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

[SPARK-49013] Change key in collationsMap for Map and Array types in scala #47497

Closed
wants to merge 1 commit into from
Closed

[SPARK-49013] Change key in collationsMap for Map and Array types in scala #47497

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
13 changes: 10 additions & 3 deletions sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,7 +223,7 @@ object DataType {
("elementType", t: JValue),
("type", JString("array"))) =>
assertValidTypeForCollations(fieldPath, "array", collationsMap)
val elementType = parseDataType(t, fieldPath + ".element", collationsMap)
val elementType = parseDataType(t, appendFieldToPath(fieldPath, "element"), collationsMap)
ArrayType(elementType, n)

case JSortedObject(
Expand All @@ -232,8 +232,8 @@ object DataType {
("valueContainsNull", JBool(n)),
("valueType", v: JValue)) =>
assertValidTypeForCollations(fieldPath, "map", collationsMap)
val keyType = parseDataType(k, fieldPath + ".key", collationsMap)
val valueType = parseDataType(v, fieldPath + ".value", collationsMap)
val keyType = parseDataType(k, appendFieldToPath(fieldPath, "key"), collationsMap)
val valueType = parseDataType(v, appendFieldToPath(fieldPath, "value"), collationsMap)
MapType(keyType, valueType, n)

case JSortedObject(
Expand Down Expand Up @@ -304,6 +304,13 @@ object DataType {
}
}

/**
* Appends a field name to a given path, using a dot separator if the path is not empty.
*/
private def appendFieldToPath(basePath: String, fieldName: String): String = {
if (basePath.isEmpty) fieldName else s"$basePath.$fieldName"
}

/**
* Returns a map of field path to collation name.
*/
Expand Down
45 changes: 45 additions & 0 deletions sql/catalyst/src/test/scala/org/apache/spark/sql/types/DataTypeSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
package org.apache.spark.sql.types

import com.fasterxml.jackson.core.JsonParseException
import org.json4s.jackson.JsonMethods

import org.apache.spark.{SparkException, SparkFunSuite, SparkIllegalArgumentException}
import org.apache.spark.sql.catalyst.analysis.{caseInsensitiveResolution, caseSensitiveResolution}
Expand Down Expand Up @@ -1001,6 +1002,50 @@ class DataTypeSuite extends SparkFunSuite {
)
}

test("parse array type with collation metadata") {
val unicodeCollationId = CollationFactory.collationNameToId("UNICODE")
val arrayJson =
s"""
|{
| "type": "array",
| "elementType": "string",
| "containsNull": true
|}
|""".stripMargin

val collationsMap = Map("element" -> "UNICODE")

// Parse without collations map
assert(DataType.parseDataType(JsonMethods.parse(arrayJson)) === ArrayType(StringType))

val parsedWithCollations = DataType.parseDataType(
JsonMethods.parse(arrayJson), collationsMap = collationsMap)
assert(parsedWithCollations === ArrayType(StringType(unicodeCollationId)))
}

test("parse map type with collation metadata") {
val unicodeCollationId = CollationFactory.collationNameToId("UNICODE")
val mapJson =
s"""
|{
| "type": "map",
| "keyType": "string",
| "valueType": "string",
| "valueContainsNull": true
|}
|""".stripMargin

val collationsMap = Map("key" -> "UNICODE", "value" -> "UNICODE")

// Parse without collations map
assert(DataType.parseDataType(JsonMethods.parse(mapJson)) === MapType(StringType, StringType))

val parsedWithCollations = DataType.parseDataType(
JsonMethods.parse(mapJson), collationsMap = collationsMap)
assert(parsedWithCollations ===
MapType(StringType(unicodeCollationId), StringType(unicodeCollationId)))
}

test("SPARK-48680: Add CharType and VarcharType to DataTypes JAVA API") {
assert(DataTypes.createCharType(1) === CharType(1))
assert(DataTypes.createVarcharType(100) === VarcharType(100))
Expand Down