在Pig

时间:2017-02-14 13:45:31

标签: xml hadoop hive apache-pig hcatalog

我正在尝试使用猪中的 Hcatalog 来加载我的hive表,因为我已经写了下面的代码,但是我收到了错误。我正在使用pig -useHCatalog

打开我的猪壳

代码:

A = LOAD 'patient_info' USING org.apache.hive.hcatalog.pig.HCatLoader();

错误:

  

错误hive.ql.metadata.Table - 无法从serde获取字段:   com.ibm.spss.hive.serde2.xml.XmlSerDe java.lang.RuntimeException:   MetaException(消息:java.lang.ClassNotFoundException类   com.ibm.spss.hive.serde2.xml.XmlSerDe not found)at   org.apache.hadoop.hive.ql.metadata.Table.getDeserializerFromMetaStore(Table.java:275)     在   org.apache.hadoop.hive.ql.metadata.Table.getDeserializer(Table.java:255)     在org.apache.hadoop.hive.ql.metadata.Table.getCols(Table.java:602)     在   org.apache.hive.hcatalog.common.HCatUtil.getTableSchemaWithPtnCols(HCatUtil.java:184)     在   org.apache.hive.hcatalog.pig.HCatLoader.getSchema(HCatLoader.java:216)     在   org.apache.pig.newplan.logical.relational.LOLoad.getSchemaFromMetaData(LOLoad.java:175)     在   org.apache.pig.newplan.logical.relational.LOLoad。(LOLoad.java:89)     在   org.apache.pig.parser.LogicalPlanBuilder.buildLoadOp(LogicalPlanBuilder.java:866)     在   org.apache.pig.parser.LogicalPlanGenerator.load_clause(LogicalPlanGenerator.java:3568)     在   org.apache.pig.parser.LogicalPlanGenerator.op_clause(LogicalPlanGenerator.java:1625)     在   org.apache.pig.parser.LogicalPlanGenerator.general_statement(LogicalPlanGenerator.java:1102)     在   org.apache.pig.parser.LogicalPlanGenerator.statement(LogicalPlanGenerator.java:560)     在   org.apache.pig.parser.LogicalPlanGenerator.query(LogicalPlanGenerator.java:421)     在   org.apache.pig.parser.QueryParserDriver.parse(QueryParserDriver.java:188)     在org.apache.pig.PigServer $ Graph.parseQuery(PigServer.java:1688)at at   org.apache.pig.PigServer $ Graph.registerQuery(PigServer.java:1635)at   org.apache.pig.PigServer.registerQuery(PigServer.java:587)at   org.apache.pig.tools.grunt.GruntParser.processPig(GruntParser.java:1093)     在   org.apache.pig.tools.pigscript.parser.PigScriptParser.parse(PigScriptParser.java:501)     在   org.apache.pig.tools.grunt.GruntParser.parseStopOnError(GruntParser.java:198)     在   org.apache.pig.tools.grunt.GruntParser.parseStopOnError(GruntParser.java:173)     在org.apache.pig.tools.grunt.Grunt.run(Grunt.java:69)at   org.apache.pig.Main.run(Main.java:547)at   org.apache.pig.Main.main(Main.java:158)at   sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)at   sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)     在   sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)     在java.lang.reflect.Method.invoke(Method.java:606)at   org.apache.hadoop.util.RunJar.run(RunJar.java:221)at   org.apache.hadoop.util.RunJar.main(RunJar.java:136)引起:   MetaException(消息:java.lang.ClassNotFoundException类   com.ibm.spss.hive.serde2.xml.XmlSerDe not found)at   org.apache.hadoop.hive.metastore.MetaStoreUtils.getDeserializer(MetaStoreUtils.java:400)

更新

我在hive中存储数据的命令如下所示。

add jar /home/cloudera/hivexmlserde-1.0.5.3.jar;
CREATE EXTERNAL TABLE patient_info (
statusCode string,
title string,
startTime string,
endTime string,
frequencyValue string,
frequencyUnits string

)
ROW FORMAT SERDE 'com.ibm.spss.hive.serde2.xml.XmlSerDe'
WITH SERDEPROPERTIES (
"column.xpath.statusCode"="medicationsInfo/entryInfo/statusCode/text()",
"column.xpath.title"="medications/code/code/text()",
"column.xpath.startTime"="medications/xxx/startTime/text()",
"column.xpath.endTime"="medications/xxx/endTime/text()",
"column.xpath.frequencyValue"="medications/xxx/frequencyValue/text()",
"column.xpath.frequencyUnits"="medications/xxx/frequencyUnits/text()",
)
STORED AS
INPUTFORMAT 'com.ibm.spss.hive.serde2.xml.XmlInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat'
TBLPROPERTIES (
"xmlinput.start"="<medicationsInfo",
"xmlinput.end"="</medicationsInfo>");


load data inpath '/user/cloudera/xml' into table patient_info ;

示例:

 <Document>
    <ProductCode>
     <code>10160-0</code>
     <entryInfo> 
        <statusCode>completed</statusCode>
        <startTime>20110729</startTime>
        <endTime>20110822</endTime>
        <strengthValue>24</strengthValue>
        <strengthUnits>h</strengthUnits>
     </entryInfo> 
     <entryInfo>
        <statusCode>completed</statusCode>
        <startTime>20120130</startTime>
        <endTime>20120326</endTime>
        <strengthValue>12</strengthValue>
        <strengthUnits>h</strengthUnits>
     </entryInfo>
     <entryInfo>
        <statusCode>completed</statusCode>
        <startTime>20100412</startTime>
        <endTime>20110822</endTime>
        <strengthValue>8</strengthValue>
        <strengthUnits>d</strengthUnits>
     </entryInfo> 
    </ProductCode>
    <ProductCode>
     <code>10160-0</code>
     <entryInfo> 
        <statusCode>completed</statusCode>
        <startTime>20110729</startTime>
        <endTime>20110822</endTime>
        <strengthValue>24</strengthValue>
        <strengthUnits>h</strengthUnits>
     </entryInfo> 
     <entryInfo>
        <statusCode>completed</statusCode>
        <startTime>20120130</startTime>
        <endTime>20120326</endTime>
        <strengthValue>12</strengthValue>
        <strengthUnits>h</strengthUnits>
     </entryInfo>
     <entryInfo>
        <statusCode>completed</statusCode>
        <startTime>20100412</startTime>
        <endTime>20110822</endTime>
        <strengthValue>8</strengthValue>
        <strengthUnits>d</strengthUnits>
     </entryInfo> 
    </ProductCode> 
   <Medicationsinfo>
     <code>10160-0</code>
     <entryInfo> 
        <statusCode>completed</statusCode>
        <startTime>20110729</startTime>
        <endTime>20110822</endTime>
        <strengthValue>24</strengthValue>
        <strengthUnits>h</strengthUnits>
     </entryInfo> 
     <entryInfo>
        <statusCode>completed</statusCode>
        <startTime>20120130</startTime>
        <endTime>20120326</endTime>
        <strengthValue>12</strengthValue>
        <strengthUnits>h</strengthUnits>
     </entryInfo>
     <entryInfo>
        <statusCode>completed</statusCode>
        <startTime>20100412</startTime>
        <endTime>20110822</endTime>
        <strengthValue>8</strengthValue>
        <strengthUnits>d</strengthUnits>
     </entryInfo> 
    </Medicationsinfo>
    <Medicationsinfo>
     <code>10160-0</code>
     <entryInfo> 
        <statusCode>completed</statusCode>
        <startTime>20110729</startTime>
        <endTime>20110822</endTime>
        <strengthValue>24</strengthValue>
        <strengthUnits>h</strengthUnits>
     </entryInfo> 
     <entryInfo>
        <statusCode>completed</statusCode>
        <startTime>20120130</startTime>
        <endTime>20120326</endTime>
        <strengthValue>12</strengthValue>
        <strengthUnits>h</strengthUnits>
     </entryInfo>
     <entryInfo>
        <statusCode>completed</statusCode>
        <startTime>20100412</startTime>
        <endTime>20110822</endTime>
        <strengthValue>8</strengthValue>
        <strengthUnits>d</strengthUnits>
     </entryInfo> 
    </Medicationsinfo> 
    </Document>

1 个答案:

答案 0 :(得分:1)

外部表的定义无效。 以下是一些选项:

选项1

create external table patient_info 
(
    code        string
   ,entryInfo   string
)
row format serde 'com.ibm.spss.hive.serde2.xml.XmlSerDe'
with serdeproperties 
(
    "column.xpath.code"      = "/Medicationsinfo/code/text()"
   ,"column.xpath.entryInfo" = "/Medicationsinfo/entryInfo"
)
stored as
inputformat 'com.ibm.spss.hive.serde2.xml.XmlInputFormat'
outputformat 'org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat'
location '/user/hive/warehouse/patient_info'
tblproperties 
(
    "xmlinput.start" = "<Medicationsinfo"
   ,"xmlinput.end"   = "</Medicationsinfo>"
)
;

select * from patient_info
;
+-------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| patient_info.code | patient_info.entryinfo                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+-------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| 10160-0           | <string><entryInfo><statusCode>completed</statusCode><startTime>20110729</startTime><endTime>20110822</endTime><strengthValue>24</strengthValue><strengthUnits>h</strengthUnits></entryInfo><entryInfo><statusCode>completed</statusCode><startTime>20120130</startTime><endTime>20120326</endTime><strengthValue>12</strengthValue><strengthUnits>h</strengthUnits></entryInfo><entryInfo><statusCode>completed</statusCode><startTime>20100412</startTime><endTime>20110822</endTime><strengthValue>8</strengthValue><strengthUnits>d</strengthUnits></entryInfo></string> |
+-------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| 10160-0           | <string><entryInfo><statusCode>completed</statusCode><startTime>20110729</startTime><endTime>20110822</endTime><strengthValue>24</strengthValue><strengthUnits>h</strengthUnits></entryInfo><entryInfo><statusCode>completed</statusCode><startTime>20120130</startTime><endTime>20120326</endTime><strengthValue>12</strengthValue><strengthUnits>h</strengthUnits></entryInfo><entryInfo><statusCode>completed</statusCode><startTime>20100412</startTime><endTime>20110822</endTime><strengthValue>8</strengthValue><strengthUnits>d</strengthUnits></entryInfo></string> |
+-------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

选项2

create external table patient_info 
(
    code        string
   ,entryInfo   array<map<string,map<string,string>>>
)
row format serde 'com.ibm.spss.hive.serde2.xml.XmlSerDe'
with serdeproperties 
(
    "column.xpath.code"      = "/Medicationsinfo/code/text()"
   ,"column.xpath.entryInfo" = "/Medicationsinfo/entryInfo"
)
stored as
inputformat 'com.ibm.spss.hive.serde2.xml.XmlInputFormat'
outputformat 'org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat'
location '/user/hive/warehouse/patient_info'
tblproperties 
(
    "xmlinput.start" = "<Medicationsinfo"
   ,"xmlinput.end"   = "</Medicationsinfo>"
)
;

select * from patient_info
;
+-------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| patient_info.code |                                                                                                                                                                                   patient_info.entryinfo                                                                                                                                                                                   |
+-------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| 10160-0           | [{"entryInfo":{"statusCode":"completed","startTime":"20110729","strengthUnits":"h","endTime":"20110822","strengthValue":"24"}},{"entryInfo":{"statusCode":"completed","startTime":"20120130","strengthUnits":"h","endTime":"20120326","strengthValue":"12"}},{"entryInfo":{"statusCode":"completed","startTime":"20100412","strengthUnits":"d","endTime":"20110822","strengthValue":"8"}}] |
| 10160-0           | [{"entryInfo":{"statusCode":"completed","startTime":"20110729","strengthUnits":"h","endTime":"20110822","strengthValue":"24"}},{"entryInfo":{"statusCode":"completed","startTime":"20120130","strengthUnits":"h","endTime":"20120326","strengthValue":"12"}},{"entryInfo":{"statusCode":"completed","startTime":"20100412","strengthUnits":"d","endTime":"20110822","strengthValue":"8"}}] |
+-------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

选项3

create external table patient_info 
(
    code        string
   ,entryInfo   array<map<string,struct<statusCode:string,startTime:string,endTime:string,strengthValue:int,strengthUnits:string>>>
)
row format serde 'com.ibm.spss.hive.serde2.xml.XmlSerDe'
with serdeproperties 
(
    "column.xpath.code"      = "/Medicationsinfo/code/text()"
   ,"column.xpath.entryInfo" = "/Medicationsinfo/entryInfo"
)
stored as
inputformat 'com.ibm.spss.hive.serde2.xml.XmlInputFormat'
outputformat 'org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat'
location '/user/hive/warehouse/patient_info'
tblproperties 
(
    "xmlinput.start" = "<Medicationsinfo"
   ,"xmlinput.end"   = "</Medicationsinfo>"
)
;

select * from patient_info
;
+-------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| patient_info.code |                                                                                                                                                                                patient_info.entryinfo                                                                                                                                                                                |
+-------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| 10160-0           | [{"entryInfo":{"statuscode":"completed","starttime":"20110729","endtime":"20110822","strengthvalue":24,"strengthunits":"h"}},{"entryInfo":{"statuscode":"completed","starttime":"20120130","endtime":"20120326","strengthvalue":12,"strengthunits":"h"}},{"entryInfo":{"statuscode":"completed","starttime":"20100412","endtime":"20110822","strengthvalue":8,"strengthunits":"d"}}] |
| 10160-0           | [{"entryInfo":{"statuscode":"completed","starttime":"20110729","endtime":"20110822","strengthvalue":24,"strengthunits":"h"}},{"entryInfo":{"statuscode":"completed","starttime":"20120130","endtime":"20120326","strengthvalue":12,"strengthunits":"h"}},{"entryInfo":{"statuscode":"completed","starttime":"20100412","endtime":"20110822","strengthvalue":8,"strengthunits":"d"}}] |
+-------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

爆炸选项3

select  pi.code
       ,ei.i + 1    as i
       ,ei.entryInfo["entryInfo"].statusCode
       ,ei.entryInfo["entryInfo"].startTime
       ,ei.entryInfo["entryInfo"].endTime
       ,ei.entryInfo["entryInfo"].strengthValue
       ,ei.entryInfo["entryInfo"].strengthUnits

from    patient_info    pi
        lateral view  posexplode (entryInfo) ei as i,entryInfo
;
+---------+---+------------+-----------+----------+---------------+---------------+
| pi.code | i | statuscode | starttime | endtime  | strengthvalue | strengthunits |
+---------+---+------------+-----------+----------+---------------+---------------+
| 10160-0 | 1 | completed  | 20110729  | 20110822 | 24            | h             |
+---------+---+------------+-----------+----------+---------------+---------------+
| 10160-0 | 2 | completed  | 20120130  | 20120326 | 12            | h             |
+---------+---+------------+-----------+----------+---------------+---------------+
| 10160-0 | 3 | completed  | 20100412  | 20110822 | 8             | d             |
+---------+---+------------+-----------+----------+---------------+---------------+
| 10160-0 | 1 | completed  | 20110729  | 20110822 | 24            | h             |
+---------+---+------------+-----------+----------+---------------+---------------+
| 10160-0 | 2 | completed  | 20120130  | 20120326 | 12            | h             |
+---------+---+------------+-----------+----------+---------------+---------------+
| 10160-0 | 3 | completed  | 20100412  | 20110822 | 8             | d             |
+---------+---+------------+-----------+----------+---------------+---------------+