Fixes #43: Update dependencies for mistune and pyyaml to restore benchmark functionality #45
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Outdated suggestions cannot be applied.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.
Pull Request Description
Summary
This pull request addresses the compatibility issues detailed in Issue #43, specifically regarding the benchmarks that were not functioning correctly with the current versions of
mistune
andpyyaml
.Changes Made
Code Updates:
yaml.load()
withyaml.safe_load()
inbenchmark.py
to ensure safety when using PyYAML version 6.0 and above. This change mitigates potential security risks associated with untrusted input.mistune
by changing from the deprecated constructormistune.Markdown()
tomistune.create_markdown()
to align with the API changes introduced inmistune
version 2.0 and later.Requirements Updates:
conda-requirements.txt
to specify:pyyaml >=6.0
: This ensures compatibility with the newer versions of PyYAML.mistune >=2.0
: This allows the usage of the latest features and fixes from mistune.condarecipe/meta.yaml
to reflect these same requirement changes, ensuring that the environment setup correctly installs the necessary versions of the libraries.Impact
These changes should resolve the compatibility issues and allow the benchmarks to run correctly with the most up-to-date versions of
mistune
andpyyaml
, ultimately improving the reliability and security of the codebase.Conclusion
By implementing these updates, we can ensure that users will no longer need to downgrade their
mistune
andpyyaml
packages to run the benchmarks effectively.Fixes #43.