ad1happy2go commented on issue #6341:
URL: https://github.com/apache/hudi/issues/6341#issuecomment-1540480920
@neeruks @rjmblc Can you please try with later versions of Hudi. I see it
is all working seemlesly even with both the settings.
```
from pyspark.sql.types import *
from pyspark.sql.functions import *
import time
from datetime import datetime
from pyspark.sql import SparkSession
from pyspark.sql import Row
from datetime import date
spark = SparkSession \
.builder \
.master("local[1]") \
.config("spark.driver.memory", "8g") \
.config("spark.jars.packages",
"org.apache.hudi:hudi-spark3.2-bundle_2.12:0.13.0") \
.config("spark.sql.extensions",
"org.apache.spark.sql.hudi.HoodieSparkSessionExtension") \
.config("spark.sql.catalog.spark_catalog",
"org.apache.spark.sql.hudi.catalog.HoodieCatalog") \
.config("spark.serializer",
"org.apache.spark.serializer.KryoSerializer") \
.getOrCreate()
common_config={
"hoodie.datasource.write.table.type": "MERGE_ON_READ",
"hoodie.datasource.write.recordkey.field": "id",
"hoodie.datasource.write.precombine.field": "timestamp",
"hoodie.datasource.write.partitionpath.field": "id",
'hoodie.table.name': 'issue_8625',
"hoodie.datasource.write.payload.class":
"org.apache.hudi.common.model.OverwriteWithLatestAvroPayload"
}
# Define the schema
schema = StructType([
StructField("id", IntegerType(), True),
StructField("b", IntegerType(), True),
StructField("c", StringType(), True),
StructField("d", DateType(), True),
StructField("timestamp", TimestampType(), True),
StructField("f", StringType(), True)
])
df = spark.createDataFrame([
Row(id=1, b=2, c='string1', d=date(2000, 1, 1),
timestamp=datetime.strptime("2000-01-01 12:00:00", '%Y-%m-%d %H:%M:%S'), f =
"2000-01-01 12:00:00"),
Row(id=2, b=3, c='string2', d=date(2000, 2, 1),
timestamp=datetime.strptime("2000-01-01 12:00:00", '%Y-%m-%d %H:%M:%S'), f =
"2000-01-01 12:21:20"),
Row(id=4, b=5, c='string3', d=date(2000, 3, 1),
timestamp=datetime.strptime("2000-01-01 12:00:00", '%Y-%m-%d %H:%M:%S'), f =
"2000-01-03 12:00:00")
], schema)
path = "file:///tmp/issue_6341_5"
df.write.format("org.apache.hudi") \
.options(**common_config) \
.mode("append") \
.save(path)
spark.read.format("hudi").load(path).show()
newdf = spark.createDataFrame([
Row(id=1, b=16, c=None, d=None, timestamp=datetime.strptime("2000-01-01
12:35:00", '%Y-%m-%d %H:%M:%S'), f=None)
], schema)
newdf.write.format("org.apache.hudi") \
.options(**common_config) \
.option("hoodie.datasource.write.operation", "delete") \
.option('hoodie.datasource.write.payload.class',
'org.apache.hudi.common.model.EmptyHoodieRecordPayload') \
.mode("append") \
.save(path)
spark.read.format("hudi").load(path).show()
```
--
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]
