Skip to content

[SPARK-33134][SQL] Return partial results only for root JSON objects #30031

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
MaxGekk wants to merge 7 commits into from
Closed

[SPARK-33134][SQL] Return partial results only for root JSON objects #30031

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
60799f9
Add a test
MaxGekk Oct 13, 2020
12e9fb2
Fix
MaxGekk Oct 13, 2020
ae9ce52
Improve test
MaxGekk Oct 13, 2020
813127a
Simplify test
MaxGekk Oct 13, 2020
bccbb9b
Test more cases
MaxGekk Oct 13, 2020
aaf185c
Test refactoring
MaxGekk Oct 13, 2020
241eca5
Fix test
MaxGekk Oct 13, 2020
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
7 changes: 4 additions & 3 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ class JacksonParser(
new NoopFilters
}
(parser: JsonParser) => parseJsonToken[Iterable[InternalRow]](parser, st) {
case START_OBJECT => convertObject(parser, st, fieldConverters, jsonFilters)
case START_OBJECT => convertObject(parser, st, fieldConverters, jsonFilters, isRoot = true)
// SPARK-3308: support reading top level JSON arrays and take every element
// in such an array as a row
//
Expand Down Expand Up @@ -383,7 +383,8 @@ class JacksonParser(
parser: JsonParser,
schema: StructType,
fieldConverters: Array[ValueConverter],
structFilters: StructFilters = new NoopFilters()): Option[InternalRow] = {
structFilters: StructFilters = new NoopFilters(),
isRoot: Boolean = false): Option[InternalRow] = {
val row = new GenericInternalRow(schema.length)
var badRecordException: Option[Throwable] = None
var skipRow = false
Expand All @@ -397,7 +398,7 @@ class JacksonParser(
skipRow = structFilters.skipRow(row, index)
} catch {
case e: SparkUpgradeException => throw e
case NonFatal(e) =>
case NonFatal(e) if isRoot =>
badRecordException = badRecordException.orElse(Some(e))
parser.skipChildren()
}
Expand Down
14 changes: 14 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -733,4 +733,18 @@ class JsonFunctionsSuite extends QueryTest with SharedSparkSession {
| """.stripMargin)
checkAnswer(toDF("yyyy-MM-dd'T'HH:mm:ss.SSSXXX"), toDF("yyyy-MM-dd'T'HH:mm:ss[.SSS][XXX]"))
}

test("SPARK-33134: return partial results only for root JSON objects") {
val st = new StructType()
.add("c1", LongType)
.add("c2", ArrayType(new StructType().add("c3", LongType).add("c4", StringType)))
val df1 = Seq("""{"c2": [19], "c1": 123456}""").toDF("c0")
checkAnswer(df1.select(from_json($"c0", st)), Row(Row(123456, null)))
val df2 = Seq("""{"data": {"c2": [19], "c1": 123456}}""").toDF("c0")
checkAnswer(df2.select(from_json($"c0", new StructType().add("data", st))), Row(Row(null)))
val df3 = Seq("""[{"c2": [19], "c1": 123456}]""").toDF("c0")
checkAnswer(df3.select(from_json($"c0", ArrayType(st))), Row(null))
val df4 = Seq("""{"c2": [19]}""").toDF("c0")
checkAnswer(df4.select(from_json($"c0", MapType(StringType, st))), Row(null))
}
}