You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@arrow.apache.org by GitBox <gi...@apache.org> on 2021/06/23 06:56:45 UTC
[GitHub] [arrow] isichei commented on a change in pull request #10575: ARROW-13086: [Python] Expose Parquet ArrowReaderProperties::coerce_int96_timestamp_unit_
isichei commented on a change in pull request #10575:
URL: https://github.com/apache/arrow/pull/10575#discussion_r656811035
##########
File path: python/pyarrow/parquet.py
##########
@@ -213,15 +213,23 @@ class ParquetFile:
Coalesce and issue file reads in parallel to improve performance on
high-latency filesystems (e.g. S3). If True, Arrow will use a
background I/O thread pool.
+ coerce_int96_timestamp_unit: str, default None.
+ Cast timestamps that are stored in INT96 format to a particular
+ resolution (e.g. 'ms'). Setting to None is equivalent to 'ns'
+ and therefore INT96 timestamps will be infered as timestamps
+ in nanoseconds.
"""
def __init__(self, source, metadata=None, common_metadata=None,
read_dictionary=None, memory_map=False, buffer_size=0,
- pre_buffer=False):
+ pre_buffer=False, coerce_int96_timestamp_unit=None):
self.reader = ParquetReader()
- self.reader.open(source, use_memory_map=memory_map,
- buffer_size=buffer_size, pre_buffer=pre_buffer,
- read_dictionary=read_dictionary, metadata=metadata)
+ self.reader.open(
+ source, use_memory_map=memory_map,
+ buffer_size=buffer_size, pre_buffer=pre_buffer,
+ read_dictionary=read_dictionary, metadata=metadata,
Review comment:
These changes are just for linting.
##########
File path: python/pyarrow/parquet.py
##########
@@ -213,15 +213,23 @@ class ParquetFile:
Coalesce and issue file reads in parallel to improve performance on
high-latency filesystems (e.g. S3). If True, Arrow will use a
background I/O thread pool.
+ coerce_int96_timestamp_unit: str, default None.
+ Cast timestamps that are stored in INT96 format to a particular
+ resolution (e.g. 'ms'). Setting to None is equivalent to 'ns'
+ and therefore INT96 timestamps will be infered as timestamps
+ in nanoseconds.
"""
def __init__(self, source, metadata=None, common_metadata=None,
read_dictionary=None, memory_map=False, buffer_size=0,
- pre_buffer=False):
+ pre_buffer=False, coerce_int96_timestamp_unit=None):
self.reader = ParquetReader()
- self.reader.open(source, use_memory_map=memory_map,
- buffer_size=buffer_size, pre_buffer=pre_buffer,
- read_dictionary=read_dictionary, metadata=metadata)
+ self.reader.open(
+ source, use_memory_map=memory_map,
+ buffer_size=buffer_size, pre_buffer=pre_buffer,
+ read_dictionary=read_dictionary, metadata=metadata,
Review comment:
These line changes are just for linting.
--
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.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org