lucene是一款不错的针对搞全文搜索的API,可以结合JAVA使用,但在用lucene 2.0时,如果参考目前的一些文章,可能会有一些API是过期了,我在看一些讲lucene的文章时,就遇到这类的情况,于是经过查找,发现有如下的一些要注意的地方。
Field.Text(java.lang.String, java.io.Reader)
用new Field(java.lang.String, java.io.Reader)代替
Field.Keyword(java.lang.String, java.lang.String)
用
Field.Keyword(java.lang.String, java.lang.String)
代替
Query query = QueryParser.parse(q, "contents", new StandardAnalyzer ());
用
QueryParser parser = new QueryParser("contents", new StandardAnalyzer ());
Query query = parser.parse(q);
代替
因此,再摘录一个命令行方式下的简单lucene程序,来自IBM DW,效果是先对某目录下的TXT文件建立索引,然后再排序
建立索引的程序:
import java.io.File;
import java.io.FileReader;
import java.io.Reader;
import java.util.Date;
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.index.IndexWriter;
/**
* This class demonstrate the process of creating index with Lucene
* for text files
*/
public class TxtFileIndexer {
public static void main(String[] args) throws Exception{
//indexDir is the directory that hosts Lucene's index files
File indexDir = new File("D:\\luceneIndex");
//dataDir is the directory that hosts the text files that to be indexed
File dataDir = new File("D:\\luceneData");
Analyzer luceneAnalyzer = new StandardAnalyzer();
File[] dataFiles = dataDir.listFiles();
IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,true);
long startTime = new Date().getTime();
for(int i = 0; i < dataFiles.length; i++){
if(dataFiles[i].isFile() && dataFiles[i].getName().endsWith(".txt")){
System.out.println("Indexing file " + dataFiles[i].getCanonicalPath());
Document document = new Document();
Reader txtReader = new FileReader(dataFiles[i]);
document.add(new Field("path",dataFiles[i].getPath(),Field.Store.YES,Field.Index.NO));
document.add(new Field("contents",txtReader));
indexWriter.addDocument(document);
}
}
indexWriter.optimize();
indexWriter.close();
long endTime = new Date().getTime();
System.out.println("It takes " + (endTime - startTime)
+ " milliseconds to create index for the files in directory "
+ dataDir.getPath());
}
}
搜索的程序
import java.io.File;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.store.FSDirectory;
/**
* This class is used to demonstrate the
* process of searching on an existing
* Lucene index
*
*/
public class TxtFileSearcher {
public static void main(String[] args) throws Exception{
String queryStr = "我";
//This is the directory that hosts the Lucene index
File indexDir = new File("D:\\luceneIndex");
FSDirectory directory = FSDirectory.getDirectory(indexDir,false);
IndexSearcher searcher = new IndexSearcher(directory);
if(!indexDir.exists()){
System.out.println("The Lucene index is not exist");
return;
}
Term term = new Term("contents",queryStr.toLowerCase());
TermQuery luceneQuery = new TermQuery(term);
Hits hits = searcher.search(luceneQuery);
System.out.println("his result is"+hits.length());
for(int i = 0; i < hits.length(); i++){
Document document = hits.doc(i);
System.out.println("File: " + document.get("path"));
}
}
}