feat: Optimize hash util for MapArray

datafusion/common/src/hash_utils.rs

@@ -481,23 +481,39 @@ fn hash_map_array(
     let offsets = array.offsets();
 
     // Create hashes for each entry in each row
-    let mut values_hashes = vec![0u64; array.entries().len()];
-    create_hashes(array.entries().columns(), random_state, &mut values_hashes)?;
+    let first_offset = offsets.first().copied().unwrap_or_default() as usize;
+    let last_offset = offsets.last().copied().unwrap_or_default() as usize;
+    let entries_len = last_offset - first_offset;
+
+    // Only hash the entries that are actually referenced
+    let mut values_hashes = vec![0u64; entries_len];
+    let entries = array.entries();
+    let sliced_columns: Vec<ArrayRef> = entries
+        .columns()
+        .iter()
+        .map(|col| col.slice(first_offset, entries_len))
+        .collect();
+    create_hashes(&sliced_columns, random_state, &mut values_hashes)?;
 
     // Combine the hashes for entries on each row with each other and previous hash for that row
+    // Adjust indices by first_offset since values_hashes is sliced starting from first_offset
     if let Some(nulls) = nulls {
         for (i, (start, stop)) in offsets.iter().zip(offsets.iter().skip(1)).enumerate() {
             if nulls.is_valid(i) {
                 let hash = &mut hashes_buffer[i];
-                for values_hash in &values_hashes[start.as_usize()..stop.as_usize()] {
+                for values_hash in &values_hashes
+                    [start.as_usize() - first_offset..stop.as_usize() - first_offset]
+                {
                     *hash = combine_hashes(*hash, *values_hash);
                 }
             }
         }
     } else {
         for (i, (start, stop)) in offsets.iter().zip(offsets.iter().skip(1)).enumerate() {
             let hash = &mut hashes_buffer[i];
-            for values_hash in &values_hashes[start.as_usize()..stop.as_usize()] {
+            for values_hash in &values_hashes
+                [start.as_usize() - first_offset..stop.as_usize() - first_offset]
+            {
                 *hash = combine_hashes(*hash, *values_hash);
             }
         }