feat(linter): add UseStartsEndsWith rule #8582
Conversation
|
github-actions
bot
added
A-Project
You-saku
changed the title
CodSpeed Performance ReportMerging #8582 will not alter performanceComparing Summary
Footnotes
|
WalkthroughAdds a new nursery lint rule Suggested reviewers
🚥 Pre-merge checks | ✅ 4✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ 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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🧹 Nitpick comments (3)
crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/valid.js (1)
1-3: Valid test cases look good, though coverage could be expanded.These correctly verify that direct
startsWith/endsWithusage doesn't trigger diagnostics. Consider adding more edge cases in future iterations, such as:
foo.indexOf('bar') === 1(non-zero index)foo.slice(1, 3) === 'ar'(non-zero start)- Dynamic patterns like
foo.startsWith(variable)crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs (2)
83-83: Consider using the options struct instead of unit type.An options struct
UseStartsEndsWithOptionswas created inbiome_rule_options, but this rule usestype Options = (). Either remove the unused options struct or wire it up here for consistency and future extensibility.
346-379: Regex parsing may produce false positives on complex patterns.The current implementation extracts the raw pattern and checks for
^/$anchors. This works for simple cases like/^bar/but may produce incorrect suggestions for:
- Patterns with character classes like
/[^abc]/(negation, not anchor)- Patterns with alternations like
/^foo|bar/- Patterns with quantifiers or special regex syntax
Consider either:
- Limiting the rule to simple alphanumeric patterns
- Adding a proper regex parser to validate the pattern is a simple literal
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (7)
crates/biome_configuration/src/analyzer/linter/rules.rsis excluded by!**/rules.rsand included by**crates/biome_diagnostics_categories/src/categories.rsis excluded by!**/categories.rsand included by**crates/biome_js_analyze/src/lint/nursery.rsis excluded by!**/nursery.rsand included by**crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js.snapis excluded by!**/*.snapand included by**crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/valid.js.snapis excluded by!**/*.snapand included by**packages/@biomejs/backend-jsonrpc/src/workspace.tsis excluded by!**/backend-jsonrpc/src/workspace.tsand included by**packages/@biomejs/biome/configuration_schema.jsonis excluded by!**/configuration_schema.jsonand included by**
📒 Files selected for processing (5)
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rscrates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.jscrates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/valid.jscrates/biome_rule_options/src/lib.rscrates/biome_rule_options/src/use_starts_ends_with.rs
🧰 Additional context used
📓 Path-based instructions (1)
**/*.rs
📄 CodeRabbit inference engine (CONTRIBUTING.md)
**/*.rs: Use inline rustdoc documentation for rules, assists, and their options
Use thedbg!()macro for debugging output in Rust tests and code
Use doc tests (doctest) format with code blocks in rustdoc comments; ensure assertions pass in tests
Files:
crates/biome_rule_options/src/lib.rscrates/biome_rule_options/src/use_starts_ends_with.rscrates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
🧠 Learnings (31)
📓 Common learnings
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Use `RuleSource::Eslint(...).same()` when implementing a rule that matches the behavior of an ESLint rule
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Commit rule work with message format `feat(biome_<language>_analyze): <ruleName>`
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Use `RuleSource::Eslint(...).inspired()` when implementing a rule inspired by but with different behavior than an ESLint rule
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Add `sources` field with `RuleSource` to cite ESLint or other rules that inspired the implementation
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/lint/**/*.rs : Lint rules should perform static analysis of source code to detect invalid or error-prone patterns and emit diagnostics with proposed fixes
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/biome_rule_options/lib/**/*.rs : Wrap rule options fields in `Option<>` to properly track set and unset options during merge
Applied to files:
crates/biome_rule_options/src/lib.rscrates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/biome_rule_options/lib/**/*.rs : Rule options must be placed inside the `biome_rule_options` crate
Applied to files:
crates/biome_rule_options/src/lib.rscrates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/biome_rule_options/lib/**/*.rs : Use `rename_all = "camelCase"` in serde derive macro for rule options
Applied to files:
crates/biome_rule_options/src/lib.rscrates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/biome_rule_options/lib/**/*.rs : Use `deny_unknown_fields` in serde derive macro for rule options
Applied to files:
crates/biome_rule_options/src/lib.rscrates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/biome_rule_options/lib/**/*.rs : Use `Box<[T]>` instead of `Vec<T>` for rule options arrays to save memory
Applied to files:
crates/biome_rule_options/src/lib.rscrates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/biome_rule_options/lib/**/*.rs : Implement `Merge` trait for rule options to support configuration inheritance
Applied to files:
crates/biome_rule_options/src/lib.rscrates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Use language-specific rule names if the rule is meant for a specific language only
Applied to files:
crates/biome_rule_options/src/lib.rscrates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Rule documentation must include `## Options` section if the rule has options
Applied to files:
crates/biome_rule_options/src/lib.rscrates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Use generic rule names if the rule could potentially be implemented for multiple languages
Applied to files:
crates/biome_rule_options/src/lib.rscrates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : The first paragraph of rule documentation must be a single line describing what the rule does
Applied to files:
crates/biome_rule_options/src/lib.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Use `use_options` code block property for code examples that follow an options configuration in documentation
Applied to files:
crates/biome_rule_options/src/lib.rscrates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/tests/specs/**/*valid* : Create test files prefixed with `valid` for code that should not trigger the rule
Applied to files:
crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/valid.jscrates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/tests/specs/**/*invalid* : Create test files prefixed with `invalid` for code that should trigger the rule
Applied to files:
crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/valid.jscrates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/tests/specs/**/*.jsonc : Use `.jsonc` files to contain arrays of code snippet strings for snapshot tests
Applied to files:
crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/valid.jscrates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/biome_rule_options/lib/**/*.rs : Rule options struct must derive `Deserializable`, `Serialize`, `Deserialize`, and optionally `JsonSchema`
Applied to files:
crates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Use `options` code block property for rule-specific configuration snippets in documentation
Applied to files:
crates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Use `full_options` code block property for complete biome.json configuration snippets in documentation
Applied to files:
crates/biome_rule_options/src/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Each invalid code example in rule documentation must emit exactly one diagnostic
Applied to files:
crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.jscrates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Invalid code examples in rule documentation must be marked with `expect_diagnostic` code block property
Applied to files:
crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js
📚 Learning: 2025-12-04T13:29:49.287Z
Learnt from: dyc3
Repo: biomejs/biome PR: 8291
File: crates/biome_html_formatter/tests/specs/prettier/vue/html-vue/elastic-header.html:10-10
Timestamp: 2025-12-04T13:29:49.287Z
Learning: Files under `crates/biome_html_formatter/tests/specs/prettier` are test fixtures synced from Prettier and should not receive detailed code quality reviews (e.g., HTTP vs HTTPS, formatting suggestions, etc.). These files are test data meant to validate formatter behavior and should be preserved as-is.
Applied to files:
crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Use `RuleSource::Eslint(...).same()` when implementing a rule that matches the behavior of an ESLint rule
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/lint/**/*.rs : Lint rules should perform static analysis of source code to detect invalid or error-prone patterns and emit diagnostics with proposed fixes
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Use `declare_lint_rule!` macro to declare analyzer rule types and implement the RuleMeta trait
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/lint/nursery/**/*.rs : Add `issue_number` field to `declare_lint_rule!` macro for work-in-progress rules
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Use `RuleSource::Eslint(...).inspired()` when implementing a rule inspired by but with different behavior than an ESLint rule
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Add `sources` field with `RuleSource` to cite ESLint or other rules that inspired the implementation
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/lint/nursery/**/*.rs : Place new rules inside the `nursery` group during development
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/lint/**/*.rs : Lint rules should check syntax according to language specification and emit error diagnostics
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-19T12:53:30.413Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-12-19T12:53:30.413Z
Learning: Applies to crates/biome_analyze/**/*analyze/src/**/*.rs : Valid code examples in rule documentation should not trigger any diagnostics
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-22T09:26:56.943Z
Learnt from: ematipico
Repo: biomejs/biome PR: 8537
File: crates/biome_js_analyze/src/lint/nursery/no_leaked_render.rs:167-210
Timestamp: 2025-12-22T09:26:56.943Z
Learning: When defining lint rules (declare_lint_rule!), only specify fix_kind if the rule implements an action(...) function. Rules that only emit diagnostics without a code fix should omit fix_kind. This applies to all Rust lint rule definitions under crates/.../src/lint (e.g., crates/biome_js_analyze/src/lint/...).
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
🧬 Code graph analysis (1)
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs (1)
crates/biome_js_syntax/src/expr_ext.rs (1)
callee(33-38)
🔇 Additional comments (4)
crates/biome_rule_options/src/use_starts_ends_with.rs (1)
1-6: Well-structured options definition.The struct correctly follows the biome rule options conventions:
deny_unknown_fields,rename_all = "camelCase", and all required trait derivations. As a unit-like struct with no fields, it's ready for future expansion if options are needed. Based on learnings.crates/biome_rule_options/src/lib.rs (1)
376-376: LGTM!Module export correctly placed in alphabetical order.
crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js (1)
1-15: Comprehensive invalid test coverage.Good selection of patterns covering all the detection paths: computed member access,
charAt,indexOf,lastIndexOf,slice,substring,match, and regextest. BothstartsWithandendsWithvariants are exercised.crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs (1)
94-114: LGTM!Clear and helpful diagnostic message with appropriate note showing the suggested replacement.
| Some( | ||
| RuleDiagnostic::new( | ||
| rule_category!(), | ||
| node.range(), | ||
| markup! { | ||
| "Use `"{method_name}"()` method for string comparison." | ||
| }, | ||
| ) | ||
| .note(markup! { | ||
| "This pattern can be replaced with `"{method_name}"('"{ &state.pattern }"')`." | ||
| }), | ||
| ) |
There was a problem hiding this comment.
Remember the rule pillars (see contributing docs). You've only told the how to fix the error, but not what is the error, and why its an error.
| } | ||
|
|
||
| impl Rule for UseStartsEndsWith { | ||
| type Query = Ast<AnyStringCheckExpression>; |
There was a problem hiding this comment.
The source rule uses type information to only make these suggestions for checks against actual strings. For example foo[0] === "b" could have foo be an array, and this rule would flag it as a false positive.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (3)
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs (3)
408-415: Avoid string allocation inextract_string_literal.The function returns
Option<String>and calls.to_string(), which allocates. According to coding guidelines, avoid string allocations by usingTokenTextor&strwhere possible.♻️ Suggested refactor using TokenText
-fn extract_string_literal(expr: &AnyJsExpression) -> Option<String> { +fn extract_string_literal(expr: &AnyJsExpression) -> Option<impl std::fmt::Display> { if let AnyJsExpression::AnyJsLiteralExpression(literal) = expr && let Some(string) = literal.as_js_string_literal_expression() { - return Some(string.inner_string_text().ok()?.to_string()); + return Some(string.inner_string_text().ok()?); } None }You'll need to update
UseStartsEndsWithState.patternto storeTokenTextinstead ofString, or evaluate whether the state genuinely needs to own the string data.Based on learnings, avoid
.to_string()allocations where possible.
382-382: Additional string allocations incheck_regex.Lines 382 and 390 use
.to_string()to allocate pattern strings. Consider whetherTokenTextslices could be used here as well to avoid allocations.Based on learnings, minimise string allocations throughout the rule implementation.
Also applies to: 390-390
280-287: Consider validating pattern length more defensively.Line 281 uses
pattern.chars().count()to calculate pattern length for validation. Whilst correct for Unicode, it could be expensive for long patterns. Additionally, the validation logic assumes the numeric literal precisely equals the pattern length—consider whether off-by-one edge cases or non-literal expressions could bypass this check.The current logic is sound, but documenting why the length check is necessary (to avoid false positives with
lastIndexOf) would aid maintainability.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js.snapis excluded by!**/*.snapand included by**
📒 Files selected for processing (1)
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
🧰 Additional context used
📓 Path-based instructions (1)
**/*.rs
📄 CodeRabbit inference engine (CONTRIBUTING.md)
**/*.rs: Use inline rustdoc documentation for rules, assists, and their options
Use thedbg!()macro for debugging output in Rust tests and code
Use doc tests (doctest) format with code blocks in rustdoc comments; ensure assertions pass in tests
Files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
🧠 Learnings (17)
📓 Common learnings
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : When porting rules from other linters, use `sources` metadata with `RuleSource::Eslint().same()` for identical behavior or `.inspired()` for different behavior
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Rule names should use the `use` prefix when the rule's sole intention is to mandate a single concept
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Rule names should use the `use` prefix when the rule's sole intention is to mandate a single concept
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Deprecated rules must include a `deprecated` field in the `declare_lint_rule!` macro with an explanation of what rule to use instead
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : New rules must be placed inside the `nursery` group before promotion to other groups
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : When porting rules from other linters, use `sources` metadata with `RuleSource::Eslint().same()` for identical behavior or `.inspired()` for different behavior
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Avoid string allocations by using `&str` or `TokenText` instead of `to_string()`
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Use `declare_lint_rule!` macro with a `version` field set to `next` for new rules
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Rule names should use the `no` prefix when the rule's sole intention is to forbid a single concept
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Use `rule_category!()` macro to refer to the diagnostic category instead of dynamically parsing its string name
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Use the `Semantic<T>` query type to access semantic information about bindings, references, and scope within a rule
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-22T09:26:56.943Z
Learnt from: ematipico
Repo: biomejs/biome PR: 8537
File: crates/biome_js_analyze/src/lint/nursery/no_leaked_render.rs:167-210
Timestamp: 2025-12-22T09:26:56.943Z
Learning: When defining lint rules (declare_lint_rule!), only specify fix_kind if the rule implements an action(...) function. Rules that only emit diagnostics without a code fix should omit fix_kind. This applies to all Rust lint rule definitions under crates/.../src/lint (e.g., crates/biome_js_analyze/src/lint/...).
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : The first paragraph of rule documentation must be written in a single line to ensure proper rendering in the rules overview table
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-31T15:35:32.899Z
Learnt from: dyc3
Repo: biomejs/biome PR: 8639
File: crates/biome_js_analyze/src/lint/nursery/no_excessive_lines_per_file.rs:101-108
Timestamp: 2025-12-31T15:35:32.899Z
Learning: In Rust lint rules under the nursery category, the issue_number field in declare_lint_rule! is optional and should not be added unless there is a compelling reason. In code reviews, verify that no unnecessary issue_number is included in nursery lint declarations. Only add issue_number if there is an explicit, justified reason (e.g., tracked issue for external observers). This guidance broadly applies to all nursery lint rule files, not just the single file.
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Mark rules with `issue_number` in the `declare_lint_rule!` macro if they are work-in-progress to indicate missing features
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Code blocks in rule documentation must specify a language identifier and be tagged with `expect_diagnostic` for invalid examples or remain untagged for valid examples
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Invalid code snippets in rule documentation must emit exactly one diagnostic
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Rules should explain to users what the error is, why it is triggered, and what they should do to fix it
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
🔇 Additional comments (4)
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs (4)
121-438: Overall implementation is solid.The rule comprehensively covers various string-checking patterns (computed member access,
charAt,indexOf,lastIndexOf,slice,substring,match, regex literals). Logic is generally sound, and the dispatch structure is clean.Nice work porting this rule! The coverage is thorough and the code is well-structured. Once the escape-checking and string-allocation concerns are addressed, this should be ready for merging.
11-16: Reformat the first paragraph to a single line.The first paragraph of rule documentation must be written in a single line to ensure proper rendering in the rules overview table.
📝 Suggested fix
- /// Enforce using `String.startsWith()` and `String.endsWith()` over more complex alternatives. - /// - /// There are multiple ways to verify if a string starts or ends with a certain string, - /// such as `foo.indexOf('bar') === 0` or `foo.slice(0, 3) === 'bar'`. - /// - /// This rule is aimed to enforce a consistent and more readable style using `startsWith()` and `endsWith()` methods. + /// Enforce using `String.startsWith()` and `String.endsWith()` over more complex alternatives. + /// + /// There are multiple ways to verify if a string starts or ends with a certain string, such as `foo.indexOf('bar') === 0` or `foo.slice(0, 3) === 'bar'`. This rule is aimed to enforce a consistent and more readable style using `startsWith()` and `endsWith()` methods.Based on learnings, the first paragraph must be single-line for proper table rendering.
⛔ Skipped due to learnings
Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-01-02T14:58:16.536Z Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : The first paragraph of rule documentation must be written in a single line to ensure proper rendering in the rules overview tableLearnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-01-02T14:58:16.536Z Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Rule names should use the `use` prefix when the rule's sole intention is to mandate a single conceptLearnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-01-02T14:58:16.536Z Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Rule documentation must include an `## Examples` section followed by `### Invalid` and `### Valid` subsections, with Invalid appearing firstLearnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-01-02T14:58:16.536Z Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Rule names should use the `no` prefix when the rule's sole intention is to forbid a single conceptLearnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-01-02T14:58:16.536Z Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Invalid code snippets in rule documentation must emit exactly one diagnosticLearnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-01-02T14:58:16.536Z Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Code blocks in rule documentation must specify a language identifier and be tagged with `expect_diagnostic` for invalid examples or remain untagged for valid examplesLearnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-01-02T14:58:16.536Z Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Deprecated rules must include a `deprecated` field in the `declare_lint_rule!` macro with an explanation of what rule to use insteadLearnt from: dyc3 Repo: biomejs/biome PR: 8639 File: crates/biome_js_analyze/src/lint/nursery/no_excessive_lines_per_file.rs:101-108 Timestamp: 2025-12-31T15:35:41.261Z Learning: In crates/biome_analyze/**/*analyze/src/lint/nursery/**/*.rs, the `issue_number` field in `declare_lint_rule!` macro is optional and the vast majority of nursery rules do not need it. Do not recommend adding `issue_number` unless there's a specific reason.Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-01-02T14:58:16.536Z Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : When porting rules from other linters, use `sources` metadata with `RuleSource::Eslint().same()` for identical behavior or `.inspired()` for different behaviorLearnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-01-02T14:58:16.536Z Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Use `declare_lint_rule!` macro with a `version` field set to `next` for new rules
427-438: No change required—the text comparison approach is intentional and already documented.The function uses syntax text comparison by design since the rule operates at the syntactic level (
Ast<AnyStringCheckExpression>rather thanSemantic<T>). The comment at line 435 already explains this trade-off.Your concern about false positives from shadowed variables (e.g., different
xin nested scopes) is theoretically valid but practically unlikely in this context. The function is only called when verifying specific string-operation patterns, and variable shadowing would be rare at that granularity. If semantic binding verification becomes necessary later for stricter matching, update the comment to explain why.
375-376: The regex escape checking logic is actually correct.The pattern extraction and checks at lines 375-376 properly distinguish between anchors and escaped characters. For
/^bar/, the pattern is^bar, and for/^\^bar/(escaped caret after anchor), the pattern is^\\^bar—the trim removes the anchor and preserves the escaped caret. The second condition (!pattern.starts_with(r"\^")) is redundant but harmless; a string cannot simultaneously start with^and\^.The existing test suite covers the intended use cases (simple anchored patterns). If escaped anchors need additional coverage, consider adding test cases like
/^\^bar/,/^\\bar/, etc., but the current implementation handles them correctly.
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Fix all issues with AI agents
In @crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs:
- Around line 370-403: check_regex currently returns suggestions for anchored
patterns without ensuring the pattern is a literal string; add validation after
deriving `pattern` (and before returning any `UseStartsEndsWithState`) to reject
patterns containing regex metacharacters. Specifically, detect any unallowed
characters such as . * + ? [ ] { } ( ) | and backslash (treat backslash-escaped
sequences as non-literal) and if any are present return None; perform this check
prior to creating `clean_pattern` and returning from the StartsWith or EndsWith
branches in `check_regex` so only simple literal patterns produce a suggestion.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
🧰 Additional context used
📓 Path-based instructions (1)
**/*.rs
📄 CodeRabbit inference engine (CONTRIBUTING.md)
**/*.rs: Use inline rustdoc documentation for rules, assists, and their options
Use thedbg!()macro for debugging output in Rust tests and code
Use doc tests (doctest) format with code blocks in rustdoc comments; ensure assertions pass in tests
Files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
🧠 Learnings (18)
📓 Common learnings
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : When porting rules from other linters, use `sources` metadata with `RuleSource::Eslint().same()` for identical behavior or `.inspired()` for different behavior
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Rule names should use the `use` prefix when the rule's sole intention is to mandate a single concept
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Deprecated rules must include a `deprecated` field in the `declare_lint_rule!` macro with an explanation of what rule to use instead
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : New rules must be placed inside the `nursery` group before promotion to other groups
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Avoid string allocations by using `&str` or `TokenText` instead of `to_string()`
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : When porting rules from other linters, use `sources` metadata with `RuleSource::Eslint().same()` for identical behavior or `.inspired()` for different behavior
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Rule names should use the `no` prefix when the rule's sole intention is to forbid a single concept
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Use `declare_lint_rule!` macro with a `version` field set to `next` for new rules
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Implement custom `Queryable` and `Visitor` types for rules that require deep inspection of child nodes to avoid inefficient traversals
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-22T09:26:56.943Z
Learnt from: ematipico
Repo: biomejs/biome PR: 8537
File: crates/biome_js_analyze/src/lint/nursery/no_leaked_render.rs:167-210
Timestamp: 2025-12-22T09:26:56.943Z
Learning: When defining lint rules (declare_lint_rule!), only specify fix_kind if the rule implements an action(...) function. Rules that only emit diagnostics without a code fix should omit fix_kind. This applies to all Rust lint rule definitions under crates/.../src/lint (e.g., crates/biome_js_analyze/src/lint/...).
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Use the `Semantic<T>` query type to access semantic information about bindings, references, and scope within a rule
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : The first paragraph of rule documentation must be written in a single line to ensure proper rendering in the rules overview table
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2025-12-31T15:35:32.899Z
Learnt from: dyc3
Repo: biomejs/biome PR: 8639
File: crates/biome_js_analyze/src/lint/nursery/no_excessive_lines_per_file.rs:101-108
Timestamp: 2025-12-31T15:35:32.899Z
Learning: In Rust lint rules under the nursery category, the issue_number field in declare_lint_rule! is optional and should not be added unless there is a compelling reason. In code reviews, verify that no unnecessary issue_number is included in nursery lint declarations. Only add issue_number if there is an explicit, justified reason (e.g., tracked issue for external observers). This guidance broadly applies to all nursery lint rule files, not just the single file.
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Mark rules with `issue_number` in the `declare_lint_rule!` macro if they are work-in-progress to indicate missing features
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Code blocks in rule documentation must specify a language identifier and be tagged with `expect_diagnostic` for invalid examples or remain untagged for valid examples
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Invalid code snippets in rule documentation must emit exactly one diagnostic
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Rules should explain to users what the error is, why it is triggered, and what they should do to fix it
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
📚 Learning: 2026-01-02T14:58:16.536Z
Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2026-01-02T14:58:16.536Z
Learning: Applies to crates/biome_analyze/**/*_analyze/**/src/lint/**/*.rs : Check if a variable is global using the semantic model before reporting diagnostics for rules that ban global functions or variables
Applied to files:
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs
🔇 Additional comments (5)
crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs (5)
10-62: Rule declaration follows conventions properly.The metadata is correctly configured with
version: "next", proper ESLint source attribution using.same(), and appropriate documentation structure. The first paragraph is a single line as required, and invalid examples are tagged withexpect_diagnostic.
64-78: Type definitions are sound.The
Stringtype for the pattern field is appropriate here since the state must be stored and outlive the query context for diagnostic emission.
80-119: LGTM!The Rule implementation correctly dispatches based on expression type and provides clear, actionable diagnostics.
121-178: LGTM!The bidirectional checking of binary expression sides ensures the rule catches patterns regardless of operand order.
435-446: Object comparison by syntax text is a reasonable heuristic.Line 443 compares objects using their text representation. Whilst this could theoretically have edge cases with formatting differences, it's a pragmatic approach for detecting the same object reference in
str[str.length - 1]patterns.
| // Validate that the right operand is a numeric literal equal to pattern length | ||
| let right = binary.right().ok()?; | ||
| let pattern_length = pattern.chars().count(); | ||
|
|
||
| if let AnyJsExpression::AnyJsLiteralExpression(literal) = right | ||
| && let Some(number) = literal.as_js_number_literal_expression() | ||
| && let Ok(value) = number.value_token() | ||
| && let Ok(parsed) = value.text_trimmed().parse::<usize>() | ||
| && parsed == pattern_length | ||
| { | ||
| return Some(UseStartsEndsWithState { | ||
| variant: StartsEndsWithVariant::EndsWith, | ||
| pattern, | ||
| }); | ||
| } |
There was a problem hiding this comment.
Incorrect string length calculation for Unicode strings.
Line 289 uses pattern.chars().count() which counts Unicode scalar values, but JavaScript's lastIndexOf and string length use UTF-16 code units. For strings with characters outside the Basic Multilingual Plane (e.g., emoji, mathematical symbols like 𝟘), this will cause incorrect pattern matching.
For example:
- JavaScript:
"𝟘".length === 2(UTF-16 code units) - Rust:
"𝟘".chars().count() === 1(Unicode scalar values)
🔧 Proposed fix using UTF-16 code unit count
let left = binary.left().ok()?;
if is_length_access(&left) {
// Validate that the right operand is a numeric literal equal to pattern length
let right = binary.right().ok()?;
- let pattern_length = pattern.chars().count();
+ let pattern_length = pattern.encode_utf16().count();
if let AnyJsExpression::AnyJsLiteralExpression(literal) = right
&& let Some(number) = literal.as_js_number_literal_expression()📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| // Validate that the right operand is a numeric literal equal to pattern length | |
| let right = binary.right().ok()?; | |
| let pattern_length = pattern.chars().count(); | |
| if let AnyJsExpression::AnyJsLiteralExpression(literal) = right | |
| && let Some(number) = literal.as_js_number_literal_expression() | |
| && let Ok(value) = number.value_token() | |
| && let Ok(parsed) = value.text_trimmed().parse::<usize>() | |
| && parsed == pattern_length | |
| { | |
| return Some(UseStartsEndsWithState { | |
| variant: StartsEndsWithVariant::EndsWith, | |
| pattern, | |
| }); | |
| } | |
| // Validate that the right operand is a numeric literal equal to pattern length | |
| let right = binary.right().ok()?; | |
| let pattern_length = pattern.encode_utf16().count(); | |
| if let AnyJsExpression::AnyJsLiteralExpression(literal) = right | |
| && let Some(number) = literal.as_js_number_literal_expression() | |
| && let Ok(value) = number.value_token() | |
| && let Ok(parsed) = value.text_trimmed().parse::<usize>() | |
| && parsed == pattern_length | |
| { | |
| return Some(UseStartsEndsWithState { | |
| variant: StartsEndsWithVariant::EndsWith, | |
| pattern, | |
| }); | |
| } |
| fn check_regex(regex: &JsRegexLiteralExpression) -> Option<UseStartsEndsWithState> { | ||
| let token = regex.value_token().ok()?; | ||
| let text = token.text_trimmed(); | ||
|
|
||
| let first_slash = text.find('/')?; | ||
| let last_slash = text.rfind('/')?; | ||
|
|
||
| if first_slash >= last_slash { | ||
| return None; | ||
| } | ||
|
|
||
| let pattern = &text[first_slash + 1..last_slash]; | ||
|
|
||
| let has_start = pattern.starts_with('^') && !pattern.starts_with(r"\^"); | ||
| let has_end = pattern.ends_with('$') && !pattern.ends_with(r"\$"); | ||
|
|
||
| if has_start { | ||
| let clean_pattern = pattern.trim_start_matches('^'); | ||
| return Some(UseStartsEndsWithState { | ||
| variant: StartsEndsWithVariant::StartsWith, | ||
| pattern: clean_pattern.to_string(), | ||
| }); | ||
| } | ||
|
|
||
| if has_end { | ||
| let clean_pattern = pattern.trim_end_matches('$'); | ||
| return Some(UseStartsEndsWithState { | ||
| variant: StartsEndsWithVariant::EndsWith, | ||
| pattern: clean_pattern.to_string(), | ||
| }); | ||
| } | ||
|
|
||
| None | ||
| } |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# First, locate the file and understand its full context
find . -name "use_starts_ends_with.rs" -type fRepository: biomejs/biome
Length of output: 179
🏁 Script executed:
# Look for test cases related to this lint rule
find . -name "*use_starts_ends_with*" -type fRepository: biomejs/biome
Length of output: 179
🏁 Script executed:
# Search for any validation of metacharacters in the file
rg "metachar|escape|literal" crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs -A 2 -B 2Repository: biomejs/biome
Length of output: 5054
🌐 Web query:
ESLint prefer-string-starts-ends-with rule regex metacharacters metachar validation
💡 Result:
Short answer
- The prefer-string-starts-ends-with rules (typescript-eslint and unicorn variants) target cases where code uses string checks or simple anchored regexes like /^foo/ or /foo$/ and can be replaced by foo.startsWith('foo') / foo.endsWith('foo'). [1][2]
- They do not change regexes that rely on regex metacharacters (character classes, quantifiers, anchors with more complex patterns, lookarounds, etc.), because those have different semantics than a plain literal prefix/suffix; such patterns are not safe to auto-replace. The docs show the rule flags simple anchored literals (e.g. /^bar/, /bar$/) as examples. [1][2]
- If you worry about invalid/unsupported regex syntax (constructor strings, bad flags), use ESLint’s no-invalid-regexp (or eslint-plugin-regexp) which validates regex literals/constructors per the spec. [3][4]
If you want, I can check a specific regex you’re concerned about and tell whether the rule will flag or auto-fix it.
🏁 Script executed:
# Look for test snapshots or test data
find . -path "*use_starts_ends_with*" -name "*.snap" -o -path "*use_starts_ends_with*" -name "*.js" -o -path "*use_starts_ends_with*" -name "*.json"Repository: biomejs/biome
Length of output: 39
🏁 Script executed:
# Read the full file to understand the context and any validation
wc -l crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 125
🏁 Script executed:
# Read specific sections around check_regex and look for test cases
head -430 crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs | tail -80Repository: biomejs/biome
Length of output: 2503
🏁 Script executed:
# Search for test snapshots or test configurations
find . -name "*use_starts_ends_with*" -type f | grep -E "(snap|test)"Repository: biomejs/biome
Length of output: 39
🏁 Script executed:
# Search more broadly for test files
find . -type f -name "*.rs" | xargs grep -l "use_starts_ends_with" | head -20Repository: biomejs/biome
Length of output: 95
🏁 Script executed:
# Look at the directory structure for test files
find crates/biome_js_analyze -type d -name "*test*" -o -type d -name "*nursery*"Repository: biomejs/biome
Length of output: 171
🏁 Script executed:
# Find snapshot files or test data
find crates/biome_js_analyze -name "*.snap" | head -10Repository: biomejs/biome
Length of output: 772
🏁 Script executed:
# Check if there's a test module in the file itself
grep -n "mod test\|#\[test\]" crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 39
🏁 Script executed:
# Look at the end of the file to see if there are test cases
tail -100 crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 3302
🏁 Script executed:
# Search for test specifications for this rule
find crates/biome_js_analyze/tests/specs/nursery -name "*useStartsEndsWith*" -o -name "*use_starts_ends_with*"Repository: biomejs/biome
Length of output: 118
🏁 Script executed:
# List files in the nursery test specs directory
ls crates/biome_js_analyze/tests/specs/nursery/ | grep -i "start\|end"Repository: biomejs/biome
Length of output: 89
🏁 Script executed:
# Check if there's a directory for this rule
ls -la crates/biome_js_analyze/tests/specs/nursery/ | head -30Repository: biomejs/biome
Length of output: 1968
🏁 Script executed:
# List files in the useStartsEndsWith test directory
ls -la crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/Repository: biomejs/biome
Length of output: 426
🏁 Script executed:
# Read the test files to see what patterns are tested
cat crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.jsRepository: biomejs/biome
Length of output: 474
🏁 Script executed:
# Also check the valid cases
cat crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/valid.jsRepository: biomejs/biome
Length of output: 138
🏁 Script executed:
# Check if there's a snapshot file with expected outputs
ls crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/*.snapRepository: biomejs/biome
Length of output: 210
🏁 Script executed:
# Read the snapshot file to see what patterns are tested
head -100 crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js.snapRepository: biomejs/biome
Length of output: 3196
🏁 Script executed:
# Look at more of the snapshot to see if there are tests with metacharacters
cat crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js.snap | grep -A 5 -B 5 "\.\*\|\\+" | head -50Repository: biomejs/biome
Length of output: 39
🏁 Script executed:
# Check if there are tests with regex metacharacters in the test files or snapshots
rg "\\.\*|\\[.*\\]|\\\+" crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/Repository: biomejs/biome
Length of output: 1333
🏁 Script executed:
# Check the entire invalid.js file to be sure
cat crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.jsRepository: biomejs/biome
Length of output: 474
🏁 Script executed:
# Now let's trace through the code to understand the full flow
# Read the entire check_regex implementation and see how it's called
sed -n '1,100p' crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 2995
🏁 Script executed:
# Search for where UseStartsEndsWithState is used - to see if there's validation later
rg "UseStartsEndsWithState" crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 1176
🏁 Script executed:
# Let's trace through what happens with a pattern like /^a.*b/
# Read the entire check_regex function and the calling code to see the full flow
sed -n '370,410p' crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 1397
🏁 Script executed:
# Let's verify by creating a test scenario - what pattern would the function return for /^a.*b/?
# First, let's understand how the diagnostic is generated with the pattern
sed -n '50,120p' crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 2111
🏁 Script executed:
# Look for any utility functions that might validate regex patterns
rg "is_literal|validate|metachar" crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 39
🏁 Script executed:
# Check if there are any comments or documentation about handling regex metacharacters
sed -n '340,410p' crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 2308
🏁 Script executed:
# Look at the full file to see if there's any mention of literal-only patterns
head -50 crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs | tail -40Repository: biomejs/biome
Length of output: 1127
🏁 Script executed:
# Check if there are integration tests with more complex patterns
find crates -name "*.js" -o -name "*.ts" | xargs grep -l "useStartsEndsWith\|use_starts_ends_with" | head -5Repository: biomejs/biome
Length of output: 39
🏁 Script executed:
# Let's create a simple test to trace through what would happen with a metacharacter pattern
# First, check if there's any documentation about the rule's scope
cat crates/biome_rule_options/src/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 409
🏁 Script executed:
# Search the entire codebase to see if there are any comments or commits about metacharacters
rg -B 3 -A 3 "check_regex" crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs | head -40Repository: biomejs/biome
Length of output: 665
🏁 Script executed:
# Let's verify by checking if there's a regex pattern in the test file that might contain metacharacters
cat crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.js | grep "/"Repository: biomejs/biome
Length of output: 177
🏁 Script executed:
# Let me check what the actual behavior would be if we had a pattern with metacharacters
# First, verify the test file doesn't contain any complex patterns
grep -E '\^\^|\.\\*|\[.*\]|\+|\\+' crates/biome_js_analyze/tests/specs/nursery/useStartsEndsWith/invalid.jsRepository: biomejs/biome
Length of output: 443
🏁 Script executed:
# Check if there's any escaping logic or validation in the entire file that I might have missed
wc -l crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs && echo "---" && cat crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs | grep -n "is_literal\|validate\|check.*pattern\|regex.*meta"Repository: biomejs/biome
Length of output: 318
🏁 Script executed:
# Let's trace through what the code would do step by step with /^a.*b/ pattern
python3 << 'EOF'
# Simulating what check_regex would do with /^a.*b/
regex_text = r"/^a.*b/"
# Find first and last /
first_slash = regex_text.find('/')
last_slash = regex_text.rfind('/')
print(f"Regex text: {regex_text}")
print(f"First slash at: {first_slash}, Last slash at: {last_slash}")
# Extract pattern
pattern = regex_text[first_slash + 1:last_slash]
print(f"Extracted pattern: {pattern}")
# Check for ^ and $
has_start = pattern.startswith('^') and not pattern.startswith('\\^')
print(f"has_start (starts with ^ not \\^): {has_start}")
if has_start:
# Trim start
clean_pattern = pattern.lstrip('^')
print(f"After trimming ^: {clean_pattern}")
print(f"Would suggest: foo.startsWith('{clean_pattern}')")
print(f"But regex /^a.*b/ matches 'a' then any chars then 'b'")
print(f"While startsWith('a.*b') looks for literal string 'a.*b'")
print(f"These are NOT equivalent!")
EOFRepository: biomejs/biome
Length of output: 143
🏁 Script executed:
# Let me check if there's any filtering or validation in how the result is used
sed -n '50,100p' crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rsRepository: biomejs/biome
Length of output: 1519
🏁 Script executed:
# Check if there's any documentation or comments about literal-only patterns
grep -B 5 -A 5 "literal\|simple" crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs | head -30Repository: biomejs/biome
Length of output: 956
Add validation to reject regex patterns with metacharacters.
The check_regex() function extracts patterns from regexes like /^foo/ without checking whether they contain regex metacharacters. For example, /^a.*b/ would suggest startsWith("a.*b"), but the regex matches "a" followed by any characters followed by "b", whilst startsWith() matches the literal string "a.*b". ESLint's rule avoids this by only suggesting replacements for simple anchored regexes.
Validate that the extracted pattern is literal (contains no metacharacters such as ., *, +, ?, [, ], {, }, (, ), |, etc.) before returning a suggestion.
🤖 Prompt for AI Agents
In @crates/biome_js_analyze/src/lint/nursery/use_starts_ends_with.rs around
lines 370 - 403, check_regex currently returns suggestions for anchored patterns
without ensuring the pattern is a literal string; add validation after deriving
`pattern` (and before returning any `UseStartsEndsWithState`) to reject patterns
containing regex metacharacters. Specifically, detect any unallowed characters
such as . * + ? [ ] { } ( ) | and backslash (treat backslash-escaped sequences
as non-literal) and if any are present return None; perform this check prior to
creating `clean_pattern` and returning from the StartsWith or EndsWith branches
in `check_regex` so only simple literal patterns produce a suggestion.
| fn is_string_type(expr: &AnyJsExpression) -> bool { | ||
| // If it's a string literal, it's definitely a string | ||
| if let AnyJsExpression::AnyJsLiteralExpression(literal) = expr { | ||
| if literal.as_js_string_literal_expression().is_some() { | ||
| return true; | ||
| } | ||
| } | ||
|
|
||
| // Check for template literals | ||
| if matches!(expr, AnyJsExpression::JsTemplateExpression(_)) { | ||
| return true; | ||
| } | ||
|
|
||
| // Check for array literals - these are not strings | ||
| if matches!(expr, AnyJsExpression::JsArrayExpression(_)) { | ||
| return false; | ||
| } | ||
|
|
||
| // For now, we allow unknown types or types that could be strings | ||
| // This is conservative but helps avoid false positives | ||
| true | ||
| } |
There was a problem hiding this comment.
Conservative type checking may cause false positives on arrays.
The function returns true for most expression types (line 468), which means patterns like arr[0] === 'x' on array identifiers will be flagged, even though arrays don't have startsWith/endsWith methods. Whilst the comment notes this is intentional, it could frustrate users with false positives on legitimate array operations.
Consider leveraging semantic model type information if available, or document this limitation in the rule description. For a nursery rule, this tradeoff might be acceptable initially.
2 participants
Summary
Ported the typescript-esilnt rule
prefer-string-starts-ends-withto a new Biome lint ruleUseStartsEndsWith.There are multiple ways to verify if a string starts or ends with a specific string, such as foo.indexOf('bar') === 0. As of ES2015, the most common way in JavaScript is to use String#startsWith and String#endsWith. Keeping to those methods consistently helps with code readability.
This rule reports when a string method can be replaced safely with String#startsWith or String#endsWith.
closes #7653
Supplement
I'm not good at Rust lang.
So, I implement this rule with borrowing generative ai(copilot) power.
If code quality is bad, please comment this pr.