Skip to content

[SPARK-6607][SQL] Check invalid characters for Parquet schema and show error messages #5263

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
viirya wants to merge 3 commits into from
Closed

[SPARK-6607][SQL] Check invalid characters for Parquet schema and show error messages #5263

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1de001d
Replace special characters '(' and ')' of Parquet schema.
viirya Mar 30, 2015
463dff4
Instead of replacing special chars, showing error message to user to …
viirya Mar 31, 2015
2d70542
Address comment.
viirya Apr 4, 2015
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
14 changes: 14 additions & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -390,6 +390,7 @@ private[parquet] object ParquetTypesConverter extends Logging {

def convertFromAttributes(attributes: Seq[Attribute],
toThriftSchemaNames: Boolean = false): MessageType = {
checkSpecialCharacters(attributes)
val fields = attributes.map(
attribute =>
fromDataType(attribute.dataType, attribute.name, attribute.nullable,
Expand All @@ -404,7 +405,20 @@ private[parquet] object ParquetTypesConverter extends Logging {
}
}

private def checkSpecialCharacters(schema: Seq[Attribute]) = {
// ,;{}()\n\t= and space character are special characters in Parquet schema
schema.map(_.name).foreach { name =>
if (name.matches(".*[ ,;{}()\n\t=].*")) {
sys.error(
s"""Attribute name "$name" contains invalid character(s) among " ,;{}()\n\t=".
|Please use alias to rename it.
""".stripMargin.split("\n").mkString(" "))
}
}
}

def convertToString(schema: Seq[Attribute]): String = {
checkSpecialCharacters(schema)
StructType.fromAttributes(schema).json
}

Expand Down
16 changes: 16 additions & 0 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -578,6 +578,22 @@ class ParquetDataSourceOnSourceSuite extends ParquetSourceSuiteBase {

sql("DROP TABLE alwaysNullable")
}

test("Aggregation attribute names can't contain special chars \" ,;{}()\\n\\t=\"") {
val tempDir = Utils.createTempDir()
val filePath = new File(tempDir, "testParquet").getCanonicalPath
val filePath2 = new File(tempDir, "testParquet2").getCanonicalPath

val df = Seq(1,2,3).map(i => (i, i.toString)).toDF("int", "str")
val df2 = df.as('x).join(df.as('y), $"x.str" === $"y.str").groupBy("y.str").max("y.int")
intercept[RuntimeException](df2.saveAsParquetFile(filePath))

val df3 = df2.toDF("str", "max_int")
df3.saveAsParquetFile(filePath2)
val df4 = parquetFile(filePath2)
checkAnswer(df4, Row("1", 1) :: Row("2", 2) :: Row("3", 3) :: Nil)
assert(df4.columns === Array("str", "max_int"))
}
}

class ParquetDataSourceOffSourceSuite extends ParquetSourceSuiteBase {
Expand Down