feat(arrow): support ArrowReaderOptions in get_metadata

Respect ArrowReaderOptions by extracting metadata_options and passing
it to ParquetMetaDataReader via with_metadata_options(). This allows
callers to configure metadata decoding behavior.

This change requires parquet 57.1.0 which added the
ParquetMetaDataReader::with_metadata_options() API.

Changes:
- Update arrow and parquet dependencies from 57.0 to 57.1
- Update bindings/python/Cargo.lock for the new versions
- Use metadata_options from ArrowReaderOptions in get_metadata

Closes #1934

Author: xbattlax

Cargo.toml

@@ -42,14 +42,14 @@ rust-version = "1.88"
 anyhow = "1.0.72"
 apache-avro = { version = "0.21", features = ["zstandard"] }
 array-init = "2"
-arrow-arith = "57.0"
-arrow-array = "57.0"
-arrow-buffer = "57.0"
-arrow-cast = "57.0"
-arrow-ord = "57.0"
-arrow-schema = "57.0"
-arrow-select = "57.0"
-arrow-string = "57.0"
+arrow-arith = "57.1"
+arrow-array = "57.1"
+arrow-buffer = "57.1"
+arrow-cast = "57.1"
+arrow-ord = "57.1"
+arrow-schema = "57.1"
+arrow-select = "57.1"
+arrow-string = "57.1"
 as-any = "0.3.2"
 async-trait = "0.1.89"
 aws-config = "1.8.7"
@@ -101,7 +101,7 @@ num-bigint = "0.4.6"
 once_cell = "1.20"
 opendal = "0.55.0"
 ordered-float = "4"
-parquet = "57.0"
+parquet = "57.1"
 pilota = "0.11.10"
 port_scanner = "0.1.5"
 pretty_assertions = "1.4"

bindings/python/Cargo.lock

@@ -1705,19 +1705,21 @@ impl<R: FileRead> AsyncFileReader for ArrowFileReader<R> {
         )
     }
 
-    // TODO: currently we don't respect `ArrowReaderOptions` cause it don't expose any method to access the option field
-    // we will fix it after `v55.1.0` is released in https://github.com/apache/arrow-rs/issues/7393
     fn get_metadata(
         &mut self,
-        _options: Option<&'_ ArrowReaderOptions>,
+        options: Option<&'_ ArrowReaderOptions>,
     ) -> BoxFuture<'_, parquet::errors::Result<Arc<ParquetMetaData>>> {
+        // Extract metadata options from ArrowReaderOptions if provided
+        let metadata_options = options.map(|o| o.metadata_options().clone());
+
         async move {
             let reader = ParquetMetaDataReader::new()
                 .with_prefetch_hint(self.metadata_size_hint)
                 // Set the page policy first because it updates both column and offset policies.
                 .with_page_index_policy(PageIndexPolicy::from(self.preload_page_index))
                 .with_column_index_policy(PageIndexPolicy::from(self.preload_column_index))
-                .with_offset_index_policy(PageIndexPolicy::from(self.preload_offset_index));
+                .with_offset_index_policy(PageIndexPolicy::from(self.preload_offset_index))
+                .with_metadata_options(metadata_options);
             let size = self.meta.size;
             let meta = reader.load_and_finish(self, size).await?;