package com.icrate.service.study.demo;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
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.search.highlight.Formatter;
import org.apache.lucene.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.Scorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;
/**
*
* LuenceProcess.java
*
* @version : 1.1
*
*
* @since : 1.0 創建時間: Apr 3, 2013 11:48:11 AM
*
* TODO : Luence中使用IK分詞器
*
*/
public class LuceneIKUtil {
private Directory directory ;
private Analyzer analyzer ;
/**
* 帶參數構造,參數用來指定索引文件目錄
* @param indexFilePath
*/
public LuceneIKUtil(String indexFilePath){
try {
directory = FSDirectory.open(new File(indexFilePath));
analyzer = new IKAnalyzer();
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 默認構造,使用系統默認的路徑作爲索引
*/
public LuceneIKUtil(){
this("/luence/index");
}
/**
* 創建索引
* Description:
* @throws Exception
*/
public void createIndex()throws Exception{
IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_35,analyzer);
IndexWriter indexWriter = new IndexWriter(directory,indexWriterConfig);
indexWriter.deleteAll();
List<Medicine> list = DataFactory.getInstance().getData();
for(int i=0; i<list.size(); i++){
Medicine medicine = list.get(i);
Document document = addDocument(medicine.getId(), medicine.getName(), medicine.getFunction());
indexWriter.addDocument(document);
}
indexWriter.close();
}
/**
*
* Description:
* @param id
* @param title
* @param content
* @return
*/
public Document addDocument(Integer id, String name, String function){
Document doc = new Document();
//Field.Index.NO 表示不索引
//Field.Index.ANALYZED 表示分詞且索引
//Field.Index.NOT_ANALYZED 表示不分詞且索引
doc.add(new Field("id",String.valueOf(id),Field.Store.YES,Field.Index.NOT_ANALYZED));
doc.add(new Field("name",name,Field.Store.YES,Field.Index.ANALYZED));
doc.add(new Field("function",function,Field.Store.YES,Field.Index.ANALYZED));
return doc;
}
/**
*
* Description: 更新索引
* @param id
* @param title
* @param content
*/
public void update(Integer id,String title, String content){
try {
IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_35,analyzer);
IndexWriter indexWriter = new IndexWriter(directory,indexWriterConfig);
Document document = addDocument(id, title, content);
Term term = new Term("id",String.valueOf(id));
indexWriter.updateDocument(term, document);
indexWriter.close();
} catch (Exception e) {
e.printStackTrace();
}
}
/**
*
* Description:按照ID進行索引
* @param id
*/
public void delete(Integer id){
try {
IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_35,analyzer);
IndexWriter indexWriter = new IndexWriter(directory,indexWriterConfig);
Term term = new Term("id",String.valueOf(id));
indexWriter.deleteDocuments(term);
indexWriter.close();
} catch (Exception e) {
e.printStackTrace();
}
}
/**
*
* Description:查詢
* @param where 查詢條件
* @param scoreDoc 分頁時用
*/
public List<Medicine> search(String[] fields,String keyword){
IndexSearcher indexSearcher = null;
List<Medicine> result = new ArrayList<Medicine>();
try {
//創建索引搜索器,且只讀
IndexReader indexReader = IndexReader.open(directory,true);
indexSearcher = new IndexSearcher(indexReader);
MultiFieldQueryParser queryParser =new MultiFieldQueryParser(Version.LUCENE_35, fields,analyzer);
Query query = queryParser.parse(keyword);
//返回前number條記錄
TopDocs topDocs = indexSearcher.search(query, 10);
//信息展示
int totalCount = topDocs.totalHits;
System.out.println("共檢索出 "+totalCount+" 條記錄");
//高亮顯示
/*
創建高亮器,使搜索的結果高亮顯示
SimpleHTMLFormatter:用來控制你要加亮的關鍵字的高亮方式
此類有2個構造方法
1:SimpleHTMLFormatter()默認的構造方法.加亮方式:<B>關鍵字</B>
2:SimpleHTMLFormatter(String preTag, String postTag).加亮方式:preTag關鍵字postTag
*/
Formatter formatter = new SimpleHTMLFormatter("<font color='red'>","</font>");
/*
QueryScorer
QueryScorer 是內置的計分器。計分器的工作首先是將片段排序。QueryScorer使用的項是從用戶輸入的查詢中得到的;
它會從原始輸入的單詞、詞組和布爾查詢中提取項,並且基於相應的加權因子(boost factor)給它們加權。
爲了便於QueryScoere使用,還必須對查詢的原始形式進行重寫。
比如,帶通配符查詢、模糊查詢、前綴查詢以及範圍查詢 等,都被重寫爲BoolenaQuery中所使用的項。
在將Query實例傳遞到QueryScorer之前,可以調用Query.rewrite (IndexReader)方法來重寫Query對象
*/
Scorer fragmentScorer = new QueryScorer(query);
Highlighter highlighter = new Highlighter(formatter,fragmentScorer);
Fragmenter fragmenter = new SimpleFragmenter(100);
/*
Highlighter利用Fragmenter將原始文本分割成多個片段。
內置的SimpleFragmenter將原始文本分割成相同大小的片段,片段默認的大小爲100個字符。這個大小是可控制的。
*/
highlighter.setTextFragmenter(fragmenter);
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for(ScoreDoc scDoc : scoreDocs){
Document document = indexSearcher.doc(scDoc.doc);
Integer id = Integer.parseInt(document.get("id"));
String name = document.get("name");
String function = document.get("function");
//float score = scDoc.score; //相似度
String lighterName = highlighter.getBestFragment(analyzer, "name", name);
if(null==lighterName){
lighterName = name;
}
String lighterFunciton = highlighter.getBestFragment(analyzer, "function", function);
if(null==lighterFunciton){
lighterFunciton = function;
}
Medicine medicine = new Medicine();
medicine.setId(id);
medicine.setName(lighterName);
medicine.setFunction(lighterFunciton);
result.add(medicine);
}
} catch (Exception e) {
e.printStackTrace();
}finally{
try {
indexSearcher.close();
} catch (IOException e) {
e.printStackTrace();
}
}
return result;
}
public static void main(String[] args) {
LuceneIKUtil luceneProcess = new LuenceIKUtil("F:/index");
try {
luceneProcess.createIndex();
} catch (Exception e) {
e.printStackTrace();
}
//修改測試
luceneProcess.update(2, "測試內容", "修改測試。。。");
//查詢測試
String [] fields = {"name","function"};
List<Medicine> list = luenceProcess.search(fields,"感冒");
for(int i=0; i<list.size(); i++){
Medicine medicine = list.get(i);
System.out.println("("+medicine.getId()+")"+medicine.getName() + "\t" + medicine.getFunction());
}
//刪除測試
//luenceProcess.delete(1);
}
}