[clang] [clang] Move the diagnostic of unexpected token after module name from phase 4 to phase 7 (PR #187846)
Yihan Wang via cfe-commits
cfe-commits at lists.llvm.org
Mon Jun 22 02:42:39 PDT 2026
https://github.com/yronglin updated https://github.com/llvm/llvm-project/pull/187846
>From 92f8d9bb3a6636a2b2cd2dc376d427d07781d018 Mon Sep 17 00:00:00 2001
From: yronglin <yronglin777 at gmail.com>
Date: Sat, 21 Mar 2026 15:54:55 +0800
Subject: [PATCH 1/2] [clang] Diag unexpected token after module name in phase
7
Signed-off-by: yronglin <yronglin777 at gmail.com>
---
clang/docs/ReleaseNotes.rst | 1 +
clang/include/clang/Basic/DiagnosticLexKinds.td | 3 ---
.../include/clang/Basic/DiagnosticParseKinds.td | 3 +++
clang/lib/Lex/PPDirectives.cpp | 16 ----------------
clang/lib/Parse/Parser.cpp | 6 ++++--
clang/test/CXX/basic/basic.link/p3.cpp | 2 +-
clang/test/CXX/drs/cwg2947.cpp | 4 ++--
.../basic/basic.link/module-declaration.cpp | 2 +-
clang/test/CXX/module/cpp.pre/p1.cpp | 6 +++---
9 files changed, 15 insertions(+), 28 deletions(-)
diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst
index d8ab080cecbe6..739a83c132eeb 100644
--- a/clang/docs/ReleaseNotes.rst
+++ b/clang/docs/ReleaseNotes.rst
@@ -702,6 +702,7 @@ Bug Fixes in This Version
- Fixed crash when checking for overflow for unary operator that can't overflow (#GH170072)
- Clang no longer handles a `" q-char-sequence "` header name as a string literal (#GH132643).
- Fixed an assertion when ``__attribute__((alloc_size))`` is used with an argument type wider than the target's pointer width. (#GH190445)
+- Fixed a crash when module directive export module foo not following a semicolon and there are no rest pp-tokens in current module file. (#GH187771)
Bug Fixes to Compiler Builtins
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
diff --git a/clang/include/clang/Basic/DiagnosticLexKinds.td b/clang/include/clang/Basic/DiagnosticLexKinds.td
index 383bf1a7fdb3f..b5813ea44ce19 100644
--- a/clang/include/clang/Basic/DiagnosticLexKinds.td
+++ b/clang/include/clang/Basic/DiagnosticLexKinds.td
@@ -1035,9 +1035,6 @@ def err_pp_module_name_is_macro : Error<
"%select{module|partition}0 name component %1 cannot be a object-like macro">;
def err_pp_module_expected_ident : Error<
"expected %select{identifier after '.' in |}0module name">;
-def err_pp_unexpected_tok_after_module_name : Error<
- "unexpected preprocessing token '%0' after module name, "
- "only ';' and '[' (start of attribute specifier sequence) are allowed">;
def warn_pp_extra_tokens_at_module_directive_eol
: Warning<"extra tokens after semicolon in '%0' directive">,
InGroup<ExtraTokens>;
diff --git a/clang/include/clang/Basic/DiagnosticParseKinds.td b/clang/include/clang/Basic/DiagnosticParseKinds.td
index 0dc7d0fbeac0b..56854aa6446ea 100644
--- a/clang/include/clang/Basic/DiagnosticParseKinds.td
+++ b/clang/include/clang/Basic/DiagnosticParseKinds.td
@@ -1792,6 +1792,9 @@ def ext_bit_int : Extension<
} // end of Parse Issue category.
let CategoryName = "Modules Issue" in {
+def err_unexpected_tok_after_module_name : Error<
+ "unexpected '%0' after module name, only ';' and '[' (start of attribute "
+ "specifier sequence) are allowed">;
def err_unexpected_module_or_import_decl : Error<
"%select{module|import}0 declaration can only appear at the top level">;
def err_attribute_not_module_attr : Error<
diff --git a/clang/lib/Lex/PPDirectives.cpp b/clang/lib/Lex/PPDirectives.cpp
index eb21a510dcf83..42f0dca37b799 100644
--- a/clang/lib/Lex/PPDirectives.cpp
+++ b/clang/lib/Lex/PPDirectives.cpp
@@ -4416,22 +4416,6 @@ void Preprocessor::HandleCXXModuleDirective(Token ModuleTok) {
break;
}
- // Consume the pp-import-suffix and expand any macros in it now, if we're not
- // at the semicolon already.
- std::optional<Token> NextPPTok =
- DirToks.back().is(tok::eod) ? peekNextPPToken() : DirToks.back();
-
- // Only ';' and '[' are allowed after module name.
- // We also check 'private' because the previous is not a module name.
- if (NextPPTok) {
- if (NextPPTok->is(tok::raw_identifier))
- LookUpIdentifierInfo(*NextPPTok);
- if (!NextPPTok->isOneOf(tok::semi, tok::eod, tok::l_square,
- tok::kw_private))
- Diag(*NextPPTok, diag::err_pp_unexpected_tok_after_module_name)
- << getSpelling(*NextPPTok);
- }
-
if (!DirToks.back().isOneOf(tok::semi, tok::eod)) {
// Consume the pp-import-suffix and expand any macros in it now. We'll add
// it back into the token stream later.
diff --git a/clang/lib/Parse/Parser.cpp b/clang/lib/Parse/Parser.cpp
index 5e1fd4df1a3f0..f62dce87db924 100644
--- a/clang/lib/Parse/Parser.cpp
+++ b/clang/lib/Parse/Parser.cpp
@@ -2382,9 +2382,11 @@ Parser::ParseModuleDecl(Sema::ModuleImportState &ImportState) {
}
// This should already diagnosed in phase 4, just skip unil semicolon.
- if (!Tok.isOneOf(tok::semi, tok::l_square))
+ if (!Tok.isOneOf(tok::semi, tok::l_square)) {
+ Diag(Tok, diag::err_unexpected_tok_after_module_name)
+ << PP.getSpelling(Tok);
SkipUntil(tok::semi, SkipUntilFlags::StopBeforeMatch);
-
+ }
// We don't support any module attributes yet; just parse them and diagnose.
ParsedAttributes Attrs(AttrFactory);
MaybeParseCXX11Attributes(Attrs);
diff --git a/clang/test/CXX/basic/basic.link/p3.cpp b/clang/test/CXX/basic/basic.link/p3.cpp
index bc3622c7bbd64..0784a7d879d7d 100644
--- a/clang/test/CXX/basic/basic.link/p3.cpp
+++ b/clang/test/CXX/basic/basic.link/p3.cpp
@@ -14,7 +14,7 @@ constexpr int n = 123;
export module m; // #1
module y = {}; // expected-error {{multiple module declarations}}
-// expected-error at -1 {{unexpected preprocessing token '=' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
+// expected-error at -1 {{unexpected '=' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
// expected-note@#1 {{previous module declaration}}
::import x = {};
diff --git a/clang/test/CXX/drs/cwg2947.cpp b/clang/test/CXX/drs/cwg2947.cpp
index 3d9d738f40de3..1fa59b4e00ab2 100644
--- a/clang/test/CXX/drs/cwg2947.cpp
+++ b/clang/test/CXX/drs/cwg2947.cpp
@@ -37,7 +37,7 @@
//--- cwg2947_example1.cpp
// #define DOT_BAR .bar
export module foo DOT_BAR; // error: expansion of DOT_BAR; does not begin with ; or [
-// expected-error at -1 {{unexpected preprocessing token '.' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
+// expected-error at -1 {{unexpected '.' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
//--- cwg2947_example2.cpp
export module M MOD_ATTR; // OK
@@ -46,7 +46,7 @@ export module M MOD_ATTR; // OK
//--- cwg2947_example3.cpp
export module a
.b; // error: preprocessing token after pp-module-name is not ; or [
-// expected-error at -1 {{unexpected preprocessing token '.' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
+// expected-error at -1 {{unexpected '.' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
//--- cwg2947_example4.cpp
export module M [[
diff --git a/clang/test/CXX/module/basic/basic.link/module-declaration.cpp b/clang/test/CXX/module/basic/basic.link/module-declaration.cpp
index 52ba1d9f82f2f..b22fc87aa296c 100644
--- a/clang/test/CXX/module/basic/basic.link/module-declaration.cpp
+++ b/clang/test/CXX/module/basic/basic.link/module-declaration.cpp
@@ -47,7 +47,7 @@ export module x;
//--- invalid_module_name.cppm
export module z elderberry;
-// expected-error at -1 {{unexpected preprocessing token 'elderberry' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
+// expected-error at -1 {{unexpected 'elderberry' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
//--- empty_attribute.cppm
// expected-no-diagnostics
diff --git a/clang/test/CXX/module/cpp.pre/p1.cpp b/clang/test/CXX/module/cpp.pre/p1.cpp
index 989915004ff57..dc5a3c36d4139 100644
--- a/clang/test/CXX/module/cpp.pre/p1.cpp
+++ b/clang/test/CXX/module/cpp.pre/p1.cpp
@@ -153,7 +153,7 @@ export module m:n;
//--- unexpected_character_in_pp_module_suffix.cpp
export module m();
-// expected-error at -1 {{unexpected preprocessing token '(' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
+// expected-error at -1 {{unexpected '(' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
//--- semi_in_same_line.cpp
export module m // OK
@@ -189,13 +189,13 @@ module x;
//--- func_like_macro.cpp
// #define m(x) x
export module m
- (foo); // expected-error {{unexpected preprocessing token '(' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
+ (foo); // expected-error {{unexpected '(' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
//--- lparen.cpp
// #define m(x) x
// #define LPAREN (
export module m
- LPAREN foo); // expected-error {{unexpected preprocessing token 'LPAREN' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
+ LPAREN foo); // expected-error {{unexpected '(' after module name, only ';' and '[' (start of attribute specifier sequence) are allowed}}
//--- control_line.cpp
#if 0 // #1
>From ed3aa52cb1981d09848ea496d2a82988d98a4c73 Mon Sep 17 00:00:00 2001
From: yronglin <yronglin777 at gmail.com>
Date: Fri, 12 Jun 2026 01:40:42 +0800
Subject: [PATCH 2/2] Don't diag when Tok is eof
Signed-off-by: yronglin <yronglin777 at gmail.com>
---
clang/lib/Parse/Parser.cpp | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/clang/lib/Parse/Parser.cpp b/clang/lib/Parse/Parser.cpp
index f62dce87db924..387d930588eac 100644
--- a/clang/lib/Parse/Parser.cpp
+++ b/clang/lib/Parse/Parser.cpp
@@ -2381,12 +2381,12 @@ Parser::ParseModuleDecl(Sema::ModuleImportState &ImportState) {
return nullptr;
}
- // This should already diagnosed in phase 4, just skip unil semicolon.
- if (!Tok.isOneOf(tok::semi, tok::l_square)) {
+ if (Tok.isNoneOf(tok::semi, tok::l_square, tok::eof)) {
Diag(Tok, diag::err_unexpected_tok_after_module_name)
<< PP.getSpelling(Tok);
SkipUntil(tok::semi, SkipUntilFlags::StopBeforeMatch);
}
+
// We don't support any module attributes yet; just parse them and diagnose.
ParsedAttributes Attrs(AttrFactory);
MaybeParseCXX11Attributes(Attrs);
More information about the cfe-commits
mailing list