Created
October 16, 2022 10:08
-
-
Save alamb/acd653c49e318ff70672b61325ba3443 to your computer and use it in GitHub Desktop.
Nested structure parquet encoding example
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#[test] | |
fn test_foo() { | |
let mut a = ListBuilder::new(Int32Builder::new()); | |
a.values().append_value(1); | |
a.append(true); | |
a.append(false); | |
a.values().append_null(); | |
a.values().append_null(); | |
a.append(true); | |
let values = Arc::new(a.finish()) as ArrayRef; | |
let mut builder = LevelInfoBuilder::try_new( | |
&Field::new("test", values.data_type().clone(), true), | |
Default::default(), | |
) | |
.unwrap(); | |
builder.write(&values, 0..3); | |
let levels = builder.finish(); | |
assert_eq!(levels.len(), 1); | |
let list_level = levels.get(0).unwrap(); | |
let expected_level = LevelInfo { | |
def_levels: Some(vec![3, 0, 2, 2]), | |
rep_levels: Some(vec![0, 0, 0, 1]), | |
non_null_indices: vec![0], | |
max_def_level: 3, | |
max_rep_level: 1, | |
}; | |
assert_eq!(list_level, &expected_level); | |
let b2 = DataType::List(Box::new(Field::new("element", DataType::Int32, false))); | |
let s = StructBuilder::new( | |
vec![ | |
Field::new("b1", DataType::Int32, false), | |
Field::new("b2", b2, true), | |
], | |
vec![ | |
Box::new(Int32Builder::new()), | |
Box::new(ListBuilder::new(Int32Builder::new())), | |
], | |
); | |
let mut b = ListBuilder::new(s); | |
b.values() | |
.field_builder::<Int32Builder>(0) | |
.unwrap() | |
.append_value(1); | |
b.values() | |
.field_builder::<ListBuilder<Int32Builder>>(1) | |
.unwrap() | |
.append(false); | |
b.values().append(true); | |
b.values() | |
.field_builder::<Int32Builder>(0) | |
.unwrap() | |
.append_value(1); | |
b.values() | |
.field_builder::<ListBuilder<Int32Builder>>(1) | |
.unwrap() | |
.values() | |
.append_value(3); | |
b.values() | |
.field_builder::<ListBuilder<Int32Builder>>(1) | |
.unwrap() | |
.values() | |
.append_value(4); | |
b.values() | |
.field_builder::<ListBuilder<Int32Builder>>(1) | |
.unwrap() | |
.append(true); | |
b.values().append(true); | |
b.append(true); | |
b.values() | |
.field_builder::<Int32Builder>(0) | |
.unwrap() | |
.append_value(2); | |
b.values() | |
.field_builder::<ListBuilder<Int32Builder>>(1) | |
.unwrap() | |
.append(false); | |
b.values().append(true); | |
b.append(true); | |
b.values() | |
.field_builder::<Int32Builder>(0) | |
.unwrap() | |
.append_value(0); | |
b.values() | |
.field_builder::<ListBuilder<Int32Builder>>(1) | |
.unwrap() | |
.append(false); | |
b.values().append_null(); | |
b.append(true); | |
let values = Arc::new(b.finish()) as ArrayRef; | |
let mut builder = LevelInfoBuilder::try_new( | |
&Field::new("test", values.data_type().clone(), false), | |
Default::default(), | |
) | |
.unwrap(); | |
builder.write(&values, 0..3); | |
let levels = builder.finish(); | |
assert_eq!(levels.len(), 2); | |
let list_level = levels.get(0).unwrap(); | |
let expected_level = LevelInfo { | |
def_levels: Some(vec![2, 2, 2, 1]), | |
rep_levels: Some(vec![0, 1, 0, 0]), | |
non_null_indices: vec![0, 1, 2], | |
max_def_level: 2, | |
max_rep_level: 1, | |
}; | |
assert_eq!(list_level, &expected_level); | |
let list_level = levels.get(1).unwrap(); | |
let expected_level = LevelInfo { | |
def_levels: Some(vec![2, 4, 4, 2, 1]), | |
rep_levels: Some(vec![0, 1, 2, 0, 0]), | |
non_null_indices: vec![0, 1], | |
max_def_level: 4, | |
max_rep_level: 2, | |
}; | |
assert_eq!(list_level, &expected_level); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment