You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@myfaces.apache.org by ms...@apache.org on 2010/10/28 22:43:50 UTC

svn commit: r1028467 - in /myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main: java/org/apache/myfaces/trinidadinternal/agent/ java/org/apache/myfaces/trinidadinternal/ui/laf/ java/org/apache/myfaces/trinidadinternal/ui/laf/base/deskt...

Author: mstarets
Date: Thu Oct 28 20:43:50 2010
New Revision: 1028467

URL: http://svn.apache.org/viewvc?rev=1028467&view=rev
Log:
Agent support for web crawlers

Modified:
    myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/AgentFactoryImpl.java
    myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/AgentNameUtil.java
    myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/TrinidadAgent.java
    myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/NameAndAgentScorer.java
    myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/base/desktop/BaseDesktopUtils.java
    myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/base/pda/PdaHtmlLafUtils.java
    myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/simple/pda/SimplePdaUtils.java
    myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/resources/META-INF/agent/capabilities.xml

Modified: myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/AgentFactoryImpl.java
URL: http://svn.apache.org/viewvc/myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/AgentFactoryImpl.java?rev=1028467&r1=1028466&r2=1028467&view=diff
==============================================================================
--- myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/AgentFactoryImpl.java (original)
+++ myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/AgentFactoryImpl.java Thu Oct 28 20:43:50 2010
@@ -115,6 +115,28 @@ public class AgentFactoryImpl implements
       _populateUnknownAgentImpl(null, agent);
       return;
     }
+    
+    // Temporary for testing !!!
+    if (facesContext != null && facesContext.getExternalContext().getRequestParameterMap().
+                        get("googlebot") != null)
+    {
+      _populateGoogleCrawlerAgentImpl("Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)", agent, 25);
+      return;
+    }
+    
+    int googlebotIndex = userAgent.indexOf(_GOOGLEBOT_ID);
+    if (googlebotIndex >= 0)
+    {
+      _populateGoogleCrawlerAgentImpl(userAgent, agent, googlebotIndex);
+      return;
+    }
+    
+    if (userAgent.startsWith(_MSNBOT_ID))
+    {
+      _populateMsnCrawlerAgentImpl(userAgent, agent);
+      return;
+    }
+    
 
     //the useragent string for telnet and PDA design time will start with
     //OracleJDevMobile because in each of these cases we know we have an
@@ -932,6 +954,37 @@ public class AgentFactoryImpl implements
     agentObj.setMakeModel(Agent.MAKE_MODEL_UNKNOWN);
 
   }
+  
+  /**
+   * Returns an AgentEntry for the Google web crawler
+   */
+  private void _populateGoogleCrawlerAgentImpl(String userAgent, AgentImpl agentObj, int idIndex)
+  {
+    agentObj.setType(Agent.TYPE_WEBCRAWLER);
+
+    agentObj.setAgent(Agent.AGENT_GOOGLEBOT);
+    agentObj.setAgentVersion(_getVersion(userAgent, idIndex + _GOOGLEBOT_ID.length()));
+    agentObj.setPlatform(Agent.PLATFORM_UNKNOWN);
+    agentObj.setPlatformVersion(Agent.PLATFORM_VERSION_UNKNOWN);
+    agentObj.setMakeModel(Agent.MAKE_MODEL_UNKNOWN);
+
+  }
+  
+  
+  /**
+   * Returns an AgentEntry for the msnbot (Bing, Yahoo) web crawler
+   */
+  private void _populateMsnCrawlerAgentImpl(String userAgent, AgentImpl agentObj)
+  {
+    agentObj.setType(Agent.TYPE_WEBCRAWLER);
+
+    agentObj.setAgent(Agent.AGENT_MSNBOT);
+    agentObj.setAgentVersion(_getVersion(userAgent, userAgent.indexOf('/')));
+    agentObj.setPlatform(Agent.PLATFORM_UNKNOWN);
+    agentObj.setPlatformVersion(Agent.PLATFORM_VERSION_UNKNOWN);
+    agentObj.setMakeModel(Agent.MAKE_MODEL_UNKNOWN);
+
+  }
 
 
   /**
@@ -995,4 +1048,6 @@ public class AgentFactoryImpl implements
   static final private String _IASW_DEVICE_HINT_PARAM = "X-Oracle-Device.Class";
   static final private TrinidadLogger _LOG = TrinidadLogger.createTrinidadLogger(AgentFactoryImpl.class);
 
+  static final private String _GOOGLEBOT_ID = "Googlebot";
+  static final private String _MSNBOT_ID = "msnbot";
 }

Modified: myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/AgentNameUtil.java
URL: http://svn.apache.org/viewvc/myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/AgentNameUtil.java?rev=1028467&r1=1028466&r2=1028467&view=diff
==============================================================================
--- myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/AgentNameUtil.java (original)
+++ myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/AgentNameUtil.java Thu Oct 28 20:43:50 2010
@@ -106,6 +106,11 @@ public class AgentNameUtil
     {
       return TrinidadAgent.TYPE_PHONE;
     }
+    
+    if (otype == Agent.TYPE_WEBCRAWLER)
+    {
+      return TrinidadAgent.TYPE_WEBCRAWLER;
+    }
 
     //Default to desktop (This is UIX 2.2 logic)
     return TrinidadAgent.TYPE_DESKTOP;

Modified: myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/TrinidadAgent.java
URL: http://svn.apache.org/viewvc/myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/TrinidadAgent.java?rev=1028467&r1=1028466&r2=1028467&view=diff
==============================================================================
--- myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/TrinidadAgent.java (original)
+++ myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/agent/TrinidadAgent.java Thu Oct 28 20:43:50 2010
@@ -258,6 +258,11 @@ public abstract class TrinidadAgent impl
    * Application constant for voice
    */
   static public final int TYPE_VOICE = 3;
+  
+  /**
+   * Application constant for web crawlers
+   */
+  static public final int TYPE_WEBCRAWLER = 4;
 
   /**
    * Enumeration representing an Application
@@ -336,7 +341,15 @@ public abstract class TrinidadAgent impl
     /**
      * Application enum for opera.
      */
-    OPERA("opera", AGENT_OPERA);
+    OPERA("opera", AGENT_OPERA),
+    /**
+     * Application enum for Google web crawler.
+     */
+    GOOGLEBOT("googlebot", AGENT_GOOGLEBOT),
+    /**
+     * Application enum for Bing web crawler.
+     */
+    MSNBOT("msnbot", AGENT_MSNBOT);
 
     /**
      * Return the appropriate Application instance given the name of an Application
@@ -525,6 +538,16 @@ public abstract class TrinidadAgent impl
   static public final int APPLICATION_OPERA = Application.OPERA.ordinal();
   
   /**
+   * Application constant for Google web crawler.
+   */
+  static public final int APPLICATION_GOOGLEBOT = Application.GOOGLEBOT.ordinal();
+  
+  /**
+   * Application constant for Bing web crawler.
+   */
+  static public final int APPLICATION_MSNBOT = Application.MSNBOT.ordinal();
+  
+  /**
    * OS constant for an unknown operating system.
    */
   static public final int OS_UNKNOWN = 0;

Modified: myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/NameAndAgentScorer.java
URL: http://svn.apache.org/viewvc/myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/NameAndAgentScorer.java?rev=1028467&r1=1028466&r2=1028467&view=diff
==============================================================================
--- myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/NameAndAgentScorer.java (original)
+++ myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/NameAndAgentScorer.java Thu Oct 28 20:43:50 2010
@@ -40,14 +40,14 @@ public class NameAndAgentScorer extends 
    */
   public NameAndAgentScorer(
     String  requiredLafName,
-    Integer requiredAgentType,
     Integer requiredAgentApplication,
     Integer requiredAgentMajorVersion,
-    Integer requiredAgentOS
+    Integer requiredAgentOS,
+    Integer... requiredAgentTypes
     )
   {
     _lafName           = requiredLafName;
-    _agentType         = requiredAgentType;
+    _agentTypes        = requiredAgentTypes;
     _agentApplication  = requiredAgentApplication;
     _agentMajorVersion = requiredAgentMajorVersion;
     _agentOS           = requiredAgentOS;
@@ -76,7 +76,14 @@ public class NameAndAgentScorer extends 
     int nameScore = _scoreName(lafName);
 
     TrinidadAgent agent = context. getAgent();
-    int typeScore = _score(_agentType, agent.getAgentType());
+    
+    int typeScore = NO_MATCH;
+    int agentType = agent.getAgentType();
+    for (int type: _agentTypes)
+    {
+      typeScore = Math.max(typeScore, _score(type, agentType));
+    }
+    
     int appScore = _score(_agentApplication, agent.getAgentApplication().ordinal());
     int versScore = _score(_agentMajorVersion, agent.getAgentMajorVersion());
     int osScore = _score(_agentOS, agent.getAgentOS());
@@ -124,7 +131,7 @@ public class NameAndAgentScorer extends 
   }
   
   private String  _lafName;
-  private Integer _agentType;
+  private Integer _agentTypes[];
   private Integer _agentApplication;
   private Integer _agentMajorVersion;
   private Integer _agentOS;

Modified: myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/base/desktop/BaseDesktopUtils.java
URL: http://svn.apache.org/viewvc/myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/base/desktop/BaseDesktopUtils.java?rev=1028467&r1=1028466&r2=1028467&view=diff
==============================================================================
--- myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/base/desktop/BaseDesktopUtils.java (original)
+++ myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/base/desktop/BaseDesktopUtils.java Thu Oct 28 20:43:50 2010
@@ -69,7 +69,7 @@ public class BaseDesktopUtils extends Xh
 
   // We use a scorer which matches base/desktop - but not Netscape
   private static final NameAndAgentScorer _SCORER =
-    new NoNetscapeScorer("base");
+    new NoNetscapeScorer("base", TrinidadAgent.TYPE_DESKTOP, TrinidadAgent.TYPE_WEBCRAWLER);
 
   /**
    * @deprecated This class comes from the old Java 1.2 UIX codebase and should not be used anymore.
@@ -77,14 +77,15 @@ public class BaseDesktopUtils extends Xh
   @Deprecated
   private static class NoNetscapeScorer extends NameAndAgentScorer
   {
-    public NoNetscapeScorer(String lafName)
+    public NoNetscapeScorer(String lafName, int type1, int type2)
     {
-      // Initialize the NameAndAgentScorer for base/desktop
+      // Initialize the NameAndAgentScorer for base
       super(lafName,
-            TrinidadAgent.TYPE_DESKTOP,
             null,
             null,
-            null);
+            null,
+            type1,
+            type2);
     }
 
     @Override

Modified: myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/base/pda/PdaHtmlLafUtils.java
URL: http://svn.apache.org/viewvc/myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/base/pda/PdaHtmlLafUtils.java?rev=1028467&r1=1028466&r2=1028467&view=diff
==============================================================================
--- myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/base/pda/PdaHtmlLafUtils.java (original)
+++ myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/base/pda/PdaHtmlLafUtils.java Thu Oct 28 20:43:50 2010
@@ -82,8 +82,8 @@ public class PdaHtmlLafUtils extends Xht
 
   private static final NameAndAgentScorer _SCORER =
     new NameAndAgentScorer(null,
-                           TrinidadAgent.TYPE_PDA,
                            null,
                            null,
-                           null);
+                           null,
+                           TrinidadAgent.TYPE_PDA);
 }

Modified: myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/simple/pda/SimplePdaUtils.java
URL: http://svn.apache.org/viewvc/myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/simple/pda/SimplePdaUtils.java?rev=1028467&r1=1028466&r2=1028467&view=diff
==============================================================================
--- myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/simple/pda/SimplePdaUtils.java (original)
+++ myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/java/org/apache/myfaces/trinidadinternal/ui/laf/simple/pda/SimplePdaUtils.java Thu Oct 28 20:43:50 2010
@@ -49,10 +49,10 @@ public class SimplePdaUtils extends PdaH
 
   private static final NameAndAgentScorer _PDA_SCORER =
     new NameAndAgentScorer("simple",
-                           TrinidadAgent.TYPE_PDA,
                            null,
                            null,
-                           null);
+                           null,
+                           TrinidadAgent.TYPE_PDA);
 
 
 }

Modified: myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/resources/META-INF/agent/capabilities.xml
URL: http://svn.apache.org/viewvc/myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/resources/META-INF/agent/capabilities.xml?rev=1028467&r1=1028466&r2=1028467&view=diff
==============================================================================
--- myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/resources/META-INF/agent/capabilities.xml (original)
+++ myfaces/trinidad/branches/mstarets_webcrawler/trinidad-impl/src/main/resources/META-INF/agent/capabilities.xml Thu Oct 28 20:43:50 2010
@@ -74,6 +74,16 @@
       <include refid="html" />
       <include src="email.xml" />
     </capabilities>
+    
+    <capabilities id="googlebot" agents="googlebot">
+      <include refid="html" />
+      <include src="email.xml" />
+    </capabilities>
+    
+    <capabilities id="msnbot" agents="msnbot">
+      <include refid="html" />
+      <include src="email.xml" />
+    </capabilities>
 
     <capabilities id="webkit" agents="webkit">
       <include refid="html" />