[clang] [Modules] Fix ModuleDeclState transition when module is used as a regular identifier (PR #71134)

[Fangrui Song via cfe-commits]

https://github.com/MaskRay updated https://github.com/llvm/llvm-project/pull/71134

>From 92cfc6e1306321ae8beb05775e2c7f8ac720f5e6 Mon Sep 17 00:00:00 2001
From: Fangrui Song <i at maskray.me>
Date: Thu, 2 Nov 2023 19:42:09 -0700
Subject: [PATCH 1/2] [Modules] Fix ModuleDeclState transition when module is
 used as a regular identifier

`ModuleDeclState` is incorrectly changed to `NamedModuleImplementation`
for `struct module {}; void foo(module a);`. This is mostly benign but
leads to a spurious warning after #69555.

A real world example is:
```
// pybind11.h
class module_ { ... };
using module = module_;

// tensorflow
void DefineMetricsModule(pybind11::module main_module);
// `module main_module);` incorrectly changes `ModuleDeclState` to `NamedModuleImplementation`
```
---
 clang/lib/Lex/Preprocessor.cpp                | 37 ++++++++++---------
 .../include-in-module-purview.cppm            |  8 ++++
 2 files changed, 27 insertions(+), 18 deletions(-)

diff --git a/clang/lib/Lex/Preprocessor.cpp b/clang/lib/Lex/Preprocessor.cpp
index ede4c51487ffbe7..482d73f87df07b7 100644
--- a/clang/lib/Lex/Preprocessor.cpp
+++ b/clang/lib/Lex/Preprocessor.cpp
@@ -957,26 +957,27 @@ void Preprocessor::Lex(Token &Result) {
       ModuleDeclState.handlePeriod();
       break;
     case tok::identifier:
-      if (Result.getIdentifierInfo()->isModulesImport()) {
-        TrackGMFState.handleImport(StdCXXImportSeqState.afterTopLevelSeq());
-        StdCXXImportSeqState.handleImport();
-        if (StdCXXImportSeqState.afterImportSeq()) {
-          ModuleImportLoc = Result.getLocation();
-          NamedModuleImportPath.clear();
-          IsAtImport = false;
-          ModuleImportExpectsIdentifier = true;
-          CurLexerKind = CLK_LexAfterModuleImport;
-        }
-        break;
-      } else if (Result.getIdentifierInfo() == getIdentifierInfo("module")) {
-        TrackGMFState.handleModule(StdCXXImportSeqState.afterTopLevelSeq());
-        ModuleDeclState.handleModule();
-        break;
-      } else {
-        ModuleDeclState.handleIdentifier(Result.getIdentifierInfo());
-        if (ModuleDeclState.isModuleCandidate())
+      if (StdCXXImportSeqState.atTopLevel()) {
+        if (Result.getIdentifierInfo()->isModulesImport()) {
+          TrackGMFState.handleImport(StdCXXImportSeqState.afterTopLevelSeq());
+          StdCXXImportSeqState.handleImport();
+          if (StdCXXImportSeqState.afterImportSeq()) {
+            ModuleImportLoc = Result.getLocation();
+            NamedModuleImportPath.clear();
+            IsAtImport = false;
+            ModuleImportExpectsIdentifier = true;
+            CurLexerKind = CLK_LexAfterModuleImport;
+          }
           break;
+        } else if (Result.getIdentifierInfo() == getIdentifierInfo("module")) {
+          TrackGMFState.handleModule(StdCXXImportSeqState.afterTopLevelSeq());
+          ModuleDeclState.handleModule();
+          break;
+        }
       }
+      ModuleDeclState.handleIdentifier(Result.getIdentifierInfo());
+      if (ModuleDeclState.isModuleCandidate())
+        break;
       [[fallthrough]];
     default:
       TrackGMFState.handleMisc();
diff --git a/clang/test/Preprocessor/include-in-module-purview.cppm b/clang/test/Preprocessor/include-in-module-purview.cppm
index 0a080112b43277c..4a7883653ac45dd 100644
--- a/clang/test/Preprocessor/include-in-module-purview.cppm
+++ b/clang/test/Preprocessor/include-in-module-purview.cppm
@@ -5,6 +5,7 @@
 // RUN: %clang_cc1 -std=c++20 %t/a.cppm -E -P -I%t -o %t/tmp 2>&1 | FileCheck %t/a.cppm
 // RUN: %clang_cc1 -std=c++20 %t/a.cppm -E -P -I%t -o - 2>&1 \
 // RUN:     -Wno-include-angled-in-module-purview | FileCheck %t/a.cppm --check-prefix=CHECK-NO-WARN
+// RUN: %clang_cc1 -std=c++20 %t/b.cpp -E -P -I%t -o - 2>&1 | FileCheck %t/a.cppm --check-prefix=CHECK-NO-WARN
 
 //--- a.h
 // left empty
@@ -58,3 +59,10 @@ module :private;
 // CHECK: 10 warnings generated.
 
 // CHECK-NO-WARN-NOT: warning
+
+//--- b.cpp
+/// Don't recognize `module m);` as a module purview or report a spurious
+/// warning for <stddef.h>.
+struct module {};
+void foo(module m);
+#include <stddef.h>

>From 20ce58dd34d9613dcd0d6e16d48340ef84e7beb7 Mon Sep 17 00:00:00 2001
From: Fangrui Song <i at maskray.me>
Date: Thu, 2 Nov 2023 22:09:30 -0700
Subject: [PATCH 2/2] add a comment

---
 clang/lib/Lex/Preprocessor.cpp | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/clang/lib/Lex/Preprocessor.cpp b/clang/lib/Lex/Preprocessor.cpp
index 482d73f87df07b7..45c0f848da66047 100644
--- a/clang/lib/Lex/Preprocessor.cpp
+++ b/clang/lib/Lex/Preprocessor.cpp
@@ -957,6 +957,8 @@ void Preprocessor::Lex(Token &Result) {
       ModuleDeclState.handlePeriod();
       break;
     case tok::identifier:
+      // Check "import" and "module" when there is no open bracket. The two
+      // identifiers are not meaningful with open brackets.
       if (StdCXXImportSeqState.atTopLevel()) {
         if (Result.getIdentifierInfo()->isModulesImport()) {
           TrackGMFState.handleImport(StdCXXImportSeqState.afterTopLevelSeq());