Merge branch 'main' into fix-is-not-null-proto-hooks

Author: chakkk309

.github/workflows/audit.yml

@@ -45,7 +45,7 @@ jobs:
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
       - name: Install cargo-audit
-        uses: taiki-e/install-action@213ccc1a076163c093f914550b94feb90fab916d  # v2.79.2
+        uses: taiki-e/install-action@920ab1831fbf4fb3ef75c8ead83556c918bb7290  # v2.79.8
         with:
           tool: cargo-audit
       - name: Run audit check

.github/workflows/breaking_changes_detector.yml

@@ -89,7 +89,7 @@ jobs:
 
       - name: Install cargo-semver-checks
         if: steps.changed_crates.outputs.packages != ''
-        uses: taiki-e/install-action@213ccc1a076163c093f914550b94feb90fab916d  # v2.79.2
+        uses: taiki-e/install-action@920ab1831fbf4fb3ef75c8ead83556c918bb7290  # v2.79.8
         with:
           tool: cargo-semver-checks
 

.github/workflows/codeql.yml

@@ -45,11 +45,11 @@ jobs:
         persist-credentials: false
 
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@9e0d7b8d25671d64c341c19c0152d693099fb5ba # v4
+      uses: github/codeql-action/init@7211b7c8077ea37d8641b6271f6a365a22a5fbfa # v4
       with:
         languages: actions
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@9e0d7b8d25671d64c341c19c0152d693099fb5ba # v4
+      uses: github/codeql-action/analyze@7211b7c8077ea37d8641b6271f6a365a22a5fbfa # v4
       with:
         category: "/language:actions"

.github/workflows/dev.yml

@@ -64,7 +64,7 @@ jobs:
           source ci/scripts/utils/tool_versions.sh
           echo "LYCHEE_VERSION=${LYCHEE_VERSION}" >> "$GITHUB_ENV"
       - name: Install lychee
-        uses: taiki-e/install-action@213ccc1a076163c093f914550b94feb90fab916d  # v2.79.2
+        uses: taiki-e/install-action@920ab1831fbf4fb3ef75c8ead83556c918bb7290  # v2.79.8
         with:
           tool: lychee@${{ env.LYCHEE_VERSION }}
       - name: Run markdown link check

.github/workflows/rust.yml

@@ -429,7 +429,7 @@ jobs:
           sudo apt-get update -qq
           sudo apt-get install -y -qq clang
       - name: Setup wasm-pack
-        uses: taiki-e/install-action@213ccc1a076163c093f914550b94feb90fab916d  # v2.79.2
+        uses: taiki-e/install-action@920ab1831fbf4fb3ef75c8ead83556c918bb7290  # v2.79.8
         with:
           tool: wasm-pack
       - name: Run tests with headless mode
@@ -773,7 +773,7 @@ jobs:
       - name: Setup Rust toolchain
         uses: ./.github/actions/setup-builder
       - name: Install cargo-msrv
-        uses: taiki-e/install-action@213ccc1a076163c093f914550b94feb90fab916d  # v2.79.2
+        uses: taiki-e/install-action@920ab1831fbf4fb3ef75c8ead83556c918bb7290  # v2.79.8
         with:
           tool: cargo-msrv
 

.github/workflows/stale.yml

@@ -28,7 +28,7 @@ jobs:
       issues: write
       pull-requests: write
     steps:
-      - uses: actions/stale@b5d41d4e1d5dceea10e7104786b73624c18a190f  # v10.2.0
+      - uses: actions/stale@eb5cf3af3ac0a1aa4c9c45633dd1ae542a27a899  # v10.3.0
         with:
           stale-pr-message: "Thank you for your contribution. Unfortunately, this pull request is stale because it has been open 60 days with no activity. Please remove the stale label or comment or this will be closed in 7 days."
           days-before-pr-stale: 60

Cargo.lock

@@ -32,7 +32,7 @@ use datafusion_datasource::file_sink_config::{FileOutputMode, FileSinkConfig};
 #[expect(deprecated)]
 use datafusion_datasource::schema_adapter::SchemaAdapterFactory;
 use datafusion_datasource::{
-    ListingTableUrl, PartitionedFile, TableSchema, compute_all_files_statistics,
+    ListingTableUrl, PartitionedFile, TableSchemaBuilder, compute_all_files_statistics,
 };
 use datafusion_execution::cache::TableScopedPath;
 use datafusion_execution::cache::cache_manager::FileStatisticsCache;
@@ -321,14 +321,15 @@ impl ListingTable {
 
     /// Creates a file source for this table
     fn create_file_source(&self) -> Arc<dyn FileSource> {
-        let table_schema = TableSchema::new(
-            Arc::clone(&self.file_schema),
-            self.options
-                .table_partition_cols
-                .iter()
-                .map(|(col, field)| Arc::new(Field::new(col, field.clone(), false)))
-                .collect(),
-        );
+        let table_schema = TableSchemaBuilder::from(&self.file_schema)
+            .with_table_partition_cols(
+                self.options
+                    .table_partition_cols
+                    .iter()
+                    .map(|(col, field)| Arc::new(Field::new(col, field.clone(), false)))
+                    .collect::<Vec<_>>(),
+            )
+            .build();
 
         self.options.format.file_source(table_schema)
     }

datafusion/catalog-listing/src/table.rs

@@ -26,6 +26,7 @@ use async_trait::async_trait;
 use datafusion_common::{Constraints, Statistics, not_impl_err};
 use datafusion_common::{Result, internal_err};
 use datafusion_expr::Expr;
+use datafusion_expr::statistics::StatisticsRequest;
 
 use datafusion_expr::dml::InsertOp;
 use datafusion_expr::{
@@ -406,6 +407,7 @@ pub struct ScanArgs<'a> {
     filters: Option<&'a [Expr]>,
     projection: Option<&'a [usize]>,
     limit: Option<usize>,
+    statistics_requests: &'a [StatisticsRequest],
 }
 
 impl<'a> ScanArgs<'a> {
@@ -467,6 +469,32 @@ impl<'a> ScanArgs<'a> {
     pub fn limit(&self) -> Option<usize> {
         self.limit
     }
+
+    /// Specifies the statistics the caller may use when optimizing the query.
+    ///
+    /// This is intended to allow the `TableProvider` to cheaply provide
+    /// statistics that may help, such as those it has in an in-memory catalog
+    /// or from some other metadata source.
+    ///
+    /// `TableProvider`s read these via [`Self::statistics_requests()`]; anything
+    /// a `TableProvider` cannot answer cheaply it simply ignores. DataFusion's
+    /// own `TableProvider`s ignore this field — it exists so a request can be
+    /// threaded from a custom optimizer rule (which annotates
+    /// `TableScan::statistics_requests`) through to a custom `TableProvider`.
+    pub fn with_statistics_requests(
+        mut self,
+        statistics_requests: &'a [StatisticsRequest],
+    ) -> Self {
+        self.statistics_requests = statistics_requests;
+        self
+    }
+
+    /// Get the statistics requests for the scan. Empty if none were set.
+    ///
+    /// See [`Self::with_statistics_requests`] for more details
+    pub fn statistics_requests(&self) -> &'a [StatisticsRequest] {
+        self.statistics_requests
+    }
 }
 
 /// Result of a table scan operation from [`TableProvider::scan_with_args`].

datafusion/catalog/src/table.rs

@@ -67,7 +67,7 @@ pub(crate) mod test_util {
                 .await?
         };
 
-        let table_schema = TableSchema::new(file_schema.clone(), vec![]);
+        let table_schema = TableSchema::from(&file_schema);
 
         let statistics = format
             .infer_stats(state, &store, file_schema.clone(), &meta)