incubator-connectors-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From shinich...@apache.org
Subject svn commit: r1137907 [8/8] - in /incubator/lcf/site/publish: ./ images/ skin/ skin/css/ skin/images/ skin/scripts/ skin/translations/
Date Tue, 21 Jun 2011 08:36:59 GMT
Propchange: incubator/lcf/site/publish/skin/skinconf.xsl
------------------------------------------------------------------------------
    svn:eol-style = native

Propchange: incubator/lcf/site/publish/skin/skinconf.xsl
------------------------------------------------------------------------------
    svn:keywords = Date Author Id Revision HeadURL

Added: incubator/lcf/site/publish/who.html
URL: http://svn.apache.org/viewvc/incubator/lcf/site/publish/who.html?rev=1137907&view=auto
==============================================================================
--- incubator/lcf/site/publish/who.html (added)
+++ incubator/lcf/site/publish/who.html Tue Jun 21 08:36:54 2011
@@ -0,0 +1,282 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+<head>
+<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
+<meta content="Apache Forrest" name="Generator">
+<meta name="Forrest-version" content="0.9">
+<meta name="Forrest-skin-name" content="lucene">
+<title>Who We Are</title>
+<link type="text/css" href="skin/basic.css" rel="stylesheet">
+<link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet">
+<link media="print" type="text/css" href="skin/print.css" rel="stylesheet">
+<link type="text/css" href="skin/profile.css" rel="stylesheet">
+<script src="skin/getBlank.js" language="javascript" type="text/javascript"></script><script src="skin/getMenu.js" language="javascript" type="text/javascript"></script><script src="skin/fontsize.js" language="javascript" type="text/javascript"></script>
+<link rel="shortcut icon" href="images/favicon.ico">
+</head>
+<body onload="init()">
+<script type="text/javascript">ndeSetTextSize();</script>
+<div id="top">
+<!--+
+    |breadtrail
+    +-->
+<div class="breadtrail">
+<a href="http://www.apache.org/">Apache</a> &gt; <a href="http://incubator.apache.org/">Incubator</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script>
+</div>
+<!--+
+    |header
+    +-->
+<div class="header">
+<!--+
+    |start group logo
+    +-->
+<div class="grouplogo">
+<a href="http://www.apache.org"><img class="logoImage" alt="Apache" src="images/apache_feather.gif" title="Apache Software Foundation"></a>
+</div>
+<!--+
+    |end group logo
+    +-->
+<!--+
+    |start Project Logo
+    +-->
+<div class="projectlogo">
+<a href="http://incubator.apache.org/lcf"><img class="logoImage" alt="Apache ManifoldCF" src="images/ManifoldCF-logo.PNG" title="ManifoldCF"></a>
+</div>
+<!--+
+    |end Project Logo
+    +-->
+<!--+
+    |start Search
+    +-->
+<div class="searchbox">
+<form action="http://www.lucidimagination.com/search/" method="get" class="roundtopsmall">
+<input onFocus="getBlank (this, 'Search the site with Solr');" size="25" name="q" id="query" type="text" value="Search the site with Solr">&nbsp; 
+                    <input name="Search" value="Search" type="submit">
+</form>
+<div style="position: relative; top: -5px; left: -10px">Powered by <a href="http://www.lucidimagination.com" style="color: #033268">Lucid Imagination</a>
+</div>
+</div>
+<!--+
+    |end search
+    +-->
+<!--+
+    |start Tabs
+    +-->
+<ul id="tabs">
+<li class="current">
+<a class="selected" href="index.html">Main</a>
+</li>
+<li>
+<a class="unselected" href="http://cwiki.apache.org/confluence/display/CONNECTORS/Index">Wiki</a>
+</li>
+</ul>
+<!--+
+    |end Tabs
+    +-->
+</div>
+</div>
+<div id="main">
+<div id="publishedStrip">
+<!--+
+    |start Subtabs
+    +-->
+<div id="level2tabs"></div>
+<!--+
+    |end Endtabs
+    +-->
+<script type="text/javascript"><!--
+document.write("Last Published: " + document.lastModified);
+//  --></script>
+</div>
+<!--+
+    |breadtrail
+    +-->
+<div class="breadtrail">
+
+             &nbsp;
+           </div>
+<!--+
+    |start Menu, mainarea
+    +-->
+<!--+
+    |start Menu
+    +-->
+<div id="menu">
+<div onclick="SwitchMenu('menu_selected_1.1', 'skin/')" id="menu_selected_1.1Title" class="menutitle" style="background-image: url('skin/images/chapter_open.gif');">About</div>
+<div id="menu_selected_1.1" class="selectedmenuitemgroup" style="display: block;">
+<div class="menuitem">
+<a href="index.html">Welcome</a>
+</div>
+<div class="menupage">
+<div class="menupagetitle">Who We Are</div>
+</div>
+<div class="menuitem">
+<a href="http://www.manning.com/wright/">Get the Book</a>
+</div>
+<div class="menuitem">
+<a href="http://www.cafepress.com/lucene/">Buy Stuff</a>
+</div>
+<div class="menuitem">
+<a href="http://www.apache.org/foundation/sponsorship.html">Sponsor Apache</a>
+</div>
+<div class="menuitem">
+<a href="http://www.apache.org/foundation/thanks.html">Sponsors of Apache</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.2', 'skin/')" id="menu_1.2Title" class="menutitle">Documentation</div>
+<div id="menu_1.2" class="menuitemgroup">
+<div class="menuitem">
+<a href="concepts.html">Concepts</a>
+</div>
+<div class="menuitem">
+<a href="included-connectors.html">Compatibility Matrix</a>
+</div>
+<div class="menuitem">
+<a href="faq.html">Frequently Asked Questions</a>
+</div>
+<div class="menuitem">
+<a href="programmatic-operation.html">API Documentation</a>
+</div>
+<div class="menuitem">
+<a href="javadoc.html">Javadoc</a>
+</div>
+<div class="menuitem">
+<a href="how-to-build-and-deploy.html">Building and Deploying</a>
+</div>
+<div class="menuitem">
+<a href="end-user-documentation.html">End-user Documentation (HTML)</a>
+</div>
+<div class="menuitem">
+<a href="end-user-documentation.pdf">End-user Documentation (PDF)</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.3', 'skin/')" id="menu_1.3Title" class="menutitle">Resources</div>
+<div id="menu_1.3" class="menuitemgroup">
+<div class="menuitem">
+<a href="download.html">Download</a>
+</div>
+<div class="menuitem">
+<a href="mail.html">Mailing Lists</a>
+</div>
+<div class="menuitem">
+<a href="developer-resources.html">Developer/Integrator Resources</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.4', 'skin/')" id="menu_1.4Title" class="menutitle">Related-Projects</div>
+<div id="menu_1.4" class="menuitemgroup">
+<div class="menuitem">
+<a href="http://incubator.apache.org/droids/">Droids</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/java/">Java</a>
+</div>
+<div class="menuitem">
+<a href="http://incubator.apache.org/lucene.net/">Lucene.Net</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/lucy/">Lucy</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/mahout/">Mahout</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/nutch/">Nutch</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/openrelevance/">Open Relevance</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/pylucene/">PyLucene</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/solr/">Solr</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/tika/">Tika</a>
+</div>
+</div>
+<div id="credit"></div>
+<div id="roundbottom">
+<img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div>
+<!--+
+  |alternative credits
+  +-->
+<div id="credit2"></div>
+</div>
+<!--+
+    |end Menu
+    +-->
+<!--+
+    |start content
+    +-->
+<div id="content">
+<h1>Who We Are</h1>
+<div id="minitoc-area">
+<ul class="minitoc">
+<li>
+<a href="#Committers">Committers</a>
+</li>
+</ul>
+</div> 
+
+      
+<a name="N1000E"></a><a name="Committers"></a>
+<h2 class="h3">Committers</h2>
+<div class="section">
+<p>
+        (in alphabetical order): 
+        </p>
+<ul>
+        
+<li>Shinichiro Abe &lt;shinichiro&gt; </li>
+        
+<li>Erlend Gar&aring;sen &lt;ridder&gt; </li>
+        
+<li>Grant Ingersoll &lt;gsingers&gt; </li>
+	
+<li>Shalin Shekhar Mangar &lt;shalin&gt; </li>
+        
+<li>Mark Miller &lt;markrmiller&gt; </li>
+        
+<li>Robert Muir &lt;rmuir&gt; </li>
+        
+<li>Ryan McKinley &lt;ryan&gt; </li>
+        
+<li>Sami Siren &lt;siren&gt; </li>
+        
+<li>Tommaso Teofili &lt;tommaso&gt;</li>
+        
+<li>Simon Willnauer &lt;simonw&gt; </li>
+        
+<li>Karl Wright &lt;kwright&gt; </li>
+        
+<li>Jukka Zitting &lt;jukka&gt; </li>
+        
+</ul>
+</div>
+
+  
+</div>
+<!--+
+    |end content
+    +-->
+<div class="clearboth">&nbsp;</div>
+</div>
+<div id="footer">
+<!--+
+    |start bottomstrip
+    +-->
+<div class="lastmodified">
+<script type="text/javascript"><!--
+document.write("Last Published: " + document.lastModified);
+//  --></script>
+</div>
+<div class="copyright">
+        Copyright &copy;
+         2009, 2010, 2011 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a>
+</div>
+<!--+
+    |end bottomstrip
+    +-->
+</div>
+</body>
+</html>

Propchange: incubator/lcf/site/publish/who.html
------------------------------------------------------------------------------
    svn:eol-style = native

Propchange: incubator/lcf/site/publish/who.html
------------------------------------------------------------------------------
    svn:keywords = Date Author Id Revision HeadURL

Added: incubator/lcf/site/publish/writing-authority-connectors.html
URL: http://svn.apache.org/viewvc/incubator/lcf/site/publish/writing-authority-connectors.html?rev=1137907&view=auto
==============================================================================
--- incubator/lcf/site/publish/writing-authority-connectors.html (added)
+++ incubator/lcf/site/publish/writing-authority-connectors.html Tue Jun 21 08:36:54 2011
@@ -0,0 +1,446 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+<head>
+<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
+<meta content="Apache Forrest" name="Generator">
+<meta name="Forrest-version" content="0.9">
+<meta name="Forrest-skin-name" content="lucene">
+<title>Writing authority connectors</title>
+<link type="text/css" href="skin/basic.css" rel="stylesheet">
+<link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet">
+<link media="print" type="text/css" href="skin/print.css" rel="stylesheet">
+<link type="text/css" href="skin/profile.css" rel="stylesheet">
+<script src="skin/getBlank.js" language="javascript" type="text/javascript"></script><script src="skin/getMenu.js" language="javascript" type="text/javascript"></script><script src="skin/fontsize.js" language="javascript" type="text/javascript"></script>
+<link rel="shortcut icon" href="images/favicon.ico">
+</head>
+<body onload="init()">
+<script type="text/javascript">ndeSetTextSize();</script>
+<div id="top">
+<!--+
+    |breadtrail
+    +-->
+<div class="breadtrail">
+<a href="http://www.apache.org/">Apache</a> &gt; <a href="http://incubator.apache.org/">Incubator</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script>
+</div>
+<!--+
+    |header
+    +-->
+<div class="header">
+<!--+
+    |start group logo
+    +-->
+<div class="grouplogo">
+<a href="http://www.apache.org"><img class="logoImage" alt="Apache" src="images/apache_feather.gif" title="Apache Software Foundation"></a>
+</div>
+<!--+
+    |end group logo
+    +-->
+<!--+
+    |start Project Logo
+    +-->
+<div class="projectlogo">
+<a href="http://incubator.apache.org/lcf"><img class="logoImage" alt="Apache ManifoldCF" src="images/ManifoldCF-logo.PNG" title="ManifoldCF"></a>
+</div>
+<!--+
+    |end Project Logo
+    +-->
+<!--+
+    |start Search
+    +-->
+<div class="searchbox">
+<form action="http://www.lucidimagination.com/search/" method="get" class="roundtopsmall">
+<input onFocus="getBlank (this, 'Search the site with Solr');" size="25" name="q" id="query" type="text" value="Search the site with Solr">&nbsp; 
+                    <input name="Search" value="Search" type="submit">
+</form>
+<div style="position: relative; top: -5px; left: -10px">Powered by <a href="http://www.lucidimagination.com" style="color: #033268">Lucid Imagination</a>
+</div>
+</div>
+<!--+
+    |end search
+    +-->
+<!--+
+    |start Tabs
+    +-->
+<ul id="tabs">
+<li class="current">
+<a class="selected" href="index.html">Main</a>
+</li>
+<li>
+<a class="unselected" href="http://cwiki.apache.org/confluence/display/CONNECTORS/Index">Wiki</a>
+</li>
+</ul>
+<!--+
+    |end Tabs
+    +-->
+</div>
+</div>
+<div id="main">
+<div id="publishedStrip">
+<!--+
+    |start Subtabs
+    +-->
+<div id="level2tabs"></div>
+<!--+
+    |end Endtabs
+    +-->
+<script type="text/javascript"><!--
+document.write("Last Published: " + document.lastModified);
+//  --></script>
+</div>
+<!--+
+    |breadtrail
+    +-->
+<div class="breadtrail">
+
+             &nbsp;
+           </div>
+<!--+
+    |start Menu, mainarea
+    +-->
+<!--+
+    |start Menu
+    +-->
+<div id="menu">
+<div onclick="SwitchMenu('menu_1.1', 'skin/')" id="menu_1.1Title" class="menutitle">About</div>
+<div id="menu_1.1" class="menuitemgroup">
+<div class="menuitem">
+<a href="index.html">Welcome</a>
+</div>
+<div class="menuitem">
+<a href="who.html">Who We Are</a>
+</div>
+<div class="menuitem">
+<a href="http://www.manning.com/wright/">Get the Book</a>
+</div>
+<div class="menuitem">
+<a href="http://www.cafepress.com/lucene/">Buy Stuff</a>
+</div>
+<div class="menuitem">
+<a href="http://www.apache.org/foundation/sponsorship.html">Sponsor Apache</a>
+</div>
+<div class="menuitem">
+<a href="http://www.apache.org/foundation/thanks.html">Sponsors of Apache</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.2', 'skin/')" id="menu_1.2Title" class="menutitle">Documentation</div>
+<div id="menu_1.2" class="menuitemgroup">
+<div class="menuitem">
+<a href="concepts.html">Concepts</a>
+</div>
+<div class="menuitem">
+<a href="included-connectors.html">Compatibility Matrix</a>
+</div>
+<div class="menuitem">
+<a href="faq.html">Frequently Asked Questions</a>
+</div>
+<div class="menuitem">
+<a href="programmatic-operation.html">API Documentation</a>
+</div>
+<div class="menuitem">
+<a href="javadoc.html">Javadoc</a>
+</div>
+<div class="menuitem">
+<a href="how-to-build-and-deploy.html">Building and Deploying</a>
+</div>
+<div class="menuitem">
+<a href="end-user-documentation.html">End-user Documentation (HTML)</a>
+</div>
+<div class="menuitem">
+<a href="end-user-documentation.pdf">End-user Documentation (PDF)</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.3', 'skin/')" id="menu_1.3Title" class="menutitle">Resources</div>
+<div id="menu_1.3" class="menuitemgroup">
+<div class="menuitem">
+<a href="download.html">Download</a>
+</div>
+<div class="menuitem">
+<a href="mail.html">Mailing Lists</a>
+</div>
+<div class="menuitem">
+<a href="developer-resources.html">Developer/Integrator Resources</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.4', 'skin/')" id="menu_1.4Title" class="menutitle">Related-Projects</div>
+<div id="menu_1.4" class="menuitemgroup">
+<div class="menuitem">
+<a href="http://incubator.apache.org/droids/">Droids</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/java/">Java</a>
+</div>
+<div class="menuitem">
+<a href="http://incubator.apache.org/lucene.net/">Lucene.Net</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/lucy/">Lucy</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/mahout/">Mahout</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/nutch/">Nutch</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/openrelevance/">Open Relevance</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/pylucene/">PyLucene</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/solr/">Solr</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/tika/">Tika</a>
+</div>
+</div>
+<div id="credit"></div>
+<div id="roundbottom">
+<img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div>
+<!--+
+  |alternative credits
+  +-->
+<div id="credit2"></div>
+</div>
+<!--+
+    |end Menu
+    +-->
+<!--+
+    |start content
+    +-->
+<div id="content">
+<h1>Writing authority connectors</h1>
+<div id="minitoc-area">
+<ul class="minitoc">
+<li>
+<a href="#Writing+an+Authority+Connector">Writing an Authority Connector</a>
+<ul class="minitoc">
+<li>
+<a href="#Key+concepts">Key concepts</a>
+</li>
+<li>
+<a href="#Implementing+the+Authority+Connector+class">Implementing the Authority Connector class</a>
+<ul class="minitoc">
+<li>
+<a href="#Principle+methods">Principle methods</a>
+</li>
+<li>
+<a href="#Notes+on+connector+UI+methods">Notes on connector UI methods</a>
+</li>
+</ul>
+</li>
+<li>
+<a href="#Implementation+support+provided+by+the+framework">Implementation support provided by the framework</a>
+</li>
+<li>
+<a href="#DO%27s+and+DON%27T+DO%27s">DO's and DON'T DO's</a>
+</li>
+</ul>
+</li>
+</ul>
+</div> 
+    
+<a name="N1000E"></a><a name="Writing+an+Authority+Connector"></a>
+<h2 class="h3">Writing an Authority Connector</h2>
+<div class="section">
+<p></p>
+<p>An authority connector to a repository allows a repository's security model to be enforced by a search engine.  Its only function is to convert a user name (which is often a Kerberos principal name) into a set of _access tokens_.</p>
+<p></p>
+<p>The definition of an access token within ManifoldCF for a given repository is completely defined by the connectors that deal with that repository, with one exception.  That exception is for Active Directory.  Active Directory is so prevalent as a repository authorization mechanism that ManifoldCF currently treats it as the "default" authority - that is, if you don't specify another authority when you define a repository connection, ManifoldCF presumes that you mean that Active Directory should be the controlling authority for the connection.  In that case, an access token is simply an Active Directory SID.</p>
+<p></p>
+<p>For those repositories that do not use Active Directory as their authorization mechanism, an authority connector should be written, along with the repository connector for the repository.  Access tokens in that case represent a contract between your implementation of the authority connector for the repository, and the repository connector for the repository.  They must work together to define access tokens that will limit document access when used properly within any search engine query.</p>
+<p></p>
+<p>As is the case with all connectors under the ManifoldCF umbrella, an authority connector consists of a single parts:</p>
+<p></p>
+<ul>
+        
+<li>A class implementing an interface (in this case, <em>org.apache.manifoldcf.authorities.interfaces.IAuthorityConnector</em>)</li>
+      
+</ul>
+<p></p>
+<a name="N10035"></a><a name="Key+concepts"></a>
+<h3 class="h4">Key concepts</h3>
+<p></p>
+<p>The authority connector abstraction makes use of, or introduces, the following concepts:</p>
+<p></p>
+<table class="ForrestTable" cellspacing="1" cellpadding="4">
+          
+<tr>
+<th colspan="1" rowspan="1">Concept</th><th colspan="1" rowspan="1">What it is</th>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Configuration parameters</td><td colspan="1" rowspan="1">A hierarchical structure, internally represented as an XML document, which describes a specific configuration of a specific authority connector, i.e. <strong>how</strong> the connector should do its job; see <em>org.apache.manifoldcf.core.interfaces.ConfigParams</em></td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Authority connection</td><td colspan="1" rowspan="1">An authority connector instance that has been furnished with configuration data</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">User name</td><td colspan="1" rowspan="1">The name of a user, which is often a Kerberos principal name, e.g. <em>john@apache.org</em></td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Access token</td><td colspan="1" rowspan="1">An arbitrary string, which is only meaningful within the context of a specific authority connector, that describes a quantum of authorization</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Connection management/threading/pooling model</td><td colspan="1" rowspan="1">How an individual authority connector class instance is managed and used</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Service interruption</td><td colspan="1" rowspan="1">A specific kind of exception that signals ManifoldCF that the output repository is unavailable, and gives a best estimate of when it might become available again; see <em>org.apache.manifoldcf.agents.interfaces.ServiceInterruption</em></td>
+</tr>
+        
+</table>
+<p></p>
+<a name="N10097"></a><a name="Implementing+the+Authority+Connector+class"></a>
+<h3 class="h4">Implementing the Authority Connector class</h3>
+<p></p>
+<p>A very good place to start is to read the javadoc for the authority connector interface.  You will note that the javadoc describes the usage and pooling model for a connector class pretty thoroughly.  It is very important to understand the model thoroughly in order to write reliable connectors!  Use of static variables, for one thing, must be done in a very careful way, to avoid issues that would be hard to detect with a cursory test.</p>
+<p></p>
+<p>The second thing to do is to examine some of the provided authority connector implementations.  The Documentum connector, the LiveLink connector, the Memex connector, and the Meridio connector all include authority connectors which demonstrate (to some degree) the sorts of techniques you will need for an effective implementation.  You will also note that all of these connectors extend a framework-provided authority connector base class, found at <em>org.apache.manifoldcf.authorities.authorities.BaseAuthorityConnector</em>.  This base class furnishes some basic bookkeeping logic for managing the connector pool, as well as default implementations of some of the less typical functionality a connector may have.  For example, connectors are allowed to have database tables of their own, which are instantiated when the connector is registered, and are torn down when the connector is removed.  This is, however, not very typical, and the base implementation reflects that.</p>
+<p></p>
+<a name="N100AC"></a><a name="Principle+methods"></a>
+<h4>Principle methods</h4>
+<p></p>
+<p>The principle methods an implementer should be concerned with for creating an authority connector are the following:</p>
+<p></p>
+<table class="ForrestTable" cellspacing="1" cellpadding="4">
+            
+<tr>
+<th colspan="1" rowspan="1">Method</th><th colspan="1" rowspan="1">What it should do</th>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>getAuthorizationResponse()</strong></td><td colspan="1" rowspan="1">Obtain the authorization response, given a user name</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>outputConfigurationHeader()</strong></td><td colspan="1" rowspan="1">Output the head-section part of an authority connection <em>ConfigParams</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>outputConfigurationBody()</strong></td><td colspan="1" rowspan="1">Output the body-section part of an authority connection <em>ConfigParams</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>processConfigurationPost()</strong></td><td colspan="1" rowspan="1">Receive and process form data from an authority connection <em>ConfigParams</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>viewConfiguration()</strong></td><td colspan="1" rowspan="1">Output the viewing HTML for an authority connection <em>ConfigParams</em> object</td>
+</tr>
+          
+</table>
+<p></p>
+<p>These methods come in two broad classes: (a) functional methods for doing the work of the connector; (b) UI methods for configuring a connection.  Together they do the heavy lifting of your connector.</p>
+<p></p>
+<p>The <em>getAuthorizationResponse()</em> method returns an <em>AuthorizationResponse</em> object, which can describe a number of conditions:</p>
+<p></p>
+<table class="ForrestTable" cellspacing="1" cellpadding="4">
+            
+<tr>
+<th colspan="1" rowspan="1">Condition</th><th colspan="1" rowspan="1">Meaning</th>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1">RESPONSE_OK</td><td colspan="1" rowspan="1">The access tokens for the user were successfully obtained from the repository, and are being returned</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1">RESPONSE_UNREACHABLE</td><td colspan="1" rowspan="1">The repository is currently unreachable, and appropriate disabling tokens are being returned</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1">RESPONSE_USERNOTFOUND</td><td colspan="1" rowspan="1">The user was not found within the repository, and appropriate disabling tokens are being returned</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1">RESPONSE_USERUNAUTHORIZED</td><td colspan="1" rowspan="1">The user was found, but was in some way disabled, and appropriate disabling tokens are being returned</td>
+</tr>
+          
+</table>
+<p></p>
+<p></p>
+<p>In all cases, the connector returns access tokens.  But in the case where token lookup has failed in some way, it is the responsibility of the connector to insure that inappropriate content is not viewed.  Usually, this is done by ingesting a "global deny" token attached to all documents from the given repository, and then having the associated authority connector return this global deny token when error conditions apply.</p>
+<p></p>
+<p></p>
+<a name="N1015C"></a><a name="Notes+on+connector+UI+methods"></a>
+<h4>Notes on connector UI methods</h4>
+<p></p>
+<p>The crawler UI uses a tabbed layout structure, and thus each of these elements must properly implement the tabbed model.  This means that the "header" methods above must add the desired tab names to a specified array, and the "body" methods must provide appropriate HTML which handles both the case where a tab is displayed, and where it is not displayed.  Also, it makes sense to use the appropriate css definitions, so that the connector UI pages have a similar look-and-feel to the rest of ManifoldCF's crawler ui.  We strongly suggest starting with one of the supplied authority connector's UI code, both for a description of the arguments to each page, and for some decent ideas of ways to organize your connector's UI code.</p>
+<p></p>
+<a name="N1016B"></a><a name="Implementation+support+provided+by+the+framework"></a>
+<h3 class="h4">Implementation support provided by the framework</h3>
+<p></p>
+<p>ManifoldCF's framework provides a number of helpful services designed to make the creation of a connector easier.  These services are summarized below.  (This is not an exhaustive list, by any means.)</p>
+<p></p>
+<ul>
+          
+<li>Lock management and synchronization (see <em>org.apache.manifoldcf.core.interfaces.LockManagerFactory</em>)</li>
+          
+<li>Cache management (see <em>org.apache.manifoldcf.core.interfaces.CacheManagerFactory</em>)</li>
+          
+<li>Local keystore management (see <em>org.apache.manifoldcf.core.KeystoreManagerFactory</em>)</li>
+          
+<li>Database management (see <em>org.apache.manifoldcf.core.DBInterfaceFactory</em>)</li>
+        
+</ul>
+<p></p>
+<p>For UI method support, these too are very useful:</p>
+<p></p>
+<ul>
+          
+<li>Multipart form processing (see <em>org.apache.manifoldcf.ui.multipart.MultipartWrapper</em>)</li>
+          
+<li>HTML encoding (see <em>org.apache.manifoldcf.ui.util.Encoder</em>)</li>
+          
+<li>HTML formatting (see <em>org.apache.manifoldcf.ui.util.Formatter</em>)</li>
+        
+</ul>
+<p></p>
+<a name="N101B2"></a><a name="DO%27s+and+DON%27T+DO%27s"></a>
+<h3 class="h4">DO's and DON'T DO's</h3>
+<p></p>
+<p>It's always a good idea to make use of an existing infrastructure component, if it's meant for that purpose, rather than inventing your own.  There are, however, some limitations we recommend you adhere to.</p>
+<p></p>
+<ul>
+          
+<li>DO make use of infrastructure components described in the section above</li>
+          
+<li>DON'T make use of infrastructure components that aren't mentioned, without checking first</li>
+          
+<li>NEVER write connector code that directly uses framework database tables, other than the ones installed and managed by your connector</li>
+        
+</ul>
+<p></p>
+<p>If you are tempted to violate these rules, it may well mean you don't understand something important.  At the very least, we'd like to know why.  Send email to connectors-dev@incubator.apache.org with a description of your problem and how you are tempted to solve it.</p>
+</div>
+  
+</div>
+<!--+
+    |end content
+    +-->
+<div class="clearboth">&nbsp;</div>
+</div>
+<div id="footer">
+<!--+
+    |start bottomstrip
+    +-->
+<div class="lastmodified">
+<script type="text/javascript"><!--
+document.write("Last Published: " + document.lastModified);
+//  --></script>
+</div>
+<div class="copyright">
+        Copyright &copy;
+         2009, 2010, 2011 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a>
+</div>
+<!--+
+    |end bottomstrip
+    +-->
+</div>
+</body>
+</html>

Propchange: incubator/lcf/site/publish/writing-authority-connectors.html
------------------------------------------------------------------------------
    svn:eol-style = native

Propchange: incubator/lcf/site/publish/writing-authority-connectors.html
------------------------------------------------------------------------------
    svn:keywords = Date Author Id Revision HeadURL

Added: incubator/lcf/site/publish/writing-output-connectors.html
URL: http://svn.apache.org/viewvc/incubator/lcf/site/publish/writing-output-connectors.html?rev=1137907&view=auto
==============================================================================
--- incubator/lcf/site/publish/writing-output-connectors.html (added)
+++ incubator/lcf/site/publish/writing-output-connectors.html Tue Jun 21 08:36:54 2011
@@ -0,0 +1,466 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+<head>
+<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
+<meta content="Apache Forrest" name="Generator">
+<meta name="Forrest-version" content="0.9">
+<meta name="Forrest-skin-name" content="lucene">
+<title>Writing output connectors</title>
+<link type="text/css" href="skin/basic.css" rel="stylesheet">
+<link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet">
+<link media="print" type="text/css" href="skin/print.css" rel="stylesheet">
+<link type="text/css" href="skin/profile.css" rel="stylesheet">
+<script src="skin/getBlank.js" language="javascript" type="text/javascript"></script><script src="skin/getMenu.js" language="javascript" type="text/javascript"></script><script src="skin/fontsize.js" language="javascript" type="text/javascript"></script>
+<link rel="shortcut icon" href="images/favicon.ico">
+</head>
+<body onload="init()">
+<script type="text/javascript">ndeSetTextSize();</script>
+<div id="top">
+<!--+
+    |breadtrail
+    +-->
+<div class="breadtrail">
+<a href="http://www.apache.org/">Apache</a> &gt; <a href="http://incubator.apache.org/">Incubator</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script>
+</div>
+<!--+
+    |header
+    +-->
+<div class="header">
+<!--+
+    |start group logo
+    +-->
+<div class="grouplogo">
+<a href="http://www.apache.org"><img class="logoImage" alt="Apache" src="images/apache_feather.gif" title="Apache Software Foundation"></a>
+</div>
+<!--+
+    |end group logo
+    +-->
+<!--+
+    |start Project Logo
+    +-->
+<div class="projectlogo">
+<a href="http://incubator.apache.org/lcf"><img class="logoImage" alt="Apache ManifoldCF" src="images/ManifoldCF-logo.PNG" title="ManifoldCF"></a>
+</div>
+<!--+
+    |end Project Logo
+    +-->
+<!--+
+    |start Search
+    +-->
+<div class="searchbox">
+<form action="http://www.lucidimagination.com/search/" method="get" class="roundtopsmall">
+<input onFocus="getBlank (this, 'Search the site with Solr');" size="25" name="q" id="query" type="text" value="Search the site with Solr">&nbsp; 
+                    <input name="Search" value="Search" type="submit">
+</form>
+<div style="position: relative; top: -5px; left: -10px">Powered by <a href="http://www.lucidimagination.com" style="color: #033268">Lucid Imagination</a>
+</div>
+</div>
+<!--+
+    |end search
+    +-->
+<!--+
+    |start Tabs
+    +-->
+<ul id="tabs">
+<li class="current">
+<a class="selected" href="index.html">Main</a>
+</li>
+<li>
+<a class="unselected" href="http://cwiki.apache.org/confluence/display/CONNECTORS/Index">Wiki</a>
+</li>
+</ul>
+<!--+
+    |end Tabs
+    +-->
+</div>
+</div>
+<div id="main">
+<div id="publishedStrip">
+<!--+
+    |start Subtabs
+    +-->
+<div id="level2tabs"></div>
+<!--+
+    |end Endtabs
+    +-->
+<script type="text/javascript"><!--
+document.write("Last Published: " + document.lastModified);
+//  --></script>
+</div>
+<!--+
+    |breadtrail
+    +-->
+<div class="breadtrail">
+
+             &nbsp;
+           </div>
+<!--+
+    |start Menu, mainarea
+    +-->
+<!--+
+    |start Menu
+    +-->
+<div id="menu">
+<div onclick="SwitchMenu('menu_1.1', 'skin/')" id="menu_1.1Title" class="menutitle">About</div>
+<div id="menu_1.1" class="menuitemgroup">
+<div class="menuitem">
+<a href="index.html">Welcome</a>
+</div>
+<div class="menuitem">
+<a href="who.html">Who We Are</a>
+</div>
+<div class="menuitem">
+<a href="http://www.manning.com/wright/">Get the Book</a>
+</div>
+<div class="menuitem">
+<a href="http://www.cafepress.com/lucene/">Buy Stuff</a>
+</div>
+<div class="menuitem">
+<a href="http://www.apache.org/foundation/sponsorship.html">Sponsor Apache</a>
+</div>
+<div class="menuitem">
+<a href="http://www.apache.org/foundation/thanks.html">Sponsors of Apache</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.2', 'skin/')" id="menu_1.2Title" class="menutitle">Documentation</div>
+<div id="menu_1.2" class="menuitemgroup">
+<div class="menuitem">
+<a href="concepts.html">Concepts</a>
+</div>
+<div class="menuitem">
+<a href="included-connectors.html">Compatibility Matrix</a>
+</div>
+<div class="menuitem">
+<a href="faq.html">Frequently Asked Questions</a>
+</div>
+<div class="menuitem">
+<a href="programmatic-operation.html">API Documentation</a>
+</div>
+<div class="menuitem">
+<a href="javadoc.html">Javadoc</a>
+</div>
+<div class="menuitem">
+<a href="how-to-build-and-deploy.html">Building and Deploying</a>
+</div>
+<div class="menuitem">
+<a href="end-user-documentation.html">End-user Documentation (HTML)</a>
+</div>
+<div class="menuitem">
+<a href="end-user-documentation.pdf">End-user Documentation (PDF)</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.3', 'skin/')" id="menu_1.3Title" class="menutitle">Resources</div>
+<div id="menu_1.3" class="menuitemgroup">
+<div class="menuitem">
+<a href="download.html">Download</a>
+</div>
+<div class="menuitem">
+<a href="mail.html">Mailing Lists</a>
+</div>
+<div class="menuitem">
+<a href="developer-resources.html">Developer/Integrator Resources</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.4', 'skin/')" id="menu_1.4Title" class="menutitle">Related-Projects</div>
+<div id="menu_1.4" class="menuitemgroup">
+<div class="menuitem">
+<a href="http://incubator.apache.org/droids/">Droids</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/java/">Java</a>
+</div>
+<div class="menuitem">
+<a href="http://incubator.apache.org/lucene.net/">Lucene.Net</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/lucy/">Lucy</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/mahout/">Mahout</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/nutch/">Nutch</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/openrelevance/">Open Relevance</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/pylucene/">PyLucene</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/solr/">Solr</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/tika/">Tika</a>
+</div>
+</div>
+<div id="credit"></div>
+<div id="roundbottom">
+<img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div>
+<!--+
+  |alternative credits
+  +-->
+<div id="credit2"></div>
+</div>
+<!--+
+    |end Menu
+    +-->
+<!--+
+    |start content
+    +-->
+<div id="content">
+<h1>Writing output connectors</h1>
+<div id="minitoc-area">
+<ul class="minitoc">
+<li>
+<a href="#Writing+an+Output+Connector">Writing an Output Connector</a>
+<ul class="minitoc">
+<li>
+<a href="#Key+concepts">Key concepts</a>
+</li>
+<li>
+<a href="#Implementing+the+Output+Connector+class">Implementing the Output Connector class</a>
+<ul class="minitoc">
+<li>
+<a href="#Principle+methods">Principle methods</a>
+</li>
+<li>
+<a href="#Choosing+the+form+of+the+output+version+string">Choosing the form of the output version string</a>
+</li>
+<li>
+<a href="#Notes+on+connector+UI+methods">Notes on connector UI methods</a>
+</li>
+</ul>
+</li>
+<li>
+<a href="#Implementation+support+provided+by+the+framework">Implementation support provided by the framework</a>
+</li>
+<li>
+<a href="#DO%27s+and+DON%27T+DO%27s">DO's and DON'T DO's</a>
+</li>
+</ul>
+</li>
+</ul>
+</div> 
+    
+<a name="N1000E"></a><a name="Writing+an+Output+Connector"></a>
+<h2 class="h3">Writing an Output Connector</h2>
+<div class="section">
+<p></p>
+<p>An output connector furnishes the mechanism by which content that has been fetched from a repository gets handed to a back-end repository for processing.  It also furnishes a mechanism for removing previously-processed content from that back end repository.</p>
+<p></p>
+<p>As is the case with all connectors under the ManifoldCF umbrella, an output connector consists of a single part, which is:</p>
+<p></p>
+<ul>
+        
+<li>A class implementing an interface (in this case, <em>org.apache.manifoldcf.agents.interfaces.IOutputConnector</em>)</li>
+      
+</ul>
+<p></p>
+<a name="N1002B"></a><a name="Key+concepts"></a>
+<h3 class="h4">Key concepts</h3>
+<p></p>
+<p>The output connector abstraction makes use of, or introduces, the following concepts:</p>
+<p></p>
+<table class="ForrestTable" cellspacing="1" cellpadding="4">
+          
+<tr>
+<th colspan="1" rowspan="1">Concept</th><th colspan="1" rowspan="1">What it is</th>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Configuration parameters</td><td colspan="1" rowspan="1">A hierarchical structure, internally represented as an XML document, which describes a specific configuration of a specific output connector, i.e. <strong>how</strong> the connector should do its job; see <em>org.apache.manifoldcf.core.interfaces.ConfigParams</em></td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Output connection</td><td colspan="1" rowspan="1">An output connector instance that has been furnished with configuration data</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Document URI</td><td colspan="1" rowspan="1">The unique URI (or, in some cases, file IRI) of a document, which is meant to be displayed in search engine results as the link to the document</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Repository document</td><td colspan="1" rowspan="1">An object that describes a document's contents, including raw document data (as a stream), metadata (as either strings or streams), and access tokens; see <em>org.apache.manifoldcf.agents.interfaces.RepositoryDocument</em></td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Connection management/threading/pooling model</td><td colspan="1" rowspan="1">How an individual output connector class instance is managed and used</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Activity infrastructure</td><td colspan="1" rowspan="1">The framework API provided to specific methods allowing those methods to perform specific actions within the framework, e.g. recording activities; see <em>org.apache.manifoldcf.agents.interfaces.IOutputAddActivity</em> and <em>org.apache.manifoldcf.agents.interfaces.IOutputRemoveActivity</em></td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Output specification</td><td colspan="1" rowspan="1">A hierarchical structure, internally represented as an XML document, which describes <strong>what</strong> a specific output connector should do in the context of a specific job; see <em>org.apache.manifoldcf.agents.interfaces.OutputSpecification</em></td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Output version string</td><td colspan="1" rowspan="1">A simple string, used for comparison purposes, that allows ManifoldCF to figure out if an ingestion operation needs to be repeated as a result of changes to the output specification in effect for a document</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Service interruption</td><td colspan="1" rowspan="1">A specific kind of exception that signals ManifoldCF that the output repository is unavailable, and gives a best estimate of when it might become available again; see <em>org.apache.manifoldcf.agents.interfaces.ServiceInterruption</em></td>
+</tr>
+        
+</table>
+<p></p>
+<p></p>
+<a name="N100B7"></a><a name="Implementing+the+Output+Connector+class"></a>
+<h3 class="h4">Implementing the Output Connector class</h3>
+<p></p>
+<p>A very good place to start is to read the javadoc for the output connector interface.  You will note that the javadoc describes the usage and pooling model for a connector class pretty thoroughly.  It is very important to understand the model thoroughly in order to write reliable connectors!  Use of static variables, for one thing, must be done in a very careful way, to avoid issues that would be hard to detect with a cursory test.</p>
+<p></p>
+<p>The second thing to do is to examine some of the provided output connector implementations.  The GTS connector, the SOLR connector, and the Null Output connector all are output connectors which demonstrate (to some degree) the sorts of techniques you will need for an effective implementation.  You will also note that all of these connectors extend a framework-provided output connector base class, found at <em>org.apache.manifoldcf.agents.output.BaseOutputConnector</em>.  This base class furnishes some basic bookkeeping logic for managing the connector pool, as well as default implementations of some of the less typical functionality a connector may have.  For example, connectors are allowed to have database tables of their own, which are instantiated when the connector is registered, and are torn down when the connector is removed.  This is, however, not very typical, and the base implementation reflects that.</p>
+<p></p>
+<a name="N100CC"></a><a name="Principle+methods"></a>
+<h4>Principle methods</h4>
+<p></p>
+<p>The principle methods an implementer should be concerned with for creating an output connector are the following:</p>
+<p></p>
+<table class="ForrestTable" cellspacing="1" cellpadding="4">
+            
+<tr>
+<th colspan="1" rowspan="1">Method</th><th colspan="1" rowspan="1">What it should do</th>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>checkDocumentIndexable()</strong></td><td colspan="1" rowspan="1">Decide whether a file is indexable or not</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>getOutputDescription()</strong></td><td colspan="1" rowspan="1">Use the supplied output specification to come up with an output version string</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>addOrReplaceDocument()</strong></td><td colspan="1" rowspan="1">Add or replace the specified document within the target repository, or signal if the document cannot be handled</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>removeDocument()</strong></td><td colspan="1" rowspan="1">Remove the specified document from the target repository</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>outputConfigurationHeader()</strong></td><td colspan="1" rowspan="1">Output the head-section part of an output connection <em>ConfigParams</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>outputConfigurationBody()</strong></td><td colspan="1" rowspan="1">Output the body-section part of an output connection <em>ConfigParams</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>processConfigurationPost()</strong></td><td colspan="1" rowspan="1">Receive and process form data from an output connection <em>ConfigParams</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>viewConfiguration()</strong></td><td colspan="1" rowspan="1">Output the viewing HTML for an output connection <em>ConfigParams</em> object</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>outputSpecificationHeader()</strong></td><td colspan="1" rowspan="1">Output the head-section part of an <em>OutputSpecification</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>outputSpecificationBody()</strong></td><td colspan="1" rowspan="1">Output the body-section part of an <em>OutputSpecification</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>processSpecificationPost()</strong></td><td colspan="1" rowspan="1">Receive and process form data from an <em>OutputSpecification</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>viewSpecification()</strong></td><td colspan="1" rowspan="1">Output the viewing page for an <em>OutputSpecification</em> object</td>
+</tr>
+          
+</table>
+<p></p>
+<p>These methods come in three broad classes: (a) functional methods for doing the work of the connector; (b) UI methods for configuring a connection; and (c) UI methods for editing the output specification for a job.  Together they do the heavy lifting of your connector.  But before you can write any code at all, you need to plan things out a bit.</p>
+<p></p>
+<a name="N1018A"></a><a name="Choosing+the+form+of+the+output+version+string"></a>
+<h4>Choosing the form of the output version string</h4>
+<p></p>
+<p>The output version string is used by ManifoldCF to determine whether or not the output specification or configuration changed in such a way as to require that the document be reprocessed.  ManifoldCF therefore requests the output version string for any document that is ready for processing, and usually does not process the document again if the returned output version string agrees with the output version string it has stored.</p>
+<p></p>
+<p>Thinking about it more carefully, it is clear that what an output connector writer needs to do is include everything in the output version string that could potentially affect how the document gets ingested, save that which is specific to the repository connector.  That may include bits of output connector configuration information, as well as data from the output specification.  When it's time to ingest, it's usually the correct thing to do to obtain the necessary data for ingestion out of the output version string, rather than calculating it or fetching it anew, because that guarantees that the document processing was done in a manner that agrees with its recorded output version string, thus eliminating any chance of ManifoldCF getting confused.</p>
+<p></p>
+<a name="N1019D"></a><a name="Notes+on+connector+UI+methods"></a>
+<h4>Notes on connector UI methods</h4>
+<p></p>
+<p>The crawler UI uses a tabbed layout structure, and thus each of the UI methods must properly implement the tabbed model.  This means that the "header" methods above must add the desired tab names to a specified array, and the "body" methods must provide appropriate HTML which handles both the case where a tab is displayed, and where it is not displayed.  Also, it makes sense to use the appropriate css definitions, so that the connector UI pages have a similar look-and-feel to the rest of ManifoldCF's crawler ui.  We strongly suggest starting with one of the supplied connector's UI code, both for a description of the arguments to each method, and for some decent ideas of ways to organize your connector's UI code.</p>
+<p></p>
+<p>Please also note that it is good practice to name the form fields in your HTML in such a way that they cannot collide with form fields that may come from the framework's HTML or any specific repository connector's HTML.  The <em>OutputSpecification</em> HTML especially may be prone to collisions, because within any given job, this HTML is included in the same page as HTML from the chosen repository connector.</p>
+<p></p>
+<p></p>
+<a name="N101B6"></a><a name="Implementation+support+provided+by+the+framework"></a>
+<h3 class="h4">Implementation support provided by the framework</h3>
+<p></p>
+<p>ManifoldCF's framework provides a number of helpful services designed to make the creation of a connector easier.  These services are summarized below.  (This is not an exhaustive list, by any means.)</p>
+<p></p>
+<ul>
+          
+<li>Lock management and synchronization (see <em>org.apache.manifoldcf.core.interfaces.LockManagerFactory</em>)</li>
+          
+<li>Cache management (see <em>org.apache.manifoldcf.core.interfaces.CacheManagerFactory</em>)</li>
+          
+<li>Local keystore management (see <em>org.apache.manifoldcf.core.KeystoreManagerFactory</em>)</li>
+          
+<li>Database management (see <em>org.apache.manifoldcf.core.DBInterfaceFactory</em>)</li>
+        
+</ul>
+<p></p>
+<p>For UI method support, these too are very useful:</p>
+<p></p>
+<ul>
+          
+<li>Multipart form processing (see <em>org.apache.manifoldcf.ui.multipart.MultipartWrapper</em>)</li>
+          
+<li>HTML encoding (see <em>org.apache.manifoldcf.ui.util.Encoder</em>)</li>
+          
+<li>HTML formatting (see <em>org.apache.manifoldcf.ui.util.Formatter</em>)</li>
+        
+</ul>
+<p></p>
+<a name="N101FD"></a><a name="DO%27s+and+DON%27T+DO%27s"></a>
+<h3 class="h4">DO's and DON'T DO's</h3>
+<p></p>
+<p>It's always a good idea to make use of an existing infrastructure component, if it's meant for that purpose, rather than inventing your own.  There are, however, some limitations we recommend you adhere to.</p>
+<p></p>
+<ul>
+          
+<li>DO make use of infrastructure components described in the section above</li>
+          
+<li>DON'T make use of infrastructure components that aren't mentioned, without checking first</li>
+          
+<li>NEVER write connector code that directly uses framework database tables, other than the ones installed and managed by your connector</li>
+        
+</ul>
+<p></p>
+<p>If you are tempted to violate these rules, it may well mean you don't understand something important.  At the very least, we'd like to know why.  Send email to connectors-dev@incubator.apache.org with a description of your problem and how you are tempted to solve it.</p>
+</div>
+  
+</div>
+<!--+
+    |end content
+    +-->
+<div class="clearboth">&nbsp;</div>
+</div>
+<div id="footer">
+<!--+
+    |start bottomstrip
+    +-->
+<div class="lastmodified">
+<script type="text/javascript"><!--
+document.write("Last Published: " + document.lastModified);
+//  --></script>
+</div>
+<div class="copyright">
+        Copyright &copy;
+         2009, 2010, 2011 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a>
+</div>
+<!--+
+    |end bottomstrip
+    +-->
+</div>
+</body>
+</html>

Propchange: incubator/lcf/site/publish/writing-output-connectors.html
------------------------------------------------------------------------------
    svn:eol-style = native

Propchange: incubator/lcf/site/publish/writing-output-connectors.html
------------------------------------------------------------------------------
    svn:keywords = Date Author Id Revision HeadURL

Added: incubator/lcf/site/publish/writing-repository-connectors.html
URL: http://svn.apache.org/viewvc/incubator/lcf/site/publish/writing-repository-connectors.html?rev=1137907&view=auto
==============================================================================
--- incubator/lcf/site/publish/writing-repository-connectors.html (added)
+++ incubator/lcf/site/publish/writing-repository-connectors.html Tue Jun 21 08:36:54 2011
@@ -0,0 +1,551 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+<head>
+<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
+<meta content="Apache Forrest" name="Generator">
+<meta name="Forrest-version" content="0.9">
+<meta name="Forrest-skin-name" content="lucene">
+<title>Writing repository connectors</title>
+<link type="text/css" href="skin/basic.css" rel="stylesheet">
+<link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet">
+<link media="print" type="text/css" href="skin/print.css" rel="stylesheet">
+<link type="text/css" href="skin/profile.css" rel="stylesheet">
+<script src="skin/getBlank.js" language="javascript" type="text/javascript"></script><script src="skin/getMenu.js" language="javascript" type="text/javascript"></script><script src="skin/fontsize.js" language="javascript" type="text/javascript"></script>
+<link rel="shortcut icon" href="images/favicon.ico">
+</head>
+<body onload="init()">
+<script type="text/javascript">ndeSetTextSize();</script>
+<div id="top">
+<!--+
+    |breadtrail
+    +-->
+<div class="breadtrail">
+<a href="http://www.apache.org/">Apache</a> &gt; <a href="http://incubator.apache.org/">Incubator</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script>
+</div>
+<!--+
+    |header
+    +-->
+<div class="header">
+<!--+
+    |start group logo
+    +-->
+<div class="grouplogo">
+<a href="http://www.apache.org"><img class="logoImage" alt="Apache" src="images/apache_feather.gif" title="Apache Software Foundation"></a>
+</div>
+<!--+
+    |end group logo
+    +-->
+<!--+
+    |start Project Logo
+    +-->
+<div class="projectlogo">
+<a href="http://incubator.apache.org/lcf"><img class="logoImage" alt="Apache ManifoldCF" src="images/ManifoldCF-logo.PNG" title="ManifoldCF"></a>
+</div>
+<!--+
+    |end Project Logo
+    +-->
+<!--+
+    |start Search
+    +-->
+<div class="searchbox">
+<form action="http://www.lucidimagination.com/search/" method="get" class="roundtopsmall">
+<input onFocus="getBlank (this, 'Search the site with Solr');" size="25" name="q" id="query" type="text" value="Search the site with Solr">&nbsp; 
+                    <input name="Search" value="Search" type="submit">
+</form>
+<div style="position: relative; top: -5px; left: -10px">Powered by <a href="http://www.lucidimagination.com" style="color: #033268">Lucid Imagination</a>
+</div>
+</div>
+<!--+
+    |end search
+    +-->
+<!--+
+    |start Tabs
+    +-->
+<ul id="tabs">
+<li class="current">
+<a class="selected" href="index.html">Main</a>
+</li>
+<li>
+<a class="unselected" href="http://cwiki.apache.org/confluence/display/CONNECTORS/Index">Wiki</a>
+</li>
+</ul>
+<!--+
+    |end Tabs
+    +-->
+</div>
+</div>
+<div id="main">
+<div id="publishedStrip">
+<!--+
+    |start Subtabs
+    +-->
+<div id="level2tabs"></div>
+<!--+
+    |end Endtabs
+    +-->
+<script type="text/javascript"><!--
+document.write("Last Published: " + document.lastModified);
+//  --></script>
+</div>
+<!--+
+    |breadtrail
+    +-->
+<div class="breadtrail">
+
+             &nbsp;
+           </div>
+<!--+
+    |start Menu, mainarea
+    +-->
+<!--+
+    |start Menu
+    +-->
+<div id="menu">
+<div onclick="SwitchMenu('menu_1.1', 'skin/')" id="menu_1.1Title" class="menutitle">About</div>
+<div id="menu_1.1" class="menuitemgroup">
+<div class="menuitem">
+<a href="index.html">Welcome</a>
+</div>
+<div class="menuitem">
+<a href="who.html">Who We Are</a>
+</div>
+<div class="menuitem">
+<a href="http://www.manning.com/wright/">Get the Book</a>
+</div>
+<div class="menuitem">
+<a href="http://www.cafepress.com/lucene/">Buy Stuff</a>
+</div>
+<div class="menuitem">
+<a href="http://www.apache.org/foundation/sponsorship.html">Sponsor Apache</a>
+</div>
+<div class="menuitem">
+<a href="http://www.apache.org/foundation/thanks.html">Sponsors of Apache</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.2', 'skin/')" id="menu_1.2Title" class="menutitle">Documentation</div>
+<div id="menu_1.2" class="menuitemgroup">
+<div class="menuitem">
+<a href="concepts.html">Concepts</a>
+</div>
+<div class="menuitem">
+<a href="included-connectors.html">Compatibility Matrix</a>
+</div>
+<div class="menuitem">
+<a href="faq.html">Frequently Asked Questions</a>
+</div>
+<div class="menuitem">
+<a href="programmatic-operation.html">API Documentation</a>
+</div>
+<div class="menuitem">
+<a href="javadoc.html">Javadoc</a>
+</div>
+<div class="menuitem">
+<a href="how-to-build-and-deploy.html">Building and Deploying</a>
+</div>
+<div class="menuitem">
+<a href="end-user-documentation.html">End-user Documentation (HTML)</a>
+</div>
+<div class="menuitem">
+<a href="end-user-documentation.pdf">End-user Documentation (PDF)</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.3', 'skin/')" id="menu_1.3Title" class="menutitle">Resources</div>
+<div id="menu_1.3" class="menuitemgroup">
+<div class="menuitem">
+<a href="download.html">Download</a>
+</div>
+<div class="menuitem">
+<a href="mail.html">Mailing Lists</a>
+</div>
+<div class="menuitem">
+<a href="developer-resources.html">Developer/Integrator Resources</a>
+</div>
+</div>
+<div onclick="SwitchMenu('menu_1.4', 'skin/')" id="menu_1.4Title" class="menutitle">Related-Projects</div>
+<div id="menu_1.4" class="menuitemgroup">
+<div class="menuitem">
+<a href="http://incubator.apache.org/droids/">Droids</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/java/">Java</a>
+</div>
+<div class="menuitem">
+<a href="http://incubator.apache.org/lucene.net/">Lucene.Net</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/lucy/">Lucy</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/mahout/">Mahout</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/nutch/">Nutch</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/openrelevance/">Open Relevance</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/pylucene/">PyLucene</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/solr/">Solr</a>
+</div>
+<div class="menuitem">
+<a href="http://lucene.apache.org/tika/">Tika</a>
+</div>
+</div>
+<div id="credit"></div>
+<div id="roundbottom">
+<img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div>
+<!--+
+  |alternative credits
+  +-->
+<div id="credit2"></div>
+</div>
+<!--+
+    |end Menu
+    +-->
+<!--+
+    |start content
+    +-->
+<div id="content">
+<h1>Writing repository connectors</h1>
+<div id="minitoc-area">
+<ul class="minitoc">
+<li>
+<a href="#Writing+repository+connectors">Writing repository connectors</a>
+<ul class="minitoc">
+<li>
+<a href="#Key+concepts">Key concepts</a>
+</li>
+<li>
+<a href="#Implementing+the+Repository+Connector+class">Implementing the Repository Connector class</a>
+<ul class="minitoc">
+<li>
+<a href="#Principle+methods">Principle methods</a>
+</li>
+<li>
+<a href="#Model">Model</a>
+</li>
+<li>
+<a href="#Choosing+a+document+identifier+format">Choosing a document identifier format</a>
+</li>
+<li>
+<a href="#Choosing+the+form+of+the+document+version+string">Choosing the form of the document version string</a>
+</li>
+<li>
+<a href="#Notes+on+connector+UI+methods">Notes on connector UI methods</a>
+</li>
+</ul>
+</li>
+<li>
+<a href="#Implementation+support+provided+by+the+framework">Implementation support provided by the framework</a>
+</li>
+<li>
+<a href="#DO%27s+and+DON%27T+DO%27s">DO's and DON'T DO's</a>
+</li>
+</ul>
+</li>
+</ul>
+</div> 
+    
+<a name="N1000E"></a><a name="Writing+repository+connectors"></a>
+<h2 class="h3">Writing repository connectors</h2>
+<div class="section">
+<p></p>
+<p>A repository connector furnishes the mechanism for obtaining documents, metadata, and authority tokens from a repository.  The documents are expected to be handed to an output connector (described elsewhere) for ingestion into some other back-end repository.</p>
+<p></p>
+<p>As is the case with all connectors under the ManifoldCF umbrella, an output connector consists of only one part:</p>
+<p></p>
+<ul>
+        
+<li>A class implementing an interface (in this case, <em>org.apache.manifoldcf.crawler.interfaces.IRepositoryConnector</em>)</li>
+      
+</ul>
+<p></p>
+<a name="N1002B"></a><a name="Key+concepts"></a>
+<h3 class="h4">Key concepts</h3>
+<p></p>
+<p>The repository connector abstraction makes use of, or introduces, the following concepts:</p>
+<p></p>
+<table class="ForrestTable" cellspacing="1" cellpadding="4">
+          
+<tr>
+<th colspan="1" rowspan="1">Concept</th><th colspan="1" rowspan="1">What it is</th>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Configuration parameters</td><td colspan="1" rowspan="1">A hierarchical structure, internally represented as an XML document, which describes a specific configuration of a specific repository connector, i.e. <strong>how</strong> the connector should do its job; see <em>org.apache.manifoldcf.core.interfaces.ConfigParams</em></td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Repository connection</td><td colspan="1" rowspan="1">A repository connector instance that has been furnished with configuration data</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Document identifier</td><td colspan="1" rowspan="1">An arbitrary identifier, whose meaning determined only within the context of a specific repository connector, which the connector uses to describe a document within a repository</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Document URI</td><td colspan="1" rowspan="1">The unique URI (or, in some cases, file IRI) of a document, which is meant to be displayed in search engine results as the link to the document</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Repository document</td><td colspan="1" rowspan="1">An object that describes a document's contents, including raw document data (as a stream), metadata (as either strings or streams), and access tokens; see <em>org.apache.manifoldcf.agents.interfaces.RepositoryDocument</em></td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Access token</td><td colspan="1" rowspan="1">A string, which is only meaningful in the context of a specific authority, that describes a quantum of authorization for a user</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Connection management/threading/pooling model</td><td colspan="1" rowspan="1">How an individual repository connector class instance is managed and used</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Activity infrastructure</td><td colspan="1" rowspan="1">The framework API provided to specific methods allowing those methods to perform specific actions within the framework, e.g. recording the activity history; see <em>org.apache.manifoldcf.crawler.interfaces.IVersionActivity</em>, and <em>org.apache.manifoldcf.crawler.interfaces.IProcessActivity</em>, and <em>org.apache.manifoldcf.crawler.interfaces.ISeedingActivity</em></td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Document specification</td><td colspan="1" rowspan="1">A hierarchical structure, internally represented as an XML document, which describes <strong>what</strong> a specific repository connector should do in the context of a specific job; see <em>org.apache.manifoldcf.crawler.interfaces.DocumentSpecification</em></td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Document version string</td><td colspan="1" rowspan="1">A simple string, used for comparison purposes, that allows ManifoldCF to figure out if a fetch or ingestion operation needs to be repeated as a result of changes to the document specification in effect for a document, or because of changes to the document itself</td>
+</tr>
+          
+<tr>
+<td colspan="1" rowspan="1">Service interruption</td><td colspan="1" rowspan="1">A specific kind of exception that signals ManifoldCF that the output repository is unavailable, and gives a best estimate of when it might become available again; see <em>org.apache.manifoldcf.agents.interfaces.ServiceInterruption</em></td>
+</tr>
+        
+</table>
+<p></p>
+<a name="N100CC"></a><a name="Implementing+the+Repository+Connector+class"></a>
+<h3 class="h4">Implementing the Repository Connector class</h3>
+<p></p>
+<p>A very good place to start is to read the javadoc for the repository connector interface.  You will note that the javadoc describes the usage and pooling model for a connector class pretty thoroughly.  It is very important to understand the model thoroughly in order to write reliable connectors!  Use of static variables, for one thing, must be done in a very careful way, to avoid issues that would be hard to detect with a cursory test.</p>
+<p></p>
+<p>The second thing to do is to examine some of the provided repository connector implementations.  There are a wide variety of connectors include with ManifoldCF that exercise just about every aspect of the repository connector interface.  These are:</p>
+<p></p>
+<ul>
+          
+<li>Documentum (uses RMI to segregate native code, etc.)</li>
+          
+<li>FileNet (also uses RMI, but because it is picky about its open-source jar versions)</li>
+          
+<li>File system (a good, but simple, example)</li>
+          
+<li>LiveLink (demonstrates use of local keystore infrastructure)</li>
+          
+<li>Meridio (local keystore, web services, result sets)</li>
+          
+<li>SharePoint (local keystore, web services)</li>
+          
+<li>RSS (local keystore, binning)</li>
+          
+<li>Web (local database schema, local keystore, binning, events and prerequisites, cache management)</li>
+        
+</ul>
+<p></p>
+<p>You will also note that all of these connectors extend a framework-provided repository connector base class, found at <em>org.apache.manifoldcf.crawler.connectors.BaseRepositoryConnector</em>.  This base class furnishes some basic bookkeeping logic for managing the connector pool, as well as default implementations of some of the less typical functionality a connector may have.  For example, connectors are allowed to have database tables of their own, which are instantiated when the connector is registered, and are torn down when the connector is removed.  This is, however, not very typical, and the base implementation reflects that.</p>
+<p></p>
+<a name="N10103"></a><a name="Principle+methods"></a>
+<h4>Principle methods</h4>
+<p></p>
+<p>The principle methods an implementer should be concerned with for creating a repository connector are the following:</p>
+<p></p>
+<table class="ForrestTable" cellspacing="1" cellpadding="4">
+            
+<tr>
+<th colspan="1" rowspan="1">Method</th><th colspan="1" rowspan="1">What it should do</th>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>addSeedDocuments()</strong></td><td colspan="1" rowspan="1">Use the supplied document specification to come up with an initial set of document identifiers</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>getDocumentVersions()</strong></td><td colspan="1" rowspan="1">Come up with a version string for each of the documents described by the supplied set of document identifiers, or signal if the document is no longer present</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>processDocuments()</strong></td><td colspan="1" rowspan="1">Take the appropriate action (e.g. ingest, or extract references from, or whatever) for a given set of documents described by document identifier and version string</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>outputConfigurationHeader()</strong></td><td colspan="1" rowspan="1">Output the head-section part of a repository connection <em>ConfigParams</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>outputConfigurationBody()</strong></td><td colspan="1" rowspan="1">Output the body-section part of a repository connection <em>ConfigParams</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>processConfigurationPost()</strong></td><td colspan="1" rowspan="1">Receive and process form data from a repository connection <em>ConfigParams</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>viewConfiguration()</strong></td><td colspan="1" rowspan="1">Output the viewing HTML for a repository connection <em>ConfigParams</em> object</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>outputSpecificationHeader()</strong></td><td colspan="1" rowspan="1">Output the head-section part of an <em>DocumentSpecification</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>outputSpecificationBody()</strong></td><td colspan="1" rowspan="1">Output the body-section part of an <em>DocumentSpecification</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>processSpecificationPost()</strong></td><td colspan="1" rowspan="1">Receive and process form data from an <em>DocumentSpecification</em> editing page</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><strong>viewSpecification()</strong></td><td colspan="1" rowspan="1">Output the viewing page for an <em>DocumentSpecification</em> object</td>
+</tr>
+          
+</table>
+<p></p>
+<p>These methods come in three broad classes: (a) functional methods for doing the work of the connector; (b) UI methods for configuring a connection; and (c) UI methods for editing the document specification for a job.  Together they do the heavy lifting of your connector.  But before you can write any code at all, you need to plan things out a bit.</p>
+<p></p>
+<a name="N101B6"></a><a name="Model"></a>
+<h4>Model</h4>
+<p></p>
+<p>Each connector must declare a specific model which it adheres to.  These models basically describe what the <strong>addSeedDocuments()</strong> method actually does, and are described below.</p>
+<p></p>
+<table class="ForrestTable" cellspacing="1" cellpadding="4">
+            
+<tr>
+<th colspan="1" rowspan="1">Model</th><th colspan="1" rowspan="1">Description</th>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><em>MODEL_ADD</em></td><td colspan="1" rowspan="1">The <strong>addSeedDocuments()</strong> method supplies at least all the matching documents that have been added to the repository, within the specified time interval</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><em>MODEL_ADD_CHANGE</em></td><td colspan="1" rowspan="1">The <strong>addSeedDocuments()</strong> method supplies at least those matching documents that have been added or changed in the repository, within the specified time interval</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><em>MODEL_ADD_CHANGE_DELETE</em></td><td colspan="1" rowspan="1">The <strong>addSeedDocuments()</strong> method supplies at least those matching documents that have been added, changed, or removed in the repository, within the specified time interval</td>
+</tr>
+            
+<tr>
+<td colspan="1" rowspan="1"><em>MODEL_PARTIAL</em></td><td colspan="1" rowspan="1">The <strong>addSeedDocuments()</strong> does not return a complete list of documents that match the criteria and time interval, because some of those documents are no longer discoverable</td>
+</tr>
+          
+</table>
+<p></p>
+<p>Note that the choice of model is actually much more subtle than the above description might indicate.  It may, for one thing, be affected by characteristics of the repository, such as whether the repository considers a document to have been changed if its security information was changed.  This would mean that, even though most document changes are picked up and thus one might be tempted to declare the connector to be <em>MODEL_ADD_CHANGE</em>, the correct choice would in fact be <em>MODEL_ADD</em>.</p>
+<p></p>
+<p>Another subtle point is what documents the connector is actually supposed to return by means of the <strong>addSeedDocuments()</strong> method.  The start time and end time parameters handed to the method do not have to be strictly adhered to, for instance; it is always okay to return more documents.  It is never okay for the connector to return fewer documents than were requested, on the other hand.</p>
+<p></p>
+<a name="N10221"></a><a name="Choosing+a+document+identifier+format"></a>
+<h4>Choosing a document identifier format</h4>
+<p></p>
+<p>In order to decide on the format for a document identifier, you need to understand what this identifier is used for, and what it represents.  A document identifier usually corresponds to some entity within the source repository, such as a document or a folder.  Note that there is <strong>no</strong> requirement that the identifier represent indexable content.</p>
+<p></p>
+<p>The document identifier must be capable of furnishing enough information to:</p>
+<p></p>
+<ul>
+            
+<li>Calculate a version string for the document</li>
+            
+<li>Find child references for the document</li>
+            
+<li>Get the document's content, metadata, and access tokens</li>
+          
+</ul>
+<p></p>
+<p>We highly recommend that no additional information be included in the document identifier, other than what is needed for the above, as that will almost certainly cause problems.</p>
+<p></p>
+<a name="N1024A"></a><a name="Choosing+the+form+of+the+document+version+string"></a>
+<h4>Choosing the form of the document version string</h4>
+<p></p>
+<p>The document version string is used by ManifoldCF to determine whether or not the document or configuration changed in such a way as to require that the document be reprocessed.  ManifoldCF therefore requests the version string for any document that is ready for processing, and usually does not process the document again if the returned version string agrees with the version string it has stored.</p>
+<p></p>
+<p>Thinking about it more carefully, it is clear that what a connector writer needs to do is include everything in the version string that could potentially affect how the document gets processed.  That may include the version of the document in the repository, bits of configuration information, metadata, and even access tokens (if the underlying repository versions these things independently from the document itself).  Storing all of that information in the version string seems like a lot - but the string is unlimited in length, and it actually serves another useful purpose to do it that way.  Specifically, when it comes time to do the actual processing, it's often the correct thing to do to obtain the necessary data out of the version string, rather than calculating it or fetching it anew.  That way of working guarantees that the document processing was done in a manner that agrees with its recorded version string, thus eliminating any chance of ManifoldCF getting confused
 .</p>
+<p></p>
+<p>For longer data that needs to persist between the <strong>getDocumentVersions()</strong> method call and the <strong>processDocuments()</strong> method call, the connector is welcome to save this information in a temporary disk file.  To help make sure nothing leaks which this approach is used, the IRepositoryConnector interface has a method that will be called to clean up any temporary files that might have been created in the handling of a given document identifier.</p>
+<p></p>
+<a name="N10268"></a><a name="Notes+on+connector+UI+methods"></a>
+<h4>Notes on connector UI methods</h4>
+<p></p>
+<p>The crawler UI uses a tabbed layout structure, and thus each of these elements must properly implement the tabbed model.  This means that the "header" methods above must add the desired tab names to a specified array, and the "body" methods must provide appropriate HTML which handles both the case where a tab is displayed, and where it is not displayed.  Also, it makes sense to use the appropriate css definitions, so that the connector UI pages have a similar look-and-feel to the rest of ManifoldCF's crawler ui.  We strongly suggest starting with one of the supplied connector's UI code, both for a description of the arguments to each page, and for some decent ideas of ways to organize your connector's UI code.  </p>
+<p></p>
+<p>Please also note that it is good practice to name the form fields in your HTML in such a way that they cannot collide with form fields that may come from the framework's HTML or any specific output connector's HTML.  The <em>DocumentSpecification</em> editing HTML especially may be prone to collisions, because within any given job, this HTML is included in the same page as HTML from the chosen output connector.</p>
+<p></p>
+<p></p>
+<a name="N10281"></a><a name="Implementation+support+provided+by+the+framework"></a>
+<h3 class="h4">Implementation support provided by the framework</h3>
+<p></p>
+<p>ManifoldCF's framework provides a number of helpful services designed to make the creation of a connector easier.  These services are summarized below.  (This is not an exhaustive list, by any means.)</p>
+<p></p>
+<ul>
+          
+<li>Lock management and synchronization (see <em>org.apache.manifoldcf.core.interfaces.LockManagerFactory</em>)</li>
+          
+<li>Cache management (see <em>org.apache.manifoldcf.core.interfaces.CacheManagerFactory</em>)</li>
+          
+<li>Local keystore management (see <em>org.apache.manifoldcf.core.KeystoreManagerFactory</em>)</li>
+          
+<li>Database management (see <em>org.apache.manifoldcf.core.DBInterfaceFactory</em>)</li>
+        
+</ul>
+<p></p>
+<p>For UI method support, these too are very useful:</p>
+<p></p>
+<ul>
+          
+<li>Multipart form processing (see <em>org.apache.manifoldcf.ui.multipart.MultipartWrapper</em>)</li>
+          
+<li>HTML encoding (see <em>org.apache.manifoldcf.ui.util.Encoder</em>)</li>
+          
+<li>HTML formatting (see <em>org.apache.manifoldcf.ui.util.Formatter</em>)</li>
+        
+</ul>
+<p></p>
+<a name="N102C8"></a><a name="DO%27s+and+DON%27T+DO%27s"></a>
+<h3 class="h4">DO's and DON'T DO's</h3>
+<p></p>
+<p>It's always a good idea to make use of an existing infrastructure component, if it's meant for that purpose, rather than inventing your own.  There are, however, some limitations we recommend you adhere to.</p>
+<p></p>
+<ul>
+          
+<li>DO make use of infrastructure components described in the section above</li>
+          
+<li>DON'T make use of infrastructure components that aren't mentioned, without checking first</li>
+          
+<li>NEVER write connector code that directly uses framework database tables, other than the ones installed and managed by your connector</li>
+        
+</ul>
+<p></p>
+<p>If you are tempted to violate these rules, it may well mean you don't understand something important.  At the very least, we'd like to know why.  Send email to connectors-dev@incubator.apache.org with a description of your problem and how you are tempted to solve it.</p>
+</div>
+  
+</div>
+<!--+
+    |end content
+    +-->
+<div class="clearboth">&nbsp;</div>
+</div>
+<div id="footer">
+<!--+
+    |start bottomstrip
+    +-->
+<div class="lastmodified">
+<script type="text/javascript"><!--
+document.write("Last Published: " + document.lastModified);
+//  --></script>
+</div>
+<div class="copyright">
+        Copyright &copy;
+         2009, 2010, 2011 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a>
+</div>
+<!--+
+    |end bottomstrip
+    +-->
+</div>
+</body>
+</html>

Propchange: incubator/lcf/site/publish/writing-repository-connectors.html
------------------------------------------------------------------------------
    svn:eol-style = native

Propchange: incubator/lcf/site/publish/writing-repository-connectors.html
------------------------------------------------------------------------------
    svn:keywords = Date Author Id Revision HeadURL



Mime
View raw message