archive-access-cvs Mailing List for Web Archive Access Utilities (Page 15)

Brought to you by: binzino, bradtofel, gojomo, ia_igor, and 5 others

archive-access-cvs — CVS commits

You can subscribe to this list here.

2005	Jan	Feb	Mar	Apr	May	Jun	Jul (1)	Aug (10)	Sep (36)	Oct (339)	Nov (103)	Dec (152)
2006	Jan (141)	Feb (102)	Mar (125)	Apr (203)	May (57)	Jun (30)	Jul (139)	Aug (46)	Sep (64)	Oct (105)	Nov (34)	Dec (162)
2007	Jan (81)	Feb (57)	Mar (141)	Apr (72)	May (9)	Jun (1)	Jul (144)	Aug (88)	Sep (40)	Oct (43)	Nov (34)	Dec (20)
2008	Jan (44)	Feb (45)	Mar (16)	Apr (36)	May (8)	Jun (77)	Jul (177)	Aug (66)	Sep (8)	Oct (33)	Nov (13)	Dec (37)
2009	Jan (2)	Feb (5)	Mar (8)	Apr	May (36)	Jun (19)	Jul (46)	Aug (8)	Sep (1)	Oct (66)	Nov (61)	Dec (10)
2010	Jan (13)	Feb (16)	Mar (38)	Apr (76)	May (47)	Jun (32)	Jul (35)	Aug (45)	Sep (20)	Oct (61)	Nov (24)	Dec (16)
2011	Jan (22)	Feb (34)	Mar (11)	Apr (8)	May (24)	Jun (23)	Jul (11)	Aug (42)	Sep (81)	Oct (48)	Nov (21)	Dec (20)
2012	Jan (30)	Feb (25)	Mar (4)	Apr (6)	May (1)	Jun (5)	Jul (5)	Aug (8)	Sep (6)	Oct (6)	Nov	Dec

Flat | Threaded

<< < 1 .. 13 14 15 16 17 .. 171 > >> (Page 15 of 171)

[Archive-access-cvs] SF.net SVN: archive-access:[3453] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/ RobotExclusionFilter.java

From: <bra...@us...> - 2011-05-25 01:40:36

Revision: 3453
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3453&view=rev
Author:   bradtofel
Date:     2011-05-25 01:40:30 +0000 (Wed, 25 May 2011)

Log Message:
-----------
OPTIMIZ: now uses UrlOperations.getUrlPath() instead of constructing a URL object when determining if URLs are /robots.txt

Modified Paths:
--------------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java	2011-05-25 01:37:48 UTC (rev 3452)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java	2011-05-25 01:40:30 UTC (rev 3453)
@@ -39,6 +39,7 @@
 import org.archive.wayback.liveweb.LiveWebCache;
 import org.archive.wayback.resourceindex.filters.ExclusionFilter;
 import org.archive.wayback.util.ObjectFilter;
+import org.archive.wayback.util.url.UrlOperations;
 
 /**
  * CaptureSearchResult Filter that uses a LiveWebCache to retrieve robots.txt
@@ -230,6 +231,17 @@
 			}
 			notifiedSeen = true;
 		}
+		String resultURL = r.getOriginalUrl();
+		String path = UrlOperations.getURLPath(resultURL);
+		if(path.equals(ROBOT_SUFFIX)) {
+			if(!notifiedPassed) {
+				if(filterGroup != null) {
+					filterGroup.setPassedRobots();
+				}
+				notifiedPassed = true;
+			}
+			return ObjectFilter.FILTER_INCLUDE;
+		}
 		int filterResult = ObjectFilter.FILTER_EXCLUDE; 
 		RobotRules rules = getRules(r);
 		if(rules == null) {
@@ -237,26 +249,17 @@
 				return ObjectFilter.FILTER_ABORT;
 			}
 		} else {
-			String resultURL = r.getOriginalUrl();
-			URL url;
-			try {
-				url = new URL(ArchiveUtils.addImpliedHttpIfNecessary(resultURL));
-				String path = url.getPath();
-				if(path.equals(ROBOT_SUFFIX) || 
-						!rules.blocksPathForUA(path, userAgent)) {
-					if(!notifiedPassed) {
-						if(filterGroup != null) {
-							filterGroup.setPassedRobots();
-						}
-						notifiedPassed = true;
+			if(!rules.blocksPathForUA(path, userAgent)) {
+				if(!notifiedPassed) {
+					if(filterGroup != null) {
+						filterGroup.setPassedRobots();
 					}
-					filterResult = ObjectFilter.FILTER_INCLUDE;
-					LOGGER.fine("ROBOT: ALLOWED("+resultURL+")");
-				} else {
-					LOGGER.info("ROBOT: BLOCKED("+resultURL+")");
+					notifiedPassed = true;
 				}
-			} catch (MalformedURLException e) {
-				e.printStackTrace();
+				filterResult = ObjectFilter.FILTER_INCLUDE;
+				LOGGER.fine("ROBOT: ALLOWED("+resultURL+")");
+			} else {
+				LOGGER.info("ROBOT: BLOCKED("+resultURL+")");
 			}
 		}
 		return filterResult;


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

[Archive-access-cvs] SF.net SVN: archive-access:[3452] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/archivalurl

From: <bra...@us...> - 2011-05-25 01:37:54

Revision: 3452
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3452&view=rev
Author:   bradtofel
Date:     2011-05-25 01:37:48 +0000 (Wed, 25 May 2011)

Log Message:
-----------
REFACTOR: moved flag assignment and parsing code into ArchivalUrl

Modified Paths:
--------------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrl.java
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlDateRedirectReplayRenderer.java
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlRequestParser.java
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ReplayRequestParser.java

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrl.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrl.java	2011-05-25 01:37:10 UTC (rev 3451)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrl.java	2011-05-25 01:37:48 UTC (rev 3452)
@@ -61,37 +61,106 @@
 	public String toReplayString(String url) {
 		return toString(wbRequest.getReplayTimestamp(),url);
 	}
+	public String getDateSpec() {
+		return getDateSpec(wbRequest.getReplayTimestamp());
+	}
 
-	public String toString(String datespec, String url) {
+	/**
+	 * Given a date, create a new datespec + flags
+	 * which represent the same options as requested by the WaybackRequest
+	 * @param timestamp the 14-digit timestamp to use
+	 * @return a String representing the flags on the WaybackRequest for the
+	 * specified date
+	 */
+	public String getDateSpec(String datespec) {
 		int dateLen = 0;
 		if(datespec != null) {
 			dateLen = datespec.length();
 		}
 		StringBuilder sb = 
-			new StringBuilder(url.length() + dateLen +10);
+			new StringBuilder(dateLen +10);
 		if(dateLen > 0) {
 			sb.append(datespec);
 		}
+
 		if(wbRequest.isCSSContext()) {
 			sb.append(ArchivalUrlRequestParser.CSS_CONTEXT);
 			sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
+			dateLen++;
 		}
 		if(wbRequest.isJSContext()) {
 			sb.append(ArchivalUrlRequestParser.JS_CONTEXT);
 			sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
+			dateLen++;
 		}
 		if(wbRequest.isIMGContext()) {
 			sb.append(ArchivalUrlRequestParser.IMG_CONTEXT);
 			sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
+			dateLen++;
 		}
 		if(wbRequest.isIdentityContext()) {
 			sb.append(ArchivalUrlRequestParser.IDENTITY_CONTEXT);
 			sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
+			dateLen++;
 		}
-		if(dateLen > 0) {
+		if(wbRequest.isIFrameWrapperContext()) {
+			sb.append(ArchivalUrlRequestParser.IFRAME_WRAPPED_CONTEXT);
+			sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
+			dateLen++;
+		}
+		if(wbRequest.isFrameWrapperContext()) {
+			sb.append(ArchivalUrlRequestParser.FRAME_WRAPPED_CONTEXT);
+			sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
+			dateLen++;
+		}
+		return sb.toString();
+	}
+	
+	public String toString(String datespec, String url) {
+		int dateLen = 0;
+		if(datespec != null) {
+			dateLen = datespec.length();
+		}
+		StringBuilder sb = 
+			new StringBuilder(url.length() + dateLen +10);
+		String dateSpec = getDateSpec(datespec);
+		sb.append(dateSpec);
+		if(dateSpec.length() > 0) {
 			sb.append("/");
 		}
 		sb.append(UrlOperations.stripDefaultPortFromUrl(url));
 		return sb.toString();
 	}
+
+	/**
+	 * @param wbRequest
+	 * @param flagsStr : "js_", "", "cs_", "cs_js_"
+	 */
+	public static void assignFlags(WaybackRequest wbRequest, String flagsStr) {
+		if(flagsStr != null) {
+			String[] flags = flagsStr.split(
+					ArchivalUrlRequestParser.FLAG_DELIM);
+			for(String flag: flags) {
+				if(flag.equals(ArchivalUrlRequestParser.CSS_CONTEXT)) {
+					wbRequest.setCSSContext(true);
+				} else if(flag.equals(ArchivalUrlRequestParser.JS_CONTEXT)) {
+					wbRequest.setJSContext(true);
+				} else if(flag.equals(ArchivalUrlRequestParser.IMG_CONTEXT)) {
+					wbRequest.setIMGContext(true);
+				} else if(flag.equals(ArchivalUrlRequestParser.IDENTITY_CONTEXT)) {
+					wbRequest.setIdentityContext(true);
+				} else if(flag.equals(ArchivalUrlRequestParser.FRAME_WRAPPED_CONTEXT)) {
+					wbRequest.setFrameWrapperContext(true);
+				} else if(flag.equals(ArchivalUrlRequestParser.IFRAME_WRAPPED_CONTEXT)) {
+					wbRequest.setIFrameWrapperContext(true);
+				} else if(flag.startsWith(ArchivalUrlRequestParser.CHARSET_MODE)) {
+					String modeString = flag.substring(
+							ArchivalUrlRequestParser.CHARSET_MODE.length());
+					int mode = Integer.parseInt(modeString);
+					wbRequest.setCharsetMode(mode);
+				}
+			}
+		}
+	}
+	
 }

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlDateRedirectReplayRenderer.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlDateRedirectReplayRenderer.java	2011-05-25 01:37:10 UTC (rev 3451)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlDateRedirectReplayRenderer.java	2011-05-25 01:37:48 UTC (rev 3452)
@@ -52,41 +52,9 @@
 
 		// redirect to the better version:
 		String url = result.getOriginalUrl();
-		String captureDate = makeFlagDateSpec(
-				result.getCaptureTimestamp(),wbRequest);
-
-		String betterURI = uriConverter.makeReplayURI(captureDate,url);
+		ArchivalUrl aUrl = new ArchivalUrl(wbRequest);
+		String dateSpec = aUrl.getDateSpec(result.getCaptureTimestamp());
+		String betterURI = uriConverter.makeReplayURI(dateSpec,url);
 		httpResponse.sendRedirect(betterURI);
 	}
-
-	/**
-	 * Given a date, and a WaybackRequest object, create a new datespec + flags
-	 * which represent the same options as requested by the WaybackRequest
-	 * @param timestamp the 14-digit timestamp to use
-	 * @param request the WaybackRequest from which o get extra request option 
-	 * flags
-	 * @return a String representing the flags on the WaybackRequest for the
-	 * specified date
-	 */
-	public static String makeFlagDateSpec(String timestamp, WaybackRequest request) {
-		StringBuilder sb = new StringBuilder();
-		sb.append(timestamp);
-		if(request.isCSSContext()) {
-			sb.append(ArchivalUrlRequestParser.CSS_CONTEXT);
-			sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
-		}
-		if(request.isJSContext()) {
-			sb.append(ArchivalUrlRequestParser.JS_CONTEXT);
-			sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
-		}
-		if(request.isIMGContext()) {
-			sb.append(ArchivalUrlRequestParser.IMG_CONTEXT);
-			sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
-		}
-		if(request.isIdentityContext()) {
-			sb.append(ArchivalUrlRequestParser.IDENTITY_CONTEXT);
-			sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
-		}
-		return sb.toString();
-	}
 }

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlRequestParser.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlRequestParser.java	2011-05-25 01:37:10 UTC (rev 3451)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlRequestParser.java	2011-05-25 01:37:48 UTC (rev 3452)
@@ -60,6 +60,14 @@
 	 */
 	public final static String IDENTITY_CONTEXT = "id";
 	/**
+	 * frame-wrapper context
+	 */
+	public final static String FRAME_WRAPPED_CONTEXT = "fw";
+	/**
+	 * iframe-wrapped context
+	 */
+	public final static String IFRAME_WRAPPED_CONTEXT = "if";
+	/**
 	 * Charset detection strategy context - should be followed by an integer
 	 * indicating which strategy to use 
 	 */

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ReplayRequestParser.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ReplayRequestParser.java	2011-05-25 01:37:10 UTC (rev 3451)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ReplayRequestParser.java	2011-05-25 01:37:48 UTC (rev 3452)
@@ -22,6 +22,7 @@
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
+import org.archive.wayback.archivalurl.ArchivalUrl;
 import org.archive.wayback.archivalurl.ArchivalUrlRequestParser;
 import org.archive.wayback.core.WaybackRequest;
 import org.archive.wayback.exception.BetterRequestException;
@@ -62,7 +63,7 @@
 			String dateStr = matcher.group(1);
 			urlStr = matcher.group(4);
 			String flags = matcher.group(2);
-			assignFlags(wbRequest,flags);
+			ArchivalUrl.assignFlags(wbRequest,flags);
 
 			// The logic of the classic WM wrt timestamp bounding:
 			// if 14-digits are specified, assume min-max range boundaries
@@ -134,30 +135,5 @@
 		return wbRequest;
 	}
 
-	/**
-	 * @param wbRequest
-	 * @param flagsStr : "js_", "", "cs_", "cs_js_"
-	 */
-	private void assignFlags(WaybackRequest wbRequest, String flagsStr) {
-		if(flagsStr != null) {
-			String[] flags = flagsStr.split(
-					ArchivalUrlRequestParser.FLAG_DELIM);
-			for(String flag: flags) {
-				if(flag.equals(ArchivalUrlRequestParser.CSS_CONTEXT)) {
-					wbRequest.setCSSContext(true);
-				} else if(flag.equals(ArchivalUrlRequestParser.JS_CONTEXT)) {
-					wbRequest.setJSContext(true);
-				} else if(flag.equals(ArchivalUrlRequestParser.IMG_CONTEXT)) {
-					wbRequest.setIMGContext(true);
-				} else if(flag.equals(ArchivalUrlRequestParser.IDENTITY_CONTEXT)) {
-					wbRequest.setIdentityContext(true);
-				} else if(flag.startsWith(ArchivalUrlRequestParser.CHARSET_MODE)) {
-					String modeString = flag.substring(
-							ArchivalUrlRequestParser.CHARSET_MODE.length());
-					int mode = Integer.parseInt(modeString);
-					wbRequest.setCharsetMode(mode);
-				}
-			}
-		}
-	}
+
 }


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

[Archive-access-cvs] SF.net SVN: archive-access:[3451] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/archivalurl/ ArchivalUrlSAXRewriteReplayRenderer.java

From: <bra...@us...> - 2011-05-25 01:37:16

Revision: 3451
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3451&view=rev
Author:   bradtofel
Date:     2011-05-25 01:37:10 +0000 (Wed, 25 May 2011)

Log Message:
-----------
FEATURE: added FrameWrapped state tracking code

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

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlSAXRewriteReplayRenderer.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlSAXRewriteReplayRenderer.java	2011-05-25 01:36:49 UTC (rev 3450)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlSAXRewriteReplayRenderer.java	2011-05-25 01:37:10 UTC (rev 3451)
@@ -19,10 +19,12 @@
  */
 package org.archive.wayback.archivalurl;
 
+import java.io.ByteArrayInputStream;
 import java.io.ByteArrayOutputStream;
 import java.io.IOException;
 import java.net.MalformedURLException;
 import java.net.URL;
+import java.nio.charset.Charset;
 import java.util.Map;
 
 import javax.servlet.ServletException;
@@ -39,15 +41,19 @@
 import org.archive.wayback.replay.HttpHeaderOperation;
 import org.archive.wayback.replay.HttpHeaderProcessor;
 import org.archive.wayback.replay.JSPExecutor;
+import org.archive.wayback.replay.TagMagix;
 import org.archive.wayback.replay.TextReplayRenderer;
 import org.archive.wayback.replay.charset.CharsetDetector;
 import org.archive.wayback.replay.charset.StandardCharsetDetector;
 import org.archive.wayback.replay.html.ReplayParseContext;
+import org.archive.wayback.util.ByteOp;
 import org.archive.wayback.util.htmllex.ContextAwareLexer;
 import org.archive.wayback.util.htmllex.ParseEventHandler;
 import org.htmlparser.Node;
+import org.htmlparser.lexer.InputStreamSource;
 import org.htmlparser.lexer.Lexer;
 import org.htmlparser.lexer.Page;
+import org.htmlparser.lexer.Source;
 import org.htmlparser.util.ParserException;
 
 /**
@@ -62,7 +68,16 @@
 	private HttpHeaderProcessor httpHeaderProcessor;
 	private CharsetDetector charsetDetector = new StandardCharsetDetector();
 	private final static String OUTPUT_CHARSET = "utf-8";
+	private static int FRAMESET_SCAN_BUFFER_SIZE = 16 * 1024;
+	private static ReplayRenderer frameWrappingRenderer = null;
+	public static ReplayRenderer getFrameWrappingRenderer() {
+		return frameWrappingRenderer;
+	}
 
+	public static void setFrameWrappingRenderer(ReplayRenderer frameWrappingRenderer) {
+		ArchivalUrlSAXRewriteReplayRenderer.frameWrappingRenderer = frameWrappingRenderer;
+	}
+
 	/**
 	 * @param httpHeaderProcessor which should process HTTP headers
 	 */
@@ -77,6 +92,51 @@
 			ResultURIConverter uriConverter, CaptureSearchResults results)
 			throws ServletException, IOException, WaybackException {
 
+		// The URL of the page, for resolving in-page relative URLs: 
+    	URL url = null;
+		try {
+			url = new URL(result.getOriginalUrl());
+		} catch (MalformedURLException e1) {
+			// TODO: this shouldn't happen...
+			e1.printStackTrace();
+			throw new IOException(e1.getMessage());
+		}
+		// determine the character set used to encode the document bytes:
+		String charSet = charsetDetector.getCharset(resource, wbRequest);
+
+		ArchivalUrlContextResultURIConverterFactory fact = 
+			new ArchivalUrlContextResultURIConverterFactory(
+					(ArchivalUrlResultURIConverter) uriConverter);
+		// set up the context:
+		ReplayParseContext context = 
+			new ReplayParseContext(fact,url,result.getCaptureTimestamp());
+
+		if(!wbRequest.isFrameWrapperContext()) {
+			// in case this is an HTML page with FRAMEs, peek ahead an look:
+			// TODO: make ThreadLocal:
+			byte buffer[] = new byte[FRAMESET_SCAN_BUFFER_SIZE];
+
+			resource.mark(FRAMESET_SCAN_BUFFER_SIZE);
+			int amtRead = resource.read(buffer);
+			resource.reset();
+			
+			if(amtRead > 0) {
+				StringBuilder foo = new StringBuilder(new String(buffer,charSet));
+				int frameIdx = TagMagix.getEndOfFirstTag(foo, "FRAMESET");
+				if(frameIdx != -1) {
+					// insert flag so we don't add FRAMESET:
+					context.putData(FastArchivalUrlReplayParseEventHandler.FERRET_DONE_KEY,"");
+
+//					// top-level Frameset: Draw the frame wrapper thingy:
+//					frameWrappingRenderer.renderResource(httpRequest, 
+//							httpResponse, wbRequest, result, resource, 
+//							uriConverter, results);
+//					return;
+				}
+			}
+		}
+		
+		
 		// copy the HTTP response code:
 		HttpHeaderOperation.copyHTTPMessageHeader(resource, httpResponse);
 
@@ -90,31 +150,14 @@
 		JSPExecutor jspExec = new JSPExecutor(uriConverter, httpRequest, 
 				httpResponse, wbRequest, results, result, resource);
 		
-		// The URL of the page, for resolving in-page relative URLs: 
-    	URL url = null;
-		try {
-			url = new URL(result.getOriginalUrl());
-		} catch (MalformedURLException e1) {
-			// TODO: this shouldn't happen...
-			e1.printStackTrace();
-			throw new IOException(e1.getMessage());
-		}
 
 		// To make sure we get the length, we have to buffer it all up...
 		ByteArrayOutputStream baos = new ByteArrayOutputStream();
 
-		ArchivalUrlContextResultURIConverterFactory fact = 
-			new ArchivalUrlContextResultURIConverterFactory(
-					(ArchivalUrlResultURIConverter) uriConverter);
-		// set up the context:
-		ReplayParseContext context = 
-			new ReplayParseContext(fact,url,result.getCaptureTimestamp());
 		context.setOutputCharset(OUTPUT_CHARSET);
 		context.setOutputStream(baos);
 		context.setJspExec(jspExec);
 
-		// determine the character set used to encode the document bytes:
-		String charSet = charsetDetector.getCharset(resource, wbRequest);
 		
 		// and finally, parse, using the special lexer that knows how to
 		// handle javascript blocks containing unescaped HTML entities:


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

[Archive-access-cvs] SF.net SVN: archive-access:[3450] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback

From: <bra...@us...> - 2011-05-25 01:36:55

Revision: 3450
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3450&view=rev
Author:   bradtofel
Date:     2011-05-25 01:36:49 +0000 (Wed, 25 May 2011)

Log Message:
-----------
FEATURE: added FrameWrapped state tracking code

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

Added Paths:
-----------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/selector/FrameEmbeddedRequestSelector.java
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/selector/IFrameEmbeddedRequestSelector.java

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/FastArchivalUrlReplayParseEventHandler.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/FastArchivalUrlReplayParseEventHandler.java	2011-05-25 01:33:03 UTC (rev 3449)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/FastArchivalUrlReplayParseEventHandler.java	2011-05-25 01:36:49 UTC (rev 3450)
@@ -53,7 +53,7 @@
 public class FastArchivalUrlReplayParseEventHandler implements
 		ParseEventHandler {
 
-	private final static String FERRET_DONE_KEY = 
+	public final static String FERRET_DONE_KEY = 
 		FastArchivalUrlReplayParseEventHandler.class.toString();
 
 	private String jspInsertPath = "/WEB-INF/replay/DisclaimChooser.jsp";
@@ -79,6 +79,8 @@
 		anchorUrlTrans = new URLStringTransformer();
 		anchorUrlTrans.setJsTransformer(jsBlockTrans);
 	}
+	private static URLStringTransformer framesetUrlTrans =
+		new URLStringTransformer("fw_");
 	private static URLStringTransformer cssUrlTrans =
 		new URLStringTransformer("cs_");
 	private static URLStringTransformer jsUrlTrans =
@@ -227,7 +229,7 @@
 			transformAttr(context, tagNode, "ACTION", anchorUrlTrans);
 
 		} else if(tagName.equals("FRAME")) {
-			transformAttr(context, tagNode, "SRC", anchorUrlTrans);
+			transformAttr(context, tagNode, "SRC", framesetUrlTrans);
 
 		} else if(tagName.equals("LINK")) {
 			if(transformAttrWhere(context, tagNode, "REL", "STYLESHEET", 

Added: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/selector/FrameEmbeddedRequestSelector.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/selector/FrameEmbeddedRequestSelector.java	                        (rev 0)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/selector/FrameEmbeddedRequestSelector.java	2011-05-25 01:36:49 UTC (rev 3450)
@@ -0,0 +1,18 @@
+package org.archive.wayback.replay.selector;
+
+import org.archive.wayback.core.CaptureSearchResult;
+import org.archive.wayback.core.Resource;
+import org.archive.wayback.core.WaybackRequest;
+
+public class FrameEmbeddedRequestSelector extends BaseReplayRendererSelector {
+
+	/* (non-Javadoc)
+	 * @see org.archive.wayback.replay.selector.BaseReplayRendererSelector#canHandle(org.archive.wayback.core.WaybackRequest, org.archive.wayback.core.CaptureSearchResult, org.archive.wayback.core.Resource)
+	 */
+	@Override
+	public boolean canHandle(WaybackRequest wbRequest,
+			CaptureSearchResult result, Resource resource) {
+		return wbRequest.isFrameWrapperContext();
+	}
+
+}

Added: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/selector/IFrameEmbeddedRequestSelector.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/selector/IFrameEmbeddedRequestSelector.java	                        (rev 0)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/selector/IFrameEmbeddedRequestSelector.java	2011-05-25 01:36:49 UTC (rev 3450)
@@ -0,0 +1,18 @@
+package org.archive.wayback.replay.selector;
+
+import org.archive.wayback.core.CaptureSearchResult;
+import org.archive.wayback.core.Resource;
+import org.archive.wayback.core.WaybackRequest;
+
+public class IFrameEmbeddedRequestSelector extends BaseReplayRendererSelector {
+
+	/* (non-Javadoc)
+	 * @see org.archive.wayback.replay.selector.BaseReplayRendererSelector#canHandle(org.archive.wayback.core.WaybackRequest, org.archive.wayback.core.CaptureSearchResult, org.archive.wayback.core.Resource)
+	 */
+	@Override
+	public boolean canHandle(WaybackRequest wbRequest,
+			CaptureSearchResult result, Resource resource) {
+		return wbRequest.isIFrameWrapperContext();
+	}
+
+}


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

[Archive-access-cvs] SF.net SVN: archive-access:[3449] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/core/WaybackRequest.java

From: <bra...@us...> - 2011-05-25 01:33:09

Revision: 3449
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3449&view=rev
Author:   bradtofel
Date:     2011-05-25 01:33:03 +0000 (Wed, 25 May 2011)

Log Message:
-----------
FEATURE: added FrameWrapped state tracking code

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

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/WaybackRequest.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/WaybackRequest.java	2011-05-25 01:30:18 UTC (rev 3448)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/WaybackRequest.java	2011-05-25 01:33:03 UTC (rev 3449)
@@ -266,6 +266,17 @@
 	 */
 	public static final String REQUEST_IDENTITY_CONTEXT = "identitycontext";
 		
+	/**
+	 * Request: Content should be wrapped in a frame 
+	 */
+	public static final String REQUEST_FRAME_WRAPPER_CONTEXT = 
+		"framewrappercontext";
+		
+	/**
+	 * Request: Display context for embedded metadata in an IFrame
+	 */
+	public static final String REQUEST_IFRAME_WRAPPER_CONTEXT = 
+		"iframewrappercontext";
 	
 	/**
 	 * Request: Charset detection mode 
@@ -784,6 +795,20 @@
 		return getBoolean(REQUEST_IDENTITY_CONTEXT);
 	}
 
+	public void setFrameWrapperContext(boolean isFrameWrapperContext) {
+		setBoolean(REQUEST_FRAME_WRAPPER_CONTEXT,isFrameWrapperContext);
+	}
+	public boolean isFrameWrapperContext() {
+		return getBoolean(REQUEST_FRAME_WRAPPER_CONTEXT);
+	}
+
+	public void setIFrameWrapperContext(boolean isIFrameWrapperContext) {
+		setBoolean(REQUEST_IFRAME_WRAPPER_CONTEXT,isIFrameWrapperContext);
+	}
+	public boolean isIFrameWrapperContext() {
+		return getBoolean(REQUEST_IFRAME_WRAPPER_CONTEXT);
+	}
+
 	public void setCharsetMode(int mode) {
 		setInt(REQUEST_CHARSET_MODE,mode);
 	}


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

[Archive-access-cvs] SF.net SVN: archive-access:[3448] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/core/UIResults.java

From: <bra...@us...> - 2011-05-25 01:30:25

Revision: 3448
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3448&view=rev
Author:   bradtofel
Date:     2011-05-25 01:30:18 +0000 (Wed, 25 May 2011)

Log Message:
-----------
BUGFIX: returns "", not "/", for getXXXPrefix() when no accessPoint is available, allowing deployment at non-ROOT context

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

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/UIResults.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/UIResults.java	2011-05-25 01:26:48 UTC (rev 3447)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/UIResults.java	2011-05-25 01:30:18 UTC (rev 3448)
@@ -299,7 +299,7 @@
 				return wbRequest.getAccessPoint().getStaticPrefix();
 			}
 		}
-		return "/";
+		return "";
 	}
 
 	/**
@@ -311,7 +311,7 @@
 				return wbRequest.getAccessPoint().getQueryPrefix();
 			}
 		}
-		return "/";
+		return "";
 	}
 
 	/**
@@ -323,7 +323,7 @@
 				return wbRequest.getAccessPoint().getReplayPrefix();
 			}
 		}
-		return "/";
+		return "";
 	}
 
 	/*


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

[Archive-access-cvs] SF.net SVN: archive-access:[3447] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/replay/TagMagix.java

From: <bra...@us...> - 2011-05-25 01:26:55

Revision: 3447
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3447&view=rev
Author:   bradtofel
Date:     2011-05-25 01:26:48 +0000 (Wed, 25 May 2011)

Log Message:
-----------
TWEAK: removed unneeded TagMagix class identifier

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

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TagMagix.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TagMagix.java	2011-05-25 01:21:30 UTC (rev 3446)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TagMagix.java	2011-05-25 01:26:48 UTC (rev 3447)
@@ -333,7 +333,7 @@
 	public static String getTagAttrWhere(StringBuilder page, final String tag,
 			final String findAttr, final String whereAttr, final String whereVal) {
 
-		Pattern tagPattern = TagMagix.getWholeTagPattern(tag);
+		Pattern tagPattern = getWholeTagPattern(tag);
 		Pattern findAttrPattern = getAttrPattern(findAttr);
 		Pattern whereAttrPattern = getAttrPattern(whereAttr);
 		Matcher tagMatcher = tagPattern.matcher(page);


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

[Archive-access-cvs] SF.net SVN: archive-access:[3446] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/resourceindex/ziplines/ ZiplinesSearchResultSource.java

From: <bra...@us...> - 2011-05-25 01:21:36

Revision: 3446
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3446&view=rev
Author:   bradtofel
Date:     2011-05-25 01:21:30 +0000 (Wed, 25 May 2011)

Log Message:
-----------
FEATURE: added "-blockDump" argument, which only produces a list of matching block-offset tuples to STDOUT

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

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/ziplines/ZiplinesSearchResultSource.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/ziplines/ZiplinesSearchResultSource.java	2011-05-25 01:20:09 UTC (rev 3445)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/ziplines/ZiplinesSearchResultSource.java	2011-05-25 01:21:30 UTC (rev 3446)
@@ -276,6 +276,7 @@
 		ZiplinesSearchResultSource zl = new ZiplinesSearchResultSource(format);
 		PrintWriter pw = new PrintWriter(System.out);
 		int idx;
+		boolean blockDump = false;
 		for(idx = 0; idx < args.length; idx++) {
 			if(args[idx].equals("-format")) {
 				idx++;
@@ -288,6 +289,8 @@
 					e1.printStackTrace();
 					System.exit(1);
 				}
+			} else if(args[idx].equals("-blockDump")) {
+				blockDump = true;
 			} else if(args[idx].equals("-max")) {
 				idx++;
 				if(idx >= args.length) {
@@ -322,15 +325,25 @@
 		
 		try {
 			zl.init();
-			Iterator<String> itr = zl.getStringPrefixIterator(key);
-			boolean truncated = ((StringPrefixIterator)itr).isTruncated();
-			while(itr.hasNext()) {
-				pw.println(itr.next());
+			if(blockDump) {
+				
+				ArrayList<ZiplinedBlock> blocks = zl.getBlockListForPrefix(key);
+				for(ZiplinedBlock block : blocks) {
+					pw.format("%s\t%s\n", block.urlOrPath, block.offset);
+				}
+				pw.close();
+
+			} else {
+				Iterator<String> itr = zl.getStringPrefixIterator(key);
+				boolean truncated = ((StringPrefixIterator)itr).isTruncated();
+				while(itr.hasNext()) {
+					pw.println(itr.next());
+				}
+				pw.close();
+				if(truncated) {
+					System.err.println("Note that results are truncated...");
+				}
 			}
-			pw.close();
-			if(truncated) {
-				System.err.println("Note that results are truncated...");
-			}
 		} catch (ResourceIndexNotAvailableException e) {
 			// TODO Auto-generated catch block
 			e.printStackTrace();


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

[Archive-access-cvs] SF.net SVN: archive-access:[3445] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/resourcestore/indexer/ HTTPRecordAnnotater.java

From: <bra...@us...> - 2011-05-25 01:20:20

Revision: 3445
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3445&view=rev
Author:   bradtofel
Date:     2011-05-25 01:20:09 +0000 (Wed, 25 May 2011)

Log Message:
-----------
BUGFIX(unreported) NPEs

Modified Paths:
--------------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/indexer/HTTPRecordAnnotater.java

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/indexer/HTTPRecordAnnotater.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/indexer/HTTPRecordAnnotater.java	2011-05-25 01:19:41 UTC (rev 3444)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/indexer/HTTPRecordAnnotater.java	2011-05-25 01:20:09 UTC (rev 3445)
@@ -73,6 +73,9 @@
 	}
 	
 	public String transformHTTPMime(String input) {
+		if(input == null) {
+			return null;
+		}
 		int semiIdx = input.indexOf(";");
 		if(semiIdx > 0) {
 			return escapeSpaces(input.substring(0,semiIdx).trim());
@@ -121,6 +124,9 @@
 			// nothing present in the HTTP headers.. Use the WARC field:
 			mimeType = transformHTTPMime(mimeGuess);
 		}
+		if(mimeType == null) {
+			mimeType = "unknown";
+		}
 		result.setMimeType(mimeType);
 		// Now the sticky part: If it looks like an HTML document, look for
 		// robot meta tags:


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

[Archive-access-cvs] SF.net SVN: archive-access:[3444] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/resourcestore/indexer/ WARCRecordToSearchResultAdapter.java

From: <bra...@us...> - 2011-05-25 01:19:47

Revision: 3444
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3444&view=rev
Author:   bradtofel
Date:     2011-05-25 01:19:41 +0000 (Wed, 25 May 2011)

Log Message:
-----------
BUGFIX(unreported) NPEs

Modified Paths:
--------------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/indexer/WARCRecordToSearchResultAdapter.java

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/indexer/WARCRecordToSearchResultAdapter.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/indexer/WARCRecordToSearchResultAdapter.java	2011-05-25 01:16:36 UTC (rev 3443)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/indexer/WARCRecordToSearchResultAdapter.java	2011-05-25 01:19:41 UTC (rev 3444)
@@ -99,7 +99,7 @@
 
 		if(type.equals(WARCConstants.RESPONSE)) {
 			String mime = annotater.transformHTTPMime(header.getMimetype());
-			if(mime.equals("text/dns")) {
+			if(mime != null && mime.equals("text/dns")) {
 				// close to complete reading, then the digest is legit
 				// TODO: DO we want to use the WARC header digest for this?
 				rec.close();
@@ -272,7 +272,8 @@
         int eolCharCount = getEolCharsCount(statusBytes);
         if (eolCharCount <= 0) {
             throw new RecoverableIOException("Failed to read http status where one " +
-                " was expected: " + new String(statusBytes));
+                    " was expected: " + 
+                    ((statusBytes == null) ? "(null)" : new String(statusBytes)));
         }
         String statusLine = EncodingUtil.getString(statusBytes, 0,
             statusBytes.length - eolCharCount, ARCConstants.DEFAULT_ENCODING);


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

[Archive-access-cvs] SF.net SVN: archive-access:[3443] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/util/Timestamp.java

From: <bra...@us...> - 2011-05-25 01:16:43

Revision: 3443
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3443&view=rev
Author:   bradtofel
Date:     2011-05-25 01:16:36 +0000 (Wed, 25 May 2011)

Log Message:
-----------
OPTIMIZ: removed all internal references to Calendars, now depending mostly on ArchiveUtils date parsing - this was causing lots of lock contention in related TimeZone code.

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

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/Timestamp.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/Timestamp.java	2011-05-25 01:08:38 UTC (rev 3442)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/Timestamp.java	2011-05-25 01:16:36 UTC (rev 3443)
@@ -19,13 +19,16 @@
  */
 package org.archive.wayback.util;
 
+import java.text.ParseException;
 import java.util.Calendar;
 import java.util.Date;
 import java.util.GregorianCalendar;
 import java.util.SimpleTimeZone;
 import java.util.TimeZone;
 
+import org.archive.util.ArchiveUtils;
 
+
 /**
  * Represents a moment in time as a 14-digit string, and interally as a Date.
  * 
@@ -54,6 +57,32 @@
 	private final static String[] months = { "Jan", "Feb", "Mar", "Apr", "May",
 			"Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec" };
 
+	private final static String DAYS_IN_MONTH[][];
+	private final static int DIM_START_YEAR = 1972;
+	private final static int DIM_END_YEAR = 2032;
+	static {
+		Calendar cal = Calendar.getInstance(TimeZone.getTimeZone("GMT"));
+		cal.clear();
+		int years = DIM_END_YEAR - DIM_START_YEAR;
+		DAYS_IN_MONTH = new String[years][12];
+		for(int y = 0; y < years; y++) {
+			for(int m = 0; m < 12; m++) {
+				cal.set(Calendar.YEAR,DIM_START_YEAR + y);
+				cal.set(Calendar.MONTH,m);
+				cal.set(Calendar.DAY_OF_MONTH,1);
+				int calV = cal.getActualMaximum(Calendar.DAY_OF_MONTH);
+				String maxDayOfMonth = String.valueOf(calV);
+				if(maxDayOfMonth.length() == 1) {
+					maxDayOfMonth = "0" + maxDayOfMonth;
+				}
+				DAYS_IN_MONTH[y][m] = maxDayOfMonth;
+			}
+		}
+	}
+	private static String getDaysInMonthBound(int year, int month) {
+		return DAYS_IN_MONTH[year - DIM_START_YEAR][month];
+	}
+	
 	private String dateStr = null;
 	private Date date = null;
 
@@ -61,50 +90,42 @@
 	 * Constructor
 	 */
 	public Timestamp() {
-		super();
 	}
 	
 	/**
 	 * Construct and initialize structure from a 14-digit String timestamp. If
 	 * the argument is too short, or specifies an invalid timestamp, cleanup
 	 * will be attempted to create the earliest legal timestamp given the input.
-	 * @param dateStr
+	 * @param dateStr from which to set date
 	 */
 	public Timestamp(final String dateStr) {
-		super();
-
-		Calendar cal = dateStrToCalendar(dateStr);
-		setDate(cal.getTime());
+		setDate(dateStrToDate(dateStr));
 	}
 
 	/**
 	 * Construct and initialize structure from an integer number of seconds
 	 * since the epoch.
-	 * @param sse
+	 * @param sse SecondsSinceEpoch
 	 */
 	public Timestamp(final int sse) {
-		super();
 		setSse(sse);
 	}
 
 	/**
 	 * Construct and initialize structure from an Date
-	 * @param date
+	 * @param date from which date should be set
 	 */
 	public Timestamp(final Date date) {
-		super();
 		setDate(date);
 	}
 
 	/**
 	 * set internal structure using Date argument
-	 * @param date
+	 * @param date from which date should be set
 	 */
 	public void setDate(final Date date) {
 		this.date = (Date) date.clone();
-		Calendar cal = getCalendar();
-		cal.setTime(this.date);
-		dateStr = calendarToDateStr(cal);		
+		dateStr = ArchiveUtils.get14DigitDate(date);
 	}
 	
 	
@@ -117,7 +138,7 @@
 
 	/**
 	 * set internal structure using seconds since the epoch integer argument
-	 * @param sse
+	 * @param sse SecondsSinceEpoch
 	 */
 	public void setSse(final int sse) {
 		setDate(new Date(((long)sse) * 1000));
@@ -128,11 +149,10 @@
 	 * argument. Will clean up timestamp as needed to yield the ealiest
 	 * possible timestamp given the possible partial or wrong argument.
 	 * 
-	 * @param dateStr
+	 * @param dateStr containing the timestamp
 	 */
 	public void setDateStr(String dateStr) {
-		Calendar cal = dateStrToCalendar(dateStr);
-		setDate(cal.getTime());
+		setDate(dateStrToDate(dateStr));
 	}
 
 	/**
@@ -156,7 +176,7 @@
 	 * timeStamp and the arguments timeStamp. result is the absolute number of
 	 * seconds difference.
 	 * 
-	 * @param otherTimeStamp
+	 * @param otherTimeStamp to compare
 	 * @return int absolute seconds between the argument and this records
 	 *         timestamp.
 	 */
@@ -170,7 +190,7 @@
 	 * timeStamp is less than the argument, positive if it is greater, and 0 if
 	 * the same.
 	 * 
-	 * @param otherTimeStamp
+	 * @param otherTimeStamp to compare
 	 * @return int milliseconds
 	 */
 	public int distanceFromTimestamp(final Timestamp otherTimeStamp) {
@@ -238,18 +258,6 @@
 	 * 
 	 */
 	
-	private static String frontZeroPad(final String input, final int digits) {
-		int missing = digits - input.length();
-		String padded = "";
-		for(int i = 0; i < missing; i++) {
-			padded += "0";
-		}
-		padded += input;
-		return padded;
-	}
-	private static String frontZeroPad(final int input, final int digits) {
-		return frontZeroPad(String.valueOf(input)	,digits);
-	}
 	
 	private static Calendar getCalendar() {
 		String[] ids = TimeZone.getAvailableIDs(0);
@@ -259,19 +267,15 @@
 		TimeZone gmt = new SimpleTimeZone(0, ids[0]);
 		return new GregorianCalendar(gmt);		
 	}
-	
+
 	/**
-	 * cleanup the dateStr argument assuming earliest values, and return a
-	 * GMT calendar set to the time described by the dateStr.
-	 * 
-	 * @param dateStr
-	 * @return Calendar
+	 * @param dateStr up to 14 digit String representing date
+	 * @return a GMT Calendar object, set to the date represented
 	 */
 	public static Calendar dateStrToCalendar(final String dateStr) {
-		
+		Calendar cal = Calendar.getInstance(TimeZone.getTimeZone("GMT"));
 		String paddedDateStr = padStartDateStr(dateStr);
 
-		Calendar cal = getCalendar();
 		int iYear = Integer.parseInt(paddedDateStr.substring(0,4));
 		int iMonth = Integer.parseInt(paddedDateStr.substring(4,6));
 		int iDay = Integer.parseInt(paddedDateStr.substring(6,8));
@@ -289,13 +293,24 @@
 		
 		return cal;
 	}
-	private static String calendarToDateStr(Calendar cal) {
-		return frontZeroPad(cal.get(Calendar.YEAR),4) +
-			frontZeroPad(cal.get(Calendar.MONTH) + 1 ,2) +
-			frontZeroPad(cal.get(Calendar.DAY_OF_MONTH),2) +
-			frontZeroPad(cal.get(Calendar.HOUR_OF_DAY),2) +
-			frontZeroPad(cal.get(Calendar.MINUTE),2) +
-			frontZeroPad(cal.get(Calendar.SECOND),2);
+	/**
+	 * cleanup the dateStr argument assuming earliest values, and return a
+	 * GMT calendar set to the time described by the dateStr.
+	 * 
+	 * @param dateStr from which to create Calendar
+	 * @return Calendar
+	 */
+	public static Date dateStrToDate(final String dateStr) {
+		
+		String paddedDateStr = padStartDateStr(dateStr);
+		try {
+			return ArchiveUtils.parse14DigitDate(paddedDateStr);
+		} catch (ParseException e) {
+			e.printStackTrace();
+			// TODO: This is certainly not the right thing, but padStartDateStr
+			// should ensure we *never* get here..
+			return new Date(SSE_1996);
+		}
 	}
 	
 
@@ -333,18 +348,16 @@
 		}
 		return test;
 	}
-	
+
 	// check each of YEAR, MONTH, DAY, HOUR, MINUTE, SECOND to make sure they
 	// are not too large or too small, factoring in the month, leap years, etc.
+	// BUGBUG: Leap second bug here.. How long till someone notices?
 	private static String boundTimestamp(String input) {
 		String boundTimestamp = "";
 		if(input == null) {
 			input = "";
 		}
 		// MAKE SURE THE YEAR IS WITHIN LEGAL BOUNDARIES:
-		Calendar tmpCal = getCalendar();
-		tmpCal.setTime(new Date());
-
 		boundTimestamp = boundDigits(input.substring(0,4),
 				YEAR_LOWER_LIMIT,YEAR_UPPER_LIMIT);
 
@@ -354,18 +367,10 @@
 		
 		// NOW DEPENDING ON THE YEAR + MONTH, MAKE SURE THE DAY OF MONTH IS
 		// WITHIN LEGAL BOUNDARIES:
-		Calendar cal = getCalendar();
-		cal.clear();
 		int iYear = Integer.parseInt(boundTimestamp.substring(0,4));
 		int iMonth = Integer.parseInt(boundTimestamp.substring(4,6));
-		cal.set(Calendar.YEAR,iYear);
-		cal.set(Calendar.MONTH,iMonth - 1);
-		cal.set(Calendar.DAY_OF_MONTH,1);
+		String maxDayOfMonth = getDaysInMonthBound(iYear, iMonth-1);
 
-		String maxDayOfMonth = String.valueOf(cal.getActualMaximum(Calendar.DAY_OF_MONTH));
-		if(maxDayOfMonth.length() == 1) {
-			maxDayOfMonth = "0" + maxDayOfMonth;
-		}
 		boundTimestamp += boundDigits(input.substring(6,8),
 				DAY_LOWER_LIMIT,maxDayOfMonth);
 		
@@ -383,7 +388,7 @@
 
 		return boundTimestamp;		
 	}
-	
+
 	/**
 	 * clean up timestamp argument assuming latest possible values for missing 
 	 * or bogus digits.
@@ -407,7 +412,7 @@
 	}
 
 	/**
-	 * @param dateStr
+	 * @param dateStr containing timestamp
 	 * @return Timestamp object representing the earliest date represented by
 	 *         the (possibly) partial digit-string argument.
 	 */
@@ -416,7 +421,7 @@
 	}
 
 	/**
-	 * @param dateStr
+	 * @param dateStr containing timestamp
 	 * @return Timestamp object representing the latest date represented by the
 	 *         (possibly) partial digit-string argument.
 	 */
@@ -425,7 +430,7 @@
 	}
 
 	/**
-	 * @param sse
+	 * @param sse SecondsSinceEpoch
 	 * @return Timestamp object representing the seconds since epoch argument.
 	 */
 	public static Timestamp fromSse(final int sse) {


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

[Archive-access-cvs] SF.net SVN: archive-access:[3442] trunk/archive-access/projects/wayback/ wayback-core/src

From: <bra...@us...> - 2011-05-25 01:08:44

Revision: 3442
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3442&view=rev
Author:   bradtofel
Date:     2011-05-25 01:08:38 +0000 (Wed, 25 May 2011)

Log Message:
-----------
BUGFIX: urlToPath was not handling ports correctly

Modified Paths:
--------------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java
    trunk/archive-access/projects/wayback/wayback-core/src/test/java/org/archive/wayback/util/url/UrlOperationsTest.java

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java	2011-05-25 01:04:11 UTC (rev 3441)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java	2011-05-25 01:08:38 UTC (rev 3442)
@@ -220,25 +220,28 @@
 	 * @return the path component of the URL, or "" if it contains no path.
 	 */
 	public static String getURLPath(String url) {
-		int portIdx = url.indexOf(UrlOperations.PORT_SEPARATOR);
+		url = stripURLScheme(url);
 		int pathIdx = url.indexOf(UrlOperations.PATH_START);
-		if(portIdx == -1 && pathIdx == -1) {
-			return "";
-		}
-		if(portIdx == -1) {
-			return url.substring(pathIdx);
-		}
 		if(pathIdx == -1) {
-			return url.substring(portIdx);
+			return "/";
 		}
-		if(pathIdx > portIdx) {
-			return url.substring(portIdx);
-		} else {
-			return url.substring(pathIdx);
-		}
+		return url.substring(pathIdx);
 	}
-	
 	/**
+	 * Attempt to extract the path component of a url String argument.
+	 * @param url the URL which may contain a path, sans scheme.
+	 * @return the path component of the URL, or "" if it contains no path.
+	 */
+	public static String stripURLScheme(String url) {
+		String lcUrl = url.toLowerCase();
+		for(String scheme : ALL_SCHEMES) {
+			if(lcUrl.startsWith(scheme)) {
+				return url.substring(scheme.length());
+			}
+		}
+		return url;
+	}	
+	/**
 	 * Attempt to strip default ports out of URL strings.
 	 * @param url the original URL possibly including a port
 	 * @return the URL sans port, if the scheme was recognized and the default
@@ -279,6 +282,11 @@
 		return sb.toString();
 	}
 
+	/**
+	 * @param orig String containing a URL, possibly beginning with "http:/".
+	 * @return original string if orig begins with "http://", or a new String
+	 * with the extra slash, if orig only had one slash.
+	 */
 	public static String fixupHTTPUrlWithOneSlash(String orig) {
 		if(orig.startsWith("http:/") && ! orig.startsWith(HTTP_SCHEME)) {
 			// very likely the IE "you must have meant 1 slash, not 2 bug:

Modified: trunk/archive-access/projects/wayback/wayback-core/src/test/java/org/archive/wayback/util/url/UrlOperationsTest.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/test/java/org/archive/wayback/util/url/UrlOperationsTest.java	2011-05-25 01:04:11 UTC (rev 3441)
+++ trunk/archive-access/projects/wayback/wayback-core/src/test/java/org/archive/wayback/util/url/UrlOperationsTest.java	2011-05-25 01:08:38 UTC (rev 3442)
@@ -205,7 +205,29 @@
 		
 		
 	}
+	public void testUrlPath() {
+		assertEquals("/",UrlOperations.getURLPath("http://foo.com"));
+		assertEquals("/",UrlOperations.getURLPath("http://foo.com/"));
+		assertEquals("/",UrlOperations.getURLPath("http://foo.com:80/"));
+		assertEquals("/blue",UrlOperations.getURLPath("http://foo.com:80/blue"));
+		assertEquals("/blue/red",UrlOperations.getURLPath("http://foo.com:80/blue/red"));
+		assertEquals("/blue/red:colon",UrlOperations.getURLPath("http://foo.com:80/blue/red:colon"));
 
+		assertEquals("/",UrlOperations.getURLPath("foo.com"));
+		assertEquals("/",UrlOperations.getURLPath("foo.com:80"));
+		assertEquals("/",UrlOperations.getURLPath("foo.com:8080"));
+		assertEquals("/",UrlOperations.getURLPath("foo.com/"));
+		assertEquals("/",UrlOperations.getURLPath("foo.com:80/"));
+		assertEquals("/",UrlOperations.getURLPath("foo.com:8080/"));
+		assertEquals("/bar",UrlOperations.getURLPath("foo.com/bar"));
+		assertEquals("/bar",UrlOperations.getURLPath("foo.com:80/bar"));
+		assertEquals("/bar",UrlOperations.getURLPath("foo.com:8080/bar"));
+
+		assertEquals("/bar/baz",UrlOperations.getURLPath("foo.com/bar/baz"));
+		assertEquals("/bar/baz",UrlOperations.getURLPath("foo.com:80/bar/baz"));
+		assertEquals("/bar/baz",UrlOperations.getURLPath("foo.com:8080/bar/baz"));
+
+	}
 	public void testStripDefaultPort() {
 		assertSDP("http://foo.com/","http://foo.com/");
 		assertSDP("http://foo.com","http://foo.com");


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

[Archive-access-cvs] SF.net SVN: archive-access:[3441] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/webapp/LiveWebAccessPoint. java

From: <bra...@us...> - 2011-05-25 01:04:17

Revision: 3441
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3441&view=rev
Author:   bradtofel
Date:     2011-05-25 01:04:11 +0000 (Wed, 25 May 2011)

Log Message:
-----------
TWEAK: live web AccessPoint no longer attempts to retrieve non HTTP documents.

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

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/LiveWebAccessPoint.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/LiveWebAccessPoint.java	2011-05-25 01:03:17 UTC (rev 3440)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/LiveWebAccessPoint.java	2011-05-25 01:04:11 UTC (rev 3441)
@@ -77,6 +77,9 @@
 		wbRequest.setRequestUrl(urlString);
 		URL url = null;
 		try {
+			if(!urlString.startsWith(UrlOperations.HTTP_SCHEME)) {
+				throw new ResourceNotInArchiveException(urlString);
+			}
 			Thread.currentThread().setName("Thread " + 
 					Thread.currentThread().getId() + " " + getBeanName() + 
 					" handling: " + urlString);


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

[Archive-access-cvs] SF.net SVN: archive-access:[3440] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java

From: <bra...@us...> - 2011-05-25 01:03:23

Revision: 3440
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3440&view=rev
Author:   bradtofel
Date:     2011-05-25 01:03:17 +0000 (Wed, 25 May 2011)

Log Message:
-----------
JAVADOC

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

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java	2011-05-25 01:02:18 UTC (rev 3439)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java	2011-05-25 01:03:17 UTC (rev 3440)
@@ -702,7 +702,7 @@
 	}
 
 	/**
-	 * @param filePrefixes List of String file prefixes that will be matched
+	 * @param fileIncludePrefixes List of String file prefixes that will be matched
 	 * 		when querying the ResourceIndex - only SearchResults from files 
 	 * 		with a prefix matching one of those in this List will be returned.
 	 */
@@ -719,7 +719,7 @@
 	}
 
 	/**
-	 * @param filePrefixes List of String file prefixes that will be matched
+	 * @param fileExcludePrefixes List of String file prefixes that will be matched
 	 * 		when querying the ResourceIndex - only SearchResults from files 
 	 * 		with a prefix matching one of those in this List will be returned.
 	 */
@@ -893,9 +893,15 @@
 		this.bounceToQueryPrefix = bounceToQueryPrefix;
 	}
 
+	/**
+	 * @return the configured number of MS for min age to return from the index
+	 */
 	public long getEmbargoMS() {
 		return embargoMS;
 	}
+	/**
+	 * @param ms minimum number of MS age for content to be served from the index
+	 */
 	public void setEmbargoMS(long ms) {
 		this.embargoMS = ms;
 	}


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

[Archive-access-cvs] SF.net SVN: archive-access:[3439] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/util/webapp/PortMapper.java

From: <bra...@us...> - 2011-05-25 01:02:24

Revision: 3439
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3439&view=rev
Author:   bradtofel
Date:     2011-05-25 01:02:18 +0000 (Wed, 25 May 2011)

Log Message:
-----------
BUGFIX: needed to add extra slash to pathPrefix for non-ROOT deployment to function.
FEATURE: re-enabled production of correct AccessPoint lists, when clients fail to specify the final path component of an AccessPoint

Modified Paths:
--------------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/webapp/PortMapper.java

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/webapp/PortMapper.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/webapp/PortMapper.java	2011-05-17 17:41:50 UTC (rev 3438)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/webapp/PortMapper.java	2011-05-25 01:02:18 UTC (rev 3439)
@@ -19,6 +19,7 @@
  */
 package org.archive.wayback.util.webapp;
 
+import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.logging.Logger;
 
@@ -130,9 +131,9 @@
 		String host = requestToHost(request);
 		String contextPath = request.getContextPath();
 		StringBuilder pathPrefix = new StringBuilder(contextPath);
-		if(contextPath.length() == 0) {
+//		if(contextPath.length() == 0) {
 			pathPrefix.append("/");
-		}
+//		}
 		String firstPath = requestToFirstPath(request);
 		RequestHandler handler = pathMap.get(hostPathToKey(host,firstPath));
 		if(handler != null) {
@@ -152,6 +153,20 @@
 		if(handler != null) {
 			return new RequestHandlerContext(handler,contextPath);
 		}
+		// Nothing matching this port:host:path. Try to help get user back on
+		// track. Note this won't help with hostname mismatches at the moment:
+		ArrayList<String> paths = new ArrayList<String>();
+		for(String tmp : pathMap.keySet()) {
+			// slice off last chunk:
+			int idx = tmp.lastIndexOf('/');
+			if(idx != -1) {
+				String path = tmp.substring(idx+1);
+				paths.add(path);
+			}
+		}
+		if(paths.size() > 0) {
+			request.setAttribute("AccessPointNames", paths);
+		}
 		return null;
 	}
 }


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

[Archive-access-cvs] SF.net SVN: archive-access:[3438] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile

From: <bra...@us...> - 2011-05-17 17:41:56

Revision: 3438
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3438&view=rev
Author:   bradtofel
Date:     2011-05-17 17:41:50 +0000 (Tue, 17 May 2011)

Log Message:
-----------
BUGFIX(unreported): No longer relies on Heritrix ArchiveReader to perform seek() operation, as this behavior seems to have been broken.

Modified Paths:
--------------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ArcResource.java
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ResourceFactory.java
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/WarcResource.java

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ArcResource.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ArcResource.java	2011-04-19 22:41:25 UTC (rev 3437)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ArcResource.java	2011-05-17 17:41:50 UTC (rev 3438)
@@ -28,8 +28,8 @@
 import java.util.Set;
 
 import org.apache.commons.httpclient.Header;
+import org.archive.io.ArchiveReader;
 import org.archive.io.ArchiveRecord;
-import org.archive.io.arc.ARCReader;
 import org.archive.io.arc.ARCRecord;
 import org.archive.wayback.core.Resource;
 import org.archive.wayback.replay.HttpHeaderOperation;
@@ -54,7 +54,7 @@
 	 * object for ARCReader -- need to hold on to this in order to call close()
 	 * to release filehandle after completing access to this record. optional
 	 */
-	ARCReader arcReader = null;
+	ArchiveReader arcReader = null;
 	/**
 	 * flag to indicate if the ARCRecord skipHTTPHeader() has been called
 	 */
@@ -71,7 +71,7 @@
 	 * @param rec
 	 * @param reader 
 	 */
-	public ArcResource(final ARCRecord rec,final ARCReader reader) {
+	public ArcResource(final ARCRecord rec,final ArchiveReader reader) {
 		super();
 		arcRecord = rec;
 		arcReader = reader;

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ResourceFactory.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ResourceFactory.java	2011-04-19 22:41:25 UTC (rev 3437)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ResourceFactory.java	2011-05-17 17:41:50 UTC (rev 3438)
@@ -20,7 +20,10 @@
 package org.archive.wayback.resourcestore.resourcefile;
 
 import java.io.File;
+import java.io.FileInputStream;
 import java.io.IOException;
+import java.io.InputStream;
+import java.io.RandomAccessFile;
 import java.net.URL;
 
 import org.archive.io.ArchiveReader;
@@ -62,15 +65,18 @@
 			name = name.substring(0, name.length()
 					- ArcWarcFilenameFilter.OPEN_SUFFIX.length());
 		}
+		RandomAccessFile raf = new RandomAccessFile(file, "r");
+		raf.seek(offset);
+		InputStream is = new FileInputStream(raf.getFD());
+		String fPath = file.getAbsolutePath();
 		if (isArc(name)) {
+			ArchiveReader reader = ARCReaderFactory.get(fPath, is, false);
+			r = ARCArchiveRecordToResource(reader.get(), reader);
 
-			ARCReader reader = ARCReaderFactory.get(file,offset);
-			r = ARCArchiveRecordToResource(reader.get(),reader);
-
 		} else if (isWarc(name)) {
 
-			WARCReader reader = WARCReaderFactory.get(file,offset);
-			r = WARCArchiveRecordToResource(reader.get(),reader);
+			ArchiveReader reader = WARCReaderFactory.get(fPath, is, false);
+			r = WARCArchiveRecordToResource(reader.get(), reader);
 
 		} else {
 			throw new ResourceNotAvailableException("Unknown extension");
@@ -78,7 +84,6 @@
 
 		return r;
 	}
-
 	public static Resource getResource(URL url, long offset)
 	throws IOException, ResourceNotAvailableException {
 		
@@ -114,7 +119,7 @@
 	}
 	
 	public static Resource ARCArchiveRecordToResource(ArchiveRecord rec,
-			ARCReader reader) throws ResourceNotAvailableException, IOException {
+			ArchiveReader reader) throws ResourceNotAvailableException, IOException {
 
 		if (!(rec instanceof ARCRecord)) {
 			throw new ResourceNotAvailableException("Bad ARCRecord format");
@@ -125,7 +130,7 @@
 	}
 
 	public static Resource WARCArchiveRecordToResource(ArchiveRecord rec,
-			WARCReader reader) throws ResourceNotAvailableException, IOException {
+			ArchiveReader reader) throws ResourceNotAvailableException, IOException {
 
 		if (!(rec instanceof WARCRecord)) {
 			throw new ResourceNotAvailableException("Bad WARCRecord format");

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/WarcResource.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/WarcResource.java	2011-04-19 22:41:25 UTC (rev 3437)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/WarcResource.java	2011-05-17 17:41:50 UTC (rev 3438)
@@ -27,21 +27,21 @@
 import org.apache.commons.httpclient.HttpParser;
 import org.apache.commons.httpclient.StatusLine;
 import org.apache.commons.httpclient.util.EncodingUtil;
+import org.archive.io.ArchiveReader;
 import org.archive.io.RecoverableIOException;
 import org.archive.io.arc.ARCConstants;
-import org.archive.io.warc.WARCReader;
 import org.archive.io.warc.WARCRecord;
 import org.archive.wayback.core.Resource;
 import org.archive.wayback.replay.HttpHeaderOperation;
 
 public class WarcResource extends Resource {
 	private WARCRecord rec = null;
-	private WARCReader reader = null;
+	private ArchiveReader reader = null;
 	private Map<String, String> headers = null;
 	private long length = 0;
 	private int status = 0;
 	private boolean parsedHeaders = false;
-	public WarcResource(WARCRecord rec, WARCReader reader) {
+	public WarcResource(WARCRecord rec, ArchiveReader reader) {
 		this.rec = rec;
 		this.reader = reader;
 	}


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

[Archive-access-cvs] SF.net SVN: archive-access:[3437] branches/wayback-1_6_1

From: <bra...@us...> - 2011-04-19 22:41:32

Revision: 3437
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3437&view=rev
Author:   bradtofel
Date:     2011-04-19 22:41:25 +0000 (Tue, 19 Apr 2011)

Log Message:
-----------
BUGFIX + 1.6.1 RELEASE CANDIDATE:

Modified Paths:
--------------
    branches/wayback-1_6_1/dist/pom.xml
    branches/wayback-1_6_1/pom.xml
    branches/wayback-1_6_1/wayback-core/pom.xml
    branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/liveweb/ARCCacheDirectory.java
    branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ArcResource.java
    branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ResourceFactory.java
    branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/WarcResource.java
    branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/ARCCreator.java
    branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/WARCHeader.java
    branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/webapp/PortMapper.java
    branches/wayback-1_6_1/wayback-hadoop/pom.xml
    branches/wayback-1_6_1/wayback-hadoop-java/pom.xml
    branches/wayback-1_6_1/wayback-webapp/pom.xml

Modified: branches/wayback-1_6_1/dist/pom.xml
===================================================================
--- branches/wayback-1_6_1/dist/pom.xml	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/dist/pom.xml	2011-04-19 22:41:25 UTC (rev 3437)
@@ -7,7 +7,7 @@
   <parent>
     <artifactId>wayback</artifactId>
     <groupId>org.archive.wayback</groupId>
-    <version>1.6.0</version>
+    <version>1.6.1</version>
   </parent>
 
   <artifactId>dist</artifactId>

Modified: branches/wayback-1_6_1/pom.xml
===================================================================
--- branches/wayback-1_6_1/pom.xml	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/pom.xml	2011-04-19 22:41:25 UTC (rev 3437)
@@ -7,7 +7,7 @@
   <groupId>org.archive.wayback</groupId>
   <artifactId>wayback</artifactId>
   <packaging>pom</packaging>
-  <version>1.6.0</version>
+  <version>1.6.1</version>
   <name>Wayback</name>
 
   <modules>
@@ -262,7 +262,7 @@
       <dependency>
         <groupId>org.archive.heritrix</groupId>
         <artifactId>heritrix-commons</artifactId>
-        <version>3.1.1-SNAPSHOT</version>
+        <version>3.0.1-SNAPSHOT</version>
       </dependency>
       <dependency>
         <groupId>org.archive.access-control</groupId>

Modified: branches/wayback-1_6_1/wayback-core/pom.xml
===================================================================
--- branches/wayback-1_6_1/wayback-core/pom.xml	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-core/pom.xml	2011-04-19 22:41:25 UTC (rev 3437)
@@ -8,7 +8,7 @@
   <parent>
     <artifactId>wayback</artifactId>
     <groupId>org.archive.wayback</groupId>
-    <version>1.6.0</version>
+    <version>1.6.1</version>
   </parent>
 
   <artifactId>wayback-core</artifactId>

Modified: branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/liveweb/ARCCacheDirectory.java
===================================================================
--- branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/liveweb/ARCCacheDirectory.java	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/liveweb/ARCCacheDirectory.java	2011-04-19 22:41:25 UTC (rev 3437)
@@ -159,6 +159,15 @@
 			public String getTemplate() {
 				return LIVE_WAYBACK_TEMPLATE;
 			}
+
+			public boolean getFrequentFlushes() {
+				// TODO Auto-generated method stub
+				return false;
+			}
+
+			public int getWriteBufferSize() {
+				return 4096;
+			}
 		};
 	}
 

Modified: branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ArcResource.java
===================================================================
--- branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ArcResource.java	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ArcResource.java	2011-04-19 22:41:25 UTC (rev 3437)
@@ -28,6 +28,7 @@
 import java.util.Set;
 
 import org.apache.commons.httpclient.Header;
+import org.archive.io.ArchiveReader;
 import org.archive.io.ArchiveRecord;
 import org.archive.io.arc.ARCReader;
 import org.archive.io.arc.ARCRecord;
@@ -54,7 +55,7 @@
 	 * object for ARCReader -- need to hold on to this in order to call close()
 	 * to release filehandle after completing access to this record. optional
 	 */
-	ARCReader arcReader = null;
+	ArchiveReader arcReader = null;
 	/**
 	 * flag to indicate if the ARCRecord skipHTTPHeader() has been called
 	 */
@@ -71,7 +72,7 @@
 	 * @param rec
 	 * @param reader 
 	 */
-	public ArcResource(final ARCRecord rec,final ARCReader reader) {
+	public ArcResource(final ARCRecord rec,final ArchiveReader reader) {
 		super();
 		arcRecord = rec;
 		arcReader = reader;

Modified: branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ResourceFactory.java
===================================================================
--- branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ResourceFactory.java	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/ResourceFactory.java	2011-04-19 22:41:25 UTC (rev 3437)
@@ -20,7 +20,10 @@
 package org.archive.wayback.resourcestore.resourcefile;
 
 import java.io.File;
+import java.io.FileInputStream;
 import java.io.IOException;
+import java.io.InputStream;
+import java.io.RandomAccessFile;
 import java.net.URL;
 
 import org.archive.io.ArchiveReader;
@@ -62,14 +65,19 @@
 			name = name.substring(0, name.length()
 					- ArcWarcFilenameFilter.OPEN_SUFFIX.length());
 		}
+		RandomAccessFile raf = new RandomAccessFile(file, "r");
+		raf.seek(offset);
+		InputStream is = new FileInputStream(raf.getFD());
+		String fPath = file.getAbsolutePath();
 		if (isArc(name)) {
-
-			ARCReader reader = ARCReaderFactory.get(file,offset);
+//			ARCReader reader = ARCReaderFactory.get(file,offset);
+			ArchiveReader reader = ARCReaderFactory.get(fPath,is,false);
 			r = ARCArchiveRecordToResource(reader.get(),reader);
 
 		} else if (isWarc(name)) {
 
-			WARCReader reader = WARCReaderFactory.get(file,offset);
+			ArchiveReader reader = WARCReaderFactory.get(fPath,is,false);
+//			WARCReader reader = WARCReaderFactory.get(file,offset);
 			r = WARCArchiveRecordToResource(reader.get(),reader);
 
 		} else {
@@ -114,7 +122,7 @@
 	}
 	
 	public static Resource ARCArchiveRecordToResource(ArchiveRecord rec,
-			ARCReader reader) throws ResourceNotAvailableException, IOException {
+			ArchiveReader reader) throws ResourceNotAvailableException, IOException {
 
 		if (!(rec instanceof ARCRecord)) {
 			throw new ResourceNotAvailableException("Bad ARCRecord format");
@@ -125,7 +133,7 @@
 	}
 
 	public static Resource WARCArchiveRecordToResource(ArchiveRecord rec,
-			WARCReader reader) throws ResourceNotAvailableException, IOException {
+			ArchiveReader reader) throws ResourceNotAvailableException, IOException {
 
 		if (!(rec instanceof WARCRecord)) {
 			throw new ResourceNotAvailableException("Bad WARCRecord format");

Modified: branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/WarcResource.java
===================================================================
--- branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/WarcResource.java	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/resourcestore/resourcefile/WarcResource.java	2011-04-19 22:41:25 UTC (rev 3437)
@@ -27,6 +27,7 @@
 import org.apache.commons.httpclient.HttpParser;
 import org.apache.commons.httpclient.StatusLine;
 import org.apache.commons.httpclient.util.EncodingUtil;
+import org.archive.io.ArchiveReader;
 import org.archive.io.RecoverableIOException;
 import org.archive.io.arc.ARCConstants;
 import org.archive.io.warc.WARCReader;
@@ -36,12 +37,12 @@
 
 public class WarcResource extends Resource {
 	private WARCRecord rec = null;
-	private WARCReader reader = null;
+	private ArchiveReader reader = null;
 	private Map<String, String> headers = null;
 	private long length = 0;
 	private int status = 0;
 	private boolean parsedHeaders = false;
-	public WarcResource(WARCRecord rec, WARCReader reader) {
+	public WarcResource(WARCRecord rec, ArchiveReader reader) {
 		this.rec = rec;
 		this.reader = reader;
 	}

Modified: branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/ARCCreator.java
===================================================================
--- branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/ARCCreator.java	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/ARCCreator.java	2011-04-19 22:41:25 UTC (rev 3437)
@@ -26,9 +26,11 @@
 import java.text.ParseException;
 import java.util.Arrays;
 import java.util.HashMap;
+import java.util.List;
 import java.util.concurrent.atomic.AtomicInteger;
 import java.util.logging.Logger;
 
+import org.archive.io.WriterPoolSettings;
 import org.archive.io.arc.ARCConstants;
 import org.archive.io.arc.ARCWriter;
 import org.archive.util.ArchiveUtils;
@@ -98,9 +100,12 @@
 	throws IOException {
 		
 		File target[] = {tgtDir};
+
+//		ARCWriter writer = new ARCWriter(new AtomicInteger(),
+//				Arrays.asList(target),prefix,true,
+//				ARCConstants.DEFAULT_MAX_ARC_FILE_SIZE);
 		ARCWriter writer = new ARCWriter(new AtomicInteger(),
-				Arrays.asList(target),prefix,true,
-				ARCConstants.DEFAULT_MAX_ARC_FILE_SIZE);
+				getSettings(true,prefix,Arrays.asList(target)));
 		File sources[] = srcDir.listFiles();
 		LOGGER.info("Found " + sources.length + " files in " + srcDir);
 		for(int i = 0; i<sources.length; i++) {
@@ -121,6 +126,43 @@
 		LOGGER.info("Closed arc file named " + 
 				writer.getFile().getAbsolutePath());
 	}
+	private WriterPoolSettings getSettings(final boolean isCompressed,
+			final String prefix, final List<File> arcDirs) {
+		return new WriterPoolSettings() {
+			public List<File> getOutputDirs() {
+				return arcDirs;
+			}
+
+			@SuppressWarnings({ "unchecked", "rawtypes" })
+			public List getMetadata() {
+				return null;
+			}
+
+			public String getPrefix() {
+				return prefix;
+			}
+
+			public boolean getCompress() {
+				return isCompressed;
+			}
+
+			public long getMaxFileSizeBytes() {
+				return ARCConstants.DEFAULT_MAX_ARC_FILE_SIZE;
+			}
+
+			public String getTemplate() {
+				return "${prefix}-${timestamp17}-${serialno}";
+			}
+
+			public boolean getFrequentFlushes() {
+				return false;
+			}
+
+			public int getWriteBufferSize() {
+				return 4096;
+			}
+		};
+	}
 	
 	/**
 	 * @param args

Modified: branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/WARCHeader.java
===================================================================
--- branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/WARCHeader.java	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/WARCHeader.java	2011-04-19 22:41:25 UTC (rev 3437)
@@ -26,8 +26,14 @@
 import java.io.IOException;
 import java.util.ArrayList;
 import java.util.List;
+import java.util.concurrent.atomic.AtomicInteger;
 
+import org.archive.io.WriterPoolSettings;
+import org.archive.io.arc.ARCConstants;
 import org.archive.io.warc.WARCWriter;
+import org.archive.io.warc.WARCWriterPoolSettings;
+import org.archive.uid.RecordIDGenerator;
+import org.archive.uid.UUIDGenerator;
 import org.archive.util.anvl.ANVLRecord;
 
 public class WARCHeader {
@@ -45,8 +51,9 @@
 		List<String> metadata = new ArrayList<String>(1);
 		metadata.add(ar.toString());
 
-		writer = new WARCWriter(null, bos, target, true, null,
-				metadata);
+//		writer = new WARCWriter(new AtomicInteger(),null, bos, target, true, null,
+//				metadata);
+		writer = new WARCWriter(new AtomicInteger(),bos,target,getSettings(true, null, null, metadata));
 		// Write a warcinfo record with description about how this WARC
 		// was made.
 		writer.writeWarcinfoRecord(target.getName(), "Made from "
@@ -54,7 +61,48 @@
 				+ this.getClass().getName());
 
 	}
+	private WARCWriterPoolSettings getSettings(final boolean isCompressed,
+			final String prefix, final List<File> arcDirs, final List metadata) {
+		return new WARCWriterPoolSettings() {
+			public List<File> getOutputDirs() {
+				return arcDirs;
+			}
 
+			@SuppressWarnings({ "unchecked", "rawtypes" })
+			public List getMetadata() {
+				return metadata;
+			}
+
+			public String getPrefix() {
+				return prefix;
+			}
+
+			public boolean getCompress() {
+				return isCompressed;
+			}
+
+			public long getMaxFileSizeBytes() {
+				return ARCConstants.DEFAULT_MAX_ARC_FILE_SIZE;
+			}
+
+			public String getTemplate() {
+				return "${prefix}-${timestamp17}-${serialno}";
+			}
+
+			public boolean getFrequentFlushes() {
+				return false;
+			}
+
+			public int getWriteBufferSize() {
+				return 4096;
+			}
+
+			public RecordIDGenerator getRecordIDGenerator() {
+				return new UUIDGenerator();
+			}
+		};
+	}
+
 	public static void main(String[] args) {
 		if (args.length != 3) {
 			System.err.println("USAGE: tgtWarc fieldsSrc id");

Modified: branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/webapp/PortMapper.java
===================================================================
--- branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/webapp/PortMapper.java	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-core/src/main/java/org/archive/wayback/util/webapp/PortMapper.java	2011-04-19 22:41:25 UTC (rev 3437)
@@ -130,9 +130,9 @@
 		String host = requestToHost(request);
 		String contextPath = request.getContextPath();
 		StringBuilder pathPrefix = new StringBuilder(contextPath);
-		if(contextPath.length() == 0) {
+//		if(contextPath.length() == 0) {
 			pathPrefix.append("/");
-		}
+//		}
 		String firstPath = requestToFirstPath(request);
 		RequestHandler handler = pathMap.get(hostPathToKey(host,firstPath));
 		if(handler != null) {

Modified: branches/wayback-1_6_1/wayback-hadoop/pom.xml
===================================================================
--- branches/wayback-1_6_1/wayback-hadoop/pom.xml	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-hadoop/pom.xml	2011-04-19 22:41:25 UTC (rev 3437)
@@ -8,7 +8,7 @@
   <parent>
     <artifactId>wayback</artifactId>
     <groupId>org.archive.wayback</groupId>
-    <version>1.6.0</version>
+    <version>1.6.1</version>
   </parent>
 
   <artifactId>wayback-hadoop</artifactId>

Modified: branches/wayback-1_6_1/wayback-hadoop-java/pom.xml
===================================================================
--- branches/wayback-1_6_1/wayback-hadoop-java/pom.xml	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-hadoop-java/pom.xml	2011-04-19 22:41:25 UTC (rev 3437)
@@ -8,7 +8,7 @@
   <parent>
     <artifactId>wayback</artifactId>
     <groupId>org.archive.wayback</groupId>
-    <version>1.6.0</version>
+    <version>1.6.1</version>
   </parent>
 
   <artifactId>wayback-hadoop-java</artifactId>

Modified: branches/wayback-1_6_1/wayback-webapp/pom.xml
===================================================================
--- branches/wayback-1_6_1/wayback-webapp/pom.xml	2011-04-16 17:37:26 UTC (rev 3436)
+++ branches/wayback-1_6_1/wayback-webapp/pom.xml	2011-04-19 22:41:25 UTC (rev 3437)
@@ -7,7 +7,7 @@
   <parent>
     <artifactId>wayback</artifactId>
     <groupId>org.archive.wayback</groupId>
-    <version>1.6.0</version>
+    <version>1.6.1</version>
   </parent>
 
   <artifactId>wayback-webapp</artifactId>


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

[Archive-access-cvs] SF.net SVN: archive-access:[3436] tags/nutchwax-0_13-JIRA-WAX-75/archive

From: <bi...@us...> - 2011-04-16 17:37:32

Revision: 3436
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3436&view=rev
Author:   binzino
Date:     2011-04-16 17:37:26 +0000 (Sat, 16 Apr 2011)

Log Message:
-----------
Fix WAX-77.  Import Heritrix3 commons library which handles the gzip problem.

Modified Paths:
--------------
    tags/nutchwax-0_13-JIRA-WAX-75/archive/build.xml

Added Paths:
-----------
    tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/commons-lang-2.3.jar
    tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/guava-r08.jar
    tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/heritrix-commons-3.0.1-SNAPSHOT.jar
    tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/kryo-1.01.jar

Removed Paths:
-------------
    tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/commons-2.0.1-SNAPSHOT.LICENSE
    tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/commons-2.0.1-SNAPSHOT.jar

Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/build.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/build.xml	2011-04-16 17:21:25 UTC (rev 3435)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/build.xml	2011-04-16 17:37:26 UTC (rev 3436)
@@ -27,6 +27,7 @@
   <property name="dist.dir"  value="${build.dir}/${final.name}" />
 
   <target name="init">
+    <delete file="../../lib/commons-lang-2.1.jar" />
     <exec executable="rsync">
       <arg value="-vacC"/>
       <arg value="src/nutch/"/>

Deleted: tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/commons-2.0.1-SNAPSHOT.LICENSE
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/commons-2.0.1-SNAPSHOT.LICENSE	2011-04-16 17:21:25 UTC (rev 3435)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/commons-2.0.1-SNAPSHOT.LICENSE	2011-04-16 17:37:26 UTC (rev 3436)
@@ -1,504 +0,0 @@
-		  GNU LESSER GENERAL PUBLIC LICENSE
-		       Version 2.1, February 1999
-
- Copyright (C) 1991, 1999 Free Software Foundation, Inc.
- 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-[This is the first released version of the Lesser GPL.  It also counts
- as the successor of the GNU Library Public License, version 2, hence
- the version number 2.1.]
-
-			    Preamble
-
-  The licenses for most software are designed to take away your
-freedom to share and change it.  By contrast, the GNU General Public
-Licenses are intended to guarantee your freedom to share and change
-free software--to make sure the software is free for all its users.
-
-  This license, the Lesser General Public License, applies to some
-specially designated software packages--typically libraries--of the
-Free Software Foundation and other authors who decide to use it.  You
-can use it too, but we suggest you first think carefully about whether
-this license or the ordinary General Public License is the better
-strategy to use in any particular case, based on the explanations below.
-
-  When we speak of free software, we are referring to freedom of use,
-not price.  Our General Public Licenses are designed to make sure that
-you have the freedom to distribute copies of free software (and charge
-for this service if you wish); that you receive source code or can get
-it if you want it; that you can change the software and use pieces of
-it in new free programs; and that you are informed that you can do
-these things.
-
-  To protect your rights, we need to make restrictions that forbid
-distributors to deny you these rights or to ask you to surrender these
-rights.  These restrictions translate to certain responsibilities for
-you if you distribute copies of the library or if you modify it.
-
-  For example, if you distribute copies of the library, whether gratis
-or for a fee, you must give the recipients all the rights that we gave
-you.  You must make sure that they, too, receive or can get the source
-code.  If you link other code with the library, you must provide
-complete object files to the recipients, so that they can relink them
-with the library after making changes to the library and recompiling
-it.  And you must show them these terms so they know their rights.
-
-  We protect your rights with a two-step method: (1) we copyright the
-library, and (2) we offer you this license, which gives you legal
-permission to copy, distribute and/or modify the library.
-
-  To protect each distributor, we want to make it very clear that
-there is no warranty for the free library.  Also, if the library is
-modified by someone else and passed on, the recipients should know
-that what they have is not the original version, so that the original
-author's reputation will not be affected by problems that might be
-introduced by others.
-
-  Finally, software patents pose a constant threat to the existence of
-any free program.  We wish to make sure that a company cannot
-effectively restrict the users of a free program by obtaining a
-restrictive license from a patent holder.  Therefore, we insist that
-any patent license obtained for a version of the library must be
-consistent with the full freedom of use specified in this license.
-
-  Most GNU software, including some libraries, is covered by the
-ordinary GNU General Public License.  This license, the GNU Lesser
-General Public License, applies to certain designated libraries, and
-is quite different from the ordinary General Public License.  We use
-this license for certain libraries in order to permit linking those
-libraries into non-free programs.
-
-  When a program is linked with a library, whether statically or using
-a shared library, the combination of the two is legally speaking a
-combined work, a derivative of the original library.  The ordinary
-General Public License therefore permits such linking only if the
-entire combination fits its criteria of freedom.  The Lesser General
-Public License permits more lax criteria for linking other code with
-the library.
-
-  We call this license the "Lesser" General Public License because it
-does Less to protect the user's freedom than the ordinary General
-Public License.  It also provides other free software developers Less
-of an advantage over competing non-free programs.  These disadvantages
-are the reason we use the ordinary General Public License for many
-libraries.  However, the Lesser license provides advantages in certain
-special circumstances.
-
-  For example, on rare occasions, there may be a special need to
-encourage the widest possible use of a certain library, so that it becomes
-a de-facto standard.  To achieve this, non-free programs must be
-allowed to use the library.  A more frequent case is that a free
-library does the same job as widely used non-free libraries.  In this
-case, there is little to gain by limiting the free library to free
-software only, so we use the Lesser General Public License.
-
-  In other cases, permission to use a particular library in non-free
-programs enables a greater number of people to use a large body of
-free software.  For example, permission to use the GNU C Library in
-non-free programs enables many more people to use the whole GNU
-operating system, as well as its variant, the GNU/Linux operating
-system.
-
-  Although the Lesser General Public License is Less protective of the
-users' freedom, it does ensure that the user of a program that is
-linked with the Library has the freedom and the wherewithal to run
-that program using a modified version of the Library.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.  Pay close attention to the difference between a
-"work based on the library" and a "work that uses the library".  The
-former contains code derived from the library, whereas the latter must
-be combined with the library in order to run.
-
-		  GNU LESSER GENERAL PUBLIC LICENSE
-   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
-
-  0. This License Agreement applies to any software library or other
-program which contains a notice placed by the copyright holder or
-other authorized party saying it may be distributed under the terms of
-this Lesser General Public License (also called "this License").
-Each licensee is addressed as "you".
-
-  A "library" means a collection of software functions and/or data
-prepared so as to be conveniently linked with application programs
-(which use some of those functions and data) to form executables.
-
-  The "Library", below, refers to any such software library or work
-which has been distributed under these terms.  A "work based on the
-Library" means either the Library or any derivative work under
-copyright law: that is to say, a work containing the Library or a
-portion of it, either verbatim or with modifications and/or translated
-straightforwardly into another language.  (Hereinafter, translation is
-included without limitation in the term "modification".)
-
-  "Source code" for a work means the preferred form of the work for
-making modifications to it.  For a library, complete source code means
-all the source code for all modules it contains, plus any associated
-interface definition files, plus the scripts used to control compilation
-and installation of the library.
-
-  Activities other than copying, distribution and modification are not
-covered by this License; they are outside its scope.  The act of
-running a program using the Library is not restricted, and output from
-such a program is covered only if its contents constitute a work based
-on the Library (independent of the use of the Library in a tool for
-writing it).  Whether that is true depends on what the Library does
-and what the program that uses the Library does.
-  
-  1. You may copy and distribute verbatim copies of the Library's
-complete source code as you receive it, in any medium, provided that
-you conspicuously and appropriately publish on each copy an
-appropriate copyright notice and disclaimer of warranty; keep intact
-all the notices that refer to this License and to the absence of any
-warranty; and distribute a copy of this License along with the
-Library.
-
-  You may charge a fee for the physical act of transferring a copy,
-and you may at your option offer warranty protection in exchange for a
-fee.
-
-  2. You may modify your copy or copies of the Library or any portion
-of it, thus forming a work based on the Library, and copy and
-distribute such modifications or work under the terms of Section 1
-above, provided that you also meet all of these conditions:
-
-    a) The modified work must itself be a software library.
-
-    b) You must cause the files modified to carry prominent notices
-    stating that you changed the files and the date of any change.
-
-    c) You must cause the whole of the work to be licensed at no
-    charge to all third parties under the terms of this License.
-
-    d) If a facility in the modified Library refers to a function or a
-    table of data to be supplied by an application program that uses
-    the facility, other than as an argument passed when the facility
-    is invoked, then you must make a good faith effort to ensure that,
-    in the event an application does not supply such function or
-    table, the facility still operates, and performs whatever part of
-    its purpose remains meaningful.
-
-    (For example, a function in a library to compute square roots has
-    a purpose that is entirely well-defined independent of the
-    application.  Therefore, Subsection 2d requires that any
-    application-supplied function or table used by this function must
-    be optional: if the application does not supply it, the square
-    root function must still compute square roots.)
-
-These requirements apply to the modified work as a whole.  If
-identifiable sections of that work are not derived from the Library,
-and can be reasonably considered independent and separate works in
-themselves, then this License, and its terms, do not apply to those
-sections when you distribute them as separate works.  But when you
-distribute the same sections as part of a whole which is a work based
-on the Library, the distribution of the whole must be on the terms of
-this License, whose permissions for other licensees extend to the
-entire whole, and thus to each and every part regardless of who wrote
-it.
-
-Thus, it is not the intent of this section to claim rights or contest
-your rights to work written entirely by you; rather, the intent is to
-exercise the right to control the distribution of derivative or
-collective works based on the Library.
-
-In addition, mere aggregation of another work not based on the Library
-with the Library (or with a work based on the Library) on a volume of
-a storage or distribution medium does not bring the other work under
-the scope of this License.
-
-  3. You may opt to apply the terms of the ordinary GNU General Public
-License instead of this License to a given copy of the Library.  To do
-this, you must alter all the notices that refer to this License, so
-that they refer to the ordinary GNU General Public License, version 2,
-instead of to this License.  (If a newer version than version 2 of the
-ordinary GNU General Public License has appeared, then you can specify
-that version instead if you wish.)  Do not make any other change in
-these notices.
-
-  Once this change is made in a given copy, it is irreversible for
-that copy, so the ordinary GNU General Public License applies to all
-subsequent copies and derivative works made from that copy.
-
-  This option is useful when you wish to copy part of the code of
-the Library into a program that is not a library.
-
-  4. You may copy and distribute the Library (or a portion or
-derivative of it, under Section 2) in object code or executable form
-under the terms of Sections 1 and 2 above provided that you accompany
-it with the complete corresponding machine-readable source code, which
-must be distributed under the terms of Sections 1 and 2 above on a
-medium customarily used for software interchange.
-
-  If distribution of object code is made by offering access to copy
-from a designated place, then offering equivalent access to copy the
-source code from the same place satisfies the requirement to
-distribute the source code, even though third parties are not
-compelled to copy the source along with the object code.
-
-  5. A program that contains no derivative of any portion of the
-Library, but is designed to work with the Library by being compiled or
-linked with it, is called a "work that uses the Library".  Such a
-work, in isolation, is not a derivative work of the Library, and
-therefore falls outside the scope of this License.
-
-  However, linking a "work that uses the Library" with the Library
-creates an executable that is a derivative of the Library (because it
-contains portions of the Library), rather than a "work that uses the
-library".  The executable is therefore covered by this License.
-Section 6 states terms for distribution of such executables.
-
-  When a "work that uses the Library" uses material from a header file
-that is part of the Library, the object code for the work may be a
-derivative work of the Library even though the source code is not.
-Whether this is true is especially significant if the work can be
-linked without the Library, or if the work is itself a library.  The
-threshold for this to be true is not precisely defined by law.
-
-  If such an object file uses only numerical parameters, data
-structure layouts and accessors, and small macros and small inline
-functions (ten lines or less in length), then the use of the object
-file is unrestricted, regardless of whether it is legally a derivative
-work.  (Executables containing this object code plus portions of the
-Library will still fall under Section 6.)
-
-  Otherwise, if the work is a derivative of the Library, you may
-distribute the object code for the work under the terms of Section 6.
-Any executables containing that work also fall under Section 6,
-whether or not they are linked directly with the Library itself.
-
-  6. As an exception to the Sections above, you may also combine or
-link a "work that uses the Library" with the Library to produce a
-work containing portions of the Library, and distribute that work
-under terms of your choice, provided that the terms permit
-modification of the work for the customer's own use and reverse
-engineering for debugging such modifications.
-
-  You must give prominent notice with each copy of the work that the
-Library is used in it and that the Library and its use are covered by
-this License.  You must supply a copy of this License.  If the work
-during execution displays copyright notices, you must include the
-copyright notice for the Library among them, as well as a reference
-directing the user to the copy of this License.  Also, you must do one
-of these things:
-
-    a) Accompany the work with the complete corresponding
-    machine-readable source code for the Library including whatever
-    changes were used in the work (which must be distributed under
-    Sections 1 and 2 above); and, if the work is an executable linked
-    with the Library, with the complete machine-readable "work that
-    uses the Library", as object code and/or source code, so that the
-    user can modify the Library and then relink to produce a modified
-    executable containing the modified Library.  (It is understood
-    that the user who changes the contents of definitions files in the
-    Library will not necessarily be able to recompile the application
-    to use the modified definitions.)
-
-    b) Use a suitable shared library mechanism for linking with the
-    Library.  A suitable mechanism is one that (1) uses at run time a
-    copy of the library already present on the user's computer system,
-    rather than copying library functions into the executable, and (2)
-    will operate properly with a modified version of the library, if
-    the user installs one, as long as the modified version is
-    interface-compatible with the version that the work was made with.
-
-    c) Accompany the work with a written offer, valid for at
-    least three years, to give the same user the materials
-    specified in Subsection 6a, above, for a charge no more
-    than the cost of performing this distribution.
-
-    d) If distribution of the work is made by offering access to copy
-    from a designated place, offer equivalent access to copy the above
-    specified materials from the same place.
-
-    e) Verify that the user has already received a copy of these
-    materials or that you have already sent this user a copy.
-
-  For an executable, the required form of the "work that uses the
-Library" must include any data and utility programs needed for
-reproducing the executable from it.  However, as a special exception,
-the materials to be distributed need not include anything that is
-normally distributed (in either source or binary form) with the major
-components (compiler, kernel, and so on) of the operating system on
-which the executable runs, unless that component itself accompanies
-the executable.
-
-  It may happen that this requirement contradicts the license
-restrictions of other proprietary libraries that do not normally
-accompany the operating system.  Such a contradiction means you cannot
-use both them and the Library together in an executable that you
-distribute.
-
-  7. You may place library facilities that are a work based on the
-Library side-by-side in a single library together with other library
-facilities not covered by this License, and distribute such a combined
-library, provided that the separate distribution of the work based on
-the Library and of the other library facilities is otherwise
-permitted, and provided that you do these two things:
-
-    a) Accompany the combined library with a copy of the same work
-    based on the Library, uncombined with any other library
-    facilities.  This must be distributed under the terms of the
-    Sections above.
-
-    b) Give prominent notice with the combined library of the fact
-    that part of it is a work based on the Library, and explaining
-    where to find the accompanying uncombined form of the same work.
-
-  8. You may not copy, modify, sublicense, link with, or distribute
-the Library except as expressly provided under this License.  Any
-attempt otherwise to copy, modify, sublicense, link with, or
-distribute the Library is void, and will automatically terminate your
-rights under this License.  However, parties who have received copies,
-or rights, from you under this License will not have their licenses
-terminated so long as such parties remain in full compliance.
-
-  9. You are not required to accept this License, since you have not
-signed it.  However, nothing else grants you permission to modify or
-distribute the Library or its derivative works.  These actions are
-prohibited by law if you do not accept this License.  Therefore, by
-modifying or distributing the Library (or any work based on the
-Library), you indicate your acceptance of this License to do so, and
-all its terms and conditions for copying, distributing or modifying
-the Library or works based on it.
-
-  10. Each time you redistribute the Library (or any work based on the
-Library), the recipient automatically receives a license from the
-original licensor to copy, distribute, link with or modify the Library
-subject to these terms and conditions.  You may not impose any further
-restrictions on the recipients' exercise of the rights granted herein.
-You are not responsible for enforcing compliance by third parties with
-this License.
-
-  11. If, as a consequence of a court judgment or allegation of patent
-infringement or for any other reason (not limited to patent issues),
-conditions are imposed on you (whether by court order, agreement or
-otherwise) that contradict the conditions of this License, they do not
-excuse you from the conditions of this License.  If you cannot
-distribute so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you
-may not distribute the Library at all.  For example, if a patent
-license would not permit royalty-free redistribution of the Library by
-all those who receive copies directly or indirectly through you, then
-the only way you could satisfy both it and this License would be to
-refrain entirely from distribution of the Library.
-
-If any portion of this section is held invalid or unenforceable under any
-particular circumstance, the balance of the section is intended to apply,
-and the section as a whole is intended to apply in other circumstances.
-
-It is not the purpose of this section to induce you to infringe any
-patents or other property right claims or to contest validity of any
-such claims; this section has the sole purpose of protecting the
-integrity of the free software distribution system which is
-implemented by public license practices.  Many people have made
-generous contributions to the wide range of software distributed
-through that system in reliance on consistent application of that
-system; it is up to the author/donor to decide if he or she is willing
-to distribute software through any other system and a licensee cannot
-impose that choice.
-
-This section is intended to make thoroughly clear what is believed to
-be a consequence of the rest of this License.
-
-  12. If the distribution and/or use of the Library is restricted in
-certain countries either by patents or by copyrighted interfaces, the
-original copyright holder who places the Library under this License may add
-an explicit geographical distribution limitation excluding those countries,
-so that distribution is permitted only in or among countries not thus
-excluded.  In such case, this License incorporates the limitation as if
-written in the body of this License.
-
-  13. The Free Software Foundation may publish revised and/or new
-versions of the Lesser General Public License from time to time.
-Such new versions will be similar in spirit to the present version,
-but may differ in detail to address new problems or concerns.
-
-Each version is given a distinguishing version number.  If the Library
-specifies a version number of this License which applies to it and
-"any later version", you have the option of following the terms and
-conditions either of that version or of any later version published by
-the Free Software Foundation.  If the Library does not specify a
-license version number, you may choose any version ever published by
-the Free Software Foundation.
-
-  14. If you wish to incorporate parts of the Library into other free
-programs whose distribution conditions are incompatible with these,
-write to the author to ask for permission.  For software which is
-copyrighted by the Free Software Foundation, write to the Free
-Software Foundation; we sometimes make exceptions for this.  Our
-decision will be guided by the two goals of preserving the free status
-of all derivatives of our free software and of promoting the sharing
-and reuse of software generally.
-
-			    NO WARRANTY
-
-  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
-WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
-EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
-OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
-KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
-LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
-THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
-
-  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
-WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
-AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
-FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
-CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
-LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
-RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
-FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
-SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
-DAMAGES.
-
-		     END OF TERMS AND CONDITIONS
-
-           How to Apply These Terms to Your New Libraries
-
-  If you develop a new library, and you want it to be of the greatest
-possible use to the public, we recommend making it free software that
-everyone can redistribute and change.  You can do so by permitting
-redistribution under these terms (or, alternatively, under the terms of the
-ordinary General Public License).
-
-  To apply these terms, attach the following notices to the library.  It is
-safest to attach them to the start of each source file to most effectively
-convey the exclusion of warranty; and each file should have at least the
-"copyright" line and a pointer to where the full notice is found.
-
-    <one line to give the library's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
-
-    This library is free software; you can redistribute it and/or
-    modify it under the terms of the GNU Lesser General Public
-    License as published by the Free Software Foundation; either
-    version 2.1 of the License, or (at your option) any later version.
-
-    This library 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 General Public License for more details.
-
-    You should have received a copy of the GNU Lesser General Public
-    License along with this library; if not, write to the Free Software
-    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
-
-Also add information on how to contact you by electronic and paper mail.
-
-You should also get your employer (if you work as a programmer) or your
-school, if any, to sign a "copyright disclaimer" for the library, if
-necessary.  Here is a sample; alter the names:
-
-  Yoyodyne, Inc., hereby disclaims all copyright interest in the
-  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
-
-  <signature of Ty Coon>, 1 April 1990
-  Ty Coon, President of Vice
-
-That's all there is to it!
-
-

Deleted: tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/commons-2.0.1-SNAPSHOT.jar
===================================================================
(Binary files differ)

Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/commons-lang-2.3.jar
===================================================================
(Binary files differ)


Property changes on: tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/commons-lang-2.3.jar
___________________________________________________________________
Added: svn:mime-type
   + application/octet-stream

Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/guava-r08.jar
===================================================================
(Binary files differ)


Property changes on: tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/guava-r08.jar
___________________________________________________________________
Added: svn:mime-type
   + application/octet-stream

Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/heritrix-commons-3.0.1-SNAPSHOT.jar
===================================================================
(Binary files differ)


Property changes on: tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/heritrix-commons-3.0.1-SNAPSHOT.jar
___________________________________________________________________
Added: svn:mime-type
   + application/octet-stream

Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/kryo-1.01.jar
===================================================================
(Binary files differ)


Property changes on: tags/nutchwax-0_13-JIRA-WAX-75/archive/lib/kryo-1.01.jar
___________________________________________________________________
Added: svn:mime-type
   + application/octet-stream


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

[Archive-access-cvs] SF.net SVN: archive-access:[3435] tags/nutchwax-0_13-JIRA-WAX-75/archive/ src/nutch/src/java/org/apache/nutch

From: <bi...@us...> - 2011-04-16 17:21:31

Revision: 3435
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3435&view=rev
Author:   binzino
Date:     2011-04-16 17:21:25 +0000 (Sat, 16 Apr 2011)

Log Message:
-----------
Remove 'content', 'crawl_parse', and 'crawl_data' subdirs from Nutch segment.  Not used for NutchWAX.

Added Paths:
-----------
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/fetcher/
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/fetcher/FetcherOutputFormat.java
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/parse/ParseOutputFormat.java

Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/fetcher/FetcherOutputFormat.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/fetcher/FetcherOutputFormat.java	                        (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/fetcher/FetcherOutputFormat.java	2011-04-16 17:21:25 UTC (rev 3435)
@@ -0,0 +1,124 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.nutch.fetcher;
+
+import java.io.IOException;
+
+import org.apache.nutch.crawl.CrawlDatum;
+import org.apache.nutch.crawl.NutchWritable;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+
+import org.apache.hadoop.io.MapFile;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.SequenceFile.CompressionType;
+
+import org.apache.hadoop.mapred.FileOutputFormat;
+import org.apache.hadoop.mapred.OutputFormat;
+import org.apache.hadoop.mapred.RecordWriter;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.mapred.SequenceFileOutputFormat;
+import org.apache.hadoop.util.Progressable;
+
+import org.apache.nutch.parse.Parse;
+import org.apache.nutch.parse.ParseOutputFormat;
+import org.apache.nutch.protocol.Content;
+
+/** Splits FetcherOutput entries into multiple map files. */
+public class FetcherOutputFormat implements OutputFormat<Text, NutchWritable> {
+
+  public void checkOutputSpecs(FileSystem fs, JobConf job) throws IOException {
+    Path out = FileOutputFormat.getOutputPath(job);
+    if (fs.exists(new Path(out, CrawlDatum.FETCH_DIR_NAME)))
+      throw new IOException("Segment already fetched!");
+  }
+
+  public RecordWriter<Text, NutchWritable> getRecordWriter(final FileSystem fs,
+                                      final JobConf job,
+                                      final String name,
+                                      final Progressable progress) throws IOException {
+
+    Path out = FileOutputFormat.getOutputPath(job);
+    /*
+    final Path fetch =
+      new Path(new Path(out, CrawlDatum.FETCH_DIR_NAME), name);
+    final Path content =
+      new Path(new Path(out, Content.DIR_NAME), name);
+    */
+    final CompressionType compType = SequenceFileOutputFormat.getOutputCompressionType(job);
+
+    /*
+    final MapFile.Writer fetchOut =
+      new MapFile.Writer(job, fs, fetch.toString(), Text.class, CrawlDatum.class,
+          compType, progress);
+    */
+    
+    return new RecordWriter<Text, NutchWritable>() {
+      //private MapFile.Writer contentOut;
+        private RecordWriter<Text, Parse> parseOut;
+
+        {
+          /*
+          if (Fetcher.isStoringContent(job)) {
+            contentOut = new MapFile.Writer(job, fs, content.toString(),
+                                            Text.class, Content.class,
+                                            compType, progress);
+          }
+          */
+
+          if (Fetcher.isParsing(job)) {
+            parseOut = new ParseOutputFormat().getRecordWriter(fs, job, name, progress);
+          }
+        }
+
+        public void write(Text key, NutchWritable value)
+          throws IOException {
+
+          Writable w = value.get();
+          
+          //if (w instanceof CrawlDatum)
+          //  fetchOut.append(key, w);
+          //else if (w instanceof Content)
+          //  contentOut.append(key, w);
+          //else if (w instanceof Parse)
+          //  parseOut.write(key, (Parse)w);
+          if (w instanceof Parse)
+            parseOut.write(key, (Parse)w);
+        }
+
+        public void close(Reporter reporter) throws IOException {
+          /*
+          if (fetchOut != null) {
+            fetchOut.close();
+          }
+          if (contentOut != null) {
+            contentOut.close();
+          }
+          */
+          if (parseOut != null) {
+            parseOut.close(reporter);
+          }
+        }
+
+      };
+
+  }      
+}
+

Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/parse/ParseOutputFormat.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/parse/ParseOutputFormat.java	                        (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/parse/ParseOutputFormat.java	2011-04-16 17:21:25 UTC (rev 3435)
@@ -0,0 +1,284 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.nutch.parse;
+
+// Commons Logging imports
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+
+import org.apache.hadoop.io.*;
+import org.apache.hadoop.io.SequenceFile.CompressionType;
+import org.apache.nutch.crawl.CrawlDatum;
+import org.apache.nutch.fetcher.Fetcher;
+import org.apache.hadoop.fs.*;
+import org.apache.hadoop.mapred.*;
+import org.apache.nutch.scoring.ScoringFilterException;
+import org.apache.nutch.scoring.ScoringFilters;
+import org.apache.nutch.util.StringUtil;
+import org.apache.nutch.util.URLUtil;
+import org.apache.nutch.metadata.Nutch;
+import org.apache.nutch.net.*;
+
+import java.io.*;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map.Entry;
+
+import org.apache.hadoop.util.Progressable;
+
+/* Parse content in a segment. */
+public class ParseOutputFormat implements OutputFormat<Text, Parse> {
+  private static final Log LOG = LogFactory.getLog(ParseOutputFormat.class);
+
+  private URLFilters filters;
+  private URLNormalizers normalizers;
+  private ScoringFilters scfilters;
+  
+  private static class SimpleEntry implements Entry<Text, CrawlDatum> {
+    private Text key;
+    private CrawlDatum value;
+    
+    public SimpleEntry(Text key, CrawlDatum value) {
+      this.key = key;
+      this.value = value;
+    }
+    
+    public Text getKey() {
+      return key;
+    }
+    
+    public CrawlDatum getValue() {
+      return value;
+    }
+
+    public CrawlDatum setValue(CrawlDatum value) {
+      this.value = value;
+      return this.value;
+    }
+  }
+
+  public void checkOutputSpecs(FileSystem fs, JobConf job) throws IOException {
+    Path out = FileOutputFormat.getOutputPath(job);
+    if (fs.exists(out))
+      throw new IOException("Segment already exists:" + out);
+  }
+
+  public RecordWriter<Text, Parse> getRecordWriter(FileSystem fs, JobConf job,
+                                      String name, Progressable progress) throws IOException {
+
+    this.filters = new URLFilters(job);
+    this.normalizers = new URLNormalizers(job, URLNormalizers.SCOPE_OUTLINK);
+    this.scfilters = new ScoringFilters(job);
+    final int interval = job.getInt("db.fetch.interval.default", 2592000);
+    final boolean ignoreExternalLinks = job.getBoolean("db.ignore.external.links", false);
+    int maxOutlinksPerPage = job.getInt("db.max.outlinks.per.page", 100);
+    final int maxOutlinks = (maxOutlinksPerPage < 0) ? Integer.MAX_VALUE
+                                                     : maxOutlinksPerPage;
+    final CompressionType compType = SequenceFileOutputFormat.getOutputCompressionType(job);
+    Path out = FileOutputFormat.getOutputPath(job);
+    
+    Path text = new Path(new Path(out, ParseText.DIR_NAME), name);
+    Path data = new Path(new Path(out, ParseData.DIR_NAME), name);
+    //Path crawl = new Path(new Path(out, CrawlDatum.PARSE_DIR_NAME), name);
+    
+    final String[] parseMDtoCrawlDB = job.get("db.parsemeta.to.crawldb","").split(" *, *");
+    
+    final MapFile.Writer textOut =
+      new MapFile.Writer(job, fs, text.toString(), Text.class, ParseText.class,
+          CompressionType.RECORD, progress);
+    
+    final MapFile.Writer dataOut =
+      new MapFile.Writer(job, fs, data.toString(), Text.class, ParseData.class,
+          compType, progress);
+    
+    /*
+    final SequenceFile.Writer crawlOut =
+      SequenceFile.createWriter(fs, job, crawl, Text.class, CrawlDatum.class,
+          compType, progress);
+    */
+    
+    return new RecordWriter<Text, Parse>() {
+
+
+        public void write(Text key, Parse parse)
+          throws IOException {
+          
+          String fromUrl = key.toString();
+          String fromHost = null; 
+          String toHost = null;          
+          textOut.append(key, new ParseText(parse.getText()));
+          
+          ParseData parseData = parse.getData();
+          // recover the signature prepared by Fetcher or ParseSegment
+          String sig = parseData.getContentMeta().get(Nutch.SIGNATURE_KEY);
+          if (sig != null) {
+            byte[] signature = StringUtil.fromHexString(sig);
+            if (signature != null) {
+              // append a CrawlDatum with a signature
+              CrawlDatum d = new CrawlDatum(CrawlDatum.STATUS_SIGNATURE, 0);
+              d.setSignature(signature);
+              //crawlOut.append(key, d);
+            }
+          }
+          
+        // see if the parse metadata contain things that we'd like
+        // to pass to the metadata of the crawlDB entry
+        CrawlDatum parseMDCrawlDatum = null;
+        for (String mdname : parseMDtoCrawlDB) {
+          String mdvalue = parse.getData().getParseMeta().get(mdname);
+          if (mdvalue != null) {
+            if (parseMDCrawlDatum == null) parseMDCrawlDatum = new CrawlDatum(
+                CrawlDatum.STATUS_PARSE_META, 0);
+            parseMDCrawlDatum.getMetaData().put(new Text(mdname),
+                new Text(mdvalue));
+          }
+        }
+        // if (parseMDCrawlDatum != null) crawlOut.append(key, parseMDCrawlDatum);
+
+          try {
+            ParseStatus pstatus = parseData.getStatus();
+            if (pstatus != null && pstatus.isSuccess() &&
+                pstatus.getMinorCode() == ParseStatus.SUCCESS_REDIRECT) {
+              String newUrl = pstatus.getMessage();
+              int refreshTime = Integer.valueOf(pstatus.getArgs()[1]);
+              try {
+                newUrl = normalizers.normalize(newUrl,
+                    URLNormalizers.SCOPE_FETCHER);
+              } catch (MalformedURLException mfue) {
+                newUrl = null;
+              }
+              if (newUrl != null) newUrl = filters.filter(newUrl);
+              String url = key.toString();
+              if (newUrl != null && !newUrl.equals(url)) {
+                String reprUrl =
+                  URLUtil.chooseRepr(url, newUrl,
+                                     refreshTime < Fetcher.PERM_REFRESH_TIME);
+                CrawlDatum newDatum = new CrawlDatum();
+                newDatum.setStatus(CrawlDatum.STATUS_LINKED);
+                if (reprUrl != null && !reprUrl.equals(newUrl)) {
+                  newDatum.getMetaData().put(Nutch.WRITABLE_REPR_URL_KEY,
+                                             new Text(reprUrl));
+                }
+                //crawlOut.append(new Text(newUrl), newDatum);
+              }
+            }
+          } catch (URLFilterException e) {
+            // ignore
+          }
+
+          // collect outlinks for subsequent db update
+          Outlink[] links = parseData.getOutlinks();
+          int outlinksToStore = Math.min(maxOutlinks, links.length);
+          if (ignoreExternalLinks) {
+            try {
+              fromHost = new URL(fromUrl).getHost().toLowerCase();
+            } catch (MalformedURLException e) {
+              fromHost = null;
+            }
+          } else {
+            fromHost = null;
+          }
+
+          int validCount = 0;
+          CrawlDatum adjust = null;
+          List<Entry<Text, CrawlDatum>> targets = new ArrayList<Entry<Text, CrawlDatum>>(outlinksToStore);
+          List<Outlink> outlinkList = new ArrayList<Outlink>(outlinksToStore);
+          for (int i = 0; i < links.length && validCount < outlinksToStore; i++) {
+            String toUrl = links[i].getToUrl();
+            // ignore links to self (or anchors within the page)
+            if (fromUrl.equals(toUrl)) {
+              continue;
+            }
+            if (ignoreExternalLinks) {
+              try {
+                toHost = new URL(toUrl).getHost().toLowerCase();
+              } catch (MalformedURLException e) {
+                toHost = null;
+              }
+              if (toHost == null || !toHost.equals(fromHost)) { // external links
+                continue; // skip it
+              }
+            }
+            try {
+              toUrl = normalizers.normalize(toUrl,
+                          URLNormalizers.SCOPE_OUTLINK); // normalize the url
+              toUrl = filters.filter(toUrl);   // filter the url
+              if (toUrl == null) {
+                continue;
+              }
+            } catch (Exception e) {
+              continue;
+            }
+            CrawlDatum target = new CrawlDatum(CrawlDatum.STATUS_LINKED, interval);
+            Text targetUrl = new Text(toUrl);
+            try {
+              scfilters.initialScore(targetUrl, target);
+            } catch (ScoringFilterException e) {
+              LOG.warn("Cannot filter init score for url " + key +
+                       ", using default: " + e.getMessage());
+              target.setScore(0.0f);
+            }
+            
+            targets.add(new SimpleEntry(targetUrl, target));
+            outlinkList.add(links[i]);
+            validCount++;
+          }
+          try {
+            // compute score contributions and adjustment to the original score
+            adjust = scfilters.distributeScoreToOutlinks((Text)key, parseData, 
+                      targets, null, links.length);
+          } catch (ScoringFilterException e) {
+            LOG.warn("Cannot distribute score from " + key + ": " + e.getMessage());
+          }
+          for (Entry<Text, CrawlDatum> target : targets) {
+            // crawlOut.append(target.getKey(), target.getValue());
+          }
+          // if (adjust != null) crawlOut.append(key, adjust);
+
+          Outlink[] filteredLinks = outlinkList.toArray(new Outlink[outlinkList.size()]);
+          parseData = new ParseData(parseData.getStatus(), parseData.getTitle(), 
+                                    filteredLinks, parseData.getContentMeta(), 
+                                    parseData.getParseMeta());
+          dataOut.append(key, parseData);
+          if (!parse.isCanonical()) {
+            CrawlDatum datum = new CrawlDatum();
+            datum.setStatus(CrawlDatum.STATUS_FETCH_SUCCESS);
+            String timeString = parse.getData().getContentMeta().get(Nutch.FETCH_TIME_KEY);
+            try {
+              datum.setFetchTime(Long.parseLong(timeString));
+            } catch (Exception e) {
+              LOG.warn("Can't read fetch time for: " + key);
+              datum.setFetchTime(System.currentTimeMillis());
+            }
+            //crawlOut.append(key, datum);
+          }
+        }
+        
+        public void close(Reporter reporter) throws IOException {
+          textOut.close();
+          dataOut.close();
+          //crawlOut.close();
+        }
+        
+      };
+    
+  }
+
+}


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

[Archive-access-cvs] SF.net SVN: archive-access:[3434] tags/nutchwax-0_13-JIRA-WAX-75/archive/ src/plugin/html-decorator/src/java/org/archive/nutchwax/html/HtmlDecorator. java

From: <bi...@us...> - 2011-04-16 02:38:46

Revision: 3434
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3434&view=rev
Author:   binzino
Date:     2011-04-16 02:38:39 +0000 (Sat, 16 Apr 2011)

Log Message:
-----------
Put keywords and description into content metadata, not parse metadata.  Remove System.out messages.

Modified Paths:
--------------
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/nutchwax/html/HtmlDecorator.java

Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/nutchwax/html/HtmlDecorator.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/nutchwax/html/HtmlDecorator.java	2011-04-16 00:02:08 UTC (rev 3433)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/nutchwax/html/HtmlDecorator.java	2011-04-16 02:38:39 UTC (rev 3434)
@@ -32,15 +32,13 @@
     // If there are no meta-tags, just return.
     if ( metaTags == null ) return parseResult;
 
-    Metadata parseMeta = parseResult.get( content.getUrl( ) ).getData().getParseMeta();
+    Metadata contentMeta = parseResult.get( content.getUrl( ) ).getData().getContentMeta();
     
     for ( String key : new String[] { "description", "keywords" } )
       {
         String value = metaTags.getGeneralTags().getProperty( key, "" );
 
-        System.out.println( key + ": " + value );
-
-        parseMeta.set( key, value );
+        contentMeta.set( key, value );
       }
 
     return parseResult;


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

[Archive-access-cvs] SF.net SVN: archive-access:[3433] tags/nutchwax-0_13-JIRA-WAX-75/archive

From: <bi...@us...> - 2011-04-16 00:02:15

Revision: 3433
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3433&view=rev
Author:   binzino
Date:     2011-04-16 00:02:08 +0000 (Sat, 16 Apr 2011)

Log Message:
-----------
Fix WAX-79.  HTML description and keywords meta tags are extracted.

Modified Paths:
--------------
    tags/nutchwax-0_13-JIRA-WAX-75/archive/build.xml
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/build.xml
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/nutch-site.xml
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/plugin/build.xml

Added Paths:
-----------
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/build.xml
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/plugin.xml
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/nutchwax/
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/nutchwax/html/
    tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/nutchwax/html/HtmlDecorator.java

Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/build.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/build.xml	2011-04-15 01:16:28 UTC (rev 3432)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/build.xml	2011-04-16 00:02:08 UTC (rev 3433)
@@ -23,7 +23,7 @@
   <property name="lib.dir"   value="lib" />
   <property name="build.dir" value="${nutch.dir}/build" />
   <!-- HACK: Need to import default.properties like Nutch does -->
-  <property name="final.name" value="nutch-1.0" />
+  <property name="final.name" value="nutch-1.1" />
   <property name="dist.dir"  value="${build.dir}/${final.name}" />
 
   <target name="init">

Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/build.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/build.xml	2011-04-15 01:16:28 UTC (rev 3432)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/build.xml	2011-04-16 00:02:08 UTC (rev 3433)
@@ -376,6 +376,7 @@
       <packageset dir="${plugins.dir}/query-nutchwax/src/java"/>
       <packageset dir="${plugins.dir}/scoring-nutchwax/src/java"/>
       <packageset dir="${plugins.dir}/urlfilter-nutchwax/src/java"/>
+      <packageset dir="${plugins.dir}/html-decorator/src/java"/>
 
       <link href="${javadoc.link.java}"/>
       <link href="${javadoc.link.lucene}"/>

Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/nutch-site.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/nutch-site.xml	2011-04-15 01:16:28 UTC (rev 3432)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/nutch-site.xml	2011-04-16 00:02:08 UTC (rev 3433)
@@ -10,7 +10,7 @@
   <!-- Add 'index-nutchwax' and 'query-nutchwax' to plugin list. -->
   <!-- Also, add 'parse-pdf' -->
   <!-- Remove 'urlfilter-regex' and 'normalizer-(pass|regex|basic)' -->
-  <value>protocol-http|parse-(pdf2|tika|text|html)|index-nutchwax|query-(basic|nutchwax)|summary-basic|scoring-nutchwax|urlfilter-nutchwax</value>
+  <value>protocol-http|parse-(pdf2|tika|text|html)|index-nutchwax|query-(basic|nutchwax)|summary-basic|scoring-nutchwax|urlfilter-nutchwax|html-decorator</value>
 </property>
 
 <!-- 

Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/plugin/build.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/plugin/build.xml	2011-04-15 01:16:28 UTC (rev 3432)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/plugin/build.xml	2011-04-16 00:02:08 UTC (rev 3433)
@@ -92,6 +92,7 @@
      <ant dir="scoring-nutchwax" target="deploy" />
      <ant dir="urlfilter-nutchwax" target="deploy" />
      <ant dir="parse-pdf2" target="deploy" />
+     <ant dir="html-decorator" target="deploy" />
 
   </target>
 
@@ -204,5 +205,6 @@
     <ant dir="scoring-nutchwax" target="clean" />
     <ant dir="urlfilter-nutchwax" target="clean" />
     <ant dir="parse-pdf2" target="clean" />
+    <ant dir="html-decorator" target="clean" />
   </target>
 </project>

Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/build.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/build.xml	                        (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/build.xml	2011-04-16 00:02:08 UTC (rev 3433)
@@ -0,0 +1,22 @@
+<?xml version="1.0"?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+<project name="html-decorator" default="jar-core">
+
+  <import file="../build-plugin.xml"/>
+
+</project>

Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/plugin.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/plugin.xml	                        (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/plugin.xml	2011-04-16 00:02:08 UTC (rev 3433)
@@ -0,0 +1,25 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<plugin
+   id="html-decorator"
+   name="NutchWAX HTML Decorator"
+   version="1.0.0"
+   provider-name="nutch.org">
+
+  <runtime>
+    <library name="html-decorator.jar">
+      <export name="*"/>
+    </library>
+  </runtime>
+  
+  <requires>
+    <import plugin="nutch-extensionpoints"/>
+  </requires>
+  
+  <extension id="org.archive.nutchwax.html.HtmlDecorator"
+             name="NutchWAX HTML Decorator"
+             point="org.apache.nutch.parse.HtmlParseFilter">
+    <implementation id="HtmlDecorator"
+                    class="org.archive.nutchwax.html.HtmlDecorator" />
+  </extension>
+  
+</plugin>

Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/nutchwax/html/HtmlDecorator.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/nutchwax/html/HtmlDecorator.java	                        (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/html-decorator/src/java/org/archive/nutchwax/html/HtmlDecorator.java	2011-04-16 00:02:08 UTC (rev 3433)
@@ -0,0 +1,58 @@
+
+package org.archive.nutchwax.html;
+
+import java.util.*;
+
+import org.apache.hadoop.conf.Configuration;
+
+import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.parse.HTMLMetaTags;
+import org.apache.nutch.parse.Parse;
+import org.apache.nutch.parse.ParseResult;
+import org.apache.nutch.parse.HtmlParseFilter;
+import org.apache.nutch.protocol.Content;
+import org.apache.nutch.util.NodeWalker;
+
+import org.w3c.dom.DocumentFragment;
+
+
+public class HtmlDecorator implements HtmlParseFilter
+{
+  private Configuration conf;
+
+
+  public ParseResult filter( Content      content, 
+                             ParseResult  parseResult, 
+                             HTMLMetaTags metaTags, 
+                             DocumentFragment doc )
+  {
+    // If no parse result, just return.
+    if ( parseResult == null ) return parseResult;
+
+    // If there are no meta-tags, just return.
+    if ( metaTags == null ) return parseResult;
+
+    Metadata parseMeta = parseResult.get( content.getUrl( ) ).getData().getParseMeta();
+    
+    for ( String key : new String[] { "description", "keywords" } )
+      {
+        String value = metaTags.getGeneralTags().getProperty( key, "" );
+
+        System.out.println( key + ": " + value );
+
+        parseMeta.set( key, value );
+      }
+
+    return parseResult;
+  }
+
+  public void setConf(Configuration conf) {
+    this.conf = conf;
+  }
+
+  public Configuration getConf() {
+    return this.conf;
+  }
+
+
+}
\ No newline at end of file


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

[Archive-access-cvs] SF.net SVN: archive-access:[3432] branches/wayback-1_6_1/

From: <bra...@us...> - 2011-04-15 01:16:34

Revision: 3432
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3432&view=rev
Author:   bradtofel
Date:     2011-04-15 01:16:28 +0000 (Fri, 15 Apr 2011)

Log Message:
-----------


Added Paths:
-----------
    branches/wayback-1_6_1/


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

[Archive-access-cvs] SF.net SVN: archive-access:[3431] branches/wayback-1_6_1/

From: <bra...@us...> - 2011-04-15 01:15:49

Revision: 3431
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3431&view=rev
Author:   bradtofel
Date:     2011-04-15 01:15:43 +0000 (Fri, 15 Apr 2011)

Log Message:
-----------


Removed Paths:
-------------
    branches/wayback-1_6_1/


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

[Archive-access-cvs] SF.net SVN: archive-access:[3430] branches/wayback-1_6_1/

From: <bra...@us...> - 2011-04-15 01:14:18

Revision: 3430
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3430&view=rev
Author:   bradtofel
Date:     2011-04-15 01:14:12 +0000 (Fri, 15 Apr 2011)

Log Message:
-----------
1.6.1...

Added Paths:
-----------
    branches/wayback-1_6_1/


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

[Archive-access-cvs] SF.net SVN: archive-access:[3429] trunk/archive-access/projects/wayback/ wayback-core/src/main/java/org/archive/wayback

From: <bra...@us...> - 2011-03-09 05:56:23

Revision: 3429
          http://archive-access.svn.sourceforge.net/archive-access/?rev=3429&view=rev
Author:   bradtofel
Date:     2011-03-09 05:56:17 +0000 (Wed, 09 Mar 2011)

Log Message:
-----------
FEATURE: Now detects a LiveWebTimeout, or LiveRobotsTimeout request, and aborts subsequent attempts, which are also likely to timeout within this request. More of a BugFix, since this caused dramatic problems, hanging up the thread to timeout on robots request for each search result.. 

Modified Paths:
--------------
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java
    trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/filterfactory/ExclusionCaptureFilterGroup.java

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java	2011-03-09 05:53:57 UTC (rev 3428)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java	2011-03-09 05:56:17 UTC (rev 3429)
@@ -35,6 +35,7 @@
 import org.archive.wayback.core.CaptureSearchResult;
 import org.archive.wayback.exception.LiveDocumentNotAvailableException;
 import org.archive.wayback.exception.LiveWebCacheUnavailableException;
+import org.archive.wayback.exception.LiveWebTimeoutException;
 import org.archive.wayback.liveweb.LiveWebCache;
 import org.archive.wayback.resourceindex.filters.ExclusionFilter;
 import org.archive.wayback.util.ObjectFilter;
@@ -188,7 +189,7 @@
 					rulesCache.put(firstUrlString,tmpRules);
 					rules = tmpRules;
 					LOGGER.info("ROBOT: Downloaded("+urlString+")");
-					
+
 				} catch (LiveDocumentNotAvailableException e) {
 					LOGGER.info("ROBOT: LiveDocumentNotAvailableException("+urlString+")");
 
@@ -201,7 +202,12 @@
 					return null;
 				} catch (LiveWebCacheUnavailableException e) {
 					LOGGER.info("ROBOT: LiveWebCacheUnavailableException("+urlString+")");
+					filterGroup.setLiveWebGone();
 					return null;
+				} catch (LiveWebTimeoutException e) {
+					LOGGER.info("ROBOT: LiveDocumentTimedOutException("+urlString+")");
+					filterGroup.setRobotTimedOut();
+					return null;
 				}
 			}
 		}
@@ -226,7 +232,11 @@
 		}
 		int filterResult = ObjectFilter.FILTER_EXCLUDE; 
 		RobotRules rules = getRules(r);
-		if(rules != null) {
+		if(rules == null) {
+			if(filterGroup.getRobotTimedOut() || filterGroup.getLiveWebGone()) {
+				return ObjectFilter.FILTER_ABORT;
+			}
+		} else {
 			String resultURL = r.getOriginalUrl();
 			URL url;
 			try {

Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/filterfactory/ExclusionCaptureFilterGroup.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/filterfactory/ExclusionCaptureFilterGroup.java	2011-03-09 05:53:57 UTC (rev 3428)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/resourceindex/filterfactory/ExclusionCaptureFilterGroup.java	2011-03-09 05:56:17 UTC (rev 3429)
@@ -26,8 +26,11 @@
 import org.archive.wayback.core.WaybackRequest;
 import org.archive.wayback.exception.AccessControlException;
 import org.archive.wayback.exception.AdministrativeAccessControlException;
+import org.archive.wayback.exception.LiveWebCacheUnavailableException;
 import org.archive.wayback.exception.ResourceNotInArchiveException;
 import org.archive.wayback.exception.RobotAccessControlException;
+import org.archive.wayback.exception.RobotNotAvailableException;
+import org.archive.wayback.exception.RobotTimedOutAccessControlException;
 import org.archive.wayback.resourceindex.filters.CounterFilter;
 import org.archive.wayback.resourceindex.filters.ExclusionFilter;
 import org.archive.wayback.util.ObjectFilter;
@@ -41,6 +44,8 @@
 	String requestUrl = null;
 	private boolean sawRobots = false;
 	private boolean passedRobots = false;
+	private boolean robotTimedOut = false;
+	private boolean liveWebGone = false;
 	private boolean sawAdministrative = false;
 	private boolean passedAdministrative = false;
 	
@@ -67,7 +72,16 @@
 	}
 
 	public void annotateResults(SearchResults results)
-			throws AccessControlException, ResourceNotInArchiveException {
+			throws AccessControlException, ResourceNotInArchiveException,
+			RobotNotAvailableException {
+		if(robotTimedOut) {
+			throw new RobotTimedOutAccessControlException("Unable to check" +
+					" robots.txt for " + requestUrl);
+		}
+		if(liveWebGone) {
+			throw new RobotNotAvailableException("The URL " + requestUrl +
+			" is blocked by the sites robots.txt file");
+		}
 		if(sawRobots && !passedRobots) {
 			throw new RobotAccessControlException("The URL " + requestUrl +
 					" is blocked by the sites robots.txt file");
@@ -91,4 +105,18 @@
 	public void setSawAdministrative() {
 		sawAdministrative = true;
 	}
+
+	public void setRobotTimedOut() {
+		robotTimedOut = true;
+	}
+	public boolean getRobotTimedOut() {
+		return robotTimedOut;
+	}
+
+	public void setLiveWebGone() {
+		liveWebGone = true;
+	}
+	public boolean getLiveWebGone() {
+		return liveWebGone;
+	}
 }


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

Flat | Threaded

<< < 1 .. 13 14 15 16 17 .. 171 > >> (Page 15 of 171)