My xml looks like this
<TAG>
<REQUEST_ID>1</REQUEST_ID>
<APPLICATION_ID>2</APPLICATION_ID>
<EXTERNAL_SYSTEM_CODE>RB</EXTERNAL_SYSTEM_CODE>
<CCM_CHECK>
<CCM_CHECK_ID>101</CCM_CHECK_ID>
<CCM_CHECK_RESULT>10</CCM_CHECK_RESULT>
</CCM_CHECK>
<VERIF_ANSWERS>
<CHECK_CODE>101</CHECK_CODE>
<QUESTION_CODE>1</QUESTION_CODE>
<BOOKMARK_NUMBER>1</BOOKMARK_NUMBER>
<ANSWER_VALUE>NN</ANSWER_VALUE>
</VERIF_ANSWERS>
<VERIF_ANSWERS>
<CHECK_CODE>101</CHECK_CODE>
<QUESTION_CODE>2</QUESTION_CODE>
<BOOKMARK_NUMBER>1</BOOKMARK_NUMBER>
<ANSWER_VALUE>NN</ANSWER_VALUE>
</VERIF_ANSWERS>
</TAG>
this is how I create a table from it
CREATE EXTERNAL TABLE s_sourcedata.evkuzmin_test_xml(
request_id string
, application_id string
, external_system_code string
, ccm_check map<string, string>
, verif_answers array<struct<verif_answer:array<map<string, string>>>>
)
ROW FORMAT SERDE 'com.ibm.spss.hive.serde2.xml.XmlSerDe'
WITH SERDEPROPERTIES (
"column.xpath.request_id"="/TAG/REQUEST_ID/text()",
"column.xpath.application_id"="/TAG/APPLICATION_ID/text()",
"column.xpath.external_system_code"="/TAG/EXTERNAL_SYSTEM_CODE/text()",
"column.xpath.ccm_check"="/TAG/CCM_CHECK/*",
"column.xpath.verif_answers"="/TAG")
STORED AS
INPUTFORMAT 'com.ibm.spss.hive.serde2.xml.XmlInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat'
LOCATION '/storage/s_sourcedata/db/evkuzmin_test_xml'
TBLPROPERTIES (
"xmlinput.start"="<TAG",
"xmlinput.end"="</TAG>"
);
which results in the following
1,2,RB,"{""CCM_CHECK_ID"":""101"",""CCM_CHECK_RESULT"":""10""}","[{""verif_answer"":null}]"
How can i turn verif_answers
into an array of key valur pairs like I did for ccm_check
?
I tried doing it the same way I did for ccm_check
? but got only the first VERIF_ANSWERS
.
The number of VERIF_ANSWERS
can vary. In this case there are 2? but there can be 0 or 10.