Changeset 12976 for trunk/indexers

Timestamp:

2006-10-03T14:22:03+13:00 (18 years ago)

Author:

mdewsnip

Message:

Rearranged some code to make the fact that the term information is now independent of the search results clearer.

File:

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

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

@@ -125 +125 @@
             query = query.rewrite(reader);
 
+            // Return the list of expanded query terms and their frequencies
+            HashSet terms = new HashSet();
+            query.extractTerms(terms);
+            Iterator term_iterator = terms.iterator();
+            System.out.println("  <QueryTermsInfo num=\"" + terms.size() + "\"/>");
+            while (term_iterator.hasNext()) {
+            Term term = (Term) term_iterator.next();
+
+            // Get the term frequency over all the documents
+            TermDocs term_docs = reader.termDocs(term);
+            int term_freq = term_docs.freq();
+            while (term_docs.next()) {
+                term_freq += term_docs.freq();
+            }
+
+            // If you wanted to limit this to just text terms add
+            // something like this:
+            // if (term.field().equals(TEXTFIELD))
+            System.out.println("  <Term value=\"" + term.text() + "\" field=\"" + term.field() + "\" freq=\"" + term_freq + "\" />");
+            }
+            
+            // Return the list of stop words removed from the query
+            HashSet terms_including_stop_words = new HashSet();
+            query_including_stop_words.extractTerms(terms_including_stop_words);
+            Iterator terms_including_stop_words_iter = terms_including_stop_words.iterator();
+            while (terms_including_stop_words_iter.hasNext()) {
+            Term term = (Term) terms_including_stop_words_iter.next();
+            if (!terms.contains(term)) {
+                System.out.println("  <StopWord value=\"" + term.text() + "\"/>");
+            }
+            }
+
             // Perform the query (filter and sorter may be null)
             Hits hits = searcher.search(query, filter, sorter);
@@ -152 +184 @@
 
             ++counter;
-            }
-
-            // Return the list of expanded query terms and their frequencies
-            HashSet terms = new HashSet();
-            query.extractTerms(terms);
-            Iterator term_iterator = terms.iterator();
-            System.out.println("  <QueryTermsInfo num=\"" + terms.size() + "\"/>");
-            while (term_iterator.hasNext()) {
-            Term term = (Term) term_iterator.next();
-
-            // Get the term frequency over all the documents
-            TermDocs term_docs = reader.termDocs(term);
-            int term_freq = term_docs.freq();
-            while (term_docs.next()) {
-                term_freq += term_docs.freq();
-            }
-
-            // If you wanted to limit this to just text terms add
-            // something like this:
-            // if (term.field().equals(TEXTFIELD))
-            System.out.println("  <Term value=\"" + term.text() + "\" field=\"" + term.field() + "\" freq=\"" + term_freq + "\" />");
-            }
-            
-            // Return the list of stop words removed from the query
-            HashSet terms_including_stop_words = new HashSet();
-            query_including_stop_words.extractTerms(terms_including_stop_words);
-            Iterator terms_including_stop_words_iter = terms_including_stop_words.iterator();
-            while (terms_including_stop_words_iter.hasNext()) {
-            Term term = (Term) terms_including_stop_words_iter.next();
-            if (!terms.contains(term)) {
-                System.out.println("  <StopWord value=\"" + term.text() + "\"/>");
-            }
             }
         }