[clang] Add -fkeep-system-includes modifier for -E (PR #67684)
Paul T Robinson via cfe-commits
cfe-commits at lists.llvm.org
Fri Sep 29 13:35:59 PDT 2023
https://github.com/pogo59 updated https://github.com/llvm/llvm-project/pull/67684
>From 2a0dd575dbbc6666f80d1cd264d6dbc8de8fa897 Mon Sep 17 00:00:00 2001
From: Paul Robinson <paul.robinson at sony.com>
Date: Wed, 27 Sep 2023 15:30:52 -0700
Subject: [PATCH 1/4] [NFC] Change a reference member to pointer
This will allow the raw_ostream to be redirected in a subsequent commit.
---
.../lib/Frontend/PrintPreprocessedOutput.cpp | 208 +++++++++---------
1 file changed, 104 insertions(+), 104 deletions(-)
diff --git a/clang/lib/Frontend/PrintPreprocessedOutput.cpp b/clang/lib/Frontend/PrintPreprocessedOutput.cpp
index 1b262d9e6f7cb3b..f86ba08d36223be 100644
--- a/clang/lib/Frontend/PrintPreprocessedOutput.cpp
+++ b/clang/lib/Frontend/PrintPreprocessedOutput.cpp
@@ -32,42 +32,42 @@ using namespace clang;
/// PrintMacroDefinition - Print a macro definition in a form that will be
/// properly accepted back as a definition.
static void PrintMacroDefinition(const IdentifierInfo &II, const MacroInfo &MI,
- Preprocessor &PP, raw_ostream &OS) {
- OS << "#define " << II.getName();
+ Preprocessor &PP, raw_ostream *OS) {
+ *OS << "#define " << II.getName();
if (MI.isFunctionLike()) {
- OS << '(';
+ *OS << '(';
if (!MI.param_empty()) {
MacroInfo::param_iterator AI = MI.param_begin(), E = MI.param_end();
for (; AI+1 != E; ++AI) {
- OS << (*AI)->getName();
- OS << ',';
+ *OS << (*AI)->getName();
+ *OS << ',';
}
// Last argument.
if ((*AI)->getName() == "__VA_ARGS__")
- OS << "...";
+ *OS << "...";
else
- OS << (*AI)->getName();
+ *OS << (*AI)->getName();
}
if (MI.isGNUVarargs())
- OS << "..."; // #define foo(x...)
+ *OS << "..."; // #define foo(x...)
- OS << ')';
+ *OS << ')';
}
// GCC always emits a space, even if the macro body is empty. However, do not
// want to emit two spaces if the first token has a leading space.
if (MI.tokens_empty() || !MI.tokens_begin()->hasLeadingSpace())
- OS << ' ';
+ *OS << ' ';
SmallString<128> SpellingBuffer;
for (const auto &T : MI.tokens()) {
if (T.hasLeadingSpace())
- OS << ' ';
+ *OS << ' ';
- OS << PP.getSpelling(T, SpellingBuffer);
+ *OS << PP.getSpelling(T, SpellingBuffer);
}
}
@@ -81,7 +81,7 @@ class PrintPPOutputPPCallbacks : public PPCallbacks {
SourceManager &SM;
TokenConcatenation ConcatInfo;
public:
- raw_ostream &OS;
+ raw_ostream *OS;
private:
unsigned CurLine;
@@ -102,7 +102,7 @@ class PrintPPOutputPPCallbacks : public PPCallbacks {
Token PrevPrevTok;
public:
- PrintPPOutputPPCallbacks(Preprocessor &pp, raw_ostream &os, bool lineMarkers,
+ PrintPPOutputPPCallbacks(Preprocessor &pp, raw_ostream *os, bool lineMarkers,
bool defines, bool DumpIncludeDirectives,
bool UseLineDirectives, bool MinimizeWhitespace,
bool DirectivesOnly)
@@ -235,23 +235,23 @@ void PrintPPOutputPPCallbacks::WriteLineInfo(unsigned LineNo,
// Emit #line directives or GNU line markers depending on what mode we're in.
if (UseLineDirectives) {
- OS << "#line" << ' ' << LineNo << ' ' << '"';
- OS.write_escaped(CurFilename);
- OS << '"';
+ *OS << "#line" << ' ' << LineNo << ' ' << '"';
+ OS->write_escaped(CurFilename);
+ *OS << '"';
} else {
- OS << '#' << ' ' << LineNo << ' ' << '"';
- OS.write_escaped(CurFilename);
- OS << '"';
+ *OS << '#' << ' ' << LineNo << ' ' << '"';
+ OS->write_escaped(CurFilename);
+ *OS << '"';
if (ExtraLen)
- OS.write(Extra, ExtraLen);
+ OS->write(Extra, ExtraLen);
if (FileType == SrcMgr::C_System)
- OS.write(" 3", 2);
+ OS->write(" 3", 2);
else if (FileType == SrcMgr::C_ExternCSystem)
- OS.write(" 3 4", 4);
+ OS->write(" 3 4", 4);
}
- OS << '\n';
+ *OS << '\n';
}
/// MoveToLine - Move the output to the source line specified by the location
@@ -266,7 +266,7 @@ bool PrintPPOutputPPCallbacks::MoveToLine(unsigned LineNo,
bool StartedNewLine = false;
if ((RequireStartOfLine && EmittedTokensOnThisLine) ||
EmittedDirectiveOnThisLine) {
- OS << '\n';
+ *OS << '\n';
StartedNewLine = true;
CurLine += 1;
EmittedTokensOnThisLine = false;
@@ -283,12 +283,12 @@ bool PrintPPOutputPPCallbacks::MoveToLine(unsigned LineNo,
// Printing a single line has priority over printing a #line directive, even
// when minimizing whitespace which otherwise would print #line directives
// for every single line.
- OS << '\n';
+ *OS << '\n';
StartedNewLine = true;
} else if (!DisableLineMarkers) {
if (LineNo - CurLine <= 8) {
const char *NewLines = "\n\n\n\n\n\n\n\n";
- OS.write(NewLines, LineNo - CurLine);
+ OS->write(NewLines, LineNo - CurLine);
} else {
// Emit a #line or line marker.
WriteLineInfo(LineNo, nullptr, 0);
@@ -297,7 +297,7 @@ bool PrintPPOutputPPCallbacks::MoveToLine(unsigned LineNo,
} else if (EmittedTokensOnThisLine) {
// If we are not on the correct line and don't need to be line-correct,
// at least ensure we start on a new line.
- OS << '\n';
+ *OS << '\n';
StartedNewLine = true;
}
@@ -312,7 +312,7 @@ bool PrintPPOutputPPCallbacks::MoveToLine(unsigned LineNo,
void PrintPPOutputPPCallbacks::startNewLineIfNeeded() {
if (EmittedTokensOnThisLine || EmittedDirectiveOnThisLine) {
- OS << '\n';
+ *OS << '\n';
EmittedTokensOnThisLine = false;
EmittedDirectiveOnThisLine = false;
}
@@ -399,9 +399,9 @@ void PrintPPOutputPPCallbacks::InclusionDirective(
MoveToLine(HashLoc, /*RequireStartOfLine=*/true);
const std::string TokenText = PP.getSpelling(IncludeTok);
assert(!TokenText.empty());
- OS << "#" << TokenText << " "
- << (IsAngled ? '<' : '"') << FileName << (IsAngled ? '>' : '"')
- << " /* clang -E -dI */";
+ *OS << "#" << TokenText << " "
+ << (IsAngled ? '<' : '"') << FileName << (IsAngled ? '>' : '"')
+ << " /* clang -E -dI */";
setEmittedDirectiveOnThisLine();
}
@@ -412,11 +412,11 @@ void PrintPPOutputPPCallbacks::InclusionDirective(
case tok::pp_import:
case tok::pp_include_next:
MoveToLine(HashLoc, /*RequireStartOfLine=*/true);
- OS << "#pragma clang module import " << Imported->getFullModuleName(true)
- << " /* clang -E: implicit import for "
- << "#" << PP.getSpelling(IncludeTok) << " "
- << (IsAngled ? '<' : '"') << FileName << (IsAngled ? '>' : '"')
- << " */";
+ *OS << "#pragma clang module import " << Imported->getFullModuleName(true)
+ << " /* clang -E: implicit import for "
+ << "#" << PP.getSpelling(IncludeTok) << " "
+ << (IsAngled ? '<' : '"') << FileName << (IsAngled ? '>' : '"')
+ << " */";
setEmittedDirectiveOnThisLine();
break;
@@ -438,14 +438,14 @@ void PrintPPOutputPPCallbacks::InclusionDirective(
/// Handle entering the scope of a module during a module compilation.
void PrintPPOutputPPCallbacks::BeginModule(const Module *M) {
startNewLineIfNeeded();
- OS << "#pragma clang module begin " << M->getFullModuleName(true);
+ *OS << "#pragma clang module begin " << M->getFullModuleName(true);
setEmittedDirectiveOnThisLine();
}
/// Handle leaving the scope of a module during a module compilation.
void PrintPPOutputPPCallbacks::EndModule(const Module *M) {
startNewLineIfNeeded();
- OS << "#pragma clang module end /*" << M->getFullModuleName(true) << "*/";
+ *OS << "#pragma clang module end /*" << M->getFullModuleName(true) << "*/";
setEmittedDirectiveOnThisLine();
}
@@ -454,8 +454,8 @@ void PrintPPOutputPPCallbacks::EndModule(const Module *M) {
void PrintPPOutputPPCallbacks::Ident(SourceLocation Loc, StringRef S) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS.write("#ident ", strlen("#ident "));
- OS.write(S.begin(), S.size());
+ OS->write("#ident ", strlen("#ident "));
+ OS->write(S.begin(), S.size());
setEmittedTokensOnThisLine();
}
@@ -491,19 +491,19 @@ void PrintPPOutputPPCallbacks::MacroUndefined(const Token &MacroNameTok,
return;
MoveToLine(MacroNameTok.getLocation(), /*RequireStartOfLine=*/true);
- OS << "#undef " << MacroNameTok.getIdentifierInfo()->getName();
+ *OS << "#undef " << MacroNameTok.getIdentifierInfo()->getName();
setEmittedDirectiveOnThisLine();
}
-static void outputPrintable(raw_ostream &OS, StringRef Str) {
+static void outputPrintable(raw_ostream *OS, StringRef Str) {
for (unsigned char Char : Str) {
if (isPrintable(Char) && Char != '\\' && Char != '"')
- OS << (char)Char;
+ *OS << (char)Char;
else // Output anything hard as an octal escape.
- OS << '\\'
- << (char)('0' + ((Char >> 6) & 7))
- << (char)('0' + ((Char >> 3) & 7))
- << (char)('0' + ((Char >> 0) & 7));
+ *OS << '\\'
+ << (char)('0' + ((Char >> 6) & 7))
+ << (char)('0' + ((Char >> 3) & 7))
+ << (char)('0' + ((Char >> 0) & 7));
}
}
@@ -512,25 +512,25 @@ void PrintPPOutputPPCallbacks::PragmaMessage(SourceLocation Loc,
PragmaMessageKind Kind,
StringRef Str) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma ";
+ *OS << "#pragma ";
if (!Namespace.empty())
- OS << Namespace << ' ';
+ *OS << Namespace << ' ';
switch (Kind) {
case PMK_Message:
- OS << "message(\"";
+ *OS << "message(\"";
break;
case PMK_Warning:
- OS << "warning \"";
+ *OS << "warning \"";
break;
case PMK_Error:
- OS << "error \"";
+ *OS << "error \"";
break;
}
outputPrintable(OS, Str);
- OS << '"';
+ *OS << '"';
if (Kind == PMK_Message)
- OS << ')';
+ *OS << ')';
setEmittedDirectiveOnThisLine();
}
@@ -538,8 +538,8 @@ void PrintPPOutputPPCallbacks::PragmaDebug(SourceLocation Loc,
StringRef DebugType) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma clang __debug ";
- OS << DebugType;
+ *OS << "#pragma clang __debug ";
+ *OS << DebugType;
setEmittedDirectiveOnThisLine();
}
@@ -547,14 +547,14 @@ void PrintPPOutputPPCallbacks::PragmaDebug(SourceLocation Loc,
void PrintPPOutputPPCallbacks::
PragmaDiagnosticPush(SourceLocation Loc, StringRef Namespace) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma " << Namespace << " diagnostic push";
+ *OS << "#pragma " << Namespace << " diagnostic push";
setEmittedDirectiveOnThisLine();
}
void PrintPPOutputPPCallbacks::
PragmaDiagnosticPop(SourceLocation Loc, StringRef Namespace) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma " << Namespace << " diagnostic pop";
+ *OS << "#pragma " << Namespace << " diagnostic pop";
setEmittedDirectiveOnThisLine();
}
@@ -563,25 +563,25 @@ void PrintPPOutputPPCallbacks::PragmaDiagnostic(SourceLocation Loc,
diag::Severity Map,
StringRef Str) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma " << Namespace << " diagnostic ";
+ *OS << "#pragma " << Namespace << " diagnostic ";
switch (Map) {
case diag::Severity::Remark:
- OS << "remark";
+ *OS << "remark";
break;
case diag::Severity::Warning:
- OS << "warning";
+ *OS << "warning";
break;
case diag::Severity::Error:
- OS << "error";
+ *OS << "error";
break;
case diag::Severity::Ignored:
- OS << "ignored";
+ *OS << "ignored";
break;
case diag::Severity::Fatal:
- OS << "fatal";
+ *OS << "fatal";
break;
}
- OS << " \"" << Str << '"';
+ *OS << " \"" << Str << '"';
setEmittedDirectiveOnThisLine();
}
@@ -590,69 +590,69 @@ void PrintPPOutputPPCallbacks::PragmaWarning(SourceLocation Loc,
ArrayRef<int> Ids) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma warning(";
+ *OS << "#pragma warning(";
switch(WarningSpec) {
- case PWS_Default: OS << "default"; break;
- case PWS_Disable: OS << "disable"; break;
- case PWS_Error: OS << "error"; break;
- case PWS_Once: OS << "once"; break;
- case PWS_Suppress: OS << "suppress"; break;
- case PWS_Level1: OS << '1'; break;
- case PWS_Level2: OS << '2'; break;
- case PWS_Level3: OS << '3'; break;
- case PWS_Level4: OS << '4'; break;
+ case PWS_Default: *OS << "default"; break;
+ case PWS_Disable: *OS << "disable"; break;
+ case PWS_Error: *OS << "error"; break;
+ case PWS_Once: *OS << "once"; break;
+ case PWS_Suppress: *OS << "suppress"; break;
+ case PWS_Level1: *OS << '1'; break;
+ case PWS_Level2: *OS << '2'; break;
+ case PWS_Level3: *OS << '3'; break;
+ case PWS_Level4: *OS << '4'; break;
}
- OS << ':';
+ *OS << ':';
for (ArrayRef<int>::iterator I = Ids.begin(), E = Ids.end(); I != E; ++I)
- OS << ' ' << *I;
- OS << ')';
+ *OS << ' ' << *I;
+ *OS << ')';
setEmittedDirectiveOnThisLine();
}
void PrintPPOutputPPCallbacks::PragmaWarningPush(SourceLocation Loc,
int Level) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma warning(push";
+ *OS << "#pragma warning(push";
if (Level >= 0)
- OS << ", " << Level;
- OS << ')';
+ *OS << ", " << Level;
+ *OS << ')';
setEmittedDirectiveOnThisLine();
}
void PrintPPOutputPPCallbacks::PragmaWarningPop(SourceLocation Loc) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma warning(pop)";
+ *OS << "#pragma warning(pop)";
setEmittedDirectiveOnThisLine();
}
void PrintPPOutputPPCallbacks::PragmaExecCharsetPush(SourceLocation Loc,
StringRef Str) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma character_execution_set(push";
+ *OS << "#pragma character_execution_set(push";
if (!Str.empty())
- OS << ", " << Str;
- OS << ')';
+ *OS << ", " << Str;
+ *OS << ')';
setEmittedDirectiveOnThisLine();
}
void PrintPPOutputPPCallbacks::PragmaExecCharsetPop(SourceLocation Loc) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma character_execution_set(pop)";
+ *OS << "#pragma character_execution_set(pop)";
setEmittedDirectiveOnThisLine();
}
void PrintPPOutputPPCallbacks::
PragmaAssumeNonNullBegin(SourceLocation Loc) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma clang assume_nonnull begin";
+ *OS << "#pragma clang assume_nonnull begin";
setEmittedDirectiveOnThisLine();
}
void PrintPPOutputPPCallbacks::
PragmaAssumeNonNullEnd(SourceLocation Loc) {
MoveToLine(Loc, /*RequireStartOfLine=*/true);
- OS << "#pragma clang assume_nonnull end";
+ *OS << "#pragma clang assume_nonnull end";
setEmittedDirectiveOnThisLine();
}
@@ -673,7 +673,7 @@ void PrintPPOutputPPCallbacks::HandleWhitespaceBeforeTok(const Token &Tok,
if (MinimizeWhitespace) {
// Avoid interpreting hash as a directive under -fpreprocessed.
if (Tok.is(tok::hash))
- OS << ' ';
+ *OS << ' ';
} else {
// Print out space characters so that the first token on a line is
// indented for easy reading.
@@ -693,11 +693,11 @@ void PrintPPOutputPPCallbacks::HandleWhitespaceBeforeTok(const Token &Tok,
// is not handled as a #define next time through the preprocessor if in
// -fpreprocessed mode.
if (ColNo <= 1 && Tok.is(tok::hash))
- OS << ' ';
+ *OS << ' ';
// Otherwise, indent the appropriate number of spaces.
for (; ColNo > 1; --ColNo)
- OS << ' ';
+ *OS << ' ';
}
} else {
// Insert whitespace between the previous and next token if either
@@ -709,7 +709,7 @@ void PrintPPOutputPPCallbacks::HandleWhitespaceBeforeTok(const Token &Tok,
if (RequireSpace || (!MinimizeWhitespace && Tok.hasLeadingSpace()) ||
((EmittedTokensOnThisLine || EmittedDirectiveOnThisLine) &&
AvoidConcat(PrevPrevTok, PrevTok, Tok)))
- OS << ' ';
+ *OS << ' ';
}
PrevPrevTok = PrevTok;
@@ -758,7 +758,7 @@ struct UnknownPragmaHandler : public PragmaHandler {
// Figure out what line we went to and insert the appropriate number of
// newline characters.
Callbacks->MoveToLine(PragmaTok.getLocation(), /*RequireStartOfLine=*/true);
- Callbacks->OS.write(Prefix, strlen(Prefix));
+ Callbacks->OS->write(Prefix, strlen(Prefix));
Callbacks->setEmittedTokensOnThisLine();
if (ShouldExpandTokens) {
@@ -779,7 +779,7 @@ struct UnknownPragmaHandler : public PragmaHandler {
/*RequireSameLine=*/true);
IsFirst = false;
std::string TokSpell = PP.getSpelling(PragmaTok);
- Callbacks->OS.write(&TokSpell[0], TokSpell.size());
+ Callbacks->OS->write(&TokSpell[0], TokSpell.size());
Callbacks->setEmittedTokensOnThisLine();
if (ShouldExpandTokens)
@@ -795,7 +795,7 @@ struct UnknownPragmaHandler : public PragmaHandler {
static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
PrintPPOutputPPCallbacks *Callbacks,
- raw_ostream &OS) {
+ raw_ostream *OS) {
bool DropComments = PP.getLangOpts().TraditionalCPP &&
!PP.getCommentRetentionState();
@@ -863,7 +863,7 @@ static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
// components. We don't have a good way to round-trip those.
Module *M = reinterpret_cast<Module *>(Tok.getAnnotationValue());
std::string Name = M->getFullModuleName();
- OS.write(Name.data(), Name.size());
+ OS->write(Name.data(), Name.size());
Callbacks->HandleNewlinesInToken(Name.data(), Name.size());
} else if (Tok.isAnnotation()) {
// Ignore annotation tokens created by pragmas - the pragmas themselves
@@ -871,14 +871,14 @@ static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
PP.Lex(Tok);
continue;
} else if (IdentifierInfo *II = Tok.getIdentifierInfo()) {
- OS << II->getName();
+ *OS << II->getName();
} else if (Tok.isLiteral() && !Tok.needsCleaning() &&
Tok.getLiteralData()) {
- OS.write(Tok.getLiteralData(), Tok.getLength());
+ OS->write(Tok.getLiteralData(), Tok.getLength());
} else if (Tok.getLength() < std::size(Buffer)) {
const char *TokPtr = Buffer;
unsigned Len = PP.getSpelling(Tok, TokPtr);
- OS.write(TokPtr, Len);
+ OS->write(TokPtr, Len);
// Tokens that can contain embedded newlines need to adjust our current
// line number.
@@ -895,7 +895,7 @@ static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
}
} else {
std::string S = PP.getSpelling(Tok);
- OS.write(S.data(), S.size());
+ OS->write(S.data(), S.size());
// Tokens that can contain embedded newlines need to adjust our current
// line number.
@@ -947,7 +947,7 @@ static void DoPrintMacros(Preprocessor &PP, raw_ostream *OS) {
// Ignore computed macros like __LINE__ and friends.
if (MI.isBuiltinMacro()) continue;
- PrintMacroDefinition(*MacrosByID[i].first, MI, PP, *OS);
+ PrintMacroDefinition(*MacrosByID[i].first, MI, PP, OS);
*OS << '\n';
}
}
@@ -968,7 +968,7 @@ void clang::DoPrintPreprocessedInput(Preprocessor &PP, raw_ostream *OS,
PP.SetCommentRetentionState(Opts.ShowComments, Opts.ShowMacroComments);
PrintPPOutputPPCallbacks *Callbacks = new PrintPPOutputPPCallbacks(
- PP, *OS, !Opts.ShowLineMarkers, Opts.ShowMacros,
+ PP, OS, !Opts.ShowLineMarkers, Opts.ShowMacros,
Opts.ShowIncludeDirectives, Opts.UseLineDirectives,
Opts.MinimizeWhitespace, Opts.DirectivesOnly);
@@ -1028,7 +1028,7 @@ void clang::DoPrintPreprocessedInput(Preprocessor &PP, raw_ostream *OS,
} while (true);
// Read all the preprocessed tokens, printing them out to the stream.
- PrintPreprocessedTokens(PP, Tok, Callbacks, *OS);
+ PrintPreprocessedTokens(PP, Tok, Callbacks, OS);
*OS << '\n';
// Remove the handlers we just added to leave the preprocessor in a sane state
>From a71131f734c90aeaff9c3fb0cdc57c0f81dd8971 Mon Sep 17 00:00:00 2001
From: Paul Robinson <paul.robinson at sony.com>
Date: Thu, 28 Sep 2023 07:18:11 -0700
Subject: [PATCH 2/4] Add -fkeep-system-includes modifier for -E
This option will cause -E to preserve the #include directives
for system headers, rather than expanding them into the output.
This can greatly reduce the volume of preprocessed source text
in a test case, making test case reduction simpler.
Note that -fkeep-system-includes is not always appropriate. For
example, if the problem you want to reproduce is induced by a
system header file, it's better to expand those headers fully.
If your source defines symbols that influence the content of a
system header (e.g., _POSIX_SOURCE) then -E will eliminate the
definition, potentially changing the meaning of the preprocessed
source. If you use -isystem to point to non-system headers, for
example to suppress warnings in third-party software, those will
not be expanded and might make the preprocessed source less useful
as a test case.
---
.../clang/Basic/DiagnosticDriverKinds.td | 4 +-
clang/include/clang/Driver/Options.td | 7 +++
.../Frontend/PreprocessorOutputOptions.h | 2 +
clang/lib/Driver/ToolChains/Clang.cpp | 18 +++++++-
.../lib/Frontend/PrintPreprocessedOutput.cpp | 43 ++++++++++++-------
clang/test/Frontend/Inputs/dashE/dashE.h | 3 ++
clang/test/Frontend/Inputs/dashE/sys/a.h | 3 ++
clang/test/Frontend/Inputs/dashE/sys/b.h | 1 +
clang/test/Frontend/dashE-sysincludes.cpp | 23 ++++++++++
.../minimize-whitespace-messages.c | 15 ++++---
10 files changed, 94 insertions(+), 25 deletions(-)
create mode 100644 clang/test/Frontend/Inputs/dashE/dashE.h
create mode 100644 clang/test/Frontend/Inputs/dashE/sys/a.h
create mode 100644 clang/test/Frontend/Inputs/dashE/sys/b.h
create mode 100644 clang/test/Frontend/dashE-sysincludes.cpp
diff --git a/clang/include/clang/Basic/DiagnosticDriverKinds.td b/clang/include/clang/Basic/DiagnosticDriverKinds.td
index 2a48c063e243ee0..446a610f56f0379 100644
--- a/clang/include/clang/Basic/DiagnosticDriverKinds.td
+++ b/clang/include/clang/Basic/DiagnosticDriverKinds.td
@@ -172,8 +172,8 @@ def err_drv_invalid_Xopenmp_target_with_args : Error<
"invalid -Xopenmp-target argument: '%0', options requiring arguments are unsupported">;
def err_drv_argument_only_allowed_with : Error<
"invalid argument '%0' only allowed with '%1'">;
-def err_drv_minws_unsupported_input_type : Error<
- "'-fminimize-whitespace' invalid for input of type %0">;
+def err_drv_opt_unsupported_input_type : Error<
+ "'%0' invalid for input of type %1">;
def err_drv_amdgpu_ieee_without_no_honor_nans : Error<
"invalid argument '-mno-amdgpu-ieee' only allowed with relaxed NaN handling">;
def err_drv_argument_not_allowed_with : Error<
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index f8143651cd3c151..4a64aee64d3f06e 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -2483,6 +2483,13 @@ defm minimize_whitespace : BoolFOption<"minimize-whitespace",
"whitespace such that two files with only formatting changes are "
"equal.\n\nOnly valid with -E on C-like inputs and incompatible "
"with -traditional-cpp.">, NegFlag<SetFalse>>;
+defm keep_system_includes : BoolFOption<"keep-system-includes",
+ PreprocessorOutputOpts<"KeepSystemIncludes">, DefaultFalse,
+ PosFlag<SetTrue, [], [ClangOption, CC1Option],
+ "Instead of expanding system headers when emitting preprocessor "
+ "output, preserve the #include directive. Useful when producing "
+ "preprocessed output for test case reduction.\n\nOnly valid with -E.">,
+ NegFlag<SetFalse>>;
def ffreestanding : Flag<["-"], "ffreestanding">, Group<f_Group>,
Visibility<[ClangOption, CC1Option]>,
diff --git a/clang/include/clang/Frontend/PreprocessorOutputOptions.h b/clang/include/clang/Frontend/PreprocessorOutputOptions.h
index d542032431b14c8..db2ec9f2ae20698 100644
--- a/clang/include/clang/Frontend/PreprocessorOutputOptions.h
+++ b/clang/include/clang/Frontend/PreprocessorOutputOptions.h
@@ -26,6 +26,7 @@ class PreprocessorOutputOptions {
unsigned RewriteImports : 1; ///< Include contents of transitively-imported modules.
unsigned MinimizeWhitespace : 1; ///< Ignore whitespace from input.
unsigned DirectivesOnly : 1; ///< Process directives but do not expand macros.
+ unsigned KeepSystemIncludes : 1; ///< Do not expand system headers.
public:
PreprocessorOutputOptions() {
@@ -40,6 +41,7 @@ class PreprocessorOutputOptions {
RewriteImports = 0;
MinimizeWhitespace = 0;
DirectivesOnly = 0;
+ KeepSystemIncludes = 0;
}
};
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index dda6aef641904aa..1101add97b65e85 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -68,7 +68,9 @@ using namespace llvm::opt;
static void CheckPreprocessingOptions(const Driver &D, const ArgList &Args) {
if (Arg *A = Args.getLastArg(clang::driver::options::OPT_C, options::OPT_CC,
options::OPT_fminimize_whitespace,
- options::OPT_fno_minimize_whitespace)) {
+ options::OPT_fno_minimize_whitespace,
+ options::OPT_fkeep_system_includes,
+ options::OPT_fno_keep_system_includes)) {
if (!Args.hasArg(options::OPT_E) && !Args.hasArg(options::OPT__SLASH_P) &&
!Args.hasArg(options::OPT__SLASH_EP) && !D.CCCIsCPP()) {
D.Diag(clang::diag::err_drv_argument_only_allowed_with)
@@ -6713,11 +6715,23 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
options::OPT_fno_minimize_whitespace, false)) {
types::ID InputType = Inputs[0].getType();
if (!isDerivedFromC(InputType))
- D.Diag(diag::err_drv_minws_unsupported_input_type)
+ D.Diag(diag::err_drv_opt_unsupported_input_type)
+ << "-fminimize-whitespace"
<< types::getTypeName(InputType);
CmdArgs.push_back("-fminimize-whitespace");
}
+ // -fno-keep-system-includes is default.
+ if (Args.hasFlag(options::OPT_fkeep_system_includes,
+ options::OPT_fno_keep_system_includes, false)) {
+ types::ID InputType = Inputs[0].getType();
+ if (!isDerivedFromC(InputType))
+ D.Diag(diag::err_drv_opt_unsupported_input_type)
+ << "-fkeep-system-includes"
+ << types::getTypeName(InputType);
+ CmdArgs.push_back("-fkeep-system-includes");
+ }
+
// -fms-extensions=0 is default.
if (Args.hasFlag(options::OPT_fms_extensions, options::OPT_fno_ms_extensions,
IsWindowsMSVC))
diff --git a/clang/lib/Frontend/PrintPreprocessedOutput.cpp b/clang/lib/Frontend/PrintPreprocessedOutput.cpp
index f86ba08d36223be..4056649e85c28a9 100644
--- a/clang/lib/Frontend/PrintPreprocessedOutput.cpp
+++ b/clang/lib/Frontend/PrintPreprocessedOutput.cpp
@@ -97,6 +97,9 @@ class PrintPPOutputPPCallbacks : public PPCallbacks {
bool IsFirstFileEntered;
bool MinimizeWhitespace;
bool DirectivesOnly;
+ bool KeepSystemIncludes;
+ raw_ostream *OrigOS;
+ std::unique_ptr<llvm::raw_null_ostream> NullOS;
Token PrevTok;
Token PrevPrevTok;
@@ -105,12 +108,13 @@ class PrintPPOutputPPCallbacks : public PPCallbacks {
PrintPPOutputPPCallbacks(Preprocessor &pp, raw_ostream *os, bool lineMarkers,
bool defines, bool DumpIncludeDirectives,
bool UseLineDirectives, bool MinimizeWhitespace,
- bool DirectivesOnly)
+ bool DirectivesOnly, bool KeepSystemIncludes)
: PP(pp), SM(PP.getSourceManager()), ConcatInfo(PP), OS(os),
DisableLineMarkers(lineMarkers), DumpDefines(defines),
DumpIncludeDirectives(DumpIncludeDirectives),
UseLineDirectives(UseLineDirectives),
- MinimizeWhitespace(MinimizeWhitespace), DirectivesOnly(DirectivesOnly) {
+ MinimizeWhitespace(MinimizeWhitespace), DirectivesOnly(DirectivesOnly),
+ KeepSystemIncludes(KeepSystemIncludes), OrigOS(os) {
CurLine = 0;
CurFilename += "<uninit>";
EmittedTokensOnThisLine = false;
@@ -118,6 +122,8 @@ class PrintPPOutputPPCallbacks : public PPCallbacks {
FileType = SrcMgr::C_User;
Initialized = false;
IsFirstFileEntered = false;
+ if (KeepSystemIncludes)
+ NullOS = std::make_unique<llvm::raw_null_ostream>();
PrevTok.startToken();
PrevPrevTok.startToken();
@@ -350,6 +356,10 @@ void PrintPPOutputPPCallbacks::FileChanged(SourceLocation Loc,
CurLine = NewLine;
+ // In KeepSystemIncludes mode, redirect OS as needed.
+ if (KeepSystemIncludes && (isSystem(FileType) != isSystem(NewFileType)))
+ OS = isSystem(FileType) ? OrigOS : NullOS.get();
+
CurFilename.clear();
CurFilename += UserLoc.getFilename();
FileType = NewFileType;
@@ -394,14 +404,16 @@ void PrintPPOutputPPCallbacks::InclusionDirective(
StringRef SearchPath, StringRef RelativePath, const Module *Imported,
SrcMgr::CharacteristicKind FileType) {
// In -dI mode, dump #include directives prior to dumping their content or
- // interpretation.
- if (DumpIncludeDirectives) {
+ // interpretation. Similar for -fkeep-system-includes.
+ if (DumpIncludeDirectives || (KeepSystemIncludes && isSystem(FileType))) {
MoveToLine(HashLoc, /*RequireStartOfLine=*/true);
const std::string TokenText = PP.getSpelling(IncludeTok);
assert(!TokenText.empty());
*OS << "#" << TokenText << " "
<< (IsAngled ? '<' : '"') << FileName << (IsAngled ? '>' : '"')
- << " /* clang -E -dI */";
+ << " /* clang -E "
+ << (DumpIncludeDirectives ? "-dI" : "-fkeep-system-includes")
+ << " */";
setEmittedDirectiveOnThisLine();
}
@@ -412,7 +424,8 @@ void PrintPPOutputPPCallbacks::InclusionDirective(
case tok::pp_import:
case tok::pp_include_next:
MoveToLine(HashLoc, /*RequireStartOfLine=*/true);
- *OS << "#pragma clang module import " << Imported->getFullModuleName(true)
+ *OS << "#pragma clang module import "
+ << Imported->getFullModuleName(true)
<< " /* clang -E: implicit import for "
<< "#" << PP.getSpelling(IncludeTok) << " "
<< (IsAngled ? '<' : '"') << FileName << (IsAngled ? '>' : '"')
@@ -794,8 +807,7 @@ struct UnknownPragmaHandler : public PragmaHandler {
static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
- PrintPPOutputPPCallbacks *Callbacks,
- raw_ostream *OS) {
+ PrintPPOutputPPCallbacks *Callbacks) {
bool DropComments = PP.getLangOpts().TraditionalCPP &&
!PP.getCommentRetentionState();
@@ -863,7 +875,7 @@ static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
// components. We don't have a good way to round-trip those.
Module *M = reinterpret_cast<Module *>(Tok.getAnnotationValue());
std::string Name = M->getFullModuleName();
- OS->write(Name.data(), Name.size());
+ Callbacks->OS->write(Name.data(), Name.size());
Callbacks->HandleNewlinesInToken(Name.data(), Name.size());
} else if (Tok.isAnnotation()) {
// Ignore annotation tokens created by pragmas - the pragmas themselves
@@ -871,14 +883,14 @@ static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
PP.Lex(Tok);
continue;
} else if (IdentifierInfo *II = Tok.getIdentifierInfo()) {
- *OS << II->getName();
+ *Callbacks->OS << II->getName();
} else if (Tok.isLiteral() && !Tok.needsCleaning() &&
Tok.getLiteralData()) {
- OS->write(Tok.getLiteralData(), Tok.getLength());
+ Callbacks->OS->write(Tok.getLiteralData(), Tok.getLength());
} else if (Tok.getLength() < std::size(Buffer)) {
const char *TokPtr = Buffer;
unsigned Len = PP.getSpelling(Tok, TokPtr);
- OS->write(TokPtr, Len);
+ Callbacks->OS->write(TokPtr, Len);
// Tokens that can contain embedded newlines need to adjust our current
// line number.
@@ -895,7 +907,7 @@ static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
}
} else {
std::string S = PP.getSpelling(Tok);
- OS->write(S.data(), S.size());
+ Callbacks->OS->write(S.data(), S.size());
// Tokens that can contain embedded newlines need to adjust our current
// line number.
@@ -970,7 +982,8 @@ void clang::DoPrintPreprocessedInput(Preprocessor &PP, raw_ostream *OS,
PrintPPOutputPPCallbacks *Callbacks = new PrintPPOutputPPCallbacks(
PP, OS, !Opts.ShowLineMarkers, Opts.ShowMacros,
Opts.ShowIncludeDirectives, Opts.UseLineDirectives,
- Opts.MinimizeWhitespace, Opts.DirectivesOnly);
+ Opts.MinimizeWhitespace, Opts.DirectivesOnly,
+ Opts.KeepSystemIncludes);
// Expand macros in pragmas with -fms-extensions. The assumption is that
// the majority of pragmas in such a file will be Microsoft pragmas.
@@ -1028,7 +1041,7 @@ void clang::DoPrintPreprocessedInput(Preprocessor &PP, raw_ostream *OS,
} while (true);
// Read all the preprocessed tokens, printing them out to the stream.
- PrintPreprocessedTokens(PP, Tok, Callbacks, OS);
+ PrintPreprocessedTokens(PP, Tok, Callbacks);
*OS << '\n';
// Remove the handlers we just added to leave the preprocessor in a sane state
diff --git a/clang/test/Frontend/Inputs/dashE/dashE.h b/clang/test/Frontend/Inputs/dashE/dashE.h
new file mode 100644
index 000000000000000..c1a9df40e34ddde
--- /dev/null
+++ b/clang/test/Frontend/Inputs/dashE/dashE.h
@@ -0,0 +1,3 @@
+int dashE_1;
+#include <a.h>
+int dashE_2;
diff --git a/clang/test/Frontend/Inputs/dashE/sys/a.h b/clang/test/Frontend/Inputs/dashE/sys/a.h
new file mode 100644
index 000000000000000..55b2bcb4ccb4083
--- /dev/null
+++ b/clang/test/Frontend/Inputs/dashE/sys/a.h
@@ -0,0 +1,3 @@
+int a_1;
+#include <b.h>
+int a_2;
diff --git a/clang/test/Frontend/Inputs/dashE/sys/b.h b/clang/test/Frontend/Inputs/dashE/sys/b.h
new file mode 100644
index 000000000000000..67bdce58dfb976e
--- /dev/null
+++ b/clang/test/Frontend/Inputs/dashE/sys/b.h
@@ -0,0 +1 @@
+int b_1;
diff --git a/clang/test/Frontend/dashE-sysincludes.cpp b/clang/test/Frontend/dashE-sysincludes.cpp
new file mode 100644
index 000000000000000..db0c488d715775d
--- /dev/null
+++ b/clang/test/Frontend/dashE-sysincludes.cpp
@@ -0,0 +1,23 @@
+// RUN: mkdir %t.dir
+// RUN: %clang_cc1 -E -fkeep-system-includes -I %S/Inputs/dashE -isystem %S/Inputs/dashE/sys %s | FileCheck %s
+
+int main_1 = 1;
+#include <a.h>
+int main_2 = 1;
+#include "dashE.h"
+int main_3 = 1;
+
+// CHECK: main_1
+// CHECK: #include <a.h>
+// CHECK-NOT: a_1
+// CHECK-NOT: a_2
+// CHECK-NOT: b.h
+// CHECK: main_2
+// CHECK-NOT: #include "dashE.h"
+// CHECK: dashE_1
+// CHECK: #include <a.h>
+// CHECK-NOT: a_1
+// CHECK-NOT: a_2
+// CHECK-NOT: b.h
+// CHECK: dashE_2
+// CHECK: main_3
diff --git a/clang/test/Preprocessor/minimize-whitespace-messages.c b/clang/test/Preprocessor/minimize-whitespace-messages.c
index a78ddb471fb7c08..f930bbe9c257f2c 100644
--- a/clang/test/Preprocessor/minimize-whitespace-messages.c
+++ b/clang/test/Preprocessor/minimize-whitespace-messages.c
@@ -1,8 +1,11 @@
-// RUN: not %clang -c -fminimize-whitespace %s 2>&1 | FileCheck %s --check-prefix=ON
-// ON: error: invalid argument '-fminimize-whitespace' only allowed with '-E'
+// RUN: not %clang -c -fminimize-whitespace %s 2>&1 | FileCheck %s --check-prefix=ON -DOPT=-fminimize-whitespace
+// RUN: not %clang -c -fkeep-system-includes %s 2>&1 | FileCheck %s --check-prefix=ON -DOPT=-fkeep-system-includes
+// ON: error: invalid argument '[[OPT]]' only allowed with '-E'
-// RUN: not %clang -c -fno-minimize-whitespace %s 2>&1 | FileCheck %s --check-prefix=OFF
-// OFF: error: invalid argument '-fno-minimize-whitespace' only allowed with '-E'
+// RUN: not %clang -c -fno-minimize-whitespace %s 2>&1 | FileCheck %s --check-prefix=OFF -DOPT=-fno-minimize-whitespace
+// RUN: not %clang -c -fno-keep-system-includes %s 2>&1 | FileCheck %s --check-prefix=OFF -DOPT=-fno-keep-system-includes
+// OFF: error: invalid argument '[[OPT]]' only allowed with '-E'
-// RUN: not %clang -E -fminimize-whitespace -x assembler-with-cpp %s 2>&1 | FileCheck %s --check-prefix=ASM
-// ASM: error: '-fminimize-whitespace' invalid for input of type assembler-with-cpp
+// RUN: not %clang -E -fminimize-whitespace -x assembler-with-cpp %s 2>&1 | FileCheck %s --check-prefix=ASM -DOPT=-fminimize-whitespace
+// RUN: not %clang -E -fkeep-system-includes -x assembler-with-cpp %s 2>&1 | FileCheck %s --check-prefix=ASM -DOPT=-fkeep-system-includes
+// ASM: error: '[[OPT]]' invalid for input of type assembler-with-cpp
>From a10c5e32d135f7bc456d6eb79f360f87378c270b Mon Sep 17 00:00:00 2001
From: Paul Robinson <paul.robinson at sony.com>
Date: Fri, 29 Sep 2023 12:18:30 -0700
Subject: [PATCH 3/4] Add caveats to the help text.
---
clang/include/clang/Driver/Options.td | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index 4a64aee64d3f06e..ea95f415c8aad2d 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -2488,7 +2488,11 @@ defm keep_system_includes : BoolFOption<"keep-system-includes",
PosFlag<SetTrue, [], [ClangOption, CC1Option],
"Instead of expanding system headers when emitting preprocessor "
"output, preserve the #include directive. Useful when producing "
- "preprocessed output for test case reduction.\n\nOnly valid with -E.">,
+ "preprocessed output for test case reduction. May produce incorrect "
+ "output if preprocessor symbols that control the included content "
+ "(e.g. _XOPEN_SOURCE) are defined in the including source file. The "
+ "portability of the resulting source to other compilation environments "
+ "is not guaranteed.\n\nOnly valid with -E.">,
NegFlag<SetFalse>>;
def ffreestanding : Flag<["-"], "ffreestanding">, Group<f_Group>,
>From 6c8908db85fc53ef8208b9a1682df216e4fcbe88 Mon Sep 17 00:00:00 2001
From: Paul Robinson <paul.robinson at sony.com>
Date: Fri, 29 Sep 2023 13:35:46 -0700
Subject: [PATCH 4/4] Add doc and release note
---
clang/docs/CommandGuide/clang.rst | 15 +++++++++++++++
clang/docs/ReleaseNotes.rst | 4 ++++
2 files changed, 19 insertions(+)
diff --git a/clang/docs/CommandGuide/clang.rst b/clang/docs/CommandGuide/clang.rst
index 139c8f25137d3fb..e1c872cdc55396a 100644
--- a/clang/docs/CommandGuide/clang.rst
+++ b/clang/docs/CommandGuide/clang.rst
@@ -684,6 +684,21 @@ Preprocessor Options
Do not search clang's builtin directory for include files.
+.. option:: -fkeep-system-includes
+
+ Usable only with :option:`-E`. Do not copy the preprocessed content of
+ "system" headers to the output; instead, preserve the #include directive.
+ This can greatly reduce the volume of text produced by :option:`-E` which
+ can be helpful when trying to produce a "small" reproduceable test case.
+
+ This option does not guarantee reproduceability, however. If the including
+ source defines preprocessor symbols that influence the behavior of system
+ headers (for example, ``_XOPEN_SOURCE``) the operation of :option:`-E` will
+ remove that definition and thus can change the semantics of the included
+ header. Also, using a different version of the system headers (especially a
+ different version of the STL) may result in different behavior. Always verify
+ the preprocessed file by compiling it separately.
+
ENVIRONMENT
-----------
diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst
index 68172d5317a13ba..d13e4ac7e0fe5e8 100644
--- a/clang/docs/ReleaseNotes.rst
+++ b/clang/docs/ReleaseNotes.rst
@@ -141,6 +141,10 @@ Non-comprehensive list of changes in this release
New Compiler Flags
------------------
+- ``-fkeep-system-includes`` modifies the behavior of the ``-E`` option,
+ preserving ``#include`` directives for "system" headers instead of copying
+ the preprocessed text to the output. This can greatly reduce the size of the
+ preprocessed output, which can be helpful when trying to reduce a test case.
Deprecated Compiler Flags
-------------------------
More information about the cfe-commits
mailing list