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

[SPARK-16548][SQL] Inconsistent error handling in JSON parsing SQL functions #17693

Closed
wants to merge 3 commits into from
Closed

[SPARK-16548][SQL] Inconsistent error handling in JSON parsing SQL functions #17693

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8ef9b6a
fix SPARK-20314
Apr 19, 2017
f706ce3
more efficient fix; add test
Apr 21, 2017
91bb487
add requested comment
Apr 25, 2017
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
8 changes: 5 additions & 3 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@

package org.apache.spark.sql.catalyst.expressions

import java.io.{ByteArrayOutputStream, CharArrayWriter, StringWriter}
import java.io.{ByteArrayInputStream, ByteArrayOutputStream, CharArrayWriter, InputStreamReader, StringWriter}

import scala.util.parsing.combinator.RegexParsers

Expand Down Expand Up @@ -149,7 +149,8 @@ case class GetJsonObject(json: Expression, path: Expression)

if (parsed.isDefined) {
try {
Utils.tryWithResource(jsonFactory.createParser(jsonStr.getBytes)) { parser =>
Utils.tryWithResource(jsonFactory.createParser(new InputStreamReader(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

please add some comments to say that, this is to avoid a bug in encoding detection, and we explicitly specify the encoding(UTF8) here.

new ByteArrayInputStream(jsonStr.getBytes), "UTF-8"))) { parser =>
val output = new ByteArrayOutputStream()
val matched = Utils.tryWithResource(
jsonFactory.createGenerator(output, JsonEncoding.UTF8)) { generator =>
Expand Down Expand Up @@ -393,7 +394,8 @@ case class JsonTuple(children: Seq[Expression])
}

try {
Utils.tryWithResource(jsonFactory.createParser(json.getBytes)) {
Utils.tryWithResource(jsonFactory.createParser(new InputStreamReader(
new ByteArrayInputStream(json.getBytes), "UTF-8"))) {
parser => parseRow(parser, input)
}
} catch {
Expand Down
17 changes: 17 additions & 0 deletions ...alyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,10 @@ class JsonExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
|"fb:testid":"1234"}
|""".stripMargin

/* invalid json with leading nulls would trigger java.io.CharConversionException
in Jackson's JsonFactory.createParser(byte[]) due to RFC-4627 encoding detection */
val badJson = "\0\0\0A\1AAA"

test("$.store.bicycle") {
checkEvaluation(
GetJsonObject(Literal(json), Literal("$.store.bicycle")),
Expand Down Expand Up @@ -224,6 +228,13 @@ class JsonExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
null)
}

test("SPARK-16548: character conversion") {
checkEvaluation(
GetJsonObject(Literal(badJson), Literal("$.a")),
null
)
}

test("non foldable literal") {
checkEvaluation(
GetJsonObject(NonFoldableLiteral(json), NonFoldableLiteral("$.fb:testid")),
Expand Down Expand Up @@ -340,6 +351,12 @@ class JsonExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
InternalRow(null, null, null, null, null))
}

test("SPARK-16548: json_tuple - invalid json with leading nulls") {
checkJsonTuple(
JsonTuple(Literal(badJson) :: jsonTupleQuery),
InternalRow(null, null, null, null, null))
}

test("json_tuple - preserve newlines") {
checkJsonTuple(
JsonTuple(Literal("{\"a\":\"b\nc\"}") :: Literal("a") :: Nil),
Expand Down