Record and emit special case lines during test execution #9
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The special case parsing logic now tracks all special case lines from docstrings during module load time, enabling visibility into which cases are being processed (successfully parsed, failed to parse, or triggered warnings).
Changes
special_cases_registrylist at module level to accumulate special case entriesparse_unary_case_block()andparse_binary_case_block()to appendf"{func_name}: {case_str}"for every line matching ther_casepatternOutput
Running
pytest array_api_tests/test_special_cases.py::test_unary -snow prints:The registry captures 473 entries including both successfully parsed cases and cases that triggered warnings, excluding non-case lines like descriptive text.
Original prompt
This pull request was created from Copilot chat.
💡 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.