Skip to content
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

Jump to bottom

[HUDI-3670] fix temp view leak in deltastreamer's Sql transformers #5080

Merged
merged 1 commit into from
Jun 1, 2022
Merged

[HUDI-3670] fix temp view leak in deltastreamer's Sql transformers #5080

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 4 additions & 2 deletions hudi-utilities/src/main/java/org/apache/hudi/utilities/transform/FlatteningTransformer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,8 +49,10 @@ public Dataset<Row> apply(JavaSparkContext jsc, SparkSession sparkSession, Datas
// tmp table name doesn't like dashes
String tmpTable = TMP_TABLE.concat(UUID.randomUUID().toString().replace("-", "_"));
LOG.info("Registering tmp table : " + tmpTable);
rowDataset.registerTempTable(tmpTable);
return sparkSession.sql("select " + flattenSchema(rowDataset.schema(), null) + " from " + tmpTable);
rowDataset.createOrReplaceTempView(tmpTable);
Dataset<Row> transformed = sparkSession.sql("select " + flattenSchema(rowDataset.schema(), null) + " from " + tmpTable);
sparkSession.catalog().dropTempView(tmpTable);
return transformed;
}

public String flattenSchema(StructType schema, String prefix) {
Expand Down
4 changes: 3 additions & 1 deletion ...-utilities/src/main/java/org/apache/hudi/utilities/transform/SqlFileBasedTransformer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ public Dataset<Row> apply(
// tmp table name doesn't like dashes
final String tmpTable = TMP_TABLE.concat(UUID.randomUUID().toString().replace("-", "_"));
LOG.info("Registering tmp table : " + tmpTable);
rowDataset.registerTempTable(tmpTable);
rowDataset.createOrReplaceTempView(tmpTable);

try (final Scanner scanner = new Scanner(fs.open(new Path(sqlFile)), "UTF-8")) {
Dataset<Row> rows = null;
Expand All @@ -95,6 +95,8 @@ public Dataset<Row> apply(
return rows;
} catch (final IOException ioe) {
throw new HoodieIOException("Error reading transformer SQL file.", ioe);
} finally {
sparkSession.catalog().dropTempView(tmpTable);
}
}

Expand Down
6 changes: 4 additions & 2 deletions ...utilities/src/main/java/org/apache/hudi/utilities/transform/SqlQueryBasedTransformer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,9 +60,11 @@ public Dataset<Row> apply(JavaSparkContext jsc, SparkSession sparkSession, Datas
// tmp table name doesn't like dashes
String tmpTable = TMP_TABLE.concat(UUID.randomUUID().toString().replace("-", "_"));
LOG.info("Registering tmp table : " + tmpTable);
rowDataset.registerTempTable(tmpTable);
rowDataset.createOrReplaceTempView(tmpTable);
String sqlStr = transformerSQL.replaceAll(SRC_PATTERN, tmpTable);
LOG.debug("SQL Query for transformation : (" + sqlStr + ")");
return sparkSession.sql(sqlStr);
Dataset<Row> transformed = sparkSession.sql(sqlStr);
sparkSession.catalog().dropTempView(tmpTable);
return transformed;
}
}