Merge union_by_name and union_by_name_distinct into a single method with distinct flag

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: timsaucer

crates/core/src/dataframe.rs

@@ -971,22 +971,15 @@ impl PyDataFrame {
     }
 
     /// Union two DataFrames matching columns by name
-    fn union_by_name(&self, py_df: PyDataFrame) -> PyDataFusionResult<Self> {
-        let new_df = self
-            .df
-            .as_ref()
-            .clone()
-            .union_by_name(py_df.df.as_ref().clone())?;
-        Ok(Self::new(new_df))
-    }
-
-    /// Union two DataFrames by name with deduplication
-    fn union_by_name_distinct(&self, py_df: PyDataFrame) -> PyDataFusionResult<Self> {
-        let new_df = self
-            .df
-            .as_ref()
-            .clone()
-            .union_by_name_distinct(py_df.df.as_ref().clone())?;
+    #[pyo3(signature = (py_df, distinct=false))]
+    fn union_by_name(&self, py_df: PyDataFrame, distinct: bool) -> PyDataFusionResult<Self> {
+        let base = self.df.as_ref().clone();
+        let other = py_df.df.as_ref().clone();
+        let new_df = if distinct {
+            base.union_by_name_distinct(other)?
+        } else {
+            base.union_by_name(other)?
+        };
         Ok(Self::new(new_df))
     }
 

python/datafusion/dataframe.py

@@ -1300,9 +1300,7 @@ def union_by_name(self, other: DataFrame, distinct: bool = False) -> DataFrame:
             >>> df1.union_by_name(df2, distinct=True).to_pydict()
             {'a': [1], 'b': [10]}
         """
-        if distinct:
-            return DataFrame(self.df.union_by_name_distinct(other.df))
-        return DataFrame(self.df.union_by_name(other.df))
+        return DataFrame(self.df.union_by_name(other.df, distinct))
 
     def distinct_on(
         self,