feat: support upper and lower for stringview

apache · Aug 23, 2024 · b4e0974 · b4e0974
1 parent 8fd9d69
commit b4e0974
Show file tree

Hide file tree

Showing 4 changed files with 53 additions and 8 deletions.
diff --git a/datafusion/functions/src/string/common.rs b/datafusion/functions/src/string/common.rs
@@ -23,7 +23,7 @@ use std::sync::Arc;
 use arrow::array::{
     new_null_array, Array, ArrayAccessor, ArrayDataBuilder, ArrayIter, ArrayRef,
     GenericStringArray, GenericStringBuilder, OffsetSizeTrait, StringArray,
-    StringViewArray,
+    StringBuilder, StringViewArray,
 };
 use arrow::buffer::{Buffer, MutableBuffer, NullBuffer};
 use arrow::datatypes::DataType;
@@ -214,6 +214,23 @@ where
                 i64,
                 _,
             >(array, op)?)),
+            DataType::Utf8View => {
+                let string_array = as_string_view_array(array)?;
+                let mut string_builder = StringBuilder::with_capacity(
+                    string_array.len(),
+                    string_array.get_array_memory_size(),
+                );
+
+                for str in string_array.iter() {
+                    if let Some(str) = str {
+                        string_builder.append_value(op(str));
+                    } else {
+                        string_builder.append_null();
+                    }
+                }
+
+                Ok(ColumnarValue::Array(Arc::new(string_builder.finish())))
+            }
             other => exec_err!("Unsupported data type {other:?} for function {name}"),
         },
         ColumnarValue::Scalar(scalar) => match scalar {
@@ -225,6 +242,10 @@ where
                 let result = a.as_ref().map(|x| op(x));
                 Ok(ColumnarValue::Scalar(ScalarValue::LargeUtf8(result)))
             }
+            ScalarValue::Utf8View(a) => {
+                let result = a.as_ref().map(|x| op(x));
+                Ok(ColumnarValue::Scalar(ScalarValue::Utf8(result)))
+            }
             other => exec_err!("Unsupported data type {other:?} for function {name}"),
         },
     }

diff --git a/datafusion/functions/src/string/lower.rs b/datafusion/functions/src/string/lower.rs
@@ -43,7 +43,7 @@ impl LowerFunc {
         Self {
             signature: Signature::uniform(
                 1,
-                vec![Utf8, LargeUtf8],
+                vec![Utf8, LargeUtf8, Utf8View],
                 Volatility::Immutable,
             ),
         }

diff --git a/datafusion/functions/src/string/upper.rs b/datafusion/functions/src/string/upper.rs
@@ -40,7 +40,7 @@ impl UpperFunc {
         Self {
             signature: Signature::uniform(
                 1,
-                vec![Utf8, LargeUtf8],
+                vec![Utf8, LargeUtf8, Utf8View],
                 Volatility::Immutable,
             ),
         }

diff --git a/datafusion/sqllogictest/test_files/string_view.slt b/datafusion/sqllogictest/test_files/string_view.slt
@@ -460,8 +460,6 @@ Xiangpeng
 Raphael
 NULL
 
-
-
 ### Initcap
 
 query TT
@@ -501,7 +499,7 @@ SELECT
   INITCAP(column1_large_utf8_lower) as c3
 FROM test_lowercase;
 ----
-Andrew Andrew Andrew    
+Andrew Andrew Andrew
 Xiangpeng Xiangpeng Xiangpeng
 Raphael Raphael Raphael
 NULL NULL NULL
@@ -828,16 +826,42 @@ logical_plan
 02)--TableScan: test projection=[column1_utf8view, column2_utf8view]
 
 ## Ensure no casts for LOWER
-## TODO https://github.com/apache/datafusion/issues/11855
 query TT
 EXPLAIN SELECT
   LOWER(column1_utf8view) as c1
 FROM test;
 ----
 logical_plan
-01)Projection: lower(CAST(test.column1_utf8view AS Utf8)) AS c1
+01)Projection: lower(test.column1_utf8view) AS c1
+02)--TableScan: test projection=[column1_utf8view]
+
+query T
+SELECT LOWER(column1_utf8view) as c1
+FROM test;
+----
+andrew
+xiangpeng
+raphael
+NULL
+
+## Ensure no casts for UPPER
+query TT
+EXPLAIN SELECT
+  UPPER(column1_utf8view) as c1
+FROM test;
+----
+logical_plan
+01)Projection: upper(test.column1_utf8view) AS c1
 02)--TableScan: test projection=[column1_utf8view]
 
+query T
+SELECT UPPER(column1_utf8view) as c1
+FROM test;
+----
+ANDREW
+XIANGPENG
+RAPHAEL
+NULL
 
 ## Ensure no casts for LPAD
 query TT