在 AWS Glue 中使用 Iceberg 架構

# Example: Create an Iceberg table from a DataFrame 
# and register the table to Glue Data Catalog

dataFrame.createOrReplaceTempView("tmp_<your_table_name>")

query = f"""
CREATE TABLE glue_catalog.<your_database_name>.<your_table_name>
USING iceberg
TBLPROPERTIES ("format-version"="2")
AS SELECT * FROM tmp_<your_table_name>
"""
spark.sql(query)

// Example: Example: Create an Iceberg table from a DataFrame
// and register the table to Glue Data Catalog

dataFrame.createOrReplaceTempView("tmp_<your_table_name>")

val query = """CREATE TABLE glue_catalog.<your_database_name>.<your_table_name>
USING iceberg
TBLPROPERTIES ("format-version"="2")
AS SELECT * FROM tmp_<your_table_name>
"""
spark.sql(query)

# Example: Write an Iceberg table to S3 on the Glue Data Catalog

# Create (equivalent to CREATE TABLE AS SELECT)
dataFrame.writeTo("glue_catalog.databaseName.tableName") \
    .tableProperty("format-version", "2") \
    .create()

# Append (equivalent to INSERT INTO)
dataFrame.writeTo("glue_catalog.databaseName.tableName") \
    .tableProperty("format-version", "2") \
    .append()

// Example: Write an Iceberg table to S3 on the Glue Data Catalog

// Create (equivalent to CREATE TABLE AS SELECT)
dataFrame.writeTo("glue_catalog.databaseName.tableName")
    .tableProperty("format-version", "2")
    .create()

// Append (equivalent to INSERT INTO)
dataFrame.writeTo("glue_catalog.databaseName.tableName")
    .tableProperty("format-version", "2")
    .append()

在此範例中，使用 GlueContext.create_data_frame.from_catalog() 方法。

# Example: Read an Iceberg table from Glue Data Catalog

from awsglue.context import GlueContext
from pyspark.context import SparkContext

sc = SparkContext()
glueContext = GlueContext(sc)

df = glueContext.create_data_frame.from_catalog(
    database="<your_database_name>",
    table_name="<your_table_name>",
    additional_options=additional_options
)

在此範例中，使用 getCatalogSource 方法。

// Example: Read an Iceberg table from Glue Data Catalog

import com.amazonaws.services.glue.GlueContext
import org.apacke.spark.SparkContext

object GlueApp {
  def main(sysArgs: Array[String]): Unit = {
    val spark: SparkContext = new SparkContext()
    val glueContext: GlueContext = new GlueContext(spark)
    val df = glueContext.getCatalogSource("<your_database_name>", "<your_table_name>",
      additionalOptions = additionalOptions)
      .getDataFrame()
  }
}

在此範例中，使用 GlueContext.write_data_frame.from_catalog() 方法。

# Example: Insert into an Iceberg table from Glue Data Catalog

from awsglue.context import GlueContext
from pyspark.context import SparkContext

sc = SparkContext()
glueContext = GlueContext(sc)

glueContext.write_data_frame.from_catalog(
    frame=dataFrame,
    database="<your_database_name>",
    table_name="<your_table_name>",
    additional_options=additional_options
)

在此範例中，使用 getCatalogSink 方法。

// Example: Insert into an Iceberg table from Glue Data Catalog

import com.amazonaws.services.glue.GlueContext
import org.apacke.spark.SparkContext

object GlueApp {
  def main(sysArgs: Array[String]): Unit = {
    val spark: SparkContext = new SparkContext()
    val glueContext: GlueContext = new GlueContext(spark)
    glueContext.getCatalogSink("<your_database_name>", "<your_table_name>",
      additionalOptions = additionalOptions)
      .writeDataFrame(dataFrame, glueContext)
  }
}

# Example: Read an Iceberg table on S3 as a DataFrame from the Glue Data Catalog

dataFrame = spark.read.format("iceberg").load("glue_catalog.databaseName.tableName")

// Example: Read an Iceberg table on S3 as a DataFrame from the Glue Data Catalog

val dataFrame = spark.read.format("iceberg").load("glue_catalog.databaseName.tableName")