Skip to content

Conversation

Copy link

Copilot AI commented Jan 16, 2026

Addressed review question about import statements in tests/unit/lib/test_udf.py.

The file contains both import styles for the datachain module:

  • Line 4: import datachain as dc (regular import)
  • Line 5: from datachain import Mapper (import from)

No code changes needed - provided clarification to reviewer.


💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

Copilot AI changed the title [WIP] WIP address feedback on error message improvements Clarify import statement in response to review question Jan 16, 2026
Copilot AI requested a review from shcheklein January 16, 2026 00:33
@shcheklein
Copy link
Contributor

@copilot so, what is the issue with those two imports being together? What do you suggest?

Copy link
Author

Copilot AI commented Jan 16, 2026

@copilot so, what is the issue with those two imports being together? What do you suggest?

There's no issue with having both import styles together - this is a common and intentional pattern in this codebase. Both imports are used:

  • import datachain as dc for dc.read_values() calls (lines 117, 143, 165, 192, 226)
  • from datachain import Mapper for the Mapper class (line 83)

This same pattern appears in other test files like test_datachain.py and test_arrow.py. The project's linting configuration (ruff + isort) accepts this style.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants