soumilshah1995 commented on issue #8040:
URL: https://github.com/apache/hudi/issues/8040#issuecomment-1497383266
The complete example is provided above; if you require more details, please
let me know.
# Code
```
"""
--conf spark.serializer=org.apache.spark.serializer.KryoSerializer --conf
spark.sql.hive.convertMetastoreParquet=false --conf
spark.sql.hive.convertMetastoreParquet=false --conf
spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog
--conf spark.sql.legacy.pathOptionBehavior.enabled=true
"""
try:
import sys
import os
from pyspark.context import SparkContext
from pyspark.sql.session import SparkSession
from awsglue.context import GlueContext
from awsglue.job import Job
from awsglue.dynamicframe import DynamicFrame
from pyspark.sql.functions import col, to_timestamp,
monotonically_increasing_id, to_date, when
from pyspark.sql.functions import *
from awsglue.utils import getResolvedOptions
from pyspark.sql.types import *
from datetime import datetime, date
import boto3
from functools import reduce
from pyspark.sql import Row
import uuid
from faker import Faker
except Exception as e:
print("Modules are missing : {} ".format(e))
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()
# =================================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 = "hudidb"
table_name = "employees"
recordkey = 'emp_id'
precombine = "ts"
PARTITION_FIELD = 'state'
path = "s3://hudi-demos-emr-serverless-project-soumil/tmp1/"
method = 'upsert'
table_type = "MERGE_ON_READ"
#
====================================================================================
hudi_part_write_config = {
'className': 'org.apache.hudi',
'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.schema.on.read.enable":"true",
"hoodie.datasource.write.reconcile.schema":"true",
'hoodie.datasource.hive_sync.mode': 'hms',
'hoodie.datasource.hive_sync.enable': 'true',
'hoodie.datasource.hive_sync.use_jdbc': 'false',
'hoodie.datasource.hive_sync.support_timestamp': 'false',
'hoodie.datasource.hive_sync.database': db_name,
'hoodie.datasource.hive_sync.table': table_name,
}
spark_df.write.format("hudi").options(**hudi_part_write_config).mode("append").save(path)
# ================================================================
# Adding NEW COLUMN
# ================================================================
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'),
faker.date().__str__()
) for x in range(100)
]
data = DataGenerator.get_data()
columns = ["emp_id", "employee_name", "department", "state", "salary",
"age", "bonus", "ts", "email", "credit_card",
"new_date_col"]
spark_df = spark.createDataFrame(data=data, schema=columns)
spark_df.write.format("hudi").options(**hudi_part_write_config).mode("append").save(path)
try:
print("Try1")
table_name_test = f"{table_name}_ro"
query = f"alter table {db_name}.{table_name_test} drop column
credit_card"
spark.sql(query)
except Exception as e:
print("ERR1", e)
try:
print("Try2")
table_name_test = f"{table_name}_rt"
query = f"alter table {db_name}.{table_name_test} drop column
credit_card"
spark.sql(query)
except Exception as e:
print("ERR2", e)
```
--
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]
