Crawl from local file : faster task end when manually terminating crawl.

htroot/yacysearchitem.java

@@ -376,13 +376,13 @@ public class yacysearchitem {
 	 *         is null
 	 */
 	private static String processFaviconURL(final boolean authenticated, DigestURL faviconURL) {
-		final String iconUrlExt = MultiProtocolURL.getFileExtension(faviconURL.getFileName());
-	    /* Image format ouput for ViewFavicon servlet : default is png, except with gif and svg icons */
-	    final String viewFaviconExt = !iconUrlExt.isEmpty() && ImageViewer.isBrowserRendered(iconUrlExt) ? iconUrlExt : "png";
-		
 		/* Only use licence code for non authentified users. For authenticated users licence would never be released and would unnecessarily fill URLLicense.permissions. */
 		StringBuilder contentFaviconURL = new StringBuilder();
 		if (faviconURL != null) {
+			final String iconUrlExt = MultiProtocolURL.getFileExtension(faviconURL.getFileName());
+		    /* Image format ouput for ViewFavicon servlet : default is png, except with gif and svg icons */
+		    final String viewFaviconExt = !iconUrlExt.isEmpty() && ImageViewer.isBrowserRendered(iconUrlExt) ? iconUrlExt : "png";
+		    
 			contentFaviconURL.append("ViewFavicon.").append(viewFaviconExt).append("?maxwidth=16&maxheight=16&isStatic=true&quadratic");
 			if (authenticated) {
 				contentFaviconURL.append("&url=").append(faviconURL.toNormalform(true));

source/net/yacy/crawler/CrawlStacker.java

@@ -172,6 +172,7 @@ public final class CrawlStacker {
      * @param hyperlinks crawl starting points links to stack
      * @param replace Specify whether old indexed entries should be replaced
      * @param timezoneOffset local time-zone offset
+     * @throws IllegalCrawlProfileException when the crawl profile is not active
      */
     public void enqueueEntries(
             final byte[] initiator,
@@ -189,8 +190,9 @@ public final class CrawlStacker {
             } else {
             	error = "Rejected " + hyperlinks.size() + " crawl entries. Reason : LOST STACKER PROFILE HANDLE '" + profileHandle + "'";            	
             }
-            CrawlStacker.log.info(error); // this is NOT an error but a normal effect when terminating a crawl queue
+            CrawlStacker.log.info(error); // this is NOT an error but a normal behavior when terminating a crawl queue
-            return;
+            /* Throw an exception to signal caller it can stop stacking URLs using this crawl profile */
+            throw new IllegalCrawlProfileException("Profile " + profileHandle + " is no more active");
         }
         if (replace) {
             // delete old entries, if exists to force a re-load of the url (thats wanted here)

source/net/yacy/crawler/FileCrawlStarterTask.java

@@ -156,9 +156,17 @@ public class FileCrawlStarterTask extends Thread {
 			writer.close();
 		} catch (IOException e) {
 			log.severe("Error parsing the crawlingFile " + this.crawlingFile.getAbsolutePath(), e);
-		} catch (Throwable t) {
+		} catch (IllegalCrawlProfileException e) {
-			/* Other errors are likely to occur when the crawl is interrupted : still log this at warning level to avoid polluting regular error log level */
+			/* We should get here when the crawl is stopped manually before termination */
-			log.warn("Error parsing the crawlingFile " + this.crawlingFile.getAbsolutePath(), t);
+			log.info("Parsing crawlingFile " + this.crawlingFile.getAbsolutePath() + " terminated. Crawl profile "
+					+ this.profile.handle() + " is no more active.");
+		} catch (Exception e) {
+			/*
+			 * Other errors are likely to occur when the crawl is interrupted :
+			 * still log this at warning level to avoid polluting regular error
+			 * log level
+			 */
+			log.warn("Error parsing the crawlingFile " + this.crawlingFile.getAbsolutePath(), e);
 		} finally {
 			if (inStream != null) {
 				try {

source/net/yacy/crawler/IllegalCrawlProfileException.java

@@ -0,0 +1,50 @@
+// IllegalCrawlProfileException.java
+// Copyright 2016 by luccioman; https://github.com/luccioman
+//
+// This is a part of YaCy, a peer-to-peer based web search engine
+//
+// LICENSE
+//
+// This program is free software; you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation; either version 2 of the License, or
+// (at your option) any later version.
+//
+// This program 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 General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with this program; if not, write to the Free Software
+// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+package net.yacy.crawler;
+
+import net.yacy.crawler.data.CrawlProfile;
+
+/**
+ * Exception used to signal that an operation is trying to use an inactive or deleted {@link CrawlProfile}.
+ * @author luccioman
+ *
+ */
+public class IllegalCrawlProfileException extends RuntimeException {
+
+	/** Generated serial ID */
+	private static final long serialVersionUID = 8482302347823257958L;
+	
+	/**
+	 * Default constructor : use a generic message
+	 */
+	public IllegalCrawlProfileException() {
+		super("Crawl profile can not be used");
+	}
+
+	/**
+	 * @param message detail message
+	 */
+	public IllegalCrawlProfileException(String message) {
+		super(message);
+	}
+
+}