libregrtest from 3.14.2 #6818

youknowone · 2026-01-20T15:03:09Z

Summary by CodeRabbit

Refactor
- Updated timeout parameter implementation to accept a broader range of numeric input values with enhanced validation and improved error handling.
- Added robust edge-case management for special input values including negative numbers and numeric overflow detection.
- All core functionality and existing error handling mechanisms remain unchanged.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

coderabbitai · 2026-01-20T15:03:19Z

📝 Walkthrough

Walkthrough

The WaitForSingleObject function signature in the Windows API wrapper was updated to accept i64 milliseconds instead of u32. Input validation logic was added to map negative values to INFINITE, reject values exceeding u32::MAX with an overflow error, and cast valid values to u32 for the underlying Windows API call.

Changes

Cohort / File(s)	Summary
WaitForSingleObject validation enhancement `crates/vm/src/stdlib/winapi.rs`	Updated function signature to accept `ms: i64` parameter. Added downstream validation: negative values map to INFINITE, overflow checking for values exceeding u32::MAX, and conditional casting to u32.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Poem

🐰 A timer once bound by thirty-two bits,
Now takes the full range—no more throwing fits!
We handle the negatives, check for the spills,
And cast safely down through validation's mills.
Windows will wait, and our logic rings true,
A hop toward robustness, through and through! 🐇

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Title check	⚠️ Warning	The PR title 'libregrtest from 3.14.2' does not align with the actual changes, which involve updating WaitForSingleObject function signature and adding input validation for the Windows API wrapper.	Update the PR title to accurately reflect the main change, such as 'Update WaitForSingleObject signature to accept i64 with validation' or 'Add input validation to WaitForSingleObject for ms parameter'.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

📝 Generate docstrings

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.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

coderabbitai

Actionable comments posted: 1

🤖 Fix all issues with AI agents

In `@crates/stdlib/src/gc.rs`:
- Around line 5-13: The module attribute definition for gc.garbage uses
#[pyattr] which recreates an empty list on each access; change the attribute to
#[pyattr(once)] on the garbage function so the created list is stored/persistent
across accesses (matching CPython semantics) — update the attribute macro on the
garbage function (fn garbage(vm: &VirtualMachine) -> PyObjectRef) to
#[pyattr(once)] so gc.garbage returns the same mutable list instance each time.

coderabbitai · 2026-01-20T16:30:02Z

crates/stdlib/src/gc.rs

+    use crate::vm::{PyObjectRef, PyResult, VirtualMachine, function::FuncArgs};
+
+    /// A list of objects which the collector found to be unreachable
+    /// but could not be freed. RustPython doesn't have cyclic GC,
+    /// so this is always an empty list.
+    #[pyattr]
+    fn garbage(vm: &VirtualMachine) -> PyObjectRef {
+        vm.ctx.new_list(vec![]).into()
+    }


⚠️ Potential issue | 🟠 Major

🧩 Analysis chain

🏁 Script executed:

# Find the #[pyattr] macro definition fd -t f "*.rs" | xargs rg -l "#\[pyattr\]" | head -5

Repository: RustPython/RustPython

Length of output: 515

🏁 Script executed:

# Search for how #[pyattr] macro is defined rg -t rs "macro.*pyattr|impl.*pyattr" --max-count=20

Repository: RustPython/RustPython

Length of output: 91

🏁 Script executed:

# Look at the gc module context around this function cat -n crates/stdlib/src/gc.rs

Repository: RustPython/RustPython

Length of output: 2976

🏁 Script executed:

# Check if there's any module initialization or attribute setting rg -t rs "garbage" crates/stdlib/src/gc.rs -B 5 -A 5

Repository: RustPython/RustPython

Length of output: 91

🏁 Script executed:

# Look for gc.garbage tests in CPython test suite or RustPython tests fd -t f "test_gc.py" -o "gc_test*" -o "*gc*.py" | xargs rg -l "garbage" 2>/dev/null | head -10

Repository: RustPython/RustPython

Length of output: 467

🏁 Script executed:

# Search for #[pyattr] macro definition and implementation fd "lib.rs" crates | xargs grep -l "pyattr" | head -5

Repository: RustPython/RustPython

Length of output: 144

🏁 Script executed:

# Look for pyattr macro in derive or macro crates fd "*.rs" crates | xargs grep -l "macro.*pyattr\|#\[proc_macro"

Repository: RustPython/RustPython

Length of output: 350

🏁 Script executed:

# Search for how pyattr is used elsewhere in stdlib fd "*.rs" crates/stdlib/src | xargs grep -A 3 "#\[pyattr\]" | head -40

Repository: RustPython/RustPython

Length of output: 348

🏁 Script executed:

# Check for any cached or persistent attribute patterns in the module system rg "pyattr|PyAttr" crates/pymodule --max-count=30 -B 2 -A 2

Repository: RustPython/RustPython

Length of output: 120

🏁 Script executed:

# Search test directory for gc.garbage related tests fd "test.*gc\|gc.*test" Lib/test 2>/dev/null || fd "test" Lib | grep gc

Repository: RustPython/RustPython

Length of output: 47

🏁 Script executed:

# Look directly for gc.garbage in test files rg "garbage" Lib/test -l 2>/dev/null | head -5

Repository: RustPython/RustPython

Length of output: 213

🏁 Script executed:

# Read the pyattr macro definition head -200 crates/derive/src/lib.rs | tail -100

Repository: RustPython/RustPython

Length of output: 3916

🏁 Script executed:

# Get more of the derive lib file to find pyattr rg "pyattr" crates/derive/src/lib.rs -B 5 -A 15 | head -80

Repository: RustPython/RustPython

Length of output: 2635

🏁 Script executed:

# Check how pyattr is used in hashlib rg "#\[pyattr\]" crates/stdlib/src/hashlib.rs -B 2 -A 5

Repository: RustPython/RustPython

Length of output: 725

🏁 Script executed:

# Check how pyattr is used in zlib rg "#\[pyattr\]" crates/stdlib/src/zlib.rs -B 2 -A 5

Repository: RustPython/RustPython

Length of output: 1542

🏁 Script executed:

# Search for pyattr in entire codebase with more context rg "pyattr" --max-count=50 -B 3 -A 3 crates

Repository: RustPython/RustPython

Length of output: 50378

🏁 Script executed:

# Check if there are any RustPython tests for gc.garbage fd "gc" Lib/test --type f | head -10

Repository: RustPython/RustPython

Length of output: 255

🏁 Script executed:

# Look for how gc module is initialized or used in tests rg "gc\.garbage" Lib 2>/dev/null | head -20

Repository: RustPython/RustPython

Length of output: 1114

Use #[pyattr(once)] to make gc.garbage persistent across accesses.

The #[pyattr] macro without (once) recomputes the value on each attribute access, creating a new empty list every time. This breaks compatibility with CPython, where gc.garbage is a mutable list that persists between reads. Code that modifies it (e.g., gc.garbage.clear() in tests) will lose those changes. Use #[pyattr(once)] instead to cache the result in a static cell, matching the pattern used elsewhere in RustPython for persistent module attributes.

🤖 Prompt for AI Agents

In `@crates/stdlib/src/gc.rs` around lines 5 - 13, The module attribute definition for gc.garbage uses #[pyattr] which recreates an empty list on each access; change the attribute to #[pyattr(once)] on the garbage function so the created list is stored/persistent across accesses (matching CPython semantics) — update the attribute macro on the garbage function (fn garbage(vm: &VirtualMachine) -> PyObjectRef) to #[pyattr(once)] so gc.garbage returns the same mutable list instance each time.

fanninpm · 2026-01-20T18:47:40Z

Lib/test/libregrtest/single.py

+    if gc.garbage:
+        support.environment_altered = True
+        print_warning(f"{test_name} created {len(gc.garbage)} "
+                      f"uncollectable object(s)")

-    #     # move the uncollectable objects somewhere,  # TODO: RUSTPYTHON, build a functional garbage collector into the interpreter
-    #     # so we don't see them again  # TODO: RUSTPYTHON, build a functional garbage collector into the interpreter
-    #     GC_GARBAGE.extend(gc.garbage)  # TODO: RUSTPYTHON, build a functional garbage collector into the interpreter
-    #     gc.garbage.clear()  # TODO: RUSTPYTHON, build a functional garbage collector into the interpreter
+        # move the uncollectable objects somewhere,
+        # so we don't see them again
+        GC_GARBAGE.extend(gc.garbage)
+        gc.garbage.clear()


youknowone force-pushed the regrtest branch from 41daaca to fed77cd Compare January 20, 2026 16:12

youknowone marked this pull request as ready for review January 20, 2026 16:23

coderabbitai bot reviewed Jan 20, 2026

View reviewed changes

fanninpm reviewed Jan 20, 2026

View reviewed changes

youknowone force-pushed the regrtest branch 2 times, most recently from eff49b4 to 6c17e07 Compare January 21, 2026 09:14

youknowone added 2 commits January 21, 2026 20:44

winapi.WaitForSingleObject

2fb2a7e

Update libregrtest from v3.14.2

9e9bfa5

youknowone force-pushed the regrtest branch from 6c17e07 to 9e9bfa5 Compare January 21, 2026 11:44

youknowone merged commit 726a053 into RustPython:main Jan 21, 2026
14 checks passed

youknowone deleted the regrtest branch January 21, 2026 12:35

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

libregrtest from 3.14.2 #6818

libregrtest from 3.14.2 #6818

Uh oh!

youknowone commented Jan 20, 2026 •

edited by coderabbitai bot

Loading

Uh oh!

coderabbitai bot commented Jan 20, 2026 •

edited

Loading

Walkthrough

Changes

Estimated code review effort

Poem

Uh oh!

coderabbitai bot left a comment

Uh oh!

coderabbitai bot Jan 20, 2026

Uh oh!

fanninpm Jan 20, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

libregrtest from 3.14.2 #6818

libregrtest from 3.14.2 #6818

Uh oh!

Conversation

youknowone commented Jan 20, 2026 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

coderabbitai bot commented Jan 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Poem

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

coderabbitai bot Jan 20, 2026

Choose a reason for hiding this comment

Uh oh!

fanninpm Jan 20, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

youknowone commented Jan 20, 2026 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Jan 20, 2026 •

edited

Loading