fix: pre-warm listing file statistics cache during listing table creation (#18971)

Pre-warm listing file statistics cache during create listing table flow
as suggested in #18952.
Reused `list_files_for_scan` to pre-warm.

## 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 #18952.

## 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.
-->

## 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.
-->

## Are these changes tested?

<!--
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

If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->
Yes unit tested.

## 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.
-->

---------

Signed-off-by: bharath-techie <[email protected]>
Co-authored-by: Andrew Lamb <[email protected]>

Author: bharath-techie

datafusion/core/src/datasource/listing_table_factory.rs

@@ -190,6 +190,16 @@ impl TableProviderFactory for ListingTableFactory {
             .with_definition(cmd.definition.clone())
             .with_constraints(cmd.constraints.clone())
             .with_column_defaults(cmd.column_defaults.clone());
+
+        // Pre-warm statistics cache if collect_statistics is enabled
+        if session_state.config().collect_statistics() {
+            let filters = &[];
+            let limit = None;
+            if let Err(e) = table.list_files_for_scan(state, filters, limit).await {
+                log::warn!("Failed to pre-warm statistics cache: {e}");
+            }
+        }
+
         Ok(Arc::new(table))
     }
 }
@@ -205,17 +215,21 @@ fn get_extension(path: &str) -> String {
 
 #[cfg(test)]
 mod tests {
+    use super::*;
+    use crate::{
+        datasource::file_format::csv::CsvFormat, execution::context::SessionContext,
+        test_util::parquet_test_data,
+    };
+    use datafusion_execution::cache::cache_manager::CacheManagerConfig;
+    use datafusion_execution::cache::cache_unit::DefaultFileStatisticsCache;
+    use datafusion_execution::cache::CacheAccessor;
     use datafusion_execution::config::SessionConfig;
+    use datafusion_execution::runtime_env::RuntimeEnvBuilder;
     use glob::Pattern;
     use std::collections::HashMap;
     use std::fs;
     use std::path::PathBuf;
 
-    use super::*;
-    use crate::{
-        datasource::file_format::csv::CsvFormat, execution::context::SessionContext,
-    };
-
     use datafusion_common::parsers::CompressionTypeVariant;
     use datafusion_common::{Constraints, DFSchema, TableReference};
 
@@ -519,4 +533,93 @@ mod tests {
         let listing_options = listing_table.options();
         assert!(listing_options.table_partition_cols.is_empty());
     }
+
+    #[tokio::test]
+    async fn test_statistics_cache_prewarming() {
+        let factory = ListingTableFactory::new();
+
+        let location = PathBuf::from(parquet_test_data())
+            .join("alltypes_tiny_pages_plain.parquet")
+            .to_string_lossy()
+            .to_string();
+
+        // Test with collect_statistics enabled
+        let file_statistics_cache = Arc::new(DefaultFileStatisticsCache::default());
+        let cache_config = CacheManagerConfig::default()
+            .with_files_statistics_cache(Some(file_statistics_cache.clone()));
+        let runtime = RuntimeEnvBuilder::new()
+            .with_cache_manager(cache_config)
+            .build_arc()
+            .unwrap();
+
+        let mut config = SessionConfig::new();
+        config.options_mut().execution.collect_statistics = true;
+        let context = SessionContext::new_with_config_rt(config, runtime);
+        let state = context.state();
+        let name = TableReference::bare("test");
+
+        let cmd = CreateExternalTable {
+            name,
+            location: location.clone(),
+            file_type: "parquet".to_string(),
+            schema: Arc::new(DFSchema::empty()),
+            table_partition_cols: vec![],
+            if_not_exists: false,
+            or_replace: false,
+            temporary: false,
+            definition: None,
+            order_exprs: vec![],
+            unbounded: false,
+            options: HashMap::new(),
+            constraints: Constraints::default(),
+            column_defaults: HashMap::new(),
+        };
+
+        let _table_provider = factory.create(&state, &cmd).await.unwrap();
+
+        assert!(
+            file_statistics_cache.len() > 0,
+            "Statistics cache should be pre-warmed when collect_statistics is enabled"
+        );
+
+        // Test with collect_statistics disabled
+        let file_statistics_cache = Arc::new(DefaultFileStatisticsCache::default());
+        let cache_config = CacheManagerConfig::default()
+            .with_files_statistics_cache(Some(file_statistics_cache.clone()));
+        let runtime = RuntimeEnvBuilder::new()
+            .with_cache_manager(cache_config)
+            .build_arc()
+            .unwrap();
+
+        let mut config = SessionConfig::new();
+        config.options_mut().execution.collect_statistics = false;
+        let context = SessionContext::new_with_config_rt(config, runtime);
+        let state = context.state();
+        let name = TableReference::bare("test");
+
+        let cmd = CreateExternalTable {
+            name,
+            location,
+            file_type: "parquet".to_string(),
+            schema: Arc::new(DFSchema::empty()),
+            table_partition_cols: vec![],
+            if_not_exists: false,
+            or_replace: false,
+            temporary: false,
+            definition: None,
+            order_exprs: vec![],
+            unbounded: false,
+            options: HashMap::new(),
+            constraints: Constraints::default(),
+            column_defaults: HashMap::new(),
+        };
+
+        let _table_provider = factory.create(&state, &cmd).await.unwrap();
+
+        assert_eq!(
+            file_statistics_cache.len(),
+            0,
+            "Statistics cache should not be pre-warmed when collect_statistics is disabled"
+        );
+    }
 }