https://github.com/owenca updated
https://github.com/llvm/llvm-project/pull/81390
>From 37a6723b2c9b95c0556ca53992192795e74c27ce Mon Sep 17 00:00:00 2001
From: Owen Pan <owenpi...@gmail.com>
Date: Sat, 10 Feb 2024 17:14:19 -0800
Subject: [PATCH 1/3] [clang-format][NFC] Make LangOpts global in namespace
Format
---
clang/include/clang/Format/Format.h | 6 +---
clang/lib/Format/Format.cpp | 30 ----------------
clang/lib/Format/FormatTokenLexer.cpp | 6 ++--
clang/lib/Format/FormatTokenLexer.h | 2 --
.../Format/IntegerLiteralSeparatorFixer.cpp | 2 +-
clang/lib/Format/TokenAnalyzer.cpp | 36 ++++++++++++++++++-
clang/unittests/Format/TestLexer.h | 4 ++-
7 files changed, 43 insertions(+), 43 deletions(-)
diff --git a/clang/include/clang/Format/Format.h
b/clang/include/clang/Format/Format.h
index ab56cc8b6f9135..bede7e88cdbc7a 100644
--- a/clang/include/clang/Format/Format.h
+++ b/clang/include/clang/Format/Format.h
@@ -14,7 +14,6 @@
#ifndef LLVM_CLANG_FORMAT_FORMAT_H
#define LLVM_CLANG_FORMAT_FORMAT_H
-#include "clang/Basic/LangOptions.h"
#include "clang/Tooling/Core/Replacement.h"
#include "clang/Tooling/Inclusions/IncludeStyle.h"
#include "llvm/ADT/ArrayRef.h"
@@ -5179,10 +5178,7 @@ tooling::Replacements sortUsingDeclarations(const
FormatStyle &Style,
ArrayRef<tooling::Range> Ranges,
StringRef FileName = "<stdin>");
-/// Returns the ``LangOpts`` that the formatter expects you to set.
-///
-/// \param Style determines specific settings for lexing mode.
-LangOptions getFormattingLangOpts(const FormatStyle &Style = getLLVMStyle());
+extern LangOptions LangOpts;
/// Description to be used for help text for a ``llvm::cl`` option for
/// specifying format style. The description is closely related to the
operation
diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index d2cc466744acbd..8431d3cfb14432 100644
--- a/clang/lib/Format/Format.cpp
+++ b/clang/lib/Format/Format.cpp
@@ -3823,36 +3823,6 @@ tooling::Replacements sortUsingDeclarations(const
FormatStyle &Style,
return UsingDeclarationsSorter(*Env, Style).process().first;
}
-LangOptions getFormattingLangOpts(const FormatStyle &Style) {
- LangOptions LangOpts;
-
- FormatStyle::LanguageStandard LexingStd = Style.Standard;
- if (LexingStd == FormatStyle::LS_Auto)
- LexingStd = FormatStyle::LS_Latest;
- if (LexingStd == FormatStyle::LS_Latest)
- LexingStd = FormatStyle::LS_Cpp20;
- LangOpts.CPlusPlus = 1;
- LangOpts.CPlusPlus11 = LexingStd >= FormatStyle::LS_Cpp11;
- LangOpts.CPlusPlus14 = LexingStd >= FormatStyle::LS_Cpp14;
- LangOpts.CPlusPlus17 = LexingStd >= FormatStyle::LS_Cpp17;
- LangOpts.CPlusPlus20 = LexingStd >= FormatStyle::LS_Cpp20;
- LangOpts.Char8 = LexingStd >= FormatStyle::LS_Cpp20;
- // Turning on digraphs in standards before C++0x is error-prone, because e.g.
- // the sequence "<::" will be unconditionally treated as "[:".
- // Cf. Lexer::LexTokenInternal.
- LangOpts.Digraphs = LexingStd >= FormatStyle::LS_Cpp11;
-
- LangOpts.LineComment = 1;
- bool AlternativeOperators = Style.isCpp();
- LangOpts.CXXOperatorNames = AlternativeOperators ? 1 : 0;
- LangOpts.Bool = 1;
- LangOpts.ObjC = 1;
- LangOpts.MicrosoftExt = 1; // To get kw___try, kw___finally.
- LangOpts.DeclSpecKeyword = 1; // To get __declspec.
- LangOpts.C99 = 1; // To get kw_restrict for non-underscore-prefixed restrict.
- return LangOpts;
-}
-
const char *StyleOptionHelpDescription =
"Set coding style. <string> can be:\n"
"1. A preset: LLVM, GNU, Google, Chromium, Microsoft,\n"
diff --git a/clang/lib/Format/FormatTokenLexer.cpp
b/clang/lib/Format/FormatTokenLexer.cpp
index a87d0ba3dbbf9b..e517e413ec91fb 100644
--- a/clang/lib/Format/FormatTokenLexer.cpp
+++ b/clang/lib/Format/FormatTokenLexer.cpp
@@ -28,12 +28,12 @@ FormatTokenLexer::FormatTokenLexer(
llvm::SpecificBumpPtrAllocator<FormatToken> &Allocator,
IdentifierTable &IdentTable)
: FormatTok(nullptr), IsFirstToken(true), StateStack({LexerState::NORMAL}),
- Column(Column), TrailingWhitespace(0),
- LangOpts(getFormattingLangOpts(Style)), SourceMgr(SourceMgr), ID(ID),
+ Column(Column), TrailingWhitespace(0), SourceMgr(SourceMgr), ID(ID),
Style(Style), IdentTable(IdentTable), Keywords(IdentTable),
Encoding(Encoding), Allocator(Allocator), FirstInLineIndex(0),
FormattingDisabled(false), MacroBlockBeginRegex(Style.MacroBlockBegin),
MacroBlockEndRegex(Style.MacroBlockEnd) {
+ assert(LangOpts.CPlusPlus);
Lex.reset(new Lexer(ID, SourceMgr.getBufferOrFake(ID), SourceMgr, LangOpts));
Lex->SetKeepWhitespaceMode(true);
@@ -1442,7 +1442,7 @@ void FormatTokenLexer::readRawToken(FormatToken &Tok) {
void FormatTokenLexer::resetLexer(unsigned Offset) {
StringRef Buffer = SourceMgr.getBufferData(ID);
- LangOpts = getFormattingLangOpts(Style);
+ assert(LangOpts.CPlusPlus);
Lex.reset(new Lexer(SourceMgr.getLocForStartOfFile(ID), LangOpts,
Buffer.begin(), Buffer.begin() + Offset, Buffer.end()));
Lex->SetKeepWhitespaceMode(true);
diff --git a/clang/lib/Format/FormatTokenLexer.h
b/clang/lib/Format/FormatTokenLexer.h
index 65dd733bd53352..0d0f36f1ea5308 100644
--- a/clang/lib/Format/FormatTokenLexer.h
+++ b/clang/lib/Format/FormatTokenLexer.h
@@ -17,7 +17,6 @@
#include "Encoding.h"
#include "FormatToken.h"
-#include "clang/Basic/LangOptions.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Format/Format.h"
@@ -120,7 +119,6 @@ class FormatTokenLexer {
unsigned Column;
unsigned TrailingWhitespace;
std::unique_ptr<Lexer> Lex;
- LangOptions LangOpts;
const SourceManager &SourceMgr;
FileID ID;
const FormatStyle &Style;
diff --git a/clang/lib/Format/IntegerLiteralSeparatorFixer.cpp
b/clang/lib/Format/IntegerLiteralSeparatorFixer.cpp
index 87823ae32b1138..3c2ceddd5599cf 100644
--- a/clang/lib/Format/IntegerLiteralSeparatorFixer.cpp
+++ b/clang/lib/Format/IntegerLiteralSeparatorFixer.cpp
@@ -79,7 +79,7 @@ IntegerLiteralSeparatorFixer::process(const Environment &Env,
AffectedRangeManager AffectedRangeMgr(SourceMgr, Env.getCharRanges());
const auto ID = Env.getFileID();
- const auto LangOpts = getFormattingLangOpts(Style);
+ assert(LangOpts.CPlusPlus);
Lexer Lex(ID, SourceMgr.getBufferOrFake(ID), SourceMgr, LangOpts);
Lex.SetCommentRetentionState(true);
diff --git a/clang/lib/Format/TokenAnalyzer.cpp
b/clang/lib/Format/TokenAnalyzer.cpp
index bd648c430f9b0a..4e7768332b41d5 100644
--- a/clang/lib/Format/TokenAnalyzer.cpp
+++ b/clang/lib/Format/TokenAnalyzer.cpp
@@ -35,6 +35,38 @@
namespace clang {
namespace format {
+LangOptions LangOpts;
+
+/// Sets `LangOpts` for the formatter.
+///
+/// \param `Style` determines specific settings for lexing mode.
+static void setFormattingLangOpts(const FormatStyle &Style) {
+ FormatStyle::LanguageStandard LexingStd = Style.Standard;
+ if (LexingStd == FormatStyle::LS_Auto)
+ LexingStd = FormatStyle::LS_Latest;
+ if (LexingStd == FormatStyle::LS_Latest)
+ LexingStd = FormatStyle::LS_Cpp20;
+ LangOpts.CPlusPlus = 1;
+ LangOpts.CPlusPlus11 = LexingStd >= FormatStyle::LS_Cpp11;
+ LangOpts.CPlusPlus14 = LexingStd >= FormatStyle::LS_Cpp14;
+ LangOpts.CPlusPlus17 = LexingStd >= FormatStyle::LS_Cpp17;
+ LangOpts.CPlusPlus20 = LexingStd >= FormatStyle::LS_Cpp20;
+ LangOpts.Char8 = LexingStd >= FormatStyle::LS_Cpp20;
+ // Turning on digraphs in standards before C++0x is error-prone, because e.g.
+ // the sequence "<::" will be unconditionally treated as "[:".
+ // Cf. Lexer::LexTokenInternal.
+ LangOpts.Digraphs = LexingStd >= FormatStyle::LS_Cpp11;
+
+ LangOpts.LineComment = 1;
+ bool AlternativeOperators = Style.isCpp();
+ LangOpts.CXXOperatorNames = AlternativeOperators ? 1 : 0;
+ LangOpts.Bool = 1;
+ LangOpts.ObjC = 1;
+ LangOpts.MicrosoftExt = 1; // To get kw___try, kw___finally.
+ LangOpts.DeclSpecKeyword = 1; // To get __declspec.
+ LangOpts.C99 = 1; // To get kw_restrict for non-underscore-prefixed restrict.
+}
+
// FIXME: Instead of printing the diagnostic we should store it and have a
// better way to return errors through the format APIs.
class FatalDiagnosticConsumer : public DiagnosticConsumer {
@@ -99,9 +131,11 @@ TokenAnalyzer::TokenAnalyzer(const Environment &Env, const
FormatStyle &Style)
std::pair<tooling::Replacements, unsigned>
TokenAnalyzer::process(bool SkipAnnotation) {
+ setFormattingLangOpts(Style);
+
tooling::Replacements Result;
llvm::SpecificBumpPtrAllocator<FormatToken> Allocator;
- IdentifierTable IdentTable(getFormattingLangOpts(Style));
+ IdentifierTable IdentTable(LangOpts);
FormatTokenLexer Lex(Env.getSourceManager(), Env.getFileID(),
Env.getFirstStartColumn(), Style, Encoding, Allocator,
IdentTable);
diff --git a/clang/unittests/Format/TestLexer.h
b/clang/unittests/Format/TestLexer.h
index 8b5949b32fc9ed..6a3d0bdedcee0a 100644
--- a/clang/unittests/Format/TestLexer.h
+++ b/clang/unittests/Format/TestLexer.h
@@ -61,7 +61,9 @@ class TestLexer : public UnwrappedLineConsumer {
std::vector<std::unique_ptr<llvm::MemoryBuffer>> &Buffers,
FormatStyle Style = getLLVMStyle())
: Allocator(Allocator), Buffers(Buffers), Style(Style),
- SourceMgr("test.cpp", ""), IdentTable(getFormattingLangOpts(Style)) {}
+ SourceMgr("test.cpp", ""), IdentTable(LangOpts) {
+ assert(LangOpts.CPlusPlus);
+ }
TokenList lex(llvm::StringRef Code) {
FormatTokenLexer Lex = getNewLexer(Code);
>From 44f0695fb21bfc1929a8b7b4070ca5f789046ec6 Mon Sep 17 00:00:00 2001
From: Owen Pan <owenpi...@gmail.com>
Date: Sat, 10 Feb 2024 17:41:09 -0800
Subject: [PATCH 2/3] Move the declaration of LangOpts from Format.h to
TokenAnalyzer.h
---
clang/include/clang/Format/Format.h | 2 --
clang/lib/Format/FormatTokenLexer.cpp | 1 +
clang/lib/Format/TokenAnalyzer.h | 2 ++
3 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/clang/include/clang/Format/Format.h
b/clang/include/clang/Format/Format.h
index bede7e88cdbc7a..b78b82a2ec6cc3 100644
--- a/clang/include/clang/Format/Format.h
+++ b/clang/include/clang/Format/Format.h
@@ -5178,8 +5178,6 @@ tooling::Replacements sortUsingDeclarations(const
FormatStyle &Style,
ArrayRef<tooling::Range> Ranges,
StringRef FileName = "<stdin>");
-extern LangOptions LangOpts;
-
/// Description to be used for help text for a ``llvm::cl`` option for
/// specifying format style. The description is closely related to the
operation
/// of ``getStyle()``.
diff --git a/clang/lib/Format/FormatTokenLexer.cpp
b/clang/lib/Format/FormatTokenLexer.cpp
index e517e413ec91fb..bcc763613439c1 100644
--- a/clang/lib/Format/FormatTokenLexer.cpp
+++ b/clang/lib/Format/FormatTokenLexer.cpp
@@ -14,6 +14,7 @@
#include "FormatTokenLexer.h"
#include "FormatToken.h"
+#include "TokenAnalyzer.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Format/Format.h"
diff --git a/clang/lib/Format/TokenAnalyzer.h b/clang/lib/Format/TokenAnalyzer.h
index 4086dab1c94c3a..18c1431eb37612 100644
--- a/clang/lib/Format/TokenAnalyzer.h
+++ b/clang/lib/Format/TokenAnalyzer.h
@@ -34,6 +34,8 @@
namespace clang {
namespace format {
+extern LangOptions LangOpts;
+
class Environment {
public:
// This sets up an virtual file system with file \p FileName containing the
>From df7b65ee3ffb2a3a07079dbde610daaeda4d0085 Mon Sep 17 00:00:00 2001
From: Owen Pan <owenpi...@gmail.com>
Date: Sat, 10 Feb 2024 23:24:45 -0800
Subject: [PATCH 3/3] Remove redundant #include lines.
---
clang/lib/Format/FormatTokenLexer.cpp | 5 -----
1 file changed, 5 deletions(-)
diff --git a/clang/lib/Format/FormatTokenLexer.cpp
b/clang/lib/Format/FormatTokenLexer.cpp
index bcc763613439c1..a57659fd422720 100644
--- a/clang/lib/Format/FormatTokenLexer.cpp
+++ b/clang/lib/Format/FormatTokenLexer.cpp
@@ -13,12 +13,7 @@
//===----------------------------------------------------------------------===//
#include "FormatTokenLexer.h"
-#include "FormatToken.h"
#include "TokenAnalyzer.h"
-#include "clang/Basic/SourceLocation.h"
-#include "clang/Basic/SourceManager.h"
-#include "clang/Format/Format.h"
-#include "llvm/Support/Regex.h"
namespace clang {
namespace format {
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
