This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 39569d5a8ac [SPARK-41657][CONNECT][DOCS][TESTS] Enable doctests in
pyspark.sql.connect.session
39569d5a8ac is described below
commit 39569d5a8ac0bf192748220d28f76dfe3fc357d3
Author: Hyukjin Kwon <gurwls...@apache.org>
AuthorDate: Mon Jan 2 19:58:46 2023 +0900
[SPARK-41657][CONNECT][DOCS][TESTS] Enable doctests in
pyspark.sql.connect.session
### What changes were proposed in this pull request?
This PR proposes to enable doctests in `pyspark.sql.connect.session` that
is virtually the same as `pyspark.sql.session`.
### Why are the changes needed?
To make sure on the PySpark compatibility and test coverage.
### Does this PR introduce _any_ user-facing change?
No, test-only.
### How was this patch tested?
CI in this PR should test this out.
Closes #39341 from HyukjinKwon/SPARK-41657.
Authored-by: Hyukjin Kwon <gurwls...@apache.org>
Signed-off-by: Hyukjin Kwon <gurwls...@apache.org>
---
dev/sparktestsupport/modules.py | 1 +
python/pyspark/sql/connect/session.py | 60 +++++++++++++++++++++++++++++++++++
python/pyspark/sql/session.py | 4 +--
3 files changed, 63 insertions(+), 2 deletions(-)
diff --git a/dev/sparktestsupport/modules.py b/dev/sparktestsupport/modules.py
index dff17792148..99f1cc6894f 100644
--- a/dev/sparktestsupport/modules.py
+++ b/dev/sparktestsupport/modules.py
@@ -506,6 +506,7 @@ pyspark_connect = Module(
# doctests
"pyspark.sql.connect.catalog",
"pyspark.sql.connect.group",
+ "pyspark.sql.connect.session",
"pyspark.sql.connect.window",
"pyspark.sql.connect.column",
# unittests
diff --git a/python/pyspark/sql/connect/session.py
b/python/pyspark/sql/connect/session.py
index ae228317696..a461372c08c 100644
--- a/python/pyspark/sql/connect/session.py
+++ b/python/pyspark/sql/connect/session.py
@@ -22,6 +22,7 @@ import numpy as np
import pandas as pd
import pyarrow as pa
+from pyspark import SparkContext, SparkConf
from pyspark.sql.session import classproperty, SparkSession as PySparkSession
from pyspark.sql.types import (
_infer_schema,
@@ -311,3 +312,62 @@ class SparkSession:
SparkSession.__doc__ = PySparkSession.__doc__
+
+
+def _test() -> None:
+ import os
+ import sys
+ import doctest
+ from pyspark.sql import SparkSession as PySparkSession
+ from pyspark.testing.connectutils import should_test_connect,
connect_requirement_message
+
+ os.chdir(os.environ["SPARK_HOME"])
+
+ if should_test_connect:
+ import pyspark.sql.connect.session
+
+ globs = pyspark.sql.connect.session.__dict__.copy()
+ # Works around to create a regular Spark session
+ sc = SparkContext("local[4]", "sql.connect.session tests",
conf=SparkConf())
+ globs["_spark"] = PySparkSession(
+ sc, options={"spark.app.name": "sql.connect.session tests"}
+ )
+
+ # Creates a remote Spark session.
+ os.environ["SPARK_REMOTE"] = "sc://localhost"
+ globs["spark"] =
PySparkSession.builder.remote("sc://localhost").getOrCreate()
+
+ # Uses PySpark session to test builder.
+ globs["SparkSession"] = PySparkSession
+ # Spark Connect does not support to set master together.
+ pyspark.sql.connect.session.SparkSession.__doc__ = None
+ del pyspark.sql.connect.session.SparkSession.Builder.master.__doc__
+
+ # TODO(SPARK-41746): SparkSession.createDataFrame does not respect the
column names in
+ # dictionary
+ del pyspark.sql.connect.session.SparkSession.createDataFrame.__doc__
+ del pyspark.sql.connect.session.SparkSession.read.__doc__
+ # TODO(SPARK-41811): Implement SparkSession.sql's string formatter
+ del pyspark.sql.connect.session.SparkSession.sql.__doc__
+
+ (failure_count, test_count) = doctest.testmod(
+ pyspark.sql.connect.session,
+ globs=globs,
+ optionflags=doctest.ELLIPSIS
+ | doctest.NORMALIZE_WHITESPACE
+ | doctest.IGNORE_EXCEPTION_DETAIL,
+ )
+
+ globs["spark"].stop()
+ globs["_spark"].stop()
+ if failure_count:
+ sys.exit(-1)
+ else:
+ print(
+ f"Skipping pyspark.sql.connect.session doctests:
{connect_requirement_message}",
+ file=sys.stderr,
+ )
+
+
+if __name__ == "__main__":
+ _test()
diff --git a/python/pyspark/sql/session.py b/python/pyspark/sql/session.py
index 3f99dc7ab84..1e4e6f5e3ad 100644
--- a/python/pyspark/sql/session.py
+++ b/python/pyspark/sql/session.py
@@ -676,7 +676,7 @@ class SparkSession(SparkConversionMixin):
Examples
--------
>>> spark.catalog
- <pyspark.sql.catalog.Catalog object ...>
+ <...Catalog object ...>
Create a temp view, show the list, and drop it.
@@ -1460,7 +1460,7 @@ class SparkSession(SparkConversionMixin):
Examples
--------
>>> spark.read
- <pyspark.sql.readwriter.DataFrameReader object ...>
+ <...DataFrameReader object ...>
Write a DataFrame into a JSON file and read it back.
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
