aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Lex
diff options
context:
space:
mode:
authorDimitry Andric <dim@FreeBSD.org>2017-05-08 17:13:11 +0000
committerDimitry Andric <dim@FreeBSD.org>2017-05-08 17:13:11 +0000
commit0a5fb09b599c1bdea3cd11168bb8f4ff4040316e (patch)
tree5e94367d1a8032322c6871cfe16714c0982fd61a /lib/Lex
parentf0c0337bbfb63d1f9edf145aab535bdf82c20454 (diff)
downloadsrc-0a5fb09b599c1bdea3cd11168bb8f4ff4040316e.tar.gz
src-0a5fb09b599c1bdea3cd11168bb8f4ff4040316e.zip
Vendor import of clang trunk r302418:vendor/clang/clang-trunk-r302418
Notes
Notes: svn path=/vendor/clang/dist/; revision=317951 svn path=/vendor/clang/clang-trunk-r302418/; revision=317952; tag=vendor/clang/clang-trunk-r302418
Diffstat (limited to 'lib/Lex')
-rw-r--r--lib/Lex/HeaderSearch.cpp10
-rw-r--r--lib/Lex/Lexer.cpp66
-rw-r--r--lib/Lex/ModuleMap.cpp58
-rw-r--r--lib/Lex/PPDirectives.cpp8
-rw-r--r--lib/Lex/PPLexerChange.cpp57
-rw-r--r--lib/Lex/PPMacroExpansion.cpp2
-rw-r--r--lib/Lex/Pragma.cpp167
-rw-r--r--lib/Lex/Preprocessor.cpp8
-rw-r--r--lib/Lex/TokenLexer.cpp30
9 files changed, 298 insertions, 108 deletions
diff --git a/lib/Lex/HeaderSearch.cpp b/lib/Lex/HeaderSearch.cpp
index bd425a07c33a..f5b7c59e446f 100644
--- a/lib/Lex/HeaderSearch.cpp
+++ b/lib/Lex/HeaderSearch.cpp
@@ -1325,7 +1325,8 @@ static const FileEntry *getPrivateModuleMap(const FileEntry *File,
return FileMgr.getFile(PrivateFilename);
}
-bool HeaderSearch::loadModuleMapFile(const FileEntry *File, bool IsSystem) {
+bool HeaderSearch::loadModuleMapFile(const FileEntry *File, bool IsSystem,
+ FileID ID, unsigned *Offset) {
// Find the directory for the module. For frameworks, that may require going
// up from the 'Modules' directory.
const DirectoryEntry *Dir = nullptr;
@@ -1344,7 +1345,7 @@ bool HeaderSearch::loadModuleMapFile(const FileEntry *File, bool IsSystem) {
}
}
- switch (loadModuleMapFileImpl(File, IsSystem, Dir)) {
+ switch (loadModuleMapFileImpl(File, IsSystem, Dir, ID, Offset)) {
case LMM_AlreadyLoaded:
case LMM_NewlyLoaded:
return false;
@@ -1357,7 +1358,8 @@ bool HeaderSearch::loadModuleMapFile(const FileEntry *File, bool IsSystem) {
HeaderSearch::LoadModuleMapResult
HeaderSearch::loadModuleMapFileImpl(const FileEntry *File, bool IsSystem,
- const DirectoryEntry *Dir) {
+ const DirectoryEntry *Dir, FileID ID,
+ unsigned *Offset) {
assert(File && "expected FileEntry");
// Check whether we've already loaded this module map, and mark it as being
@@ -1366,7 +1368,7 @@ HeaderSearch::loadModuleMapFileImpl(const FileEntry *File, bool IsSystem,
if (!AddResult.second)
return AddResult.first->second ? LMM_AlreadyLoaded : LMM_InvalidModuleMap;
- if (ModMap.parseModuleMapFile(File, IsSystem, Dir)) {
+ if (ModMap.parseModuleMapFile(File, IsSystem, Dir, ID, Offset)) {
LoadedModuleMaps[File] = false;
return LMM_InvalidModuleMap;
}
diff --git a/lib/Lex/Lexer.cpp b/lib/Lex/Lexer.cpp
index 003c9b5eed1b..3d6fe91115a9 100644
--- a/lib/Lex/Lexer.cpp
+++ b/lib/Lex/Lexer.cpp
@@ -452,6 +452,29 @@ bool Lexer::getRawToken(SourceLocation Loc, Token &Result,
return false;
}
+/// Returns the pointer that points to the beginning of line that contains
+/// the given offset, or null if the offset if invalid.
+static const char *findBeginningOfLine(StringRef Buffer, unsigned Offset) {
+ const char *BufStart = Buffer.data();
+ if (Offset >= Buffer.size())
+ return nullptr;
+ const char *StrData = BufStart + Offset;
+
+ if (StrData[0] == '\n' || StrData[0] == '\r')
+ return StrData;
+
+ const char *LexStart = StrData;
+ while (LexStart != BufStart) {
+ if (LexStart[0] == '\n' || LexStart[0] == '\r') {
+ ++LexStart;
+ break;
+ }
+
+ --LexStart;
+ }
+ return LexStart;
+}
+
static SourceLocation getBeginningOfFileToken(SourceLocation Loc,
const SourceManager &SM,
const LangOptions &LangOpts) {
@@ -467,27 +490,15 @@ static SourceLocation getBeginningOfFileToken(SourceLocation Loc,
// Back up from the current location until we hit the beginning of a line
// (or the buffer). We'll relex from that point.
- const char *BufStart = Buffer.data();
- if (LocInfo.second >= Buffer.size())
- return Loc;
-
- const char *StrData = BufStart+LocInfo.second;
- if (StrData[0] == '\n' || StrData[0] == '\r')
+ const char *StrData = Buffer.data() + LocInfo.second;
+ const char *LexStart = findBeginningOfLine(Buffer, LocInfo.second);
+ if (!LexStart || LexStart == StrData)
return Loc;
-
- const char *LexStart = StrData;
- while (LexStart != BufStart) {
- if (LexStart[0] == '\n' || LexStart[0] == '\r') {
- ++LexStart;
- break;
- }
-
- --LexStart;
- }
// Create a lexer starting at the beginning of this token.
SourceLocation LexerStartLoc = Loc.getLocWithOffset(-LocInfo.second);
- Lexer TheLexer(LexerStartLoc, LangOpts, BufStart, LexStart, Buffer.end());
+ Lexer TheLexer(LexerStartLoc, LangOpts, Buffer.data(), LexStart,
+ Buffer.end());
TheLexer.SetCommentRetentionState(true);
// Lex tokens until we find the token that contains the source location.
@@ -1038,6 +1049,27 @@ bool Lexer::isIdentifierBodyChar(char c, const LangOptions &LangOpts) {
return isIdentifierBody(c, LangOpts.DollarIdents);
}
+StringRef Lexer::getIndentationForLine(SourceLocation Loc,
+ const SourceManager &SM) {
+ if (Loc.isInvalid() || Loc.isMacroID())
+ return "";
+ std::pair<FileID, unsigned> LocInfo = SM.getDecomposedLoc(Loc);
+ if (LocInfo.first.isInvalid())
+ return "";
+ bool Invalid = false;
+ StringRef Buffer = SM.getBufferData(LocInfo.first, &Invalid);
+ if (Invalid)
+ return "";
+ const char *Line = findBeginningOfLine(Buffer, LocInfo.second);
+ if (!Line)
+ return "";
+ StringRef Rest = Buffer.substr(Line - Buffer.data());
+ size_t NumWhitespaceChars = Rest.find_first_not_of(" \t");
+ return NumWhitespaceChars == StringRef::npos
+ ? ""
+ : Rest.take_front(NumWhitespaceChars);
+}
+
//===----------------------------------------------------------------------===//
// Diagnostics forwarding code.
//===----------------------------------------------------------------------===//
diff --git a/lib/Lex/ModuleMap.cpp b/lib/Lex/ModuleMap.cpp
index 512d7dc5de68..70d37d3d7082 100644
--- a/lib/Lex/ModuleMap.cpp
+++ b/lib/Lex/ModuleMap.cpp
@@ -1132,14 +1132,17 @@ namespace clang {
}
bool parseModuleMapFile();
+
+ bool terminatedByDirective() { return false; }
+ SourceLocation getLocation() { return Tok.getLocation(); }
};
}
SourceLocation ModuleMapParser::consumeToken() {
-retry:
SourceLocation Result = Tok.getLocation();
+
+retry:
Tok.clear();
-
Token LToken;
L.LexFromRawLexer(LToken);
Tok.Location = LToken.getLocation().getRawEncoding();
@@ -1232,9 +1235,28 @@ retry:
case tok::comment:
goto retry;
-
+
+ case tok::hash:
+ // A module map can be terminated prematurely by
+ // #pragma clang module contents
+ // When building the module, we'll treat the rest of the file as the
+ // contents of the module.
+ {
+ auto NextIsIdent = [&](StringRef Str) -> bool {
+ L.LexFromRawLexer(LToken);
+ return !LToken.isAtStartOfLine() && LToken.is(tok::raw_identifier) &&
+ LToken.getRawIdentifier() == Str;
+ };
+ if (NextIsIdent("pragma") && NextIsIdent("clang") &&
+ NextIsIdent("module") && NextIsIdent("contents")) {
+ Tok.Kind = MMToken::EndOfFile;
+ break;
+ }
+ }
+ LLVM_FALLTHROUGH;
+
default:
- Diags.Report(LToken.getLocation(), diag::err_mmap_unknown_token);
+ Diags.Report(Tok.getLocation(), diag::err_mmap_unknown_token);
HadError = true;
goto retry;
}
@@ -1682,7 +1704,8 @@ void ModuleMapParser::parseExternModuleDecl() {
File, /*IsSystem=*/false,
Map.HeaderInfo.getHeaderSearchOpts().ModuleMapFileHomeIsCwd
? Directory
- : File->getDir(), ExternLoc);
+ : File->getDir(),
+ FileID(), nullptr, ExternLoc);
}
/// Whether to add the requirement \p Feature to the module \p M.
@@ -2522,28 +2545,45 @@ bool ModuleMapParser::parseModuleMapFile() {
}
bool ModuleMap::parseModuleMapFile(const FileEntry *File, bool IsSystem,
- const DirectoryEntry *Dir,
+ const DirectoryEntry *Dir, FileID ID,
+ unsigned *Offset,
SourceLocation ExternModuleLoc) {
+ assert(Target && "Missing target information");
llvm::DenseMap<const FileEntry *, bool>::iterator Known
= ParsedModuleMap.find(File);
if (Known != ParsedModuleMap.end())
return Known->second;
+ // If the module map file wasn't already entered, do so now.
+ if (ID.isInvalid()) {
+ auto FileCharacter = IsSystem ? SrcMgr::C_System : SrcMgr::C_User;
+ ID = SourceMgr.createFileID(File, ExternModuleLoc, FileCharacter);
+ }
+
assert(Target && "Missing target information");
- auto FileCharacter = IsSystem ? SrcMgr::C_System : SrcMgr::C_User;
- FileID ID = SourceMgr.createFileID(File, ExternModuleLoc, FileCharacter);
const llvm::MemoryBuffer *Buffer = SourceMgr.getBuffer(ID);
if (!Buffer)
return ParsedModuleMap[File] = true;
+ assert((!Offset || *Offset <= Buffer->getBufferSize()) &&
+ "invalid buffer offset");
// Parse this module map file.
- Lexer L(ID, SourceMgr.getBuffer(ID), SourceMgr, MMapLangOpts);
+ Lexer L(SourceMgr.getLocForStartOfFile(ID), MMapLangOpts,
+ Buffer->getBufferStart(),
+ Buffer->getBufferStart() + (Offset ? *Offset : 0),
+ Buffer->getBufferEnd());
SourceLocation Start = L.getSourceLocation();
ModuleMapParser Parser(L, SourceMgr, Target, Diags, *this, File, Dir,
BuiltinIncludeDir, IsSystem);
bool Result = Parser.parseModuleMapFile();
ParsedModuleMap[File] = Result;
+ if (Offset) {
+ auto Loc = SourceMgr.getDecomposedLoc(Parser.getLocation());
+ assert(Loc.first == ID && "stopped in a different file?");
+ *Offset = Loc.second;
+ }
+
// Notify callbacks that we parsed it.
for (const auto &Cb : Callbacks)
Cb->moduleMapFileRead(Start, *File, IsSystem);
diff --git a/lib/Lex/PPDirectives.cpp b/lib/Lex/PPDirectives.cpp
index 4826e399afda..06fee8e5b0a8 100644
--- a/lib/Lex/PPDirectives.cpp
+++ b/lib/Lex/PPDirectives.cpp
@@ -2049,12 +2049,12 @@ void Preprocessor::HandleIncludeDirective(SourceLocation HashLoc,
M->getTopLevelModuleName() == getLangOpts().CurrentModule)
return;
- assert(!CurSubmodule && "should not have marked this as a module yet");
- CurSubmodule = M;
+ assert(!CurLexerSubmodule && "should not have marked this as a module yet");
+ CurLexerSubmodule = M;
// Let the macro handling code know that any future macros are within
// the new submodule.
- EnterSubmodule(M, HashLoc);
+ EnterSubmodule(M, HashLoc, /*ForPragma*/false);
// Let the parser know that any future declarations are within the new
// submodule.
@@ -2082,7 +2082,7 @@ void Preprocessor::HandleIncludeNextDirective(SourceLocation HashLoc,
} else if (isInPrimaryFile()) {
Lookup = nullptr;
Diag(IncludeNextTok, diag::pp_include_next_in_primary);
- } else if (CurSubmodule) {
+ } else if (CurLexerSubmodule) {
// Start looking up in the directory *after* the one in which the current
// file would be found, if any.
assert(CurPPLexer && "#include_next directive in macro?");
diff --git a/lib/Lex/PPLexerChange.cpp b/lib/Lex/PPLexerChange.cpp
index fcc49b387034..1938328c904d 100644
--- a/lib/Lex/PPLexerChange.cpp
+++ b/lib/Lex/PPLexerChange.cpp
@@ -117,7 +117,7 @@ void Preprocessor::EnterSourceFileWithLexer(Lexer *TheLexer,
CurLexer.reset(TheLexer);
CurPPLexer = TheLexer;
CurDirLookup = CurDir;
- CurSubmodule = nullptr;
+ CurLexerSubmodule = nullptr;
if (CurLexerKind != CLK_LexAfterModuleImport)
CurLexerKind = CLK_Lexer;
@@ -142,7 +142,7 @@ void Preprocessor::EnterSourceFileWithPTH(PTHLexer *PL,
CurDirLookup = CurDir;
CurPTHLexer.reset(PL);
CurPPLexer = CurPTHLexer.get();
- CurSubmodule = nullptr;
+ CurLexerSubmodule = nullptr;
if (CurLexerKind != CLK_LexAfterModuleImport)
CurLexerKind = CLK_PTHLexer;
@@ -337,6 +337,26 @@ bool Preprocessor::HandleEndOfFile(Token &Result, bool isEndOfMacro) {
assert(!CurTokenLexer &&
"Ending a file when currently in a macro!");
+ // If we have an unclosed module region from a pragma at the end of a
+ // module, complain and close it now.
+ // FIXME: This is not correct if we are building a module from PTH.
+ const bool LeavingSubmodule = CurLexer && CurLexerSubmodule;
+ if ((LeavingSubmodule || IncludeMacroStack.empty()) &&
+ !BuildingSubmoduleStack.empty() &&
+ BuildingSubmoduleStack.back().IsPragma) {
+ Diag(BuildingSubmoduleStack.back().ImportLoc,
+ diag::err_pp_module_begin_without_module_end);
+ Module *M = LeaveSubmodule(/*ForPragma*/true);
+
+ Result.startToken();
+ const char *EndPos = getCurLexerEndPos();
+ CurLexer->BufferPtr = EndPos;
+ CurLexer->FormTokenWithChars(Result, EndPos, tok::annot_module_end);
+ Result.setAnnotationEndLoc(Result.getLocation());
+ Result.setAnnotationValue(M);
+ return true;
+ }
+
// See if this file had a controlling macro.
if (CurPPLexer) { // Not ending a macro, ignore it.
if (const IdentifierInfo *ControllingMacro =
@@ -442,18 +462,17 @@ bool Preprocessor::HandleEndOfFile(Token &Result, bool isEndOfMacro) {
if (Callbacks && !isEndOfMacro && CurPPLexer)
ExitedFID = CurPPLexer->getFileID();
- bool LeavingSubmodule = CurSubmodule && CurLexer;
if (LeavingSubmodule) {
+ // We're done with this submodule.
+ Module *M = LeaveSubmodule(/*ForPragma*/false);
+
// Notify the parser that we've left the module.
const char *EndPos = getCurLexerEndPos();
Result.startToken();
CurLexer->BufferPtr = EndPos;
CurLexer->FormTokenWithChars(Result, EndPos, tok::annot_module_end);
Result.setAnnotationEndLoc(Result.getLocation());
- Result.setAnnotationValue(CurSubmodule);
-
- // We're done with this submodule.
- LeaveSubmodule();
+ Result.setAnnotationValue(M);
}
// We're done with the #included file.
@@ -628,11 +647,13 @@ void Preprocessor::HandleMicrosoftCommentPaste(Token &Tok) {
assert(!FoundLexer && "Lexer should return EOD before EOF in PP mode");
}
-void Preprocessor::EnterSubmodule(Module *M, SourceLocation ImportLoc) {
+void Preprocessor::EnterSubmodule(Module *M, SourceLocation ImportLoc,
+ bool ForPragma) {
if (!getLangOpts().ModulesLocalVisibility) {
// Just track that we entered this submodule.
- BuildingSubmoduleStack.push_back(BuildingSubmoduleInfo(
- M, ImportLoc, CurSubmoduleState, PendingModuleMacroNames.size()));
+ BuildingSubmoduleStack.push_back(
+ BuildingSubmoduleInfo(M, ImportLoc, ForPragma, CurSubmoduleState,
+ PendingModuleMacroNames.size()));
return;
}
@@ -673,8 +694,9 @@ void Preprocessor::EnterSubmodule(Module *M, SourceLocation ImportLoc) {
}
// Track that we entered this module.
- BuildingSubmoduleStack.push_back(BuildingSubmoduleInfo(
- M, ImportLoc, CurSubmoduleState, PendingModuleMacroNames.size()));
+ BuildingSubmoduleStack.push_back(
+ BuildingSubmoduleInfo(M, ImportLoc, ForPragma, CurSubmoduleState,
+ PendingModuleMacroNames.size()));
// Switch to this submodule as the current submodule.
CurSubmoduleState = &State;
@@ -697,7 +719,13 @@ bool Preprocessor::needModuleMacros() const {
return getLangOpts().isCompilingModule();
}
-void Preprocessor::LeaveSubmodule() {
+Module *Preprocessor::LeaveSubmodule(bool ForPragma) {
+ if (BuildingSubmoduleStack.empty() ||
+ BuildingSubmoduleStack.back().IsPragma != ForPragma) {
+ assert(ForPragma && "non-pragma module enter/leave mismatch");
+ return nullptr;
+ }
+
auto &Info = BuildingSubmoduleStack.back();
Module *LeavingMod = Info.M;
@@ -711,7 +739,7 @@ void Preprocessor::LeaveSubmodule() {
// of pending names for the surrounding submodule.
BuildingSubmoduleStack.pop_back();
makeModuleVisible(LeavingMod, ImportLoc);
- return;
+ return LeavingMod;
}
// Create ModuleMacros for any macros defined in this submodule.
@@ -800,4 +828,5 @@ void Preprocessor::LeaveSubmodule() {
// A nested #include makes the included submodule visible.
makeModuleVisible(LeavingMod, ImportLoc);
+ return LeavingMod;
}
diff --git a/lib/Lex/PPMacroExpansion.cpp b/lib/Lex/PPMacroExpansion.cpp
index 196223981d74..6c7663994a49 100644
--- a/lib/Lex/PPMacroExpansion.cpp
+++ b/lib/Lex/PPMacroExpansion.cpp
@@ -1453,7 +1453,7 @@ static bool EvaluateHasIncludeNext(Token &Tok,
} else if (PP.isInPrimaryFile()) {
Lookup = nullptr;
PP.Diag(Tok, diag::pp_include_next_in_primary);
- } else if (PP.getCurrentSubmodule()) {
+ } else if (PP.getCurrentLexerSubmodule()) {
// Start looking up in the directory *after* the one in which the current
// file would be found, if any.
assert(PP.getCurrentLexer() && "#include_next directive in macro?");
diff --git a/lib/Lex/Pragma.cpp b/lib/Lex/Pragma.cpp
index 576151a98b2c..99d56182c1bb 100644
--- a/lib/Lex/Pragma.cpp
+++ b/lib/Lex/Pragma.cpp
@@ -534,47 +534,6 @@ void Preprocessor::HandlePragmaDependency(Token &DependencyTok) {
}
}
-void Preprocessor::HandlePragmaModuleImport(Token &ImportTok) {
- SourceLocation ImportLoc = ImportTok.getLocation();
-
- Token Tok;
-
- llvm::SmallVector<std::pair<IdentifierInfo *, SourceLocation>, 8> ModuleName;
- while (true) {
- LexUnexpandedToken(Tok);
- if (Tok.isNot(tok::identifier)) {
- Diag(Tok.getLocation(),
- diag::err_pragma_module_import_expected_module_name) << 0;
- return;
- }
-
- ModuleName.emplace_back(Tok.getIdentifierInfo(), Tok.getLocation());
-
- LexUnexpandedToken(Tok);
- assert(Tok.isNot(tok::eof));
- if (Tok.is(tok::eod))
- break;
- if (Tok.isNot(tok::period)) {
- Diag(Tok.getLocation(),
- diag::err_pragma_module_import_expected_module_name) << 1;
- return;
- }
- }
-
- // If we have a non-empty module path, load the named module.
- Module *Imported =
- TheModuleLoader.loadModule(ImportLoc, ModuleName, Module::Hidden,
- /*IsIncludeDirective=*/false);
- if (!Imported)
- return;
-
- makeModuleVisible(Imported, ImportLoc);
- EnterAnnotationToken(SourceRange(ImportLoc, Tok.getLocation()),
- tok::annot_module_include, Imported);
- if (Callbacks)
- Callbacks->moduleImport(ImportLoc, ModuleName, Imported);
-}
-
/// ParsePragmaPushOrPopMacro - Handle parsing of pragma push_macro/pop_macro.
/// Return the IdentifierInfo* associated with the macro to push or pop.
IdentifierInfo *Preprocessor::ParsePragmaPushOrPopMacro(Token &Tok) {
@@ -1342,6 +1301,26 @@ public:
}
};
+static bool LexModuleName(
+ Preprocessor &PP, Token &Tok,
+ llvm::SmallVectorImpl<std::pair<IdentifierInfo *, SourceLocation>>
+ &ModuleName) {
+ while (true) {
+ PP.LexUnexpandedToken(Tok);
+ if (Tok.isAnnotation() || !Tok.getIdentifierInfo()) {
+ PP.Diag(Tok.getLocation(), diag::err_pp_expected_module_name)
+ << ModuleName.empty();
+ return true;
+ }
+
+ ModuleName.emplace_back(Tok.getIdentifierInfo(), Tok.getLocation());
+
+ PP.LexUnexpandedToken(Tok);
+ if (Tok.isNot(tok::period))
+ return false;
+ }
+}
+
/// Handle the clang \#pragma module import extension. The syntax is:
/// \code
/// #pragma clang module import some.module.name
@@ -1350,8 +1329,108 @@ struct PragmaModuleImportHandler : public PragmaHandler {
PragmaModuleImportHandler() : PragmaHandler("import") {}
void HandlePragma(Preprocessor &PP, PragmaIntroducerKind Introducer,
- Token &ImportTok) override {
- PP.HandlePragmaModuleImport(ImportTok);
+ Token &Tok) override {
+ SourceLocation ImportLoc = Tok.getLocation();
+
+ // Read the module name.
+ llvm::SmallVector<std::pair<IdentifierInfo *, SourceLocation>, 8>
+ ModuleName;
+ if (LexModuleName(PP, Tok, ModuleName))
+ return;
+
+ if (Tok.isNot(tok::eod))
+ PP.Diag(Tok, diag::ext_pp_extra_tokens_at_eol) << "pragma";
+
+ // If we have a non-empty module path, load the named module.
+ Module *Imported =
+ PP.getModuleLoader().loadModule(ImportLoc, ModuleName, Module::Hidden,
+ /*IsIncludeDirective=*/false);
+ if (!Imported)
+ return;
+
+ PP.makeModuleVisible(Imported, ImportLoc);
+ PP.EnterAnnotationToken(SourceRange(ImportLoc, ModuleName.back().second),
+ tok::annot_module_include, Imported);
+ if (auto *CB = PP.getPPCallbacks())
+ CB->moduleImport(ImportLoc, ModuleName, Imported);
+ }
+};
+
+/// Handle the clang \#pragma module begin extension. The syntax is:
+/// \code
+/// #pragma clang module begin some.module.name
+/// ...
+/// #pragma clang module end
+/// \endcode
+struct PragmaModuleBeginHandler : public PragmaHandler {
+ PragmaModuleBeginHandler() : PragmaHandler("begin") {}
+
+ void HandlePragma(Preprocessor &PP, PragmaIntroducerKind Introducer,
+ Token &Tok) override {
+ SourceLocation BeginLoc = Tok.getLocation();
+
+ // Read the module name.
+ llvm::SmallVector<std::pair<IdentifierInfo *, SourceLocation>, 8>
+ ModuleName;
+ if (LexModuleName(PP, Tok, ModuleName))
+ return;
+
+ if (Tok.isNot(tok::eod))
+ PP.Diag(Tok, diag::ext_pp_extra_tokens_at_eol) << "pragma";
+
+ // We can only enter submodules of the current module.
+ StringRef Current = PP.getLangOpts().CurrentModule;
+ if (ModuleName.front().first->getName() != Current) {
+ PP.Diag(ModuleName.front().second, diag::err_pp_module_begin_wrong_module)
+ << ModuleName.front().first << (ModuleName.size() > 1)
+ << Current.empty() << Current;
+ return;
+ }
+
+ // Find the module we're entering. We require that a module map for it
+ // be loaded or implicitly loadable.
+ // FIXME: We could create the submodule here. We'd need to know whether
+ // it's supposed to be explicit, but not much else.
+ Module *M = PP.getHeaderSearchInfo().getModuleMap().findModule(Current);
+ if (!M) {
+ PP.Diag(ModuleName.front().second,
+ diag::err_pp_module_begin_no_module_map) << Current;
+ return;
+ }
+ for (unsigned I = 1; I != ModuleName.size(); ++I) {
+ auto *NewM = M->findSubmodule(ModuleName[I].first->getName());
+ if (!NewM) {
+ PP.Diag(ModuleName[I].second, diag::err_pp_module_begin_no_submodule)
+ << M->getFullModuleName() << ModuleName[I].first;
+ return;
+ }
+ M = NewM;
+ }
+
+ // Enter the scope of the submodule.
+ PP.EnterSubmodule(M, BeginLoc, /*ForPragma*/true);
+ PP.EnterAnnotationToken(SourceRange(BeginLoc, ModuleName.back().second),
+ tok::annot_module_begin, M);
+ }
+};
+
+/// Handle the clang \#pragma module end extension.
+struct PragmaModuleEndHandler : public PragmaHandler {
+ PragmaModuleEndHandler() : PragmaHandler("end") {}
+
+ void HandlePragma(Preprocessor &PP, PragmaIntroducerKind Introducer,
+ Token &Tok) override {
+ SourceLocation Loc = Tok.getLocation();
+
+ PP.LexUnexpandedToken(Tok);
+ if (Tok.isNot(tok::eod))
+ PP.Diag(Tok, diag::ext_pp_extra_tokens_at_eol) << "pragma";
+
+ Module *M = PP.LeaveSubmodule(/*ForPragma*/true);
+ if (M)
+ PP.EnterAnnotationToken(SourceRange(Loc), tok::annot_module_end, M);
+ else
+ PP.Diag(Loc, diag::err_pp_module_end_without_module_begin);
}
};
@@ -1582,6 +1661,8 @@ void Preprocessor::RegisterBuiltinPragmas() {
auto *ModuleHandler = new PragmaNamespace("module");
AddPragmaHandler("clang", ModuleHandler);
ModuleHandler->AddPragma(new PragmaModuleImportHandler());
+ ModuleHandler->AddPragma(new PragmaModuleBeginHandler());
+ ModuleHandler->AddPragma(new PragmaModuleEndHandler());
AddPragmaHandler("STDC", new PragmaSTDC_FENV_ACCESSHandler());
AddPragmaHandler("STDC", new PragmaSTDC_CX_LIMITED_RANGEHandler());
diff --git a/lib/Lex/Preprocessor.cpp b/lib/Lex/Preprocessor.cpp
index babef5dcc7ca..e409ab036535 100644
--- a/lib/Lex/Preprocessor.cpp
+++ b/lib/Lex/Preprocessor.cpp
@@ -85,10 +85,10 @@ Preprocessor::Preprocessor(std::shared_ptr<PreprocessorOptions> PPOpts,
LastTokenWasAt(false), ModuleImportExpectsIdentifier(false),
CodeCompletionReached(false), CodeCompletionII(nullptr),
MainFileDir(nullptr), SkipMainFilePreamble(0, true), CurPPLexer(nullptr),
- CurDirLookup(nullptr), CurLexerKind(CLK_Lexer), CurSubmodule(nullptr),
- Callbacks(nullptr), CurSubmoduleState(&NullSubmoduleState),
- MacroArgCache(nullptr), Record(nullptr), MIChainHead(nullptr),
- DeserialMIChainHead(nullptr) {
+ CurDirLookup(nullptr), CurLexerKind(CLK_Lexer),
+ CurLexerSubmodule(nullptr), Callbacks(nullptr),
+ CurSubmoduleState(&NullSubmoduleState), MacroArgCache(nullptr),
+ Record(nullptr), MIChainHead(nullptr), DeserialMIChainHead(nullptr) {
OwnsHeaderSearch = OwnsHeaders;
CounterValue = 0; // __COUNTER__ starts at 0.
diff --git a/lib/Lex/TokenLexer.cpp b/lib/Lex/TokenLexer.cpp
index a53c8014ebaf..049e046cece1 100644
--- a/lib/Lex/TokenLexer.cpp
+++ b/lib/Lex/TokenLexer.cpp
@@ -183,6 +183,12 @@ void TokenLexer::ExpandFunctionArguments() {
// preprocessor already verified that the following token is a macro name
// when the #define was parsed.
const Token &CurTok = Tokens[i];
+ // We don't want a space for the next token after a paste
+ // operator. In valid code, the token will get smooshed onto the
+ // preceding one anyway. In assembler-with-cpp mode, invalid
+ // pastes are allowed through: in this case, we do not want the
+ // extra whitespace to be added. For example, we want ". ## foo"
+ // -> ".foo" not ". foo".
if (i != 0 && !Tokens[i-1].is(tok::hashhash) && CurTok.hasLeadingSpace())
NextTokGetsSpace = true;
@@ -317,6 +323,7 @@ void TokenLexer::ExpandFunctionArguments() {
const Token *ArgToks = ActualArgs->getUnexpArgument(ArgNo);
unsigned NumToks = MacroArgs::getArgLength(ArgToks);
if (NumToks) { // Not an empty argument?
+ bool VaArgsPseudoPaste = false;
// If this is the GNU ", ## __VA_ARGS__" extension, and we just learned
// that __VA_ARGS__ expands to multiple tokens, avoid a pasting error when
// the expander trys to paste ',' with the first token of the __VA_ARGS__
@@ -325,6 +332,7 @@ void TokenLexer::ExpandFunctionArguments() {
ResultToks[ResultToks.size()-2].is(tok::comma) &&
(unsigned)ArgNo == Macro->getNumArgs()-1 &&
Macro->isVariadic()) {
+ VaArgsPseudoPaste = true;
// Remove the paste operator, report use of the extension.
PP.Diag(ResultToks.pop_back_val().getLocation(), diag::ext_paste_comma);
}
@@ -344,18 +352,16 @@ void TokenLexer::ExpandFunctionArguments() {
ResultToks.end()-NumToks, ResultToks.end());
}
- // If this token (the macro argument) was supposed to get leading
- // whitespace, transfer this information onto the first token of the
- // expansion.
- //
- // Do not do this if the paste operator occurs before the macro argument,
- // as in "A ## MACROARG". In valid code, the first token will get
- // smooshed onto the preceding one anyway (forming AMACROARG). In
- // assembler-with-cpp mode, invalid pastes are allowed through: in this
- // case, we do not want the extra whitespace to be added. For example,
- // we want ". ## foo" -> ".foo" not ". foo".
- if (NextTokGetsSpace)
- ResultToks[ResultToks.size()-NumToks].setFlag(Token::LeadingSpace);
+ // Transfer the leading whitespace information from the token
+ // (the macro argument) onto the first token of the
+ // expansion. Note that we don't do this for the GNU
+ // pseudo-paste extension ", ## __VA_ARGS__".
+ if (!VaArgsPseudoPaste) {
+ ResultToks[ResultToks.size() - NumToks].setFlagValue(Token::StartOfLine,
+ false);
+ ResultToks[ResultToks.size() - NumToks].setFlagValue(
+ Token::LeadingSpace, NextTokGetsSpace);
+ }
NextTokGetsSpace = false;
continue;