Skip to content

Improve pg_catalog type mapping #305

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

Open
mjgarton wants to merge 2 commits into
base: master
Choose a base branch
from
+20 −27
Open

Improve pg_catalog type mapping #305

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
fcf6aca
Improve pg_catalog type mapping
mjgarton Mar 9, 2026
626d704
Revert back to signed ints for iod
mjgarton Mar 10, 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
1 change: 1 addition & 0 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions datafusion-pg-catalog/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ include = [
[dependencies]
async-trait = "0.1"
datafusion = { workspace = true, features = ["sql"] }
arrow-pg = { path = "../arrow-pg", version = "0.12.2", default-features = false, features = ["datafusion"] }
futures.workspace = true
log = "0.4"
postgres-types.workspace = true
Expand Down
45 changes: 18 additions & 27 deletions datafusion-pg-catalog/src/pg_catalog/pg_attribute.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ use datafusion::error::Result;
use datafusion::execution::{SendableRecordBatchStream, TaskContext};
use datafusion::physical_plan::stream::RecordBatchStreamAdapter;
use datafusion::physical_plan::streaming::PartitionStream;
use postgres_types::Oid;
use postgres_types::{Oid, Type};
use tokio::sync::RwLock;

use crate::pg_catalog::catalog_info::CatalogInfo;
Expand Down Expand Up @@ -141,7 +141,7 @@ impl<C: CatalogInfo> PgAttributeTable<C> {

attrelids.push(table_oid as i32);
attnames.push(field.name().clone());
atttypids.push(pg_type_oid);
atttypids.push(pg_type_oid as i32);
attstattargets.push(-1); // Default statistics target
attlens.push(type_len);
attnums.push(attnum);
Expand Down Expand Up @@ -211,31 +211,22 @@ impl<C: CatalogInfo> PgAttributeTable<C> {
}

/// Map DataFusion data types to PostgreSQL type information
fn datafusion_to_pg_type(data_type: &DataType) -> (i32, i16, bool, &'static str, &'static str) {
match data_type {
DataType::Boolean => (16, 1, true, "c", "p"), // bool
DataType::Int8 => (18, 1, true, "c", "p"), // char
DataType::Int16 => (21, 2, true, "s", "p"), // int2
DataType::Int32 => (23, 4, true, "i", "p"), // int4
DataType::Int64 => (20, 8, true, "d", "p"), // int8
DataType::UInt8 => (18, 2, true, "s", "p"), // char
DataType::UInt16 => (21, 4, true, "i", "p"), // int2
DataType::UInt32 => (23, 8, true, "d", "p"), // int4
DataType::UInt64 => (20, -1, false, "i", "m"), // int8
DataType::Float32 => (700, 4, true, "i", "p"), // float4
DataType::Float64 => (701, 8, true, "d", "p"), // float8
DataType::Utf8 => (25, -1, false, "i", "x"), // text
DataType::LargeUtf8 => (25, -1, false, "i", "x"), // text
DataType::Binary => (17, -1, false, "i", "x"), // bytea
DataType::LargeBinary => (17, -1, false, "i", "x"), // bytea
DataType::Date32 => (1082, 4, true, "i", "p"), // date
DataType::Date64 => (1082, 4, true, "i", "p"), // date
DataType::Time32(_) => (1083, 8, true, "d", "p"), // time
DataType::Time64(_) => (1083, 8, true, "d", "p"), // time
DataType::Timestamp(_, _) => (1114, 8, true, "d", "p"), // timestamp
DataType::Decimal128(_, _) => (1700, -1, false, "i", "m"), // numeric
DataType::Decimal256(_, _) => (1700, -1, false, "i", "m"), // numeric
_ => (25, -1, false, "i", "x"), // Default to text for unknown types
fn datafusion_to_pg_type(data_type: &DataType) -> (u32, i16, bool, &'static str, &'static str) {
match arrow_pg::datatypes::into_pg_type(data_type) {
Ok(t @ Type::BOOL) => (t.oid(), 1, true, "c", "p"),
Ok(t @ Type::CHAR) => (t.oid(), 1, true, "c", "p"),
Ok(t @ Type::INT2) => (t.oid(), 2, true, "s", "p"),
Ok(t @ Type::INT4) => (t.oid(), 4, true, "i", "p"),
Ok(t @ Type::INT8) => (t.oid(), 8, true, "d", "p"),
Ok(t @ Type::FLOAT4) => (t.oid(), 4, true, "i", "p"),
Ok(t @ Type::FLOAT8) => (t.oid(), 8, true, "d", "p"),
Ok(t @ Type::TEXT) => (t.oid(), -1, false, "i", "x"),
Ok(t @ Type::BYTEA) => (t.oid(), -1, false, "i", "x"),
Ok(t @ Type::DATE) => (t.oid(), 4, true, "i", "p"),
Ok(t @ Type::TIME) => (t.oid(), 8, true, "d", "p"),
Ok(t @ Type::TIMESTAMP) => (t.oid(), 8, true, "d", "p"),
Ok(t @ Type::NUMERIC) => (t.oid(), -1, false, "i", "m"),
_ => (Type::TEXT.oid(), -1, false, "i", "x"), // Default to text for unknown types
}
}
}
Expand Down
Loading