adamreeve commented on code in PR #7283:
URL: https://github.com/apache/arrow-rs/pull/7283#discussion_r1994601568
##########
parquet/src/arrow/mod.rs:
##########
@@ -93,6 +93,57 @@
//!
//! println!("Read {} records.", record_batch.num_rows());
//! ```
+//!
+//! # Example of reading non-uniformly encrypted parquet file into arrow
record batch
+//!
Review Comment:
Can we add a note here that this requires the experimental `encryption`
feature to be enabled?
##########
parquet/src/arrow/mod.rs:
##########
@@ -93,6 +93,57 @@
//!
//! println!("Read {} records.", record_batch.num_rows());
//! ```
+//!
+//! # Example of reading non-uniformly encrypted parquet file into arrow
record batch
+//!
+#![cfg_attr(feature = "encryption", doc = "```rust")]
+#![cfg_attr(not(feature = "encryption"), doc = "```ignore")]
+//! # use arrow_array::{Int32Array, ArrayRef};
+//! # use arrow_array::{types, RecordBatch};
+//! # use parquet::arrow::arrow_reader::{
+//! # ArrowReaderMetadata, ArrowReaderOptions,
ParquetRecordBatchReaderBuilder,
+//! # };
+//! # use arrow_array::cast::AsArray;
+//! # use parquet::file::metadata::ParquetMetaData;
+//! # use tempfile::tempfile;
+//! # use std::fs::File;
+//! # use parquet::encryption::decrypt::FileDecryptionProperties;
+//! # let test_data = arrow::util::test_util::parquet_test_data();
+//! # let path =
format!("{test_data}/encrypt_columns_and_footer.parquet.encrypted");
+//! #
+//! let file = File::open(path).unwrap();
+//!
+//! // Define the AES encryption keys required required for decrypting the
footer metadata
+//! // and column-specific data. If only a footer key is used then it is
assumed that the
+//! // file uses uniform encryption and all columns are encrypted with the
footer key.
+//! // If any column keys are specified, other columns without a key provided
are assumed
+//! // to be unencrypted
+//! let footer_key = "0123456789012345".as_bytes(); // Keys are 128 bits (16
bytes)
+//! let column_1_key = "1234567890123450".as_bytes();
+//! let column_2_key = "1234567890123451".as_bytes();
+//!
+//! let decryption_properties =
FileDecryptionProperties::builder(footer_key.to_vec())
+//! .with_column_key("double_field", column_1_key.to_vec())
+//! .with_column_key("float_field", column_2_key.to_vec())
+//! .build()
+//! .unwrap();
+//!
+//! let options =
+//!
ArrowReaderOptions::default().with_file_decryption_properties(decryption_properties);
+//! let reader_metadata = ArrowReaderMetadata::load(&file,
options.clone()).unwrap();
+//! let metadata = reader_metadata.metadata();
+//! let file_metadata = metadata.file_metadata();
+//!
+//! println!("Read {} rows.", file_metadata.num_rows());
+//!
+//! let builder = ParquetRecordBatchReaderBuilder::try_new_with_options(file,
options).unwrap();
+//! println!("Converted arrow schema is: {}", builder.schema());
+//!
+//! let mut reader = builder.build().unwrap();
+//!
+//! let record_batch = reader.next().unwrap().unwrap();
+//!
+//! println!("Read {} records.", record_batch.num_rows());
Review Comment:
I think this can be simplified and tidied up a little, we don't need to
repeat some of the details that are in examples above:
```suggestion
//! let file_metadata = reader_metadata.metadata().file_metadata();
//! println!("File has {} rows.", file_metadata.num_rows());
//!
//! let mut reader =
ParquetRecordBatchReaderBuilder::try_new_with_options(file,
options).unwrap().build().unwrap();
//!
//! let record_batch = reader.next().unwrap().unwrap();
//! println!("Read {} records.", record_batch.num_rows());
//! ```
```
(I also added a closing ```, although the docs seemed to build fine without
it?)
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
