Skip to content

[SPARK-54002][DEPLOY] Support integrating BeeLine with Connect JDBC driver #52706

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

Closed
wants to merge 2 commits into from
Closed

[SPARK-54002][DEPLOY] Support integrating BeeLine with Connect JDBC driver #52706

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
c8a66f8
[SPARK-54002][DEPLOY] Support integrating BeeLine with Connect JDBC d…
pan3793 Oct 23, 2025
1b1a48f
Add a flag SPARK_CONNECT_BEELINE
pan3793 Oct 27, 2025
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
2 changes: 2 additions & 0 deletions dev/make-distribution.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,9 +322,11 @@ if [ "$MAKE_TGZ" == "true" ]; then
rm -rf "$TARDIR"
cp -r "$DISTDIR" "$TARDIR"
# Set the Spark Connect system variable in these scripts to enable it by default.
awk 'NR==1{print; print "export SPARK_CONNECT_BEELINE=${SPARK_CONNECT_BEELINE:-1}"; next} {print}' "$TARDIR/bin/beeline" > tmp && cat tmp > "$TARDIR/bin/beeline"
awk 'NR==1{print; print "export SPARK_CONNECT_MODE=${SPARK_CONNECT_MODE:-1}"; next} {print}' "$TARDIR/bin/pyspark" > tmp && cat tmp > "$TARDIR/bin/pyspark"
awk 'NR==1{print; print "export SPARK_CONNECT_MODE=${SPARK_CONNECT_MODE:-1}"; next} {print}' "$TARDIR/bin/spark-shell" > tmp && cat tmp > "$TARDIR/bin/spark-shell"
awk 'NR==1{print; print "export SPARK_CONNECT_MODE=${SPARK_CONNECT_MODE:-1}"; next} {print}' "$TARDIR/bin/spark-submit" > tmp && cat tmp > "$TARDIR/bin/spark-submit"
awk 'NR==1{print; print "if [%SPARK_CONNECT_BEELINE%] == [] set SPARK_CONNECT_BEELINE=1"; next} {print}' "$TARDIR/bin/beeline.cmd" > tmp && cat tmp > "$TARDIR/bin/beeline.cmd"
awk 'NR==1{print; print "if [%SPARK_CONNECT_MODE%] == [] set SPARK_CONNECT_MODE=1"; next} {print}' "$TARDIR/bin/pyspark2.cmd" > tmp && cat tmp > "$TARDIR/bin/pyspark2.cmd"
awk 'NR==1{print; print "if [%SPARK_CONNECT_MODE%] == [] set SPARK_CONNECT_MODE=1"; next} {print}' "$TARDIR/bin/spark-shell2.cmd" > tmp && cat tmp > "$TARDIR/bin/spark-shell2.cmd"
awk 'NR==1{print; print "if [%SPARK_CONNECT_MODE%] == [] set SPARK_CONNECT_MODE=1"; next} {print}' "$TARDIR/bin/spark-submit2.cmd" > tmp && cat tmp > "$TARDIR/bin/spark-submit2.cmd"
Expand Down
18 changes: 12 additions & 6 deletions launcher/src/main/java/org/apache/spark/launcher/AbstractCommandBuilder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,8 @@ abstract class AbstractCommandBuilder {
*/
protected boolean isRemote = System.getenv().containsKey("SPARK_REMOTE");

protected boolean isBeeLine = false;

AbstractCommandBuilder() {
this.appArgs = new ArrayList<>();
this.childEnv = new HashMap<>();
Expand Down Expand Up @@ -195,6 +197,10 @@ List<String> buildClassPath(String appClassPath) throws IOException {
if (isRemote && "1".equals(getenv("SPARK_SCALA_SHELL")) && project.equals("sql/core")) {
continue;
}
if (isBeeLine && "1".equals(getenv("SPARK_CONNECT_BEELINE")) &&
project.equals("sql/core")) {
continue;
}
// SPARK-49534: The assumption here is that if `spark-hive_xxx.jar` is not in the
// classpath, then the `-Phive` profile was not used during package, and therefore
// the Hive-related jars should also not be in the classpath. To avoid failure in
Expand Down Expand Up @@ -241,13 +247,13 @@ List<String> buildClassPath(String appClassPath) throws IOException {
}
}

if (isRemote) {
if (isRemote || (isBeeLine && "1".equals(getenv("SPARK_CONNECT_BEELINE")))) {
for (File f: new File(jarsDir).listFiles()) {
// Exclude Spark Classic SQL and Spark Connect server jars
// if we're in Spark Connect Shell. Also exclude Spark SQL API and
// Spark Connect Common which Spark Connect client shades.
// Then, we add the Spark Connect shell and its dependencies in connect-repl
// See also SPARK-48936.
// Exclude Spark Classic SQL and Spark Connect server jars if we're in
// Spark Connect Shell or BeeLine with Connect JDBC driver. Also exclude
// Spark SQL API and Spark Connect Common which Spark Connect client shades.
// Then, we add the Spark Connect shell and its dependencies in connect-repl.
// See also SPARK-48936, SPARK-54002.
if (f.isDirectory() && f.getName().equals("connect-repl")) {
addToClassPath(cp, join(File.separator, f.toString(), "*"));
} else if (
Expand Down
3 changes: 3 additions & 0 deletions launcher/src/main/java/org/apache/spark/launcher/SparkClassCommandBuilder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,9 @@ class SparkClassCommandBuilder extends AbstractCommandBuilder {
SparkClassCommandBuilder(String className, List<String> classArgs) {
this.className = className;
this.classArgs = classArgs;
if ("org.apache.hive.beeline.BeeLine".equals(className)) {
this.isBeeLine = true;
}
}

@Override
Expand Down