add mynlp

This commit is contained in:
Looly
2019-09-03 19:18:39 +08:00
parent 1caf64f4ac
commit bea37293ad
9 changed files with 173 additions and 0 deletions

View File

@@ -3,6 +3,7 @@ package cn.hutool.extra.tokenizer;
import java.util.Iterator;
import org.junit.Assert;
import org.junit.Ignore;
import org.junit.Test;
import cn.hutool.core.collection.CollUtil;
@@ -12,6 +13,7 @@ import cn.hutool.extra.tokenizer.engine.ikanalyzer.IKAnalyzerEngine;
import cn.hutool.extra.tokenizer.engine.jcseg.JcsegEngine;
import cn.hutool.extra.tokenizer.engine.jieba.JiebaEngine;
import cn.hutool.extra.tokenizer.engine.mmseg.MmsegEngine;
import cn.hutool.extra.tokenizer.engine.mynlp.MynlpEngine;
import cn.hutool.extra.tokenizer.engine.word.WordEngine;
/**
@@ -86,6 +88,16 @@ public class TokenizerUtilTest {
Assert.assertEquals("这两个 方法 的 区别 在于 返回值", resultStr);
}
@Test
@Ignore
public void mynlpTest() {
// 此单元测试需要JDK8默认忽略
TokenizerEngine engine = new MynlpEngine();
Result result = engine.parse(text);
String resultStr = CollUtil.join((Iterator<Word>)result, " ");
Assert.assertEquals("这 两个 方法 的 区别 在于 返回 值", resultStr);
}
private void checkResult(Result result) {
String resultStr = CollUtil.join((Iterator<Word>)result, " ");
Assert.assertEquals("这 两个 方法 的 区别 在于 返回 值", resultStr);