alamb commented on code in PR #19389:
URL: https://github.com/apache/datafusion/pull/19389#discussion_r2645641612
##########
datafusion/functions/src/core/getfield.rs:
##########
@@ -15,64 +15,76 @@
// specific language governing permissions and limitations
// under the License.
+use std::any::Any;
+use std::sync::Arc;
+
use arrow::array::{
Array, BooleanArray, Capacities, MutableArrayData, Scalar, make_array,
make_comparator,
};
use arrow::compute::SortOptions;
use arrow::datatypes::{DataType, Field, FieldRef};
use arrow_buffer::NullBuffer;
+
use datafusion_common::cast::{as_map_array, as_struct_array};
use datafusion_common::{
Result, ScalarValue, exec_err, internal_err, plan_datafusion_err,
- utils::take_function_args,
};
+use datafusion_expr::expr::ScalarFunction;
+use datafusion_expr::simplify::ExprSimplifyResult;
use datafusion_expr::{
- ColumnarValue, Documentation, Expr, ReturnFieldArgs, ScalarFunctionArgs,
+ ColumnarValue, Documentation, Expr, ReturnFieldArgs, ScalarFunctionArgs,
ScalarUDF,
+ ScalarUDFImpl, Signature, Volatility,
};
-use datafusion_expr::{ScalarUDFImpl, Signature, Volatility};
use datafusion_macros::user_doc;
-use std::any::Any;
-use std::sync::Arc;
#[user_doc(
doc_section(label = "Other Functions"),
description = r#"Returns a field within a map or a struct with the given
key.
+ Supports nested field access by providing multiple field names.
Note: most users invoke `get_field` indirectly via field access
syntax such as `my_struct_col['field_name']` which results in a call to
- `get_field(my_struct_col, 'field_name')`."#,
- syntax_example = "get_field(expression1, expression2)",
+ `get_field(my_struct_col, 'field_name')`.
+ Nested access like `my_struct['a']['b']` is optimized to a single call:
+ `get_field(my_struct, 'a', 'b')`."#,
+ syntax_example = "get_field(expression, field_name[, field_name2, ...])",
sql_example = r#"```sql
-> create table t (idx varchar, v varchar) as values ('data','fusion'),
('apache', 'arrow');
-> select struct(idx, v) from t as c;
-+-------------------------+
-| struct(c.idx,c.v) |
-+-------------------------+
-| {c0: data, c1: fusion} |
-| {c0: apache, c1: arrow} |
-+-------------------------+
-> select get_field((select struct(idx, v) from t), 'c0');
-+-----------------------+
-| struct(t.idx,t.v)[c0] |
-+-----------------------+
-| data |
-| apache |
-+-----------------------+
-> select get_field((select struct(idx, v) from t), 'c1');
-+-----------------------+
-| struct(t.idx,t.v)[c1] |
-+-----------------------+
-| fusion |
-| arrow |
-+-----------------------+
+> -- Access a field from a struct column
+> create table test( struct_col) as values
+ ({name: 'Alice', age: 30}),
+ ({name: 'Bob', age: 25});
+> select struct_col from test;
++-----------------------------+
+| struct_col |
++-----------------------------+
+| {name: Alice, age: 30} |
+| {name: Bob, age: 25} |
++-----------------------------+
+> select struct_col['name'] as name from test;
++-------+
+| name |
++-------+
+| Alice |
+| Bob |
++-------+
+
+> -- Nested field access with multiple arguments
+> create table test(struct_col) as values
+ ({outer: {inner_val: 42}});
+> select struct_col['outer']['inner_val'] as result from test;
Review Comment:
nice!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
