Jefffrey commented on code in PR #9936:
URL: https://github.com/apache/arrow-rs/pull/9936#discussion_r3292032405


##########
arrow/src/util/data_gen.rs:
##########
@@ -230,6 +233,62 @@ fn create_random_decimal_array(field: &Field, size: usize, 
null_density: f32) ->
         ))),
     }
 }
+#[inline]
+fn create_random_run_end_encoded_array(
+    index: &Field,
+    value: &Field,
+    size: usize,
+    null_density: f32,
+    true_density: f32,
+) -> Result<ArrayRef> {
+    const MIN_RUN: usize = 8;

Review Comment:
   Probably fine as is for now



##########
arrow/src/util/data_gen.rs:
##########
@@ -648,6 +707,36 @@ mod tests {
         assert_eq!(col_d_y.null_count(), 0);
     }
 
+    #[test]
+    fn test_create_run_end_encoded_array() {
+        let size = 1000;
+        let ree_field = Field::new(
+            "ree",
+            DataType::RunEndEncoded(
+                Arc::new(Field::new("run_ends", DataType::Int32, false)),
+                Arc::new(Field::new("values", DataType::Utf8, true)),
+            ),
+            false,
+        );
+
+        let array = create_random_array(&ree_field, size, 0.25, 0.0).unwrap();
+        assert_eq!(array.len(), size);
+
+        let ree = array
+            .as_any()
+            .downcast_ref::<RunArray<Int32Type>>()
+            .unwrap();
+        let run_ends = ree.run_ends().values();
+        let num_runs = run_ends.len();
+
+        for w in run_ends.windows(2) {
+            assert!(w[0] < w[1]);

Review Comment:
   nit: this is technically enforced during `RunArray::try_new` validation 
anyway



##########
parquet/benches/arrow_writer.rs:
##########
@@ -363,8 +384,10 @@ fn write_batch_with_option(
 
     bench.iter(|| {
         let mut file = Empty::default();
-        let mut writer =
-            ArrowWriter::try_new(&mut file, batch.schema(), 
Some(props.clone())).unwrap();
+        let Ok(mut writer) = ArrowWriter::try_new(&mut file, batch.schema(), 
Some(props.clone()))

Review Comment:
   I don't follow; why do we need these changes in the first place?



##########
arrow/src/util/data_gen.rs:
##########
@@ -648,6 +707,36 @@ mod tests {
         assert_eq!(col_d_y.null_count(), 0);
     }
 
+    #[test]
+    fn test_create_run_end_encoded_array() {
+        let size = 1000;
+        let ree_field = Field::new(
+            "ree",
+            DataType::RunEndEncoded(
+                Arc::new(Field::new("run_ends", DataType::Int32, false)),
+                Arc::new(Field::new("values", DataType::Utf8, true)),
+            ),
+            false,
+        );
+
+        let array = create_random_array(&ree_field, size, 0.25, 0.0).unwrap();
+        assert_eq!(array.len(), size);
+
+        let ree = array
+            .as_any()
+            .downcast_ref::<RunArray<Int32Type>>()
+            .unwrap();

Review Comment:
   ```suggestion
           let ree = array.as_run::<Int32Type>();
   ```



-- 
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]

Reply via email to