31 July 2014

需求,做一个桌面搜索小工具,将制定的目录下的文件,生成索引,提供一个搜索界面,输入关键字,在内容里搜索匹配的文件,列出文件信息:

点击查看项目主页

step1:构建索引:

图片:

图1

代码:

/**
 * 根据指定的文件/目录生成索引
 *
 * @param file
 * @throws Exception
 */
private void createIndex(File file) throws Exception {
 
    if (file.isDirectory()) {
        File[] files = file.listFiles();
        for (File child : files) {
            createIndex(child);
        }
    } else {
        String fileName = file.getName();
 
        String extName = fileName.substring(fileName.lastIndexOf(".") + 1)
                .toLowerCase();
 
        if ("txt".equals(extName) || "properties".equals(extName)
                || "java".equals(extName) || "jsp".equals(extName)
                || "js".equals(extName) || "css".equals(extName)) {
            logger.log(Level.INFO, "索引:" + file.getAbsolutePath());
            Document doc = new Document();
            doc.add(new Field("id", String.valueOf(new Date().getTime()),
                    Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
            doc.add(new Field("filename", file.getName(), Field.Store.YES,
                    Field.Index.ANALYZED));
            doc.add(new Field("filepath", file.getAbsolutePath(),
                    Field.Store.YES, Field.Index.NOT_ANALYZED));
            doc.add(new Field("content", IOUtils.toString(
                    new FileInputStream(file), "UTF-8"), Field.Store.NO,
                    Field.Index.ANALYZED));
            doc.add(new NumericField("inputdate", Field.Store.YES, true)
                    .setLongValue(new Date().getTime()));
            indexWriter.addDocument(doc);
        }
    }
}
  • step2:进行搜索,返回符合条件的前50条记录:

图片:

图2

代码:

/**
 * 根据制定的关键字查询内容匹配的项目
 * @param keyword
 * @return
 * @throws Exception
 */
public List<ResultItem> query(String keyword) throws Exception {
    IndexSearcher searcher = new IndexSearcher(FSDirectory.open(new File(
            Contants.indexDir)), true);
    searcher.setDefaultFieldSortScoring(true, false);
    QueryParser parser = new QueryParser(Version.LUCENE_30, "content",
            new StandardAnalyzer(Version.LUCENE_30));
    Query query = parser.parse(keyword);
    org.apache.lucene.search.Sort sort = new org.apache.lucene.search.Sort(
            new SortField("updatetime", SortField.LONG, true));
    TopDocs result = searcher.search(query, null, Integer.MAX_VALUE, sort);
 
    ScoreDoc[] docs = result.scoreDocs;
    System.out.println(docs.length);
    List<ResultItem> list = new ArrayList<ResultItem>();
    for (int i = 0; i < (docs.length > 50 ? 50 : docs.length); i++) {
        Document doc = searcher.doc(docs[i].doc);
        ResultItem item = new ResultItem();
        item.setId(doc.getField("id").stringValue());
        item.setFileName(doc.getField("filename").stringValue());
        item.setFilePath(doc.getField("filepath").stringValue());
        item.setUpdateTime(new Date(Long.valueOf(doc.getField("inputdate")
                .stringValue())));
        list.add(item);
        logger.info(item.toString());
 
    }
    return list;
 
}




blog comments powered by Disqus
Fork me on GitHub