Lucene5学习之创建索引入门示例
Lucene更新实在太快了，只好紧跟脚步开始学习Lucene5,花了点时间写了一个demo，就是程序根据用户提供的一个文件夹，读取该文件夹下的所有文件，然后读取文件里的内容写入索引。读取文件部分采用的是最新的NIO2.0API,因此，JDK必须使用1.7及以上版本。Lucene5开发压缩包请在Lucene官网下载。不多说了，对于码农来说，最直接的就是上代码。
package com.yida.framework.lucene5.core;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.nio.charset.StandardCharsets;
import java.nio.file.FileVisitResult;
import java.nio.file.Files;
import java.nio.file.LinkOption;
import java.nio.file.OpenOption;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.nio.file.SimpleFileVisitor;
import java.nio.file.attribute.BasicFileAttributes;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.LongField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
/**
* 读取硬盘文件，创建索引
*
* @author Lanxiaowei
*
*/
@SuppressWarnings({ "unchecked", "unused", "rawtypes" })
public class IndexFile {
public static void main(String[] args) throws IOException {
String dirPath = "D:/docPath";
String indexPath = "D:/lucenedir";
createIndex(dirPath, indexPath);
}
/**
* 创建索引
* @param dirPath 需要读取的文件所在文件目录
* @param indexPath 索引存放目录
* @throws IOException
*/
public static void createIndex(String dirPath, String indexPath) throws IOException {
createIndex(dirPath, indexPath, false);
}
/**
* 创建索引
* @param dirPath 需要读取的文件所在文件目录
* @param indexPath 索引存放目录
* @param createOrAppend 始终重建索引/不存在则追加索引
* @throws IOException
*/
public static void createIndex(String dirPath, String indexPath,
boolean createOrAppend) throws IOException {
long start = System.currentTimeMillis();
Directory dir = FSDirectory.open(Paths.get(indexPath, new String[0]));
Path docDirPath = Paths.get(dirPath, new String[0]);
Analyzer analyzer = new StandardAnalyzer();
IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
if (createOrAppend) {
indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
} else {
indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
}
IndexWriter writer = new IndexWriter(dir, indexWriterConfig);
indexDocs(writer, docDirPath);
writer.close();
long end = System.currentTimeMillis();
System.out.println("Time consumed:" + (end - start) + " ms");
}
/**
*
* @param writer
* 索引写入器
* @param path
* 文件路径
* @throws IOException
*/
public static void indexDocs(final IndexWriter writer, Path path)
throws IOException {
// 如果是目录，查找目录下的文件
if (Files.isDirectory(path, new LinkOption[0])) {
System.out.println("directory");
Files.walkFileTree(path, new SimpleFileVisitor() {
@Override
public FileVisitResult visitFile(Object file,
BasicFileAttributes attrs) throws IOException {
Path path = (Path)file;
System.out.println(path.getFileName());
indexDoc(writer, path, attrs.lastModifiedTime().toMillis());
return FileVisitResult.CONTINUE;
}
});
} else {
indexDoc(writer, path,
Files.getLastModifiedTime(path, new LinkOption[0])
.toMillis());
}
}
/**
* 读取文件创建索引
*
* @param writer
* 索引写入器
* @param file
* 文件路径
* @param lastModified
* 文件最后一次修改时间
* @throws IOException
*/
public static void indexDoc(IndexWriter writer, Path file, long lastModified)
throws IOException {
InputStream stream = Files.newInputStream(file, new OpenOption[0]);
Document doc = new Document();
Field pathField = new StringField("path", file.toString(),
Field.Store.YES);
doc.add(pathField);
doc.add(new LongField("modified", lastModified, Field.Store.NO));
doc.add(new TextField("contents", new BufferedReader(
new InputStreamReader(stream, StandardCharsets.UTF_8))));
if (writer.getConfig().getOpenMode() == IndexWriterConfig.OpenMode.CREATE) {
System.out.println("adding " + file);
writer.addDocument(doc);
} else {
System.out.println("updating " + file);
writer.updateDocument(new Term("path", file.toString()), doc);
}
writer.commit();
}
}
项目采用的是Maven构建，怎么创建Maven Project就不用介绍了吧，我就贴下pom配置吧。
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.yida.framework</groupId>
<artifactId>lucene5</artifactId>
<packaging>war</packaging>
<version>1.0</version>
<name>lucene5 Maven Webapp</name>
<url>http://maven.apache.org</url>
<properties>
<lucene.version>5.0.0</lucene.version>
</properties>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-core</artifactId>
<version>${lucene.version}</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-analyzers-common</artifactId>
<version>${lucene.version}</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-queryparser</artifactId>
<version>${lucene.version}</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-highlighter</artifactId>
<version>${lucene.version}</version>
</dependency>
</dependencies>
<build>
<finalName>lucene5</finalName>
</build>
</project>
项目结构图如图：
运行之前，先在D盘新建两个文件夹，如图：
然后在docPath文件夹里随便放几个文本文件，如图：
然后运行测试类，就会在lucenedir文件夹下创建索引。
代码很简单，没什么需要过多解释的，demo源码请在附件里下载。
希望能对大家学习Lucene有所帮助，其次也算是对自己学习轨迹的一个记录，写博客这个习惯
我会努力保持下去。
转自http://iamyida.iteye.com/blog/2192938