-
Notifications
You must be signed in to change notification settings - Fork 1.4k
Resolve test_inspect bytecode parity gaps #7926
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
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Outdated suggestions cannot be applied.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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧩 Analysis chain
🌐 Web query:
In CPython, does the compiler always store the syntheticclasscellinto the class locals namespace, even when the class body declaresglobal classcellornonlocal classcell?💡 Result:
No—CPython does not always end up storing the synthetic
classcellinto the class-body locals namespace when the class body declaresglobal classcellornonlocal classcell. In CPython, the zero-argumentsuper()mechanism is implemented by injecting a hiddenclass/classcellcell during compilation, but CPython also standardizes behavior so thatclassand (in 3.6+)classcelldo not show up in the class locals while the class body executes [1]. Additionally, the generator/symbol-table machinery forclass/classcellinteracts “strangely” with explicitnonlocal classin nested namespaces: the injection behaves like a closure/free variable and can be accessed vianonlocalfrom a nested class, without being treated as a normal local in the class-body locals mapping [1]. This directly implies that declaringnonlocal classcell(analogous to theclasscase discussed) preventsclasscellfrom being stored like a regular local entry in the class locals namespace. So, when you explicitly declareglobal classcellornonlocal classcell, CPython’s compiler/symbol-table handling will not necessarily (and in these cases generally does not) place the syntheticclasscellinto the class locals mapping the way it would for a normal class body without such declarations; instead the injected cell remains hidden/handled specially forLOAD_BUILD_CLASSand zero-argumentsuper()semantics [1].Citations:
🏁 Script executed:
# First, check the file size and read the relevant sections wc -l crates/codegen/src/compile.rsRepository: RustPython/RustPython
Length of output: 101
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 690
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 557
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 134
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 661
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 684
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 380
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 1960
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 154
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 386
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 1639
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 1309
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 502
🏁 Script executed:
Repository: RustPython/RustPython
Length of output: 234
Use unconditional class-local stores for
__classcell__and__classdictcell__instead of routing throughstore_name().These are class-creation protocol slots that must always be stored to the class namespace, regardless of
globalornonlocaldeclarations in the class body. Routing them throughstore_name()causes them to honor such declarations, converting them toSTORE_DEREForSTORE_GLOBAL, which prevents the class namespace from receiving the cells that__build_class__expects. Note that__classdict__is already correctly handled with a directInstruction::StoreDeref(line 6652); apply the same pattern to both locations.🤖 Prompt for AI Agents