You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by "zhengruifeng (via GitHub)" <gi...@apache.org> on 2023/09/18 02:18:00 UTC
[GitHub] [spark] zhengruifeng commented on a diff in pull request #42938: [SPARK-44788][CONNECT][PYTHON][SQL] Add from_xml and schema_of_xml to pyspark, spark connect and sql function
zhengruifeng commented on code in PR #42938:
URL: https://github.com/apache/spark/pull/42938#discussion_r1328198653
##########
python/pyspark/sql/tests/connect/test_connect_function.py:
##########
@@ -1821,6 +1821,111 @@ def test_json_functions(self):
sdf.select(SF.to_json(SF.struct(SF.lit("a"), SF.lit("b")), {"mode": "FAILFAST"})),
)
+ def test_xml_functions(self):
+ query = """
+ SELECT * FROM VALUES
+ ('<p><a>1</a></p>', '<p><a>1</a><a>2</a><a>3</a></p>',
+ '<p><a attr="s"><b>5.0</b></a></p>'),
+ ('<p><a>0</a></p>', '<p><a>4</a><a>5</a><a>6</a></p>', '<p><a attr="t"></a></p>')
+ AS tab(a, b, c)
+ """
+ # +---------------+-------------------------------+---------------------------------+
+ # | a| b| c|
+ # +---------------+-------------------------------+---------------------------------+
+ # |<p><a>1</a></p>|<p><a>1</a><a>2</a><a>3</a></p>|<p><a attr="s"><b>5.0</b></a></p>|
+ # |<p><a>1</a></p>|<p><a>4</a><a>5</a><a>6</a></p>| <p><a attr="t"></a></p>|
+ # +---------------+-------------------------------+---------------------------------+
+
+ cdf = self.connect.sql(query)
+ sdf = self.spark.sql(query)
+
+ # test from_xml
+ for schema in [
+ "a INT",
+ # StructType([StructField("a", IntegerType())]),
+ # StructType([StructField("a", ArrayType(IntegerType()))]),
Review Comment:
are they supported?
##########
python/pyspark/sql/tests/connect/test_connect_function.py:
##########
@@ -1821,6 +1821,111 @@ def test_json_functions(self):
sdf.select(SF.to_json(SF.struct(SF.lit("a"), SF.lit("b")), {"mode": "FAILFAST"})),
)
+ def test_xml_functions(self):
+ query = """
+ SELECT * FROM VALUES
+ ('<p><a>1</a></p>', '<p><a>1</a><a>2</a><a>3</a></p>',
+ '<p><a attr="s"><b>5.0</b></a></p>'),
+ ('<p><a>0</a></p>', '<p><a>4</a><a>5</a><a>6</a></p>', '<p><a attr="t"></a></p>')
+ AS tab(a, b, c)
+ """
+ # +---------------+-------------------------------+---------------------------------+
+ # | a| b| c|
+ # +---------------+-------------------------------+---------------------------------+
+ # |<p><a>1</a></p>|<p><a>1</a><a>2</a><a>3</a></p>|<p><a attr="s"><b>5.0</b></a></p>|
+ # |<p><a>1</a></p>|<p><a>4</a><a>5</a><a>6</a></p>| <p><a attr="t"></a></p>|
+ # +---------------+-------------------------------+---------------------------------+
+
+ cdf = self.connect.sql(query)
+ sdf = self.spark.sql(query)
+
+ # test from_xml
+ for schema in [
+ "a INT",
+ # StructType([StructField("a", IntegerType())]),
+ # StructType([StructField("a", ArrayType(IntegerType()))]),
+ ]:
+ self.compare_by_show(
+ cdf.select(CF.from_xml(cdf.a, schema)),
+ sdf.select(SF.from_xml(sdf.a, schema)),
+ )
+ self.compare_by_show(
+ cdf.select(CF.from_xml("a", schema)),
+ sdf.select(SF.from_xml("a", schema)),
+ )
+ self.compare_by_show(
+ cdf.select(CF.from_xml(cdf.a, schema, {"mode": "FAILFAST"})),
+ sdf.select(SF.from_xml(sdf.a, schema, {"mode": "FAILFAST"})),
+ )
+ self.compare_by_show(
+ cdf.select(CF.from_xml("a", schema, {"mode": "FAILFAST"})),
+ sdf.select(SF.from_xml("a", schema, {"mode": "FAILFAST"})),
+ )
+
+ for schema in [
+ "STRUCT<a: ARRAY<INT>>",
+ # StructType([StructField("a", ArrayType(IntegerType()))]),
Review Comment:
is this supported?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org