Bael 6556 3 (#4382)
* Added parent module on poms that have no parent defined * Removed dependency reduced pom from undertow module * [BAEL-6556] - Next set of renames of testcases * [BAEL-6556] - Next set of renames of testcases * [BAEL-6556] - Next set of renames of testcases * [BAEL-6556] - Next set of renames of testcases
This commit is contained in:
committed by
Grzegorz Piwowarek
parent
cfa5f07c96
commit
7206e64bef
@@ -0,0 +1,36 @@
|
||||
package com.baeldung.apache.opennlp;
|
||||
|
||||
import java.io.InputStream;
|
||||
import opennlp.tools.tokenize.SimpleTokenizer;
|
||||
import opennlp.tools.tokenize.TokenizerME;
|
||||
import opennlp.tools.tokenize.TokenizerModel;
|
||||
import opennlp.tools.tokenize.WhitespaceTokenizer;
|
||||
import static org.assertj.core.api.Assertions.assertThat;
|
||||
import org.junit.Test;
|
||||
|
||||
public class TokenizerUnitTest {
|
||||
|
||||
@Test
|
||||
public void givenEnglishModel_whenTokenize_thenTokensAreDetected() throws Exception {
|
||||
InputStream inputStream = getClass().getResourceAsStream("/models/en-token.bin");
|
||||
TokenizerModel model = new TokenizerModel(inputStream);
|
||||
TokenizerME tokenizer = new TokenizerME(model);
|
||||
String[] tokens = tokenizer.tokenize("Baeldung is a Spring Resource.");
|
||||
assertThat(tokens).contains("Baeldung", "is", "a", "Spring", "Resource", ".");
|
||||
}
|
||||
|
||||
@Test
|
||||
public void givenWhitespaceTokenizer_whenTokenize_thenTokensAreDetected() throws Exception {
|
||||
WhitespaceTokenizer tokenizer = WhitespaceTokenizer.INSTANCE;
|
||||
String[] tokens = tokenizer.tokenize("Baeldung is a Spring Resource.");
|
||||
assertThat(tokens).contains("Baeldung", "is", "a", "Spring", "Resource.");
|
||||
}
|
||||
|
||||
@Test
|
||||
public void givenSimpleTokenizer_whenTokenize_thenTokensAreDetected() throws Exception {
|
||||
SimpleTokenizer tokenizer = SimpleTokenizer.INSTANCE;
|
||||
String[] tokens = tokenizer.tokenize("Baeldung is a Spring Resource.");
|
||||
assertThat(tokens).contains("Baeldung", "is", "a", "Spring", "Resource", ".");
|
||||
}
|
||||
|
||||
}
|
||||
Reference in New Issue
Block a user