tonyair/silverstripe-fulltextsearch
1
0
Fork 0
mirror of https://github.com/silverstripe/silverstripe-fulltextsearch synced 2024-10-22 14:05:29 +02:00
Code Issues Projects Releases Wiki Activity

Merge pull request #35 from hafriedlander/solr4

Browse Source 
API Add support for Solr 4 and make it the default
This commit is contained in:
Mateusz U 2013-11-07 19:04:02 -08:00
commit efdc96e937
23 changed files with 6364 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

108
code/solr/Solr.php
View File

@ -11,9 +11,13 @@ class Solr {
* path (default: /solr) - The suburl the solr service is available on
*
* Optional fields:
* extraspath (default: <basefolder>/fulltextsearch/conf/extras/) - Absolute path to
* version (default: 4) - The Solr server version. Currently supports 3 and 4 (you can add a sub-version like 4.5 if
* you like, but currently it has no effect)
* service (default: depends on version, Solr3Service for 3, Solr4Service for 4)
* the class that provides actual communcation to the Solr server
* extraspath (default: <basefolder>/fulltextsearch/conf/solr/{version}/extras/) - Absolute path to
* the folder containing templates which are used for generating the schema and field definitions.
* templates (default: <basefolder>/fulltextsearch/conf/templates/) - Absolute path to
* templates (default: <basefolder>/fulltextsearch/conf/solr/{version}/templates/) - Absolute path to
* the configuration default files, e.g. solrconfig.xml.
*
* indexstore => an array with
@ -29,36 +33,87 @@ class Solr {
* path (default: /solrindex) - The suburl on the solr host that is set up to accept index configurations via webdav
* remotepath - The path that the Solr server will read the index configurations from
*/
static $solr_options = array();
protected static $solr_options = array();
/** A cache of solr_options with the defaults all merged in */
protected static $merged_solr_options = null;
/**
* Update the configuration for Solr. See $solr_options for a discussion of the accepted array keys
* @param array $options - The options to update
*/
static function configure_server($options = array()) {
self::$solr_options = array_merge(array(
self::$solr_options = array_merge(self::$solr_options, $options);
self::$merged_solr_options = null;
self::$service_singleton = null;
self::$service_core_singletons = array();
}
/**
* Get the configured Solr options with the defaults all merged in
* @return array - The merged options
*/
static function solr_options() {
if (self::$merged_solr_options) return self::$merged_solr_options;
$defaults = array(
'host' => 'localhost',
'port' => 8983,
'path' => '/solr',
'extraspath' => Director::baseFolder().'/fulltextsearch/conf/extras/',
'templatespath' => Director::baseFolder().'/fulltextsearch/conf/templates/',
), self::$solr_options, $options);
}
'version' => '4'
);
static protected $service_class = 'SolrService';
// Build some by-version defaults
$version = isset(self::$solr_options['version']) ? self::$solr_options['version'] : $defaults['version'];
static function set_service_class($class) {
self::$service_class = $class;
self::$service = null;
}
static protected $service = null;
static function service($core = null) {
if (!self::$service) {
if (!self::$solr_options) user_error('No configuration for Solr server provided', E_USER_ERROR);
$class = self::$service_class;
self::$service = new $class(self::$solr_options['host'], self::$solr_options['port'], self::$solr_options['path']);
if (version_compare($version, '4', '>=')){
$versionDefaults = array(
'service' => 'Solr4Service',
'extraspath' => Director::baseFolder().'/fulltextsearch/conf/solr/4/extras/',
'templatespath' => Director::baseFolder().'/fulltextsearch/conf/solr/4/templates/',
);
}
else {
$versionDefaults = array(
'service' => 'Solr3Service',
'extraspath' => Director::baseFolder().'/fulltextsearch/conf/solr/3/extras/',
'templatespath' => Director::baseFolder().'/fulltextsearch/conf/solr/3/templates/',
);
}
return $core ? self::$service->serviceForCore($core) : self::$service;
return (self::$merged_solr_options = array_merge($defaults, $versionDefaults, self::$solr_options));
}
static function set_service_class($class) {
user_error('set_service_class is deprecated - pass as part of $options to configure_server', E_USER_WARNING);
self::configure_server(array('service' => $class));
}
/** @var SolrService | null - The instance of SolrService for core management */
static protected $service_singleton = null;
/** @var [SolrService_Core] - The instances of SolrService_Core for each core */
static protected $service_core_singletons = array();
static function service($core = null) {
$options = self::solr_options();
if (!self::$service_singleton) {
self::$service_singleton = Object::create(
$options['service'], $options['host'], $options['port'], $options['path']
);
}
if ($core) {
if (!isset(self::$service_core_singletons[$core])) {
self::$service_core_singletons[$core] = self::$service_singleton->serviceForCore($core);
}
return self::$service_core_singletons[$core];
} else {
return self::$service_singleton;
}
}
static function get_indexes() {
@ -66,8 +121,8 @@ class Solr {
}
/**
* Include the thirdparty Solr client api library. Done this way to avoid issues where code is called in mysite/_config
* before fulltextsearch/_config has a change to update the include path.
* Include the thirdparty Solr client api library. Done this way to avoid issues where code is called in
* mysite/_config before fulltextsearch/_config has a change to update the include path.
*/
static function include_client_api() {
static $included = false;
@ -88,8 +143,9 @@ class Solr_Configure extends BuildTask {
public function run($request) {
$service = Solr::service();
$indexes = Solr::get_indexes();
$options = Solr::solr_options();
if (!isset(Solr::$solr_options['indexstore']) || !($indexstore = Solr::$solr_options['indexstore'])) {
if (!isset($options['indexstore']) || !($indexstore = $options['indexstore'])) {
user_error('No index configuration for Solr provided', E_USER_ERROR);
}

8
code/solr/Solr3Service.php Normal file
View File

@ -0,0 +1,8 @@
<?php
class Solr3Service_Core extends SolrService_Core {
}
class Solr3Service extends SolrService {
private static $core_class = 'Solr3Service_Core';
}

25
code/solr/Solr4Service.php Normal file
View File

@ -0,0 +1,25 @@
<?php
class Solr4Service_Core extends SolrService_Core {
/**
* Replace underlying commit function to remove waitFlush in 4.0+, since it's been deprecated and 4.4 throws errors
* if you pass it
*/
public function commit($expungeDeletes = false, $waitFlush = null, $waitSearcher = true, $timeout = 3600) {
if ($waitFlush) {
user_error('waitFlush must be false when using Solr 4.0+' . E_USER_ERROR);
}
$expungeValue = $expungeDeletes ? 'true' : 'false';
$searcherValue = $waitSearcher ? 'true' : 'false';
$rawPost = '<commit expungeDeletes="' . $expungeValue . '" waitSearcher="' . $searcherValue . '" />';
return $this->_sendRawPost($this->_updateUrl, $rawPost, $timeout);
}
}
class Solr4Service extends SolrService {
private static $core_class = 'Solr4Service_Core';
}

4
code/solr/SolrConfigStore.php
View File

@ -80,10 +80,12 @@ class SolrConfigStore_File implements SolrConfigStore {
*/
class SolrConfigStore_WebDAV implements SolrConfigStore {
function __construct($config) {
$options = Solr::solr_options();
$this->url = implode('', array(
'http://',
isset($config['auth']) ? $config['auth'].'@' : '',
Solr::$solr_options['host'] . ':' . Solr::$solr_options['port'],
$options['host'].':'.$options['port'],
$config['path']
));
$this->remote = $config['remotepath'];

6
code/solr/SolrIndex.php
View File

@ -36,7 +36,8 @@ abstract class SolrIndex extends SearchIndex {
* templates which are used for generating the schema and field definitions.
*/
function getTemplatesPath() {
return $this->templatesPath ? $this->templatesPath : Solr::$solr_options['templatespath'];
$globalOptions = Solr::solr_options();
return $this->templatesPath ? $this->templatesPath : $globalOptions['templatespath'];
}
/**
@ -44,7 +45,8 @@ abstract class SolrIndex extends SearchIndex {
* e.g. solrconfig.xml.
*/
function getExtrasPath() {
return $this->extrasPath ? $this->extrasPath : Solr::$solr_options['extraspath'];
$globalOptions = Solr::solr_options();
return $this->extrasPath ? $this->extrasPath : $globalOptions['extraspath'];
}
function generateSchema() {

42
code/solr/SolrService.php
View File

@ -2,10 +2,22 @@
Solr::include_client_api();
class SolrService extends Apache_Solr_Service {
/**
* The API for accessing a specific core of a Solr server. Exactly the same as Apache_Solr_Service for now.
*/
class SolrService_Core extends Apache_Solr_Service {
}
/**
* The API for accessing the primary Solr installation, which includes both SolrService_Core,
* plus extra methods for interrogating, creating, reloading and getting SolrService_Core instances
* for Solr cores.
*/
class SolrService extends SolrService_Core {
private static $core_class = 'SolrService_Core';
/**
* @return Apache_Solr_Response
* Handle encoding the GET parameters and making the HTTP call to execute a core command
*/
protected function coreCommand($command, $core, $params=array()) {
$command = strtoupper($command);
@ -17,7 +29,9 @@ class SolrService extends Apache_Solr_Service {
}
/**
* @return boolean
* Is the passed core active?
* @param $core string - The name of the core
* @return boolean - True if that core exists & is active
*/
public function coreIsActive($core) {
$result = $this->coreCommand('STATUS', $core);
@ -25,6 +39,12 @@ class SolrService extends Apache_Solr_Service {
}
/**
* Create a new core
* @param $core string - The name of the core
* @param $instancedir string - The base path of the core on the server
* @param $config string - The filename of solrconfig.xml on the server. Default is $instancedir/solrconfig.xml
* @param $schema string - The filename of schema.xml on the server. Default is $instancedir/schema.xml
* @param $datadir string - The path to store data for this core on the server. Default depends on solrconfig.xml
* @return Apache_Solr_Response
*/
public function coreCreate($core, $instancedir, $config=null, $schema=null, $datadir=null) {
@ -37,19 +57,21 @@ class SolrService extends Apache_Solr_Service {
}
/**
* Reload a core
* @param $core string - The name of the core
* @return Apache_Solr_Response
*/
public function coreReload($core) {
return $this->coreCommand('RELOAD', $core);
}
protected $_serviceCache = array();
/**
* Create a new Solr3Service_Core instance for the passed core
* @param $core string - The name of the core
* @return Solr3Service_Core
*/
public function serviceForCore($core) {
if (!isset($this->_serviceCache[$core])) {
$this->_serviceCache[$core] = new Apache_Solr_Service($this->_host, $this->_port, $this->_path."$core", $this->_httpTransport);
}
return $this->_serviceCache[$core];
$klass = Config::inst()->get(get_called_class(), 'core_class');
return new $klass($this->_host, $this->_port, $this->_path.$core, $this->_httpTransport);
}
}

0
conf/extras/elevate.xml → conf/solr/3/extras/elevate.xml
View File

0
conf/extras/mapping-FoldToASCII.txt → conf/solr/3/extras/mapping-FoldToASCII.txt
View File

0
conf/extras/protwords.txt → conf/solr/3/extras/protwords.txt
View File

0
conf/extras/solrconfig.xml → conf/solr/3/extras/solrconfig.xml
View File

0
conf/extras/stopwords.txt → conf/solr/3/extras/stopwords.txt
View File

0
conf/extras/synonyms.txt → conf/solr/3/extras/synonyms.txt
View File

0
conf/templates/schema.ss → conf/solr/3/templates/schema.ss
View File

0
conf/templates/types.ss → conf/solr/3/templates/types.ss
View File

36
conf/solr/4/extras/elevate.xml Normal file
View File

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

3813
conf/solr/4/extras/mapping-FoldToASCII.txt Normal file
View File

@ -0,0 +1,3813 @@
# 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 map converts alphabetic, numeric, and symbolic Unicode characters
# which are not in the first 127 ASCII characters (the "Basic Latin" Unicode
# block) into their ASCII equivalents, if one exists.
#
# Characters from the following Unicode blocks are converted; however, only
# those characters with reasonable ASCII alternatives are converted:
#
# - C1 Controls and Latin-1 Supplement: http://www.unicode.org/charts/PDF/U0080.pdf
# - Latin Extended-A: http://www.unicode.org/charts/PDF/U0100.pdf
# - Latin Extended-B: http://www.unicode.org/charts/PDF/U0180.pdf
# - Latin Extended Additional: http://www.unicode.org/charts/PDF/U1E00.pdf
# - Latin Extended-C: http://www.unicode.org/charts/PDF/U2C60.pdf
# - Latin Extended-D: http://www.unicode.org/charts/PDF/UA720.pdf
# - IPA Extensions: http://www.unicode.org/charts/PDF/U0250.pdf
# - Phonetic Extensions: http://www.unicode.org/charts/PDF/U1D00.pdf
# - Phonetic Extensions Supplement: http://www.unicode.org/charts/PDF/U1D80.pdf
# - General Punctuation: http://www.unicode.org/charts/PDF/U2000.pdf
# - Superscripts and Subscripts: http://www.unicode.org/charts/PDF/U2070.pdf
# - Enclosed Alphanumerics: http://www.unicode.org/charts/PDF/U2460.pdf
# - Dingbats: http://www.unicode.org/charts/PDF/U2700.pdf
# - Supplemental Punctuation: http://www.unicode.org/charts/PDF/U2E00.pdf
# - Alphabetic Presentation Forms: http://www.unicode.org/charts/PDF/UFB00.pdf
# - Halfwidth and Fullwidth Forms: http://www.unicode.org/charts/PDF/UFF00.pdf
#
# See: http://en.wikipedia.org/wiki/Latin_characters_in_Unicode
#
# The set of character conversions supported by this map is a superset of
# those supported by the map represented by mapping-ISOLatin1Accent.txt.
#
# See the bottom of this file for the Perl script used to generate the contents
# of this file (without this header) from ASCIIFoldingFilter.java.
# Syntax:
# "source" => "target"
# "source".length() > 0 (source cannot be empty.)
# "target".length() >= 0 (target can be empty.)
# À [LATIN CAPITAL LETTER A WITH GRAVE]
"\u00C0" => "A"
# Á [LATIN CAPITAL LETTER A WITH ACUTE]
"\u00C1" => "A"
# Â [LATIN CAPITAL LETTER A WITH CIRCUMFLEX]
"\u00C2" => "A"
# Ã [LATIN CAPITAL LETTER A WITH TILDE]
"\u00C3" => "A"
# Ä [LATIN CAPITAL LETTER A WITH DIAERESIS]
"\u00C4" => "A"
# Å [LATIN CAPITAL LETTER A WITH RING ABOVE]
"\u00C5" => "A"
# Ā [LATIN CAPITAL LETTER A WITH MACRON]
"\u0100" => "A"
# Ă [LATIN CAPITAL LETTER A WITH BREVE]
"\u0102" => "A"
# Ą [LATIN CAPITAL LETTER A WITH OGONEK]
"\u0104" => "A"
# Ə http://en.wikipedia.org/wiki/Schwa [LATIN CAPITAL LETTER SCHWA]
"\u018F" => "A"
# Ǎ [LATIN CAPITAL LETTER A WITH CARON]
"\u01CD" => "A"
# Ǟ [LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON]
"\u01DE" => "A"
# Ǡ [LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON]
"\u01E0" => "A"
# Ǻ [LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE]
"\u01FA" => "A"
# Ȁ [LATIN CAPITAL LETTER A WITH DOUBLE GRAVE]
"\u0200" => "A"
# Ȃ [LATIN CAPITAL LETTER A WITH INVERTED BREVE]
"\u0202" => "A"
# Ȧ [LATIN CAPITAL LETTER A WITH DOT ABOVE]
"\u0226" => "A"
# Ⱥ [LATIN CAPITAL LETTER A WITH STROKE]
"\u023A" => "A"
# ᴀ [LATIN LETTER SMALL CAPITAL A]
"\u1D00" => "A"
# Ḁ [LATIN CAPITAL LETTER A WITH RING BELOW]
"\u1E00" => "A"
# Ạ [LATIN CAPITAL LETTER A WITH DOT BELOW]
"\u1EA0" => "A"
# Ả [LATIN CAPITAL LETTER A WITH HOOK ABOVE]
"\u1EA2" => "A"
# Ấ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE]
"\u1EA4" => "A"
# Ầ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE]
"\u1EA6" => "A"
# Ẩ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
"\u1EA8" => "A"
# Ẫ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE]
"\u1EAA" => "A"
# Ậ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
"\u1EAC" => "A"
# Ắ [LATIN CAPITAL LETTER A WITH BREVE AND ACUTE]
"\u1EAE" => "A"
# Ằ [LATIN CAPITAL LETTER A WITH BREVE AND GRAVE]
"\u1EB0" => "A"
# Ẳ [LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE]
"\u1EB2" => "A"
# Ẵ [LATIN CAPITAL LETTER A WITH BREVE AND TILDE]
"\u1EB4" => "A"
# Ặ [LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW]
"\u1EB6" => "A"
# Ⓐ [CIRCLED LATIN CAPITAL LETTER A]
"\u24B6" => "A"
# Ａ [FULLWIDTH LATIN CAPITAL LETTER A]
"\uFF21" => "A"
# à [LATIN SMALL LETTER A WITH GRAVE]
"\u00E0" => "a"
# á [LATIN SMALL LETTER A WITH ACUTE]
"\u00E1" => "a"
# â [LATIN SMALL LETTER A WITH CIRCUMFLEX]
"\u00E2" => "a"
# ã [LATIN SMALL LETTER A WITH TILDE]
"\u00E3" => "a"
# ä [LATIN SMALL LETTER A WITH DIAERESIS]
"\u00E4" => "a"
# å [LATIN SMALL LETTER A WITH RING ABOVE]
"\u00E5" => "a"
# ā [LATIN SMALL LETTER A WITH MACRON]
"\u0101" => "a"
# ă [LATIN SMALL LETTER A WITH BREVE]
"\u0103" => "a"
# ą [LATIN SMALL LETTER A WITH OGONEK]
"\u0105" => "a"
# ǎ [LATIN SMALL LETTER A WITH CARON]
"\u01CE" => "a"
# ǟ [LATIN SMALL LETTER A WITH DIAERESIS AND MACRON]
"\u01DF" => "a"
# ǡ [LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON]
"\u01E1" => "a"
# ǻ [LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE]
"\u01FB" => "a"
# ȁ [LATIN SMALL LETTER A WITH DOUBLE GRAVE]
"\u0201" => "a"
# ȃ [LATIN SMALL LETTER A WITH INVERTED BREVE]
"\u0203" => "a"
# ȧ [LATIN SMALL LETTER A WITH DOT ABOVE]
"\u0227" => "a"
# ɐ [LATIN SMALL LETTER TURNED A]
"\u0250" => "a"
# ə [LATIN SMALL LETTER SCHWA]
"\u0259" => "a"
# ɚ [LATIN SMALL LETTER SCHWA WITH HOOK]
"\u025A" => "a"
# ᶏ [LATIN SMALL LETTER A WITH RETROFLEX HOOK]
"\u1D8F" => "a"
# ᶕ [LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK]
"\u1D95" => "a"
# ạ [LATIN SMALL LETTER A WITH RING BELOW]
"\u1E01" => "a"
# ả [LATIN SMALL LETTER A WITH RIGHT HALF RING]
"\u1E9A" => "a"
# ạ [LATIN SMALL LETTER A WITH DOT BELOW]
"\u1EA1" => "a"
# ả [LATIN SMALL LETTER A WITH HOOK ABOVE]
"\u1EA3" => "a"
# ấ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE]
"\u1EA5" => "a"
# ầ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE]
"\u1EA7" => "a"
# ẩ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
"\u1EA9" => "a"
# ẫ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE]
"\u1EAB" => "a"
# ậ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
"\u1EAD" => "a"
# ắ [LATIN SMALL LETTER A WITH BREVE AND ACUTE]
"\u1EAF" => "a"
# ằ [LATIN SMALL LETTER A WITH BREVE AND GRAVE]
"\u1EB1" => "a"
# ẳ [LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE]
"\u1EB3" => "a"
# ẵ [LATIN SMALL LETTER A WITH BREVE AND TILDE]
"\u1EB5" => "a"
# ặ [LATIN SMALL LETTER A WITH BREVE AND DOT BELOW]
"\u1EB7" => "a"
# ₐ [LATIN SUBSCRIPT SMALL LETTER A]
"\u2090" => "a"
# ₔ [LATIN SUBSCRIPT SMALL LETTER SCHWA]
"\u2094" => "a"
# ⓐ [CIRCLED LATIN SMALL LETTER A]
"\u24D0" => "a"
# ⱥ [LATIN SMALL LETTER A WITH STROKE]
"\u2C65" => "a"
# Ɐ [LATIN CAPITAL LETTER TURNED A]
"\u2C6F" => "a"
# ａ [FULLWIDTH LATIN SMALL LETTER A]
"\uFF41" => "a"
# Ꜳ [LATIN CAPITAL LETTER AA]
"\uA732" => "AA"
# Æ [LATIN CAPITAL LETTER AE]
"\u00C6" => "AE"
# Ǣ [LATIN CAPITAL LETTER AE WITH MACRON]
"\u01E2" => "AE"
# Ǽ [LATIN CAPITAL LETTER AE WITH ACUTE]
"\u01FC" => "AE"
# ᴁ [LATIN LETTER SMALL CAPITAL AE]
"\u1D01" => "AE"
# Ꜵ [LATIN CAPITAL LETTER AO]
"\uA734" => "AO"
# Ꜷ [LATIN CAPITAL LETTER AU]
"\uA736" => "AU"
# Ꜹ [LATIN CAPITAL LETTER AV]
"\uA738" => "AV"
# Ꜻ [LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR]
"\uA73A" => "AV"
# Ꜽ [LATIN CAPITAL LETTER AY]
"\uA73C" => "AY"
# ⒜ [PARENTHESIZED LATIN SMALL LETTER A]
"\u249C" => "(a)"
# ꜳ [LATIN SMALL LETTER AA]
"\uA733" => "aa"
# æ [LATIN SMALL LETTER AE]
"\u00E6" => "ae"
# ǣ [LATIN SMALL LETTER AE WITH MACRON]
"\u01E3" => "ae"
# ǽ [LATIN SMALL LETTER AE WITH ACUTE]
"\u01FD" => "ae"
# ᴂ [LATIN SMALL LETTER TURNED AE]
"\u1D02" => "ae"
# ꜵ [LATIN SMALL LETTER AO]
"\uA735" => "ao"
# ꜷ [LATIN SMALL LETTER AU]
"\uA737" => "au"
# ꜹ [LATIN SMALL LETTER AV]
"\uA739" => "av"
# ꜻ [LATIN SMALL LETTER AV WITH HORIZONTAL BAR]
"\uA73B" => "av"
# ꜽ [LATIN SMALL LETTER AY]
"\uA73D" => "ay"
# Ɓ [LATIN CAPITAL LETTER B WITH HOOK]
"\u0181" => "B"
# Ƃ [LATIN CAPITAL LETTER B WITH TOPBAR]
"\u0182" => "B"
# Ƀ [LATIN CAPITAL LETTER B WITH STROKE]
"\u0243" => "B"
# ʙ [LATIN LETTER SMALL CAPITAL B]
"\u0299" => "B"
# ᴃ [LATIN LETTER SMALL CAPITAL BARRED B]
"\u1D03" => "B"
# Ḃ [LATIN CAPITAL LETTER B WITH DOT ABOVE]
"\u1E02" => "B"
# Ḅ [LATIN CAPITAL LETTER B WITH DOT BELOW]
"\u1E04" => "B"
# Ḇ [LATIN CAPITAL LETTER B WITH LINE BELOW]
"\u1E06" => "B"
# Ⓑ [CIRCLED LATIN CAPITAL LETTER B]
"\u24B7" => "B"
# Ｂ [FULLWIDTH LATIN CAPITAL LETTER B]
"\uFF22" => "B"
# ƀ [LATIN SMALL LETTER B WITH STROKE]
"\u0180" => "b"
# ƃ [LATIN SMALL LETTER B WITH TOPBAR]
"\u0183" => "b"
# ɓ [LATIN SMALL LETTER B WITH HOOK]
"\u0253" => "b"
# ᵬ [LATIN SMALL LETTER B WITH MIDDLE TILDE]
"\u1D6C" => "b"
# ᶀ [LATIN SMALL LETTER B WITH PALATAL HOOK]
"\u1D80" => "b"
# ḃ [LATIN SMALL LETTER B WITH DOT ABOVE]
"\u1E03" => "b"
# ḅ [LATIN SMALL LETTER B WITH DOT BELOW]
"\u1E05" => "b"
# ḇ [LATIN SMALL LETTER B WITH LINE BELOW]
"\u1E07" => "b"
# ⓑ [CIRCLED LATIN SMALL LETTER B]
"\u24D1" => "b"
# ｂ [FULLWIDTH LATIN SMALL LETTER B]
"\uFF42" => "b"
# ⒝ [PARENTHESIZED LATIN SMALL LETTER B]
"\u249D" => "(b)"
# Ç [LATIN CAPITAL LETTER C WITH CEDILLA]
"\u00C7" => "C"
# Ć [LATIN CAPITAL LETTER C WITH ACUTE]
"\u0106" => "C"
# Ĉ [LATIN CAPITAL LETTER C WITH CIRCUMFLEX]
"\u0108" => "C"
# Ċ [LATIN CAPITAL LETTER C WITH DOT ABOVE]
"\u010A" => "C"
# Č [LATIN CAPITAL LETTER C WITH CARON]
"\u010C" => "C"
# Ƈ [LATIN CAPITAL LETTER C WITH HOOK]
"\u0187" => "C"
# Ȼ [LATIN CAPITAL LETTER C WITH STROKE]
"\u023B" => "C"
# ʗ [LATIN LETTER STRETCHED C]
"\u0297" => "C"
# ᴄ [LATIN LETTER SMALL CAPITAL C]
"\u1D04" => "C"
# Ḉ [LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE]
"\u1E08" => "C"
# Ⓒ [CIRCLED LATIN CAPITAL LETTER C]
"\u24B8" => "C"
# Ｃ [FULLWIDTH LATIN CAPITAL LETTER C]
"\uFF23" => "C"
# ç [LATIN SMALL LETTER C WITH CEDILLA]
"\u00E7" => "c"
# ć [LATIN SMALL LETTER C WITH ACUTE]
"\u0107" => "c"
# ĉ [LATIN SMALL LETTER C WITH CIRCUMFLEX]
"\u0109" => "c"
# ċ [LATIN SMALL LETTER C WITH DOT ABOVE]
"\u010B" => "c"
# č [LATIN SMALL LETTER C WITH CARON]
"\u010D" => "c"
# ƈ [LATIN SMALL LETTER C WITH HOOK]
"\u0188" => "c"
# ȼ [LATIN SMALL LETTER C WITH STROKE]
"\u023C" => "c"
# ɕ [LATIN SMALL LETTER C WITH CURL]
"\u0255" => "c"
# ḉ [LATIN SMALL LETTER C WITH CEDILLA AND ACUTE]
"\u1E09" => "c"
# ↄ [LATIN SMALL LETTER REVERSED C]
"\u2184" => "c"
# ⓒ [CIRCLED LATIN SMALL LETTER C]
"\u24D2" => "c"
# Ꜿ [LATIN CAPITAL LETTER REVERSED C WITH DOT]
"\uA73E" => "c"
# ꜿ [LATIN SMALL LETTER REVERSED C WITH DOT]
"\uA73F" => "c"
# ｃ [FULLWIDTH LATIN SMALL LETTER C]
"\uFF43" => "c"
# ⒞ [PARENTHESIZED LATIN SMALL LETTER C]
"\u249E" => "(c)"
# Ð [LATIN CAPITAL LETTER ETH]
"\u00D0" => "D"
# Ď [LATIN CAPITAL LETTER D WITH CARON]
"\u010E" => "D"
# Đ [LATIN CAPITAL LETTER D WITH STROKE]
"\u0110" => "D"
# Ɖ [LATIN CAPITAL LETTER AFRICAN D]
"\u0189" => "D"
# Ɗ [LATIN CAPITAL LETTER D WITH HOOK]
"\u018A" => "D"
# Ƌ [LATIN CAPITAL LETTER D WITH TOPBAR]
"\u018B" => "D"
# ᴅ [LATIN LETTER SMALL CAPITAL D]
"\u1D05" => "D"
# ᴆ [LATIN LETTER SMALL CAPITAL ETH]
"\u1D06" => "D"
# Ḋ [LATIN CAPITAL LETTER D WITH DOT ABOVE]
"\u1E0A" => "D"
# Ḍ [LATIN CAPITAL LETTER D WITH DOT BELOW]
"\u1E0C" => "D"
# Ḏ [LATIN CAPITAL LETTER D WITH LINE BELOW]
"\u1E0E" => "D"
# Ḑ [LATIN CAPITAL LETTER D WITH CEDILLA]
"\u1E10" => "D"
# Ḓ [LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW]
"\u1E12" => "D"
# Ⓓ [CIRCLED LATIN CAPITAL LETTER D]
"\u24B9" => "D"
# Ꝺ [LATIN CAPITAL LETTER INSULAR D]
"\uA779" => "D"
# Ｄ [FULLWIDTH LATIN CAPITAL LETTER D]
"\uFF24" => "D"
# ð [LATIN SMALL LETTER ETH]
"\u00F0" => "d"
# ď [LATIN SMALL LETTER D WITH CARON]
"\u010F" => "d"
# đ [LATIN SMALL LETTER D WITH STROKE]
"\u0111" => "d"
# ƌ [LATIN SMALL LETTER D WITH TOPBAR]
"\u018C" => "d"
# ȡ [LATIN SMALL LETTER D WITH CURL]
"\u0221" => "d"
# ɖ [LATIN SMALL LETTER D WITH TAIL]
"\u0256" => "d"
# ɗ [LATIN SMALL LETTER D WITH HOOK]
"\u0257" => "d"
# ᵭ [LATIN SMALL LETTER D WITH MIDDLE TILDE]
"\u1D6D" => "d"
# ᶁ [LATIN SMALL LETTER D WITH PALATAL HOOK]
"\u1D81" => "d"
# ᶑ [LATIN SMALL LETTER D WITH HOOK AND TAIL]
"\u1D91" => "d"
# ḋ [LATIN SMALL LETTER D WITH DOT ABOVE]
"\u1E0B" => "d"
# ḍ [LATIN SMALL LETTER D WITH DOT BELOW]
"\u1E0D" => "d"
# ḏ [LATIN SMALL LETTER D WITH LINE BELOW]
"\u1E0F" => "d"
# ḑ [LATIN SMALL LETTER D WITH CEDILLA]
"\u1E11" => "d"
# ḓ [LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW]
"\u1E13" => "d"
# ⓓ [CIRCLED LATIN SMALL LETTER D]
"\u24D3" => "d"
# ꝺ [LATIN SMALL LETTER INSULAR D]
"\uA77A" => "d"
# ｄ [FULLWIDTH LATIN SMALL LETTER D]
"\uFF44" => "d"
# DŽ [LATIN CAPITAL LETTER DZ WITH CARON]
"\u01C4" => "DZ"
# DZ [LATIN CAPITAL LETTER DZ]
"\u01F1" => "DZ"
# Dž [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON]
"\u01C5" => "Dz"
# Dz [LATIN CAPITAL LETTER D WITH SMALL LETTER Z]
"\u01F2" => "Dz"
# ⒟ [PARENTHESIZED LATIN SMALL LETTER D]
"\u249F" => "(d)"
# ȸ [LATIN SMALL LETTER DB DIGRAPH]
"\u0238" => "db"
# dž [LATIN SMALL LETTER DZ WITH CARON]
"\u01C6" => "dz"
# dz [LATIN SMALL LETTER DZ]
"\u01F3" => "dz"
# ʣ [LATIN SMALL LETTER DZ DIGRAPH]
"\u02A3" => "dz"
# ʥ [LATIN SMALL LETTER DZ DIGRAPH WITH CURL]
"\u02A5" => "dz"
# È [LATIN CAPITAL LETTER E WITH GRAVE]
"\u00C8" => "E"
# É [LATIN CAPITAL LETTER E WITH ACUTE]
"\u00C9" => "E"
# Ê [LATIN CAPITAL LETTER E WITH CIRCUMFLEX]
"\u00CA" => "E"
# Ë [LATIN CAPITAL LETTER E WITH DIAERESIS]
"\u00CB" => "E"
# Ē [LATIN CAPITAL LETTER E WITH MACRON]
"\u0112" => "E"
# Ĕ [LATIN CAPITAL LETTER E WITH BREVE]
"\u0114" => "E"
# Ė [LATIN CAPITAL LETTER E WITH DOT ABOVE]
"\u0116" => "E"
# Ę [LATIN CAPITAL LETTER E WITH OGONEK]
"\u0118" => "E"
# Ě [LATIN CAPITAL LETTER E WITH CARON]
"\u011A" => "E"
# Ǝ [LATIN CAPITAL LETTER REVERSED E]
"\u018E" => "E"
# Ɛ [LATIN CAPITAL LETTER OPEN E]
"\u0190" => "E"
# Ȅ [LATIN CAPITAL LETTER E WITH DOUBLE GRAVE]
"\u0204" => "E"
# Ȇ [LATIN CAPITAL LETTER E WITH INVERTED BREVE]
"\u0206" => "E"
# Ȩ [LATIN CAPITAL LETTER E WITH CEDILLA]
"\u0228" => "E"
# Ɇ [LATIN CAPITAL LETTER E WITH STROKE]
"\u0246" => "E"
# ᴇ [LATIN LETTER SMALL CAPITAL E]
"\u1D07" => "E"
# Ḕ [LATIN CAPITAL LETTER E WITH MACRON AND GRAVE]
"\u1E14" => "E"
# Ḗ [LATIN CAPITAL LETTER E WITH MACRON AND ACUTE]
"\u1E16" => "E"
# Ḙ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW]
"\u1E18" => "E"
# Ḛ [LATIN CAPITAL LETTER E WITH TILDE BELOW]
"\u1E1A" => "E"
# Ḝ [LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE]
"\u1E1C" => "E"
# Ẹ [LATIN CAPITAL LETTER E WITH DOT BELOW]
"\u1EB8" => "E"
# Ẻ [LATIN CAPITAL LETTER E WITH HOOK ABOVE]
"\u1EBA" => "E"
# Ẽ [LATIN CAPITAL LETTER E WITH TILDE]
"\u1EBC" => "E"
# Ế [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE]
"\u1EBE" => "E"
# Ề [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE]
"\u1EC0" => "E"
# Ể [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE]
"\u1EC2" => "E"
# Ễ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE]
"\u1EC4" => "E"
# Ệ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW]
"\u1EC6" => "E"
# Ⓔ [CIRCLED LATIN CAPITAL LETTER E]
"\u24BA" => "E"
# ⱻ [LATIN LETTER SMALL CAPITAL TURNED E]
"\u2C7B" => "E"
# Ｅ [FULLWIDTH LATIN CAPITAL LETTER E]
"\uFF25" => "E"
# è [LATIN SMALL LETTER E WITH GRAVE]
"\u00E8" => "e"
# é [LATIN SMALL LETTER E WITH ACUTE]
"\u00E9" => "e"
# ê [LATIN SMALL LETTER E WITH CIRCUMFLEX]
"\u00EA" => "e"
# ë [LATIN SMALL LETTER E WITH DIAERESIS]
"\u00EB" => "e"
# ē [LATIN SMALL LETTER E WITH MACRON]
"\u0113" => "e"
# ĕ [LATIN SMALL LETTER E WITH BREVE]
"\u0115" => "e"
# ė [LATIN SMALL LETTER E WITH DOT ABOVE]
"\u0117" => "e"
# ę [LATIN SMALL LETTER E WITH OGONEK]
"\u0119" => "e"
# ě [LATIN SMALL LETTER E WITH CARON]
"\u011B" => "e"
# ǝ [LATIN SMALL LETTER TURNED E]
"\u01DD" => "e"
# ȅ [LATIN SMALL LETTER E WITH DOUBLE GRAVE]
"\u0205" => "e"
# ȇ [LATIN SMALL LETTER E WITH INVERTED BREVE]
"\u0207" => "e"
# ȩ [LATIN SMALL LETTER E WITH CEDILLA]
"\u0229" => "e"
# ɇ [LATIN SMALL LETTER E WITH STROKE]
"\u0247" => "e"
# ɘ [LATIN SMALL LETTER REVERSED E]
"\u0258" => "e"
# ɛ [LATIN SMALL LETTER OPEN E]
"\u025B" => "e"
# ɜ [LATIN SMALL LETTER REVERSED OPEN E]
"\u025C" => "e"
# ɝ [LATIN SMALL LETTER REVERSED OPEN E WITH HOOK]
"\u025D" => "e"
# ɞ [LATIN SMALL LETTER CLOSED REVERSED OPEN E]
"\u025E" => "e"
# ʚ [LATIN SMALL LETTER CLOSED OPEN E]
"\u029A" => "e"
# ᴈ [LATIN SMALL LETTER TURNED OPEN E]
"\u1D08" => "e"
# ᶒ [LATIN SMALL LETTER E WITH RETROFLEX HOOK]
"\u1D92" => "e"
# ᶓ [LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK]
"\u1D93" => "e"
# ᶔ [LATIN SMALL LETTER REVERSED OPEN E WITH RETROFLEX HOOK]
"\u1D94" => "e"
# ḕ [LATIN SMALL LETTER E WITH MACRON AND GRAVE]
"\u1E15" => "e"
# ḗ [LATIN SMALL LETTER E WITH MACRON AND ACUTE]
"\u1E17" => "e"
# ḙ [LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW]
"\u1E19" => "e"
# ḛ [LATIN SMALL LETTER E WITH TILDE BELOW]
"\u1E1B" => "e"
# ḝ [LATIN SMALL LETTER E WITH CEDILLA AND BREVE]
"\u1E1D" => "e"
# ẹ [LATIN SMALL LETTER E WITH DOT BELOW]
"\u1EB9" => "e"
# ẻ [LATIN SMALL LETTER E WITH HOOK ABOVE]
"\u1EBB" => "e"
# ẽ [LATIN SMALL LETTER E WITH TILDE]
"\u1EBD" => "e"
# ế [LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE]
"\u1EBF" => "e"
# ề [LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE]
"\u1EC1" => "e"
# ể [LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE]
"\u1EC3" => "e"
# ễ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE]
"\u1EC5" => "e"
# ệ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW]
"\u1EC7" => "e"
# ₑ [LATIN SUBSCRIPT SMALL LETTER E]
"\u2091" => "e"
# ⓔ [CIRCLED LATIN SMALL LETTER E]
"\u24D4" => "e"
# ⱸ [LATIN SMALL LETTER E WITH NOTCH]
"\u2C78" => "e"
# ｅ [FULLWIDTH LATIN SMALL LETTER E]
"\uFF45" => "e"
# ⒠ [PARENTHESIZED LATIN SMALL LETTER E]
"\u24A0" => "(e)"
# Ƒ [LATIN CAPITAL LETTER F WITH HOOK]
"\u0191" => "F"
# Ḟ [LATIN CAPITAL LETTER F WITH DOT ABOVE]
"\u1E1E" => "F"
# Ⓕ [CIRCLED LATIN CAPITAL LETTER F]
"\u24BB" => "F"
# ꜰ [LATIN LETTER SMALL CAPITAL F]
"\uA730" => "F"
# Ꝼ [LATIN CAPITAL LETTER INSULAR F]
"\uA77B" => "F"
# ꟻ [LATIN EPIGRAPHIC LETTER REVERSED F]
"\uA7FB" => "F"
# Ｆ [FULLWIDTH LATIN CAPITAL LETTER F]
"\uFF26" => "F"
# ƒ [LATIN SMALL LETTER F WITH HOOK]
"\u0192" => "f"
# ᵮ [LATIN SMALL LETTER F WITH MIDDLE TILDE]
"\u1D6E" => "f"
# ᶂ [LATIN SMALL LETTER F WITH PALATAL HOOK]
"\u1D82" => "f"
# ḟ [LATIN SMALL LETTER F WITH DOT ABOVE]
"\u1E1F" => "f"
# ẛ [LATIN SMALL LETTER LONG S WITH DOT ABOVE]
"\u1E9B" => "f"
# ⓕ [CIRCLED LATIN SMALL LETTER F]
"\u24D5" => "f"
# ꝼ [LATIN SMALL LETTER INSULAR F]
"\uA77C" => "f"
# ｆ [FULLWIDTH LATIN SMALL LETTER F]
"\uFF46" => "f"
# ⒡ [PARENTHESIZED LATIN SMALL LETTER F]
"\u24A1" => "(f)"
# ff [LATIN SMALL LIGATURE FF]
"\uFB00" => "ff"
# ffi [LATIN SMALL LIGATURE FFI]
"\uFB03" => "ffi"
# ffl [LATIN SMALL LIGATURE FFL]
"\uFB04" => "ffl"
# fi [LATIN SMALL LIGATURE FI]
"\uFB01" => "fi"
# fl [LATIN SMALL LIGATURE FL]
"\uFB02" => "fl"
# Ĝ [LATIN CAPITAL LETTER G WITH CIRCUMFLEX]
"\u011C" => "G"
# Ğ [LATIN CAPITAL LETTER G WITH BREVE]
"\u011E" => "G"
# Ġ [LATIN CAPITAL LETTER G WITH DOT ABOVE]
"\u0120" => "G"
# Ģ [LATIN CAPITAL LETTER G WITH CEDILLA]
"\u0122" => "G"
# Ɠ [LATIN CAPITAL LETTER G WITH HOOK]
"\u0193" => "G"
# Ǥ [LATIN CAPITAL LETTER G WITH STROKE]
"\u01E4" => "G"
# ǥ [LATIN SMALL LETTER G WITH STROKE]
"\u01E5" => "G"
# Ǧ [LATIN CAPITAL LETTER G WITH CARON]
"\u01E6" => "G"
# ǧ [LATIN SMALL LETTER G WITH CARON]
"\u01E7" => "G"
# Ǵ [LATIN CAPITAL LETTER G WITH ACUTE]
"\u01F4" => "G"
# ɢ [LATIN LETTER SMALL CAPITAL G]
"\u0262" => "G"
# ʛ [LATIN LETTER SMALL CAPITAL G WITH HOOK]
"\u029B" => "G"
# Ḡ [LATIN CAPITAL LETTER G WITH MACRON]
"\u1E20" => "G"
# Ⓖ [CIRCLED LATIN CAPITAL LETTER G]
"\u24BC" => "G"
# Ᵹ [LATIN CAPITAL LETTER INSULAR G]
"\uA77D" => "G"
# Ꝿ [LATIN CAPITAL LETTER TURNED INSULAR G]
"\uA77E" => "G"
# Ｇ [FULLWIDTH LATIN CAPITAL LETTER G]
"\uFF27" => "G"
# ĝ [LATIN SMALL LETTER G WITH CIRCUMFLEX]
"\u011D" => "g"
# ğ [LATIN SMALL LETTER G WITH BREVE]
"\u011F" => "g"
# ġ [LATIN SMALL LETTER G WITH DOT ABOVE]
"\u0121" => "g"
# ģ [LATIN SMALL LETTER G WITH CEDILLA]
"\u0123" => "g"
# ǵ [LATIN SMALL LETTER G WITH ACUTE]
"\u01F5" => "g"
# ɠ [LATIN SMALL LETTER G WITH HOOK]
"\u0260" => "g"
# ɡ [LATIN SMALL LETTER SCRIPT G]
"\u0261" => "g"
# ᵷ [LATIN SMALL LETTER TURNED G]
"\u1D77" => "g"
# ᵹ [LATIN SMALL LETTER INSULAR G]
"\u1D79" => "g"
# ᶃ [LATIN SMALL LETTER G WITH PALATAL HOOK]
"\u1D83" => "g"
# ḡ [LATIN SMALL LETTER G WITH MACRON]
"\u1E21" => "g"
# ⓖ [CIRCLED LATIN SMALL LETTER G]
"\u24D6" => "g"
# ꝿ [LATIN SMALL LETTER TURNED INSULAR G]
"\uA77F" => "g"
# ｇ [FULLWIDTH LATIN SMALL LETTER G]
"\uFF47" => "g"
# ⒢ [PARENTHESIZED LATIN SMALL LETTER G]
"\u24A2" => "(g)"
# Ĥ [LATIN CAPITAL LETTER H WITH CIRCUMFLEX]
"\u0124" => "H"
# Ħ [LATIN CAPITAL LETTER H WITH STROKE]
"\u0126" => "H"
# Ȟ [LATIN CAPITAL LETTER H WITH CARON]
"\u021E" => "H"
# ʜ [LATIN LETTER SMALL CAPITAL H]
"\u029C" => "H"
# Ḣ [LATIN CAPITAL LETTER H WITH DOT ABOVE]
"\u1E22" => "H"
# Ḥ [LATIN CAPITAL LETTER H WITH DOT BELOW]
"\u1E24" => "H"
# Ḧ [LATIN CAPITAL LETTER H WITH DIAERESIS]
"\u1E26" => "H"
# Ḩ [LATIN CAPITAL LETTER H WITH CEDILLA]
"\u1E28" => "H"
# Ḫ [LATIN CAPITAL LETTER H WITH BREVE BELOW]
"\u1E2A" => "H"
# Ⓗ [CIRCLED LATIN CAPITAL LETTER H]
"\u24BD" => "H"
# Ⱨ [LATIN CAPITAL LETTER H WITH DESCENDER]
"\u2C67" => "H"
# Ⱶ [LATIN CAPITAL LETTER HALF H]
"\u2C75" => "H"
# Ｈ [FULLWIDTH LATIN CAPITAL LETTER H]
"\uFF28" => "H"
# ĥ [LATIN SMALL LETTER H WITH CIRCUMFLEX]
"\u0125" => "h"
# ħ [LATIN SMALL LETTER H WITH STROKE]
"\u0127" => "h"
# ȟ [LATIN SMALL LETTER H WITH CARON]
"\u021F" => "h"
# ɥ [LATIN SMALL LETTER TURNED H]
"\u0265" => "h"
# ɦ [LATIN SMALL LETTER H WITH HOOK]
"\u0266" => "h"
# ʮ [LATIN SMALL LETTER TURNED H WITH FISHHOOK]
"\u02AE" => "h"
# ʯ [LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL]
"\u02AF" => "h"
# ḣ [LATIN SMALL LETTER H WITH DOT ABOVE]
"\u1E23" => "h"
# ḥ [LATIN SMALL LETTER H WITH DOT BELOW]
"\u1E25" => "h"
# ḧ [LATIN SMALL LETTER H WITH DIAERESIS]
"\u1E27" => "h"
# ḩ [LATIN SMALL LETTER H WITH CEDILLA]
"\u1E29" => "h"
# ḫ [LATIN SMALL LETTER H WITH BREVE BELOW]
"\u1E2B" => "h"
# ẖ [LATIN SMALL LETTER H WITH LINE BELOW]
"\u1E96" => "h"
# ⓗ [CIRCLED LATIN SMALL LETTER H]
"\u24D7" => "h"
# ⱨ [LATIN SMALL LETTER H WITH DESCENDER]
"\u2C68" => "h"
# ⱶ [LATIN SMALL LETTER HALF H]
"\u2C76" => "h"
# ｈ [FULLWIDTH LATIN SMALL LETTER H]
"\uFF48" => "h"
# Ƕ http://en.wikipedia.org/wiki/Hwair [LATIN CAPITAL LETTER HWAIR]
"\u01F6" => "HV"
# ⒣ [PARENTHESIZED LATIN SMALL LETTER H]
"\u24A3" => "(h)"
# ƕ [LATIN SMALL LETTER HV]
"\u0195" => "hv"
# Ì [LATIN CAPITAL LETTER I WITH GRAVE]
"\u00CC" => "I"
# Í [LATIN CAPITAL LETTER I WITH ACUTE]
"\u00CD" => "I"
# Î [LATIN CAPITAL LETTER I WITH CIRCUMFLEX]
"\u00CE" => "I"
# Ï [LATIN CAPITAL LETTER I WITH DIAERESIS]
"\u00CF" => "I"
# Ĩ [LATIN CAPITAL LETTER I WITH TILDE]
"\u0128" => "I"
# Ī [LATIN CAPITAL LETTER I WITH MACRON]
"\u012A" => "I"
# Ĭ [LATIN CAPITAL LETTER I WITH BREVE]
"\u012C" => "I"
# Į [LATIN CAPITAL LETTER I WITH OGONEK]
"\u012E" => "I"
# İ [LATIN CAPITAL LETTER I WITH DOT ABOVE]
"\u0130" => "I"
# Ɩ [LATIN CAPITAL LETTER IOTA]
"\u0196" => "I"
# Ɨ [LATIN CAPITAL LETTER I WITH STROKE]
"\u0197" => "I"
# Ǐ [LATIN CAPITAL LETTER I WITH CARON]
"\u01CF" => "I"
# Ȉ [LATIN CAPITAL LETTER I WITH DOUBLE GRAVE]
"\u0208" => "I"
# Ȋ [LATIN CAPITAL LETTER I WITH INVERTED BREVE]
"\u020A" => "I"
# ɪ [LATIN LETTER SMALL CAPITAL I]
"\u026A" => "I"
# ᵻ [LATIN SMALL CAPITAL LETTER I WITH STROKE]
"\u1D7B" => "I"
# Ḭ [LATIN CAPITAL LETTER I WITH TILDE BELOW]
"\u1E2C" => "I"
# Ḯ [LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE]
"\u1E2E" => "I"
# Ỉ [LATIN CAPITAL LETTER I WITH HOOK ABOVE]
"\u1EC8" => "I"
# Ị [LATIN CAPITAL LETTER I WITH DOT BELOW]
"\u1ECA" => "I"
# Ⓘ [CIRCLED LATIN CAPITAL LETTER I]
"\u24BE" => "I"
# ꟾ [LATIN EPIGRAPHIC LETTER I LONGA]
"\uA7FE" => "I"
# Ｉ [FULLWIDTH LATIN CAPITAL LETTER I]
"\uFF29" => "I"
# ì [LATIN SMALL LETTER I WITH GRAVE]
"\u00EC" => "i"
# í [LATIN SMALL LETTER I WITH ACUTE]
"\u00ED" => "i"
# î [LATIN SMALL LETTER I WITH CIRCUMFLEX]
"\u00EE" => "i"
# ï [LATIN SMALL LETTER I WITH DIAERESIS]
"\u00EF" => "i"
# ĩ [LATIN SMALL LETTER I WITH TILDE]
"\u0129" => "i"
# ī [LATIN SMALL LETTER I WITH MACRON]
"\u012B" => "i"
# ĭ [LATIN SMALL LETTER I WITH BREVE]
"\u012D" => "i"
# į [LATIN SMALL LETTER I WITH OGONEK]
"\u012F" => "i"
# ı [LATIN SMALL LETTER DOTLESS I]
"\u0131" => "i"
# ǐ [LATIN SMALL LETTER I WITH CARON]
"\u01D0" => "i"
# ȉ [LATIN SMALL LETTER I WITH DOUBLE GRAVE]
"\u0209" => "i"
# ȋ [LATIN SMALL LETTER I WITH INVERTED BREVE]
"\u020B" => "i"
# ɨ [LATIN SMALL LETTER I WITH STROKE]
"\u0268" => "i"
# ᴉ [LATIN SMALL LETTER TURNED I]
"\u1D09" => "i"
# ᵢ [LATIN SUBSCRIPT SMALL LETTER I]
"\u1D62" => "i"
# ᵼ [LATIN SMALL LETTER IOTA WITH STROKE]
"\u1D7C" => "i"
# ᶖ [LATIN SMALL LETTER I WITH RETROFLEX HOOK]
"\u1D96" => "i"
# ḭ [LATIN SMALL LETTER I WITH TILDE BELOW]
"\u1E2D" => "i"
# ḯ [LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE]
"\u1E2F" => "i"
# ỉ [LATIN SMALL LETTER I WITH HOOK ABOVE]
"\u1EC9" => "i"
# ị [LATIN SMALL LETTER I WITH DOT BELOW]
"\u1ECB" => "i"
# ⁱ [SUPERSCRIPT LATIN SMALL LETTER I]
"\u2071" => "i"
# ⓘ [CIRCLED LATIN SMALL LETTER I]
"\u24D8" => "i"
# ｉ [FULLWIDTH LATIN SMALL LETTER I]
"\uFF49" => "i"
# IJ [LATIN CAPITAL LIGATURE IJ]
"\u0132" => "IJ"
# ⒤ [PARENTHESIZED LATIN SMALL LETTER I]
"\u24A4" => "(i)"
# ij [LATIN SMALL LIGATURE IJ]
"\u0133" => "ij"
# Ĵ [LATIN CAPITAL LETTER J WITH CIRCUMFLEX]
"\u0134" => "J"
# Ɉ [LATIN CAPITAL LETTER J WITH STROKE]
"\u0248" => "J"
# ᴊ [LATIN LETTER SMALL CAPITAL J]
"\u1D0A" => "J"
# Ⓙ [CIRCLED LATIN CAPITAL LETTER J]
"\u24BF" => "J"
# Ｊ [FULLWIDTH LATIN CAPITAL LETTER J]
"\uFF2A" => "J"
# ĵ [LATIN SMALL LETTER J WITH CIRCUMFLEX]
"\u0135" => "j"
# ǰ [LATIN SMALL LETTER J WITH CARON]
"\u01F0" => "j"
# ȷ [LATIN SMALL LETTER DOTLESS J]
"\u0237" => "j"
# ɉ [LATIN SMALL LETTER J WITH STROKE]
"\u0249" => "j"
# ɟ [LATIN SMALL LETTER DOTLESS J WITH STROKE]
"\u025F" => "j"
# ʄ [LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK]
"\u0284" => "j"
# ʝ [LATIN SMALL LETTER J WITH CROSSED-TAIL]
"\u029D" => "j"
# ⓙ [CIRCLED LATIN SMALL LETTER J]
"\u24D9" => "j"
# ⱼ [LATIN SUBSCRIPT SMALL LETTER J]
"\u2C7C" => "j"
# ｊ [FULLWIDTH LATIN SMALL LETTER J]
"\uFF4A" => "j"
# ⒥ [PARENTHESIZED LATIN SMALL LETTER J]
"\u24A5" => "(j)"
# Ķ [LATIN CAPITAL LETTER K WITH CEDILLA]
"\u0136" => "K"
# Ƙ [LATIN CAPITAL LETTER K WITH HOOK]
"\u0198" => "K"
# Ǩ [LATIN CAPITAL LETTER K WITH CARON]
"\u01E8" => "K"
# ᴋ [LATIN LETTER SMALL CAPITAL K]
"\u1D0B" => "K"
# Ḱ [LATIN CAPITAL LETTER K WITH ACUTE]
"\u1E30" => "K"
# Ḳ [LATIN CAPITAL LETTER K WITH DOT BELOW]
"\u1E32" => "K"
# Ḵ [LATIN CAPITAL LETTER K WITH LINE BELOW]
"\u1E34" => "K"
# Ⓚ [CIRCLED LATIN CAPITAL LETTER K]
"\u24C0" => "K"
# Ⱪ [LATIN CAPITAL LETTER K WITH DESCENDER]
"\u2C69" => "K"
# Ꝁ [LATIN CAPITAL LETTER K WITH STROKE]
"\uA740" => "K"
# Ꝃ [LATIN CAPITAL LETTER K WITH DIAGONAL STROKE]
"\uA742" => "K"
# Ꝅ [LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE]
"\uA744" => "K"
# Ｋ [FULLWIDTH LATIN CAPITAL LETTER K]
"\uFF2B" => "K"
# ķ [LATIN SMALL LETTER K WITH CEDILLA]
"\u0137" => "k"
# ƙ [LATIN SMALL LETTER K WITH HOOK]
"\u0199" => "k"
# ǩ [LATIN SMALL LETTER K WITH CARON]
"\u01E9" => "k"
# ʞ [LATIN SMALL LETTER TURNED K]
"\u029E" => "k"
# ᶄ [LATIN SMALL LETTER K WITH PALATAL HOOK]
"\u1D84" => "k"
# ḱ [LATIN SMALL LETTER K WITH ACUTE]
"\u1E31" => "k"
# ḳ [LATIN SMALL LETTER K WITH DOT BELOW]
"\u1E33" => "k"
# ḵ [LATIN SMALL LETTER K WITH LINE BELOW]
"\u1E35" => "k"
# ⓚ [CIRCLED LATIN SMALL LETTER K]
"\u24DA" => "k"
# ⱪ [LATIN SMALL LETTER K WITH DESCENDER]
"\u2C6A" => "k"
# ꝁ [LATIN SMALL LETTER K WITH STROKE]
"\uA741" => "k"
# ꝃ [LATIN SMALL LETTER K WITH DIAGONAL STROKE]
"\uA743" => "k"
# ꝅ [LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE]
"\uA745" => "k"
# ｋ [FULLWIDTH LATIN SMALL LETTER K]
"\uFF4B" => "k"
# ⒦ [PARENTHESIZED LATIN SMALL LETTER K]
"\u24A6" => "(k)"
# Ĺ [LATIN CAPITAL LETTER L WITH ACUTE]
"\u0139" => "L"
# Ļ [LATIN CAPITAL LETTER L WITH CEDILLA]
"\u013B" => "L"
# Ľ [LATIN CAPITAL LETTER L WITH CARON]
"\u013D" => "L"
# Ŀ [LATIN CAPITAL LETTER L WITH MIDDLE DOT]
"\u013F" => "L"
# Ł [LATIN CAPITAL LETTER L WITH STROKE]
"\u0141" => "L"
# Ƚ [LATIN CAPITAL LETTER L WITH BAR]
"\u023D" => "L"
# ʟ [LATIN LETTER SMALL CAPITAL L]
"\u029F" => "L"
# ᴌ [LATIN LETTER SMALL CAPITAL L WITH STROKE]
"\u1D0C" => "L"
# Ḷ [LATIN CAPITAL LETTER L WITH DOT BELOW]
"\u1E36" => "L"
# Ḹ [LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON]
"\u1E38" => "L"
# Ḻ [LATIN CAPITAL LETTER L WITH LINE BELOW]
"\u1E3A" => "L"
# Ḽ [LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW]
"\u1E3C" => "L"
# Ⓛ [CIRCLED LATIN CAPITAL LETTER L]
"\u24C1" => "L"
# Ⱡ [LATIN CAPITAL LETTER L WITH DOUBLE BAR]
"\u2C60" => "L"
# Ɫ [LATIN CAPITAL LETTER L WITH MIDDLE TILDE]
"\u2C62" => "L"
# Ꝇ [LATIN CAPITAL LETTER BROKEN L]
"\uA746" => "L"
# Ꝉ [LATIN CAPITAL LETTER L WITH HIGH STROKE]
"\uA748" => "L"
# Ꞁ [LATIN CAPITAL LETTER TURNED L]
"\uA780" => "L"
# Ｌ [FULLWIDTH LATIN CAPITAL LETTER L]
"\uFF2C" => "L"
# ĺ [LATIN SMALL LETTER L WITH ACUTE]
"\u013A" => "l"
# ļ [LATIN SMALL LETTER L WITH CEDILLA]
"\u013C" => "l"
# ľ [LATIN SMALL LETTER L WITH CARON]
"\u013E" => "l"
# ŀ [LATIN SMALL LETTER L WITH MIDDLE DOT]
"\u0140" => "l"
# ł [LATIN SMALL LETTER L WITH STROKE]
"\u0142" => "l"
# ƚ [LATIN SMALL LETTER L WITH BAR]
"\u019A" => "l"
# ȴ [LATIN SMALL LETTER L WITH CURL]
"\u0234" => "l"
# ɫ [LATIN SMALL LETTER L WITH MIDDLE TILDE]
"\u026B" => "l"
# ɬ [LATIN SMALL LETTER L WITH BELT]
"\u026C" => "l"
# ɭ [LATIN SMALL LETTER L WITH RETROFLEX HOOK]
"\u026D" => "l"
# ᶅ [LATIN SMALL LETTER L WITH PALATAL HOOK]
"\u1D85" => "l"
# ḷ [LATIN SMALL LETTER L WITH DOT BELOW]
"\u1E37" => "l"
# ḹ [LATIN SMALL LETTER L WITH DOT BELOW AND MACRON]
"\u1E39" => "l"
# ḻ [LATIN SMALL LETTER L WITH LINE BELOW]
"\u1E3B" => "l"
# ḽ [LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW]
"\u1E3D" => "l"
# ⓛ [CIRCLED LATIN SMALL LETTER L]
"\u24DB" => "l"
# ⱡ [LATIN SMALL LETTER L WITH DOUBLE BAR]
"\u2C61" => "l"
# ꝇ [LATIN SMALL LETTER BROKEN L]
"\uA747" => "l"
# ꝉ [LATIN SMALL LETTER L WITH HIGH STROKE]
"\uA749" => "l"
# ꞁ [LATIN SMALL LETTER TURNED L]
"\uA781" => "l"
# ｌ [FULLWIDTH LATIN SMALL LETTER L]
"\uFF4C" => "l"
# LJ [LATIN CAPITAL LETTER LJ]
"\u01C7" => "LJ"
# Ỻ [LATIN CAPITAL LETTER MIDDLE-WELSH LL]
"\u1EFA" => "LL"
# Lj [LATIN CAPITAL LETTER L WITH SMALL LETTER J]
"\u01C8" => "Lj"
# ⒧ [PARENTHESIZED LATIN SMALL LETTER L]
"\u24A7" => "(l)"
# lj [LATIN SMALL LETTER LJ]
"\u01C9" => "lj"
# ỻ [LATIN SMALL LETTER MIDDLE-WELSH LL]
"\u1EFB" => "ll"
# ʪ [LATIN SMALL LETTER LS DIGRAPH]
"\u02AA" => "ls"
# ʫ [LATIN SMALL LETTER LZ DIGRAPH]
"\u02AB" => "lz"
# Ɯ [LATIN CAPITAL LETTER TURNED M]
"\u019C" => "M"
# ᴍ [LATIN LETTER SMALL CAPITAL M]
"\u1D0D" => "M"
# Ḿ [LATIN CAPITAL LETTER M WITH ACUTE]
"\u1E3E" => "M"
# Ṁ [LATIN CAPITAL LETTER M WITH DOT ABOVE]
"\u1E40" => "M"
# Ṃ [LATIN CAPITAL LETTER M WITH DOT BELOW]
"\u1E42" => "M"
# Ⓜ [CIRCLED LATIN CAPITAL LETTER M]
"\u24C2" => "M"
# Ɱ [LATIN CAPITAL LETTER M WITH HOOK]
"\u2C6E" => "M"
# ꟽ [LATIN EPIGRAPHIC LETTER INVERTED M]
"\uA7FD" => "M"
# ꟿ [LATIN EPIGRAPHIC LETTER ARCHAIC M]
"\uA7FF" => "M"
# Ｍ [FULLWIDTH LATIN CAPITAL LETTER M]
"\uFF2D" => "M"
# ɯ [LATIN SMALL LETTER TURNED M]
"\u026F" => "m"
# ɰ [LATIN SMALL LETTER TURNED M WITH LONG LEG]
"\u0270" => "m"
# ɱ [LATIN SMALL LETTER M WITH HOOK]
"\u0271" => "m"
# ᵯ [LATIN SMALL LETTER M WITH MIDDLE TILDE]
"\u1D6F" => "m"
# ᶆ [LATIN SMALL LETTER M WITH PALATAL HOOK]
"\u1D86" => "m"
# ḿ [LATIN SMALL LETTER M WITH ACUTE]
"\u1E3F" => "m"
# ṁ [LATIN SMALL LETTER M WITH DOT ABOVE]
"\u1E41" => "m"
# ṃ [LATIN SMALL LETTER M WITH DOT BELOW]
"\u1E43" => "m"
# ⓜ [CIRCLED LATIN SMALL LETTER M]
"\u24DC" => "m"
# ｍ [FULLWIDTH LATIN SMALL LETTER M]
"\uFF4D" => "m"
# ⒨ [PARENTHESIZED LATIN SMALL LETTER M]
"\u24A8" => "(m)"
# Ñ [LATIN CAPITAL LETTER N WITH TILDE]
"\u00D1" => "N"
# Ń [LATIN CAPITAL LETTER N WITH ACUTE]
"\u0143" => "N"
# Ņ [LATIN CAPITAL LETTER N WITH CEDILLA]
"\u0145" => "N"
# Ň [LATIN CAPITAL LETTER N WITH CARON]
"\u0147" => "N"
# Ŋ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN CAPITAL LETTER ENG]
"\u014A" => "N"
# Ɲ [LATIN CAPITAL LETTER N WITH LEFT HOOK]
"\u019D" => "N"
# Ǹ [LATIN CAPITAL LETTER N WITH GRAVE]
"\u01F8" => "N"
# Ƞ [LATIN CAPITAL LETTER N WITH LONG RIGHT LEG]
"\u0220" => "N"
# ɴ [LATIN LETTER SMALL CAPITAL N]
"\u0274" => "N"
# ᴎ [LATIN LETTER SMALL CAPITAL REVERSED N]
"\u1D0E" => "N"
# Ṅ [LATIN CAPITAL LETTER N WITH DOT ABOVE]
"\u1E44" => "N"
# Ṇ [LATIN CAPITAL LETTER N WITH DOT BELOW]
"\u1E46" => "N"
# Ṉ [LATIN CAPITAL LETTER N WITH LINE BELOW]
"\u1E48" => "N"
# Ṋ [LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW]
"\u1E4A" => "N"
# Ⓝ [CIRCLED LATIN CAPITAL LETTER N]
"\u24C3" => "N"
# Ｎ [FULLWIDTH LATIN CAPITAL LETTER N]
"\uFF2E" => "N"
# ñ [LATIN SMALL LETTER N WITH TILDE]
"\u00F1" => "n"
# ń [LATIN SMALL LETTER N WITH ACUTE]
"\u0144" => "n"
# ņ [LATIN SMALL LETTER N WITH CEDILLA]
"\u0146" => "n"
# ň [LATIN SMALL LETTER N WITH CARON]
"\u0148" => "n"
# ʼn [LATIN SMALL LETTER N PRECEDED BY APOSTROPHE]
"\u0149" => "n"
# ŋ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN SMALL LETTER ENG]
"\u014B" => "n"
# ƞ [LATIN SMALL LETTER N WITH LONG RIGHT LEG]
"\u019E" => "n"
# ǹ [LATIN SMALL LETTER N WITH GRAVE]
"\u01F9" => "n"
# ȵ [LATIN SMALL LETTER N WITH CURL]
"\u0235" => "n"
# ɲ [LATIN SMALL LETTER N WITH LEFT HOOK]
"\u0272" => "n"
# ɳ [LATIN SMALL LETTER N WITH RETROFLEX HOOK]
"\u0273" => "n"
# ᵰ [LATIN SMALL LETTER N WITH MIDDLE TILDE]
"\u1D70" => "n"
# ᶇ [LATIN SMALL LETTER N WITH PALATAL HOOK]
"\u1D87" => "n"
# ṅ [LATIN SMALL LETTER N WITH DOT ABOVE]
"\u1E45" => "n"
# ṇ [LATIN SMALL LETTER N WITH DOT BELOW]
"\u1E47" => "n"
# ṉ [LATIN SMALL LETTER N WITH LINE BELOW]
"\u1E49" => "n"
# ṋ [LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW]
"\u1E4B" => "n"
# ⁿ [SUPERSCRIPT LATIN SMALL LETTER N]
"\u207F" => "n"
# ⓝ [CIRCLED LATIN SMALL LETTER N]
"\u24DD" => "n"
# ｎ [FULLWIDTH LATIN SMALL LETTER N]
"\uFF4E" => "n"
# NJ [LATIN CAPITAL LETTER NJ]
"\u01CA" => "NJ"
# Nj [LATIN CAPITAL LETTER N WITH SMALL LETTER J]
"\u01CB" => "Nj"
# ⒩ [PARENTHESIZED LATIN SMALL LETTER N]
"\u24A9" => "(n)"
# nj [LATIN SMALL LETTER NJ]
"\u01CC" => "nj"
# Ò [LATIN CAPITAL LETTER O WITH GRAVE]
"\u00D2" => "O"
# Ó [LATIN CAPITAL LETTER O WITH ACUTE]
"\u00D3" => "O"
# Ô [LATIN CAPITAL LETTER O WITH CIRCUMFLEX]
"\u00D4" => "O"
# Õ [LATIN CAPITAL LETTER O WITH TILDE]
"\u00D5" => "O"
# Ö [LATIN CAPITAL LETTER O WITH DIAERESIS]
"\u00D6" => "O"
# Ø [LATIN CAPITAL LETTER O WITH STROKE]
"\u00D8" => "O"
# Ō [LATIN CAPITAL LETTER O WITH MACRON]
"\u014C" => "O"
# Ŏ [LATIN CAPITAL LETTER O WITH BREVE]
"\u014E" => "O"
# Ő [LATIN CAPITAL LETTER O WITH DOUBLE ACUTE]
"\u0150" => "O"
# Ɔ [LATIN CAPITAL LETTER OPEN O]
"\u0186" => "O"
# Ɵ [LATIN CAPITAL LETTER O WITH MIDDLE TILDE]
"\u019F" => "O"
# Ơ [LATIN CAPITAL LETTER O WITH HORN]
"\u01A0" => "O"
# Ǒ [LATIN CAPITAL LETTER O WITH CARON]
"\u01D1" => "O"
# Ǫ [LATIN CAPITAL LETTER O WITH OGONEK]
"\u01EA" => "O"
# Ǭ [LATIN CAPITAL LETTER O WITH OGONEK AND MACRON]
"\u01EC" => "O"
# Ǿ [LATIN CAPITAL LETTER O WITH STROKE AND ACUTE]
"\u01FE" => "O"
# Ȍ [LATIN CAPITAL LETTER O WITH DOUBLE GRAVE]
"\u020C" => "O"
# Ȏ [LATIN CAPITAL LETTER O WITH INVERTED BREVE]
"\u020E" => "O"
# Ȫ [LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON]
"\u022A" => "O"
# Ȭ [LATIN CAPITAL LETTER O WITH TILDE AND MACRON]
"\u022C" => "O"
# Ȯ [LATIN CAPITAL LETTER O WITH DOT ABOVE]
"\u022E" => "O"
# Ȱ [LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON]
"\u0230" => "O"
# ᴏ [LATIN LETTER SMALL CAPITAL O]
"\u1D0F" => "O"
# ᴐ [LATIN LETTER SMALL CAPITAL OPEN O]
"\u1D10" => "O"
# Ṍ [LATIN CAPITAL LETTER O WITH TILDE AND ACUTE]
"\u1E4C" => "O"
# Ṏ [LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS]
"\u1E4E" => "O"
# Ṑ [LATIN CAPITAL LETTER O WITH MACRON AND GRAVE]
"\u1E50" => "O"
# Ṓ [LATIN CAPITAL LETTER O WITH MACRON AND ACUTE]
"\u1E52" => "O"
# Ọ [LATIN CAPITAL LETTER O WITH DOT BELOW]
"\u1ECC" => "O"
# Ỏ [LATIN CAPITAL LETTER O WITH HOOK ABOVE]
"\u1ECE" => "O"
# Ố [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE]
"\u1ED0" => "O"
# Ồ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE]
"\u1ED2" => "O"
# Ổ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE]
"\u1ED4" => "O"
# Ỗ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE]
"\u1ED6" => "O"
# Ộ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW]
"\u1ED8" => "O"
# Ớ [LATIN CAPITAL LETTER O WITH HORN AND ACUTE]
"\u1EDA" => "O"
# Ờ [LATIN CAPITAL LETTER O WITH HORN AND GRAVE]
"\u1EDC" => "O"
# Ở [LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE]
"\u1EDE" => "O"
# Ỡ [LATIN CAPITAL LETTER O WITH HORN AND TILDE]
"\u1EE0" => "O"
# Ợ [LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW]
"\u1EE2" => "O"
# Ⓞ [CIRCLED LATIN CAPITAL LETTER O]
"\u24C4" => "O"
# Ꝋ [LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY]
"\uA74A" => "O"
# Ꝍ [LATIN CAPITAL LETTER O WITH LOOP]
"\uA74C" => "O"
# Ｏ [FULLWIDTH LATIN CAPITAL LETTER O]
"\uFF2F" => "O"
# ò [LATIN SMALL LETTER O WITH GRAVE]
"\u00F2" => "o"
# ó [LATIN SMALL LETTER O WITH ACUTE]
"\u00F3" => "o"
# ô [LATIN SMALL LETTER O WITH CIRCUMFLEX]
"\u00F4" => "o"
# õ [LATIN SMALL LETTER O WITH TILDE]
"\u00F5" => "o"
# ö [LATIN SMALL LETTER O WITH DIAERESIS]
"\u00F6" => "o"
# ø [LATIN SMALL LETTER O WITH STROKE]
"\u00F8" => "o"
# ō [LATIN SMALL LETTER O WITH MACRON]
"\u014D" => "o"
# ŏ [LATIN SMALL LETTER O WITH BREVE]
"\u014F" => "o"
# ő [LATIN SMALL LETTER O WITH DOUBLE ACUTE]
"\u0151" => "o"
# ơ [LATIN SMALL LETTER O WITH HORN]
"\u01A1" => "o"
# ǒ [LATIN SMALL LETTER O WITH CARON]
"\u01D2" => "o"
# ǫ [LATIN SMALL LETTER O WITH OGONEK]
"\u01EB" => "o"
# ǭ [LATIN SMALL LETTER O WITH OGONEK AND MACRON]
"\u01ED" => "o"
# ǿ [LATIN SMALL LETTER O WITH STROKE AND ACUTE]
"\u01FF" => "o"
# ȍ [LATIN SMALL LETTER O WITH DOUBLE GRAVE]
"\u020D" => "o"
# ȏ [LATIN SMALL LETTER O WITH INVERTED BREVE]
"\u020F" => "o"
# ȫ [LATIN SMALL LETTER O WITH DIAERESIS AND MACRON]
"\u022B" => "o"
# ȭ [LATIN SMALL LETTER O WITH TILDE AND MACRON]
"\u022D" => "o"
# ȯ [LATIN SMALL LETTER O WITH DOT ABOVE]
"\u022F" => "o"
# ȱ [LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON]
"\u0231" => "o"
# ɔ [LATIN SMALL LETTER OPEN O]
"\u0254" => "o"
# ɵ [LATIN SMALL LETTER BARRED O]
"\u0275" => "o"
# ᴖ [LATIN SMALL LETTER TOP HALF O]
"\u1D16" => "o"
# ᴗ [LATIN SMALL LETTER BOTTOM HALF O]
"\u1D17" => "o"
# ᶗ [LATIN SMALL LETTER OPEN O WITH RETROFLEX HOOK]
"\u1D97" => "o"
# ṍ [LATIN SMALL LETTER O WITH TILDE AND ACUTE]
"\u1E4D" => "o"
# ṏ [LATIN SMALL LETTER O WITH TILDE AND DIAERESIS]
"\u1E4F" => "o"
# ṑ [LATIN SMALL LETTER O WITH MACRON AND GRAVE]
"\u1E51" => "o"
# ṓ [LATIN SMALL LETTER O WITH MACRON AND ACUTE]
"\u1E53" => "o"
# ọ [LATIN SMALL LETTER O WITH DOT BELOW]
"\u1ECD" => "o"
# ỏ [LATIN SMALL LETTER O WITH HOOK ABOVE]
"\u1ECF" => "o"
# ố [LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE]
"\u1ED1" => "o"
# ồ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE]
"\u1ED3" => "o"
# ổ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE]
"\u1ED5" => "o"
# ỗ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE]
"\u1ED7" => "o"
# ộ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW]
"\u1ED9" => "o"
# ớ [LATIN SMALL LETTER O WITH HORN AND ACUTE]
"\u1EDB" => "o"
# ờ [LATIN SMALL LETTER O WITH HORN AND GRAVE]
"\u1EDD" => "o"
# ở [LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE]
"\u1EDF" => "o"
# ỡ [LATIN SMALL LETTER O WITH HORN AND TILDE]
"\u1EE1" => "o"
# ợ [LATIN SMALL LETTER O WITH HORN AND DOT BELOW]
"\u1EE3" => "o"
# ₒ [LATIN SUBSCRIPT SMALL LETTER O]
"\u2092" => "o"
# ⓞ [CIRCLED LATIN SMALL LETTER O]
"\u24DE" => "o"
# ⱺ [LATIN SMALL LETTER O WITH LOW RING INSIDE]
"\u2C7A" => "o"
# ꝋ [LATIN SMALL LETTER O WITH LONG STROKE OVERLAY]
"\uA74B" => "o"
# ꝍ [LATIN SMALL LETTER O WITH LOOP]
"\uA74D" => "o"
# ｏ [FULLWIDTH LATIN SMALL LETTER O]
"\uFF4F" => "o"
# Π[LATIN CAPITAL LIGATURE OE]
"\u0152" => "OE"
# ɶ [LATIN LETTER SMALL CAPITAL OE]
"\u0276" => "OE"
# Ꝏ [LATIN CAPITAL LETTER OO]
"\uA74E" => "OO"
# Ȣ http://en.wikipedia.org/wiki/OU [LATIN CAPITAL LETTER OU]
"\u0222" => "OU"
# ᴕ [LATIN LETTER SMALL CAPITAL OU]
"\u1D15" => "OU"
# ⒪ [PARENTHESIZED LATIN SMALL LETTER O]
"\u24AA" => "(o)"
# œ [LATIN SMALL LIGATURE OE]
"\u0153" => "oe"
# ᴔ [LATIN SMALL LETTER TURNED OE]
"\u1D14" => "oe"
# ꝏ [LATIN SMALL LETTER OO]
"\uA74F" => "oo"
# ȣ http://en.wikipedia.org/wiki/OU [LATIN SMALL LETTER OU]
"\u0223" => "ou"
# Ƥ [LATIN CAPITAL LETTER P WITH HOOK]
"\u01A4" => "P"
# ᴘ [LATIN LETTER SMALL CAPITAL P]
"\u1D18" => "P"
# Ṕ [LATIN CAPITAL LETTER P WITH ACUTE]
"\u1E54" => "P"
# Ṗ [LATIN CAPITAL LETTER P WITH DOT ABOVE]
"\u1E56" => "P"
# Ⓟ [CIRCLED LATIN CAPITAL LETTER P]
"\u24C5" => "P"
# Ᵽ [LATIN CAPITAL LETTER P WITH STROKE]
"\u2C63" => "P"
# Ꝑ [LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER]
"\uA750" => "P"
# Ꝓ [LATIN CAPITAL LETTER P WITH FLOURISH]
"\uA752" => "P"
# Ꝕ [LATIN CAPITAL LETTER P WITH SQUIRREL TAIL]
"\uA754" => "P"
# Ｐ [FULLWIDTH LATIN CAPITAL LETTER P]
"\uFF30" => "P"
# ƥ [LATIN SMALL LETTER P WITH HOOK]
"\u01A5" => "p"
# ᵱ [LATIN SMALL LETTER P WITH MIDDLE TILDE]
"\u1D71" => "p"
# ᵽ [LATIN SMALL LETTER P WITH STROKE]
"\u1D7D" => "p"
# ᶈ [LATIN SMALL LETTER P WITH PALATAL HOOK]
"\u1D88" => "p"
# ṕ [LATIN SMALL LETTER P WITH ACUTE]
"\u1E55" => "p"
# ṗ [LATIN SMALL LETTER P WITH DOT ABOVE]
"\u1E57" => "p"
# ⓟ [CIRCLED LATIN SMALL LETTER P]
"\u24DF" => "p"
# ꝑ [LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER]
"\uA751" => "p"
# ꝓ [LATIN SMALL LETTER P WITH FLOURISH]
"\uA753" => "p"
# ꝕ [LATIN SMALL LETTER P WITH SQUIRREL TAIL]
"\uA755" => "p"
# ꟼ [LATIN EPIGRAPHIC LETTER REVERSED P]
"\uA7FC" => "p"
# ｐ [FULLWIDTH LATIN SMALL LETTER P]
"\uFF50" => "p"
# ⒫ [PARENTHESIZED LATIN SMALL LETTER P]
"\u24AB" => "(p)"
# Ɋ [LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL]
"\u024A" => "Q"
# Ⓠ [CIRCLED LATIN CAPITAL LETTER Q]
"\u24C6" => "Q"
# Ꝗ [LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER]
"\uA756" => "Q"
# Ꝙ [LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE]
"\uA758" => "Q"
# Ｑ [FULLWIDTH LATIN CAPITAL LETTER Q]
"\uFF31" => "Q"
# ĸ http://en.wikipedia.org/wiki/Kra_(letter) [LATIN SMALL LETTER KRA]
"\u0138" => "q"
# ɋ [LATIN SMALL LETTER Q WITH HOOK TAIL]
"\u024B" => "q"
# ʠ [LATIN SMALL LETTER Q WITH HOOK]
"\u02A0" => "q"
# ⓠ [CIRCLED LATIN SMALL LETTER Q]
"\u24E0" => "q"
# ꝗ [LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER]
"\uA757" => "q"
# ꝙ [LATIN SMALL LETTER Q WITH DIAGONAL STROKE]
"\uA759" => "q"
# ｑ [FULLWIDTH LATIN SMALL LETTER Q]
"\uFF51" => "q"
# ⒬ [PARENTHESIZED LATIN SMALL LETTER Q]
"\u24AC" => "(q)"
# ȹ [LATIN SMALL LETTER QP DIGRAPH]
"\u0239" => "qp"
# Ŕ [LATIN CAPITAL LETTER R WITH ACUTE]
"\u0154" => "R"
# Ŗ [LATIN CAPITAL LETTER R WITH CEDILLA]
"\u0156" => "R"
# Ř [LATIN CAPITAL LETTER R WITH CARON]
"\u0158" => "R"
# Ȓ [LATIN CAPITAL LETTER R WITH DOUBLE GRAVE]
"\u0210" => "R"
# Ȓ [LATIN CAPITAL LETTER R WITH INVERTED BREVE]
"\u0212" => "R"
# Ɍ [LATIN CAPITAL LETTER R WITH STROKE]
"\u024C" => "R"
# ʀ [LATIN LETTER SMALL CAPITAL R]
"\u0280" => "R"
# ʁ [LATIN LETTER SMALL CAPITAL INVERTED R]
"\u0281" => "R"
# ᴙ [LATIN LETTER SMALL CAPITAL REVERSED R]
"\u1D19" => "R"
# ᴚ [LATIN LETTER SMALL CAPITAL TURNED R]
"\u1D1A" => "R"
# Ṙ [LATIN CAPITAL LETTER R WITH DOT ABOVE]
"\u1E58" => "R"
# Ṛ [LATIN CAPITAL LETTER R WITH DOT BELOW]
"\u1E5A" => "R"
# Ṝ [LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON]
"\u1E5C" => "R"
# Ṟ [LATIN CAPITAL LETTER R WITH LINE BELOW]
"\u1E5E" => "R"
# Ⓡ [CIRCLED LATIN CAPITAL LETTER R]
"\u24C7" => "R"
# Ɽ [LATIN CAPITAL LETTER R WITH TAIL]
"\u2C64" => "R"
# Ꝛ [LATIN CAPITAL LETTER R ROTUNDA]
"\uA75A" => "R"
# Ꞃ [LATIN CAPITAL LETTER INSULAR R]
"\uA782" => "R"
# Ｒ [FULLWIDTH LATIN CAPITAL LETTER R]
"\uFF32" => "R"
# ŕ [LATIN SMALL LETTER R WITH ACUTE]
"\u0155" => "r"
# ŗ [LATIN SMALL LETTER R WITH CEDILLA]
"\u0157" => "r"
# ř [LATIN SMALL LETTER R WITH CARON]
"\u0159" => "r"
# ȑ [LATIN SMALL LETTER R WITH DOUBLE GRAVE]
"\u0211" => "r"
# ȓ [LATIN SMALL LETTER R WITH INVERTED BREVE]
"\u0213" => "r"
# ɍ [LATIN SMALL LETTER R WITH STROKE]
"\u024D" => "r"
# ɼ [LATIN SMALL LETTER R WITH LONG LEG]
"\u027C" => "r"
# ɽ [LATIN SMALL LETTER R WITH TAIL]
"\u027D" => "r"
# ɾ [LATIN SMALL LETTER R WITH FISHHOOK]
"\u027E" => "r"
# ɿ [LATIN SMALL LETTER REVERSED R WITH FISHHOOK]
"\u027F" => "r"
# ᵣ [LATIN SUBSCRIPT SMALL LETTER R]
"\u1D63" => "r"
# ᵲ [LATIN SMALL LETTER R WITH MIDDLE TILDE]
"\u1D72" => "r"
# ᵳ [LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE]
"\u1D73" => "r"
# ᶉ [LATIN SMALL LETTER R WITH PALATAL HOOK]
"\u1D89" => "r"
# ṙ [LATIN SMALL LETTER R WITH DOT ABOVE]
"\u1E59" => "r"
# ṛ [LATIN SMALL LETTER R WITH DOT BELOW]
"\u1E5B" => "r"
# ṝ [LATIN SMALL LETTER R WITH DOT BELOW AND MACRON]
"\u1E5D" => "r"
# ṟ [LATIN SMALL LETTER R WITH LINE BELOW]
"\u1E5F" => "r"
# ⓡ [CIRCLED LATIN SMALL LETTER R]
"\u24E1" => "r"
# ꝛ [LATIN SMALL LETTER R ROTUNDA]
"\uA75B" => "r"
# ꞃ [LATIN SMALL LETTER INSULAR R]
"\uA783" => "r"
# ｒ [FULLWIDTH LATIN SMALL LETTER R]
"\uFF52" => "r"
# ⒭ [PARENTHESIZED LATIN SMALL LETTER R]
"\u24AD" => "(r)"
# Ś [LATIN CAPITAL LETTER S WITH ACUTE]
"\u015A" => "S"
# Ŝ [LATIN CAPITAL LETTER S WITH CIRCUMFLEX]
"\u015C" => "S"
# Ş [LATIN CAPITAL LETTER S WITH CEDILLA]
"\u015E" => "S"
# Š [LATIN CAPITAL LETTER S WITH CARON]
"\u0160" => "S"
# Ș [LATIN CAPITAL LETTER S WITH COMMA BELOW]
"\u0218" => "S"
# Ṡ [LATIN CAPITAL LETTER S WITH DOT ABOVE]
"\u1E60" => "S"
# Ṣ [LATIN CAPITAL LETTER S WITH DOT BELOW]
"\u1E62" => "S"
# Ṥ [LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE]
"\u1E64" => "S"
# Ṧ [LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE]
"\u1E66" => "S"
# Ṩ [LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE]
"\u1E68" => "S"
# Ⓢ [CIRCLED LATIN CAPITAL LETTER S]
"\u24C8" => "S"
# ꜱ [LATIN LETTER SMALL CAPITAL S]
"\uA731" => "S"
# ꞅ [LATIN SMALL LETTER INSULAR S]
"\uA785" => "S"
# Ｓ [FULLWIDTH LATIN CAPITAL LETTER S]
"\uFF33" => "S"
# ś [LATIN SMALL LETTER S WITH ACUTE]
"\u015B" => "s"
# ŝ [LATIN SMALL LETTER S WITH CIRCUMFLEX]
"\u015D" => "s"
# ş [LATIN SMALL LETTER S WITH CEDILLA]
"\u015F" => "s"
# š [LATIN SMALL LETTER S WITH CARON]
"\u0161" => "s"
# ſ http://en.wikipedia.org/wiki/Long_S [LATIN SMALL LETTER LONG S]
"\u017F" => "s"
# ș [LATIN SMALL LETTER S WITH COMMA BELOW]
"\u0219" => "s"
# ȿ [LATIN SMALL LETTER S WITH SWASH TAIL]
"\u023F" => "s"
# ʂ [LATIN SMALL LETTER S WITH HOOK]
"\u0282" => "s"
# ᵴ [LATIN SMALL LETTER S WITH MIDDLE TILDE]
"\u1D74" => "s"
# ᶊ [LATIN SMALL LETTER S WITH PALATAL HOOK]
"\u1D8A" => "s"
# ṡ [LATIN SMALL LETTER S WITH DOT ABOVE]
"\u1E61" => "s"
# ṣ [LATIN SMALL LETTER S WITH DOT BELOW]
"\u1E63" => "s"
# ṥ [LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE]
"\u1E65" => "s"
# ṧ [LATIN SMALL LETTER S WITH CARON AND DOT ABOVE]
"\u1E67" => "s"
# ṩ [LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE]
"\u1E69" => "s"
# ẜ [LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE]
"\u1E9C" => "s"
# ẝ [LATIN SMALL LETTER LONG S WITH HIGH STROKE]
"\u1E9D" => "s"
# ⓢ [CIRCLED LATIN SMALL LETTER S]
"\u24E2" => "s"
# Ꞅ [LATIN CAPITAL LETTER INSULAR S]
"\uA784" => "s"
# ｓ [FULLWIDTH LATIN SMALL LETTER S]
"\uFF53" => "s"
# ẞ [LATIN CAPITAL LETTER SHARP S]
"\u1E9E" => "SS"
# ⒮ [PARENTHESIZED LATIN SMALL LETTER S]
"\u24AE" => "(s)"
# ß [LATIN SMALL LETTER SHARP S]
"\u00DF" => "ss"
# st [LATIN SMALL LIGATURE ST]
"\uFB06" => "st"
# Ţ [LATIN CAPITAL LETTER T WITH CEDILLA]
"\u0162" => "T"
# Ť [LATIN CAPITAL LETTER T WITH CARON]
"\u0164" => "T"
# Ŧ [LATIN CAPITAL LETTER T WITH STROKE]
"\u0166" => "T"
# Ƭ [LATIN CAPITAL LETTER T WITH HOOK]
"\u01AC" => "T"
# Ʈ [LATIN CAPITAL LETTER T WITH RETROFLEX HOOK]
"\u01AE" => "T"
# Ț [LATIN CAPITAL LETTER T WITH COMMA BELOW]
"\u021A" => "T"
# Ⱦ [LATIN CAPITAL LETTER T WITH DIAGONAL STROKE]
"\u023E" => "T"
# ᴛ [LATIN LETTER SMALL CAPITAL T]
"\u1D1B" => "T"
# Ṫ [LATIN CAPITAL LETTER T WITH DOT ABOVE]
"\u1E6A" => "T"
# Ṭ [LATIN CAPITAL LETTER T WITH DOT BELOW]
"\u1E6C" => "T"
# Ṯ [LATIN CAPITAL LETTER T WITH LINE BELOW]
"\u1E6E" => "T"
# Ṱ [LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW]
"\u1E70" => "T"
# Ⓣ [CIRCLED LATIN CAPITAL LETTER T]
"\u24C9" => "T"
# Ꞇ [LATIN CAPITAL LETTER INSULAR T]
"\uA786" => "T"
# Ｔ [FULLWIDTH LATIN CAPITAL LETTER T]
"\uFF34" => "T"
# ţ [LATIN SMALL LETTER T WITH CEDILLA]
"\u0163" => "t"
# ť [LATIN SMALL LETTER T WITH CARON]
"\u0165" => "t"
# ŧ [LATIN SMALL LETTER T WITH STROKE]
"\u0167" => "t"
# ƫ [LATIN SMALL LETTER T WITH PALATAL HOOK]
"\u01AB" => "t"
# ƭ [LATIN SMALL LETTER T WITH HOOK]
"\u01AD" => "t"
# ț [LATIN SMALL LETTER T WITH COMMA BELOW]
"\u021B" => "t"
# ȶ [LATIN SMALL LETTER T WITH CURL]
"\u0236" => "t"
# ʇ [LATIN SMALL LETTER TURNED T]
"\u0287" => "t"
# ʈ [LATIN SMALL LETTER T WITH RETROFLEX HOOK]
"\u0288" => "t"
# ᵵ [LATIN SMALL LETTER T WITH MIDDLE TILDE]
"\u1D75" => "t"
# ṫ [LATIN SMALL LETTER T WITH DOT ABOVE]
"\u1E6B" => "t"
# ṭ [LATIN SMALL LETTER T WITH DOT BELOW]
"\u1E6D" => "t"
# ṯ [LATIN SMALL LETTER T WITH LINE BELOW]
"\u1E6F" => "t"
# ṱ [LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW]
"\u1E71" => "t"
# ẗ [LATIN SMALL LETTER T WITH DIAERESIS]
"\u1E97" => "t"
# ⓣ [CIRCLED LATIN SMALL LETTER T]
"\u24E3" => "t"
# ⱦ [LATIN SMALL LETTER T WITH DIAGONAL STROKE]
"\u2C66" => "t"
# ｔ [FULLWIDTH LATIN SMALL LETTER T]
"\uFF54" => "t"
# Þ [LATIN CAPITAL LETTER THORN]
"\u00DE" => "TH"
# Ꝧ [LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER]
"\uA766" => "TH"
# Ꜩ [LATIN CAPITAL LETTER TZ]
"\uA728" => "TZ"
# ⒯ [PARENTHESIZED LATIN SMALL LETTER T]
"\u24AF" => "(t)"
# ʨ [LATIN SMALL LETTER TC DIGRAPH WITH CURL]
"\u02A8" => "tc"
# þ [LATIN SMALL LETTER THORN]
"\u00FE" => "th"
# ᵺ [LATIN SMALL LETTER TH WITH STRIKETHROUGH]
"\u1D7A" => "th"
# ꝧ [LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER]
"\uA767" => "th"
# ʦ [LATIN SMALL LETTER TS DIGRAPH]
"\u02A6" => "ts"
# ꜩ [LATIN SMALL LETTER TZ]
"\uA729" => "tz"
# Ù [LATIN CAPITAL LETTER U WITH GRAVE]
"\u00D9" => "U"
# Ú [LATIN CAPITAL LETTER U WITH ACUTE]
"\u00DA" => "U"
# Û [LATIN CAPITAL LETTER U WITH CIRCUMFLEX]
"\u00DB" => "U"
# Ü [LATIN CAPITAL LETTER U WITH DIAERESIS]
"\u00DC" => "U"
# Ũ [LATIN CAPITAL LETTER U WITH TILDE]
"\u0168" => "U"
# Ū [LATIN CAPITAL LETTER U WITH MACRON]
"\u016A" => "U"
# Ŭ [LATIN CAPITAL LETTER U WITH BREVE]
"\u016C" => "U"
# Ů [LATIN CAPITAL LETTER U WITH RING ABOVE]
"\u016E" => "U"
# Ű [LATIN CAPITAL LETTER U WITH DOUBLE ACUTE]
"\u0170" => "U"
# Ų [LATIN CAPITAL LETTER U WITH OGONEK]
"\u0172" => "U"
# Ư [LATIN CAPITAL LETTER U WITH HORN]
"\u01AF" => "U"
# Ǔ [LATIN CAPITAL LETTER U WITH CARON]
"\u01D3" => "U"
# Ǖ [LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON]
"\u01D5" => "U"
# Ǘ [LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE]
"\u01D7" => "U"
# Ǚ [LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON]
"\u01D9" => "U"
# Ǜ [LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE]
"\u01DB" => "U"
# Ȕ [LATIN CAPITAL LETTER U WITH DOUBLE GRAVE]
"\u0214" => "U"
# Ȗ [LATIN CAPITAL LETTER U WITH INVERTED BREVE]
"\u0216" => "U"
# Ʉ [LATIN CAPITAL LETTER U BAR]
"\u0244" => "U"
# ᴜ [LATIN LETTER SMALL CAPITAL U]
"\u1D1C" => "U"
# ᵾ [LATIN SMALL CAPITAL LETTER U WITH STROKE]
"\u1D7E" => "U"
# Ṳ [LATIN CAPITAL LETTER U WITH DIAERESIS BELOW]
"\u1E72" => "U"
# Ṵ [LATIN CAPITAL LETTER U WITH TILDE BELOW]
"\u1E74" => "U"
# Ṷ [LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW]
"\u1E76" => "U"
# Ṹ [LATIN CAPITAL LETTER U WITH TILDE AND ACUTE]
"\u1E78" => "U"
# Ṻ [LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS]
"\u1E7A" => "U"
# Ụ [LATIN CAPITAL LETTER U WITH DOT BELOW]
"\u1EE4" => "U"
# Ủ [LATIN CAPITAL LETTER U WITH HOOK ABOVE]
"\u1EE6" => "U"
# Ứ [LATIN CAPITAL LETTER U WITH HORN AND ACUTE]
"\u1EE8" => "U"
# Ừ [LATIN CAPITAL LETTER U WITH HORN AND GRAVE]
"\u1EEA" => "U"
# Ử [LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE]
"\u1EEC" => "U"
# Ữ [LATIN CAPITAL LETTER U WITH HORN AND TILDE]
"\u1EEE" => "U"
# Ự [LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW]
"\u1EF0" => "U"
# Ⓤ [CIRCLED LATIN CAPITAL LETTER U]
"\u24CA" => "U"
# Ｕ [FULLWIDTH LATIN CAPITAL LETTER U]
"\uFF35" => "U"
# ù [LATIN SMALL LETTER U WITH GRAVE]
"\u00F9" => "u"
# ú [LATIN SMALL LETTER U WITH ACUTE]
"\u00FA" => "u"
# û [LATIN SMALL LETTER U WITH CIRCUMFLEX]
"\u00FB" => "u"
# ü [LATIN SMALL LETTER U WITH DIAERESIS]
"\u00FC" => "u"
# ũ [LATIN SMALL LETTER U WITH TILDE]
"\u0169" => "u"
# ū [LATIN SMALL LETTER U WITH MACRON]
"\u016B" => "u"
# ŭ [LATIN SMALL LETTER U WITH BREVE]
"\u016D" => "u"
# ů [LATIN SMALL LETTER U WITH RING ABOVE]
"\u016F" => "u"
# ű [LATIN SMALL LETTER U WITH DOUBLE ACUTE]
"\u0171" => "u"
# ų [LATIN SMALL LETTER U WITH OGONEK]
"\u0173" => "u"
# ư [LATIN SMALL LETTER U WITH HORN]
"\u01B0" => "u"
# ǔ [LATIN SMALL LETTER U WITH CARON]
"\u01D4" => "u"
# ǖ [LATIN SMALL LETTER U WITH DIAERESIS AND MACRON]
"\u01D6" => "u"
# ǘ [LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE]
"\u01D8" => "u"
# ǚ [LATIN SMALL LETTER U WITH DIAERESIS AND CARON]
"\u01DA" => "u"
# ǜ [LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE]
"\u01DC" => "u"
# ȕ [LATIN SMALL LETTER U WITH DOUBLE GRAVE]
"\u0215" => "u"
# ȗ [LATIN SMALL LETTER U WITH INVERTED BREVE]
"\u0217" => "u"
# ʉ [LATIN SMALL LETTER U BAR]
"\u0289" => "u"
# ᵤ [LATIN SUBSCRIPT SMALL LETTER U]
"\u1D64" => "u"
# ᶙ [LATIN SMALL LETTER U WITH RETROFLEX HOOK]
"\u1D99" => "u"
# ṳ [LATIN SMALL LETTER U WITH DIAERESIS BELOW]
"\u1E73" => "u"
# ṵ [LATIN SMALL LETTER U WITH TILDE BELOW]
"\u1E75" => "u"
# ṷ [LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW]
"\u1E77" => "u"
# ṹ [LATIN SMALL LETTER U WITH TILDE AND ACUTE]
"\u1E79" => "u"
# ṻ [LATIN SMALL LETTER U WITH MACRON AND DIAERESIS]
"\u1E7B" => "u"
# ụ [LATIN SMALL LETTER U WITH DOT BELOW]
"\u1EE5" => "u"
# ủ [LATIN SMALL LETTER U WITH HOOK ABOVE]
"\u1EE7" => "u"
# ứ [LATIN SMALL LETTER U WITH HORN AND ACUTE]
"\u1EE9" => "u"
# ừ [LATIN SMALL LETTER U WITH HORN AND GRAVE]
"\u1EEB" => "u"
# ử [LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE]
"\u1EED" => "u"
# ữ [LATIN SMALL LETTER U WITH HORN AND TILDE]
"\u1EEF" => "u"
# ự [LATIN SMALL LETTER U WITH HORN AND DOT BELOW]
"\u1EF1" => "u"
# ⓤ [CIRCLED LATIN SMALL LETTER U]
"\u24E4" => "u"
# ｕ [FULLWIDTH LATIN SMALL LETTER U]
"\uFF55" => "u"
# ⒰ [PARENTHESIZED LATIN SMALL LETTER U]
"\u24B0" => "(u)"
# ᵫ [LATIN SMALL LETTER UE]
"\u1D6B" => "ue"
# Ʋ [LATIN CAPITAL LETTER V WITH HOOK]
"\u01B2" => "V"
# Ʌ [LATIN CAPITAL LETTER TURNED V]
"\u0245" => "V"
# ᴠ [LATIN LETTER SMALL CAPITAL V]
"\u1D20" => "V"
# Ṽ [LATIN CAPITAL LETTER V WITH TILDE]
"\u1E7C" => "V"
# Ṿ [LATIN CAPITAL LETTER V WITH DOT BELOW]
"\u1E7E" => "V"
# Ỽ [LATIN CAPITAL LETTER MIDDLE-WELSH V]
"\u1EFC" => "V"
# Ⓥ [CIRCLED LATIN CAPITAL LETTER V]
"\u24CB" => "V"
# Ꝟ [LATIN CAPITAL LETTER V WITH DIAGONAL STROKE]
"\uA75E" => "V"
# Ꝩ [LATIN CAPITAL LETTER VEND]
"\uA768" => "V"
# Ｖ [FULLWIDTH LATIN CAPITAL LETTER V]
"\uFF36" => "V"
# ʋ [LATIN SMALL LETTER V WITH HOOK]
"\u028B" => "v"
# ʌ [LATIN SMALL LETTER TURNED V]
"\u028C" => "v"
# ᵥ [LATIN SUBSCRIPT SMALL LETTER V]
"\u1D65" => "v"
# ᶌ [LATIN SMALL LETTER V WITH PALATAL HOOK]
"\u1D8C" => "v"
# ṽ [LATIN SMALL LETTER V WITH TILDE]
"\u1E7D" => "v"
# ṿ [LATIN SMALL LETTER V WITH DOT BELOW]
"\u1E7F" => "v"
# ⓥ [CIRCLED LATIN SMALL LETTER V]
"\u24E5" => "v"
# ⱱ [LATIN SMALL LETTER V WITH RIGHT HOOK]
"\u2C71" => "v"
# ⱴ [LATIN SMALL LETTER V WITH CURL]
"\u2C74" => "v"
# ꝟ [LATIN SMALL LETTER V WITH DIAGONAL STROKE]
"\uA75F" => "v"
# ｖ [FULLWIDTH LATIN SMALL LETTER V]
"\uFF56" => "v"
# Ꝡ [LATIN CAPITAL LETTER VY]
"\uA760" => "VY"
# ⒱ [PARENTHESIZED LATIN SMALL LETTER V]
"\u24B1" => "(v)"
# ꝡ [LATIN SMALL LETTER VY]
"\uA761" => "vy"
# Ŵ [LATIN CAPITAL LETTER W WITH CIRCUMFLEX]
"\u0174" => "W"
# Ƿ http://en.wikipedia.org/wiki/Wynn [LATIN CAPITAL LETTER WYNN]
"\u01F7" => "W"
# ᴡ [LATIN LETTER SMALL CAPITAL W]
"\u1D21" => "W"
# Ẁ [LATIN CAPITAL LETTER W WITH GRAVE]
"\u1E80" => "W"
# Ẃ [LATIN CAPITAL LETTER W WITH ACUTE]
"\u1E82" => "W"
# Ẅ [LATIN CAPITAL LETTER W WITH DIAERESIS]
"\u1E84" => "W"
# Ẇ [LATIN CAPITAL LETTER W WITH DOT ABOVE]
"\u1E86" => "W"
# Ẉ [LATIN CAPITAL LETTER W WITH DOT BELOW]
"\u1E88" => "W"
# Ⓦ [CIRCLED LATIN CAPITAL LETTER W]
"\u24CC" => "W"
# Ⱳ [LATIN CAPITAL LETTER W WITH HOOK]
"\u2C72" => "W"
# Ｗ [FULLWIDTH LATIN CAPITAL LETTER W]
"\uFF37" => "W"
# ŵ [LATIN SMALL LETTER W WITH CIRCUMFLEX]
"\u0175" => "w"
# ƿ http://en.wikipedia.org/wiki/Wynn [LATIN LETTER WYNN]
"\u01BF" => "w"
# ʍ [LATIN SMALL LETTER TURNED W]
"\u028D" => "w"
# ẁ [LATIN SMALL LETTER W WITH GRAVE]
"\u1E81" => "w"
# ẃ [LATIN SMALL LETTER W WITH ACUTE]
"\u1E83" => "w"
# ẅ [LATIN SMALL LETTER W WITH DIAERESIS]
"\u1E85" => "w"
# ẇ [LATIN SMALL LETTER W WITH DOT ABOVE]
"\u1E87" => "w"
# ẉ [LATIN SMALL LETTER W WITH DOT BELOW]
"\u1E89" => "w"
# ẘ [LATIN SMALL LETTER W WITH RING ABOVE]
"\u1E98" => "w"
# ⓦ [CIRCLED LATIN SMALL LETTER W]
"\u24E6" => "w"
# ⱳ [LATIN SMALL LETTER W WITH HOOK]
"\u2C73" => "w"
# ｗ [FULLWIDTH LATIN SMALL LETTER W]
"\uFF57" => "w"
# ⒲ [PARENTHESIZED LATIN SMALL LETTER W]
"\u24B2" => "(w)"
# Ẋ [LATIN CAPITAL LETTER X WITH DOT ABOVE]
"\u1E8A" => "X"
# Ẍ [LATIN CAPITAL LETTER X WITH DIAERESIS]
"\u1E8C" => "X"
# Ⓧ [CIRCLED LATIN CAPITAL LETTER X]
"\u24CD" => "X"
# Ｘ [FULLWIDTH LATIN CAPITAL LETTER X]
"\uFF38" => "X"
# ᶍ [LATIN SMALL LETTER X WITH PALATAL HOOK]
"\u1D8D" => "x"
# ẋ [LATIN SMALL LETTER X WITH DOT ABOVE]
"\u1E8B" => "x"
# ẍ [LATIN SMALL LETTER X WITH DIAERESIS]
"\u1E8D" => "x"
# ₓ [LATIN SUBSCRIPT SMALL LETTER X]
"\u2093" => "x"
# ⓧ [CIRCLED LATIN SMALL LETTER X]
"\u24E7" => "x"
# ｘ [FULLWIDTH LATIN SMALL LETTER X]
"\uFF58" => "x"
# ⒳ [PARENTHESIZED LATIN SMALL LETTER X]
"\u24B3" => "(x)"
# Ý [LATIN CAPITAL LETTER Y WITH ACUTE]
"\u00DD" => "Y"
# Ŷ [LATIN CAPITAL LETTER Y WITH CIRCUMFLEX]
"\u0176" => "Y"
# Ÿ [LATIN CAPITAL LETTER Y WITH DIAERESIS]
"\u0178" => "Y"
# Ƴ [LATIN CAPITAL LETTER Y WITH HOOK]
"\u01B3" => "Y"
# Ȳ [LATIN CAPITAL LETTER Y WITH MACRON]
"\u0232" => "Y"
# Ɏ [LATIN CAPITAL LETTER Y WITH STROKE]
"\u024E" => "Y"
# ʏ [LATIN LETTER SMALL CAPITAL Y]
"\u028F" => "Y"
# Ẏ [LATIN CAPITAL LETTER Y WITH DOT ABOVE]
"\u1E8E" => "Y"
# Ỳ [LATIN CAPITAL LETTER Y WITH GRAVE]
"\u1EF2" => "Y"
# Ỵ [LATIN CAPITAL LETTER Y WITH DOT BELOW]
"\u1EF4" => "Y"
# Ỷ [LATIN CAPITAL LETTER Y WITH HOOK ABOVE]
"\u1EF6" => "Y"
# Ỹ [LATIN CAPITAL LETTER Y WITH TILDE]
"\u1EF8" => "Y"
# Ỿ [LATIN CAPITAL LETTER Y WITH LOOP]
"\u1EFE" => "Y"
# Ⓨ [CIRCLED LATIN CAPITAL LETTER Y]
"\u24CE" => "Y"
# Ｙ [FULLWIDTH LATIN CAPITAL LETTER Y]
"\uFF39" => "Y"
# ý [LATIN SMALL LETTER Y WITH ACUTE]
"\u00FD" => "y"
# ÿ [LATIN SMALL LETTER Y WITH DIAERESIS]
"\u00FF" => "y"
# ŷ [LATIN SMALL LETTER Y WITH CIRCUMFLEX]
"\u0177" => "y"
# ƴ [LATIN SMALL LETTER Y WITH HOOK]
"\u01B4" => "y"
# ȳ [LATIN SMALL LETTER Y WITH MACRON]
"\u0233" => "y"
# ɏ [LATIN SMALL LETTER Y WITH STROKE]
"\u024F" => "y"
# ʎ [LATIN SMALL LETTER TURNED Y]
"\u028E" => "y"
# ẏ [LATIN SMALL LETTER Y WITH DOT ABOVE]
"\u1E8F" => "y"
# ẙ [LATIN SMALL LETTER Y WITH RING ABOVE]
"\u1E99" => "y"
# ỳ [LATIN SMALL LETTER Y WITH GRAVE]
"\u1EF3" => "y"
# ỵ [LATIN SMALL LETTER Y WITH DOT BELOW]
"\u1EF5" => "y"
# ỷ [LATIN SMALL LETTER Y WITH HOOK ABOVE]
"\u1EF7" => "y"
# ỹ [LATIN SMALL LETTER Y WITH TILDE]
"\u1EF9" => "y"
# ỿ [LATIN SMALL LETTER Y WITH LOOP]
"\u1EFF" => "y"
# ⓨ [CIRCLED LATIN SMALL LETTER Y]
"\u24E8" => "y"
# ｙ [FULLWIDTH LATIN SMALL LETTER Y]
"\uFF59" => "y"
# ⒴ [PARENTHESIZED LATIN SMALL LETTER Y]
"\u24B4" => "(y)"
# Ź [LATIN CAPITAL LETTER Z WITH ACUTE]
"\u0179" => "Z"
# Ż [LATIN CAPITAL LETTER Z WITH DOT ABOVE]
"\u017B" => "Z"
# Ž [LATIN CAPITAL LETTER Z WITH CARON]
"\u017D" => "Z"
# Ƶ [LATIN CAPITAL LETTER Z WITH STROKE]
"\u01B5" => "Z"
# Ȝ http://en.wikipedia.org/wiki/Yogh [LATIN CAPITAL LETTER YOGH]
"\u021C" => "Z"
# Ȥ [LATIN CAPITAL LETTER Z WITH HOOK]
"\u0224" => "Z"
# ᴢ [LATIN LETTER SMALL CAPITAL Z]
"\u1D22" => "Z"
# Ẑ [LATIN CAPITAL LETTER Z WITH CIRCUMFLEX]
"\u1E90" => "Z"
# Ẓ [LATIN CAPITAL LETTER Z WITH DOT BELOW]
"\u1E92" => "Z"
# Ẕ [LATIN CAPITAL LETTER Z WITH LINE BELOW]
"\u1E94" => "Z"
# Ⓩ [CIRCLED LATIN CAPITAL LETTER Z]
"\u24CF" => "Z"
# Ⱬ [LATIN CAPITAL LETTER Z WITH DESCENDER]
"\u2C6B" => "Z"
# Ꝣ [LATIN CAPITAL LETTER VISIGOTHIC Z]
"\uA762" => "Z"
# Ｚ [FULLWIDTH LATIN CAPITAL LETTER Z]
"\uFF3A" => "Z"
# ź [LATIN SMALL LETTER Z WITH ACUTE]
"\u017A" => "z"
# ż [LATIN SMALL LETTER Z WITH DOT ABOVE]
"\u017C" => "z"
# ž [LATIN SMALL LETTER Z WITH CARON]
"\u017E" => "z"
# ƶ [LATIN SMALL LETTER Z WITH STROKE]
"\u01B6" => "z"
# ȝ http://en.wikipedia.org/wiki/Yogh [LATIN SMALL LETTER YOGH]
"\u021D" => "z"
# ȥ [LATIN SMALL LETTER Z WITH HOOK]
"\u0225" => "z"
# ɀ [LATIN SMALL LETTER Z WITH SWASH TAIL]
"\u0240" => "z"
# ʐ [LATIN SMALL LETTER Z WITH RETROFLEX HOOK]
"\u0290" => "z"
# ʑ [LATIN SMALL LETTER Z WITH CURL]
"\u0291" => "z"
# ᵶ [LATIN SMALL LETTER Z WITH MIDDLE TILDE]
"\u1D76" => "z"
# ᶎ [LATIN SMALL LETTER Z WITH PALATAL HOOK]
"\u1D8E" => "z"
# ẑ [LATIN SMALL LETTER Z WITH CIRCUMFLEX]
"\u1E91" => "z"
# ẓ [LATIN SMALL LETTER Z WITH DOT BELOW]
"\u1E93" => "z"
# ẕ [LATIN SMALL LETTER Z WITH LINE BELOW]
"\u1E95" => "z"
# ⓩ [CIRCLED LATIN SMALL LETTER Z]
"\u24E9" => "z"
# ⱬ [LATIN SMALL LETTER Z WITH DESCENDER]
"\u2C6C" => "z"
# ꝣ [LATIN SMALL LETTER VISIGOTHIC Z]
"\uA763" => "z"
# ｚ [FULLWIDTH LATIN SMALL LETTER Z]
"\uFF5A" => "z"
# ⒵ [PARENTHESIZED LATIN SMALL LETTER Z]
"\u24B5" => "(z)"
# ⁰ [SUPERSCRIPT ZERO]
"\u2070" => "0"
# ₀ [SUBSCRIPT ZERO]
"\u2080" => "0"
# ⓪ [CIRCLED DIGIT ZERO]
"\u24EA" => "0"
# ⓿ [NEGATIVE CIRCLED DIGIT ZERO]
"\u24FF" => "0"
# ０ [FULLWIDTH DIGIT ZERO]
"\uFF10" => "0"
# ¹ [SUPERSCRIPT ONE]
"\u00B9" => "1"
# ₁ [SUBSCRIPT ONE]
"\u2081" => "1"
# ① [CIRCLED DIGIT ONE]
"\u2460" => "1"
# ⓵ [DOUBLE CIRCLED DIGIT ONE]
"\u24F5" => "1"
# ❶ [DINGBAT NEGATIVE CIRCLED DIGIT ONE]
"\u2776" => "1"
# ➀ [DINGBAT CIRCLED SANS-SERIF DIGIT ONE]
"\u2780" => "1"
# ➊ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE]
"\u278A" => "1"
# １ [FULLWIDTH DIGIT ONE]
"\uFF11" => "1"
# ⒈ [DIGIT ONE FULL STOP]
"\u2488" => "1."
# ⑴ [PARENTHESIZED DIGIT ONE]
"\u2474" => "(1)"
# ² [SUPERSCRIPT TWO]
"\u00B2" => "2"
# ₂ [SUBSCRIPT TWO]
"\u2082" => "2"
# ② [CIRCLED DIGIT TWO]
"\u2461" => "2"
# ⓶ [DOUBLE CIRCLED DIGIT TWO]
"\u24F6" => "2"
# ❷ [DINGBAT NEGATIVE CIRCLED DIGIT TWO]
"\u2777" => "2"
# ➁ [DINGBAT CIRCLED SANS-SERIF DIGIT TWO]
"\u2781" => "2"
# ➋ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO]
"\u278B" => "2"
# ２ [FULLWIDTH DIGIT TWO]
"\uFF12" => "2"
# ⒉ [DIGIT TWO FULL STOP]
"\u2489" => "2."
# ⑵ [PARENTHESIZED DIGIT TWO]
"\u2475" => "(2)"
# ³ [SUPERSCRIPT THREE]
"\u00B3" => "3"
# ₃ [SUBSCRIPT THREE]
"\u2083" => "3"
# ③ [CIRCLED DIGIT THREE]
"\u2462" => "3"
# ⓷ [DOUBLE CIRCLED DIGIT THREE]
"\u24F7" => "3"
# ❸ [DINGBAT NEGATIVE CIRCLED DIGIT THREE]
"\u2778" => "3"
# ➂ [DINGBAT CIRCLED SANS-SERIF DIGIT THREE]
"\u2782" => "3"
# ➌ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE]
"\u278C" => "3"
# ３ [FULLWIDTH DIGIT THREE]
"\uFF13" => "3"
# ⒊ [DIGIT THREE FULL STOP]
"\u248A" => "3."
# ⑶ [PARENTHESIZED DIGIT THREE]
"\u2476" => "(3)"
# ⁴ [SUPERSCRIPT FOUR]
"\u2074" => "4"
# ₄ [SUBSCRIPT FOUR]
"\u2084" => "4"
# ④ [CIRCLED DIGIT FOUR]
"\u2463" => "4"
# ⓸ [DOUBLE CIRCLED DIGIT FOUR]
"\u24F8" => "4"
# ❹ [DINGBAT NEGATIVE CIRCLED DIGIT FOUR]
"\u2779" => "4"
# ➃ [DINGBAT CIRCLED SANS-SERIF DIGIT FOUR]
"\u2783" => "4"
# ➍ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR]
"\u278D" => "4"
# ４ [FULLWIDTH DIGIT FOUR]
"\uFF14" => "4"
# ⒋ [DIGIT FOUR FULL STOP]
"\u248B" => "4."
# ⑷ [PARENTHESIZED DIGIT FOUR]
"\u2477" => "(4)"
# ⁵ [SUPERSCRIPT FIVE]
"\u2075" => "5"
# ₅ [SUBSCRIPT FIVE]
"\u2085" => "5"
# ⑤ [CIRCLED DIGIT FIVE]
"\u2464" => "5"
# ⓹ [DOUBLE CIRCLED DIGIT FIVE]
"\u24F9" => "5"
# ❺ [DINGBAT NEGATIVE CIRCLED DIGIT FIVE]
"\u277A" => "5"
# ➄ [DINGBAT CIRCLED SANS-SERIF DIGIT FIVE]
"\u2784" => "5"
# ➎ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE]
"\u278E" => "5"
# ５ [FULLWIDTH DIGIT FIVE]
"\uFF15" => "5"
# ⒌ [DIGIT FIVE FULL STOP]
"\u248C" => "5."
# ⑸ [PARENTHESIZED DIGIT FIVE]
"\u2478" => "(5)"
# ⁶ [SUPERSCRIPT SIX]
"\u2076" => "6"
# ₆ [SUBSCRIPT SIX]
"\u2086" => "6"
# ⑥ [CIRCLED DIGIT SIX]
"\u2465" => "6"
# ⓺ [DOUBLE CIRCLED DIGIT SIX]
"\u24FA" => "6"
# ❻ [DINGBAT NEGATIVE CIRCLED DIGIT SIX]
"\u277B" => "6"
# ➅ [DINGBAT CIRCLED SANS-SERIF DIGIT SIX]
"\u2785" => "6"
# ➏ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX]
"\u278F" => "6"
# ６ [FULLWIDTH DIGIT SIX]
"\uFF16" => "6"
# ⒍ [DIGIT SIX FULL STOP]
"\u248D" => "6."
# ⑹ [PARENTHESIZED DIGIT SIX]
"\u2479" => "(6)"
# ⁷ [SUPERSCRIPT SEVEN]
"\u2077" => "7"
# ₇ [SUBSCRIPT SEVEN]
"\u2087" => "7"
# ⑦ [CIRCLED DIGIT SEVEN]
"\u2466" => "7"
# ⓻ [DOUBLE CIRCLED DIGIT SEVEN]
"\u24FB" => "7"
# ❼ [DINGBAT NEGATIVE CIRCLED DIGIT SEVEN]
"\u277C" => "7"
# ➆ [DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN]
"\u2786" => "7"
# ➐ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN]
"\u2790" => "7"
# ７ [FULLWIDTH DIGIT SEVEN]
"\uFF17" => "7"
# ⒎ [DIGIT SEVEN FULL STOP]
"\u248E" => "7."
# ⑺ [PARENTHESIZED DIGIT SEVEN]
"\u247A" => "(7)"
# ⁸ [SUPERSCRIPT EIGHT]
"\u2078" => "8"
# ₈ [SUBSCRIPT EIGHT]
"\u2088" => "8"
# ⑧ [CIRCLED DIGIT EIGHT]
"\u2467" => "8"
# ⓼ [DOUBLE CIRCLED DIGIT EIGHT]
"\u24FC" => "8"
# ❽ [DINGBAT NEGATIVE CIRCLED DIGIT EIGHT]
"\u277D" => "8"
# ➇ [DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT]
"\u2787" => "8"
# ➑ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT]
"\u2791" => "8"
# ８ [FULLWIDTH DIGIT EIGHT]
"\uFF18" => "8"
# ⒏ [DIGIT EIGHT FULL STOP]
"\u248F" => "8."
# ⑻ [PARENTHESIZED DIGIT EIGHT]
"\u247B" => "(8)"
# ⁹ [SUPERSCRIPT NINE]
"\u2079" => "9"
# ₉ [SUBSCRIPT NINE]
"\u2089" => "9"
# ⑨ [CIRCLED DIGIT NINE]
"\u2468" => "9"
# ⓽ [DOUBLE CIRCLED DIGIT NINE]
"\u24FD" => "9"
# ❾ [DINGBAT NEGATIVE CIRCLED DIGIT NINE]
"\u277E" => "9"
# ➈ [DINGBAT CIRCLED SANS-SERIF DIGIT NINE]
"\u2788" => "9"
# ➒ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE]
"\u2792" => "9"
# ９ [FULLWIDTH DIGIT NINE]
"\uFF19" => "9"
# ⒐ [DIGIT NINE FULL STOP]
"\u2490" => "9."
# ⑼ [PARENTHESIZED DIGIT NINE]
"\u247C" => "(9)"
# ⑩ [CIRCLED NUMBER TEN]
"\u2469" => "10"
# ⓾ [DOUBLE CIRCLED NUMBER TEN]
"\u24FE" => "10"
# ❿ [DINGBAT NEGATIVE CIRCLED NUMBER TEN]
"\u277F" => "10"
# ➉ [DINGBAT CIRCLED SANS-SERIF NUMBER TEN]
"\u2789" => "10"
# ➓ [DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN]
"\u2793" => "10"
# ⒑ [NUMBER TEN FULL STOP]
"\u2491" => "10."
# ⑽ [PARENTHESIZED NUMBER TEN]
"\u247D" => "(10)"
# ⑪ [CIRCLED NUMBER ELEVEN]
"\u246A" => "11"
# ⓫ [NEGATIVE CIRCLED NUMBER ELEVEN]
"\u24EB" => "11"
# ⒒ [NUMBER ELEVEN FULL STOP]
"\u2492" => "11."
# ⑾ [PARENTHESIZED NUMBER ELEVEN]
"\u247E" => "(11)"
# ⑫ [CIRCLED NUMBER TWELVE]
"\u246B" => "12"
# ⓬ [NEGATIVE CIRCLED NUMBER TWELVE]
"\u24EC" => "12"
# ⒓ [NUMBER TWELVE FULL STOP]
"\u2493" => "12."
# ⑿ [PARENTHESIZED NUMBER TWELVE]
"\u247F" => "(12)"
# ⑬ [CIRCLED NUMBER THIRTEEN]
"\u246C" => "13"
# ⓭ [NEGATIVE CIRCLED NUMBER THIRTEEN]
"\u24ED" => "13"
# ⒔ [NUMBER THIRTEEN FULL STOP]
"\u2494" => "13."
# ⒀ [PARENTHESIZED NUMBER THIRTEEN]
"\u2480" => "(13)"
# ⑭ [CIRCLED NUMBER FOURTEEN]
"\u246D" => "14"
# ⓮ [NEGATIVE CIRCLED NUMBER FOURTEEN]
"\u24EE" => "14"
# ⒕ [NUMBER FOURTEEN FULL STOP]
"\u2495" => "14."
# ⒁ [PARENTHESIZED NUMBER FOURTEEN]
"\u2481" => "(14)"
# ⑮ [CIRCLED NUMBER FIFTEEN]
"\u246E" => "15"
# ⓯ [NEGATIVE CIRCLED NUMBER FIFTEEN]
"\u24EF" => "15"
# ⒖ [NUMBER FIFTEEN FULL STOP]
"\u2496" => "15."
# ⒂ [PARENTHESIZED NUMBER FIFTEEN]
"\u2482" => "(15)"
# ⑯ [CIRCLED NUMBER SIXTEEN]
"\u246F" => "16"
# ⓰ [NEGATIVE CIRCLED NUMBER SIXTEEN]
"\u24F0" => "16"
# ⒗ [NUMBER SIXTEEN FULL STOP]
"\u2497" => "16."
# ⒃ [PARENTHESIZED NUMBER SIXTEEN]
"\u2483" => "(16)"
# ⑰ [CIRCLED NUMBER SEVENTEEN]
"\u2470" => "17"
# ⓱ [NEGATIVE CIRCLED NUMBER SEVENTEEN]
"\u24F1" => "17"
# ⒘ [NUMBER SEVENTEEN FULL STOP]
"\u2498" => "17."
# ⒄ [PARENTHESIZED NUMBER SEVENTEEN]
"\u2484" => "(17)"
# ⑱ [CIRCLED NUMBER EIGHTEEN]
"\u2471" => "18"
# ⓲ [NEGATIVE CIRCLED NUMBER EIGHTEEN]
"\u24F2" => "18"
# ⒙ [NUMBER EIGHTEEN FULL STOP]
"\u2499" => "18."
# ⒅ [PARENTHESIZED NUMBER EIGHTEEN]
"\u2485" => "(18)"
# ⑲ [CIRCLED NUMBER NINETEEN]
"\u2472" => "19"
# ⓳ [NEGATIVE CIRCLED NUMBER NINETEEN]
"\u24F3" => "19"
# ⒚ [NUMBER NINETEEN FULL STOP]
"\u249A" => "19."
# ⒆ [PARENTHESIZED NUMBER NINETEEN]
"\u2486" => "(19)"
# ⑳ [CIRCLED NUMBER TWENTY]
"\u2473" => "20"
# ⓴ [NEGATIVE CIRCLED NUMBER TWENTY]
"\u24F4" => "20"
# ⒛ [NUMBER TWENTY FULL STOP]
"\u249B" => "20."
# ⒇ [PARENTHESIZED NUMBER TWENTY]
"\u2487" => "(20)"
# « [LEFT-POINTING DOUBLE ANGLE QUOTATION MARK]
"\u00AB" => "\""
# » [RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK]
"\u00BB" => "\""
# “ [LEFT DOUBLE QUOTATION MARK]
"\u201C" => "\""
# ” [RIGHT DOUBLE QUOTATION MARK]
"\u201D" => "\""
# „ [DOUBLE LOW-9 QUOTATION MARK]
"\u201E" => "\""
# ″ [DOUBLE PRIME]
"\u2033" => "\""
# ‶ [REVERSED DOUBLE PRIME]
"\u2036" => "\""
# ❝ [HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT]
"\u275D" => "\""
# ❞ [HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT]
"\u275E" => "\""
# ❮ [HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT]
"\u276E" => "\""
# ❯ [HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT]
"\u276F" => "\""
# ＂ [FULLWIDTH QUOTATION MARK]
"\uFF02" => "\""
# ‘ [LEFT SINGLE QUOTATION MARK]
"\u2018" => "\'"
# ’ [RIGHT SINGLE QUOTATION MARK]
"\u2019" => "\'"
# ‚ [SINGLE LOW-9 QUOTATION MARK]
"\u201A" => "\'"
# ‛ [SINGLE HIGH-REVERSED-9 QUOTATION MARK]
"\u201B" => "\'"
# ′ [PRIME]
"\u2032" => "\'"
# ‵ [REVERSED PRIME]
"\u2035" => "\'"
# ‹ [SINGLE LEFT-POINTING ANGLE QUOTATION MARK]
"\u2039" => "\'"
# › [SINGLE RIGHT-POINTING ANGLE QUOTATION MARK]
"\u203A" => "\'"
# ❛ [HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT]
"\u275B" => "\'"
# ❜ [HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT]
"\u275C" => "\'"
# ＇ [FULLWIDTH APOSTROPHE]
"\uFF07" => "\'"
# ‐ [HYPHEN]
"\u2010" => "-"
# ‑ [NON-BREAKING HYPHEN]
"\u2011" => "-"
# ‒ [FIGURE DASH]
"\u2012" => "-"
# – [EN DASH]
"\u2013" => "-"
# — [EM DASH]
"\u2014" => "-"
# ⁻ [SUPERSCRIPT MINUS]
"\u207B" => "-"
# ₋ [SUBSCRIPT MINUS]
"\u208B" => "-"
# － [FULLWIDTH HYPHEN-MINUS]
"\uFF0D" => "-"
# ⁅ [LEFT SQUARE BRACKET WITH QUILL]
"\u2045" => "["
# ❲ [LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT]
"\u2772" => "["
# ［ [FULLWIDTH LEFT SQUARE BRACKET]
"\uFF3B" => "["
# ⁆ [RIGHT SQUARE BRACKET WITH QUILL]
"\u2046" => "]"
# ❳ [LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT]
"\u2773" => "]"
# ］ [FULLWIDTH RIGHT SQUARE BRACKET]
"\uFF3D" => "]"
# ⁽ [SUPERSCRIPT LEFT PARENTHESIS]
"\u207D" => "("
# ₍ [SUBSCRIPT LEFT PARENTHESIS]
"\u208D" => "("
# ❨ [MEDIUM LEFT PARENTHESIS ORNAMENT]
"\u2768" => "("
# ❪ [MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT]
"\u276A" => "("
# （ [FULLWIDTH LEFT PARENTHESIS]
"\uFF08" => "("
# ⸨ [LEFT DOUBLE PARENTHESIS]
"\u2E28" => "(("
# ⁾ [SUPERSCRIPT RIGHT PARENTHESIS]
"\u207E" => ")"
# ₎ [SUBSCRIPT RIGHT PARENTHESIS]
"\u208E" => ")"
# ❩ [MEDIUM RIGHT PARENTHESIS ORNAMENT]
"\u2769" => ")"
# ❫ [MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT]
"\u276B" => ")"
# ） [FULLWIDTH RIGHT PARENTHESIS]
"\uFF09" => ")"
# ⸩ [RIGHT DOUBLE PARENTHESIS]
"\u2E29" => "))"
# ❬ [MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT]
"\u276C" => "<"
# ❰ [HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT]
"\u2770" => "<"
# ＜ [FULLWIDTH LESS-THAN SIGN]
"\uFF1C" => "<"
# ❭ [MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT]
"\u276D" => ">"
# ❱ [HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT]
"\u2771" => ">"
# ＞ [FULLWIDTH GREATER-THAN SIGN]
"\uFF1E" => ">"
# ❴ [MEDIUM LEFT CURLY BRACKET ORNAMENT]
"\u2774" => "{"
# ｛ [FULLWIDTH LEFT CURLY BRACKET]
"\uFF5B" => "{"
# ❵ [MEDIUM RIGHT CURLY BRACKET ORNAMENT]
"\u2775" => "}"
# ｝ [FULLWIDTH RIGHT CURLY BRACKET]
"\uFF5D" => "}"
# ⁺ [SUPERSCRIPT PLUS SIGN]
"\u207A" => "+"
# ₊ [SUBSCRIPT PLUS SIGN]
"\u208A" => "+"
# ＋ [FULLWIDTH PLUS SIGN]
"\uFF0B" => "+"
# ⁼ [SUPERSCRIPT EQUALS SIGN]
"\u207C" => "="
# ₌ [SUBSCRIPT EQUALS SIGN]
"\u208C" => "="
# ＝ [FULLWIDTH EQUALS SIGN]
"\uFF1D" => "="
# ！ [FULLWIDTH EXCLAMATION MARK]
"\uFF01" => "!"
# ‼ [DOUBLE EXCLAMATION MARK]
"\u203C" => "!!"
# ⁉ [EXCLAMATION QUESTION MARK]
"\u2049" => "!?"
# ＃ [FULLWIDTH NUMBER SIGN]
"\uFF03" => "#"
# ＄ [FULLWIDTH DOLLAR SIGN]
"\uFF04" => "$"
# ⁒ [COMMERCIAL MINUS SIGN]
"\u2052" => "%"
# ％ [FULLWIDTH PERCENT SIGN]
"\uFF05" => "%"
# ＆ [FULLWIDTH AMPERSAND]
"\uFF06" => "&"
# ⁎ [LOW ASTERISK]
"\u204E" => "*"
# ＊ [FULLWIDTH ASTERISK]
"\uFF0A" => "*"
# ， [FULLWIDTH COMMA]
"\uFF0C" => ","
# ． [FULLWIDTH FULL STOP]
"\uFF0E" => "."
# ⁄ [FRACTION SLASH]
"\u2044" => "/"
# ／ [FULLWIDTH SOLIDUS]
"\uFF0F" => "/"
# ： [FULLWIDTH COLON]
"\uFF1A" => ":"
# ⁏ [REVERSED SEMICOLON]
"\u204F" => ";"
# ； [FULLWIDTH SEMICOLON]
"\uFF1B" => ";"
# ？ [FULLWIDTH QUESTION MARK]
"\uFF1F" => "?"
# ⁇ [DOUBLE QUESTION MARK]
"\u2047" => "??"
# ⁈ [QUESTION EXCLAMATION MARK]
"\u2048" => "?!"
# ＠ [FULLWIDTH COMMERCIAL AT]
"\uFF20" => "@"
# ＼ [FULLWIDTH REVERSE SOLIDUS]
"\uFF3C" => "\\"
# ‸ [CARET]
"\u2038" => "^"
# ＾ [FULLWIDTH CIRCUMFLEX ACCENT]
"\uFF3E" => "^"
# ＿ [FULLWIDTH LOW LINE]
"\uFF3F" => "_"
# ⁓ [SWUNG DASH]
"\u2053" => "~"
# ～ [FULLWIDTH TILDE]
"\uFF5E" => "~"
################################################################
# Below is the Perl script used to generate the above mappings #
# from ASCIIFoldingFilter.java: #
################################################################
#
# #!/usr/bin/perl
#
# use warnings;
# use strict;
#
# my @source_chars = ();
# my @source_char_descriptions = ();
# my $target = '';
#
# while (<>) {
# if (/case\s+'(\\u[A-F0-9]+)':\s*\/\/\s*(.*)/i) {
# push @source_chars, $1;
# push @source_char_descriptions, $2;
# next;
# }
# if (/output\[[^\]]+\]\s*=\s*'(\\'|\\\\|.)'/) {
# $target .= $1;
# next;
# }
# if (/break;/) {
# $target = "\\\"" if ($target eq '"');
# for my $source_char_num (0..$#source_chars) {
# print "# $source_char_descriptions[$source_char_num]\n";
# print "\"$source_chars[$source_char_num]\" => \"$target\"\n\n";
# }
# @source_chars = ();
# @source_char_descriptions = ();
# $target = '';
# }
# }

21
conf/solr/4/extras/protwords.txt Normal file
View File

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

1823
conf/solr/4/extras/solrconfig.xml Normal file
View File

@ -0,0 +1,1823 @@
<?xml version="1.0" encoding="UTF-8" ?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
<!--
For more details about configurations options that may appear in
this file, see http://wiki.apache.org/solr/SolrConfigXml.
-->
<config>
<!-- In all configuration below, a prefix of "solr." for class names
is an alias that causes solr to search appropriate packages,
including org.apache.solr.(search|update|request|core|analysis)
You may also specify a fully qualified Java classname if you
have your own custom plugins.
-->
<!-- Controls what version of Lucene various components of Solr
adhere to. Generally, you want to use the latest version to
get all bug fixes and improvements. It is highly recommended
that you fully re-index after changing this setting as it can
affect both how text is indexed and queried.
-->
<luceneMatchVersion>4.4</luceneMatchVersion>
<!-- <lib/> directives can be used to instruct Solr to load an Jars
identified and use them to resolve any "plugins" specified in
your solrconfig.xml or schema.xml (ie: Analyzers, Request
Handlers, etc...).
All directories and paths are resolved relative to the
instanceDir.
Please note that <lib/> directives are processed in the order
that they appear in your solrconfig.xml file, and are "stacked"
on top of each other when building a ClassLoader - so if you have
plugin jars with dependencies on other jars, the "lower level"
dependency jars should be loaded first.
If a "./lib" directory exists in your instanceDir, all files
found in it are included as if you had used the following
syntax...
<lib dir="./lib" />
-->
<!-- A 'dir' option by itself adds any files found in the directory
to the classpath, this is useful for including all jars in a
directory.
When a 'regex' is specified in addition to a 'dir', only the
files in that directory which completely match the regex
(anchored on both ends) will be included.
If a 'dir' option (with or without a regex) is used and nothing
is found that matches, a warning will be logged.
The examples below can be used to load some solr-contribs along
with their external dependencies.
-->
<lib dir="../../../contrib/extraction/lib" regex=".*\.jar" />
<lib dir="../../../dist/" regex="solr-cell-\d.*\.jar" />
<lib dir="../../../contrib/clustering/lib/" regex=".*\.jar" />
<lib dir="../../../dist/" regex="solr-clustering-\d.*\.jar" />
<lib dir="../../../contrib/langid/lib/" regex=".*\.jar" />
<lib dir="../../../dist/" regex="solr-langid-\d.*\.jar" />
<lib dir="../../../contrib/velocity/lib" regex=".*\.jar" />
<lib dir="../../../dist/" regex="solr-velocity-\d.*\.jar" />
<!-- an exact 'path' can be used instead of a 'dir' to specify a
specific jar file. This will cause a serious error to be logged
if it can't be loaded.
-->
<!--
<lib path="../a-jar-that-does-not-exist.jar" />
-->
<!-- Data Directory
Used to specify an alternate directory to hold all index data
other than the default ./data under the Solr home. If
replication is in use, this should match the replication
configuration.
-->
<dataDir>${solr.data.dir:}</dataDir>
<!-- The DirectoryFactory to use for indexes.
solr.StandardDirectoryFactory is filesystem
based and tries to pick the best implementation for the current
JVM and platform. solr.NRTCachingDirectoryFactory, the default,
wraps solr.StandardDirectoryFactory and caches small files in memory
for better NRT performance.
One can force a particular implementation via solr.MMapDirectoryFactory,
solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
solr.RAMDirectoryFactory is memory based, not
persistent, and doesn't work with replication.
-->
<directoryFactory name="DirectoryFactory"
class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
<!-- The CodecFactory for defining the format of the inverted index.
The default implementation is SchemaCodecFactory, which is the official Lucene
index format, but hooks into the schema to provide per-field customization of
the postings lists and per-document values in the fieldType element
(postingsFormat/docValuesFormat). Note that most of the alternative implementations
are experimental, so if you choose to customize the index format, its a good
idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
before upgrading to a newer version to avoid unnecessary reindexing.
-->
<codecFactory class="solr.SchemaCodecFactory"/>
<!-- To enable dynamic schema REST APIs, use the following for <schemaFactory>:
<schemaFactory class="ManagedIndexSchemaFactory">
<bool name="mutable">true</bool>
<str name="managedSchemaResourceName">managed-schema</str>
</schemaFactory>
When ManagedIndexSchemaFactory is specified, Solr will load the schema from
he resource named in 'managedSchemaResourceName', rather than from schema.xml.
Note that the managed schema resource CANNOT be named schema.xml. If the managed
schema does not exist, Solr will create it after reading schema.xml, then rename
'schema.xml' to 'schema.xml.bak'.
Do NOT hand edit the managed schema - external modifications will be ignored and
overwritten as a result of schema modification REST API calls.
When ManagedIndexSchemaFactory is specified with mutable = true, schema
modification REST API calls will be allowed; otherwise, error responses will be
sent back for these requests.
-->
<schemaFactory class="ClassicIndexSchemaFactory"/>
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Index Config - These settings control low-level behavior of indexing
Most example settings here show the default value, but are commented
out, to more easily see where customizations have been made.
Note: This replaces <indexDefaults> and <mainIndex> from older versions
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
<indexConfig>
<!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
LimitTokenCountFilterFactory in your fieldType definition. E.g.
<filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
-->
<!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
<!-- <writeLockTimeout>1000</writeLockTimeout> -->
<!-- The maximum number of simultaneous threads that may be
indexing documents at once in IndexWriter; if more than this
many threads arrive they will wait for others to finish.
Default in Solr/Lucene is 8. -->
<!-- <maxIndexingThreads>8</maxIndexingThreads> -->
<!-- Expert: Enabling compound file will use less files for the index,
using fewer file descriptors on the expense of performance decrease.
Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
<!-- <useCompoundFile>false</useCompoundFile> -->
<!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
indexing for buffering added documents and deletions before they are
flushed to the Directory.
maxBufferedDocs sets a limit on the number of documents buffered
before flushing.
If both ramBufferSizeMB and maxBufferedDocs is set, then
Lucene will flush based on whichever limit is hit first.
The default is 100 MB. -->
<!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
<!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
<!-- Expert: Merge Policy
The Merge Policy in Lucene controls how merging of segments is done.
The default since Solr/Lucene 3.3 is TieredMergePolicy.
The default since Lucene 2.3 was the LogByteSizeMergePolicy,
Even older versions of Lucene used LogDocMergePolicy.
-->
<!--
<mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
<int name="maxMergeAtOnce">10</int>
<int name="segmentsPerTier">10</int>
</mergePolicy>
-->
<!-- Merge Factor
The merge factor controls how many segments will get merged at a time.
For TieredMergePolicy, mergeFactor is a convenience parameter which
will set both MaxMergeAtOnce and SegmentsPerTier at once.
For LogByteSizeMergePolicy, mergeFactor decides how many new segments
will be allowed before they are merged into one.
Default is 10 for both merge policies.
-->
<!--
<mergeFactor>10</mergeFactor>
-->
<!-- Expert: Merge Scheduler
The Merge Scheduler in Lucene controls how merges are
performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
can perform merges in the background using separate threads.
The SerialMergeScheduler (Lucene 2.2 default) does not.
-->
<!--
<mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
-->
<!-- LockFactory
This option specifies which Lucene LockFactory implementation
to use.
single = SingleInstanceLockFactory - suggested for a
read-only index or when there is no possibility of
another process trying to modify the index.
native = NativeFSLockFactory - uses OS native file locking.
Do not use when multiple solr webapps in the same
JVM are attempting to share a single index.
simple = SimpleFSLockFactory - uses a plain file for locking
Defaults: 'native' is default for Solr3.6 and later, otherwise
'simple' is the default
More details on the nuances of each LockFactory...
http://wiki.apache.org/lucene-java/AvailableLockFactories
-->
<lockType>${solr.lock.type:native}</lockType>
<!-- Unlock On Startup
If true, unlock any held write or commit locks on startup.
This defeats the locking mechanism that allows multiple
processes to safely access a lucene index, and should be used
with care. Default is "false".
This is not needed if lock type is 'single'
-->
<!--
<unlockOnStartup>false</unlockOnStartup>
-->
<!-- Expert: Controls how often Lucene loads terms into memory
Default is 128 and is likely good for most everyone.
-->
<!-- <termIndexInterval>128</termIndexInterval> -->
<!-- If true, IndexReaders will be reopened (often more efficient)
instead of closed and then opened. Default: true
-->
<!--
<reopenReaders>true</reopenReaders>
-->
<!-- Commit Deletion Policy
Custom deletion policies can be specified here. The class must
implement org.apache.lucene.index.IndexDeletionPolicy.
The default Solr IndexDeletionPolicy implementation supports
deleting index commit points on number of commits, age of
commit point and optimized status.
The latest commit point should always be preserved regardless
of the criteria.
-->
<!--
<deletionPolicy class="solr.SolrDeletionPolicy">
-->
<!-- The number of commit points to be kept -->
<!-- <str name="maxCommitsToKeep">1</str> -->
<!-- The number of optimized commit points to be kept -->
<!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
<!--
Delete all commit points once they have reached the given age.
Supports DateMathParser syntax e.g.
-->
<!--
<str name="maxCommitAge">30MINUTES</str>
<str name="maxCommitAge">1DAY</str>
-->
<!--
</deletionPolicy>
-->
<!-- Lucene Infostream
To aid in advanced debugging, Lucene provides an "InfoStream"
of detailed information when indexing.
Setting the value to true will instruct the underlying Lucene
IndexWriter to write its info stream to solr's log. By default,
this is enabled here, and controlled through log4j.properties.
-->
<infoStream>true</infoStream>
</indexConfig>
<!-- JMX
This example enables JMX if and only if an existing MBeanServer
is found, use this if you want to configure JMX through JVM
parameters. Remove this to disable exposing Solr configuration
and statistics to JMX.
For more details see http://wiki.apache.org/solr/SolrJmx
-->
<jmx />
<!-- If you want to connect to a particular server, specify the
agentId
-->
<!-- <jmx agentId="myAgent" /> -->
<!-- If you want to start a new MBeanServer, specify the serviceUrl -->
<!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
-->
<!-- The default high-performance update handler -->
<updateHandler class="solr.DirectUpdateHandler2">
<!-- Enables a transaction log, used for real-time get, durability, and
and solr cloud replica recovery. The log can grow as big as
uncommitted changes to the index, so use of a hard autoCommit
is recommended (see below).
"dir" - the target directory for transaction logs, defaults to the
solr data directory. -->
<updateLog>
<str name="dir">${solr.ulog.dir:}</str>
</updateLog>
<!-- AutoCommit
Perform a hard commit automatically under certain conditions.
Instead of enabling autoCommit, consider using "commitWithin"
when adding documents.
http://wiki.apache.org/solr/UpdateXmlMessages
maxDocs - Maximum number of documents to add since the last
commit before automatically triggering a new commit.
maxTime - Maximum amount of time in ms that is allowed to pass
since a document was added before automatically
triggering a new commit.
openSearcher - if false, the commit causes recent index changes
to be flushed to stable storage, but does not cause a new
searcher to be opened to make those changes visible.
If the updateLog is enabled, then it's highly recommended to
have some sort of hard autoCommit to limit the log size.
-->
<autoCommit>
<maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
<openSearcher>false</openSearcher>
</autoCommit>
<!-- softAutoCommit is like autoCommit except it causes a
'soft' commit which only ensures that changes are visible
but does not ensure that data is synced to disk. This is
faster and more near-realtime friendly than a hard commit.
-->
<autoSoftCommit>
<maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
</autoSoftCommit>
<!-- Update Related Event Listeners
Various IndexWriter related events can trigger Listeners to
take actions.
postCommit - fired after every commit or optimize command
postOptimize - fired after every optimize command
-->
<!-- The RunExecutableListener executes an external command from a
hook such as postCommit or postOptimize.
exe - the name of the executable to run
dir - dir to use as the current working directory. (default=".")
wait - the calling thread waits until the executable returns.
(default="true")
args - the arguments to pass to the program. (default is none)
env - environment variables to set. (default is none)
-->
<!-- This example shows how RunExecutableListener could be used
with the script based replication...
http://wiki.apache.org/solr/CollectionDistribution
-->
<!--
<listener event="postCommit" class="solr.RunExecutableListener">
<str name="exe">solr/bin/snapshooter</str>
<str name="dir">.</str>
<bool name="wait">true</bool>
<arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
<arr name="env"> <str>MYVAR=val1</str> </arr>
</listener>
-->
</updateHandler>
<!-- IndexReaderFactory
Use the following format to specify a custom IndexReaderFactory,
which allows for alternate IndexReader implementations.
** Experimental Feature **
Please note - Using a custom IndexReaderFactory may prevent
certain other features from working. The API to
IndexReaderFactory may change without warning or may even be
removed from future releases if the problems cannot be
resolved.
** Features that may not work with custom IndexReaderFactory **
The ReplicationHandler assumes a disk-resident index. Using a
custom IndexReader implementation may cause incompatibility
with ReplicationHandler and may cause replication to not work
correctly. See SOLR-1366 for details.
-->
<!--
<indexReaderFactory name="IndexReaderFactory" class="package.class">
<str name="someArg">Some Value</str>
</indexReaderFactory >
-->
<!-- By explicitly declaring the Factory, the termIndexDivisor can
be specified.
-->
<!--
<indexReaderFactory name="IndexReaderFactory"
class="solr.StandardIndexReaderFactory">
<int name="setTermIndexDivisor">12</int>
</indexReaderFactory >
-->
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Query section - these settings control query time things like caches
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
<query>
<!-- Max Boolean Clauses
Maximum number of clauses in each BooleanQuery, an exception
is thrown if exceeded.
** WARNING **
This option actually modifies a global Lucene property that
will affect all SolrCores. If multiple solrconfig.xml files
disagree on this property, the value at any given moment will
be based on the last SolrCore to be initialized.
-->
<maxBooleanClauses>1024</maxBooleanClauses>
<!-- Solr Internal Query Caches
There are two implementations of cache available for Solr,
LRUCache, based on a synchronized LinkedHashMap, and
FastLRUCache, based on a ConcurrentHashMap.
FastLRUCache has faster gets and slower puts in single
threaded operation and thus is generally faster than LRUCache
when the hit ratio of the cache is high (> 75%), and may be
faster under other scenarios on multi-cpu systems.
-->
<!-- Filter Cache
Cache used by SolrIndexSearcher for filters (DocSets),
unordered sets of *all* documents that match a query. When a
new searcher is opened, its caches may be prepopulated or
"autowarmed" using data from caches in the old searcher.
autowarmCount is the number of items to prepopulate. For
LRUCache, the autowarmed items will be the most recently
accessed items.
Parameters:
class - the SolrCache implementation LRUCache or
(LRUCache or FastLRUCache)
size - the maximum number of entries in the cache
initialSize - the initial capacity (number of entries) of
the cache. (see java.util.HashMap)
autowarmCount - the number of entries to prepopulate from
and old cache.
-->
<filterCache class="solr.FastLRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- Query Result Cache
Caches results of searches - ordered lists of document ids
(DocList) based on a query, a sort, and the range of documents requested.
-->
<queryResultCache class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- Document Cache
Caches Lucene Document objects (the stored fields for each
document). Since Lucene internal document ids are transient,
this cache will not be autowarmed.
-->
<documentCache class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- Field Value Cache
Cache used to hold field values that are quickly accessible
by document id. The fieldValueCache is created by default
even if not configured here.
-->
<!--
<fieldValueCache class="solr.FastLRUCache"
size="512"
autowarmCount="128"
showItems="32" />
-->
<!-- Custom Cache
Example of a generic cache. These caches may be accessed by
name through SolrIndexSearcher.getCache(),cacheLookup(), and
cacheInsert(). The purpose is to enable easy caching of
user/application level data. The regenerator argument should
be specified as an implementation of solr.CacheRegenerator
if autowarming is desired.
-->
<!--
<cache name="myUserCache"
class="solr.LRUCache"
size="4096"
initialSize="1024"
autowarmCount="1024"
regenerator="com.mycompany.MyRegenerator"
/>
-->
<!-- Lazy Field Loading
If true, stored fields that are not requested will be loaded
lazily. This can result in a significant speed improvement
if the usual case is to not load all stored fields,
especially if the skipped fields are large compressed text
fields.
-->
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<!-- Use Filter For Sorted Query
A possible optimization that attempts to use a filter to
satisfy a search. If the requested sort does not include
score, then the filterCache will be checked for a filter
matching the query. If found, the filter will be used as the
source of document ids, and then the sort will be applied to
that.
For most situations, this will not be useful unless you
frequently get the same search repeatedly with different sort
options, and none of them ever use "score"
-->
<!--
<useFilterForSortedQuery>true</useFilterForSortedQuery>
-->
<!-- Result Window Size
An optimization for use with the queryResultCache. When a search
is requested, a superset of the requested number of document ids
are collected. For example, if a search for a particular query
requests matching documents 10 through 19, and queryWindowSize is 50,
then documents 0 through 49 will be collected and cached. Any further
requests in that range can be satisfied via the cache.
-->
<queryResultWindowSize>20</queryResultWindowSize>
<!-- Maximum number of documents to cache for any entry in the
queryResultCache.
-->
<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
<!-- Query Related Event Listeners
Various IndexSearcher related events can trigger Listeners to
take actions.
newSearcher - fired whenever a new searcher is being prepared
and there is a current searcher handling requests (aka
registered). It can be used to prime certain caches to
prevent long request times for certain requests.
firstSearcher - fired whenever a new searcher is being
prepared but there is no current registered searcher to handle
requests or to gain autowarming data from.
-->
<!-- QuerySenderListener takes an array of NamedList and executes a
local query request for each NamedList in sequence.
-->
<listener event="newSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<!--
<lst><str name="q">solr</str><str name="sort">price asc</str></lst>
<lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
-->
</arr>
</listener>
<listener event="firstSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<lst>
<str name="q">static firstSearcher warming in solrconfig.xml</str>
</lst>
</arr>
</listener>
<!-- Use Cold Searcher
If a search request comes in and there is no current
registered searcher, then immediately register the still
warming searcher and use it. If "false" then all requests
will block until the first searcher is done warming.
-->
<useColdSearcher>false</useColdSearcher>
<!-- Max Warming Searchers
Maximum number of searchers that may be warming in the
background concurrently. An error is returned if this limit
is exceeded.
Recommend values of 1-2 for read-only slaves, higher for
masters w/o cache warming.
-->
<maxWarmingSearchers>2</maxWarmingSearchers>
</query>
<!-- Request Dispatcher
This section contains instructions for how the SolrDispatchFilter
should behave when processing requests for this SolrCore.
handleSelect is a legacy option that affects the behavior of requests
such as /select?qt=XXX
handleSelect="true" will cause the SolrDispatchFilter to process
the request and dispatch the query to a handler specified by the
"qt" param, assuming "/select" isn't already registered.
handleSelect="false" will cause the SolrDispatchFilter to
ignore "/select" requests, resulting in a 404 unless a handler
is explicitly registered with the name "/select"
handleSelect="true" is not recommended for new users, but is the default
for backwards compatibility
-->
<requestDispatcher handleSelect="false" >
<!-- Request Parsing
These settings indicate how Solr Requests may be parsed, and
what restrictions may be placed on the ContentStreams from
those requests
enableRemoteStreaming - enables use of the stream.file
and stream.url parameters for specifying remote streams.
multipartUploadLimitInKB - specifies the max size (in KiB) of
Multipart File Uploads that Solr will allow in a Request.
formdataUploadLimitInKB - specifies the max size (in KiB) of
form data (application/x-www-form-urlencoded) sent via
POST. You can use POST to pass request parameters not
fitting into the URL.
addHttpRequestToContext - if set to true, it will instruct
the requestParsers to include the original HttpServletRequest
object in the context map of the SolrQueryRequest under the
key "httpRequest". It will not be used by any of the existing
Solr components, but may be useful when developing custom
plugins.
*** WARNING ***
The settings below authorize Solr to fetch remote files, You
should make sure your system has some authentication before
using enableRemoteStreaming="true"
-->
<requestParsers enableRemoteStreaming="true"
multipartUploadLimitInKB="2048000"
formdataUploadLimitInKB="2048"
addHttpRequestToContext="false"/>
<!-- HTTP Caching
Set HTTP caching related parameters (for proxy caches and clients).
The options below instruct Solr not to output any HTTP Caching
related headers
-->
<httpCaching never304="true" />
<!-- If you include a <cacheControl> directive, it will be used to
generate a Cache-Control header (as well as an Expires header
if the value contains "max-age=")
By default, no Cache-Control header is generated.
You can use the <cacheControl> option even if you have set
never304="true"
-->
<!--
<httpCaching never304="true" >
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
-->
<!-- To enable Solr to respond with automatically generated HTTP
Caching headers, and to response to Cache Validation requests
correctly, set the value of never304="false"
This will cause Solr to generate Last-Modified and ETag
headers based on the properties of the Index.
The following options can also be specified to affect the
values of these headers...
lastModFrom - the default value is "openTime" which means the
Last-Modified value (and validation against If-Modified-Since
requests) will all be relative to when the current Searcher
was opened. You can change it to lastModFrom="dirLastMod" if
you want the value to exactly correspond to when the physical
index was last modified.
etagSeed="..." is an option you can change to force the ETag
header (and validation against If-None-Match requests) to be
different even if the index has not changed (ie: when making
significant changes to your config file)
(lastModifiedFrom and etagSeed are both ignored if you use
the never304="true" option)
-->
<!--
<httpCaching lastModifiedFrom="openTime"
etagSeed="Solr">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
-->
</requestDispatcher>
<!-- Request Handlers
http://wiki.apache.org/solr/SolrRequestHandler
Incoming queries will be dispatched to a specific handler by name
based on the path specified in the request.
Legacy behavior: If the request path uses "/select" but no Request
Handler has that name, and if handleSelect="true" has been specified in
the requestDispatcher, then the Request Handler is dispatched based on
the qt parameter. Handlers without a leading '/' are accessed this way
like so: http://host/app/[core/]select?qt=name If no qt is
given, then the requestHandler that declares default="true" will be
used or the one named "standard".
If a Request Handler is declared with startup="lazy", then it will
not be initialized until the first request that uses it.
-->
<!-- SearchHandler
http://wiki.apache.org/solr/SearchHandler
For processing Search Queries, the primary Request Handler
provided with Solr is "SearchHandler" It delegates to a sequent
of SearchComponents (see below) and supports distributed
queries across multiple shards
-->
<requestHandler name="/select" class="solr.SearchHandler">
<!-- default values for query parameters can be specified, these
will be overridden by parameters in the request
-->
<lst name="defaults">
<str name="echoParams">explicit</str>
<int name="rows">10</int>
<str name="df">_text</str>
</lst>
<!-- In addition to defaults, "appends" params can be specified
to identify values which should be appended to the list of
multi-val params from the query (or the existing "defaults").
-->
<!-- In this example, the param "fq=instock:true" would be appended to
any query time fq params the user may specify, as a mechanism for
partitioning the index, independent of any user selected filtering
that may also be desired (perhaps as a result of faceted searching).
NOTE: there is *absolutely* nothing a client can do to prevent these
"appends" values from being used, so don't use this mechanism
unless you are sure you always want it.
-->
<!--
<lst name="appends">
<str name="fq">inStock:true</str>
</lst>
-->
<!-- "invariants" are a way of letting the Solr maintainer lock down
the options available to Solr clients. Any params values
specified here are used regardless of what values may be specified
in either the query, the "defaults", or the "appends" params.
In this example, the facet.field and facet.query params would
be fixed, limiting the facets clients can use. Faceting is
not turned on by default - but if the client does specify
facet=true in the request, these are the only facets they
will be able to see counts for; regardless of what other
facet.field or facet.query params they may specify.
NOTE: there is *absolutely* nothing a client can do to prevent these
"invariants" values from being used, so don't use this mechanism
unless you are sure you always want it.
-->
<!--
<lst name="invariants">
<str name="facet.field">cat</str>
<str name="facet.field">manu_exact</str>
<str name="facet.query">price:[* TO 500]</str>
<str name="facet.query">price:[500 TO *]</str>
</lst>
-->
<!-- If the default list of SearchComponents is not desired, that
list can either be overridden completely, or components can be
prepended or appended to the default list. (see below)
-->
<!--
<arr name="components">
<str>nameOfCustomComponent1</str>
<str>nameOfCustomComponent2</str>
</arr>
-->
</requestHandler>
<!-- A request handler that returns indented JSON by default -->
<requestHandler name="/query" class="solr.SearchHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
<str name="wt">json</str>
<str name="indent">true</str>
<str name="df">_text</str>
</lst>
</requestHandler>
<!-- realtime get handler, guaranteed to return the latest stored fields of
any document, without the need to commit or open a new searcher. The
current implementation relies on the updateLog feature being enabled. -->
<requestHandler name="/get" class="solr.RealTimeGetHandler">
<lst name="defaults">
<str name="omitHeader">true</str>
<str name="wt">json</str>
<str name="indent">true</str>
</lst>
</requestHandler>
<!-- A Robust Example
This example SearchHandler declaration shows off usage of the
SearchHandler with many defaults declared
Note that multiple instances of the same Request Handler
(SearchHandler) can be registered multiple times with different
names (and different init parameters)
-->
<requestHandler name="/browse" class="solr.SearchHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
<!-- VelocityResponseWriter settings -->
<str name="wt">velocity</str>
<str name="v.template">browse</str>
<str name="v.layout">layout</str>
<str name="title">Solritas</str>
<!-- Query settings -->
<str name="defType">edismax</str>
<str name="qf">
text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
title^10.0 description^5.0 keywords^5.0 author^2.0 resourcename^1.0
</str>
<str name="df">_text</str>
<str name="mm">100%</str>
<str name="q.alt">*:*</str>
<str name="rows">10</str>
<str name="fl">*,score</str>
<str name="mlt.qf">
text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
title^10.0 description^5.0 keywords^5.0 author^2.0 resourcename^1.0
</str>
<str name="mlt.fl">text,features,name,sku,id,manu,cat,title,description,keywords,author,resourcename</str>
<int name="mlt.count">3</int>
<!-- Faceting defaults -->
<str name="facet">on</str>
<str name="facet.field">cat</str>
<str name="facet.field">manu_exact</str>
<str name="facet.field">content_type</str>
<str name="facet.field">author_s</str>
<str name="facet.query">ipod</str>
<str name="facet.query">GB</str>
<str name="facet.mincount">1</str>
<str name="facet.pivot">cat,inStock</str>
<str name="facet.range.other">after</str>
<str name="facet.range">price</str>
<int name="f.price.facet.range.start">0</int>
<int name="f.price.facet.range.end">600</int>
<int name="f.price.facet.range.gap">50</int>
<str name="facet.range">popularity</str>
<int name="f.popularity.facet.range.start">0</int>
<int name="f.popularity.facet.range.end">10</int>
<int name="f.popularity.facet.range.gap">3</int>
<str name="facet.range">manufacturedate_dt</str>
<str name="f.manufacturedate_dt.facet.range.start">NOW/YEAR-10YEARS</str>
<str name="f.manufacturedate_dt.facet.range.end">NOW</str>
<str name="f.manufacturedate_dt.facet.range.gap">+1YEAR</str>
<str name="f.manufacturedate_dt.facet.range.other">before</str>
<str name="f.manufacturedate_dt.facet.range.other">after</str>
<!-- Highlighting defaults -->
<str name="hl">on</str>
<str name="hl.fl">content features title name</str>
<str name="hl.encoder">html</str>
<str name="hl.simple.pre">&lt;b&gt;</str>
<str name="hl.simple.post">&lt;/b&gt;</str>
<str name="f.title.hl.fragsize">0</str>
<str name="f.title.hl.alternateField">title</str>
<str name="f.name.hl.fragsize">0</str>
<str name="f.name.hl.alternateField">name</str>
<str name="f.content.hl.snippets">3</str>
<str name="f.content.hl.fragsize">200</str>
<str name="f.content.hl.alternateField">content</str>
<str name="f.content.hl.maxAlternateFieldLength">750</str>
<!-- Spell checking defaults -->
<str name="spellcheck">on</str>
<str name="spellcheck.extendedResults">false</str>
<str name="spellcheck.count">5</str>
<str name="spellcheck.alternativeTermCount">2</str>
<str name="spellcheck.maxResultsForSuggest">5</str>
<str name="spellcheck.collate">true</str>
<str name="spellcheck.collateExtendedResults">true</str>
<str name="spellcheck.maxCollationTries">5</str>
<str name="spellcheck.maxCollations">3</str>
</lst>
<!-- append spellchecking to our list of components -->
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<!-- Update Request Handler.
http://wiki.apache.org/solr/UpdateXmlMessages
The canonical Request Handler for Modifying the Index through
commands specified using XML, JSON, CSV, or JAVABIN
Note: Since solr1.1 requestHandlers requires a valid content
type header if posted in the body. For example, curl now
requires: -H 'Content-type:text/xml; charset=utf-8'
To override the request content type and force a specific
Content-type, use the request parameter:
?update.contentType=text/csv
This handler will pick a response format to match the input
if the 'wt' parameter is not explicit
-->
<requestHandler name="/update" class="solr.UpdateRequestHandler">
<!-- See below for information on defining
updateRequestProcessorChains that can be used by name
on each Update Request
-->
<!--
<lst name="defaults">
<str name="update.chain">dedupe</str>
</lst>
-->
</requestHandler>
<!-- for back compat with clients using /update/json and /update/csv -->
<requestHandler name="/update/json" class="solr.JsonUpdateRequestHandler">
<lst name="defaults">
<str name="stream.contentType">application/json</str>
</lst>
</requestHandler>
<requestHandler name="/update/csv" class="solr.CSVRequestHandler">
<lst name="defaults">
<str name="stream.contentType">application/csv</str>
</lst>
</requestHandler>
<!-- Solr Cell Update Request Handler
http://wiki.apache.org/solr/ExtractingRequestHandler
-->
<requestHandler name="/update/extract"
startup="lazy"
class="solr.extraction.ExtractingRequestHandler" >
<lst name="defaults">
<str name="lowernames">true</str>
<str name="uprefix">ignored_</str>
<!-- capture link hrefs but ignore div attributes -->
<str name="captureAttr">true</str>
<str name="fmap.a">links</str>
<str name="fmap.div">ignored_</str>
</lst>
</requestHandler>
<!-- Field Analysis Request Handler
RequestHandler that provides much the same functionality as
analysis.jsp. Provides the ability to specify multiple field
types and field names in the same request and outputs
index-time and query-time analysis for each of them.
Request parameters are:
analysis.fieldname - field name whose analyzers are to be used
analysis.fieldtype - field type whose analyzers are to be used
analysis.fieldvalue - text for index-time analysis
q (or analysis.q) - text for query time analysis
analysis.showmatch (true|false) - When set to true and when
query analysis is performed, the produced tokens of the
field value analysis will be marked as "matched" for every
token that is produces by the query analysis
-->
<requestHandler name="/analysis/field"
startup="lazy"
class="solr.FieldAnalysisRequestHandler" />
<!-- Document Analysis Handler
http://wiki.apache.org/solr/AnalysisRequestHandler
An analysis handler that provides a breakdown of the analysis
process of provided documents. This handler expects a (single)
content stream with the following format:
<docs>
<doc>
<field name="id">1</field>
<field name="name">The Name</field>
<field name="text">The Text Value</field>
</doc>
<doc>...</doc>
<doc>...</doc>
...
</docs>
Note: Each document must contain a field which serves as the
unique key. This key is used in the returned response to associate
an analysis breakdown to the analyzed document.
Like the FieldAnalysisRequestHandler, this handler also supports
query analysis by sending either an "analysis.query" or "q"
request parameter that holds the query text to be analyzed. It
also supports the "analysis.showmatch" parameter which when set to
true, all field tokens that match the query tokens will be marked
as a "match".
-->
<requestHandler name="/analysis/document"
class="solr.DocumentAnalysisRequestHandler"
startup="lazy" />
<!-- Admin Handlers
Admin Handlers - This will register all the standard admin
RequestHandlers.
-->
<requestHandler name="/admin/"
class="solr.admin.AdminHandlers" />
<!-- This single handler is equivalent to the following... -->
<!--
<requestHandler name="/admin/luke" class="solr.admin.LukeRequestHandler" />
<requestHandler name="/admin/system" class="solr.admin.SystemInfoHandler" />
<requestHandler name="/admin/plugins" class="solr.admin.PluginInfoHandler" />
<requestHandler name="/admin/threads" class="solr.admin.ThreadDumpHandler" />
<requestHandler name="/admin/properties" class="solr.admin.PropertiesRequestHandler" />
<requestHandler name="/admin/file" class="solr.admin.ShowFileRequestHandler" >
-->
<!-- If you wish to hide files under ${solr.home}/conf, explicitly
register the ShowFileRequestHandler using:
-->
<!--
<requestHandler name="/admin/file"
class="solr.admin.ShowFileRequestHandler" >
<lst name="invariants">
<str name="hidden">synonyms.txt</str>
<str name="hidden">anotherfile.txt</str>
</lst>
</requestHandler>
-->
<!-- ping/healthcheck -->
<requestHandler name="/admin/ping" class="solr.PingRequestHandler">
<lst name="invariants">
<str name="q">solrpingquery</str>
</lst>
<lst name="defaults">
<str name="echoParams">all</str>
</lst>
<!-- An optional feature of the PingRequestHandler is to configure the
handler with a "healthcheckFile" which can be used to enable/disable
the PingRequestHandler.
relative paths are resolved against the data dir
-->
<!-- <str name="healthcheckFile">server-enabled.txt</str> -->
</requestHandler>
<!-- Echo the request contents back to the client -->
<requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
<lst name="defaults">
<str name="echoParams">explicit</str>
<str name="echoHandler">true</str>
</lst>
</requestHandler>
<!-- Solr Replication
The SolrReplicationHandler supports replicating indexes from a
"master" used for indexing and "slaves" used for queries.
http://wiki.apache.org/solr/SolrReplication
It is also necessary for SolrCloud to function (in Cloud mode, the
replication handler is used to bulk transfer segments when nodes
are added or need to recover).
https://wiki.apache.org/solr/SolrCloud/
-->
<requestHandler name="/replication" class="solr.ReplicationHandler" >
<!--
To enable simple master/slave replication, uncomment one of the
sections below, depending on whether this solr instance should be
the "master" or a "slave". If this instance is a "slave" you will
also need to fill in the masterUrl to point to a real machine.
-->
<!--
<lst name="master">
<str name="replicateAfter">commit</str>
<str name="replicateAfter">startup</str>
<str name="confFiles">schema.xml,stopwords.txt</str>
</lst>
-->
<!--
<lst name="slave">
<str name="masterUrl">http://your-master-hostname:8983/solr</str>
<str name="pollInterval">00:00:60</str>
</lst>
-->
</requestHandler>
<!-- Search Components
Search components are registered to SolrCore and used by
instances of SearchHandler (which can access them by name)
By default, the following components are available:
<searchComponent name="query" class="solr.QueryComponent" />
<searchComponent name="facet" class="solr.FacetComponent" />
<searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
<searchComponent name="highlight" class="solr.HighlightComponent" />
<searchComponent name="stats" class="solr.StatsComponent" />
<searchComponent name="debug" class="solr.DebugComponent" />
Default configuration in a requestHandler would look like:
<arr name="components">
<str>query</str>
<str>facet</str>
<str>mlt</str>
<str>highlight</str>
<str>stats</str>
<str>debug</str>
</arr>
If you register a searchComponent to one of the standard names,
that will be used instead of the default.
To insert components before or after the 'standard' components, use:
<arr name="first-components">
<str>myFirstComponentName</str>
</arr>
<arr name="last-components">
<str>myLastComponentName</str>
</arr>
NOTE: The component registered with the name "debug" will
always be executed after the "last-components"
-->
<!-- Spell Check
The spell check component can return a list of alternative spelling
suggestions.
http://wiki.apache.org/solr/SpellCheckComponent
-->
<searchComponent name="spellcheck" class="solr.SpellCheckComponent">
<str name="queryAnalyzerFieldType">text_general</str>
<!-- Multiple "Spell Checkers" can be declared and used by this
component
-->
<!-- a spellchecker built from a field of the main index -->
<lst name="spellchecker">
<str name="name">default</str>
<str name="field">text</str>
<str name="classname">solr.DirectSolrSpellChecker</str>
<!-- the spellcheck distance measure used, the default is the internal levenshtein -->
<str name="distanceMeasure">internal</str>
<!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
<float name="accuracy">0.5</float>
<!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
<int name="maxEdits">2</int>
<!-- the minimum shared prefix when enumerating terms -->
<int name="minPrefix">1</int>
<!-- maximum number of inspections per result. -->
<int name="maxInspections">5</int>
<!-- minimum length of a query term to be considered for correction -->
<int name="minQueryLength">4</int>
<!-- maximum threshold of documents a query term can appear to be considered for correction -->
<float name="maxQueryFrequency">0.01</float>
<!-- uncomment this to require suggestions to occur in 1% of the documents
<float name="thresholdTokenFrequency">.01</float>
-->
</lst>
<!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
<lst name="spellchecker">
<str name="name">wordbreak</str>
<str name="classname">solr.WordBreakSolrSpellChecker</str>
<str name="field">name</str>
<str name="combineWords">true</str>
<str name="breakWords">true</str>
<int name="maxChanges">10</int>
</lst>
<!-- a spellchecker that uses a different distance measure -->
<!--
<lst name="spellchecker">
<str name="name">jarowinkler</str>
<str name="field">spell</str>
<str name="classname">solr.DirectSolrSpellChecker</str>
<str name="distanceMeasure">
org.apache.lucene.search.spell.JaroWinklerDistance
</str>
</lst>
-->
<!-- a spellchecker that use an alternate comparator
comparatorClass be one of:
1. score (default)
2. freq (Frequency first, then score)
3. A fully qualified class name
-->
<!--
<lst name="spellchecker">
<str name="name">freq</str>
<str name="field">lowerfilt</str>
<str name="classname">solr.DirectSolrSpellChecker</str>
<str name="comparatorClass">freq</str>
-->
<!-- A spellchecker that reads the list of words from a file -->
<!--
<lst name="spellchecker">
<str name="classname">solr.FileBasedSpellChecker</str>
<str name="name">file</str>
<str name="sourceLocation">spellings.txt</str>
<str name="characterEncoding">UTF-8</str>
<str name="spellcheckIndexDir">spellcheckerFile</str>
</lst>
-->
</searchComponent>
<!-- A request handler for demonstrating the spellcheck component.
NOTE: This is purely as an example. The whole purpose of the
SpellCheckComponent is to hook it into the request handler that
handles your normal user queries so that a separate request is
not needed to get suggestions.
IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
See http://wiki.apache.org/solr/SpellCheckComponent for details
on the request parameters.
-->
<requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<str name="df">_text</str>
<!-- Solr will use suggestions from both the 'default' spellchecker
and from the 'wordbreak' spellchecker and combine them.
collations (re-written queries) can include a combination of
corrections from both spellcheckers -->
<str name="spellcheck.dictionary">default</str>
<str name="spellcheck.dictionary">wordbreak</str>
<str name="spellcheck">on</str>
<str name="spellcheck.extendedResults">true</str>
<str name="spellcheck.count">10</str>
<str name="spellcheck.alternativeTermCount">5</str>
<str name="spellcheck.maxResultsForSuggest">5</str>
<str name="spellcheck.collate">true</str>
<str name="spellcheck.collateExtendedResults">true</str>
<str name="spellcheck.maxCollationTries">10</str>
<str name="spellcheck.maxCollations">5</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<!-- Term Vector Component
http://wiki.apache.org/solr/TermVectorComponent
-->
<searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
<!-- A request handler for demonstrating the term vector component
This is purely as an example.
In reality you will likely want to add the component to your
already specified request handlers.
-->
<requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<str name="df">_text</str>
<bool name="tv">true</bool>
</lst>
<arr name="last-components">
<str>tvComponent</str>
</arr>
</requestHandler>
<!-- Clustering Component
http://wiki.apache.org/solr/ClusteringComponent
You'll need to set the solr.clustering.enabled system property
when running solr to run with clustering enabled:
java -Dsolr.clustering.enabled=true -jar start.jar
-->
<searchComponent name="clustering"
enable="${solr.clustering.enabled:false}"
class="solr.clustering.ClusteringComponent" >
<!-- Declare an engine -->
<lst name="engine">
<!-- The name, only one can be named "default" -->
<str name="name">default</str>
<!-- Class name of Carrot2 clustering algorithm.
Currently available algorithms are:
* org.carrot2.clustering.lingo.LingoClusteringAlgorithm
* org.carrot2.clustering.stc.STCClusteringAlgorithm
* org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm
See http://project.carrot2.org/algorithms.html for the
algorithm's characteristics.
-->
<str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
<!-- Overriding values for Carrot2 default algorithm attributes.
For a description of all available attributes, see:
http://download.carrot2.org/stable/manual/#chapter.components.
Use attribute key as name attribute of str elements
below. These can be further overridden for individual
requests by specifying attribute key as request parameter
name and attribute value as parameter value.
-->
<str name="LingoClusteringAlgorithm.desiredClusterCountBase">20</str>
<!-- Location of Carrot2 lexical resources.
A directory from which to load Carrot2-specific stop words
and stop labels. Absolute or relative to Solr config directory.
If a specific resource (e.g. stopwords.en) is present in the
specified dir, it will completely override the corresponding
default one that ships with Carrot2.
For an overview of Carrot2 lexical resources, see:
http://download.carrot2.org/head/manual/#chapter.lexical-resources
-->
<str name="carrot.lexicalResourcesDir">clustering/carrot2</str>
<!-- The language to assume for the documents.
For a list of allowed values, see:
http://download.carrot2.org/stable/manual/#section.attribute.lingo.MultilingualClustering.defaultLanguage
-->
<str name="MultilingualClustering.defaultLanguage">ENGLISH</str>
</lst>
<lst name="engine">
<str name="name">stc</str>
<str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
</lst>
</searchComponent>
<!-- A request handler for demonstrating the clustering component
This is purely as an example.
In reality you will likely want to add the component to your
already specified request handlers.
-->
<requestHandler name="/clustering"
startup="lazy"
enable="${solr.clustering.enabled:false}"
class="solr.SearchHandler">
<lst name="defaults">
<bool name="clustering">true</bool>
<str name="clustering.engine">default</str>
<bool name="clustering.results">true</bool>
<!-- The title field -->
<str name="carrot.title">name</str>
<str name="carrot.url">id</str>
<!-- The field to cluster on -->
<str name="carrot.snippet">features</str>
<!-- produce summaries -->
<bool name="carrot.produceSummary">true</bool>
<!-- the maximum number of labels per cluster -->
<!--<int name="carrot.numDescriptions">5</int>-->
<!-- produce sub clusters -->
<bool name="carrot.outputSubClusters">false</bool>
<str name="defType">edismax</str>
<str name="qf">
text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
</str>
<str name="q.alt">*:*</str>
<str name="rows">10</str>
<str name="fl">*,score</str>
</lst>
<arr name="last-components">
<str>clustering</str>
</arr>
</requestHandler>
<!-- Terms Component
http://wiki.apache.org/solr/TermsComponent
A component to return terms and document frequency of those
terms
-->
<searchComponent name="terms" class="solr.TermsComponent"/>
<!-- A request handler for demonstrating the terms component -->
<requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<bool name="terms">true</bool>
<bool name="distrib">false</bool>
</lst>
<arr name="components">
<str>terms</str>
</arr>
</requestHandler>
<!-- Query Elevation Component
http://wiki.apache.org/solr/QueryElevationComponent
a search component that enables you to configure the top
results for a given query regardless of the normal lucene
scoring.
-->
<searchComponent name="elevator" class="solr.QueryElevationComponent" >
<!-- pick a fieldType to analyze queries -->
<str name="queryFieldType">string</str>
<str name="config-file">elevate.xml</str>
</searchComponent>
<!-- A request handler for demonstrating the elevator component -->
<requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<str name="echoParams">explicit</str>
<str name="df">text</str>
</lst>
<arr name="last-components">
<str>elevator</str>
</arr>
</requestHandler>
<!-- Highlighting Component
http://wiki.apache.org/solr/HighlightingParameters
-->
<searchComponent class="solr.HighlightComponent" name="highlight">
<highlighting>
<!-- Configure the standard fragmenter -->
<!-- This could most likely be commented out in the "default" case -->
<fragmenter name="gap"
default="true"
class="solr.highlight.GapFragmenter">
<lst name="defaults">
<int name="hl.fragsize">100</int>
</lst>
</fragmenter>
<!-- A regular-expression-based fragmenter
(for sentence extraction)
-->
<fragmenter name="regex"
class="solr.highlight.RegexFragmenter">
<lst name="defaults">
<!-- slightly smaller fragsizes work better because of slop -->
<int name="hl.fragsize">70</int>
<!-- allow 50% slop on fragment sizes -->
<float name="hl.regex.slop">0.5</float>
<!-- a basic sentence pattern -->
<str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
</lst>
</fragmenter>
<!-- Configure the standard formatter -->
<formatter name="html"
default="true"
class="solr.highlight.HtmlFormatter">
<lst name="defaults">
<str name="hl.simple.pre"><![CDATA[<em>]]></str>
<str name="hl.simple.post"><![CDATA[</em>]]></str>
</lst>
</formatter>
<!-- Configure the standard encoder -->
<encoder name="html"
class="solr.highlight.HtmlEncoder" />
<!-- Configure the standard fragListBuilder -->
<fragListBuilder name="simple"
class="solr.highlight.SimpleFragListBuilder"/>
<!-- Configure the single fragListBuilder -->
<fragListBuilder name="single"
class="solr.highlight.SingleFragListBuilder"/>
<!-- Configure the weighted fragListBuilder -->
<fragListBuilder name="weighted"
default="true"
class="solr.highlight.WeightedFragListBuilder"/>
<!-- default tag FragmentsBuilder -->
<fragmentsBuilder name="default"
default="true"
class="solr.highlight.ScoreOrderFragmentsBuilder">
<!--
<lst name="defaults">
<str name="hl.multiValuedSeparatorChar">/</str>
</lst>
-->
</fragmentsBuilder>
<!-- multi-colored tag FragmentsBuilder -->
<fragmentsBuilder name="colored"
class="solr.highlight.ScoreOrderFragmentsBuilder">
<lst name="defaults">
<str name="hl.tag.pre"><![CDATA[
<b style="background:yellow">,<b style="background:lawgreen">,
<b style="background:aquamarine">,<b style="background:magenta">,
<b style="background:palegreen">,<b style="background:coral">,
<b style="background:wheat">,<b style="background:khaki">,
<b style="background:lime">,<b style="background:deepskyblue">]]></str>
<str name="hl.tag.post"><![CDATA[</b>]]></str>
</lst>
</fragmentsBuilder>
<boundaryScanner name="default"
default="true"
class="solr.highlight.SimpleBoundaryScanner">
<lst name="defaults">
<str name="hl.bs.maxScan">10</str>
<str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
</lst>
</boundaryScanner>
<boundaryScanner name="breakIterator"
class="solr.highlight.BreakIteratorBoundaryScanner">
<lst name="defaults">
<!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
<str name="hl.bs.type">WORD</str>
<!-- language and country are used when constructing Locale object. -->
<!-- And the Locale object will be used when getting instance of BreakIterator -->
<str name="hl.bs.language">en</str>
<str name="hl.bs.country">US</str>
</lst>
</boundaryScanner>
</highlighting>
</searchComponent>
<!-- Update Processors
Chains of Update Processor Factories for dealing with Update
Requests can be declared, and then used by name in Update
Request Processors
http://wiki.apache.org/solr/UpdateRequestProcessor
-->
<!-- Deduplication
An example dedup update processor that creates the "id" field
on the fly based on the hash code of some other fields. This
example has overwriteDupes set to false since we are using the
id field as the signatureField and Solr will maintain
uniqueness based on that anyway.
-->
<!--
<updateRequestProcessorChain name="dedupe">
<processor class="solr.processor.SignatureUpdateProcessorFactory">
<bool name="enabled">true</bool>
<str name="signatureField">id</str>
<bool name="overwriteDupes">false</bool>
<str name="fields">name,features,cat</str>
<str name="signatureClass">solr.processor.Lookup3Signature</str>
</processor>
<processor class="solr.LogUpdateProcessorFactory" />
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
-->
<!-- Language identification
This example update chain identifies the language of the incoming
documents using the langid contrib. The detected language is
written to field language_s. No field name mapping is done.
The fields used for detection are text, title, subject and description,
making this example suitable for detecting languages form full-text
rich documents injected via ExtractingRequestHandler.
See more about langId at http://wiki.apache.org/solr/LanguageDetection
-->
<!--
<updateRequestProcessorChain name="langid">
<processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
<str name="langid.fl">text,title,subject,description</str>
<str name="langid.langField">language_s</str>
<str name="langid.fallback">en</str>
</processor>
<processor class="solr.LogUpdateProcessorFactory" />
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
-->
<!-- Script update processor
This example hooks in an update processor implemented using JavaScript.
See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
-->
<!--
<updateRequestProcessorChain name="script">
<processor class="solr.StatelessScriptUpdateProcessorFactory">
<str name="script">update-script.js</str>
<lst name="params">
<str name="config_param">example config parameter</str>
</lst>
</processor>
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
-->
<!-- Response Writers
http://wiki.apache.org/solr/QueryResponseWriter
Request responses will be written using the writer specified by
the 'wt' request parameter matching the name of a registered
writer.
The "default" writer is the default and will be used if 'wt' is
not specified in the request.
-->
<!-- The following response writers are implicitly configured unless
overridden...
-->
<!--
<queryResponseWriter name="xml"
default="true"
class="solr.XMLResponseWriter" />
<queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
<queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
<queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
<queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
<queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
<queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
<queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
-->
<queryResponseWriter name="json" class="solr.JSONResponseWriter">
<!-- For the purposes of the tutorial, JSON responses are written as
plain text so that they are easy to read in *any* browser.
If you expect a MIME type of "application/json" just remove this override.
-->
<str name="content-type">text/plain; charset=UTF-8</str>
</queryResponseWriter>
<!--
Custom response writers can be declared as needed...
-->
<queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy"/>
<!-- XSLT response writer transforms the XML output by any xslt file found
in Solr's conf/xslt directory. Changes to xslt files are checked for
every xsltCacheLifetimeSeconds.
-->
<queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
<int name="xsltCacheLifetimeSeconds">5</int>
</queryResponseWriter>
<!-- Query Parsers
http://wiki.apache.org/solr/SolrQuerySyntax
Multiple QParserPlugins can be registered by name, and then
used in either the "defType" param for the QueryComponent (used
by SearchHandler) or in LocalParams
-->
<!-- example of registering a query parser -->
<!--
<queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
-->
<!-- Function Parsers
http://wiki.apache.org/solr/FunctionQuery
Multiple ValueSourceParsers can be registered by name, and then
used as function names when using the "func" QParser.
-->
<!-- example of registering a custom function parser -->
<!--
<valueSourceParser name="myfunc"
class="com.mycompany.MyValueSourceParser" />
-->
<!-- Document Transformers
http://wiki.apache.org/solr/DocTransformers
-->
<!--
Could be something like:
<transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
<int name="connection">jdbc://....</int>
</transformer>
To add a constant value to all docs, use:
<transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
<int name="value">5</int>
</transformer>
If you want the user to still be able to change it with _value:something_ use this:
<transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
<double name="defaultValue">5</double>
</transformer>
If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
EditorialMarkerFactory will do exactly that:
<transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
-->
<!-- Legacy config for the admin interface -->
<admin>
<defaultQuery>*:*</defaultQuery>
</admin>
</config>

58
conf/solr/4/extras/stopwords.txt Normal file
View File

@ -0,0 +1,58 @@
# 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
s
such
t
that
the
their
then
there
these
they
this
to
was
will
with

29
conf/solr/4/extras/synonyms.txt Normal file
View File

@ -0,0 +1,29 @@
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#-----------------------------------------------------------------------
#some test synonym mappings unlikely to appear in real input text
aaafoo => aaabar
bbbfoo => bbbfoo bbbbar
cccfoo => cccbar cccbaz
fooaaa,baraaa,bazaaa
# Some synonym groups specific to this example
GB,gib,gigabyte,gigabytes
MB,mib,megabyte,megabytes
Television, Televisions, TV, TVs
#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
#after us won't split it into two words.
# Synonym mappings can be used for spelling correction too
pixima => pixma

68
conf/solr/4/templates/schema.ss Normal file
View File

@ -0,0 +1,68 @@
<?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="$IndexName" version="1.5">
<types>
$Types
</types>
<fields>
$FieldDefinitions
<field name="_version_" type="long" indexed="true" stored="true" multiValued="false"/>
</fields>
$CopyFieldDefinitions
<uniqueKey>_documentid</uniqueKey>
<defaultSearchField>_text</defaultSearchField>
<solrQueryParser defaultOperator="OR"/>
</schema>

360
conf/solr/4/templates/types.ss Normal file
View File

@ -0,0 +1,360 @@
<!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
<fieldtype name="binary" class="solr.BinaryField"/>
<!-- The optional sortMissingLast and sortMissingFirst attributes are
currently supported on types that are sorted internally as strings.
This includes "string","boolean","sint","slong","sfloat","sdouble","pdate"
- If sortMissingLast="true", then a sort on this field will cause documents
without the field to come after documents with the field,
regardless of the requested sort order (asc or desc).
- If sortMissingFirst="true", then a sort on this field will cause documents
without the field to come before documents with the field,
regardless of the requested sort order.
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the
field first in an ascending sort and last in a descending sort.
-->
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-->
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<!--
Numeric field types that index each value at various levels of precision
to accelerate range queries when the number of values between the range
endpoints is large. See the javadoc for NumericRangeQuery for internal
implementation details.
Smaller precisionStep values (specified in bits) will lead to more tokens
indexed per value, slightly larger index size, and faster range queries.
A precisionStep of 0 disables indexing at different precision levels.
-->
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory.
Expressions can also be used to denote calculations that should be
performed relative to "NOW" to determine the value, ie...
NOW/HOUR
... Round to the start of the current hour
NOW-1DAY
... Exactly 1 day prior to now
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
Consult the DateField javadocs for more information.
Note: For faster range queries, consider the tdate type
-->
<fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
<!-- A Trie based date field for faster date range queries and date faceting. -->
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
<!-- The "RandomSortField" is not used to store or search any
data. You can declare fields of this type it in your schema
to generate pseudo-random orderings of your docs for sorting
purposes. The ordering is generated based on the field name
and the version of the index, As long as the index version
remains unchanged, and the same field name is reused,
the ordering of the docs will be consistent.
If you want different psuedo-random orderings of documents,
for the same version of the index, use a dynamicField and
change the name
-->
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<!-- solr.TextField allows the specification of custom text analyzers
specified as a tokenizer and a list of token filters. Different
analyzers may be specified for indexing and querying.
The optional positionIncrementGap puts space between multiple fields of
this type on the same document, with the purpose of preventing false phrase
matching across fields.
For more info on customizing your analyzer chain, please see
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-->
<!-- One can also specify an existing Analyzer class that has a
default constructor via the class attribute on the analyzer element
<fieldType name="text_greek" class="solr.TextField">
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
</fieldType>
-->
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
Synonyms and stopwords are customized by external files, and stemming is enabled.
The attribute autoGeneratePhraseQueries="true" (the default) causes words that get split to
form phrase queries. For example, WordDelimiterFilter splitting text:pdp-11 will cause the parser
to generate text:"pdp 11" rather than (text:PDP OR text:11).
NOTE: autoGeneratePhraseQueries="true" tends to not work well for non whitespace delimited languages.
-->
<fieldType name="text" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
add enablePositionIncrements=true in both the index and query
analyzers to leave a 'gap' for more accurate phrase queries.
-->
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- A copy of text that has the HTMLStripCharFilterFactory as the first index analyzer, so that html can be provided -->
<fieldType name="htmltext" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.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>
<!-- Text optimized for spelling corrections, with minimal alterations (e.g. no stemming) -->
<fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory" />
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
<filter class="solr.LengthFilterFactory" min="4" max="20" />
<filter class="solr.LowerCaseFilterFactory" />
<filter class="solr.RemoveDuplicatesTokenFilterFactory" />
</analyzer>
</fieldType>
<!-- A general unstemmed text field - good if one does not know the language of the field -->
<fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- A general unstemmed text field that indexes tokens normally and also
reversed (via ReversedWildcardFilterFactory), to enable more efficient
leading wildcard queries. -->
<fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- charFilter + WhitespaceTokenizer -->
<!--
<fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
-->
<!-- This is an example of using the KeywordTokenizer along
With various TokenFilterFactories to produce a sortable field
that does not include some properties of the source text
-->
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
which may include back references to portions of the original
string matched by the pattern.
See the Java Regular Expression documentation for more
information on pattern and replacement string syntax.
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
</fieldType>
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldtype>
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
Attributes of the DelimitedPayloadTokenFilterFactory :
"delimiter" - a one character delimiter. Default is | (pipe)
"encoder" - how to encode the following value into a playload
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
integer -> o.a.l.a.p.IntegerEncoder
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
</analyzer>
</fieldtype>
<!-- lowercases the entire field value, keeping it as a single token. -->
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.PathHierarchyTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- since fields of this type are by default not stored or indexed,
any data added to them will be ignored outright. -->
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
<!-- This point type indexes the coordinates as separate fields (subFields)
If subFieldType is defined, it references a type, and a dynamic field
definition is created matching *___<typename>. Alternately, if
subFieldSuffix is defined, that is used to create the subFields.
Example: if subFieldType="double", then the coordinates would be
indexed in fields myloc_0___double,myloc_1___double.
Example: if subFieldSuffix="_d" then the coordinates would be indexed
in fields myloc_0_d,myloc_1_d
The subFields are an implementation detail of the fieldType, and end
users normally should not need to know about them.
-->
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
<!--
A Geohash is a compact representation of a latitude longitude pair in a single field.
See http://wiki.apache.org/solr/SpatialSearch
-->
<fieldtype name="geohash" class="solr.GeoHashField"/>

4
tests/SolrIndexTest.php
View File

@ -103,11 +103,11 @@ class SolrIndexTest extends SapphireTest {
}
protected function getServiceMock() {
return Phockito::mock('SolrService');
return Phockito::mock('Solr3Service');
}
protected function getServiceSpy() {
$serviceSpy = Phockito::spy('SolrService');
$serviceSpy = Phockito::spy('Solr3Service');
Phockito::when($serviceSpy)->_sendRawPost()->return($this->getFakeRawSolrResponse());
return $serviceSpy;