iajoiner commented on a change in pull request #9702:
URL: https://github.com/apache/arrow/pull/9702#discussion_r787116289



##########
File path: python/pyarrow/orc.py
##########
@@ -117,21 +185,92 @@ def read(self, columns=None):
         return self.reader.read(columns=columns)
 
 
+_orc_writer_args_docs = """file_version : {"0.11", "0.12"}, default "0.12"
+    Determine which ORC file version to use. Hive 0.11 / ORC v0 is the older
+    version as defined `here <https://orc.apache.org/specification/ORCv0/>`
+    while Hive 0.12 / ORC v1 is the newer one as defined
+    `here <https://orc.apache.org/specification/ORCv1/>`.
+batch_size : int, default 1024
+    Number of rows the ORC writer writes at a time.
+stripe_size : int, default 64 * 1024 * 1024
+    Size of each ORC stripe.
+compression : string, default 'zlib'
+    Specify the compression codec.
+    Valid values: {'UNCOMPRESSED', 'SNAPPY', 'ZLIB', 'LZ0', 'LZ4', 'ZSTD'}
+compression_block_size : int, default 64 * 1024
+    Specify the size of each compression block.
+compression_strategy : string, default 'speed'
+    Specify the compression strategy i.e. speed vs size reduction.
+    Valid values: {'SPEED', 'COMPRESSION'}
+row_index_stride : int, default 10000
+    Specify the row index stride i.e. the number of rows per
+    an entry in the row index.
+padding_tolerance : double, default 0.0
+    Set the padding tolerance.
+dictionary_key_size_threshold : double, default 0.0
+    Set the dictionary key size threshold. 0 to disable dictionary encoding.
+    1 to always enable dictionary encoding.
+bloom_filter_columns : None, set-like or list-like, default None
+    Set columns that use the bloom filter.
+bloom_filter_fpp: double, default 0.05
+    Set false positive probability of the bloom filter.
+"""
+
+
 class ORCWriter:
-    """
-    Writer interface for a single ORC file
+    __doc__ = """
+Writer interface for a single ORC file
 
-    Parameters
-    ----------
-    where : str or pyarrow.io.NativeFile
-        Writable target. For passing Python file objects or byte buffers,
-        see pyarrow.io.PythonFileInterface, pyarrow.io.BufferOutputStream
-        or pyarrow.io.FixedSizeBufferWriter.
-    """
+Parameters
+----------
+where : str or pyarrow.io.NativeFile
+    Writable target. For passing Python file objects or byte buffers,
+    see pyarrow.io.PythonFileInterface, pyarrow.io.BufferOutputStream
+    or pyarrow.io.FixedSizeBufferWriter.
+{}
+""".format(_orc_writer_args_docs)
+
+    def __init__(self, where, file_version='0.12',
+                 batch_size=1024,
+                 stripe_size=67108864,
+                 compression='zlib',

Review comment:
       Sure! I will change that now.




-- 
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]


Reply via email to