Skip to content

Add helper functions to create LogicalType struct variants #9996

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

Merged
alamb merged 7 commits into from
May 20, 2026
Merged

Add helper functions to create LogicalType struct variants #9996

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
3597c16
add helper functions for complex logical types
etseidl May 18, 2026
dbf0860
format
etseidl May 18, 2026
8b41623
fix some tests to match original
etseidl May 18, 2026
c3cf5d2
add missing test
etseidl May 18, 2026
8171989
rename int as integer to be consistent with other helpers
etseidl May 18, 2026
5fbd22d
change parquet_derive too
etseidl May 18, 2026
48fae3e
add docstrings
etseidl May 18, 2026
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
18 changes: 8 additions & 10 deletions parquet/src/arrow/schema/extension.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,9 +112,7 @@ pub(crate) fn has_extension_type(parquet_type: &Type) -> bool {
pub(crate) fn logical_type_for_struct(field: &Field) -> Option<LogicalType> {
use parquet_variant_compute::VariantType;
if field.has_valid_extension_type::<VariantType>() {
Some(LogicalType::Variant {
specification_version: None,
})
Some(LogicalType::variant(None))
} else {
None
}
Expand Down Expand Up @@ -167,13 +165,13 @@ pub(crate) fn logical_type_for_binary(field: &Field) -> Option<LogicalType> {
match field.extension_type_name() {
Some(n) if n == WkbType::NAME => match field.try_extension_type::<WkbType>() {
Ok(wkb_type) => match wkb_type.metadata().type_hint() {
WkbTypeHint::Geometry => Some(LogicalType::Geometry {
crs: wkb_type.metadata().crs.as_ref().map(|c| c.to_string()),
}),
WkbTypeHint::Geography => Some(LogicalType::Geography {
crs: wkb_type.metadata().crs.as_ref().map(|c| c.to_string()),
algorithm: wkb_type.metadata().algorithm.map(|a| a.into()),
}),
WkbTypeHint::Geometry => Some(LogicalType::geometry(
wkb_type.metadata().crs.as_ref().map(|c| c.to_string()),
)),
WkbTypeHint::Geography => Some(LogicalType::geography(
wkb_type.metadata().crs.as_ref().map(|c| c.to_string()),
wkb_type.metadata().algorithm.map(|a| a.into()),
)),
},
Err(_e) => None,
},
Expand Down
59 changes: 19 additions & 40 deletions parquet/src/arrow/schema/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -556,18 +556,12 @@ fn arrow_to_parquet_type(field: &Field, coerce_types: bool) -> Result<Type> {
.with_id(id)
.build(),
DataType::Int8 => Type::primitive_type_builder(name, PhysicalType::INT32)
.with_logical_type(Some(LogicalType::Integer {
bit_width: 8,
is_signed: true,
}))
.with_logical_type(Some(LogicalType::integer(8, true)))
.with_repetition(repetition)
.with_id(id)
.build(),
DataType::Int16 => Type::primitive_type_builder(name, PhysicalType::INT32)
.with_logical_type(Some(LogicalType::Integer {
bit_width: 16,
is_signed: true,
}))
.with_logical_type(Some(LogicalType::integer(16, true)))
.with_repetition(repetition)
.with_id(id)
.build(),
Expand All @@ -580,34 +574,22 @@ fn arrow_to_parquet_type(field: &Field, coerce_types: bool) -> Result<Type> {
.with_id(id)
.build(),
DataType::UInt8 => Type::primitive_type_builder(name, PhysicalType::INT32)
.with_logical_type(Some(LogicalType::Integer {
bit_width: 8,
is_signed: false,
}))
.with_logical_type(Some(LogicalType::integer(8, false)))
.with_repetition(repetition)
.with_id(id)
.build(),
DataType::UInt16 => Type::primitive_type_builder(name, PhysicalType::INT32)
.with_logical_type(Some(LogicalType::Integer {
bit_width: 16,
is_signed: false,
}))
.with_logical_type(Some(LogicalType::integer(16, false)))
.with_repetition(repetition)
.with_id(id)
.build(),
DataType::UInt32 => Type::primitive_type_builder(name, PhysicalType::INT32)
.with_logical_type(Some(LogicalType::Integer {
bit_width: 32,
is_signed: false,
}))
.with_logical_type(Some(LogicalType::integer(32, false)))
.with_repetition(repetition)
.with_id(id)
.build(),
DataType::UInt64 => Type::primitive_type_builder(name, PhysicalType::INT64)
.with_logical_type(Some(LogicalType::Integer {
bit_width: 64,
is_signed: false,
}))
.with_logical_type(Some(LogicalType::integer(64, false)))
.with_repetition(repetition)
.with_id(id)
.build(),
Expand All @@ -634,16 +616,16 @@ fn arrow_to_parquet_type(field: &Field, coerce_types: bool) -> Result<Type> {
}
DataType::Timestamp(time_unit, tz) => {
Type::primitive_type_builder(name, PhysicalType::INT64)
.with_logical_type(Some(LogicalType::Timestamp {
.with_logical_type(Some(LogicalType::timestamp(
// If timezone set, values are normalized to UTC timezone
is_adjusted_to_u_t_c: matches!(tz, Some(z) if !z.as_ref().is_empty()),
unit: match time_unit {
matches!(tz, Some(z) if !z.as_ref().is_empty()),
match time_unit {
TimeUnit::Second => unreachable!(),
TimeUnit::Millisecond => ParquetTimeUnit::MILLIS,
TimeUnit::Microsecond => ParquetTimeUnit::MICROS,
TimeUnit::Nanosecond => ParquetTimeUnit::NANOS,
},
}))
)))
.with_repetition(repetition)
.with_id(id)
.build()
Expand Down Expand Up @@ -675,25 +657,25 @@ fn arrow_to_parquet_type(field: &Field, coerce_types: bool) -> Result<Type> {
.build()
}
DataType::Time32(unit) => Type::primitive_type_builder(name, PhysicalType::INT32)
.with_logical_type(Some(LogicalType::Time {
is_adjusted_to_u_t_c: field.metadata().contains_key("adjusted_to_utc"),
unit: match unit {
.with_logical_type(Some(LogicalType::time(
field.metadata().contains_key("adjusted_to_utc"),
match unit {
TimeUnit::Millisecond => ParquetTimeUnit::MILLIS,
u => unreachable!("Invalid unit for Time32: {:?}", u),
},
}))
)))
.with_repetition(repetition)
.with_id(id)
.build(),
DataType::Time64(unit) => Type::primitive_type_builder(name, PhysicalType::INT64)
.with_logical_type(Some(LogicalType::Time {
is_adjusted_to_u_t_c: field.metadata().contains_key("adjusted_to_utc"),
unit: match unit {
.with_logical_type(Some(LogicalType::time(
field.metadata().contains_key("adjusted_to_utc"),
match unit {
TimeUnit::Microsecond => ParquetTimeUnit::MICROS,
TimeUnit::Nanosecond => ParquetTimeUnit::NANOS,
u => unreachable!("Invalid unit for Time64: {:?}", u),
},
}))
)))
.with_repetition(repetition)
.with_id(id)
.build(),
Expand Down Expand Up @@ -749,10 +731,7 @@ fn arrow_to_parquet_type(field: &Field, coerce_types: bool) -> Result<Type> {
.with_repetition(repetition)
.with_id(id)
.with_length(length)
.with_logical_type(Some(LogicalType::Decimal {
scale: *scale as i32,
precision: *precision as i32,
}))
.with_logical_type(Some(LogicalType::decimal(*scale as i32, *precision as i32)))
.with_precision(*precision as i32)
.with_scale(*scale as i32)
.build()
Expand Down
Loading
Loading