Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
7 changes: 4 additions & 3 deletions datafusion/datasource-parquet/src/file_format.rs
Original file line number Diff line number Diff line change
Expand Up @@ -24,11 +24,12 @@ use std::sync::Arc;

// Re-export so the historical `file_format::*` paths still resolve.
#[expect(deprecated)]
pub use crate::schema_coercion::coerce_int96_to_resolution;
pub use crate::schema_coercion::{
Int96Coercer, apply_file_schema_type_coercions, coerce_file_schema_to_string_type,
coerce_file_schema_to_view_type, coerce_int96_to_resolution,
transform_binary_to_string, transform_schema_to_view,
Int96Coercer, apply_file_schema_type_coercions, transform_binary_to_string,
transform_schema_to_view,
};

pub use crate::sink::ParquetSink;

use arrow::datatypes::{Fields, Schema, SchemaRef};
Expand Down
6 changes: 3 additions & 3 deletions datafusion/datasource-parquet/src/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -55,10 +55,10 @@ pub use row_filter::build_row_filter;
pub use row_filter::can_expr_be_pushed_down_with_schemas;
pub use row_group_filter::RowGroupAccessPlanFilter;
#[expect(deprecated)]
pub use schema_coercion::coerce_int96_to_resolution;
pub use schema_coercion::{
Int96Coercer, apply_file_schema_type_coercions, coerce_file_schema_to_string_type,
coerce_file_schema_to_view_type, coerce_int96_to_resolution,
transform_binary_to_string, transform_schema_to_view,
Int96Coercer, apply_file_schema_type_coercions, transform_binary_to_string,
transform_schema_to_view,
};
pub use sink::ParquetSink;
pub use virtual_column::ParquetVirtualColumn;
Expand Down
112 changes: 0 additions & 112 deletions datafusion/datasource-parquet/src/schema_coercion.rs
Original file line number Diff line number Diff line change
Expand Up @@ -418,118 +418,6 @@ fn coerce_int96_to_resolution_impl(
Some(transformed_schema)
}

/// Coerces the file schema if the table schema uses a view type.
#[deprecated(
since = "47.0.0",
note = "Use `apply_file_schema_type_coercions` instead"
)]
pub fn coerce_file_schema_to_view_type(
table_schema: &Schema,
file_schema: &Schema,
) -> Option<Schema> {
let mut transform = false;
let table_fields: HashMap<_, _> = table_schema
.fields
.iter()
.map(|f| {
let dt = f.data_type();
if dt.equals_datatype(&DataType::Utf8View)
|| dt.equals_datatype(&DataType::BinaryView)
{
transform = true;
}
(f.name(), dt)
})
.collect();

if !transform {
return None;
}

let transformed_fields: Vec<Arc<Field>> = file_schema
.fields
.iter()
.map(
|field| match (table_fields.get(field.name()), field.data_type()) {
(Some(DataType::Utf8View), DataType::Utf8 | DataType::LargeUtf8) => {
field_with_new_type(field, DataType::Utf8View)
}
(
Some(DataType::BinaryView),
DataType::Binary | DataType::LargeBinary,
) => field_with_new_type(field, DataType::BinaryView),
_ => Arc::clone(field),
},
)
.collect();

Some(Schema::new_with_metadata(
transformed_fields,
file_schema.metadata.clone(),
))
}

/// If the table schema uses a string type, coerce the file schema to use a string type.
///
/// See [`ParquetFormat::binary_as_string`](crate::file_format::ParquetFormat::binary_as_string) for details
#[deprecated(
since = "47.0.0",
note = "Use `apply_file_schema_type_coercions` instead"
)]
pub fn coerce_file_schema_to_string_type(
table_schema: &Schema,
file_schema: &Schema,
) -> Option<Schema> {
let mut transform = false;
let table_fields: HashMap<_, _> = table_schema
.fields
.iter()
.map(|f| (f.name(), f.data_type()))
.collect();
let transformed_fields: Vec<Arc<Field>> = file_schema
.fields
.iter()
.map(
|field| match (table_fields.get(field.name()), field.data_type()) {
// table schema uses string type, coerce the file schema to use string type
(
Some(DataType::Utf8),
DataType::Binary | DataType::LargeBinary | DataType::BinaryView,
) => {
transform = true;
field_with_new_type(field, DataType::Utf8)
}
// table schema uses large string type, coerce the file schema to use large string type
(
Some(DataType::LargeUtf8),
DataType::Binary | DataType::LargeBinary | DataType::BinaryView,
) => {
transform = true;
field_with_new_type(field, DataType::LargeUtf8)
}
// table schema uses string view type, coerce the file schema to use view type
(
Some(DataType::Utf8View),
DataType::Binary | DataType::LargeBinary | DataType::BinaryView,
) => {
transform = true;
field_with_new_type(field, DataType::Utf8View)
}
_ => Arc::clone(field),
},
)
.collect();

if !transform {
None
} else {
Some(Schema::new_with_metadata(
transformed_fields,
file_schema.metadata.clone(),
))
}
}

/// Create a new field with the specified data type, copying the other
/// properties from the input field
fn field_with_new_type(field: &FieldRef, new_type: DataType) -> FieldRef {
Expand Down
Loading