/rpm/solr/SPECS/solr.spec
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/rpm/solr/SPECS/solr.spec b/bigtop-packages/src/rpm/solr/SPECS/solr.spec
index e8de186..328d2c3 100644
--- a/bigtop-packages/src/rpm/solr/SPECS/solr.spec
+++ b/bigtop-packages/src/rpm/solr/SPECS/solr.spec
@@ -57,6 +57,9 @@ Source4: web.xml
Source5: logging.properties
Source6: solr.default
Source7: solr-server.init
+Source8: schema.xml
+Source9: solrconfig.xml
+Source10: solrctl.sh
Requires: bigtop-utils >= 0.7, bigtop-tomcat
# CentOS 5 does not have any dist macro
@@ -156,7 +159,7 @@ fi
%config(noreplace) %{config_solr}.dist
%config(noreplace) /etc/default/solr
%{lib_solr}
-# %{bin_solr}/solr
+%{bin_solr}/solrctl
%defattr(-,solr,solr,755)
/var/lib/solr
/var/run/solr
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop.mk
----------------------------------------------------------------------
diff --git a/bigtop.mk b/bigtop.mk
index c5aebae..253a8b1 100644
--- a/bigtop.mk
+++ b/bigtop.mk
@@ -213,8 +213,8 @@ $(eval $(call PACKAGE,datafu,DATAFU))
SOLR_NAME=solr
SOLR_RELNOTES_NAME=Search engine server
SOLR_PKG_NAME=solr
-SOLR_BASE_VERSION=4.2.1
-SOLR_PKG_VERSION=4.2.1
+SOLR_BASE_VERSION=4.4.0
+SOLR_PKG_VERSION=4.4.0
SOLR_RELEASE_VERSION=1
SOLR_TARBALL_DST=solr-$(SOLR_BASE_VERSION)-src.tgz
SOLR_TARBALL_SRC=$(SOLR_TARBALL_DST)
[5/5] git commit: BIGTOP-1095. oozie deb packaging doesn't remove
tomcat alternatives
Posted by rv...@apache.org.
BIGTOP-1095. oozie deb packaging doesn't remove tomcat alternatives
Project: http://git-wip-us.apache.org/repos/asf/bigtop/repo
Commit: http://git-wip-us.apache.org/repos/asf/bigtop/commit/3d5a79f9
Tree: http://git-wip-us.apache.org/repos/asf/bigtop/tree/3d5a79f9
Diff: http://git-wip-us.apache.org/repos/asf/bigtop/diff/3d5a79f9
Branch: refs/heads/master
Commit: 3d5a79f9bc2eb39075d994f9c3ed5c79757bda1a
Parents: 40801ba
Author: Roman Shaposhnik <rv...@cloudera.com>
Authored: Wed Sep 25 12:17:24 2013 -0700
Committer: Roman Shaposhnik <rv...@cloudera.com>
Committed: Wed Sep 25 12:20:25 2013 -0700
----------------------------------------------------------------------
bigtop-packages/src/deb/oozie/oozie.prerm | 2 ++
bigtop-packages/src/rpm/oozie/SPECS/oozie.spec | 3 +++
2 files changed, 5 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/bigtop/blob/3d5a79f9/bigtop-packages/src/deb/oozie/oozie.prerm
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/deb/oozie/oozie.prerm b/bigtop-packages/src/deb/oozie/oozie.prerm
index aecfdf9..59a0b31 100644
--- a/bigtop-packages/src/deb/oozie/oozie.prerm
+++ b/bigtop-packages/src/deb/oozie/oozie.prerm
@@ -39,6 +39,8 @@ set -e
case "$1" in
remove|upgrade|deconfigure)
+ update-alternatives --remove oozie-tomcat-conf /etc/oozie/conf/tomcat-deployment.default || :
+ update-alternatives --remove oozie-tomcat-conf /etc/oozie/conf/tomcat-deployment.secure || :
update-alternatives --remove oozie-conf /etc/oozie/conf.dist || :
;;
http://git-wip-us.apache.org/repos/asf/bigtop/blob/3d5a79f9/bigtop-packages/src/rpm/oozie/SPECS/oozie.spec
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/rpm/oozie/SPECS/oozie.spec b/bigtop-packages/src/rpm/oozie/SPECS/oozie.spec
index 74c9d23..67049af 100644
--- a/bigtop-packages/src/rpm/oozie/SPECS/oozie.spec
+++ b/bigtop-packages/src/rpm/oozie/SPECS/oozie.spec
@@ -170,6 +170,8 @@ if [ "$1" = 0 ]; then
rm /etc/oozie/conf/tomcat-deployment
/sbin/service oozie stop > /dev/null
/sbin/chkconfig --del oozie
+ %{alternatives_cmd} --remove %{name}-tomcat-conf %{conf_tomcat}.default || :
+ %{alternatives_cmd} --remove %{name}-tomcat-conf %{conf_tomcat}.secure || :
%{alternatives_cmd} --remove %{name}-conf %{conf_oozie_dist} || :
fi
@@ -192,6 +194,7 @@ fi
%{lib_oozie}/libext
%{initd_dir}/oozie
%defattr(-, oozie, oozie)
+%dir %{_sysconfdir}/%{name}
%dir %{_localstatedir}/log/oozie
%dir %{_localstatedir}/run/oozie
%attr(0755,oozie,oozie) %{data_oozie}
[3/5] git commit: BIGTOP-1079. bump version of Solr to 4.4.0
Posted by rv...@apache.org.
BIGTOP-1079. bump version of Solr to 4.4.0
Project: http://git-wip-us.apache.org/repos/asf/bigtop/repo
Commit: http://git-wip-us.apache.org/repos/asf/bigtop/commit/83a688b3
Tree: http://git-wip-us.apache.org/repos/asf/bigtop/tree/83a688b3
Diff: http://git-wip-us.apache.org/repos/asf/bigtop/diff/83a688b3
Branch: refs/heads/master
Commit: 83a688b3133fe53d8ee93e30fad99c1248ae7cc3
Parents: 8ecc8e3
Author: Roman Shaposhnik <rv...@cloudera.com>
Authored: Tue Sep 24 14:27:18 2013 -0700
Committer: Roman Shaposhnik <rv...@cloudera.com>
Committed: Tue Sep 24 14:27:18 2013 -0700
----------------------------------------------------------------------
.../src/common/solr/do-component-build | 6 +-
bigtop-packages/src/common/solr/install_solr.sh | 142 +-
.../src/common/solr/logging.properties | 2 +-
bigtop-packages/src/common/solr/schema.xml | 1118 +++++++++++
.../src/common/solr/solr-server.init.debian | 22 +-
bigtop-packages/src/common/solr/solr.default | 16 +-
bigtop-packages/src/common/solr/solrconfig.xml | 1817 ++++++++++++++++++
bigtop-packages/src/common/solr/solrctl.sh | 425 ++++
bigtop-packages/src/deb/solr/solr.install | 2 +-
.../src/rpm/solr/SOURCES/solr-server.init | 22 +-
bigtop-packages/src/rpm/solr/SPECS/solr.spec | 5 +-
bigtop.mk | 4 +-
12 files changed, 3535 insertions(+), 46 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/common/solr/do-component-build
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/common/solr/do-component-build b/bigtop-packages/src/common/solr/do-component-build
index 53ab45f..624f9ca 100755
--- a/bigtop-packages/src/common/solr/do-component-build
+++ b/bigtop-packages/src/common/solr/do-component-build
@@ -19,11 +19,15 @@ set -ex
. `dirname $0`/bigtop.bom
IVY_MIRROR_PROP=${IVY_MIRROR_PROP:-http://repo1.maven.org/maven2/}
-BUILD_OPTS="-Dversion=${FULL_VERSION} \
+BUILD_OPTS="-Dversion=${FULL_VERSION} -Dhadoop.version=${HADOOP_VERSION} \
+ -Dslf4j.binding=slf4j-log4j12 -Dexclude.from.war=nothing \
-Divy.home=${HOME}/.ivy2 -Drepo.maven.org=$IVY_MIRROR_PROP \
-Divy_install_path=${HOME}/.ant/lib -lib ${HOME}/.ant/lib \
-Dreactor.repo=file://${HOME}/.m2/repository"
+# FIXME: the following really needs to be made flexible at the product level
+sed -i -e '/ENTITY.*hadoop.version/s#"[^"]*"#"'${HADOOP_VERSION}'"#' ./solr/test-framework/ivy.xml ./solr/core/ivy.xml
+
# FIXME: this needs to be fixed at the product level
ant $BUILD_OPTS ivy-bootstrap
mkdir -p solr/test-framework/lib || :
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/common/solr/install_solr.sh
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/common/solr/install_solr.sh b/bigtop-packages/src/common/solr/install_solr.sh
index 732e820..0aa4097 100644
--- a/bigtop-packages/src/common/solr/install_solr.sh
+++ b/bigtop-packages/src/common/solr/install_solr.sh
@@ -111,22 +111,20 @@ VAR_DIR=$PREFIX/var
install -d -m 0755 $PREFIX/$LIB_DIR
cp -ra ${BUILD_DIR}/dist/*.*ar $PREFIX/$LIB_DIR
cp -ra ${BUILD_DIR}/dist/solrj-lib $PREFIX/$LIB_DIR/lib
+cp -ra ${BUILD_DIR}/example/solr/collection1/conf $PREFIX/$LIB_DIR/coreconfig-template
+cp -fa $DISTRO_DIR/solrconfig.xml $PREFIX/$LIB_DIR/coreconfig-template
+cp -fa $DISTRO_DIR/schema.xml $PREFIX/$LIB_DIR/coreconfig-template
install -d -m 0755 $PREFIX/$LIB_DIR/contrib
cp -ra ${BUILD_DIR}/contrib/velocity $PREFIX/$LIB_DIR/contrib
-# Copy in the configuration files
-install -d -m 0755 $PREFIX/$DEFAULT_DIR
-cp $DISTRO_DIR/solr.default $PREFIX/$DEFAULT_DIR/solr
-
-install -d -m 0755 $PREFIX/${CONF_DIR}.dist
-cp -ra ${BUILD_DIR}/example/solr/* $PREFIX/${CONF_DIR}.dist
-
-install -d -m 0755 $PREFIX/$LIB_DIR/webapps/solr
-(cd $PREFIX/$LIB_DIR/webapps/solr ; jar xf ../../*.war)
+install -d -m 0755 $PREFIX/$LIB_DIR/server/webapps/solr
+(cd $PREFIX/$LIB_DIR/server/webapps/solr ; jar xf ../../../*.war)
+ln -s /var/lib/solr $PREFIX/$LIB_DIR/server/work
+cp ${BUILD_DIR}/example/lib/ext/*.jar $PREFIX/$LIB_DIR/server/webapps/solr/WEB-INF/lib/
-install -d -m 0755 $PREFIX/$LIB_DIR/webapps/ROOT
-cat > $PREFIX/$LIB_DIR/webapps/ROOT/index.html <<__EOT__
+install -d -m 0755 $PREFIX/$LIB_DIR/server/webapps/ROOT
+cat > $PREFIX/$LIB_DIR/server/webapps/ROOT/index.html <<__EOT__
<html><head><meta http-equiv="refresh" content="0;url=./solr"></head><body><a href="/solr">Solr Console</a></body></html>
__EOT__
@@ -140,14 +138,23 @@ cp -ra ${BUILD_DIR}/dist/solrj-lib $PREFIX/$LIB_DIR/lib
install -d -m 0755 $PREFIX/$LIB_DIR/bin
cp -a ${BUILD_DIR}/example/cloud-scripts/*.sh $PREFIX/$LIB_DIR/bin
+sed -i -e 's#/../solr-webapp/webapp/WEB-INF/lib/#/../server/webapps/solr/WEB-INF/lib/#' $PREFIX/$LIB_DIR/bin/zkcli.sh
+chmod 755 $PREFIX/$LIB_DIR/bin/*
install -d -m 0755 $PREFIX/$DOC_DIR
cp -a ${BUILD_DIR}/*.txt $PREFIX/$DOC_DIR
cp -ra ${BUILD_DIR}/docs/* $PREFIX/$DOC_DIR
cp -ra ${BUILD_DIR}/example/ $PREFIX/$DOC_DIR/
+# Copy in the configuration files
+install -d -m 0755 $PREFIX/$DEFAULT_DIR
+cp $DISTRO_DIR/solr.default $PREFIX/$DEFAULT_DIR/solr
+
+install -d -m 0755 $PREFIX/${CONF_DIR}.dist
+cp ${BUILD_DIR}/example/resources/log4j.properties $PREFIX/${CONF_DIR}.dist
+
# Copy in the wrapper
-cat > $PREFIX/$LIB_DIR/bin/solrd <<EOF
+cat > $PREFIX/$LIB_DIR/bin/solrd <<'EOF'
#!/bin/bash
BIGTOP_DEFAULTS_DIR=${BIGTOP_DEFAULTS_DIR-/etc/default}
@@ -156,32 +163,113 @@ BIGTOP_DEFAULTS_DIR=${BIGTOP_DEFAULTS_DIR-/etc/default}
# Autodetect JAVA_HOME if not defined
. /usr/lib/bigtop-utils/bigtop-detect-javahome
-export CATALINA_HOME=$LIB_DIR/../bigtop-tomcat
-export CATALINA_BASE=/var/lib/solr/tomcat-deployment
+# resolve links - $0 may be a softlink
+PRG="${BASH_SOURCE[0]}"
+
+while [ -h "${PRG}" ]; do
+ ls=`ls -ld "${PRG}"`
+ link=`expr "$ls" : '.*-> \(.*\)$'`
+ if expr "$link" : '/.*' > /dev/null; then
+ PRG="$link"
+ else
+ PRG=`dirname "${PRG}"`/"$link"
+ fi
+done
+
+BASEDIR=`dirname ${PRG}`
+BASEDIR=`cd ${BASEDIR}/..;pwd`
+
+SOLR_PORT=${SOLR_PORT:-8983}
+SOLR_ADMIN_PORT=${SOLR_ADMIN_PORT:-8984}
+SOLR_LOG=${SOLR_LOG:-/var/log/solr}
+SOLR_HOME=${SOLR_HOME:-/var/lib/solr}
+SOLR_LOG4J_CONFIG=${SOLR_LOG4J_CONFIG:-/etc/solr/conf/log4j.properties}
+
+export CATALINA_HOME=${CATALINA_HOME:-$BASEDIR/../bigtop-tomcat}
+export CATALINA_BASE=${CATALINA_BASE:-$BASEDIR/server}
+
+export CATALINA_TMPDIR=${SOLR_DATA:-/var/lib/solr/}
+export CATALINA_PID=${SOLR_RUN:-/var/run/solr}/solr.pid
+export CATALINA_OUT=${SOLR_LOG:-/var/log/solr}/solr.out
+
+die() {
+ echo "$@" >&2
+ exit 1
+}
+
+# Preflight checks:
+# 1. We are only supporting SolrCloud mode
+if [ -z "$SOLR_ZK_ENSEMBLE" ] ; then
+ die "Error: SOLR_ZK_ENSEMBLE is not set in /etc/default/solr"
+fi
+
+CATALINA_OPTS="${CATALINA_OPTS} -DzkHost=${SOLR_ZK_ENSEMBLE} -Dsolr.solrxml.location=zookeeper"
+
+if [ -n "$SOLR_HDFS_HOME" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.hdfs.home=${SOLR_HDFS_HOME}"
+fi
+
+if [ -n "$SOLR_HDFS_CONFIG" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.hdfs.confdir=${SOLR_HDFS_CONFIG}"
+fi
-export CATALINA_TMPDIR=\${SOLR_DATA:-/var/lib/solr/}temp
-export CATALINA_PID=\${SOLR_RUN:-/var/run/solr/}solr.pid
-export CATALINA_OUT=\${SOLR_LOG:-/var/log/solr}/solr.out
+if [ "$SOLR_KERBEROS_ENABLED" == "true" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.hdfs.security.kerberos.enabled=${SOLR_KERBEROS_ENABLED}"
+fi
+
+if [ -n "$SOLR_KERBEROS_KEYTAB" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.hdfs.security.kerberos.keytabfile=${SOLR_KERBEROS_KEYTAB}"
+fi
-# FIXME: perhaps we have to have a better way of detecting SolCloud (SOLR_ZK_ROOT)
-if [ -n "\$SOLR_ZK_ENSEMBLE" ] ; then
- CATALINA_OPTS="\${CATALINA_OPTS} -DzkHost=\${SOLR_ZK_ENSEMBLE}"
+if [ -n "$SOLR_KERBEROS_PRINCIPAL" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.hdfs.security.kerberos.principal=${SOLR_KERBEROS_PRINCIPAL}"
fi
-export CATALINA_OPTS="\${CATALINA_OPTS} -Dsolr.port=\${SOLR_PORT:-8080}
- -Dsolr.log=\${SOLR_LOG:-/var/log/solr}
- -Dsolr.admin.port=\${SOLR_ADMIN_PORT:-8081}
- -Dsolr.data.dir=\${SOLR_DATA_DIR:-/var/lib/solr/index}
- -Dsolr.solr.home=\${SOLR_HOME:-/etc/solr/conf}"
+if [ -n "$SOLR_AUTHENTICATION_TYPE" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.authentication.type=${SOLR_AUTHENTICATION_TYPE}"
+fi
+
+if [ -n "$SOLR_AUTHENTICATION_KERBEROS_KEYTAB" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.authentication.kerberos.keytab=${SOLR_AUTHENTICATION_KERBEROS_KEYTAB}"
+fi
+
+if [ -n "$SOLR_AUTHENTICATION_KERBEROS_PRINCIPAL" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.authentication.kerberos.principal=${SOLR_AUTHENTICATION_KERBEROS_PRINCIPAL}"
+fi
+
+if [ -n "$SOLR_AUTHENTICATION_KERBEROS_NAME_RULES" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.authentication.kerberos.name.rules=${SOLR_AUTHENTICATION_KERBEROS_NAME_RULES}"
+fi
+
+if [ -n "$SOLR_AUTHENTICATION_SIMPLE_ALLOW_ANON" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.authentication.simple.anonymous.allowed=${SOLR_AUTHENTICATION_SIMPLE_ALLOW_ANON}"
+fi
+
+if [ -n "$SOLR_AUTHENTICATION_JAAS_CONF" ] ; then
+ CATALINA_OPTS="${CATALINA_OPTS} -Djava.security.auth.login.config=${SOLR_AUTHENTICATION_JAAS_CONF}"
+fi
+
+# FIXME: we need to set this because of the jetty-centric default solr.xml
+CATALINA_OPTS="${CATALINA_OPTS} -Dhost=$HOSTNAME -Djetty.port=$SOLR_PORT"
+
+export CATALINA_OPTS="${CATALINA_OPTS} -Dsolr.host=$HOSTNAME
+ -Dsolr.port=$SOLR_PORT
+ -Dlog4j.configuration=file://$SOLR_LOG4J_CONFIG
+ -Dsolr.log=$SOLR_LOG
+ -Dsolr.admin.port=$SOLR_ADMIN_PORT
+ -Dsolr.solr.home=$SOLR_HOME"
# FIXME: for some reason catalina doesn't use CATALINA_OPTS for stop action
# and thus doesn't know the admin port
-export JAVA_OPTS="\$CATALINA_OPTS"
+export JAVA_OPTS="$CATALINA_OPTS"
-exec \${CATALINA_HOME}/bin/catalina.sh "\$@"
+exec ${CATALINA_HOME}/bin/catalina.sh "$@"
EOF
chmod 755 $PREFIX/$LIB_DIR/bin/solrd
+# installing the only script that goes into /usr/bin
+install -D -m 0755 $DISTRO_DIR/solrctl.sh $PREFIX/usr/bin/solrctl
+
# precreating /var layout
install -d -m 0755 $VAR_DIR/log/solr
install -d -m 0755 $VAR_DIR/run/solr
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/common/solr/logging.properties
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/common/solr/logging.properties b/bigtop-packages/src/common/solr/logging.properties
index 459c6f6..9161ee0 100644
--- a/bigtop-packages/src/common/solr/logging.properties
+++ b/bigtop-packages/src/common/solr/logging.properties
@@ -24,7 +24,7 @@ handlers = 1catalina.org.apache.juli.FileHandler, 2localhost.org.apache.juli.Fil
1catalina.org.apache.juli.FileHandler.level = FINE
1catalina.org.apache.juli.FileHandler.directory = ${solr.log}
-1catalina.org.apache.juli.FileHandler.prefix = solr.
+1catalina.org.apache.juli.FileHandler.prefix = catalina.
2localhost.org.apache.juli.FileHandler.level = FINE
2localhost.org.apache.juli.FileHandler.directory = ${solr.log}
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/common/solr/schema.xml
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/common/solr/schema.xml b/bigtop-packages/src/common/solr/schema.xml
new file mode 100644
index 0000000..9406807
--- /dev/null
+++ b/bigtop-packages/src/common/solr/schema.xml
@@ -0,0 +1,1118 @@
+<?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="example" version="1.5">
+ <!-- attribute "name" is the name of this schema and is only used for display purposes.
+ version="x.y" 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: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+ behavior when a single string produces multiple tokens. Defaults
+ to off for version >= 1.4
+ 1.5: omitNorms defaults to true for primitive field types
+ (int, float, boolean, string...)
+ -->
+
+ <fields>
+ <!-- Valid attributes for fields:
+ name: mandatory - the name for the field
+ type: mandatory - the name of a field type from the
+ <types> fieldType section
+ indexed: true if this field should be indexed (searchable or sortable)
+ stored: true if this field should be retrievable
+ docValues: true if this field should have doc values. Doc values are
+ useful for faceting, grouping, sorting and function queries. Although not
+ required, doc values will make the index faster to load, more
+ NRT-friendly and more memory-efficient. They however come with some
+ limitations: they are currently only supported by StrField, UUIDField
+ and all Trie*Fields, and depending on the field type, they might
+ require the field to be single-valued, be required or have a default
+ value (check the documentation of the field type you're interested in
+ for more information)
+ 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.
+ Norms are omitted for primitive (non-analyzed) types by default.
+ 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.
+ required: The field is required. It will throw an error if the
+ value does not exist
+ default: a value that should be used if no value is specified
+ when adding a document.
+ -->
+
+ <!-- field names should consist of alphanumeric or underscore characters only and
+ not start with a digit. This is not currently strictly enforced,
+ but other field names will not have first class support from all components
+ and back compatibility is not guaranteed. Names with both leading and
+ trailing underscores (e.g. _version_) are reserved.
+ -->
+
+ <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+ <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>
+ <field name="name" type="text_general" indexed="true" stored="true"/>
+ <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/>
+ <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
+ <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>
+ <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
+
+ <field name="weight" type="float" indexed="true" stored="true"/>
+ <field name="price" type="float" indexed="true" stored="true"/>
+ <field name="popularity" type="int" indexed="true" stored="true" />
+ <field name="inStock" type="boolean" indexed="true" stored="true" />
+
+ <field name="store" type="location" 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. Some metadata is parsed from the documents,
+ but there are some which come from the client context:
+ "content_type": From the HTTP headers of incoming stream
+ "resourcename": From SolrCell request param resource.name
+ -->
+ <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="resourcename" type="text_general" indexed="true" stored="true"/>
+ <field name="url" 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"/>
+
+ <!-- Main body of document extracted by SolrCell.
+ NOTE: This field is not indexed by default, since it is also copied to "text"
+ using copyField below. This is to save space. Use this field for returning and
+ highlighting document content. Use the "text" field to search the content. -->
+ <field name="content" type="text_general" indexed="false" 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"/>
+
+ <!-- non-tokenized version of manufacturer to make it easier to sort or group
+ results by manufacturer. copied from "manu" via copyField -->
+ <field name="manu_exact" type="string" indexed="true" stored="false"/>
+
+ <field name="payloads" type="payloads" indexed="true" stored="true"/>
+
+ <field name="_version_" type="long" indexed="true" stored="true"/>
+
+ <!--
+ Some fields such as popularity and manu_exact could be modified to
+ leverage doc values:
+ <field name="popularity" type="int" indexed="true" stored="true" docValues="true" default="0" />
+ <field name="manu_exact" type="string" indexed="false" stored="false" docValues="true" default="" />
+
+ Although it would make indexing slightly slower and the index bigger, it
+ would also make the index faster to load, more memory-efficient and more
+ NRT-friendly.
+ -->
+
+ <!-- Dynamic field definitions allow using convention over configuration
+ for fields via the specification of patterns to match field names.
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
+ RESTRICTION: the glob-like pattern in the name attribute must have
+ a "*" only at the start or the end. -->
+
+ <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+ <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true" />
+ <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="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="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="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="*_dts" type="date" indexed="true" stored="true" multiValued="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="*_c" type="currency" 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>
+
+ <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
+ parsing a query string that isn't explicit about the field. Machine (non-user)
+ generated queries are best made explicit, or they can use the "df" request parameter
+ which takes precedence over this.
+ Note: Un-commenting defaultSearchField will be insufficient if your request handler
+ in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
+ <defaultSearchField>text</defaultSearchField> -->
+
+ <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
+ when parsing a query string to determine if a clause of the query should be marked as
+ required or optional, assuming the clause isn't already marked by some operator.
+ The default is OR, which is generally assumed so it is not a good idea to change it
+ globally here. The "q.op" request parameter takes precedence over this.
+ <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="cat" dest="text"/>
+ <copyField source="name" dest="text"/>
+ <copyField source="manu" dest="text"/>
+ <copyField source="features" dest="text"/>
+ <copyField source="includes" dest="text"/>
+ <copyField source="manu" dest="manu_exact"/>
+
+ <!-- Copy the price into a currency enabled field (default USD) -->
+ <copyField source="price" dest="price_c"/>
+
+ <!-- Text fields from SolrCell to search by default in our catch-all field -->
+ <copyField source="title" dest="text"/>
+ <copyField source="author" dest="text"/>
+ <copyField source="description" dest="text"/>
+ <copyField source="keywords" dest="text"/>
+ <copyField source="content" dest="text"/>
+ <copyField source="content_type" dest="text"/>
+ <copyField source="resourcename" dest="text"/>
+ <copyField source="url" dest="text"/>
+
+ <!-- Create a string version of author for faceting -->
+ <copyField source="author" dest="author_s"/>
+
+ <!-- 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"/> -->
+
+ <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 a
+ standard package such as org.apache.solr.analysis
+ -->
+
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+ It supports doc values but in that case the field needs to be
+ single-valued and either required or have a default value.
+ -->
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
+
+ <!-- boolean type: "true" or "false" -->
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+ <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+ currently supported on types that are sorted internally as strings
+ and on numeric types.
+ This includes "string","boolean", and, as of 3.5 (and 4.x),
+ int, float, long, date, double, including the "Trie" variants.
+ - 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.
+
+ These fields support doc values, but they require the field to be
+ single-valued and either be required or have a default value.
+ -->
+ <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" 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" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" 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" precisionStep="0" positionIncrementGap="0"/>
+
+ <!-- A Trie based date field for faster date range queries and date faceting. -->
+ <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
+
+
+ <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+ <fieldtype name="binary" class="solr.BinaryField"/>
+
+ <!--
+ Note:
+ These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
+ Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
+
+ Plain numeric field types that store and index the text
+ value verbatim (and hence don't correctly support range queries, since the
+ lexicographic ordering isn't equal to the numeric ordering)
+ -->
+ <fieldType name="pint" class="solr.IntField"/>
+ <fieldType name="plong" class="solr.LongField"/>
+ <fieldType name="pfloat" class="solr.FloatField"/>
+ <fieldType name="pdouble" class="solr.DoubleField"/>
+ <fieldType name="pdate" class="solr.DateField" sortMissingLast="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
+ or function 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 field name in the request.
+ -->
+ <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.
+ Example:
+ <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" />
+ <!-- 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" />
+ <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
+ (lang/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.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <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="lang/stopwords_en.txt"
+ />
+ <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".
+ -->
+ <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.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <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="lang/stopwords_en.txt"
+ />
+ <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="lang/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" />
+ <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" />
+ <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/1.6.0/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>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at index time, so
+ queries for paths match documents at that path, or in descendent paths
+ -->
+ <fieldType name="descendent_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ </fieldType>
+ <!--
+ Example of using PathHierarchyTokenizerFactory at query time, so
+ queries for paths match documents at that path, or in ancestor paths
+ -->
+ <fieldType name="ancestor_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </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"/>
+
+ <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
+ For more information about this and other Spatial fields new to Solr 4, see:
+ http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
+ -->
+ <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+ geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
+
+ <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
+ Parameters:
+ defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
+ precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
+ providerClass: Lets you plug in other exchange provider backend:
+ solr.FileExchangeRateProvider is the default and takes one parameter:
+ currencyConfig: name of an xml file holding exchange rates
+ solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
+ ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
+ refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
+ -->
+ <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
+
+
+
+ <!-- some examples for different languages (generally ordered by ISO code) -->
+
+ <!-- Arabic -->
+ <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- for any non-arabic -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+ <!-- normalizes ﻯ to ﻱ, etc -->
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.ArabicStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Bulgarian -->
+ <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
+ <filter class="solr.BulgarianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Catalan -->
+ <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+ <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- for any non-CJK -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.CJKBigramFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Czech -->
+ <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+ <filter class="solr.CzechStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Danish -->
+ <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- German -->
+ <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+ <filter class="solr.GermanNormalizationFilterFactory"/>
+ <filter class="solr.GermanLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Greek -->
+ <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- greek specific lowercase for sigma -->
+ <filter class="solr.GreekLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+ <filter class="solr.GreekStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Spanish -->
+ <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+ <filter class="solr.SpanishLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Basque -->
+ <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Persian -->
+ <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <!-- for ZWNJ -->
+ <charFilter class="solr.PersianCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.PersianNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Finnish -->
+ <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+ <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- French -->
+ <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+ <filter class="solr.FrenchLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Irish -->
+ <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes d', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+ <!-- removes n-, etc. position increments is intentionally false! -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+ <filter class="solr.IrishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Galician -->
+ <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+ <filter class="solr.GalicianStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Hindi -->
+ <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- normalizes unicode representation -->
+ <filter class="solr.IndicNormalizationFilterFactory"/>
+ <!-- normalizes variation in spelling -->
+ <filter class="solr.HindiNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+ <filter class="solr.HindiStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Hungarian -->
+ <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+ <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Armenian -->
+ <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Indonesian -->
+ <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+ <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+ <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Italian -->
+ <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+ <filter class="solr.ItalianLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+ NOTE: If you want to optimize search for precision, use default operator AND in your query
+ parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
+ OR if you would like to optimize for recall (default).
+ -->
+ <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+ <analyzer>
+ <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+ Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
+ is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+ Valid values for attribute mode are:
+ normal: regular segmentation
+ search: segmentation useful for search with synonyms compounds (default)
+ extended: same as search mode, but unigrams unknown words (experimental)
+
+ For some applications it might be good to use search mode for indexing and normal mode for
+ queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+ Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+ Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+ model with your own entries for segmentation, part-of-speech tags and readings without a need
+ to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+ User dictionary attributes are:
+ userDictionary: user dictionary filename
+ userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+ See lang/userdict_ja.txt for a sample user dictionary file.
+
+ Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
+
+ See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+ -->
+ <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+ <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+ <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+ <filter class="solr.JapaneseBaseFormFilterFactory"/>
+ <!-- Removes tokens with certain part-of-speech tags -->
+ <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+ <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+ <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+ <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+ <!-- Lower-cases romaji characters -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Latvian -->
+ <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+ <filter class="solr.LatvianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Dutch -->
+ <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+ <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Norwegian -->
+ <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+ <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
+ <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
+ <!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Portuguese -->
+ <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+ <filter class="solr.PortugueseLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+ <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Romanian -->
+ <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Russian -->
+ <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+ <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Swedish -->
+ <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+ <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Thai -->
+ <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ThaiWordFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Turkish -->
+ <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.TurkishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+ </analyzer>
+ </fieldType>
+
+ </types>
+
+ <!-- Similarity is the scoring routine for each document vs. a query.
+ A custom Similarity or SimilarityFactory may be specified here, but
+ the default is fine for most applications.
+ For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+ -->
+ <!--
+ <similarity class="com.example.solr.CustomSimilarityFactory">
+ <str name="paramkey">param value</str>
+ </similarity>
+ -->
+
+</schema>
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/common/solr/solr-server.init.debian
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/common/solr/solr-server.init.debian b/bigtop-packages/src/common/solr/solr-server.init.debian
index 6671e19..f14a89e 100644
--- a/bigtop-packages/src/common/solr/solr-server.init.debian
+++ b/bigtop-packages/src/common/solr/solr-server.init.debian
@@ -48,7 +48,12 @@ SOLR_LOCK_DIR="/var/lock/subsys/"
LOCKFILE="${SOLR_LOCK_DIR}/solr"
desc="Solr server daemon"
-EXEC_PATH=$SOLR_HOME/bin/solrd
+EXEC_PATH=". $SOLR_HOME/bin/solrd"
+
+BIGTOP_DEFAULTS_DIR=${BIGTOP_DEFAULTS_DIR-/etc/default}
+[ -n "${BIGTOP_DEFAULTS_DIR}" -a -r ${BIGTOP_DEFAULTS_DIR}/solr ] && \
+ EXEC_PATH=". ${BIGTOP_DEFAULTS_DIR}/solr ; ${EXEC_PATH}"
+
SOLR_PID_FILE=${SOLR_RUN_DIR}/solr.pid
# These directories may be tmpfs and may or may not exist
@@ -71,7 +76,7 @@ tomcat_deployment() {
start() {
[ -x $exec ] || exit $ERROR_PROGRAM_NOT_INSTALLED
- checkstatus
+ checkstatus > /dev/null 2>&1
status=$?
if [ "$status" -eq "$STATUS_RUNNING" ]; then
exit 0
@@ -87,8 +92,8 @@ start() {
stop() {
if [ ! -e $SOLR_PID_FILE ]; then
- log_failure_msg "$desc is not running"
- exit 0
+ log_success_msg "$desc is not running"
+ return 0
fi
log_success_msg "Stopping ${desc}: "
@@ -131,6 +136,10 @@ condrestart(){
[ -e ${LOCKFILE} ] && restart || :
}
+init(){
+ rm -rf /var/lib/solr/*
+}
+
case "$1" in
start)
start
@@ -147,8 +156,11 @@ case "$1" in
condrestart|try-restart)
condrestart
;;
+ init)
+ init
+ ;;
*)
- echo $"Usage: $0 {start|stop|status|restart|try-restart|condrestart}"
+ echo $"Usage: $0 {start|stop|status|restart|try-restart|condrestart|init}"
exit 1
esac
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/common/solr/solr.default
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/common/solr/solr.default b/bigtop-packages/src/common/solr/solr.default
index 6581844..3c73053 100644
--- a/bigtop-packages/src/common/solr/solr.default
+++ b/bigtop-packages/src/common/solr/solr.default
@@ -12,8 +12,18 @@
# 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.
-SOLR_PORT=1978
-SOLR_ADMIN_PORT=1979
+SOLR_PORT=8983
+SOLR_ADMIN_PORT=8984
SOLR_LOG=/var/log/solr
-SOLR_DATA_DIR=/var/lib/solr/index
# SOLR_ZK_ENSEMBLE=localhost:2181/solr
+# SOLR_HDFS_HOME=hdfs://localhost:8020/solr
+# SOLR_HDFS_CONFIG=/etc/hadoop/conf
+# SOLR_KERBEROS_ENABLED=true
+# SOLR_KERBEROS_KEYTAB=/etc/solr/conf/solr.keytab
+# SOLR_KERBEROS_PRINCIPAL=solr/localhost@LOCALHOST
+SOLR_AUTHENTICATION_TYPE=simple
+SOLR_AUTHENTICATION_SIMPLE_ALLOW_ANON=true
+# SOLR_AUTHENTICATION_KERBEROS_KEYTAB=/etc/solr/conf/solr.keytab
+# SOLR_AUTHENTICATION_KERBEROS_PRINCIPAL=HTTP/localhost@LOCALHOST
+# SOLR_AUTHENTICATION_KERBEROS_NAME_RULES=DEFAULT
+# SOLR_AUTHENTICATION_JAAS_CONF=/etc/solr/conf/jaas.conf
[4/5] git commit: BIGTOP-1094. spark SPEC mistakenly re-defines
alternatives command on SLES/OpenSUSE
Posted by rv...@apache.org.
BIGTOP-1094. spark SPEC mistakenly re-defines alternatives command on SLES/OpenSUSE
Project: http://git-wip-us.apache.org/repos/asf/bigtop/repo
Commit: http://git-wip-us.apache.org/repos/asf/bigtop/commit/40801baf
Tree: http://git-wip-us.apache.org/repos/asf/bigtop/tree/40801baf
Diff: http://git-wip-us.apache.org/repos/asf/bigtop/diff/40801baf
Branch: refs/heads/master
Commit: 40801baf0f9ad219a5d6c38872213ec7891eb489
Parents: 83a688b
Author: Roman Shaposhnik <rv...@cloudera.com>
Authored: Wed Sep 25 12:14:09 2013 -0700
Committer: Roman Shaposhnik <rv...@cloudera.com>
Committed: Wed Sep 25 12:14:09 2013 -0700
----------------------------------------------------------------------
bigtop-packages/src/rpm/spark/SPECS/spark.spec | 1 -
1 file changed, 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/bigtop/blob/40801baf/bigtop-packages/src/rpm/spark/SPECS/spark.spec
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/rpm/spark/SPECS/spark.spec b/bigtop-packages/src/rpm/spark/SPECS/spark.spec
index a95cbf1..e6f5e2d 100644
--- a/bigtop-packages/src/rpm/spark/SPECS/spark.spec
+++ b/bigtop-packages/src/rpm/spark/SPECS/spark.spec
@@ -58,7 +58,6 @@ Requires(preun): /sbin/service
%if %{?suse_version:1}0
# Required for init scripts
Requires: insserv
-%define alternatives_cmd alternatives
%global initd_dir %{_sysconfdir}/rc.d
%else
[2/5] BIGTOP-1079. bump version of Solr to 4.4.0
Posted by rv...@apache.org.
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/common/solr/solrconfig.xml
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/common/solr/solrconfig.xml b/bigtop-packages/src/common/solr/solrconfig.xml
new file mode 100644
index 0000000..821dc0a
--- /dev/null
+++ b/bigtop-packages/src/common/solr/solrconfig.xml
@@ -0,0 +1,1817 @@
+<?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.
+-->
+
+<!--
+ For more details about configurations options that may appear in
+ this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
+<config>
+ <!-- In all configuration below, a prefix of "solr." for class names
+ is an alias that causes solr to search appropriate packages,
+ including org.apache.solr.(search|update|request|core|analysis)
+
+ You may also specify a fully qualified Java classname if you
+ have your own custom plugins.
+ -->
+
+ <!-- Controls what version of Lucene various components of Solr
+ adhere to. Generally, you want to use the latest version to
+ get all bug fixes and improvements. It is highly recommended
+ that you fully re-index after changing this setting as it can
+ affect both how text is indexed and queried.
+ -->
+ <luceneMatchVersion>4.4</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" />
+ -->
+
+ <!-- A 'dir' option by itself adds any files found in the directory
+ to the classpath, this is useful for including all jars in a
+ directory.
+
+ When a 'regex' is specified in addition to a 'dir', only the
+ files in that directory which completely match the regex
+ (anchored on both ends) will be included.
+
+ If a 'dir' option (with or without a regex) is used and nothing
+ is found that matches, a warning will be logged.
+
+ The examples below can be used to load some solr-contribs along
+ with their external dependencies.
+ -->
+ <lib dir="../../../contrib/extraction/lib" regex=".*\.jar" />
+ <lib dir="../../../dist/" regex="solr-cell-\d.*\.jar" />
+
+ <lib dir="../../../contrib/clustering/lib/" regex=".*\.jar" />
+ <lib dir="../../../dist/" regex="solr-clustering-\d.*\.jar" />
+
+ <lib dir="../../../contrib/langid/lib/" regex=".*\.jar" />
+ <lib dir="../../../dist/" regex="solr-langid-\d.*\.jar" />
+
+ <lib dir="../../../contrib/velocity/lib" regex=".*\.jar" />
+ <lib dir="../../../dist/" regex="solr-velocity-\d.*\.jar" />
+
+ <!-- an exact 'path' can be used instead of a 'dir' to specify a
+ specific jar file. This will cause a serious error to be logged
+ if it can't be loaded.
+ -->
+ <!--
+ <lib path="../a-jar-that-does-not-exist.jar" />
+ -->
+
+ <!-- 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,
+ wraps solr.StandardDirectoryFactory and caches small files in memory
+ for better NRT performance.
+
+ One can force a particular implementation via solr.MMapDirectoryFactory,
+ solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+ solr.RAMDirectoryFactory is memory based, not
+ persistent, and doesn't work with replication.
+ -->
+ <directoryFactory name="DirectoryFactory" class="org.apache.solr.core.HdfsDirectoryFactory">
+ <str name="solr.hdfs.home">${solr.hdfs.home:}</str>
+ <str name="solr.hdfs.confdir">${solr.hdfs.confdir:}</str>
+ <str name="solr.hdfs.security.kerberos.enabled">${solr.hdfs.security.kerberos.enabled:false}</str>
+ <str name="solr.hdfs.security.kerberos.keytabfile">${solr.hdfs.security.kerberos.keytabfile:}</str>
+ <str name="solr.hdfs.security.kerberos.principal">${solr.hdfs.security.kerberos.principal:}</str>
+ <bool name="solr.hdfs.blockcache.enabled">${solr.hdfs.blockcache.enabled:true}</bool>
+ <int name="solr.hdfs.blockcache.slab.count">${solr.hdfs.blockcache.slab.count:1}</int>
+ <bool name="solr.hdfs.blockcache.direct.memory.allocation">${solr.hdfs.blockcache.direct.memory.allocation:true}</bool>
+ <int name="solr.hdfs.blockcache.blocksperbank">${solr.hdfs.blockcache.blocksperbank:16384}</int>
+ <bool name="solr.hdfs.blockcache.read.enabled">${solr.hdfs.blockcache.read.enabled:true}</bool>
+ <bool name="solr.hdfs.blockcache.write.enabled">${solr.hdfs.blockcache.write.enabled:true}</bool>
+ <bool name="solr.hdfs.nrtcachingdirectory.enable">${solr.hdfs.nrtcachingdirectory.enable:true}</bool>
+ <int name="solr.hdfs.nrtcachingdirectory.maxmergesizemb">${solr.hdfs.nrtcachingdirectory.maxmergesizemb:16}</int>
+ <int name="solr.hdfs.nrtcachingdirectory.maxcachedmb">${solr.hdfs.nrtcachingdirectory.maxcachedmb:192}</int>
+ </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, its 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"/>
+
+ <!-- To enable dynamic schema REST APIs, use the following for <schemaFactory>:
+
+ <schemaFactory class="ManagedIndexSchemaFactory">
+ <bool name="mutable">true</bool>
+ <str name="managedSchemaResourceName">managed-schema</str>
+ </schemaFactory>
+
+ When ManagedIndexSchemaFactory is specified, Solr will load the schema from
+ he resource named in 'managedSchemaResourceName', rather than from schema.xml.
+ Note that the managed schema resource CANNOT be named schema.xml. If the managed
+ schema does not exist, Solr will create it after reading schema.xml, then rename
+ 'schema.xml' to 'schema.xml.bak'.
+
+ Do NOT hand edit the managed schema - external modifications will be ignored and
+ overwritten as a result of schema modification REST API calls.
+
+ When ManagedIndexSchemaFactory is specified with mutable = true, schema
+ modification REST API calls will be allowed; otherwise, error responses will be
+ sent back for these requests.
+ -->
+ <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"/>
+ -->
+ <!-- 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>${solr.maxIndexingThreads:8}</maxIndexingThreads>
+
+ <!-- Expert: Enabling compound file will use less files for the index,
+ using fewer file descriptors on the expense of performance decrease.
+ Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
+ <!-- <useCompoundFile>false</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>128</ramBufferSizeMB>
+ <!-- <maxBufferedDocs>1000</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.
+ -->
+ <!--
+ <mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
+ <int name="maxMergeAtOnce">10</int>
+ <int name="segmentsPerTier">10</int>
+ </mergePolicy>
+ -->
+
+ <!-- Merge Factor
+ The merge factor controls how many segments will get merged at a time.
+ For TieredMergePolicy, mergeFactor is a convenience parameter which
+ will set both MaxMergeAtOnce and SegmentsPerTier at once.
+ For LogByteSizeMergePolicy, mergeFactor decides how many new segments
+ will be allowed before they are merged into one.
+ Default is 10 for both merge policies.
+ -->
+ <!--
+ <mergeFactor>10</mergeFactor>
+ -->
+
+ <!-- Expert: Merge Scheduler
+ 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 class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+ -->
+
+ <!-- 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
+ -->
+ <lockType>${solr.lock.type:hdfs}</lockType>
+
+ <!-- Unlock On Startup
+
+ 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. Default is "false".
+
+ This is not needed if lock type is 'single'
+ -->
+ <!--
+ <unlockOnStartup>false</unlockOnStartup>
+ -->
+
+ <!-- Expert: Controls how often Lucene loads terms into memory
+ Default is 128 and is likely good for most everyone.
+ -->
+ <!-- <termIndexInterval>128</termIndexInterval> -->
+
+ <!-- If true, IndexReaders will be reopened (often more efficient)
+ instead of closed and then opened. Default: true
+ -->
+ <!--
+ <reopenReaders>true</reopenReaders>
+ -->
+
+ <!-- Commit Deletion Policy
+ Custom deletion policies can be specified here. The class must
+ implement org.apache.lucene.index.IndexDeletionPolicy.
+
+ The default Solr IndexDeletionPolicy implementation supports
+ deleting index commit points on number of commits, age of
+ commit point and optimized status.
+
+ The latest commit point should always be preserved regardless
+ of the criteria.
+ -->
+ <!--
+ <deletionPolicy class="solr.SolrDeletionPolicy">
+ -->
+ <!-- The number of commit points to be kept -->
+ <!-- <str name="maxCommitsToKeep">1</str> -->
+ <!-- The number of optimized commit points to be kept -->
+ <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+ <!--
+ Delete all commit points once they have reached the given age.
+ Supports DateMathParser syntax e.g.
+ -->
+ <!--
+ <str name="maxCommitAge">30MINUTES</str>
+ <str name="maxCommitAge">1DAY</str>
+ -->
+ <!--
+ </deletionPolicy>
+ -->
+
+ <!-- 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.
+ -->
+ <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
+ and solr cloud replica recovery. The log can grow as big as
+ 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. -->
+ <updateLog>
+ <str name="dir">${solr.ulog.dir:}</str>
+ </updateLog>
+
+ <!-- AutoCommit
+
+ Perform a hard commit automatically under certain conditions.
+ Instead of enabling autoCommit, consider using "commitWithin"
+ when adding documents.
+
+ http://wiki.apache.org/solr/UpdateXmlMessages
+
+ maxDocs - Maximum number of documents to add since the last
+ commit before automatically triggering a new commit.
+
+ maxTime - Maximum amount of time in ms that is allowed to pass
+ since a document was added before automatically
+ triggering a new commit.
+ openSearcher - if false, the commit causes recent index changes
+ to be flushed to stable storage, but does not cause a new
+ searcher to be opened to make those changes visible.
+
+ If the updateLog is enabled, then it's highly recommended to
+ have some sort of hard autoCommit to limit the log size.
+ -->
+ <autoCommit>
+ <maxTime>${solr.autoCommit.maxTime:60000}</maxTime>
+ <openSearcher>false</openSearcher>
+ </autoCommit>
+
+ <!-- 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>${solr.autoSoftCommit.maxTime:1000}</maxTime>
+ </autoSoftCommit>
+
+
+ <!-- Update Related Event Listeners
+
+ Various IndexWriter related events can trigger Listeners to
+ take actions.
+
+ postCommit - fired after every commit or optimize command
+ postOptimize - fired after every optimize command
+ -->
+ <!-- The RunExecutableListener executes an external command from a
+ hook such as postCommit or postOptimize.
+
+ exe - the name of the executable to run
+ dir - dir to use as the current working directory. (default=".")
+ wait - the calling thread waits until the executable returns.
+ (default="true")
+ args - the arguments to pass to the program. (default is none)
+ env - environment variables to set. (default is none)
+ -->
+ <!-- This example shows how RunExecutableListener could be used
+ with the script based replication...
+ http://wiki.apache.org/solr/CollectionDistribution
+ -->
+ <!--
+ <listener event="postCommit" class="solr.RunExecutableListener">
+ <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>
+ </listener>
+ -->
+
+ </updateHandler>
+
+ <!-- IndexReaderFactory
+
+ Use the following format to specify a custom IndexReaderFactory,
+ which allows for alternate IndexReader implementations.
+
+ ** Experimental Feature **
+
+ Please note - Using a custom IndexReaderFactory may prevent
+ certain other features from working. The API to
+ IndexReaderFactory may change without warning or may even be
+ removed from future releases if the problems cannot be
+ resolved.
+
+
+ ** Features that may not work with custom IndexReaderFactory **
+
+ The ReplicationHandler assumes a disk-resident index. Using a
+ custom IndexReader implementation may cause incompatibility
+ with ReplicationHandler and may cause replication to not work
+ correctly. See SOLR-1366 for details.
+
+ -->
+ <!--
+ <indexReaderFactory name="IndexReaderFactory" class="package.class">
+ <str name="someArg">Some Value</str>
+ </indexReaderFactory >
+ -->
+ <!-- By explicitly declaring the Factory, the termIndexDivisor can
+ be specified.
+ -->
+ <!--
+ <indexReaderFactory name="IndexReaderFactory"
+ class="solr.StandardIndexReaderFactory">
+ <int name="setTermIndexDivisor">12</int>
+ </indexReaderFactory >
+ -->
+
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ 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>
+
+
+ <!-- Solr Internal Query Caches
+
+ There are two implementations of cache available for Solr,
+ LRUCache, based on a synchronized LinkedHashMap, and
+ FastLRUCache, based on a ConcurrentHashMap.
+
+ FastLRUCache has faster gets and slower puts in single
+ threaded operation and thus is generally faster than LRUCache
+ when the hit ratio of the cache is high (> 75%), and may be
+ faster under other scenarios on multi-cpu systems.
+ -->
+
+ <!-- Filter Cache
+
+ Cache used by SolrIndexSearcher for filters (DocSets),
+ unordered sets of *all* documents that match a query. When a
+ new searcher is opened, its caches may be prepopulated or
+ "autowarmed" using data from caches in the old searcher.
+ autowarmCount is the number of items to prepopulate. For
+ LRUCache, the autowarmed items will be the most recently
+ accessed items.
+
+ Parameters:
+ class - the SolrCache implementation LRUCache or
+ (LRUCache or FastLRUCache)
+ size - the maximum number of entries in the cache
+ 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.
+ -->
+ <filterCache class="solr.FastLRUCache"
+ size="512"
+ initialSize="512"
+ 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.
+ -->
+ <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.
+ -->
+ <documentCache class="solr.LRUCache"
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+
+ <!-- Field Value Cache
+
+ Cache used to hold field values that are quickly accessible
+ by document id. The fieldValueCache is created by default
+ even if not configured here.
+ -->
+ <!--
+ <fieldValueCache class="solr.FastLRUCache"
+ size="512"
+ autowarmCount="128"
+ showItems="32" />
+ -->
+
+ <!-- Custom Cache
+
+ Example of a generic cache. These caches may be accessed by
+ name through SolrIndexSearcher.getCache(),cacheLookup(), and
+ cacheInsert(). The purpose is to enable easy caching of
+ user/application level data. The regenerator argument should
+ be specified as an implementation of solr.CacheRegenerator
+ if autowarming is desired.
+ -->
+ <!--
+ <cache name="myUserCache"
+ class="solr.LRUCache"
+ size="4096"
+ initialSize="1024"
+ autowarmCount="1024"
+ regenerator="com.mycompany.MyRegenerator"
+ />
+ -->
+
+
+ <!-- Lazy Field Loading
+
+ If true, stored fields that are not requested will be loaded
+ lazily. This can result in a significant speed improvement
+ if the usual case is to not load all stored fields,
+ especially if the skipped fields are large compressed text
+ fields.
+ -->
+ <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
+ 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 49 will be collected and cached. Any further
+ 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.
+ -->
+ <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.
+
+
+ -->
+ <!-- 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="sort">price asc</str></lst>
+ <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
+ -->
+ </arr>
+ </listener>
+ <listener event="firstSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <lst>
+ <str name="q">static firstSearcher warming in solrconfig.xml</str>
+ </lst>
+ </arr>
+ </listener>
+
+ <!-- Use Cold Searcher
+
+ If a search request comes in and there is no current
+ registered searcher, then immediately register the still
+ warming searcher and use it. If "false" then all requests
+ will block until the first searcher is done warming.
+ -->
+ <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.
+
+ Recommend values of 1-2 for read-only slaves, higher for
+ masters w/o cache warming.
+ -->
+ <maxWarmingSearchers>4</maxWarmingSearchers>
+
+ </query>
+
+
+ <!-- Request Dispatcher
+
+ This section contains instructions for how the SolrDispatchFilter
+ should behave when processing requests for this SolrCore.
+
+ handleSelect is a legacy option that affects the behavior of requests
+ 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
+ "qt" param, assuming "/select" isn't already registered.
+
+ handleSelect="false" will cause the SolrDispatchFilter to
+ ignore "/select" requests, resulting in a 404 unless a handler
+ is explicitly registered with the name "/select"
+
+ handleSelect="true" is not recommended for new users, but is the default
+ for backwards compatibility
+ -->
+ <requestDispatcher handleSelect="false" >
+ <!-- Request Parsing
+
+ These settings indicate how Solr Requests may be parsed, and
+ what restrictions may be placed on the ContentStreams from
+ those requests
+
+ enableRemoteStreaming - enables use of the stream.file
+ and stream.url parameters for specifying remote streams.
+
+ 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
+
+ Set HTTP caching related parameters (for proxy caches and clients).
+
+ The options below instruct Solr not to output any HTTP Caching
+ 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
+
+ http://wiki.apache.org/solr/SolrRequestHandler
+
+ Incoming queries will be dispatched to a specific handler by name
+ based on the path specified in the request.
+
+ Legacy behavior: If the request path uses "/select" but no Request
+ Handler has that name, and if handleSelect="true" has been specified in
+ the requestDispatcher, then the Request Handler is dispatched based on
+ the qt parameter. Handlers without a leading '/' are accessed this way
+ like so: http://host/app/[core/]select?qt=name If no qt is
+ given, then the requestHandler that declares default="true" will be
+ used or the one named "standard".
+
+ If a Request Handler is declared with startup="lazy", then it will
+ not be initialized until the first request that uses it.
+
+ -->
+ <!-- SearchHandler
+
+ http://wiki.apache.org/solr/SearchHandler
+
+ For processing Search Queries, the primary Request Handler
+ provided with Solr is "SearchHandler" It delegates to a sequent
+ of SearchComponents (see below) and supports distributed
+ queries across multiple shards
+ -->
+ <requestHandler name="/select" class="solr.SearchHandler">
+ <!-- default values for query parameters can be specified, these
+ will be overridden by parameters in the request
+ -->
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <int name="rows">10</int>
+ <str name="df">text</str>
+ </lst>
+ <!-- In addition to defaults, "appends" params can be specified
+ to identify values which should be appended to the list of
+ multi-val params from the query (or the existing "defaults").
+ -->
+ <!-- In this example, the param "fq=instock:true" would be appended to
+ any query time fq params the user may specify, as a mechanism for
+ partitioning the index, independent of any user selected filtering
+ that may also be desired (perhaps as a result of faceted searching).
+
+ NOTE: there is *absolutely* nothing a client can do to prevent these
+ "appends" values from being used, so don't use this mechanism
+ unless you are sure you always want it.
+ -->
+ <!--
+ <lst name="appends">
+ <str name="fq">inStock:true</str>
+ </lst>
+ -->
+ <!-- "invariants" are a way of letting the Solr maintainer lock down
+ the options available to Solr clients. Any params values
+ specified here are used regardless of what values may be specified
+ in either the query, the "defaults", or the "appends" params.
+
+ In this example, the facet.field and facet.query params would
+ be fixed, limiting the facets clients can use. Faceting is
+ not turned on by default - but if the client does specify
+ facet=true in the request, these are the only facets they
+ will be able to see counts for; regardless of what other
+ facet.field or facet.query params they may specify.
+
+ NOTE: there is *absolutely* nothing a client can do to prevent these
+ "invariants" values from being used, so don't use this mechanism
+ unless you are sure you always want it.
+ -->
+ <!--
+ <lst name="invariants">
+ <str name="facet.field">cat</str>
+ <str name="facet.field">manu_exact</str>
+ <str name="facet.query">price:[* TO 500]</str>
+ <str name="facet.query">price:[500 TO *]</str>
+ </lst>
+ -->
+ <!-- If the default list of SearchComponents is not desired, that
+ list can either be overridden completely, or components can be
+ prepended or appended to the default list. (see below)
+ -->
+ <!--
+ <arr name="components">
+ <str>nameOfCustomComponent1</str>
+ <str>nameOfCustomComponent2</str>
+ </arr>
+ -->
+ </requestHandler>
+
+ <!-- A request handler that returns indented JSON by default -->
+ <requestHandler name="/query" class="solr.SearchHandler">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <str name="wt">json</str>
+ <str name="indent">true</str>
+ <str name="df">text</str>
+ </lst>
+ </requestHandler>
+
+
+ <!-- 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>
+
+
+ <!-- A Robust Example
+
+ This example SearchHandler declaration shows off usage of the
+ SearchHandler with many defaults declared
+
+ Note that multiple instances of the same Request Handler
+ (SearchHandler) can be registered multiple times with different
+ names (and different init parameters)
+ -->
+ <requestHandler name="/browse" class="solr.SearchHandler">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+
+ <!-- VelocityResponseWriter settings -->
+ <str name="wt">velocity</str>
+ <str name="v.template">browse</str>
+ <str name="v.layout">layout</str>
+ <str name="title">Solritas</str>
+
+ <!-- Query settings -->
+ <str name="defType">edismax</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
+ title^10.0 description^5.0 keywords^5.0 author^2.0 resourcename^1.0
+ </str>
+ <str name="df">text</str>
+ <str name="mm">100%</str>
+ <str name="q.alt">*:*</str>
+ <str name="rows">10</str>
+ <str name="fl">*,score</str>
+
+ <str name="mlt.qf">
+ text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
+ title^10.0 description^5.0 keywords^5.0 author^2.0 resourcename^1.0
+ </str>
+ <str name="mlt.fl">text,features,name,sku,id,manu,cat,title,description,keywords,author,resourcename</str>
+ <int name="mlt.count">3</int>
+
+ <!-- Faceting defaults -->
+ <str name="facet">on</str>
+ <str name="facet.field">cat</str>
+ <str name="facet.field">manu_exact</str>
+ <str name="facet.field">content_type</str>
+ <str name="facet.field">author_s</str>
+ <str name="facet.query">ipod</str>
+ <str name="facet.query">GB</str>
+ <str name="facet.mincount">1</str>
+ <str name="facet.pivot">cat,inStock</str>
+ <str name="facet.range.other">after</str>
+ <str name="facet.range">price</str>
+ <int name="f.price.facet.range.start">0</int>
+ <int name="f.price.facet.range.end">600</int>
+ <int name="f.price.facet.range.gap">50</int>
+ <str name="facet.range">popularity</str>
+ <int name="f.popularity.facet.range.start">0</int>
+ <int name="f.popularity.facet.range.end">10</int>
+ <int name="f.popularity.facet.range.gap">3</int>
+ <str name="facet.range">manufacturedate_dt</str>
+ <str name="f.manufacturedate_dt.facet.range.start">NOW/YEAR-10YEARS</str>
+ <str name="f.manufacturedate_dt.facet.range.end">NOW</str>
+ <str name="f.manufacturedate_dt.facet.range.gap">+1YEAR</str>
+ <str name="f.manufacturedate_dt.facet.range.other">before</str>
+ <str name="f.manufacturedate_dt.facet.range.other">after</str>
+
+ <!-- Highlighting defaults -->
+ <str name="hl">on</str>
+ <str name="hl.fl">content features title name</str>
+ <str name="hl.encoder">html</str>
+ <str name="hl.simple.pre"><b></str>
+ <str name="hl.simple.post"></b></str>
+ <str name="f.title.hl.fragsize">0</str>
+ <str name="f.title.hl.alternateField">title</str>
+ <str name="f.name.hl.fragsize">0</str>
+ <str name="f.name.hl.alternateField">name</str>
+ <str name="f.content.hl.snippets">3</str>
+ <str name="f.content.hl.fragsize">200</str>
+ <str name="f.content.hl.alternateField">content</str>
+ <str name="f.content.hl.maxAlternateFieldLength">750</str>
+
+ <!-- Spell checking defaults -->
+ <str name="spellcheck">on</str>
+ <str name="spellcheck.extendedResults">false</str>
+ <str name="spellcheck.count">5</str>
+ <str name="spellcheck.alternativeTermCount">2</str>
+ <str name="spellcheck.maxResultsForSuggest">5</str>
+ <str name="spellcheck.collate">true</str>
+ <str name="spellcheck.collateExtendedResults">true</str>
+ <str name="spellcheck.maxCollationTries">5</str>
+ <str name="spellcheck.maxCollations">3</str>
+ </lst>
+
+ <!-- append spellchecking to our list of components -->
+ <arr name="last-components">
+ <str>spellcheck</str>
+ </arr>
+ </requestHandler>
+
+
+ <!-- Update Request Handler.
+
+ http://wiki.apache.org/solr/UpdateXmlMessages
+
+ The canonical Request Handler for Modifying the Index through
+ commands specified using XML, JSON, CSV, or JAVABIN
+
+ Note: Since solr1.1 requestHandlers requires a valid content
+ type header if posted in the body. For example, curl now
+ requires: -H 'Content-type:text/xml; charset=utf-8'
+
+ To override the request content type and force a specific
+ Content-type, use the request parameter:
+ ?update.contentType=text/csv
+
+ This handler will pick a response format to match the input
+ if the 'wt' parameter is not explicit
+ -->
+ <requestHandler name="/update" class="solr.UpdateRequestHandler">
+ <!-- See below for information on defining
+ updateRequestProcessorChains that can be used by name
+ on each Update Request
+ -->
+ <!--
+ <lst name="defaults">
+ <str name="update.chain">dedupe</str>
+ </lst>
+ -->
+ </requestHandler>
+
+ <!-- for back compat with clients using /update/json and /update/csv -->
+ <requestHandler name="/update/json" class="solr.JsonUpdateRequestHandler">
+ <lst name="defaults">
+ <str name="stream.contentType">application/json</str>
+ </lst>
+ </requestHandler>
+ <requestHandler name="/update/csv" class="solr.CSVRequestHandler">
+ <lst name="defaults">
+ <str name="stream.contentType">application/csv</str>
+ </lst>
+ </requestHandler>
+
+
+ <!-- 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" />
+
+
+ <!-- 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" />
+
+ <!-- Admin Handlers
+
+ Admin Handlers - This will register all the standard admin
+ RequestHandlers.
+ -->
+ <requestHandler name="/admin/"
+ class="solr.admin.AdminHandlers" />
+ <!-- This single handler is equivalent to the following... -->
+ <!--
+ <requestHandler name="/admin/luke" class="solr.admin.LukeRequestHandler" />
+ <requestHandler name="/admin/system" class="solr.admin.SystemInfoHandler" />
+ <requestHandler name="/admin/plugins" class="solr.admin.PluginInfoHandler" />
+ <requestHandler name="/admin/threads" class="solr.admin.ThreadDumpHandler" />
+ <requestHandler name="/admin/properties" class="solr.admin.PropertiesRequestHandler" />
+ <requestHandler name="/admin/file" class="solr.admin.ShowFileRequestHandler" >
+ -->
+ <!-- If you wish to hide files under ${solr.home}/conf, explicitly
+ register the ShowFileRequestHandler using:
+ -->
+ <!--
+ <requestHandler name="/admin/file"
+ class="solr.admin.ShowFileRequestHandler" >
+ <lst name="invariants">
+ <str name="hidden">synonyms.txt</str>
+ <str name="hidden">anotherfile.txt</str>
+ </lst>
+ </requestHandler>
+ -->
+
+ <!-- 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>
+ <!-- An optional feature of the PingRequestHandler is to configure the
+ handler with a "healthcheckFile" which can be used to enable/disable
+ the PingRequestHandler.
+ relative paths are resolved against the data dir
+ -->
+ <!-- <str name="healthcheckFile">server-enabled.txt</str> -->
+ </requestHandler>
+
+ <!-- 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="echoHandler">true</str>
+ </lst>
+ </requestHandler>
+
+ <!-- Solr Replication
+
+ The SolrReplicationHandler supports replicating indexes from a
+ "master" used for indexing and "slaves" used for queries.
+
+ http://wiki.apache.org/solr/SolrReplication
+
+ It is also necessary for SolrCloud to function (in Cloud mode, the
+ replication handler is used to bulk transfer segments when nodes
+ are added or need to recover).
+
+ https://wiki.apache.org/solr/SolrCloud/
+ -->
+ <requestHandler name="/replication" class="solr.ReplicationHandler" >
+ <!--
+ To enable simple master/slave replication, uncomment one of the
+ sections below, depending on whether this solr instance should be
+ the "master" or a "slave". If this instance is a "slave" you will
+ also need to fill in the masterUrl to point to a real machine.
+ -->
+ <!--
+ <lst name="master">
+ <str name="replicateAfter">commit</str>
+ <str name="replicateAfter">startup</str>
+ <str name="confFiles">schema.xml,stopwords.txt</str>
+ </lst>
+ -->
+ <!--
+ <lst name="slave">
+ <str name="masterUrl">http://your-master-hostname:8983/solr</str>
+ <str name="pollInterval">00:00:60</str>
+ </lst>
+ -->
+ </requestHandler>
+
+ <!-- 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" />
+
+ Default configuration in a requestHandler would look like:
+
+ <arr name="components">
+ <str>query</str>
+ <str>facet</str>
+ <str>mlt</str>
+ <str>highlight</str>
+ <str>stats</str>
+ <str>debug</str>
+ </arr>
+
+ If you register a searchComponent to one of the standard names,
+ that will be used instead of the default.
+
+ To insert components before or after the 'standard' components, use:
+
+ <arr name="first-components">
+ <str>myFirstComponentName</str>
+ </arr>
+
+ <arr name="last-components">
+ <str>myLastComponentName</str>
+ </arr>
+
+ NOTE: The component registered with the name "debug" will
+ always be executed after the "last-components"
+
+ -->
+
+ <!-- Spell Check
+
+ The spell check component can return a list of alternative spelling
+ suggestions.
+
+ http://wiki.apache.org/solr/SpellCheckComponent
+ -->
+ <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+ <str name="queryAnalyzerFieldType">text_general</str>
+
+ <!-- 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">text</str>
+ <str name="classname">solr.DirectSolrSpellChecker</str>
+ <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
+ <str name="distanceMeasure">internal</str>
+ <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
+ <float name="accuracy">0.5</float>
+ <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
+ <int name="maxEdits">2</int>
+ <!-- the minimum shared prefix when enumerating terms -->
+ <int name="minPrefix">1</int>
+ <!-- maximum number of inspections per result. -->
+ <int name="maxInspections">5</int>
+ <!-- minimum length of a query term to be considered for correction -->
+ <int name="minQueryLength">4</int>
+ <!-- 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>
+ -->
+ </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="field">name</str>
+ <str name="combineWords">true</str>
+ <str name="breakWords">true</str>
+ <int name="maxChanges">10</int>
+ </lst>
+
+ <!-- a spellchecker that uses a different distance measure -->
+ <!--
+ <lst name="spellchecker">
+ <str name="name">jarowinkler</str>
+ <str name="field">spell</str>
+ <str name="classname">solr.DirectSolrSpellChecker</str>
+ <str name="distanceMeasure">
+ org.apache.lucene.search.spell.JaroWinklerDistance
+ </str>
+ </lst>
+ -->
+
+ <!-- a spellchecker that use an alternate comparator
+
+ comparatorClass be one of:
+ 1. score (default)
+ 2. freq (Frequency first, then score)
+ 3. A fully qualified class name
+ -->
+ <!--
+ <lst name="spellchecker">
+ <str name="name">freq</str>
+ <str name="field">lowerfilt</str>
+ <str name="classname">solr.DirectSolrSpellChecker</str>
+ <str name="comparatorClass">freq</str>
+ -->
+
+ <!-- A spellchecker that reads the list of words from a file -->
+ <!--
+ <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 for demonstrating the spellcheck component.
+
+ NOTE: This is purely as an example. The whole purpose of the
+ SpellCheckComponent is to hook it into the request handler that
+ handles your normal user queries so that a separate request is
+ not needed to get suggestions.
+
+ IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
+ NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
+
+ See http://wiki.apache.org/solr/SpellCheckComponent for details
+ on the request parameters.
+ -->
+ <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <str name="df">text</str>
+ <!-- Solr will use suggestions from both the 'default' spellchecker
+ and from the 'wordbreak' spellchecker and combine them.
+ collations (re-written queries) can include a combination of
+ corrections from both spellcheckers -->
+ <str name="spellcheck.dictionary">default</str>
+ <str name="spellcheck.dictionary">wordbreak</str>
+ <str name="spellcheck">on</str>
+ <str name="spellcheck.extendedResults">true</str>
+ <str name="spellcheck.count">10</str>
+ <str name="spellcheck.alternativeTermCount">5</str>
+ <str name="spellcheck.maxResultsForSuggest">5</str>
+ <str name="spellcheck.collate">true</str>
+ <str name="spellcheck.collateExtendedResults">true</str>
+ <str name="spellcheck.maxCollationTries">10</str>
+ <str name="spellcheck.maxCollations">5</str>
+ </lst>
+ <arr name="last-components">
+ <str>spellcheck</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Term Vector Component
+
+ http://wiki.apache.org/solr/TermVectorComponent
+ -->
+ <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
+
+ <!-- A request handler for demonstrating the term vector component
+
+ This is purely as an example.
+
+ In reality you will likely want to add the component to your
+ already specified request handlers.
+ -->
+ <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <str name="df">text</str>
+ <bool name="tv">true</bool>
+ </lst>
+ <arr name="last-components">
+ <str>tvComponent</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Clustering Component
+
+ http://wiki.apache.org/solr/ClusteringComponent
+
+ You'll need to set the solr.clustering.enabled system property
+ when running solr to run with clustering enabled:
+
+ java -Dsolr.clustering.enabled=true -jar start.jar
+
+ -->
+ <searchComponent name="clustering"
+ enable="${solr.clustering.enabled:false}"
+ class="solr.clustering.ClusteringComponent" >
+ <!-- Declare an engine -->
+ <lst name="engine">
+ <!-- The name, only one can be named "default" -->
+ <str name="name">default</str>
+
+ <!-- Class name of Carrot2 clustering algorithm.
+
+ Currently available algorithms are:
+
+ * org.carrot2.clustering.lingo.LingoClusteringAlgorithm
+ * org.carrot2.clustering.stc.STCClusteringAlgorithm
+ * org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm
+
+ See http://project.carrot2.org/algorithms.html for the
+ algorithm's characteristics.
+ -->
+ <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
+
+ <!-- Overriding values for Carrot2 default algorithm attributes.
+
+ For a description of all available attributes, see:
+ http://download.carrot2.org/stable/manual/#chapter.components.
+ Use attribute key as name attribute of str elements
+ below. These can be further overridden for individual
+ requests by specifying attribute key as request parameter
+ name and attribute value as parameter value.
+ -->
+ <str name="LingoClusteringAlgorithm.desiredClusterCountBase">20</str>
+
+ <!-- Location of Carrot2 lexical resources.
+
+ A directory from which to load Carrot2-specific stop words
+ and stop labels. Absolute or relative to Solr config directory.
+ If a specific resource (e.g. stopwords.en) is present in the
+ specified dir, it will completely override the corresponding
+ default one that ships with Carrot2.
+
+ For an overview of Carrot2 lexical resources, see:
+ http://download.carrot2.org/head/manual/#chapter.lexical-resources
+ -->
+ <str name="carrot.lexicalResourcesDir">clustering/carrot2</str>
+
+ <!-- The language to assume for the documents.
+
+ For a list of allowed values, see:
+ http://download.carrot2.org/stable/manual/#section.attribute.lingo.MultilingualClustering.defaultLanguage
+ -->
+ <str name="MultilingualClustering.defaultLanguage">ENGLISH</str>
+ </lst>
+ <lst name="engine">
+ <str name="name">stc</str>
+ <str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
+ </lst>
+ </searchComponent>
+
+ <!-- A request handler for demonstrating the clustering component
+
+ This is purely as an example.
+
+ In reality you will likely want to add the component to your
+ already specified request handlers.
+ -->
+ <requestHandler name="/clustering"
+ startup="lazy"
+ enable="${solr.clustering.enabled:false}"
+ class="solr.SearchHandler">
+ <lst name="defaults">
+ <bool name="clustering">true</bool>
+ <str name="clustering.engine">default</str>
+ <bool name="clustering.results">true</bool>
+ <!-- The title field -->
+ <str name="carrot.title">name</str>
+ <str name="carrot.url">id</str>
+ <!-- The field to cluster on -->
+ <str name="carrot.snippet">features</str>
+ <!-- produce summaries -->
+ <bool name="carrot.produceSummary">true</bool>
+ <!-- the maximum number of labels per cluster -->
+ <!--<int name="carrot.numDescriptions">5</int>-->
+ <!-- produce sub clusters -->
+ <bool name="carrot.outputSubClusters">false</bool>
+
+ <str name="defType">edismax</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="q.alt">*:*</str>
+ <str name="rows">10</str>
+ <str name="fl">*,score</str>
+ </lst>
+ <arr name="last-components">
+ <str>clustering</str>
+ </arr>
+ </requestHandler>
+
+ <!-- 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"/>
+
+ <!-- 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>
+
+
+ <!-- Query Elevation Component
+
+ http://wiki.apache.org/solr/QueryElevationComponent
+
+ 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 for demonstrating the elevator component -->
+ <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <str name="df">text</str>
+ </lst>
+ <arr name="last-components">
+ <str>elevator</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Highlighting Component
+
+ http://wiki.apache.org/solr/HighlightingParameters
+ -->
+ <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\"']{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">.,!? 	 </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>
+
+ <!-- Update Processors
+
+ Chains of Update Processor Factories for dealing with Update
+ Requests can be declared, and then used by name in Update
+ Request Processors
+
+ http://wiki.apache.org/solr/UpdateRequestProcessor
+
+ -->
+ <!-- Deduplication
+
+ An example dedup update processor that creates the "id" field
+ on the fly based on the hash code of some other fields. This
+ example has overwriteDupes set to false since we are using the
+ id field as the signatureField and Solr will maintain
+ uniqueness based on that anyway.
+
+ -->
+ <!--
+ <updateRequestProcessorChain name="dedupe">
+ <processor class="solr.processor.SignatureUpdateProcessorFactory">
+ <bool name="enabled">true</bool>
+ <str name="signatureField">id</str>
+ <bool name="overwriteDupes">false</bool>
+ <str name="fields">name,features,cat</str>
+ <str name="signatureClass">solr.processor.Lookup3Signature</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory" />
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Language identification
+
+ This example update chain identifies the language of the incoming
+ documents using the langid contrib. The detected language is
+ written to field language_s. No field name mapping is done.
+ The fields used for detection are text, title, subject and description,
+ making this example suitable for detecting languages form full-text
+ rich documents injected via ExtractingRequestHandler.
+ See more about langId at http://wiki.apache.org/solr/LanguageDetection
+ -->
+ <!--
+ <updateRequestProcessorChain name="langid">
+ <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
+ <str name="langid.fl">text,title,subject,description</str>
+ <str name="langid.langField">language_s</str>
+ <str name="langid.fallback">en</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory" />
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Script update processor
+
+ This example hooks in an update processor implemented using JavaScript.
+
+ See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
+ -->
+ <!--
+ <updateRequestProcessorChain name="script">
+ <processor class="solr.StatelessScriptUpdateProcessorFactory">
+ <str name="script">update-script.js</str>
+ <lst name="params">
+ <str name="config_param">example config parameter</str>
+ </lst>
+ </processor>
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Response Writers
+
+ http://wiki.apache.org/solr/QueryResponseWriter
+
+ Request responses will be written using the writer specified by
+ the 'wt' request parameter matching the name of a registered
+ writer.
+
+ The "default" writer is the default and will be used if 'wt' is
+ not specified in the request.
+ -->
+ <!-- The following response writers are implicitly configured unless
+ overridden...
+ -->
+ <!--
+ <queryResponseWriter name="xml"
+ default="true"
+ class="solr.XMLResponseWriter" />
+ <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
+ <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
+ <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
+ <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
+ <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
+ <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+ <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
+ -->
+
+ <queryResponseWriter name="json" class="solr.JSONResponseWriter">
+ <!-- For the purposes of the tutorial, JSON responses are written as
+ plain text so that they are easy to read in *any* browser.
+ If you expect a MIME type of "application/json" just remove this override.
+ -->
+ <str name="content-type">text/plain; charset=UTF-8</str>
+ </queryResponseWriter>
+
+ <!--
+ Custom response writers can be declared as needed...
+ -->
+ <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy"/>
+
+
+ <!-- XSLT response writer transforms the XML output by any xslt file found
+ in Solr's conf/xslt directory. Changes to xslt files are checked for
+ every xsltCacheLifetimeSeconds.
+ -->
+ <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
+ <int name="xsltCacheLifetimeSeconds">5</int>
+ </queryResponseWriter>
+
+ <!-- Query Parsers
+
+ http://wiki.apache.org/solr/SolrQuerySyntax
+
+ Multiple QParserPlugins can be registered by name, and then
+ used in either the "defType" param for the QueryComponent (used
+ by SearchHandler) or in LocalParams
+ -->
+ <!-- example of registering a query parser -->
+ <!--
+ <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
+ -->
+
+ <!-- Function Parsers
+
+ http://wiki.apache.org/solr/FunctionQuery
+
+ Multiple ValueSourceParsers can be registered by name, and then
+ used as function names when using the "func" QParser.
+ -->
+ <!-- example of registering a custom function parser -->
+ <!--
+ <valueSourceParser name="myfunc"
+ class="com.mycompany.MyValueSourceParser" />
+ -->
+
+
+ <!-- Document Transformers
+ http://wiki.apache.org/solr/DocTransformers
+ -->
+ <!--
+ Could be something like:
+ <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
+ <int name="connection">jdbc://....</int>
+ </transformer>
+
+ To add a constant value to all docs, use:
+ <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+ <int name="value">5</int>
+ </transformer>
+
+ If you want the user to still be able to change it with _value:something_ use this:
+ <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+ <double name="defaultValue">5</double>
+ </transformer>
+
+ If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
+ EditorialMarkerFactory will do exactly that:
+ <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
+ -->
+
+
+ <!-- Legacy config for the admin interface -->
+ <admin>
+ <defaultQuery>*:*</defaultQuery>
+ </admin>
+
+</config>
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/common/solr/solrctl.sh
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/common/solr/solrctl.sh b/bigtop-packages/src/common/solr/solrctl.sh
new file mode 100644
index 0000000..5b9f434
--- /dev/null
+++ b/bigtop-packages/src/common/solr/solrctl.sh
@@ -0,0 +1,425 @@
+#!/bin/bash
+
+# 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.
+
+SOLR_XML='<solr>
+
+ <solrcloud>
+ <str name="host">${host:}</str>
+ <int name="hostPort">${solr.port:8983}</int>
+ <str name="hostContext">${hostContext:solr}</str>
+ <int name="zkClientTimeout">${zkClientTimeout:15000}</int>
+ <bool name="genericCoreNodeNames">${genericCoreNodeNames:true}</bool>
+ </solrcloud>
+
+ <shardHandlerFactory name="shardHandlerFactory"
+ class="HttpShardHandlerFactory">
+ <int name="socketTimeout">${socketTimeout:0}</int>
+ <int name="connTimeout">${connTimeout:0}</int>
+ </shardHandlerFactory>
+
+</solr>'
+
+usage() {
+ [ $# -eq 0 ] || echo "$@"
+ echo "
+usage: $0 [options] command [command-arg] [command [command-arg]] ...
+
+Options:
+ --solr solr_uri
+ --zk zk_ensemble
+ --help
+ --quiet
+
+Commands:
+ init [--force]
+
+ instancedir [--generate path]
+ [--create name path]
+ [--update name path]
+ [--get name path]
+ [--delete name]
+ [--list]
+
+ collection [--create name -s <numShards>
+ [-c <collection.configName>]
+ [-r <replicationFactor>]
+ [-m <maxShardsPerNode>]
+ [-n <createNodeSet>]]
+ [--delete name]
+ [--reload name]
+ [--stat name]
+ [--deletedocs name]
+ [--list]
+
+ core [--create name [-p name=value]...]
+ [--reload name]
+ [--unload name]
+ [--status name]
+ "
+ exit 1
+}
+
+die() {
+ echo "$1"
+ exit 1
+}
+
+# FIXME: this is here only for testing purposes
+local_coreconfig() {
+ case "$2" in
+ put)
+ echo "$4" > "/var/lib/solr/$3"
+ ;;
+ list)
+ ls -d /var/lib/solr/*/conf 2>/dev/null | sed -e 's#var/lib/solr#configs#'
+ ;;
+ clear)
+ if [ "$3" != "/" ] ; then
+ sudo -u solr rm -rf /var/lib/solr/`basename $3`/* 2>/dev/null
+ fi
+ ;;
+ upconfig)
+ # the following trick gets us around permission issues
+ rm -rf /tmp/solr_conf.$$
+ cp -r $4 /tmp/solr_conf.$$
+ chmod o+r -R /tmp/solr_conf.$$
+ sudo -u solr bash -c "mkdir /var/lib/solr/$6 2>/dev/null ; cp -r /tmp/solr_conf.$$ /var/lib/solr/$6/conf"
+ RES=$?
+ rm -rf /tmp/solr_conf.$$
+ return $RES
+ ;;
+ downconfig)
+ mkdir -p $4
+ cp -r /var/lib/solr/$6/conf/* $4
+ ;;
+ esac
+}
+
+solr_webapi() {
+ # If SOLR_ADMIN_URI wasn't given explicitly via --solr we need to guess it
+ if [ -z "$SOLR_ADMIN_URI" ] ; then
+ for node in `get_solr_state | sed -ne 's#/live_nodes/\(.*:[0-9][0-9]*\).*$#\1#p'` localhost:$SOLR_PORT ; do
+ if $SOLR_ADMIN_CURL "http://$node/solr" >/dev/null 2>&1 ; then
+ SOLR_ADMIN_URI="http://$node/solr"
+ break
+ fi
+ done
+ [ -n "$SOLR_ADMIN_URI" ] || die "Error: can't discover Solr URI. Please specify it explicitly via --solr."
+ fi
+
+ URI="$SOLR_ADMIN_URI/$1"
+ shift
+ local WEB_OUT=`$SOLR_ADMIN_CURL $URI "$@" | sed -e 's#>#>\n#g'`
+
+ if [ $? -eq 0 ] && (echo "$WEB_OUT" | grep -q 'HTTP/.*200.*OK') ; then
+ echo "$WEB_OUT" | egrep -q '<lst name="(failure|exception|error)">' || return 0
+ fi
+
+ die "Error: A call to SolrCloud WEB APIs failed: $WEB_OUT"
+}
+
+get_solr_state() {
+ if [ -z "$SOLR_STATE" ] ; then
+ SOLR_STATE=`eval $SOLR_ADMIN_ZK_CMD -cmd list 2>/dev/null`
+ fi
+
+ echo "$SOLR_STATE" | grep -v '^/ '
+}
+
+SOLR_CONF_DIR=${SOLR_CONF_DIR:-/etc/solr/conf}
+
+if [ -e "$SOLR_CONF_DIR/solr-env.sh" ] ; then
+ . "$SOLR_CONF_DIR/solr-env.sh"
+elif [ -e /etc/default/solr ] ; then
+ . /etc/default/solr
+else
+ SOLR_PORT=8983
+fi
+
+SOLR_ADMIN_CURL='curl -i --retry 5 -s -L -k --negotiate -u :'
+SOLR_ADMIN_CHAT=echo
+SOLR_ADMIN_API_CMD='solr_webapi'
+
+SOLR_HOME=${SOLR_HOME:-/usr/lib/solr/}
+
+# First eat up all the global options
+
+while test $# != 0 ; do
+ case "$1" in
+ --help)
+ usage
+ ;;
+ --quiet)
+ SOLR_ADMIN_CHAT=/bin/true
+ shift 1
+ ;;
+ --solr)
+ [ $# -gt 1 ] || usage "Error: $1 requires an argument"
+ SOLR_ADMIN_URI="$2"
+ shift 2
+ ;;
+ --zk)
+ [ $# -gt 1 ] || usage "Error: $1 requires an argument"
+ SOLR_ZK_ENSEMBLE="$2"
+ shift 2
+ ;;
+ *)
+ break
+ ;;
+ esac
+done
+
+if [ -z "$SOLR_ZK_ENSEMBLE" ] ; then
+ SOLR_ADMIN_ZK_CMD="local_coreconfig"
+ cat >&2 <<-__EOT__
+ Warning: Non-SolrCloud mode has been completely deprecated
+ Please configure SolrCloud via SOLR_ZK_ENSEMBLE setting in
+ /etc/default/solr
+ If you running remotely, please use --zk zk_ensemble.
+ __EOT__
+else
+ SOLR_ADMIN_ZK_CMD='${SOLR_HOME}/bin/zkcli.sh -zkhost $SOLR_ZK_ENSEMBLE 2>/dev/null'
+fi
+
+
+# Now start parsing commands -- there has to be at least one!
+[ $# -gt 0 ] || usage
+while test $# != 0 ; do
+ case "$1" in
+ debug-dump)
+ get_solr_state
+
+ shift 1
+ ;;
+
+ init)
+ if [ "$2" == "--force" ] ; then
+ shift 1
+ else
+ LIVE_NODES=`get_solr_state | sed -ne 's#/live_nodes/##p'`
+
+ if [ -n "$LIVE_NODES" ] ; then
+ die "Warning: It appears you have live SolrCloud nodes running: `printf '\n%s\nPlease shut them down.' \"${LIVE_NODES}\"`"
+ elif [ -n "`get_solr_state`" ] ; then
+ die "Warning: Solr appears to be initialized (use --force to override)"
+ fi
+ fi
+
+ eval $SOLR_ADMIN_ZK_CMD -cmd makepath / > /dev/null 2>&1 || :
+ eval $SOLR_ADMIN_ZK_CMD -cmd clear / || die "Error: failed to initialize Solr"
+
+ eval $SOLR_ADMIN_ZK_CMD -cmd put /solr.xml "'$SOLR_XML'"
+
+ shift 1
+ ;;
+
+ coreconfig)
+ $SOLR_ADMIN_CHAT "Warning: coreconfig is deprecated, please use instancedir instead (consult documentation on differences in behaviour)."
+ shift 1
+ set instancedir "$@"
+ ;;
+ instancedir)
+ [ $# -gt 1 ] || usage "Error: incorrect specification of arguments for $1"
+ case "$2" in
+ --create)
+ [ $# -gt 3 ] || usage "Error: incorrect specification of arguments for $1 $2"
+
+ if [ -d $4/conf ] ; then
+ INSTANCE_DIR="$4/conf"
+ else
+ INSTANCE_DIR="$4"
+ fi
+
+ [ -e ${INSTANCE_DIR}/solrconfig.xml -a -e ${INSTANCE_DIR}/schema.xml ] || die "Error: ${INSTANCE_DIR} must be a directory with at least solrconfig.xml and schema.xml"
+
+ get_solr_state | grep -q '^ */configs/'"$3/" && die "Error: \"$3\" configuration already exists. Aborting. Try --update if you want to override"
+
+ $SOLR_ADMIN_CHAT "Uploading configs from ${INSTANCE_DIR} to $SOLR_ZK_ENSEMBLE. This may take up to a minute."
+ eval $SOLR_ADMIN_ZK_CMD -cmd upconfig -confdir ${INSTANCE_DIR} -confname $3 2>/dev/null || die "Error: can't upload configuration"
+ shift 4
+ ;;
+ --update)
+ [ $# -gt 3 ] || usage "Error: incorrect specification of arguments for $1 $2"
+
+ if [ -d $4/conf ] ; then
+ INSTANCE_DIR="$4/conf"
+ else
+ INSTANCE_DIR="$4"
+ fi
+
+ [ -e ${INSTANCE_DIR}/solrconfig.xml -a -e ${INSTANCE_DIR}/schema.xml ] || die "Error: ${INSTANCE_DIR} must be a directory with at least solrconfig.xml and schema.xml"
+
+ eval $SOLR_ADMIN_ZK_CMD -cmd clear /configs/$3 2>/dev/null || die "Error: can't delete configuration"
+
+ $SOLR_ADMIN_CHAT "Uploading configs from ${INSTANCE_DIR} to $SOLR_ZK_ENSEMBLE. This may take up to a minute."
+ eval $SOLR_ADMIN_ZK_CMD -cmd upconfig -confdir ${INSTANCE_DIR} -confname $3 2>/dev/null || die "Error: can't upload configuration"
+ shift 4
+ ;;
+ --get)
+ [ $# -gt 3 ] || usage "Error: incorrect specification of arguments for $1 $2"
+
+ [ -e "$4" ] && die "Error: subdirectory $4 already exists"
+
+ $SOLR_ADMIN_CHAT "Downloading configs from $SOLR_ZK_ENSEMBLE to $4. This may take up to a minute."
+ eval $SOLR_ADMIN_ZK_CMD -cmd downconfig -confdir "$4/conf" -confname "$3" 2>/dev/null || die "Error: can't download configuration"
+ shift 4
+ ;;
+ --delete)
+ [ $# -gt 2 ] || usage "Error: incorrect specification of arguments for $1"
+
+ eval $SOLR_ADMIN_ZK_CMD -cmd clear /configs/$3 2>/dev/null || die "Error: can't delete configuration"
+ shift 3
+ ;;
+ --generate)
+ [ $# -gt 2 ] || usage "Error: incorrect specification of arguments for $1"
+
+ [ -e "$3" ] && die "Error: subdirectory $3 already exists"
+
+ mkdir -p "$3" > /dev/null 2>&1
+ [ -d "$3" ] || usage "Error: $3 has to be a directory"
+ cp -r ${SOLR_HOME}/coreconfig-template "$3/conf"
+ shift 3
+ ;;
+ --list)
+ get_solr_state | sed -n -e '/\/configs\//s#^.*/configs/\([^/]*\)/.*$#\1#p' | sort -u
+ shift 2
+ ;;
+ *)
+ shift 1
+ ;;
+ esac
+ ;;
+
+ collection)
+ [ "$2" = "--list" ] || [ $# -gt 2 ] || usage "Error: incorrect specification of arguments for $1"
+ case "$2" in
+ --create)
+ COL_CREATE_NAME=$3
+ COL_CREATE_NUMSHARDS=1
+ shift 3
+ while test $# -gt 0 ; do
+ case "$1" in
+ -s)
+ [ $# -gt 1 ] || usage "Error: collection --create name $1 requires an argument"
+ COL_CREATE_NUMSHARDS="$2"
+ shift 2
+ ;;
+ -c)
+ [ $# -gt 1 ] || usage "Error: collection --create name $1 requires an argument"
+ COL_CREATE_CONFNAME="$2"
+ shift 2
+ ;;
+ -r)
+ [ $# -gt 1 ] || usage "Error: collection --create name $1 requires an argument"
+ COL_CREATE_REPL="$2"
+ shift 2
+ ;;
+ -m)
+ [ $# -gt 1 ] || usage "Error: collection --create name $1 requires an argument"
+ COL_CREATE_MAXSHARDS="$2"
+ shift 2
+ ;;
+ -n)
+ [ $# -gt 1 ] || usage "Error: collection --create name $1 requires an argument"
+ COL_CREATE_NODESET="$2"
+ shift 2
+ ;;
+ *)
+ break
+ ;;
+ esac
+ done
+
+ COL_CREATE_CALL="&name=${COL_CREATE_NAME}"
+ if [ "$COL_CREATE_NUMSHARDS" -gt 0 ] ; then
+ COL_CREATE_CALL="${COL_CREATE_CALL}&numShards=${COL_CREATE_NUMSHARDS}"
+ else
+ usage "Error: collection --create name needs to have more than 0 shards specified"
+ fi
+ [ -n "$COL_CREATE_CONFNAME" ] && COL_CREATE_CALL="${COL_CREATE_CALL}&collection.configName=${COL_CREATE_CONFNAME}"
+ [ -n "$COL_CREATE_REPL" ] && COL_CREATE_CALL="${COL_CREATE_CALL}&replicationFactor=${COL_CREATE_REPL}"
+ [ -n "$COL_CREATE_MAXSHARDS" ] && COL_CREATE_CALL="${COL_CREATE_CALL}&maxShardsPerNode=${COL_CREATE_MAXSHARDS}"
+ [ -n "$COL_CREATE_NODESET" ] && COL_CREATE_CALL="${COL_CREATE_CALL}&createNodeSet=${COL_CREATE_NODESET}"
+
+ eval $SOLR_ADMIN_API_CMD "'/admin/collections?action=CREATE${COL_CREATE_CALL}'"
+
+ shift 4
+ ;;
+ --delete|--reload)
+ COL_ACTION=`echo $2 | tr '[a-z]-' '[A-Z] '`
+ eval $SOLR_ADMIN_API_CMD "'/admin/collections?action=`echo $COL_ACTION`&name=$3'"
+ shift 3
+ ;;
+ --deletedocs)
+ eval $SOLR_ADMIN_API_CMD "'/$3/update?commit=true'" -H "'Content-Type: text/xml'" "--data-binary '<delete><query>*:*</query></delete>'"
+ shift 3
+ ;;
+ --stat)
+ get_solr_state | sed -ne '/\/collections\//s#^.*/collections/##p' | sed -ne '/election\//s###p' | grep "$3/"
+ shift 3
+ ;;
+ --list)
+ get_solr_state | sed -ne '/\/collections\/[^\/]*$/s#^.*/collections/##p'
+ shift 2
+ ;;
+ *)
+ shift 1
+ ;;
+ esac
+ ;;
+
+ core)
+ [ $# -gt 2 ] || usage "Error: incorrect specification of arguments for $1"
+ case "$2" in
+ --create)
+ CORE_CREATE_NAME="$3"
+ shift 3
+ while test $# -gt 0 ; do
+ case "$1" in
+ -p)
+ [ $# -gt 1 ] || usage "Error: core --create name $1 requires an argument of key=value"
+ CORE_KV_PAIRS="${CORE_KV_PAIRS}&${2}"
+ shift 2
+ ;;
+ *)
+ break
+ ;;
+ esac
+ done
+ [ -n "$CORE_KV_PAIRS" ] || CORE_KV_PAIRS="&instanceDir=${CORE_CREATE_NAME}"
+
+ eval $SOLR_ADMIN_API_CMD "'/admin/cores?action=CREATE&name=${CORE_CREATE_NAME}${CORE_KV_PAIRS}'"
+ ;;
+ --reload|--unload|--status)
+ CORE_ACTION=`echo $2 | tr '[a-z]-' '[A-Z] '`
+ eval $SOLR_ADMIN_API_CMD "'/admin/cores?action=`echo $CORE_ACTION`&core=$3'"
+ shift 3
+ ;;
+ *)
+ shift 1
+ ;;
+ esac
+ ;;
+
+ *)
+ usage "Error: unrecognized command $1"
+ ;;
+ esac
+done
+
+# If none of the above commands ended up calling die -- we're OK
+exit 0
http://git-wip-us.apache.org/repos/asf/bigtop/blob/83a688b3/bigtop-packages/src/deb/solr/solr.install
----------------------------------------------------------------------
diff --git a/bigtop-packages/src/deb/solr/solr.install b/bigtop-packages/src/deb/solr/solr.install
index 5b26a0d..721c3f6 100644
--- a/bigtop-packages/src/deb/solr/solr.install
+++ b/bigtop-packages/src/deb/solr/solr.install
@@ -2,4 +2,4 @@
/etc/default
/usr/lib/solr
/var
-# /usr/bin/solr
+/usr/bin/solrctl