Skip to content

fix(spec): tolerate DuckDB manifest entry schemas #2791

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
fm100 wants to merge 1 commit into
base: main
Choose a base branch
from
+99 −31
Open

fix(spec): tolerate DuckDB manifest entry schemas #2791

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: 43 additions & 31 deletions crates/iceberg/src/spec/manifest/metadata.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,21 +44,6 @@ pub struct ManifestMetadata {
impl ManifestMetadata {
/// Parse from metadata in avro file.
pub fn parse(meta: &HashMap<String, Vec<u8>>) -> Result<Self> {
let schema = Arc::new({
let bs = meta.get("schema").ok_or_else(|| {
Error::new(
ErrorKind::DataInvalid,
"schema is required in manifest metadata but not found",
)
})?;
serde_json::from_slice::<Schema>(bs).map_err(|err| {
Error::new(
ErrorKind::DataInvalid,
"Fail to parse schema in manifest metadata",
)
.with_source(err)
})?
});
let schema_id: i32 = meta
.get("schema-id")
.map(|bs| {
Expand All @@ -72,22 +57,39 @@ impl ManifestMetadata {
})
.transpose()?
.unwrap_or(0);
let raw_schema = meta.get("schema").ok_or_else(|| {
Error::new(
ErrorKind::DataInvalid,
"schema is required in manifest metadata but not found",
)
})?;
let partition_fields = {
let bs = meta.get("partition-spec").ok_or_else(|| {
Error::new(
ErrorKind::DataInvalid,
"partition-spec is required in manifest metadata but not found",
)
})?;
serde_json::from_slice::<Vec<PartitionField>>(bs).map_err(|err| {
Error::new(
ErrorKind::DataInvalid,
"Fail to parse partition spec in manifest metadata",
)
.with_source(err)
})?
};
let schema = Arc::new(parse_manifest_table_schema(raw_schema).or_else(|err| {
if partition_fields.is_empty() {
// Some writers store the manifest-entry schema under the
// `schema` metadata key. For unpartitioned manifests we can
// still plan file scans; column bounds that require the table
// schema are ignored when their field ids cannot be resolved.
Schema::builder().with_schema_id(schema_id).build()
} else {
Err(err)
}
})?);
let partition_spec = {
let fields = {
let bs = meta.get("partition-spec").ok_or_else(|| {
Error::new(
ErrorKind::DataInvalid,
"partition-spec is required in manifest metadata but not found",
)
})?;
serde_json::from_slice::<Vec<PartitionField>>(bs).map_err(|err| {
Error::new(
ErrorKind::DataInvalid,
"Fail to parse partition spec in manifest metadata",
)
.with_source(err)
})?
};
let spec_id = meta
.get("partition-spec-id")
.map(|bs| {
Expand All @@ -103,7 +105,7 @@ impl ManifestMetadata {
.unwrap_or(0);
PartitionSpec::builder(schema.clone())
.with_spec_id(spec_id)
.add_unbound_fields(fields.into_iter().map(|f| f.into_unbound()))?
.add_unbound_fields(partition_fields.into_iter().map(|f| f.into_unbound()))?
.build()?
};
let format_version = if let Some(bs) = meta.get("format-version") {
Expand Down Expand Up @@ -157,3 +159,13 @@ impl ManifestMetadata {
&self.content
}
}

fn parse_manifest_table_schema(bs: &[u8]) -> Result<Schema> {
serde_json::from_slice::<Schema>(bs).map_err(|err| {
Error::new(
ErrorKind::DataInvalid,
"Fail to parse schema in manifest metadata",
)
.with_source(err)
})
}
56 changes: 56 additions & 0 deletions crates/iceberg/src/spec/manifest/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,6 +169,62 @@ mod tests {
use crate::io::FileIO;
use crate::spec::{Literal, NestedField, PrimitiveType, Struct, Transform, Type};

#[test]
fn test_manifest_metadata_with_manifest_entry_schema_for_unpartitioned_table() {
let mut meta = HashMap::new();
meta.insert("schema-id".to_string(), b"0".to_vec());
meta.insert("partition-spec".to_string(), b"[]".to_vec());
meta.insert("partition-spec-id".to_string(), b"0".to_vec());
meta.insert("format-version".to_string(), b"2".to_vec());
meta.insert("content".to_string(), b"data".to_vec());
meta.insert(
"schema".to_string(),
br#"{
"type": "struct",
"schema-id": 0,
"fields": [
{"id": 0, "name": "status", "required": true, "type": "int"},
{"id": 1, "name": "snapshot_id", "required": false, "type": "long"},
{
"id": 2,
"name": "data_file",
"required": true,
"type": {
"type": "struct",
"fields": [
{"id": 100, "name": "file_path", "required": true, "type": "string"},
{
"id": 125,
"name": "lower_bounds",
"required": false,
"type": {
"type": "array",
"items": {
"type": "record",
"name": "k126_k127",
"fields": [
{"name": "key", "type": "int", "id": 126},
{"name": "value", "type": "binary", "id": 127}
]
}
}
}
]
}
}
]
}"#
.to_vec(),
);

let metadata = ManifestMetadata::parse(&meta).unwrap();
assert_eq!(metadata.schema_id(), 0);
assert!(metadata.schema().as_struct().fields().is_empty());
assert!(metadata.partition_spec().fields().is_empty());
assert_eq!(metadata.format_version(), &FormatVersion::V2);
assert_eq!(metadata.content(), &ManifestContentType::Data);
}

#[tokio::test]
async fn test_parse_manifest_v2_unpartition() {
let schema = Arc::new(
Expand Down
Loading