org.apache.lucene.search.highlight.SimpleFragmenter#org.wltea.analyzer.lucene.IKAnalyzer源码实例Demo

private static void showSearchResults(IndexSearcher searcher, ScoreDoc[] hits, Query query, IKAnalyzer ikAnalyzer) throws IOException {
    System.out.println("找到 " + hits.length + " 个命中.");
    System.out.println("序号\t匹配度得分\t结果");
    for (int i = 0; i < hits.length; i++) {
        ScoreDoc scoreDoc = hits[i];
        int docId = scoreDoc.doc;
        Document document = searcher.doc(docId);
        List<IndexableField> fields = document.getFields();
        System.out.print((i + 1));
        System.out.print("\t" + scoreDoc.score);
        for (IndexableField f : fields) {
            System.out.print("\t" + document.get(f.name()));
        }
        System.out.println();

    }
}
 

/**
 * 封裝一个方法，用于将数据库中的数据解析为一个个关键字词存储到索引文件中
 * @param document
 * @throws IOException
 */
public static void write(Document document) throws IOException {
    //索引库的存储目录
    Directory directory = FSDirectory.open(Paths.get(dir));
    //在 6.6 以上版本中 version 不再是必要的，并且，存在无参构造方法，可以直接使用默认的 StandardAnalyzer 分词器。
    //创建索引写入配置
    Analyzer analyzer = new IKAnalyzer();
    IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
    //创建索引写入对象
    IndexWriter indexWriter = new IndexWriter(directory,indexWriterConfig);
    //写入到目录文件中
    indexWriter.addDocument(document);
    //提交事务
    indexWriter.commit();
    //关闭流
    indexWriter.close();
}
 

/**
 * 根据ID更新搜索内容
 * @param blogArticle
 * @throws IOException
 */
public static void updateIndexById(BlogArticle blogArticle) throws IOException{
    Directory directory = FSDirectory.open(Paths.get(dir));// 打开文件索引目录
    Analyzer analyzer = new IKAnalyzer();
    IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
    //创建索引写入对象
    IndexWriter writer = new IndexWriter(directory,indexWriterConfig);
    Document doc = new Document();
    doc.add(new LongPoint("id",blogArticle.getId()));
    doc.add(new TextField("title",blogArticle.getTitle(), Field.Store.YES));
    doc.add(new TextField("marks",blogArticle.getMarks()==null?"":blogArticle.getMarks(),Field.Store.YES));
    doc.add(new TextField("text",blogArticle.getText()==null?"":blogArticle.getText(),Field.Store.YES));
    doc.add(new StoredField("href",blogArticle.getBlogChannel().getHref()));
    doc.add(new StoredField("show_pic",blogArticle.getShowPic()==null?"":blogArticle.getShowPic()));
    writer.updateDocument(new Term("id", blogArticle.getId().toString()), doc);
    writer.commit();// 提交
    writer.close();// 关闭
}
 

@RequestMapping("searchBook.do")
public ModelAndView searchBook(Book book) throws IOException, ParseException {

    ModelAndView mav = new ModelAndView("searchBook");

    // 关键字
    String keyword = book.getName();
    System.out.println(keyword);
    // 准备中文分词器
    IKAnalyzer analyzer = new IKAnalyzer();
    // 索引
    Directory index = createIndex(analyzer);
    // 查询器
    Query query = new QueryParser("name",analyzer).parse(keyword);
    // 搜索
    IndexReader reader = DirectoryReader.open(index);
    IndexSearcher searcher = new IndexSearcher(reader);
    int numberPerPage = 10;
    ScoreDoc[] hits = searcher.search(query,numberPerPage).scoreDocs;
    List<Book> books = new ArrayList<>();
    for (int i = 0; i < hits.length; i++) {
        ScoreDoc scoreDoc = hits[i];
        int docId = scoreDoc.doc;
        Document document = searcher.doc(docId);
        Book tmpBook = bookService.get(Integer.parseInt(document.get("id")));
        books.add(tmpBook);
    }

    mav.addObject("books",books);
    return mav;
}
 

private Directory createIndex(IKAnalyzer analyzer) throws IOException {
    Directory index = new RAMDirectory();
    IndexWriterConfig config = new IndexWriterConfig(analyzer);
    IndexWriter writer = new IndexWriter(index,config);
    List<Book> books = bookService.listByBookType(1);
    for (Book book : books) {
        addDoc(writer,book);
    }
    writer.close();
    return index;
}
 

public static void main(String[] args) throws IOException, ParseException {

        // 1. 准备中文分词器
        IKAnalyzer analyzer = new IKAnalyzer();

        // 2. 索引
        List<String> productNames = new ArrayList<>();
        productNames.add("飞利浦led灯泡e27螺口暖白球泡灯家用照明超亮节能灯泡转色温灯泡");
        productNames.add("飞利浦led灯泡e14螺口蜡烛灯泡3W尖泡拉尾节能灯泡暖黄光源Lamp");
        productNames.add("雷士照明 LED灯泡 e27大螺口节能灯3W球泡灯 Lamp led节能灯泡");
        productNames.add("飞利浦 led灯泡 e27螺口家用3w暖白球泡灯节能灯5W灯泡LED单灯7w");
        productNames.add("飞利浦led小球泡e14螺口4.5w透明款led节能灯泡照明光源lamp单灯");
        productNames.add("飞利浦蒲公英护眼台灯工作学习阅读节能灯具30508带光源");
        productNames.add("欧普照明led灯泡蜡烛节能灯泡e14螺口球泡灯超亮照明单灯光源");
        productNames.add("欧普照明led灯泡节能灯泡超亮光源e14e27螺旋螺口小球泡暖黄家用");
        productNames.add("聚欧普照明led灯泡节能灯泡e27螺口球泡家用led照明单灯超亮光源");
        Directory index = createIndex(analyzer, productNames);

        // 3. 查询器
        String keyword = "护眼带光源";
        Query query = new QueryParser("name",analyzer).parse(keyword);

        // 4. 搜索
        IndexReader reader = DirectoryReader.open(index);
        IndexSearcher searcher = new IndexSearcher(reader);
        int numberPerPage = 1000;
        System.out.printf("当前一共有%d条数据%n",productNames.size());
        System.out.printf("查询关键字是：\"%s\"%n",keyword);
        ScoreDoc[] hits = searcher.search(query,numberPerPage).scoreDocs;

        // 5. 显示查询结果
        showSearchResults(searcher, hits, query, analyzer);
    }
 

private static Directory createIndex(IKAnalyzer analyzer, List<String> products) throws IOException {
    Directory index = new RAMDirectory();
    IndexWriterConfig config = new IndexWriterConfig(analyzer);
    IndexWriter writer = new IndexWriter(index,config);

    for (String name : products){
        addDoc(writer,name);
    }
    writer.close();
    return  index;
}
 

/**
 * 根据ID删除索引
 * @param id
 * @throws IOException
 */
public static void deleteIndexById(String id) throws IOException{
    Directory directory = FSDirectory.open(Paths.get(dir));// 打开文件索引目录
    Analyzer analyzer = new IKAnalyzer();
    IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
    //创建索引写入对象
    IndexWriter writer = new IndexWriter(directory,indexWriterConfig);
    IndexReader reader = DirectoryReader.open(directory);// 读取目
    Query q = new TermQuery(new Term("id", id));
    writer.deleteDocuments(q);// 删除指定ID的Document
    writer.commit();// 提交
    writer.close();// 关闭
    reader.close();// 关闭
}
 

public static void main(String[] args) {  
    String keyWord = "Java的分词效果到底怎么样呢，我们来看一下吧[抱抱]";  
    //创建IKAnalyzer中文分词对象  
    IKAnalyzer analyzer = new IKAnalyzer();  
    // 使用智能分词  
    analyzer.setUseSmart(true);  
    // 打印分词结果  
    try {  
        printAnalysisResult(analyzer, keyWord);  
    } catch (Exception e) {  
        e.printStackTrace();  
    }  
}
 

public void indexInit() throws Exception {
	Analyzer analyzer = new IKAnalyzer();
//	Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_44);
	this.indexSettings = new LuceneIndexSettings(analyzer);
	this.indexSettings.createFSDirectory("f:\\file");
	this.luceneIndex = new LuceneIndex(this.indexSettings);
	this.luceneIndexSearch = new LuceneIndexSearch(indexSettings, new LuceneResultCollector(indexSettings));
}
 

@Inject
public IKAnalyzerProvider(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
    super(index, indexSettings, name, settings);

    loader = ServiceLoader.load(Configuration.class);
    Iterator<Configuration> iterator = loader.iterator();
    if (!iterator.hasNext()) {
        throw new NotFoundIKAnalyzerConfigurationImplementation();
    }
    analyzer = new IKAnalyzer(iterator.next().init(index, indexSettings, env, name, settings));
}
 

@Override public IKAnalyzer get() {
    return this.analyzer;
}
 

@Override
public IKAnalyzer get() {
    return this.analyzer;
}
 

public IkAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings,boolean useSmart) {
    super(indexSettings, name, settings);

    Configuration configuration=new Configuration(env,settings).setUseSmart(useSmart);

    analyzer=new IKAnalyzer(configuration);
}