分布式全文检索服务器——ElasticSearch(2)

写在前面

前文学习了如何安装和使用自带的Restful API对其进行操作，接下来学习一下Java的相关API。

构建环境

我们使用maven工程，来导入所需的jar包:

<dependencies>
        <dependency>
            <groupId>org.elasticsearch</groupId>
            <artifactId>elasticsearch</artifactId>
            <version>7.8.0</version>
        </dependency>
        <dependency>
            <groupId>org.elasticsearch.client</groupId>
            <artifactId>transport</artifactId>
            <version>7.8.0</version>
        </dependency>
        <dependency>
            <groupId>org.elasticsearch.client</groupId>
            <artifactId>elasticsearch-rest-high-level-client</artifactId>
            <version>7.8.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-to-slf4j</artifactId>
            <version></version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>1.7.24</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-simple</artifactId>
            <version>1.7.21</version>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.12</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <dependency>
            <groupId>com.fasterxml.jackson.core</groupId>
            <artifactId>jackson-databind</artifactId>
            <version>2.9.6</version>
        </dependency>
        <dependency>
            <groupId>com.fasterxml.jackson.core</groupId>
            <artifactId>jackson-annotations</artifactId>
            <version>2.9.0</version>
        </dependency>
    </dependencies>

创建索引

在一切开始前，我们将必须使用的对象初始化：

private RestHighLevelClient client;
    @Before
    public void init() {
        client = new RestHighLevelClient(RestClient.builder(
                new HttpHost("localhost", 9201,"http"),
                new HttpHost("localhost", 9202,"http"),
                new HttpHost("localhost", 9203,"http")
        ));
    }

注:由于TransportClient已经被官方标为弃用了，官方建议使用RestHighLevelClient来作为替代，我们这里学习就顺应官方要求了。
之后就可以开始创建索引了:

    @Test
    public void createIndex() throws Exception {
        // 创建索引
        CreateIndexRequest request = new CreateIndexRequest("index_hello2");
        // 创建索引时的参数设置,这里设置成5片,各备份一片
        request.settings(Settings.builder()
                .put("index.number_of_shards", 5)
                .put("index.number_of_replicas", 1)
        );
        // 同步创建索引
        CreateIndexResponse createIndexResponse = client.indices().create(request, RequestOptions.DEFAULT);
        // 通过返回的值来确定是否创建成功
        if(createIndexResponse.isAcknowledged()){
            System.out.println("创建成功啦！");
        }else{
            System.out.println("创建失败啦！");
        }
    }

设置mapping

设置mapping有很多方式，这里使用了XContentBuilder：

@Test
    public void setMapping() throws Exception{
        PutMappingRequest request = new PutMappingRequest("index_hello2");
        //使用XContentBuilder创建一个mapping信息
        XContentBuilder builder = XContentFactory.jsonBuilder()
                .startObject()
                .startObject("properties")
                .startObject("ids")
                .field("type", "long")
                .field("store", true)
                .endObject()
                .startObject("title")
                .field("type", "text")
                .field("store", true)
                .field("analyzer", "ik_smart")
                .endObject()
                .startObject("content")
                .field("type", "text")
                .field("store", true)
                .field("analyzer", "ik_smart")
                .endObject()
                .endObject()
                .endObject();
        // 将mapping信息设置给request
        request.source(builder);
        // 同步创建索引
        AcknowledgedResponse acknowledgedResponse = client.indices().putMapping(request, RequestOptions.DEFAULT);
        // 通过返回的值来确定是否创建成功
        if(acknowledgedResponse.isAcknowledged()){
            System.out.println("创建mapping成功啦！");
        }else{
            System.out.println("创建失败啦！");
        }
        client.close();
    }

添加文档

    @Test
    public void testAddDocument() throws Exception{
        // 创建一个IndexRequest对象来创建一个文档
        IndexRequest indexRequest = new IndexRequest("index_hello2");
        // 设置添加的文档id
        indexRequest.id("2");
        // 通过Map来设置值
        Map<String,Object> map = new HashMap<>(4);
        map.put("ids",2L);
        map.put("title","我爱谔谔");
        map.put("content","？？？？");
        // 把map设置给indexRequest
        indexRequest.source(map);
        // 执行操作
        IndexResponse indexResponse = client.index(indexRequest, RequestOptions.DEFAULT);
        // 输出返回结果
        System.out.println(indexResponse.toString());
        // 关闭client
        client.close();
    }

这里使用了Map的方式来插入，其实有很多方式，具体可以查看官网API文档：https://www.elastic.co/guide/en/elasticsearch/client/java-api/7.8/index.html

查询

首先把一些通用的变量和方法抽出来:

    private RestHighLevelClient client;
    private SearchRequest searchRequest;
    private SearchSourceBuilder searchSourceBuilder;
    @Before
    public void init() {
        client = new RestHighLevelClient(RestClient.builder(
                new HttpHost("localhost", 9201,"http"),
                new HttpHost("localhost", 9202,"http"),
                new HttpHost("localhost", 9203,"http")
        ));
        // 新建一个查询请求
        searchRequest = new SearchRequest("index_hello");
        // 新建一个查询条件Builder
        searchSourceBuilder = new SearchSourceBuilder();
    }

这里我把三个搜索方法进行了提取:(普通查询，带分页的查询，高亮查询)

private void search(QueryBuilder queryBuilder) throws IOException {
        // 将该query赋值给builder
        searchSourceBuilder.query(queryBuilder);
        // 将builder赋值给request
        searchRequest.source(searchSourceBuilder);
        // 发起请求，返回结果
        SearchResponse response = client.search(searchRequest, RequestOptions.DEFAULT);
        SearchHits hits = response.getHits();
        System.out.println("总条数为："+hits.getTotalHits());
        Iterator<SearchHit> iterator = hits.iterator();
        while(iterator.hasNext()){
            SearchHit searchHit = iterator.next();
            // 打印整个json字符串
            System.out.println(searchHit.getSourceAsString());
            System.out.println("-----------文档的属性");
            Map<String, Object> source = searchHit.getSourceAsMap();
            System.out.println(source.get("ids"));
            System.out.println(source.get("title"));
            System.out.println(source.get("content"));
        }
    }
    private void search(QueryBuilder queryBuilder, String highLightField) throws IOException {
        // 将该query赋值给builder
        searchSourceBuilder.query(queryBuilder);
        HighlightBuilder highlightBuilder = new HighlightBuilder();
        highlightBuilder.field(highLightField);
        highlightBuilder.preTags("<em>");
        highlightBuilder.postTags("</em>");
        searchSourceBuilder.highlighter(highlightBuilder);
        // 将builder赋值给request
        searchRequest.source(searchSourceBuilder);
        // 发起请求，返回结果
        SearchResponse response = client.search(searchRequest, RequestOptions.DEFAULT);
        SearchHits hits = response.getHits();
        System.out.println("总条数为："+hits.getTotalHits());
        Iterator<SearchHit> iterator = hits.iterator();
        while(iterator.hasNext()){
            SearchHit searchHit = iterator.next();
            // 打印整个json字符串
            System.out.println(searchHit.getSourceAsString());
            System.out.println("-----------文档的属性");
            Map<String, Object> source = searchHit.getSourceAsMap();
            System.out.println(source.get("id"));
            System.out.println(source.get("title"));
            System.out.println(source.get("content"));
            System.out.println("*********** 高亮属性");
            Map<String, HighlightField> highlightFields = searchHit.getHighlightFields();
            System.out.println(highlightFields);
            // 取title高亮显示的结果
            HighlightField field = highlightFields.get(highLightField);
            Text[] fragments = field.getFragments();
            if(fragments!=null){
                String  fragment = fragments[0].toString();
                System.out.println(fragment);
            }
        }
    }
    private void searchByPage(QueryBuilder queryBuilder) throws IOException {
        // 将该query赋值给builder
        searchSourceBuilder.query(queryBuilder);
        // 设置分页参数，从0开始每页五条
        searchSourceBuilder.from(0);
        searchSourceBuilder.size(5);
        // 将builder赋值给request
        searchRequest.source(searchSourceBuilder);
        // 发起请求，返回结果
        SearchResponse response = client.search(searchRequest, RequestOptions.DEFAULT);
        SearchHits hits = response.getHits();
        System.out.println("总条数为："+hits.getTotalHits());
        Iterator<SearchHit> iterator = hits.iterator();
        while(iterator.hasNext()){
            SearchHit searchHit = iterator.next();
            // 打印整个json字符串
            System.out.println(searchHit.getSourceAsString());
            System.out.println("-----------文档的属性");
            Map<String, Object> source = searchHit.getSourceAsMap();
            System.out.println(source.get("ids"));
            System.out.println(source.get("title"));
            System.out.println(source.get("content"));
        }
    }

基于ID的查询

    @Test
    public void findById() throws Exception{
        // 使用ID查询
        QueryBuilder queryBuilder = QueryBuilders.idsQuery().addIds("1");
        search(queryBuilder);
    }

基于Term的关键字查询

    @Test
    public void findByTerm() throws Exception{
        // 使用Term查询
        QueryBuilder queryBuilder = QueryBuilders.termQuery("title","淫荡");
        search(queryBuilder);
    }

基于QueryString的分词查询

    @Test
    public void testQueryString() throws Exception{
        // 创建一个QueryBuilder对象
        QueryBuilder queryBuilder = QueryBuilders.queryStringQuery("谁不爱呢").defaultField("content");
        // 执行查询
        search(queryBuilder,"content");
        // 执行分页查询
//        searchByPage(queryBuilder);
    }

可以看到，三个查询方法都十分类型，都是构建了一个QueryBuilder对象。

SpringData-ElasticSearch

这是Spring公司封装的API，可以在保留基本特性的基础上达到简化操作的目的。但百度搜到的内容都过于老旧，使用了过时的API，官网的文档我也看不大懂。这里就先放置下，日后需要使用时再好好研究

总结

可以看到，ElasticSearch的更新迭代很快，而且整体操作和使用起来也比较复杂。考虑到很多大型公司都在使用，这个搜索服务器我只学习了皮毛，其他的使用等需要使用时再好好研究吧。