Skip to content

[SPARK-18333] [SQL] Revert hacks in parquet and orc reader to support case insensitive resolution #15799

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 3 commits into from
Closed

[SPARK-18333] [SQL] Revert hacks in parquet and orc reader to support case insensitive resolution #15799

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ddc39b8
Fri Nov 4 15:54:23 PDT 2016
ericl Nov 4, 2016
8921868
Merge branch 'master' into sc-4929
ericl Nov 7, 2016
7f02648
Tue Nov 8 15:44:21 PST 2016
ericl Nov 8, 2016
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: 1 addition & 5 deletions ...rc/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetReadSupport.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,15 +269,11 @@ private[parquet] object ParquetReadSupport {
*/
private def clipParquetGroupFields(
parquetRecord: GroupType, structType: StructType): Seq[Type] = {
val parquetFieldMap = parquetRecord.getFields.asScala
.map(f => f.getName -> f).toMap
val caseInsensitiveParquetFieldMap = parquetRecord.getFields.asScala
.map(f => f.getName.toLowerCase -> f).toMap
val parquetFieldMap = parquetRecord.getFields.asScala.map(f => f.getName -> f).toMap
val toParquet = new ParquetSchemaConverter(writeLegacyParquetFormat = false)
structType.map { f =>
parquetFieldMap
.get(f.name)
.orElse(caseInsensitiveParquetFieldMap.get(f.name.toLowerCase))
.map(clipParquetType(_, f.dataType))
.getOrElse(toParquet.convertField(f))
}
Expand Down
28 changes: 0 additions & 28 deletions ...rc/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1080,34 +1080,6 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
}
}

testSchemaClipping(
"falls back to case insensitive resolution",

parquetSchema =
"""message root {
| required group A {
| optional int32 B;
| }
| optional int32 c;
|}
""".stripMargin,

catalystSchema = {
val nestedType = new StructType().add("b", IntegerType, nullable = true)
new StructType()
.add("a", nestedType, nullable = true)
.add("c", IntegerType, nullable = true)
},

expectedSchema =
"""message root {
| required group A {
| optional int32 B;
| }
| optional int32 c;
|}
""".stripMargin)

testSchemaClipping(
"simple nested struct",

Expand Down
12 changes: 1 addition & 11 deletions sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileFormat.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -305,17 +305,7 @@ private[orc] object OrcRelation extends HiveInspectors {

def setRequiredColumns(
conf: Configuration, physicalSchema: StructType, requestedSchema: StructType): Unit = {
val caseInsensitiveFieldMap: Map[String, Int] = physicalSchema.fieldNames
.zipWithIndex
.map(f => (f._1.toLowerCase, f._2))
.toMap
val ids = requestedSchema.map { a =>
val exactMatch: Option[Int] = physicalSchema.getFieldIndex(a.name)
val res = exactMatch.getOrElse(
caseInsensitiveFieldMap.getOrElse(a.name,
throw new IllegalArgumentException(s"""Field "$a.name" does not exist.""")))
res: Integer
}
val ids = requestedSchema.map(a => physicalSchema.fieldIndex(a.name): Integer)
val (sortedIDs, sortedNames) = ids.zip(requestedSchema.fieldNames).sorted.unzip
HiveShim.appendReadColumns(conf, sortedIDs, sortedNames)
}
Expand Down