fix(es/resolver): Merge re-opened TypeScript namespace scopes by MavenRain · Pull Request #11872 · swc-project/swc

MavenRain · 2026-05-20T02:30:43Z

Description

Closes #11607. Unblocks #11514.

In TypeScript, re-declaring a namespace with the same name merges it;
identifiers in any declaration's body see bindings declared in earlier
declarations. SWC's resolver was creating a fresh block scope (with
Mark::fresh) for every namespace X { ... } body, leaving sibling
re-declarations with disjoint scopes. Lookups in the second body walked their
own (empty) scope, then fell through to the outer scope and resolved to
whatever happened to be declared there.

Repro (also added as tests/ts-resolver/namespace_reopen)

  namespace Test {
      export const a = 1;
  }
  const a = "out";
  namespace Test {
      export const b = a + 1;  // `a` should be Test.a, not outer
  }

Before: a resolved to outer const a (a__2).
After: a resolves to Test.a from the first body (a__3).

Fix

A Resolver now carries a Rc<RefCell<FxHashMap<(Mark, Atom), NamespaceBody>>>
cache keyed by (parent_scope.mark, namespace_name). On
visit_mut_ts_module_decl:

If a cache entry exists for this key, the child scope adopts the cached
mark, declared symbols, and declared types before visiting the body. All
earlier-declaration bindings are visible to lookups, and the merged scope's
mark is preserved so identifiers across declarations share a SyntaxContext.
After visiting, the child writes its accumulated bindings back to the
cache, so a third (or fourth) re-declaration sees the union.

Cache keying on the parent scope's mark makes nested namespace re-opens behave
correctly: namespace Outer { namespace Inner {} } namespace Outer { namespace
Inner {} } merges the outer pair, then the inner pair (whose parent mark is
now the outer's merged mark) also merges.

Test coverage

The new fixture under tests/ts-resolver/namespace_reopen exercises the issue's
exact repro. The full swc_ecma_transforms_base test suite (~7500 tests,
including the 5182-fixture ts_resolver corpus) passes unchanged.

changeset-bot · 2026-05-20T02:30:49Z

⚠️ No Changeset found

Latest commit: 22dca84

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.

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

CLAassistant · 2026-05-20T02:30:50Z

All committers have signed the CLA.

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: b94ef6823a

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

codspeed-hq · 2026-05-20T02:48:06Z

Merging this PR will not alter performance

✅ 189 untouched benchmarks
⏩ 120 skipped benchmarks¹

_{Comparing MavenRain:fix/resolver-namespace-merge (22dca84) with main (dcc0f2d)²}

120 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. ↩
No successful run was found on main (bef16f3) during the generation of this report, so dcc0f2d was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩

MavenRain · 2026-05-20T22:24:52Z

I updated 18 fixture files (16 crates/swc/tests/tsc-references/* files, plus swc_ecma_transforms_typescript's namespace_004 snapshot and namespace-and-enum/output.js) to reflect the merged-namespace resolver
output. All eight CI-failing fixtures exercise re-opened module/namespace blocks; after the resolver fix the downstream TypeScript transform correctly recognizes them as the same binding and emits (N.E) instead of the defensive (N.E || (N.E = {})) on re-opens after the first. Runtime behavior is unchanged (|| short-circuits to the already-created object in the old emission).

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: cee5448477

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

@magic-akari

Address review feedback from @magic-akari / Codex on swc-project#11872: only `export …` declarations should be shared across sibling re-opens of a TypeScript namespace, not every declaration. Each re-open now gets a fresh per-body scope for its private bindings; only exported names live in the cache-backed `NamespaceExportScope`, which the body scope exposes via a `shared` link so reference lookups still see sibling-declared exports with a stable `SyntaxContext`. A per-body pre-scan of `export` declarations drives the routing in `modify`, making the decision order-independent: TypeScript's var/function same-body merge still holds (`export var a = 1; for (var a; …)`) while a non-exported re-open of a sibling-exported name stays isolated — fixing the `namespace_004` `MyEnum.A` `1`→`2` regression Codex flagged. Added tests/ts-resolver/namespace_reopen_private covering @magic-akari's example; updated fixture snapshots accordingly (re-opened non-exported classes / enums no longer trigger the "defined multiple times" diagnostic). Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: d9ffafbeba

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

…pens Address Codex P1 on swc-project#11872: the cache key for `TsModuleDecl` previously used `self.namespace_export.mark` whenever it was present, so a nested namespace declared inside an outer namespace body was always keyed to the outer's stable export mark. That made the two `Inner` declarations in namespace Outer { namespace Inner { export const a = 1 } } namespace Outer { namespace Inner { export const b = a } } collide on a single cache entry and merge, even though TypeScript keeps non-exported members local to each declaration body. The cache-parent mark now falls back to `self.current.mark` (the outer re-open's per-body mark) unless the nested namespace name is in the enclosing body's pre-scanned `namespace_export_names`. Two outer re-opens hold distinct body marks, so their non-exported `Inner` children land in disjoint cache entries and stay isolated; exported nested namespaces still key on the outer's stable export mark and merge across re-opens. Added tests/ts-resolver/namespace_reopen_nested_private exercising the Codex case (second `Inner`'s reference to `a` is unresolved, confirming isolation). nested namespaces still key on the outer's stable export mark and merge across re-opens. Added tests/ts-resolver/namespace_reopen_nested_private exercising the Codex case (second `Inner`'s reference to `a` is unresolved, confirming isolation). Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: bf4ec2a736

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

@magic-akari

Address review feedback from @magic-akari / Codex on swc-project#11872: only `export …` declarations should be shared across sibling re-opens of a TypeScript namespace, not every declaration. Each re-open now gets a fresh per-body scope for its private bindings; only exported names live in the cache-backed `NamespaceExportScope`, which the body scope exposes via a `shared` link so reference lookups still see sibling-declared exports with a stable `SyntaxContext`. A per-body pre-scan of `export` declarations drives the routing in `modify`, making the decision order-independent: TypeScript's var/function same-body merge still holds (`export var a = 1; for (var a; …)`) while a non-exported re-open of a sibling-exported name stays isolated — fixing the `namespace_004` `MyEnum.A` `1`→`2` regression Codex flagged. Added tests/ts-resolver/namespace_reopen_private covering @magic-akari's example; updated fixture snapshots accordingly (re-opened non-exported classes / enums no longer trigger the "defined multiple times" diagnostic). Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

…pens Address Codex P1 on swc-project#11872: the cache key for `TsModuleDecl` previously used `self.namespace_export.mark` whenever it was present, so a nested namespace declared inside an outer namespace body was always keyed to the outer's stable export mark. That made the two `Inner` declarations in namespace Outer { namespace Inner { export const a = 1 } } namespace Outer { namespace Inner { export const b = a } } collide on a single cache entry and merge, even though TypeScript keeps non-exported members local to each declaration body. The cache-parent mark now falls back to `self.current.mark` (the outer re-open's per-body mark) unless the nested namespace name is in the enclosing body's pre-scanned `namespace_export_names`. Two outer re-opens hold distinct body marks, so their non-exported `Inner` children land in disjoint cache entries and stay isolated; exported nested namespaces still key on the outer's stable export mark and merge across re-opens. Added tests/ts-resolver/namespace_reopen_nested_private exercising the Codex case (second `Inner`'s reference to `a` is unresolved, confirming isolation). nested namespaces still key on the outer's stable export mark and merge across re-opens. Added tests/ts-resolver/namespace_reopen_nested_private exercising the Codex case (second `Inner`'s reference to `a` is unresolved, confirming isolation). Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 450fd85e81

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

@magic-akari

Address review feedback from @magic-akari / Codex on swc-project#11872: only `export …` declarations should be shared across sibling re-opens of a TypeScript namespace, not every declaration. Each re-open now gets a fresh per-body scope for its private bindings; only exported names live in the cache-backed `NamespaceExportScope`, which the body scope exposes via a `shared` link so reference lookups still see sibling-declared exports with a stable `SyntaxContext`. A per-body pre-scan of `export` declarations drives the routing in `modify`, making the decision order-independent: TypeScript's var/function same-body merge still holds (`export var a = 1; for (var a; …)`) while a non-exported re-open of a sibling-exported name stays isolated — fixing the `namespace_004` `MyEnum.A` `1`→`2` regression Codex flagged. Added tests/ts-resolver/namespace_reopen_private covering @magic-akari's example; updated fixture snapshots accordingly (re-opened non-exported classes / enums no longer trigger the "defined multiple times" diagnostic). Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

…pens Address Codex P1 on swc-project#11872: the cache key for `TsModuleDecl` previously used `self.namespace_export.mark` whenever it was present, so a nested namespace declared inside an outer namespace body was always keyed to the outer's stable export mark. That made the two `Inner` declarations in namespace Outer { namespace Inner { export const a = 1 } } namespace Outer { namespace Inner { export const b = a } } collide on a single cache entry and merge, even though TypeScript keeps non-exported members local to each declaration body. The cache-parent mark now falls back to `self.current.mark` (the outer re-open's per-body mark) unless the nested namespace name is in the enclosing body's pre-scanned `namespace_export_names`. Two outer re-opens hold distinct body marks, so their non-exported `Inner` children land in disjoint cache entries and stay isolated; exported nested namespaces still key on the outer's stable export mark and merge across re-opens. Added tests/ts-resolver/namespace_reopen_nested_private exercising the Codex case (second `Inner`'s reference to `a` is unresolved, confirming isolation). nested namespaces still key on the outer's stable export mark and merge across re-opens. Added tests/ts-resolver/namespace_reopen_nested_private exercising the Codex case (second `Inner`'s reference to `a` is unresolved, confirming isolation). Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

…wc-project#11607) Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

…pe resolver output Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

@magic-akari

Address review feedback from @magic-akari / Codex on swc-project#11872: only `export …` declarations should be shared across sibling re-opens of a TypeScript namespace, not every declaration. Each re-open now gets a fresh per-body scope for its private bindings; only exported names live in the cache-backed `NamespaceExportScope`, which the body scope exposes via a `shared` link so reference lookups still see sibling-declared exports with a stable `SyntaxContext`. A per-body pre-scan of `export` declarations drives the routing in `modify`, making the decision order-independent: TypeScript's var/function same-body merge still holds (`export var a = 1; for (var a; …)`) while a non-exported re-open of a sibling-exported name stays isolated — fixing the `namespace_004` `MyEnum.A` `1`→`2` regression Codex flagged. Added tests/ts-resolver/namespace_reopen_private covering @magic-akari's example; updated fixture snapshots accordingly (re-opened non-exported classes / enums no longer trigger the "defined multiple times" diagnostic). Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

…pens Address Codex P1 on swc-project#11872: the cache key for `TsModuleDecl` previously used `self.namespace_export.mark` whenever it was present, so a nested namespace declared inside an outer namespace body was always keyed to the outer's stable export mark. That made the two `Inner` declarations in namespace Outer { namespace Inner { export const a = 1 } } namespace Outer { namespace Inner { export const b = a } } collide on a single cache entry and merge, even though TypeScript keeps non-exported members local to each declaration body. The cache-parent mark now falls back to `self.current.mark` (the outer re-open's per-body mark) unless the nested namespace name is in the enclosing body's pre-scanned `namespace_export_names`. Two outer re-opens hold distinct body marks, so their non-exported `Inner` children land in disjoint cache entries and stay isolated; exported nested namespaces still key on the outer's stable export mark and merge across re-opens. Added tests/ts-resolver/namespace_reopen_nested_private exercising the Codex case (second `Inner`'s reference to `a` is unresolved, confirming isolation). nested namespaces still key on the outer's stable export mark and merge across re-opens. Added tests/ts-resolver/namespace_reopen_nested_private exercising the Codex case (second `Inner`'s reference to `a` is unresolved, confirming isolation). Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

`pre_scan_namespace_exports` only inspected `ModuleDecl::ExportDecl`, so `export import A = ...` (a `TsImportEqualsDecl { is_export: true, .. }`) was never added to `namespace_export_names`. The alias binding was then routed to the body-local scope instead of the namespace's merged export scope, and references from sibling re-opens of the same namespace fell through to outer/unresolved bindings, violating TypeScript's namespace-merge semantics. Recognise the exported import-equals form in the pre-scan, adding the alias to `values` (and to `types` when not `is_type_only`), mirroring how `export namespace`/`export class`/`export enum` are tracked. The existing `visit_mut_ts_import_equals_decl` `modify` call now routes the binding to the shared export scope, and type-position lookups in sibling bodies resolve through `mark_for_ref_inner`'s `declared_types -> declared_symbols` fall-through. Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

kdy1 · 2026-06-12T08:33:23Z

@magic-akari Can you take a look?

magic-akari · 2026-06-17T14:36:39Z

After reviewing the test snapshots and generated outputs, no issues have been found so far.

magic-akari · 2026-06-17T14:37:56Z

@codex review

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 7aa055b10c

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

chatgpt-codex-connector · 2026-06-17T14:51:30Z

+/// bindings, violating TypeScript's namespace-merge semantics.
+fn pre_scan_namespace_exports(body: &TsNamespaceBody) -> NamespaceExportNames {
+    let mut scan = NamespaceExportNames::default();
+    if let TsNamespaceBody::TsModuleBlock(block) = body {


Handle dotted namespace reopens

When the reopened namespace is written in dotted form (namespace Outer.Inner { ... }), the Inner body is represented as TsNamespaceBody::TsNamespaceDecl, so this branch never pre-scans its exports and the existing visit_mut_ts_namespace_decl path never installs a shared namespace export scope for Inner. A pair such as namespace Outer.Inner { export const a = 1 } followed by namespace Outer.Inner { export const b = a } still leaves a unresolved/outer-scoped instead of resolving to Outer.Inner.a, even though TypeScript emits Inner.a for that case.

Useful? React with 👍 / 👎.

chatgpt-codex-connector · 2026-06-17T14:51:30Z

+            scan.values.insert(f.ident.sym.clone());
+        }
+        Decl::Class(c) => {
+            scan.values.insert(c.ident.sym.clone());


Qualify reopened class and function exports

When a later namespace reopen references an exported class or function from an earlier reopen, adding these names to the shared value scope gives the reference the exported declaration's context, but the TypeScript transform still does not add ExportDecl classes/functions to semantic.exported_binding (unlike vars/enums/modules/import aliases), so ExportQuery never rewrites the later-body reference to N.C/N.f. For namespace N { export class C {} } namespace N { new C() }, the generated code keeps a free C inside the second IIFE instead of reading N.C, causing a runtime ReferenceError.

Useful? React with 👍 / 👎.

chatgpt-codex-connector · 2026-06-17T14:51:30Z

+                if exp.declared_symbols.contains_key(sym) {
+                    return Some(exp.mark);


Predeclare later namespace exports before lookups

This lookup only sees names already accumulated in the shared scope, so references in an earlier namespace body cannot resolve to exports declared by a later reopen. Valid var cases like namespace Test { export var b = a + 1 } namespace Test { export var a = 1 } should emit the first initializer as Test.a + 1; with the current one-pass cache, a is unresolved/outer-scoped while visiting the first body, producing a free a instead of the namespace property.

Useful? React with 👍 / 👎.

magic-akari

I added additional test cases that should pass according to the expected behavior, but they are failing on my machine.
This suggests the current implementation may not fully match the expected behavior and may require a fix.

MavenRain requested a review from a team as a code owner May 20, 2026 02:30

chatgpt-codex-connector Bot reviewed May 20, 2026

View reviewed changes

Comment thread crates/swc_ecma_transforms_base/src/resolver/mod.rs Outdated

kdy1 requested a review from magic-akari May 20, 2026 04:06

magic-akari requested changes May 20, 2026

View reviewed changes

Comment thread crates/swc_ecma_transforms_base/src/resolver/mod.rs Outdated

MavenRain force-pushed the fix/resolver-namespace-merge branch from b94ef68 to cee5448 Compare May 20, 2026 22:22

MavenRain requested a review from magic-akari May 20, 2026 22:25

chatgpt-codex-connector Bot reviewed May 20, 2026

View reviewed changes

Comment thread crates/swc_ecma_transforms_base/src/resolver/mod.rs Outdated

Comment thread crates/swc_ecma_transforms_base/src/resolver/mod.rs Outdated

MavenRain force-pushed the fix/resolver-namespace-merge branch from cee5448 to d9ffafb Compare May 21, 2026 13:46

chatgpt-codex-connector Bot reviewed May 21, 2026

View reviewed changes

Comment thread crates/swc_ecma_transforms_base/src/resolver/mod.rs Outdated

chatgpt-codex-connector Bot reviewed May 21, 2026

View reviewed changes

Comment thread crates/swc_ecma_transforms_base/src/resolver/mod.rs Outdated

Comment thread crates/swc_ecma_transforms_base/src/resolver/mod.rs

Comment thread crates/swc_ecma_transforms_base/src/resolver/mod.rs

MavenRain force-pushed the fix/resolver-namespace-merge branch from bf4ec2a to 450fd85 Compare May 21, 2026 20:55

chatgpt-codex-connector Bot reviewed May 21, 2026

View reviewed changes

Comment thread crates/swc_ecma_transforms_base/src/resolver/mod.rs Outdated

MavenRain force-pushed the fix/resolver-namespace-merge branch from 78b7d08 to a9c8700 Compare May 22, 2026 16:00

MavenRain added 5 commits May 26, 2026 12:54

fix(es/resolver): Merge re-opened TypeScript namespace scopes (close s…

d4174ae

…wc-project#11607) Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

test: Update tsc-references and namespace fixtures for the merged-sco…

4c6fe52

…pe resolver output Signed-off-by: Onyeka Obi <softwareengineerasaservant@isurvivable.cv>

MavenRain force-pushed the fix/resolver-namespace-merge branch from a9c8700 to 7aa055b Compare May 26, 2026 19:55

kdy1 mentioned this pull request Jun 15, 2026

It is not to recognize exported variables when transforming namesapce nodejs/amaro#393

Closed

chatgpt-codex-connector Bot reviewed Jun 17, 2026

View reviewed changes

test: Add more test cases

22dca84

magic-akari requested changes Jun 17, 2026

View reviewed changes

		if exp.declared_symbols.contains_key(sym) {
		return Some(exp.mark);

Uh oh!

Uh oh!

Conversation

MavenRain commented May 20, 2026

Uh oh!

changeset-bot Bot commented May 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

⚠️ No Changeset found

Uh oh!

CLAassistant commented May 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

codspeed-hq Bot commented May 20, 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!

Uh oh!

MavenRain commented May 20, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

kdy1 commented Jun 12, 2026

Uh oh!

magic-akari commented Jun 17, 2026

Uh oh!

magic-akari commented Jun 17, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot Jun 17, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot Jun 17, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot Jun 17, 2026

Choose a reason for hiding this comment

Uh oh!

magic-akari left a comment

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Milestone

Development

Uh oh!

4 participants

changeset-bot Bot commented May 20, 2026 •

edited

Loading

CLAassistant commented May 20, 2026 •

edited

Loading

codspeed-hq Bot commented May 20, 2026 •

edited

Loading