mapleFU commented on code in PR #37400:
URL: https://github.com/apache/arrow/pull/37400#discussion_r1539562568
##########
cpp/src/parquet/column_writer.cc:
##########
@@ -2363,12 +2390,151 @@ Status
TypedColumnWriterImpl<FLBAType>::WriteArrowDense(
return Status::OK();
}
+template <typename DType>
+void TypedColumnWriterImpl<DType>::UpdateBloomFilter(const T* values,
+ int64_t num_values) {
+ if (bloom_filter_) {
+ std::array<uint64_t, kHashBatchSize> hashes;
+ for (int64_t i = 0; i < num_values; i += kHashBatchSize) {
+ int64_t current_hash_batch_size = std::min(kHashBatchSize, num_values -
i);
+ bloom_filter_->Hashes(values, static_cast<int>(current_hash_batch_size),
+ hashes.data());
+ bloom_filter_->InsertHashes(hashes.data(),
+ static_cast<int>(current_hash_batch_size));
+ }
+ }
+}
+
+template <>
+void TypedColumnWriterImpl<FLBAType>::UpdateBloomFilter(const FLBA* values,
+ int64_t num_values) {
+ if (bloom_filter_) {
+ std::array<uint64_t, kHashBatchSize> hashes;
+ for (int64_t i = 0; i < num_values; i += kHashBatchSize) {
+ int64_t current_hash_batch_size = std::min(kHashBatchSize, num_values -
i);
+ bloom_filter_->Hashes(values, descr_->type_length(),
+ static_cast<int>(current_hash_batch_size),
hashes.data());
+ bloom_filter_->InsertHashes(hashes.data(),
+ static_cast<int>(current_hash_batch_size));
+ }
+ }
+}
+
+template <>
+void TypedColumnWriterImpl<BooleanType>::UpdateBloomFilter(const bool*,
int64_t) {
+ DCHECK(bloom_filter_ == nullptr);
+}
+
+template <typename DType>
+void TypedColumnWriterImpl<DType>::UpdateBloomFilterSpaced(const T* values,
+ int64_t num_values,
+ const uint8_t*
valid_bits,
+ int64_t
valid_bits_offset) {
+ if (bloom_filter_) {
+ std::array<uint64_t, kHashBatchSize> hashes;
+ ::arrow::internal::VisitSetBitRunsVoid(
+ valid_bits, valid_bits_offset, num_values, [&](int64_t position,
int64_t length) {
+ for (int64_t i = 0; i < length; i += kHashBatchSize) {
+ auto current_hash_batch_size = std::min(kHashBatchSize, length -
i);
+ bloom_filter_->Hashes(values + i + position,
+ static_cast<int>(current_hash_batch_size),
+ hashes.data());
+ bloom_filter_->InsertHashes(hashes.data(),
+
static_cast<int>(current_hash_batch_size));
+ }
+ });
+ }
+}
+
+template <>
+void TypedColumnWriterImpl<BooleanType>::UpdateBloomFilterSpaced(const bool*,
int64_t,
+ const
uint8_t*,
+ int64_t) {
+ DCHECK(bloom_filter_ == nullptr);
+}
+
+template <>
+void TypedColumnWriterImpl<FLBAType>::UpdateBloomFilterSpaced(const FLBA*
values,
+ int64_t
num_values,
+ const uint8_t*
valid_bits,
+ int64_t
valid_bits_offset) {
+ if (bloom_filter_) {
+ std::array<uint64_t, kHashBatchSize> hashes;
+ ::arrow::internal::VisitSetBitRunsVoid(
+ valid_bits, valid_bits_offset, num_values, [&](int64_t position,
int64_t length) {
+ for (int64_t i = 0; i < length; i += kHashBatchSize) {
+ auto current_hash_batch_size = std::min(kHashBatchSize, length -
i);
+ bloom_filter_->Hashes(values + i + position, descr_->type_length(),
+ static_cast<int>(current_hash_batch_size),
+ hashes.data());
+ bloom_filter_->InsertHashes(hashes.data(),
+
static_cast<int>(current_hash_batch_size));
+ }
+ });
+ }
+}
+
+template <typename ArrayType>
+void UpdateBinaryBloomFilter(BloomFilter* bloom_filter, const ArrayType&
array) {
+ // Using a smaller size because an extra `byte_arrays` are used.
+ constexpr int64_t kBinaryHashBatchSize = 64;
+ std::array<ByteArray, kBinaryHashBatchSize> byte_arrays;
+ std::array<uint64_t, kBinaryHashBatchSize> hashes;
+ int hashes_idx = 0;
+ auto flush_hashes = [&]() {
+ DCHECK(hashes_idx != 0);
Review Comment:
```suggestion
DCHECK_NE(0, hashes_idx);
```
--
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]
