some updates to dublin core, metadata browsing, file indexing and parser stability

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@6342 6c8d7289-2bf4-0310-a012-ef5d649a1542

htroot/ViewFile.html

@@ -19,7 +19,7 @@
       <fieldset><legend>View URL Content</legend>
         <dl>
           <dt>URL:</dt>        <dd><a href="#[url]#">#[url]#</a></dd>
-          <dt>Hash:</dt>       <dd>#[hash]#</dd>
+          <dt>Hash:</dt>       <dd><a href="/api/yacydoc.html?urlhash=#[hash]#">#[hash]#</a></dd>
           <dt>Word Count:</dt> <dd>#[wordCount]#</dd>
           <dt>Description:</dt><dd>#[desc]#</dd>
           <dt>Size:</dt>       <dd>#[size]# Bytes</dd>#(mimeTypeAvailable)#::

htroot/api/yacydoc.xml

@@ -7,18 +7,18 @@ you can validate it with http://www.stg.brown.edu/service/xmlvalid/
 -->
 
 <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:yacy="http://yacy.net/">
-  <dc:Title LANG="#[dc_language]#">#[dc_title]#</dc:Title>
-  <dc:Creator>#[dc_creator]#</dc:Creator>
-  <dc:Contributor>#[dc_contributor]#</dc:Contributor>
-  <dc:Subject SCHEME="item-list">#[dc_subject]#</dc:Subject>
-  <dc:Description LANG="#[dc_language]#">#[dc_description]#</dc:Description>
-  <dc:Publisher.URL>#[dc_publisher]#</dc:Publisher.URL>
-  <dc:Date>#[dc_date]#</dc:Date>
-  <dc:Type>yacy:doctype:#[dc_type]#</dc:Type>
-  <dc:Identifier SCHEME="yacy:urlhash">yacy:urlhash:#[dc_identifier]#</dc:Identifier>
-  <dc:Identifier SCHEME="URL">#[dc_publisher]#</dc:Identifier>
-  <dc:Format.Extent>#[yacy_size]#</dc:Format.Extent>
-  <dc:Language SCHEME="ISO639-2">#[dc_language]#</dc:Language>
+  <dc:title LANG="#[dc_language]#">#[dc_title]#</dc:title>
+  <dc:creator>#[dc_creator]#</dc:creator>
+  <dc:contributor>#[dc_contributor]#</dc:contributor>
+  <dc:subject SCHEME="item-list">#[dc_subject]#</dc:subject>
+  <dc:description LANG="#[dc_language]#">#[dc_description]#</dc:description>
+  <dc:publisher.URL>#[dc_publisher]#</dc:publisher.URL>
+  <dc:date>#[dc_date]#</dc:date>
+  <dc:type>yacy:doctype:#[dc_type]#</dc:type>
+  <dc:identifier SCHEME="yacy:urlhash">yacy:urlhash:#[dc_identifier]#</dc:identifier>
+  <dc:identifier SCHEME="URL">#[dc_publisher]#</dc:identifier>
+  <dc:format.extent>#[yacy_size]#</dc:format.extent>
+  <dc:language SCHEME="ISO639-2">#[dc_language]#</dc:language>
   <yacy:loaddate>#[yacy_loaddate]#</yacy:loaddate>
   <yacy:referrer.hash>yacy:urlhash:#[yacy_referrer_hash]#</yacy:referrer.hash>
   <yacy:referrer.url>#[yacy_referrer_url]#</yacy:referrer.url>

source/de/anomic/document/parser/pdfParser.java

@@ -50,6 +50,7 @@ import de.anomic.document.Document;
 import de.anomic.kelondro.util.FileUtils;
 import de.anomic.server.serverCharBuffer;
 import de.anomic.yacy.yacyURL;
+import de.anomic.yacy.logging.Log;
 
 public class pdfParser extends AbstractParser implements Idiom {
 
@@ -134,8 +135,11 @@ public class pdfParser extends AbstractParser implements Idiom {
             } else {
                 writer = new serverCharBuffer(); 
             }
-
-            stripper.writeText(theDocument, writer );
+            try {
+                stripper.writeText(theDocument, writer ); // may throw a NPE
+            } catch (Exception e) {
+                Log.logWarning("pdfParser", e.getMessage());
+            }
             theDocument.close(); theDocument = null;            
             writer.close();
 

source/de/anomic/document/parser/vsdParser.java

@@ -39,6 +39,8 @@ import de.anomic.yacy.yacyURL;
 import org.apache.poi.hdgf.extractor.VisioTextExtractor;
 import org.apache.poi.hpsf.SummaryInformation;
 
+import de.anomic.yacy.logging.Log;
+
 public class vsdParser extends AbstractParser implements Idiom {
 
     /**
@@ -91,7 +93,7 @@ public class vsdParser extends AbstractParser implements Idiom {
             	contents = extractor.getText();
                 summary = extractor.getSummaryInformation();
             } catch (Exception e) {
-            	e.printStackTrace();
+            	Log.logWarning("vsdParser", e.getMessage());
             }
 
             String author = null;

source/de/anomic/kelondro/text/DocumentIndex.java

@@ -124,7 +124,7 @@ public class DocumentIndex extends Segment {
      */
     public void addAll(File start) {
         assert (start != null);
-        assert (start.canRead());
+        assert (start.canRead()) : start.toString();
         if (!start.isDirectory()) {
             try {
                 this.queue.put(start);
@@ -192,7 +192,7 @@ public class DocumentIndex extends Segment {
      * @return a list of files that contain the word
      */
     public ArrayList<File> find(String querystring) {
-        return find(querystring, 0, 20);
+        return find(querystring, 0, 100);
     }
     
     /**

source/de/anomic/kelondro/text/Segment.java

@@ -188,8 +188,6 @@ public class Segment {
             wordCount++;
         }
         
-        
-        
         return wordCount;
     }
 

source/migration.java

@@ -78,6 +78,10 @@ public class migration {
         if(file.exists())
             delete(file);
     }
+    
+    /*
+     * copy skins from the release to DATA/SKINS.
+     */
     public static void installSkins(final Switchboard sb){
         final File skinsPath = sb.getConfigPath("skinPath", "DATA/SKINS");
         final File defaultSkinsPath = new File(sb.getRootPath(), "skins");
@@ -86,8 +90,10 @@ public class migration {
             mkdirs(skinsPath);
             for (String skinFile : skinFiles){
                 if (skinFile.endsWith(".css")){
-                    try{
-                        FileUtils.copy(new File(defaultSkinsPath, skinFile), new File(skinsPath, skinFile));
+                    File from = new File(defaultSkinsPath, skinFile);
+                    File to = new File(skinsPath, skinFile);
+                    if (from.lastModified() > to.lastModified()) try {
+                        FileUtils.copy(from, to);
                     } catch (final IOException e) {}
                 }
             }