-1.0 [IN PROGRESS]
- - Documentation updates
- - Clean up unused files
+0.10 [IN PROGRESS]
+ - Documentation updates
+ - Clean up unused files
+ - schema/solrconfig updates for Solr 5
+ - Includes Solr 5.5.1
+ - Remove RHEL packaging
+ - Rebuild Debian packaging
0.9 Thu Oct 22 12:35:00 UTC 2015
- Includes SOLR 4.9.1
NAME=masterkey-lui-solr
-VERSION=0.9
-DEBIAN_DIST="jessie squeeze wheezy"
+VERSION=0.10
+DEBIAN_DIST="jessie wheezy"
UBUNTU_DIST=""
--- /dev/null
+#!/usr/bin/env 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.
+
+if [[ $EUID -ne 0 ]]; then
+ echo -e "\nERROR: This script must be run as root\n" 1>&2
+ exit 1
+fi
+
+print_usage() {
+ ERROR_MSG="$1"
+
+ if [ "$ERROR_MSG" != "" ]; then
+ echo -e "\nERROR: $ERROR_MSG\n" 1>&2
+ fi
+
+ echo ""
+ echo "Usage: install_solr_service.sh path_to_solr_distribution_archive OPTIONS"
+ echo ""
+ echo " The first argument to the script must be a path to a Solr distribution archive, such as solr-5.0.0.tgz"
+ echo " (only .tgz or .zip are supported formats for the archive)"
+ echo ""
+ echo " Supported OPTIONS include:"
+ echo ""
+ echo " -d Directory for live / writable Solr files, such as logs, pid files, and index data; defaults to /var/solr"
+ echo ""
+ echo " -i Directory to extract the Solr installation archive; defaults to /opt/"
+ echo " The specified path must exist prior to using this script."
+ echo ""
+ echo " -p Port Solr should bind to; default is 8983"
+ echo ""
+ echo " -s Service name; defaults to solr"
+ echo ""
+ echo " -u User to own the Solr files and run the Solr process as; defaults to solr"
+ echo " This script will create the specified user account if it does not exist."
+ echo ""
+ echo " -f Upgrade Solr. Overwrite symlink and init script of previous installation."
+ echo ""
+ echo " NOTE: Must be run as the root user"
+ echo ""
+} # end print_usage
+
+if [ -f "/proc/version" ]; then
+ proc_version=`cat /proc/version`
+else
+ proc_version=`uname -a`
+fi
+
+if [[ $proc_version == *"Debian"* ]]; then
+ distro=Debian
+elif [[ $proc_version == *"Red Hat"* ]]; then
+ distro=RedHat
+elif [[ $proc_version == *"Ubuntu"* ]]; then
+ distro=Ubuntu
+elif [[ $proc_version == *"SUSE"* ]]; then
+ distro=SUSE
+else
+ echo -e "\nERROR: Your Linux distribution ($proc_version) not supported by this script!\nYou'll need to setup Solr as a service manually using the documentation provided in the Solr Reference Guide.\n" 1>&2
+ exit 1
+fi
+
+if [ -z "$1" ]; then
+ print_usage "Must specify the path to the Solr installation archive, such as solr-5.0.0.tgz"
+ exit 1
+fi
+
+SOLR_ARCHIVE=$1
+if [ ! -f "$SOLR_ARCHIVE" ]; then
+ print_usage "Specified Solr installation archive $SOLR_ARCHIVE not found!"
+ exit 1
+fi
+
+# strip off path info
+SOLR_INSTALL_FILE=${SOLR_ARCHIVE##*/}
+is_tar=true
+if [ ${SOLR_INSTALL_FILE: -4} == ".tgz" ]; then
+ SOLR_DIR=${SOLR_INSTALL_FILE%.tgz}
+elif [ ${SOLR_INSTALL_FILE: -4} == ".zip" ]; then
+ SOLR_DIR=${SOLR_INSTALL_FILE%.zip}
+ is_tar=false
+else
+ print_usage "Solr installation archive $SOLR_ARCHIVE is invalid, expected a .tgz or .zip file!"
+ exit 1
+fi
+
+if [ $# -gt 1 ]; then
+ shift
+ while true; do
+ case $1 in
+ -i)
+ if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
+ print_usage "Directory path is required when using the $1 option!"
+ exit 1
+ fi
+ SOLR_EXTRACT_DIR=$2
+ shift 2
+ ;;
+ -d)
+ if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
+ print_usage "Directory path is required when using the $1 option!"
+ exit 1
+ fi
+ SOLR_VAR_DIR="$2"
+ shift 2
+ ;;
+ -u)
+ if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
+ print_usage "Username is required when using the $1 option!"
+ exit 1
+ fi
+ SOLR_USER="$2"
+ shift 2
+ ;;
+ -s)
+ if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
+ print_usage "Service name is required when using the $1 option!"
+ exit 1
+ fi
+ SOLR_SERVICE="$2"
+ shift 2
+ ;;
+ -p)
+ if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
+ print_usage "Port is required when using the $1 option!"
+ exit 1
+ fi
+ SOLR_PORT="$2"
+ shift 2
+ ;;
+ -f)
+ SOLR_UPGRADE="YES"
+ shift 1
+ ;;
+ -help|-usage)
+ print_usage ""
+ exit 0
+ ;;
+ --)
+ shift
+ break
+ ;;
+ *)
+ if [ "$1" != "" ]; then
+ print_usage "Unrecognized or misplaced argument: $1!"
+ exit 1
+ else
+ break # out-of-args, stop looping
+ fi
+ ;;
+ esac
+ done
+fi
+
+if [ -z "$SOLR_EXTRACT_DIR" ]; then
+ SOLR_EXTRACT_DIR=/opt
+fi
+
+if [ ! -d "$SOLR_EXTRACT_DIR" ]; then
+ print_usage "Installation directory $SOLR_EXTRACT_DIR not found! Please create it before running this script."
+ exit 1
+fi
+
+if [ -z "$SOLR_SERVICE" ]; then
+ SOLR_SERVICE=solr
+fi
+
+if [ -z "$SOLR_VAR_DIR" ]; then
+ SOLR_VAR_DIR="/var/$SOLR_SERVICE"
+fi
+
+if [ -z "$SOLR_USER" ]; then
+ SOLR_USER=solr
+fi
+
+if [ -z "$SOLR_PORT" ]; then
+ SOLR_PORT=8983
+fi
+
+if [ -z "$SOLR_UPGRADE" ]; then
+ SOLR_UPGRADE=NO
+fi
+
+if [ ! "$SOLR_UPGRADE" = "YES" ]; then
+ if [ -f "/etc/init.d/$SOLR_SERVICE" ]; then
+ print_usage "/etc/init.d/$SOLR_SERVICE already exists! Perhaps Solr is already setup as a service on this host? To upgrade Solr use the -f option."
+ exit 1
+ fi
+
+ if [ -e "$SOLR_EXTRACT_DIR/$SOLR_SERVICE" ]; then
+ print_usage "$SOLR_EXTRACT_DIR/$SOLR_SERVICE already exists! Please move this directory / link or choose a different service name using the -s option."
+ exit 1
+ fi
+fi
+
+# stop running instance
+if [ -f "/etc/init.d/$SOLR_SERVICE" ]; then
+ echo -e "\nStopping Solr instance if exists ...\n"
+ service "$SOLR_SERVICE" stop
+fi
+
+# create user if not exists
+solr_uid="`id -u "$SOLR_USER"`"
+if [ $? -ne 0 ]; then
+ echo "Creating new user: $SOLR_USER"
+ if [ "$distro" == "RedHat" ]; then
+ adduser "$SOLR_USER"
+ elif [ "$distro" == "SUSE" ]; then
+ useradd -m "$SOLR_USER"
+ else
+ adduser --system --shell /bin/bash --group --disabled-password --home "$SOLR_VAR_DIR" "$SOLR_USER"
+ fi
+fi
+
+# extract
+SOLR_INSTALL_DIR="$SOLR_EXTRACT_DIR/$SOLR_DIR"
+if [ ! -d "$SOLR_INSTALL_DIR" ]; then
+
+ echo -e "\nExtracting $SOLR_ARCHIVE to $SOLR_EXTRACT_DIR\n"
+
+ if $is_tar ; then
+ tar zxf "$SOLR_ARCHIVE" -C "$SOLR_EXTRACT_DIR"
+ else
+ unzip -q "$SOLR_ARCHIVE" -d "$SOLR_EXTRACT_DIR"
+ fi
+
+ if [ ! -d "$SOLR_INSTALL_DIR" ]; then
+ echo -e "\nERROR: Expected directory $SOLR_INSTALL_DIR not found after extracting $SOLR_ARCHIVE ... script fails.\n" 1>&2
+ exit 1
+ fi
+
+ chown -R root: "$SOLR_INSTALL_DIR"
+ find "$SOLR_INSTALL_DIR" -type d -print0 | xargs -0 chmod 0755
+ find "$SOLR_INSTALL_DIR" -type f -print0 | xargs -0 chmod 0644
+ chmod -R 0755 "$SOLR_INSTALL_DIR/bin"
+else
+ echo -e "\nWARNING: $SOLR_INSTALL_DIR already exists! Skipping extract ...\n"
+fi
+
+# create a symlink for easier scripting
+if [ -h "$SOLR_EXTRACT_DIR/$SOLR_SERVICE" ]; then
+ echo -e "\nRemoving old symlink $SOLR_EXTRACT_DIR/$SOLR_SERVICE ...\n"
+ rm "$SOLR_EXTRACT_DIR/$SOLR_SERVICE"
+fi
+if [ -e "$SOLR_EXTRACT_DIR/$SOLR_SERVICE" ]; then
+ echo -e "\nWARNING: $SOLR_EXTRACT_DIR/$SOLR_SERVICE is not symlink! Skipping symlink update ...\n"
+else
+ echo -e "\nInstalling symlink $SOLR_EXTRACT_DIR/$SOLR_SERVICE -> $SOLR_INSTALL_DIR ...\n"
+ ln -s "$SOLR_INSTALL_DIR" "$SOLR_EXTRACT_DIR/$SOLR_SERVICE"
+fi
+
+# install init.d script
+echo -e "\nInstalling /etc/init.d/$SOLR_SERVICE script ...\n"
+cp "$SOLR_INSTALL_DIR/bin/init.d/solr" "/etc/init.d/$SOLR_SERVICE"
+chmod 0744 "/etc/init.d/$SOLR_SERVICE"
+chown root: "/etc/init.d/$SOLR_SERVICE"
+# do some basic variable substitution on the init.d script
+sed_expr1="s#SOLR_INSTALL_DIR=.*#SOLR_INSTALL_DIR=\"$SOLR_EXTRACT_DIR/$SOLR_SERVICE\"#"
+sed_expr2="s#SOLR_ENV=.*#SOLR_ENV=\"/etc/default/$SOLR_SERVICE.in.sh\"#"
+sed_expr3="s#RUNAS=.*#RUNAS=\"$SOLR_USER\"#"
+sed_expr4="s#Provides:.*#Provides: $SOLR_SERVICE#"
+sed -i -e "$sed_expr1" -e "$sed_expr2" -e "$sed_expr3" -e "$sed_expr4" "/etc/init.d/$SOLR_SERVICE"
+
+# install/move configuration
+if [ ! -d /etc/default ]; then
+ mkdir /etc/default
+ chown root: /etc/default
+ chmod 0755 /etc/default
+fi
+if [ -f "$SOLR_VAR_DIR/solr.in.sh" ]; then
+ echo -e "\nMoving existing $SOLR_VAR_DIR/solr.in.sh to /etc/default/$SOLR_SERVICE.in.sh ...\n"
+ mv "$SOLR_VAR_DIR/solr.in.sh" "/etc/default/$SOLR_SERVICE.in.sh"
+elif [ -f "/etc/default/$SOLR_SERVICE.in.sh" ]; then
+ echo -e "\n/etc/default/$SOLR_SERVICE.in.sh already exist. Skipping install ...\n"
+else
+ echo -e "\nInstalling /etc/default/$SOLR_SERVICE.in.sh ...\n"
+ cp "$SOLR_INSTALL_DIR/bin/solr.in.sh" "/etc/default/$SOLR_SERVICE.in.sh"
+ echo "SOLR_PID_DIR=\"$SOLR_VAR_DIR\"
+SOLR_HOME=\"$SOLR_VAR_DIR/data\"
+LOG4J_PROPS=\"$SOLR_VAR_DIR/log4j.properties\"
+SOLR_LOGS_DIR=\"$SOLR_VAR_DIR/logs\"
+SOLR_PORT=\"$SOLR_PORT\"
+" >> "/etc/default/$SOLR_SERVICE.in.sh"
+fi
+chown root: "/etc/default/$SOLR_SERVICE.in.sh"
+chmod 0644 "/etc/default/$SOLR_SERVICE.in.sh"
+
+# install data directories and files
+mkdir -p "$SOLR_VAR_DIR/data"
+mkdir -p "$SOLR_VAR_DIR/logs"
+if [ -f "$SOLR_VAR_DIR/data/solr.xml" ]; then
+ echo -e "\n$SOLR_VAR_DIR/data/solr.xml already exists. Skipping install ...\n"
+else
+ cp "$SOLR_INSTALL_DIR/server/solr/solr.xml" "$SOLR_VAR_DIR/data/solr.xml"
+fi
+if [ -f "$SOLR_VAR_DIR/log4j.properties" ]; then
+ echo -e "\n$SOLR_VAR_DIR/log4j.properties already exists. Skipping install ...\n"
+else
+ cp "$SOLR_INSTALL_DIR/server/resources/log4j.properties" "$SOLR_VAR_DIR/log4j.properties"
+ sed_expr="s#solr.log=.*#solr.log=\${solr.solr.home}/../logs#"
+ sed -i -e "$sed_expr" "$SOLR_VAR_DIR/log4j.properties"
+fi
+chown -R "$SOLR_USER:" "$SOLR_VAR_DIR"
+find "$SOLR_VAR_DIR" -type d -print0 | xargs -0 chmod 0750
+find "$SOLR_VAR_DIR" -type f -print0 | xargs -0 chmod 0640
+
+# configure autostart of service
+if [[ "$distro" == "RedHat" || "$distro" == "SUSE" ]]; then
+ chkconfig "$SOLR_SERVICE" on
+else
+ update-rc.d "$SOLR_SERVICE" defaults
+fi
+
+# start service
+service "$SOLR_SERVICE" start
+sleep 5
+service "$SOLR_SERVICE" status
+
+echo "Service $SOLR_SERVICE installed."
+++ /dev/null
-#! /bin/sh
-#
-# skeleton example file to build /etc/init.d/ scripts.
-# This file should be used to construct scripts for /etc/init.d.
-#
-# Written by Miquel van Smoorenburg <miquels@cistron.nl>.
-# Modified for Debian GNU/Linux
-# by Ian Murdock <imurdock@gnu.ai.mit.edu>.
-#
-# Version: @(#)skeleton 1.8 03-Mar-1998 miquels@cistron.nl
-
-### BEGIN INIT INFO
-# Provides: indexdata-solr
-# Required-Start: $network
-# Required-Stop: $network
-# Should-Start:
-# Default-Start: 2 3 4 5
-# Default-Stop: 0 1 6
-# Short-Description: Indexdata Cloud Solr (Solr with Zookeeper)
-# Description: startes the services on port xxxx
-### END INIT INFO
-#
-
-PATH=/usr/bin
-DAEMON=/usr/share/masterkey/lui/solr4/zookeeper/zookeeper.sh
-SERVICES=""
-DESC="Index Data Services (SOLR Zookeeper)"
-NAME=indexdata-solr-zookeeper
-DEFAULT=/etc/default/indexdata-solr-zookeeper
-if [ -f "$DEFAULT" ] ; then
- . $DEFAULT
-fi
-
-# test -d $SERVICES || exit 0
-
-set -e
-
-case "$1" in
- start)
- for SERVICE in $SERVICES ; do
- if [ -d "$SERVICE" ] ; then
- echo "starting $SERVICE"
- cd $SERVICE
- $DAEMON $1
- else
- echo "No directory at $SERVICE"
- fi
- done
- ;;
- stop)
- for SERVICE in $SERVICES ; do
- if [ -d "$SERVICE" ] ; then
- echo "Stopping $SERVICE"
- cd $SERVICE
- $DAEMON stop
- else
- echo "No directory at $SERVICE"
- fi
- done
- ;;
- status)
- for SERVICE in $SERVICES ; do
- if [ -d "$SERVICE" ] ; then
- echo "checking $SERVICE"
- cd $SERVICE
- $DAEMON status
- else
- echo "No directory at $SERVICE"
- fi
- done
- ;;
- #reload)
- #
- # If the daemon can reload its config files on the fly
- # for example by sending it SIGHUP, do it here.
- #
- # If the daemon responds to changes in its config file
- # directly anyway, make this a do-nothing entry.
- #
- # echo "Reloading $DESC configuration files."
- # start-stop-daemon --stop --signal 1 --quiet --pidfile \
- # /var/run/$NAME.pid --exec $DAEMON
- #;;
- restart|force-reload)
- #
- # If the "reload" option is implemented, move the "force-reload"
- # option to the "reload" entry above. If not, "force-reload" is
- # just the same as "restart".
- #
- echo "Restarting $DESC: "
- for srv in $SERVICES ; do
- $srv restart
- done
- ;;
- *)
- N=/etc/init.d/$NAME
- # echo "Usage: $N {start|stop|restart|reload|force-reload}" >&2
- echo "Usage: $N {start|stop|restart|force-reload}" >&2
- exit 1
- ;;
-esac
-
-exit 0
+++ /dev/null
-<?xml version="1.0"?>
-<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
- xmlns:pz="http://www.indexdata.com/pazpar2/1.0" >
- <xsl:template match="/">
- <add>
- <xsl:apply-templates></xsl:apply-templates>
- </add>
- </xsl:template>
-
- <xsl:template match="pz:record">
- <doc>
- <xsl:apply-templates></xsl:apply-templates>
- </doc>
- </xsl:template>
- <xsl:template match="pz:metadata">
- <xsl:if test="@type">
- <field>
- <xsl:attribute name="name">
- <xsl:value-of select="@type"/>
- </xsl:attribute>
- <xsl:value-of select="."/>
- </field>
- </xsl:if>
- </xsl:template>
-</xsl:stylesheet>
+++ /dev/null
-<?xml version="1.0" encoding="utf-8"?>
-<Context
- docBase="../solr-4.6.0.war"
->
- <Environment name="solr/home" type="java.lang.String" value="lui-solr4" override="true"/>
-</Context>
+++ /dev/null
-<?xml version="1.0" encoding="utf-8"?>
-<!-- Version 0.6.2. Adding comment to force config update -->
-<Context
- docBase="/usr/share/masterkey/lui/solr4/war/solr.war"
- path="/solr4"
->
- <Environment name="solr/home" type="java.lang.String" value="/usr/share/masterkey/lui/solr4/master" override="true"/>
-</Context>
+++ /dev/null
-<?xml version="1.0" encoding="utf-8"?>
-<!-- Version 0.6.2. Adding comment to force check -->
-<Context
- docBase="/usr/share/masterkey/lui/solr4/war/solr.war"
- path="/solr4-slave"
->
- <Environment name="solr/home" type="java.lang.String" value="/usr/share/masterkey/lui/solr4/slave" override="true"/>
-</Context>
+++ /dev/null
-#!/usr/bin/env 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.
-
-if [[ $EUID -ne 0 ]]; then
- echo -e "\nERROR: This script must be run as root\n" 1>&2
- exit 1
-fi
-
-print_usage() {
- ERROR_MSG="$1"
-
- if [ "$ERROR_MSG" != "" ]; then
- echo -e "\nERROR: $ERROR_MSG\n" 1>&2
- fi
-
- echo ""
- echo "Usage: install_solr_service.sh path_to_solr_distribution_archive OPTIONS"
- echo ""
- echo " The first argument to the script must be a path to a Solr distribution archive, such as solr-5.0.0.tgz"
- echo " (only .tgz or .zip are supported formats for the archive)"
- echo ""
- echo " Supported OPTIONS include:"
- echo ""
- echo " -d Directory for live / writable Solr files, such as logs, pid files, and index data; defaults to /var/solr"
- echo ""
- echo " -i Directory to extract the Solr installation archive; defaults to /opt/"
- echo " The specified path must exist prior to using this script."
- echo ""
- echo " -p Port Solr should bind to; default is 8983"
- echo ""
- echo " -s Service name; defaults to solr"
- echo ""
- echo " -u User to own the Solr files and run the Solr process as; defaults to solr"
- echo " This script will create the specified user account if it does not exist."
- echo ""
- echo " -f Upgrade Solr. Overwrite symlink and init script of previous installation."
- echo ""
- echo " NOTE: Must be run as the root user"
- echo ""
-} # end print_usage
-
-if [ -f "/proc/version" ]; then
- proc_version=`cat /proc/version`
-else
- proc_version=`uname -a`
-fi
-
-if [[ $proc_version == *"Debian"* ]]; then
- distro=Debian
-elif [[ $proc_version == *"Red Hat"* ]]; then
- distro=RedHat
-elif [[ $proc_version == *"Ubuntu"* ]]; then
- distro=Ubuntu
-elif [[ $proc_version == *"SUSE"* ]]; then
- distro=SUSE
-else
- echo -e "\nERROR: Your Linux distribution ($proc_version) not supported by this script!\nYou'll need to setup Solr as a service manually using the documentation provided in the Solr Reference Guide.\n" 1>&2
- exit 1
-fi
-
-if [ -z "$1" ]; then
- print_usage "Must specify the path to the Solr installation archive, such as solr-5.0.0.tgz"
- exit 1
-fi
-
-SOLR_ARCHIVE=$1
-if [ ! -f "$SOLR_ARCHIVE" ]; then
- print_usage "Specified Solr installation archive $SOLR_ARCHIVE not found!"
- exit 1
-fi
-
-# strip off path info
-SOLR_INSTALL_FILE=${SOLR_ARCHIVE##*/}
-is_tar=true
-if [ ${SOLR_INSTALL_FILE: -4} == ".tgz" ]; then
- SOLR_DIR=${SOLR_INSTALL_FILE%.tgz}
-elif [ ${SOLR_INSTALL_FILE: -4} == ".zip" ]; then
- SOLR_DIR=${SOLR_INSTALL_FILE%.zip}
- is_tar=false
-else
- print_usage "Solr installation archive $SOLR_ARCHIVE is invalid, expected a .tgz or .zip file!"
- exit 1
-fi
-
-if [ $# -gt 1 ]; then
- shift
- while true; do
- case $1 in
- -i)
- if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
- print_usage "Directory path is required when using the $1 option!"
- exit 1
- fi
- SOLR_EXTRACT_DIR=$2
- shift 2
- ;;
- -d)
- if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
- print_usage "Directory path is required when using the $1 option!"
- exit 1
- fi
- SOLR_VAR_DIR="$2"
- shift 2
- ;;
- -u)
- if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
- print_usage "Username is required when using the $1 option!"
- exit 1
- fi
- SOLR_USER="$2"
- shift 2
- ;;
- -s)
- if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
- print_usage "Service name is required when using the $1 option!"
- exit 1
- fi
- SOLR_SERVICE="$2"
- shift 2
- ;;
- -p)
- if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
- print_usage "Port is required when using the $1 option!"
- exit 1
- fi
- SOLR_PORT="$2"
- shift 2
- ;;
- -f)
- SOLR_UPGRADE="YES"
- shift 1
- ;;
- -help|-usage)
- print_usage ""
- exit 0
- ;;
- --)
- shift
- break
- ;;
- *)
- if [ "$1" != "" ]; then
- print_usage "Unrecognized or misplaced argument: $1!"
- exit 1
- else
- break # out-of-args, stop looping
- fi
- ;;
- esac
- done
-fi
-
-if [ -z "$SOLR_EXTRACT_DIR" ]; then
- SOLR_EXTRACT_DIR=/opt
-fi
-
-if [ ! -d "$SOLR_EXTRACT_DIR" ]; then
- print_usage "Installation directory $SOLR_EXTRACT_DIR not found! Please create it before running this script."
- exit 1
-fi
-
-if [ -z "$SOLR_SERVICE" ]; then
- SOLR_SERVICE=solr
-fi
-
-if [ -z "$SOLR_VAR_DIR" ]; then
- SOLR_VAR_DIR="/var/$SOLR_SERVICE"
-fi
-
-if [ -z "$SOLR_USER" ]; then
- SOLR_USER=solr
-fi
-
-if [ -z "$SOLR_PORT" ]; then
- SOLR_PORT=8983
-fi
-
-if [ -z "$SOLR_UPGRADE" ]; then
- SOLR_UPGRADE=NO
-fi
-
-if [ ! "$SOLR_UPGRADE" = "YES" ]; then
- if [ -f "/etc/init.d/$SOLR_SERVICE" ]; then
- print_usage "/etc/init.d/$SOLR_SERVICE already exists! Perhaps Solr is already setup as a service on this host? To upgrade Solr use the -f option."
- exit 1
- fi
-
- if [ -e "$SOLR_EXTRACT_DIR/$SOLR_SERVICE" ]; then
- print_usage "$SOLR_EXTRACT_DIR/$SOLR_SERVICE already exists! Please move this directory / link or choose a different service name using the -s option."
- exit 1
- fi
-fi
-
-# stop running instance
-if [ -f "/etc/init.d/$SOLR_SERVICE" ]; then
- echo -e "\nStopping Solr instance if exists ...\n"
- service "$SOLR_SERVICE" stop
-fi
-
-# create user if not exists
-solr_uid="`id -u "$SOLR_USER"`"
-if [ $? -ne 0 ]; then
- echo "Creating new user: $SOLR_USER"
- if [ "$distro" == "RedHat" ]; then
- adduser "$SOLR_USER"
- elif [ "$distro" == "SUSE" ]; then
- useradd -m "$SOLR_USER"
- else
- adduser --system --shell /bin/bash --group --disabled-password --home "$SOLR_VAR_DIR" "$SOLR_USER"
- fi
-fi
-
-# extract
-SOLR_INSTALL_DIR="$SOLR_EXTRACT_DIR/$SOLR_DIR"
-if [ ! -d "$SOLR_INSTALL_DIR" ]; then
-
- echo -e "\nExtracting $SOLR_ARCHIVE to $SOLR_EXTRACT_DIR\n"
-
- if $is_tar ; then
- tar zxf "$SOLR_ARCHIVE" -C "$SOLR_EXTRACT_DIR"
- else
- unzip -q "$SOLR_ARCHIVE" -d "$SOLR_EXTRACT_DIR"
- fi
-
- if [ ! -d "$SOLR_INSTALL_DIR" ]; then
- echo -e "\nERROR: Expected directory $SOLR_INSTALL_DIR not found after extracting $SOLR_ARCHIVE ... script fails.\n" 1>&2
- exit 1
- fi
-
- chown -R root: "$SOLR_INSTALL_DIR"
- find "$SOLR_INSTALL_DIR" -type d -print0 | xargs -0 chmod 0755
- find "$SOLR_INSTALL_DIR" -type f -print0 | xargs -0 chmod 0644
- chmod -R 0755 "$SOLR_INSTALL_DIR/bin"
-else
- echo -e "\nWARNING: $SOLR_INSTALL_DIR already exists! Skipping extract ...\n"
-fi
-
-# create a symlink for easier scripting
-if [ -h "$SOLR_EXTRACT_DIR/$SOLR_SERVICE" ]; then
- echo -e "\nRemoving old symlink $SOLR_EXTRACT_DIR/$SOLR_SERVICE ...\n"
- rm "$SOLR_EXTRACT_DIR/$SOLR_SERVICE"
-fi
-if [ -e "$SOLR_EXTRACT_DIR/$SOLR_SERVICE" ]; then
- echo -e "\nWARNING: $SOLR_EXTRACT_DIR/$SOLR_SERVICE is not symlink! Skipping symlink update ...\n"
-else
- echo -e "\nInstalling symlink $SOLR_EXTRACT_DIR/$SOLR_SERVICE -> $SOLR_INSTALL_DIR ...\n"
- ln -s "$SOLR_INSTALL_DIR" "$SOLR_EXTRACT_DIR/$SOLR_SERVICE"
-fi
-
-# install init.d script
-echo -e "\nInstalling /etc/init.d/$SOLR_SERVICE script ...\n"
-cp "$SOLR_INSTALL_DIR/bin/init.d/solr" "/etc/init.d/$SOLR_SERVICE"
-chmod 0744 "/etc/init.d/$SOLR_SERVICE"
-chown root: "/etc/init.d/$SOLR_SERVICE"
-# do some basic variable substitution on the init.d script
-sed_expr1="s#SOLR_INSTALL_DIR=.*#SOLR_INSTALL_DIR=\"$SOLR_EXTRACT_DIR/$SOLR_SERVICE\"#"
-sed_expr2="s#SOLR_ENV=.*#SOLR_ENV=\"/etc/default/$SOLR_SERVICE.in.sh\"#"
-sed_expr3="s#RUNAS=.*#RUNAS=\"$SOLR_USER\"#"
-sed_expr4="s#Provides:.*#Provides: $SOLR_SERVICE#"
-sed -i -e "$sed_expr1" -e "$sed_expr2" -e "$sed_expr3" -e "$sed_expr4" "/etc/init.d/$SOLR_SERVICE"
-
-# install/move configuration
-if [ ! -d /etc/default ]; then
- mkdir /etc/default
- chown root: /etc/default
- chmod 0755 /etc/default
-fi
-if [ -f "$SOLR_VAR_DIR/solr.in.sh" ]; then
- echo -e "\nMoving existing $SOLR_VAR_DIR/solr.in.sh to /etc/default/$SOLR_SERVICE.in.sh ...\n"
- mv "$SOLR_VAR_DIR/solr.in.sh" "/etc/default/$SOLR_SERVICE.in.sh"
-elif [ -f "/etc/default/$SOLR_SERVICE.in.sh" ]; then
- echo -e "\n/etc/default/$SOLR_SERVICE.in.sh already exist. Skipping install ...\n"
-else
- echo -e "\nInstalling /etc/default/$SOLR_SERVICE.in.sh ...\n"
- cp "$SOLR_INSTALL_DIR/bin/solr.in.sh" "/etc/default/$SOLR_SERVICE.in.sh"
- echo "SOLR_PID_DIR=\"$SOLR_VAR_DIR\"
-SOLR_HOME=\"$SOLR_VAR_DIR/data\"
-LOG4J_PROPS=\"$SOLR_VAR_DIR/log4j.properties\"
-SOLR_LOGS_DIR=\"$SOLR_VAR_DIR/logs\"
-SOLR_PORT=\"$SOLR_PORT\"
-" >> "/etc/default/$SOLR_SERVICE.in.sh"
-fi
-chown root: "/etc/default/$SOLR_SERVICE.in.sh"
-chmod 0644 "/etc/default/$SOLR_SERVICE.in.sh"
-
-# install data directories and files
-mkdir -p "$SOLR_VAR_DIR/data"
-mkdir -p "$SOLR_VAR_DIR/logs"
-if [ -f "$SOLR_VAR_DIR/data/solr.xml" ]; then
- echo -e "\n$SOLR_VAR_DIR/data/solr.xml already exists. Skipping install ...\n"
-else
- cp "$SOLR_INSTALL_DIR/server/solr/solr.xml" "$SOLR_VAR_DIR/data/solr.xml"
-fi
-if [ -f "$SOLR_VAR_DIR/log4j.properties" ]; then
- echo -e "\n$SOLR_VAR_DIR/log4j.properties already exists. Skipping install ...\n"
-else
- cp "$SOLR_INSTALL_DIR/server/resources/log4j.properties" "$SOLR_VAR_DIR/log4j.properties"
- sed_expr="s#solr.log=.*#solr.log=\${solr.solr.home}/../logs#"
- sed -i -e "$sed_expr" "$SOLR_VAR_DIR/log4j.properties"
-fi
-chown -R "$SOLR_USER:" "$SOLR_VAR_DIR"
-find "$SOLR_VAR_DIR" -type d -print0 | xargs -0 chmod 0750
-find "$SOLR_VAR_DIR" -type f -print0 | xargs -0 chmod 0640
-
-# configure autostart of service
-if [[ "$distro" == "RedHat" || "$distro" == "SUSE" ]]; then
- chkconfig "$SOLR_SERVICE" on
-else
- update-rc.d "$SOLR_SERVICE" defaults
-fi
-
-# start service
-service "$SOLR_SERVICE" start
-sleep 5
-service "$SOLR_SERVICE" status
-
-echo "Service $SOLR_SERVICE installed."
+++ /dev/null
-# Logging level
-log4j.rootLogger=INFO, file, CONSOLE
-
-log4j.appender.CONSOLE=org.apache.log4j.ConsoleAppender
-
-log4j.appender.CONSOLE.layout=org.apache.log4j.PatternLayout
-log4j.appender.CONSOLE.layout.ConversionPattern=%-4r [%t] %-5p %c %x \u2013 %m%n
-
-#- size rotation with log cleanup.
-log4j.appender.file=org.apache.log4j.RollingFileAppender
-log4j.appender.file.MaxFileSize=4MB
-log4j.appender.file.MaxBackupIndex=9
-
-#- File to log to and log format
-log4j.appender.file.File=logs/solr.log
-log4j.appender.file.layout=org.apache.log4j.PatternLayout
-log4j.appender.file.layout.ConversionPattern=%-5p - %d{yyyy-MM-dd HH:mm:ss.SSS}; %C; %m\n
-
-log4j.logger.org.apache.zookeeper=WARN
\ No newline at end of file
+++ /dev/null
-Summary: Local Unified Index (Solr)
-Name: masterkey-lui-solr
-Version: 0.3.0
-Release: 1.indexdata
-License: IndexData
-Group: Applications/Internet
-Vendor: Index Data ApS <info@indexdata.dk>
-Source: masterkey-lui-solr-%{version}.tar.gz
-BuildArch: noarch
-BuildRoot: %{_tmppath}/%{name}-%{version}-root
-Packager: Dennis Schafroth <dennis@indexdata.com>
-URL: http://www.indexdata.dk/masterkey
-
-%description
-The Local Unified Index is a index that contains multiple logical indexes. The underlying index is a Solr/lucene index configured to use a specific LUI schema.
-
-%package -n masterkey-lui-solr-tomcat
-Summary: Local Unified Index Solr Tomcat
-Requires: masterkey-lui-solr
-Group: Applications/Internet
-
-%package -n masterkey-lui-solr-tomcat6
-Summary: Local Unified Index Solr Tomcat 6 integration
-Requires: tomcat6 masterkey-lui-solr-tomcat
-Group: Applications/Internet
-
-#%description -n masterkey-lui-solr-initd
-#The LUI is the stand-alone Solr/Lucene Index with the LUI schema
-
-%description -n masterkey-lui-solr-tomcat
-The LUI Tomcat is part of the MasterKey suite. This package provides the LUI Tomcat context
-
-%description -n masterkey-lui-solr-tomcat6
-The LUI is part of the MasterKey suite. This package provides Tomcat 6 integration.
-
-%prep
-%setup
-%build
-
-%install
-mkdir -p ${RPM_BUILD_ROOT}/%{_datadir}/masterkey/lui/solr/war
-cp -a dist/* ${RPM_BUILD_ROOT}/%{_datadir}/masterkey/lui/solr/war
-mkdir -p ${RPM_BUILD_ROOT}/%{_datadir}/masterkey/lui/solr/conf
-cp -a solr-conf/* ${RPM_BUILD_ROOT}/%{_datadir}/masterkey/lui/solr/conf
-
-mkdir -p ${RPM_BUILD_ROOT}/%{_sysconfdir}/masterkey/lui/solr
-# cp -a etc/harvester.properties ${RPM_BUILD_ROOT}/%{_sysconfdir}/masterkey/lui/solr
-
-#mkdir -p ${RPM_BUILD_ROOT}/%{_localstatedir}/log/masterkey/lui/solr
-mkdir -p ${RPM_BUILD_ROOT}/%{_localstatedir}/lib/masterkey/lui/solr/data
-
-#tomcat context
-sed -e 's@docBase=".*"@docBase="%{_datadir}\/masterkey\/lui\/solr\/war\/apache-solr-3.3.0.war"@g' etc/solr-tomcat-context.xml > ${RPM_BUILD_ROOT}/%{_sysconfdir}/masterkey/lui/solr/lui-solr-context.xml
-
-# Solr config
-sed -e 's@${solr.data.dir:.*}@${solr.data.dir:%{_localstatedir}\/lib\/masterkey\/lui\/solr\/data}@g' solr-conf/solrconfig.xml > ${RPM_BUILD_ROOT}/%{_datadir}/masterkey/lui/solr/conf/solrconfig.xml
-
-%clean
-rm -fr ${RPM_BUILD_ROOT}
-
-%post -n masterkey-lui-solr-tomcat6
-ln -sf %{_sysconfdir}/masterkey/lui/solr/lui-solr-context.xml %{_sysconfdir}/tomcat6/Catalina/localhost/lui-solr.xml
-
-%postun -n masterkey-lui-solr-tomcat6
-if [ $1 = 0 ]; then
- rm -rf %{_sysconfdir}/tomcat6/Catalina/localhost/lui-solr.xml
-fi
-
-%files
-%defattr(755,tomcat,tomcat)
-%{_datadir}/masterkey/lui/solr
-%{_localstatedir}/lib/masterkey/lui/solr
-%{_localstatedir}/lib/masterkey/lui/solr/data
-%attr(755,tomcat,tomcat) %dir %{_localstatedir}/lib/masterkey/lui/solr
-
-%files -n masterkey-lui-solr-tomcat
-%defattr(-,root,root)
-%config %{_sysconfdir}/masterkey/lui/solr/lui-solr-context.xml
-
-%files -n masterkey-lui-solr-tomcat6
+++ /dev/null
-#!/bin/bash
-HOST_PORT=localhost:8080
-
-if [ "$2" != "" ] ; then
- HOST_PORT="$2"
-fi
-
-SOLR_PATH=solr4
-if [ "$2" != "" ] ; then
- SOLR_PATH="$2"
-fi
-
-if [ "$1" == "-h" ] ; then
- echo "$0 [[HOST:PORT] SOLR_PATH] (default $HOST_PORT/$SOLR_PATH)"
-fi
-
-curl http://$HOST:$PORT/$SOLR_PATH/update -H "Content-Type: text/xml" --data-binary '<commit waitFlush="false" waitSearcher="false" expungeDeletes="true"/>'
\ No newline at end of file
+++ /dev/null
-#!/bin/bash
-
-HOST_PORT="localhost:8080"
-
-if [ "$2" != "" ] ; then
- HOST_PORT="$2"
-fi
-
-SOLR_PATH=solr4
-if [ "$3" != "" ] ; then
- SOLR_PATH="$3"
-fi
-
-if [ "$1" == "" ] ; then
- echo "$0 databaseid [[HOST:PORT] PATH] (default $HOST_PORT/$PATH)"
- exit 1 ;
-fi
-
-curl http://${HOST_PORT}/$SOLR_PATH/update -H "Content-Type: text/xml" --data-binary "<delete><query>database:$1</query></delete>"
-curl http://${HOST_PORT}/$SOLR_PATH/update -H "Content-Type: text/xml" --data-binary '<commit waitFlush="false" waitSearcher="false"/>'
+++ /dev/null
-#!/bin/bash
-
-INSTALL_PATH=`pwd`
-CONFIG=$1
-mkdir -p ${CONFIG}
-ln -s ${INSTALL_PATH}/etc ${CONFIG}/
-ln -s ${INSTALL_PATH}/contexts ${CONFIG}/
-ln -s ${INSTALL_PATH}/lib ${CONFIG}/
-ln -s ${INSTALL_PATH}/webapps ${CONFIG}/
-ln -s ${INSTALL_PATH}/resources ${CONFIG}/
-ln -s ${INSTALL_PATH}/start.jar ${CONFIG}/
-ln -s ${INSTALL_PATH}/zookeeper.sh ${CONFIG}/
-cp -rp ${INSTALL_PATH}/solr ${CONFIG}/
-mkdir -p ${CONFIG}/logs
\ No newline at end of file
+++ /dev/null
-#!/bin/bash
-
-HOST_PORT=localhost:8080
-
-if [ "$2" != "" ] ; then
- HOST_PORT="$2"
-fi
-
-SOLR_PATH=solr4
-if [ "$3" != "" ] ; then
- SOLR_PATH="$3"
-fi
-
-if [ "$1" != "YES" ] ; then
- echo "$0 YES [[HOST:PORT] SOLR_PATH] (default $HOST_PORT/$SOLR_PATH)"
- exit 1 ;
-fi
-
-
-curl http://${HOST_PORT}/$SOLR_PATH/update -H "Content-Type: text/xml" --data-binary '<optimize waitSearcher="false" expungeDeletes="true" />'
+++ /dev/null
-#!/bin/bash
-
-NAME="indexdata-lui-solr-zookeeper"
-HOST=localhost
-PORT=8983
-SHARDS=2
-PID_FILE=/var/run/${NAME}.pid
-LOG_FILE=/var/log/${NAME}.log
-ZOOKEEPER=yes
-OPTIONS=${OPTIONS:-options}
-
-if [ -f "$OPTIONS" ]; then
- source $OPTIONS
-else
- echo "No options file ($OPTIONS). Using defaults."
-fi
-let ZKPORT=$PORT+1000
-if [ "$ZKHOSTS" == "" ] ; then
- ZKHOSTS=${HOST}:${ZKPORT}
-fi
-
-if [ "$BOOTSTRAP_CONF" != "" ] ; then
- BOOTSTRAP_OPT="-Dbootstrap_confdir=$BOOTSTRAP_CONF"
-fi
-if [ "$PORT" == "" ] ; then
- echo Port missing
-
-fi
-if [ "$ZKHOSTS" == "" ] ; then
- echo ZKHOSTS missing
-fi
-if [ "$SHARDS" == "" ] ; then
- echo SHARDS missing
-fi
-if [ "$ZOOKEEPER" == "yes" ] ; then
- ZKRUN="-DzkRun -DnumShards=${SHARDS}"
-fi
-if [ "${SOLR_HOME}" != "" ] ; then
- SOLR_HOME_OPT="-Dsolr.solr.home=${SOLR_HOME}"
-fi
-
-OPTIONS=" $SOLR_HOME_OPT -Djetty.port=$PORT ${BOOTSTRAP_OPT} -Dcollection.configName=$NAME ${ZKRUN} -DzkHost=${ZKHOSTS} "
-if [ "$1" == "start" ]; then
- if [ -f "${PID_FILE}" ] ; then
- echo "pid file ${PID_FILE} exists. Already running?"
- else
- java $OPTIONS -jar start.jar > $LOG_FILE &
- echo $! > ${PID_FILE}
- fi
-elif [ "$1" == "stop" ]; then
- if [ -f "${PID_FILE}" ] ; then
- PID="`/bin/cat ${PID_FILE}`"
- if [ "$PID" != "" ] ; then
- kill $PID
- /bin/rm ${PID_FILE}
- else
- echo "Unable to extract PID from ${PID_FILE}"
- fi
- else
- echo "No pid file ($PID_FILE) found"
- fi
-else
- echo "$0 [start|stop|status]"
-fi
+++ /dev/null
-*.log
-*.pid
-logs/
-solr/zoo_data
-solr-webapp/
\ No newline at end of file
+++ /dev/null
-# 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 example
-------------
-
-This directory contains an instance of the Jetty Servlet container setup to
-run Solr using an example configuration.
-
-To run this example:
-
- java -jar start.jar
-
-in this example directory, and when Solr is started connect to
-
- http://localhost:8983/solr/
-
-To add documents to the index, use the post.jar (or post.sh script) in
-the example/exampledocs subdirectory (while Solr is running), for example:
-
- cd exampledocs
- java -jar post.jar *.xml
-Or: sh post.sh *.xml
-
-For more information about this example please read...
-
- * example/solr/README.txt
- For more information about the "Solr Home" and Solr specific configuration
- * http://lucene.apache.org/solr/tutorial.html
- For a Tutorial using this example configuration
- * http://wiki.apache.org/solr/SolrResources
- For a list of other tutorials and introductory articles.
-
-Notes About These Examples
---------------------------
-
-* SolrHome *
-
-By default, start.jar starts Solr in Jetty using the default Solr Home
-directory of "./solr/" (relative to the working directory of hte servlet
-container). To run other example configurations, you can specify the
-solr.solr.home system property when starting jetty...
-
- java -Dsolr.solr.home=multicore -jar start.jar
- java -Dsolr.solr.home=example-DIH/solr -jar start.jar
-
-* References to Jar Files Outside This Directory *
-
-Various example SolrHome dirs contained in this directory may use "<lib>"
-statements in the solrconfig.xml file to reference plugin jars outside of
-this directory for loading "contrib" plugins via relative paths.
-
-If you make a copy of this example server and wish to use the
-ExtractingRequestHandler (SolrCell), DataImportHandler (DIH), UIMA, the
-clustering component, or any other modules in "contrib", you will need to
-copy the required jars or update the paths to those jars in your
-solrconfig.xml.
-
-* Logging *
-
-By default, Jetty & Solr will log to the console a logs/solr.log. This can be convenient when
-first getting started, but eventually you will want to log just to a file. To
-configure logging, edit the log4j.properties file in "resources".
-
-It is also possible to setup log4j or other popular logging frameworks.
-
+++ /dev/null
-# Logging level
-log4j.rootLogger=INFO, stderr
-
-# log to stderr
-log4j.appender.stderr = org.apache.log4j.ConsoleAppender
-log4j.appender.stderr.Target = System.err
-log4j.appender.stderr.layout = org.apache.log4j.PatternLayout
-log4j.appender.stderr.layout.ConversionPattern=%-5p - %d{yyyy-MM-dd HH:mm:ss.SSS}; %C; %m\n
+++ /dev/null
-REM You can override pass the following parameters to this script:\r
-REM \r
-\r
-set JVM=java\r
-\r
-REM Find location of this script\r
-\r
-set SDIR=%~dp0\r
-if "%SDIR:~-1%"=="\" set SDIR=%SDIR:~0,-1%\r
-\r
-"%JVM%" -Dlog4j.configuration=file:%SDIR%\log4j.properties -classpath "%SDIR%\..\solr-webapp\webapp\WEB-INF\lib\*;%SDIR%\..\lib\ext\*" org.apache.solr.cloud.ZkCLI %*\r
+++ /dev/null
-#!/usr/bin/env bash
-
-# You can override pass the following parameters to this script:
-#
-
-JVM="java"
-
-# Find location of this script
-
-sdir="`dirname \"$0\"`"
-
-PATH=$JAVA_HOME/bin:$PATH $JVM -Dlog4j.configuration=file:$sdir/log4j.properties -classpath "$sdir/../solr-webapp/webapp/WEB-INF/lib/*:$sdir/../lib/ext/*" org.apache.solr.cloud.ZkCLI ${1+"$@"}
-
+++ /dev/null
-<?xml version="1.0"?>
-<!DOCTYPE Configure PUBLIC "-//Jetty//Configure//EN" "http://www.eclipse.org/jetty/configure.dtd">
-<Configure class="org.eclipse.jetty.webapp.WebAppContext">
- <Set name="contextPath"><SystemProperty name="hostContext" default="/solr"/></Set>
- <Set name="war"><SystemProperty name="jetty.home"/>/webapps/solr.war</Set>
- <Set name="defaultsDescriptor"><SystemProperty name="jetty.home"/>/etc/webdefault.xml</Set>
- <Set name="tempDirectory"><Property name="jetty.home" default="."/>/solr-webapp</Set>
-</Configure>
+++ /dev/null
-#!/bin/bash -ex
-
-# 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 script shows how the solrtest.keystore file used for solr tests
-# and these example configs was generated.
-#
-# Running this script should only be necessary if the keystore file
-# needs to be replaced, which shouldn't be required until sometime around
-# the year 4751.
-#
-# NOTE: the "-ext" option used in the "keytool" command requires that you have
-# the java7 version of keytool, but the generated key will work with any
-# version of java
-
-echo "### remove old keystore"
-rm -f solrtest.keystore
-
-echo "### create keystore and keys"
-keytool -keystore solrtest.keystore -storepass "secret" -alias solrtest -keypass "secret" -genkey -keyalg RSA -dname "cn=localhost, ou=SolrTest, o=lucene.apache.org, c=US" -ext "san=ip:127.0.0.1" -validity 999999
-
-
+++ /dev/null
-<?xml version="1.0"?>
-<!DOCTYPE Configure PUBLIC "-//Jetty//Configure//EN" "http://www.eclipse.org/jetty/configure.dtd">
-
-<!-- =============================================================== -->
-<!-- Configure the Jetty Server -->
-<!-- -->
-<!-- Documentation of this file format can be found at: -->
-<!-- http://wiki.eclipse.org/Jetty/Reference/jetty.xml_syntax -->
-<!-- -->
-<!-- =============================================================== -->
-
-
-<Configure id="Server" class="org.eclipse.jetty.server.Server">
-
- <!-- =========================================================== -->
- <!-- Server Thread Pool -->
- <!-- =========================================================== -->
- <Set name="ThreadPool">
- <!-- Default queued blocking threadpool -->
- <New class="org.eclipse.jetty.util.thread.QueuedThreadPool">
- <Set name="minThreads">10</Set>
- <Set name="maxThreads">10000</Set>
- <Set name="detailedDump">false</Set>
- </New>
- </Set>
-
- <!-- =========================================================== -->
- <!-- Set connectors -->
- <!-- =========================================================== -->
-
- <!--
- <Call name="addConnector">
- <Arg>
- <New class="org.eclipse.jetty.server.nio.SelectChannelConnector">
- <Set name="host"><SystemProperty name="jetty.host" /></Set>
- <Set name="port"><SystemProperty name="jetty.port" default="8983"/></Set>
- <Set name="maxIdleTime">50000</Set>
- <Set name="Acceptors">2</Set>
- <Set name="statsOn">false</Set>
- <Set name="confidentialPort">8443</Set>
- <Set name="lowResourcesConnections">5000</Set>
- <Set name="lowResourcesMaxIdleTime">5000</Set>
- </New>
- </Arg>
- </Call>
- -->
-
- <!-- This connector is currently being used for Solr because it
- showed better performance than nio.SelectChannelConnector
- for typical Solr requests. -->
- <Call name="addConnector">
- <Arg>
- <New class="org.eclipse.jetty.server.bio.SocketConnector">
- <Call class="java.lang.System" name="setProperty"> <Arg>log4j.configuration</Arg> <Arg>etc/log4j.properties</Arg> </Call>
- <Set name="host"><SystemProperty name="jetty.host" /></Set>
- <Set name="port"><SystemProperty name="jetty.port" default="8983"/></Set>
- <Set name="maxIdleTime">50000</Set>
- <Set name="lowResourceMaxIdleTime">1500</Set>
- <Set name="statsOn">false</Set>
- </New>
- </Arg>
- </Call>
-
- <!-- if the connector below is uncommented, then jetty will also accept SSL
- connections on port 8984, using a self signed certificate and can
- optionally require the client to authenticate with a certificate.
- (which can be the same as the server certificate_
-
- # Run solr example with SSL on port 8984
- java -jar start.jar
- #
- # Run post.jar so that it trusts the server cert...
- java -Djavax.net.ssl.trustStore=../etc/solrtest.keystore -Durl=https://localhost:8984/solr/update -jar post.jar *.xml
-
- # Run solr example with SSL requiring client certs on port 8984
- java -Djetty.ssl.clientAuth=true -jar start.jar
- #
- # Run post.jar so that it trusts the server cert,
- # and authenticates with a client cert
- java -Djavax.net.ssl.keyStorePassword=secret -Djavax.net.ssl.keyStore=../etc/solrtest.keystore -Djavax.net.ssl.trustStore=../etc/solrtest.keystore -Durl=https://localhost:8984/solr/update -jar post.jar *.xml
-
- -->
- <!--
- <Call name="addConnector">
- <Arg>
- <New class="org.eclipse.jetty.server.ssl.SslSelectChannelConnector">
- <Arg>
- <New class="org.eclipse.jetty.http.ssl.SslContextFactory">
- <Set name="keyStore"><SystemProperty name="jetty.home" default="."/>/etc/solrtest.keystore</Set>
- <Set name="keyStorePassword">secret</Set>
- <Set name="needClientAuth"><SystemProperty name="jetty.ssl.clientAuth" default="false"/></Set>
- </New>
- </Arg>
- <Set name="port"><SystemProperty name="jetty.ssl.port" default="8984"/></Set>
- <Set name="maxIdleTime">30000</Set>
- </New>
- </Arg>
- </Call>
- -->
-
- <!-- =========================================================== -->
- <!-- Set handler Collection Structure -->
- <!-- =========================================================== -->
- <Set name="handler">
- <New id="Handlers" class="org.eclipse.jetty.server.handler.HandlerCollection">
- <Set name="handlers">
- <Array type="org.eclipse.jetty.server.Handler">
- <Item>
- <New id="Contexts" class="org.eclipse.jetty.server.handler.ContextHandlerCollection"/>
- </Item>
- <Item>
- <New id="DefaultHandler" class="org.eclipse.jetty.server.handler.DefaultHandler"/>
- </Item>
- <Item>
- <New id="RequestLog" class="org.eclipse.jetty.server.handler.RequestLogHandler"/>
- </Item>
- </Array>
- </Set>
- </New>
- </Set>
-
- <!-- =========================================================== -->
- <!-- Configure Request Log -->
- <!-- =========================================================== -->
- <!--
- <Ref id="Handlers">
- <Call name="addHandler">
- <Arg>
- <New id="RequestLog" class="org.eclipse.jetty.server.handler.RequestLogHandler">
- <Set name="requestLog">
- <New id="RequestLogImpl" class="org.eclipse.jetty.server.NCSARequestLog">
- <Set name="filename">
- logs/request.yyyy_mm_dd.log
- </Set>
- <Set name="filenameDateFormat">yyyy_MM_dd</Set>
- <Set name="retainDays">90</Set>
- <Set name="append">true</Set>
- <Set name="extended">false</Set>
- <Set name="logCookies">false</Set>
- <Set name="LogTimeZone">UTC</Set>
- </New>
- </Set>
- </New>
- </Arg>
- </Call>
- </Ref>
- -->
-
- <!-- =========================================================== -->
- <!-- extra options -->
- <!-- =========================================================== -->
- <Set name="stopAtShutdown">true</Set>
- <Set name="sendServerVersion">false</Set>
- <Set name="sendDateHeader">false</Set>
- <Set name="gracefulShutdown">1000</Set>
- <Set name="dumpAfterStart">false</Set>
- <Set name="dumpBeforeStop">false</Set>
-
-
-
-
- <Call name="addBean">
- <Arg>
- <New id="DeploymentManager" class="org.eclipse.jetty.deploy.DeploymentManager">
- <Set name="contexts">
- <Ref id="Contexts" />
- </Set>
- <Call name="setContextAttribute">
- <Arg>org.eclipse.jetty.server.webapp.ContainerIncludeJarPattern</Arg>
- <Arg>.*/servlet-api-[^/]*\.jar$</Arg>
- </Call>
-
-
- <!-- Add a customize step to the deployment lifecycle -->
- <!-- uncomment and replace DebugBinding with your extended AppLifeCycle.Binding class
- <Call name="insertLifeCycleNode">
- <Arg>deployed</Arg>
- <Arg>starting</Arg>
- <Arg>customise</Arg>
- </Call>
- <Call name="addLifeCycleBinding">
- <Arg>
- <New class="org.eclipse.jetty.deploy.bindings.DebugBinding">
- <Arg>customise</Arg>
- </New>
- </Arg>
- </Call>
- -->
-
- </New>
- </Arg>
- </Call>
-
- <Ref id="DeploymentManager">
- <Call name="addAppProvider">
- <Arg>
- <New class="org.eclipse.jetty.deploy.providers.ContextProvider">
- <Set name="monitoredDirName"><SystemProperty name="jetty.home" default="."/>/contexts</Set>
- <Set name="scanInterval">0</Set>
- </New>
- </Arg>
- </Call>
- </Ref>
-
-</Configure>
+++ /dev/null
-#
-# 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.
-#
-
-# To use this log config, start solr with the following system property:
-# -Djava.util.logging.config.file=etc/logging.properties
-
-## Default global logging level:
-.level = INFO
-
-## Log every update command (add, delete, commit, ...)
-#org.apache.solr.update.processor.LogUpdateProcessor.level = FINE
-
-## Where to log (space separated list).
-handlers = java.util.logging.FileHandler
-
-java.util.logging.FileHandler.level = FINE
-
-java.util.logging.FileHandler.formatter = java.util.logging.SimpleFormatter
-
-# 1 GB limit per file
-java.util.logging.FileHandler.limit = 1073741824
-
-# Log to the logs directory, with log files named solrxxx.log
-java.util.logging.FileHandler.pattern = ./logs/solr%u.log
\ No newline at end of file
+++ /dev/null
-<?xml version="1.0" encoding="ISO-8859-1"?>
-
- <!-- ===================================================================== -->
- <!-- This file contains the default descriptor for web applications. -->
- <!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
- <!-- The intent of this descriptor is to include jetty specific or common -->
- <!-- configuration for all webapps. If a context has a webdefault.xml -->
- <!-- descriptor, it is applied before the contexts own web.xml file -->
- <!-- -->
- <!-- A context may be assigned a default descriptor by: -->
- <!-- + Calling WebApplicationContext.setDefaultsDescriptor -->
- <!-- + Passed an arg to addWebApplications -->
- <!-- -->
- <!-- This file is used both as the resource within the jetty.jar (which is -->
- <!-- used as the default if no explicit defaults descriptor is set) and it -->
- <!-- is copied to the etc directory of the Jetty distro and explicitly -->
- <!-- by the jetty.xml file. -->
- <!-- -->
- <!-- ===================================================================== -->
-<web-app
- xmlns="http://java.sun.com/xml/ns/javaee"
- xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
- xsi:schemaLocation="http://java.sun.com/xml/ns/javaee http://java.sun.com/xml/ns/javaee/web-app_2_5.xsd"
- metadata-complete="true"
- version="2.5"
->
-
- <description>
- Default web.xml file.
- This file is applied to a Web application before it's own WEB_INF/web.xml file
- </description>
-
- <!-- ==================================================================== -->
- <!-- Removes static references to beans from javax.el.BeanELResolver to -->
- <!-- ensure webapp classloader can be released on undeploy -->
- <!-- ==================================================================== -->
- <listener>
- <listener-class>org.eclipse.jetty.servlet.listener.ELContextCleaner</listener-class>
- </listener>
-
- <!-- ==================================================================== -->
- <!-- Removes static cache of Methods from java.beans.Introspector to -->
- <!-- ensure webapp classloader can be released on undeploy -->
- <!-- ==================================================================== -->
- <listener>
- <listener-class>org.eclipse.jetty.servlet.listener.IntrospectorCleaner</listener-class>
- </listener>
-
-
- <!-- ==================================================================== -->
- <!-- Context params to control Session Cookies -->
- <!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
- <!--
- UNCOMMENT TO ACTIVATE <context-param> <param-name>org.eclipse.jetty.servlet.SessionDomain</param-name> <param-value>127.0.0.1</param-value> </context-param> <context-param>
- <param-name>org.eclipse.jetty.servlet.SessionPath</param-name> <param-value>/</param-value> </context-param> <context-param> <param-name>org.eclipse.jetty.servlet.MaxAge</param-name>
- <param-value>-1</param-value> </context-param>
- -->
-
- <!-- ==================================================================== -->
- <!-- The default servlet. -->
- <!-- This servlet, normally mapped to /, provides the handling for static -->
- <!-- content, OPTIONS and TRACE methods for the context. -->
- <!-- The following initParameters are supported: -->
- <!--
- * acceptRanges If true, range requests and responses are
- * supported
- *
- * dirAllowed If true, directory listings are returned if no
- * welcome file is found. Else 403 Forbidden.
- *
- * welcomeServlets If true, attempt to dispatch to welcome files
- * that are servlets, but only after no matching static
- * resources could be found. If false, then a welcome
- * file must exist on disk. If "exact", then exact
- * servlet matches are supported without an existing file.
- * Default is true.
- *
- * This must be false if you want directory listings,
- * but have index.jsp in your welcome file list.
- *
- * redirectWelcome If true, welcome files are redirected rather than
- * forwarded to.
- *
- * gzip If set to true, then static content will be served as
- * gzip content encoded if a matching resource is
- * found ending with ".gz"
- *
- * resourceBase Set to replace the context resource base
- *
- * resourceCache If set, this is a context attribute name, which the servlet
- * will use to look for a shared ResourceCache instance.
- *
- * relativeResourceBase
- * Set with a pathname relative to the base of the
- * servlet context root. Useful for only serving static content out
- * of only specific subdirectories.
- *
- * aliases If True, aliases of resources are allowed (eg. symbolic
- * links and caps variations). May bypass security constraints.
- *
- * maxCacheSize The maximum total size of the cache or 0 for no cache.
- * maxCachedFileSize The maximum size of a file to cache
- * maxCachedFiles The maximum number of files to cache
- *
- * useFileMappedBuffer
- * If set to true, it will use mapped file buffer to serve static content
- * when using NIO connector. Setting this value to false means that
- * a direct buffer will be used instead of a mapped file buffer.
- * By default, this is set to true.
- *
- * cacheControl If set, all static content will have this value set as the cache-control
- * header.
- -->
-
-
- <!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
- <servlet>
- <servlet-name>default</servlet-name>
- <servlet-class>org.eclipse.jetty.servlet.DefaultServlet</servlet-class>
- <init-param>
- <param-name>aliases</param-name>
- <param-value>false</param-value>
- </init-param>
- <init-param>
- <param-name>acceptRanges</param-name>
- <param-value>true</param-value>
- </init-param>
- <init-param>
- <param-name>dirAllowed</param-name>
- <param-value>true</param-value>
- </init-param>
- <init-param>
- <param-name>welcomeServlets</param-name>
- <param-value>false</param-value>
- </init-param>
- <init-param>
- <param-name>redirectWelcome</param-name>
- <param-value>false</param-value>
- </init-param>
- <init-param>
- <param-name>maxCacheSize</param-name>
- <param-value>256000000</param-value>
- </init-param>
- <init-param>
- <param-name>maxCachedFileSize</param-name>
- <param-value>200000000</param-value>
- </init-param>
- <init-param>
- <param-name>maxCachedFiles</param-name>
- <param-value>2048</param-value>
- </init-param>
- <init-param>
- <param-name>gzip</param-name>
- <param-value>true</param-value>
- </init-param>
- <init-param>
- <param-name>useFileMappedBuffer</param-name>
- <param-value>true</param-value>
- </init-param>
- <!--
- <init-param>
- <param-name>resourceCache</param-name>
- <param-value>resourceCache</param-value>
- </init-param>
- -->
- <!--
- <init-param>
- <param-name>cacheControl</param-name>
- <param-value>max-age=3600,public</param-value>
- </init-param>
- -->
- <load-on-startup>0</load-on-startup>
- </servlet>
-
- <servlet-mapping>
- <servlet-name>default</servlet-name>
- <url-pattern>/</url-pattern>
- </servlet-mapping>
-
-
- <!-- ==================================================================== -->
- <!-- JSP Servlet -->
- <!-- This is the jasper JSP servlet from the jakarta project -->
- <!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
- <!-- The JSP page compiler and execution servlet, which is the mechanism -->
- <!-- used by Glassfish to support JSP pages. Traditionally, this servlet -->
- <!-- is mapped to URL patterh "*.jsp". This servlet supports the -->
- <!-- following initialization parameters (default values are in square -->
- <!-- brackets): -->
- <!-- -->
- <!-- checkInterval If development is false and reloading is true, -->
- <!-- background compiles are enabled. checkInterval -->
- <!-- is the time in seconds between checks to see -->
- <!-- if a JSP page needs to be recompiled. [300] -->
- <!-- -->
- <!-- compiler Which compiler Ant should use to compile JSP -->
- <!-- pages. See the Ant documenation for more -->
- <!-- information. [javac] -->
- <!-- -->
- <!-- classdebuginfo Should the class file be compiled with -->
- <!-- debugging information? [true] -->
- <!-- -->
- <!-- classpath What class path should I use while compiling -->
- <!-- generated servlets? [Created dynamically -->
- <!-- based on the current web application] -->
- <!-- Set to ? to make the container explicitly set -->
- <!-- this parameter. -->
- <!-- -->
- <!-- development Is Jasper used in development mode (will check -->
- <!-- for JSP modification on every access)? [true] -->
- <!-- -->
- <!-- enablePooling Determines whether tag handler pooling is -->
- <!-- enabled [true] -->
- <!-- -->
- <!-- fork Tell Ant to fork compiles of JSP pages so that -->
- <!-- a separate JVM is used for JSP page compiles -->
- <!-- from the one Tomcat is running in. [true] -->
- <!-- -->
- <!-- ieClassId The class-id value to be sent to Internet -->
- <!-- Explorer when using <jsp:plugin> tags. -->
- <!-- [clsid:8AD9C840-044E-11D1-B3E9-00805F499D93] -->
- <!-- -->
- <!-- javaEncoding Java file encoding to use for generating java -->
- <!-- source files. [UTF-8] -->
- <!-- -->
- <!-- keepgenerated Should we keep the generated Java source code -->
- <!-- for each page instead of deleting it? [true] -->
- <!-- -->
- <!-- logVerbosityLevel The level of detailed messages to be produced -->
- <!-- by this servlet. Increasing levels cause the -->
- <!-- generation of more messages. Valid values are -->
- <!-- FATAL, ERROR, WARNING, INFORMATION, and DEBUG. -->
- <!-- [WARNING] -->
- <!-- -->
- <!-- mappedfile Should we generate static content with one -->
- <!-- print statement per input line, to ease -->
- <!-- debugging? [false] -->
- <!-- -->
- <!-- -->
- <!-- reloading Should Jasper check for modified JSPs? [true] -->
- <!-- -->
- <!-- suppressSmap Should the generation of SMAP info for JSR45 -->
- <!-- debugging be suppressed? [false] -->
- <!-- -->
- <!-- dumpSmap Should the SMAP info for JSR45 debugging be -->
- <!-- dumped to a file? [false] -->
- <!-- False if suppressSmap is true -->
- <!-- -->
- <!-- scratchdir What scratch directory should we use when -->
- <!-- compiling JSP pages? [default work directory -->
- <!-- for the current web application] -->
- <!-- -->
- <!-- tagpoolMaxSize The maximum tag handler pool size [5] -->
- <!-- -->
- <!-- xpoweredBy Determines whether X-Powered-By response -->
- <!-- header is added by generated servlet [false] -->
- <!-- -->
- <!-- If you wish to use Jikes to compile JSP pages: -->
- <!-- Set the init parameter "compiler" to "jikes". Define -->
- <!-- the property "-Dbuild.compiler.emacs=true" when starting Jetty -->
- <!-- to cause Jikes to emit error messages in a format compatible with -->
- <!-- Jasper. -->
- <!-- If you get an error reporting that jikes can't use UTF-8 encoding, -->
- <!-- try setting the init parameter "javaEncoding" to "ISO-8859-1". -->
- <!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
- <servlet
- id="jsp"
- >
- <servlet-name>jsp</servlet-name>
- <servlet-class>org.apache.jasper.servlet.JspServlet</servlet-class>
- <init-param>
- <param-name>logVerbosityLevel</param-name>
- <param-value>DEBUG</param-value>
- </init-param>
- <init-param>
- <param-name>fork</param-name>
- <param-value>false</param-value>
- </init-param>
- <init-param>
- <param-name>xpoweredBy</param-name>
- <param-value>false</param-value>
- </init-param>
- <!--
- <init-param>
- <param-name>classpath</param-name>
- <param-value>?</param-value>
- </init-param>
- -->
- <load-on-startup>0</load-on-startup>
- </servlet>
-
- <servlet-mapping>
- <servlet-name>jsp</servlet-name>
- <url-pattern>*.jsp</url-pattern>
- <url-pattern>*.jspf</url-pattern>
- <url-pattern>*.jspx</url-pattern>
- <url-pattern>*.xsp</url-pattern>
- <url-pattern>*.JSP</url-pattern>
- <url-pattern>*.JSPF</url-pattern>
- <url-pattern>*.JSPX</url-pattern>
- <url-pattern>*.XSP</url-pattern>
- </servlet-mapping>
-
- <!-- ==================================================================== -->
- <!-- Dynamic Servlet Invoker. -->
- <!-- This servlet invokes anonymous servlets that have not been defined -->
- <!-- in the web.xml or by other means. The first element of the pathInfo -->
- <!-- of a request passed to the envoker is treated as a servlet name for -->
- <!-- an existing servlet, or as a class name of a new servlet. -->
- <!-- This servlet is normally mapped to /servlet/* -->
- <!-- This servlet support the following initParams: -->
- <!-- -->
- <!-- nonContextServlets If false, the invoker can only load -->
- <!-- servlets from the contexts classloader. -->
- <!-- This is false by default and setting this -->
- <!-- to true may have security implications. -->
- <!-- -->
- <!-- verbose If true, log dynamic loads -->
- <!-- -->
- <!-- * All other parameters are copied to the -->
- <!-- each dynamic servlet as init parameters -->
- <!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
- <!--
- Uncomment for dynamic invocation <servlet> <servlet-name>invoker</servlet-name> <servlet-class>org.eclipse.jetty.servlet.Invoker</servlet-class> <init-param> <param-name>verbose</param-name>
- <param-value>false</param-value> </init-param> <init-param> <param-name>nonContextServlets</param-name> <param-value>false</param-value> </init-param> <init-param>
- <param-name>dynamicParam</param-name> <param-value>anyValue</param-value> </init-param> <load-on-startup>0</load-on-startup> </servlet> <servlet-mapping> <servlet-name>invoker</servlet-name>
- <url-pattern>/servlet/*</url-pattern> </servlet-mapping>
- -->
-
-
-
- <!-- ==================================================================== -->
- <session-config>
- <session-timeout>30</session-timeout>
- </session-config>
-
- <!-- ==================================================================== -->
- <!-- Default MIME mappings -->
- <!-- The default MIME mappings are provided by the mime.properties -->
- <!-- resource in the org.eclipse.jetty.server.jar file. Additional or modified -->
- <!-- mappings may be specified here -->
- <!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
- <!-- UNCOMMENT TO ACTIVATE
- <mime-mapping>
- <extension>mysuffix</extension>
- <mime-type>mymime/type</mime-type>
- </mime-mapping>
- -->
-
- <!-- ==================================================================== -->
- <welcome-file-list>
- <welcome-file>index.html</welcome-file>
- <welcome-file>index.htm</welcome-file>
- <welcome-file>index.jsp</welcome-file>
- </welcome-file-list>
-
- <!-- ==================================================================== -->
- <locale-encoding-mapping-list>
- <locale-encoding-mapping>
- <locale>ar</locale>
- <encoding>ISO-8859-6</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>be</locale>
- <encoding>ISO-8859-5</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>bg</locale>
- <encoding>ISO-8859-5</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>ca</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>cs</locale>
- <encoding>ISO-8859-2</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>da</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>de</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>el</locale>
- <encoding>ISO-8859-7</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>en</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>es</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>et</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>fi</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>fr</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>hr</locale>
- <encoding>ISO-8859-2</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>hu</locale>
- <encoding>ISO-8859-2</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>is</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>it</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>iw</locale>
- <encoding>ISO-8859-8</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>ja</locale>
- <encoding>Shift_JIS</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>ko</locale>
- <encoding>EUC-KR</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>lt</locale>
- <encoding>ISO-8859-2</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>lv</locale>
- <encoding>ISO-8859-2</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>mk</locale>
- <encoding>ISO-8859-5</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>nl</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>no</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>pl</locale>
- <encoding>ISO-8859-2</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>pt</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>ro</locale>
- <encoding>ISO-8859-2</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>ru</locale>
- <encoding>ISO-8859-5</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>sh</locale>
- <encoding>ISO-8859-5</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>sk</locale>
- <encoding>ISO-8859-2</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>sl</locale>
- <encoding>ISO-8859-2</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>sq</locale>
- <encoding>ISO-8859-2</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>sr</locale>
- <encoding>ISO-8859-5</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>sv</locale>
- <encoding>ISO-8859-1</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>tr</locale>
- <encoding>ISO-8859-9</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>uk</locale>
- <encoding>ISO-8859-5</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>zh</locale>
- <encoding>GB2312</encoding>
- </locale-encoding-mapping>
- <locale-encoding-mapping>
- <locale>zh_TW</locale>
- <encoding>Big5</encoding>
- </locale-encoding-mapping>
- </locale-encoding-mapping-list>
-
- <security-constraint>
- <web-resource-collection>
- <web-resource-name>Disable TRACE</web-resource-name>
- <url-pattern>/</url-pattern>
- <http-method>TRACE</http-method>
- </web-resource-collection>
- <auth-constraint/>
- </security-constraint>
-
-</web-app>
-
+++ /dev/null
-<?xml version="1.0" ?>
-<!--
- 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.
--->
-
-<!-- Example exchange rates file for CurrencyField type named "currency" in example schema -->
-
-<currencyConfig version="1.0">
- <rates>
- <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 -->
- <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" />
- <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" />
- <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" />
- <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" />
- <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" />
- <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" />
- <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" />
- <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" />
- <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" />
- <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" />
- <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" />
- <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" />
- <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" />
- <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" />
- <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" />
- <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" />
- <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" />
- <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" />
- <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" />
- <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" />
- <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" />
- <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" />
- <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" />
- <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" />
- <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" />
- <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" />
- <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" />
- <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" />
- <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" />
- <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" />
- <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" />
- <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" />
- <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" />
- <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" />
- <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" />
- <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" />
- <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" />
-
- <!-- Cross-rates for some common currencies -->
- <rate from="EUR" to="GBP" rate="0.869914" />
- <rate from="EUR" to="NOK" rate="7.800095" />
- <rate from="GBP" to="NOK" rate="8.966508" />
- </rates>
-</currencyConfig>
+++ /dev/null
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- If this file is found in the config directory, it will only be
- loaded once at startup. If it is found in Solr's data
- directory, it will be re-loaded every commit.
-
- See http://wiki.apache.org/solr/QueryElevationComponent for more info
-
--->
-<elevate>
- <query text="foo bar">
- <doc id="1" />
- <doc id="2" />
- <doc id="3" />
- </query>
-
- <query text="ipod">
- <doc id="MA147LL/A" /> <!-- put the actual ipod at the top -->
- <doc id="IW-02" exclude="true" /> <!-- exclude this cable -->
- </query>
-
-</elevate>
+++ /dev/null
-# Set of Catalan contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-d
-l
-m
-n
-s
-t
+++ /dev/null
-# Set of French contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-l
-m
-t
-qu
-n
-s
-j
-d
-c
-jusqu
-quoiqu
-lorsqu
-puisqu
+++ /dev/null
-# Set of Irish contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-d
-m
-b
+++ /dev/null
-# Set of Italian contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-c
-l
-all
-dall
-dell
-nell
-sull
-coll
-pell
-gl
-agl
-dagl
-degl
-negl
-sugl
-un
-m
-t
-s
-v
-d
+++ /dev/null
-# Set of Irish hyphenations for StopFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-h
-n
-t
+++ /dev/null
-# Set of overrides for the dutch stemmer
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-fiets fiets
-bromfiets bromfiets
-ei eier
-kind kinder
+++ /dev/null
-#
-# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
-#
-# Any token with a part-of-speech tag that exactly matches those defined in this
-# file are removed from the token stream.
-#
-# Set your own stoptags by uncommenting the lines below. Note that comments are
-# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
-# etc. that can be useful for building you own stoptag set.
-#
-# The entire possible tagset is provided below for convenience.
-#
-#####
-# noun: unclassified nouns
-#名詞
-#
-# noun-common: Common nouns or nouns where the sub-classification is undefined
-#名詞-一般
-#
-# noun-proper: Proper nouns where the sub-classification is undefined
-#名詞-固有名詞
-#
-# noun-proper-misc: miscellaneous proper nouns
-#名詞-固有名詞-一般
-#
-# noun-proper-person: Personal names where the sub-classification is undefined
-#名詞-固有名詞-人名
-#
-# noun-proper-person-misc: names that cannot be divided into surname and
-# given name; foreign names; names where the surname or given name is unknown.
-# e.g. お市の方
-#名詞-固有名詞-人名-一般
-#
-# noun-proper-person-surname: Mainly Japanese surnames.
-# e.g. 山田
-#名詞-固有名詞-人名-姓
-#
-# noun-proper-person-given_name: Mainly Japanese given names.
-# e.g. 太郎
-#名詞-固有名詞-人名-名
-#
-# noun-proper-organization: Names representing organizations.
-# e.g. 通産省, NHK
-#名詞-固有名詞-組織
-#
-# noun-proper-place: Place names where the sub-classification is undefined
-#名詞-固有名詞-地域
-#
-# noun-proper-place-misc: Place names excluding countries.
-# e.g. アジア, バルセロナ, 京都
-#名詞-固有名詞-地域-一般
-#
-# noun-proper-place-country: Country names.
-# e.g. 日本, オーストラリア
-#名詞-固有名詞-地域-国
-#
-# noun-pronoun: Pronouns where the sub-classification is undefined
-#名詞-代名詞
-#
-# noun-pronoun-misc: miscellaneous pronouns:
-# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
-#名詞-代名詞-一般
-#
-# noun-pronoun-contraction: Spoken language contraction made by combining a
-# pronoun and the particle 'wa'.
-# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ
-#名詞-代名詞-縮約
-#
-# noun-adverbial: Temporal nouns such as names of days or months that behave
-# like adverbs. Nouns that represent amount or ratios and can be used adverbially,
-# e.g. 金曜, 一月, 午後, 少量
-#名詞-副詞可能
-#
-# noun-verbal: Nouns that take arguments with case and can appear followed by
-# 'suru' and related verbs (する, できる, なさる, くださる)
-# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
-#名詞-サ変接続
-#
-# noun-adjective-base: The base form of adjectives, words that appear before な ("na")
-# e.g. 健康, 安易, 駄目, だめ
-#名詞-形容動詞語幹
-#
-# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
-# e.g. 0, 1, 2, 何, 数, 幾
-#名詞-数
-#
-# noun-affix: noun affixes where the sub-classification is undefined
-#名詞-非自立
-#
-# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that
-# attach to the base form of inflectional words, words that cannot be classified
-# into any of the other categories below. This category includes indefinite nouns.
-# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第,
-# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み,
-# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
-# わり, 割り, 割, ん-口語/, もん-口語/
-#名詞-非自立-一般
-#
-# noun-affix-adverbial: noun affixes that that can behave as adverbs.
-# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ,
-# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか,
-# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所,
-# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま,
-# 儘, 侭, みぎり, 矢先
-#名詞-非自立-副詞可能
-#
-# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars
-# with the stem よう(だ) ("you(da)").
-# e.g. よう, やう, 様 (よう)
-#名詞-非自立-助動詞語幹
-#
-# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
-# connection form な (aux "da").
-# e.g. みたい, ふう
-#名詞-非自立-形容動詞語幹
-#
-# noun-special: special nouns where the sub-classification is undefined.
-#名詞-特殊
-#
-# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is
-# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base
-# form of inflectional words.
-# e.g. そう
-#名詞-特殊-助動詞語幹
-#
-# noun-suffix: noun suffixes where the sub-classification is undefined.
-#名詞-接尾
-#
-# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
-# to ガル or タイ and can combine into compound nouns, words that cannot be classified into
-# any of the other categories below. In general, this category is more inclusive than
-# 接尾語 ("suffix") and is usually the last element in a compound noun.
-# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
-# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
-#名詞-接尾-一般
-#
-# noun-suffix-person: Suffixes that form nouns and attach to person names more often
-# than other nouns.
-# e.g. 君, 様, 著
-#名詞-接尾-人名
-#
-# noun-suffix-place: Suffixes that form nouns and attach to place names more often
-# than other nouns.
-# e.g. 町, 市, 県
-#名詞-接尾-地域
-#
-# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
-# can appear before スル ("suru").
-# e.g. 化, 視, 分け, 入り, 落ち, 買い
-#名詞-接尾-サ変接続
-#
-# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions,
-# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the
-# conjunctive form of inflectional words.
-# e.g. そう
-#名詞-接尾-助動詞語幹
-#
-# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
-# form of inflectional words and appear before the copula だ ("da").
-# e.g. 的, げ, がち
-#名詞-接尾-形容動詞語幹
-#
-# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
-# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
-#名詞-接尾-副詞可能
-#
-# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
-# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach
-# to numbers.
-# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
-#名詞-接尾-助数詞
-#
-# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
-# e.g. (楽し) さ, (考え) 方
-#名詞-接尾-特殊
-#
-# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
-# together.
-# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
-#名詞-接続詞的
-#
-# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are
-# semantically verb-like.
-# e.g. ごらん, ご覧, 御覧, 頂戴
-#名詞-動詞非自立的
-#
-# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
-# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation")
-# is いわく ("iwaku").
-#名詞-引用文字列
-#
-# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
-# behave like an adjective.
-# e.g. 申し訳, 仕方, とんでも, 違い
-#名詞-ナイ形容詞語幹
-#
-#####
-# prefix: unclassified prefixes
-#接頭詞
-#
-# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
-# excluding numerical expressions.
-# e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
-#接頭詞-名詞接続
-#
-# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
-# in conjunctive form followed by なる/なさる/くださる.
-# e.g. お (読みなさい), お (座り)
-#接頭詞-動詞接続
-#
-# prefix-adjectival: Prefixes that attach to adjectives.
-# e.g. お (寒いですねえ), バカ (でかい)
-#接頭詞-形容詞接続
-#
-# prefix-numerical: Prefixes that attach to numerical expressions.
-# e.g. 約, およそ, 毎時
-#接頭詞-数接続
-#
-#####
-# verb: unclassified verbs
-#動詞
-#
-# verb-main:
-#動詞-自立
-#
-# verb-auxiliary:
-#動詞-非自立
-#
-# verb-suffix:
-#動詞-接尾
-#
-#####
-# adjective: unclassified adjectives
-#形容詞
-#
-# adjective-main:
-#形容詞-自立
-#
-# adjective-auxiliary:
-#形容詞-非自立
-#
-# adjective-suffix:
-#形容詞-接尾
-#
-#####
-# adverb: unclassified adverbs
-#副詞
-#
-# adverb-misc: Words that can be segmented into one unit and where adnominal
-# modification is not possible.
-# e.g. あいかわらず, 多分
-#副詞-一般
-#
-# adverb-particle_conjunction: Adverbs that can be followed by の, は, に,
-# な, する, だ, etc.
-# e.g. こんなに, そんなに, あんなに, なにか, なんでも
-#副詞-助詞類接続
-#
-#####
-# adnominal: Words that only have noun-modifying forms.
-# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう,
-# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした,
-# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
-#連体詞
-#
-#####
-# conjunction: Conjunctions that can occur independently.
-# e.g. が, けれども, そして, じゃあ, それどころか
-接続詞
-#
-#####
-# particle: unclassified particles.
-助詞
-#
-# particle-case: case particles where the subclassification is undefined.
-助詞-格助詞
-#
-# particle-case-misc: Case particles.
-# e.g. から, が, で, と, に, へ, より, を, の, にて
-助詞-格助詞-一般
-#
-# particle-case-quote: the "to" that appears after nouns, a person’s speech,
-# quotation marks, expressions of decisions from a meeting, reasons, judgements,
-# conjectures, etc.
-# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
-助詞-格助詞-引用
-#
-# particle-case-compound: Compounds of particles and verbs that mainly behave
-# like case particles.
-# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
-# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける,
-# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し,
-# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして,
-# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
-# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る,
-# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
-# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
-助詞-格助詞-連語
-#
-# particle-conjunctive:
-# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども,
-# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/,
-# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
-助詞-接続助詞
-#
-# particle-dependency:
-# e.g. こそ, さえ, しか, すら, は, も, ぞ
-助詞-係助詞
-#
-# particle-adverbial:
-# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/,
-# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
-# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに,
-# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
-# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
-助詞-副助詞
-#
-# particle-interjective: particles with interjective grammatical roles.
-# e.g. (松島) や
-助詞-間投助詞
-#
-# particle-coordinate:
-# e.g. と, たり, だの, だり, とか, なり, や, やら
-助詞-並立助詞
-#
-# particle-final:
-# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ,
-# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
-助詞-終助詞
-#
-# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
-# adverbial, conjunctive, or sentence final. For example:
-# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
-# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
-# 「(祈りが届いたせい) か (, 試験に合格した.)」
-# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
-# e.g. か
-助詞-副助詞／並立助詞／終助詞
-#
-# particle-adnominalizer: The "no" that attaches to nouns and modifies
-# non-inflectional words.
-助詞-連体化
-#
-# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
-# that are giongo, giseigo, or gitaigo.
-# e.g. に, と
-助詞-副詞化
-#
-# particle-special: A particle that does not fit into one of the above classifications.
-# This includes particles that are used in Tanka, Haiku, and other poetry.
-# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
-助詞-特殊
-#
-#####
-# auxiliary-verb:
-助動詞
-#
-#####
-# interjection: Greetings and other exclamations.
-# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます,
-# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
-#感動詞
-#
-#####
-# symbol: unclassified Symbols.
-記号
-#
-# symbol-misc: A general symbol not in one of the categories below.
-# e.g. [○◎@$〒→+]
-記号-一般
-#
-# symbol-comma: Commas
-# e.g. [,、]
-記号-読点
-#
-# symbol-period: Periods and full stops.
-# e.g. [.．。]
-記号-句点
-#
-# symbol-space: Full-width whitespace.
-記号-空白
-#
-# symbol-open_bracket:
-# e.g. [({‘“『【]
-記号-括弧開
-#
-# symbol-close_bracket:
-# e.g. [)}’”』」】]
-記号-括弧閉
-#
-# symbol-alphabetic:
-#記号-アルファベット
-#
-#####
-# other: unclassified other
-#その他
-#
-# other-interjection: Words that are hard to classify as noun-suffixes or
-# sentence-final particles.
-# e.g. (だ)ァ
-その他-間投
-#
-#####
-# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
-# e.g. あの, うんと, えと
-フィラー
-#
-#####
-# non-verbal: non-verbal sound.
-非言語音
-#
-#####
-# fragment:
-#語断片
-#
-#####
-# unknown: unknown part of speech.
-#未知語
-#
-##### End of file
+++ /dev/null
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# Cleaned on October 11, 2009 (not normalized, so use before normalization)
-# This means that when modifying this list, you might need to add some
-# redundant entries, for example containing forms with both أ and ا
-من
-ومن
-منها
-منه
-في
-وفي
-فيها
-فيه
-و
-ف
-ثم
-او
-أو
-ب
-بها
-به
-ا
-أ
-اى
-اي
-أي
-أى
-لا
-ولا
-الا
-ألا
-إلا
-لكن
-ما
-وما
-كما
-فما
-عن
-مع
-اذا
-إذا
-ان
-أن
-إن
-انها
-أنها
-إنها
-انه
-أنه
-إنه
-بان
-بأن
-فان
-فأن
-وان
-وأن
-وإن
-التى
-التي
-الذى
-الذي
-الذين
-الى
-الي
-إلى
-إلي
-على
-عليها
-عليه
-اما
-أما
-إما
-ايضا
-أيضا
-كل
-وكل
-لم
-ولم
-لن
-ولن
-هى
-هي
-هو
-وهى
-وهي
-وهو
-فهى
-فهي
-فهو
-انت
-أنت
-لك
-لها
-له
-هذه
-هذا
-تلك
-ذلك
-هناك
-كانت
-كان
-يكون
-تكون
-وكانت
-وكان
-غير
-بعض
-قد
-نحو
-بين
-بينما
-منذ
-ضمن
-حيث
-الان
-الآن
-خلال
-بعد
-قبل
-حتى
-عند
-عندما
-لدى
-جميع
+++ /dev/null
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-а
-аз
-ако
-ала
-бе
-без
-беше
-би
-бил
-била
-били
-било
-близо
-бъдат
-бъде
-бяха
-в
-вас
-ваш
-ваша
-вероятно
-вече
-взема
-ви
-вие
-винаги
-все
-всеки
-всички
-всичко
-всяка
-във
-въпреки
-върху
-г
-ги
-главно
-го
-д
-да
-дали
-до
-докато
-докога
-дори
-досега
-доста
-е
-едва
-един
-ето
-за
-зад
-заедно
-заради
-засега
-затова
-защо
-защото
-и
-из
-или
-им
-има
-имат
-иска
-й
-каза
-как
-каква
-какво
-както
-какъв
-като
-кога
-когато
-което
-които
-кой
-който
-колко
-която
-къде
-където
-към
-ли
-м
-ме
-между
-мен
-ми
-мнозина
-мога
-могат
-може
-моля
-момента
-му
-н
-на
-над
-назад
-най
-направи
-напред
-например
-нас
-не
-него
-нея
-ни
-ние
-никой
-нито
-но
-някои
-някой
-няма
-обаче
-около
-освен
-особено
-от
-отгоре
-отново
-още
-пак
-по
-повече
-повечето
-под
-поне
-поради
-после
-почти
-прави
-пред
-преди
-през
-при
-пък
-първо
-с
-са
-само
-се
-сега
-си
-скоро
-след
-сме
-според
-сред
-срещу
-сте
-съм
-със
-също
-т
-тази
-така
-такива
-такъв
-там
-твой
-те
-тези
-ти
-тн
-то
-това
-тогава
-този
-той
-толкова
-точно
-трябва
-тук
-тъй
-тя
-тях
-у
-харесва
-ч
-че
-често
-чрез
-ще
-щом
-я
+++ /dev/null
-# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
-a
-abans
-ací
-ah
-així
-això
-al
-als
-aleshores
-algun
-alguna
-algunes
-alguns
-alhora
-allà
-allí
-allò
-altra
-altre
-altres
-amb
-ambdós
-ambdues
-apa
-aquell
-aquella
-aquelles
-aquells
-aquest
-aquesta
-aquestes
-aquests
-aquí
-baix
-cada
-cadascú
-cadascuna
-cadascunes
-cadascuns
-com
-contra
-d'un
-d'una
-d'unes
-d'uns
-dalt
-de
-del
-dels
-des
-després
-dins
-dintre
-donat
-doncs
-durant
-e
-eh
-el
-els
-em
-en
-encara
-ens
-entre
-érem
-eren
-éreu
-es
-és
-esta
-està
-estàvem
-estaven
-estàveu
-esteu
-et
-etc
-ets
-fins
-fora
-gairebé
-ha
-han
-has
-havia
-he
-hem
-heu
-hi
-ho
-i
-igual
-iguals
-ja
-l'hi
-la
-les
-li
-li'n
-llavors
-m'he
-ma
-mal
-malgrat
-mateix
-mateixa
-mateixes
-mateixos
-me
-mentre
-més
-meu
-meus
-meva
-meves
-molt
-molta
-moltes
-molts
-mon
-mons
-n'he
-n'hi
-ne
-ni
-no
-nogensmenys
-només
-nosaltres
-nostra
-nostre
-nostres
-o
-oh
-oi
-on
-pas
-pel
-pels
-per
-però
-perquè
-poc
-poca
-pocs
-poques
-potser
-propi
-qual
-quals
-quan
-quant
-que
-què
-quelcom
-qui
-quin
-quina
-quines
-quins
-s'ha
-s'han
-sa
-semblant
-semblants
-ses
-seu
-seus
-seva
-seva
-seves
-si
-sobre
-sobretot
-sóc
-solament
-sols
-son
-són
-sons
-sota
-sou
-t'ha
-t'han
-t'he
-ta
-tal
-també
-tampoc
-tan
-tant
-tanta
-tantes
-teu
-teus
-teva
-teves
-ton
-tons
-tot
-tota
-totes
-tots
-un
-una
-unes
-uns
-us
-va
-vaig
-vam
-van
-vas
-veu
-vosaltres
-vostra
-vostre
-vostres
+++ /dev/null
-a
-s
-k
-o
-i
-u
-v
-z
-dnes
-cz
-tímto
-budeš
-budem
-byli
-jseš
-můj
-svým
-ta
-tomto
-tohle
-tuto
-tyto
-jej
-zda
-proč
-máte
-tato
-kam
-tohoto
-kdo
-kteří
-mi
-nám
-tom
-tomuto
-mít
-nic
-proto
-kterou
-byla
-toho
-protože
-asi
-ho
-naši
-napište
-re
-což
-tím
-takže
-svých
-její
-svými
-jste
-aj
-tu
-tedy
-teto
-bylo
-kde
-ke
-pravé
-ji
-nad
-nejsou
-či
-pod
-téma
-mezi
-přes
-ty
-pak
-vám
-ani
-když
-však
-neg
-jsem
-tento
-článku
-články
-aby
-jsme
-před
-pta
-jejich
-byl
-ještě
-až
-bez
-také
-pouze
-první
-vaše
-která
-nás
-nový
-tipy
-pokud
-může
-strana
-jeho
-své
-jiné
-zprávy
-nové
-není
-vás
-jen
-podle
-zde
-už
-být
-více
-bude
-již
-než
-který
-by
-které
-co
-nebo
-ten
-tak
-má
-při
-od
-po
-jsou
-jak
-další
-ale
-si
-se
-ve
-to
-jako
-za
-zpět
-ze
-do
-pro
-je
-na
-atd
-atp
-jakmile
-přičemž
-já
-on
-ona
-ono
-oni
-ony
-my
-vy
-jí
-ji
-mě
-mne
-jemu
-tomu
-těm
-těmu
-němu
-němuž
-jehož
-jíž
-jelikož
-jež
-jakož
-načež
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
- | A Danish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
-
-og | and
-i | in
-jeg | I
-det | that (dem. pronoun)/it (pers. pronoun)
-at | that (in front of a sentence)/to (with infinitive)
-en | a/an
-den | it (pers. pronoun)/that (dem. pronoun)
-til | to/at/for/until/against/by/of/into, more
-er | present tense of "to be"
-som | who, as
-på | on/upon/in/on/at/to/after/of/with/for, on
-de | they
-med | with/by/in, along
-han | he
-af | of/by/from/off/for/in/with/on, off
-for | at/for/to/from/by/of/ago, in front/before, because
-ikke | not
-der | who/which, there/those
-var | past tense of "to be"
-mig | me/myself
-sig | oneself/himself/herself/itself/themselves
-men | but
-et | a/an/one, one (number), someone/somebody/one
-har | present tense of "to have"
-om | round/about/for/in/a, about/around/down, if
-vi | we
-min | my
-havde | past tense of "to have"
-ham | him
-hun | she
-nu | now
-over | over/above/across/by/beyond/past/on/about, over/past
-da | then, when/as/since
-fra | from/off/since, off, since
-du | you
-ud | out
-sin | his/her/its/one's
-dem | them
-os | us/ourselves
-op | up
-man | you/one
-hans | his
-hvor | where
-eller | or
-hvad | what
-skal | must/shall etc.
-selv | myself/youself/herself/ourselves etc., even
-her | here
-alle | all/everyone/everybody etc.
-vil | will (verb)
-blev | past tense of "to stay/to remain/to get/to become"
-kunne | could
-ind | in
-når | when
-være | present tense of "to be"
-dog | however/yet/after all
-noget | something
-ville | would
-jo | you know/you see (adv), yes
-deres | their/theirs
-efter | after/behind/according to/for/by/from, later/afterwards
-ned | down
-skulle | should
-denne | this
-end | than
-dette | this
-mit | my/mine
-også | also
-under | under/beneath/below/during, below/underneath
-have | have
-dig | you
-anden | other
-hende | her
-mine | my
-alt | everything
-meget | much/very, plenty of
-sit | his, her, its, one's
-sine | his, her, its, one's
-vor | our
-mod | against
-disse | these
-hvis | if
-din | your/yours
-nogle | some
-hos | by/at
-blive | be/become
-mange | many
-ad | by/through
-bliver | present tense of "to be/to become"
-hendes | her/hers
-været | be
-thi | for (conj)
-jer | you
-sådan | such, like this/like that
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
- | A German stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | The number of forms in this list is reduced significantly by passing it
- | through the German stemmer.
-
-
-aber | but
-
-alle | all
-allem
-allen
-aller
-alles
-
-als | than, as
-also | so
-am | an + dem
-an | at
-
-ander | other
-andere
-anderem
-anderen
-anderer
-anderes
-anderm
-andern
-anderr
-anders
-
-auch | also
-auf | on
-aus | out of
-bei | by
-bin | am
-bis | until
-bist | art
-da | there
-damit | with it
-dann | then
-
-der | the
-den
-des
-dem
-die
-das
-
-daß | that
-
-derselbe | the same
-derselben
-denselben
-desselben
-demselben
-dieselbe
-dieselben
-dasselbe
-
-dazu | to that
-
-dein | thy
-deine
-deinem
-deinen
-deiner
-deines
-
-denn | because
-
-derer | of those
-dessen | of him
-
-dich | thee
-dir | to thee
-du | thou
-
-dies | this
-diese
-diesem
-diesen
-dieser
-dieses
-
-
-doch | (several meanings)
-dort | (over) there
-
-
-durch | through
-
-ein | a
-eine
-einem
-einen
-einer
-eines
-
-einig | some
-einige
-einigem
-einigen
-einiger
-einiges
-
-einmal | once
-
-er | he
-ihn | him
-ihm | to him
-
-es | it
-etwas | something
-
-euer | your
-eure
-eurem
-euren
-eurer
-eures
-
-für | for
-gegen | towards
-gewesen | p.p. of sein
-hab | have
-habe | have
-haben | have
-hat | has
-hatte | had
-hatten | had
-hier | here
-hin | there
-hinter | behind
-
-ich | I
-mich | me
-mir | to me
-
-
-ihr | you, to her
-ihre
-ihrem
-ihren
-ihrer
-ihres
-euch | to you
-
-im | in + dem
-in | in
-indem | while
-ins | in + das
-ist | is
-
-jede | each, every
-jedem
-jeden
-jeder
-jedes
-
-jene | that
-jenem
-jenen
-jener
-jenes
-
-jetzt | now
-kann | can
-
-kein | no
-keine
-keinem
-keinen
-keiner
-keines
-
-können | can
-könnte | could
-machen | do
-man | one
-
-manche | some, many a
-manchem
-manchen
-mancher
-manches
-
-mein | my
-meine
-meinem
-meinen
-meiner
-meines
-
-mit | with
-muss | must
-musste | had to
-nach | to(wards)
-nicht | not
-nichts | nothing
-noch | still, yet
-nun | now
-nur | only
-ob | whether
-oder | or
-ohne | without
-sehr | very
-
-sein | his
-seine
-seinem
-seinen
-seiner
-seines
-
-selbst | self
-sich | herself
-
-sie | they, she
-ihnen | to them
-
-sind | are
-so | so
-
-solche | such
-solchem
-solchen
-solcher
-solches
-
-soll | shall
-sollte | should
-sondern | but
-sonst | else
-über | over
-um | about, around
-und | and
-
-uns | us
-unse
-unsem
-unsen
-unser
-unses
-
-unter | under
-viel | much
-vom | von + dem
-von | from
-vor | before
-während | while
-war | was
-waren | were
-warst | wast
-was | what
-weg | away, off
-weil | because
-weiter | further
-
-welche | which
-welchem
-welchen
-welcher
-welches
-
-wenn | when
-werde | will
-werden | will
-wie | how
-wieder | again
-will | want
-wir | we
-wird | will
-wirst | willst
-wo | where
-wollen | want
-wollte | wanted
-würde | would
-würden | would
-zu | to
-zum | zu + dem
-zur | zu + der
-zwar | indeed
-zwischen | between
-
+++ /dev/null
-# Lucene Greek Stopwords list
-# Note: by default this file is used after GreekLowerCaseFilter,
-# so when modifying this file use 'σ' instead of 'ς'
-ο
-η
-το
-οι
-τα
-του
-τησ
-των
-τον
-την
-και
-κι
-κ
-ειμαι
-εισαι
-ειναι
-ειμαστε
-ειστε
-στο
-στον
-στη
-στην
-μα
-αλλα
-απο
-για
-προσ
-με
-σε
-ωσ
-παρα
-αντι
-κατα
-μετα
-θα
-να
-δε
-δεν
-μη
-μην
-επι
-ενω
-εαν
-αν
-τοτε
-που
-πωσ
-ποιοσ
-ποια
-ποιο
-ποιοι
-ποιεσ
-ποιων
-ποιουσ
-αυτοσ
-αυτη
-αυτο
-αυτοι
-αυτων
-αυτουσ
-αυτεσ
-αυτα
-εκεινοσ
-εκεινη
-εκεινο
-εκεινοι
-εκεινεσ
-εκεινα
-εκεινων
-εκεινουσ
-οπωσ
-ομωσ
-ισωσ
-οσο
-οτι
+++ /dev/null
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# a couple of test stopwords to test that the words are really being
-# configured from this file:
-stopworda
-stopwordb
-
-# Standard english stop words taken from Lucene's StopAnalyzer
-a
-an
-and
-are
-as
-at
-be
-but
-by
-for
-if
-in
-into
-is
-it
-no
-not
-of
-on
-or
-such
-that
-the
-their
-then
-there
-these
-they
-this
-to
-was
-will
-with
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
- | A Spanish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-
- | The following is a ranked list (commonest to rarest) of stopwords
- | deriving from a large sample of text.
-
- | Extra words have been added at the end.
-
-de | from, of
-la | the, her
-que | who, that
-el | the
-en | in
-y | and
-a | to
-los | the, them
-del | de + el
-se | himself, from him etc
-las | the, them
-por | for, by, etc
-un | a
-para | for
-con | with
-no | no
-una | a
-su | his, her
-al | a + el
- | es from SER
-lo | him
-como | how
-más | more
-pero | pero
-sus | su plural
-le | to him, her
-ya | already
-o | or
- | fue from SER
-este | this
- | ha from HABER
-sí | himself etc
-porque | because
-esta | this
- | son from SER
-entre | between
- | está from ESTAR
-cuando | when
-muy | very
-sin | without
-sobre | on
- | ser from SER
- | tiene from TENER
-también | also
-me | me
-hasta | until
-hay | there is/are
-donde | where
- | han from HABER
-quien | whom, that
- | están from ESTAR
- | estado from ESTAR
-desde | from
-todo | all
-nos | us
-durante | during
- | estados from ESTAR
-todos | all
-uno | a
-les | to them
-ni | nor
-contra | against
-otros | other
- | fueron from SER
-ese | that
-eso | that
- | había from HABER
-ante | before
-ellos | they
-e | and (variant of y)
-esto | this
-mí | me
-antes | before
-algunos | some
-qué | what?
-unos | a
-yo | I
-otro | other
-otras | other
-otra | other
-él | he
-tanto | so much, many
-esa | that
-estos | these
-mucho | much, many
-quienes | who
-nada | nothing
-muchos | many
-cual | who
- | sea from SER
-poco | few
-ella | she
-estar | to be
- | haber from HABER
-estas | these
- | estaba from ESTAR
- | estamos from ESTAR
-algunas | some
-algo | something
-nosotros | we
-
- | other forms
-
-mi | me
-mis | mi plural
-tú | thou
-te | thee
-ti | thee
-tu | thy
-tus | tu plural
-ellas | they
-nosotras | we
-vosotros | you
-vosotras | you
-os | you
-mío | mine
-mía |
-míos |
-mías |
-tuyo | thine
-tuya |
-tuyos |
-tuyas |
-suyo | his, hers, theirs
-suya |
-suyos |
-suyas |
-nuestro | ours
-nuestra |
-nuestros |
-nuestras |
-vuestro | yours
-vuestra |
-vuestros |
-vuestras |
-esos | those
-esas | those
-
- | forms of estar, to be (not including the infinitive):
-estoy
-estás
-está
-estamos
-estáis
-están
-esté
-estés
-estemos
-estéis
-estén
-estaré
-estarás
-estará
-estaremos
-estaréis
-estarán
-estaría
-estarías
-estaríamos
-estaríais
-estarían
-estaba
-estabas
-estábamos
-estabais
-estaban
-estuve
-estuviste
-estuvo
-estuvimos
-estuvisteis
-estuvieron
-estuviera
-estuvieras
-estuviéramos
-estuvierais
-estuvieran
-estuviese
-estuvieses
-estuviésemos
-estuvieseis
-estuviesen
-estando
-estado
-estada
-estados
-estadas
-estad
-
- | forms of haber, to have (not including the infinitive):
-he
-has
-ha
-hemos
-habéis
-han
-haya
-hayas
-hayamos
-hayáis
-hayan
-habré
-habrás
-habrá
-habremos
-habréis
-habrán
-habría
-habrías
-habríamos
-habríais
-habrían
-había
-habías
-habíamos
-habíais
-habían
-hube
-hubiste
-hubo
-hubimos
-hubisteis
-hubieron
-hubiera
-hubieras
-hubiéramos
-hubierais
-hubieran
-hubiese
-hubieses
-hubiésemos
-hubieseis
-hubiesen
-habiendo
-habido
-habida
-habidos
-habidas
-
- | forms of ser, to be (not including the infinitive):
-soy
-eres
-es
-somos
-sois
-son
-sea
-seas
-seamos
-seáis
-sean
-seré
-serás
-será
-seremos
-seréis
-serán
-sería
-serías
-seríamos
-seríais
-serían
-era
-eras
-éramos
-erais
-eran
-fui
-fuiste
-fue
-fuimos
-fuisteis
-fueron
-fuera
-fueras
-fuéramos
-fuerais
-fueran
-fuese
-fueses
-fuésemos
-fueseis
-fuesen
-siendo
-sido
- | sed also means 'thirst'
-
- | forms of tener, to have (not including the infinitive):
-tengo
-tienes
-tiene
-tenemos
-tenéis
-tienen
-tenga
-tengas
-tengamos
-tengáis
-tengan
-tendré
-tendrás
-tendrá
-tendremos
-tendréis
-tendrán
-tendría
-tendrías
-tendríamos
-tendríais
-tendrían
-tenía
-tenías
-teníamos
-teníais
-tenían
-tuve
-tuviste
-tuvo
-tuvimos
-tuvisteis
-tuvieron
-tuviera
-tuvieras
-tuviéramos
-tuvierais
-tuvieran
-tuviese
-tuvieses
-tuviésemos
-tuvieseis
-tuviesen
-teniendo
-tenido
-tenida
-tenidos
-tenidas
-tened
-
+++ /dev/null
-# example set of basque stopwords
-al
-anitz
-arabera
-asko
-baina
-bat
-batean
-batek
-bati
-batzuei
-batzuek
-batzuetan
-batzuk
-bera
-beraiek
-berau
-berauek
-bere
-berori
-beroriek
-beste
-bezala
-da
-dago
-dira
-ditu
-du
-dute
-edo
-egin
-ere
-eta
-eurak
-ez
-gainera
-gu
-gutxi
-guzti
-haiei
-haiek
-haietan
-hainbeste
-hala
-han
-handik
-hango
-hara
-hari
-hark
-hartan
-hau
-hauei
-hauek
-hauetan
-hemen
-hemendik
-hemengo
-hi
-hona
-honek
-honela
-honetan
-honi
-hor
-hori
-horiei
-horiek
-horietan
-horko
-horra
-horrek
-horrela
-horretan
-horri
-hortik
-hura
-izan
-ni
-noiz
-nola
-non
-nondik
-nongo
-nor
-nora
-ze
-zein
-zen
-zenbait
-zenbat
-zer
-zergatik
-ziren
-zituen
-zu
-zuek
-zuen
-zuten
+++ /dev/null
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# Note: by default this file is used after normalization, so when adding entries
-# to this file, use the arabic 'ي' instead of 'ی'
-انان
-نداشته
-سراسر
-خياه
-ايشان
-وي
-تاكنون
-بيشتري
-دوم
-پس
-ناشي
-وگو
-يا
-داشتند
-سپس
-هنگام
-هرگز
-پنج
-نشان
-امسال
-ديگر
-گروهي
-شدند
-چطور
-ده
-و
-دو
-نخستين
-ولي
-چرا
-چه
-وسط
-ه
-كدام
-قابل
-يك
-رفت
-هفت
-همچنين
-در
-هزار
-بله
-بلي
-شايد
-اما
-شناسي
-گرفته
-دهد
-داشته
-دانست
-داشتن
-خواهيم
-ميليارد
-وقتيكه
-امد
-خواهد
-جز
-اورده
-شده
-بلكه
-خدمات
-شدن
-برخي
-نبود
-بسياري
-جلوگيري
-حق
-كردند
-نوعي
-بعري
-نكرده
-نظير
-نبايد
-بوده
-بودن
-داد
-اورد
-هست
-جايي
-شود
-دنبال
-داده
-بايد
-سابق
-هيچ
-همان
-انجا
-كمتر
-كجاست
-گردد
-كسي
-تر
-مردم
-تان
-دادن
-بودند
-سري
-جدا
-ندارند
-مگر
-يكديگر
-دارد
-دهند
-بنابراين
-هنگامي
-سمت
-جا
-انچه
-خود
-دادند
-زياد
-دارند
-اثر
-بدون
-بهترين
-بيشتر
-البته
-به
-براساس
-بيرون
-كرد
-بعضي
-گرفت
-توي
-اي
-ميليون
-او
-جريان
-تول
-بر
-مانند
-برابر
-باشيم
-مدتي
-گويند
-اكنون
-تا
-تنها
-جديد
-چند
-بي
-نشده
-كردن
-كردم
-گويد
-كرده
-كنيم
-نمي
-نزد
-روي
-قصد
-فقط
-بالاي
-ديگران
-اين
-ديروز
-توسط
-سوم
-ايم
-دانند
-سوي
-استفاده
-شما
-كنار
-داريم
-ساخته
-طور
-امده
-رفته
-نخست
-بيست
-نزديك
-طي
-كنيد
-از
-انها
-تمامي
-داشت
-يكي
-طريق
-اش
-چيست
-روب
-نمايد
-گفت
-چندين
-چيزي
-تواند
-ام
-ايا
-با
-ان
-ايد
-ترين
-اينكه
-ديگري
-راه
-هايي
-بروز
-همچنان
-پاعين
-كس
-حدود
-مختلف
-مقابل
-چيز
-گيرد
-ندارد
-ضد
-همچون
-سازي
-شان
-مورد
-باره
-مرسي
-خويش
-برخوردار
-چون
-خارج
-شش
-هنوز
-تحت
-ضمن
-هستيم
-گفته
-فكر
-بسيار
-پيش
-براي
-روزهاي
-انكه
-نخواهد
-بالا
-كل
-وقتي
-كي
-چنين
-كه
-گيري
-نيست
-است
-كجا
-كند
-نيز
-يابد
-بندي
-حتي
-توانند
-عقب
-خواست
-كنند
-بين
-تمام
-همه
-ما
-باشند
-مثل
-شد
-اري
-باشد
-اره
-طبق
-بعد
-اگر
-صورت
-غير
-جاي
-بيش
-ريزي
-اند
-زيرا
-چگونه
-بار
-لطفا
-مي
-درباره
-من
-ديده
-همين
-گذاري
-برداري
-علت
-گذاشته
-هم
-فوق
-نه
-ها
-شوند
-اباد
-همواره
-هر
-اول
-خواهند
-چهار
-نام
-امروز
-مان
-هاي
-قبل
-كنم
-سعي
-تازه
-را
-هستند
-زير
-جلوي
-عنوان
-بود
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
-| forms of BE
-
-olla
-olen
-olet
-on
-olemme
-olette
-ovat
-ole | negative form
-
-oli
-olisi
-olisit
-olisin
-olisimme
-olisitte
-olisivat
-olit
-olin
-olimme
-olitte
-olivat
-ollut
-olleet
-
-en | negation
-et
-ei
-emme
-ette
-eivät
-
-|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans
-minä minun minut minua minussa minusta minuun minulla minulta minulle | I
-sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you
-hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she
-me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we
-te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you
-he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they
-
-tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this
-tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that
-se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it
-nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these
-nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those
-ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they
-
-kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
-ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl)
-mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what
-mitkä | (pl)
-
-joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which
-jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl)
-
-| conjunctions
-
-että | that
-ja | and
-jos | if
-koska | because
-kuin | than
-mutta | but
-niin | so
-sekä | and
-sillä | for
-tai | or
-vaan | but
-vai | or
-vaikka | although
-
-
-| prepositions
-
-kanssa | with
-mukaan | according to
-noin | about
-poikki | across
-yli | over, across
-
-| other
-
-kun | when
-niin | so
-nyt | now
-itse | self
-
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
- | A French stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-au | a + le
-aux | a + les
-avec | with
-ce | this
-ces | these
-dans | with
-de | of
-des | de + les
-du | de + le
-elle | she
-en | `of them' etc
-et | and
-eux | them
-il | he
-je | I
-la | the
-le | the
-leur | their
-lui | him
-ma | my (fem)
-mais | but
-me | me
-même | same; as in moi-même (myself) etc
-mes | me (pl)
-moi | me
-mon | my (masc)
-ne | not
-nos | our (pl)
-notre | our
-nous | we
-on | one
-ou | where
-par | by
-pas | not
-pour | for
-qu | que before vowel
-que | that
-qui | who
-sa | his, her (fem)
-se | oneself
-ses | his (pl)
-son | his, her (masc)
-sur | on
-ta | thy (fem)
-te | thee
-tes | thy (pl)
-toi | thee
-ton | thy (masc)
-tu | thou
-un | a
-une | a
-vos | your (pl)
-votre | your
-vous | you
-
- | single letter forms
-
-c | c'
-d | d'
-j | j'
-l | l'
-à | to, at
-m | m'
-n | n'
-s | s'
-t | t'
-y | there
-
- | forms of être (not including the infinitive):
-été
-étée
-étées
-étés
-étant
-suis
-es
-est
-sommes
-êtes
-sont
-serai
-seras
-sera
-serons
-serez
-seront
-serais
-serait
-serions
-seriez
-seraient
-étais
-était
-étions
-étiez
-étaient
-fus
-fut
-fûmes
-fûtes
-furent
-sois
-soit
-soyons
-soyez
-soient
-fusse
-fusses
-fût
-fussions
-fussiez
-fussent
-
- | forms of avoir (not including the infinitive):
-ayant
-eu
-eue
-eues
-eus
-ai
-as
-avons
-avez
-ont
-aurai
-auras
-aura
-aurons
-aurez
-auront
-aurais
-aurait
-aurions
-auriez
-auraient
-avais
-avait
-avions
-aviez
-avaient
-eut
-eûmes
-eûtes
-eurent
-aie
-aies
-ait
-ayons
-ayez
-aient
-eusse
-eusses
-eût
-eussions
-eussiez
-eussent
-
- | Later additions (from Jean-Christophe Deschamps)
-ceci | this
-cela | that
-celà | that
-cet | this
-cette | this
-ici | here
-ils | they
-les | the (pl)
-leurs | their (pl)
-quel | which
-quels | which
-quelle | which
-quelles | which
-sans | without
-soi | oneself
-
+++ /dev/null
-
-a
-ach
-ag
-agus
-an
-aon
-ar
-arna
-as
-b'
-ba
-beirt
-bhúr
-caoga
-ceathair
-ceathrar
-chomh
-chtó
-chuig
-chun
-cois
-céad
-cúig
-cúigear
-d'
-daichead
-dar
-de
-deich
-deichniúr
-den
-dhá
-do
-don
-dtí
-dá
-dár
-dó
-faoi
-faoin
-faoina
-faoinár
-fara
-fiche
-gach
-gan
-go
-gur
-haon
-hocht
-i
-iad
-idir
-in
-ina
-ins
-inár
-is
-le
-leis
-lena
-lenár
-m'
-mar
-mo
-mé
-na
-nach
-naoi
-naonúr
-ná
-ní
-níor
-nó
-nócha
-ocht
-ochtar
-os
-roimh
-sa
-seacht
-seachtar
-seachtó
-seasca
-seisear
-siad
-sibh
-sinn
-sna
-sé
-sí
-tar
-thar
-thú
-triúr
-trí
-trína
-trínár
-tríocha
-tú
-um
-ár
-é
-éis
-í
-ó
-ón
-óna
-ónár
+++ /dev/null
-# galican stopwords
-a
-aínda
-alí
-aquel
-aquela
-aquelas
-aqueles
-aquilo
-aquí
-ao
-aos
-as
-así
-á
-ben
-cando
-che
-co
-coa
-comigo
-con
-connosco
-contigo
-convosco
-coas
-cos
-cun
-cuns
-cunha
-cunhas
-da
-dalgunha
-dalgunhas
-dalgún
-dalgúns
-das
-de
-del
-dela
-delas
-deles
-desde
-deste
-do
-dos
-dun
-duns
-dunha
-dunhas
-e
-el
-ela
-elas
-eles
-en
-era
-eran
-esa
-esas
-ese
-eses
-esta
-estar
-estaba
-está
-están
-este
-estes
-estiven
-estou
-eu
-é
-facer
-foi
-foron
-fun
-había
-hai
-iso
-isto
-la
-las
-lle
-lles
-lo
-los
-mais
-me
-meu
-meus
-min
-miña
-miñas
-moi
-na
-nas
-neste
-nin
-no
-non
-nos
-nosa
-nosas
-noso
-nosos
-nós
-nun
-nunha
-nuns
-nunhas
-o
-os
-ou
-ó
-ós
-para
-pero
-pode
-pois
-pola
-polas
-polo
-polos
-por
-que
-se
-senón
-ser
-seu
-seus
-sexa
-sido
-sobre
-súa
-súas
-tamén
-tan
-te
-ten
-teñen
-teño
-ter
-teu
-teus
-ti
-tido
-tiña
-tiven
-túa
-túas
-un
-unha
-unhas
-uns
-vos
-vosa
-vosas
-voso
-vosos
-vós
+++ /dev/null
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# Note: by default this file also contains forms normalized by HindiNormalizer
-# for spelling variation (see section below), such that it can be used whether or
-# not you enable that feature. When adding additional entries to this list,
-# please add the normalized form as well.
-अंदर
-अत
-अपना
-अपनी
-अपने
-अभी
-आदि
-आप
-इत्यादि
-इन
-इनका
-इन्हीं
-इन्हें
-इन्हों
-इस
-इसका
-इसकी
-इसके
-इसमें
-इसी
-इसे
-उन
-उनका
-उनकी
-उनके
-उनको
-उन्हीं
-उन्हें
-उन्हों
-उस
-उसके
-उसी
-उसे
-एक
-एवं
-एस
-ऐसे
-और
-कई
-कर
-करता
-करते
-करना
-करने
-करें
-कहते
-कहा
-का
-काफ़ी
-कि
-कितना
-किन्हें
-किन्हों
-किया
-किर
-किस
-किसी
-किसे
-की
-कुछ
-कुल
-के
-को
-कोई
-कौन
-कौनसा
-गया
-घर
-जब
-जहाँ
-जा
-जितना
-जिन
-जिन्हें
-जिन्हों
-जिस
-जिसे
-जीधर
-जैसा
-जैसे
-जो
-तक
-तब
-तरह
-तिन
-तिन्हें
-तिन्हों
-तिस
-तिसे
-तो
-था
-थी
-थे
-दबारा
-दिया
-दुसरा
-दूसरे
-दो
-द्वारा
-न
-नहीं
-ना
-निहायत
-नीचे
-ने
-पर
-पर
-पहले
-पूरा
-पे
-फिर
-बनी
-बही
-बहुत
-बाद
-बाला
-बिलकुल
-भी
-भीतर
-मगर
-मानो
-मे
-में
-यदि
-यह
-यहाँ
-यही
-या
-यिह
-ये
-रखें
-रहा
-रहे
-ऱ्वासा
-लिए
-लिये
-लेकिन
-व
-वर्ग
-वह
-वह
-वहाँ
-वहीं
-वाले
-वुह
-वे
-वग़ैरह
-संग
-सकता
-सकते
-सबसे
-सभी
-साथ
-साबुत
-साभ
-सारा
-से
-सो
-ही
-हुआ
-हुई
-हुए
-है
-हैं
-हो
-होता
-होती
-होते
-होना
-होने
-# additional normalized forms of the above
-अपनि
-जेसे
-होति
-सभि
-तिंहों
-इंहों
-दवारा
-इसि
-किंहें
-थि
-उंहों
-ओर
-जिंहें
-वहिं
-अभि
-बनि
-हि
-उंहिं
-उंहें
-हें
-वगेरह
-एसे
-रवासा
-कोन
-निचे
-काफि
-उसि
-पुरा
-भितर
-हे
-बहि
-वहां
-कोइ
-यहां
-जिंहों
-तिंहें
-किसि
-कइ
-यहि
-इंहिं
-जिधर
-इंहें
-अदि
-इतयादि
-हुइ
-कोनसा
-इसकि
-दुसरे
-जहां
-अप
-किंहों
-उनकि
-भि
-वरग
-हुअ
-जेसा
-नहिं
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
-| Hungarian stop word list
-| prepared by Anna Tordai
-
-a
-ahogy
-ahol
-aki
-akik
-akkor
-alatt
-által
-általában
-amely
-amelyek
-amelyekben
-amelyeket
-amelyet
-amelynek
-ami
-amit
-amolyan
-amíg
-amikor
-át
-abban
-ahhoz
-annak
-arra
-arról
-az
-azok
-azon
-azt
-azzal
-azért
-aztán
-azután
-azonban
-bár
-be
-belül
-benne
-cikk
-cikkek
-cikkeket
-csak
-de
-e
-eddig
-egész
-egy
-egyes
-egyetlen
-egyéb
-egyik
-egyre
-ekkor
-el
-elég
-ellen
-elő
-először
-előtt
-első
-én
-éppen
-ebben
-ehhez
-emilyen
-ennek
-erre
-ez
-ezt
-ezek
-ezen
-ezzel
-ezért
-és
-fel
-felé
-hanem
-hiszen
-hogy
-hogyan
-igen
-így
-illetve
-ill.
-ill
-ilyen
-ilyenkor
-ison
-ismét
-itt
-jó
-jól
-jobban
-kell
-kellett
-keresztül
-keressünk
-ki
-kívül
-között
-közül
-legalább
-lehet
-lehetett
-legyen
-lenne
-lenni
-lesz
-lett
-maga
-magát
-majd
-majd
-már
-más
-másik
-meg
-még
-mellett
-mert
-mely
-melyek
-mi
-mit
-míg
-miért
-milyen
-mikor
-minden
-mindent
-mindenki
-mindig
-mint
-mintha
-mivel
-most
-nagy
-nagyobb
-nagyon
-ne
-néha
-nekem
-neki
-nem
-néhány
-nélkül
-nincs
-olyan
-ott
-össze
-ő
-ők
-őket
-pedig
-persze
-rá
-s
-saját
-sem
-semmi
-sok
-sokat
-sokkal
-számára
-szemben
-szerint
-szinte
-talán
-tehát
-teljes
-tovább
-továbbá
-több
-úgy
-ugyanis
-új
-újabb
-újra
-után
-utána
-utolsó
-vagy
-vagyis
-valaki
-valami
-valamint
-való
-vagyok
-van
-vannak
-volt
-voltam
-voltak
-voltunk
-vissza
-vele
-viszont
-volna
+++ /dev/null
-# example set of Armenian stopwords.
-այդ
-այլ
-այն
-այս
-դու
-դուք
-եմ
-են
-ենք
-ես
-եք
-է
-էի
-էին
-էինք
-էիր
-էիք
-էր
-ըստ
-թ
-ի
-ին
-իսկ
-իր
-կամ
-համար
-հետ
-հետո
-մենք
-մեջ
-մի
-ն
-նա
-նաև
-նրա
-նրանք
-որ
-որը
-որոնք
-որպես
-ու
-ում
-պիտի
-վրա
-և
+++ /dev/null
-# from appendix D of: A Study of Stemming Effects on Information
-# Retrieval in Bahasa Indonesia
-ada
-adanya
-adalah
-adapun
-agak
-agaknya
-agar
-akan
-akankah
-akhirnya
-aku
-akulah
-amat
-amatlah
-anda
-andalah
-antar
-diantaranya
-antara
-antaranya
-diantara
-apa
-apaan
-mengapa
-apabila
-apakah
-apalagi
-apatah
-atau
-ataukah
-ataupun
-bagai
-bagaikan
-sebagai
-sebagainya
-bagaimana
-bagaimanapun
-sebagaimana
-bagaimanakah
-bagi
-bahkan
-bahwa
-bahwasanya
-sebaliknya
-banyak
-sebanyak
-beberapa
-seberapa
-begini
-beginian
-beginikah
-beginilah
-sebegini
-begitu
-begitukah
-begitulah
-begitupun
-sebegitu
-belum
-belumlah
-sebelum
-sebelumnya
-sebenarnya
-berapa
-berapakah
-berapalah
-berapapun
-betulkah
-sebetulnya
-biasa
-biasanya
-bila
-bilakah
-bisa
-bisakah
-sebisanya
-boleh
-bolehkah
-bolehlah
-buat
-bukan
-bukankah
-bukanlah
-bukannya
-cuma
-percuma
-dahulu
-dalam
-dan
-dapat
-dari
-daripada
-dekat
-demi
-demikian
-demikianlah
-sedemikian
-dengan
-depan
-di
-dia
-dialah
-dini
-diri
-dirinya
-terdiri
-dong
-dulu
-enggak
-enggaknya
-entah
-entahlah
-terhadap
-terhadapnya
-hal
-hampir
-hanya
-hanyalah
-harus
-haruslah
-harusnya
-seharusnya
-hendak
-hendaklah
-hendaknya
-hingga
-sehingga
-ia
-ialah
-ibarat
-ingin
-inginkah
-inginkan
-ini
-inikah
-inilah
-itu
-itukah
-itulah
-jangan
-jangankan
-janganlah
-jika
-jikalau
-juga
-justru
-kala
-kalau
-kalaulah
-kalaupun
-kalian
-kami
-kamilah
-kamu
-kamulah
-kan
-kapan
-kapankah
-kapanpun
-dikarenakan
-karena
-karenanya
-ke
-kecil
-kemudian
-kenapa
-kepada
-kepadanya
-ketika
-seketika
-khususnya
-kini
-kinilah
-kiranya
-sekiranya
-kita
-kitalah
-kok
-lagi
-lagian
-selagi
-lah
-lain
-lainnya
-melainkan
-selaku
-lalu
-melalui
-terlalu
-lama
-lamanya
-selama
-selama
-selamanya
-lebih
-terlebih
-bermacam
-macam
-semacam
-maka
-makanya
-makin
-malah
-malahan
-mampu
-mampukah
-mana
-manakala
-manalagi
-masih
-masihkah
-semasih
-masing
-mau
-maupun
-semaunya
-memang
-mereka
-merekalah
-meski
-meskipun
-semula
-mungkin
-mungkinkah
-nah
-namun
-nanti
-nantinya
-nyaris
-oleh
-olehnya
-seorang
-seseorang
-pada
-padanya
-padahal
-paling
-sepanjang
-pantas
-sepantasnya
-sepantasnyalah
-para
-pasti
-pastilah
-per
-pernah
-pula
-pun
-merupakan
-rupanya
-serupa
-saat
-saatnya
-sesaat
-saja
-sajalah
-saling
-bersama
-sama
-sesama
-sambil
-sampai
-sana
-sangat
-sangatlah
-saya
-sayalah
-se
-sebab
-sebabnya
-sebuah
-tersebut
-tersebutlah
-sedang
-sedangkan
-sedikit
-sedikitnya
-segala
-segalanya
-segera
-sesegera
-sejak
-sejenak
-sekali
-sekalian
-sekalipun
-sesekali
-sekaligus
-sekarang
-sekarang
-sekitar
-sekitarnya
-sela
-selain
-selalu
-seluruh
-seluruhnya
-semakin
-sementara
-sempat
-semua
-semuanya
-sendiri
-sendirinya
-seolah
-seperti
-sepertinya
-sering
-seringnya
-serta
-siapa
-siapakah
-siapapun
-disini
-disinilah
-sini
-sinilah
-sesuatu
-sesuatunya
-suatu
-sesudah
-sesudahnya
-sudah
-sudahkah
-sudahlah
-supaya
-tadi
-tadinya
-tak
-tanpa
-setelah
-telah
-tentang
-tentu
-tentulah
-tentunya
-tertentu
-seterusnya
-tapi
-tetapi
-setiap
-tiap
-setidaknya
-tidak
-tidakkah
-tidaklah
-toh
-waduh
-wah
-wahai
-sewaktu
-walau
-walaupun
-wong
-yaitu
-yakni
-yang
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
- | An Italian stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-ad | a (to) before vowel
-al | a + il
-allo | a + lo
-ai | a + i
-agli | a + gli
-all | a + l'
-agl | a + gl'
-alla | a + la
-alle | a + le
-con | with
-col | con + il
-coi | con + i (forms collo, cogli etc are now very rare)
-da | from
-dal | da + il
-dallo | da + lo
-dai | da + i
-dagli | da + gli
-dall | da + l'
-dagl | da + gll'
-dalla | da + la
-dalle | da + le
-di | of
-del | di + il
-dello | di + lo
-dei | di + i
-degli | di + gli
-dell | di + l'
-degl | di + gl'
-della | di + la
-delle | di + le
-in | in
-nel | in + el
-nello | in + lo
-nei | in + i
-negli | in + gli
-nell | in + l'
-negl | in + gl'
-nella | in + la
-nelle | in + le
-su | on
-sul | su + il
-sullo | su + lo
-sui | su + i
-sugli | su + gli
-sull | su + l'
-sugl | su + gl'
-sulla | su + la
-sulle | su + le
-per | through, by
-tra | among
-contro | against
-io | I
-tu | thou
-lui | he
-lei | she
-noi | we
-voi | you
-loro | they
-mio | my
-mia |
-miei |
-mie |
-tuo |
-tua |
-tuoi | thy
-tue |
-suo |
-sua |
-suoi | his, her
-sue |
-nostro | our
-nostra |
-nostri |
-nostre |
-vostro | your
-vostra |
-vostri |
-vostre |
-mi | me
-ti | thee
-ci | us, there
-vi | you, there
-lo | him, the
-la | her, the
-li | them
-le | them, the
-gli | to him, the
-ne | from there etc
-il | the
-un | a
-uno | a
-una | a
-ma | but
-ed | and
-se | if
-perché | why, because
-anche | also
-come | how
-dov | where (as dov')
-dove | where
-che | who, that
-chi | who
-cui | whom
-non | not
-più | more
-quale | who, that
-quanto | how much
-quanti |
-quanta |
-quante |
-quello | that
-quelli |
-quella |
-quelle |
-questo | this
-questi |
-questa |
-queste |
-si | yes
-tutto | all
-tutti | all
-
- | single letter forms:
-
-a | at
-c | as c' for ce or ci
-e | and
-i | the
-l | as l'
-o | or
-
- | forms of avere, to have (not including the infinitive):
-
-ho
-hai
-ha
-abbiamo
-avete
-hanno
-abbia
-abbiate
-abbiano
-avrò
-avrai
-avrà
-avremo
-avrete
-avranno
-avrei
-avresti
-avrebbe
-avremmo
-avreste
-avrebbero
-avevo
-avevi
-aveva
-avevamo
-avevate
-avevano
-ebbi
-avesti
-ebbe
-avemmo
-aveste
-ebbero
-avessi
-avesse
-avessimo
-avessero
-avendo
-avuto
-avuta
-avuti
-avute
-
- | forms of essere, to be (not including the infinitive):
-sono
-sei
-è
-siamo
-siete
-sia
-siate
-siano
-sarò
-sarai
-sarà
-saremo
-sarete
-saranno
-sarei
-saresti
-sarebbe
-saremmo
-sareste
-sarebbero
-ero
-eri
-era
-eravamo
-eravate
-erano
-fui
-fosti
-fu
-fummo
-foste
-furono
-fossi
-fosse
-fossimo
-fossero
-essendo
-
- | forms of fare, to do (not including the infinitive, fa, fat-):
-faccio
-fai
-facciamo
-fanno
-faccia
-facciate
-facciano
-farò
-farai
-farà
-faremo
-farete
-faranno
-farei
-faresti
-farebbe
-faremmo
-fareste
-farebbero
-facevo
-facevi
-faceva
-facevamo
-facevate
-facevano
-feci
-facesti
-fece
-facemmo
-faceste
-fecero
-facessi
-facesse
-facessimo
-facessero
-facendo
-
- | forms of stare, to be (not including the infinitive):
-sto
-stai
-sta
-stiamo
-stanno
-stia
-stiate
-stiano
-starò
-starai
-starà
-staremo
-starete
-staranno
-starei
-staresti
-starebbe
-staremmo
-stareste
-starebbero
-stavo
-stavi
-stava
-stavamo
-stavate
-stavano
-stetti
-stesti
-stette
-stemmo
-steste
-stettero
-stessi
-stesse
-stessimo
-stessero
-stando
+++ /dev/null
-#
-# This file defines a stopword set for Japanese.
-#
-# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
-# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
-# for frequency lists, etc. that can be useful for making your own set (if desired)
-#
-# Note that there is an overlap between these stopwords and the terms stopped when used
-# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
-# that comments are not allowed on the same line as stopwords.
-#
-# Also note that stopping is done in a case-insensitive manner. Change your StopFilter
-# configuration if you need case-sensitive stopping. Lastly, note that stopping is done
-# using the same character width as the entries in this file. Since this StopFilter is
-# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
-# entries to be in half-width and your kana entries to be in full-width.
-#
-の
-に
-は
-を
-た
-が
-で
-て
-と
-し
-れ
-さ
-ある
-いる
-も
-する
-から
-な
-こと
-として
-い
-や
-れる
-など
-なっ
-ない
-この
-ため
-その
-あっ
-よう
-また
-もの
-という
-あり
-まで
-られ
-なる
-へ
-か
-だ
-これ
-によって
-により
-おり
-より
-による
-ず
-なり
-られる
-において
-ば
-なかっ
-なく
-しかし
-について
-せ
-だっ
-その後
-できる
-それ
-う
-ので
-なお
-のみ
-でき
-き
-つ
-における
-および
-いう
-さらに
-でも
-ら
-たり
-その他
-に関する
-たち
-ます
-ん
-なら
-に対して
-特に
-せる
-及び
-これら
-とき
-では
-にて
-ほか
-ながら
-うち
-そして
-とともに
-ただし
-かつて
-それぞれ
-または
-お
-ほど
-ものの
-に対する
-ほとんど
-と共に
-といった
-です
-とも
-ところ
-ここ
-##### End of file
+++ /dev/null
-# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
-# the original list of over 800 forms was refined:
-# pronouns, adverbs, interjections were removed
-#
-# prepositions
-aiz
-ap
-ar
-apakš
-ārpus
-augšpus
-bez
-caur
-dēļ
-gar
-iekš
-iz
-kopš
-labad
-lejpus
-līdz
-no
-otrpus
-pa
-par
-pār
-pēc
-pie
-pirms
-pret
-priekš
-starp
-šaipus
-uz
-viņpus
-virs
-virspus
-zem
-apakšpus
-# Conjunctions
-un
-bet
-jo
-ja
-ka
-lai
-tomēr
-tikko
-turpretī
-arī
-kaut
-gan
-tādēļ
-tā
-ne
-tikvien
-vien
-kā
-ir
-te
-vai
-kamēr
-# Particles
-ar
-diezin
-droši
-diemžēl
-nebūt
-ik
-it
-taču
-nu
-pat
-tiklab
-iekšpus
-nedz
-tik
-nevis
-turpretim
-jeb
-iekam
-iekām
-iekāms
-kolīdz
-līdzko
-tiklīdz
-jebšu
-tālab
-tāpēc
-nekā
-itin
-jā
-jau
-jel
-nē
-nezin
-tad
-tikai
-vis
-tak
-iekams
-vien
-# modal verbs
-būt
-biju
-biji
-bija
-bijām
-bijāt
-esmu
-esi
-esam
-esat
-būšu
-būsi
-būs
-būsim
-būsiet
-tikt
-tiku
-tiki
-tika
-tikām
-tikāt
-tieku
-tiec
-tiek
-tiekam
-tiekat
-tikšu
-tiks
-tiksim
-tiksiet
-tapt
-tapi
-tapāt
-topat
-tapšu
-tapsi
-taps
-tapsim
-tapsiet
-kļūt
-kļuvu
-kļuvi
-kļuva
-kļuvām
-kļuvāt
-kļūstu
-kļūsti
-kļūst
-kļūstam
-kļūstat
-kļūšu
-kļūsi
-kļūs
-kļūsim
-kļūsiet
-# verbs
-varēt
-varēju
-varējām
-varēšu
-varēsim
-var
-varēji
-varējāt
-varēsi
-varēsiet
-varat
-varēja
-varēs
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
- | A Dutch stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large sample of Dutch text.
-
- | Dutch stop words frequently exhibit homonym clashes. These are indicated
- | clearly below.
-
-de | the
-en | and
-van | of, from
-ik | I, the ego
-te | (1) chez, at etc, (2) to, (3) too
-dat | that, which
-die | that, those, who, which
-in | in, inside
-een | a, an, one
-hij | he
-het | the, it
-niet | not, nothing, naught
-zijn | (1) to be, being, (2) his, one's, its
-is | is
-was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
-op | on, upon, at, in, up, used up
-aan | on, upon, to (as dative)
-met | with, by
-als | like, such as, when
-voor | (1) before, in front of, (2) furrow
-had | had, past tense all persons sing. of 'hebben' (have)
-er | there
-maar | but, only
-om | round, about, for etc
-hem | him
-dan | then
-zou | should/would, past tense all persons sing. of 'zullen'
-of | or, whether, if
-wat | what, something, anything
-mijn | possessive and noun 'mine'
-men | people, 'one'
-dit | this
-zo | so, thus, in this way
-door | through by
-over | over, across
-ze | she, her, they, them
-zich | oneself
-bij | (1) a bee, (2) by, near, at
-ook | also, too
-tot | till, until
-je | you
-mij | me
-uit | out of, from
-der | Old Dutch form of 'van der' still found in surnames
-daar | (1) there, (2) because
-haar | (1) her, their, them, (2) hair
-naar | (1) unpleasant, unwell etc, (2) towards, (3) as
-heb | present first person sing. of 'to have'
-hoe | how, why
-heeft | present third person sing. of 'to have'
-hebben | 'to have' and various parts thereof
-deze | this
-u | you
-want | (1) for, (2) mitten, (3) rigging
-nog | yet, still
-zal | 'shall', first and third person sing. of verb 'zullen' (will)
-me | me
-zij | she, they
-nu | now
-ge | 'thou', still used in Belgium and south Netherlands
-geen | none
-omdat | because
-iets | something, somewhat
-worden | to become, grow, get
-toch | yet, still
-al | all, every, each
-waren | (1) 'were' (2) to wander, (3) wares, (3)
-veel | much, many
-meer | (1) more, (2) lake
-doen | to do, to make
-toen | then, when
-moet | noun 'spot/mote' and present form of 'to must'
-ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
-zonder | without
-kan | noun 'can' and present form of 'to be able'
-hun | their, them
-dus | so, consequently
-alles | all, everything, anything
-onder | under, beneath
-ja | yes, of course
-eens | once, one day
-hier | here
-wie | who
-werd | imperfect third person sing. of 'become'
-altijd | always
-doch | yet, but etc
-wordt | present third person sing. of 'become'
-wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
-kunnen | to be able
-ons | us/our
-zelf | self
-tegen | against, towards, at
-na | after, near
-reeds | already
-wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
-kon | could; past tense of 'to be able'
-niets | nothing
-uw | your
-iemand | somebody
-geweest | been; past participle of 'be'
-andere | other
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
- | A Norwegian stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This stop word list is for the dominant bokmål dialect. Words unique
- | to nynorsk are marked *.
-
- | Revised by Jan Bruusgaard <Jan.Bruusgaard@ssb.no>, Jan 2005
-
-og | and
-i | in
-jeg | I
-det | it/this/that
-at | to (w. inf.)
-en | a/an
-et | a/an
-den | it/this/that
-til | to
-er | is/am/are
-som | who/that
-på | on
-de | they / you(formal)
-med | with
-han | he
-av | of
-ikke | not
-ikkje | not *
-der | there
-så | so
-var | was/were
-meg | me
-seg | you
-men | but
-ett | one
-har | have
-om | about
-vi | we
-min | my
-mitt | my
-ha | have
-hadde | had
-hun | she
-nå | now
-over | over
-da | when/as
-ved | by/know
-fra | from
-du | you
-ut | out
-sin | your
-dem | them
-oss | us
-opp | up
-man | you/one
-kan | can
-hans | his
-hvor | where
-eller | or
-hva | what
-skal | shall/must
-selv | self (reflective)
-sjøl | self (reflective)
-her | here
-alle | all
-vil | will
-bli | become
-ble | became
-blei | became *
-blitt | have become
-kunne | could
-inn | in
-når | when
-være | be
-kom | come
-noen | some
-noe | some
-ville | would
-dere | you
-som | who/which/that
-deres | their/theirs
-kun | only/just
-ja | yes
-etter | after
-ned | down
-skulle | should
-denne | this
-for | for/because
-deg | you
-si | hers/his
-sine | hers/his
-sitt | hers/his
-mot | against
-å | to
-meget | much
-hvorfor | why
-dette | this
-disse | these/those
-uten | without
-hvordan | how
-ingen | none
-din | your
-ditt | your
-blir | become
-samme | same
-hvilken | which
-hvilke | which (plural)
-sånn | such a
-inni | inside/within
-mellom | between
-vår | our
-hver | each
-hvem | who
-vors | us/ours
-hvis | whose
-både | both
-bare | only/just
-enn | than
-fordi | as/because
-før | before
-mange | many
-også | also
-slik | just
-vært | been
-være | to be
-båe | both *
-begge | both
-siden | since
-dykk | your *
-dykkar | yours *
-dei | they *
-deira | them *
-deires | theirs *
-deim | them *
-di | your (fem.) *
-då | as/when *
-eg | I *
-ein | a/an *
-eit | a/an *
-eitt | a/an *
-elles | or *
-honom | he *
-hjå | at *
-ho | she *
-hoe | she *
-henne | her
-hennar | her/hers
-hennes | hers
-hoss | how *
-hossen | how *
-ikkje | not *
-ingi | noone *
-inkje | noone *
-korleis | how *
-korso | how *
-kva | what/which *
-kvar | where *
-kvarhelst | where *
-kven | who/whom *
-kvi | why *
-kvifor | why *
-me | we *
-medan | while *
-mi | my *
-mine | my *
-mykje | much *
-no | now *
-nokon | some (masc./neut.) *
-noka | some (fem.) *
-nokor | some *
-noko | some *
-nokre | some *
-si | his/hers *
-sia | since *
-sidan | since *
-so | so *
-somt | some *
-somme | some *
-um | about*
-upp | up *
-vere | be *
-vore | was *
-verte | become *
-vort | become *
-varte | became *
-vart | became *
-
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
- | A Portuguese stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-
- | The following is a ranked list (commonest to rarest) of stopwords
- | deriving from a large sample of text.
-
- | Extra words have been added at the end.
-
-de | of, from
-a | the; to, at; her
-o | the; him
-que | who, that
-e | and
-do | de + o
-da | de + a
-em | in
-um | a
-para | for
- | é from SER
-com | with
-não | not, no
-uma | a
-os | the; them
-no | em + o
-se | himself etc
-na | em + a
-por | for
-mais | more
-as | the; them
-dos | de + os
-como | as, like
-mas | but
- | foi from SER
-ao | a + o
-ele | he
-das | de + as
- | tem from TER
-à | a + a
-seu | his
-sua | her
-ou | or
- | ser from SER
-quando | when
-muito | much
- | há from HAV
-nos | em + os; us
-já | already, now
- | está from EST
-eu | I
-também | also
-só | only, just
-pelo | per + o
-pela | per + a
-até | up to
-isso | that
-ela | he
-entre | between
- | era from SER
-depois | after
-sem | without
-mesmo | same
-aos | a + os
- | ter from TER
-seus | his
-quem | whom
-nas | em + as
-me | me
-esse | that
-eles | they
- | estão from EST
-você | you
- | tinha from TER
- | foram from SER
-essa | that
-num | em + um
-nem | nor
-suas | her
-meu | my
-às | a + as
-minha | my
- | têm from TER
-numa | em + uma
-pelos | per + os
-elas | they
- | havia from HAV
- | seja from SER
-qual | which
- | será from SER
-nós | we
- | tenho from TER
-lhe | to him, her
-deles | of them
-essas | those
-esses | those
-pelas | per + as
-este | this
- | fosse from SER
-dele | of him
-
- | other words. There are many contractions such as naquele = em+aquele,
- | mo = me+o, but they are rare.
- | Indefinite article plural forms are also rare.
-
-tu | thou
-te | thee
-vocês | you (plural)
-vos | you
-lhes | to them
-meus | my
-minhas
-teu | thy
-tua
-teus
-tuas
-nosso | our
-nossa
-nossos
-nossas
-
-dela | of her
-delas | of them
-
-esta | this
-estes | these
-estas | these
-aquele | that
-aquela | that
-aqueles | those
-aquelas | those
-isto | this
-aquilo | that
-
- | forms of estar, to be (not including the infinitive):
-estou
-está
-estamos
-estão
-estive
-esteve
-estivemos
-estiveram
-estava
-estávamos
-estavam
-estivera
-estivéramos
-esteja
-estejamos
-estejam
-estivesse
-estivéssemos
-estivessem
-estiver
-estivermos
-estiverem
-
- | forms of haver, to have (not including the infinitive):
-hei
-há
-havemos
-hão
-houve
-houvemos
-houveram
-houvera
-houvéramos
-haja
-hajamos
-hajam
-houvesse
-houvéssemos
-houvessem
-houver
-houvermos
-houverem
-houverei
-houverá
-houveremos
-houverão
-houveria
-houveríamos
-houveriam
-
- | forms of ser, to be (not including the infinitive):
-sou
-somos
-são
-era
-éramos
-eram
-fui
-foi
-fomos
-foram
-fora
-fôramos
-seja
-sejamos
-sejam
-fosse
-fôssemos
-fossem
-for
-formos
-forem
-serei
-será
-seremos
-serão
-seria
-seríamos
-seriam
-
- | forms of ter, to have (not including the infinitive):
-tenho
-tem
-temos
-tém
-tinha
-tínhamos
-tinham
-tive
-teve
-tivemos
-tiveram
-tivera
-tivéramos
-tenha
-tenhamos
-tenham
-tivesse
-tivéssemos
-tivessem
-tiver
-tivermos
-tiverem
-terei
-terá
-teremos
-terão
-teria
-teríamos
-teriam
+++ /dev/null
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-acea
-aceasta
-această
-aceea
-acei
-aceia
-acel
-acela
-acele
-acelea
-acest
-acesta
-aceste
-acestea
-aceşti
-aceştia
-acolo
-acum
-ai
-aia
-aibă
-aici
-al
-ăla
-ale
-alea
-ălea
-altceva
-altcineva
-am
-ar
-are
-aş
-aşadar
-asemenea
-asta
-ăsta
-astăzi
-astea
-ăstea
-ăştia
-asupra
-aţi
-au
-avea
-avem
-aveţi
-azi
-bine
-bucur
-bună
-ca
-că
-căci
-când
-care
-cărei
-căror
-cărui
-cât
-câte
-câţi
-către
-câtva
-ce
-cel
-ceva
-chiar
-cînd
-cine
-cineva
-cît
-cîte
-cîţi
-cîtva
-contra
-cu
-cum
-cumva
-curând
-curînd
-da
-dă
-dacă
-dar
-datorită
-de
-deci
-deja
-deoarece
-departe
-deşi
-din
-dinaintea
-dintr
-dintre
-drept
-după
-ea
-ei
-el
-ele
-eram
-este
-eşti
-eu
-face
-fără
-fi
-fie
-fiecare
-fii
-fim
-fiţi
-iar
-ieri
-îi
-îl
-îmi
-împotriva
-în
-înainte
-înaintea
-încât
-încît
-încotro
-între
-întrucât
-întrucît
-îţi
-la
-lângă
-le
-li
-lîngă
-lor
-lui
-mă
-mâine
-mea
-mei
-mele
-mereu
-meu
-mi
-mine
-mult
-multă
-mulţi
-ne
-nicăieri
-nici
-nimeni
-nişte
-noastră
-noastre
-noi
-noştri
-nostru
-nu
-ori
-oricând
-oricare
-oricât
-orice
-oricînd
-oricine
-oricît
-oricum
-oriunde
-până
-pe
-pentru
-peste
-pînă
-poate
-pot
-prea
-prima
-primul
-prin
-printr
-sa
-să
-săi
-sale
-sau
-său
-se
-şi
-sînt
-sîntem
-sînteţi
-spre
-sub
-sunt
-suntem
-sunteţi
-ta
-tăi
-tale
-tău
-te
-ţi
-ţie
-tine
-toată
-toate
-tot
-toţi
-totuşi
-tu
-un
-una
-unde
-undeva
-unei
-unele
-uneori
-unor
-vă
-vi
-voastră
-voastre
-voi
-voştri
-vostru
-vouă
-vreo
-vreun
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
- | a russian stop word list. comments begin with vertical bar. each stop
- | word is at the start of a line.
-
- | this is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
- | letter `ё' is translated to `е'.
-
-и | and
-в | in/into
-во | alternative form
-не | not
-что | what/that
-он | he
-на | on/onto
-я | i
-с | from
-со | alternative form
-как | how
-а | milder form of `no' (but)
-то | conjunction and form of `that'
-все | all
-она | she
-так | so, thus
-его | him
-но | but
-да | yes/and
-ты | thou
-к | towards, by
-у | around, chez
-же | intensifier particle
-вы | you
-за | beyond, behind
-бы | conditional/subj. particle
-по | up to, along
-только | only
-ее | her
-мне | to me
-было | it was
-вот | here is/are, particle
-от | away from
-меня | me
-еще | still, yet, more
-нет | no, there isnt/arent
-о | about
-из | out of
-ему | to him
-теперь | now
-когда | when
-даже | even
-ну | so, well
-вдруг | suddenly
-ли | interrogative particle
-если | if
-уже | already, but homonym of `narrower'
-или | or
-ни | neither
-быть | to be
-был | he was
-него | prepositional form of его
-до | up to
-вас | you accusative
-нибудь | indef. suffix preceded by hyphen
-опять | again
-уж | already, but homonym of `adder'
-вам | to you
-сказал | he said
-ведь | particle `after all'
-там | there
-потом | then
-себя | oneself
-ничего | nothing
-ей | to her
-может | usually with `быть' as `maybe'
-они | they
-тут | here
-где | where
-есть | there is/are
-надо | got to, must
-ней | prepositional form of ей
-для | for
-мы | we
-тебя | thee
-их | them, their
-чем | than
-была | she was
-сам | self
-чтоб | in order to
-без | without
-будто | as if
-человек | man, person, one
-чего | genitive form of `what'
-раз | once
-тоже | also
-себе | to oneself
-под | beneath
-жизнь | life
-будет | will be
-ж | short form of intensifer particle `же'
-тогда | then
-кто | who
-этот | this
-говорил | was saying
-того | genitive form of `that'
-потому | for that reason
-этого | genitive form of `this'
-какой | which
-совсем | altogether
-ним | prepositional form of `его', `они'
-здесь | here
-этом | prepositional form of `этот'
-один | one
-почти | almost
-мой | my
-тем | instrumental/dative plural of `тот', `то'
-чтобы | full form of `in order that'
-нее | her (acc.)
-кажется | it seems
-сейчас | now
-были | they were
-куда | where to
-зачем | why
-сказать | to say
-всех | all (acc., gen. preposn. plural)
-никогда | never
-сегодня | today
-можно | possible, one can
-при | by
-наконец | finally
-два | two
-об | alternative form of `о', about
-другой | another
-хоть | even
-после | after
-над | above
-больше | more
-тот | that one (masc.)
-через | across, in
-эти | these
-нас | us
-про | about
-всего | in all, only, of all
-них | prepositional form of `они' (they)
-какая | which, feminine
-много | lots
-разве | interrogative particle
-сказала | she said
-три | three
-эту | this, acc. fem. sing.
-моя | my, feminine
-впрочем | moreover, besides
-хорошо | good
-свою | ones own, acc. fem. sing.
-этой | oblique form of `эта', fem. `this'
-перед | in front of
-иногда | sometimes
-лучше | better
-чуть | a little
-том | preposn. form of `that one'
-нельзя | one must not
-такой | such a one
-им | to them
-более | more
-всегда | always
-конечно | of course
-всю | acc. fem. sing of `all'
-между | between
-
-
- | b: some paradigms
- |
- | personal pronouns
- |
- | я меня мне мной [мною]
- | ты тебя тебе тобой [тобою]
- | он его ему им [него, нему, ним]
- | она ее эи ею [нее, нэи, нею]
- | оно его ему им [него, нему, ним]
- |
- | мы нас нам нами
- | вы вас вам вами
- | они их им ими [них, ним, ними]
- |
- | себя себе собой [собою]
- |
- | demonstrative pronouns: этот (this), тот (that)
- |
- | этот эта это эти
- | этого эты это эти
- | этого этой этого этих
- | этому этой этому этим
- | этим этой этим [этою] этими
- | этом этой этом этих
- |
- | тот та то те
- | того ту то те
- | того той того тех
- | тому той тому тем
- | тем той тем [тою] теми
- | том той том тех
- |
- | determinative pronouns
- |
- | (a) весь (all)
- |
- | весь вся все все
- | всего всю все все
- | всего всей всего всех
- | всему всей всему всем
- | всем всей всем [всею] всеми
- | всем всей всем всех
- |
- | (b) сам (himself etc)
- |
- | сам сама само сами
- | самого саму само самих
- | самого самой самого самих
- | самому самой самому самим
- | самим самой самим [самою] самими
- | самом самой самом самих
- |
- | stems of verbs `to be', `to have', `to do' and modal
- |
- | быть бы буд быв есть суть
- | име
- | дел
- | мог мож мочь
- | уме
- | хоч хот
- | долж
- | можн
- | нужн
- | нельзя
-
+++ /dev/null
- | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
-
- | A Swedish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
- | Swedish stop words occasionally exhibit homonym clashes. For example
- | så = so, but also seed. These are indicated clearly below.
-
-och | and
-det | it, this/that
-att | to (with infinitive)
-i | in, at
-en | a
-jag | I
-hon | she
-som | who, that
-han | he
-på | on
-den | it, this/that
-med | with
-var | where, each
-sig | him(self) etc
-för | for
-så | so (also: seed)
-till | to
-är | is
-men | but
-ett | a
-om | if; around, about
-hade | had
-de | they, these/those
-av | of
-icke | not, no
-mig | me
-du | you
-henne | her
-då | then, when
-sin | his
-nu | now
-har | have
-inte | inte någon = no one
-hans | his
-honom | him
-skulle | 'sake'
-hennes | her
-där | there
-min | my
-man | one (pronoun)
-ej | nor
-vid | at, by, on (also: vast)
-kunde | could
-något | some etc
-från | from, off
-ut | out
-när | when
-efter | after, behind
-upp | up
-vi | we
-dem | them
-vara | be
-vad | what
-över | over
-än | than
-dig | you
-kan | can
-sina | his
-här | here
-ha | have
-mot | towards
-alla | all
-under | under (also: wonder)
-någon | some etc
-eller | or (else)
-allt | all
-mycket | much
-sedan | since
-ju | why
-denna | this/that
-själv | myself, yourself etc
-detta | this/that
-åt | to
-utan | without
-varit | was
-hur | how
-ingen | no
-mitt | my
-ni | you
-bli | to be, become
-blev | from bli
-oss | us
-din | thy
-dessa | these/those
-några | some etc
-deras | their
-blir | from bli
-mina | my
-samma | (the) same
-vilken | who, that
-er | you, your
-sådan | such a
-vår | our
-blivit | from bli
-dess | its
-inom | within
-mellan | between
-sådant | such a
-varför | why
-varje | each
-vilka | who, that
-ditt | thy
-vem | who
-vilket | who, that
-sitta | his
-sådana | such a
-vart | each
-dina | thy
-vars | whose
-vårt | our
-våra | our
-ert | your
-era | your
-vilkas | whose
-
+++ /dev/null
-# Thai stopwords from:
-# "Opinion Detection in Thai Political News Columns
-# Based on Subjectivity Analysis"
-# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
-ไว้
-ไม่
-ไป
-ได้
-ให้
-ใน
-โดย
-แห่ง
-แล้ว
-และ
-แรก
-แบบ
-แต่
-เอง
-เห็น
-เลย
-เริ่ม
-เรา
-เมื่อ
-เพื่อ
-เพราะ
-เป็นการ
-เป็น
-เปิดเผย
-เปิด
-เนื่องจาก
-เดียวกัน
-เดียว
-เช่น
-เฉพาะ
-เคย
-เข้า
-เขา
-อีก
-อาจ
-อะไร
-ออก
-อย่าง
-อยู่
-อยาก
-หาก
-หลาย
-หลังจาก
-หลัง
-หรือ
-หนึ่ง
-ส่วน
-ส่ง
-สุด
-สําหรับ
-ว่า
-วัน
-ลง
-ร่วม
-ราย
-รับ
-ระหว่าง
-รวม
-ยัง
-มี
-มาก
-มา
-พร้อม
-พบ
-ผ่าน
-ผล
-บาง
-น่า
-นี้
-นํา
-นั้น
-นัก
-นอกจาก
-ทุก
-ที่สุด
-ที่
-ทําให้
-ทํา
-ทาง
-ทั้งนี้
-ทั้ง
-ถ้า
-ถูก
-ถึง
-ต้อง
-ต่างๆ
-ต่าง
-ต่อ
-ตาม
-ตั้งแต่
-ตั้ง
-ด้าน
-ด้วย
-ดัง
-ซึ่ง
-ช่วง
-จึง
-จาก
-จัด
-จะ
-คือ
-ความ
-ครั้ง
-คง
-ขึ้น
-ของ
-ขอ
-ขณะ
-ก่อน
-ก็
-การ
-กับ
-กัน
-กว่า
-กล่าว
+++ /dev/null
-# Turkish stopwords from LUCENE-559
-# merged with the list from "Information Retrieval on Turkish Texts"
-# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
-acaba
-altmış
-altı
-ama
-ancak
-arada
-aslında
-ayrıca
-bana
-bazı
-belki
-ben
-benden
-beni
-benim
-beri
-beş
-bile
-bin
-bir
-birçok
-biri
-birkaç
-birkez
-birşey
-birşeyi
-biz
-bize
-bizden
-bizi
-bizim
-böyle
-böylece
-bu
-buna
-bunda
-bundan
-bunlar
-bunları
-bunların
-bunu
-bunun
-burada
-çok
-çünkü
-da
-daha
-dahi
-de
-defa
-değil
-diğer
-diye
-doksan
-dokuz
-dolayı
-dolayısıyla
-dört
-edecek
-eden
-ederek
-edilecek
-ediliyor
-edilmesi
-ediyor
-eğer
-elli
-en
-etmesi
-etti
-ettiği
-ettiğini
-gibi
-göre
-halen
-hangi
-hatta
-hem
-henüz
-hep
-hepsi
-her
-herhangi
-herkesin
-hiç
-hiçbir
-için
-iki
-ile
-ilgili
-ise
-işte
-itibaren
-itibariyle
-kadar
-karşın
-katrilyon
-kendi
-kendilerine
-kendini
-kendisi
-kendisine
-kendisini
-kez
-ki
-kim
-kimden
-kime
-kimi
-kimse
-kırk
-milyar
-milyon
-mu
-mü
-mı
-nasıl
-ne
-neden
-nedenle
-nerde
-nerede
-nereye
-niye
-niçin
-o
-olan
-olarak
-oldu
-olduğu
-olduğunu
-olduklarını
-olmadı
-olmadığı
-olmak
-olması
-olmayan
-olmaz
-olsa
-olsun
-olup
-olur
-olursa
-oluyor
-on
-ona
-ondan
-onlar
-onlardan
-onları
-onların
-onu
-onun
-otuz
-oysa
-öyle
-pek
-rağmen
-sadece
-sanki
-sekiz
-seksen
-sen
-senden
-seni
-senin
-siz
-sizden
-sizi
-sizin
-şey
-şeyden
-şeyi
-şeyler
-şöyle
-şu
-şuna
-şunda
-şundan
-şunları
-şunu
-tarafından
-trilyon
-tüm
-üç
-üzere
-var
-vardı
-ve
-veya
-ya
-yani
-yapacak
-yapılan
-yapılması
-yapıyor
-yapmak
-yaptı
-yaptığı
-yaptığını
-yaptıkları
-yedi
-yerine
-yetmiş
-yine
-yirmi
-yoksa
-yüz
-zaten
+++ /dev/null
-#
-# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
-#
-# Add entries to this file in order to override the statistical model in terms
-# of segmentation, readings and part-of-speech tags. Notice that entries do
-# not have weights since they are always used when found. This is by-design
-# in order to maximize ease-of-use.
-#
-# Entries are defined using the following CSV format:
-# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
-#
-# Notice that a single half-width space separates tokens and readings, and
-# that the number tokens and readings must match exactly.
-#
-# Also notice that multiple entries with the same <text> is undefined.
-#
-# Whitespace only lines are ignored. Comments are not allowed on entry lines.
-#
-
-# Custom segmentation for kanji compounds
-日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
-関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
-
-# Custom segmentation for compound katakana
-トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
-ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
-
-# Custom reading for former sumo wrestler
-朝青龍,朝青龍,アサショウリュウ,カスタム人名
+++ /dev/null
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# Use a protected word file to protect against the stemmer reducing two
-# unrelated words to the same base word.
-
-# Some non-words that normally won't be encountered,
-# just to test that they won't be stemmed.
-dontstems
-zwhacky
-
+++ /dev/null
-<?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-schemaless" 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.
- -->
-
- <!-- In this "schemaless" example, only two fields are pre-declared: id and _version_.
- All other fields will be type guessed and added via the
- "add-unknown-fields-to-the-schema" update request processor chain declared
- in solrconfig.xml.
- -->
- <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
- <field name="_version_" type="long" indexed="true" stored="true"/>
-
-
- <!-- 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
-
- NB: use of "*" dynamic fields will disable field type guessing and adding
- unknown fields to the schema. -->
- <!--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"/>
-
- <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="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"/>
-
- <fieldType name="tints" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tfloats" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tlongs" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tdoubles" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
-
- <!-- 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"/>
-
- <fieldType name="tdates" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
-
-
- <!--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" multiValued="true">
- <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://docs.oracle.com/javase/7/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"/> -->
- <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
- </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>
projects / lui-solr.git / commitdiff