Skip to content

Add full_table mode for single-relation Iceberg loading #253

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
hbarthels wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Add full_table mode for single-relation Iceberg loading #253

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
1e56096
Add full_table mode for Iceberg loading (single-relation output)
hbarthels Jun 1, 2026
6e57d54
Remove comments from IcebergTarget fields in logic.proto; regenerate
hbarthels Jun 2, 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
27 changes: 19 additions & 8 deletions meta/src/meta/grammar.y
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,6 +123,7 @@
%nonterm iceberg_catalog_config_scope String
%nonterm iceberg_catalog_uri String
%nonterm iceberg_data logic.IcebergData
%nonterm full_table logic.IcebergTarget
%nonterm iceberg_from_snapshot String
%nonterm iceberg_locator logic.IcebergLocator
%nonterm iceberg_locator_namespace Sequence[String]
Expand Down Expand Up @@ -1225,16 +1226,24 @@ iceberg_to_snapshot
construct: $$ = $3
deconstruct: $3: String = $$

full_table
: "(" "full_table" relation_id "[" type* "]" ")"
construct: $$ = logic.IcebergTarget(target_id=$3, types=$5)
deconstruct:
$3: logic.RelationId = $$.target_id
$5: Sequence[logic.Type] = $$.types

iceberg_data
: "(" "iceberg_data" iceberg_locator iceberg_catalog_config gnf_columns iceberg_from_snapshot? iceberg_to_snapshot? boolean_value ")"
construct: $$ = construct_iceberg_data($3, $4, $5, $6, $7, $8)
: "(" "iceberg_data" iceberg_locator iceberg_catalog_config gnf_columns? full_table? iceberg_from_snapshot? iceberg_to_snapshot? boolean_value ")"
construct: $$ = construct_iceberg_data($3, $4, $5, $6, $7, $8, $9)
deconstruct:
$3: logic.IcebergLocator = $$.locator
$4: logic.IcebergCatalogConfig = $$.config
$5: Sequence[logic.GNFColumn] = $$.columns
$6: Optional[String] = deconstruct_iceberg_data_from_snapshot_optional($$)
$7: Optional[String] = deconstruct_iceberg_data_to_snapshot_optional($$)
$8: Boolean = $$.returns_delta
$5: Optional[Sequence[logic.GNFColumn]] = $$.columns if not builtin.is_empty($$.columns) else None
$6: Optional[logic.IcebergTarget] = $$.target if builtin.has_proto_field($$, 'target') else None
$7: Optional[String] = deconstruct_iceberg_data_from_snapshot_optional($$)
$8: Optional[String] = deconstruct_iceberg_data_to_snapshot_optional($$)
$9: Boolean = $$.returns_delta

undefine
: "(" "undefine" fragment_id ")"
Expand Down Expand Up @@ -1724,15 +1733,17 @@ def deconstruct_iceberg_catalog_config_scope_optional(msg: logic.IcebergCatalogC
def construct_iceberg_data(
locator: logic.IcebergLocator,
config: logic.IcebergCatalogConfig,
columns: Sequence[logic.GNFColumn],
columns_opt: Optional[Sequence[logic.GNFColumn]],
target_opt: Optional[logic.IcebergTarget],
from_snapshot_opt: Optional[String],
to_snapshot_opt: Optional[String],
returns_delta: Boolean,
) -> logic.IcebergData:
return logic.IcebergData(
locator=locator,
config=config,
columns=columns,
columns=builtin.unwrap_option_or(columns_opt, list[logic.GNFColumn]()),
target=target_opt,
from_snapshot=builtin.some(builtin.unwrap_option_or(from_snapshot_opt, "")),
to_snapshot=builtin.some(builtin.unwrap_option_or(to_snapshot_opt, "")),
returns_delta=returns_delta,
Expand Down
6 changes: 6 additions & 0 deletions proto/relationalai/lqp/v1/logic.proto
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -316,13 +316,19 @@ message CSVConfig {
int64 partition_size_mb = 12;
}

message IcebergTarget {
RelationId target_id = 1;
repeated Type types = 2;
}

message IcebergData {
IcebergLocator locator = 1;
IcebergCatalogConfig config = 2;
repeated GNFColumn columns = 3;
optional string from_snapshot = 4;
optional string to_snapshot = 5;
bool returns_delta = 6;
optional IcebergTarget target = 7;
}

message IcebergLocator {
Expand Down
Loading
Loading