在 Amazon Glue 中使用 Delta Lake 框架

# Example: Create a Delta Lake table from a DataFrame 
# and register the table to Glue Data Catalog

additional_options = {
    "path": "s3://<s3Path>"
}
dataFrame.write \
    .format("delta") \
    .options(**additional_options) \
    .mode("append") \
    .partitionBy("<your_partitionkey_field>") \
    .saveAsTable("<your_database_name>.<your_table_name>")

// Example: Example: Create a Delta Lake table from a DataFrame
// and register the table to Glue Data Catalog

val additional_options = Map(
  "path" -> "s3://<s3Path>"
)
dataFrame.write.format("delta")
  .options(additional_options)
  .mode("append")
  .partitionBy("<your_partitionkey_field>")
  .saveAsTable("<your_database_name>.<your_table_name>")

在本示例中，使用 create_data_frame.from_catalog 方法。

# Example: Read a Delta Lake 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
)

在本示例中，使用 getCatalogSource 方法。

// Example: Read a Delta Lake 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()
  }
}

在本示例中，使用 write_data_frame.from_catalog 方法。

# Example: Insert into a Delta Lake table in S3 using 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
)

在本示例中，使用 getCatalogSink 方法。

// Example: Insert into a Delta Lake table in S3 using 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 a Delta Lake table from S3 using a Spark DataFrame

dataFrame = spark.read.format("delta").load("s3://<s3path/>")

// Example: Read a Delta Lake table from S3 using a Spark DataFrame

val dataFrame = spark.read.format("delta").load("s3://<s3path/>")

# Example: Write a Delta Lake table to S3 using a Spark DataFrame

dataFrame.write.format("delta") \
    .options(**additional_options) \
    .mode("overwrite") \
    .partitionBy("<your_partitionkey_field>")
    .save("s3://<s3Path>")

// Example: Write a Delta Lake table to S3 using a Spark DataFrame

dataFrame.write.format("delta")
  .options(additionalOptions)
  .mode("overwrite")
  .partitionBy("<your_partitionkey_field>")
  .save("s3://<s3path/>")