import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
public String segWords(Reader input, String wordSpilt) throws IOException {
	StringBuilder sb = new StringBuilder();
	Seg seg = getSeg();	//取得不同的分词具体算法
	MMSeg mmSeg = new MMSeg(input, seg);
	Word word = null;
	boolean first = true;
	while((word=mmSeg.next())!=null) {
		if(!first) {
			sb.append(wordSpilt);
		}
		String w = word.getString();
		sb.append(w);
		first = false;
		
	}
	return sb.toString();
}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
private void assertTokenizerFactory(final String fieldName, final Seg seg) throws IOException {
	logger.info("assert TokenizerFactory field type={}", fieldName);
	FileInputStream fis = new FileInputStream("src/test/resources/text-sentence.txt");
	try {
		Dictionary.load(fis, new FileLoading() {

			@Override
			public void row(String line, int n) {
				List<String> mwords = AnalyzerTest.toMMsegWords(line, seg);

				assertU(adoc("id", String.valueOf(n), fieldName, line));
				assertU(commit());

				logger.debug("words = {}", mwords);
				for (String word : mwords) {
					assertQ(req("q", "id:" + String.valueOf(n) + " AND " + fieldName + ":" + word),
							"//*[@numFound='1']",
							"//result/doc[1]/int[@name='id'][.='" + String.valueOf(n) + "']");
				}
			}
		});
	} finally {
		fis.close();
	}
}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
public MMSegTokenizer(Seg seg, Reader input) {
	super(input);
	mmSeg = new MMSeg(input, seg);

	termAtt = addAttribute(CharTermAttribute.class);
	offsetAtt = addAttribute(OffsetAttribute.class);
	typeAtt = addAttribute(TypeAttribute.class);
}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
public MMSegTokenizer(Seg seg) {
	this.seg = seg;

	termAtt = addAttribute(CharTermAttribute.class);
	offsetAtt = addAttribute(OffsetAttribute.class);
	typeAtt = addAttribute(TypeAttribute.class);
}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
public static List<String> toMMsegWords(String txt, Seg seg) {
	List<String> words = new ArrayList<String>();
	MMSeg mmSeg = new MMSeg(new StringReader(txt), seg);
	Word word = null;
	try {
		while ((word = mmSeg.next()) != null) {
			String w = word.getString();
			words.add(w);
		}
	} catch (IOException e) {
		e.printStackTrace();
	}
	return words;
}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
protected Seg newSeg() {
	return new SimpleSeg(dic);
}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
protected Seg newSeg() {
	return new MaxWordSeg(dic);
}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
protected Seg newSeg() {
	return new ComplexSeg(dic);
}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
protected Seg getSeg() {
	return new ComplexSeg(dic);
}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
public AssertFileLoading(Seg seg, Analyzer analyzer) {
	this.seg = seg;
	this.analyzer = analyzer;
}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
protected Seg getSeg() {

		return new MaxWordSeg(dic);
	}
 

import com.chenlb.mmseg4j.Seg; //导入依赖的package包/类
protected Seg getSeg() {

		return new SimpleSeg(dic);
	}