You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by ko...@apache.org on 2018/05/22 09:04:34 UTC
[opennlp] branch master updated: OPENNLP-1198: add more tests to
NGramGeneratorTest (#319)
This is an automated email from the ASF dual-hosted git repository.
koji pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/opennlp.git
The following commit(s) were added to refs/heads/master by this push:
new 95b2fe9 OPENNLP-1198: add more tests to NGramGeneratorTest (#319)
95b2fe9 is described below
commit 95b2fe97c7f191e43b7fe11e8e027d87eb47f15e
Author: Koji Sekiguchi <ko...@rondhuit.com>
AuthorDate: Tue May 22 18:04:32 2018 +0900
OPENNLP-1198: add more tests to NGramGeneratorTest (#319)
---
.../opennlp/tools/ngram/NGramGeneratorTest.java | 150 ++++++++++++++++++---
1 file changed, 129 insertions(+), 21 deletions(-)
diff --git a/opennlp-tools/src/test/java/opennlp/tools/ngram/NGramGeneratorTest.java b/opennlp-tools/src/test/java/opennlp/tools/ngram/NGramGeneratorTest.java
index b1da5d6..8f73882 100644
--- a/opennlp-tools/src/test/java/opennlp/tools/ngram/NGramGeneratorTest.java
+++ b/opennlp-tools/src/test/java/opennlp/tools/ngram/NGramGeneratorTest.java
@@ -25,43 +25,151 @@ import org.junit.Assert;
import org.junit.Test;
public class NGramGeneratorTest {
-
+
@Test
- public void generateListTest() {
-
+ public void generateListTest1() {
+
+ final List<String> input = Arrays.asList("This", "is", "a", "sentence");
+ final int window = 1;
+ final String separator = "-";
+
+ final List<String> ngrams = NGramGenerator.generate(input, window, separator);
+
+ Assert.assertEquals(4, ngrams.size());
+ Assert.assertEquals("This", ngrams.get(0));
+ Assert.assertEquals("is", ngrams.get(1));
+ Assert.assertEquals("a", ngrams.get(2));
+ Assert.assertEquals("sentence", ngrams.get(3));
+
+ }
+
+ @Test
+ public void generateListTest2() {
+
final List<String> input = Arrays.asList("This", "is", "a", "sentence");
final int window = 2;
final String separator = "-";
-
+
final List<String> ngrams = NGramGenerator.generate(input, window, separator);
-
+
Assert.assertEquals(3, ngrams.size());
- Assert.assertTrue(ngrams.contains("This-is"));
- Assert.assertTrue(ngrams.contains("is-a"));
- Assert.assertTrue(ngrams.contains("a-sentence"));
-
+ Assert.assertEquals("This-is", ngrams.get(0));
+ Assert.assertEquals("is-a", ngrams.get(1));
+ Assert.assertEquals("a-sentence", ngrams.get(2));
+
}
-
+
+ @Test
+ public void generateListTest3() {
+
+ final List<String> input = Arrays.asList("This", "is", "a", "sentence");
+ final int window = 3;
+ final String separator = "-";
+
+ final List<String> ngrams = NGramGenerator.generate(input, window, separator);
+
+ Assert.assertEquals(2, ngrams.size());
+ Assert.assertEquals("This-is-a", ngrams.get(0));
+ Assert.assertEquals("is-a-sentence", ngrams.get(1));
+
+ }
+
+ @Test
+ public void generateListTest4() {
+
+ final List<String> input = Arrays.asList("This", "is", "a", "sentence");
+ final int window = 4;
+ final String separator = "-";
+
+ final List<String> ngrams = NGramGenerator.generate(input, window, separator);
+
+ Assert.assertEquals(1, ngrams.size());
+ Assert.assertEquals("This-is-a-sentence", ngrams.get(0));
+
+ }
+
+ @Test
+ public void generateCharTest1() {
+
+ final char[] input = "Test".toCharArray();
+ final int window = 1;
+ final String separator = "-";
+
+ final List<String> ngrams = NGramGenerator.generate(input, window, separator);
+
+ Assert.assertEquals(4, ngrams.size());
+ Assert.assertEquals("T", ngrams.get(0));
+ Assert.assertEquals("e", ngrams.get(1));
+ Assert.assertEquals("s", ngrams.get(2));
+ Assert.assertEquals("t", ngrams.get(3));
+
+ }
+
+ @Test
+ public void generateCharTest2() {
+
+ final char[] input = "Test".toCharArray();
+ final int window = 2;
+ final String separator = "-";
+
+ final List<String> ngrams = NGramGenerator.generate(input, window, separator);
+
+ Assert.assertEquals(3, ngrams.size());
+ Assert.assertEquals("T-e", ngrams.get(0));
+ Assert.assertEquals("e-s", ngrams.get(1));
+ Assert.assertEquals("s-t", ngrams.get(2));
+
+ }
+
+ @Test
+ public void generateCharTest3() {
+
+ final char[] input = "Test".toCharArray();
+ final int window = 3;
+ final String separator = "-";
+
+ final List<String> ngrams = NGramGenerator.generate(input, window, separator);
+
+ Assert.assertEquals(2, ngrams.size());
+ Assert.assertEquals("T-e-s", ngrams.get(0));
+ Assert.assertEquals("e-s-t", ngrams.get(1));
+
+ }
+
+ @Test
+ public void generateCharTest4() {
+
+ final char[] input = "Test".toCharArray();
+ final int window = 4;
+ final String separator = "-";
+
+ final List<String> ngrams = NGramGenerator.generate(input, window, separator);
+
+ Assert.assertEquals(1, ngrams.size());
+ Assert.assertEquals("T-e-s-t", ngrams.get(0));
+
+ }
+
@Test
public void generateCharTest() {
-
+
final char[] input = "Test again".toCharArray();
final int window = 4;
final String separator = "-";
-
+
final List<String> ngrams = NGramGenerator.generate(input, window, separator);
Assert.assertEquals(7, ngrams.size());
- Assert.assertTrue(ngrams.contains("T-e-s-t"));
- Assert.assertTrue(ngrams.contains("e-s-t- "));
- Assert.assertTrue(ngrams.contains("s-t- -a"));
- Assert.assertTrue(ngrams.contains("t- -a-g"));
- Assert.assertTrue(ngrams.contains(" -a-g-a"));
- Assert.assertTrue(ngrams.contains("a-g-a-i"));
- Assert.assertTrue(ngrams.contains("g-a-i-n"));
-
+ Assert.assertEquals(("T-e-s-t"), ngrams.get(0));
+ Assert.assertEquals(("e-s-t- "), ngrams.get(1));
+ Assert.assertEquals(("s-t- -a"), ngrams.get(2));
+ Assert.assertEquals(("t- -a-g"), ngrams.get(3));
+ Assert.assertEquals((" -a-g-a"), ngrams.get(4));
+ Assert.assertEquals(("a-g-a-i"), ngrams.get(5));
+ Assert.assertEquals(("g-a-i-n"), ngrams.get(6));
+
}
-
+
@Test
public void generateLargerWindowThanListTest() {
--
To stop receiving notification emails like this one, please contact
koji@apache.org.