diff --git a/data/artifact-tests/crc/README.md b/data/artifact-tests/crc/README.md new file mode 100644 index 0000000000000..df9af41064444 --- /dev/null +++ b/data/artifact-tests/crc/README.md @@ -0,0 +1,5 @@ +The CRCs for a specific file are stored in a text file with the same name (excluding the original extension). + +The CRCs are calculated for data chunks of `32768 bytes` (individual CRCs) and are newline delimited. + +The CRCs were calculated using https://simplycalc.com/crc32-file.php \ No newline at end of file diff --git a/data/artifact-tests/crc/junitLargeJar.txt b/data/artifact-tests/crc/junitLargeJar.txt new file mode 100644 index 0000000000000..3e89631dea57c --- /dev/null +++ b/data/artifact-tests/crc/junitLargeJar.txt @@ -0,0 +1,12 @@ +902183889 +2415704507 +1084811487 +1951510 +1158852476 +2003120166 +3026803842 +3850244775 +3409267044 +652109216 +104029242 +3019434266 \ No newline at end of file diff --git a/data/artifact-tests/crc/smallJar.txt b/data/artifact-tests/crc/smallJar.txt new file mode 100644 index 0000000000000..df32adcce7ab5 --- /dev/null +++ b/data/artifact-tests/crc/smallJar.txt @@ -0,0 +1 @@ +1631702900 \ No newline at end of file diff --git a/data/artifact-tests/junitLargeJar.jar b/data/artifact-tests/junitLargeJar.jar new file mode 100755 index 0000000000000..6da55d8b8520d Binary files /dev/null and b/data/artifact-tests/junitLargeJar.jar differ diff --git a/data/artifact-tests/smallJar.jar b/data/artifact-tests/smallJar.jar new file mode 100755 index 0000000000000..3c4930e8e9549 Binary files /dev/null and b/data/artifact-tests/smallJar.jar differ diff --git a/python/pyspark/sql/tests/connect/client/test_artifact.py b/python/pyspark/sql/tests/connect/client/test_artifact.py index 50a8a7f2f1e1d..9bc0822898f1e 100644 --- a/python/pyspark/sql/tests/connect/client/test_artifact.py +++ b/python/pyspark/sql/tests/connect/client/test_artifact.py @@ -33,9 +33,7 @@ class ArtifactTests(ReusedConnectTestCase): def setUpClass(cls): super(ArtifactTests, cls).setUpClass() cls.artifact_manager: ArtifactManager = cls.spark._client._artifact_manager - cls.base_resource_dir = os.path.join( - SPARK_HOME, "connector", "connect", "common", "src", "test", "resources" - ) + cls.base_resource_dir = os.path.join(SPARK_HOME, "data") cls.artifact_file_path = os.path.join( cls.base_resource_dir, "artifact-tests",