[Archive-access-cvs] SF.net SVN: archive-access:[2487] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback

[<bra...@us...>]

Revision: 2487
          http://archive-access.svn.sourceforge.net/archive-access/?rev=2487&view=rev
Author:   bradtofel
Date:     2008-07-23 01:06:29 +0000 (Wed, 23 Jul 2008)

Log Message:
-----------
REFACTOR: moved various Adapter<*SearchResult> into org.archive.wayback.resourceindex.adapters

Modified Paths:
--------------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/LocalResourceIndex.java

Added Paths:
-----------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/adapters/CaptureToUrlSearchResultAdapter.java
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/adapters/DeduplicationSearchResultAnnotationAdapter.java

Removed Paths:
-------------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/CaptureToUrlSearchResultAdapter.java
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/DeduplicationSearchResultAnnotationAdapter.java

Deleted: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/CaptureToUrlSearchResultAdapter.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/CaptureToUrlSearchResultAdapter.java	2008-07-23 01:04:09 UTC (rev 2486)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/CaptureToUrlSearchResultAdapter.java	2008-07-23 01:06:29 UTC (rev 2487)
@@ -1,113 +0,0 @@
-/* CaptureToUrlSearchResultAdapter
- *
- * $Id$
- *
- * Created on 4:45:55 PM Jun 28, 2008.
- *
- * Copyright (C) 2008 Internet Archive.
- *
- * This file is part of wayback.
- *
- * wayback is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser Public License as published by
- * the Free Software Foundation; either version 2.1 of the License, or
- * any later version.
- *
- * wayback is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser Public License for more details.
- *
- * You should have received a copy of the GNU Lesser Public License
- * along with wayback; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-package org.archive.wayback.core;
-
-import java.util.HashMap;
-
-import org.archive.wayback.util.AdaptedIterator;
-import org.archive.wayback.util.Adapter;
-import org.archive.wayback.util.CloseableIterator;
-
-/**
- *
- *
- * @author brad
- * @version $Date$, $Revision$
- */
-public class CaptureToUrlSearchResultAdapter
-	implements Adapter<CaptureSearchResult, UrlSearchResult> {
-
-	private String currentUrl;
-	private String originalUrl;
-	private String firstCapture;
-	private String lastCapture;
-	private int numCaptures;
-	private HashMap<String,Object> digests;
-	private UrlSearchResult resultRef = null;
-	public CaptureToUrlSearchResultAdapter() {
-		
-	}
-	private UrlSearchResult makeUrlSearchResult(CaptureSearchResult result) {
-		currentUrl = result.getUrlKey();
-		originalUrl = result.getOriginalUrl();
-		firstCapture = result.getCaptureTimestamp();
-		lastCapture = firstCapture;
-		digests = new HashMap<String,Object>();
-		digests.put(result.getDigest(),null);
-		numCaptures = 1;
-
-		resultRef = new UrlSearchResult();
-		resultRef.setUrlKey(currentUrl);
-		resultRef.setOriginalUrl(originalUrl);
-		resultRef.setFirstCapture(firstCapture);
-		resultRef.setLastCapture(lastCapture);
-		resultRef.setNumCaptures(1);
-		resultRef.setNumVersions(1);
-		return resultRef;
-	}
-
-	/* (non-Javadoc)
-	 * @see org.archive.wayback.util.Adapter#adapt(java.lang.Object)
-	 */
-	public UrlSearchResult adapt(CaptureSearchResult c) {
-		String urlKey = c.getUrlKey();
-		if(resultRef == null || !currentUrl.equals(urlKey)) {
-			return makeUrlSearchResult(c);
-		}
-
-		// same url -- accumulate into the last one we returned:
-		String captureDate = c.getCaptureTimestamp();
-		if(captureDate.compareTo(firstCapture) < 0) {
-			firstCapture = captureDate;
-			resultRef.setFirstCapture(firstCapture);
-		}
-		if(captureDate.compareTo(lastCapture) > 0) {
-			lastCapture = captureDate;
-			resultRef.setLastCapture(lastCapture);
-		}
-		numCaptures++;
-		digests.put(c.getDigest(), null);
-		resultRef.setNumCaptures(numCaptures);
-		resultRef.setNumVersions(digests.size());
-		return null;
-	}
-	public static CloseableIterator<UrlSearchResult> adaptCaptureIterator(
-			CloseableIterator<CaptureSearchResult> itr) {
-
-		// HACKHACK: this is pretty lame. We return an UrlSearchResult the
-		// first time we see a new urlKey, and cache a reference to the returned
-		// UrlSearchResult, updating it as we see subsequent CaptureSearchResult
-		// objects with the same urlKey.
-		// This means that users of the returned UrlSearchResult need to wait
-		// until they've got the *next* returned UrlSearchResult before using
-		// the *previous* UrlSearchResult.
-		// At the moment, this all happens inside a LocalResourceIndex, so
-		// none of the UrlSearchResult objects should be seen/used in any 
-		// significant way before they've all be accumulated into an 
-		// UrlSearchResults object..
-		return new AdaptedIterator<CaptureSearchResult,UrlSearchResult>(itr,
-				new CaptureToUrlSearchResultAdapter());
-	}
-}

Deleted: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/DeduplicationSearchResultAnnotationAdapter.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/DeduplicationSearchResultAnnotationAdapter.java	2008-07-23 01:04:09 UTC (rev 2486)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/DeduplicationSearchResultAnnotationAdapter.java	2008-07-23 01:06:29 UTC (rev 2487)
@@ -1,63 +0,0 @@
-package org.archive.wayback.resourceindex;
-
-import java.util.HashMap;
-
-import org.archive.wayback.core.CaptureSearchResult;
-import org.archive.wayback.util.Adapter;
-
-/**
- * Adapter class that observes a stream of SearchResults tracking for each
- * complete record, a mapping of that records digest to:
- *   Arc/Warc Filename
- * 	 Arc/Warc offset
- *   HTTP Response
- *   MIME-Type
- *   Redirect URL
- *   
- * If subsequent SearchResults are missing these fields ("-") and the Digest 
- * field has been seen, then the subsequent SearchResults are updated with the 
- * values from the kept copy matching that digest, and an additional annotation
- * field is added.
- * 
- * 
- * @author brad
- * @version $Date$, $Revision$
- */
-public class DeduplicationSearchResultAnnotationAdapter 
-implements Adapter<CaptureSearchResult,CaptureSearchResult> {
-	private final static String EMPTY_VALUE = "-";
-
-	private HashMap<String,CaptureSearchResult> memory = null;
-
-	public DeduplicationSearchResultAnnotationAdapter() {
-		memory = new HashMap<String,CaptureSearchResult>();
-	}
-
-	private CaptureSearchResult annotate(CaptureSearchResult o) {
-		String thisDigest = o.getDigest();
-		CaptureSearchResult last = memory.get(thisDigest);
-		if(last == null) {
-			// TODO: log missing record digest reference
-			return null;
-		}
-		o.setFile(last.getFile());
-		o.setOffset(last.getOffset());
-		o.setHttpCode(last.getHttpCode());
-		o.setMimeType(last.getMimeType());
-		o.setRedirectUrl(last.getRedirectUrl());
-		o.flagDuplicateDigest(last.getCaptureTimestamp());
-		return o;
-	}
-
-	private CaptureSearchResult remember(CaptureSearchResult o) {
-		memory.put(o.getDigest(),o);
-		return o;
-	}
-
-	public CaptureSearchResult adapt(CaptureSearchResult o) {
-		if(o.getFile().equals(EMPTY_VALUE)) {
-			return annotate(o);
-		}
-		return remember(o);
-	}
-}
\ No newline at end of file

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/LocalResourceIndex.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/LocalResourceIndex.java	2008-07-23 01:04:09 UTC (rev 2486)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/LocalResourceIndex.java	2008-07-23 01:06:29 UTC (rev 2487)
@@ -34,7 +34,6 @@
 import org.archive.wayback.UrlCanonicalizer;
 import org.archive.wayback.core.CaptureSearchResult;
 import org.archive.wayback.core.CaptureSearchResults;
-import org.archive.wayback.core.CaptureToUrlSearchResultAdapter;
 import org.archive.wayback.core.SearchResult;
 import org.archive.wayback.core.SearchResults;
 import org.archive.wayback.core.UrlSearchResult;
@@ -44,6 +43,8 @@
 import org.archive.wayback.exception.BadQueryException;
 import org.archive.wayback.exception.ResourceIndexNotAvailableException;
 import org.archive.wayback.exception.ResourceNotInArchiveException;
+import org.archive.wayback.resourceindex.adapters.CaptureToUrlSearchResultAdapter;
+import org.archive.wayback.resourceindex.adapters.DeduplicationSearchResultAnnotationAdapter;
 import org.archive.wayback.resourceindex.filters.CounterFilter;
 import org.archive.wayback.resourceindex.filters.DateRangeFilter;
 import org.archive.wayback.resourceindex.filters.DuplicateRecordFilter;

Copied: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/adapters/CaptureToUrlSearchResultAdapter.java (from rev 2448, trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/CaptureToUrlSearchResultAdapter.java)
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/adapters/CaptureToUrlSearchResultAdapter.java	                        (rev 0)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/adapters/CaptureToUrlSearchResultAdapter.java	2008-07-23 01:06:29 UTC (rev 2487)
@@ -0,0 +1,115 @@
+/* CaptureToUrlSearchResultAdapter
+ *
+ * $Id$
+ *
+ * Created on 4:45:55 PM Jun 28, 2008.
+ *
+ * Copyright (C) 2008 Internet Archive.
+ *
+ * This file is part of wayback.
+ *
+ * wayback is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser Public License as published by
+ * the Free Software Foundation; either version 2.1 of the License, or
+ * any later version.
+ *
+ * wayback is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser Public License
+ * along with wayback; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+package org.archive.wayback.resourceindex.adapters;
+
+import java.util.HashMap;
+
+import org.archive.wayback.core.CaptureSearchResult;
+import org.archive.wayback.core.UrlSearchResult;
+import org.archive.wayback.util.AdaptedIterator;
+import org.archive.wayback.util.Adapter;
+import org.archive.wayback.util.CloseableIterator;
+
+/**
+ *
+ *
+ * @author brad
+ * @version $Date$, $Revision$
+ */
+public class CaptureToUrlSearchResultAdapter
+	implements Adapter<CaptureSearchResult, UrlSearchResult> {
+
+	private String currentUrl;
+	private String originalUrl;
+	private String firstCapture;
+	private String lastCapture;
+	private int numCaptures;
+	private HashMap<String,Object> digests;
+	private UrlSearchResult resultRef = null;
+	public CaptureToUrlSearchResultAdapter() {
+		
+	}
+	private UrlSearchResult makeUrlSearchResult(CaptureSearchResult result) {
+		currentUrl = result.getUrlKey();
+		originalUrl = result.getOriginalUrl();
+		firstCapture = result.getCaptureTimestamp();
+		lastCapture = firstCapture;
+		digests = new HashMap<String,Object>();
+		digests.put(result.getDigest(),null);
+		numCaptures = 1;
+
+		resultRef = new UrlSearchResult();
+		resultRef.setUrlKey(currentUrl);
+		resultRef.setOriginalUrl(originalUrl);
+		resultRef.setFirstCapture(firstCapture);
+		resultRef.setLastCapture(lastCapture);
+		resultRef.setNumCaptures(1);
+		resultRef.setNumVersions(1);
+		return resultRef;
+	}
+
+	/* (non-Javadoc)
+	 * @see org.archive.wayback.util.Adapter#adapt(java.lang.Object)
+	 */
+	public UrlSearchResult adapt(CaptureSearchResult c) {
+		String urlKey = c.getUrlKey();
+		if(resultRef == null || !currentUrl.equals(urlKey)) {
+			return makeUrlSearchResult(c);
+		}
+
+		// same url -- accumulate into the last one we returned:
+		String captureDate = c.getCaptureTimestamp();
+		if(captureDate.compareTo(firstCapture) < 0) {
+			firstCapture = captureDate;
+			resultRef.setFirstCapture(firstCapture);
+		}
+		if(captureDate.compareTo(lastCapture) > 0) {
+			lastCapture = captureDate;
+			resultRef.setLastCapture(lastCapture);
+		}
+		numCaptures++;
+		digests.put(c.getDigest(), null);
+		resultRef.setNumCaptures(numCaptures);
+		resultRef.setNumVersions(digests.size());
+		return null;
+	}
+	public static CloseableIterator<UrlSearchResult> adaptCaptureIterator(
+			CloseableIterator<CaptureSearchResult> itr) {
+
+		// HACKHACK: this is pretty lame. We return an UrlSearchResult the
+		// first time we see a new urlKey, and cache a reference to the returned
+		// UrlSearchResult, updating it as we see subsequent CaptureSearchResult
+		// objects with the same urlKey.
+		// This means that users of the returned UrlSearchResult need to wait
+		// until they've got the *next* returned UrlSearchResult before using
+		// the *previous* UrlSearchResult.
+		// At the moment, this all happens inside a LocalResourceIndex, so
+		// none of the UrlSearchResult objects should be seen/used in any 
+		// significant way before they've all be accumulated into an 
+		// UrlSearchResults object..
+		return new AdaptedIterator<CaptureSearchResult,UrlSearchResult>(itr,
+				new CaptureToUrlSearchResultAdapter());
+	}
+}

Copied: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/adapters/DeduplicationSearchResultAnnotationAdapter.java (from rev 2448, trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/DeduplicationSearchResultAnnotationAdapter.java)
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/adapters/DeduplicationSearchResultAnnotationAdapter.java	                        (rev 0)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/adapters/DeduplicationSearchResultAnnotationAdapter.java	2008-07-23 01:06:29 UTC (rev 2487)
@@ -0,0 +1,63 @@
+package org.archive.wayback.resourceindex.adapters;
+
+import java.util.HashMap;
+
+import org.archive.wayback.core.CaptureSearchResult;
+import org.archive.wayback.util.Adapter;
+
+/**
+ * Adapter class that observes a stream of SearchResults tracking for each
+ * complete record, a mapping of that records digest to:
+ *   Arc/Warc Filename
+ * 	 Arc/Warc offset
+ *   HTTP Response
+ *   MIME-Type
+ *   Redirect URL
+ *   
+ * If subsequent SearchResults are missing these fields ("-") and the Digest 
+ * field has been seen, then the subsequent SearchResults are updated with the 
+ * values from the kept copy matching that digest, and an additional annotation
+ * field is added.
+ * 
+ * 
+ * @author brad
+ * @version $Date$, $Revision$
+ */
+public class DeduplicationSearchResultAnnotationAdapter 
+implements Adapter<CaptureSearchResult,CaptureSearchResult> {
+	private final static String EMPTY_VALUE = "-";
+
+	private HashMap<String,CaptureSearchResult> memory = null;
+
+	public DeduplicationSearchResultAnnotationAdapter() {
+		memory = new HashMap<String,CaptureSearchResult>();
+	}
+
+	private CaptureSearchResult annotate(CaptureSearchResult o) {
+		String thisDigest = o.getDigest();
+		CaptureSearchResult last = memory.get(thisDigest);
+		if(last == null) {
+			// TODO: log missing record digest reference
+			return null;
+		}
+		o.setFile(last.getFile());
+		o.setOffset(last.getOffset());
+		o.setHttpCode(last.getHttpCode());
+		o.setMimeType(last.getMimeType());
+		o.setRedirectUrl(last.getRedirectUrl());
+		o.flagDuplicateDigest(last.getCaptureTimestamp());
+		return o;
+	}
+
+	private CaptureSearchResult remember(CaptureSearchResult o) {
+		memory.put(o.getDigest(),o);
+		return o;
+	}
+
+	public CaptureSearchResult adapt(CaptureSearchResult o) {
+		if(o.getFile().equals(EMPTY_VALUE)) {
+			return annotate(o);
+		}
+		return remember(o);
+	}
+}
\ No newline at end of file


This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.