add HanLPTest

master
ziyonghong 5 years ago
parent 6d611f7ce4
commit a800017dd6

@ -0,0 +1,17 @@
<?xml version="1.0" encoding="UTF-8"?>
<projectDescription>
<name>paz2s9bc5</name>
<comment>Project paz2s9bc5 created by Buildship.</comment>
<projects>
</projects>
<buildSpec>
<buildCommand>
<name>org.eclipse.buildship.core.gradleprojectbuilder</name>
<arguments>
</arguments>
</buildCommand>
</buildSpec>
<natures>
<nature>org.eclipse.buildship.core.gradleprojectnature</nature>
</natures>
</projectDescription>

@ -0,0 +1,2 @@
connection.project.dir=
eclipse.preferences.version=1

@ -0,0 +1,42 @@
import java.util.ArrayList;
import java.util.List;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.mllib.classification.NaiveBayes;
import org.apache.spark.mllib.classification.NaiveBayesModel;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.linalg.Vectors;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.junit.Test;
import com.appleyk.process.ModelProcess;
import com.hankcs.hanlp.HanLP;
import com.hankcs.hanlp.dictionary.CustomDictionary;
import com.hankcs.hanlp.seg.Segment;
import com.hankcs.hanlp.seg.common.Term;
public class HanLPTest {
@Test
public void TestA(){
String lineStr = "明天虽然会下雨,但是我还是会看周杰伦的演唱会。";
try{
Segment segment = HanLP.newSegment();
segment.enableCustomDictionary(true);
/**
* +
*/
CustomDictionary.add("虽然会","ng 0");
List<Term> seg = segment.seg(lineStr);
for (Term term : seg) {
System.out.println(term.toString());
}
}catch(Exception ex){
System.out.println(ex.getClass()+","+ex.getMessage());
}
}
}
Loading…
Cancel
Save