wgtmac commented on code in PR #36574:
URL: https://github.com/apache/arrow/pull/36574#discussion_r1302681571


##########
cpp/src/parquet/encryption/test_encryption_util.cc:
##########
@@ -509,4 +513,178 @@ void FileDecryptor::CheckFile(parquet::ParquetFileReader* 
file_reader,
   }
 }
 
+void FileDecryptor::DecryptPageIndex(
+    const std::string& file,
+    const std::shared_ptr<FileDecryptionProperties>& 
file_decryption_properties) {
+  std::string exception_msg;
+  parquet::ReaderProperties reader_properties = 
parquet::default_reader_properties();
+  if (file_decryption_properties) {
+    
reader_properties.file_decryption_properties(file_decryption_properties->DeepClone());
+  }
+
+  std::shared_ptr<::arrow::io::RandomAccessFile> source;
+  PARQUET_ASSIGN_OR_THROW(
+      source, ::arrow::io::ReadableFile::Open(file, 
reader_properties.memory_pool()));
+
+  auto file_reader = parquet::ParquetFileReader::Open(source, 
reader_properties);
+  CheckPageIndex(file_reader.get(), file_decryption_properties);
+
+  ASSERT_NO_FATAL_FAILURE(file_reader->Close());
+  PARQUET_THROW_NOT_OK(source->Close());
+}
+
+void FileDecryptor::CheckPageIndex(
+    parquet::ParquetFileReader* file_reader,
+    const std::shared_ptr<FileDecryptionProperties>& 
file_decryption_properties) {
+  std::shared_ptr<PageIndexReader> page_index_reader = 
file_reader->GetPageIndexReader();
+  ASSERT_NE(page_index_reader, nullptr);
+
+  const std::shared_ptr<parquet::FileMetaData> file_metadata = 
file_reader->metadata();
+  const int num_row_groups = file_metadata->num_row_groups();
+  const int num_columns = file_metadata->num_columns();
+  ASSERT_EQ(num_columns, 8);
+
+  // We cannot read page index of encrypted columns in the plaintext mode
+  std::vector<int32_t> need_row_groups(num_row_groups);
+  std::for_each(need_row_groups.begin(), need_row_groups.end(),
+                [i = 0](int32_t& v) mutable { v = i++; });
+  std::vector<int32_t> need_columns;
+  if (file_decryption_properties == nullptr) {
+    need_columns = {0, 1, 2, 3, 6, 7};

Review Comment:
   Right, checking the code below we can know that `path_to_double_field_` and 
`path_to_float_field_` are encrypted...



-- 
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]

Reply via email to