Changeset 12980

Timestamp:

2006-10-03T15:35:04+13:00 (18 years ago)

Author:

mdewsnip

Message:

Now passes the endresults value (if defined) into the Searcher.search() call so only the required number of documents are returned.

Location:

trunk

Files:

• gsdl/bin/java/LuceneWrap.jar (modified) ( previous)
• gsdl/src/java/org/nzdl/gsdl/LuceneWrap/GS2LuceneQuery.java (modified) (4 diffs)
• indexers/lucene-gs/src/org/greenstone/LuceneWrapper/GS2LuceneQuery.java (modified) (4 diffs)

trunk/gsdl/src/java/org/nzdl/gsdl/LuceneWrap/GS2LuceneQuery.java

@@ -31 +31 @@
 import org.apache.lucene.search.RangeFilter;
 import org.apache.lucene.search.Searcher;
+import org.apache.lucene.search.ScoreDoc;
 import org.apache.lucene.search.Sort;
+import org.apache.lucene.search.TopFieldDocs;
 
 
@@ -57 +59 @@
         QueryParser query_parser_no_stop_words = new QueryParser(TEXTFIELD, new StandardAnalyzer(new String[] { }));
 
-        Sort sorter = null;
+        Sort sorter = new Sort();
         Filter filter = null;
         String fuzziness = null;
@@ -63 +65 @@
         // Paging
         int start_results = 1;
-        int end_results = -1;
+        int end_results = Integer.MAX_VALUE;
 
             // New code to allow the default conjunction operator to be
@@ -157 +159 @@
             }
 
-            // Perform the query (filter and sorter may be null)
-            Hits hits = searcher.search(query, filter, sorter);
-
-            // Do we need to use a hit iterator to get sorted results?
-            System.out.println("  <MatchingDocsInfo num=\"" + hits.length() + "\"/>");
-            System.out.println("  <StartResults num=\"" + start_results + "\" />");
-            System.out.println("  <EndsResults num=\"" + end_results + "\" />");
-
-            int counter = 1;
-            Iterator hit_iter = hits.iterator();
-            while (hit_iter.hasNext()) {
-            Hit hit = (Hit) hit_iter.next();
-            Document doc = hit.getDocument();
-            
-            // May not be paging results
-            if (start_results == 1 && end_results == -1) {
-                String node_id = doc.get("nodeID");
-                System.out.println("  <Match id=\"" + node_id + "\" />");
+            // Simple case for getting all the matching documents
+            if (end_results == Integer.MAX_VALUE) {
+            // Perform the query (filter and sorter may be null)
+            Hits hits = searcher.search(query, filter, sorter);
+            System.out.println("  <MatchingDocsInfo num=\"" + hits.length() + "\"/>");
+
+            // Output the matching documents
+            System.out.println("  <StartResults num=\"" + start_results + "\" />");
+            System.out.println("  <EndsResults num=\"" + hits.length() + "\" />");
+            for (int i = start_results; i <= hits.length(); i++) {
+                Document doc = hits.doc(i - 1);
+                System.out.println("  <Match id=\"" + doc.get("nodeID") + "\" />");
             }
-            // Otherwise skip up until page offset
-            else if (start_results <= counter && counter <= end_results) {
-                String node_id = doc.get("nodeID");
-                System.out.println("  <Match id=\"" + node_id + "\" />");
+            }
+
+            // Slightly more complicated case for returning a subset of the matching documents
+            else {
+            // Perform the query (filter may be null)
+            TopFieldDocs hits = searcher.search(query, filter, end_results, sorter);
+            System.out.println("  <MatchingDocsInfo num=\"" + hits.totalHits + "\"/>");
+
+            // Output the matching documents
+            System.out.println("  <StartResults num=\"" + start_results + "\" />");
+            System.out.println("  <EndsResults num=\"" + end_results + "\" />");
+            for (int i = start_results; (i <= hits.scoreDocs.length && i <= end_results); i++) {
+                Document doc = reader.document(hits.scoreDocs[i - 1].doc);
+                System.out.println("  <Match id=\"" + doc.get("nodeID") + "\" />");
             }
-            // And skip all the rest
-
-            ++counter;
             }
         }

trunk/indexers/lucene-gs/src/org/greenstone/LuceneWrapper/GS2LuceneQuery.java

@@ -31 +31 @@
 import org.apache.lucene.search.RangeFilter;
 import org.apache.lucene.search.Searcher;
+import org.apache.lucene.search.ScoreDoc;
 import org.apache.lucene.search.Sort;
+import org.apache.lucene.search.TopFieldDocs;
 
 
@@ -57 +59 @@
         QueryParser query_parser_no_stop_words = new QueryParser(TEXTFIELD, new StandardAnalyzer(new String[] { }));
 
-        Sort sorter = null;
+        Sort sorter = new Sort();
         Filter filter = null;
         String fuzziness = null;
@@ -63 +65 @@
         // Paging
         int start_results = 1;
-        int end_results = -1;
+        int end_results = Integer.MAX_VALUE;
 
             // New code to allow the default conjunction operator to be
@@ -157 +159 @@
             }
 
-            // Perform the query (filter and sorter may be null)
-            Hits hits = searcher.search(query, filter, sorter);
-
-            // Do we need to use a hit iterator to get sorted results?
-            System.out.println("  <MatchingDocsInfo num=\"" + hits.length() + "\"/>");
-            System.out.println("  <StartResults num=\"" + start_results + "\" />");
-            System.out.println("  <EndsResults num=\"" + end_results + "\" />");
-
-            int counter = 1;
-            Iterator hit_iter = hits.iterator();
-            while (hit_iter.hasNext()) {
-            Hit hit = (Hit) hit_iter.next();
-            Document doc = hit.getDocument();
-            
-            // May not be paging results
-            if (start_results == 1 && end_results == -1) {
-                String node_id = doc.get("nodeID");
-                System.out.println("  <Match id=\"" + node_id + "\" />");
+            // Simple case for getting all the matching documents
+            if (end_results == Integer.MAX_VALUE) {
+            // Perform the query (filter and sorter may be null)
+            Hits hits = searcher.search(query, filter, sorter);
+            System.out.println("  <MatchingDocsInfo num=\"" + hits.length() + "\"/>");
+
+            // Output the matching documents
+            System.out.println("  <StartResults num=\"" + start_results + "\" />");
+            System.out.println("  <EndsResults num=\"" + hits.length() + "\" />");
+            for (int i = start_results; i <= hits.length(); i++) {
+                Document doc = hits.doc(i - 1);
+                System.out.println("  <Match id=\"" + doc.get("nodeID") + "\" />");
             }
-            // Otherwise skip up until page offset
-            else if (start_results <= counter && counter <= end_results) {
-                String node_id = doc.get("nodeID");
-                System.out.println("  <Match id=\"" + node_id + "\" />");
+            }
+
+            // Slightly more complicated case for returning a subset of the matching documents
+            else {
+            // Perform the query (filter may be null)
+            TopFieldDocs hits = searcher.search(query, filter, end_results, sorter);
+            System.out.println("  <MatchingDocsInfo num=\"" + hits.totalHits + "\"/>");
+
+            // Output the matching documents
+            System.out.println("  <StartResults num=\"" + start_results + "\" />");
+            System.out.println("  <EndsResults num=\"" + end_results + "\" />");
+            for (int i = start_results; (i <= hits.scoreDocs.length && i <= end_results); i++) {
+                Document doc = reader.document(hits.scoreDocs[i - 1].doc);
+                System.out.println("  <Match id=\"" + doc.get("nodeID") + "\" />");
             }
-            // And skip all the rest
-
-            ++counter;
             }
         }