You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2010/11/05 09:19:34 UTC
svn commit: r1031467 - in /lucene/dev/trunk/lucene/contrib: CHANGES.txt
demo/src/java/org/apache/lucene/demo/html/HTMLParser.java
demo/src/java/org/apache/lucene/demo/html/HTMLParser.jj
demo/src/test/org/apache/lucene/demo/html/TestHtmlParser.java
Author: rmuir
Date: Fri Nov 5 08:19:34 2010
New Revision: 1031467
URL: http://svn.apache.org/viewvc?rev=1031467&view=rev
Log:
LUCENE-590: Demo HTML parser gives incorrect summaries when title is repeated as a heading
Modified:
lucene/dev/trunk/lucene/contrib/CHANGES.txt
lucene/dev/trunk/lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.java
lucene/dev/trunk/lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.jj
lucene/dev/trunk/lucene/contrib/demo/src/test/org/apache/lucene/demo/html/TestHtmlParser.java
Modified: lucene/dev/trunk/lucene/contrib/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/CHANGES.txt?rev=1031467&r1=1031466&r2=1031467&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/CHANGES.txt (original)
+++ lucene/dev/trunk/lucene/contrib/CHANGES.txt Fri Nov 5 08:19:34 2010
@@ -140,6 +140,9 @@ Bug fixes
* LUCENE-2246: Fix contrib/demo for Turkish html documents.
(Selim Nadi via Robert Muir)
+
+* LUCENE-590: Demo HTML parser gives incorrect summaries when title is repeated as a heading
+ (Curtis d'Entremont via Robert Muir)
API Changes
Modified: lucene/dev/trunk/lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.java?rev=1031467&r1=1031466&r2=1031467&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.java (original)
+++ lucene/dev/trunk/lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.java Fri Nov 5 08:19:34 2010
@@ -84,7 +84,7 @@ InterruptedException {
String sum = summary.toString().trim();
String tit = getTitle();
- if (sum.startsWith(tit) || sum.equals(""))
+ if (sum.equals(""))
return tit;
else
return sum;
Modified: lucene/dev/trunk/lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.jj
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.jj?rev=1031467&r1=1031466&r2=1031467&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.jj (original)
+++ lucene/dev/trunk/lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.jj Fri Nov 5 08:19:34 2010
@@ -111,7 +111,7 @@ InterruptedException {
String sum = summary.toString().trim();
String tit = getTitle();
- if (sum.startsWith(tit) || sum.equals(""))
+ if (sum.equals(""))
return tit;
else
return sum;
Modified: lucene/dev/trunk/lucene/contrib/demo/src/test/org/apache/lucene/demo/html/TestHtmlParser.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/demo/src/test/org/apache/lucene/demo/html/TestHtmlParser.java?rev=1031467&r1=1031466&r2=1031467&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/demo/src/test/org/apache/lucene/demo/html/TestHtmlParser.java (original)
+++ lucene/dev/trunk/lucene/contrib/demo/src/test/org/apache/lucene/demo/html/TestHtmlParser.java Fri Nov 5 08:19:34 2010
@@ -105,6 +105,13 @@ public class TestHtmlParser extends Luce
assertEquals(200, parser.getSummary().length());
}
+ // LUCENE-590
+ public void testSummaryTitle() throws Exception {
+ String text = "<html><head><title>Summary</title></head><body>Summary of the document</body></html>";
+ HTMLParser parser = new HTMLParser(new StringReader(text));
+ assertEquals("Summary of the document", parser.getSummary());
+ }
+
// LUCENE-2246
public void testTurkish() throws Exception {
String text = "<html><body>" +