Support binary data type in build_struct_array. (#702)

* Support binary data type in `build_struct_array`. * Modify test case. * cargo fmt Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>
apache · Aug 21, 2021 · 8308615 · 8308615
1 parent 38e5d22
commit 8308615
Show file tree

Hide file tree

Showing 2 changed files with 41 additions and 1 deletion.
diff --git a/arrow/src/array/array.rs b/arrow/src/array/array.rs
@@ -668,7 +668,7 @@ mod tests {
                 "entry",
                 DataType::Struct(vec![
                     Field::new("key", DataType::Utf8, false),
-                    Field::new("key", DataType::Int32, true),
+                    Field::new("value", DataType::Int32, true),
                 ]),
                 false,
             )),

diff --git a/arrow/src/json/reader.rs b/arrow/src/json/reader.rs
@@ -1225,6 +1225,14 @@ impl Decoder {
                             })
                             .collect::<StringArray>(),
                     ) as ArrayRef),
+                    DataType::Binary => Ok(Arc::new(
+                        rows.iter()
+                            .map(|row| {
+                                let maybe_value = row.get(field.name());
+                                maybe_value.and_then(|value| value.as_str())
+                            })
+                            .collect::<BinaryArray>(),
+                    ) as ArrayRef),
                     DataType::List(ref list_field) => {
                         match list_field.data_type() {
                             DataType::Dictionary(ref key_ty, _) => {
@@ -3140,6 +3148,38 @@ mod tests {
         assert_eq!(batch.num_rows(), 3);
     }
 
+    #[test]
+    fn test_json_read_binary_structs() {
+        let schema = Schema::new(vec![Field::new("c1", DataType::Binary, true)]);
+        let decoder = Decoder::new(Arc::new(schema), 1024, None);
+        let batch = decoder
+            .next_batch(
+                &mut vec![
+                    Ok(serde_json::json!({
+                        "c1": "₁₂₃",
+                    })),
+                    Ok(serde_json::json!({
+                        "c1": "foo",
+                    })),
+                ]
+                .into_iter(),
+            )
+            .unwrap()
+            .unwrap();
+        let data = batch.columns().iter().collect::<Vec<_>>();
+
+        let schema = Schema::new(vec![Field::new("c1", DataType::Binary, true)]);
+        let binary_values = BinaryArray::from(vec!["₁₂₃".as_bytes(), "foo".as_bytes()]);
+        let expected_batch =
+            RecordBatch::try_new(Arc::new(schema), vec![Arc::new(binary_values)])
+                .unwrap();
+        let expected_data = expected_batch.columns().iter().collect::<Vec<_>>();
+
+        assert_eq!(data, expected_data);
+        assert_eq!(batch.num_columns(), 1);
+        assert_eq!(batch.num_rows(), 2);
+    }
+
     #[test]
     fn test_json_iterator() {
         let builder = ReaderBuilder::new().infer_schema(None).with_batch_size(5);