Lucene(5.3.1) demo

Lucene包含两部分内容：创建索引、检索。

package demo.mytest.lucene;

import java.io.IOException;
import java.nio.file.FileSystems;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.Encoder;
import org.apache.lucene.search.highlight.Formatter;
import org.apache.lucene.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.Scorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLEncoder;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.BytesRef;
import org.junit.Test;

import demo.mytest.lucene.utils.LuceneUtils;

public class HelloWorld {

public static final String dataDir = "F:\\workspace\\luceneDemo\\dataDir\\CHANGES.txt";//文档所在路径 CHANGES.txt
public static final String dataDir2 = "F:\\workspace\\luceneDemo\\dataDir\\bye.txt";
public static final String indexDir = "F:\\workspace\\luceneDemo\\indexDir";//索引文件存储位置
public static final Analyzer analyzer = new StandardAnalyzer();

/**
*
* testCreateIndex 创建索引库
*
* @Description
* @throws Exception void
* @see
*/
@Test
public void testCreateIndex() throws Exception {

IndexWriterConfig config = new IndexWriterConfig(analyzer);
config.setOpenMode(OpenMode.CREATE);//设置indexWriter的打开方式，是新建或覆盖（CREATE）？是追加(APPEND)？还是两者结合(CREATE_OR_APPEND)？
Directory directory = this.getFsIndexDirectory();//将索引文件保存的指定路径
IndexWriter indexWriter = new IndexWriter(directory, config);//创建indexWriter对象
//		indexWriter.deleteAll();//删除索引库的所有文件

Document doc = LuceneUtils.file2Document(dataDir);//处理、转换。将文件转换成文档对象
indexWriter.addDocument(doc);

Document doc2 = LuceneUtils.file2Document(dataDir2);//处理、转换。将文件转换成文档对象
indexWriter.addDocument(doc2);

indexWriter.close();//用完一定要关闭！
/*
* 新添加一个Document并不会马上将它的索引写入最终的索引大文件,它的索引会暂时存于缓存。
* 当关闭时，会将缓存中的索引归并到索引大文件。如果此处没有关闭操作，那么刚刚添加的Document的索引不会保存到最终的索引大文件。
*/
directory.close();
}

/**
*
* testTermQuery 关键词查询
* @throws IOException
*
* @Description
* @see
*/
@Test
public void testTermQuery() throws IOException {
String queryStr = "bye.txt";
Term term = new Term("fileName", queryStr);
Query query = new TermQuery(term) ;

this.queryAndPrintResult(query);
}

/**
*
* testTermRangeQuery 范围查询
*
* @Description
* @throws IOException void
* @see
*/
@Test
public void testTermRangeQuery() throws IOException {
Query query = new TermRangeQuery("fileSize",new BytesRef(10),new BytesRef(2000), true, true);
this.queryAndPrintResult(query);
}

/**
*
* queryAndPrintResult 测试查询对象用到的方法
*
* @Description
* @throws IOException void
* @see
*/
private void queryAndPrintResult(Query query) throws IOException {
Directory directory = this.getFsIndexDirectory();//获取索引文件的存储路径
IndexReader indexReader = DirectoryReader.open(directory);
IndexSearcher indexSearcher = new IndexSearcher(indexReader);//从指定的路径的索引库检索指定的文本

TopDocs topDocs = indexSearcher.search(query, 100000);

ScoreDoc[] scoreDocs = topDocs.scoreDocs;

System.out.println("共有【"+ topDocs.totalHits+"】条查询结果。\n----------------");
//打印文档对象信息
for(int i=0;i<scoreDocs.length;i++) {
Document document = indexSearcher.doc(scoreDocs[i].doc);//按照文档编号取出相应的文档对象
LuceneUtils.printDocumentInfo(document);
}

indexReader.close();//用完一定要关闭！
directory.close();
}

/**
*
* testSearch 检索
*
* @Description
* @throws IOException
* @throws ParseException void
* @see
*/
@Test
public void testSearch() throws IOException, ParseException {
String queryStr = "ok";//ok,Ok,OK,oK都能检索到文档中的OK关键字

Directory directory = this.getFsIndexDirectory();//获取索引文件的存储路径
IndexReader indexReader = DirectoryReader.open(directory);
IndexSearcher indexSearcher = new IndexSearcher(indexReader);//从指定的路径的索引库检索指定的文本

String[] fields = {"fileName","content"};
QueryParser parser = new MultiFieldQueryParser(fields,analyzer);//在多个文本域中检索的解析器
//		QueryParser parser = new QueryParser("content", analyzer);//在content域中检索的解析器
Query query = parser.parse(queryStr);//通过解析器将待检索的字符串转化成Query对象
//		System.out.println(",,,,,,,,,,,"+query.);
//Filter filter = null;
//indexSearcher.search(query, filter, 2000);//5.3.1中已经废止该方法

TopDocs topDocs = indexSearcher.search(query, 100000);

ScoreDoc[] scoreDocs = topDocs.scoreDocs;
System.out.println("共有【"+ topDocs.totalHits+"】条查询结果。\n----------------");

//打印文档对象信息
for(int i=0;i<scoreDocs.length;i++) {
Document document = indexSearcher.doc(scoreDocs[i].doc);//按照文档编号取出相应的文档对象
//			document.getField("content").
LuceneUtils.printDocumentInfo(document);
}

indexReader.close();//用完一定要关闭！
directory.close();
}

/**
*
* testHighlighter 将搜索结果中的关键字高亮显示，并生成摘要文本
* @throws Exception
*
* @Description
* @see
*/
@Test
public void testHighlighter() throws Exception {
String queryStr = "bye.txt";
Directory directory = this.getFsIndexDirectory();//获取索引文件的存储路径
IndexReader indexReader = DirectoryReader.open(directory);
IndexSearcher indexSearcher = new IndexSearcher(indexReader);//从指定的路径的索引库检索指定的文本

String[] fields = {"fileName","content"};
QueryParser parser = new MultiFieldQueryParser(fields,analyzer);//在多个文本域中检索的解析器
Query query = parser.parse(queryStr);//通过解析器将待检索的字符串转化成Query对象

//1.获得查询结果-文档集合
ScoreDoc[] scoreDocs = indexSearcher.search(query, 100000).scoreDocs;

//2.高亮处理（构造高亮器+使用高亮器-高亮关键词），并打印文档对象信息
//2.1 构造高亮器
//--------------------
Formatter formatter = new SimpleHTMLFormatter("<font color='red'>","</font>");

Encoder encoder = new SimpleHTMLEncoder();

Scorer fragmentScorer = new QueryScorer(query);
Highlighter highlighter = new Highlighter(formatter, encoder, fragmentScorer);
//设置高亮器
final int FRAGMENT_SIZE = 50;
Fragmenter fragmenter = new SimpleFragmenter(FRAGMENT_SIZE);//每一个fragment的字符长度
highlighter.setTextFragmenter(fragmenter);
//--------------------

for(int i=0;i<scoreDocs.length;i++) {
Document document = indexSearcher.doc(scoreDocs[i].doc);//按照文档编号取出相应的文档对象
//2.2生成摘要文本，并将摘要中的关键词高亮显示
//--------------------
//抽取与关键词最相近的文本片段作为摘要文本
String text = document.get("content");
String ht = highlighter.getBestFragment(analyzer, "content", text);
if(ht == null) {//若fileName域中包含关键词，而content域中没有关键词，ht则为空
//显示文档从头开始的部分文本
ht = text.substring(0, Math.min(text.length(), FRAGMENT_SIZE));
}
System.out.println("ht.length()="+ht.length());
//将标记过关键词的信息重新设置到文档对象中
//document.getField("content").setValue(ht);//没有setValue方法
document.removeField("content");
document.add(new Field("content", ht,TextField.TYPE_STORED));
//--------------------

LuceneUtils.printDocumentInfo(document);
}

indexReader.close();//用完一定要关闭！
directory.close();
}

/**
*
* test
* @throws IOException
*
* @Description
* 1.当应用启动时，将磁盘中的索引文件读入内存。
* 2.应用运行过程中，只对内存中的索引文件进行操作。保证运行速度
* 3.在应用关闭前，将内存中的索引文件同步到磁盘。保证数据不丢失
* void
* @see
*/
@Test
public void test() throws Exception {
//1.当应用启动时，将磁盘中的索引文件读入内存。
//获取磁盘上的索引库路径
Directory fsDir = this.getFsIndexDirectory();

//2.应用运行过程中，只对内存中的索引文件进行操作
//创建基于内存的IndexWriter
Directory ramDir = new RAMDirectory((FSDirectory)fsDir, new IOContext() );//创建对象的同时，将磁盘上的索引文件加载到内存
IndexWriterConfig ramConfig = new IndexWriterConfig(analyzer);
ramConfig.setOpenMode(OpenMode.CREATE);
IndexWriter ramIndexWriter = new IndexWriter(ramDir,ramConfig);

//应用程序运行过程中，添加Document对象
String tmpDir = "F:\\workspace\\luceneDemo\\dataDir\\CHANGES.txt";//1.txt   CHANGES.txt
Document doc = LuceneUtils.file2Document(tmpDir);//处理、转换。将文件转换成文档对象
ramIndexWriter.addDocument(doc);

ramIndexWriter.close();//操作完毕，一定要关闭！！！

//3.在应用关闭前，将内存中的索引文件同步到磁盘。
//创建基于磁盘的IndexWriter
IndexWriterConfig fsConfig = new IndexWriterConfig(analyzer);
fsConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
IndexWriter fsIndexWriter = new IndexWriter(fsDir,fsConfig);
fsIndexWriter.addIndexes(new Directory[] {ramDir});

fsIndexWriter.close();//操作完毕，一定要关闭！！！

}

/**
*
* testForceMerge 合并索引文件
*
* @Description 优化操作
* @throws Exception void
* @see
*/
@Test
public void testForceMerge() throws Exception {
Directory fsDir = this.getFsIndexDirectory();
IndexWriterConfig fsConfig = new IndexWriterConfig(analyzer);
fsConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
IndexWriter fsIndexWriter = new IndexWriter(fsDir,fsConfig);

fsIndexWriter.commit();
fsIndexWriter.forceMerge(2);//forceMerge()内部有flush操作
fsIndexWriter.close();//操作完毕，一定要关闭！！！
}

/**
*
* testAnalyzer 分词器的使用
*
* @Description 英文有英文分词器，中文有中文分词器。根据语言不同，选择相应的分词器（第三方jar）
* @throws IOException void
* @see
*/
@Test
public void testAnalyzer() throws IOException {
String enText = "This house builds well.She really wants to live in.";
String zhText = "这个房子真好，她很想住进来。再见";
Analyzer en1 = new StandardAnalyzer();
//		Analyzer zh1 = new SimpleAnalyzer();
this.analyze(en1, enText);
System.out.println("--------------------");
this.analyze(en1, zhText);

}

/**
*
* analyze 分词
*
* @Description
* @param analyzer 分词器
* @param text 文本
* @throws IOException void
* @see
*/
private void analyze(Analyzer analyzer, String text) throws IOException {
TokenStream tokenStream = analyzer.tokenStream("content", text);

//addAttribute()：检查AttributeSource是否存在指定类的实例，如果存在，则返回该实例；不存在，则在AttributeSource中添加实例，并返回实例。
OffsetAttribute offsetAtt = tokenStream.addAttribute(OffsetAttribute.class);//OffsetAttribute：token的开始、结束偏移量属性。

//从tokenStream中获取CharTermAttribute
CharTermAttribute termAtt = tokenStream.addAttribute(CharTermAttribute.class);//CharTermAttribute：token的词语（term）属性。

try {
tokenStream.reset(); //清除状态，已到TokenStream的开始位置。在调用incrementToken()之前一定要调用reset()。 Resets this stream to the beginning. (Required)
while(tokenStream.incrementToken()) {//移动到下一个token。已到TokenStream末尾，返回false
System.out.println("----------CharTermAttribute----------");
System.out.println("词语："+termAtt.toString());
System.out.println("----------OffsetAttribute----------");
System.out.println("token: " + tokenStream.reflectAsString(false));
System.out.println("\ttoken开始偏移量: " + offsetAtt.startOffset());
System.out.println("\ttoken结束偏移量: " + offsetAtt.endOffset());
}
} catch (Exception e) {
e.printStackTrace();
} finally {
tokenStream.end();//到达TokenStream末尾后调用end(). Perform end-of-stream operations, e.g. set the final offset.
tokenStream.close();//释放与流有关的资源
}

}

/**
*
* getFsIndexDirectory 获取索引库的Directory
*
* @Description
* @return Directory
* @see
*/
private Directory getFsIndexDirectory() {
try {
return FSDirectory.open(FileSystems.getDefault().getPath(indexDir));//基于磁盘的索引库，也可以基于内存：Directory directory = new RAMDirectory();
} catch (IOException e) {
throw new RuntimeException(e);
}
}
}

 使用到的工具类：

package demo.mytest.lucene.utils;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;

import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;

/**
*
* LuceneUtils 工具类
*
*/
public class LuceneUtils {

/**
*
* file2Document 将文件转换成文档对象
*
* @Description
* @param path
* @return
* @throws Exception Document
* @see
*/
public static Document file2Document(String path) throws Exception {
File file = new File(path);
Document doc = new Document();
doc.add(new Field("fileName", file.getName(), TextField.TYPE_STORED));
doc.add(new Field("content", getFileContent(file),TextField.TYPE_STORED));
doc.add(new Field("fileSize", String.valueOf(file.getTotalSpace()), TextField.TYPE_STORED));
doc.add(new Field("path", file.getAbsolutePath(),TextField.TYPE_STORED));
//doc.add(new Field("fileName",String.valueOf(file.getName()),Store.YES, Index.ANALYZED));
System.out.println(file.getAbsolutePath()+"\t"+file.isDirectory()+"\n"+getFileContent(file));
doc.add(new Field("isDirectory",String.valueOf(file.isDirectory()),TextField.TYPE_STORED));

return doc;
}

/**
*
* printDocumentInfo 打印文档对象信息
*
* @Description 打印文档对象信息
* @param document 文档对象
* void
* @see
*/
public static void printDocumentInfo(Document document) {
//		IndexableField field = document.getField("fileName");
//		System.out.println(field.name() + ":" +field.stringValue());//结果---fileName:CHANGES.txt。此处的document.getField("fileName").stringValue()相当于document.get("fileName")
//打印文档对象信息
System.out.println("文档（"+document.get("fileName")+"）的信息-"
+"内容："+document.get("content")+"\t存储位置："+document.get("path")
+"\t文件大小：" + document.get("fileSize") +"\t是否为文件夹："+ document.get("isDirectory"));
}

/**
*
* getFileContent 取得文件内容
*
* @Description
* @param file
* @return
* @throws Exception String
* @see
*/
private static String getFileContent(File file) throws Exception {
StringBuffer sbf = new StringBuffer();
BufferedReader br = new BufferedReader(new FileReader(file));
String line = null;
while ((line = br.readLine()) != null) {
sbf.append(line).append("\n");
}
br.close();
return sbf.toString();
}
}