功能简介

HBase通过原生的scan API来支持全文索引能力，同使用Scan读取数据类似。在此基础上，需要在configuration中配置HBASE_CLIENT_CONNECTION_IMPL为"org.apache.hadoop.hbase.client.LemonConnectionImplementation"，同时将全文检索条件传入CloudTable定制好的过滤器ESColumnValueFilter。

样例代码

1. configuration定义HBASECLIENTCONNECTION_IMPL为LemonConnectionImplementation实现类。

   样例代码如下：

   conf = HBaseConfiguration.create();
   conf.set(HConnection.HBASE_CLIENT_CONNECTION_IMPL, "org.apache.hadoop.hbase.client.LemonConnectionImplementation");
   Connection conn = ConnectionFactory.createConnection(conf);

2. 全文检索条件通过ESColumnValueFilter的httpParameters或reqBodyJson传入，参数格式和开源Elasticsearch的官方文档一致，请分别参见URI Search和Request Body Search。

   如下样例代码通过httpParameters来查询（请将代码中的字符串“***replace_with_Chinese_keywords_01***”替换为中文检索词）：

     public void testScanDataWithES1() {
       LOG.info("Entering testScanDataWithES1.");
   
       Table table = null;
       // Instantiate a ResultScanner object.
       ResultScanner rScanner = null;
       try {
         // Create the Configuration instance.
         table = conn.getTable(tableName);
         assert table instanceof LemonWrapperHTable;
   
         // set specified qualifier.
         Scan scan = new Scan();
         scan.addColumn(CF1, QUA_ARTICLE_CONTENT_CHINESE);
         scan.addColumn(CF2, QUA_ARTICLE_CONTENT_English);
         scan.addColumn(CF1, QUA_ARTICLE_ID);
   
         // Set the cache size.
         scan.setCaching(1000);
   
         // with special filter
         Map<String, String> httpParameters = new HashMap<>();
         httpParameters.put("q", "contentCh:***replace_with_Chinese_keywords_01***");
         List<String> indexNames = new ArrayList();
         indexNames.add(ES_INDEX_NAME);
         ESColumnValueFilter filter = new ESColumnValueFilter(indexNames, httpParameters, "");
         scan.setFilter(filter);
   
         // Submit a scan request.
         rScanner = table.getScanner(scan);
   
         // Print query results.
         for (Result r = rScanner.next(); r != null; r = rScanner.next()) {
           for (Cell cell : r.rawCells()) {
             LOG.info("testScanDataWithES1 by text type condition, scan result:" + Bytes.toString(CellUtil.cloneRow(cell)) + ":"
               + Bytes.toString(CellUtil.cloneFamily(cell)) + ","
               + Bytes.toString(CellUtil.cloneQualifier(cell)) + ","
               + convertCellValue(Bytes.toString(CellUtil.cloneQualifier(cell)), CellUtil.cloneValue(cell)));
           }
         }
   
         LOG.info("Scan data successfully.");
       } catch (IOException e) {
         LOG.error("Scan data failed ", e);
       } finally {
         if (rScanner != null) {
           // Close the scanner object.
           rScanner.close();
         }
         if (table != null) {
           try {
             // Close the HTable object.
             table.close();
           } catch (IOException e) {
             LOG.error("Close table failed ", e);
           }
         }
       }
       LOG.info("Exiting testScanDataWithES1.");
     }

   如下样例代码通过reqBodyJson来查询（请将代码中的字符串“***replace_with_Chinese_keywords_02***”替换为中文检索词）：

     public void testScanDataWithES2() {
       LOG.info("Entering testScanDataWithES2.");
   
       Table table = null;
       // Instantiate a ResultScanner object.
       ResultScanner rScanner = null;
       try {
         // Create the Configuration instance.
         table = conn.getTable(tableName);
         assert table instanceof LemonWrapperHTable;
   
         // set specified qualifier.
         Scan scan = new Scan();
         scan.addColumn(CF1, QUA_ARTICLE_CONTENT_CHINESE);
         scan.addColumn(CF2, QUA_ARTICLE_CONTENT_English);
         scan.addColumn(CF1, QUA_ARTICLE_ID);
   
         // Set the cache size.
         scan.setCaching(1000);
   
         // with special filter
         Map<String, String> httpParameters = Collections.emptyMap();
         List<String> indexNames = new ArrayList();
         indexNames.add(ES_INDEX_NAME);
         String reqBodyJson =
           "{" +
             "    \"query\" : {" +
             "        \"term\" : { \"contentCh\" : \"***replace_with_Chinese_keywords_02***\" }" +
             "    }" +
             "}";
         ESColumnValueFilter filter = new ESColumnValueFilter(indexNames, httpParameters, reqBodyJson);
         scan.setFilter(filter);
   
         // Submit a scan request.
         rScanner = table.getScanner(scan);
   
         // Print query results.
         for (Result r = rScanner.next(); r != null; r = rScanner.next()) {
           for (Cell cell : r.rawCells()) {
             LOG.info("testScanDataWithES2 by text type condition, scan result:" + Bytes.toString(CellUtil.cloneRow(cell)) + ":"
               + Bytes.toString(CellUtil.cloneFamily(cell)) + ","
               + Bytes.toString(CellUtil.cloneQualifier(cell)) + ","
               + convertCellValue(Bytes.toString(CellUtil.cloneQualifier(cell)), CellUtil.cloneValue(cell)));
           }
         }
   
         LOG.info("Scan data successfully.");
       } catch (IOException e) {
         LOG.error("Scan data failed ", e);
       } finally {
         if (rScanner != null) {
           // Close the scanner object.
           rScanner.close();
         }
         if (table != null) {
           try {
             // Close the HTable object.
             table.close();
           } catch (IOException e) {
             LOG.error("Close table failed ", e);
           }
         }
       }
   
       LOG.info("Exiting testScanDataWithES2.");
     }