etseidl commented on code in PR #8340:
URL: https://github.com/apache/arrow-rs/pull/8340#discussion_r2383143528
##########
parquet/src/file/metadata/parser.rs:
##########
@@ -43,6 +43,86 @@ use crate::encryption::{
#[cfg(feature = "encryption")]
use crate::format::EncryptionAlgorithm;
+/// Helper struct for metadata parsing
+///
+/// This structure parses thrift-encoded bytes into the correct Rust structs,
+/// such as [`ParquetMetaData`], handling decryption if necessary.
+//
+// Note this structure is used to minimize the number of
+// places need to add `#[cfg(feature = "encryption")]` checks.
+pub(crate) use inner::MetadataParser;
+
+#[cfg(feature = "encryption")]
+mod inner {
+ use super::*;
+ use crate::encryption::decrypt::FileDecryptionProperties;
+ use crate::errors::Result;
+
+ /// API for decoding metadata that may be encrypted
+ #[derive(Debug, Default)]
+ pub(crate) struct MetadataParser {
+ // the credentials and keys needed to decrypt metadata
+ file_decryption_properties: Option<Arc<FileDecryptionProperties>>,
+ }
+
+ impl MetadataParser {
+ pub(crate) fn new() -> Self {
+ MetadataParser::default()
+ }
+
+ pub(crate) fn with_file_decryption_properties(
+ mut self,
+ file_decryption_properties: Option<Arc<FileDecryptionProperties>>,
+ ) -> Self {
+ self.file_decryption_properties = file_decryption_properties;
+ self
+ }
+
+ pub(crate) fn decode_metadata(
+ &self,
+ buf: &[u8],
+ encrypted_footer: bool,
+ ) -> Result<ParquetMetaData> {
+ decode_metadata_with_encryption(
+ buf,
+ encrypted_footer,
+ self.file_decryption_properties.as_deref(),
+ )
+ }
+ }
+}
+
+#[cfg(not(feature = "encryption"))]
+mod inner {
+ use super::*;
+ use crate::errors::Result;
+ /// parallel implementation when encryption feature is not enabled
+ ///
+ /// This has the same API as the encryption-enabled version
+ #[derive(Debug, Default)]
+ pub(crate) struct MetadataParser;
+
+ impl MetadataParser {
+ pub(crate) fn new() -> Self {
+ MetadataParser
+ }
+
+ pub(crate) fn decode_metadata(
+ &self,
+ buf: &[u8],
+ encrypted_footer: bool,
+ ) -> Result<ParquetMetaData> {
+ if encrypted_footer {
+ Err(general_err!(
+ "Parquet file has an encrypted footer but the encryption
feature is disabled"
+ ))
+ } else {
+ decode_metadata(buf)
Review Comment:
Sorry, this was mostly a note to myself. When I did the merge I changed the
`decode_metadata` call to
```rust
let mut prot = ThriftSliceInputProtocol::new(buf);
ParquetMetaData::read_thrift(&mut prot)
```
Instead I should do the same in `parser::decode_metadata`.
No changes on your end are necessary 😄
--
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]
