Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-590: Demo HTML parser gives incorrect summaries when title is repeated as a heading 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1031467 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2010-11-05 08:19:34 +00:00
parent 048cdb57f4
commit c54ea4da67
4 changed files with 12 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lucene/contrib/CHANGES.txt
View File

@ -141,6 +141,9 @@ 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
* LUCENE-2147: Spatial GeoHashUtils now always decode GeoHash strings

2
lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.java
View File

@ -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;

2
lucene/contrib/demo/src/java/org/apache/lucene/demo/html/HTMLParser.jj
View File

@ -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;

7
lucene/contrib/demo/src/test/org/apache/lucene/demo/html/TestHtmlParser.java
View File

@ -105,6 +105,13 @@ public class TestHtmlParser extends LuceneTestCase {
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>" +