【Lucene3.6.2入門系列】第03節_簡述Lucene中常見的搜索功能

package com.jadyer.lucene;

import java.io.File;
import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.NumericField;
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.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.NumericRangeQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

/**
 * 【Lucene3.6.2入門系列】第03節_簡述Lucene中常見的搜索功能
 * @create Aug 1, 2013 3:54:27 PM
 * @author 玄玉<http://blog.csdn.net/jadyer>
 */
public class HelloSearch {
    private Directory directory;
    private IndexReader reader;
    private String[] ids = {"1", "2", "3", "4", "5", "6"};
    private String[] names = {"Michael", "Scofield", "Tbag", "Jack", "Jade", "Jadyer"};
    private String[] emails = {"[email protected]", "[email protected]", "[email protected]", "[email protected]", "[email protected]", "[email protected]"};
    private String[] contents = {"my java blog is http://blog.csdn.net/jadyer", "my website is http://www.jadyer.cn", "my name is jadyer", "I am JavaDeveloper", "I am from Haerbin", "I like Lucene"};
    private int[] attachs = {9,3,5,4,1,2};
    private Date[] dates = new Date[ids.length];

    public HelloSearch(){
        IndexWriter writer = null;
        Document doc = null;
        SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd");
        try {
            dates[0] = sdf.parse("20120601");
            dates[1] = sdf.parse("20120603");
            dates[2] = sdf.parse("20120605");
            dates[3] = sdf.parse("20120607");
            dates[4] = sdf.parse("20120609");
            dates[5] = sdf.parse("20120611");
            directory = FSDirectory.open(new File("myExample/03_index/"));
            writer = new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_36, new StandardAnalyzer(Version.LUCENE_36)));
            writer.deleteAll();              //創建索引之前,先把文檔清空掉
            for(int i=0; i<ids.length; i++){ //遍歷ID來創建文檔
                doc = new Document();
                doc.add(new Field("id", ids[i], Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
                doc.add(new Field("name", names[i], Field.Store.YES, Field.Index.ANALYZED_NO_NORMS));
                doc.add(new Field("email", emails[i], Field.Store.YES, Field.Index.NOT_ANALYZED));
                doc.add(new Field("email", "test"+i+""+i+"@jadyer.com", Field.Store.YES, Field.Index.NOT_ANALYZED));
                doc.add(new Field("content", contents[i], Field.Store.NO, Field.Index.ANALYZED));
                doc.add(new NumericField("attach", Field.Store.YES, true).setIntValue(attachs[i]));        //爲數字加索引(第三個參數指定是否索引)
                doc.add(new NumericField("attach", Field.Store.YES, true).setIntValue((i+1)*100));         //假設有多個附件
                doc.add(new NumericField("date", Field.Store.YES, true).setLongValue(dates[i].getTime())); //爲日期加索引
                writer.addDocument(doc);
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if(null != writer){
                try {
                    writer.close();
                } catch (IOException ce) {
                    ce.printStackTrace();
                }
            }
        }
    }


    /**
     * 針對分頁搜索創建索引
     */
    public HelloSearch(boolean pageFlag){
        String[] myNames = new String[50];
        String[] myContents = new String[50];
        for(int i=0; i<50; i++){
            myNames[i] = "file(" + i + ")";
            myContents[i] = "I love JavaSE, also love Lucene(" + i + ")";
        }
        IndexWriter writer = null;
        Document doc = null;
        try {
            directory = FSDirectory.open(new File("myExample/03_index/"));
            writer = new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_36, new StandardAnalyzer(Version.LUCENE_36)));
            writer.deleteAll();
            for(int i=0; i<myNames.length; i++){
                doc = new Document();
                doc.add(new Field("myname", myNames[i], Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
                doc.add(new Field("mycontent", myContents[i], Field.Store.YES, Field.Index.ANALYZED));
                writer.addDocument(doc);
            }
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if(null != writer){
                try {
                    writer.close();
                } catch (IOException ce) {
                    ce.printStackTrace();
                }
            }
        }
    }


    /**
     * 獲取IndexSearcher實例
     */
    private IndexSearcher getIndexSearcher(){
        try {
            if(reader == null){
                reader = IndexReader.open(directory);
            }else{
                //if the index was changed since the provided reader was opened, open and return a new reader; else,return null
                //如果當前reader在打開期間index發生改變,則打開並返回一個新的IndexReader,否則返回null
                IndexReader ir = IndexReader.openIfChanged(reader);
                if(ir != null){
                    reader.close(); //關閉原reader
                    reader = ir;    //賦予新reader
                }
            }
            return new IndexSearcher(reader);
        }catch(Exception e) {
            e.printStackTrace();
        }
        return null; //發生異常則返回null
    }


    /**
     * 執行搜索操作
     * @param query 搜索的Query對象
     */
    private void doSearch(Query query){
        IndexSearcher searcher = this.getIndexSearcher();
        try {
            //第二個參數指定搜索後顯示的最多的記錄數,其與tds.totalHits沒有聯繫
            TopDocs tds = searcher.search(query, 10);
            System.out.println("本次搜索到[" + tds.totalHits + "]條記錄");
            for(ScoreDoc sd : tds.scoreDocs){
                Document doc = searcher.doc(sd.doc);
                System.out.print("文檔編號=" + sd.doc + "  文檔權值=" + doc.getBoost() + "  文檔評分=" + sd.score + "    ");
                System.out.print("id=" + doc.get("id") + "  email=" + doc.get("email") + "  name=" + doc.get("name") + "  ");
                //獲取多個同名域的方式
                String[] attachValues = doc.getValues("attach");
                for(String attach : attachValues){
                    System.out.print("attach=" + attach + "  ");
                }
                System.out.println();
            }
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if(null != searcher){
                try {
                    searcher.close(); //記得關閉IndexSearcher
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }


    /**
     * 精確匹配搜索
     * @param fieldName 域名(相當於表的字段名)
     * @param keyWords  搜索的關鍵字
     */
    public void searchByTerm(String fieldName, String keyWords){
        Query query = new TermQuery(new Term(fieldName, keyWords));
        this.doSearch(query);
    }


    /**
     * 基於範圍的搜索
     * @param fieldName 域名(相當於表的字段名)
     * @param start     開始字符
     * @param end       結束字符
     */
    public void searchByTermRange(String fieldName, String start, String end){
        Query query = new TermRangeQuery(fieldName, start, end, true, true); //後面兩個參數用於指定開區間或閉區間
        this.doSearch(query);
    }


    /**
     * 針對數字的搜索
     */
    public void searchByNumericRange(String fieldName, int min, int max){
        Query query = NumericRangeQuery.newIntRange(fieldName, min, max, true, true);
        this.doSearch(query);
    }


    /**
     * 基於前綴的搜索
     * @see 它是對Field分詞後的結果進行前綴查找的結果
     */
    public void searchByPrefix(String fieldName, String prefix){
        Query query = new PrefixQuery(new Term(fieldName, prefix));
        this.doSearch(query);
    }


    /**
     * 基於通配符的搜索
     * @see *-->任意多個字符
     * @see ?-->一個字符
     */
    public void searchByWildcard(String fieldName, String wildcard){
        Query query = new WildcardQuery(new Term(fieldName, wildcard));
        this.doSearch(query);
    }


    /**
     * 模糊搜索
     * @see 與通配符搜索不同
     */
    public void searchByFuzzy(String fieldName, String fuzzy){
        Query query = new FuzzyQuery(new Term(fieldName, fuzzy));
        this.doSearch(query);
    }


    /**
     * 多條件搜索
     * @see 本例中搜索name值中以Ja開頭,且content中包含am的內容
     * @see Occur.MUST------表示此條件必須爲true
     * @see Occur.MUST_NOT--表示此條件必須爲false
     * @see Occur.SHOULD----表示此條件非必須
     */
    public void searchByBoolean(){
        BooleanQuery query = new BooleanQuery();
        query.add(new WildcardQuery(new Term("name", "Ja*")), Occur.MUST);
        query.add(new TermQuery(new Term("content", "am")), Occur.MUST);
        this.doSearch(query);
    }


    /**
     * 短語搜索
     * @see 很遺憾的是短語查詢對中文搜索沒有太大的作用,但對英文搜索是很好用的,但它的開銷比較大,儘量少用
     */
    public void searchByPhrase(){
        PhraseQuery query = new PhraseQuery();
        query.setSlop(1);                          //設置跳數
        query.add(new Term("content", "am"));      //第一個Term
        query.add(new Term("content", "Haerbin")); //產生距離之後的第二個Term
        this.doSearch(query);
    }


    /**
     * 基於QueryParser的搜索
     */
    public void searchByQueryParse(){
        QueryParser parser = new QueryParser(Version.LUCENE_36, "content", new StandardAnalyzer(Version.LUCENE_36));
        Query query = null;
        try {
//          query = parser.parse("Haerbin");           //搜索content中包含[Haerbin]的記錄
//          query = parser.parse("I AND Haerbin");     //搜索content中包含[I]和[Haerbin]的記錄
//          query = parser.parse("Lucene OR Haerbin"); //搜索content中包含[Lucene]或者[Haerbin]的記錄
//          query = parser.parse("Lucene Haerbin");    //搜索content中包含[Lucene]或者[Haerbin]的記錄
//          parser.setDefaultOperator(Operator.AND);   //將空格的默認操作OR修改爲AND
//          //1)如果name域在索引時,不進行分詞,那麼無論這裏寫成[name:Jadyer]還是[name:jadyer],最後得到的都是0條記錄
//          //2)由於name原值爲大寫[J],若索引時不對name分詞,除非修改name原值爲小寫[j],並且搜索[name:jadyer]才能得到記錄
//          query = parser.parse("name:Jadyer");       //修改搜索域爲name=Jadyer的記錄
//          query = parser.parse("name:Ja*");          //支持通配符
//          query = parser.parse("\"I am\"");          //搜索content中包含[I am]的記錄(注意不能使用parse("content:'I am'"))
//          parser.setAllowLeadingWildcard(true);      //設置允許[*]或[?]出現在查詢字符的第一位,即[name:*de],否則[name:*de]會報異常
//          query = parser.parse("name:*de");          //Lucene默認的第一個字符不允許爲通配符,因爲這樣效率比較低
//          //parse("+am +name:Jade")--------------搜索content中包括[am]的,並且name=Jade的記錄
//          //parse("am AND NOT name:Jade")--------搜索content中包括[am]的,並且nam不是Jade的記錄
//          //parse("(blog OR am) AND name:Jade")--搜索content中包括[blog]或者[am]的,並且name=Jade的記錄
//          query = parser.parse("-name:Jack +I");     //搜索content中包括[I]的,並且name不是Jack的記錄(加減號要放到域說明的前面)
//          query = parser.parse("id:[1 TO 3]");       //搜索id值從1到3的記錄(TO必須大寫,且這種方式沒有辦法匹配數字)
//          query = parser.parse("id:{1 TO 3}");       //搜索id=2的記錄
            query = parser.parse("name:Jadk~");        //模糊搜索
        } catch (ParseException e) {
            e.printStackTrace();
        }
        this.doSearch(query);
    }


    /**
     * 普通的分頁搜索
     * @see 適用於lucene3.5之前
     * @param expr      搜索表達式
     * @param pageIndex 頁碼
     * @param pageSize  分頁大小
     */
    public void searchPage(String expr, int pageIndex, int pageSize){
        IndexSearcher searcher = this.getIndexSearcher();
        QueryParser parser = new QueryParser(Version.LUCENE_36, "mycontent", new StandardAnalyzer(Version.LUCENE_36));
        try {
            Query query = parser.parse(expr);
            TopDocs tds = searcher.search(query, pageIndex*pageSize);
            ScoreDoc[] sds = tds.scoreDocs;
            for(int i=(pageIndex-1)*pageSize; i<pageIndex*pageSize; i++){
                Document doc = searcher.doc(sds[i].doc);
                System.out.println("文檔編號:" + sds[i].doc + "-->" + doc.get("myname") + "-->" + doc.get("mycontent"));
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if(null != searcher){
                try {
                    searcher.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }


    /**
     * 基於searchAfter的分頁搜索
     * @see 適用於Lucene3.5
     * @param expr      搜索表達式
     * @param pageIndex 頁碼
     * @param pageSize  分頁大小
     */
    public void searchPageByAfter(String expr, int pageIndex, int pageSize){
        IndexSearcher searcher = this.getIndexSearcher();
        QueryParser parser = new QueryParser(Version.LUCENE_36, "mycontent", new StandardAnalyzer(Version.LUCENE_36));
        try {
            Query query = parser.parse(expr);
            TopDocs tds = searcher.search(query, (pageIndex-1)*pageSize);
            //使用IndexSearcher.searchAfter()搜索,該方法第一個參數爲上一頁記錄中的最後一條記錄
            if(pageIndex > 1){
                tds = searcher.searchAfter(tds.scoreDocs[(pageIndex-1)*pageSize-1], query, pageSize);
            }else{
                tds = searcher.searchAfter(null, query, pageSize);
            }
            for(ScoreDoc sd : tds.scoreDocs){
                Document doc = searcher.doc(sd.doc);
                System.out.println("文檔編號:" + sd.doc + "-->" + doc.get("myname") + "-->" + doc.get("mycontent"));
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if(null != searcher){
                try {
                    searcher.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }
}

下面是JUnit4.x編寫的測試

package com.jadyer.test;

import java.io.File;

import org.junit.Before;
import org.junit.Test;

import com.jadyer.lucene.HelloSearch;

public class HelloSearchTest {
    private HelloSearch hello;

    @Before
    public void init(){
        hello = new HelloSearch();
    }


    @Test
    public void searchByTerm(){
        hello.searchByTerm("content", "my");
    }


    @Test
    public void searchByTermRange(){
        hello.searchByTermRange("name", "M", "o");
    }


    @Test
    public void searchByNumericRange(){
        hello.searchByNumericRange("attach", 2, 5);
    }


    @Test
    public void searchByPrefix(){
        hello.searchByPrefix("content", "b");
    }


    @Test
    public void searchByWildcard(){
        hello.searchByWildcard("name", "Ja??er");
    }


    @Test
    public void searchByFuzzy(){
        hello.searchByFuzzy("name", "Jadk");
    }


    @Test
    public void searchByBoolean(){
        hello.searchByBoolean();
    }


    @Test
    public void searchByPhrase(){
        hello.searchByPhrase();
    }


    @Test
    public void searchByQueryParse(){
        hello.searchByQueryParse();
    }


    @Test
    public void searchPage(){
        for(File file : new File("myExample/03_index/").listFiles()){
            file.delete();
        }
        hello = new HelloSearch(true);
        hello.searchPage("mycontent:javase", 2, 10);
    }


    @Test
    public void searchPageByAfter(){
        for(File file : new File("myExample/03_index/").listFiles()){
            file.delete();
        }
        hello = new HelloSearch(true);
        hello.searchPageByAfter("mycontent:javase", 3, 10);
    }
}