示例应用
为了测试索引过程，我们需要创建一个 Lucene 应用程序测试。
| 步 |
描述 |
| 1 |
创建一个名称的项目LuceneFirstApplication一个包下com.jc2182.lucene作为解释Lucene的-第一个应用程序的章节。您还可以使用在EJB - First Application章节中创建的项目来理解本章的索引过程。
|
| 2 |
创建LuceneConstants.java，TextFileFilter.java和Indexer.java作为解释Lucene的-第一个应用程序的章节。保持其余文件不变。
|
| 3 |
如下所述创建LuceneTester.java。
|
| 4 |
清理并构建应用程序以确保业务逻辑按照要求工作。
|
LuceneConstants.java
此类用于提供要在整个示例应用程序中使用的各种常量。
package com.jc2182.lucene;
public class LuceneConstants {
public static final String CONTENTS = "contents";
public static final String FILE_NAME = "filename";
public static final String FILE_PATH = "filepath";
public static final int MAX_SEARCH = 10;
}
TextFileFilter.java
此类用作 .txt 文件过滤器。
package com.jc2182.lucene;
import java.io.File;
import java.io.FileFilter;
public class TextFileFilter implements FileFilter {
@Override
public boolean accept(File pathname) {
return pathname.getName().toLowerCase().endsWith(".txt");
}
}
Indexer.java
此类用于索引原始数据，以便我们可以使用 Lucene 库对其进行搜索。
package com.jc2182.lucene;
import java.io.File;
import java.io.FileFilter;
import java.io.FileReader;
import java.io.IOException;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
public class Indexer {
private IndexWriter writer;
public Indexer(String indexDirectoryPath) throws IOException {
//this directory will contain the indexes
Directory indexDirectory =
FSDirectory.open(new File(indexDirectoryPath));
//create the indexer
writer = new IndexWriter(indexDirectory,
new StandardAnalyzer(Version.LUCENE_36),true,
IndexWriter.MaxFieldLength.UNLIMITED);
}
public void close() throws CorruptIndexException, IOException {
writer.close();
}
private Document getDocument(File file) throws IOException {
Document document = new Document();
//index file contents
Field contentField = new Field(LuceneConstants.CONTENTS,
new FileReader(file));
//index file name
Field fileNameField = new Field(LuceneConstants.FILE_NAME,
file.getName(),
Field.Store.YES,Field.Index.NOT_ANALYZED);
//index file path
Field filePathField = new Field(LuceneConstants.FILE_PATH,
file.getCanonicalPath(),
Field.Store.YES,Field.Index.NOT_ANALYZED);
document.add(contentField);
document.add(fileNameField);
document.add(filePathField);
return document;
}
private void indexFile(File file) throws IOException {
System.out.println("Indexing "+file.getCanonicalPath());
Document document = getDocument(file);
writer.addDocument(document);
}
public int createIndex(String dataDirPath, FileFilter filter)
throws IOException {
//get all files in the data directory
File[] files = new File(dataDirPath).listFiles();
for (File file : files) {
if(!file.isDirectory()
&& !file.isHidden()
&& file.exists()
&& file.canRead()
&& filter.accept(file)
){
indexFile(file);
}
}
return writer.numDocs();
}
}
LuceneTester.java
该类用于测试 Lucene 库的索引能力。
package com.jc2182.lucene;
import java.io.IOException;
public class LuceneTester {
String indexDir = "E:\\Lucene\\Index";
String dataDir = "E:\\Lucene\\Data";
Indexer indexer;
public static void main(String[] args) {
LuceneTester tester;
try {
tester = new LuceneTester();
tester.createIndex();
} catch (IOException e) {
e.printStackTrace();
}
}
private void createIndex() throws IOException {
indexer = new Indexer(indexDir);
int numIndexed;
long startTime = System.currentTimeMillis();
numIndexed = indexer.createIndex(dataDir, new TextFileFilter());
long endTime = System.currentTimeMillis();
indexer.close();
System.out.println(numIndexed+" File indexed, time taken: "
+(endTime-startTime)+" ms");
}
}
