lucene 简单demo

package com.weiquan.Lucene;

import java.io.IOException;
import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
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.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TxtFileIndexer {

    
    
    

    public static void main(String[] args) throws IOException, ParseException {
        Analyzer analyzer = new SingleAnalyzer();
        //使用指定位置索引文件
        Directory index=FSDirectory.open(Paths.get("E:/luceneIndex")); 
        

        //创建索引器
        IndexWriterConfig config = new IndexWriterConfig(analyzer);
        IndexWriter w = new IndexWriter(index, config);
        //添加文档，根据分词器创建索引
        
        addDoc(w, "Thee Art f Computer Science", "12");
        addDoc(w, "Thee Art f Computer Science", "23");
        addDoc(w, "Thee Art f Computer Science", "34");
        addDoc(w, "Thee Art f Computer Science", "45");
        addDoc(w, "Thee Art f Computer Science", "56");
//        Query delQuery=new QueryParser("text", analyzer).parse("11155");
//        w.deleteDocuments(delQuery);
//        Term isbnTerm=new Term("isbn", "55320055Z");
//        Term textTerm=new Term("title", "今日头条Bc");
//        
//        Term[] terms=new Term[]{isbnTerm,textTerm};//条件满足其一就会删除
        
        w.close();
        
        

        // 2. query
//        String querystr ="11155";

        // the "title" arg specifies the default field to use
        // when no field is explicitly specified in the query.
//        Query q = new QueryParser("text", analyzer).parse(querystr);
//        System.out.println(q.toString());
        String[] queries ={"12"};
        String[] fields ={"isbn"};
//        Query query = MultiFieldQueryParser.parse(queries, fields, analyzer);
        BooleanQuery query = new BooleanQuery();
        PhraseQuery query1=new PhraseQuery();
        query1.add(new Term("isbn", "12"));
        PhraseQuery query2=new PhraseQuery();
        query2.add(new Term("text", "c"));
//        query.add(query1, BooleanClause.Occur.MUST);
        query.add(query2, BooleanClause.Occur.MUST);
        query.add(query1,BooleanClause.Occur.MUST);
        
        int hitsPerPage = 10;
        IndexReader reader = DirectoryReader.open(index);
        IndexSearcher searcher = new IndexSearcher(reader);
        TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage);
        
        searcher.search(query, collector);
        ScoreDoc[] hits = collector.topDocs().scoreDocs;
        ScoreDoc sd=null;
        
//        if(hits.length>0){
//            System.out.println(hits.length);
//            sd=hits[hits.length-1];
            ScoreDoc sd2=new ScoreDoc(0, 0.26554886f);
            
            //分页
//            hits=searcher.searchAfter(sd2, query, hitsPerPage).scoreDocs;
//        }else{
//            
//        }
        System.out.println("total :"+collector.getTotalHits());
//        searcher.search(query, collector);
        
//        searcher.searchAfter(after, query, 1);
//        searcher.searchAfter(null, query, 1);
        
        
        // 4. display results
        System.out.println("Found " + hits.length + " hits.");
        for (int i = 0; i < hits.length; ++i) {
            int docId = hits[i].doc;
            System.out.println(hits[i].toString());
            Document d = searcher.doc(docId);
            System.out.println((i + 1) + ". " + d.get("text")+" . "+d.get("isbn")) ;
        }

        // reader can only be closed when there
        // is no need to access the documents any more.
        reader.close();
    }

    private static void addDoc(IndexWriter w, String title, String isbn)
            throws IOException {
        Document doc = new Document();
        doc.add(new TextField("text", title, Field.Store.YES));

        // use a string field for isbn because we don't want it tokenized
        doc.add(new StringField("isbn", isbn, Field.Store.YES));
        w.addDocument(doc);
    }

    

    
}

package com.weiquan.Lucene;

import java.io.IOException;
import java.io.Reader;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.util.AttributeFactory;

public class SingleTokenizer extends Tokenizer {

    private int offset = 0, bufferIndex = 0, dataLen = 0;
    private final static int MAX_WORD_LEN = 255;
    private final static int IO_BUFFER_SIZE = 1024;
    private final char[] buffer = new char[MAX_WORD_LEN];
    private final char[] ioBuffer = new char[IO_BUFFER_SIZE];
    private int length = 0;
    private int start = 0;
    private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
    private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);

    private final boolean flush() {
        if (length > 0) {
            termAtt.copyBuffer(buffer, 0, length);
            offsetAtt.setOffset(correctOffset(start), correctOffset(start
                    + length));
            return true;
        } else
            return false;
    }

    private final void push(char c) {
        if (length == 0)
            start = offset - 1; // start of token
        buffer[length++] = Character.toLowerCase(c); // buffer it
    }

    @Override
    public boolean incrementToken() throws IOException {
        clearAttributes();
        length = 0;
        start = offset;
        while (true) {
            final char c;
            offset++;
            if (bufferIndex >= dataLen) {
                dataLen = input.read(ioBuffer);
                bufferIndex = 0;
            }
            if (dataLen == -1) {
                offset--;
                return flush();
            } else
                c = ioBuffer[bufferIndex++];
            switch (Character.getType(c)) {
            case Character.DECIMAL_DIGIT_NUMBER:// 注意此部分不过滤一些熟悉或者字母
            case Character.LOWERCASE_LETTER:// 注意此部分
            case Character.UPPERCASE_LETTER:// 注意此部分
                // push(c);
                // if (length == MAX_WORD_LEN) return flush();
                // break;
            case Character.OTHER_LETTER:
                if (length > 0) {
                    bufferIndex--;
                    offset--;
                    return flush();
                }
                push(c);
                return flush();
            default:
                if (length > 0)
                    return flush();
                break;
            }
        }
    }

    @Override
    public final void end() {
        // set final offset
        final int finalOffset = correctOffset(offset);
        this.offsetAtt.setOffset(finalOffset, finalOffset);
    }

    @Override
    public void reset() throws IOException {
        super.reset();
        offset = bufferIndex = dataLen = 0;
    }

}

package com.weiquan.Lucene;

import java.util.Arrays;
import java.util.List;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.util.CharArraySet;

public class SingleAnalyzer extends Analyzer {

    /**
     * 禁用某些搜索词，比如黄赌毒
     */
    private CharArraySet stops;

    public SingleAnalyzer() {
        List<String> stopWords = Arrays.asList(new String[] {});

        CharArraySet stopSet = new CharArraySet(stopWords, false);
        stops = CharArraySet.unmodifiableSet(stopSet);
    }

    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        Tokenizer token = new SingleTokenizer();
        return new TokenStreamComponents(token);
    }

}