Tom-Newton commented on code in PR #36627:
URL: https://github.com/apache/arrow/pull/36627#discussion_r1425347124
##########
python/pyarrow/io.pxi:
##########
@@ -2120,6 +2120,140 @@ cdef CCompressionType _ensure_compression(str name)
except *:
raise ValueError('Invalid value for compression: {!r}'.format(name))
+cdef class CacheOptions(_Weakrefable):
+ """
+ Cache options for a pre-buffered fragment scan.
+
+ Parameters
+ ----------
+ hole_size_limit : int, default 8Ki
+ The maximum distance in bytes between two consecutive ranges; beyond
+ this value, ranges are not combined.
+ range_size_limit : int, default 32Mi
+ The maximum size in bytes of a combined range; if combining two
+ consecutive ranges would produce a range of a size greater than this,
+ they are not combined
+ lazy : bool, default False
+ lazy = false: request all byte ranges when PreBuffer or WillNeed is
called.
+ lazy = True, prefetch_limit = 0: request merged byte ranges only after
the reader
+ needs them.
+ lazy = True, prefetch_limit = k: prefetch up to k merged byte ranges
ahead of the
+ range that is currently being read.
+ prefetch_limit : int, default 0
+ The maximum number of ranges to be prefetched. This is only used for
+ lazy cache to asynchronously read some ranges after reading the target
+ range.
+ """
+
+ def __init__(self, *, hole_size_limit=None, range_size_limit=None,
lazy=None, prefetch_limit=None):
+ self.wrapped = CCacheOptions.Defaults()
+ if hole_size_limit is not None:
+ self.hole_size_limit = hole_size_limit
+ if range_size_limit is not None:
+ self.range_size_limit = range_size_limit
+ if lazy is not None:
+ self.lazy = lazy
+ if prefetch_limit is not None:
+ self.prefetch_limit = prefetch_limit
+
+ cdef void init(self, CCacheOptions options):
+ self.wrapped = options
+
+ cdef inline CCacheOptions unwrap(self):
+ return self.wrapped
+
+ @staticmethod
+ cdef wrap(CCacheOptions options):
+ self = CacheOptions()
+ self.init(options)
+ return self
+
+ @property
+ def hole_size_limit(self):
+ return self.wrapped.hole_size_limit
+
+ @hole_size_limit.setter
+ def hole_size_limit(self, hole_size_limit):
+ self.wrapped.hole_size_limit = hole_size_limit
+
+ @property
+ def range_size_limit(self):
+ return self.wrapped.range_size_limit
+
+ @range_size_limit.setter
+ def range_size_limit(self, range_size_limit):
+ self.wrapped.range_size_limit = range_size_limit
+
+ @property
+ def lazy(self):
+ return self.wrapped.lazy
+
+ @lazy.setter
+ def lazy(self, lazy):
+ self.wrapped.lazy = lazy
+
+ @property
+ def prefetch_limit(self):
+ return self.wrapped.prefetch_limit
+
+ @prefetch_limit.setter
+ def prefetch_limit(self, prefetch_limit):
+ self.wrapped.prefetch_limit = prefetch_limit
+
+ def __eq__(self, CacheOptions other):
+ try:
+ return self.unwrap().Equals(other.unwrap())
+ except TypeError:
+ return False
+
+ @staticmethod
+ def from_network_metrics(time_to_first_byte_millis,
transfer_bandwidth_mib_per_sec,
+ ideal_bandwidth_utilization_frac,
max_ideal_request_size_mib):
Review Comment:
I couldn't work out how to link them from the C++ side but copying them is
definitely better than having no defaults at all :+1:.
--
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]
