자바 키워드 전체 텍스트 검색 인 스 턴 스
18080 단어 lucene
package javaLucene;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileReader;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
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.Store;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
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.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
public class TestLucene {
private static TestLucene indexManager;
private static String content="";
private static String INDEX_DIR = "G:\\Unity3dziyuan";
private static String DATA_DIR = "G:\\Unity3dziyuan";
private static Analyzer analyzer = null;
private static Directory directory = null;
private static IndexWriter indexWriter = null;
/**
*
* @return
*/
public TestLucene getManager(){
if(indexManager == null){
this.indexManager = new TestLucene();
}
return indexManager;
}
/**
*
* @param path
* @return
*/
public static boolean createIndex(String path){
Date date1 = new Date();
List fileList = getFileList(path);
for (File file : fileList) {
content = "";
//
String type = file.getName().substring(file.getName().lastIndexOf(".")+1);
if("txt".equalsIgnoreCase(type)){
content += txt2String(file);
}else if("doc".equalsIgnoreCase(type)){
content += doc2String(file);
}else if("xls".equalsIgnoreCase(type)){
content += xls2String(file);
}
System.out.println("name :"+file.getName());
System.out.println("path :"+file.getPath());
// System.out.println("content :"+content);
System.out.println();
try{
analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
directory = FSDirectory.open(new File(INDEX_DIR));
File indexFile = new File(INDEX_DIR);
if (!indexFile.exists()) {
indexFile.mkdirs();
}
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_CURRENT, analyzer);
indexWriter = new IndexWriter(directory, config);
Document document = new Document();
document.add(new TextField("filename", file.getName(), Store.YES));
document.add(new TextField("content", content, Store.YES));
document.add(new TextField("path", file.getPath(), Store.YES));
indexWriter.addDocument(document);
indexWriter.commit();
closeWriter();
}catch(Exception e){
e.printStackTrace();
}
content = "";
}
Date date2 = new Date();
System.out.println(" ----- :" + (date2.getTime() - date1.getTime()) + "ms
");
return true;
}
/**
* txt
* @param file
* @return
*/
public static String txt2String(File file){
String result = "";
try{
BufferedReader br = new BufferedReader(new FileReader(file));// BufferedReader
String s = null;
while((s = br.readLine())!=null){// readLine ,
result = result + "
" +s;
}
br.close();
}catch(Exception e){
e.printStackTrace();
}
return result;
}
/**
* doc
* @param file
* @return
*/
public static String doc2String(File file){
String result = "";
try{
FileInputStream fis = new FileInputStream(file);
HWPFDocument doc = new HWPFDocument(fis);
Range rang = doc.getRange();
result += rang.text();
fis.close();
}catch(Exception e){
e.printStackTrace();
}
return result;
}
/**
* xls
* @param file
* @return
*/
public static String xls2String(File file){
String result = "";
try{
FileInputStream fis = new FileInputStream(file);
StringBuilder sb = new StringBuilder();
jxl.Workbook rwb = Workbook.getWorkbook(fis);
Sheet[] sheet = rwb.getSheets();
for (int i = 0; i < sheet.length; i++) {
Sheet rs = rwb.getSheet(i);
for (int j = 0; j < rs.getRows(); j++) {
Cell[] cells = rs.getRow(j);
for(int k=0;kcatch(Exception e){
e.printStackTrace();
}
return result;
}
/**
* ,
* @param text
* @return List
*/
public static void searchIndex(String text){
Date date1 = new Date();
try{
directory = FSDirectory.open(new File(INDEX_DIR));
analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
DirectoryReader ireader = DirectoryReader.open(directory);
IndexSearcher isearcher = new IndexSearcher(ireader);
QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, "content", analyzer);
Query query = parser.parse(text);
ScoreDoc[] hits = isearcher.search(query, null, 1000).scoreDocs;
for (int i = 0; i < hits.length; i++) {
Document hitDoc = isearcher.doc(hits[i].doc);
System.out.println("____________________________");
System.out.println(hitDoc.get("filename"));
System.out.println(hitDoc.get("content"));
System.out.println(hitDoc.get("path"));
System.out.println("____________________________");
}
ireader.close();
directory.close();
}catch(Exception e){
e.printStackTrace();
}
Date date2 = new Date();
System.out.println(" ----- :" + (date2.getTime() - date1.getTime()) + "ms
");
}
/**
*
* @param dirPath
* @return list
*/
public static List getFileList(String dirPath) {
File[] files = new File(dirPath).listFiles();
List fileList = new ArrayList();
for (File file : files) {
if (isTxtFile(file.getName())) {
fileList.add(file);
}
}
return fileList;
}
/**
* , txt xls doc
* @param fileName
* @return , true; false
*/
public static boolean isTxtFile(String fileName) {
if (fileName.lastIndexOf(".txt") > 0) {
return true;
}else if (fileName.lastIndexOf(".xls") > 0) {
return true;
}else if (fileName.lastIndexOf(".doc") > 0) {
return true;
}
return false;
}
public static void closeWriter() throws Exception {
if (indexWriter != null) {
indexWriter.close();
}
}
/**
*
* @param file
* @return , true.
*/
public static boolean deleteDir(File file){
if(file.isDirectory()){
File[] files = file.listFiles();
for(int i=0; ireturn true;
}
public static void main(String[] args){
//File fileIndex = new File(INDEX_DIR);
/*if(deleteDir(fileIndex)){
fileIndex.mkdir();
}else{
fileIndex.mkdir();
}*/
createIndex(DATA_DIR);
searchIndex("man");
}
}
이 내용에 흥미가 있습니까?
현재 기사가 여러분의 문제를 해결하지 못하는 경우 AI 엔진은 머신러닝 분석(스마트 모델이 방금 만들어져 부정확한 경우가 있을 수 있음)을 통해 가장 유사한 기사를 추천합니다:
자바 키워드 전체 텍스트 검색 인 스 턴 스package javaLucene; import java.io.BufferedReader; import java.io.File; import java.io.FileInputStream; import java.io.F...
텍스트를 자유롭게 공유하거나 복사할 수 있습니다.하지만 이 문서의 URL은 참조 URL로 남겨 두십시오.
CC BY-SA 2.5, CC BY-SA 3.0 및 CC BY-SA 4.0에 따라 라이센스가 부여됩니다.