Skip to content

fix: Fix miner path #749

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
wants to merge 3 commits into from
Closed

fix: Fix miner path #749

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4f8a2c5
chore: fix-miner-path
abhishekagrawal-atlan Oct 1, 2025
8fa4df1
fix: pre-commit
abhishekagrawal-atlan Oct 1, 2025
41abcc7
fix: path_gen logic to take into account start and end_marker
abhishekagrawal-atlan Oct 3, 2025
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
3 changes: 3 additions & 0 deletions application_sdk/activities/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -195,6 +195,9 @@ async def get_workflow_args(
workflow_args["output_prefix"] = workflow_args.get(
"output_prefix", TEMPORARY_PATH
)

workflow_args["parent_run_id"] = workflow_args.get("workflow_run_id", None)

workflow_args["output_path"] = os.path.join(
workflow_args["output_prefix"], build_output_path()
)
Expand Down
6 changes: 6 additions & 0 deletions application_sdk/activities/query_extraction/sql.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -209,6 +209,12 @@ async def fetch_queries(
)
sql_input = await sql_input.get_dataframe()

parent_run_id = workflow_args.get("parent_run_id", None)
if parent_run_id:
workflow_args["output_path"] = os.path.join(
os.path.dirname(workflow_args["output_path"]), parent_run_id
)

raw_output = ParquetOutput(
output_path=workflow_args["output_path"],
output_suffix="raw/query",
Expand Down
9 changes: 6 additions & 3 deletions application_sdk/outputs/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,9 +109,12 @@ def path_gen(
Returns:
str: Generated file path for the chunk.
"""
# For Query Extraction - use start and end markers without chunk count
# For Query Extraction - use start and end markers
if start_marker and end_marker:
return f"{start_marker}_{end_marker}{self._EXTENSION}"
if chunk_count is None:
return f"atlan_raw_mined_{str(start_marker)}_{str(chunk_part)}{self._EXTENSION}"
else:
return f"atlan_raw_mined_{str(start_marker)}_{str(chunk_count)}_{str(chunk_part)}{self._EXTENSION}"

# For regular chunking - include chunk count
if chunk_count is None:
Expand Down Expand Up @@ -213,7 +216,7 @@ async def write_dataframe(self, dataframe: "pd.DataFrame"):
self.current_buffer_size_bytes + chunk_size_bytes
> self.max_file_size_bytes
):
output_file_name = f"{self.output_path}/{self.path_gen(self.chunk_count, self.chunk_part)}"
output_file_name = f"{self.output_path}/{self.path_gen(self.chunk_count, self.chunk_part, self.start_marker, self.end_marker)}"
if os.path.exists(output_file_name):
await self._upload_file(output_file_name)
self.chunk_part += 1
Expand Down
Loading