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

LUCENE-2014: add a thai test to prevent any similar regression 

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@831189 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2009-10-30 03:26:44 +00:00
parent 19e55ea991
commit 8861ba2ffd
1 changed files with 20 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
contrib/analyzers/common/src/test/org/apache/lucene/analysis/th/TestThaiAnalyzer.java
View File

@ -90,6 +90,26 @@ public class TestThaiAnalyzer extends BaseTokenStreamTestCase {
new String[] { "ประโยค", "ว่า", "quick", "brown", "fox", "jumped", "over", "lazy", "dogs" });
}
/*
* Test that position increments are adjusted correctly for stopwords.
*/
public void testPositionIncrements() throws Exception {
ThaiAnalyzer analyzer = new ThaiAnalyzer(Version.LUCENE_CURRENT);
assertAnalyzesTo(analyzer, "ประโยคว่า the ประโยคว่า",
new String[] { "ประโยค", "ว่า", "ประโยค", "ว่า" },
new int[] { 0, 6, 14, 20 },
new int[] { 6, 9, 20, 23 },
new int[] { 1, 1, 2, 1 });
// case that a stopword is adjacent to thai text, with no whitespace
assertAnalyzesTo(analyzer, "ประโยคว่าtheประโยคว่า",
new String[] { "ประโยค", "ว่า", "ประโยค", "ว่า" },
new int[] { 0, 6, 12, 18 },
new int[] { 6, 9, 18, 21 },
new int[] { 1, 1, 2, 1 });
}
public void testReusableTokenStream() throws Exception {
ThaiAnalyzer analyzer = new ThaiAnalyzer(Version.LUCENE_CURRENT);
assertAnalyzesToReuse(analyzer, "", new String[] {});