mindol1004/spring-boot-rest
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

BAEL-1557 Intro to Apache OpenNlp

Browse Source
This commit is contained in:
mansi2392
2018-03-30 11:28:42 +05:30
parent 764ccb54a9
commit db10f66e60
15 changed files with 301773 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
apache-opennlp/src/test/java/com/baeldung/apache/opennlp/ChunkerTest.java Normal file
View File

@@ -0,0 +1,36 @@
package com.baeldung.apache.opennlp;
import java.io.FileInputStream;
import java.io.InputStream;
import opennlp.tools.chunker.ChunkerME;
import opennlp.tools.chunker.ChunkerModel;
import opennlp.tools.postag.POSModel;
import opennlp.tools.postag.POSTaggerME;
import opennlp.tools.tokenize.SimpleTokenizer;
import static org.assertj.core.api.Assertions.assertThat;
import org.junit.Test;
/**
*
* @author Parth
*/
public class ChunkerTest {
@Test
public void givenSentence_whenChunk_thenGetChunks() throws Exception {
SimpleTokenizer tokenizer = SimpleTokenizer.INSTANCE;
String[] tokens = tokenizer.tokenize("He reckons the current account deficit will narrow to only 8 billion.");
InputStream inputStreamPOSTagger = new FileInputStream("src/main/resources/models/en-pos-maxent.bin");
POSModel posModel = new POSModel(inputStreamPOSTagger);
POSTaggerME posTagger = new POSTaggerME(posModel);
String tags[] = posTagger.tag(tokens);
InputStream inputStreamChunker = new FileInputStream("src/main/resources/models/en-chunker.bin");
ChunkerModel chunkerModel = new ChunkerModel(inputStreamChunker);
ChunkerME chunker = new ChunkerME(chunkerModel);
String[] chunks = chunker.chunk(tokens, tags);
assertThat(chunks).contains("B-NP", "B-VP", "B-NP", "I-NP", "I-NP", "I-NP", "B-VP", "I-VP", "B-PP", "B-NP", "I-NP", "I-NP", "O");
}
}