From 27fa6a66ad194d68b6a5ad8cac86d5ba29e9cbaa Mon Sep 17 00:00:00 2001
From: orbiter <orbiter@6c8d7289-2bf4-0310-a012-ef5d649a1542>
Date: Mon, 8 Jun 2009 23:30:12 +0000
Subject: [PATCH] - completed the author navigation - removed some unused
 variables

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@6037 6c8d7289-2bf4-0310-a012-ef5d649a1542
---
 htroot/yacy/search.java                       |  5 ++-
 htroot/yacysearch.java                        | 23 ++++++++++++
 htroot/yacysearchtrailer.html                 | 14 ++++---
 htroot/yacysearchtrailer.java                 |  6 ++-
 htroot/yacysearchtrailer.json                 | 15 +++++++-
 source/de/anomic/data/blogBoard.java          |  2 +-
 source/de/anomic/data/blogBoardComments.java  |  2 +-
 source/de/anomic/data/bookmarksDB.java        |  6 +--
 source/de/anomic/data/messageBoard.java       |  2 +-
 source/de/anomic/data/userDB.java             |  2 +-
 source/de/anomic/data/wiki/wikiBoard.java     |  4 +-
 source/de/anomic/kelondro/blob/BLOBTree.java  | 19 +++-------
 .../anomic/plasma/plasmaRankingCRProcess.java |  2 +-
 .../de/anomic/plasma/plasmaSearchQuery.java   |  5 +++
 .../plasma/plasmaSearchRankingProcess.java    | 37 +++++++++++--------
 15 files changed, 95 insertions(+), 49 deletions(-)

diff --git a/htroot/yacy/search.java b/htroot/yacy/search.java
index c8d9b72b3..a755ca8d8 100644
--- a/htroot/yacy/search.java
+++ b/htroot/yacy/search.java
@@ -90,6 +90,7 @@ public final class search {
         final String  contentdom = post.get("contentdom", "text");
         final String  filter = post.get("filter", ".*");
         String  sitehash = post.get("sitehash", ""); if (sitehash.length() == 0) sitehash = null;
+        String  authorhash = post.get("authorhash", ""); if (authorhash.length() == 0) authorhash = null;
         String  language = post.get("language", "");
         if (!iso639.exists(language)) {
             // take language from the user agent
@@ -204,6 +205,7 @@ public final class search {
                     null,
                     false,
                     sitehash, 
+                    authorhash,
                     yacyURL.TLD_any_zone_filter,
                     client,
                     false);
@@ -255,7 +257,8 @@ public final class search {
                     -1, 
                     constraint, 
                     false,
-                    sitehash, 
+                    sitehash,
+                    authorhash,
                     yacyURL.TLD_any_zone_filter,
                     client, 
                     false);
diff --git a/htroot/yacysearch.java b/htroot/yacysearch.java
index c048b983b..b1d7aa6fe 100644
--- a/htroot/yacysearch.java
+++ b/htroot/yacysearch.java
@@ -282,6 +282,28 @@ public class yacysearch {
                 while(domain.endsWith(".")) domain = domain.substring(0, domain.length() - 1);
                 sitehash = yacyURL.domhash(domain);
             }
+            int authori = querystring.indexOf("author:");
+        	String authorhash = null;
+            if (authori >= 0) {
+            	// check if the author was given with single quotes or without
+            	boolean quotes = false;
+            	if (querystring.charAt(authori + 7) == (char) 39) {
+            		quotes = true;
+            	}
+            	String author;
+            	if (quotes) {
+            		int ftb = querystring.indexOf((char) 39, authori + 8);
+                    if (ftb == -1) ftb = querystring.length() + 1;
+                    author = querystring.substring(authori + 8, ftb);
+                    querystring = querystring.replace("author:'" + author + "'", "");
+            	} else {
+            		int ftb = querystring.indexOf(' ', authori);
+            		if (ftb == -1) ftb = querystring.length();
+            		author = querystring.substring(authori + 7, ftb);
+                    querystring = querystring.replace("author:" + author, "");
+            	}
+            	authorhash = new String(Word.word2hash(author));
+            }
             int tld = querystring.indexOf("tld:");
             if (tld >= 0) {
                 int ftb = querystring.indexOf(' ', tld);
@@ -401,6 +423,7 @@ public class yacysearch {
                     constraint,
                     true,
                     sitehash,
+                    authorhash,
                     yacyURL.TLD_any_zone_filter,
                     client,
                     authenticated);
diff --git a/htroot/yacysearchtrailer.html b/htroot/yacysearchtrailer.html
index 62d3d190f..c6f458d1b 100644
--- a/htroot/yacysearchtrailer.html
+++ b/htroot/yacysearchtrailer.html
@@ -4,12 +4,7 @@
 <li>#[url]#</li>
 #{/element}#</ul></div>
 #(/nav-domains)#
-#(nav-topics)#::
-<h3 style="padding-left:25px;">Topics</h3>
-<div><ul style="padding-left: 0px;">#{element}#
-<li>#[url]#</li>
-#{/element}#</ul></div>
-#(/nav-topics)#
+
 #(nav-authors)#::
 <h3 style="padding-left:25px;">Authors</h3>
 <div><ul style="padding-left: 0px;">#{element}#
@@ -17,6 +12,13 @@
 #{/element}#</ul></div>
 #(/nav-authors)#
 
+#(nav-topics)#::
+<h3 style="padding-left:25px;">Topics</h3>
+<div><ul style="padding-left: 0px;">#{element}#
+<li>#[url]#</li>
+#{/element}#</ul></div>
+#(/nav-topics)#
+
 <h3 style="padding-left:25px;">Timeline</h3>
 <div>
 <p>
diff --git a/htroot/yacysearchtrailer.java b/htroot/yacysearchtrailer.java
index 0fc758602..d13cb07a8 100644
--- a/htroot/yacysearchtrailer.java
+++ b/htroot/yacysearchtrailer.java
@@ -115,11 +115,13 @@ public class yacysearchtrailer {
             prop.put("nav-authors", 1);
             NavigatorEntry entry;
             int i;
+            String anav;
             for (i = 0; i < authorNavigator.size(); i++) {
                 entry = authorNavigator.get(i);
+                anav = (entry.name.indexOf(' ') < 0) ? "author:" + entry.name : "author:'" + entry.name + "'";
                 prop.put("nav-authors_element_" + i + "_name", entry.name);
-                prop.put("nav-authors_element_" + i + "_url", "<a href=\"" + plasmaSearchQuery.navurl("html", 0, display, theQuery, theQuery.urlMask, "author:'" + entry.name + "'", theQuery.navigators) + "\">" + entry.name + " (" + entry.count + ")</a>");
-                prop.putJSON("nav-authors_element_" + i + "_url-json", plasmaSearchQuery.navurl("json", 0, display, theQuery, theQuery.urlMask, "author:'" + entry.name + "'", theQuery.navigators));
+                prop.put("nav-authors_element_" + i + "_url", "<a href=\"" + plasmaSearchQuery.navurl("html", 0, display, theQuery, theQuery.urlMask, anav, theQuery.navigators) + "\">" + entry.name + " (" + entry.count + ")</a>");
+                prop.putJSON("nav-authors_element_" + i + "_url-json", plasmaSearchQuery.navurl("json", 0, display, theQuery, theQuery.urlMask, anav, theQuery.navigators));
                 prop.put("nav-authors_element_" + i + "_count", entry.count);
                 prop.put("nav-authors_element_" + i + "_modifier", "author:'" + entry.name + "'");
                 prop.put("nav-authors_element_" + i + "_nl", 1);
diff --git a/htroot/yacysearchtrailer.json b/htroot/yacysearchtrailer.json
index a621522ad..3a394b505 100644
--- a/htroot/yacysearchtrailer.json
+++ b/htroot/yacysearchtrailer.json
@@ -11,7 +11,20 @@
         {"name": "#[name]#", "count": "#[count]#", "modifier": "#[modifier]#", "url": "#[url-json]#"}#(nl)#::,#(/nl)#
 #{/element}#
       ]
-    },#(/nav-domains)##(nav-topics)#::
+    },#(/nav-domains)##(nav-authors)#::
+    {
+      "facetname": "authors",
+      "displayname": "Authors",
+      "type": "String",
+      "min": "0",
+      "max": "0",
+      "mean": "0",
+      "elements": [
+#{element}#
+        {"name": "#[name]#", "count": "#[count]#", "modifier": "#[modifier]#", "url": "#[url-json]#"}#(nl)#::,#(/nl)#
+#{/element}#
+      ]
+    }#(/nav-authors)##(nav-topics)#::
     {
       "facetname": "topwords",
       "displayname": "Topics",
diff --git a/source/de/anomic/data/blogBoard.java b/source/de/anomic/data/blogBoard.java
index c36d08e96..46095a265 100644
--- a/source/de/anomic/data/blogBoard.java
+++ b/source/de/anomic/data/blogBoard.java
@@ -67,7 +67,7 @@ public class blogBoard {
         new File(actpath.getParent()).mkdir();
         new File(newFile.getParent()).mkdir();
         if (database == null) {
-            database = new MapView(BLOBTree.toHeap(actpath, true, true, keyLength, recordSize, '_', NaturalOrder.naturalOrder, false, false, newFile), 500, '_');
+            database = new MapView(BLOBTree.toHeap(actpath, true, true, keyLength, recordSize, '_', NaturalOrder.naturalOrder, newFile), 500, '_');
         }
     }
     
diff --git a/source/de/anomic/data/blogBoardComments.java b/source/de/anomic/data/blogBoardComments.java
index 69f070c42..911d400d8 100644
--- a/source/de/anomic/data/blogBoardComments.java
+++ b/source/de/anomic/data/blogBoardComments.java
@@ -70,7 +70,7 @@ public class blogBoardComments {
         new File(actpath.getParent()).mkdir();
         new File(newFile.getParent()).mkdir();
         if (database == null) {
-            database = new MapView(BLOBTree.toHeap(actpath, true, true, keyLength, recordSize, '_', NaturalOrder.naturalOrder, false, false, newFile), 500, '_');
+            database = new MapView(BLOBTree.toHeap(actpath, true, true, keyLength, recordSize, '_', NaturalOrder.naturalOrder, newFile), 500, '_');
         }
     }
     
diff --git a/source/de/anomic/data/bookmarksDB.java b/source/de/anomic/data/bookmarksDB.java
index 9d373f486..b7fbf0932 100644
--- a/source/de/anomic/data/bookmarksDB.java
+++ b/source/de/anomic/data/bookmarksDB.java
@@ -116,17 +116,17 @@ public class bookmarksDB {
         tagCache=new TreeMap<String, Tag>();
         bookmarksFile.getParentFile().mkdirs();
         //this.bookmarksTable = new kelondroMap(kelondroDyn.open(bookmarksFile, bufferkb * 1024, preloadTime, 12, 256, '_', true, false));
-        this.bookmarksTable = new MapView(BLOBTree.toHeap(bookmarksFile, true, true, 12, 256, '_', NaturalOrder.naturalOrder, false, false, bookmarksFileNew), 1000, '_');
+        this.bookmarksTable = new MapView(BLOBTree.toHeap(bookmarksFile, true, true, 12, 256, '_', NaturalOrder.naturalOrder, bookmarksFileNew), 1000, '_');
 
         // tags
         tagsFile.getParentFile().mkdirs();
         final boolean tagsFileExisted = tagsFile.exists();
-        this.tagsTable = new MapView(BLOBTree.toHeap(tagsFile, true, true, 12, 256, '_', NaturalOrder.naturalOrder, false, false, tagsFileNew), 500, '_');
+        this.tagsTable = new MapView(BLOBTree.toHeap(tagsFile, true, true, 12, 256, '_', NaturalOrder.naturalOrder, tagsFileNew), 500, '_');
         if (!tagsFileExisted) rebuildTags();
 
         // dates
         final boolean datesExisted = datesFile.exists();
-        this.datesTable = new MapView(BLOBTree.toHeap(datesFile, true, true, 20, 256, '_', NaturalOrder.naturalOrder, false, false, datesFileNew), 500, '_');
+        this.datesTable = new MapView(BLOBTree.toHeap(datesFile, true, true, 20, 256, '_', NaturalOrder.naturalOrder, datesFileNew), 500, '_');
         if (!datesExisted) rebuildDates();
 
         // autoReCrawl
diff --git a/source/de/anomic/data/messageBoard.java b/source/de/anomic/data/messageBoard.java
index 7f4b86f91..a7645f614 100644
--- a/source/de/anomic/data/messageBoard.java
+++ b/source/de/anomic/data/messageBoard.java
@@ -55,7 +55,7 @@ public class messageBoard {
         new File(path.getParent()).mkdir();
         new File(pathNew.getParent()).mkdir();
         if (database == null) {
-            database = new MapView(BLOBTree.toHeap(path, true, true, categoryLength + dateFormat.length() + 2, recordSize, '_', NaturalOrder.naturalOrder, false, false, pathNew), 500, '_');
+            database = new MapView(BLOBTree.toHeap(path, true, true, categoryLength + dateFormat.length() + 2, recordSize, '_', NaturalOrder.naturalOrder, pathNew), 500, '_');
         }
         sn = 0;
     }
diff --git a/source/de/anomic/data/userDB.java b/source/de/anomic/data/userDB.java
index ba48bdf9a..0091c4fb3 100644
--- a/source/de/anomic/data/userDB.java
+++ b/source/de/anomic/data/userDB.java
@@ -60,7 +60,7 @@ public final class userDB {
         this.userTableFile = userTableFileNew;
         userTableFile.getParentFile().mkdirs();
         userTableFileNew.getParentFile().mkdirs();
-        this.userTable = new MapView(BLOBTree.toHeap(userTableFile, true, true, 128, 256, '_', NaturalOrder.naturalOrder, false, false, userTableFile), 10, '_');
+        this.userTable = new MapView(BLOBTree.toHeap(userTableFile, true, true, 128, 256, '_', NaturalOrder.naturalOrder, userTableFile), 10, '_');
     }
     
     void resetDatabase() {
diff --git a/source/de/anomic/data/wiki/wikiBoard.java b/source/de/anomic/data/wiki/wikiBoard.java
index f472339e5..13bd3cd1c 100644
--- a/source/de/anomic/data/wiki/wikiBoard.java
+++ b/source/de/anomic/data/wiki/wikiBoard.java
@@ -57,11 +57,11 @@ public class wikiBoard {
             final File bkppath, final File bkppathNew) throws IOException {
         new File(actpath.getParent()).mkdirs();
         if (datbase == null) {
-            datbase = new MapView(BLOBTree.toHeap(actpath, true, true, keyLength, recordSize, '_', NaturalOrder.naturalOrder, false, false, actpathNew), 500, '_');
+            datbase = new MapView(BLOBTree.toHeap(actpath, true, true, keyLength, recordSize, '_', NaturalOrder.naturalOrder, actpathNew), 500, '_');
         }
         new File(bkppath.getParent()).mkdirs();
         if (bkpbase == null) {
-            bkpbase = new MapView(BLOBTree.toHeap(bkppath, true, true, keyLength + dateFormat.length(), recordSize, '_', NaturalOrder.naturalOrder, false, false, bkppathNew), 500, '_');
+            bkpbase = new MapView(BLOBTree.toHeap(bkppath, true, true, keyLength + dateFormat.length(), recordSize, '_', NaturalOrder.naturalOrder, bkppathNew), 500, '_');
         }
     }
 
diff --git a/source/de/anomic/kelondro/blob/BLOBTree.java b/source/de/anomic/kelondro/blob/BLOBTree.java
index 2e38d1741..178432473 100644
--- a/source/de/anomic/kelondro/blob/BLOBTree.java
+++ b/source/de/anomic/kelondro/blob/BLOBTree.java
@@ -70,7 +70,7 @@ public class BLOBTree {
      * Deprecated Class. Please use kelondroBLOBHeap instead
      */
     private BLOBTree(final File file, final boolean useNodeCache, final boolean useObjectCache, final int key,
-            final int nodesize, final char fillChar, final ByteOrder objectOrder, final boolean writebuffer, final boolean resetOnFail) {
+            final int nodesize, final char fillChar, final ByteOrder objectOrder) {
         // creates or opens a dynamic tree
         rowdef = new Row("byte[] key-" + (key + counterlen) + ", byte[] node-" + nodesize, objectOrder);
         ObjectIndex fbi;
@@ -78,17 +78,8 @@ public class BLOBTree {
 			fbi = new Tree(file, useNodeCache, 0, rowdef, 1, 8);
 		} catch (final IOException e) {
 			e.printStackTrace();
-			if (resetOnFail) {
-			    FileUtils.deletedelete(file);
-				try {
-					fbi = new Tree(file, useNodeCache, -1, rowdef, 1, 8);
-				} catch (final IOException e1) {
-					e1.printStackTrace();
-					throw new kelondroException(e.getMessage());
-				}
-			} else {
-				throw new kelondroException(e.getMessage());
-			}
+			FileUtils.deletedelete(file);
+			throw new kelondroException(e.getMessage());
 		}
         this.index = ((useObjectCache) && (!(fbi instanceof EcoTable))) ? (ObjectIndex) new Cache(fbi) : fbi;
         this.keylen = key;
@@ -100,13 +91,13 @@ public class BLOBTree {
     }
     
     public static BLOBHeap toHeap(final File file, final boolean useNodeCache, final boolean useObjectCache, final int key,
-            final int nodesize, final char fillChar, final ByteOrder objectOrder, final boolean writebuffer, final boolean resetOnFail, final File blob) throws IOException {
+            final int nodesize, final char fillChar, final ByteOrder objectOrder, final File blob) throws IOException {
         if (blob.exists() || !file.exists()) {
             // open the blob file and ignore the tree
             return new BLOBHeap(blob, key, objectOrder, 1024 * 64);
         }
         // open a Tree and migrate everything to a Heap
-        BLOBTree tree = new BLOBTree(file, useNodeCache, useObjectCache, key, nodesize, fillChar, objectOrder, writebuffer, resetOnFail);
+        BLOBTree tree = new BLOBTree(file, useNodeCache, useObjectCache, key, nodesize, fillChar, objectOrder);
         BLOBHeap heap = new BLOBHeap(blob, key, objectOrder, 1024 * 64);
         Iterator<byte[]> i = tree.keys(true, false);
         byte[] k, kk = new byte[key], v;
diff --git a/source/de/anomic/plasma/plasmaRankingCRProcess.java b/source/de/anomic/plasma/plasmaRankingCRProcess.java
index 1de71aeae..e5b6aaf00 100644
--- a/source/de/anomic/plasma/plasmaRankingCRProcess.java
+++ b/source/de/anomic/plasma/plasmaRankingCRProcess.java
@@ -144,7 +144,7 @@ public class plasmaRankingCRProcess {
         return true;
     }
     
-    private static boolean accumulate_upd(final File f, final ObjectIndex acc, final IndexCell<CitationReferenceRow> seq) throws IOException {
+    public static boolean accumulate_upd(final File f, final ObjectIndex acc, final IndexCell<CitationReferenceRow> seq) throws IOException {
         // open file
         AttrSeq source_cr = null;
         try {
diff --git a/source/de/anomic/plasma/plasmaSearchQuery.java b/source/de/anomic/plasma/plasmaSearchQuery.java
index 3c74186f6..e61292f16 100644
--- a/source/de/anomic/plasma/plasmaSearchQuery.java
+++ b/source/de/anomic/plasma/plasmaSearchQuery.java
@@ -74,6 +74,7 @@ public final class plasmaSearchQuery {
     public plasmaSearchRankingProfile ranking;
     public String host; // this is the client host that starts the query, not a site operator
     public String sitehash; // this is a domain hash, 6 bytes long or null
+    public String authorhash;
     public yacySeed remotepeer;
     public Long handle;
     // values that are set after a search:
@@ -113,6 +114,7 @@ public final class plasmaSearchQuery {
         this.onlineSnippetFetch = false;
         this.host = null;
         this.sitehash = null;
+        this.authorhash = null;
         this.remotepeer = null;
         this.handle = Long.valueOf(System.currentTimeMillis());
         this.specialRights = false;
@@ -132,6 +134,7 @@ public final class plasmaSearchQuery {
         final int domType, final String domGroupName, final int domMaxTargets,
         final Bitfield constraint, final boolean allofconstraint,
         final String site,
+        final String authorhash,
         final int domainzone,
         final String host,
         final boolean specialRights) {
@@ -155,6 +158,7 @@ public final class plasmaSearchQuery {
 		this.constraint = constraint;
 		this.allofconstraint = allofconstraint;
 		this.sitehash = site; assert site == null || site.length() == 6;
+		this.authorhash = authorhash; assert authorhash == null || authorhash.length() > 0;
 		this.onlineSnippetFetch = onlineSnippetFetch;
 		this.host = host;
         this.remotepeer = null;
@@ -325,6 +329,7 @@ public final class plasmaSearchQuery {
             "*" + this.prefer +
             "*" + this.urlMask +
             "*" + this.sitehash +
+            "*" + this.authorhash +
             "*" + this.targetlang +
             "*" + this.constraint +
             "*" + this.maxDistance;
diff --git a/source/de/anomic/plasma/plasmaSearchRankingProcess.java b/source/de/anomic/plasma/plasmaSearchRankingProcess.java
index 7da3d6540..612bce706 100644
--- a/source/de/anomic/plasma/plasmaSearchRankingProcess.java
+++ b/source/de/anomic/plasma/plasmaSearchRankingProcess.java
@@ -35,13 +35,11 @@ import java.util.HashMap;
 import java.util.Iterator;
 import java.util.Map;
 import java.util.Set;
-import java.util.TreeMap;
 import java.util.TreeSet;
 import java.util.concurrent.ConcurrentHashMap;
 
 import de.anomic.htmlFilter.htmlFilterContentScraper;
 import de.anomic.kelondro.index.BinSearch;
-import de.anomic.kelondro.order.Base64Order;
 import de.anomic.kelondro.order.Digest;
 import de.anomic.kelondro.text.Reference;
 import de.anomic.kelondro.text.ReferenceContainer;
@@ -78,9 +76,9 @@ public final class plasmaSearchRankingProcess {
     private final Segment indexSegment;
     private HashMap<byte[], ReferenceContainer<WordReference>> localSearchInclusion;
     private final int[] domZones;
-    private final ConcurrentHashMap<String, HostInfo> hostNavigator;
     private final ConcurrentHashMap<String, Integer> ref;  // reference score computation for the commonSense heuristic
-    private final TreeMap<byte[], AuthorInfo> authorNavigator;
+    private final ConcurrentHashMap<String, HostInfo> hostNavigator;
+    private final ConcurrentHashMap<String, AuthorInfo> authorNavigator;
     
     public plasmaSearchRankingProcess(
             final Segment indexSegment,
@@ -107,7 +105,7 @@ public final class plasmaSearchRankingProcess {
         this.flagcount = new int[32];
         for (int i = 0; i < 32; i++) {this.flagcount[i] = 0;}
         this.hostNavigator = new ConcurrentHashMap<String, HostInfo>();
-        this.authorNavigator = new TreeMap<byte[], AuthorInfo>(Base64Order.enhancedCoder);
+        this.authorNavigator = new ConcurrentHashMap<String, AuthorInfo>();
         this.ref = new ConcurrentHashMap<String, Integer>();
         this.domZones = new int[8];
         for (int i = 0; i < 8; i++) {this.domZones[i] = 0;}
@@ -330,16 +328,25 @@ public final class plasmaSearchRankingProcess {
                     // author navigation:
                     String author = metadata.dc_creator();
                     if (author != null && author.length() > 0) {
-                        byte[] authorhash = Word.word2hash(author);
-                        //synchronized (this.authorNavigator) {
-                            AuthorInfo in = this.authorNavigator.get(authorhash);
-                            if (in == null) {
-                                this.authorNavigator.put(authorhash, new AuthorInfo(author));
-                            } else {
-                                in.inc();
-                                this.authorNavigator.put(authorhash, in);
-                            }
-                        //}
+                    	// add author to the author navigator
+                        String authorhash = new String(Word.word2hash(author));
+                        System.out.println("*** DEBUG authorhash = " + authorhash + ", query.authorhash = " + this.query.authorhash + ", author = " + author);
+                        
+                        // check if we already are filtering for authors
+                    	if (this.query.authorhash != null && !this.query.authorhash.equals(authorhash)) {
+                    		continue;
+                    	}
+                    	
+                    	// add author to the author navigator
+                        AuthorInfo in = this.authorNavigator.get(authorhash);
+                        if (in == null) {
+                            this.authorNavigator.put(authorhash, new AuthorInfo(author));
+                        } else {
+                            in.inc();
+                            this.authorNavigator.put(authorhash, in);
+                        }
+                    } else if (this.query.authorhash != null) {
+                    	continue;
                     }
                     
                     // get the url