Skip to content

[SPARK-46382][SQL]XML: Default ignoreSurroundingSpaces to true #44629

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
shujingyang-db wants to merge 1 commit into from
Closed

[SPARK-46382][SQL]XML: Default ignoreSurroundingSpaces to true #44629

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
2 changes: 1 addition & 1 deletion sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlOptions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,7 @@ class XmlOptions(
val nullValue = parameters.getOrElse(NULL_VALUE, XmlOptions.DEFAULT_NULL_VALUE)
val columnNameOfCorruptRecord =
parameters.getOrElse(COLUMN_NAME_OF_CORRUPT_RECORD, defaultColumnNameOfCorruptRecord)
val ignoreSurroundingSpaces = getBool(IGNORE_SURROUNDING_SPACES, false)
val ignoreSurroundingSpaces = getBool(IGNORE_SURROUNDING_SPACES, true)
val parseMode = ParseMode.fromString(parameters.getOrElse(MODE, PermissiveMode.name))
val inferSchema = getBool(INFER_SCHEMA, true)
val rowValidationXSDPath = parameters.get(ROW_VALIDATION_XSD_PATH).orNull
Expand Down
14 changes: 7 additions & 7 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -732,7 +732,7 @@ class XmlSuite extends QueryTest with SharedSparkSession {
.collect()

assert(results(0) === Row("alice", "35"))
assert(results(1) === Row("bob", " "))
assert(results(1) === Row("bob", ""))
assert(results(2) === Row("coc", "24"))
}

Expand Down Expand Up @@ -818,7 +818,7 @@ class XmlSuite extends QueryTest with SharedSparkSession {
assert(result(0) === Row(Row(null)))
assert(result(1) === Row(Row(Row(null, null))))
assert(result(2) === Row(Row(Row("E", null))))
assert(result(3) === Row(Row(Row("E", " "))))
assert(result(3) === Row(Row(Row("E", ""))))
assert(result(4) === Row(Row(Row("E", ""))))
}

Expand Down Expand Up @@ -1146,18 +1146,18 @@ class XmlSuite extends QueryTest with SharedSparkSession {
.option("inferSchema", true)
.xml(getTestResourcePath(resDir + "mixed_children.xml"))
val mixedRow = mixedDF.head()
assert(mixedRow.getAs[Row](0) === Row(List(" issue ", " text ignored "), " lorem "))
assert(mixedRow.getString(1) === " ipsum ")
assert(mixedRow.getAs[Row](0) === Row(List("issue", "text ignored"), "lorem"))
assert(mixedRow.getString(1) === "ipsum")
}

test("test mixed text and complex element children") {
val mixedDF = spark.read
.option("rowTag", "root")
.option("inferSchema", true)
.xml(getTestResourcePath(resDir + "mixed_children_2.xml"))
assert(mixedDF.select("foo.bar").head().getString(0) === " lorem ")
assert(mixedDF.select("foo.bar").head().getString(0) === "lorem")
assert(mixedDF.select("foo.baz.bing").head().getLong(0) === 2)
assert(mixedDF.select("missing").head().getString(0) === " ipsum ")
assert(mixedDF.select("missing").head().getString(0) === "ipsum")
}

test("test XSD validation") {
Expand Down Expand Up @@ -1721,7 +1721,7 @@ class XmlSuite extends QueryTest with SharedSparkSession {
assert(result(1).getAs[String]("_attr") == "attr1"
&& result(1).getAs[String]("_VALUE") == "value2")
// comments aren't included in valueTag
assert(result(2).getAs[String]("_VALUE") == "\n value3\n ")
assert(result(2).getAs[String]("_VALUE") == "value3")
}
}

Expand Down