Skip to content

feat: basic hudi support #437

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 27, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
63 changes: 27 additions & 36 deletions cloud_aws/BUILD.bazel
Original file line number Diff line number Diff line change
@@ -1,3 +1,24 @@
shared_libs = [
maven_artifact("software.amazon.awssdk:dynamodb"),
maven_artifact("software.amazon.awssdk:regions"),
maven_artifact("software.amazon.awssdk:aws-core"),
maven_artifact("software.amazon.awssdk:sdk-core"),
maven_artifact("software.amazon.awssdk:utils"),
maven_artifact("com.google.guava:guava"),
maven_artifact("org.slf4j:slf4j-api"),
maven_artifact("org.apache.hudi:hudi-aws-bundle"),
maven_artifact("junit:junit"),
maven_artifact("com.novocode:junit-interface"),
maven_artifact("com.fasterxml.jackson.module:jackson-module-afterburner"),
scala_artifact_with_suffix("org.apache.hudi:hudi-spark3.5-bundle"),
scala_artifact_with_suffix("org.scala-lang.modules:scala-collection-compat"),
"//api:lib",
"//api:thrift_java",
"//online:lib",
"//spark:lib",
"//tools/build_rules/spark:spark-exec",
]

scala_library(
name = "cloud_aws_lib",
srcs = glob(["src/main/**/*.scala"]),
Expand All @@ -6,54 +27,24 @@ scala_library(
"//conditions:default": True, # Enable for other versions
}),
visibility = ["//visibility:public"],
deps = [
maven_artifact("software.amazon.awssdk:dynamodb"),
maven_artifact("software.amazon.awssdk:regions"),
maven_artifact("software.amazon.awssdk:aws-core"),
maven_artifact("software.amazon.awssdk:sdk-core"),
maven_artifact("software.amazon.awssdk:utils"),
maven_artifact("com.google.guava:guava"),
maven_artifact("org.slf4j:slf4j-api"),
scala_artifact_with_suffix("org.scala-lang.modules:scala-collection-compat"),
"//api:lib",
"//api:thrift_java",
"//online:lib",
"//spark:lib",
],
deps = shared_libs,
)

test_deps = [
":cloud_aws_lib",
"//api:lib",
"//online:lib",
maven_artifact("software.amazon.awssdk:dynamodb"),
maven_artifact("software.amazon.awssdk:regions"),
maven_artifact("software.amazon.awssdk:aws-core"),
maven_artifact("software.amazon.awssdk:sdk-core"),
maven_artifact("software.amazon.awssdk:utils"),
maven_artifact("com.amazonaws:DynamoDBLocal"),
maven_artifact("org.mockito:mockito-core"),
maven_artifact("software.amazon.awssdk:auth"),
maven_artifact("software.amazon.awssdk:identity-spi"),
scala_artifact_with_suffix("org.typelevel:cats-core"),
maven_artifact("com.amazonaws:DynamoDBLocal"),
scala_artifact_with_suffix("com.chuusai:shapeless"),
scala_artifact_with_suffix("org.typelevel:cats-core"),
scala_artifact_with_suffix("org.mockito:mockito-scala"),
] + _CIRCE_DEPS + _SCALA_TEST_DEPS

scala_library(
name = "test_lib",
srcs = glob(["src/test/**/*.scala"]),
format = select({
"//tools/config:scala_2_13": False, # Disable for 2.13
"//conditions:default": True, # Enable for other versions
}),
visibility = ["//visibility:public"],
deps = test_deps,
)

scala_test_suite(
name = "tests",
srcs = glob(["src/test/**/*.scala"]),
# defined in prelude_bazel file
jvm_flags = _JVM_FLAGS_FOR_ACCESSING_BASE_JAVA_CLASSES,
visibility = ["//visibility:public"],
deps = test_deps + [":test_lib"],
deps = shared_libs + test_deps + [":cloud_aws_lib"],
)
Original file line number Diff line number Diff line change
@@ -0,0 +1,38 @@
package ai.chronon.integrations.aws


import ai.chronon.spark.{SparkSessionBuilder, TableUtils, ChrononHudiKryoRegistrator}
import org.apache.spark.sql.{SaveMode, SparkSession}
import org.junit.Assert.assertEquals
import org.scalatest.flatspec.AnyFlatSpec
import org.scalatestplus.mockito.MockitoSugar

class GlueCatalogTest extends AnyFlatSpec with MockitoSugar {

lazy val spark: SparkSession = SparkSessionBuilder.build(
classOf[GlueCatalogTest].getSimpleName,
local = true,
additionalConfig = Some(
Map(
"spark.sql.catalog.spark_catalog" -> "org.apache.spark.sql.hudi.catalog.HoodieCatalog",
"spark.sql.extensions" -> "org.apache.spark.sql.hudi.HoodieSparkSessionExtension",
"spark.kryo.registrator"-> classOf[ChrononHudiKryoRegistrator].getName,
))
)
lazy val tableUtils: TableUtils = TableUtils(spark)

"basic round trip hudi table" should "work with local metastore" in {
import spark.implicits._

val input = Set(1,2,3,4)
val sourceDF = spark.sparkContext.parallelize(input.toSeq).toDF("id")

sourceDF.write.format("hudi")
.mode(SaveMode.Overwrite)
.saveAsTable("test_hudi_table")

val back = spark.table("test_hudi_table").select("id").as[Int].collect()
assertEquals(input, back.toSet)

}
}
Loading