Changeset 12256 for trunk/indexers/lucene-gs

Timestamp:

2006-07-20T09:02:47+12:00 (18 years ago)

Author:

mdewsnip

Message:

Now returns query terms and their frequencies.

File:

• trunk/indexers/lucene-gs/src/org/greenstone/LuceneWrapper/GS2LuceneQuery.java (modified) (2 diffs)

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

@@ -1 @@
-/*
- * search.java
- *
- * Created on 25 February 2003, 02:25
- */
-
-
 /**
  *
@@ -13 +6 @@
  */
 
-import java.io.IOException;
 import java.io.BufferedReader;
 import java.io.InputStreamReader;
+import java.util.HashSet;
+import java.util.Iterator;
 
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 import org.apache.lucene.document.Document;
-import org.apache.lucene.search.Searcher;
+import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.index.Term;
+import org.apache.lucene.queryParser.QueryParser;
+import org.apache.lucene.search.Hits;
 import org.apache.lucene.search.IndexSearcher;
 import org.apache.lucene.search.Query;
-import org.apache.lucene.search.Hits;
-import org.apache.lucene.queryParser.QueryParser;
-import org.apache.lucene.search.TermQuery;
-import org.apache.lucene.index.Term;
+import org.apache.lucene.search.Searcher;
 
-public class GS2LuceneQuery  {
 
-    public static void main (String args[]) {
-    
+public class GS2LuceneQuery
+{
+    public static void main (String args[])
+    {
     if (args.length == 0) {
         System.out.println("Usage: GS2LuceneQuery <index directory>");
         return;
     }
+
         try {
         Searcher searcher = new IndexSearcher(args[0]);
         Analyzer analyzer = new StandardAnalyzer();
+        IndexReader reader = ((IndexSearcher) searcher).getIndexReader();
 
         BufferedReader in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
         while (true) {
-        String line = in.readLine();
-        
-        if (line == null) {
+        // Read the query from STDIN
+        String query_string = in.readLine();
+        if (query_string == null || query_string.length() == -1) {
             break;
         }
+        System.err.println("**** query = " + query_string);
 
-        if (line.length() == -1)
-            break;
-        
+        // Parse the query and rewrite it into individual terms (eg. for wildcard searches)
+        QueryParser query_parser = new QueryParser("TX", analyzer);
+        Query query = query_parser.parse(query_string);
+        query = query.rewrite(reader);
 
-        // Term term = new Term("TX",line);
-        // Query query = new TermQuery(term);
-
-        System.err.println("**** query = " + line);
-
-        QueryParser query_parser = new QueryParser("TX", analyzer);
-        Query query = query_parser.parse(line);
-        
+        // Perform the query
         Hits hits = searcher.search(query);
         System.out.println("<ResultSet>");
         System.out.println("  <QueryString>" + query.toString("TX")+"</QueryString>");
-        System.out.println("  <MatchingDocsInfo num=\""+hits.length()+"\"/>");
-                
-        for (int i=0; i< hits.length(); i++) {
+
+        // Return the list of expanded query terms and their frequencies
+        HashSet terms = new HashSet();
+        query.extractTerms(terms);
+        Iterator iter = terms.iterator();
+        while (iter.hasNext()) {
+            Term term = (Term) iter.next();
+            System.out.println("  <Term freq=\"" + reader.docFreq(term) + "\">" + term.text() + "</Term>");
+        }
+
+        // Return the matching documents
+        System.out.println("  <MatchingDocsInfo num=\"" + hits.length() + "\"/>");
+        for (int i = 0; i < hits.length(); i++) {
             Document doc = hits.doc(i);
-            String node_id= doc.get("nodeID");
-            System.out.println("  <Match id=\""+node_id+"\"/>");
+            String node_id = doc.get("nodeID");
+            System.out.println("  <Match id=\"" + node_id + "\"/>");
         }
+
         System.out.println("</ResultSet>");
-        
         }
         
         searcher.close();
     }
-    catch (Exception e) {
-        System.out.println(" caught a " + e.getClass() +
-                   "\n with message: " + e.getMessage());
+    catch (Exception exception) {
+        exception.printStackTrace();
         }
     }