[Python][Dataset] Change default of pre_buffer to True for reading Pa…

…rquet files

python/pyarrow/_dataset_parquet.pyx

@@ -666,7 +666,7 @@ cdef class ParquetFragmentScanOptions(FragmentScanOptions):
         Disabled by default.
     buffer_size : int, default 8192
         Size of buffered stream, if enabled. Default is 8KB.
-    pre_buffer : bool, default False
+    pre_buffer : bool, default True
         If enabled, pre-buffer the raw Parquet data instead of issuing one
         read per column chunk. This can improve performance on high-latency
         filesystems.
@@ -688,7 +688,7 @@ cdef class ParquetFragmentScanOptions(FragmentScanOptions):
 
     def __init__(self, *, bint use_buffered_stream=False,
                  buffer_size=8192,
-                 bint pre_buffer=False,
+                 bint pre_buffer=True,
                  thrift_string_size_limit=None,
                  thrift_container_size_limit=None):
         self.init(shared_ptr[CFragmentScanOptions](

python/pyarrow/tests/test_dataset.py

@@ -784,28 +784,28 @@ def test_parquet_scan_options():
     opts2 = ds.ParquetFragmentScanOptions(buffer_size=4096)
     opts3 = ds.ParquetFragmentScanOptions(
         buffer_size=2**13, use_buffered_stream=True)
-    opts4 = ds.ParquetFragmentScanOptions(buffer_size=2**13, pre_buffer=True)
+    opts4 = ds.ParquetFragmentScanOptions(buffer_size=2**13, pre_buffer=False)
     opts5 = ds.ParquetFragmentScanOptions(
         thrift_string_size_limit=123456,
         thrift_container_size_limit=987654,)
 
     assert opts1.use_buffered_stream is False
     assert opts1.buffer_size == 2**13
-    assert opts1.pre_buffer is False
+    assert opts1.pre_buffer is True
     assert opts1.thrift_string_size_limit == 100_000_000  # default in C++
     assert opts1.thrift_container_size_limit == 1_000_000  # default in C++
 
     assert opts2.use_buffered_stream is False
     assert opts2.buffer_size == 2**12
-    assert opts2.pre_buffer is False
+    assert opts2.pre_buffer is True
 
     assert opts3.use_buffered_stream is True
     assert opts3.buffer_size == 2**13
-    assert opts3.pre_buffer is False
+    assert opts3.pre_buffer is True
 
     assert opts4.use_buffered_stream is False
     assert opts4.buffer_size == 2**13
-    assert opts4.pre_buffer is True
+    assert opts4.pre_buffer is False
 
     assert opts5.thrift_string_size_limit == 123456
     assert opts5.thrift_container_size_limit == 987654