hudi mor sql update

./bin/spark-sql --packages org.apache.hudi:hudi-spark-bundle_2.11:0.10.0,org.apache.spark:spark-avro_2.11:2.4.4 \
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'   \
--conf 'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'  \
--conf 'spark.kryoserializer.buffer.max=1024m' --conf spark.rdd.compress=true --driver-memory 6g 



create table hudi_mor1 (
  VendorID int,
  tpep_pickup_datetime string,
  tpep_dropoff_datetime string,
  passenger_count int,
  trip_distance double,
  RatecodeID int,
  store_and_fwd_flag string,
  PULocationID int,
  DOLocationID int,
  payment_type int,
  fare_amount double,
  extra double,
  mta_tax double,
  tip_amount double,
  tolls_amount double,
  improvement_surcharge double,
  total_amount double,
  congestion_surcharge double,
  date_col string
) using hudi
tblproperties (
  type = 'mor',
  primaryKey = 'VendorID',
  preCombineField = 'tpep_pickup_datetime'
 )
location 'file:///tmp/hudi/hudi_mor1';


set hoodie.sql.bulk.insert.enable=true;
set hoodie.sql.insert.mode=non-strict;
set hoodie.bulkinsert.sort.mode=NONE;
set hoodie.combine.before.insert=false;


create table ny_parquet using parquet location 'file:///dataset_path/*.parquet';

insert into hudi_mor1 select * from ny_parquet ;

select count(1) from hudi_mor1 where VendorID='4';

update hudi_mor1 set DOLocationID = 200, store_and_fwd_flag = 'Y' where VendorID = '4';

select count(1) from hudi_mor1 where VendorID='4';

select DOLocationID, store_and_fwd_flag from hudi_mor1 where VendorID='4' limit 10;

update hudi_mor1 set DOLocationID = 200, store_and_fwd_flag = 'Y';