Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Handling nullable DictionaryArray in CSV parser #6830

Merged
merged 1 commit into from
Dec 5, 2024
Merged

Handling nullable DictionaryArray in CSV parser #6830

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
74 changes: 66 additions & 8 deletions arrow-csv/src/reader/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -779,42 +779,66 @@ fn parse(
match key_type.as_ref() {
DataType::Int8 => Ok(Arc::new(
rows.iter()
.map(|row| row.get(i))
.map(|row| {
let s = row.get(i);
(!null_regex.is_null(s)).then_some(s)
})
.collect::<DictionaryArray<Int8Type>>(),
) as ArrayRef),
DataType::Int16 => Ok(Arc::new(
rows.iter()
.map(|row| row.get(i))
.map(|row| {
let s = row.get(i);
(!null_regex.is_null(s)).then_some(s)
})
.collect::<DictionaryArray<Int16Type>>(),
) as ArrayRef),
DataType::Int32 => Ok(Arc::new(
rows.iter()
.map(|row| row.get(i))
.map(|row| {
let s = row.get(i);
(!null_regex.is_null(s)).then_some(s)
})
.collect::<DictionaryArray<Int32Type>>(),
) as ArrayRef),
DataType::Int64 => Ok(Arc::new(
rows.iter()
.map(|row| row.get(i))
.map(|row| {
let s = row.get(i);
(!null_regex.is_null(s)).then_some(s)
})
.collect::<DictionaryArray<Int64Type>>(),
) as ArrayRef),
DataType::UInt8 => Ok(Arc::new(
rows.iter()
.map(|row| row.get(i))
.map(|row| {
let s = row.get(i);
(!null_regex.is_null(s)).then_some(s)
})
.collect::<DictionaryArray<UInt8Type>>(),
) as ArrayRef),
DataType::UInt16 => Ok(Arc::new(
rows.iter()
.map(|row| row.get(i))
.map(|row| {
let s = row.get(i);
(!null_regex.is_null(s)).then_some(s)
})
.collect::<DictionaryArray<UInt16Type>>(),
) as ArrayRef),
DataType::UInt32 => Ok(Arc::new(
rows.iter()
.map(|row| row.get(i))
.map(|row| {
let s = row.get(i);
(!null_regex.is_null(s)).then_some(s)
})
.collect::<DictionaryArray<UInt32Type>>(),
) as ArrayRef),
DataType::UInt64 => Ok(Arc::new(
rows.iter()
.map(|row| row.get(i))
.map(|row| {
let s = row.get(i);
(!null_regex.is_null(s)).then_some(s)
})
.collect::<DictionaryArray<UInt64Type>>(),
) as ArrayRef),
_ => Err(ArrowError::ParseError(format!(
Expand Down Expand Up @@ -1475,6 +1499,40 @@ mod tests {
assert_eq!(strings.value(29), "Uckfield, East Sussex, UK");
}

#[test]
fn test_csv_with_nullable_dictionary() {
let offset_type = vec![
DataType::Int8,
DataType::Int16,
DataType::Int32,
DataType::Int64,
DataType::UInt8,
DataType::UInt16,
DataType::UInt32,
DataType::UInt64,
];
for data_type in offset_type {
let file = File::open("test/data/dictionary_nullable_test.csv").unwrap();
let dictionary_type =
DataType::Dictionary(Box::new(data_type), Box::new(DataType::Utf8));
let schema = Arc::new(Schema::new(vec![
Field::new("id", DataType::Utf8, false),
Field::new("name", dictionary_type.clone(), true),
]));

let mut csv = ReaderBuilder::new(schema)
.build(file.try_clone().unwrap())
.unwrap();

let batch = csv.next().unwrap().unwrap();
assert_eq!(3, batch.num_rows());
assert_eq!(2, batch.num_columns());

let names = arrow_cast::cast(batch.column(1), &dictionary_type).unwrap();
assert!(!names.is_null(2));
assert!(names.is_null(1));
}
}
#[test]
fn test_nulls() {
let schema = Arc::new(Schema::new(vec![
Expand Down
3 changes: 3 additions & 0 deletions arrow-csv/test/data/dictionary_nullable_test.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
id,name
1,
2,bob
Loading