leaves12138 commented on code in PR #9946:
URL: https://github.com/apache/paimon/pull/9946#discussion_r4043394313
##########
paimon-python/pypaimon/globalindex/btree/btree_index_writer.py:
##########
@@ -100,15 +106,23 @@ def finish(self) -> bytes:
class _SstFileWriter:
- def __init__(self, out: PositionOutput, block_size: int):
+ def __init__(
+ self,
+ out: PositionOutput,
+ block_size: int,
+ bloom_filter_enabled: bool,
+ ):
self._out = out
self._block_size = block_size
self._data_block_writer = _BlockWriter()
self._index_block_writer = _BlockWriter()
self._last_key: Optional[bytes] = None
+ self._bloom_hashes = array('i') if bloom_filter_enabled else None
def put(self, key: bytes, value: bytes) -> None:
self._data_block_writer.add(key, value)
+ if self._bloom_hashes is not None:
+ self._bloom_hashes.append(murmur_hash_bytes(key))
Review Comment:
Update after discussion: NaN handling is outside the agreed scope of this
PR. The concern previously raised here is withdrawn as a blocker; no change is
requested for it in this PR.
--
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]
