Skip to content

fix: escape single quotes in the seed dataset SQL literal #1109

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

Closed
xubenqiang wants to merge 1 commit into from
Closed

fix: escape single quotes in the seed dataset SQL literal #1109

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
17 changes: 11 additions & 6 deletions packages/data-designer-engine/src/data_designer/engine/resources/seed_reader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,11 @@
logger = logging.getLogger(__name__)


def _as_sql_literal(value: str) -> str:
"""Return ``value`` as a DuckDB string literal, escaping embedded single quotes."""
return "'" + value.replace("'", "''") + "'"


class SeedReaderError(DataDesignerError): ...


Expand Down Expand Up @@ -88,7 +93,7 @@ def create_context(self, *, runtime_path: str) -> SeedReaderFileSystemContext:
def ensure_root_exists(self, *, runtime_path: str) -> None:
resolved_root_path = Path(runtime_path).expanduser().resolve()
if not resolved_root_path.is_dir():
raise SeedReaderConfigError(f"🛑 Seed source directory '{resolved_root_path}' does not exist.")
raise SeedReaderConfigError(f"馃洃 Seed source directory '{resolved_root_path}' does not exist.")

@greptile-apps greptile-apps Bot Oct 28, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Error messages show garbled text

The two error messages replace 🛑 with the garbled text 馃洃. Users see these characters when a seed directory is missing or an agent rollout reader gets a non-local path. Restore 🛑 here and in the message at line 783.

Prompt To Fix With AI 
This is a comment left during a code review.
Path: packages/data-designer-engine/src/data_designer/engine/resources/seed_reader.py
Line: 96

Comment:
**Error messages show garbled text**

The two error messages replace `🛑` with the garbled text `馃洃`. Users see these characters when a seed directory is missing or an agent rollout reader gets a non-local path. Restore `🛑` here and in the message at line 783.

---

For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.



class SeedReaderBatch(Protocol):
Expand Down Expand Up @@ -298,7 +303,7 @@ def create_dataframe_duckdb_connection(
def get_seed_dataset_size(self) -> int:
self._ensure_attached()
conn = self._get_duckdb_connection()
return conn.execute(f"SELECT COUNT(*) FROM '{self.get_dataset_uri()}'").fetchone()[0]
return conn.execute(f"SELECT COUNT(*) FROM {_as_sql_literal(self.get_dataset_uri())}").fetchone()[0]

def create_batch_reader(
self,
Expand Down Expand Up @@ -349,7 +354,7 @@ def get_column_names(self) -> list[str]:
"""Returns the seed dataset's column names"""
self._ensure_attached()
conn = self._get_duckdb_connection()
describe_query = f"DESCRIBE SELECT * FROM '{self.get_dataset_uri()}'"
describe_query = f"DESCRIBE SELECT * FROM {_as_sql_literal(self.get_dataset_uri())}"
column_descriptions = conn.execute(describe_query).fetchall()
return [col[0] for col in column_descriptions]

Expand Down Expand Up @@ -378,12 +383,12 @@ def build_dataset_read_query(
offset_value = index_range.start
limit_value = index_range.end - index_range.start + 1
read_query = f"""
SELECT * FROM '{dataset_uri}'
SELECT * FROM {_as_sql_literal(dataset_uri)}
LIMIT {limit_value} OFFSET {offset_value}
"""
return f"SELECT * FROM ({read_query}){shuffle_query}"

return f"SELECT * FROM '{dataset_uri}'{shuffle_query}"
return f"SELECT * FROM {_as_sql_literal(dataset_uri)}{shuffle_query}"

def get_seed_type(self) -> str:
"""Return the seed_type of the source class this reader is generic over."""
Expand Down Expand Up @@ -775,7 +780,7 @@ def _get_parse_context(self, context: SeedReaderFileSystemContext) -> AgentRollo
root_path = context.root_path
if not isinstance(root_path, Path):
raise SeedReaderConfigError(
f"🛑 Agent rollout seed readers require a local filesystem, but got non-local root path "
f"馃洃 Agent rollout seed readers require a local filesystem, but got non-local root path "
f"{root_path!r} ({type(root_path).__name__})."
)
handler = self.get_format_handler()
Expand Down
13 changes: 13 additions & 0 deletions packages/data-designer-engine/tests/engine/resources/test_seed_reader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -476,6 +476,19 @@ def test_seed_reader_requires_attach_before_use() -> None:
reader.get_seed_dataset_size()


def test_local_file_seed_reader_escapes_single_quotes_in_path(tmp_path: Path) -> None:
quoted_dir = tmp_path / "o'brien"
quoted_dir.mkdir()
seed_path = quoted_dir / "seed.parquet"
lazy.pd.DataFrame({"name": ["a", "b"]}).to_parquet(seed_path)

reader = LocalFileSeedReader()
reader.attach(LocalFileSeedSource(path=str(seed_path)), PlaintextResolver())

assert reader.get_seed_dataset_size() == 2
assert reader.get_column_names() == ["name"]


def test_plugin_style_filesystem_seed_reader_needs_only_manifest_builder(tmp_path: Path) -> None:
(tmp_path / "alpha.txt").write_text("alpha", encoding="utf-8")
(tmp_path / "nested").mkdir()
Expand Down
Loading