lucene 2.9的简单使用

项目做的很杂，又用到了lucene对特定文件的内容进行搜索，检查特定词汇。

经过查资料，看demo，实验，终于写出来了。

ps：网上的资料大部分很老啊，类老是对不上号。

 

先建立索引

import java.io.File;
import java.io.FileFilter;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.util.HashSet;
import java.util.Set;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.wltea.analyzer.lucene.IKAnalyzer;
import vrvclient.util.ConfigUtil;
import vrvclient.util.FileListUtil;

/**
 *
 * @author lan
 */
public class Indexer extends Constants {

    private static final Log log = LogFactory.getLog(Indexer.class);

    public void index(File[] files, FileFilter filter) {
        if (files == null) {
            return;
        }
//        System.out.println(filter.getClass());
        Set<File> set = new HashSet<File>();
        for (File f : files) {//过滤掉不合要求的文件，如后缀，文件名等
            FileListUtil.list(f, filter, set);
        }
        File indexDir = new File(ConfigUtil.getIndexPath());//这里是获得索引文件的保存路径的
        Analyzer analyzer = new IKAnalyzer();//使用国产的IK分词器，很好很强大
        try {
            FSDirectory dir = FSDirectory.open(indexDir);//保存到硬盘上
            IndexWriter iw = new IndexWriter(dir, analyzer, !IndexReader.indexExists(dir), IndexWriter.MaxFieldLength.LIMITED);
            for (File f : set) {
                if (f.isFile()) {
//                    System.out.println(f.getAbsolutePath());
                    Document doc = new Document();
                    Reader reader = new FileReader(f);
                    doc.add(new Field(PATH, f.getAbsolutePath(), Field.Store.YES, Field.Index.ANALYZED));//保存路径
                    doc.add(new Field(FILE, reader));//保存文件
                    iw.addDocument(doc);
                    reader.close();
                }
            }
            iw.optimize();
            iw.close();
        } catch (CorruptIndexException ex) {
            log.error(ex.getMessage(), ex);
        } catch (LockObtainFailedException ex) {
            log.error(ex.getMessage(), ex);
        } catch (IOException ex) {
            log.error(ex.getMessage(), ex);
        }
    }
}

 

这个是搜索结果

import java.io.File;
import java.io.IOException;
import java.util.HashSet;
import java.util.Set;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
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.store.FSDirectory;
import org.wltea.analyzer.lucene.IKAnalyzer;
import vrvclient.util.ConfigUtil;

/**
 *
 * @author lan
 */
public class Searcher extends Constants {

    private static final Log log = LogFactory.getLog(Indexer.class);

    /**
     *
     * @param contents
     * @param combineMode true = and,false = or
     * @param limit -1=all
     */
    public Set<String> search(String[] contents, boolean combineMode, int limit) {
        Set<String> paths = new HashSet<String>();
        try {
            File indexDir = new File(ConfigUtil.getIndexPath());
            FSDirectory fsd = FSDirectory.open(indexDir);
            IndexSearcher is = new IndexSearcher(fsd, true);
            Analyzer analyzer = new IKAnalyzer();
            if (fsd.getFile().exists()) {
                QueryParser qp = new QueryParser(FILE, analyzer);
                StringBuilder sb = new StringBuilder();
                String jioner = "";
                if (combineMode) {//如果是and，则所有条件要同时满足
                    jioner = "+";
                }
                boolean b = true;
                for (String s : contents) {
                    s = s.replaceAll("\\s+", " AND ");//防止条件中的空格被看成“或”，把其变成“与”
                    if (!b) {
                        sb.append(" ");
                    }
                    sb.append(jioner).append("(").append(s).append(")");
                    b = false;
                }
                Query q = qp.parse(sb.toString());
                log.info(q.toString());
                if (limit == -1) {
                    limit = is.maxDoc();
                }

                TopDocs hits = is.search(q, limit);
                ScoreDoc[] sds = hits.scoreDocs;
                for (int i = 0; i < sds.length; i++) {
                    ScoreDoc sd = sds[i];
                    Document doc = is.doc(sd.doc);
//                    System.out.println("Hit:(" + sd.score + ")" + doc.toString());
//本来想同时得到命中次数，也就是词频，但是网上找到的都是老版本的，这里不能用。
                    paths.add(doc.get(PATH));//返回匹配的路径
                }
            }
            is.close();
        } catch (ParseException ex) {
            log.error(ex.getMessage(), ex);
        } catch (IOException ex) {
            log.error(ex.getMessage(), ex);
        }
        return paths;
    }
}

 

附用到的工具类：

import java.io.File;
import java.io.FileFilter;
import java.util.Map;
import java.util.Set;

/**
 *
 * @author lan
 */
public final class FileListUtil {

//返回一定数量的符合要求的文件
    public static void list(File f, FileFilter filter, Set<File> set, int limit) {
        if (limit > -1 && set.size() >= limit) {
            return;
        }
        if (f == null) {
            return;
        }
        if (f.isFile()) {
            set.add(f);
        } else if (f.isDirectory()) {
            File[] files = null;
            if (filter == null) {
                files = f.listFiles();
            } else {
                files = f.listFiles(filter);
            }
            if (files != null) {
                for (File file : files) {
                    list(file, filter, set, limit);
                }
            }
        }
    }

//返回所有的符合要求的文件，不要担心set放不上，至少我的D盘资料盘都放进去都没有内存溢出
    public static void list(File f, FileFilter filter, Set<File> set) {
        if (f == null) {
            return;
        }
        if (f.isFile()) {
            set.add(f);
        } else if (f.isDirectory()) {
            File[] files = null;
            if (filter == null) {
                files = f.listFiles();
            } else {
                files = f.listFiles(filter);
            }
            if (files != null) {
                for (File file : files) {
                    list(file, filter, set);
                }
            }
        }
    }

//其实是打包工具类用到的
    public static void list(File f, FileFilter filter, String parent, Map<String, File> map) {
        if (f == null) {
            return;
        }
        String name = f.getName();
        if (parent != null) {
            name = parent + "/" + name;
        }
        if (f.isFile()) {
            map.put(name, f);
        } else if (f.isDirectory()) {
            File[] files = null;
            if (filter == null) {
                files = f.listFiles();
            } else {
                files = f.listFiles(filter);
            }
            if (files != null) {
                for (File file : files) {
                    list(file, filter, name, map);
                }
            }
        }
    }
}

 

常量类，大部分人用接口，但是我不太喜欢用接口来保存常量，虽然更方便点，但是不合规范。

public class Constants {//可以替换成枚举，没必要了

    protected static final String PATH = "path";
    protected static final String FILE = "file";
}