Skip to main content



Hive Complex Data Types


  • Array
$ vi arrayfile
1,abc,40000,a$b$c,hyd
2,def,3000,d$f,bang
3,abc,40000,a$b$c,hyd
4,def,3000,d$f,bang
5,abc,40000,a$b$c,hyd
6,def,3000,d$f,bang
7,abc,40000,a$b$c,hyd
8,def,3000,d$f,bang
9,abc,40000,a$b$c,hyd
10,def,3000,d$f$d$e$d$e$e$r$g,bang
hive> create table array_tab (id int, name string, salary bigint, sub array<string>, city string)
    > row format delimited
    > fields terminated by ','
    > collection items terminated by '$';
hive> load data local inpath '/root/arrayfile' into table array_tab;
hive> select * from array_tab;
OK
1       abc     40000   ["a","b","c"]   hyd
2       def     3000    ["d","f"]       bang
3       abc     40000   ["a","b","c"]   hyd
4       def     3000    ["d","f"]       bang
5       abc     40000   ["a","b","c"]   hyd
6       def     3000    ["d","f"]       bang
7       abc     40000   ["a","b","c"]   hyd
8       def     3000    ["d","f"]       bang
9       abc     40000   ["a","b","c"]   hyd
10      def     3000    ["d","f","d","e","d","e","e","r","g"]   bang
hive> describe array_tab;
OK
id                      int
name                    string
salary                  bigint
sub                     array<string>
city                    string
Time taken: 0.79 seconds, Fetched: 5 row(s)
hive> select sub[0] from array_tab where id=1;
….
OK
a



  • Map

$  vi mapfile
1,abc,40000,a$b$c,pf#500$epf#200,hyd
2,def,3000,d$f,pf#500,bang
2,abc,40000,a$b$c,pf#500$epf#200,hyd
3,def,3000,d$f,pf#500,bang
4,abc,40000,a$b$c,pf#500$epf#200,hyd
5,def,3000,d$f,pf#500,bang
6,abc,40000,a$b$c,pf#500$epf#200,hyd
7,def,3000,d$f,pf#500,bang
8,abc,40000,a$b$c,pf#500$epf#200,hyd
hive> create table arr_map_tab (id int, name string, salary bigint, sub array<string>, details map<string, int>, city string)
    > row format delimited
    > fields terminated by ','
    > collection items terminated by '$'
    > map keys terminated by '#';
hive> load data local inpath 'mapfile' into table arr_map_tab;
hive> select * from arr_map_tab;
OK
1       abc     40000   ["a","b","c"]   {"pf":500,"epf":200}    hyd
2       def     3000    ["d","f"]       {"pf":500}      bang
2       abc     40000   ["a","b","c"]   {"pf":500,"epf":200}    hyd
3       def     3000    ["d","f"]       {"pf":500}      bang
4       abc     40000   ["a","b","c"]   {"pf":500,"epf":200}    hyd
5       def     3000    ["d","f"]       {"pf":500}      bang
6       abc     40000   ["a","b","c"]   {"pf":500,"epf":200}    hyd
7       def     3000    ["d","f"]       {"pf":500}      bang
8       abc     40000   ["a","b","c"]   {"pf":500,"epf":200}    hyd
Time taken: 2.04 seconds, Fetched: 9 row(s)
hive> describe arr_map_tab;
OK
id                      int
name                    string
salary                  bigint
sub                     array<string>
details                 map<string,int>
city                    string
Time taken: 0.838 seconds, Fetched: 6 row(s)
hive> select details["pf"] from arr_map_tab limit 1;
…
…
OK
500
Time taken: 33.805 seconds, Fetched: 1 row(s)


  • Struct

$  vi structfile
1,abc,40000,a$b$c,pf#500$epf#200,hyd$ap$500001
2,def,3000,d$f,pf#500,bang$kar$600038
4,abc,40000,a$b$c,pf#500$epf#200,bhopal$MP$452013
5,def,3000,d$f,pf#500,Indore$MP$452014
hive> create table arr_map_struct_tab (id int, name string, salary bigint, sub array<string>, details map<string, int>, address struct<city:string, state:string, pin:int>)
> row format delimited                                                                                                                                                  
> fields terminated by ','
> collection items terminated by '$'                                                                                                         > map keys terminated by #';
OK
Time taken: 4.982 seconds
hive> describe arr_map_struct_tab;
OK
id                      int
name                    string
salary                  bigint
sub                     array<string>
details                 map<string,int>
address                 struct<city:string,state:string,pin:int>
Time taken: 1.416 seconds, Fetched: 6 row(s)
hive> load data local inpath 'structfile' into table arr_map_struct_tab;
hive> select * from arr_map_struct_tab;
OK
1       abc     40000   ["a","b","c"]   {"pf":500,"epf":200}    {"city":"hyd","state":"ap","pin":500001}
2       def     3000    ["d","f"]       {"pf":500}      {"city":"bang","state":"kar","pin":600038}
4       abc     40000   ["a","b","c"]   {"pf":500,"epf":200}    {"city":"bhopal","state":"MP","pin":452013}
5       def     3000    ["d","f"]       {"pf":500}      {"city":"Indore","state":"MP","pin":452014}
Time taken: 1.226 seconds, Fetched: 4 row(s)
hive> select address.city from arr_map_struct_tab where details["pf"]="500" and sub[0]="a";
…
…
OK
hyd
bhopal
Time taken: 20.286 seconds, Fetched: 2 row(s)



  • Uniontype
hive> CREATE TABLE union_tab(col1 UNIONTYPE<INT, DOUBLE, STRING, ARRAY<string>, STRUCT<a:INT,b:string>>)
    > row format delimited
    > fields terminated by ','
    > COLLECTION ITEMS TERMINATED BY '|'
    > LINES TERMINATED BY '\n';
OK
Time taken: 2.356 seconds
$ vi unionfile
0|1
0|12
1|1.234
1|2.3456
2|dinesh
2|Dinesh Sachdev
hive> load data local inpath 'unionfile' overwrite into table union_tab;
hive> select * from union_tab;
OK
{0:1}
{0:12}
{1:1.234}
{1:2.3456}
{2:"dinesh"}
{2:"Dinesh Sachdev"}
Time taken: 1.211 seconds, Fetched: 6 row(s)
It becomes quiet simple to load data into uniontype for primitives. But what about complex types? For example if we edit ‘unionfile’ and append an array:
$vi unionfile
0|1
0|12
1|1.234
1|2.3456
2|dinesh
2|Dinesh Sachdev
3|din|esh|sach|dev
hive> load data local inpath 'unionfile' overwrite into table union_tab;
hive> select * from union_tab;
OK
{0:1}
{0:12}
{1:1.234}
{1:2.3456}
{2:"dinesh"}
{2:"Dinesh Sachdev"}
{3:["din|esh|sach|dev"]}
Time taken: 1.11 seconds, Fetched: 7 row(s)

There is only a single element in array whereas we expected to have array of 4 strings [“din”,”esh”,”sach”,”dev”]

For this we can use create_union UDF:

hive> insert into table union_tab
    > select create_union(4,1, 1.02,"d", array("d","f"), named_struct('a',1, 'b','dinesh')) from sample_07 limit 1;
...
...
hive> insert into table union_tab
    > select create_union(3,1, 1.02,"d", array("d","f"), named_struct('a',1, 'b','dinesh')) from sample_07 limit 1;
hive> select * from union_tab;
OK
{4:{"a":1,"b":"dinesh"}}
{3:["d","f"]}
{0:1}
{0:12}
{1:1.234}
{1:2.3456}
{2:"dinesh"}
{2:"Dinesh Sachdev"}
{3:["din|esh|sach|dev"]}
Time taken: 0.064 seconds, Fetched: 9 row(s)


Comments

  1. Sairam AsapuDecember 14, 2017 at 3:16 AM

    boss, how can I query an union? suppose say I want to say "select from union_tab where "

    ReplyDelete

Post a Comment

Popular posts

Python [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: Missing Authority Key Identifier

  Error requests.exceptions.SSLError: HTTPSConnectionPool  Max retries exceeded with url:  (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: Missing Authority Key Identifier (_ssl.c:1028)'))). Analysis & Solution Recently, we updated from Python 3.11 to 3.13, which resulted in error above. We did verify AKI = SKI in chain of certificates. Also, imported chain of certificates into certifi. Nothing worked for us. Seemingly, it is a bug with Python 3.13. So, we downgraded to Python 3.12 and it started working. Other problems and solution -  '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self-signed certificate in certificate chain (_ssl.c:1006)'))) solution  pip install pip-system-certs [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: certificate has expired  (_ssl.c:1006) solution  1# openssl s_client -showcerts -connect  signin.aws.amazon.com:443  </dev/...
Post a Comment
Read more




Spring MongoDB Rest API not returning response in 90 seconds which is leading to client timeout

  We have Spring Boot  Rest API deployed in Kubernetes cluster which integrates with MongoDB to fetch the data.  MongoDB is fed with data by a real time Spark & NiFi job.  Our clients complained that for a request what they send they don't have response within 90 seconds. Consider it like an OMS ( Order ManagEment System).  On further analysis, we found that Spark & NiFi processing is happenning within 10 seconds after consuming response data from Kafka. Thus, initally out thought was that it due to delay from upstream to produce data in to Kafka.  Thankfully, our data had create / request  timestamp, and when response was received, and when response was inserted into MongoDB. Subtracting response insert time from request time seemed to be well within 90 seconds. But, still client did timeout on not seeing a response within 90 seconds. This led to confusion on our side.  But, then we realized it was due to Read Preference . We updated this...
Post a Comment
Read more




MongoDB Regex Query taking more time in Production but same query perform well in UAT

   We came across a situation where-in, MongoDB Query was taking more time in Production like 10 seconds and 4.2 seconds but same query performed well in UAT taking under 400 ms. The very first thought that was evident to us that it is because of amount of data which differed in UAT and Production. Then we ran following to see the execution plan -   db.collection.aggregate(<queries>).explain() This gave us Winning and Rejected Plans. Under which, we analyzed that although it was using 'IXSCAN.' But, it was incorrect index- as we had one compound index built on time field and other fields, and there was other index just on time field for TTL purposes. Winning plan picked TTL index rather than compound index. Thus, we dropped TTL index and built TTL index on a different time field.  That got our query performance time from 10 seconds to 726 ms. Also, for other query the performance came down from 8 seconds to 4.3 seconds. Then, we ran following -  ...
Post a Comment
Read more




What is Leadership

 
Post a Comment
Read more




Spark MongoDB Connector Not leading to correct count or data while reading

  We are using Scala 2.11 , Spark 2.4 and Spark MongoDB Connector 2.4.4 Use Case 1 - We wanted to read a Shareded Mongo Collection and copy its data to another Mongo Collection. We noticed that after Spark Job successful completion. Output MongoDB did not had many records. Use Case 2 -  We read a MongoDB collection and doing count on dataframe lead to different count on each execution. Analysis,  We realized that MongoDB Spark Connector is missing data on bulk read as a dataframe. We tried various partitioner, listed on page -  https://www.mongodb.com/docs/spark-connector/v2.4/configuration/  But, none of them worked for us. Finally, we tried  MongoShardedPartitioner  this lead to constant count on each execution. But, it was greater than the actual count of records on the collection. This seems to be limitation with MongoDB Spark Connector. But,  MongoShardedPartitioner  seemed closest possible solution to this kind of situation. But, it per...
Post a Comment
Read more