From 7b84dd36e07a09a6dc96e87cbe377a57d3d06864 Mon Sep 17 00:00:00 2001
From: Demian Katz <demian.katz@villanova.edu>
Date: Wed, 26 Jun 2013 14:35:37 -0400
Subject: [PATCH] Progress on VUFIND-454: basic website indexing/search.
---
config/vufind/websearchspecs.yaml | 48 ++
config/vufind/website.ini | 25 +
import/sitemap.properties | 24 +
import/xsl/sitemap.xsl | 17 +
module/VuFind/config/module.config.php | 11 +
.../src/VuFind/Controller/WebController.php | 61 ++
.../src/VuFind/RecordDriver/SolrWeb.php | 77 ++
.../Search/Factory/SolrWebBackendFactory.php | 75 ++
.../src/VuFind/Search/SolrWeb/Options.php | 73 ++
.../src/VuFind/Search/SolrWeb/Params.php | 41 ++
.../src/VuFind/Search/SolrWeb/Results.php | 52 ++
.../src/VuFind/XSLT/Import/VuFindSitemap.php | 257 +++++++
solr/solr.xml | 1 +
solr/website/conf/elevate.xml | 25 +
solr/website/conf/protwords.txt | 0
solr/website/conf/schema.xml | 152 ++++
solr/website/conf/solrconfig.xml | 676 ++++++++++++++++++
solr/website/conf/stopwords.txt | 34 +
solr/website/conf/synonyms.txt | 5 +
.../RecordDriver/SolrWeb/result-list.phtml | 33 +
themes/blueprint/templates/web/home.phtml | 1 +
themes/blueprint/templates/web/results.phtml | 5 +
.../RecordDriver/SolrWeb/result-list.phtml | 26 +
themes/jquerymobile/templates/web/home.phtml | 4 +
.../jquerymobile/templates/web/results.phtml | 7 +
25 files changed, 1730 insertions(+)
create mode 100644 config/vufind/websearchspecs.yaml
create mode 100644 config/vufind/website.ini
create mode 100644 import/sitemap.properties
create mode 100644 import/xsl/sitemap.xsl
create mode 100644 module/VuFind/src/VuFind/Controller/WebController.php
create mode 100644 module/VuFind/src/VuFind/RecordDriver/SolrWeb.php
create mode 100644 module/VuFind/src/VuFind/Search/Factory/SolrWebBackendFactory.php
create mode 100644 module/VuFind/src/VuFind/Search/SolrWeb/Options.php
create mode 100644 module/VuFind/src/VuFind/Search/SolrWeb/Params.php
create mode 100644 module/VuFind/src/VuFind/Search/SolrWeb/Results.php
create mode 100644 module/VuFind/src/VuFind/XSLT/Import/VuFindSitemap.php
create mode 100644 solr/website/conf/elevate.xml
create mode 100644 solr/website/conf/protwords.txt
create mode 100644 solr/website/conf/schema.xml
create mode 100644 solr/website/conf/solrconfig.xml
create mode 100644 solr/website/conf/stopwords.txt
create mode 100644 solr/website/conf/synonyms.txt
create mode 100644 themes/blueprint/templates/RecordDriver/SolrWeb/result-list.phtml
create mode 100644 themes/blueprint/templates/web/home.phtml
create mode 100644 themes/blueprint/templates/web/results.phtml
create mode 100644 themes/jquerymobile/templates/RecordDriver/SolrWeb/result-list.phtml
create mode 100644 themes/jquerymobile/templates/web/home.phtml
create mode 100644 themes/jquerymobile/templates/web/results.phtml
diff --git a/config/vufind/websearchspecs.yaml b/config/vufind/websearchspecs.yaml
new file mode 100644
index 00000000000..263e546748f
--- /dev/null
+++ b/config/vufind/websearchspecs.yaml
@@ -0,0 +1,48 @@
+---
+# This file contains search specifications used by the website module; for details
+# on the workings of this file, see the comments in searchspecs.yaml.
+#-----------------------------------------------------------------------------------
+
+AllFields:
+ DismaxFields:
+ - title^750
+ - description_unstemmed^350
+ - description^300
+ - keywords_unstemmed^250
+ - keywords^200
+ - url_keywords^50
+ - fulltext_unstemmed^10
+ - fulltext
+ QueryFields:
+ title:
+ - [onephrase, 1000]
+ - [and, 750]
+ - [or, 10]
+ description_unstemmed:
+ - [onephrase, 400]
+ - [and, 350]
+ - [or, ~]
+ description:
+ - [onephrase, 350]
+ - [and, 300]
+ - [or, ~]
+ keywords_unstemmed:
+ - [onephrase, 300]
+ - [and, 250]
+ - [or, ~]
+ keywords:
+ - [onephrase, 250]
+ - [and, 200]
+ - [or, ~]
+ url_keywords:
+ - [onephrase, 100]
+ - [and, 50]
+ - [or, ~]
+ fulltext_unstemmed:
+ - [onephrase, 50]
+ - [and, 10]
+ - [or, ~]
+ fulltext:
+ - [onephrase, 25]
+ - [and, 5]
+ - [or, ~]
diff --git a/config/vufind/website.ini b/config/vufind/website.ini
new file mode 100644
index 00000000000..cb9638e67f4
--- /dev/null
+++ b/config/vufind/website.ini
@@ -0,0 +1,25 @@
+; This configuration file controls the Web module (for searching your website); see
+; facets.ini and searches.ini for detailed comments on the meaning of all settings.
+[General]
+default_handler = AllFields ; Search handler to use if none is specified
+default_sort = relevance
+case_sensitive_bools = true
+default_side_recommend[] = SideFacets:Facets:CheckboxFacets:website
+default_side_recommend[] = CatalogResults
+highlighting = true
+snippets = true
+
+[Basic_Searches]
+AllFields = "All Fields"
+
+[Advanced_Searches]
+AllFields = "All Fields"
+
+[Sorting]
+relevance = sort_relevance
+title = sort_title
+
+[Facets]
+category = "Category"
+linktype = "Link Type"
+subject = "Subject"
diff --git a/import/sitemap.properties b/import/sitemap.properties
new file mode 100644
index 00000000000..ea7a8eaf76a
--- /dev/null
+++ b/import/sitemap.properties
@@ -0,0 +1,24 @@
+; XSLT Import Settings for sitemaps (used for populating the special website core)
+[General]
+; REQUIRED: Name of XSLT file to apply. Path is relative to the import/xsl directory
+; of the VuFind installation (or your local override directory).
+xslt = sitemap.xsl
+; OPTIONAL: PHP function(s) to register for use within XSLT file. You may repeat
+; this line to register multiple PHP functions.
+;php_function[] = str_replace
+; OPTIONAL: PHP class filled with public static functions for use by the XSLT file.
+; The class must live within a PHP namespace. You may specify a fully-qualified
+; name; if you do not include a namespace, the class will automatically be assumed
+; to live in the \VuFind\XSLT\Import namespace.
+custom_class[] = VuFindSitemap
+; OPTIONAL: If true, all custom_class settings above will be passed to the XSLT with
+; their namespaces stripped off; for example, \VuFind\XSLT\Import\VuFind would be
+; treated as \VuFind in XSLT files. This allows more compact syntax within XSLT
+; files, but it can lead to name conflicts if used carelessly. If set to false, you
+; must use fully-qualified names in your XSLT. The false setting is recommended, but
+; the current default is "true" for compatibility with legacy configurations.
+truncate_custom_class = true
+
+; XSLT parameters -- any key/value pairs set here will be passed as parameters to
+; the XSLT file, allowing local values to be set without modifying XSLT code.
+[Parameters]
diff --git a/import/xsl/sitemap.xsl b/import/xsl/sitemap.xsl
new file mode 100644
index 00000000000..9216aa46713
--- /dev/null
+++ b/import/xsl/sitemap.xsl
@@ -0,0 +1,17 @@
+<!-- XSLT to load sitemap entries into the custom class used for
+ populating the special "website" Solr core -->
+<xsl:stylesheet version="1.0"
+ xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+ xmlns:sitemap="http://www.sitemaps.org/schemas/sitemap/0.9"
+ xmlns:php="http://php.net/xsl">
+ <xsl:output method="xml" indent="yes" encoding="utf-8"/>
+ <xsl:template match="sitemap:urlset">
+ <add>
+ <xsl:for-each select="//sitemap:loc">
+ <doc>
+ <xsl:value-of disable-output-escaping="yes" select="php:function('VuFindSitemap::getDocument', normalize-space(string(.)))"/>
+ </doc>
+ </xsl:for-each>
+ </add>
+ </xsl:template>
+</xsl:stylesheet>
diff --git a/module/VuFind/config/module.config.php b/module/VuFind/config/module.config.php
index 2172f69990f..8d4799bffdd 100644
--- a/module/VuFind/config/module.config.php
+++ b/module/VuFind/config/module.config.php
@@ -108,6 +108,7 @@ $config = array(
'tag' => 'VuFind\Controller\TagController',
'upgrade' => 'VuFind\Controller\UpgradeController',
'vudl' => 'VuFind\Controller\VudlController',
+ 'web' => 'VuFind\Controller\WebController',
'worldcat' => 'VuFind\Controller\WorldcatController',
'worldcatrecord' => 'VuFind\Controller\WorldcatrecordController',
),
@@ -677,6 +678,14 @@ $config = array(
$sm->getServiceLocator()->get('VuFind\Config')->get('searches')
);
},
+ 'solrweb' => function ($sm) {
+ return new \VuFind\RecordDriver\SolrWeb(
+ $sm->getServiceLocator()->get('VuFind\Config')->get('config'),
+ null,
+ $sm->getServiceLocator()->get('VuFind\Config')->get('website'),
+ $sm->getServiceLocator()->get('VuFind\Config')->get('website')
+ );
+ },
'summon' => function ($sm) {
$summon = $sm->getServiceLocator()->get('VuFind\Config')->get('Summon');
$driver = new \VuFind\RecordDriver\Summon(
@@ -816,6 +825,7 @@ $config = array(
'SolrAuth' => 'VuFind\Search\Factory\SolrAuthBackendFactory',
'SolrReserves' => 'VuFind\Search\Factory\SolrReservesBackendFactory',
'SolrStats' => 'VuFind\Search\Factory\SolrStatsBackendFactory',
+ 'SolrWeb' => 'VuFind\Search\Factory\SolrWebBackendFactory',
'Summon' => 'VuFind\Search\Factory\SummonBackendFactory',
'WorldCat' => 'VuFind\Search\Factory\WorldCatBackendFactory',
),
@@ -975,6 +985,7 @@ $staticRoutes = array(
'Upgrade/GetDBCredentials', 'Upgrade/GetDbEncodingPreference',
'Upgrade/GetSourceDir', 'Upgrade/Reset', 'Upgrade/ShowSQL',
'VuDL/Browse', 'VuDL/DSRecord', 'VuDL/Record',
+ 'Web/Home', 'Web/Results',
'Worldcat/Advanced', 'Worldcat/Home', 'Worldcat/Search'
);
diff --git a/module/VuFind/src/VuFind/Controller/WebController.php b/module/VuFind/src/VuFind/Controller/WebController.php
new file mode 100644
index 00000000000..97354395182
--- /dev/null
+++ b/module/VuFind/src/VuFind/Controller/WebController.php
@@ -0,0 +1,61 @@
+<?php
+/**
+ * Web Controller
+ *
+ * PHP version 5
+ *
+ * Copyright (C) Villanova University 2010.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * @category VuFind2
+ * @package Controller
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://vufind.org Main Site
+ */
+namespace VuFind\Controller;
+
+/**
+ * Web Controller
+ *
+ * @category VuFind2
+ * @package Controller
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://vufind.org Main Site
+ */
+class WebController extends AbstractSearch
+{
+ /**
+ * Constructor
+ */
+ public function __construct()
+ {
+ $this->searchClassId = 'SolrWeb';
+ parent::__construct();
+ }
+
+ /**
+ * Home action
+ *
+ * @return \Zend\View\Model\ViewModel
+ */
+ public function homeAction()
+ {
+ // Do nothing -- just display template
+ return $this->createViewModel();
+ }
+}
+
diff --git a/module/VuFind/src/VuFind/RecordDriver/SolrWeb.php b/module/VuFind/src/VuFind/RecordDriver/SolrWeb.php
new file mode 100644
index 00000000000..29cd836f106
--- /dev/null
+++ b/module/VuFind/src/VuFind/RecordDriver/SolrWeb.php
@@ -0,0 +1,77 @@
+<?php
+/**
+ * Model for Solr web records.
+ *
+ * PHP version 5
+ *
+ * Copyright (C) Villanova University 2011.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * @category VuFind2
+ * @package RecordDrivers
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://vufind.org/wiki/vufind2:record_drivers Wiki
+ */
+namespace VuFind\RecordDriver;
+
+/**
+ * Model for Solr web records.
+ *
+ * @category VuFind2
+ * @package RecordDrivers
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://vufind.org/wiki/vufind2:record_drivers Wiki
+ */
+class SolrWeb extends SolrDefault
+{
+ /**
+ * Constructor
+ *
+ * @param \Zend\Config\Config $mainConfig VuFind main configuration (omit for
+ * built-in defaults)
+ * @param \Zend\Config\Config $recordConfig Record-specific configuration file
+ * (omit to use $mainConfig as $recordConfig)
+ * @param \Zend\Config\Config $searchSettings Search-specific configuration file
+ */
+ public function __construct($mainConfig = null, $recordConfig = null,
+ $searchSettings = null
+ ) {
+ $this->preferredSnippetFields = array('description', 'fulltext');
+ parent::__construct($mainConfig, $recordConfig, $searchSettings);
+ }
+
+ /**
+ * Get text that can be displayed to represent this record in
+ * breadcrumbs.
+ *
+ * @return string Breadcrumb text to represent this record.
+ */
+ public function getBreadcrumb()
+ {
+ return $this->getTitle();
+ }
+
+ /**
+ * Get the URL for the current record.
+ *
+ * @return string
+ */
+ public function getUrl()
+ {
+ return $this->fields['url'];
+ }
+}
diff --git a/module/VuFind/src/VuFind/Search/Factory/SolrWebBackendFactory.php b/module/VuFind/src/VuFind/Search/Factory/SolrWebBackendFactory.php
new file mode 100644
index 00000000000..7c6336380d8
--- /dev/null
+++ b/module/VuFind/src/VuFind/Search/Factory/SolrWebBackendFactory.php
@@ -0,0 +1,75 @@
+<?php
+
+/**
+ * Factory for the website SOLR backend.
+ *
+ * PHP version 5
+ *
+ * Copyright (C) Villanova University 2013.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * @category VuFind2
+ * @package Search
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://vufind.org Main Site
+ */
+namespace VuFind\Search\Factory;
+use VuFindSearch\Backend\Solr\Response\Json\RecordCollectionFactory;
+use VuFindSearch\Backend\Solr\Connector;
+
+/**
+ * Factory for the website SOLR backend.
+ *
+ * @category VuFind2
+ * @package Search
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://vufind.org Main Site
+ */
+class SolrWebBackendFactory extends AbstractSolrBackendFactory
+{
+ /**
+ * Constructor
+ */
+ public function __construct()
+ {
+ parent::__construct();
+ $this->solrCore = 'website';
+ $this->searchConfig = 'website';
+ $this->searchYaml = 'websearchspecs.yaml';
+ }
+
+ /**
+ * Create the SOLR backend.
+ *
+ * @param Connector $connector Connector
+ *
+ * @return \VuFindSearch\Backend\Solr\Backend
+ */
+ protected function createBackend(Connector $connector)
+ {
+ $backend = parent::createBackend($connector);
+ $manager = $this->serviceLocator->get('VuFind\RecordDriverPluginManager');
+ $callback = function ($data) use ($manager) {
+ $driver = $manager->get('SolrWeb');
+ $driver->setRawData($data);
+ return $driver;
+ };
+ $factory = new RecordCollectionFactory($callback);
+ $backend->setRecordCollectionFactory($factory);
+ return $backend;
+ }
+}
\ No newline at end of file
diff --git a/module/VuFind/src/VuFind/Search/SolrWeb/Options.php b/module/VuFind/src/VuFind/Search/SolrWeb/Options.php
new file mode 100644
index 00000000000..58ec34db8b6
--- /dev/null
+++ b/module/VuFind/src/VuFind/Search/SolrWeb/Options.php
@@ -0,0 +1,73 @@
+<?php
+/**
+ * Solr Web aspect of the Search Multi-class (Options)
+ *
+ * PHP version 5
+ *
+ * Copyright (C) Villanova University 2011.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * @category VuFind2
+ * @package Search_SolrWeb
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://www.vufind.org Main Page
+ */
+namespace VuFind\Search\SolrWeb;
+
+/**
+ * Solr Web Search Options
+ *
+ * @category VuFind2
+ * @package Search_SolrWeb
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://www.vufind.org Main Page
+ */
+class Options extends \VuFind\Search\Solr\Options
+{
+ /**
+ * Constructor
+ *
+ * @param \VuFind\Config\PluginManager $configLoader Config loader
+ */
+ public function __construct(\VuFind\Config\PluginManager $configLoader)
+ {
+ $this->facetsIni = $this->searchIni = 'website';
+ parent::__construct($configLoader);
+ }
+
+ /**
+ * Return the route name for the search results action.
+ *
+ * @return string
+ */
+ public function getSearchAction()
+ {
+ return 'web-results';
+ }
+
+ /**
+ * Return the route name of the action used for performing advanced searches.
+ * Returns false if the feature is not supported.
+ *
+ * @return string|bool
+ */
+ public function getAdvancedSearchAction()
+ {
+ // Not currently supported:
+ return false;
+ }
+}
\ No newline at end of file
diff --git a/module/VuFind/src/VuFind/Search/SolrWeb/Params.php b/module/VuFind/src/VuFind/Search/SolrWeb/Params.php
new file mode 100644
index 00000000000..f8369390625
--- /dev/null
+++ b/module/VuFind/src/VuFind/Search/SolrWeb/Params.php
@@ -0,0 +1,41 @@
+<?php
+/**
+ * Solr Web aspect of the Search Multi-class (Params)
+ *
+ * PHP version 5
+ *
+ * Copyright (C) Villanova University 2011.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * @category VuFind2
+ * @package Search_SolrWeb
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://www.vufind.org Main Page
+ */
+namespace VuFind\Search\SolrWeb;
+
+/**
+ * Solr Web Search Parameters
+ *
+ * @category VuFind2
+ * @package Search_SolrWeb
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://www.vufind.org Main Page
+ */
+class Params extends \VuFind\Search\Solr\Params
+{
+}
\ No newline at end of file
diff --git a/module/VuFind/src/VuFind/Search/SolrWeb/Results.php b/module/VuFind/src/VuFind/Search/SolrWeb/Results.php
new file mode 100644
index 00000000000..4b8c9b41116
--- /dev/null
+++ b/module/VuFind/src/VuFind/Search/SolrWeb/Results.php
@@ -0,0 +1,52 @@
+<?php
+/**
+ * Solr Web aspect of the Search Multi-class (Results)
+ *
+ * PHP version 5
+ *
+ * Copyright (C) Villanova University 2011.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * @category VuFind2
+ * @package Search_SolrWeb
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://www.vufind.org Main Page
+ */
+namespace VuFind\Search\SolrWeb;
+
+/**
+ * Solr Web Search Parameters
+ *
+ * @category VuFind2
+ * @package Search_SolrWeb
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://www.vufind.org Main Page
+ */
+class Results extends \VuFind\Search\Solr\Results
+{
+ /**
+ * Constructor
+ *
+ * @param \VuFind\Search\Base\Params $params Object representing user search
+ * parameters.
+ */
+ public function __construct(\VuFind\Search\Base\Params $params)
+ {
+ parent::__construct($params);
+ $this->backendId = 'SolrWeb';
+ }
+}
\ No newline at end of file
diff --git a/module/VuFind/src/VuFind/XSLT/Import/VuFindSitemap.php b/module/VuFind/src/VuFind/XSLT/Import/VuFindSitemap.php
new file mode 100644
index 00000000000..cad65240405
--- /dev/null
+++ b/module/VuFind/src/VuFind/XSLT/Import/VuFindSitemap.php
@@ -0,0 +1,257 @@
+<?php
+/**
+ * XSLT importer support methods for sitemaps.
+ *
+ * PHP version 5
+ *
+ * Copyright (c) Demian Katz 2010.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * @category VuFind2
+ * @package Import_Tools
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://vufind.org/wiki/importing_records Wiki
+ */
+namespace VuFind\XSLT\Import;
+
+/**
+ * XSLT support class -- all methods of this class must be public and static;
+ * they will be automatically made available to your XSL stylesheet for use
+ * with the php:function() function.
+ *
+ * @category VuFind2
+ * @package Import_Tools
+ * @author Demian Katz <demian.katz@villanova.edu>
+ * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License
+ * @link http://vufind.org/wiki/importing_records Wiki
+ */
+class VuFindSitemap extends VuFind
+{
+ /**
+ * Load metadata about an HTML document using Aperture.
+ *
+ * @param string $htmlFile File on disk containing HTML.
+ *
+ * @return array
+ */
+ protected static function getApertureFields($htmlFile)
+ {
+ $xmlFile = tempnam('/tmp', 'apt');
+ $cmd = static::getApertureCommand($htmlFile, $xmlFile, 'filecrawler');
+ exec($cmd);
+
+ // If we failed to process the file, give up now:
+ if (!file_exists($xmlFile)) {
+ throw new \Exception('Aperture failed.');
+ }
+
+ // Extract and decode the full text from the XML:
+ $xml = file_get_contents($xmlFile);
+ @unlink($xmlFile);
+ preg_match('/<plainTextContent[^>]*>([^<]*)</ms', $xml, $matches);
+ $final = isset($matches[1]) ?
+ html_entity_decode($matches[1], ENT_QUOTES, 'UTF-8') : '';
+
+ // Extract the title from the XML:
+ preg_match('/<title[^>]*>([^<]*)</ms', $xml, $matches);
+ $title = isset($matches[1]) ?
+ html_entity_decode($matches[1], ENT_QUOTES, 'UTF-8') : '';
+
+ // Extract the keywords from the XML:
+ preg_match_all('/<keyword[^>]*>([^<]*)</ms', $xml, $matches);
+ $keywords = array();
+ if (isset($matches[1])) {
+ foreach($matches[1] as $current) {
+ $keywords[] = html_entity_decode($current, ENT_QUOTES, 'UTF-8');
+ }
+ }
+
+ // Extract the description from the XML:
+ preg_match('/<description[^>]*>([^<]*)</ms', $xml, $matches);
+ $description = isset($matches[1])
+ ? html_entity_decode($matches[1], ENT_QUOTES, 'UTF-8') : '';
+
+ // Send back the extracted fields:
+ return array(
+ 'title' => $title,
+ 'keywords' => $keywords,
+ 'description' => $description,
+ 'fulltext' => $final,
+ );
+ }
+
+ /**
+ * Load metadata about an HTML document using Tika.
+ *
+ * @param string $htmlFile File on disk containing HTML.
+ *
+ * @return array
+ */
+ protected static function getTikaFields($htmlFile)
+ {
+ // Extract and decode the full text from the XML:
+ $xml = static::harvestWithTika($htmlFile, '--xml');
+
+ // Extract the title from the XML:
+ preg_match('/<title[^>]*>([^<]*)</ms', $xml, $matches);
+ $title = isset($matches[1]) ?
+ html_entity_decode($matches[1], ENT_QUOTES, 'UTF-8') : '';
+
+ // Extract the keywords from the XML:
+ preg_match_all(
+ '/<meta name="keywords" content="([^"]*)"/ms', $xml, $matches
+ );
+ $keywords = array();
+ if (isset($matches[1])) {
+ foreach($matches[1] as $current) {
+ $keywords[] = html_entity_decode($current, ENT_QUOTES, 'UTF-8');
+ }
+ }
+
+ // Extract the description from the XML:
+ preg_match('/<meta name="description" content="([^"]*)"/ms', $xml, $matches);
+ $description = isset($matches[1])
+ ? html_entity_decode($matches[1], ENT_QUOTES, 'UTF-8') : '';
+
+ // Send back the extracted fields:
+ return array(
+ 'title' => $title,
+ 'keywords' => $keywords,
+ 'description' => $description,
+ 'fulltext' => $title . ' ' . static::harvestWithTika($htmlFile),
+ );
+ }
+
+ /**
+ * Extract key metadata from HTML.
+ *
+ * @param string $html HTML content.
+ *
+ * @return array
+ */
+ protected static function getHtmlFields($html)
+ {
+ // Extract the subjects from the HTML:
+ preg_match_all('/<meta name="subject" content="([^"]*)"/ms', $html, $matches);
+ $subjects = array();
+ if (isset($matches[1])) {
+ foreach($matches[1] as $current) {
+ $subjects[] = html_entity_decode($current, ENT_QUOTES, 'UTF-8');
+ }
+ }
+
+ // Extract the link types from the HTML:
+ preg_match_all('/<meta name="category" content="([^"]*)"/ms', $html, $matches);
+ $categories = array();
+ if (isset($matches[1])) {
+ foreach($matches[1] as $current) {
+ $categories[] = html_entity_decode($current, ENT_QUOTES, 'UTF-8');
+ }
+ }
+
+ // Extract the use count from the HTML:
+ preg_match_all('/<meta name="useCount" content="([^"]*)"/ms', $html, $matches);
+ $linkTypes = array();
+ $useCount = isset($matches[1][0]) ? $matches[1][0] : 1;
+
+ return array(
+ 'category' => $categories,
+ 'subject' => $subjects,
+ 'use_count' => $useCount,
+ );
+ }
+
+ /**
+ * Convert an associative array of fields into a Solr document.
+ *
+ * @param array $fields Field data
+ *
+ * @return string
+ */
+ public static function arrayToSolrXml($fields)
+ {
+ $xml = '';
+ foreach ($fields as $key => $value) {
+ $value = is_array($value) ? $value : array($value);
+ foreach ($value as $current) {
+ if (!empty($current)) {
+ $xml .= '<field name="' . $key . '">'
+ . htmlspecialchars($current) . '</field>';
+ }
+ }
+ }
+ return $xml;
+ }
+
+ /**
+ * Harvest the contents of a document file (PDF, Word, etc.) using Aperture.
+ * This method will only work if Aperture is properly configured in the
+ * web/conf/fulltext.ini file. Without proper configuration, this will
+ * simply return an empty string.
+ *
+ * @param string $url URL of file to retrieve.
+ *
+ * @return string text contents of file.
+ * @access public
+ */
+ public static function getDocument($url)
+ {
+ $parser = static::getParser();
+ if ($parser == 'None') {
+ return '';
+ }
+
+ // Grab the HTML and write it to disk:
+ $htmlFile = tempnam('/tmp', 'htm');
+ $html = file_get_contents($url);
+ file_put_contents($htmlFile, $html);
+
+ // Use the appropriate full text parser:
+ switch ($parser) {
+ case 'Aperture':
+ $fields = static::getApertureFields($htmlFile);
+ break;
+ case 'Tika':
+ $fields = static::getTikaFields($htmlFile);
+ break;
+ default:
+ throw new \Exception('Unexpected parser: ' . $parser);
+ }
+
+ // Clean up HTML file:
+ @unlink($htmlFile);
+
+ // Add data loaded directly from HTML:
+ $fields += static::getHtmlFields($html);
+
+ // Clean up/normalize full text:
+ $fields['fulltext'] = trim(
+ preg_replace(
+ '/\s+/', ' ', static::stripBadChars($fields['fulltext'])
+ )
+ );
+
+ // Use a hash of the URL for the ID:
+ $fields['id'] = md5($url);
+
+ // Add other key values:
+ $fields['url'] = $url;
+ $fields['last_indexed'] = date('Y-m-d\TH:i:s\Z');
+
+ // Turn the array into XML:
+ return static::arrayToSolrXml($fields);
+ }
+}
diff --git a/solr/solr.xml b/solr/solr.xml
index 694a3c36eb6..41f6d035aef 100644
--- a/solr/solr.xml
+++ b/solr/solr.xml
@@ -3,6 +3,7 @@
<core name="biblio" instanceDir="biblio"/>
<core name="authority" instanceDir="authority"/>
<core name="stats" instanceDir="stats"/>
+ <!-- uncomment to enable website core: <core name="website" instanceDir="website"/> -->
<!-- uncomment to enable reserves core: <core name="reserves" instanceDir="reserves"/> -->
</cores>
</solr>
diff --git a/solr/website/conf/elevate.xml b/solr/website/conf/elevate.xml
new file mode 100644
index 00000000000..b5ccaaea785
--- /dev/null
+++ b/solr/website/conf/elevate.xml
@@ -0,0 +1,25 @@
+<?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>
+</elevate>
diff --git a/solr/website/conf/protwords.txt b/solr/website/conf/protwords.txt
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/solr/website/conf/schema.xml b/solr/website/conf/schema.xml
new file mode 100644
index 00000000000..7931461bada
--- /dev/null
+++ b/solr/website/conf/schema.xml
@@ -0,0 +1,152 @@
+<?xml version="1.0" ?>
+<schema name="VuFind Website Index" version="1.2">
+ <types>
+ <!-- Define fieldType long as it is needed by the _version_ field required by Solr 4.x -->
+ <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
+ <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
+ <fieldType name="textFacet" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+ <analyzer>
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <!-- strip trailing punctuation from facets: -->
+ <filter class="solr.PatternReplaceFilterFactory" pattern="(?<!\b[A-Z])[.\s]*$" replacement="" replace="first"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="English"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="English"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <!-- Text Field without Stemming and Synonyms -->
+ <fieldType name="textProper" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <!-- Basic Text Field for use with Spell Correction -->
+ <fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <!-- More advanced spell checking field. -->
+ <fieldType name="textSpellShingle" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
+ <filter class="solr.ShingleFilterFactory" maxShingleSize="2" outputUnigrams="false"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
+ <filter class="solr.ShingleFilterFactory" maxShingleSize="2" outputUnigrams="false"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <!-- Text Field for Normalized ISBN/ISSN Numbers - take first chunk of text
+ prior to whitespace, force to lowercase, strip non-ISBN/ISSN characters,
+ omit results that are empty after stripping. -->
+ <fieldType name="isn" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.PatternTokenizerFactory" pattern="^(\S*)\s*.*$" group="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.PatternReplaceFilterFactory" pattern="[^0-9x]" replacement="" replace="all"/>
+ <filter class="solr.LengthFilterFactory" min="1" max="100" />
+ </analyzer>
+ </fieldType>
+ <fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
+ </types>
+ <fields>
+ <!-- Required by Solr 4.x -->
+ <field name="_version_" type="long" indexed="true" stored="true"/>
+ <!-- Core Fields -->
+ <field name="id" type="string" indexed="true" stored="true"/>
+ <field name="fulltext" type="text" indexed="true" stored="true"/>
+ <field name="fulltext_unstemmed" type="textProper" indexed="true" stored="false"/>
+ <field name="description" type="text" indexed="true" stored="true"/>
+ <field name="description_unstemmed" type="textProper" indexed="true" stored="false"/>
+ <field name="keywords" type="text" indexed="true" stored="true" multiValued="true"/>
+ <field name="keywords_unstemmed" type="textProper" indexed="true" stored="false" multiValued="true"/>
+ <field name="spelling" type="textSpell" indexed="true" stored="true"/>
+ <field name="spellingShingle" type="textSpellShingle" indexed="true" stored="true" multiValued="true"/>
+ <field name="last_indexed" type="date" indexed="true" stored="true"/>
+ <field name="title" type="text" indexed="true" stored="true"/>
+ <field name="title_sort" type="string" indexed="true" stored="false"/>
+ <field name="url" type="string" indexed="false" stored="true"/>
+ <field name="url_keywords" type="text" indexed="true" stored="false"/>
+ <!-- Popularity of page - can be used in function query for weighting -->
+ <field name="use_count" type="sint" indexed="true" stored="true"/>
+ <!-- Facet Fields -->
+ <field name="category" type="textFacet" indexed="true" stored="true" multiValued="true"/>
+ <field name="linktype" type="textFacet" indexed="true" stored="true" multiValued="true"/>
+ <field name="subject" type="textFacet" indexed="true" stored="true" multiValued="true"/>
+ <!-- Dynamic fields for customization without schema modification -->
+ <dynamicField name="*_date" type="date" indexed="true" stored="true"/>
+ <dynamicField name="*_date_mv" type="date" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_isn" type="isn" indexed="true" stored="true"/>
+ <dynamicField name="*_isn_mv" type="isn" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_str" type="string" indexed="true" stored="true"/>
+ <dynamicField name="*_str_mv" type="string" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_txt" type="text" indexed="true" stored="true"/>
+ <dynamicField name="*_txt_mv" type="text" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_txtF" type="textFacet" indexed="true" stored="true"/>
+ <dynamicField name="*_txtF_mv" type="textFacet" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_txtP" type="textProper" indexed="true" stored="true"/>
+ <dynamicField name="*_txtP_mv" type="textProper" indexed="true" stored="true" multiValued="true"/>
+ </fields>
+ <uniqueKey>id</uniqueKey>
+ <defaultSearchField>fulltext</defaultSearchField>
+ <!-- CopyFields for Spelling -->
+ <copyField source="title" dest="spellingShingle"/>
+ <!-- Copy title information to special field for sorting -->
+ <copyField source="title" dest="title_sort"/>
+ <!-- CopyFields to allow keyword searching within URL -->
+ <copyField source="url" dest="url_keywords"/>
+ <!-- CopyFields for unstemmed searching -->
+ <copyField source="fulltext" dest="fulltext_unstemmed"/>
+ <copyField source="description" dest="description_unstemmed"/>
+ <copyField source="keywords" dest="keywords_unstemmed"/>
+ <!-- CopyFields to treat category metadata as additional keywords -->
+ <copyField source="category" dest="keywords" />
+ <copyField source="subject" dest="keywords" />
+ <copyField source="linktype" dest="keywords" />
+ <copyField source="category" dest="keywords_unstemmed" />
+ <copyField source="subject" dest="keywords_unstemmed" />
+ <copyField source="linktype" dest="keywords_unstemmed" />
+ <!-- Default Boolean Operator -->
+ <solrQueryParser defaultOperator="AND"/>
+</schema>
diff --git a/solr/website/conf/solrconfig.xml b/solr/website/conf/solrconfig.xml
new file mode 100644
index 00000000000..ffe23d65132
--- /dev/null
+++ b/solr/website/conf/solrconfig.xml
@@ -0,0 +1,676 @@
+<?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.
+-->
+
+<config>
+ <!-- Set this to 'false' if you want solr to continue working after it has
+ encountered an severe configuration error. In a production environment,
+ you may want solr to keep working even if one handler is mis-configured.
+
+ You may also set this to false using by setting the system property:
+ -Dsolr.abortOnConfigurationError=false
+ -->
+ <abortOnConfigurationError>${solr.abortOnConfigurationError:false}</abortOnConfigurationError>
+
+ <!-- Controls what version of Lucene various components of Solr
+ adhere to. Generally, you want to use the latest version to
+ get all bug fixes and improvements. It is highly recommended
+ that you fully re-index after changing this setting as it can
+ affect both how text is indexed and queried.
+ -->
+ <luceneMatchVersion>LUCENE_42</luceneMatchVersion>
+
+ <!-- Used to specify an alternate directory to hold all index data
+ other than the default ./data under the Solr home.
+ If replication is in use, this should match the replication configuration. -->
+ <dataDir>${solr.solr.home:./solr}/website</dataDir>
+
+
+ <indexConfig>
+
+ <useCompoundFile>false</useCompoundFile>
+
+ <mergeFactor>10</mergeFactor>
+
+
+ <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+ indexing for buffering added documents and deletions before they are
+ flushed to the Directory.
+ maxBufferedDocs sets a limit on the number of documents buffered
+ before flushing.
+ If both ramBufferSizeMB and maxBufferedDocs is set, then
+ Lucene will flush based on whichever limit is hit first. -->
+ <ramBufferSizeMB>100</ramBufferSizeMB>
+ <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+
+
+ <!-- Commit Deletion Policy
+
+ Custom deletion policies can be specified here. The class must
+ implement org.apache.lucene.index.IndexDeletionPolicy.
+
+ http://lucene.apache.org/java/3_5_0/api/core/org/apache/lucene/index/IndexDeletionPolicy.html
+
+ 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">
+ <!-- Keep only optimized commit points -->
+ <str name="keepOptimizedOnly">false</str>
+ <!-- The maximum number of commit points to be kept -->
+ <str name="maxCommitsToKeep">1</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>
+
+ </indexConfig>
+
+ <!-- Enables JMX if and only if an existing MBeanServer is found, use
+ this if you want to configure JMX through JVM parameters. Remove
+ this to disable exposing Solr configuration and statistics to JMX.
+
+ If you want to connect to a particular server, specify the agentId
+ e.g. <jmx agentId="myAgent" />
+
+ If you want to start a new MBeanServer, specify the serviceUrl
+ e.g <jmx serviceurl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr" />
+
+ For more details see http://wiki.apache.org/solr/SolrJmx
+ -->
+ <jmx />
+
+ <!-- the default high-performance update handler -->
+ <updateHandler class="solr.DirectUpdateHandler2">
+
+
+ <!-- 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>
+
+ <!-- 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)
+ -->
+
+ <!-- Perform a <commit/> automatically under certain conditions:
+ maxDocs - number of updates since last commit is greater than this
+ maxTime - oldest uncommited update (in ms) is this long ago
+ -->
+ <autoCommit>
+ <maxTime>15000</maxTime>
+ <openSearcher>false</openSearcher>
+ </autoCommit>
+
+ <!-- The RunExecutableListener executes an external command.
+ 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=nothing
+ env - environment variables to set. default=nothing
+ -->
+ <!-- A postCommit event is fired after every commit or optimize command
+ <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>
+ -->
+ <!-- A postOptimize event is fired only after every optimize command, useful
+ in conjunction with index distribution to only distribute optimized indicies
+ <listener event="postOptimize" class="solr.RunExecutableListener">
+ <str name="exe">snapshooter</str>
+ <str name="dir">solr/bin</str>
+ <bool name="wait">true</bool>
+ </listener>
+ -->
+
+ </updateHandler>
+
+
+ <query>
+ <!-- Maximum number of clauses in a boolean query... can affect
+ range or prefix queries that expand to big boolean
+ queries. An exception is thrown if exceeded. -->
+ <maxBooleanClauses>1024</maxBooleanClauses>
+
+
+ <!-- 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 (currently only LRUCache)
+ size - the maximum number of entries in the cache
+ initialSize - the initial capacity (number of entries) of
+ the cache. (seel java.util.HashMap)
+ autowarmCount - the number of entries to prepopulate from
+ and old cache.
+ -->
+ <filterCache
+ class="solr.FastLRUCache"
+ size="300000"
+ initialSize="300000"
+ autowarmCount="50000"/>
+
+ <!-- queryResultCache 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="100000"
+ initialSize="100000"
+ autowarmCount="50000"/>
+
+ <!-- documentCache 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="50000"
+ initialSize="50000"
+ autowarmCount="10000"/>
+
+ <!-- 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>
+
+ <!-- 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.search.CacheRegenerator if autowarming is desired. -->
+ <!--
+ <cache name="myUserCache"
+ class="solr.LRUCache"
+ size="4096"
+ initialSize="1024"
+ autowarmCount="1024"
+ regenerator="org.mycompany.mypackage.MyRegenerator"
+ />
+ -->
+
+ <!-- An 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.
+ <useFilterForSortedQuery>true</useFilterForSortedQuery>
+ -->
+
+ <!-- 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>50</queryResultWindowSize>
+
+ <!-- Maximum number of documents to cache for any entry in the
+ queryResultCache. -->
+ <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+ <!-- This entry enables an int hash representation for filters (DocSets)
+ when the number of items in the set is less than maxSize. For smaller
+ sets, this representation is more memory efficient, more efficient to
+ iterate over, and faster to take intersections. -->
+ <HashDocSet maxSize="3000" loadFactor="0.75"/>
+
+ <!-- a newSearcher event is fired whenever a new searcher is being prepared
+ and there is a current searcher handling requests (aka registered). -->
+ <!-- QuerySenderListener takes an array of NamedList and executes a
+ local query request for each NamedList in sequence. -->
+ <listener event="newSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <lst>
+ <str name="q">science art business engineering history</str>
+ <str name="start">0</str>
+ <str name="rows">10</str>
+ </lst>
+ </arr>
+ </listener>
+
+ <!-- a firstSearcher event is fired whenever a new searcher is being
+ prepared but there is no current registered searcher to handle
+ requests or to gain autowarming data from. -->
+ <listener event="firstSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <lst>
+ <str name="q">science art business engineering history</str>
+ <!--
+ <str name="facet.field">format</str>
+ <str name="fq">format:book</str>
+ -->
+ </lst>
+ </arr>
+ </listener>
+
+ <!-- If a search request comes in and there is no current registered searcher,
+ then immediately register the still warming searcher and use it. If
+ "false" then all requests will block until the first searcher is done
+ warming. -->
+ <useColdSearcher>false</useColdSearcher>
+
+ <!-- Maximum number of searchers that may be warming in the background
+ concurrently. An error is returned if this limit is exceeded. Recommend
+ 1-2 for read-only slaves, higher for masters w/o cache warming. -->
+ <maxWarmingSearchers>2</maxWarmingSearchers>
+
+ </query>
+
+ <!--
+ Let the dispatch filter handler /select?qt=XXX
+ handleSelect=true will use consistent error handling for /select and /update
+ handleSelect=false will use solr1.1 style error formatting
+ -->
+ <requestDispatcher handleSelect="true" >
+ <!--Make sure your system has some authentication before enabling remote streaming! -->
+ <requestParsers enableRemoteStreaming="true"
+ multipartUploadLimitInKB="2048000"
+ formdataUploadLimitInKB="2048"/>
+
+ <!-- Set HTTP caching related parameters (for proxy caches and clients).
+
+ To get the behaviour of Solr 1.2 (ie: no caching related headers)
+ use the never304="true" option and do not specify a value for
+ <cacheControl>
+ -->
+ <!-- <httpCaching never304="true"> -->
+ <httpCaching lastModifiedFrom="openTime"
+ etagSeed="Solr">
+ <!-- lastModFrom="openTime" is the default, the Last-Modified value
+ (and validation against If-Modified-Since requests) will all be
+ relative to when the current Searcher was opened.
+ You can change it to lastModFrom="dirLastMod" if you want the
+ value to exactly corrispond to when the physical index was last
+ modified.
+
+ etagSeed="..." is an option you can change to force the ETag
+ header (and validation against If-None-Match requests) to be
+ differnet even if the index has not changed (ie: when making
+ significant changes to your config file)
+
+ lastModifiedFrom and etagSeed are both ignored if you use the
+ never304="true" option.
+ -->
+ <!-- If you include a <cacheControl> directive, it will be used to
+ generate a Cache-Control header, as well as an Expires header
+ if the value contains "max-age="
+
+ By default, no Cache-Control header is generated.
+
+ You can use the <cacheControl> option even if you have set
+ never304="true"
+ -->
+ <!-- <cacheControl>max-age=30, public</cacheControl> -->
+ </httpCaching>
+ </requestDispatcher>
+
+
+ <!-- requestHandler plugins... incoming queries will be dispatched to the
+ correct handler based on the path or the qt (query type) param.
+ Names starting with a '/' are accessed with the a path equal to the
+ registered name. Names without a leading '/' are accessed with:
+ http://host/app/select?qt=name
+ If no qt is defined, the requestHandler that declares default="true"
+ will be used.
+ -->
+ <requestHandler name="standard" class="solr.StandardRequestHandler" default="true">
+ <!-- default values for query parameters -->
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <!--
+ <int name="rows">10</int>
+ <str name="fl">*</str>
+ <str name="version">2.1</str>
+ -->
+ <str name="spellcheck.extendedResults">true</str>
+ <str name="spellcheck.onlyMorePopular">true</str>
+ <str name="spellcheck.count">20</str>
+ </lst>
+ <arr name="last-components">
+ <str>spellcheck</str>
+ </arr>
+ </requestHandler>
+
+ <!-- the following handler will be used for eligible dismax searches defined
+ in web/conf/searchspecs.yaml. Searches relying on advanced features
+ incompatible with dismax will be sent to the standard handler instead.
+ You can use this handler definition to set global Dismax settings
+ (i.e. mm / bf). If you need different settings for different types of
+ searches (i.e. Title vs. Author), you can also configure individual
+ settings in the searchspecs.yaml file.
+ -->
+ <requestHandler name="dismax" class="solr.SearchHandler">
+ <lst name="defaults">
+ <str name="defType">dismax</str>
+ <str name="echoParams">explicit</str>
+ <str name="spellcheck.extendedResults">true</str>
+ <str name="spellcheck.onlyMorePopular">true</str>
+ <str name="spellcheck.count">20</str>
+ </lst>
+ <arr name="last-components">
+ <str>spellcheck</str>
+ </arr>
+ </requestHandler>
+
+ <searchComponent name="spellcheck" class="org.apache.solr.handler.component.SpellCheckComponent">
+ <lst name="spellchecker">
+ <str name="name">default</str>
+ <str name="field">spellingShingle</str>
+ <str name="accuracy">0.75</str>
+ <str name="spellcheckIndexDir">./spellShingle</str>
+ <str name="queryAnalyzerFieldType">textSpellShingle</str>
+ <str name="buildOnOptimize">true</str>
+ </lst>
+ <lst name="spellchecker">
+ <str name="name">basicSpell</str>
+ <str name="field">spelling</str>
+ <str name="accuracy">0.75</str>
+ <str name="spellcheckIndexDir">./spellchecker</str>
+ <str name="queryAnalyzerFieldType">textSpell</str>
+ <str name="buildOnOptimize">true</str>
+ </lst>
+ </searchComponent>
+ <queryConverter name="queryConverter" class="org.apache.solr.spelling.SpellingQueryConverter"/>
+
+ <!-- Search component for extracting terms (useful for sitemap generation) -->
+ <searchComponent name="term" class="org.apache.solr.handler.component.TermsComponent">
+ </searchComponent>
+
+ <!--
+
+ Search components are registered to SolrCore and used by Search Handlers
+
+ By default, the following components are avaliable:
+
+ <searchComponent name="query" class="org.apache.solr.handler.component.QueryComponent" />
+ <searchComponent name="facet" class="org.apache.solr.handler.component.FacetComponent" />
+ <searchComponent name="mlt" class="org.apache.solr.handler.component.MoreLikeThisComponent" />
+ <searchComponent name="highlight" class="org.apache.solr.handler.component.HighlightComponent" />
+ <searchComponent name="stats" class="org.apache.solr.handler.component.StatsComponent" />
+ <searchComponent name="debug" class="org.apache.solr.handler.component.DebugComponent" />
+
+ If you register a searchComponent to one of the standard names, that will be used instead.
+
+ -->
+
+ <requestHandler name="/search" class="org.apache.solr.handler.component.SearchHandler">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ </lst>
+ <!--
+ By default, this will register the following components:
+
+ <arr name="components">
+ <str>query</str>
+ <str>facet</str>
+ <str>mlt</str>
+ <str>highlight</str>
+ <str>debug</str>
+ </arr>
+
+ To insert handlers before or after the 'standard' components, use:
+
+ <arr name="first-components">
+ <str>first</str>
+ </arr>
+
+ <arr name="last-components">
+ <str>last</str>
+ </arr>
+
+ -->
+ <arr name="last-components">
+ <str>spellcheck</str>
+ <str>elevator</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Request handler to extract terms (useful for sitemap generation) -->
+ <requestHandler name="/term" class="org.apache.solr.handler.component.SearchHandler">
+ <arr name="components">
+ <str>term</str>
+ </arr>
+ </requestHandler>
+
+ <searchComponent name="elevator" class="org.apache.solr.handler.component.QueryElevationComponent" >
+ <!-- pick a fieldType to analyze queries -->
+ <str name="queryFieldType">string</str>
+ <str name="config-file">elevate.xml</str>
+ </searchComponent>
+
+ <requestHandler name="/elevate" class="org.apache.solr.handler.component.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ </lst>
+ <arr name="last-components">
+ <str>elevator</str>
+ </arr>
+ </requestHandler>
+
+
+
+ <!-- Update request handler.
+
+ Note: Since solr1.1 requestHandlers requires a valid content type header if posted in
+ the body. For example, curl now requires: -H 'Content-type:text/xml; charset=utf-8'
+ The response format differs from solr1.1 formatting and returns a standard error code.
+
+ To enable solr1.1 behavior, remove the /update handler or change its path
+ -->
+ <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>
+ <requestHandler name="/update/json" class="solr.JsonUpdateRequestHandler"/>
+
+ <!-- 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" />
+
+
+ <!-- CSV update handler, loaded on demand -->
+ <requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy" />
+
+
+ <!--
+ Admin Handlers - This will register all the standard admin RequestHandlers. Adding
+ this single handler is equivolent to registering:
+
+ <requestHandler name="/admin/luke" class="org.apache.solr.handler.admin.LukeRequestHandler" />
+ <requestHandler name="/admin/system" class="org.apache.solr.handler.admin.SystemInfoHandler" />
+ <requestHandler name="/admin/plugins" class="org.apache.solr.handler.admin.PluginInfoHandler" />
+ <requestHandler name="/admin/threads" class="org.apache.solr.handler.admin.ThreadDumpHandler" />
+ <requestHandler name="/admin/properties" class="org.apache.solr.handler.admin.PropertiesRequestHandler" />
+ <requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" >
+
+ If you wish to hide files under ${solr.home}/conf, explicitly register the ShowFileRequestHandler using:
+ <requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" >
+ <lst name="invariants">
+ <str name="hidden">synonyms.txt</str>
+ <str name="hidden">anotherfile.txt</str>
+ </lst>
+ </requestHandler>
+ -->
+ <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
+
+ <!-- ping/healthcheck -->
+ <requestHandler name="/admin/ping" class="PingRequestHandler">
+ <lst name="defaults">
+ <str name="qt">standard</str>
+ <str name="q">solrpingquery</str>
+ <str name="echoParams">all</str>
+ </lst>
+ </requestHandler>
+
+ <!-- Echo the request contents back to the client -->
+ <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
+ <lst name="defaults">
+ <str name="echoParams">explicit</str> <!-- for all params (including the default etc) use: 'all' -->
+ <str name="echoHandler">true</str>
+ </lst>
+ </requestHandler>
+
+ <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" class="org.apache.solr.highlight.GapFragmenter" default="true">
+ <lst name="defaults">
+ <int name="hl.fragsize">100</int>
+ </lst>
+ </fragmenter>
+
+ <!-- A regular-expression-based fragmenter (f.i., for sentence extraction) -->
+ <fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
+ <lst name="defaults">
+ <!-- slightly smaller fragsizes work better because of slop -->
+ <int name="hl.fragsize">70</int>
+ <!-- allow 50% slop on fragment sizes -->
+ <float name="hl.regex.slop">0.5</float>
+ <!-- a basic sentence pattern -->
+ <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
+ </lst>
+ </fragmenter>
+
+ <!-- Configure the standard formatter -->
+ <formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
+ <lst name="defaults">
+ <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+ <str name="hl.simple.post"><![CDATA[</em>]]></str>
+ </lst>
+ </formatter>
+ </highlighting>
+ </searchComponent>
+
+ <!-- queryResponseWriter plugins... query 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. XMLResponseWriter will be used if nothing is specified here.
+ The json, python, and ruby writers are also available by default.
+
+ <queryResponseWriter name="xml" class="org.apache.solr.request.XMLResponseWriter" default="true"/>
+ <queryResponseWriter name="json" class="org.apache.solr.request.JSONResponseWriter"/>
+ <queryResponseWriter name="python" class="org.apache.solr.request.PythonResponseWriter"/>
+ <queryResponseWriter name="ruby" class="org.apache.solr.request.RubyResponseWriter"/>
+ <queryResponseWriter name="php" class="org.apache.solr.request.PHPResponseWriter"/>
+ <queryResponseWriter name="phps" class="org.apache.solr.request.PHPSerializedResponseWriter"/>
+
+ <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
+ -->
+
+ <!-- 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="org.apache.solr.response.XSLTResponseWriter">
+ <int name="xsltCacheLifetimeSeconds">5</int>
+ </queryResponseWriter>
+
+ <!-- config for the admin interface -->
+ <admin>
+ <defaultQuery>shakespeare</defaultQuery>
+
+ <!-- configure a healthcheck file for servers behind a loadbalancer
+ <healthcheck type="file">server-enabled</healthcheck>
+ -->
+ </admin>
+
+</config>
diff --git a/solr/website/conf/stopwords.txt b/solr/website/conf/stopwords.txt
new file mode 100644
index 00000000000..40a5a5fa2f1
--- /dev/null
+++ b/solr/website/conf/stopwords.txt
@@ -0,0 +1,34 @@
+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
\ No newline at end of file
diff --git a/solr/website/conf/synonyms.txt b/solr/website/conf/synonyms.txt
new file mode 100644
index 00000000000..29b05690f1a
--- /dev/null
+++ b/solr/website/conf/synonyms.txt
@@ -0,0 +1,5 @@
+I,i,1,one,One
+II,ii,2,two,Two
+III,iii,3,three,Three
+IV,iv,4,four,Four
+V,v,5,five,Five
\ No newline at end of file
diff --git a/themes/blueprint/templates/RecordDriver/SolrWeb/result-list.phtml b/themes/blueprint/templates/RecordDriver/SolrWeb/result-list.phtml
new file mode 100644
index 00000000000..5eb814bac99
--- /dev/null
+++ b/themes/blueprint/templates/RecordDriver/SolrWeb/result-list.phtml
@@ -0,0 +1,33 @@
+<?
+ $url = $this->driver->getUrl();
+?>
+<div class="listentry span-15">
+ <div class="resultItemLine1">
+ <a href="<?=$this->escapeHtml($url)?>" class="title"><?
+ $summHighlightedTitle = $this->driver->getHighlightedTitle();
+ $summTitle = $this->driver->getTitle();
+ if (!empty($summHighlightedTitle)) {
+ echo $this->highlight($this->addEllipsis($summHighlightedTitle, $summTitle));
+ } else if (!empty($summTitle)) {
+ echo $this->escapeHtml($this->truncate($summTitle, 180));
+ } else {
+ echo $this->transEsc('Title not available');
+ }
+ ?></a>
+ </div>
+
+ <div class="resultItemLine2">
+ <? $snippet = $this->driver->getHighlightedSnippet(); ?>
+ <? $summary = $this->driver->getSummary(); ?>
+ <? if (!empty($snippet)): ?>
+ <?=$this->highlight($snippet['snippet'])?>
+ <? elseif (!empty($summary)): ?>
+ <?=$this->escapeHtml($summary[0])?>
+ <? endif; ?>
+ </div>
+
+ <div class="resultItemLine3">
+ <span style="color:#008000;" class="ui-li-desc"><?=$this->escapeHtml($url)?></span>
+ </div>
+</div>
+<div class="clearer"></div>
\ No newline at end of file
diff --git a/themes/blueprint/templates/web/home.phtml b/themes/blueprint/templates/web/home.phtml
new file mode 100644
index 00000000000..d13d4348c1e
--- /dev/null
+++ b/themes/blueprint/templates/web/home.phtml
@@ -0,0 +1 @@
+<?=$this->render('search/home.phtml');?>
\ No newline at end of file
diff --git a/themes/blueprint/templates/web/results.phtml b/themes/blueprint/templates/web/results.phtml
new file mode 100644
index 00000000000..dd801a58a86
--- /dev/null
+++ b/themes/blueprint/templates/web/results.phtml
@@ -0,0 +1,5 @@
+<?
+ // Load standard settings from the default search results screen:
+ $this->hideCartControls = true;
+ echo $this->render('search/results.phtml');
+?>
\ No newline at end of file
diff --git a/themes/jquerymobile/templates/RecordDriver/SolrWeb/result-list.phtml b/themes/jquerymobile/templates/RecordDriver/SolrWeb/result-list.phtml
new file mode 100644
index 00000000000..41e08d2e44e
--- /dev/null
+++ b/themes/jquerymobile/templates/RecordDriver/SolrWeb/result-list.phtml
@@ -0,0 +1,26 @@
+<?
+ $url = $this->driver->getUrl();
+?>
+<a rel="external" href="<?=$this->escapeHtml($url)?>">
+ <div class="result">
+ <h3><?
+ $summHighlightedTitle = $this->driver->getHighlightedTitle();
+ $summTitle = $this->driver->getTitle();
+ if (!empty($summHighlightedTitle)) {
+ echo $this->highlight($this->addEllipsis($summHighlightedTitle, $summTitle));
+ } else if (!empty($summTitle)) {
+ echo $this->escapeHtml($this->truncate($summTitle, 180));
+ } else {
+ echo $this->transEsc('Title not available');
+ }
+ ?></h3>
+ </div>
+ <? $snippet = $this->driver->getHighlightedSnippet(); ?>
+ <? $summary = $this->driver->getSummary(); ?>
+ <? if (!empty($snippet)): ?>
+ <p><?=$this->highlight($snippet['snippet'])?></p>
+ <? elseif (!empty($summary)): ?>
+ <p><?=$this->escapeHtml($summary[0])?></p>
+ <? endif; ?>
+ <span style="color:#008000;" class="ui-li-desc"><?=$this->escapeHtml($url)?></span>
+</a>
diff --git a/themes/jquerymobile/templates/web/home.phtml b/themes/jquerymobile/templates/web/home.phtml
new file mode 100644
index 00000000000..881bf39a2f6
--- /dev/null
+++ b/themes/jquerymobile/templates/web/home.phtml
@@ -0,0 +1,4 @@
+<?
+ $this->overrideHomeOptions = ''; // turn off extra options
+ echo $this->render('search/home.phtml');
+?>
\ No newline at end of file
diff --git a/themes/jquerymobile/templates/web/results.phtml b/themes/jquerymobile/templates/web/results.phtml
new file mode 100644
index 00000000000..9c5b81545ee
--- /dev/null
+++ b/themes/jquerymobile/templates/web/results.phtml
@@ -0,0 +1,7 @@
+<?
+ // Override top search link:
+ $this->searchLink = 'web-home';
+
+ // Load standard settings from the default search results screen:
+ echo $this->render('search/results.phtml');
+?>
\ No newline at end of file
--
GitLab