From bdb7704b2b19fcfdfdd79bdeee4894700cbc4878 Mon Sep 17 00:00:00 2001
From: Wenchen Fan <wenchen@databricks.com>
Date: Tue, 11 Feb 2025 08:52:43 +0800
Subject: [PATCH] [SPARK-51146][INFRA] Publish a new Spark distribution with
 Spark Connect enabled (step 1)

### What changes were proposed in this pull request?

This PR is the first step to update the release scripts to publish a new distribution with spark connect enabled. I need to merge it first because the release process invokes the `make-distribution.sh` script in the upstream branch-4.0, and I can't test my change locally with dry-run mode.

### Why are the changes needed?

to publish a new Spark distribution with Spark Connect enabled

### Does this PR introduce _any_ user-facing change?

no

### How was this patch tested?

manual test to make sure `dev/create-release/release-build.sh` is working as expected.

### Was this patch authored or co-authored using generative AI tooling?

no

Closes #49865 from cloud-fan/release.

Authored-by: Wenchen Fan <wenchen@databricks.com>
Signed-off-by: Wenchen Fan <wenchen@databricks.com>
(cherry picked from commit 79db110ef701a929344c03b2a8a37e951aafa081)
Signed-off-by: Wenchen Fan <wenchen@databricks.com>
---
 dev/create-release/release-build.sh | 13 +++++++++++--
 dev/make-distribution.sh            | 20 +++++++++++++++++++-
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/dev/create-release/release-build.sh b/dev/create-release/release-build.sh
index 8654c8317ae49..a378f790572b5 100755
--- a/dev/create-release/release-build.sh
+++ b/dev/create-release/release-build.sh
@@ -276,6 +276,10 @@ if [[ "$1" == "package" ]]; then
     if [[ $BUILD_PACKAGE == *"withr"* ]]; then
       R_FLAG="--r"
     fi
+    SPARK_CONNECT_FLAG=""
+    if [[ $BUILD_PACKAGE == *"withconnect"* ]]; then
+      SPARK_CONNECT_FLAG="--connect"
+    fi
 
     echo "Building binary dist $NAME"
     cp -r spark spark-$SPARK_VERSION-bin-$NAME
@@ -295,7 +299,7 @@ if [[ "$1" == "package" ]]; then
 
     echo "Creating distribution"
     ./dev/make-distribution.sh --name $NAME --mvn $MVN_HOME/bin/mvn --tgz \
-      $PIP_FLAG $R_FLAG $FLAGS 2>&1 >  ../binary-release-$NAME.log
+      $PIP_FLAG $R_FLAG $SPARK_CONNECT_FLAG $FLAGS 2>&1 >  ../binary-release-$NAME.log
     cd ..
 
     if [[ -n $R_FLAG ]]; then
@@ -353,7 +357,12 @@ if [[ "$1" == "package" ]]; then
   fi
 
   declare -A BINARY_PKGS_EXTRA
-  BINARY_PKGS_EXTRA["hadoop3"]="withpip,withr"
+  if [[ $SPARK_VERSION > "3.5.99" ]]; then
+    # Since 4.0, we publish a new distribution with Spark Connect enable.
+    BINARY_PKGS_EXTRA["hadoop3"]="withpip,withr,withconnect"
+  else
+    BINARY_PKGS_EXTRA["hadoop3"]="withpip,withr"
+  fi
 
   # This is dead code as Scala 2.12 is no longer supported, but we keep it as a template for
   # adding new Scala version support in the future. This secondary Scala version only has one
diff --git a/dev/make-distribution.sh b/dev/make-distribution.sh
index 53c317a39ea1e..46509dc530fc7 100755
--- a/dev/make-distribution.sh
+++ b/dev/make-distribution.sh
@@ -35,6 +35,7 @@ DISTDIR="$SPARK_HOME/dist"
 MAKE_TGZ=false
 MAKE_PIP=false
 MAKE_R=false
+MAKE_SPARK_CONNECT=false
 NAME=none
 MVN="$SPARK_HOME/build/mvn"
 
@@ -43,7 +44,7 @@ function exit_with_usage {
   echo "make-distribution.sh - tool for making binary distributions of Spark"
   echo ""
   echo "usage:"
-  cl_options="[--name] [--tgz] [--pip] [--r] [--mvn <mvn-command>]"
+  cl_options="[--name] [--tgz] [--pip] [--r] [--connect] [--mvn <mvn-command>]"
   echo "make-distribution.sh $cl_options <maven build options>"
   echo "See Spark's \"Building Spark\" doc for correct Maven options."
   echo ""
@@ -62,6 +63,9 @@ while (( "$#" )); do
     --r)
       MAKE_R=true
       ;;
+    --connect)
+      MAKE_SPARK_CONNECT=true
+      ;;
     --mvn)
       MVN="$2"
       shift
@@ -308,4 +312,18 @@ if [ "$MAKE_TGZ" == "true" ]; then
   fi
   $TAR -czf "spark-$VERSION-bin-$NAME.tgz" -C "$SPARK_HOME" "$TARDIR_NAME"
   rm -rf "$TARDIR"
+  if [[ "$MAKE_SPARK_CONNECT" == "true" ]]; then
+    TARDIR_NAME=spark-$VERSION-bin-$NAME-spark-connect
+    TARDIR="$SPARK_HOME/$TARDIR_NAME"
+    rm -rf "$TARDIR"
+    cp -r "$DISTDIR" "$TARDIR"
+    sed -i -e '$s/.*/export SPARK_CONNECT_MODE=1\
+    &/' "$TARDIR/bin/pyspark"
+    sed -i -e '$s/.*/export SPARK_CONNECT_MODE=1\
+    &/' "$TARDIR/bin/spark-shell"
+    sed -i -e '$s/.*/export SPARK_CONNECT_MODE=1\
+    &/' "$TARDIR/bin/spark-submit"
+    $TAR -czf "$TARDIR_NAME.tgz" -C "$SPARK_HOME" "$TARDIR_NAME"
+    rm -rf "$TARDIR"
+  fi
 fi