Skip to content

[SPARK-8928] [SQL] Makes CatalystSchemaConverter sticking to 1.4.x- when handling Parquet LISTs in compatible mode #7304

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 1 commit into from
Closed

[SPARK-8928] [SQL] Makes CatalystSchemaConverter sticking to 1.4.x- when handling Parquet LISTs in compatible mode #7304

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 sql/core/src/main/scala/org/apache/spark/sql/parquet/CatalystSchemaConverter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -461,7 +461,8 @@ private[parquet] class CatalystSchemaConverter(
field.name,
Types
.buildGroup(REPEATED)
.addField(convertField(StructField("element", elementType, nullable)))
// "array_element" is the name chosen by parquet-hive (1.7.0 and prior version)
.addField(convertField(StructField("array_element", elementType, nullable)))
.named(CatalystConverter.ARRAY_CONTAINS_NULL_BAG_SCHEMA_NAME))

// Spark 1.4.x and prior versions convert ArrayType with non-nullable elements into a 2-level
Expand All @@ -474,7 +475,8 @@ private[parquet] class CatalystSchemaConverter(
ConversionPatterns.listType(
repetition,
field.name,
convertField(StructField("element", elementType, nullable), REPEATED))
// "array" is the name chosen by parquet-avro (1.7.0 and prior version)
convertField(StructField("array", elementType, nullable), REPEATED))

// Spark 1.4.x and prior versions convert MapType into a 3-level group annotated by
// MAP_KEY_VALUE. This is covered by `convertGroupField(field: GroupType): DataType`.
Expand Down
10 changes: 5 additions & 5 deletions sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,7 +174,7 @@ class ParquetSchemaInferenceSuite extends ParquetSchemaTest {
"""
|message root {
| optional group _1 (LIST) {
| repeated int32 element;
| repeated int32 array;
| }
|}
""".stripMargin)
Expand All @@ -198,7 +198,7 @@ class ParquetSchemaInferenceSuite extends ParquetSchemaTest {
|message root {
| optional group _1 (LIST) {
| repeated group bag {
| optional int32 element;
| optional int32 array_element;
| }
| }
|}
Expand Down Expand Up @@ -267,7 +267,7 @@ class ParquetSchemaInferenceSuite extends ParquetSchemaTest {
| optional binary _1 (UTF8);
| optional group _2 (LIST) {
| repeated group bag {
| optional group element {
| optional group array_element {
| required int32 _1;
| required double _2;
| }
Expand Down Expand Up @@ -616,7 +616,7 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
"""message root {
| optional group f1 (LIST) {
| repeated group bag {
| optional int32 element;
| optional int32 array_element;
| }
| }
|}
Expand Down Expand Up @@ -648,7 +648,7 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
nullable = true))),
"""message root {
| optional group f1 (LIST) {
| repeated int32 element;
| repeated int32 array;
| }
|}
""".stripMargin)
Expand Down