riteshghorse commented on code in PR #28855:
URL: https://github.com/apache/beam/pull/28855#discussion_r1349250279
##########
sdks/python/apache_beam/io/avroio.py:
##########
@@ -382,17 +398,32 @@ def __init__(
Returns:
A WriteToAvro transform usable for writing.
"""
- self._sink = _create_avro_sink(
+ self._schema = schema
+ self._sink_provider = lambda avro_schema: _create_avro_sink(
file_path_prefix,
- schema,
+ avro_schema,
codec,
file_name_suffix,
num_shards,
shard_name_template,
mime_type)
def expand(self, pcoll):
- return pcoll | beam.io.iobase.Write(self._sink)
+ if self._schema:
+ avro_schema = self._schema
+ records = pcoll
+ else:
+ try:
+ beam_schema = schemas.schema_from_element_type(pcoll.element_type)
+ except TypeError as exn:
+ raise ValueError(
+ "An explicit schema is required to write non-schema'd
PCollections."
+ ) from exn
+ avro_schema = beam_schema_to_avro_schema(beam_schema)
Review Comment:
got it, thanks!
--
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]
