Skip to content

Switch to Apache Beam 2.74-SNAPSHOT #5932

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.

Sign up for GitHub

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

Draft
shnapz wants to merge 2 commits into
base: main
Choose a base branch
from
+22 −34
Draft

Switch to Apache Beam 2.74-SNAPSHOT #5932

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bb7a008
Switch to Apache Beam 2.74-SNAPSHOT
shnapz May 20, 2026
f52c2bc
move bigdataoss from 2 to 3
shnapz May 20, 2026
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
27 changes: 15 additions & 12 deletions build.sbt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,16 +28,17 @@ import org.typelevel.scalacoptions.JavaMajorVersion.javaMajorVersion

// To test release candidates, find the beam repo and add it as a resolver
// ThisBuild / resolvers += "apache-beam-staging" at "https://repository.apache.org/content/repositories/"
ThisBuild / resolvers += "Apache Snapshots" at "https://repository.apache.org/content/groups/snapshots/"
val beamVendorVersion = "0.1"
val beamVersion = "2.72.0"
val beamVersion = "2.74.0-SNAPSHOT"

// check version used by beam
// https://github.com/apache/beam/blob/v2.72.0/buildSrc/src/main/groovy/org/apache/beam/gradle/BeamModulePlugin.groovy
val autoServiceVersion = "1.0.1"
val autoValueVersion = "1.9"
val avroVersion = sys.props.getOrElse("avro.version", "1.11.5")
val bigdataossVersion = "2.2.26"
val bigdataoss3Version = "3.1.3"
val bigdataoss2Version = "2.2.26"
val bigdataoss3Version = "3.1.16"
val bigtableClientVersion = "1.28.0"
val commonsCodecVersion = "1.18.0"
val commonsCompressVersion = "1.26.2"
Expand All @@ -55,6 +56,7 @@ val jodaTimeVersion = "2.14.0"
val nettyVersion = "4.1.128.Final"
val protobufVersion = "4.33.2"
val slf4jVersion = "2.0.16"
val opentelemetryVersion = "1.56.0"
val zstdJniVersion = "1.5.6-3"
// dependent versions
val googleApiServicesBigQueryVersion = s"v2-rev20251012-$googleClientsVersion"
Expand Down Expand Up @@ -377,7 +379,8 @@ val bomSettings = Def.settings(
nettyBom,
slf4jBom,
dependencyOverrides ++=
beamBom.key.value.bomDependencies ++
Seq("io.opentelemetry" % "opentelemetry-context" % opentelemetryVersion) ++
beamBom.key.value.bomDependencies ++
gcpBom.key.value.bomDependencies ++
guavaBom.key.value.bomDependencies ++
jacksonBom.key.value.bomDependencies ++
Expand Down Expand Up @@ -730,9 +733,9 @@ lazy val `scio-core` = project
"org.apache.beam" % s"beam-runners-spark-$sparkMajorVersion" % beamVersion % Provided,
"org.apache.beam" % "beam-sdks-java-extensions-google-cloud-platform-core" % beamVersion % Provided,
"org.apache.hadoop" % "hadoop-common" % hadoopVersion % Provided,
"com.google.cloud.bigdataoss" % "gcs-connector" % s"hadoop2-$bigdataossVersion" % Provided,
"com.google.cloud.bigdataoss" % "gcsio" % bigdataossVersion % Provided,
"com.google.cloud.bigdataoss" % "util-hadoop" % s"hadoop2-$bigdataossVersion" % Provided,
"com.google.cloud.bigdataoss" % "gcs-connector" % s"hadoop2-$bigdataoss2Version" % Provided,
"com.google.cloud.bigdataoss" % "gcsio" % bigdataoss3Version % Provided,
"com.google.cloud.bigdataoss" % "util-hadoop" % s"hadoop2-$bigdataoss2Version" % Provided,
// test
"com.lihaoyi" %% "fansi" % fansiVersion % Test,
"com.lihaoyi" %% "pprint" % pprintVersion % Test,
Expand Down Expand Up @@ -937,7 +940,7 @@ lazy val `scio-google-cloud-platform` = project
"com.google.cloud" % "google-cloud-bigtable" % gcpBom.key.value,
"com.google.cloud" % "google-cloud-core" % gcpBom.key.value,
"com.google.cloud" % "google-cloud-spanner" % gcpBom.key.value,
"com.google.cloud.bigdataoss" % "util" % bigdataossVersion,
"com.google.cloud.bigdataoss" % "util" % bigdataoss3Version,
"com.google.cloud.bigtable" % "bigtable-client-core" % bigtableClientVersion,
"com.google.cloud.bigtable" % "bigtable-client-core-config" % bigtableClientVersion,
"com.google.guava" % "guava" % guavaVersion,
Expand Down Expand Up @@ -1219,7 +1222,7 @@ lazy val `scio-parquet` = project
// compile
"com.softwaremill.magnolia1_2" %% "magnolia" % magnoliaVersion,
"com.google.auth" % "google-auth-library-oauth2-http" % gcpBom.key.value,
"com.google.cloud.bigdataoss" % "util-hadoop" % s"hadoop2-$bigdataossVersion",
"com.google.cloud.bigdataoss" % "util-hadoop" % s"hadoop2-$bigdataoss2Version",
"com.google.protobuf" % "protobuf-java" % protobufVersion,
"com.spotify" %% "magnolify-parquet" % magnolifyVersion,
"com.twitter" %% "chill" % chillVersion,
Expand All @@ -1240,7 +1243,7 @@ lazy val `scio-parquet` = project
"org.slf4j" % "slf4j-api" % slf4jBom.key.value,
// provided
"org.tensorflow" % "tensorflow-core-native" % tensorFlowVersion % Provided,
"com.google.cloud.bigdataoss" % "gcs-connector" % s"hadoop2-$bigdataossVersion" % Provided,
"com.google.cloud.bigdataoss" % "gcs-connector" % s"hadoop2-$bigdataoss2Version" % Provided,
// runtime
"org.apache.hadoop" % "hadoop-client" % hadoopVersion % Runtime excludeAll (Exclude.metricsCore),
"io.dropwizard.metrics" % "metrics-core" % metricsVersion % Runtime,
Expand Down Expand Up @@ -1409,7 +1412,7 @@ lazy val `scio-examples` = project
"com.google.apis" % "google-api-services-pubsub" % googleApiServicesPubsubVersion,
"com.google.auth" % "google-auth-library-credentials" % gcpBom.key.value,
"com.google.auth" % "google-auth-library-oauth2-http" % gcpBom.key.value,
"com.google.cloud.bigdataoss" % "util" % bigdataossVersion,
"com.google.cloud.bigdataoss" % "util" % bigdataoss3Version,
"com.google.code.findbugs" % "jsr305" % jsr305Version,
"com.google.guava" % "guava" % guavaVersion,
"com.google.http-client" % "google-http-client" % gcpBom.key.value,
Expand Down Expand Up @@ -1447,7 +1450,7 @@ lazy val `scio-examples` = project
"org.tensorflow" % "tensorflow-core-native" % tensorFlowVersion,
"redis.clients" % "jedis" % jedisVersion,
// runtime
"com.google.cloud.bigdataoss" % "gcs-connector" % s"hadoop2-$bigdataossVersion" % Runtime,
"com.google.cloud.bigdataoss" % "gcs-connector" % s"hadoop2-$bigdataoss2Version" % Runtime,
"com.google.cloud.sql" % "mysql-socket-factory-connector-j-8" % "1.28.2" % Runtime,
// test
"org.scalacheck" %% "scalacheck" % scalacheckVersion % Test
Expand Down
29 changes: 7 additions & 22 deletions scio-core/src/main/scala/com/spotify/scio/ScioContext.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -473,12 +473,12 @@ class ScioContext private[scio] (
.pipe(o =>
Option(config.get(GfsConfig.GCS_INPUT_STREAM_FAST_FAIL_ON_NOT_FOUND_ENABLE.getKey))
.map(_.toBoolean)
.fold(o)(o.setFastFailOnNotFound)
.fold(o)(o.setFastFailOnNotFoundEnabled)
)
.pipe(o =>
Option(config.get(GfsConfig.GCS_INPUT_STREAM_SUPPORT_GZIP_ENCODING_ENABLE.getKey))
.map(_.toBoolean)
.fold(o)(o.setSupportGzipEncoding)
.fold(o)(o.setGzipEncodingSupportEnabled)
)
.pipe(o =>
Option(config.get(GfsConfig.GCS_INPUT_STREAM_INPLACE_SEEK_LIMIT.getKey))
Expand All @@ -492,7 +492,7 @@ class ScioContext private[scio] (
)
.pipe(o =>
Option(config.get(GfsConfig.GCS_INPUT_STREAM_MIN_RANGE_REQUEST_SIZE.getKey))
.map(_.toInt)
.map(_.toLong)
.fold(o)(o.setMinRangeRequestSize)
)
.pipe(o =>
Expand All @@ -502,34 +502,19 @@ class ScioContext private[scio] (
)
.pipe(o =>
Option(config.get(GfsConfig.GCS_GRPC_READ_TIMEOUT_MS.getKey))
.map(_.toLong)
.fold(o)(o.setGrpcReadTimeoutMillis)
.map(ms => java.time.Duration.ofMillis(ms.toLong))
.fold(o)(o.setGrpcReadTimeout)
)
.pipe(o =>
Option(config.get(GfsConfig.GCS_GRPC_READ_MESSAGE_TIMEOUT_MS.getKey))
.map(_.toLong)
.fold(o)(o.setGrpcReadMessageTimeoutMillis)
)
.pipe(o =>
Option(config.get(GfsConfig.GCS_GRPC_READ_METADATA_TIMEOUT_MS.getKey))
.map(_.toLong)
.fold(o)(o.setGrpcReadMetadataTimeoutMillis)
.map(ms => java.time.Duration.ofMillis(ms.toLong))
.fold(o)(o.setGrpcReadMessageTimeout)
)
.pipe(o =>
Option(config.get(GfsConfig.GCS_GRPC_READ_ZEROCOPY_ENABLE.getKey))
.map(_.toBoolean)
.fold(o)(o.setGrpcReadZeroCopyEnabled)
)
.pipe(o =>
Option(config.get(GfsConfig.GCS_TRACE_LOG_ENABLE.getKey))
.map(_.toBoolean)
.fold(o)(o.setTraceLogEnabled)
)
.pipe(o =>
Option(config.get(GfsConfig.GCS_TRACE_LOG_TIME_THRESHOLD_MS.getKey))
.map(_.toLong)
.fold(o)(o.setTraceLogTimeThreshold)
)
.build()
)
} catch {
Expand Down
Loading