knowxyz opened a new issue, #12802:
URL: https://github.com/apache/iceberg/issues/12802
from pyspark.sql import SparkSession
spark1 = SparkSession.builder \
.appName("IcebergSave") \
.config("spark.sql.extensions",
"org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions") \
.config("spark.sql.catalog.abccatalog",
"org.apache.iceberg.spark.SparkCatalog") \
.config("spark.sql.catalog.abccatalog.type", "hadoop") \
.config("spark.jars.packages",
"org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.4.3") \
.config("spark.sql.catalog.abccatalog.warehouse",
f"{mount_point}/mywarehouse").getOrCreate()
spark1.conf.set(f"fs.azure.account.key.{storage_account_name}.blob.core.windows.net",
storage_account_key)
spark1.conf.set("spark.sql.parquet.enableVectorizedReader", "false")
spark1.conf.set("spark.sql.iceberg.vectorization.enabled", "false")
df = < read data from some source>
savetable ="abccatalog.default.table1"
# Write to Iceberg table with partitioning
df.createOrReplaceTempView("tempview1")
# Query the temporary view using SQL
resultdf1 = spark1.sql("SELECT * FROM tempview1")
# only iceberg here
resultdf1.write.format("iceberg").mode("overwrite").saveAsTable(savetable)
dfread =
spark.read.format("org.apache.iceberg.spark.source.IcebergSource").option("header",
"true").load(savetable)
show = dfread.show()
print(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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
