gaogaotiantian commented on code in PR #53898: URL: https://github.com/apache/spark/pull/53898#discussion_r2714717449
########## python/pyspark/sql/tests/streaming/test_streaming_reader_name.py: ########## @@ -0,0 +1,204 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +import tempfile +import time + +from pyspark.errors import PySparkTypeError +from pyspark.testing.sqlutils import ReusedSQLTestCase + + +class DataStreamReaderNameTests(ReusedSQLTestCase): + """Test suite for DataStreamReader.name() functionality in PySpark.""" + + @classmethod + def setUpClass(cls): + super(DataStreamReaderNameTests, cls).setUpClass() + # Enable streaming source evolution feature + cls.spark.conf.set("spark.sql.streaming.queryEvolution.enableSourceEvolution", "true") + cls.spark.conf.set("spark.sql.streaming.offsetLog.formatVersion", "2") + + def test_name_with_valid_names(self): + """Test that various valid source name patterns work correctly.""" + valid_names = [ + "mySource", + "my_source", + "MySource123", + "_private", + "source_123_test", + "123source", + ] + + for name in valid_names: + with tempfile.TemporaryDirectory(prefix=f"test_{name}_") as tmpdir: + self.spark.range(10).write.mode("overwrite").parquet(tmpdir) + df = ( + self.spark.readStream.format("parquet") + .schema("id LONG") + .name(name) + .load(tmpdir) + ) + self.assertTrue(df.isStreaming, f"DataFrame should be streaming for name: {name}") + + def test_name_method_chaining(self): + """Test that name() returns the reader for method chaining.""" + with tempfile.TemporaryDirectory(prefix="test_chaining_") as tmpdir: + self.spark.range(10).write.mode("overwrite").parquet(tmpdir) + df = ( + self.spark.readStream.format("parquet") + .schema("id LONG") + .name("my_source") + .option("maxFilesPerTrigger", "1") + .load(tmpdir) + ) + + self.assertTrue(df.isStreaming, "DataFrame should be streaming") + + def test_name_before_format(self): + """Test that order doesn't matter - name can be set before format.""" + with tempfile.TemporaryDirectory(prefix="test_before_format_") as tmpdir: + self.spark.range(10).write.mode("overwrite").parquet(tmpdir) + df = ( + self.spark.readStream.name("my_source") + .format("parquet") + .schema("id LONG") + .load(tmpdir) + ) + + self.assertTrue(df.isStreaming, "DataFrame should be streaming") + + def test_invalid_name_with_hyphen(self): Review Comment: I think you should combine all the tests with invalid names like the valid ones :) -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
