diff --git a/htroot/IndexCreateIndexingQueue_p.java b/htroot/IndexCreateIndexingQueue_p.java index b3fd74b86..8c1bbb321 100644 --- a/htroot/IndexCreateIndexingQueue_p.java +++ b/htroot/IndexCreateIndexingQueue_p.java @@ -161,7 +161,7 @@ public class IndexCreateIndexingQueue_p { prop.put("indexing-queue_list_"+entryCount+"_dark", (inProcess)? 2: ((dark) ? 1 : 0)); prop.put("indexing-queue_list_"+entryCount+"_initiator", ((initiator == null) ? "proxy" : wikiCode.replaceHTML(initiator.getName()))); prop.put("indexing-queue_list_"+entryCount+"_depth", pcentry.depth()); - prop.put("indexing-queue_list_"+entryCount+"_modified", (pcentry.responseHeader() == null) ? "" : daydate(pcentry.responseHeader().lastModified())); + prop.put("indexing-queue_list_"+entryCount+"_modified", pcentry.getModificationDate()); prop.put("indexing-queue_list_"+entryCount+"_anchor", (pcentry.anchorName()==null)?"":wikiCode.replaceHTML(pcentry.anchorName())); prop.put("indexing-queue_list_"+entryCount+"_url", wikiCode.replaceHTML(pcentry.normalizedURLString())); prop.put("indexing-queue_list_"+entryCount+"_size", bytesToString(entrySize)); diff --git a/source/de/anomic/plasma/plasmaSwitchboard.java b/source/de/anomic/plasma/plasmaSwitchboard.java index 555b04e0a..fea42ed2d 100644 --- a/source/de/anomic/plasma/plasmaSwitchboard.java +++ b/source/de/anomic/plasma/plasmaSwitchboard.java @@ -1396,11 +1396,8 @@ public final class plasmaSwitchboard extends serverAbstractSwitch implements ser private plasmaParserDocument parseResource(plasmaSwitchboardQueue.Entry entry, String initiatorHash) throws InterruptedException { plasmaParserDocument document = null; - // the http header that belongs to this entry - httpHeader entryRespHeader = entry.responseHeader(); - // the mimetype of this entry - String mimeType = (entryRespHeader == null)?null:entryRespHeader.mime(); + String mimeType = entry.getMimeType(); // the parser logger serverLog parserLogger = parser.getLogger(); @@ -1465,7 +1462,7 @@ public final class plasmaSwitchboard extends serverAbstractSwitch implements ser ", maxDepth=" + ((entry.profile() == null) ? "null" : Integer.toString(entry.profile().generalDepth())) + ", filter=" + ((entry.profile() == null) ? "null" : entry.profile().generalFilter()) + ", initiatorHash=" + initiatorPeerHash + - ", responseHeader=" + ((entry.responseHeader() == null) ? "null" : entry.responseHeader().toString()) + + //", responseHeader=" + ((entry.responseHeader() == null) ? "null" : entry.responseHeader().toString()) + ", url=" + entry.url()); // DEBUG /* ========================================================================= @@ -1480,12 +1477,7 @@ public final class plasmaSwitchboard extends serverAbstractSwitch implements ser parsingEndTime = System.currentTimeMillis(); // getting the document date - Date docDate = null; - if (entry.responseHeader() != null) { - docDate = entry.responseHeader().lastModified(); - if (docDate == null) docDate = entry.responseHeader().date(); - } - if (docDate == null) docDate = new Date(); + Date docDate = entry.getModificationDate(); /* ========================================================================= * put anchors on crawl stack diff --git a/source/de/anomic/plasma/plasmaSwitchboardQueue.java b/source/de/anomic/plasma/plasmaSwitchboardQueue.java index de6552a08..eaa0e5c9c 100644 --- a/source/de/anomic/plasma/plasmaSwitchboardQueue.java +++ b/source/de/anomic/plasma/plasmaSwitchboardQueue.java @@ -306,7 +306,7 @@ public class plasmaSwitchboardQueue { return profileEntry; } - public httpHeader responseHeader() { + private httpHeader responseHeader() { if (responseHeader == null) try { responseHeader = htCache.getCachedResponse(indexURL.urlHash(url)); } catch (IOException e) { @@ -316,6 +316,24 @@ public class plasmaSwitchboardQueue { return responseHeader; } + public String getMimeType() { + httpHeader headers = this.responseHeader(); + return (headers == null) ? null : headers.mime(); + } + + public Date getModificationDate() { + Date docDate = null; + + httpHeader headers = this.responseHeader(); + if (headers != null) { + docDate = headers.lastModified(); + if (docDate == null) docDate = headers.date(); + } + if (docDate == null) docDate = new Date(); + + return docDate; + } + public URL referrerURL() { if (referrerURL == null) { if ((referrerHash == null) || (referrerHash.equals(indexURL.dummyHash))) return null;