klimek created this revision.
klimek added a reviewer: sammccall.
Herald added a project: All.
klimek requested review of this revision.
Herald added a project: clang.
Add configuration to specify macros.
Macros will be expanded, and the code will be parsed and annotated
in the expanded state. In a second step, the formatting decisions
in the annotated expanded code will be reconstructed onto the
original unexpanded macro call.
Eventually, this will allow to remove special-case code for
various macro options we accumulated over the years in favor of
one principled mechanism.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D144170
Files:
clang/include/clang/Format/Format.h
clang/lib/Format/ContinuationIndenter.cpp
clang/lib/Format/Format.cpp
clang/lib/Format/FormatToken.h
clang/lib/Format/Macros.h
clang/lib/Format/TokenAnalyzer.cpp
clang/lib/Format/TokenAnalyzer.h
clang/lib/Format/TokenAnnotator.cpp
clang/lib/Format/TokenAnnotator.h
clang/lib/Format/UnwrappedLineFormatter.cpp
clang/lib/Format/UnwrappedLineParser.cpp
clang/lib/Format/UnwrappedLineParser.h
clang/lib/Format/WhitespaceManager.cpp
clang/unittests/Format/FormatTest.cpp
clang/unittests/Format/TestLexer.h
Index: clang/unittests/Format/TestLexer.h
===================================================================
--- clang/unittests/Format/TestLexer.h
+++ clang/unittests/Format/TestLexer.h
@@ -72,7 +72,8 @@
TokenList annotate(llvm::StringRef Code) {
FormatTokenLexer Lex = getNewLexer(Code);
auto Tokens = Lex.lex();
- UnwrappedLineParser Parser(Style, Lex.getKeywords(), 0, Tokens, *this);
+ UnwrappedLineParser Parser(SourceMgr.get(), Style, Lex.getKeywords(), 0,
+ Tokens, *this, Allocator, IdentTable);
Parser.parse();
TokenAnnotator Annotator(Style, Lex.getKeywords());
for (auto &Line : UnwrappedLines) {
Index: clang/unittests/Format/FormatTest.cpp
===================================================================
--- clang/unittests/Format/FormatTest.cpp
+++ clang/unittests/Format/FormatTest.cpp
@@ -66,7 +66,8 @@
void _verifyFormat(const char *File, int Line, llvm::StringRef Expected,
llvm::StringRef Code,
- const FormatStyle &Style = getLLVMStyle()) {
+ const FormatStyle &Style = getLLVMStyle(),
+ bool MessUp = true) {
ScopedTrace t(File, Line, ::testing::Message() << Code.str());
EXPECT_EQ(Expected.str(), format(Expected, Style))
<< "Expected code is not stable";
@@ -76,20 +77,24 @@
// needs to be checked for Objective-C++ as well.
FormatStyle ObjCStyle = Style;
ObjCStyle.Language = FormatStyle::LK_ObjC;
- EXPECT_EQ(Expected.str(), format(test::messUp(Code), ObjCStyle));
+ EXPECT_EQ(Expected.str(),
+ format(MessUp ? test::messUp(Code) : Code, ObjCStyle));
}
}
void _verifyFormat(const char *File, int Line, llvm::StringRef Code,
- const FormatStyle &Style = getLLVMStyle()) {
- _verifyFormat(File, Line, Code, test::messUp(Code), Style);
+ const FormatStyle &Style = getLLVMStyle(),
+ bool MessUp = true) {
+ _verifyFormat(File, Line, Code, MessUp ? test::messUp(Code) : Code, Style,
+ MessUp);
}
void _verifyIncompleteFormat(const char *File, int Line, llvm::StringRef Code,
- const FormatStyle &Style = getLLVMStyle()) {
+ const FormatStyle &Style = getLLVMStyle(),
+ bool MessUp = true) {
ScopedTrace t(File, Line, ::testing::Message() << Code.str());
- EXPECT_EQ(Code.str(),
- format(test::messUp(Code), Style, SC_ExpectIncomplete));
+ EXPECT_EQ(Code.str(), format(MessUp ? test::messUp(Code) : Code, Style,
+ SC_ExpectIncomplete));
}
void _verifyIndependentOfContext(const char *File, int Line,
@@ -22568,6 +22573,189 @@
"aaaallvm::outs()\n <<");
}
+TEST_F(FormatTest, UnexpandConfiguredMacros) {
+ FormatStyle Style = getLLVMStyle();
+ Style.Macros.push_back("CLASS=class C {");
+ Style.Macros.push_back("SEMI=;");
+ Style.Macros.push_back("STMT=f();");
+ Style.Macros.push_back("ID(x)=x");
+ Style.Macros.push_back("ID3(x, y, z)=x y z");
+ Style.Macros.push_back("CALL(x)=f([] { x })");
+ Style.Macros.push_back("ASSIGN_OR_RETURN(a, b, c)=a = (b) ||Â (c)");
+
+ verifyFormat("ID(nested(a(b, c), d))", Style);
+ verifyFormat("CLASS\n"
+ " a *b;\n"
+ "};",
+ Style);
+ verifyFormat("SEMI\n"
+ "SEMI\n"
+ "SEMI",
+ Style);
+ verifyFormat("STMT\n"
+ "STMT\n"
+ "STMT",
+ Style);
+ verifyFormat("void f() { ID(a *b); }", Style);
+ verifyFormat(R"(ID(
+ { ID(a *b); });
+)",
+ Style);
+ verifyIncompleteFormat(R"(ID3({, ID(a *b),
+ ;
+ });
+)",
+ Style);
+
+ verifyFormat("ID(CALL(CALL(return a * b;)));", Style);
+
+ verifyFormat("ASSIGN_OR_RETURN(MySomewhatLongType *variable,\n"
+ " MySomewhatLongFunction(SomethingElse()));\n",
+ Style);
+
+ verifyFormat(R"(
+#define MACRO(a, b) ID(a + b)
+)",
+ Style);
+ EXPECT_EQ(R"(
+int a;
+int b;
+int c;
+int d;
+int e;
+int f;
+ID(
+ namespace foo {
+ int a;
+ }
+) // namespace k
+)",
+ format(R"(
+int a;
+int b;
+int c;
+int d;
+int e;
+int f;
+ID(namespace foo { int a; }) // namespace k
+)",
+ Style));
+ verifyFormat(R"(ID(
+ //
+ ({ ; }))
+)",
+ Style);
+
+ Style.ColumnLimit = 35;
+ // FIXME: Arbitrary formatting of macros where the end of the logical
+ // line is in the middle of a macro call are not working yet.
+ verifyFormat(R"(ID(
+ void f();
+ void)
+ID(g) ID(()) ID(
+ ;
+ void g();)
+)",
+ Style);
+
+ Style.ColumnLimit = 10;
+ verifyFormat("STMT\n"
+ "STMT\n"
+ "STMT",
+ Style);
+
+ EXPECT_EQ(R"(
+ID(CALL(CALL(
+ a *b)));
+)",
+ format(R"(
+ID(CALL(CALL(a * b)));
+)",
+ Style));
+
+ // FIXME: If we want to support unbalanced braces or parens from macro
+ // expansions we need to re-think how we propagate errors in
+ // TokenAnnotator::parseLine; for investigation, switching the inner loop of
+ // TokenAnnotator::parseLine to return LT_Other instead of LT_Invalid in case
+ // of !consumeToken() changes the formatting of the test below and makes it
+ // believe it has a fully correct formatting.
+ EXPECT_EQ(R"(
+ID3(
+ {
+ CLASS
+ a *b;
+ };
+ },
+ ID(x *y);
+ ,
+ STMT
+ STMT
+ STMT)
+void f();
+)",
+ format(R"(
+ID3({CLASS a*b; };}, ID(x*y);, STMT STMT STMT)
+void f();
+)",
+ Style));
+
+ verifyFormat("ID(a(\n"
+ "#ifdef A\n"
+ " b, c\n"
+ "#else\n"
+ " d(e)\n"
+ "#endif\n"
+ " ))",
+ Style);
+ Style.ColumnLimit = 80;
+ verifyFormat(R"(ASSIGN_OR_RETURN(
+ // Comment
+ a b, c);
+)",
+ Style);
+ Style.ColumnLimit = 30;
+ verifyFormat(R"(ASSIGN_OR_RETURN(
+ // Comment
+ //
+ a b,
+ xxxxxxxxxxxx(
+ yyyyyyyyyyyyyyyyy,
+ zzzzzzzzzzzzzzzzzz),
+ f([]() {
+ a();
+ b();
+ }));
+)",
+ Style);
+ verifyFormat(R"(int a = []() {
+ ID(
+ x;
+ y;
+ z;)
+ ;
+}();
+)",
+ Style);
+ verifyIncompleteFormat(R"(ASSIGN_OR_RETURN((
+====
+#))
+})",
+ Style, /*MessUp=*/false);
+ verifyIncompleteFormat(R"(ASSIGN_OR_RETURN(
+}
+(
+====
+#),
+a))",
+ Style, /*MessUp=*/false);
+ verifyFormat(R"(ASSIGN_OR_RETURN(a
+//
+====
+#
+ <))",
+ Style, /*MessUp=*/false);
+}
+
TEST_F(FormatTest, HandleUnbalancedImplicitBracesAcrossPPBranches) {
std::string code = "#if A\n"
"#if B\n"
Index: clang/lib/Format/WhitespaceManager.cpp
===================================================================
--- clang/lib/Format/WhitespaceManager.cpp
+++ clang/lib/Format/WhitespaceManager.cpp
@@ -49,7 +49,7 @@
unsigned Spaces,
unsigned StartOfTokenColumn,
bool IsAligned, bool InPPDirective) {
- if (Tok.Finalized)
+ if (Tok.Finalized || (Tok.MacroCtx && Tok.MacroCtx->Role == MR_ExpandedArg))
return;
Tok.setDecision((Newlines > 0) ? FD_Break : FD_Continue);
Changes.push_back(Change(Tok, /*CreateReplacement=*/true, Tok.WhitespaceRange,
@@ -60,7 +60,7 @@
void WhitespaceManager::addUntouchableToken(const FormatToken &Tok,
bool InPPDirective) {
- if (Tok.Finalized)
+ if (Tok.Finalized || (Tok.MacroCtx && Tok.MacroCtx->Role == MR_ExpandedArg))
return;
Changes.push_back(Change(Tok, /*CreateReplacement=*/false,
Tok.WhitespaceRange, /*Spaces=*/0,
@@ -84,7 +84,7 @@
const FormatToken &Tok, unsigned Offset, unsigned ReplaceChars,
StringRef PreviousPostfix, StringRef CurrentPrefix, bool InPPDirective,
unsigned Newlines, int Spaces) {
- if (Tok.Finalized)
+ if (Tok.Finalized || (Tok.MacroCtx && Tok.MacroCtx->Role == MR_ExpandedArg))
return;
SourceLocation Start = Tok.getStartOfNonWhitespace().getLocWithOffset(Offset);
Changes.push_back(
Index: clang/lib/Format/UnwrappedLineParser.h
===================================================================
--- clang/lib/Format/UnwrappedLineParser.h
+++ clang/lib/Format/UnwrappedLineParser.h
@@ -15,10 +15,14 @@
#ifndef LLVM_CLANG_LIB_FORMAT_UNWRAPPEDLINEPARSER_H
#define LLVM_CLANG_LIB_FORMAT_UNWRAPPEDLINEPARSER_H
+#include "Encoding.h"
#include "FormatToken.h"
+#include "Macros.h"
#include "clang/Basic/IdentifierTable.h"
#include "clang/Format/Format.h"
+#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/BitVector.h"
+#include "llvm/ADT/DenseSet.h"
#include "llvm/Support/Regex.h"
#include <list>
#include <stack>
@@ -71,6 +75,11 @@
/// line with the corresponding closing brace.
size_t MatchingClosingBlockLineIndex = kInvalidIndex;
+ void resetIndexes() {
+ MatchingOpeningBlockLineIndex = kInvalidIndex;
+ MatchingClosingBlockLineIndex = kInvalidIndex;
+ }
+
static const size_t kInvalidIndex = -1;
unsigned FirstStartColumn = 0;
@@ -84,13 +93,17 @@
};
class FormatTokenSource;
+class MacroCallReconstructor;
class UnwrappedLineParser {
public:
- UnwrappedLineParser(const FormatStyle &Style,
+ UnwrappedLineParser(SourceManager &SourceMgr, const FormatStyle &Style,
const AdditionalKeywords &Keywords,
unsigned FirstStartColumn, ArrayRef<FormatToken *> Tokens,
- UnwrappedLineConsumer &Callback);
+ UnwrappedLineConsumer &Callback,
+ llvm::SpecificBumpPtrAllocator<FormatToken> &Allocator,
+ IdentifierTable &IdentTable);
+ ~UnwrappedLineParser();
void parse();
@@ -193,6 +206,7 @@
unsigned parseVerilogHierarchyHeader();
void parseVerilogTable();
void parseVerilogCaseLabel();
+ llvm::SmallVector<llvm::SmallVector<FormatToken *, 8>, 1> parseMacroCall();
// Used by addUnwrappedLine to denote whether to keep or remove a level
// when resetting the line state.
@@ -236,6 +250,10 @@
bool isOnNewLine(const FormatToken &FormatTok);
+ // Returns whether there is a macro expansion in the line, i.e. a token that
+ // was expanded from a macro call.
+ bool containsExpansion(const UnwrappedLine &Line);
+
// Compute hash of the current preprocessor branch.
// This is used to identify the different branches, and thus track if block
// open and close in the same branch.
@@ -246,6 +264,26 @@
// and use that everywhere in the Parser.
std::unique_ptr<UnwrappedLine> Line;
+ // Lines that are created by macro expansion.
+ // When formatting code containing macro calls, we first format the expanded
+ // lines to set the token types correctly. Afterwards, we format the
+ // reconstructed macro calls, re-using the token types determined in the first
+ // step.
+ SmallVector<UnwrappedLine, 8> ExpandedLines;
+
+ // Map from the macro identifier to a line containing the full unexpanded
+ // macro call.
+ llvm::DenseMap<FormatToken *, std::unique_ptr<UnwrappedLine>> Unexpanded;
+
+ // For recursive macro expansions, trigger reconstruction only on the
+ // outermost expansion.
+ bool InExpansion = false;
+
+ // Non-null while we reconstruct a macro call.
+ // For reconstruction, we feed the expanded lines into the reconstructor
+ // until it is finished.
+ std::unique_ptr<MacroCallReconstructor> Reconstruct;
+
// Comments are sorted into unwrapped lines by whether they are in the same
// line as the previous token, or not. If not, they belong to the next token.
// Since the next token might already be in a new unwrapped line, we need to
@@ -345,13 +383,17 @@
// does not start at the beginning of the file.
unsigned FirstStartColumn;
+ MacroExpander Macros;
+
friend class ScopedLineState;
friend class CompoundStatementIndenter;
};
struct UnwrappedLineNode {
UnwrappedLineNode() : Tok(nullptr) {}
- UnwrappedLineNode(FormatToken *Tok) : Tok(Tok) {}
+ UnwrappedLineNode(FormatToken *Tok,
+ llvm::ArrayRef<UnwrappedLine> Children = {})
+ : Tok(Tok), Children(Children.begin(), Children.end()) {}
FormatToken *Tok;
SmallVector<UnwrappedLine, 0> Children;
Index: clang/lib/Format/UnwrappedLineParser.cpp
===================================================================
--- clang/lib/Format/UnwrappedLineParser.cpp
+++ clang/lib/Format/UnwrappedLineParser.cpp
@@ -14,11 +14,15 @@
#include "UnwrappedLineParser.h"
#include "FormatToken.h"
+#include "FormatTokenLexer.h"
#include "FormatTokenSource.h"
+#include "Macros.h"
#include "TokenAnnotator.h"
#include "clang/Basic/TokenKinds.h"
#include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/StringRef.h"
#include "llvm/Support/Debug.h"
+#include "llvm/Support/raw_os_ostream.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
@@ -143,11 +147,12 @@
unsigned OldLineLevel;
};
-UnwrappedLineParser::UnwrappedLineParser(const FormatStyle &Style,
- const AdditionalKeywords &Keywords,
- unsigned FirstStartColumn,
- ArrayRef<FormatToken *> Tokens,
- UnwrappedLineConsumer &Callback)
+UnwrappedLineParser::UnwrappedLineParser(
+ SourceManager &SourceMgr, const FormatStyle &Style,
+ const AdditionalKeywords &Keywords, unsigned FirstStartColumn,
+ ArrayRef<FormatToken *> Tokens, UnwrappedLineConsumer &Callback,
+ llvm::SpecificBumpPtrAllocator<FormatToken> &Allocator,
+ IdentifierTable &IdentTable)
: Line(new UnwrappedLine), MustBreakBeforeNextToken(false),
CurrentLines(&Lines), Style(Style), Keywords(Keywords),
CommentPragmasRegex(Style.CommentPragmas), Tokens(nullptr),
@@ -155,7 +160,10 @@
IncludeGuard(Style.IndentPPDirectives == FormatStyle::PPDIS_None
? IG_Rejected
: IG_Inited),
- IncludeGuardToken(nullptr), FirstStartColumn(FirstStartColumn) {}
+ IncludeGuardToken(nullptr), FirstStartColumn(FirstStartColumn),
+ Macros(Style.Macros, SourceMgr, Style, Allocator, IdentTable) {}
+
+UnwrappedLineParser::~UnwrappedLineParser() {}
void UnwrappedLineParser::reset() {
PPBranchLevel = -1;
@@ -173,6 +181,14 @@
NestedTooDeep.clear();
PPStack.clear();
Line->FirstStartColumn = FirstStartColumn;
+
+ if (!Unexpanded.empty())
+ for (FormatToken *Token : AllTokens)
+ Token->MacroCtx.reset();
+ ExpandedLines.clear();
+ Unexpanded.clear();
+ InExpansion = false;
+ Reconstruct.reset();
}
void UnwrappedLineParser::parse() {
@@ -196,12 +212,24 @@
}
// Create line with eof token.
+ assert(FormatTok->is(tok::eof));
pushToken(FormatTok);
addUnwrappedLine();
- for (const UnwrappedLine &Line : Lines)
- Callback.consumeUnwrappedLine(Line);
+ if (!ExpandedLines.empty()) {
+ LLVM_DEBUG(llvm::dbgs() << "Expanded lines:\n");
+ for (const auto &Line : ExpandedLines) {
+ LLVM_DEBUG(printDebugInfo(Line));
+ Callback.consumeUnwrappedLine(Line);
+ }
+ Callback.finishRun();
+ }
+ LLVM_DEBUG(llvm::dbgs() << "Unwrapped lines:\n");
+ for (const UnwrappedLine &Line : Lines) {
+ LLVM_DEBUG(printDebugInfo(Line));
+ Callback.consumeUnwrappedLine(Line);
+ }
Callback.finishRun();
Lines.clear();
while (!PPLevelBranchIndex.empty() &&
@@ -4152,12 +4180,25 @@
Line->Level = OrigLevel;
}
+bool UnwrappedLineParser::containsExpansion(const UnwrappedLine &Line) {
+ for (const auto &N : Line.Tokens) {
+ if (N.Tok->MacroCtx)
+ return true;
+ for (const UnwrappedLine &Child : N.Children)
+ if (containsExpansion(Child))
+ return true;
+ }
+ return false;
+}
+
void UnwrappedLineParser::addUnwrappedLine(LineLevel AdjustLevel) {
if (Line->Tokens.empty())
return;
LLVM_DEBUG({
- if (CurrentLines == &Lines)
+ if (CurrentLines == &Lines) {
+ llvm::dbgs() << "Adding unwrapped line:\n";
printDebugInfo(*Line);
+ }
});
// If this line closes a block when in Whitesmiths mode, remember that
@@ -4168,7 +4209,44 @@
Line->MatchingOpeningBlockLineIndex != UnwrappedLine::kInvalidIndex &&
Style.BreakBeforeBraces == FormatStyle::BS_Whitesmiths;
- CurrentLines->push_back(std::move(*Line));
+ // If the current line was expanded from a macro call, we use it to
+ // reconstruct an unwrapped line from the structure of the expanded unwrapped
+ // line and the unexpanded token stream.
+ if (CurrentLines == &Lines && !InExpansion && containsExpansion(*Line)) {
+ if (!Reconstruct) {
+ Reconstruct =
+ std::make_unique<MacroCallReconstructor>(Line->Level, Unexpanded);
+ }
+ Reconstruct->addLine(*Line);
+ if (Reconstruct->finished()) {
+ UnwrappedLine Reconstructed = std::move(*Reconstruct).takeResult();
+ assert(!Reconstructed.Tokens.empty() &&
+ "Reconstructed must at least contain the macro identifier.");
+ LLVM_DEBUG({
+ if (CurrentLines == &Lines) {
+ llvm::dbgs() << "Adding unexpanded line:\n";
+ printDebugInfo(Reconstructed);
+ }
+ });
+ CurrentLines->push_back(std::move(Reconstructed));
+ Reconstruct.reset();
+ }
+ // FIXME: We format the expanded lines in an extra step that does not give
+ // the formatter all unwrapped lines, thus the indexes are invalid; to allow
+ // all features during expanded line formatting, recalcuate the indexes
+ // based on the available expanded lines where possible.
+ Line->resetIndexes();
+
+ // While the reconstructed unexpanded lines are stored in the normal
+ // flow of lines, the expanded lines are stored on the side to be analyzed
+ // in an extra step.
+ ExpandedLines.push_back(std::move(*Line));
+ } else {
+ // At the top level we only get here when no unexpansion is going on, or
+ // when conditional formatting led to unfinished macro reconstructions.
+ assert(!Reconstruct || (CurrentLines != &Lines) || PPStack.size() > 0);
+ CurrentLines->push_back(std::move(*Line));
+ }
Line->Tokens.clear();
Line->MatchingOpeningBlockLineIndex = UnwrappedLine::kInvalidIndex;
Line->FirstStartColumn = 0;
@@ -4470,6 +4548,47 @@
continue;
}
+ if (FormatTok->is(tok::identifier) &&
+ Macros.defined(FormatTok->TokenText) &&
+ // FIXME: Allow expanding macros in preprocessor directives.
+ !Line->InPPDirective) {
+ FormatToken *ID = FormatTok;
+
+ // To correctly parse the code, we need to replace the tokens of the macro
+ // call with its expansion.
+ auto PreCall = std::move(Line);
+ Line.reset(new UnwrappedLine);
+ bool OldInExpansion = InExpansion;
+ InExpansion = true;
+ // We parse the macro call into a new line.
+ auto Args = parseMacroCall();
+ InExpansion = OldInExpansion;
+ assert(Line->Tokens.front().Tok == ID);
+ // And remember the unexpanded macro call tokens.
+ Unexpanded[ID] = std::move(Line);
+
+ // Next, we insert the expanded tokens in the token stream at the current
+ // position, and continue parsing.
+ Line = std::move(PreCall);
+ SmallVector<FormatToken *, 8> New = Macros.expand(ID, Args);
+ if (!New.empty())
+ FormatTok = Tokens->insertTokens(New);
+
+ LLVM_DEBUG({
+ llvm::dbgs() << "Call: " << ID->TokenText << "(";
+ for (const auto &Arg : Args)
+ for (const auto &T : Arg)
+ llvm::dbgs() << T->TokenText << " ";
+ llvm::dbgs() << ")\n";
+ });
+ LLVM_DEBUG({
+ llvm::dbgs() << "Expanded: ";
+ for (const auto &T : New)
+ llvm::dbgs() << T->TokenText << " ";
+ llvm::dbgs() << "\n";
+ });
+ }
+
if (!FormatTok->is(tok::comment)) {
distributeComments(Comments, FormatTok);
Comments.clear();
@@ -4483,6 +4602,65 @@
Comments.clear();
}
+namespace {
+template <typename Iterator>
+void pushTokens(Iterator Begin, Iterator End,
+ llvm::SmallVectorImpl<FormatToken *> &Into) {
+ for (auto I = Begin; I != End; ++I) {
+ Into.push_back(I->Tok);
+ for (const auto &Child : I->Children)
+ pushTokens(Child.Tokens.begin(), Child.Tokens.end(), Into);
+ }
+}
+} // namespace
+
+llvm::SmallVector<llvm::SmallVector<FormatToken *, 8>, 1>
+UnwrappedLineParser::parseMacroCall() {
+ llvm::SmallVector<llvm::SmallVector<FormatToken *, 8>, 1> Args;
+ assert(Line->Tokens.empty());
+ nextToken();
+ if (FormatTok->isNot(tok::l_paren))
+ return Args;
+ nextToken();
+ auto ArgStart = std::prev(Line->Tokens.end());
+
+ int Parens = 0;
+ do {
+ switch (FormatTok->Tok.getKind()) {
+ case tok::l_paren:
+ ++Parens;
+ nextToken();
+ break;
+ case tok::r_paren: {
+ if (Parens > 0) {
+ --Parens;
+ nextToken();
+ break;
+ }
+ Args.push_back({});
+ pushTokens(std::next(ArgStart), Line->Tokens.end(), Args.back());
+ nextToken();
+ return Args;
+ }
+ case tok::comma: {
+ if (Parens > 0) {
+ nextToken();
+ break;
+ }
+ Args.push_back({});
+ pushTokens(std::next(ArgStart), Line->Tokens.end(), Args.back());
+ nextToken();
+ ArgStart = std::prev(Line->Tokens.end());
+ break;
+ }
+ default:
+ nextToken();
+ break;
+ }
+ } while (!eof());
+ return {};
+}
+
void UnwrappedLineParser::pushToken(FormatToken *Tok) {
Line->Tokens.push_back(UnwrappedLineNode(Tok));
if (MustBreakBeforeNextToken) {
Index: clang/lib/Format/UnwrappedLineFormatter.cpp
===================================================================
--- clang/lib/Format/UnwrappedLineFormatter.cpp
+++ clang/lib/Format/UnwrappedLineFormatter.cpp
@@ -7,6 +7,7 @@
//===----------------------------------------------------------------------===//
#include "UnwrappedLineFormatter.h"
+#include "FormatToken.h"
#include "NamespaceEndCommentsFixer.h"
#include "WhitespaceManager.h"
#include "llvm/Support/Debug.h"
@@ -918,9 +919,12 @@
static void markFinalized(FormatToken *Tok) {
for (; Tok; Tok = Tok->Next) {
- Tok->Finalized = true;
- for (AnnotatedLine *Child : Tok->Children)
- markFinalized(Child->First);
+ if (Tok->MacroCtx && Tok->MacroCtx->Role == MR_ExpandedArg) {
+ Tok->MacroCtx->Role = MR_UnexpandedArg;
+ Tok->SpacesRequiredBefore = 0;
+ } else {
+ Tok->Finalized = true;
+ }
}
}
@@ -975,15 +979,15 @@
bool formatChildren(LineState &State, bool NewLine, bool DryRun,
unsigned &Penalty) {
const FormatToken *LBrace = State.NextToken->getPreviousNonComment();
+ bool HasLBrace = LBrace && LBrace->is(tok::l_brace) && LBrace->is(BK_Block);
FormatToken &Previous = *State.NextToken->Previous;
- if (!LBrace || LBrace->isNot(tok::l_brace) || LBrace->isNot(BK_Block) ||
- Previous.Children.size() == 0) {
+ if (Previous.Children.size() == 0 || (!HasLBrace && !LBrace->MacroParent)) {
// The previous token does not open a block. Nothing to do. We don't
// assert so that we can simply call this function for all tokens.
return true;
}
- if (NewLine) {
+ if (NewLine || Previous.MacroParent) {
const ParenState &P = State.Stack.back();
int AdditionalIndent =
@@ -1349,11 +1353,12 @@
NextLine = Joiner.getNextMergedLine(DryRun, IndentTracker);
unsigned ColumnLimit = getColumnLimit(TheLine.InPPDirective, NextLine);
bool FitsIntoOneLine =
- TheLine.Last->TotalLength + Indent <= ColumnLimit ||
- (TheLine.Type == LT_ImportStatement &&
- (!Style.isJavaScript() || !Style.JavaScriptWrapImports)) ||
- (Style.isCSharp() &&
- TheLine.InPPDirective); // don't split #regions in C#
+ !TheLine.ContainsMacroCall &&
+ (TheLine.Last->TotalLength + Indent <= ColumnLimit ||
+ (TheLine.Type == LT_ImportStatement &&
+ (!Style.isJavaScript() || !Style.JavaScriptWrapImports)) ||
+ (Style.isCSharp() &&
+ TheLine.InPPDirective)); // don't split #regions in C#
if (Style.ColumnLimit == 0) {
NoColumnLimitLineFormatter(Indenter, Whitespaces, Style, this)
.formatLine(TheLine, NextStartColumn + Indent,
Index: clang/lib/Format/TokenAnnotator.h
===================================================================
--- clang/lib/Format/TokenAnnotator.h
+++ clang/lib/Format/TokenAnnotator.h
@@ -65,20 +65,32 @@
// left them in a different state.
First->Previous = nullptr;
FormatToken *Current = First;
+ addChildren(Line.Tokens.front(), Current);
for (const UnwrappedLineNode &Node : llvm::drop_begin(Line.Tokens)) {
+ if (Node.Tok->MacroParent)
+ ContainsMacroCall = true;
Current->Next = Node.Tok;
Node.Tok->Previous = Current;
Current = Current->Next;
- Current->Children.clear();
- for (const auto &Child : Node.Children) {
- Children.push_back(new AnnotatedLine(Child));
- Current->Children.push_back(Children.back());
- }
+ addChildren(Node, Current);
+ // FIXME: if we add children, previous will point to the token before
+ // the children; changing this requires significant changes across
+ // clang-format.
}
Last = Current;
Last->Next = nullptr;
}
+ void addChildren(const UnwrappedLineNode &Node, FormatToken *Current) {
+ Current->Children.clear();
+ for (const auto &Child : Node.Children) {
+ Children.push_back(new AnnotatedLine(Child));
+ if (Children.back()->ContainsMacroCall)
+ ContainsMacroCall = true;
+ Current->Children.push_back(Children.back());
+ }
+ }
+
~AnnotatedLine() {
for (AnnotatedLine *Child : Children)
delete Child;
@@ -149,6 +161,9 @@
bool MightBeFunctionDecl;
bool IsMultiVariableDeclStmt;
+ /// \c True if this line contains a macro call for which an expansion exists.
+ bool ContainsMacroCall = false;
+
/// \c True if this line should be formatted, i.e. intersects directly or
/// indirectly with one of the input ranges.
bool Affected;
Index: clang/lib/Format/TokenAnnotator.cpp
===================================================================
--- clang/lib/Format/TokenAnnotator.cpp
+++ clang/lib/Format/TokenAnnotator.cpp
@@ -2595,6 +2595,13 @@
// Consume operators with higher precedence.
parse(Precedence + 1);
+ // Do not assign fake parenthesis to tokens that are part of an
+ // unexpanded macro call. The line within the macro call contains
+ // the parenthesis and commas, and we will not find operators within
+ // that structure.
+ if (Current && Current->MacroParent)
+ break;
+
int CurrentPrecedence = getCurrentPrecedence();
if (Precedence == CurrentPrecedence && Current &&
@@ -4225,8 +4232,12 @@
Left.isOneOf(TT_TrailingReturnArrow, TT_LambdaArrow)) {
return true;
}
- if (Left.is(tok::comma) && !Right.is(TT_OverloadedOperatorLParen))
+ if (Left.is(tok::comma) && !Right.is(TT_OverloadedOperatorLParen) &&
+ // In an unexpanded macro call we only find the parentheses and commas
+ // in a line; the commas and closing parenthesis do not require a space.
+ (Left.Children.empty() || !Left.MacroParent)) {
return true;
+ }
if (Right.is(tok::comma))
return false;
if (Right.is(TT_ObjCBlockLParen))
Index: clang/lib/Format/TokenAnalyzer.h
===================================================================
--- clang/lib/Format/TokenAnalyzer.h
+++ clang/lib/Format/TokenAnalyzer.h
@@ -46,7 +46,7 @@
FileID getFileID() const { return ID; }
- const SourceManager &getSourceManager() const { return SM; }
+ SourceManager &getSourceManager() const { return SM; }
ArrayRef<CharSourceRange> getCharRanges() const { return CharRanges; }
Index: clang/lib/Format/TokenAnalyzer.cpp
===================================================================
--- clang/lib/Format/TokenAnalyzer.cpp
+++ clang/lib/Format/TokenAnalyzer.cpp
@@ -104,12 +104,12 @@
IdentifierTable IdentTable(getFormattingLangOpts(Style));
FormatTokenLexer Lex(Env.getSourceManager(), Env.getFileID(),
Env.getFirstStartColumn(), Style, Encoding, Allocator,
-
IdentTable);
ArrayRef<FormatToken *> Toks(Lex.lex());
SmallVector<FormatToken *, 10> Tokens(Toks.begin(), Toks.end());
- UnwrappedLineParser Parser(Style, Lex.getKeywords(),
- Env.getFirstStartColumn(), Tokens, *this);
+ UnwrappedLineParser Parser(Env.getSourceManager(), Style, Lex.getKeywords(),
+ Env.getFirstStartColumn(), Tokens, *this,
+ Allocator, IdentTable);
Parser.parse();
assert(UnwrappedLines.back().empty());
unsigned Penalty = 0;
Index: clang/lib/Format/Macros.h
===================================================================
--- clang/lib/Format/Macros.h
+++ clang/lib/Format/Macros.h
@@ -149,7 +149,7 @@
///
/// After this point, the state of the spelled/expanded stream is "in sync"
/// (both at the start of an UnwrappedLine, with no macros open), so the
-/// Unexpander can be thrown away and parsing can continue.
+/// Reconstructor can be thrown away and parsing can continue.
///
/// Given a mapping from the macro name identifier token in the macro call
/// to the tokens of the macro call, for example:
Index: clang/lib/Format/FormatToken.h
===================================================================
--- clang/lib/Format/FormatToken.h
+++ clang/lib/Format/FormatToken.h
@@ -373,6 +373,11 @@
/// binary operator.
TokenType getType() const { return Type; }
void setType(TokenType T) {
+ // If this token is a macro argument while formatting an unexpanded macro
+ // call, we do not change its type any more - the type was deduced from
+ // formatting the expanded macro stream already.
+ if (MacroCtx && MacroCtx->Role == MR_UnexpandedArg)
+ return;
assert((!TypeIsFinalized || T == Type) &&
"Please use overwriteFixedType to change a fixed type.");
Type = T;
Index: clang/lib/Format/Format.cpp
===================================================================
--- clang/lib/Format/Format.cpp
+++ clang/lib/Format/Format.cpp
@@ -1036,6 +1036,7 @@
IO.mapOptional("UseTab", Style.UseTab);
IO.mapOptional("WhitespaceSensitiveMacros",
Style.WhitespaceSensitiveMacros);
+ IO.mapOptional("Macros", Style.Macros);
// If AlwaysBreakAfterDefinitionReturnType was specified but
// AlwaysBreakAfterReturnType was not, initialize the latter from the
Index: clang/lib/Format/ContinuationIndenter.cpp
===================================================================
--- clang/lib/Format/ContinuationIndenter.cpp
+++ clang/lib/Format/ContinuationIndenter.cpp
@@ -18,6 +18,7 @@
#include "WhitespaceManager.h"
#include "clang/Basic/OperatorPrecedence.h"
#include "clang/Basic/SourceManager.h"
+#include "clang/Basic/TokenKinds.h"
#include "clang/Format/Format.h"
#include "llvm/ADT/StringSet.h"
#include "llvm/Support/Debug.h"
@@ -739,9 +740,15 @@
if (Previous.is(TT_TemplateString) && Previous.opensScope())
CurrentState.NoLineBreak = true;
+ // Align following lines within parenthesis / brackets if configured.
+ // For a line of macro parents, the commas that follow the opening parenthesis
+ // in the line come after the opening parenthesis' children - we want to align
+ // the comma with the previous token's children instead of the opening
+ // parenthesis.
if (Style.AlignAfterOpenBracket != FormatStyle::BAS_DontAlign &&
!CurrentState.IsCSharpGenericTypeConstraint && Previous.opensScope() &&
Previous.isNot(TT_ObjCMethodExpr) && Previous.isNot(TT_RequiresClause) &&
+ !(Current.MacroParent && Previous.MacroParent) &&
(Current.isNot(TT_LineComment) || Previous.is(BK_BracedInit))) {
CurrentState.Indent = State.Column + Spaces;
CurrentState.IsAligned = true;
Index: clang/include/clang/Format/Format.h
===================================================================
--- clang/include/clang/Format/Format.h
+++ clang/include/clang/Format/Format.h
@@ -2745,6 +2745,23 @@
/// \version 3.7
std::string MacroBlockEnd;
+ /// A list of macros of the form \c <definition>=<expansion> .
+ ///
+ /// Code will be parsed with macros expanded, and formatting will try to best
+ /// match the structure of the expanded call.
+ ///
+ /// For example, with the macro "A(x)=x", the code
+ /// \code
+ /// A(a * b);
+ /// \endcode
+ /// will be formatted as a declaration of the variable \c b of type \c A*
+ /// (depending on pointer-binding rules)
+ /// \code
+ /// A(a* b);
+ /// \endcode
+ /// instead of as multiplication.
+ std::vector<std::string> Macros;
+
/// The maximum number of consecutive empty lines to keep.
/// \code
/// MaxEmptyLinesToKeep: 1 vs. MaxEmptyLinesToKeep: 0
@@ -4306,7 +4323,8 @@
StatementAttributeLikeMacros == R.StatementAttributeLikeMacros &&
StatementMacros == R.StatementMacros && TabWidth == R.TabWidth &&
TypenameMacros == R.TypenameMacros && UseTab == R.UseTab &&
- WhitespaceSensitiveMacros == R.WhitespaceSensitiveMacros;
+ WhitespaceSensitiveMacros == R.WhitespaceSensitiveMacros &&
+ Macros == R.Macros;
}
std::optional<FormatStyle> GetLanguageStyle(LanguageKind Language) const;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
