wjones127 commented on code in PR #33776:
URL: https://github.com/apache/arrow/pull/33776#discussion_r1081932460
##########
cpp/src/parquet/bloom_filter.h:
##########
@@ -105,18 +105,20 @@ class PARQUET_EXPORT BloomFilter {
protected:
// Hash strategy available for Bloom filter.
- enum class HashStrategy : uint32_t { MURMUR3_X64_128 = 0 };
+ enum class HashStrategy : uint32_t { XXHASH = 0 };
// Bloom filter algorithm.
enum class Algorithm : uint32_t { BLOCK = 0 };
+
+ enum class CompressionStrategy : uint32_t { UNCOMPRESSED = 0 };
};
-// The BlockSplitBloomFilter is implemented using block-based Bloom filters
from
-// Putze et al.'s "Cache-,Hash- and Space-Efficient Bloom filters". The basic
idea is to
-// hash the item to a tiny Bloom filter which size fit a single cache line or
smaller.
-//
-// This implementation sets 8 bits in each tiny Bloom filter. Each tiny Bloom
-// filter is 32 bytes to take advantage of 32-byte SIMD instructions.
+/// The BlockSplitBloomFilter is implemented using block-based Bloom filters
from
+/// Putze et al.'s "Cache-,Hash- and Space-Efficient Bloom filters". The basic
idea is to
+/// hash the item to a tiny Bloom filter which size fit a single cache line or
smaller.
+///
+/// This implementation sets 8 bits in each tiny Bloom filter. Each tiny Bloom
+/// filter is 32 bytes to take advantage of 32-byte SIMD instructions.
class PARQUET_EXPORT BlockSplitBloomFilter : public BloomFilter {
public:
/// The constructor of BlockSplitBloomFilter. It uses murmur3_x64_128 as
hash function.
Review Comment:
Should this be updated?
```suggestion
/// The constructor of BlockSplitBloomFilter. It uses XXH64 as hash
function.
```
--
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]
