chore: bump chumsky from 0.11.2 to 0.12.0

[dependabot]

Bumps chumsky from 0.11.2 to 0.12.0.

Changelog

Sourced from chumsky's changelog.

[0.12.0] - 2025-12-15

Added

• MapExtra::emit, which allows emitting secondary errors during mapping operations
• InputRef::emit, which allows emitting secondary errors within custom parsers
• labelled_with, which avoids the need to implement Clone for labels
• Input::split_token_span, a convenience function for splitting (Token, Span) inputs so that chumsky can understand them
• Input::split_spanned, which does the same as above, but for implementors of WrappingSpan
• spanned, a combinator which automatically annotates a parser output with a span
• Experimental:
  • IterParser::parse_iter, a way to turn an IterParser (like x.repeated()) into an iterator
  • Parser::debug, which provides access to various parser debugging utilities.

Changed

• Made nested_in more flexible by allowing it to map between different input types instead of requiring the same input as the outer parser

Fixed

• A prioritisation bug with nested_in

Commits

• See full diff in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[max-sixty]

@claude please fix

[claude]

Claude finished @max-sixty's task in 39m 35s —— View job

---

Fixing chumsky 0.12.0 Upgrade ✅

• Gather context and check CI status
• Identify build/test failures - Method name conflict with with_span
• Fix method disambiguation in lexer/mod.rs
• Fix method disambiguation in parser/interpolation.rs
• Run tests to verify fix - 636 tests passed!
• Push code fix
• Push updated Cargo.lock
• CI passed ✅

Root cause: chumsky 0.12.0 introduces a new SpanWrap trait with a with_span method that conflicts with the existing WithErrorInfo::with_span method in the codebase.

Fix:

1. Used fully qualified syntax WithErrorInfo::with_span(...) instead of method syntax to disambiguate
2. Updated Cargo.lock with regenerated dependencies for chumsky 0.12.0

Changes made:

• prqlc/prqlc-parser/src/lexer/mod.rs - Disambiguated with_span call
• prqlc/prqlc-parser/src/parser/interpolation.rs - Disambiguated with_span call
• Cargo.lock - Regenerated for chumsky 0.12.0 compatibility
  | Branch

[max-sixty]

@claude should we be using the .with_span from chumsky? Open a new branch with that change if so

[claude]

Claude finished @max-sixty's task in 1m 48s —— View job

---

Investigating chumsky 0.12.0 .with_span Usage

• Understand what chumsky's .with_span does vs our WithErrorInfo::with_span
• Check if chumsky's approach would be better for our use case
• Make recommendation

Analysis

After researching the chumsky 0.12.0 changes, I found that chumsky's SpanWrap::with_span serves a completely different purpose than our WithErrorInfo::with_span:

Trait	Purpose	Example Use
chumsky's SpanWrap::with_span	Wrapping AST nodes with span info	expr.with_span(span) → (Expr, Span)
Our WithErrorInfo::with_span	Adding span info to Error types	error.with_span(span) → Error { span: ... }

Our current usage is correct. In both lexer/mod.rs (line 53) and interpolation.rs (line 66), we're adding span information to Error types, not AST nodes:

// lexer/mod.rs:53 - Adding span to an Error
WithErrorInfo::with_span(
    Error::new(Reason::Unexpected { ... }),
    Some(crate::span::Span { ... }),
)

// interpolation.rs:66 - Adding span to an Error  
WithErrorInfo::with_span(Error::new_simple(message), Some(span))

Chumsky's spanned combinator and SpanWrap::with_span are designed for wrapping parser output (AST nodes) with spans, not for error construction.

Recommendation

No change needed. The current fix using fully qualified syntax WithErrorInfo::with_span(...) is the correct approach. Chumsky's .with_span method is for a different use case (AST node spanning, not error spanning).

If we wanted to simplify the disambiguation, an alternative would be to rename our method (e.g., to with_error_span), but this would be a larger refactoring that isn't necessary—the current approach is clear and correct.

|