diff --git a/htroot/IndexCreateWWWGlobalQueue_p.java b/htroot/IndexCreateWWWGlobalQueue_p.java index 88339d46d..4bc87517d 100644 --- a/htroot/IndexCreateWWWGlobalQueue_p.java +++ b/htroot/IndexCreateWWWGlobalQueue_p.java @@ -100,10 +100,10 @@ public class IndexCreateWWWGlobalQueue_p { yacySeed initiator; String profileHandle; plasmaCrawlProfile.entry profileEntry; - int i; + int i, showNum = 0; for (i = 0; i < crawlerList.length; i++) { urle = crawlerList[i]; - if (urle != null) { + if ((urle != null)&&(urle.url()!=null)) { initiator = yacyCore.seedDB.getConnected(urle.initiator()); profileHandle = urle.profileHandle(); profileEntry = (profileHandle == null) ? null : switchboard.profiles.getEntry(profileHandle); @@ -115,9 +115,10 @@ public class IndexCreateWWWGlobalQueue_p { prop.put("crawler-queue_list_"+i+"_anchor", wikiCode.replaceHTML(urle.name())); prop.put("crawler-queue_list_"+i+"_url", wikiCode.replaceHTML(urle.url().toString())); dark = !dark; + showNum++; } } - prop.put("crawler-queue_list", i); + prop.put("crawler-queue_list", showNum); } // return rewrite properties diff --git a/htroot/IndexCreate_p.java b/htroot/IndexCreate_p.java index a8143a686..7f5ed9bf4 100644 --- a/htroot/IndexCreate_p.java +++ b/htroot/IndexCreate_p.java @@ -61,7 +61,6 @@ import de.anomic.htmlFilter.htmlFilterContentScraper; import de.anomic.htmlFilter.htmlFilterOutputStream; import de.anomic.http.httpHeader; import de.anomic.plasma.plasmaCrawlProfile; -import de.anomic.plasma.plasmaParser; import de.anomic.plasma.plasmaSwitchboard; import de.anomic.plasma.plasmaURL; import de.anomic.server.serverFileUtils; diff --git a/source/de/anomic/plasma/plasmaCrawlLURL.java b/source/de/anomic/plasma/plasmaCrawlLURL.java index 87f577aea..22fe1331d 100644 --- a/source/de/anomic/plasma/plasmaCrawlLURL.java +++ b/source/de/anomic/plasma/plasmaCrawlLURL.java @@ -430,25 +430,25 @@ public final class plasmaCrawlLURL extends plasmaURL { // if the url cannot be found, this returns null this.urlHash = urlHash; try { - byte[][] entry = urlHashCache.get(urlHash.getBytes()); - if (entry != null) { - this.url = new URL(new String(entry[1]).trim()); - this.descr = (entry[2] == null) ? this.url.toString() : new String(entry[2]).trim(); - this.moddate = new Date(86400000 * serverCodings.enhancedCoder.decodeBase64Long(new String(entry[3]))); - this.loaddate = new Date(86400000 * serverCodings.enhancedCoder.decodeBase64Long(new String(entry[4]))); - this.referrerHash = (entry[5]==null)?dummyHash:new String(entry[5]); - this.copyCount = (int) serverCodings.enhancedCoder.decodeBase64Long(new String(entry[6])); - this.flags = new String(entry[7]); - this.quality = (int) serverCodings.enhancedCoder.decodeBase64Long(new String(entry[8])); - this.language = new String(entry[9]); - this.doctype = (char) entry[10][0]; - this.size = (long) serverCodings.enhancedCoder.decodeBase64Long(new String(entry[11])); - this.wordCount = (int) serverCodings.enhancedCoder.decodeBase64Long(new String(entry[12])); - this.snippet = null; - return; - } + byte[][] entry = plasmaCrawlLURL.this.urlHashCache.get(urlHash.getBytes()); + if (entry != null) { + this.url = new URL(new String(entry[1]).trim()); + this.descr = (entry[2] == null) ? this.url.toString() : new String(entry[2]).trim(); + this.moddate = new Date(86400000 * serverCodings.enhancedCoder.decodeBase64Long(new String(entry[3]))); + this.loaddate = new Date(86400000 * serverCodings.enhancedCoder.decodeBase64Long(new String(entry[4]))); + this.referrerHash = (entry[5]==null)?dummyHash:new String(entry[5]); + this.copyCount = (int) serverCodings.enhancedCoder.decodeBase64Long(new String(entry[6])); + this.flags = new String(entry[7]); + this.quality = (int) serverCodings.enhancedCoder.decodeBase64Long(new String(entry[8])); + this.language = new String(entry[9]); + this.doctype = (char) entry[10][0]; + this.size = serverCodings.enhancedCoder.decodeBase64Long(new String(entry[11])); + this.wordCount = (int) serverCodings.enhancedCoder.decodeBase64Long(new String(entry[12])); + this.snippet = null; + return; + } } catch (Exception e) { - serverLog.logSevere("PLASMA", "INTERNAL ERROR in plasmaLURL.entry/1: " + e.toString(), e); + serverLog.logSevere("PLASMA", "INTERNAL ERROR in plasmaLURL.entry/1: " + e.toString(), e); } }