ehatcher 2004/01/25 05:16:00
Modified: contributions/miscellaneous/src/java/org/apache/lucene/misc
HighFreqTerms.java
Log:
#26396 - HighFreqTerms fixup from Jean-François Halleux
Revision Changes Path
1.3 +54 -72
jakarta-lucene-sandbox/contributions/miscellaneous/src/java/org/apache/lucene/misc/HighFreqTerms.java
Index: HighFreqTerms.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene-sandbox/contributions/miscellaneous/src/java/org/apache/lucene/misc/HighFreqTerms.java,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- HighFreqTerms.java 6 Jan 2004 01:17:37 -0000 1.2
+++ HighFreqTerms.java 25 Jan 2004 13:16:00 -0000 1.3
@@ -3,7 +3,7 @@
/* ====================================================================
* The Apache Software License, Version 1.1
*
- * Copyright (c) 2001 The Apache Software Foundation. All rights
+ * Copyright (c) 2001,2004 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -54,10 +54,10 @@
* <http://www.apache.org/>.
*/
-import org.apache.lucene.util.PriorityQueue;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.TermEnum;
+import org.apache.lucene.util.PriorityQueue;
/**
* <code>HighFreqTerms</code> class extracts terms and their frequencies out
@@ -65,77 +65,59 @@
*
* @version $Id$
*/
-public class HighFreqTerms
-{
- public static int numTerms = 100;
-
- public static void main(String[] args) throws Exception
- {
- IndexReader reader = null;
- if (args.length == 1)
- {
- reader = IndexReader.open(args[0]);
- }
- else
- {
- usage();
- System.exit(1);
- }
-
- TermInfoQueue tiq = new TermInfoQueue(numTerms);
- TermEnum terms = reader.terms();
-
- int minFreq = 0;
- while (terms.next())
- {
- if (terms.docFreq() > minFreq)
- {
- tiq.put(new TermInfo(terms.term(), terms.docFreq()));
- if (tiq.size() > numTerms) // if tiq overfull
- {
- tiq.pop(); // remove lowest
in tiq
- minFreq = ((TermInfo)tiq.top()).docFreq; // reset minFreq
- }
- }
- }
-
- while (tiq.size() != 0)
- {
- TermInfo termInfo = (TermInfo)tiq.pop();
- System.out.println(termInfo.term + " " + termInfo.docFreq);
- }
-
- reader.close();
- }
-
- private static void usage()
- {
- System.out.println("\n\n" +
- "java org.apache.lucene.misc.HighFreqTerms <index dir>\n\n");
- }
+public class HighFreqTerms {
+
+ // The top numTerms will be displayed
+ public static final int numTerms = 100;
+
+ public static void main(String[] args) throws Exception {
+ IndexReader reader = null;
+ if (args.length == 1) {
+ reader = IndexReader.open(args[0]);
+ } else {
+ usage();
+ System.exit(1);
+ }
+
+ TermInfoQueue tiq = new TermInfoQueue(numTerms);
+ TermEnum terms = reader.terms();
+
+ while (terms.next()) {
+ tiq.insert(new TermInfo(terms.term(), terms.docFreq()));
+ }
+
+ while (tiq.size() != 0) {
+ TermInfo termInfo = (TermInfo) tiq.pop();
+ System.out.println(termInfo.term + " " + termInfo.docFreq);
+ }
+
+ reader.close();
+ }
+
+ private static void usage() {
+ System.out.println(
+ "\n\n"
+ + "java org.apache.lucene.misc.HighFreqTerms <index
dir>\n\n");
+ }
}
-final class TermInfo
-{
- TermInfo(Term t, int df)
- {
- term = t;
- docFreq = df;
- }
- int docFreq;
- Term term;
+final class TermInfo {
+ TermInfo(Term t, int df) {
+ term = t;
+ docFreq = df;
+ }
+ int docFreq;
+ Term term;
}
-final class TermInfoQueue extends PriorityQueue
-{
- TermInfoQueue(int size)
- {
- initialize(size);
- }
- protected final boolean lessThan(Object a, Object b)
- {
- TermInfo termInfoA = (TermInfo)a;
- TermInfo termInfoB = (TermInfo)b;
- return termInfoA.docFreq < termInfoB.docFreq;
- }
+final class TermInfoQueue extends PriorityQueue {
+ TermInfoQueue(int size) {
+ initialize(size);
+ }
+
+ protected final boolean lessThan(Object a, Object b) {
+ TermInfo termInfoA = (TermInfo) a;
+ TermInfo termInfoB = (TermInfo) b;
+ return termInfoA.docFreq < termInfoB.docFreq;
+ }
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
