| <!DOCTYPE html> |
| <html lang="en" dir="ltr" class="client-nojs"> |
| <head> |
| <meta charset="UTF-8" /> |
| <title>SMILA/Specifications/LuceneIntegration - Eclipsepedia</title> |
| <meta http-equiv="X-UA-Compatible" content="IE=EDGE" /> |
| <meta name="generator" content="MediaWiki 1.23.2" /> |
| <link rel="shortcut icon" href="http://wiki.eclipse.org/eclipse.org-common/themes/solstice/public/images/favicon.ico" /> |
| <link rel="search" type="application/opensearchdescription+xml" href="http://wiki.eclipse.org/opensearch_desc.php" title="Eclipsepedia (en)" /> |
| <link rel="EditURI" type="application/rsd+xml" href="http://wiki.eclipse.org/api.php?action=rsd" /> |
| <link rel="alternate" type="application/atom+xml" title="Eclipsepedia Atom feed" href="http://wiki.eclipse.org/index.php?title=Special:RecentChanges&feed=atom" /> |
| <link rel="stylesheet" href="http://wiki.eclipse.org/load.php?debug=false&lang=en&modules=mediawiki.legacy.commonPrint%2Cshared%7Cmediawiki.ui.button&only=styles&skin=solstice&*" /> |
| <link rel="stylesheet" href="http://wiki.eclipse.org/skins/solstice/public/stylesheets/styles.min.css?303" media="screen, print" /><meta name="ResourceLoaderDynamicStyles" content="" /> |
| <style>a:lang(ar),a:lang(kk-arab),a:lang(mzn),a:lang(ps),a:lang(ur){text-decoration:none} |
| /* cache key: my_wiki:resourceloader:filter:minify-css:7:14ece53a42aa314864e5fd8c57f0d98f */</style> |
| <script src="http://wiki.eclipse.org/load.php?debug=false&lang=en&modules=startup&only=scripts&skin=solstice&*"></script> |
| <script>if(window.mw){ |
| mw.config.set({"wgCanonicalNamespace":"","wgCanonicalSpecialPageName":false,"wgNamespaceNumber":0,"wgPageName":"SMILA/Specifications/LuceneIntegration","wgTitle":"SMILA/Specifications/LuceneIntegration","wgCurRevisionId":141504,"wgRevisionId":141504,"wgArticleId":18062,"wgIsArticle":true,"wgIsRedirect":false,"wgAction":"view","wgUserName":null,"wgUserGroups":["*"],"wgCategories":[],"wgBreakFrames":false,"wgPageContentLanguage":"en","wgPageContentModel":"wikitext","wgSeparatorTransformTable":["",""],"wgDigitTransformTable":["",""],"wgDefaultDateFormat":"dmy","wgMonthNames":["","January","February","March","April","May","June","July","August","September","October","November","December"],"wgMonthNamesShort":["","Jan","Feb","Mar","Apr","May","Jun","Jul","Aug","Sep","Oct","Nov","Dec"],"wgRelevantPageName":"SMILA/Specifications/LuceneIntegration","wgIsProbablyEditable":false,"wgRestrictionEdit":[],"wgRestrictionMove":[],"wgWikiEditorEnabledModules":{"toolbar":false,"dialogs":false,"hidesig":true,"preview":false,"previewDialog":false,"publish":false},"wgCategoryTreePageCategoryOptions":"{\"mode\":0,\"hideprefix\":20,\"showcount\":true,\"namespaces\":false}"}); |
| }</script><script>if(window.mw){ |
| mw.loader.implement("user.options",function($,jQuery){mw.user.options.set({"ccmeonemails":0,"cols":80,"date":"default","diffonly":0,"disablemail":0,"editfont":"default","editondblclick":0,"editsectiononrightclick":0,"enotifminoredits":0,"enotifrevealaddr":0,"enotifusertalkpages":1,"enotifwatchlistpages":1,"extendwatchlist":0,"fancysig":0,"forceeditsummary":0,"gender":"unknown","hideminor":0,"hidepatrolled":0,"imagesize":2,"math":1,"minordefault":0,"newpageshidepatrolled":0,"nickname":"","norollbackdiff":0,"numberheadings":0,"previewonfirst":0,"previewontop":1,"rcdays":7,"rclimit":50,"rows":25,"showhiddencats":0,"shownumberswatching":1,"showtoolbar":1,"skin":"solstice","stubthreshold":0,"thumbsize":2,"underline":2,"uselivepreview":0,"usenewrc":0,"watchcreations":1,"watchdefault":1,"watchdeletion":0,"watchlistdays":3,"watchlisthideanons":0,"watchlisthidebots":0,"watchlisthideliu":0,"watchlisthideminor":0,"watchlisthideown":0,"watchlisthidepatrolled":0,"watchmoves":0,"wllimit":250, |
| "useeditwarning":1,"prefershttps":1,"language":"en","variant-gan":"gan","variant-iu":"iu","variant-kk":"kk","variant-ku":"ku","variant-shi":"shi","variant-sr":"sr","variant-tg":"tg","variant-uz":"uz","variant-zh":"zh","searchNs0":true,"searchNs1":false,"searchNs2":false,"searchNs3":false,"searchNs4":false,"searchNs5":false,"searchNs6":false,"searchNs7":false,"searchNs8":false,"searchNs9":false,"searchNs10":false,"searchNs11":false,"searchNs12":false,"searchNs13":false,"searchNs14":false,"searchNs15":false,"variant":"en"});},{},{});mw.loader.implement("user.tokens",function($,jQuery){mw.user.tokens.set({"editToken":"+\\","patrolToken":false,"watchToken":false});},{},{}); |
| /* cache key: my_wiki:resourceloader:filter:minify-js:7:70d74423d3fc1e1c18fa9a1ff645a84a */ |
| }</script> |
| <script>if(window.mw){ |
| mw.loader.load(["mediawiki.page.startup","mediawiki.legacy.wikibits","mediawiki.legacy.ajax"]); |
| }</script> |
| <style type="text/css">/*<![CDATA[*/ |
| .source-xml {line-height: normal;} |
| .source-xml li, .source-xml pre { |
| line-height: normal; border: 0px none white; |
| } |
| /** |
| * GeSHi Dynamically Generated Stylesheet |
| * -------------------------------------- |
| * Dynamically generated stylesheet for xml |
| * CSS class: source-xml, CSS id: |
| * GeSHi (C) 2004 - 2007 Nigel McNie, 2007 - 2008 Benny Baumann |
| * (http://qbnz.com/highlighter/ and http://geshi.org/) |
| * -------------------------------------- |
| */ |
| .xml.source-xml .de1, .xml.source-xml .de2 {font: normal normal 1em/1.2em monospace; margin:0; padding:0; background:none; vertical-align:top;} |
| .xml.source-xml {font-family:monospace;} |
| .xml.source-xml .imp {font-weight: bold; color: red;} |
| .xml.source-xml li, .xml.source-xml .li1 {font-weight: normal; vertical-align:top;} |
| .xml.source-xml .ln {width:1px;text-align:right;margin:0;padding:0 2px;vertical-align:top;} |
| .xml.source-xml .li2 {font-weight: bold; vertical-align:top;} |
| .xml.source-xml .es0 {color: #000099; font-weight: bold;} |
| .xml.source-xml .br0 {color: #66cc66;} |
| .xml.source-xml .sy0 {color: #66cc66;} |
| .xml.source-xml .st0 {color: #ff0000;} |
| .xml.source-xml .nu0 {color: #cc66cc;} |
| .xml.source-xml .sc-1 {color: #808080; font-style: italic;} |
| .xml.source-xml .sc0 {color: #00bbdd;} |
| .xml.source-xml .sc1 {color: #ddbb00;} |
| .xml.source-xml .sc2 {color: #339933;} |
| .xml.source-xml .sc3 {color: #009900;} |
| .xml.source-xml .re0 {color: #000066;} |
| .xml.source-xml .re1 {color: #000000; font-weight: bold;} |
| .xml.source-xml .re2 {color: #000000; font-weight: bold;} |
| .xml.source-xml .ln-xtra, .xml.source-xml li.ln-xtra, .xml.source-xml div.ln-xtra {background-color: #ffc;} |
| .xml.source-xml span.xtra { display:block; } |
| |
| /*]]>*/ |
| </style><meta name="viewport" content="width=device-width, initial-scale=1.0"></head> |
| <body class="mediawiki ltr sitedir-ltr ns-0 ns-subject page-SMILA_Specifications_LuceneIntegration skin-solstice action-view" id="solstice"> |
| <a class="sr-only" href="LuceneIntegration.html#content">Skip to main content</a> |
| <div class="thin-header"> |
| <header role="banner" class="hidden-print noprint"> |
| <div class="container-fluid"> |
| <div id="row-logo-search"> |
| <div id="header-left"> |
| <div class="row"> |
| <div class="hidden-xs col-sm-6 logo-container"> |
| <a href="https://www.eclipse.org/" ><img class="logo-eclipse-default" src="http://wiki.eclipse.org/skins/solstice/public/images/logo/eclipse-800x188.png" alt="Eclipsepedia"></a> |
| </div> |
| <div class="navbar col-sm-18 yamm" id="main-menu"> |
| <div class="navbar-collapse collapse" id="navbar-collapse-1"> |
| <ul class="nav navbar-nav"> |
| <li><a target="_self" href="https://eclipse.org/downloads/">Download</a></li> |
| <li><a target="_self" href="https://eclipse.org/users/">Getting Started </a></li> |
| <li><a target="_self" href="https://eclipse.org/membership/">Members</a></li> |
| <li><a target="_self" href="https://eclipse.org/projects/">Projects</a></li> |
| <li class="dropdown visible-xs"><a class="dropdown-toggle" data-toggle="dropdown" href="LuceneIntegration.html#">Community <b class="caret"></b></a><ul class="dropdown-menu"><li><a href="http://marketplace.eclipse.org">Marketplace</a></li><li><a href="http://events.eclipse.org">Events</a></li><li><a href="http://www.planeteclipse.org/">Planet Eclipse</a></li><li><a href="https://eclipse.org/community/eclipse_newsletter/">Newsletter</a></li><li><a href="https://www.youtube.com/user/EclipseFdn">Videos</a></li></ul></li><li class="dropdown visible-xs"><a class="dropdown-toggle" data-toggle="dropdown" href="LuceneIntegration.html#">Participate <b class="caret"></b></a><ul class="dropdown-menu"><li><a href="https://bugs.eclipse.org/bugs/">Report a Bug</a></li><li><a href="https://eclipse.org/forums/">Forums</a></li><li><a href="https://eclipse.org/mail/">Mailing Lists</a></li><li><a href="https://wiki.eclipse.org/">Wiki</a></li><li><a href="https://wiki.eclipse.org/IRC">IRC</a></li><li><a href="https://eclipse.org/contribute/">How to Contribute</a></li></ul></li><li class="dropdown visible-xs"><a class="dropdown-toggle" data-toggle="dropdown" href="LuceneIntegration.html#">Working Groups <b class="caret"></b></a><ul class="dropdown-menu"><li><a href="http://wiki.eclipse.org/Auto_IWG">Automotive</a></li><li><a href="http://iot.eclipse.org">Internet of Things</a></li><li><a href="http://locationtech.org">LocationTech</a></li><li><a href="http://lts.eclipse.org">Long-Term Support</a></li><li><a href="http://polarsys.org">PolarSys</a></li><li><a href="http://science.eclipse.org">Science</a></li><li><a href="http://openmdm.org">OpenMDM</a></li></ul></li><!-- More --> |
| <li class="dropdown hidden-xs"><a class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a> |
| <ul class="dropdown-menu"> |
| <li> |
| <!-- Content container to add padding --> |
| <div class="yamm-content"> |
| <div class="row"> |
| <ul class="col-sm-8 list-unstyled"><li><p><strong>Community</strong></p></li><li><a href="http://marketplace.eclipse.org">Marketplace</a></li><li><a href="http://events.eclipse.org">Events</a></li><li><a href="http://www.planeteclipse.org/">Planet Eclipse</a></li><li><a href="https://eclipse.org/community/eclipse_newsletter/">Newsletter</a></li><li><a href="https://www.youtube.com/user/EclipseFdn">Videos</a></li></ul><ul class="col-sm-8 list-unstyled"><li><p><strong>Participate</strong></p></li><li><a href="https://bugs.eclipse.org/bugs/">Report a Bug</a></li><li><a href="https://eclipse.org/forums/">Forums</a></li><li><a href="https://eclipse.org/mail/">Mailing Lists</a></li><li><a href="https://wiki.eclipse.org/">Wiki</a></li><li><a href="https://wiki.eclipse.org/IRC">IRC</a></li><li><a href="https://eclipse.org/contribute/">How to Contribute</a></li></ul><ul class="col-sm-8 list-unstyled"><li><p><strong>Working Groups</strong></p></li><li><a href="http://wiki.eclipse.org/Auto_IWG">Automotive</a></li><li><a href="http://iot.eclipse.org">Internet of Things</a></li><li><a href="http://locationtech.org">LocationTech</a></li><li><a href="http://lts.eclipse.org">Long-Term Support</a></li><li><a href="http://polarsys.org">PolarSys</a></li><li><a href="http://science.eclipse.org">Science</a></li><li><a href="http://openmdm.org">OpenMDM</a></li></ul> </div> |
| </div> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </div> |
| <div class="navbar-header"> |
| <button data-target="#navbar-collapse-1" data-toggle="collapse" class="navbar-toggle" type="button"> |
| <span class="sr-only">Toggle navigation</span> |
| <span class="icon-bar"></span> |
| <span class="icon-bar"></span> |
| <span class="icon-bar"></span> |
| <span class="icon-bar"></span> |
| </button> |
| <a href="https://www.eclipse.org/" class="visible-xs navbar-brand"><img class="logo-eclipse-default" src="http://wiki.eclipse.org/skins/solstice/public/images/logo/eclipse-800x188.png" alt="Eclipsepedia" width="174"></a> |
| </div> |
| </div> |
| </div> |
| </div> |
| </div> |
| </div> |
| </header> |
| <section class="defaut-breadcrumbs hidden-print noprint hidden-print clearfix" id="breadcrumb"> |
| <div> |
| <ol class="breadcrumb"> |
| <li><a href="https://www.eclipse.org/">Home</a></li> |
| <li><a href="http://wiki.eclipse.org/Main_Page">Eclipse Wiki</a></li> |
| <li class="active">SMILA/Specifications/LuceneIntegration</li></ol> |
| </div> |
| </section> |
| </div> |
| <div class="toolbar-menu breadcrumbs-offset noprint hidden-print margin-bottom-0 clearfix"> |
| <div class="col-md-24"> |
| <ol class="breadcrumb" role="navigation"> |
| <li id="pt-login"> |
| <a href="http://wiki.eclipse.org/index.php?title=Special:UserLogin&returnto=SMILA%2FSpecifications%2FLuceneIntegration"> |
| <i class="fa fa-sign-in fa-fw orange"></i> Log in </a> |
| </li> |
| </ul> |
| </div> |
| </div> |
| <main role="main" class="background-grey"> |
| <div class="container-full padding-top-25"> |
| |
| |
| |
| <!-- content --> |
| <section id="content" class="mw-body container-full clearfix 0"> |
| <div id="mw-js-message" style="display:none;"></div> |
| |
| |
| <!-- bodyContent --> |
| <div id="bodyContent"> |
| |
| |
| <!-- jumpto --> |
| <div id="jump-to-nav" class="mw-jump"> |
| Jump to: <a href="LuceneIntegration.html#mw-head">navigation</a>, |
| <a href="LuceneIntegration.html#p-search">search</a> |
| </div> |
| <!-- /jumpto --> |
| |
| <!-- leftcol --> |
| <aside class="col-md-4 noprint hidden-print" id="leftcol"> |
| <form class="input-group" role="form" id="form-eclipse-search" action="http://wiki.eclipse.org/index.php" id="searchform"> |
| <input id="searchInput" class="search-query form-control" type="search" accesskey="f" title="Special:Search" placeholder="Search" name="search" value=""> |
| |
| <span class="input-group-btn"> |
| <button value="search" id="mw-searchButton" type="submit" class="btn btn-default" title="Search the pages for this text" name="fulltext"> |
| <i class="fa fa-search"></i> |
| </button> |
| </span> |
| </form> |
| <select class="form-control margin-top-10 margin-bottom-10 visible-xs visible-sm" onchange="this.options[this.selectedIndex].value && (window.location = this.options[this.selectedIndex].value);"><option class="fw-700 "><span class="fw-700">---Navigation---</span></option><option value="/Main_Page">Main Page</option><option value="/Eclipsepedia:Community_portal">Community portal</option><option value="/Eclipsepedia:Current_events">Current events</option><option value="/Special:RecentChanges">Recent changes</option><option value="/Special:Random">Random page</option><option value="https://www.mediawiki.org/wiki/Special:MyLanguage/Help:Contents">Help</option></select><ul class="ul-left-nav fa-ul hidden-print leftnav hidden-xs hidden-sm"><li class="separator"><span class="separator">Navigation</span></li> <li class=""><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/Main_Page" id="n-mainpage" title="Visit the main page [z]" accesskey="z">Main Page</a></li> <li class=""><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/Eclipsepedia:Community_portal" id="n-portal" title="About the project, what you can do, where to find things">Community portal</a></li> <li class=""><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/Eclipsepedia:Current_events" id="n-currentevents" title="Find background information on current events">Current events</a></li> <li class=""><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/Special:RecentChanges" id="n-recentchanges" title="A list of recent changes in the wiki [r]" accesskey="r">Recent changes</a></li> <li class=""><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/Special:Random" id="n-randompage" title="Load a random page [x]" accesskey="x">Random page</a></li> <li class=""><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="https://www.mediawiki.org/wiki/Special:MyLanguage/Help:Contents" id="n-help" title="The place to find out">Help</a></li></ul> <select class="form-control margin-top-10 margin-bottom-10 visible-xs visible-sm" onchange="this.options[this.selectedIndex].value && (window.location = this.options[this.selectedIndex].value);"><option class="fw-700 "><span class="fw-700">---Toolbox---</span></option><option value="/index.php?title=SMILA/Specifications/LuceneIntegration&action=info">Page information</option><option value="/index.php?title=SMILA/Specifications/LuceneIntegration&oldid=141504">Permanent link</option><option value="/index.php?title=SMILA/Specifications/LuceneIntegration&printable=yes">Printable version</option><option value="/Special:SpecialPages">Special pages</option><option value="/Special:RecentChangesLinked/SMILA/Specifications/LuceneIntegration">Related changes</option><option value="/Special:WhatLinksHere/SMILA/Specifications/LuceneIntegration">What links here</option></select><ul class="ul-left-nav fa-ul hidden-print leftnav hidden-xs hidden-sm"><li class="separator"><span class="separator">Toolbox</span></li><li><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/index.php?title=SMILA/Specifications/LuceneIntegration&action=info" id="t-info">Page information</a></li><li><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/index.php?title=SMILA/Specifications/LuceneIntegration&oldid=141504" id="t-permalink" title="Permanent link to this revision of the page">Permanent link</a></li><li><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/index.php?title=SMILA/Specifications/LuceneIntegration&printable=yes" id="t-print" rel="alternate" title="Printable version of this page [p]" accesskey="p">Printable version</a></li><li><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/Special:SpecialPages" id="t-specialpages" title="A list of all special pages [q]" accesskey="q">Special pages</a></li><li><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/Special:RecentChangesLinked/SMILA/Specifications/LuceneIntegration" id="t-recentchangeslinked" title="Recent changes in pages linked from this page [k]" accesskey="k">Related changes</a></li><li><i class="fa fa-angle-double-right orange fa-fw"></i> <a href="http://wiki.eclipse.org/Special:WhatLinksHere/SMILA/Specifications/LuceneIntegration" id="t-whatlinkshere" title="A list of all wiki pages that link here [j]" accesskey="j">What links here</a></li></ul> </aside> |
| <!-- /leftcol --> |
| |
| <!-- mainContent --> |
| <div id="mainContent" class="col-md-20"> |
| <ul class="nav nav-tabs noprint hidden-print" role="tablist"> |
| <li id="ca-nstab-main" class="active"><a href="LuceneIntegration.html" title="View the content page [c]" accesskey="c" tabindex="-1">Page</a></li> |
| <li id="ca-talk" class="new"><a href="http://wiki.eclipse.org/index.php?title=Talk:SMILA/Specifications/LuceneIntegration&action=edit&redlink=1" title="Discussion about the content page [t]" accesskey="t" tabindex="-1">Discussion</a></li> |
| <li id="ca-viewsource"><a href="http://wiki.eclipse.org/index.php?title=SMILA/Specifications/LuceneIntegration&action=edit" title="This page is protected. You can view its source [e]" accesskey="e" tabindex="-1">View source</a></li> |
| <li id="ca-history" class="collapsible"><a href="http://wiki.eclipse.org/index.php?title=SMILA/Specifications/LuceneIntegration&action=history" title="Past revisions of this page [h]" accesskey="h" tabindex="-1">History</a></li> |
| </ul> <div class="tab-content background-white"> |
| <div id="tab-pane-main-page-content" class="tab-pane active"> |
| |
| |
| <h1 id="firstHeading" class="firstHeading page-header"> |
| <span dir="auto">SMILA/Specifications/LuceneIntegration</span> |
| </h1> |
| <div id="main-page-content"> |
| <!-- subtitle --> |
| <div id="contentSub" class="alert alert-small alert-warning"><span class="subpages">< <a href="../../SMILA.html" title="SMILA">SMILA</a>‎ | <a href="../Specifications.html" title="SMILA/Specifications">Specifications</a></span></div> |
| <!-- /subtitle --> |
| |
| |
| <div id="mw-content-text" lang="en" dir="ltr" class="mw-content-ltr"><div id="toc" class="toc"><div id="toctitle"><h2>Contents</h2></div> |
| <ul> |
| <li class="toclevel-1 tocsection-1"><a href="LuceneIntegration.html#Description"><span class="tocnumber">1</span> <span class="toctext">Description</span></a></li> |
| <li class="toclevel-1 tocsection-2"><a href="LuceneIntegration.html#Discussion"><span class="tocnumber">2</span> <span class="toctext">Discussion</span></a></li> |
| <li class="toclevel-1 tocsection-3"><a href="LuceneIntegration.html#Status_Quo"><span class="tocnumber">3</span> <span class="toctext">Status Quo</span></a></li> |
| <li class="toclevel-1 tocsection-4"><a href="LuceneIntegration.html#Technical_proposal"><span class="tocnumber">4</span> <span class="toctext">Technical proposal</span></a> |
| <ul> |
| <li class="toclevel-2 tocsection-5"><a href="LuceneIntegration.html#Features"><span class="tocnumber">4.1</span> <span class="toctext">Features</span></a></li> |
| <li class="toclevel-2 tocsection-6"><a href="LuceneIntegration.html#Lucene_specific_vs._generic"><span class="tocnumber">4.2</span> <span class="toctext">Lucene specific vs. generic</span></a></li> |
| <li class="toclevel-2 tocsection-7"><a href="LuceneIntegration.html#Configuration"><span class="tocnumber">4.3</span> <span class="toctext">Configuration</span></a></li> |
| <li class="toclevel-2 tocsection-8"><a href="LuceneIntegration.html#Bundles.2C_Packages.2C_Extension_Points"><span class="tocnumber">4.4</span> <span class="toctext">Bundles, Packages, Extension Points</span></a></li> |
| </ul> |
| </li> |
| </ul> |
| </div> |
| |
| <h1><span class="mw-headline" id="Description">Description</span></h1> |
| <p>This page is about the integration of Lucene as a sample indexing/search engine in Smila. |
| </p> |
| <h1><span class="mw-headline" id="Discussion">Discussion</span></h1> |
| <h1><span class="mw-headline" id="Status_Quo">Status Quo</span></h1> |
| <p>At the moment we have two ProcessingServices for indexing and searching records in Lucene: |
| </p> |
| <ul> |
| <li>LuceneIndexService |
| </li> |
| <li>LuceneSearchService |
| </li> |
| </ul> |
| <p>Both services support multiple indexes, selectable via annotations. As an integration layer between these services and the Lucene api the brox anyfinder classes are used for now. The configuration of the services and the Lucene index and some search properties is a mixture of a service specific record to index field mapping file (mappings.xml) and anyfinders own DataDictionary (DataDictionary.xml). |
| </p><p><br /> |
| </p> |
| <h1><span class="mw-headline" id="Technical_proposal">Technical proposal</span></h1> |
| <p>One of the goals of Smila was to create the framework from scratch without any legacy code. Therefore wo should refactor the anyfinder Lucene integration to contain only the classes that are needed. Below are some thoughts about issues with the current implementation and what to reuse/refactor: |
| </p> |
| <h2><span class="mw-headline" id="Features">Features</span></h2> |
| <p>The following features should be supported by the integration: |
| </p> |
| <ul> |
| <li> configuration of index fields (analyzers, indexation, tokenization) |
| </li> |
| <li> simple search (query over a dedicated text field) |
| </li> |
| <li> advanced search (query over multiple fields and filter support) |
| </li> |
| <li> simple highlighting (return a formated html text) |
| </li> |
| <li> advanced highlighting (return highlight positions and weights) |
| </li> |
| </ul> |
| <p><br /> |
| </p> |
| <h2><span class="mw-headline" id="Lucene_specific_vs._generic">Lucene specific vs. generic</span></h2> |
| <p>Anyfinder abstracts from concrete search engines, offering a generic api for search engine integration. Smila offers the same, using the BPEL Pipelet/ProcessingService approach. Therefore most abstract classes or interfaces of anyfinder can be removed or merged with concrete Lucene implementations. This will minimize the number of classes. |
| </p><p><br /> |
| </p> |
| <h2><span class="mw-headline" id="Configuration">Configuration</span></h2> |
| <p>The configuration files mappings.xml and DataDictionary.xml should be merged into one xml configuration. The configuration for result and highlighting attributes should be a default configuration which is used if the search process does not explicitly requests other results. As it is not relevant for the LuceneIndexService it could be moved in a separate config file. The defined mapping of record attributes/attachments to index fields should be reused by the LuceneSearchService (by having a reference to the LuceneIndexService and providing methods to acess the mapping information in both directions). |
| </p><p>Here are my ideas for a index and search configuration, reusing anyfinder concepts: |
| </p> |
| <div dir="ltr" class="mw-geshi mw-code mw-content-ltr"><div class="xml source-xml"><pre class="de1"><span class="sc3"><span class="re1"><LuceneIndexConfig<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Index</span> <span class="re0">Name</span>=<span class="st0">"test_index"</span> <span class="re0">MaxConnections</span>=<span class="st0">"5"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><IndexStructure<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Analyzer</span> <span class="re0">ClassName</span>=<span class="st0">"org.apache.lucene.analysis.standard.StandardAnalyzer"</span><span class="re2">/></span></span> |
| <span class="sc3"><span class="re1"><Attribute</span> <span class="re0">name</span>=<span class="st0">"Title"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><IndexField</span> <span class="re0">Name</span>=<span class="st0">"Title"</span> <span class="re0">IndexValue</span>=<span class="st0">"true"</span> <span class="re0">StoreText</span>=<span class="st0">"true"</span> <span class="re0">Tokenize</span>=<span class="st0">"true"</span> <span class="re0">Type</span>=<span class="st0">"Text"</span><span class="re2">/></span></span> |
| <span class="sc3"><span class="re1"><Attribute</span><span class="re2">/></span></span> |
| <span class="sc3"><span class="re1"><Attribute</span> <span class="re0">name</span>=<span class="st0">"Url"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><IndexField</span> <span class="re0">Name</span>=<span class="st0">"Url"</span> <span class="re0">IndexValue</span>=<span class="st0">"true"</span> <span class="re0">StoreText</span>=<span class="st0">"true"</span> <span class="re0">Tokenize</span>=<span class="st0">"false"</span> <span class="re0">Type</span>=<span class="st0">"Text"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><Analyzer</span> <span class="re0">ClassName</span>=<span class="st0">"org.apache.lucene.analysis.WhitespaceAnalyzer"</span><span class="re2">/></span></span> |
| <span class="sc3"><span class="re1"></IndexField<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Attribute</span><span class="re2">/></span></span> |
| <span class="sc3"><span class="re1"><Attribute</span> <span class="re0">name</span>=<span class="st0">"LastModifiedDate"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><IndexField</span> <span class="re0">Name</span>=<span class="st0">"LastModifiedDate"</span> <span class="re0">IndexValue</span>=<span class="st0">"true"</span> <span class="re0">StoreText</span>=<span class="st0">"true"</span> <span class="re0">Tokenize</span>=<span class="st0">"false"</span> <span class="re0">Type</span>=<span class="st0">"Text"</span><span class="re2">/></span></span> |
| <span class="sc3"><span class="re1"><Attribute</span><span class="re2">/></span></span> |
| ... |
| <span class="sc3"><span class="re1"><Attachment</span> <span class="re0">path</span>=<span class="st0">"Content"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><IndexField</span> <span class="re0">Name</span>=<span class="st0">"Content"</span> <span class="re0">IndexValue</span>=<span class="st0">"true"</span> <span class="re0">StoreText</span>=<span class="st0">"true"</span> <span class="re0">Tokenize</span>=<span class="st0">"true"</span> <span class="re0">Type</span>=<span class="st0">"Text"</span><span class="re2">/></span></span> |
| <span class="sc3"><span class="re1"><Attachment</span><span class="re2">/></span></span> |
| ... |
| <span class="sc3"><span class="re1"></IndexStructure<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></Index<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Index</span> <span class="re0">Name</span>=<span class="st0">"another_index"</span> <span class="re0">MaxConnections</span>=<span class="st0">"5"</span><span class="re2">></span></span> |
| ... |
| <span class="sc3"><span class="re1"></Index<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></LuceneIndexConfig<span class="re2">></span></span></span></pre></div></div> |
| <div dir="ltr" class="mw-geshi mw-code mw-content-ltr"><div class="xml source-xml"><pre class="de1"><span class="sc3"><span class="re1"><LuceneSearchConfig<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Index</span> <span class="re0">Name</span>=<span class="st0">"test_index"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><Result<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Attribute</span> <span class="re0">name</span>=<span class="st0">"MimeType"</span><span class="re2">/></span></span> |
| <span class="sc3"><span class="re1"><Attribute</span> <span class="re0">name</span>=<span class="st0">"LastModifiedDate"</span> <span class="re2">/></span></span> |
| <span class="sc3"><span class="re1"><Attribute</span> <span class="re0">name</span>=<span class="st0">"Url"</span> <span class="re2">/></span></span> |
| ... |
| <span class="sc3"><span class="re1"><Attachment</span> <span class="re0">name</span>=<span class="st0">"Content"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><HighlightingTransformer</span> <span class="re0">Name</span>=<span class="st0">"urn:Sentence"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><ParameterSet<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Parameter</span> <span class="re0">Name</span>=<span class="st0">"MaxLength"</span> <span class="re0">xsi:type</span>=<span class="st0">"Integer"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><Value<span class="re2">></span></span></span>300<span class="sc3"><span class="re1"></Value<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></Parameter<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Parameter</span> <span class="re0">Name</span>=<span class="st0">"MaxHLElements"</span> <span class="re0">xsi:type</span>=<span class="st0">"Integer"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><Value<span class="re2">></span></span></span>999<span class="sc3"><span class="re1"></Value<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></Parameter<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Parameter</span> <span class="re0">Name</span>=<span class="st0">"MaxSucceedingCharacters"</span> <span class="re0">xsi:type</span>=<span class="st0">"Integer"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><Value<span class="re2">></span></span></span>30<span class="sc3"><span class="re1"></Value<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></Parameter<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Parameter</span> <span class="re0">Name</span>=<span class="st0">"SucceedingCharacters"</span> <span class="re0">xsi:type</span>=<span class="st0">"String"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><Value<span class="re2">></span></span></span>...<span class="sc3"><span class="re1"></Value<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></Parameter<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Parameter</span> <span class="re0">Name</span>=<span class="st0">"SortAlgorithm"</span> <span class="re0">xsi:type</span>=<span class="st0">"String"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><Value<span class="re2">></span></span></span>Occurrence<span class="sc3"><span class="re1"></Value<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></Parameter<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"><Parameter</span> <span class="re0">Name</span>=<span class="st0">"TextHandling"</span> <span class="re0">xsi:type</span>=<span class="st0">"String"</span><span class="re2">></span></span> |
| <span class="sc3"><span class="re1"><Value<span class="re2">></span></span></span>ReturnSnipplet<span class="sc3"><span class="re1"></Value<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></Parameter<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></ParameterSet<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></HighlightingTransformer<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></Attachment<span class="re2">></span></span></span> |
| ... |
| <span class="sc3"><span class="re1"></Result<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></Index<span class="re2">></span></span></span> |
| <span class="sc3"><span class="re1"></LuceneSearchConfig<span class="re2">></span></span></span></pre></div></div> |
| <p><br /> |
| In addition, a Lucene index needs two special IndexFields that are not configurable but fixed: |
| </p> |
| <ul> |
| <li> ID: this is a hashed version of the record Id. It is used to identify the record in the index |
| </li> |
| <li> XMLID: this contains the xml representation of the record Id. It is only stored in the index and part of every result, as it is used to create Id objects from it |
| </li> |
| </ul> |
| <p><br /> |
| </p> |
| <h2><span class="mw-headline" id="Bundles.2C_Packages.2C_Extension_Points">Bundles, Packages, Extension Points</span></h2> |
| <p>All classes neeeded for Lucene integration should be in the bundle org.eclipse.smila.lucene or in bundles extending this package structure. |
| org.eclipse.smila.search should be reserved for Smila Search API and more generic stuff to come (perhaps the highlighting transformer could fit in there). |
| </p><p>There are some packages and lots of classes I don't know what they are used for: |
| </p> |
| <ul> |
| <li> org.eclipse.smila.transformation (except the Highlighting* classes) |
| </li> |
| <li> org.eclipse.smila.transformation.transformer |
| </li> |
| <li> org.eclipse.smila.search.datadictionary - should most of these classes be generated by Jaxb ? |
| </li> |
| <li> org.eclipse.smila.search.feature |
| </li> |
| <li> org.eclipse.smila.search.irm |
| </li> |
| <li> org.eclipse.smila.search.tools - why are such common classes like exception in here ? |
| </li> |
| <li> org.eclipse.smila.search.tools.indexstructur (seems to be obsolete if merged with org.eclipse.smila.lucene) |
| </li> |
| <li> what are all thos D-classes for. Why are the duplicate class names in different packages ? Semms to be some wrapper classes where in turn Lucene classes could be used. |
| </li> |
| <li> what are all those template classes about ? I guess we don't need them anymore. |
| </li> |
| </ul> |
| <p>Also anyfinder bundles make use of extension points. What is it used for ? I don't think that it is needed for a concrete Lucene integration. |
| </p> |
| <!-- |
| NewPP limit report |
| CPU time usage: 0.052 seconds |
| Real time usage: 0.055 seconds |
| Preprocessor visited node count: 48/1000000 |
| Preprocessor generated node count: 76/1000000 |
| Post‐expand include size: 0/2097152 bytes |
| Template argument size: 0/2097152 bytes |
| Highest expansion depth: 2/40 |
| Expensive parser function count: 0/100 |
| --> |
| |
| <!-- Saved in parser cache with key my_wiki:pcache:idhash:18062-0!*!*!!en!*!* and timestamp 20150414084659 and revision id 141504 |
| --> |
| </div> |
| <!-- catlinks --> |
| <div id='catlinks' class='catlinks catlinks-allhidden'></div> <!-- /catlinks --> |
| </div> |
| </div> |
| </div> |
| </div> |
| <!-- /maincontent --> |
| |
| <!-- printfooter --> |
| <div class="printfooter"> |
| Retrieved from "<a href="http://wiki.eclipse.org/index.php?title=SMILA/Specifications/LuceneIntegration&oldid=141504">http://wiki.eclipse.org/index.php?title=SMILA/Specifications/LuceneIntegration&oldid=141504</a>" </div> |
| <!-- /printfooter --> |
| |
| |
| <!-- debughtml --> |
| <!-- /debughtml --> |
| |
| </div> |
| <!-- /bodyContent --> |
| </section> |
| <!-- /content --> |
| |
| <!-- footer --> |
| |
| </div> <section id="footer-contribution-info" style="border-top:1px solid #ccc;" class="footer-offset background-white margin-top-25"><div class="container text-center padding-top-10 padding-bottom-10"><p id="footercredit">This page was last modified 12:40, 25 February 2009 by <a href="http://wiki.eclipse.org/User:Daniel.stucky.empolis.com" title="User:Daniel.stucky.empolis.com">Daniel Stucky</a>.</p><p id="footerviews">This page has been accessed 2,555 times.</p></div></section> </main> <!-- /#main-content-container-row --> |
| <p id="back-to-top" class="noprint hidden-print"> |
| <a class="visible-xs" href="LuceneIntegration.html#top">Back to the top</a> |
| </p> |
| <footer role="contentinfo" class="noprint hidden-print"> |
| <div class="container"> |
| <div class="row"> |
| <section id="footer-eclipse-foundation" class="col-xs-offset-1 col-xs-11 col-sm-7 col-md-6 col-md-offset-0"> |
| <h2 class="section-title">Eclipse Foundation</h2> |
| <ul class="nav"> |
| <li><a href="https://eclipse.org/org/">About us</a></li> |
| <li><a href="https://eclipse.org/org/foundation/contact.php">Contact Us</a></li> |
| <li><a href="https://eclipse.org/donate">Donate</a></li> |
| <li><a href="https://eclipse.org/org/documents/">Governance</a></li> |
| <li><a href="https://eclipse.org/artwork/">Logo and Artwork</a></li> |
| <li><a href="https://eclipse.org/org/foundation/directors.php">Board of Directors</a></li> |
| </ul> |
| </section> |
| <section id="footer-legal" class="col-xs-offset-1 col-xs-11 col-sm-7 col-md-6 col-md-offset-0"> |
| <h2 class="section-title">Legal</h2> |
| <ul class="nav"> |
| <li><a href="https://eclipse.org/legal/privacy.php">Privacy Policy</a></li> |
| <li><a href="https://eclipse.org/legal/termsofuse.php">Terms of Use</a></li> |
| <li><a href="https://eclipse.org/legal/copyright.php">Copyright Agent</a></li> |
| <li><a href="https://eclipse.org/org/documents/epl-v10.php">Eclipse Public License </a></li> |
| <li><a href="https://eclipse.org/legal/">Legal Resources </a></li> |
| |
| </ul> |
| </section> |
| |
| <section id="footer-useful-links" class="col-xs-offset-1 col-xs-11 col-sm-7 col-md-6 col-md-offset-0"> |
| <h2 class="section-title">Useful Links</h2> |
| <ul class="nav"> |
| <li><a href="https://bugs.eclipse.org/bugs/">Report a Bug</a></li> |
| <li><a href="http://help.eclipse.org/">Documentation</a></li> |
| <li><a href="https://eclipse.org/contribute/">How to Contribute</a></li> |
| <li><a href="https://eclipse.org/mail/">Mailing Lists</a></li> |
| <li><a href="https://eclipse.org/forums/">Forums</a></li> |
| <li><a href="http://marketplace.eclipse.org/">Marketplace</a></li> |
| </ul> |
| </section> |
| |
| <section id="footer-other" class="col-xs-offset-1 col-xs-11 col-sm-7 col-md-6 col-md-offset-0"> |
| |
| <h2 class="section-title">Other</h2> |
| <ul class="nav"> |
| <li><a href="https://eclipse.org/ide/">IDE and Tools</a></li> |
| <li><a href="https://eclipse.org/projects">Community of Projects</a></li> |
| <li><a href="https://eclipse.org/org/workinggroups/">Working Groups</a></li> |
| </ul> |
| |
| <ul class="list-inline social-media"> |
| <li><a href="https://twitter.com/EclipseFdn"><i class="fa fa-twitter-square"></i></a></li> |
| <li><a href="https://plus.google.com/+Eclipse"><i class="fa fa-google-plus-square"></i></a></li> |
| <li><a href="https://www.facebook.com/eclipse.org"><i class="fa fa-facebook-square"></i> </a></li> |
| <li><a href="https://www.youtube.com/user/EclipseFdn"><i class="fa fa-youtube-square"></i></a></li> |
| </ul> |
| |
| </section> |
| <div id="copyright" class="col-xs-offset-1 col-sm-14 col-md-24 col-md-offset-0"> |
| <div> |
| <span><img src="http://eclipse.org/eclipse.org-common/themes/solstice/public/images/logo/eclipse-logo-bw-800x188.png" alt="Eclipse.org black and white logo" width="166" height="39" id="logo-eclipse-white"/></span> |
| <p id="copyright-text">Copyright © 2014 The Eclipse Foundation. All Rights Reserved.</p> |
| </div> |
| </div> |
| <a href="LuceneIntegration.html#" class="scrollup">Back to the top</a> |
| </div> |
| </div> |
| </footer> |
| |
| <script src="http://wiki.eclipse.org/skins/solstice/public/javascript/main.min.js"></script> |
| |
| <!-- Placed at the end of the document so the pages load faster --> |
| <script type="text/javascript"> |
| |
| var _gaq = _gaq || []; |
| _gaq.push(['_setAccount', 'UA-910670-2']); |
| _gaq.push(['_trackPageview']); |
| |
| (function() { |
| var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; |
| ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; |
| var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); |
| })(); |
| |
| </script> <!-- /footer --> |
| <script>/*<![CDATA[*/window.jQuery && jQuery.ready();/*]]>*/</script><script>if(window.mw){ |
| mw.loader.state({"skins.solstice":"loading","site":"ready","user":"ready","user.groups":"ready"}); |
| }</script> |
| <script src="http://wiki.eclipse.org/load.php?debug=false&lang=en&modules=skins.solstice&only=scripts&skin=solstice&*"></script> |
| <script>if(window.mw){ |
| mw.loader.load(["mediawiki.action.view.postEdit","mediawiki.user","mediawiki.hidpi","mediawiki.page.ready","mediawiki.searchSuggest"],null,true); |
| }</script> |
| <script>if(window.mw){ |
| mw.config.set({"wgBackendResponseTime":391}); |
| }</script> </body> |
| </html> |
