Skip to content

[SPARK-5758][SQL] Use LongType as the default type for integers in JSON schema inference. #4544

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 1 commit into from
Closed

[SPARK-5758][SQL] Use LongType as the default type for integers in JSON schema inference. #4544

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
12 changes: 8 additions & 4 deletions sql/core/src/main/scala/org/apache/spark/sql/json/JsonRDD.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,13 +17,12 @@

package org.apache.spark.sql.json

import java.io.StringWriter
import java.sql.{Date, Timestamp}
import java.sql.Timestamp

import scala.collection.Map
import scala.collection.convert.Wrappers.{JMapWrapper, JListWrapper}

import com.fasterxml.jackson.core.{JsonGenerator, JsonProcessingException, JsonFactory}
import com.fasterxml.jackson.core.{JsonGenerator, JsonProcessingException}
import com.fasterxml.jackson.databind.ObjectMapper

import org.apache.spark.rdd.RDD
Expand Down Expand Up @@ -178,7 +177,12 @@ private[sql] object JsonRDD extends Logging {
}

private def typeOfPrimitiveValue: PartialFunction[Any, DataType] = {
ScalaReflection.typeOfObject orElse {
// For Integer values, use LongType by default.
val useLongType: PartialFunction[Any, DataType] = {
case value: IntegerType.JvmType => LongType
}

useLongType orElse ScalaReflection.typeOfObject orElse {
// Since we do not have a data type backed by BigInteger,
// when we see a Java BigInteger, we use DecimalType.
case value: java.math.BigInteger => DecimalType.Unlimited
Expand Down
2 changes: 1 addition & 1 deletion sql/core/src/test/java/org/apache/spark/sql/api/java/JavaApplySchemaSuite.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,7 +164,7 @@ public void applySchemaToJSON() {
fields.add(DataTypes.createStructField("bigInteger", DataTypes.createDecimalType(), true));
fields.add(DataTypes.createStructField("boolean", DataTypes.BooleanType, true));
fields.add(DataTypes.createStructField("double", DataTypes.DoubleType, true));
fields.add(DataTypes.createStructField("integer", DataTypes.IntegerType, true));
fields.add(DataTypes.createStructField("integer", DataTypes.LongType, true));
fields.add(DataTypes.createStructField("long", DataTypes.LongType, true));
fields.add(DataTypes.createStructField("null", DataTypes.StringType, true));
fields.add(DataTypes.createStructField("string", DataTypes.StringType, true));
Expand Down
16 changes: 8 additions & 8 deletions sql/core/src/test/scala/org/apache/spark/sql/json/JsonSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -222,7 +222,7 @@ class JsonSuite extends QueryTest {
StructField("bigInteger", DecimalType.Unlimited, true) ::
StructField("boolean", BooleanType, true) ::
StructField("double", DoubleType, true) ::
StructField("integer", IntegerType, true) ::
StructField("integer", LongType, true) ::
StructField("long", LongType, true) ::
StructField("null", StringType, true) ::
StructField("string", StringType, true) :: Nil)
Expand Down Expand Up @@ -252,7 +252,7 @@ class JsonSuite extends QueryTest {
StructField("arrayOfBigInteger", ArrayType(DecimalType.Unlimited, false), true) ::
StructField("arrayOfBoolean", ArrayType(BooleanType, false), true) ::
StructField("arrayOfDouble", ArrayType(DoubleType, false), true) ::
StructField("arrayOfInteger", ArrayType(IntegerType, false), true) ::
StructField("arrayOfInteger", ArrayType(LongType, false), true) ::
StructField("arrayOfLong", ArrayType(LongType, false), true) ::
StructField("arrayOfNull", ArrayType(StringType, true), true) ::
StructField("arrayOfString", ArrayType(StringType, false), true) ::
Expand All @@ -265,7 +265,7 @@ class JsonSuite extends QueryTest {
StructField("field1", BooleanType, true) ::
StructField("field2", DecimalType.Unlimited, true) :: Nil), true) ::
StructField("structWithArrayFields", StructType(
StructField("field1", ArrayType(IntegerType, false), true) ::
StructField("field1", ArrayType(LongType, false), true) ::
StructField("field2", ArrayType(StringType, false), true) :: Nil), true) :: Nil)

assert(expectedSchema === jsonDF.schema)
Expand Down Expand Up @@ -486,7 +486,7 @@ class JsonSuite extends QueryTest {
val jsonDF = jsonRDD(complexFieldValueTypeConflict)

val expectedSchema = StructType(
StructField("array", ArrayType(IntegerType, false), true) ::
StructField("array", ArrayType(LongType, false), true) ::
StructField("num_struct", StringType, true) ::
StructField("str_array", StringType, true) ::
StructField("struct", StructType(
Expand Down Expand Up @@ -540,7 +540,7 @@ class JsonSuite extends QueryTest {
val expectedSchema = StructType(
StructField("a", BooleanType, true) ::
StructField("b", LongType, true) ::
StructField("c", ArrayType(IntegerType, false), true) ::
StructField("c", ArrayType(LongType, false), true) ::
StructField("d", StructType(
StructField("field", BooleanType, true) :: Nil), true) ::
StructField("e", StringType, true) :: Nil)
Expand All @@ -560,7 +560,7 @@ class JsonSuite extends QueryTest {
StructField("bigInteger", DecimalType.Unlimited, true) ::
StructField("boolean", BooleanType, true) ::
StructField("double", DoubleType, true) ::
StructField("integer", IntegerType, true) ::
StructField("integer", LongType, true) ::
StructField("long", LongType, true) ::
StructField("null", StringType, true) ::
StructField("string", StringType, true) :: Nil)
Expand Down Expand Up @@ -781,12 +781,12 @@ class JsonSuite extends QueryTest {
ArrayType(ArrayType(ArrayType(ArrayType(StringType, false), false), true), false), true) ::
StructField("field2",
ArrayType(ArrayType(
StructType(StructField("Test", IntegerType, true) :: Nil), false), true), true) ::
StructType(StructField("Test", LongType, true) :: Nil), false), true), true) ::
StructField("field3",
ArrayType(ArrayType(
StructType(StructField("Test", StringType, true) :: Nil), true), false), true) ::
StructField("field4",
ArrayType(ArrayType(ArrayType(IntegerType, false), true), false), true) :: Nil)
ArrayType(ArrayType(ArrayType(LongType, false), true), false), true) :: Nil)

assert(schema === jsonDF.schema)

Expand Down