spark-shell操作HBase get、put and Return

各算子异常问题记录
1、当过滤器为元素为空时，无法过滤出数据，需加流程控制
    filterList.filterRow() 返回true 则表示filter 不存在元素，返回false 则表示filter 存在元素
2、对 Result 结果集数据操作时： 要预防空指针操作，采用
   Result.advance() 流程控制，数据存在则返回true,数据不存在则返回false
3、对 Result 结果集数据操作时：
   result.getValue(familyName, Qualifier) 如果列不存在会报【空指针异常】
   解决方案：
   采用result.containsColumn(familyName, Qualifier) 进行流程控制解决
4、gets 与scan 返回值均为ArrayList[Result]可迭代 进行数据处理
5、gets 异常捕捉：需谨慎处理 RowKey 存在 null 的数据

1、HBase 建表 插入数据语句
create 'DIGITOPER_CXYYGL:ZL_TEST','info'
put "DIGITOPER_CXYYGL:ZL_TEST","1508947425011","info:ID","110"
put "DIGITOPER_CXYYGL:ZL_TEST","1508947425011","info:NAME","JOE"
put "DIGITOPER_CXYYGL:ZL_TEST","1508947425011","info:AGE","10"

put "DIGITOPER_CXYYGL:ZL_TEST","1508947425012","info:ID","110"
put "DIGITOPER_CXYYGL:ZL_TEST","1508947425012","info:NAME","JOHE"
put "DIGITOPER_CXYYGL:ZL_TEST","1508947425012","info:AGE","20"

2、spark-shell 操作 并附带返回值
import org.apache.hadoop.hbase.{CellUtil, HBaseConfiguration, TableName}
import org.apache.hadoop.hbase.client.{Admin, BufferedMutator, Connection, ConnectionFactory, Delete, Get, Mutation, Put, Result, ResultScanner, Scan, Table}
import org.apache.hadoop.hbase.util.{Base64, Bytes}
import java.util
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp
import org.apache.hadoop.hbase.filter.FilterList.Operator
import org.apache.hadoop.hbase.filter.{FilterList, SingleColumnValueFilter}

scala> val hConf = HBaseConfiguration.create()
hConf: org.apache.hadoop.conf.Configuration = Configuration: core-default.xml, core-site.xml, mapred-default.xml, mapred-site.xml, yarn-default.xml, yarn-site.xml, hdfs-default.xml, hdfs-site.xml, hdfs-io-settings.xml, hbase-default.xml, hbase-site.xml

scala> val hConn = ConnectionFactory.createConnection(hConf)
hConn: org.apache.hadoop.hbase.client.Connection = hconnection-0x44485db

scala> val hTable = hConn.getTable(TableName.valueOf("DIGITOPER_CXYYGL:ZL_TEST"))
hTable: org.apache.hadoop.hbase.client.Table = DIGITOPER_CXYYGL:ZL_TEST;hconnection-0x3eff6846

scala> val get = new Get(Bytes.toBytes("1508947425011"))
get: org.apache.hadoop.hbase.client.Get = {"cacheBlocks":true,"totalColumns":0,"row":"1508947425011","families":{},"maxVersions":1,"timeRange":[0,9223372036854775807]}

scala> val filterList = new FilterList(Operator.MUST_PASS_ALL)
filterList: org.apache.hadoop.hbase.filter.FilterList = FilterList AND (0/0): []

scala> if(!filterList.filterRow()) get.setFilter(filterList)
res0: Any = {"filter":"FilterList AND (0/0): []","cacheBlocks":true,"totalColumns":0,"row":"1508947425011","families":{},"maxVersions":1,"timeRange":[0,9223372036854775807]}

scala> val result=hTable.get(get)
result: org.apache.hadoop.hbase.client.Result = keyvalues={1508947425011/info:AGE/1607578572840/Put/vlen=2/seqid=0, 1508947425011/info:ID/1607578572698/Put/vlen=3/seqid=0, 1508947425011/info:NAME/1607578572786/Put/vlen=3/seqid=0}

scala> Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("ID")))
res3: String = 110