fenfeng9 commented on code in PR #49334:
URL: https://github.com/apache/arrow/pull/49334#discussion_r2932894335
##########
cpp/src/parquet/bloom_filter.cc:
##########
@@ -106,7 +126,100 @@ static ::arrow::Status ValidateBloomFilterHeader(
BlockSplitBloomFilter BlockSplitBloomFilter::Deserialize(
const ReaderProperties& properties, ArrowInputStream* input,
- std::optional<int64_t> bloom_filter_length) {
+ std::optional<int64_t> bloom_filter_length, Decryptor* header_decryptor,
+ Decryptor* bitset_decryptor) {
+ if (header_decryptor != nullptr || bitset_decryptor != nullptr) {
+ if (header_decryptor == nullptr || bitset_decryptor == nullptr) {
+ throw ParquetException(
+ "Bloom filter decryptors must be both provided or both null");
+ }
+
+ // Encrypted path: header and bitset are encrypted separately.
+ ThriftDeserializer deserializer(properties);
+ format::BloomFilterHeader header;
+
+ // Read the length-prefixed ciphertext for the header.
+ PARQUET_ASSIGN_OR_THROW(auto length_buf,
input->Read(kCiphertextLengthSize));
+ if (ARROW_PREDICT_FALSE(length_buf->size() < kCiphertextLengthSize)) {
+ throw ParquetException("Bloom filter header read failed: not enough
data");
Review Comment:
Updated to include the expected and actual lengths in the read error
messages.
--
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]
