Skip to content

Remove redundent to_owned() and to_string() calls #5836

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 2 commits into from
Jun 25, 2025

Conversation

ShaharNaveh
Copy link
Contributor

@ShaharNaveh ShaharNaveh commented Jun 25, 2025

Followup for #5826

Code used to make this PR
# Cargo.toml

[package]
name = "rustpython-walker"
version = "0.1.0"
edition = "2024"

[dependencies]
tree-sitter = "0.24"
tree-sitter-rust = "0.23"
walkdir = "2"

[build-dependencies]
cc = "*"
// src/main.rs

use std::{
    fs,
    path::{Path, PathBuf},
};
use tree_sitter::{Parser, TreeCursor};
use walkdir::{DirEntry, WalkDir};

fn is_bad_entry(entry: &DirEntry) -> bool {
    entry
        .path()
        .components()
        .map(|comp| comp.as_os_str().to_str().unwrap())
        .any(|comp| matches!(comp, ".git" | "target"))
}

fn fix_file(path: &PathBuf, parser: &mut Parser) {
    let mut source_code = fs::read_to_string(path).unwrap();

    let tree = parser.parse(&source_code, None).unwrap();
    let root = tree.root_node();
    let mut cursor = root.walk();

    let mut edits = vec![];

    walk(&mut cursor, source_code.as_bytes(), &mut edits);

    println!("Checking: {}\n", path.display());
    if !edits.is_empty() {
        println!("Found {} edits", edits.len());

        for (start, end) in edits.into_iter().rev() {
            source_code.replace_range(start..end, "");
        }

        let _ = fs::write(path, source_code).unwrap();
    }
}

fn walk(cursor: &mut TreeCursor, source_code_bytes: &[u8], edits: &mut Vec<(usize, usize)>) {
    loop {
        let node = cursor.node();

        if node.kind() == "call_expression" {
            if let Some(func_expr) = node.child_by_field_name("function") {
                if func_expr.kind() == "field_expression" {
                    if let Some(method) = func_expr.child_by_field_name("field") {
                        if matches!(
                            method.utf8_text(source_code_bytes).unwrap(),
                            "new_attribute_error"
                                | "new_buffer_error"
                                | "new_eof_error"
                                | "new_errno_error"
                                | "new_import_error"
                                | "new_index_error"
                                | "new_lookup_error"
                                | "new_memory_error"
                                | "new_name_error"
                                | "new_not_implemented_error"
                                | "new_overflow_error"
                                | "new_recursion_error"
                                | "new_runtime_error"
                                | "new_system_error"
                                | "new_type_error"
                                | "new_unicode_decode_error"
                                | "new_unicode_encode_error"
                                | "new_value_error"
                                | "new_zero_division_error"
                        ) {
                            if let Some(args) = node.child_by_field_name("arguments") {
                                if args.named_child_count() >= 1 {
                                    let first_arg = args.named_child(0).unwrap();
                                    if first_arg.kind() == "call_expression" {
                                        if let Some(inner_func) =
                                            first_arg.child_by_field_name("function")
                                        {
                                            if inner_func.kind() == "field_expression" {
                                                let str_lit =
                                                    inner_func.child_by_field_name("value");
                                                let str_method =
                                                    inner_func.child_by_field_name("field");

                                                if let (Some(val), Some(method)) =
                                                    (str_lit, str_method)
                                                {
                                                    if val.kind() == "string_literal" {
                                                        let method_name = method
                                                            .utf8_text(source_code_bytes)
                                                            .unwrap();
                                                        if matches!(
                                                            method_name,
                                                            "to_owned" | "to_string"
                                                        ) {
                                                            let delete_start = val.end_byte();
                                                            let delete_end = first_arg.end_byte();
                                                            edits.push((delete_start, delete_end));
                                                        }
                                                    }
                                                }
                                            }
                                        }
                                    }
                                }
                            }
                        }
                    }
                }
            }
        }

        if cursor.goto_first_child() {
            walk(cursor, source_code_bytes, edits);
            cursor.goto_parent();
        }

        if !cursor.goto_next_sibling() {
            break;
        }
    }
}

fn main() {
    let mut parser = Parser::new();
    parser
        .set_language(&tree_sitter_rust::LANGUAGE.into())
        .unwrap();
    let target_dir = Path::new(env!("CARGO_MANIFEST_DIR"))
        .join("../RustPython")
        .canonicalize()
        .expect("Failed to resolve path");

    WalkDir::new(&target_dir)
        .into_iter()
        .filter_entry(|e| !is_bad_entry(e))
        .filter_map(|e| e.ok())
        .map(|e| e.into_path())
        .filter(|p| p.is_file() && p.extension().map_or(false, |ext| ext == "rs"))
        .for_each(|path| fix_file(&path, &mut parser));
}

The code ain't the prettiest but it gets the job done 😅

Summary by CodeRabbit

  • Style
    • Simplified error message handling across the codebase by removing unnecessary string conversions. Error messages are now passed as string literals rather than cloned or converted to owned strings. This change does not affect application behavior or error messages but improves internal efficiency and code readability. No user-facing functionality or error content is altered.

Copy link

coderabbitai bot commented Jun 25, 2025

Walkthrough

This change uniformly removes unnecessary .to_owned() and similar string ownership conversions from error message strings passed to error constructors throughout the codebase. Instead of creating owned String objects from string literals, string slices are now passed directly, simplifying error message construction without altering logic, control flow, or error handling.

Changes

File(s) Change Summary
stdlib/src/array.rs, stdlib/src/binascii.rs, ... Removed .to_owned()/.to_string() from error message strings, passing string slices directly to error constructors throughout all affected modules and files. No logic or control flow changes.
vm/src/builtins/asyncgenerator.rs, vm/src/builtins/bool.rs, ... Same pattern applied to builtins and VM modules: error messages now use string slices instead of owned strings for all error creation calls.
vm/src/stdlib/ctypes.rs, vm/src/stdlib/ctypes/base.rs, ... Uniform simplification of error message construction by eliminating unnecessary string allocations in ctypes and related modules.
(All other listed files) Consistent application of the same refactoring: error messages are passed as string slices, not owned strings, across all modules.

Possibly related PRs

  • RustPython/RustPython#5820: Also modifies stdlib/src/binascii.rs, introducing new arguments and logic to the hexlify function; related through changes to the same function and file.
  • RustPython/RustPython#5826: Focuses on removing unnecessary string ownership conversions in error message construction, including in stdlib/src/array.rs, closely related in approach and affected files.
  • RustPython/RustPython#5823: Modifies vm/src/builtins/function.rs, introducing new constructor logic; related by file and context, though with different focus.

Suggested reviewers

  • youknowone

Poem

A bunny hopped through fields of code,
Snipping .to_owned() where it showed.
Now strings are light, no clones in sight,
Error messages swift as flight!
With every slice, the code feels nice—
Simpler, leaner, pure delight!
🐇✨

✨ 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
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need 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)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@youknowone youknowone merged commit 1ae0781 into RustPython:main Jun 25, 2025
11 of 12 checks passed
@youknowone
Copy link
Member

Thanks!

@ShaharNaveh ShaharNaveh deleted the cln-rm-to-owned branch June 26, 2025 08:41
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants