🌐 AI搜索 & 代理 主页
Skip to content

Updated load_dataset to be resistant to bad columns #1511

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
SilasMarvin wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Updated load_dataset to be resistant to bad columns #1511

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
Updated load_dataset to be resistent to bad columns
  • Loading branch information
@SilasMarvin
SilasMarvin committed Jun 6, 2024
commit 600bbfe8541e68455479fbb0347f22b5840e3193
49 changes: 30 additions & 19 deletions pgml-extension/src/bindings/transformers/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -434,54 +434,65 @@ pub fn load_dataset(
Spi::run(&format!(r#"CREATE TABLE {table_name} ({column_types})"#))?;
let insert = format!(r#"INSERT INTO {table_name} ({column_names}) VALUES ({column_placeholders})"#);
for i in 0..num_rows {
let mut skip = false;
let mut row = Vec::with_capacity(num_cols);
for (name, values) in data {
let value = values
.as_array()
.ok_or_else(|| anyhow!("expected {values} to be an array"))?
.get(i)
.ok_or_else(|| anyhow!("invalid index {i} for {values}"))?;
match types
let (ty, datum) = match types
.get(name)
.ok_or_else(|| anyhow!("{types:?} expected to have key {name}"))?
.as_str()
.ok_or_else(|| anyhow!("json field {name} expected to be string"))?
{
"string" => row.push((
"string" => (
PgBuiltInOids::TEXTOID.oid(),
value
.as_str()
.ok_or_else(|| anyhow!("expected {value} to be string"))?
.into_datum(),
)),
"dict" | "list" => row.push((PgBuiltInOids::JSONBOID.oid(), JsonB(value.clone()).into_datum())),
"int64" | "int32" | "int16" => row.push((
.map(IntoDatum::into_datum)
.ok_or_else(|| anyhow!("expected column {name} with {value} to be string")),
),
"dict" | "list" => (PgBuiltInOids::JSONBOID.oid(), Ok(JsonB(value.clone()).into_datum())),
"int64" | "int32" | "int16" => (
PgBuiltInOids::INT8OID.oid(),
value
.as_i64()
.ok_or_else(|| anyhow!("expected {value} to be i64"))?
.into_datum(),
)),
"float64" | "float32" | "float16" => row.push((
.map(IntoDatum::into_datum)
.ok_or_else(|| anyhow!("expected column {name} with {value} to be i64")),
),
"float64" | "float32" | "float16" => (
PgBuiltInOids::FLOAT8OID.oid(),
value
.as_f64()
.ok_or_else(|| anyhow!("expected {value} to be f64"))?
.into_datum(),
)),
"bool" => row.push((
.map(IntoDatum::into_datum)
.ok_or_else(|| anyhow!("expected column {name} with {value} to be f64")),
),
"bool" => (
PgBuiltInOids::BOOLOID.oid(),
value
.as_bool()
.ok_or_else(|| anyhow!("expected {value} to be bool"))?
.into_datum(),
)),
.map(IntoDatum::into_datum)
.ok_or_else(|| anyhow!("expected column {name} with {value} to be bool")),
),
type_ => {
bail!("unhandled dataset value type while reading dataset: {value:?} {type_:?}")
}
};
match datum {
Ok(datum) => row.push((ty, datum)),
Err(e) => {
warning!("failed to convert dataset value to datum while reading dataset: {e}");
skip = true;
break;
}
}
}
Spi::run_with_args(&insert, Some(row))?
if !skip {
Spi::run_with_args(&insert, Some(row))?
}
}

Ok(num_rows)
Expand Down