soumilshah1995 commented on issue #8919:
URL: https://github.com/apache/hudi/issues/8919#issuecomment-1620207004
ALL SET
## CODE
```
try:
import sys, os, uuid
from pyspark.context import SparkContext
from pyspark.sql.session import SparkSession
from awsglue.context import GlueContext
from awsglue.job import Job
from awsglue.utils import getResolvedOptions
from pyspark.sql.types import *
from faker import Faker
except Exception as e:
print("Modules are missing: {}".format(e))
# Get command-line arguments
args = getResolvedOptions(sys.argv, ['JOB_NAME'])
# Create a Spark session and Glue context
spark = (SparkSession.builder.config('spark.serializer',
'org.apache.spark.serializer.KryoSerializer') \
.config('spark.sql.hive.convertMetastoreParquet', 'false') \
.config('spark.sql.catalog.spark_catalog',
'org.apache.spark.sql.hudi.catalog.HoodieCatalog') \
.config('spark.sql.extensions',
'org.apache.spark.sql.hudi.HoodieSparkSessionExtension') \
.config('spark.sql.legacy.pathOptionBehavior.enabled',
'true').getOrCreate())
sc = spark.sparkContext
glueContext = GlueContext(sc)
job = Job(glueContext)
logger = glueContext.get_logger()
job.init(args['JOB_NAME'], args)
# =================================INSERTING DATA
=====================================
global faker
faker = Faker()
class DataGenerator(object):
@staticmethod
def get_data():
return [
(
uuid.uuid4().__str__(),
faker.name(),
faker.random_element(elements=('IT', 'HR', 'Sales',
'Marketing')),
faker.random_element(elements=('CA', 'NY', 'TX', 'FL', 'IL',
'RJ')),
str(faker.random_int(min=10000, max=150000)),
str(faker.random_int(min=18, max=60)),
str(faker.random_int(min=0, max=100000)),
str(faker.unix_time()),
faker.email(),
faker.credit_card_number(card_type='amex'),
) for x in range(100)
]
data = DataGenerator.get_data()
columns = ["emp_id", "employee_name", "department", "state", "salary",
"age", "bonus", "ts", "email", "credit_card"]
spark_df = spark.createDataFrame(data=data, schema=columns)
# ============================== Settings
=======================================
db_name = "default"
table_name = "issue_8919"
recordkey = 'emp_id'
precombine = "ts"
PARTITION_FIELD = 'state'
path = "s3://soumilshah-hudi-demos/output/" + table_name
method = 'upsert'
table_type = "COPY_ON_WRITE"
#
====================================================================================
hudi_part_write_config = {
'className': 'org.apache.hudi',
"hoodie.schema.on.read.enable": "true",
"hoodie.datasource.write.reconcile.schema": "true",
"hoodie.avro.schema.external.transformation": "true",
'hoodie.avro.schema.validate': "true",
"hoodie.datasource.write.schema.allow.auto.evolution.column.drop":
"true",
'hoodie.table.name': table_name,
'hoodie.datasource.write.table.type': table_type,
'hoodie.datasource.write.operation': method,
'hoodie.datasource.write.recordkey.field': recordkey,
'hoodie.datasource.write.precombine.field': precombine,
'hoodie.datasource.hive_sync.mode': 'hms',
'hoodie.datasource.hive_sync.use_jdbc': 'false',
'hoodie.datasource.hive_sync.enable': 'true'
}
spark_df.write.format("hudi").options(**hudi_part_write_config).mode("append").save(path)
query_show_commits = f"call show_commits('{db_name}.{table_name}', 5)"
spark_df_commits = spark.sql(query_show_commits)
commits = list(map(lambda row: row[0], spark_df_commits.collect()))
spark_df_commits.show()
try:
print("Trying clustering 1..")
query_show_clustering = f"call run_clustering('{db_name}.{table_name}')"
spark_df_clusterings = spark.sql(query_show_clustering)
spark_df_clusterings.show()
print(" clustering 1 complete ")
except Exception as e:
print("Error 1", e)
raise e
try:
print("Try show clustering 2")
query = f"call show_clustering('{db_name}.{table_name}')"
result_df = spark.sql(query)
result_df.show()
print("Complete show clustering 2 ")
except Exception as e:
print("Error show clustering 2", e)
raise e
```
## 0/P
```
<html>
<body>
<!--StartFragment-->
+-----------------+-------------------+-----------------+-------------------+------------------------+---------------------+----------------------------+------------+\|
commit_time\|total_bytes_written\|total_files_added\|total_files_updated\|total_partitions_written\|total_records_written\|total_update_records_written\|total_errors\|+-----------------+-------------------+-----------------+-------------------+------------------------+---------------------+----------------------------+------------+\|20230704125519577\|
445969\| 1\| 0\|
1\| 100\| 0\|
0\|+-----------------+-------------------+-----------------+-------------------+------------------------+---------------------+----------------------------+------------+Trying
clustering 1..
--
+-----------------+----------------+---------+-------------------+\|
timestamp\|input_group_size\|
state\|involved_partitions\|+-----------------+----------------+---------+-------------------+\|20230704125731917\|
1\|COMPLETED\|
*\|+-----------------+----------------+---------+-------------------+
clustering 1 complete Try show clustering 2
+-----------------+----------------+---------+-------------------+\|
timestamp\|input_group_size\|
state\|involved_partitions\|+-----------------+----------------+---------+-------------------+\|20230704125731917\|
1\|COMPLETED\|
*\|+-----------------+----------------+---------+-------------------+
<!--EndFragment-->
</body>
</html>
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
