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-32025][SQL] Csv schema inference problems with different types in the same column #28896

Closed
wants to merge 7 commits into from
Closed

[SPARK-32025][SQL] Csv schema inference problems with different types in the same column #28896

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
55c013e
Fix csv type inference
planga82 Jun 22, 2020
7fbd442
Discard infer schema changes
planga82 Jun 23, 2020
ae64bb9
Fix text
planga82 Jun 23, 2020
c6bbc27
Check compatibility types
planga82 Jun 23, 2020
a3a4bfd
Move compatible type inside inferSchema
planga82 Jun 24, 2020
d167493
Pull request comments
planga82 Jun 24, 2020
4629bb5
Delete not used variable
planga82 Jun 24, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
7 changes: 3 additions & 4 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVInferSchema.scala
View file
Open in desktop
Expand Up @@ -102,20 +102,19 @@ class CSVInferSchema(val options: CSVOptions) extends Serializable {
if (field == null || field.isEmpty || field == options.nullValue) {
typeSoFar
} else {
typeSoFar match {
val typeElemInfer = typeSoFar match {
case NullType => tryParseInteger(field)
case IntegerType => tryParseInteger(field)
case LongType => tryParseLong(field)
planga82 marked this conversation as resolved.
Show resolved Hide resolved
case _: DecimalType =>
// DecimalTypes have different precisions and scales, so we try to find the common type.
compatibleType(typeSoFar, tryParseDecimal(field)).getOrElse(StringType)
case _: DecimalType => tryParseDecimal(field)
case DoubleType => tryParseDouble(field)
case TimestampType => tryParseTimestamp(field)
case BooleanType => tryParseBoolean(field)
case StringType => StringType
case other: DataType =>
throw new UnsupportedOperationException(s"Unexpected data type $other")
}
compatibleType(typeSoFar, typeElemInfer).getOrElse(StringType)
}
}

Expand Down
10 changes: 5 additions & 5 deletions sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/csv/CSVInferSchemaSuite.scala
View file
Open in desktop
Expand Up @@ -56,11 +56,11 @@ class CSVInferSchemaSuite extends SparkFunSuite with SQLHelper {
assert(inferSchema.inferField(IntegerType, "1.0") == DoubleType)
assert(inferSchema.inferField(DoubleType, null) == DoubleType)
assert(inferSchema.inferField(DoubleType, "test") == StringType)
assert(inferSchema.inferField(LongType, "2015-08-20 14:57:00") == TimestampType)
assert(inferSchema.inferField(DoubleType, "2015-08-20 15:57:00") == TimestampType)
assert(inferSchema.inferField(LongType, "True") == BooleanType)
assert(inferSchema.inferField(IntegerType, "FALSE") == BooleanType)
assert(inferSchema.inferField(TimestampType, "FALSE") == BooleanType)
assert(inferSchema.inferField(LongType, "2015-08-20 14:57:00") == StringType)
assert(inferSchema.inferField(DoubleType, "2015-08-20 15:57:00") == StringType)
assert(inferSchema.inferField(LongType, "True") == StringType)
assert(inferSchema.inferField(IntegerType, "FALSE") == StringType)
assert(inferSchema.inferField(TimestampType, "FALSE") == StringType)

val textValueOne = Long.MaxValue.toString + "0"
val decimalValueOne = new java.math.BigDecimal(textValueOne)
Expand Down
12 changes: 12 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala
View file
Open in desktop
Expand Up @@ -2341,6 +2341,18 @@ abstract class CSVSuite extends QueryTest with SharedSparkSession with TestCsvDa
checkAnswer(csv, Row(null))
}
}

test("SPARK-32025: infer the schema from mixed-type values") {
withTempPath { path =>
Seq("col_mixed_types", "2012", "1997", "True").toDS.write.text(path.getCanonicalPath)
val df = spark.read.format("csv")
.option("header", "true")
.option("inferSchema", "true")
.load(path.getCanonicalPath)

assert(df.schema.last == StructField("col_mixed_types", StringType, true))
}
}
}

class CSVv1Suite extends CSVSuite {
Expand Down