tustvold commented on code in PR #1746:
URL: https://github.com/apache/arrow-rs/pull/1746#discussion_r883014766


##########
parquet/src/arrow/levels.rs:
##########
@@ -825,495 +483,168 @@ mod tests {
 
     use arrow::array::*;
     use arrow::buffer::Buffer;
-    use arrow::datatypes::{Schema, ToByteSlice};
+    use arrow::datatypes::{Int32Type, Schema, ToByteSlice};
     use arrow::record_batch::RecordBatch;
+    use arrow::util::pretty::pretty_format_columns;
 
     #[test]
     fn test_calculate_array_levels_twitter_example() {
         // based on the example at 
https://blog.twitter.com/engineering/en_us/a/2013/dremel-made-simple-with-parquet.html
         // [[a, b, c], [d, e, f, g]], [[h], [i,j]]
-        let parent_levels = LevelInfo {
-            definition: vec![0, 0],
-            repetition: None,
-            array_offsets: vec![0, 1, 2], // 2 records, root offsets always 
sequential
-            array_mask: vec![true, true], // both lists defined
-            max_definition: 0,
-            level_type: LevelType::Root,
-            offset: 0,
-            length: 2,
-        };
-        // offset into array, each level1 has 2 values
-        let array_offsets = vec![0, 2, 4];
-        let array_mask = vec![true, true];
-
-        // calculate level1 levels
-        let levels = parent_levels.calculate_child_levels(
-            array_offsets.clone(),
-            array_mask,
-            LevelType::List(false),
-        );
-        //
-        let expected_levels = LevelInfo {
-            definition: vec![1, 1, 1, 1],
-            repetition: Some(vec![0, 1, 0, 1]),
-            array_offsets,
-            array_mask: vec![true, true, true, true],
-            max_definition: 1,
-            level_type: LevelType::List(false),
-            offset: 0,
-            length: 4,
-        };
-        // the separate asserts make it easier to see what's failing
-        assert_eq!(&levels.definition, &expected_levels.definition);
-        assert_eq!(&levels.repetition, &expected_levels.repetition);
-        assert_eq!(&levels.array_mask, &expected_levels.array_mask);
-        assert_eq!(&levels.array_offsets, &expected_levels.array_offsets);
-        assert_eq!(&levels.max_definition, &expected_levels.max_definition);
-        assert_eq!(&levels.level_type, &expected_levels.level_type);
-        // this assert is to help if there are more variables added to the 
struct
-        assert_eq!(&levels, &expected_levels);
-
-        // level2
-        let parent_levels = levels;
-        let array_offsets = vec![0, 3, 7, 8, 10];
-        let array_mask = vec![true, true, true, true];
-        let levels = parent_levels.calculate_child_levels(
-            array_offsets.clone(),
-            array_mask,
-            LevelType::List(false),
-        );
-        let expected_levels = LevelInfo {
-            definition: vec![2, 2, 2, 2, 2, 2, 2, 2, 2, 2],
-            repetition: Some(vec![0, 2, 2, 1, 2, 2, 2, 0, 1, 2]),
-            array_offsets,
-            array_mask: vec![true; 10],
-            max_definition: 2,
-            level_type: LevelType::List(false),
-            offset: 0,
-            length: 10,
+
+        let leaf_type = Field::new("item", DataType::Int32, false);
+        let inner_type = DataType::List(Box::new(leaf_type));
+        let inner_field = Field::new("l2", inner_type.clone(), false);
+        let outer_type = DataType::List(Box::new(inner_field));
+        let outer_field = Field::new("l1", outer_type.clone(), false);
+
+        let primitives = Int32Array::from_iter(0..10);
+
+        // Cannot use from_iter_primitive as always infers nullable
+        let offsets = Buffer::from_iter([0_i32, 3, 7, 8, 10]);
+        let inner_list = ArrayDataBuilder::new(inner_type)
+            .len(4)
+            .add_buffer(offsets)
+            .add_child_data(primitives.data().clone())
+            .build()
+            .unwrap();
+
+        let offsets = Buffer::from_iter([0_i32, 2, 4]);
+        let outer_list = ArrayDataBuilder::new(outer_type)
+            .len(2)
+            .add_buffer(offsets)
+            .add_child_data(inner_list)
+            .build()
+            .unwrap();
+        let outer_list = make_array(outer_list);
+
+        let levels = calculate_array_levels(&outer_list, 
&outer_field).unwrap();
+        assert_eq!(levels.len(), 1);
+
+        let expected = LevelInfo {

Review Comment:
   We no longer compute "intermediate" level info, as it isn't entirely clear 
what this concept ever actually meant. Level data only really means anything in 
the context of a leaf column.



-- 
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