dtenedor commented on code in PR #43204: URL: https://github.com/apache/spark/pull/43204#discussion_r1350762771
########## python/pyspark/sql/tests/test_udtf.py: ########## @@ -2309,6 +2309,55 @@ def terminate(self): + [Row(partition_col=42, count=3, total=3, last=None)], ) + def test_udtf_with_prepare_string_from_analyze(self): + @udtf + class TestUDTF: + def __init__(self): + self._total = 0 + self._buffer = None + + @staticmethod + def analyze(argument, _): + if ( + argument.value is None + or argument.is_table + or not isinstance(argument.value, str) + or len(argument.value) == 0 + ): + raise Exception("The first argument must be non-empty string") + assert argument.data_type == StringType() + assert not argument.is_table + return AnalyzeResult( + schema=StructType().add("total", IntegerType()).add("buffer", StringType()), + prepare_buffer=argument.value, + with_single_partition=True, + ) + + def prepare(self, buffer): Review Comment: This is done. -- 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-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org