Skip to content

[SPARK-32130][SQL] Disable the JSON option inferTimestamp by default #28966

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 6 commits into from
Closed

[SPARK-32130][SQL] Disable the JSON option inferTimestamp by default #28966

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
0b1616e
Set inferTimestamp to false by default
MaxGekk Jul 1, 2020
15b34ec
Fix JsonInferSchemaSuite
MaxGekk Jul 1, 2020
277a679
Fix JsonSuite
MaxGekk Jul 1, 2020
e21187e
Re-gen JsonBenchmark-results.txt
MaxGekk Jul 1, 2020
488f8c8
Re-gen JsonBenchmark-jdk11-results.txt
MaxGekk Jul 1, 2020
43fc9aa
Update SQL migration guide
MaxGekk Jul 1, 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
2 changes: 1 addition & 1 deletion sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JSONOptions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,7 +133,7 @@ private[sql] class JSONOptions(
* Enables inferring of TimestampType from strings matched to the timestamp pattern
* defined by the timestampFormat option.
*/
val inferTimestamp: Boolean = parameters.get("inferTimestamp").map(_.toBoolean).getOrElse(true)
val inferTimestamp: Boolean = parameters.get("inferTimestamp").map(_.toBoolean).getOrElse(false)

/** Build a Jackson [[JsonFactory]] using JSON options. */
def buildJsonFactory(): JsonFactory = {
Expand Down
56 changes: 33 additions & 23 deletions sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/json/JsonInferSchemaSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,22 +35,29 @@ class JsonInferSchemaSuite extends SparkFunSuite with SQLHelper {
assert(inferSchema.inferField(parser) === expectedType)
}

def checkTimestampType(pattern: String, json: String): Unit = {
checkType(Map("timestampFormat" -> pattern), json, TimestampType)
def checkTimestampType(pattern: String, json: String, inferTimestamp: Boolean): Unit = {
checkType(
Map("timestampFormat" -> pattern, "inferTimestamp" -> inferTimestamp.toString),
json,
if (inferTimestamp) TimestampType else StringType)
}

test("inferring timestamp type") {
Seq("legacy", "corrected").foreach { legacyParserPolicy =>
withSQLConf(SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy) {
checkTimestampType("yyyy", """{"a": "2018"}""")
checkTimestampType("yyyy=MM", """{"a": "2018=12"}""")
checkTimestampType("yyyy MM dd", """{"a": "2018 12 02"}""")
checkTimestampType(
"yyyy-MM-dd'T'HH:mm:ss.SSS",
"""{"a": "2018-12-02T21:04:00.123"}""")
checkTimestampType(
"yyyy-MM-dd'T'HH:mm:ss.SSSSSSXXX",
"""{"a": "2018-12-02T21:04:00.123567+01:00"}""")
Seq(true, false).foreach { inferTimestamp =>
Seq("legacy", "corrected").foreach { legacyParserPolicy =>
withSQLConf(SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy) {
checkTimestampType("yyyy", """{"a": "2018"}""", inferTimestamp)
checkTimestampType("yyyy=MM", """{"a": "2018=12"}""", inferTimestamp)
checkTimestampType("yyyy MM dd", """{"a": "2018 12 02"}""", inferTimestamp)
checkTimestampType(
"yyyy-MM-dd'T'HH:mm:ss.SSS",
"""{"a": "2018-12-02T21:04:00.123"}""",
inferTimestamp)
checkTimestampType(
"yyyy-MM-dd'T'HH:mm:ss.SSSSSSXXX",
"""{"a": "2018-12-02T21:04:00.123567+01:00"}""",
inferTimestamp)
}
}
}
}
Expand All @@ -71,16 +78,19 @@ class JsonInferSchemaSuite extends SparkFunSuite with SQLHelper {
}

test("skip decimal type inferring") {
Seq("legacy", "corrected").foreach { legacyParserPolicy =>
withSQLConf(SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy) {
checkType(
options = Map(
"prefersDecimal" -> "false",
"timestampFormat" -> "yyyyMMdd.HHmmssSSS"
),
json = """{"a": "20181202.210400123"}""",
dt = TimestampType
)
Seq(true, false).foreach { inferTimestamp =>
Seq("legacy", "corrected").foreach { legacyParserPolicy =>
withSQLConf(SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy) {
checkType(
options = Map(
"prefersDecimal" -> "false",
"timestampFormat" -> "yyyyMMdd.HHmmssSSS",
"inferTimestamp" -> inferTimestamp.toString
),
json = """{"a": "20181202.210400123"}""",
dt = if (inferTimestamp) TimestampType else StringType
)
}
}
}
}
Expand Down
6 changes: 5 additions & 1 deletion sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/json/JsonSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2610,7 +2610,9 @@ abstract class JsonSuite extends QueryTest with SharedSparkSession with TestJson
}

test("inferring timestamp type") {
def schemaOf(jsons: String*): StructType = spark.read.json(jsons.toDS).schema
def schemaOf(jsons: String*): StructType = {
spark.read.option("inferTimestamp", true).json(jsons.toDS).schema
}

assert(schemaOf(
"""{"a":"2018-12-17T10:11:12.123-01:00"}""",
Expand All @@ -2633,6 +2635,7 @@ abstract class JsonSuite extends QueryTest with SharedSparkSession with TestJson
val timestampsWithFormatPath = s"${dir.getCanonicalPath}/timestampsWithFormat.json"
val timestampsWithFormat = spark.read
.option("timestampFormat", "dd/MM/yyyy HH:mm")
.option("inferTimestamp", true)
.json(datesRecords)
assert(timestampsWithFormat.schema === customSchema)

Expand All @@ -2645,6 +2648,7 @@ abstract class JsonSuite extends QueryTest with SharedSparkSession with TestJson
val readBack = spark.read
.option("timestampFormat", "yyyy-MM-dd HH:mm:ss")
.option(DateTimeUtils.TIMEZONE_OPTION, "UTC")
.option("inferTimestamp", true)
.json(timestampsWithFormatPath)

assert(readBack.schema === customSchema)
Expand Down