Skip to content

Commit 8806684

Browse files
committed
add OpenLineage Spark dependency
1 parent 370d3ca commit 8806684

File tree

3 files changed

+18
-7
lines changed

3 files changed

+18
-7
lines changed

compose-flex.yml

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -245,9 +245,10 @@ services:
245245
- ./resources/spark/log4j2.properties:/opt/spark/conf/log4j2.properties:ro
246246
- ./resources/spark/hive-site.xml:/opt/spark/conf/hive-site.xml
247247
- ./resources/spark/core-site.xml:/opt/spark/conf/core-site.xml
248-
# Iceberg & Hadoop dependencies
248+
# Iceberg, Hadoop & OpenLineage dependencies
249249
- ./resources/deps/spark/iceberg/iceberg-spark-runtime-3.5_2.12-1.8.1.jar:/opt/spark/jars/iceberg-spark-runtime-3.5_2.12-1.8.1.jar
250250
- ./resources/deps/spark/iceberg/iceberg-aws-bundle-1.8.1.jar:/opt/spark/jars/iceberg-aws-bundle-1.8.1.jar
251+
- ./resources/deps/spark/lineage/openlineage-spark_2.12-1.37.0.jar:/opt/spark/jars/openlineage-spark_2.12-1.37.0.jar
251252
- ./resources/deps/hadoop/hadoop-aws-3.3.6.jar:/opt/spark/jars/hadoop-aws-3.3.6.jar
252253
- ./resources/deps/hadoop/aws-java-sdk-bundle-1.11.1026.jar:/opt/spark/jars/aws-java-sdk-bundle-1.11.1026.jar
253254
- ./resources/deps/hadoop/hadoop-common-3.3.6.jar:/opt/spark/jars/hadoop-common-3.3.6.jar

resources/setup-env.sh

Lines changed: 11 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -26,8 +26,8 @@ JAR_PATH=$SCRIPT_PATH/deps
2626
rm -rf $JAR_PATH \
2727
&& mkdir -p $JAR_PATH/flink/connector -p $JAR_PATH/flink/hive \
2828
-p $JAR_PATH/flink/iceberg -p $JAR_PATH/flink/parquet \
29-
-p $JAR_PATH/hadoop -p $JAR_PATH/hms \
30-
-p $JAR_PATH/kafka/connector -p $JAR_PATH/spark/iceberg
29+
-p $JAR_PATH/hadoop -p $JAR_PATH/hms -p $JAR_PATH/kafka/connector \
30+
-p $JAR_PATH/spark/iceberg -p $JAR_PATH/spark/lineage
3131

3232
####
3333
#### Kafka connectors
@@ -214,13 +214,13 @@ curl --silent -o $HMS_PATH/postgresql-42.7.3.jar \
214214
flag_time_taken
215215

216216
####
217-
#### Spark Iceberg dependencies
217+
#### Spark Iceberg/OpenLineage dependencies
218218
####
219219
echo ""
220-
echo "▶️ Downloading Spark Iceberg dependencies..."
220+
echo "▶️ Downloading Spark Iceberg/OpenLineage dependencies..."
221221

222222
START_TIME=$(date +%s)
223-
TOTAL_STEPS=2
223+
TOTAL_STEPS=3
224224
CURRENT_STEP=0
225225

226226
SPARK_ICEBERG_PATH=$JAR_PATH/spark/iceberg
@@ -233,6 +233,12 @@ curl --silent -o $SPARK_ICEBERG_PATH/iceberg-aws-bundle-1.8.1.jar \
233233
https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-aws-bundle/1.8.1/iceberg-aws-bundle-1.8.1.jar
234234
((CURRENT_STEP++)); progress_bar
235235

236+
SPARK_LINEAGE_PATH=$JAR_PATH/spark/lineage
237+
238+
curl --silent -o $SPARK_LINEAGE_PATH/openlineage-spark_2.12-1.37.0.jar \
239+
https://repo1.maven.org/maven2/io/openlineage/openlineage-spark_2.12/1.37.0/openlineage-spark_2.12-1.37.0.jar
240+
((CURRENT_STEP++)); progress_bar
241+
236242
flag_time_taken
237243

238244
echo ""

resources/spark/log4j2.properties

Lines changed: 5 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -75,4 +75,8 @@ appender.console.filter.1.onMismatch = neutral
7575
# logger.metastore.name = org.apache.hadoop.hive.metastore
7676
# logger.metastore.level = debug
7777
# logger.hiveexec.name = org.apache.hadoop.hive.ql.exec
78-
# logger.hiveexec.level = debug
78+
# logger.hiveexec.level = debug
79+
80+
# # OpenLineage
81+
# logger.openlineage.name = io.openlineage
82+
# logger.openlineage.level = DEBUG

0 commit comments

Comments
 (0)