Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
8 changes: 5 additions & 3 deletions src/Storages/ObjectStorage/Utils.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -342,9 +342,11 @@ std::pair<DB::ObjectStoragePtr, std::string> resolveObjectStorageForPath(
normalized_path = "s3://" + target_decomposed.authority + "/" + target_decomposed.key;
}
S3::URI s3_uri(normalized_path);

std::string key_to_use = s3_uri.key;


// Use key (parsed without URI decoding) so that percent-encoded
// characters in object keys (e.g. %2F in Iceberg partition paths) are preserved.
std::string key_to_use = target_decomposed.key;

bool use_base_storage = false;
if (base_storage->getType() == ObjectStorageType::S3)
{
Expand Down
46 changes: 46 additions & 0 deletions tests/integration/test_database_iceberg/test.py
Original file line number Diff line number Diff line change
Expand Up @@ -668,6 +668,52 @@ def test_table_with_slash(started_cluster):
assert node.query(f"SELECT * FROM {CATALOG_NAME}.`{root_namespace}.{table_encoded_name}`") == "\\N\tAAPL\t193.24\t193.31\t('bot')\n"


def test_partition_value_with_slash(started_cluster):
"""Partition value containing '/' produces object keys with %2F; reading must preserve encoding."""
node = started_cluster.instances["node1"]

test_ref = f"test_partition_slash_{uuid.uuid4()}"
table_name = f"{test_ref}_table"
root_namespace = f"{test_ref}_namespace"

# Partition by symbol (string) so partition value "us/west" becomes path segment symbol=us%2Fwest
partition_spec = PartitionSpec(
PartitionField(
source_id=2, field_id=1000, transform=IdentityTransform(), name="symbol"
)
)
schema = DEFAULT_SCHEMA

catalog = load_catalog_impl(started_cluster)
catalog.create_namespace(root_namespace)

table = create_table(
catalog,
root_namespace,
table_name,
schema,
partition_spec=partition_spec,
sort_order=DEFAULT_SORT_ORDER,
)

# Write a row with partition value containing slash (path will have %2F in S3 key)
data = [
{
"datetime": datetime.now(),
"symbol": "us/west",
"bid": 100.0,
"ask": 101.0,
"details": {"created_by": "test"},
}
]
df = pa.Table.from_pylist(data)
table.append(df)

create_clickhouse_iceberg_database(started_cluster, node, CATALOG_NAME)
assert 1 == int(node.query(f"SELECT count() FROM {CATALOG_NAME}.`{root_namespace}.{table_name}`"))
assert "us/west" in node.query(f"SELECT symbol FROM {CATALOG_NAME}.`{root_namespace}.{table_name}`")


def test_cluster_joins(started_cluster):
node = started_cluster.instances["node1"]

Expand Down
Loading