This is an automated email from the ASF dual-hosted git repository.
uros-b pushed a commit to branch branch-4.x
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-4.x by this push:
new 2e2cb90e0310 [SPARK-58222][SQL] Add `try_variant_array_append`
expression
2e2cb90e0310 is described below
commit 2e2cb90e0310506558d49b3825019e08ff86d93e
Author: bojana-db <[email protected]>
AuthorDate: Tue Jul 21 11:16:28 2026 +0000
[SPARK-58222][SQL] Add `try_variant_array_append` expression
### What changes were proposed in this pull request?
Adds the SQL function `try_variant_array_append(v, path, val)`, the
error-tolerant counterpart of `variant_array_append`. It appends a value to the
array in a Variant value at a single JSONPath location, returning NULL instead
of failing the query when the operation hits a recoverable error.
Details:
- On a valid append, behaves exactly like `variant_array_append`: appends
`val` as a new last element of the array at `path` (e.g. `$.a`, `$[0]`,
`$.a[1]`); the root path `$` targets the whole Variant, which must itself be an
array; a missing key or out-of-range array index along the path leaves `v`
unchanged;
- Recoverable errors are caught and return NULL instead of throwing: a path
type mismatch (`VARIANT_PATH_TYPE_MISMATCH`), raised when a path segment is
applied to a value of an incompatible type or when the target is not an array;
- Non-recoverable errors still throw, matching `variant_array_append`: a
malformed path is rejected with `INVALID_VARIANT_PATH` (the path is parsed
before the append), and a result exceeding the size limit raises
`VARIANT_SIZE_LIMIT`;
- Any NULL argument returns NULL;
- The value may be any expression castable to variant. An array value is
appended as a single nested element rather than flattened, and a variant null
appends a null element.
### Why are the changes needed?
Error-tolerant counterpart of `variant_array_append`.
### Does this PR introduce _any_ user-facing change?
Yes, a new SQL function `try_variant_array_append` (and the corresponding
Scala/Python `functions` API).
### How was this patch tested?
Unit tests.
### Was this patch authored or co-authored using generative AI tooling?
Generated-by: Cursor with Claude Opus 4.8
Closes #57378 from bojana-db/try-variant-array-append.
Authored-by: bojana-db <[email protected]>
Signed-off-by: Uros Bojanic <[email protected]>
(cherry picked from commit f0cbaf7862b5f054b5a9d9f83e278abba48373a4)
Signed-off-by: Uros Bojanic <[email protected]>
---
.../source/reference/pyspark.sql/functions.rst | 1 +
python/pyspark/sql/connect/functions/builtin.py | 10 ++
python/pyspark/sql/functions/__init__.py | 1 +
python/pyspark/sql/functions/builtin.py | 61 +++++++-
python/pyspark/sql/tests/test_functions.py | 9 ++
.../scala/org/apache/spark/sql/functions.scala | 45 +++++-
.../sql/catalyst/analysis/FunctionRegistry.scala | 3 +-
.../variant/VariantExpressionEvalUtils.scala | 13 +-
.../expressions/variant/variantExpressions.scala | 174 ++++++++++++++-------
.../variant/VariantExpressionSuite.scala | 116 +++++++++-----
.../apache/spark/sql/PlanGenerationTestSuite.scala | 4 +
.../function_try_variant_array_append.explain | 2 +
.../function_variant_array_append.explain | 2 +-
.../queries/function_try_variant_array_append.json | 125 +++++++++++++++
.../function_try_variant_array_append.proto.bin | Bin 0 -> 1169 bytes
.../sql-functions/sql-expression-schema.md | 3 +-
.../scala/org/apache/spark/sql/VariantSuite.scala | 50 ++++++
17 files changed, 513 insertions(+), 106 deletions(-)
diff --git a/python/docs/source/reference/pyspark.sql/functions.rst
b/python/docs/source/reference/pyspark.sql/functions.rst
index 2ccfde351d87..2e6049f37870 100644
--- a/python/docs/source/reference/pyspark.sql/functions.rst
+++ b/python/docs/source/reference/pyspark.sql/functions.rst
@@ -603,6 +603,7 @@ VARIANT Functions
schema_of_variant_agg
try_variant_get
variant_array_append
+ try_variant_array_append
variant_delete
variant_get
variant_insert
diff --git a/python/pyspark/sql/connect/functions/builtin.py
b/python/pyspark/sql/connect/functions/builtin.py
index 1caa3a9bf7f2..be5e5a4f0c6d 100644
--- a/python/pyspark/sql/connect/functions/builtin.py
+++ b/python/pyspark/sql/connect/functions/builtin.py
@@ -2262,6 +2262,16 @@ def variant_array_append(
variant_array_append.__doc__ = pysparkfuncs.variant_array_append.__doc__
+def try_variant_array_append(
+ v: "ColumnOrName", path: Union[Column, str], value: "ColumnOrName"
+) -> Column:
+ path_col = path if isinstance(path, Column) else lit(path)
+ return _invoke_function("try_variant_array_append", _to_col(v), path_col,
_to_col(value))
+
+
+try_variant_array_append.__doc__ =
pysparkfuncs.try_variant_array_append.__doc__
+
+
def variant_get(v: "ColumnOrName", path: Union[Column, str], targetType: str)
-> Column:
assert isinstance(path, (Column, str))
if isinstance(path, str):
diff --git a/python/pyspark/sql/functions/__init__.py
b/python/pyspark/sql/functions/__init__.py
index b3da0adee990..f1a0e1de5b75 100644
--- a/python/pyspark/sql/functions/__init__.py
+++ b/python/pyspark/sql/functions/__init__.py
@@ -481,6 +481,7 @@ __all__ = [ # noqa: F405
"schema_of_variant_agg",
"try_variant_get",
"variant_array_append",
+ "try_variant_array_append",
"variant_delete",
"variant_get",
"variant_insert",
diff --git a/python/pyspark/sql/functions/builtin.py
b/python/pyspark/sql/functions/builtin.py
index 724d1f90e568..9e092ef1c4fb 100644
--- a/python/pyspark/sql/functions/builtin.py
+++ b/python/pyspark/sql/functions/builtin.py
@@ -22859,8 +22859,8 @@ def variant_array_append(
) -> Column:
"""
Appends a value to the array in a variant at the given JSONPath location.
Returns the variant
- unchanged if a path key or index is absent, throws an error if a path
segment hits a value of
- an incompatible type or the target is not an array, and returns NULL if
any argument is NULL.
+ unchanged if a path key or index is absent. Throws an error if a path
segment hits a value of
+ an incompatible type or the target is not an array. Returns NULL if any
argument is NULL.
.. versionadded:: 4.3.0
@@ -22914,6 +22914,63 @@ def variant_array_append(
)
+@_try_remote_functions
+def try_variant_array_append(
+ v: "ColumnOrName", path: Union[Column, str], value: "ColumnOrName"
+) -> Column:
+ """
+ Appends a value to the array in a variant at the given JSONPath location.
Returns the variant
+ unchanged if a path key or index is absent. Returns NULL if a path segment
hits a value of an
+ incompatible type, the target is not an array, or if any argument is NULL.
+
+ .. versionadded:: 4.3.0
+
+ Parameters
+ ----------
+ v : :class:`~pyspark.sql.Column` or str
+ a variant column or column name
+ path : :class:`~pyspark.sql.Column` or str
+ the JSONPath target array. A `str` is a literal path; a
:class:`~pyspark.sql.Column`
+ supplies the path at runtime. A valid path should start with `$` and
is followed by zero or
+ more segments like `[123]`, `.name`, `['name']`, or `["name"]`.
+ value : :class:`~pyspark.sql.Column` or str
+ the value to append. Any expression castable to variant.
+
+ Returns
+ -------
+ :class:`~pyspark.sql.Column`
+ a variant column with `value` appended to the array at `path`
+
+ Examples
+ --------
+ >>> from pyspark.sql.functions import lit, parse_json, to_json,
try_variant_array_append
+ >>> df = spark.createDataFrame([{
+ ... 'json': '''[[1, 2], 5]''',
+ ... 'path': '$[0]'
+ ... }])
+ >>> v = parse_json(df.json)
+ >>> df.select(to_json(try_variant_array_append(v, "$",
lit(3))).alias("r")).collect()
+ [Row(r='[[1,2],5,3]')]
+ >>> df.select(to_json(try_variant_array_append(v, "$[5]",
lit(3))).alias("r")).collect()
+ [Row(r='[[1,2],5]')]
+ >>> df.select(to_json(try_variant_array_append(v, df.path,
lit(9))).alias("r")).collect()
+ [Row(r='[[1,2,9],5]')]
+ >>> df.select(to_json(try_variant_array_append(v, "$[1]",
lit(9))).alias("r")).collect()
+ [Row(r=None)]
+ >>> df.select(try_variant_array_append(v, "$",
lit(None)).alias("r")).collect()
+ [Row(r=None)]
+ """
+ from pyspark.sql.classic.column import _to_java_column
+
+ path_col = path if isinstance(path, Column) else lit(path)
+ return _invoke_function(
+ "try_variant_array_append",
+ _to_java_column(v),
+ _to_java_column(path_col),
+ _to_java_column(value),
+ )
+
+
@_try_remote_functions
def variant_get(v: "ColumnOrName", path: Union[Column, str], targetType: str)
-> Column:
"""
diff --git a/python/pyspark/sql/tests/test_functions.py
b/python/pyspark/sql/tests/test_functions.py
index 6367ebfdd9bf..2594c8c60b76 100644
--- a/python/pyspark/sql/tests/test_functions.py
+++ b/python/pyspark/sql/tests/test_functions.py
@@ -3569,6 +3569,15 @@ class FunctionsTestsMixin:
df.select(F.to_json(F.variant_array_append(arr, df.arrpath,
F.lit(9)))),
["[1,2,9]", "[[3,9],4]"],
)
+ check(
+ df.select(F.to_json(F.try_variant_array_append(arr, "$",
F.lit(9)))),
+ ["[1,2,9]", "[[3],4,9]"],
+ )
+ check(df.select(F.to_json(F.try_variant_array_append(arr, "$.a",
F.lit(9)))), [None, None])
+ check(
+ df.select(F.to_json(F.try_variant_array_append(arr, df.arrpath,
F.lit(9)))),
+ ["[1,2,9]", "[[3,9],4]"],
+ )
check(df.select(F.schema_of_variant(v)), ["OBJECT<a: BIGINT>",
"OBJECT<b: BIGINT>"])
check(df.select(F.schema_of_variant_agg(v)), ["OBJECT<a: BIGINT, b:
BIGINT>"])
diff --git a/sql/api/src/main/scala/org/apache/spark/sql/functions.scala
b/sql/api/src/main/scala/org/apache/spark/sql/functions.scala
index 59af71017882..6d824a675223 100644
--- a/sql/api/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/api/src/main/scala/org/apache/spark/sql/functions.scala
@@ -14292,8 +14292,8 @@ object functions {
/**
* Appends a value to the array in a variant at the given JSONPath location.
Returns the variant
- * unchanged if a path key or index is absent, throws an error if a path
segment hits a value of
- * an incompatible type or the target is not an array, and returns NULL if
any argument is NULL.
+ * unchanged if a path key or index is absent. Throws an error if a path
segment hits a value of
+ * an incompatible type or the target is not an array. Returns NULL if any
argument is NULL.
*
* @param v
* a variant column. A column that evaluates to a variant.
@@ -14311,8 +14311,8 @@ object functions {
/**
* Appends a value to the array in a variant at the given JSONPath location.
Returns the variant
- * unchanged if a path key or index is absent, throws an error if a path
segment hits a value of
- * an incompatible type or the target is not an array, and returns NULL if
any argument is NULL.
+ * unchanged if a path key or index is absent. Throws an error if a path
segment hits a value of
+ * an incompatible type or the target is not an array. Returns NULL if any
argument is NULL.
*
* @param v
* a variant column. A column that evaluates to a variant.
@@ -14328,6 +14328,43 @@ object functions {
def variant_array_append(v: Column, path: String, value: Column): Column =
Column.fn("variant_array_append", v, lit(path), value)
+ /**
+ * Appends a value to the array in a variant at the given JSONPath location.
Returns the variant
+ * unchanged if a path key or index is absent. Returns NULL if a path
segment hits a value of an
+ * incompatible type, the target is not an array, or if any argument is NULL.
+ *
+ * @param v
+ * a variant column.
+ * @param path
+ * the column containing the JSONPath string identifying the target array.
A valid path should
+ * start with `$` and is followed by zero or more segments like `[123]`,
`.name`, `['name']`,
+ * or `["name"]`.
+ * @param value
+ * the value to append. Any expression castable to variant.
+ * @group variant_funcs
+ * @since 4.3.0
+ */
+ def try_variant_array_append(v: Column, path: Column, value: Column): Column
=
+ Column.fn("try_variant_array_append", v, path, value)
+
+ /**
+ * Appends a value to the array in a variant at the given JSONPath location.
Returns the variant
+ * unchanged if a path key or index is absent. Returns NULL if a path
segment hits a value of an
+ * incompatible type, the target is not an array, or if any argument is NULL.
+ *
+ * @param v
+ * a variant column.
+ * @param path
+ * the JSONPath identifying the target array. A valid path should start
with `$` and is
+ * followed by zero or more segments like `[123]`, `.name`, `['name']`, or
`["name"]`.
+ * @param value
+ * the value to append. Any expression castable to variant.
+ * @group variant_funcs
+ * @since 4.3.0
+ */
+ def try_variant_array_append(v: Column, path: String, value: Column): Column
=
+ Column.fn("try_variant_array_append", v, lit(path), value)
+
/**
* Extracts a sub-variant from `v` according to `path` string, and then cast
the sub-variant to
* `targetType`. Returns null if the path does not exist. Throws an
exception if the cast fails.
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
index a9be95d7b951..b34a5b7ad1b0 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
@@ -989,7 +989,8 @@ object FunctionRegistry {
expressionBuilder("variant_insert", VariantInsertExpressionBuilder),
expressionBuilder("try_variant_insert", TryVariantInsertExpressionBuilder),
expressionBuilder("variant_set", VariantSetExpressionBuilder),
- expression[VariantArrayAppend]("variant_array_append"),
+ expressionBuilder("variant_array_append",
VariantArrayAppendExpressionBuilder),
+ expressionBuilder("try_variant_array_append",
TryVariantArrayAppendExpressionBuilder),
// Spatial
expression[ST_AsBinary]("st_asbinary"),
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala
index ba5d72c56474..0872cda99801 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala
@@ -224,7 +224,9 @@ object VariantExpressionEvalUtils {
* Append `value` to the array in `input` at `javaSegments`. `path` is the
source string used in
* error messages. `value` is cast to a variant first; a size overflow maps
to
* `VARIANT_SIZE_LIMIT` and a target that is not an array (or an
incompatible path segment) maps
- * to `VARIANT_PATH_TYPE_MISMATCH`.
+ * to `VARIANT_PATH_TYPE_MISMATCH`. When `failOnError` is false (the
`try_variant_array_append`
+ * mode), a path type mismatch returns null instead of throwing; a size
overflow (and a malformed
+ * path, rejected earlier during parsing) is still raised.
*/
def arrayAppendAtPath(
input: VariantVal,
@@ -232,7 +234,8 @@ object VariantExpressionEvalUtils {
path: String,
value: Any,
valueDataType: DataType,
- functionName: String): VariantVal = {
+ functionName: String,
+ failOnError: Boolean): VariantVal = {
val v = new Variant(input.getValue, input.getMetadata)
try {
val valVal = castToVariant(value, valueDataType)
@@ -240,6 +243,7 @@ object VariantExpressionEvalUtils {
val out = VariantBuilder.arrayAppendAtPath(v, javaSegments, valVariant)
new VariantVal(out.getValue, out.getMetadata)
} catch {
+ case _: VariantPathTypeMismatchException if !failOnError => null
case e: VariantPathTypeMismatchException =>
throw QueryExecutionErrors.variantPathTypeMismatch(
path, renderVariantPath(javaSegments.take(e.depth)), functionName)
@@ -253,10 +257,11 @@ object VariantExpressionEvalUtils {
path: UTF8String,
value: Any,
valueDataType: DataType,
- functionName: String): VariantVal = {
+ functionName: String,
+ failOnError: Boolean): VariantVal = {
val pathStr = path.toString
val javaSegments = toJavaSegments(parseVariantPath(pathStr, functionName,
allowRoot = true))
- arrayAppendAtPath(input, javaSegments, pathStr, value, valueDataType,
functionName)
+ arrayAppendAtPath(input, javaSegments, pathStr, value, valueDataType,
functionName, failOnError)
}
/** Cast a Spark value from `dataType` into the variant type. */
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala
index 469dc57a50ae..fa6a955097d9 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala
@@ -1192,40 +1192,11 @@ object VariantSetExpressionBuilder extends
ExpressionBuilder {
}
}
-// scalastyle:off line.size.limit
-@ExpressionDescription(
- usage = "_FUNC_(v, path, val) - Appends a value to the array in a variant at
the given JSONPath " +
- "location. Returns the variant unchanged if a path key or index is absent.
Throws an error " +
- "if a path segment hits a value of an incompatible type or the target is
not an array. " +
- "Returns NULL if any argument is NULL.",
- arguments = """
- Arguments:
- * v - A variant value to mutate.
- * path - A string expression evaluating to a JSONPath identifying the
target array. A valid
- path should start with `$` and is followed by zero or more segments
like `[123]`, `.name`,
- `['name']`, or `["name"]`.
- * val - Any expression castable to variant.
- """,
- examples = """
- Examples:
- > SELECT _FUNC_(parse_json('[1, 2, 3]'), '$', 4);
- [1,2,3,4]
- > SELECT _FUNC_(parse_json('{"a": [1, 2]}'), '$.a', 3);
- {"a":[1,2,3]}
- > SELECT _FUNC_(parse_json('[1]'), '$', parse_json('[2, 3]'));
- [1,[2,3]]
- > SELECT _FUNC_(parse_json('{"a": 1}'), '$.missing', 2);
- {"a":1}
- > SELECT _FUNC_(parse_json('[1, 2]'), '$', parse_json('null'));
- [1,2,null]
- > SELECT _FUNC_(parse_json('[1, 2]'), '$', null);
- NULL
- """,
- since = "4.3.0",
- group = "variant_funcs"
-)
-// scalastyle:on line.size.limit
-case class VariantArrayAppend(input: Expression, path: Expression, value:
Expression)
+case class VariantArrayAppend(
+ input: Expression,
+ path: Expression,
+ value: Expression,
+ failOnError: Boolean = true)
extends TernaryExpression
with ExpectsInputTypes
with QueryErrorsBase {
@@ -1235,6 +1206,7 @@ case class VariantArrayAppend(input: Expression, path:
Expression, value: Expres
override def third: Expression = value
override def nullIntolerant: Boolean = true
+ override def nullable: Boolean = !failOnError || children.exists(_.nullable)
override def dataType: DataType = VariantType
override def inputTypes: Seq[AbstractDataType] =
@@ -1279,34 +1251,47 @@ case class VariantArrayAppend(input: Expression, path:
Expression, value: Expres
foldablePath match {
case Some(parsed) =>
VariantExpressionEvalUtils.arrayAppendAtPath(
- inputVariant, parsed.javaSegments, parsed.pathStr, valValue,
value.dataType, prettyName)
+ inputVariant, parsed.javaSegments, parsed.pathStr, valValue,
value.dataType, prettyName,
+ failOnError)
case None =>
VariantExpressionEvalUtils.arrayAppendAtPath(
- inputVariant, p.asInstanceOf[UTF8String], valValue, value.dataType,
prettyName)
+ inputVariant, p.asInstanceOf[UTF8String], valValue, value.dataType,
prettyName,
+ failOnError)
}
}
override protected def doGenCode(ctx: CodegenContext, ev: ExprCode):
ExprCode = {
val cls = VariantExpressionEvalUtils.getClass.getName.stripSuffix("$")
- nullSafeCodeGen(ctx, ev, (vVal, pVal, valVal) => {
- val fromArg = ctx.addReferenceObj("from", value.dataType)
- foldablePath match {
- case Some(parsed) =>
- val parsedArg = ctx.addReferenceObj("appendPath", parsed)
- s"""
- |${ev.value} = $cls.arrayAppendAtPath(
- | $vVal, $parsedArg.javaSegments(), $parsedArg.pathStr(),
$valVal, $fromArg,
- | "$prettyName");
- """.stripMargin
- case None =>
- s"""
- |${ev.value} = $cls.arrayAppendAtPath($vVal, $pVal, $valVal,
$fromArg, "$prettyName");
- """.stripMargin
- }
- })
+ val fromArg = ctx.addReferenceObj("from", value.dataType)
+ def call(vVal: String, pVal: String, valVal: String): String =
foldablePath match {
+ case Some(parsed) =>
+ val parsedArg = ctx.addReferenceObj("appendPath", parsed)
+ s"""$cls.arrayAppendAtPath(
+ | $vVal, $parsedArg.javaSegments(), $parsedArg.pathStr(), $valVal,
$fromArg,
+ | "$prettyName", $failOnError)""".stripMargin
+ case None =>
+ s"""$cls.arrayAppendAtPath($vVal, $pVal, $valVal, $fromArg,
"$prettyName", $failOnError)"""
+ }
+ if (failOnError) {
+ nullSafeCodeGen(ctx, ev,
+ (vVal, pVal, valVal) => s"${ev.value} = ${call(vVal, pVal, valVal)};")
+ } else {
+ val resultType = CodeGenerator.javaType(VariantType)
+ val tmp = ctx.freshName("appendResult")
+ nullSafeCodeGen(ctx, ev, (vVal, pVal, valVal) =>
+ s"""
+ |$resultType $tmp = ${call(vVal, pVal, valVal)};
+ |if ($tmp == null) {
+ | ${ev.isNull} = true;
+ |} else {
+ | ${ev.value} = $tmp;
+ |}
+ """.stripMargin)
+ }
}
- override def prettyName: String = "variant_array_append"
+ override def prettyName: String =
+ if (failOnError) "variant_array_append" else "try_variant_array_append"
override protected def withNewChildrenInternal(
newFirst: Expression, newSecond: Expression, newThird: Expression):
VariantArrayAppend =
@@ -1323,6 +1308,89 @@ object VariantArrayAppend {
}
}
+abstract class VariantArrayAppendExpressionBuilderBase(failOnError: Boolean)
+ extends ExpressionBuilder {
+ override def build(funcName: String, expressions: Seq[Expression]):
Expression = {
+ val numArgs = expressions.length
+ if (numArgs == 3) {
+ VariantArrayAppend(expressions(0), expressions(1), expressions(2),
failOnError)
+ } else {
+ throw QueryCompilationErrors.wrongNumArgsError(funcName, Seq(3), numArgs)
+ }
+ }
+}
+
+// scalastyle:off line.size.limit
+@ExpressionDescription(
+ usage = "_FUNC_(v, path, val) - Appends a value to the array in a variant at
the given JSONPath " +
+ "location. Returns the variant unchanged if a path key or index is absent.
Throws an error " +
+ "if a path segment hits a value of an incompatible type or the target is
not an array. " +
+ "Returns NULL if any argument is NULL.",
+ arguments = """
+ Arguments:
+ * v - A variant value to mutate.
+ * path - A string expression evaluating to a JSONPath identifying the
target array. A valid
+ path should start with `$` and is followed by zero or more segments
like `[123]`, `.name`,
+ `['name']`, or `["name"]`.
+ * val - Any expression castable to variant.
+ """,
+ examples = """
+ Examples:
+ > SELECT _FUNC_(parse_json('[1, 2, 3]'), '$', 4);
+ [1,2,3,4]
+ > SELECT _FUNC_(parse_json('{"a": [1, 2]}'), '$.a', 3);
+ {"a":[1,2,3]}
+ > SELECT _FUNC_(parse_json('[1]'), '$', parse_json('[2, 3]'));
+ [1,[2,3]]
+ > SELECT _FUNC_(parse_json('{"a": 1}'), '$.missing', 2);
+ {"a":1}
+ > SELECT _FUNC_(parse_json('[1, 2]'), '$', parse_json('null'));
+ [1,2,null]
+ > SELECT _FUNC_(parse_json('[1, 2]'), '$', null);
+ NULL
+ """,
+ since = "4.3.0",
+ group = "variant_funcs"
+)
+// scalastyle:on line.size.limit
+object VariantArrayAppendExpressionBuilder extends
VariantArrayAppendExpressionBuilderBase(true)
+
+// scalastyle:off line.size.limit
+@ExpressionDescription(
+ usage = "_FUNC_(v, path, val) - Appends a value to the array in a variant at
the given JSONPath " +
+ "location. Returns the variant unchanged if a path key or index is absent.
Returns NULL if a " +
+ "path segment hits a value of an incompatible type, the target is not an
array, or if any " +
+ "argument is NULL.",
+ arguments = """
+ Arguments:
+ * v - A variant value to mutate.
+ * path - A string expression evaluating to a JSONPath identifying the
target array. A valid
+ path should start with `$` and is followed by zero or more segments
like `[123]`, `.name`,
+ `['name']`, or `["name"]`.
+ * val - Any expression castable to variant.
+ """,
+ examples = """
+ Examples:
+ > SELECT _FUNC_(parse_json('[1, 2, 3]'), '$', 4);
+ [1,2,3,4]
+ > SELECT _FUNC_(parse_json('{"a": [1, 2]}'), '$.a', 3);
+ {"a":[1,2,3]}
+ > SELECT _FUNC_(parse_json('[1]'), '$', parse_json('[2, 3]'));
+ [1,[2,3]]
+ > SELECT _FUNC_(parse_json('{"a": 1}'), '$.missing', 2);
+ {"a":1}
+ > SELECT _FUNC_(parse_json('{"a": 1}'), '$.a', 2);
+ NULL
+ > SELECT _FUNC_(parse_json('[1, 2]'), '$', null);
+ NULL
+ """,
+ since = "4.3.0",
+ group = "variant_funcs"
+)
+// scalastyle:on line.size.limit
+object TryVariantArrayAppendExpressionBuilder
+ extends VariantArrayAppendExpressionBuilderBase(false)
+
case class VariantExplode(child: Expression) extends UnaryExpression with
Generator
with ExpectsInputTypes {
override def inputTypes: Seq[AbstractDataType] = Seq(VariantType)
diff --git
a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionSuite.scala
b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionSuite.scala
index c5488e1f52ff..92f20bcc3127 100644
---
a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionSuite.scala
+++
b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionSuite.scala
@@ -1657,11 +1657,49 @@ class VariantExpressionSuite extends SparkFunSuite with
ExpressionEvalHelper {
test("variant_array_append") {
def checkAppend(input: String, path: String, value: Expression, expected:
String): Unit = {
- val expr = VariantArrayAppend(
- Literal(parseJson(input)), Literal.create(path, StringType), value)
+ Seq(true, false).foreach { failOnError =>
+ val expr = VariantArrayAppend(
+ Literal(parseJson(input)), Literal.create(path, StringType), value,
failOnError)
+ checkEvaluation(
+ ResolveTimeZone.resolveTimeZones(Cast(expr, StringType)),
+ expected)
+ }
+ }
+
+ // A recoverable error: `variant_array_append` throws, but
`try_variant_array_append` returns
+ // NULL.
+ def checkAppendRecoverableError(
+ input: String,
+ path: String,
+ value: Expression,
+ condition: String,
+ parameters: Map[String, String]): Unit = {
+ checkErrorInExpression[SparkRuntimeException](
+ VariantArrayAppend(Literal(parseJson(input)), Literal.create(path,
StringType), value),
+ condition,
+ parameters)
checkEvaluation(
- ResolveTimeZone.resolveTimeZones(Cast(expr, StringType)),
- expected)
+ VariantArrayAppend(Literal(parseJson(input)), Literal.create(path,
StringType), value,
+ failOnError = false),
+ null)
+ }
+
+ // An unrecoverable error (a malformed path or a size overflow): both
functions throw, and only
+ // the `functionName` in the error message differs.
+ def checkAppendUnrecoverableError(
+ input: String,
+ path: String,
+ value: Expression,
+ condition: String,
+ parameters: String => Map[String, String]): Unit = {
+ Seq("variant_array_append" -> true, "try_variant_array_append" ->
false).foreach {
+ case (name, failOnError) =>
+ checkErrorInExpression[SparkRuntimeException](
+ VariantArrayAppend(Literal(parseJson(input)), Literal.create(path,
StringType), value,
+ failOnError),
+ condition,
+ parameters(name))
+ }
}
// Append to the root array, and to nested arrays reached through object
keys / array indices.
@@ -1691,46 +1729,45 @@ class VariantExpressionSuite extends SparkFunSuite with
ExpressionEvalHelper {
checkAppend("""{"a": [1]}""", "$.missing", Literal(2), """{"a":[1]}""")
checkAppend("[[1]]", "$[5]", Literal(2), "[[1]]")
- // NULL-intolerant: any NULL argument yields NULL.
- checkEvaluation(
- VariantArrayAppend(Literal.create(null, VariantType), Literal("$"),
Literal(1)),
- null)
+ Seq(true, false).foreach { failOnError =>
+ checkEvaluation(
+ VariantArrayAppend(
+ Literal.create(null, VariantType), Literal("$"), Literal(1),
failOnError),
+ null)
+ }
checkAppend("[1]", null, Literal(1), null)
checkAppend("[1]", "$", Literal.create(null, VariantType), null)
checkAppend("[1]", "$", Literal.create(null, NullType), null)
- // Dynamic (non-foldable) path.
- val dynamic = VariantArrayAppend(
- Literal(parseJson("""{"a": [1, 2]}""")),
- BoundReference(0, StringType, nullable = true),
- Literal(3))
- checkEvaluation(
- ResolveTimeZone.resolveTimeZones(Cast(dynamic, StringType)),
- """{"a":[1,2,3]}""",
- InternalRow(UTF8String.fromString("$.a")))
+ Seq(true, false).foreach { failOnError =>
+ val dynamic = VariantArrayAppend(
+ Literal(parseJson("""{"a": [1, 2]}""")),
+ BoundReference(0, StringType, nullable = true),
+ Literal(3),
+ failOnError)
+ checkEvaluation(
+ ResolveTimeZone.resolveTimeZones(Cast(dynamic, StringType)),
+ """{"a":[1,2,3]}""",
+ InternalRow(UTF8String.fromString("$.a")))
+ }
+ // Recoverable errors: `variant_array_append` throws;
`try_variant_array_append` returns NULL.
// The target is not an array (a scalar leaf, or an object at the root).
- checkErrorInExpression[SparkRuntimeException](
- VariantArrayAppend(Literal(parseJson("""{"a": 1}""")), Literal("$.a"),
Literal(2)),
+ checkAppendRecoverableError("""{"a": 1}""", "$.a", Literal(2),
"VARIANT_PATH_TYPE_MISMATCH",
Map("path" -> "$.a", "failedAt" -> "$.a", "functionName" ->
"`variant_array_append`"))
- checkErrorInExpression[SparkRuntimeException](
- VariantArrayAppend(Literal(parseJson("""{"a": 1}""")), Literal("$"),
Literal(2)),
+ checkAppendRecoverableError("""{"a": 1}""", "$", Literal(2),
"VARIANT_PATH_TYPE_MISMATCH",
Map("path" -> "$", "failedAt" -> "$", "functionName" ->
"`variant_array_append`"))
-
// A segment applied to an incompatible container: descending into a
scalar, an array index on
// an object, or an object key on an array.
- checkErrorInExpression[SparkRuntimeException](
- VariantArrayAppend(Literal(parseJson("""{"a": 1}""")), Literal("$.a.b"),
Literal(2)),
+ checkAppendRecoverableError("""{"a": 1}""", "$.a.b", Literal(2),
"VARIANT_PATH_TYPE_MISMATCH",
Map("path" -> "$.a.b", "failedAt" -> "$.a", "functionName" ->
"`variant_array_append`"))
- checkErrorInExpression[SparkRuntimeException](
- VariantArrayAppend(Literal(parseJson("""{"a": 1}""")), Literal("$[0]"),
Literal(2)),
+ checkAppendRecoverableError("""{"a": 1}""", "$[0]", Literal(2),
"VARIANT_PATH_TYPE_MISMATCH",
Map("path" -> "$[0]", "failedAt" -> "$", "functionName" ->
"`variant_array_append`"))
- checkErrorInExpression[SparkRuntimeException](
- VariantArrayAppend(Literal(parseJson("[1, 2]")), Literal("$.a"),
Literal(2)),
+ checkAppendRecoverableError("[1, 2]", "$.a", Literal(2),
"VARIANT_PATH_TYPE_MISMATCH",
Map("path" -> "$.a", "failedAt" -> "$", "functionName" ->
"`variant_array_append`"))
@@ -1739,26 +1776,25 @@ class VariantExpressionSuite extends SparkFunSuite with
ExpressionEvalHelper {
Literal.create(null, MapType(StringType, IntegerType)),
Literal.create(null, StructType(Seq(StructField("x", IntegerType))))
).foreach { v =>
- assert(
- VariantArrayAppend(Literal(parseJson("[]")), Literal("$"),
v).checkInputDataTypes()
- .isFailure)
+ Seq(true, false).foreach { failOnError =>
+ assert(
+ VariantArrayAppend(Literal(parseJson("[]")), Literal("$"), v,
failOnError)
+ .checkInputDataTypes().isFailure)
+ }
}
- // The root `$` is a valid target here, but a malformed path is still
rejected.
- checkErrorInExpression[SparkRuntimeException](
- VariantArrayAppend(Literal(parseJson("[]")), Literal("abc"), Literal(1)),
+ // Unrecoverable errors: both functions throw. The root `$` is a valid
target, but a malformed
+ // path is still rejected, and a size overflow surfaces as
VARIANT_SIZE_LIMIT.
+ checkAppendUnrecoverableError("[]", "abc", Literal(1),
"INVALID_VARIANT_PATH",
- Map("path" -> "abc", "functionName" -> "`variant_array_append`"))
+ name => Map("path" -> "abc", "functionName" -> s"`$name`"))
checkErrorInExpression[SparkRuntimeException](
VariantArrayAppend(Literal(parseJson("[]")), Literal(""), Literal(1)),
"INVALID_VARIANT_PATH",
Map("path" -> "", "functionName" -> "`variant_array_append`"))
-
- // Appending a value that overflows the variant size limit surfaces as
VARIANT_SIZE_LIMIT.
val tooBig = "x".repeat(16 * 1024 * 1024)
- checkErrorInExpression[SparkRuntimeException](
- VariantArrayAppend(Literal(parseJson("[]")), Literal("$"),
Literal(tooBig)),
+ checkAppendUnrecoverableError("[]", "$", Literal(tooBig),
"VARIANT_SIZE_LIMIT",
- Map("sizeLimit" -> "16.0 MiB", "functionName" ->
"`variant_array_append`"))
+ name => Map("sizeLimit" -> "16.0 MiB", "functionName" -> s"`$name`"))
}
}
diff --git
a/sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/PlanGenerationTestSuite.scala
b/sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/PlanGenerationTestSuite.scala
index 77ec3eacc510..068460293f15 100644
---
a/sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/PlanGenerationTestSuite.scala
+++
b/sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/PlanGenerationTestSuite.scala
@@ -2783,6 +2783,10 @@ class PlanGenerationTestSuite extends ConnectFunSuite
with Logging {
fn.variant_array_append(fn.parse_json(fn.col("g")), "$.a", fn.lit(1))
}
+ functionTest("try_variant_array_append") {
+ fn.try_variant_array_append(fn.parse_json(fn.col("g")), "$.a", fn.lit(1))
+ }
+
functionTest("variant_get") {
fn.variant_get(fn.parse_json(fn.col("g")), "$", "int")
}
diff --git
a/sql/connect/common/src/test/resources/query-tests/explain-results/function_try_variant_array_append.explain
b/sql/connect/common/src/test/resources/query-tests/explain-results/function_try_variant_array_append.explain
new file mode 100644
index 000000000000..0905c744ce77
--- /dev/null
+++
b/sql/connect/common/src/test/resources/query-tests/explain-results/function_try_variant_array_append.explain
@@ -0,0 +1,2 @@
+Project
[try_variant_array_append(static_invoke(VariantExpressionEvalUtils.parseJson(g#0,
false, true, true)), $.a, 1, false) AS try_variant_array_append(parse_json(g),
$.a, 1)#0]
++- LocalRelation <empty>, [id#0L, a#0, b#0, d#0, e#0, f#0, g#0]
diff --git
a/sql/connect/common/src/test/resources/query-tests/explain-results/function_variant_array_append.explain
b/sql/connect/common/src/test/resources/query-tests/explain-results/function_variant_array_append.explain
index 4ebc4a11af67..4fcec34c6c2d 100644
---
a/sql/connect/common/src/test/resources/query-tests/explain-results/function_variant_array_append.explain
+++
b/sql/connect/common/src/test/resources/query-tests/explain-results/function_variant_array_append.explain
@@ -1,2 +1,2 @@
-Project
[variant_array_append(static_invoke(VariantExpressionEvalUtils.parseJson(g#0,
false, true, true)), $.a, 1) AS variant_array_append(parse_json(g), $.a, 1)#0]
+Project
[variant_array_append(static_invoke(VariantExpressionEvalUtils.parseJson(g#0,
false, true, true)), $.a, 1, true) AS variant_array_append(parse_json(g), $.a,
1)#0]
+- LocalRelation <empty>, [id#0L, a#0, b#0, d#0, e#0, f#0, g#0]
diff --git
a/sql/connect/common/src/test/resources/query-tests/queries/function_try_variant_array_append.json
b/sql/connect/common/src/test/resources/query-tests/queries/function_try_variant_array_append.json
new file mode 100644
index 000000000000..225fe01bb676
--- /dev/null
+++
b/sql/connect/common/src/test/resources/query-tests/queries/function_try_variant_array_append.json
@@ -0,0 +1,125 @@
+{
+ "common": {
+ "planId": "1"
+ },
+ "project": {
+ "input": {
+ "common": {
+ "planId": "0"
+ },
+ "localRelation": {
+ "schema":
"struct\u003cid:bigint,a:int,b:double,d:struct\u003cid:bigint,a:int,b:double\u003e,e:array\u003cint\u003e,f:map\u003cstring,struct\u003cid:bigint,a:int,b:double\u003e\u003e,g:string\u003e"
+ }
+ },
+ "expressions": [{
+ "unresolvedFunction": {
+ "functionName": "try_variant_array_append",
+ "arguments": [{
+ "unresolvedFunction": {
+ "functionName": "parse_json",
+ "arguments": [{
+ "unresolvedAttribute": {
+ "unparsedIdentifier": "g"
+ },
+ "common": {
+ "origin": {
+ "jvmOrigin": {
+ "stackTrace": [{
+ "classLoaderName": "app",
+ "declaringClass": "org.apache.spark.sql.functions$",
+ "methodName": "col",
+ "fileName": "functions.scala"
+ }, {
+ "classLoaderName": "app",
+ "declaringClass":
"org.apache.spark.sql.PlanGenerationTestSuite",
+ "methodName": "~~trimmed~anonfun~~",
+ "fileName": "PlanGenerationTestSuite.scala"
+ }]
+ }
+ }
+ }
+ }],
+ "isInternal": false
+ },
+ "common": {
+ "origin": {
+ "jvmOrigin": {
+ "stackTrace": [{
+ "classLoaderName": "app",
+ "declaringClass": "org.apache.spark.sql.functions$",
+ "methodName": "parse_json",
+ "fileName": "functions.scala"
+ }, {
+ "classLoaderName": "app",
+ "declaringClass":
"org.apache.spark.sql.PlanGenerationTestSuite",
+ "methodName": "~~trimmed~anonfun~~",
+ "fileName": "PlanGenerationTestSuite.scala"
+ }]
+ }
+ }
+ }
+ }, {
+ "literal": {
+ "string": "$.a"
+ },
+ "common": {
+ "origin": {
+ "jvmOrigin": {
+ "stackTrace": [{
+ "classLoaderName": "app",
+ "declaringClass": "org.apache.spark.sql.functions$",
+ "methodName": "try_variant_array_append",
+ "fileName": "functions.scala"
+ }, {
+ "classLoaderName": "app",
+ "declaringClass":
"org.apache.spark.sql.PlanGenerationTestSuite",
+ "methodName": "~~trimmed~anonfun~~",
+ "fileName": "PlanGenerationTestSuite.scala"
+ }]
+ }
+ }
+ }
+ }, {
+ "literal": {
+ "integer": 1
+ },
+ "common": {
+ "origin": {
+ "jvmOrigin": {
+ "stackTrace": [{
+ "classLoaderName": "app",
+ "declaringClass": "org.apache.spark.sql.functions$",
+ "methodName": "lit",
+ "fileName": "functions.scala"
+ }, {
+ "classLoaderName": "app",
+ "declaringClass":
"org.apache.spark.sql.PlanGenerationTestSuite",
+ "methodName": "~~trimmed~anonfun~~",
+ "fileName": "PlanGenerationTestSuite.scala"
+ }]
+ }
+ }
+ }
+ }],
+ "isInternal": false
+ },
+ "common": {
+ "origin": {
+ "jvmOrigin": {
+ "stackTrace": [{
+ "classLoaderName": "app",
+ "declaringClass": "org.apache.spark.sql.functions$",
+ "methodName": "try_variant_array_append",
+ "fileName": "functions.scala"
+ }, {
+ "classLoaderName": "app",
+ "declaringClass": "org.apache.spark.sql.PlanGenerationTestSuite",
+ "methodName": "~~trimmed~anonfun~~",
+ "fileName": "PlanGenerationTestSuite.scala"
+ }]
+ }
+ }
+ }
+ }]
+ }
+}
\ No newline at end of file
diff --git
a/sql/connect/common/src/test/resources/query-tests/queries/function_try_variant_array_append.proto.bin
b/sql/connect/common/src/test/resources/query-tests/queries/function_try_variant_array_append.proto.bin
new file mode 100644
index 000000000000..3124014ef2a2
Binary files /dev/null and
b/sql/connect/common/src/test/resources/query-tests/queries/function_try_variant_array_append.proto.bin
differ
diff --git a/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
b/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
index 481c17e12486..4ed20ba4aa93 100644
--- a/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
+++ b/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
@@ -554,9 +554,10 @@
| org.apache.spark.sql.catalyst.expressions.variant.SchemaOfVariantAgg |
schema_of_variant_agg | SELECT schema_of_variant_agg(parse_json(j)) FROM VALUES
('1'), ('2'), ('3') AS tab(j) |
struct<schema_of_variant_agg(parse_json(j)):string> |
| org.apache.spark.sql.catalyst.expressions.variant.ToVariantObject |
to_variant_object | SELECT to_variant_object(named_struct('a', 1, 'b', 2)) |
struct<to_variant_object(named_struct(a, 1, b, 2)):variant> |
|
org.apache.spark.sql.catalyst.expressions.variant.TryParseJsonExpressionBuilder
| try_parse_json | SELECT try_parse_json('{"a":1,"b":0.8}') |
struct<try_parse_json({"a":1,"b":0.8}):variant> |
+|
org.apache.spark.sql.catalyst.expressions.variant.TryVariantArrayAppendExpressionBuilder
| try_variant_array_append | SELECT try_variant_array_append(parse_json('[1,
2, 3]'), '$', 4) | struct<try_variant_array_append(parse_json([1, 2, 3]), $,
4):variant> |
|
org.apache.spark.sql.catalyst.expressions.variant.TryVariantGetExpressionBuilder
| try_variant_get | SELECT try_variant_get(parse_json('{"a": 1}'), '$.a',
'int') | struct<try_variant_get(parse_json({"a": 1}), $.a):int> |
|
org.apache.spark.sql.catalyst.expressions.variant.TryVariantInsertExpressionBuilder
| try_variant_insert | SELECT try_variant_insert(parse_json('{"a": 1}'),
'$.b', 2) | struct<try_variant_insert(parse_json({"a": 1}), $.b, 2):variant> |
-| org.apache.spark.sql.catalyst.expressions.variant.VariantArrayAppend |
variant_array_append | SELECT variant_array_append(parse_json('[1, 2, 3]'),
'$', 4) | struct<variant_array_append(parse_json([1, 2, 3]), $, 4):variant> |
+|
org.apache.spark.sql.catalyst.expressions.variant.VariantArrayAppendExpressionBuilder
| variant_array_append | SELECT variant_array_append(parse_json('[1, 2, 3]'),
'$', 4) | struct<variant_array_append(parse_json([1, 2, 3]), $, 4):variant> |
| org.apache.spark.sql.catalyst.expressions.variant.VariantDelete |
variant_delete | SELECT variant_delete(parse_json('{"a": 1, "b": 2, "c": 3,
"items": [1, 2, 3]}'), NULL, '$.a', '$.c') |
struct<variant_delete(parse_json({"a": 1, "b": 2, "c": 3, "items": [1, 2, 3]}),
NULL, $.a, $.c):variant> |
|
org.apache.spark.sql.catalyst.expressions.variant.VariantGetExpressionBuilder |
variant_get | SELECT variant_get(parse_json('{"a": 1}'), '$.a', 'int') |
struct<variant_get(parse_json({"a": 1}), $.a):int> |
|
org.apache.spark.sql.catalyst.expressions.variant.VariantInsertExpressionBuilder
| variant_insert | SELECT variant_insert(parse_json('{"a": 1}'), '$.b', 2) |
struct<variant_insert(parse_json({"a": 1}), $.b, 2):variant> |
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/VariantSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/VariantSuite.scala
index 02f56c6d0892..fe4dde44ec99 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/VariantSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/VariantSuite.scala
@@ -581,6 +581,56 @@ class VariantSuite extends SharedSparkSession with
ExpressionEvalHelper {
}
}
+ test("try_variant_array_append with literal arguments") {
+ def rows(results: Any*): Seq[Row] = results.map(Row(_))
+
+ checkAnswer(
+ sql("SELECT to_json(try_variant_array_append(parse_json('{\"a\": [1,
2]}'), '$.a', 3))"),
+ rows("""{"a":[1,2,3]}"""))
+ checkAnswer(
+ sql("SELECT to_json(try_variant_array_append(parse_json('[1, 2]'), '$',
3))"),
+ rows("[1,2,3]"))
+
+ checkAnswer(
+ sql("SELECT to_json(try_variant_array_append(parse_json('{\"a\": 1}'),
'$.a', 2))"),
+ rows(null))
+
+ checkAnswer(
+ sql("SELECT to_json(try_variant_array_append(parse_json('[1]'), '$',
NULL))"),
+ rows(null))
+
+ checkError(
+ exception = intercept[SparkRuntimeException] {
+ sql("SELECT try_variant_array_append(parse_json('[]'), 'bad',
1)").collect()
+ },
+ condition = "INVALID_VARIANT_PATH",
+ parameters = Map("path" -> "bad", "functionName" ->
toSQLId("try_variant_array_append")))
+ }
+
+ test("try_variant_array_append with dynamic arguments") {
+ def rows(results: Any*): Seq[Row] = results.map(Row(_))
+ Seq("CODEGEN_ONLY", "NO_CODEGEN").foreach { codegenMode =>
+ withSQLConf(SQLConf.CODEGEN_FACTORY_MODE.key -> codegenMode) {
+ val df = Seq(
+ ("""{"a": [1, 2]}""", "$.a", 3),
+ ("""{"a": 1}""", "$.a", 9),
+ (null, "$", 2)
+ ).toDF("json", "path", "val")
+ val v = parse_json(col("json"))
+
+ checkAnswer(
+ df.select(to_json(try_variant_array_append(v, col("path"),
col("val"))).alias("r")),
+ rows("""{"a":[1,2,3]}""", null, null))
+
+ val arrDf = Seq(("[1, 2]", 3), (null, 3)).toDF("json", "val")
+ val arrV = parse_json(arrDf("json"))
+ checkAnswer(
+ arrDf.select(to_json(try_variant_array_append(arrV, "$",
col("val"))).alias("r")),
+ rows("[1,2,3]", null))
+ }
+ }
+ }
+
test("round trip tests") {
withSQLConf(SQLConf.VARIANT_INFER_SHREDDING_SCHEMA.key -> "false") {
val rand = new Random(42)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
