(datafusion) 01/01: chore: remove deprecated Parquet APIs past the API health policy (#25202)

[gi...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

github-merge-queue[bot] pushed a commit to branch gh-readonly-queue/main/pr-25202-43f567a976cac1c16c341b0ae90e98b2b715835d
in repository https://gitbox.apache.org/repos/asf/datafusion.git

commit 5b7cc8703138bad8b0e9696f428e35a87300d45e
Author: WaterWhisperer <wa...@qq.com>
AuthorDate: Sun Sep 20 10:14:43 2026 +0000

    chore: remove deprecated Parquet APIs past the API health policy (#25202)
    
    ## Which issue does this PR close?
    
    <!--
    We generally require a GitHub issue to be filed for all bug fixes and
    enhancements and this helps us generate change logs for our releases.
    You can link an issue to this PR using the GitHub syntax. For example
    `Closes #123` indicates that this PR will close issue #123.
    -->
    
    - Closes #24540
    
    ## Rationale for this change
    
    <!--
    Why are you proposing this change? If this is already explained clearly
    in the issue then this section is not needed.
    Explaining clearly why changes are proposed helps reviewers understand
    your changes and offer better suggestions for fixes.
    
    Please explain the problem you are trying to solve in terms of the
    user-visible
    behavior, rather than the implementation.
    
    For example, "The code in `foo.rs` doesn't handle nulls" is a symptom of
    the
    implementation. "COUNT(DISTINCT) returns wrong results when the column
    contains
    nulls" is the user-visible problem.
    -->
    The deprecated Parquet APIs have passed the API health policy.
    
    ## What changes are included in this PR?
    
    <!--
    There is no need to duplicate the description in the issue here, but it
    is sometimes worth providing a summary of the individual changes in this
    PR.
    -->
    - Remove the deprecated `fetch_parquet_metadata`, `fetch_statistics`,
    and `statistics_from_parquet_meta_calc` functions.
    - Remove the deprecated `ParquetSource::predicate` method.
    - Remove the associated unused imports and test.
    
    ## What is the testing strategy for this PR?
    
    <!--
    We typically require tests for all PRs in order to:
    1. Prevent the code from being accidentally broken by subsequent changes
    2. Serve as another way to document the expected behavior of the code
    
    Briefly describe how this PR is tested, and point to the specific tests
    you added. For example: 'This new feature is covered by the
    `sqllogictest` cases added in `foo.slt`'.
    
    If this PR does not add tests, explain why. For example, if the change
    is already covered by existing tests, please mention it.
    
    You should also check the `codecov` bot reply on this PR to confirm the
    changed code is exercised.
    -->
    No new tests are added because this only removes deprecated apis.
    
    Tested by:
    
    ```bash
    ./dev/rust_lint.sh
    ```
    
    ## Are there any user-facing changes?
    
    <!--
    If there are user-facing changes then we may require documentation to be
    updated before approving the PR.
    
    If there are any breaking changes to public APIs, please add the `api
    change` label.
    -->
    Yes. It's a breaking Rust API change because public deprecated APIs are
    removed.
    
    Co-authored-by: Andrew Lamb <an...@nerdnetworks.org>
---
 datafusion/datasource-parquet/src/file_format.rs | 64 ------------------------
 datafusion/datasource-parquet/src/source.rs      | 17 -------
 2 files changed, 81 deletions(-)

diff --git a/datafusion/datasource-parquet/src/file_format.rs b/datafusion/datasource-parquet/src/file_format.rs
index 8bb700b68c..65ea0416b0 100644
--- a/datafusion/datasource-parquet/src/file_format.rs
+++ b/datafusion/datasource-parquet/src/file_format.rs
@@ -67,14 +67,12 @@ use crate::source::{
 use async_trait::async_trait;
 use bytes::Bytes;
 use datafusion_datasource::source::DataSourceExec;
-use datafusion_execution::cache::cache_manager::FileMetadataCache;
 use futures::future::BoxFuture;
 use futures::{FutureExt, StreamExt, TryStreamExt};
 use object_store::path::Path;
 use object_store::{ObjectMeta, ObjectStore, ObjectStoreExt};
 use parquet::arrow::async_reader::MetadataFetch;
 use parquet::errors::ParquetError;
-use parquet::file::metadata::ParquetMetaData;
 
 #[derive(Default)]
 /// Factory struct used to create [ParquetFormat]
@@ -639,68 +637,6 @@ impl MetadataFetch for ObjectStoreFetch<'_> {
     }
 }
 
-/// Fetches parquet metadata from ObjectStore for given object
-///
-/// This component is a subject to **change** in near future and is exposed for low level integrations
-/// through [`ParquetFileReaderFactory`].
-///
-/// [`ParquetFileReaderFactory`]: crate::ParquetFileReaderFactory
-#[deprecated(
-    since = "50.0.0",
-    note = "Use `DFParquetMetadata::fetch_metadata` instead"
-)]
-pub async fn fetch_parquet_metadata(
-    store: &dyn ObjectStore,
-    object_meta: &ObjectMeta,
-    size_hint: Option<usize>,
-    decryption_properties: Option<&FileDecryptionProperties>,
-    file_metadata_cache: Option<Arc<FileMetadataCache>>,
-) -> Result<Arc<ParquetMetaData>> {
-    let decryption_properties = decryption_properties.cloned().map(Arc::new);
-    DFParquetMetadata::new(store, object_meta)
-        .with_metadata_size_hint(size_hint)
-        .with_decryption_properties(decryption_properties)
-        .with_file_metadata_cache(file_metadata_cache)
-        .fetch_metadata()
-        .await
-}
-
-/// Read and parse the statistics of the Parquet file at location `path`
-///
-/// See [`statistics_from_parquet_meta_calc`] for more details
-#[deprecated(
-    since = "50.0.0",
-    note = "Use `DFParquetMetadata::fetch_statistics` instead"
-)]
-pub async fn fetch_statistics(
-    store: &dyn ObjectStore,
-    table_schema: SchemaRef,
-    file: &ObjectMeta,
-    metadata_size_hint: Option<usize>,
-    decryption_properties: Option<&FileDecryptionProperties>,
-    file_metadata_cache: Option<Arc<FileMetadataCache>>,
-) -> Result<Statistics> {
-    let decryption_properties = decryption_properties.cloned().map(Arc::new);
-    DFParquetMetadata::new(store, file)
-        .with_metadata_size_hint(metadata_size_hint)
-        .with_decryption_properties(decryption_properties)
-        .with_file_metadata_cache(file_metadata_cache)
-        .fetch_statistics(&table_schema)
-        .await
-}
-
-#[deprecated(
-    since = "50.0.0",
-    note = "Use `DFParquetMetadata::statistics_from_parquet_metadata` instead"
-)]
-#[expect(clippy::needless_pass_by_value)]
-pub fn statistics_from_parquet_meta_calc(
-    metadata: &ParquetMetaData,
-    table_schema: SchemaRef,
-) -> Result<Statistics> {
-    DFParquetMetadata::statistics_from_parquet_metadata(metadata, &table_schema)
-}
-
 #[cfg(feature = "proto")]
 use datafusion_proto_models::protobuf::{self, parquet_column_options, parquet_options};
 
diff --git a/datafusion/datasource-parquet/src/source.rs b/datafusion/datasource-parquet/src/source.rs
index e1434824e4..3df0e0e7e1 100644
--- a/datafusion/datasource-parquet/src/source.rs
+++ b/datafusion/datasource-parquet/src/source.rs
@@ -400,12 +400,6 @@ impl ParquetSource {
         &self.table_parquet_options
     }
 
-    /// Optional predicate.
-    #[deprecated(since = "50.2.0", note = "use `filter` instead")]
-    pub fn predicate(&self) -> Option<&Arc<dyn PhysicalExpr>> {
-        self.predicate.as_ref()
-    }
-
     /// return the optional file reader factory
     pub fn parquet_file_reader_factory(
         &self,
@@ -1364,17 +1358,6 @@ mod tests {
     use arrow::datatypes::Schema;
     use datafusion_physical_expr::expressions::lit;
 
-    #[test]
-    #[expect(deprecated)]
-    fn test_parquet_source_predicate_same_as_filter() {
-        let predicate = lit(true);
-
-        let parquet_source =
-            ParquetSource::new(Arc::new(Schema::empty())).with_predicate(predicate);
-        // same value. but filter() call Arc::clone internally
-        assert_eq!(parquet_source.predicate(), parquet_source.filter().as_ref());
-    }
-
     #[test]
     fn test_reverse_scan_default_value() {
         use arrow::datatypes::Schema;


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@datafusion.apache.org
For additional commands, e-mail: commits-help@datafusion.apache.org