ES008-Elasticsearch+hbase整合

1:设计索引库的settings信息的mappings信息，并把这些配置信息保存到一个配置文件中。

1.1 vi articles.json

{    "settings":{         "number_of_shards":3,         "number_of_replicas":1    },    "mappings":{         "article":{             "dynamic":"strict",             "properties":{                 "id":{"type":"integer","store":"yes"},                 "title":{"type":"string","store":"yes","index":"analyzed","analyzer":" ik"},                 "describe":{"type":"string","store":"yes","index":"analyzed","analyzer":" ik"},                 "author":{"type":"string","store":"yes","index":"no"}             }         }    }}

其中： dynamic:strict  表示禁用ElasticSearch动态匹配字段类型，title和describe使用 ik分词

1.2 命令行创建索引

curl -XPUT 'localhost:9200/articles/' -d'{"settings":{"number_of_shards":3,"number_of_replicas":1}}'

2：安装配置 es服务。

    1)：整合IK中文分词工具

    

3：启动 es。

4：创建索引库

    使用开始定义的文件进行创建，使用下面命令进行创建

    curl -XPOST ' localhost:9200/articles' -d @articles.json

5：初始化数据

把原始数据在 es中建立索引，并且还要在 hbase中保存一份。

需要使用提供的代码里面的一个类(DataImportHBaseAndIndex.java)

public class DataImportHBaseAndIndex {    public static final String FILE_PATH= "D:/bigdata/es_hbase/datasrc/article.txt" ;    public static void main(String[] args) throws java.lang.Exception {          // 读取数据源         InputStream in = new FileInputStream(new File(FILE_PATH ));         BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(in ,"UTF-8" ));         String line = null;         List<Article> articleList = new ArrayList<Article>();         Article article = null;          while ((line = bufferedReader .readLine()) != null) {             String[] split = StringUtils.split(line, "\t");              article = new Article();              article.setId( new Integer(split [0]));              article.setTitle( split[1]);              article.setAuthor( split[2]);              article.setDescribe( split[3]);              article.setContent( split[3]);              articleList.add(article );         }          for (Article a : articleList ) {              // HBase插入数据             HBaseUtils hBaseUtils = new HBaseUtils();              hBaseUtils.put(hBaseUtils .TABLE_NAME , String.valueOf(a.getId()), hBaseUtils.COLUMNFAMILY_1 ,                      hBaseUtils.COLUMNFAMILY_1_TITLE , a .getTitle());              hBaseUtils.put(hBaseUtils .TABLE_NAME , String.valueOf(a.getId()), hBaseUtils.COLUMNFAMILY_1 ,                      hBaseUtils.COLUMNFAMILY_1_AUTHOR , a.getAuthor());              hBaseUtils.put(hBaseUtils .TABLE_NAME , String.valueOf(a.getId()), hBaseUtils.COLUMNFAMILY_1 ,                      hBaseUtils.COLUMNFAMILY_1_DESCRIBE , a.getDescribe());              hBaseUtils.put(hBaseUtils .TABLE_NAME , String.valueOf(a.getId()), hBaseUtils.COLUMNFAMILY_1 ,                      hBaseUtils.COLUMNFAMILY_1_CONTENT , a.getContent());              // ElasticSearch 插入数据             EsUtil. addIndex(EsUtil.DEFAULT_INDEX, EsUtil.DEFAULT_TYPE , a );         }    }}

注意：

(1)使用 hbaseutils工具类的时候，要注意修改 zk的IP地址和hbase.rootdir的地址

还需要在集群中创建一个表（HBase集群）：

create 'article','info'

(2) 使用 es工具类的时候要注意：addIndex方法需要实现

/**     * 向ElasticSearch添加索引     *     * @param index     *            索引库名称     * @param type     *            搜索类型     * @param article     *            数据     * @return 当前doc的id     */    public static String addIndex(String index , String type, Article article ) {         HashMap<String, Object> hashMap = new HashMap<String,  Object>();          hashMap.put( "id", article .getId());          hashMap.put( "title", article .getTitle());          hashMap.put( "describe", article.getDescribe());          hashMap.put( "author", article .getAuthor());         IndexResponse response = getInstance().prepareIndex(index, type, String.valueOf(article.getId())).setSource( hashMap).get();          return response .getId();    }   

     

6：Es工具类中的search方法是否已经完善。

     

/**     * ElasticSearch查询     *     * @param skey     *            搜索关键字     * @param index     *            索引库     * @param type     *            类型     * @param start     *            开始下标     * @param row     *            每页显示最大记录书     * @return 数据记录     */    public static Map<String, Object> search(String skey, String index , String type, Integer start, Integer row) {         HashMap<String, Object> dataMap = new HashMap<String, Object>();         ArrayList<Map<String, Object>> dataList = new ArrayList<Map<String, Object>>();         SearchRequestBuilder builder = EsUtil.getInstance().prepareSearch(index);          builder.setTypes( type);         builder.setSearchType(SearchType. DFS_QUERY_THEN_FETCH);          if (StringUtils.isNotBlank( skey)) {              builder.setQuery(QueryBuilders. multiMatchQuery(skey, "title", "describe" ));// 匹配title和describe两个字段         }          builder.setFrom( start);          builder.setSize( row);          // 设置查询高亮显示          builder.addHighlightedField( "title");          builder.addHighlightedField( "describe");          builder.setHighlighterPreTags( "<font color='red'>");          builder.setHighlighterPostTags( "</font>");         SearchResponse response = builder.get(); // 执行查询         SearchHits hits = response.getHits();          long totalCount = hits .getTotalHits();// 总数         SearchHit[] hits2 = hits.getHits();         Map<String, Object> source = null;          for (SearchHit searchHit : hits2 ) {              source = searchHit.getSource();// 获取查询数据              // 查询字段title和 describle高亮控制             Map<String, HighlightField> highlightFields = searchHit .getHighlightFields();             HighlightField highlightFieldTile = highlightFields.get("title" );              if (highlightFieldTile != null) {                 Text[] fragments = highlightFieldTile.getFragments();                 String name = "";                  for (Text text : fragments ) {                       name += text;                 }                  source.put( "title", name );// 设置title高亮字段             }             HighlightField highlightFieldDescribe = highlightFields.get("describe" );              if (highlightFieldDescribe != null) {                 Text[] fragments = highlightFieldDescribe.getFragments();                 String name = "";                  for (Text text : fragments ) {                       name += text;                 }                  source.put( "describe", name ); // 设置describe高亮字段             }              dataList.add( source);         }          dataMap.put( "count", totalCount );          dataMap.put( "dataList", dataList );          return dataMap ;    }    

7：下面就可以使用 jetty进行启动。

    如何安装 jetty

         参考：http://eclipse-jetty.github.io/installation.html

8：访问：http://localhost:8080/article

   

    

9：如果使用 tomcat启动这个项目

    注意： jdk使用1.7   tomcat使用7.0