feat(markdown): implement basic formatter features by tidefield · Pull Request #9693 · biomejs/biome

tidefield · 2026-03-29T15:01:56Z

This PR was written primarily by AI agent but I manually reviewed all the code, refractor it, and add clarifying comments.

Summary

Implement formatting features for bullet, bullet_list_item, header, inline_emphasis, inline_italic, list_market_prefix.

Test Plan

$  cargo test -p biome_markdown_formatter

Docs

changeset-bot · 2026-03-29T15:02:02Z

⚠️ No Changeset found

Latest commit: 0e5da05

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

tidefield · 2026-04-01T11:38:29Z

@coderabbitai

coderabbitai · 2026-04-01T11:38:46Z

@tidefield Sure thing! I'll kick off a review of the PR. 🐇

🧠 Learnings used

Learnt from: tidefield
Repo: biomejs/biome PR: 9480
File: crates/biome_markdown_formatter/src/markdown/auxiliary/hard_line.rs:11-31
Timestamp: 2026-03-14T11:30:13.488Z
Learning: In `crates/biome_markdown_formatter/src/markdown/auxiliary/hard_line.rs`, `FormatMdHardLine::fmt_fields` is responsible for emitting `hard_line_break()` itself (not the caller). As of PR `#9480` (building on `#9331` by ematipico), the function branches on the token text: if it ends with `\` it emits `format_removed(&token)` + `text("\\", ...)` + `hard_line_break()`; otherwise it normalises to two trailing spaces via `format_removed(&token)` + `text("  ", ...)` + `hard_line_break()`. The callers in `inline_item_list.rs` and `paragraph.rs` do NOT add an extra `hard_line_break()`.

Learnt from: jfmcdowell
Repo: biomejs/biome PR: 0
File: :0-0
Timestamp: 2026-03-30T19:37:09.253Z
Learning: In `crates/biome_markdown_parser/src/syntax/fenced_code_block.rs`, there is an intentional asymmetry between opening and closing fence indent stripping inside list items:
- **Opening fence**: `check_continuation_indent` (called before the fenced code block parser runs) already consumes the list continuation indent, so the opener only needs to emit the remaining 0–3 CommonMark-allowed fence spaces (`MAX_BLOCK_PREFIX_INDENT`). Stripping `list_item_required_indent` in the opener is NOT needed.
- **Closing fence**: processes the raw line without prior consumption, so it must strip `list_item_required_indent + MAX_BLOCK_PREFIX_INDENT` itself (the fix introduced in PR `#9730`).

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.

Learnt from: CR
Repo: biomejs/biome PR: 0
File: CONTRIBUTING.md:0-0
Timestamp: 2026-03-16T13:19:14.790Z
Learning: Changeset descriptions should be concise (1-3 sentences), user-facing, and follow specific formats: use inline code for simple examples, code blocks for complex examples, diff blocks for formatter changes, and past tense for actions and present tense for Biome behavior

✅ Actions performed

Review triggered.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

codspeed-hq · 2026-04-01T11:38:54Z

Merging this PR will not alter performance

✅ 28 untouched benchmarks
⏩ 228 skipped benchmarks¹

_{Comparing tidefield:md-formatter-basic (0e5da05) with main (5b16d18)}

228 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

tidefield · 2026-04-01T11:39:01Z

cc @jfmcdowell

coderabbitai · 2026-04-01T11:45:18Z

Note

Reviews paused

It looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the reviews.auto_review.auto_pause_after_reviewed_commits setting.

Use the following commands to manage reviews:

@coderabbitai resume to resume automatic reviews.
@coderabbitai review to trigger a single review.

Use the checkboxes below for quick actions:

▶️ Resume reviews
🔍 Trigger review

Walkthrough

This PR converts multiple Markdown auxiliary formatters from verbatim, syntax-preserving output to structured, field-based formatting. Changes include: normalising bullet markers with a thematic-break conflict fallback; formatting bullet list items and list-marker prefixes via extracted fields (adding a target_marker option); reconstructing inline emphasis and italic delimiters with flanking and nesting checks plus a special-case rewrite; and adding a header formatter fallback when initial syntax slots are missing. Tests and a new bullet-list spec were added/updated accordingly.

Possibly related PRs

feat(md/fmt): links, codeblocks #9699 — similar refactor replacing verbatim node formatting with structured, field-based formatting for Markdown rules, overlapping header-related changes.
feat(md/fmt): format more nodes #9713 — related refactor converting several Markdown formatters from syntax-preserving output to field-driven formatting, including list and thematic-break logic.

Suggested reviewers

dyc3
ematipico

🚥 Pre-merge checks | ✅ 2

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main objective—implementing basic formatter features for Markdown nodes—which aligns directly with the changeset's scope across multiple formatters.
Description check	✅ Passed	The description clearly explains the motivation (implementing formatting features for specific Markdown nodes), includes an AI-assistance disclosure, and provides a test plan, all directly relevant to the changeset.

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests

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

🧹 Nitpick comments (1)

crates/biome_markdown_formatter/src/markdown/auxiliary/setext_header.rs (1)
80-95: YAML front matter detection heuristic may have false positives.

This detects any --- thematic break preceding a setext header as YAML front matter, but a standalone thematic break before a setext header (not at document start) would also match. Consider additionally checking that the thematic break has no preceding non-newline siblings for stricter detection.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@crates/biome_markdown_formatter/src/markdown/auxiliary/setext_header.rs`
around lines 80 - 95, The current is_yaml_front_matter(MdSetextHeader) returns
true whenever a MD_THEMATIC_BREAK_BLOCK precedes the setext header even if that
break is not at document start; update the heuristic to ensure the thematic
break itself has no preceding non-newline siblings (i.e., walk backward from the
found thematic break node and verify all previous siblings are MD_NEWLINE or
absent) before returning true. Locate is_yaml_front_matter and modify the
sibling-walking logic: when you detect
MarkdownSyntaxKind::MD_THEMATIC_BREAK_BLOCK, perform an additional loop from
that thematic break node checking prev_sibling() for any non-newline kinds and
only consider it YAML front matter if none exist. Ensure you still skip over
MD_NEWLINE nodes when searching in both walks.

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@crates/biome_markdown_formatter/src/markdown/auxiliary/bullet.rs`:
- Around line 22-25: The current early return in the function (checking
marker.text_trimmed() != "*" && marker.text_trimmed() != "+") causes `-` markers
to skip the alternation/normalization logic and go straight to
format_verbatim_node(node.syntax()).fmt(f); remove or modify that conditional so
alternation logic runs for `-` markers as well (i.e., include `-` in the set of
markers handled by the alternation/normalization path) and only fall back to
format_verbatim_node when genuinely necessary; update the branch that calls
format_verbatim_node and any downstream alternation code so it operates on
marker.text_trimmed() for "*", "+", and "-" consistently.

---

Nitpick comments:
In `@crates/biome_markdown_formatter/src/markdown/auxiliary/setext_header.rs`:
- Around line 80-95: The current is_yaml_front_matter(MdSetextHeader) returns
true whenever a MD_THEMATIC_BREAK_BLOCK precedes the setext header even if that
break is not at document start; update the heuristic to ensure the thematic
break itself has no preceding non-newline siblings (i.e., walk backward from the
found thematic break node and verify all previous siblings are MD_NEWLINE or
absent) before returning true. Locate is_yaml_front_matter and modify the
sibling-walking logic: when you detect
MarkdownSyntaxKind::MD_THEMATIC_BREAK_BLOCK, perform an additional loop from
that thematic break node checking prev_sibling() for any non-newline kinds and
only consider it YAML front matter if none exist. Ensure you still skip over
MD_NEWLINE nodes when searching in both walks.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

Push a commit to this branch (recommended)
Create a new PR with the fixes

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 4d0aef8b-d49f-4d0e-9bd8-a2e48370d297

📥 Commits

Reviewing files that changed from the base of the PR and between 716e4e1 and 527c209.

⛔ Files ignored due to path filters (103)

crates/biome_markdown_formatter/tests/specs/prettier/markdown/blockquote/notext-end.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/emphasis/asterisk.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/emphasis/complex.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/emphasis/special.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/front-matter/custom-parser.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/front-matter/empty.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/heading/setext.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/liquid/unbalanced-mismatched-braces.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/liquid/unbalanced-object-close-only.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/liquid/unbalanced-object-open-only.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/liquid/unbalanced-template-close-only.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/liquid/unbalanced-template-open-only.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/combined-lists.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/interrupt.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/nested-checkbox.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/nested-tab.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/tab.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/markdown/real-world-case.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/markdown/test-case.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/paragraph/special-prefix.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-108.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-117.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-120.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-132.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-133.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-140.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-141.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-152.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-244.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-260.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-27.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-272.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-277.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-28.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-282.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-288.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-325.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-35.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-356.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-36.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-363.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-364.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-367.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-368.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-369.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-373.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-376.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-377.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-378.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-379.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-380.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-384.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-385.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-386.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-387.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-388.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-395.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-396.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-397.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-399.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-401.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-402.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-403.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-404.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-408.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-413.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-414.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-418.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-42.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-423.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-424.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-427.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-429.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-433.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-436.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-438.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-439.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-440.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-442.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-444.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-450.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-482.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-485.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-489.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-49.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-499.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-50.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-51.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-52.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-54.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-57.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-58.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-59.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-602.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-603.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-611.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-63.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-64.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-70.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-71.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-83.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/strong/underscore.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/yaml/trailing-spaces.md.snap is excluded by !**/*.snap and included by **

📒 Files selected for processing (7)

crates/biome_markdown_formatter/src/markdown/auxiliary/bullet.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/bullet_list_item.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/inline_emphasis.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/inline_italic.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/list_marker_prefix.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/setext_header.rs
crates/biome_markdown_formatter/tests/quick_test.rs

tidefield · 2026-04-01T14:14:19Z

@coderabbitai

coderabbitai · 2026-04-01T14:14:38Z

@tidefield Sure! I'll kick off another review pass to cover the latest commits. 🐇

🧠 Learnings used

Learnt from: tidefield
Repo: biomejs/biome PR: 9480
File: crates/biome_markdown_formatter/src/markdown/auxiliary/hard_line.rs:11-31
Timestamp: 2026-03-14T11:30:13.488Z
Learning: In `crates/biome_markdown_formatter/src/markdown/auxiliary/hard_line.rs`, `FormatMdHardLine::fmt_fields` is responsible for emitting `hard_line_break()` itself (not the caller). As of PR `#9480` (building on `#9331` by ematipico), the function branches on the token text: if it ends with `\` it emits `format_removed(&token)` + `text("\\", ...)` + `hard_line_break()`; otherwise it normalises to two trailing spaces via `format_removed(&token)` + `text("  ", ...)` + `hard_line_break()`. The callers in `inline_item_list.rs` and `paragraph.rs` do NOT add an extra `hard_line_break()`.

Learnt from: jfmcdowell
Repo: biomejs/biome PR: 0
File: :0-0
Timestamp: 2026-03-30T19:37:09.253Z
Learning: In `crates/biome_markdown_parser/src/syntax/fenced_code_block.rs`, there is an intentional asymmetry between opening and closing fence indent stripping inside list items:
- **Opening fence**: `check_continuation_indent` (called before the fenced code block parser runs) already consumes the list continuation indent, so the opener only needs to emit the remaining 0–3 CommonMark-allowed fence spaces (`MAX_BLOCK_PREFIX_INDENT`). Stripping `list_item_required_indent` in the opener is NOT needed.
- **Closing fence**: processes the raw line without prior consumption, so it must strip `list_item_required_indent + MAX_BLOCK_PREFIX_INDENT` itself (the fix introduced in PR `#9730`).

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.

Learnt from: arendjr
Repo: biomejs/biome PR: 7593
File: crates/biome_service/src/workspace/server.rs:1306-1306
Timestamp: 2025-09-25T12:32:59.003Z
Learning: In the biomejs/biome project, do not flag compilation errors during code review as they are handled by the existing test infrastructure and CI. Focus on other code quality aspects instead.

✅ Actions performed

Review triggered.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

dyc3

Nice progress on the prettier snapshots, but there's some perf concerns. Also, would like to see some new tests outside of the prettier folder that are more isolated than the prettier tests.

dyc3 · 2026-04-01T14:36:38Z

+                format_replaced(&l_fence?, &token("**")),
+                content.format(),
+                format_replaced(&r_fence?, &token("**")),


same here, reuse the existing tokens if they don't need changing

See this test https://github.com/tidefield/biome/blob/716e4e195d6a76f02850f3cf41b8b38b757708ec/crates/biome_markdown_formatter/tests/specs/prettier/markdown/strong/underscore.md.snap.

We want to normalize the __ to **.

If we write it as r_fence.format() as @ematipico suggested, it will be preserved as-is. Is this where we want to diverge from prettier? Or should we keep prettier's behavior?

IIUC, we'll need to make parser for the fences in MdInlineEmphasisFields more granular for it to format itself.

dyc3 · 2026-04-01T14:40:22Z

+        .filter(|s| s.kind() == MarkdownSyntaxKind::MD_BULLET_LIST_ITEM)
+        .count();
+
+    if count % 2 == 0 { "-" } else { "*" }


document why this exists

It's documented in the function comment. Does that suffice?

The docs might need updating, or a inline comment here, because there's MD_NEWLINE check that we don't know why it's used

I meant to highlight this whole block, but yeah, inline comments to explain the behavior are preferable because its easier to keep track of what code maps to which requirements.

This edge case is tricky. The idea is

By default, we normalize all the bullet marker to - except for case like * - - - or + - - - because normalizing will result to a thematic break. That is already done and hopefully easy-to-understand in this PR.

There is a scenario where we have bullet lists separated by MD_NEWLINE

- list A item 1 - list A item 2 * list B item 1 + list C item 1 + list C item 2

The split is determined by the new line between them and whether they are prefixed with different markers. See list C where new line doesn't cause it to split.

Click on HTML on this playground to better see what I mean.

I will follow-up with (2) in a follow-up PR. @coderabbitai file an issue for (2) and assign to me.

🧩 Analysis chain

On it! Filing the issue now.

🏁 Script executed:

gh issue create \ --repo biomejs/biome \ --title "feat(markdown): preserve bullet list separation when normalizing bullet markers" \ --assignee tidefield \ --body "## Summary When normalizing bullet list markers in the Markdown formatter, lists separated by blank lines (\`MD_NEWLINE\`) that use different markers should remain as separate lists in the output. ### Background CommonMark treats bullet lists with different markers as distinct list groups. For example: \`\`\`markdown - list A item 1 - list A item 2 * list B item 1 + list C item 1 + list C item 2 \`\`\` The blank line between items combined with a different marker causes them to be parsed as separate lists. List C shows that a blank line alone (without a marker change) does **not** split a list. See the [CommonMark playground](https://spec.commonmark.org/dingus/?text=-%20list%20A%20item%201%0A-%20list%20A%20item%202%0A%0A*%20list%20B%20item%201%0A%0A%2B%20list%20C%20item%201%0A%0A%2B%20list%20C%20item%202) to observe the rendered HTML difference. ### Current behaviour The current \`target_marker_for_bullet\` logic in \`crates/biome_markdown_formatter/src/markdown/auxiliary/bullet.rs\` walks up the sibling tree and alternates between \`-\` and \`*\` by counting preceding \`MD_BULLET_LIST_ITEM\` siblings (including across \`MD_NEWLINE\` nodes). This is a placeholder approach that does not correctly model list separation semantics. ### Expected behaviour The formatter should detect list boundaries (marker change + blank line) and preserve distinct list groups by assigning them different normalized markers, so that the formatted output retains the same list-separation semantics as the input. ### References - PR `#9693` (where this was deferred) - Comment: https://github.com/biomejs/biome/pull/9693#discussion_r3022558130 - CommonMark spec §[Lists](https://spec.commonmark.org/0.31.2/#lists) Requested by `@tidefield`. "

Length of output: 44

Let me look up the correct GitHub username and retry.

🏁 Script executed:

gh pr view 9693 --repo biomejs/biome --json author --jq '.author.login'

Length of output: 9

tidefield isn't an org member so GitHub won't allow direct assignment. Creating the issue with a mention instead.

🏁 Script executed:

gh issue create \ --repo biomejs/biome \ --title "feat(markdown): preserve bullet list separation when normalizing bullet markers" \ --body "## Summary When normalizing bullet list markers in the Markdown formatter, lists separated by blank lines (\`MD_NEWLINE\`) that use different markers should remain as separate lists in the output. ### Background CommonMark treats bullet lists with different markers as distinct list groups. For example: \`\`\`markdown - list A item 1 - list A item 2 * list B item 1 + list C item 1 + list C item 2 \`\`\` The blank line between items combined with a different marker causes them to be parsed as separate lists. List C shows that a blank line alone (without a marker change) does **not** split a list. See the [CommonMark playground](https://spec.commonmark.org/dingus/?text=-%20list%20A%20item%201%0A-%20list%20A%20item%202%0A%0A*%20list%20B%20item%201%0A%0A%2B%20list%20C%20item%201%0A%0A%2B%20list%20C%20item%202) to observe the rendered HTML difference. ### Current Behaviour The current \`target_marker_for_bullet\` logic in \`crates/biome_markdown_formatter/src/markdown/auxiliary/bullet.rs\` walks up the sibling tree and alternates between \`-\` and \`*\` by counting preceding \`MD_BULLET_LIST_ITEM\` siblings (including across \`MD_NEWLINE\` nodes). This is a placeholder approach that does not correctly model list separation semantics. ### Expected Behaviour The formatter should detect list boundaries (marker change + blank line) and preserve distinct list groups by assigning them different normalised markers, so that the formatted output retains the same list-separation semantics as the input. ### References - PR `#9693` (where this was deferred) - Comment: https://github.com/biomejs/biome/pull/9693#discussion_r3022558130 - CommonMark spec §[Lists](https://spec.commonmark.org/0.31.2/#lists) Requested by `@tidefield`. "

Length of output: 44

@tidefield, the follow-up issue has been filed: #9772 — "feat(markdown): preserve bullet list separation when normalizing bullet markers".

Note: GitHub wouldn't let me assign you directly (you'd need to be an org collaborator for that), but you're mentioned in the body. A maintainer can assign you manually if needed.

🧠 Learnings used

Learnt from: tidefield Repo: biomejs/biome PR: 9480 File: crates/biome_markdown_formatter/src/markdown/auxiliary/hard_line.rs:11-31 Timestamp: 2026-03-14T11:30:13.488Z Learning: In `crates/biome_markdown_formatter/src/markdown/auxiliary/hard_line.rs`, `FormatMdHardLine::fmt_fields` is responsible for emitting `hard_line_break()` itself (not the caller). As of PR `#9480` (building on `#9331` by ematipico), the function branches on the token text: if it ends with `\` it emits `format_removed(&token)` + `text("\\", ...)` + `hard_line_break()`; otherwise it normalises to two trailing spaces via `format_removed(&token)` + `text(" ", ...)` + `hard_line_break()`. The callers in `inline_item_list.rs` and `paragraph.rs` do NOT add an extra `hard_line_break()`.

Learnt from: jfmcdowell Repo: biomejs/biome PR: 0 File: :0-0 Timestamp: 2026-03-30T19:37:09.253Z Learning: In `crates/biome_markdown_parser/src/syntax/fenced_code_block.rs`, there is an intentional asymmetry between opening and closing fence indent stripping inside list items: - **Opening fence**: `check_continuation_indent` (called before the fenced code block parser runs) already consumes the list continuation indent, so the opener only needs to emit the remaining 0–3 CommonMark-allowed fence spaces (`MAX_BLOCK_PREFIX_INDENT`). Stripping `list_item_required_indent` in the opener is NOT needed. - **Closing fence**: processes the raw line without prior consumption, so it must strip `list_item_required_indent + MAX_BLOCK_PREFIX_INDENT` itself (the fix introduced in PR `#9730`).

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_formatter/CONTRIBUTING.md:0-0 Timestamp: 2026-02-05T16:31:32.222Z Learning: Applies to crates/biome_formatter/**/cst.rs : In `cst.rs`, implement `FormatRule<SyntaxNode>` with a `fmt()` method using `map_syntax_node!` macro and provide `AsFormat` and `IntoFormat` trait implementations

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_formatter/CONTRIBUTING.md:0-0 Timestamp: 2026-02-05T16:31:32.222Z Learning: Applies to crates/biome_formatter/**/verbatim.rs : Create `verbatim.rs` file with helper functions for verbatim formatting

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_js_formatter/CONTRIBUTING.md:0-0 Timestamp: 2025-11-24T18:05:27.810Z Learning: Applies to crates/biome_js_formatter/**/*.rs : Import the `FormatNode` trait and implement it for your Node when creating formatters in biome_js_formatter

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_formatter/CONTRIBUTING.md:0-0 Timestamp: 2026-02-05T16:31:32.222Z Learning: Applies to crates/biome_formatter/**/lib.rs : In `lib.rs`, implement `FormatLanguage` trait and expose public `format_node()` entry point for the formatter

Learnt from: jfmcdowell Repo: biomejs/biome PR: 9467 File: crates/biome_markdown_parser/src/syntax/inline/html.rs:52-56 Timestamp: 2026-03-13T01:32:42.719Z Learning: In the CommonMark 0.31 spec (and retained in 0.31.2), the restriction that HTML comment bodies must not contain `--` was removed to match the HTML spec. Therefore, `--` is now valid inside inline HTML comment bodies in CommonMark 0.31.2. The only body constraint is that it must not end with `-`. The old pre-0.31 rule rejecting `--` is no longer applicable.

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.

Learnt from: dyc3 Repo: biomejs/biome PR: 8901 File: crates/biome_analyze_macros/src/group_macro.rs:9-9 Timestamp: 2026-01-29T22:10:30.888Z Learning: Do not import xtask inside biome crates. In the biomeps repository, ensure that biome crates (e.g., crates/biome_*/...) do not have imports like use xtask_glue::... or other xtask-related crates. The correct dependency direction is for xtask to depend on and import biome crates, not the reverse, since xtask contains heavier utilities (e.g., git2) that can inflate build times when included in biome crates. When reviewing, verify dependency declarations (Cargo.toml) and any use statements to confirm xtask crates are not pulled into biome crates; prefer having xtask depend on biome crates and export needed functionality through stable interfaces.

dyc3 · 2026-04-01T14:46:01Z

+        let target = self.target_marker.unwrap_or("-");
+
+        write!(f, [pre_marker_indent.format()])?;
+        write!(f, [format_replaced(&marker, &token(target))])?;


reuse the existing token if not changed

Given

- (and 2 spaces)

the parser makes

1: MD_BULLET@6..11 0: MD_LIST_MARKER_PREFIX@6..10 0: MD_INDENT_TOKEN_LIST@6..6 1: MINUS@6..10 "- " [] []

we want to remove the trailing spaces. This is probably a bug in the parser. The next space should be in post_marker_space_token and the remaining spaces should be in content_indent, right?

cc @jfmcdowell

@coderabbitai file a bug and assign to me

@dyc3 in the meantime, I changed the code to reuse the marker token when possible.

🧩 Analysis chain

🏁 Script executed:

gh issue create \ --repo biomejs/biome \ --title "fix(markdown_parser): trailing spaces after list marker included in MINUS token instead of post_marker_space_token/content_indent" \ --assignee tidefield \ --body "## Summary In the Markdown parser, when a list item marker is followed by more than one space (e.g. \`- \` with two trailing spaces), the trailing spaces are incorrectly included inside the \`MINUS\` token text rather than being split into \`post_marker_space_token\` and \`content_indent\` as expected. ## Steps to Reproduce Parse a Markdown document containing a list item with extra trailing spaces after the marker: \`\`\`markdown - item \`\`\` ## Observed CST \`\`\` 1: MD_BULLET@6..11 0: MD_LIST_MARKER_PREFIX@6..10 0: MD_INDENT_TOKEN_LIST@6..6 1: MINUS@6..10 \"- \" [] [] \`\`\` The \`MINUS\` token text is \`\"- \"\` (including trailing spaces) instead of \`\"-\"\`. ## Expected CST The trailing spaces should be split into \`post_marker_space_token\` (one space) and \`content_indent\` (remaining spaces), with the \`MINUS\` token containing only \`\"-\"\`. ## Impact This causes the formatter in \`list_marker_prefix.rs\` to be unable to safely reuse the existing marker token (since it contains trailing spaces), requiring a workaround via \`format_replaced\`. ## References - PR: https://github.com/biomejs/biome/pull/9693 - Comment: https://github.com/biomejs/biome/pull/9693#discussion_r3022595641 Reported by `@tidefield` "

Length of output: 44

🏁 Script executed:

gh issue create \ --repo biomejs/biome \ --title "fix(markdown_parser): trailing spaces after list marker included in MINUS token instead of post_marker_space_token/content_indent" \ --body "## Summary In the Markdown parser, when a list item marker is followed by more than one space (e.g. \`- \` with two trailing spaces), the trailing spaces are incorrectly included inside the \`MINUS\` token text rather than being split into \`post_marker_space_token\` and \`content_indent\` as expected. ## Steps to Reproduce Parse a Markdown document containing a list item with extra trailing spaces after the marker: \`\`\`markdown - item \`\`\` ## Observed CST \`\`\` 1: MD_BULLET@6..11 0: MD_LIST_MARKER_PREFIX@6..10 0: MD_INDENT_TOKEN_LIST@6..6 1: MINUS@6..10 \"- \" [] [] \`\`\` The \`MINUS\` token text is \`\"- \"\` (including trailing spaces) instead of \`\"-\"\`. ## Expected CST The trailing spaces should be split into \`post_marker_space_token\` (one space) and \`content_indent\` (remaining spaces), with the \`MINUS\` token containing only \`\"-\"\`. ## Impact This causes the formatter in \`list_marker_prefix.rs\` to be unable to safely reuse the existing marker token (since it contains trailing spaces), requiring a workaround via \`format_replaced\`. ## References - PR: https://github.com/biomejs/biome/pull/9693 - Comment: https://github.com/biomejs/biome/pull/9693#discussion_r3022595641 Reported by `@tidefield` "

Length of output: 44

@tidefield, done! Filed the parser bug here: #9770

Unfortunately the GitHub CLI couldn't resolve your username for auto-assignment — you'll need to self-assign it directly on the issue page. 🐛

🧠 Learnings used

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_formatter/CONTRIBUTING.md:0-0 Timestamp: 2026-02-05T16:31:32.222Z Learning: Applies to crates/biome_formatter/**/cst.rs : In `cst.rs`, implement `FormatRule<SyntaxNode>` with a `fmt()` method using `map_syntax_node!` macro and provide `AsFormat` and `IntoFormat` trait implementations

Learnt from: tidefield Repo: biomejs/biome PR: 9480 File: crates/biome_markdown_formatter/src/markdown/auxiliary/hard_line.rs:11-31 Timestamp: 2026-03-14T11:30:13.488Z Learning: In `crates/biome_markdown_formatter/src/markdown/auxiliary/hard_line.rs`, `FormatMdHardLine::fmt_fields` is responsible for emitting `hard_line_break()` itself (not the caller). As of PR `#9480` (building on `#9331` by ematipico), the function branches on the token text: if it ends with `\` it emits `format_removed(&token)` + `text("\\", ...)` + `hard_line_break()`; otherwise it normalises to two trailing spaces via `format_removed(&token)` + `text(" ", ...)` + `hard_line_break()`. The callers in `inline_item_list.rs` and `paragraph.rs` do NOT add an extra `hard_line_break()`.

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_js_formatter/CONTRIBUTING.md:0-0 Timestamp: 2025-11-24T18:05:27.810Z Learning: Applies to crates/biome_js_formatter/**/*.rs : Import the `FormatNode` trait and implement it for your Node when creating formatters in biome_js_formatter

Learnt from: jfmcdowell Repo: biomejs/biome PR: 0 File: :0-0 Timestamp: 2026-03-30T19:37:09.253Z Learning: In `crates/biome_markdown_parser/src/syntax/fenced_code_block.rs`, there is an intentional asymmetry between opening and closing fence indent stripping inside list items: - **Opening fence**: `check_continuation_indent` (called before the fenced code block parser runs) already consumes the list continuation indent, so the opener only needs to emit the remaining 0–3 CommonMark-allowed fence spaces (`MAX_BLOCK_PREFIX_INDENT`). Stripping `list_item_required_indent` in the opener is NOT needed. - **Closing fence**: processes the raw line without prior consumption, so it must strip `list_item_required_indent + MAX_BLOCK_PREFIX_INDENT` itself (the fix introduced in PR `#9730`).

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_formatter/CONTRIBUTING.md:0-0 Timestamp: 2026-02-05T16:31:32.222Z Learning: Applies to crates/biome_formatter/**/verbatim.rs : Create `verbatim.rs` file with helper functions for verbatim formatting

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_formatter/CONTRIBUTING.md:0-0 Timestamp: 2026-02-05T16:31:32.222Z Learning: Run `just gen-formatter` to automatically generate formatter boilerplate code in `crates/biome_<language>_formatter/src/` with module structure and default `FormatNodeRule<N>` implementations

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_formatter/CONTRIBUTING.md:0-0 Timestamp: 2026-02-05T16:31:32.222Z Learning: Applies to crates/biome_formatter/**/lib.rs : In `lib.rs`, implement `FormatLanguage` trait and expose public `format_node()` entry point for the formatter

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_js_formatter/CONTRIBUTING.md:0-0 Timestamp: 2025-11-24T18:05:27.810Z Learning: Applies to crates/biome_js_formatter/**/*.rs : When formatting AST nodes, use mandatory tokens from the AST instead of hardcoding token strings (e.g., use `node.l_paren_token().format()` instead of `token("(")`)

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_formatter/CONTRIBUTING.md:0-0 Timestamp: 2026-02-05T16:31:32.222Z Learning: Applies to crates/biome_formatter/**/context.rs : In `context.rs`, implement `FormatContext`, `FormatOptions`, and `CstFormatContext` traits with a struct holding `options`, `comments` (as `Rc<Comments>`), and optional `source_map`

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-03-21T17:22:03.949Z Learning: Applies to crates/biome_analyze/**/lint/**/*.rs : Use Starlight aside syntax (':::note', ':::tip', ':::caution', ':::danger') in rule documentation to highlight important information

Learnt from: CR Repo: biomejs/biome PR: 0 File: crates/biome_analyze/CONTRIBUTING.md:0-0 Timestamp: 2026-03-21T17:22:03.949Z Learning: Applies to crates/biome_analyze/**/lint/**/*.rs : Document rule options in a '## Options' section with h3 headers for each option, describing what it does, its default value, and providing code examples

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.

Learnt from: dyc3 Repo: biomejs/biome PR: 8901 File: crates/biome_analyze_macros/src/group_macro.rs:9-9 Timestamp: 2026-01-29T22:10:30.888Z Learning: Do not import xtask inside biome crates. In the biomeps repository, ensure that biome crates (e.g., crates/biome_*/...) do not have imports like use xtask_glue::... or other xtask-related crates. The correct dependency direction is for xtask to depend on and import biome crates, not the reverse, since xtask contains heavier utilities (e.g., git2) that can inflate build times when included in biome crates. When reviewing, verify dependency declarations (Cargo.toml) and any use statements to confirm xtask crates are not pulled into biome crates; prefer having xtask depend on biome crates and export needed functionality through stable interfaces.

coderabbitai

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@crates/biome_markdown_formatter/src/markdown/auxiliary/bullet.rs`:
- Around line 22-25: The current early-return uses
format_verbatim_node(node.syntax()).fmt(f) when marker_kind !=
MarkdownSyntaxKind::MINUS and first_block_is_dash_thematic_break(&content),
which preserves the entire item verbatim and prevents formatting later blocks;
instead, preserve only the original marker and recurse into the item content so
subsequent blocks are formatted. Replace the verbatim formatting with logic that
captures the existing marker token (use the same marker used to compute
marker_kind/target_marker), call the prefix formatter with that target_marker
(the same API the prefix formatter already accepts), and then format/recurse
into the content nodes normally (e.g., the function that formats children or
content) rather than returning the whole node as verbatim; keep the
first_block_is_dash_thematic_break guard but ensure you only emit the preserved
marker and continue formatting the rest.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

Push a commit to this branch (recommended)
Create a new PR with the fixes

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 6d9439b6-3757-4f24-a44b-96c770fbfdd2

📥 Commits

Reviewing files that changed from the base of the PR and between eec4e91 and 88b217a.

📒 Files selected for processing (1)

crates/biome_markdown_formatter/src/markdown/auxiliary/bullet.rs

ematipico

We should also tests of our own. While we have Prettier as an harness, that's not sufficient. We must add new tests as we cover all the cases.

Also:

no format_verbatim. That function is created during codegen so the formatter doesn't panic, but during the implementation must be removed
the use of format_replaced is sometimes not needed
inconsistent use of the try operator
handling of invalid syntax for now reason

@tidefield please be more careful with the emitted code, and please ask questions if you have doubts, don't always rely on the emitted code of an agent. If there's something I learnt, is that AI agents are very bad inside our formatter. It's preferable doing things manually

ematipico · 2026-04-01T15:01:38Z

+        .filter(|s| s.kind() == MarkdownSyntaxKind::MD_BULLET_LIST_ITEM)
+        .count();
+
+    if count % 2 == 0 { "-" } else { "*" }


The docs might need updating, or a inline comment here, because there's MD_NEWLINE check that we don't know why it's used

tidefield · 2026-04-01T15:21:47Z

Thanks @dyc3 @ematipico for the review. I'll address the comments.

My first major formatter PR. Sorry for silly mistakes.

tidefield

Hey @dyc3 and @ematipico . Thanks again. I addressed most of your comments except for crates/biome_markdown_formatter/src/markdown/auxiliary/inline_italic.rs. I likely will want to just revert it and re-do it in a different PR.

I'm learning a lot. I'll do better in my next PRs.

tidefield · 2026-04-02T04:52:28Z

+                format_replaced(&l_fence?, &token("**")),
+                content.format(),
+                format_replaced(&r_fence?, &token("**")),


See this test https://github.com/tidefield/biome/blob/716e4e195d6a76f02850f3cf41b8b38b757708ec/crates/biome_markdown_formatter/tests/specs/prettier/markdown/strong/underscore.md.snap.

We want to normalize the __ to **.

If we write it as r_fence.format() as @ematipico suggested, it will be preserved as-is. Is this where we want to diverge from prettier? Or should we keep prettier's behavior?

tidefield · 2026-04-02T04:54:16Z

+                format_replaced(&l_fence?, &token("**")),
+                content.format(),
+                format_replaced(&r_fence?, &token("**")),


IIUC, we'll need to make parser for the fences in MdInlineEmphasisFields more granular for it to format itself.

tidefield · 2026-04-02T09:07:32Z

+        let target = self.target_marker.unwrap_or("-");
+
+        write!(f, [pre_marker_indent.format()])?;
+        write!(f, [format_replaced(&marker, &token(target))])?;


Given

- (and 2 spaces)

the parser makes

1: MD_BULLET@6..11 0: MD_LIST_MARKER_PREFIX@6..10 0: MD_INDENT_TOKEN_LIST@6..6 1: MINUS@6..10 "- " [] []

we want to remove the trailing spaces. This is probably a bug in the parser. The next space should be in post_marker_space_token and the remaining spaces should be in content_indent, right?

cc @jfmcdowell

tidefield · 2026-04-02T09:12:29Z

+        let target = self.target_marker.unwrap_or("-");
+
+        write!(f, [pre_marker_indent.format()])?;
+        write!(f, [format_replaced(&marker, &token(target))])?;


@coderabbitai file a bug and assign to me

@dyc3 in the meantime, I changed the code to reuse the marker token when possible.

tidefield · 2026-04-02T09:20:16Z

+        write!(
+            f,
+            [
+                format_replaced(&l_fence?, &token("**")),


Hmm the fences aren't separate nodes. They are just SyntaxTokens. Should we fix the parser to make it more granular?

If not, I think l_fence.format() just keeps it as-is which will diverge from prettier's behavior. Do we want that?

coderabbitai

♻️ Duplicate comments (1)

crates/biome_markdown_formatter/src/markdown/auxiliary/inline_italic.rs (1)
27-28: ⚠️ Potential issue | 🟠 Major

Please keep the nested-italic branch field-based.

Line 28 reintroduces format_verbatim_node in active formatter logic, so nested-italic cases stop participating in formatting altogether. If this case needs a temporary escape hatch, preserving the existing fences is still a better fit than bailing out to verbatim. Based on learnings: format_verbatim_node is only acceptable as initial scaffolding; new feature code must format the node’s fields explicitly instead.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@crates/biome_markdown_formatter/src/markdown/auxiliary/inline_italic.rs`
around lines 27 - 28, The nested-italic branch currently bails out to
format_verbatim_node(node.syntax()) which removes this case from active
formatting; instead keep the nested-italic branch field-based: remove the call
to format_verbatim_node and implement explicit formatting of the node’s fields
(preserve the existing fence characters/markers) inside the same branch so
nested-italic participates in normal formatting; update the branch that checks
has_nested_italic to write to the same formatter variable f using the node’s
field accessors rather than delegating to format_verbatim_node.

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Duplicate comments:
In `@crates/biome_markdown_formatter/src/markdown/auxiliary/inline_italic.rs`:
- Around line 27-28: The nested-italic branch currently bails out to
format_verbatim_node(node.syntax()) which removes this case from active
formatting; instead keep the nested-italic branch field-based: remove the call
to format_verbatim_node and implement explicit formatting of the node’s fields
(preserve the existing fence characters/markers) inside the same branch so
nested-italic participates in normal formatting; update the branch that checks
has_nested_italic to write to the same formatter variable f using the node’s
field accessors rather than delegating to format_verbatim_node.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: c6bd12d9-709b-4a3e-a055-66b0ef42f78c

📥 Commits

Reviewing files that changed from the base of the PR and between 88b217a and 5cf9e4a.

⛔ Files ignored due to path filters (95)

crates/biome_markdown_formatter/tests/specs/markdown/blockquote.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/markdown/bullet_list.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/markdown/inline_image.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/blockquote/ignore-code.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/blockquote/notext-end.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/break/simple.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/emphasis/asterisk.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/emphasis/complex.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/emphasis/special.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/front-matter/custom-parser.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/front-matter/empty.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/liquid/unbalanced-mismatched-braces.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/liquid/unbalanced-object-close-only.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/liquid/unbalanced-object-open-only.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/liquid/unbalanced-template-close-only.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/liquid/unbalanced-template-open-only.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/combined-lists.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/interrupt.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/issue-7846.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/nested-checkbox.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/nested-tab.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/separate.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/list/tab.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/markdown/real-world-case.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/markdown/test-case.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/paragraph/special-prefix.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-117.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-120.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-133.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-140.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-141.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-152.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-222.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-244.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-260.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-269.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-272.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-277.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-28.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-282.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-288.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-325.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-35.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-356.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-36.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-363.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-364.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-367.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-368.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-369.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-373.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-376.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-377.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-378.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-379.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-380.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-384.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-385.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-386.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-387.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-388.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-395.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-396.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-397.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-399.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-401.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-402.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-403.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-404.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-408.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-413.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-414.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-418.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-42.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-423.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-424.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-427.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-429.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-433.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-436.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-438.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-439.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-440.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-442.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-444.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-450.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-482.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-485.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-489.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-499.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-602.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-603.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/spec/example-611.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/strong/underscore.md.snap is excluded by !**/*.snap and included by **
crates/biome_markdown_formatter/tests/specs/prettier/markdown/yaml/trailing-spaces.md.snap is excluded by !**/*.snap and included by **

📒 Files selected for processing (8)

crates/biome_markdown_formatter/src/markdown/auxiliary/bullet.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/bullet_list_item.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/header.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/inline_emphasis.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/inline_italic.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/list_marker_prefix.rs
crates/biome_markdown_formatter/tests/quick_test.rs
crates/biome_markdown_formatter/tests/specs/markdown/bullet_list.md

✅ Files skipped from review due to trivial changes (4)

crates/biome_markdown_formatter/tests/specs/markdown/bullet_list.md
crates/biome_markdown_formatter/src/markdown/auxiliary/bullet_list_item.rs
crates/biome_markdown_formatter/tests/quick_test.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/header.rs

🚧 Files skipped from review as they are similar to previous changes (2)

crates/biome_markdown_formatter/src/markdown/auxiliary/inline_emphasis.rs
crates/biome_markdown_formatter/src/markdown/auxiliary/list_marker_prefix.rs

tidefield · 2026-04-03T10:30:31Z

+        write!(
+            f,
+            [
+                format_replaced(&l_fence?, &token("**")),


You want to do something similar, so that you can read which fence we have. If the fence is DoubleStar, we just format it l_fence.format(), if not, we replace. Does it make sense?

Actually if we still having to end up do a if-check for DoubleStar and this level, I think we can just check for MarkdownSyntaxKind::DOUBLE_STAR without having to go the route you describe, right?

if l_fence.kind() == MarkdownSyntaxKind::DOUBLE_STAR { write!(f, [l_fence.format(), content.format(), r_fence.format()]) } else { write!( f, [ format_replaced(&l_fence, &token("**")), content.format(), format_replaced(&r_fence, &token("**")), ] ) }

will you agree with this?

tidefield · 2026-04-03T11:38:32Z

+        write!(
+            f,
+            [
+                format_replaced(&l_fence?, &token("**")),


As I write in https://github.com/biomejs/biome/pull/9693/changes#r3032530256, I think it's still better to move this logic to inside fence instead of. here. Do you mind if I tackle it in a different PR if you agree with the approach?

ematipico · 2026-04-04T05:26:15Z

@tidefield there are still comments of mine that haven't been addressed

tidefield

@ematipico sorry, I didn't mean to leave things open.

I wanted to ask you about whether we can support option for fence token before continuing.

There's another trivial code suggestion. I left it unresolved just so I don't forget to apply it.

Other than, I don't think there's anything else right?

tidefield

@ematipico I believe all your comments are addressed.

I wanted to see if there's a better way to implement the reuse logic for fence tokens but it seems we can't go further given the infrastructure.

I filed #9770 and #9772 while going through the comments so I can tackle the them separately.

Co-authored-by: Carson McManus <dyc3@users.noreply.github.com>

ematipico

Great work @tidefield , thank you

Comments addressed

github-actions bot added A-Formatter Area: formatter L-Markdown Language: Markdown labels Mar 29, 2026

tidefield force-pushed the md-formatter-basic branch from f7083fd to b1c73d8 Compare April 1, 2026 11:31

coderabbitai bot reviewed Apr 1, 2026

View reviewed changes

Comment thread crates/biome_markdown_formatter/src/markdown/auxiliary/bullet.rs Outdated

tidefield changed the title ~~[Draft] Implement basic formatting for Markdown~~ feat(markdown): Implement basic formatting features Apr 1, 2026

tidefield changed the title ~~feat(markdown): Implement basic formatting features~~ feat(markdown): implement basic formatting features Apr 1, 2026

tidefield marked this pull request as ready for review April 1, 2026 14:14

dyc3 previously requested changes Apr 1, 2026

View reviewed changes

coderabbitai bot reviewed Apr 1, 2026

View reviewed changes

Comment thread crates/biome_markdown_formatter/src/markdown/auxiliary/bullet.rs Outdated

ematipico requested changes Apr 1, 2026

View reviewed changes

tidefield commented Apr 2, 2026

View reviewed changes

tidefield force-pushed the md-formatter-basic branch from 374b488 to 5cf9e4a Compare April 2, 2026 09:37

tidefield changed the title ~~feat(markdown): implement basic formatting features~~ feat(markdown): implement basic formatter features Apr 2, 2026

coderabbitai bot reviewed Apr 2, 2026

View reviewed changes

tidefield force-pushed the md-formatter-basic branch 2 times, most recently from 903d837 to f7f561f Compare April 3, 2026 11:40

tidefield commented Apr 3, 2026

View reviewed changes

tidefield requested a review from ematipico April 3, 2026 11:42

tidefield requested a review from dyc3 April 3, 2026 11:42

coderabbitai bot mentioned this pull request Apr 3, 2026

markdown formatter: nested italic falls back to format_verbatim_node due to skipped tokens #9791

Open

tidefield commented Apr 4, 2026

View reviewed changes

Comment thread crates/biome_markdown_formatter/src/markdown/auxiliary/bullet.rs

Comment thread crates/biome_markdown_formatter/src/markdown/auxiliary/inline_italic.rs

github-actions bot added the A-Parser Area: parser label Apr 4, 2026

tidefield and others added 13 commits April 4, 2026 21:54

Implement basic formatting for Markdown

13752df

Fix FormatMdTextualOptions usage

9f12a10

Rebase with latest main

f26be38

Revert already formatted nodes

182b255

Remove complex formatting to save it to next PR

c125056

[autofix.ci] apply automated fixes

6bff558

Update bullet.rs

ff5ed7e

Co-authored-by: Carson McManus <dyc3@users.noreply.github.com>

Address code review

1a4bd5e

Address code review

b2ff64d

Address clippy warning

9a59616

Address code review

1dfa6dd

Implement typed reprensentation for fence tokens of MdInlineEmphasis

a9d4b02

clippy fix

0e5da05

tidefield force-pushed the md-formatter-basic branch from 2cfcdf5 to 0e5da05 Compare April 4, 2026 14:54

ematipico approved these changes Apr 6, 2026

View reviewed changes

ematipico merged commit 75454bd into biomejs:main Apr 6, 2026
16 checks passed

This was referenced Apr 12, 2026

feat(md/fmt): autolink, setext header #9929

Merged

feat(fmt/md): ordered lists and space normalization #9998

Open

Uh oh!

Conversation

tidefield commented Mar 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Test Plan

Docs

Uh oh!

changeset-bot bot commented Mar 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

⚠️ No Changeset found

Uh oh!

tidefield commented Apr 1, 2026

Uh oh!

coderabbitai bot commented Apr 1, 2026

Uh oh!

codspeed-hq bot commented Apr 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Merging this PR will not alter performance

Footnotes

Uh oh!

tidefield commented Apr 1, 2026

Uh oh!

coderabbitai bot commented Apr 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Reviews paused

Walkthrough

Possibly related PRs

Suggested reviewers

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

tidefield commented Apr 1, 2026

Uh oh!

coderabbitai bot commented Apr 1, 2026

Uh oh!

dyc3 left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

coderabbitai bot Apr 2, 2026

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

coderabbitai bot Apr 2, 2026

Choose a reason for hiding this comment

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

ematipico left a comment

Choose a reason for hiding this comment

Uh oh!

tidefield commented Mar 29, 2026 •

edited

Loading

changeset-bot bot commented Mar 29, 2026 •

edited

Loading

codspeed-hq bot commented Apr 1, 2026 •

edited

Loading

coderabbitai bot commented Apr 1, 2026 •

edited

Loading

tidefield commented Apr 1, 2026 •

edited

Loading

tidefield left a comment •

edited

Loading