Fix formatting

Author: Subham Singhal

datafusion/physical-expr/src/utils/mod.rs

@@ -275,13 +275,6 @@ fn get_field_id(field: &arrow::datatypes::Field) -> Option<i32> {
 }
 
 /// Find field index by field ID with fallback to name-based matching
-///
-/// # Limitations
-///
-/// TODO: Currently only supports flat schemas. For nested schemas, this function
-/// would need to accept a field path (e.g., ["address", "city"]) and return
-/// a path of indices. This requires matching nested field IDs at each level
-/// of the schema hierarchy.
 fn find_field_index(
     column_name: &str,
     source_schema: &Schema,
@@ -293,8 +286,6 @@ fn find_field_index(
     // Check if field has a field ID
     if let Some(source_field_id) = get_field_id(source_field) {
         // Search target schema for matching field ID
-        // TODO: For nested schemas, this needs to recursively match field IDs
-        // through the struct hierarchy
         for (idx, target_field) in target_schema.fields().iter().enumerate() {
             if let Some(target_field_id) = get_field_id(target_field)
                 && source_field_id == target_field_id
@@ -322,13 +313,9 @@ fn find_field_index(
 ///
 /// # Limitations
 ///
-/// TODO: Currently only supports flat schemas (top-level columns). Nested field
-/// references (e.g., "address.city") are not yet supported. Supporting nested
-/// fields would require:
-/// - Path-based field ID matching through struct hierarchies
-/// - Recursive traversal of both expression tree and schema tree
-/// - Updates to Column representation to track nested paths
-///
+/// Currently only supports flat schemas (top-level columns). Nested field
+/// references (e.g., "address.city") are not yet supported.
+/// For nested schema see: (<https://github.com/apache/datafusion/issues/20475>)
 /// # Errors
 ///
 /// This function will return an error if any column in the expression cannot be found

datafusion/sqllogictest/test_files/information_schema.slt

@@ -383,7 +383,7 @@ datafusion.execution.parquet.dictionary_enabled true (writing) Sets if dictionar
 datafusion.execution.parquet.dictionary_page_size_limit 1048576 (writing) Sets best effort maximum dictionary page size, in bytes
 datafusion.execution.parquet.enable_page_index true (reading) If true, reads the Parquet data page level metadata (the Page Index), if present, to reduce the I/O and number of rows decoded.
 datafusion.execution.parquet.encoding NULL (writing)  Sets default encoding for any column. Valid values are: plain, plain_dictionary, rle, bit_packed, delta_binary_packed, delta_length_byte_array, delta_byte_array, rle_dictionary, and byte_stream_split. These values are not case sensitive. If NULL, uses default parquet writer setting
-datafusion.execution.parquet.field_id_read_enabled false (reading) If true, use Parquet field IDs for column resolution instead of column names. This enables schema evolution with renamed/reordered columns. When field IDs are unavailable, falls back to name-based matching.
+datafusion.execution.parquet.field_id_enabled false (reading) If true, use Parquet field IDs for column resolution instead of column names. This enables schema evolution with renamed/reordered columns. When field IDs are unavailable, falls back to name-based matching.
 datafusion.execution.parquet.force_filter_selections false (reading) Force the use of RowSelections for filter results, when pushdown_filters is enabled. If false, the reader will automatically choose between a RowSelection and a Bitmap based on the number and pattern of selected rows.
 datafusion.execution.parquet.max_predicate_cache_size NULL (reading) The maximum predicate cache size, in bytes. When `pushdown_filters` is enabled, sets the maximum memory used to cache the results of predicate evaluation between filter evaluation and output generation. Decreasing this value will reduce memory usage, but may increase IO and CPU usage. None means use the default parquet reader setting. 0 means no caching.
 datafusion.execution.parquet.max_row_group_size 1048576 (writing) Target maximum number of rows in each row group (defaults to 1M rows). Writing larger row groups requires more memory to write, but can get better compression and be faster to read.