Lucene 入门示范
Lucene 入门示例
通过敲写着连个例子，大概了解了lucene 的核心类以及主要api 的功能。
package Demo;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
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.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.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
public class IndexFiles {
private IndexFiles(){}
/**Index all text files under a directory **/
/**
* @param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub
String usage = "java org.apache.lucene.demo.IndexFiles"
+ " [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\n"
+ "This indexes the documents in DOCS_PATH, creating a Lucene index"
+ "in INDEX_PATH that can be searched with SearchFiles";
String indexPath = "index";
String docsPath = args[0];
boolean create = true;
if(docsPath==null)
{
System.err.println("input the docsPath");
System.exit(1);
}
final File docDir = new File(docsPath);
if(!docDir.exists()||!docDir.canRead())
{
System.out.println("Document directory '" +docDir.getAbsolutePath()+ "' does not exist or is not readable, please check the path");
System.exit(1);
}
Date start = new Date();
try{
// System.out.println("Indexing to directory '")
Directory dir =FSDirectory.open(new File(indexPath));
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_40, analyzer);
if(create)
{
iwc.setOpenMode(OpenMode.CREATE);
}
else {
iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
}
IndexWriter writer = new IndexWriter(dir, iwc);
indexDocs(writer, docDir);
writer.close();
Date end = new Date();
System.out.println(end.getTime()-start.getTime() + "total milliseconds");
}catch(IOException e)
{
System.out.println("caught a "+ e.getClass()+
"\n with message:" + e.getMessage());
}
}
/**
* do not try to index files that cannot be read
* @throws IOException
*/
static void indexDocs(IndexWriter writer,File file) throws IOException
{
if(file.canRead())
{
if(file.isDirectory())
{
String[] files = file.list();
if(files != null){
for(int i = 0;i < files.length;i++)
{
indexDocs(writer,new File(file,files[i]));
}
}
}
else{
FileInputStream fis;
fis = new FileInputStream(file);
try{
//make a new ,empty document
Document doc = new Document();
Field pathField = new StringField("path", file.getPath(), Field.Store.YES);
doc.add(pathField);
doc.add(new LongField("modified", file.lastModified(), Field.Store.NO));
doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(fis,"UTF-8"))));
if(writer.getConfig().getOpenMode()==OpenMode.CREATE)
{
//new index so we just add the document (no old document can be there)
System.out.println("adding " + file);
writer.addDocument(doc);
}
else
{
//Existing index (an old copy of the document may have been indexed)
// so we use updataDocument instead to replace the old one matching
//the exact path,if present
System.out.println("updating " + file);
writer.updateDocument(new Term("path", file.getPath()), doc);
}
}finally{
fis.close();
}
}
}
}
}
package Demo;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.nio.Buffer;
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.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
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.TopDocs;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.xml.sax.InputSource;
public class Searchfiles {
/**
* @param args
* @throws IOException
* @throws ParseException
*/
public static void main(String[] args) throws IOException, ParseException {
// TODO Auto-generated method stub
String index = "index";
String field = "contents";
String queries = null;
int repeat = 0;
boolean raw = false;
String queryString = null;
int hitsPerPage = 10;
// 打开索引所在的文件夹
IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index)));
//根据indexReader 打开的索引文件 建立检索
IndexSearcher searcher = new IndexSearcher(reader);
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);
BufferedReader in = null;
if(queries != null)
{
in = new BufferedReader(new InputStreamReader(new FileInputStream(queries),"UTF-8"));
}
else {
in = new BufferedReader(new InputStreamReader(System.in,"UTF-8"));
}
QueryParser parser = new QueryParser(Version.LUCENE_40, field, analyzer);
while(true)
{
if(queries == null && queryString == null)
{
System.out.println("Enter query: ");
}
String line = queryString !=null ? queryString : in.readLine();
if(line==null || line.length()== -1)break;
line = line.trim();
if(line.length()==0)break;
Query query = parser.parse(line);
System.out.println("Searching for : " + query.toString(field));
if(repeat > 0) //repeat & time as benchmark
{
Date start = new Date();
for(int i =0 ;i < repeat;i++)
searcher.search(query, null,100);
Date end = new Date();
System.out.println("Time: + " +(end.getTime() - start.getTime()) + "ms.");
}
doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString==null);
if(queryString == null)break;
}
}
public static void doPagingSearch(BufferedReader in , IndexSearcher searcher,
Query query,int hitsPerPage,boolean raw ,boolean interactive ) throws IOException
{
// Collect enough docs to show 5 pages
TopDocs results = searcher.search(query, 5*hitsPerPage);
ScoreDoc[] hits =results.scoreDocs;
int numTotalHits = results.totalHits;
System.out.println(numTotalHits + " total matching documents");
int start = 0;
int end = Math.min(numTotalHits, hitsPerPage);
while(true)
{
if(end > hits.length){
System.out.println("Only results 1 - "+ hits.length
+ " of" + numTotalHits + "total matching documents collected .");
System.out.println("Collect more (y/n)?");
String line = in.readLine();
if(line.length()==0||line.charAt(0)=='n')
{
break;
}
hits =searcher.search(query, numTotalHits).scoreDocs;
}
end = Math.min(hits.length, start+hitsPerPage);
for(int i = start; i < end ;i++)
{
if(raw) // output raw format
{
System.out.println("doc="+hits[i].doc + " score= " + hits[i].score);
continue;
}
Document doc = searcher.doc(hits[i].doc);
String path = doc.get("path");
if(path!=null)
{
System.out.println((i+1)+"."+path);
String title = doc.get("title");
if(title!=null)
{
System.out.println(" Title:" + doc.get("title"));
}
}else{
System.out.println((i+1) + "." + "No path for this document");
}
}
if(!interactive || end==0)
{
break;
}
if(numTotalHits >= end)
{
boolean quit = false;
while(true)
{
System.out.print("Press ");
if(start - hitsPerPage >=0)
{
System.out.print("<p>revious page, ");
}
if(start + hitsPerPage < numTotalHits)
{
System.out.print("(n)ext page, ");
}
System.out.print("(q) uit or enter number to jump to a page.");
String line = in.readLine();
if(line.length()==0||line.charAt(0)=='q')
{
quit = true;
break;
}
if(line.charAt(0)=='p')
{
start = Math.max(0, start - hitsPerPage);
break;
}else if(line.charAt(0)=='n'){
if(start+hitsPerPage < numTotalHits)
start+=hitsPerPage;
break;
}else{
int page = Integer.parseInt(line);
if((page - 1)*hitsPerPage < numTotalHits){
start = (page -1 )*hitsPerPage;
break;
}
else {
System.out.println("No such page!");
}
}
}
if(quit)break;
end = Math.min(numTotalHits, start+hitsPerPage);
}
}
}
}