feat: added wrapper annotation to workflow catalog; closes #42 #56
Conversation
📝 Walkthrough""" WalkthroughThe changes introduce functionality to extract and display "wrapper" metadata from Snakemake workflow files. A new function parses wrapper usage, and this information is collected, stored, and rendered in workflow catalog pages. Modifications span data extraction, storage in repository objects, and conditional rendering in documentation templates. Changes
Sequence Diagram(s)sequenceDiagram
participant CatalogGen as generate-catalog.py
participant Common as common.py
participant RepoObj as Repo class
participant BuildPages as build_wf_pages.py
participant Template as workflow_page.md
CatalogGen->>Common: get_wrappers(smkfile_content)
Common-->>CatalogGen: {wrapper_name: {name, version, url}, ...}
CatalogGen->>RepoObj: Repo(..., wrappers=wrappers_dict)
BuildPages->>RepoObj: Access wrappers via repo.get("wrappers", {})
BuildPages->>Template: Render page with wrappers metadata
Template-->>User: Display wrappers as badges (if present)
Estimated code review effort2 (~20 minutes) Suggested reviewers
📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
✨ Finishing Touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (2)
scripts/common.py (1)
88-105: Consider improving regex pattern and error handling.The function implementation looks good overall, but there are a few potential improvements:
- The regex pattern
r"\n\s*wrapper:\s*(.+)\n"requires newlines before and after the wrapper declaration, which might miss wrappers at the beginning or end of files.- The hard-coded URL pattern assumes a specific documentation structure.
Consider applying this improvement to handle edge cases:
-def get_wrappers(smkfile): +def get_wrappers(smkfile): + # Ensure the content has leading/trailing newlines for consistent regex matching + smkfile = f"\n{smkfile}\n" wrappers = {} for match in re.finditer(r"\n\s*wrapper:\s*(.+)\n", smkfile):This ensures wrappers at the start or end of files are properly detected.
scripts/generate-catalog.py (1)
295-307: Good implementation with minor improvement suggestions.The wrapper extraction logic is well-implemented with proper error handling and merging of results from multiple files.
Consider making the exception handling more specific:
- except Exception as e: + except (IOError, OSError, UnicodeDecodeError) as e:This catches the most likely file reading errors while avoiding overly broad exception handling.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
scripts/common.py(2 hunks)scripts/generate-catalog.py(6 hunks)source/_templates/workflow_page.md(1 hunks)source/build_wf_pages.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
**/*.py
Instructions used from:
Sources:
⚙️ CodeRabbit Configuration File
🧠 Learnings (3)
📓 Common learnings
Learnt from: m-jahn
PR: snakemake/snakemake-workflow-catalog#50
File: topics.json:0-0
Timestamp: 2025-06-10T12:10:20.483Z
Learning: In the snakemake-workflow-catalog project, m-jahn prefers to allow cross-topic keyword mappings in topics.json, where keywords can appear in multiple topic categories. This design decision enables workflows to be discoverable under all relevant topic areas, improving user experience even though it means some workflows will be categorized under multiple topics.
source/build_wf_pages.py (1)
Learnt from: m-jahn
PR: snakemake/snakemake-workflow-catalog#33
File: source/build_wf_tables.py:51-51
Timestamp: 2025-03-14T15:04:47.868Z
Learning: In the build_wf_tables.py file, the repository list is expected to never be empty during normal operation, and an empty list would indicate an upstream problem with repository data collection that should be addressed separately.
scripts/generate-catalog.py (1)
Learnt from: m-jahn
PR: snakemake/snakemake-workflow-catalog#33
File: source/build_wf_tables.py:51-51
Timestamp: 2025-03-14T15:04:47.868Z
Learning: In the build_wf_tables.py file, the repository list is expected to never be empty during normal operation, and an empty list would indicate an upstream problem with repository data collection that should be addressed separately.
🧬 Code Graph Analysis (1)
scripts/generate-catalog.py (1)
scripts/common.py (1)
get_wrappers(88-105)
🪛 Ruff (0.12.2)
scripts/generate-catalog.py
200-200: Function definition does not bind loop variable tarball_url
(B023)
🔇 Additional comments (7)
scripts/common.py (1)
7-7: LGTM: Import added for regex functionality.The
remodule import is correctly added to support the newget_wrappersfunction.source/build_wf_pages.py (1)
75-75: LGTM: Wrappers data integration follows existing patterns.The addition of wrappers data to the workflow page generation is implemented correctly, using defensive programming with
.get()and an empty dictionary default.source/_templates/workflow_page.md (2)
43-48: LGTM: Topics section properly conditionally rendered.The conditional rendering for topics badges is implemented correctly, preventing empty sections when no topics exist.
51-56: LGTM: Wrappers section well-implemented with linked badges.The wrappers section is properly implemented with:
- Conditional rendering to avoid empty sections
- Linked badges using
bdg-link-secondarywith documentation URLs- Proper access to nested dictionary structure for wrapper metadata
scripts/generate-catalog.py (3)
20-20: LGTM: Import added for wrapper extraction.The import of
get_wrappersfrom the common module is correct and necessary for the new functionality.
59-59: LGTM: Repo class properly extended with wrappers support.The
Repoclass correctly adds thewrappersparameter to the constructor and stores it as an instance attribute, following the existing pattern.Also applies to: 71-71
319-319: LGTM: Wrappers data properly passed to Repo constructor.The wrappers data is correctly passed to the
Repoconstructor, completing the integration of wrapper functionality.
|
example workflow page with new links to wrappers in the center. |
There was a problem hiding this comment.
This is a really cool idea, great to have those linkouts in the snakemake workflow catalog. I have two parsing / check questions.
And I guess a comment on how the URLs will not match older wrapper versions, but we probably shouldn't try to fix this over here, but rather in the wrapper catalog docs...
|
Hi David @dlaehnemann, good comments! I will check. |
wrapperson the individual workflow pageSummary by CodeRabbit