package lucene;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.util.Date;
import java.util.Scanner;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.cn.ChineseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
public class IndexTest {
public static String indexDir = "data\\lucene\\luceneIndex";
public static String dataDir = "data\\lucene\\luceneData";
public static void main(String[] args) throws ParseException, IOException {
// indexDir is the directory that hosts Lucene's index files
makeIndex(indexDir, dataDir);
while(true){
System.out.print("輸入搜索關鍵字:");
Scanner sca = new Scanner(System.in);
String queryStr = sca.next();
if (queryStr!=null) {
if ("0".equals(queryStr)) {
System.exit(0);
}
search1(queryStr, indexDir);
}
}
}
public static void makeIndex(String indexDirStr,String dataDirStr) throws IOException{
File indexDir = new File(indexDirStr);
// dataDir is the directory that hosts the text files that to be indexed
File dataDir = new File(dataDirStr);
// Analyzer luceneAnalyzer = new StandardAnalyzer();
File[] dataFiles = dataDir.listFiles();
//IndexWriter indexWriter = new IndexWriter(indexDir, luceneAnalyzer,true);
IndexWriter indexWriter = new IndexWriter(indexDir, new ChineseAnalyzer(), true);
long startTime = System.currentTimeMillis();
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(Field.Text("path", dataFiles[i].getCanonicalPath()));
document.add(Field.Text("contents", txtReader));
indexWriter.addDocument(document);
}
}
indexWriter.optimize();
indexWriter.close();
long endTime = System.currentTimeMillis();
System.out.println("It takes " + (endTime - startTime)
+ " milliseconds to create index for the files in directory "
+ dataDir.getPath());
}
public static int search2(String qc, String indexDirStr) throws ParseException, IOException {
// 从索引目录创建索引
IndexSearcher _searcher = new IndexSearcher(indexDirStr);
// 创建标准分析器
Analyzer analyzer = new ChineseAnalyzer();
// 查询条件
String line = qc;
// Query是一个抽象类
Query query = QueryParser.parse(line, "contents", analyzer);
Hits hits = _searcher.search(query);
_searcher.close();
return hits.length();
}
public static void search1(String qc, String indexDirStr) throws ParseException, IOException {
// 从索引目录创建索引
IndexSearcher _searcher = new IndexSearcher(indexDirStr);
// 创建标准分析器
Analyzer analyzer = new ChineseAnalyzer();
// 查询条件
String line = qc;
// Query是一个抽象类
Query query = QueryParser.parse(line, "contents", analyzer);
Hits hits = _searcher.search(query);
System.out.println(" 总共找到[" + hits.length() + "]条匹配記錄");
final int HITS_PER_PAGE = 1;
for (int start = 0; start < hits.length(); start += HITS_PER_PAGE) {
int end = Math.min(hits.length(), start + HITS_PER_PAGE);
for (int i = start; i < end; i++) {
Document doc = hits.doc(i);
String path = doc.get("path");
if (path != null) {
System.out.println("File: " + doc.get("path"));
System.out.println(doc.get("contents"));
} else {
System.out.println("没有找到！");
}
}
}
_searcher.close();
}
}