Rebased on apache/pull/6637

.github/workflows/parquet.yml

@@ -111,6 +111,8 @@ jobs:
         run: cargo check -p parquet --all-targets --all-features
       - name: Check compilation  --all-targets --no-default-features --features json
         run: cargo check -p parquet --all-targets --no-default-features --features json
+      - name: Check compilation --no-default-features --features encryption --features async
+        run: cargo check -p parquet --no-default-features --features encryption --features async
 
   # test the parquet crate builds against wasm32 in stable rust
   wasm32-build:

parquet/Cargo.toml

@@ -30,6 +30,8 @@ rust-version = { workspace = true }
 
 [target.'cfg(target_arch = "wasm32")'.dependencies]
 ahash = { version = "0.8", default-features = false, features = ["compile-time-rng"] }
+# See https://github.com/briansmith/ring/issues/918#issuecomment-2077788925
+ring = { version = "0.17", default-features = false, features = ["wasm32_unknown_unknown_js", "std"], optional = true }
 
 [target.'cfg(not(target_arch = "wasm32"))'.dependencies]
 ahash = { version = "0.8", default-features = false, features = ["runtime-rng"] }
@@ -70,6 +72,7 @@ half = { version = "2.1", default-features = false, features = ["num-traits"] }
 sysinfo = { version = "0.33.0", optional = true, default-features = false, features = ["system"] }
 crc32fast = { version = "1.4.2", optional = true, default-features = false }
 simdutf8 = { version = "0.1.5", optional = true, default-features = false }
+ring = { version = "0.17", default-features = false, features = ["std"], optional = true }
 
 [dev-dependencies]
 base64 = { version = "0.22", default-features = false, features = ["std"] }
@@ -125,6 +128,8 @@ sysinfo = ["dep:sysinfo"]
 crc = ["dep:crc32fast"]
 # Enable SIMD UTF-8 validation
 simdutf8 = ["dep:simdutf8"]
+# Enable Parquet modular encryption support
+encryption = ["dep:ring"]
 
 
 [[example]]

parquet/README.md

@@ -63,6 +63,7 @@ The `parquet` crate provides the following features which may be enabled in your
 - `crc` - enables functionality to automatically verify checksums of each page (if present) when decoding
 - `experimental` - Experimental APIs which may change, even between minor releases
 - `simdutf8` (default) - Use the [`simdutf8`] crate for SIMD-accelerated UTF-8 validation
+- `encryption` - support for reading / writing encrypted Parquet files
 
 [`arrow`]: https://crates.io/crates/arrow
 [`simdutf8`]: https://crates.io/crates/simdutf8
@@ -76,12 +77,14 @@ The `parquet` crate provides the following features which may be enabled in your
   - [x] Row record reader
   - [x] Arrow record reader
   - [x] Async support (to Arrow)
+  - [x] Encrypted files
 - [x] Statistics support
 - [x] Write support
   - [x] Primitive column value writers
   - [ ] Row record writer
   - [x] Arrow record writer
   - [x] Async support
+  - [ ] Encrypted files
 - [x] Predicate pushdown
 - [x] Parquet format 4.0.0 support
 

parquet/examples/read_with_rowgroup.rs

@@ -35,7 +35,12 @@ async fn main() -> Result<()> {
     let mut file = File::open(&path).await.unwrap();
 
     // The metadata could be cached in other places, this example only shows how to read
-    let metadata = file.get_metadata().await?;
+    let metadata = file
+        .get_metadata(
+            #[cfg(feature = "encryption")]
+            None,
+        )
+        .await?;
 
     for rg in metadata.row_groups() {
         let mut rowgroup = InMemoryRowGroup::create(rg.clone(), ProjectionMask::all());
@@ -121,6 +126,8 @@ impl RowGroups for InMemoryRowGroup {
                     self.metadata.column(i),
                     self.num_rows(),
                     None,
+                    #[cfg(feature = "encryption")]
+                    None,
                 )?);
 
                 Ok(Box::new(ColumnChunkIterator {