blob: e424fcb34219661cd1593379542be67cac7e1157 [file] [log] [blame]
//===--- UnwrappedLineParser.cpp - Format C++ code ------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \file
/// This file contains the implementation of the UnwrappedLineParser,
/// which turns a stream of tokens into UnwrappedLines.
///
//===----------------------------------------------------------------------===//
#include "UnwrappedLineParser.h"
#include "FormatToken.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#define DEBUG_TYPE "format-parser"
namespace clang {
namespace format {
class FormatTokenSource {
public:
virtual ~FormatTokenSource() {}
virtual FormatToken *getNextToken() = 0;
virtual unsigned getPosition() = 0;
virtual FormatToken *setPosition(unsigned Position) = 0;
};
namespace {
class ScopedDeclarationState {
public:
ScopedDeclarationState(UnwrappedLine &Line, std::vector<bool> &Stack,
bool MustBeDeclaration)
: Line(Line), Stack(Stack) {
Line.MustBeDeclaration = MustBeDeclaration;
Stack.push_back(MustBeDeclaration);
}
~ScopedDeclarationState() {
Stack.pop_back();
if (!Stack.empty())
Line.MustBeDeclaration = Stack.back();
else
Line.MustBeDeclaration = true;
}
private:
UnwrappedLine &Line;
std::vector<bool> &Stack;
};
static bool isLineComment(const FormatToken &FormatTok) {
return FormatTok.is(tok::comment) && !FormatTok.TokenText.startswith("/*");
}
// Checks if \p FormatTok is a line comment that continues the line comment
// \p Previous. The original column of \p MinColumnToken is used to determine
// whether \p FormatTok is indented enough to the right to continue \p Previous.
static bool continuesLineComment(const FormatToken &FormatTok,
const FormatToken *Previous,
const FormatToken *MinColumnToken) {
if (!Previous || !MinColumnToken)
return false;
unsigned MinContinueColumn =
MinColumnToken->OriginalColumn + (isLineComment(*MinColumnToken) ? 0 : 1);
return isLineComment(FormatTok) && FormatTok.NewlinesBefore == 1 &&
isLineComment(*Previous) &&
FormatTok.OriginalColumn >= MinContinueColumn;
}
class ScopedMacroState : public FormatTokenSource {
public:
ScopedMacroState(UnwrappedLine &Line, FormatTokenSource *&TokenSource,
FormatToken *&ResetToken)
: Line(Line), TokenSource(TokenSource), ResetToken(ResetToken),
PreviousLineLevel(Line.Level), PreviousTokenSource(TokenSource),
Token(nullptr), PreviousToken(nullptr) {
FakeEOF.Tok.startToken();
FakeEOF.Tok.setKind(tok::eof);
TokenSource = this;
Line.Level = 0;
Line.InPPDirective = true;
}
~ScopedMacroState() override {
TokenSource = PreviousTokenSource;
ResetToken = Token;
Line.InPPDirective = false;
Line.Level = PreviousLineLevel;
}
FormatToken *getNextToken() override {
// The \c UnwrappedLineParser guards against this by never calling
// \c getNextToken() after it has encountered the first eof token.
assert(!eof());
PreviousToken = Token;
Token = PreviousTokenSource->getNextToken();
if (eof())
return &FakeEOF;
return Token;
}
unsigned getPosition() override { return PreviousTokenSource->getPosition(); }
FormatToken *setPosition(unsigned Position) override {
PreviousToken = nullptr;
Token = PreviousTokenSource->setPosition(Position);
return Token;
}
private:
bool eof() {
return Token && Token->HasUnescapedNewline &&
!continuesLineComment(*Token, PreviousToken,
/*MinColumnToken=*/PreviousToken);
}
FormatToken FakeEOF;
UnwrappedLine &Line;
FormatTokenSource *&TokenSource;
FormatToken *&ResetToken;
unsigned PreviousLineLevel;
FormatTokenSource *PreviousTokenSource;
FormatToken *Token;
FormatToken *PreviousToken;
};
} // end anonymous namespace
class ScopedLineState {
public:
ScopedLineState(UnwrappedLineParser &Parser,
bool SwitchToPreprocessorLines = false)
: Parser(Parser), OriginalLines(Parser.CurrentLines) {
if (SwitchToPreprocessorLines)
Parser.CurrentLines = &Parser.PreprocessorDirectives;
else if (!Parser.Line->Tokens.empty())
Parser.CurrentLines = &Parser.Line->Tokens.back().Children;
PreBlockLine = std::move(Parser.Line);
Parser.Line = std::make_unique<UnwrappedLine>();
Parser.Line->Level = PreBlockLine->Level;
Parser.Line->InPPDirective = PreBlockLine->InPPDirective;
}
~ScopedLineState() {
if (!Parser.Line->Tokens.empty()) {
Parser.addUnwrappedLine();
}
assert(Parser.Line->Tokens.empty());
Parser.Line = std::move(PreBlockLine);
if (Parser.CurrentLines == &Parser.PreprocessorDirectives)
Parser.MustBreakBeforeNextToken = true;
Parser.CurrentLines = OriginalLines;
}
private:
UnwrappedLineParser &Parser;
std::unique_ptr<UnwrappedLine> PreBlockLine;
SmallVectorImpl<UnwrappedLine> *OriginalLines;
};
class CompoundStatementIndenter {
public:
CompoundStatementIndenter(UnwrappedLineParser *Parser,
const FormatStyle &Style, unsigned &LineLevel)
: CompoundStatementIndenter(Parser, LineLevel,
Style.BraceWrapping.AfterControlStatement,
Style.BraceWrapping.IndentBraces) {}
CompoundStatementIndenter(UnwrappedLineParser *Parser, unsigned &LineLevel,
bool WrapBrace, bool IndentBrace)
: LineLevel(LineLevel), OldLineLevel(LineLevel) {
if (WrapBrace)
Parser->addUnwrappedLine();
if (IndentBrace)
++LineLevel;
}
~CompoundStatementIndenter() { LineLevel = OldLineLevel; }
private:
unsigned &LineLevel;
unsigned OldLineLevel;
};
namespace {
class IndexedTokenSource : public FormatTokenSource {
public:
IndexedTokenSource(ArrayRef<FormatToken *> Tokens)
: Tokens(Tokens), Position(-1) {}
FormatToken *getNextToken() override {
++Position;
return Tokens[Position];
}
unsigned getPosition() override {
assert(Position >= 0);
return Position;
}
FormatToken *setPosition(unsigned P) override {
Position = P;
return Tokens[Position];
}
void reset() { Position = -1; }
private:
ArrayRef<FormatToken *> Tokens;
int Position;
};
} // end anonymous namespace
UnwrappedLineParser::UnwrappedLineParser(const FormatStyle &Style,
const AdditionalKeywords &Keywords,
unsigned FirstStartColumn,
ArrayRef<FormatToken *> Tokens,
UnwrappedLineConsumer &Callback)
: Line(new UnwrappedLine), MustBreakBeforeNextToken(false),
CurrentLines(&Lines), Style(Style), Keywords(Keywords),
CommentPragmasRegex(Style.CommentPragmas), Tokens(nullptr),
Callback(Callback), AllTokens(Tokens), PPBranchLevel(-1),
IncludeGuard(Style.IndentPPDirectives == FormatStyle::PPDIS_None
? IG_Rejected
: IG_Inited),
IncludeGuardToken(nullptr), FirstStartColumn(FirstStartColumn) {}
void UnwrappedLineParser::reset() {
PPBranchLevel = -1;
IncludeGuard = Style.IndentPPDirectives == FormatStyle::PPDIS_None
? IG_Rejected
: IG_Inited;
IncludeGuardToken = nullptr;
Line.reset(new UnwrappedLine);
CommentsBeforeNextToken.clear();
FormatTok = nullptr;
MustBreakBeforeNextToken = false;
PreprocessorDirectives.clear();
CurrentLines = &Lines;
DeclarationScopeStack.clear();
PPStack.clear();
Line->FirstStartColumn = FirstStartColumn;
}
void UnwrappedLineParser::parse() {
IndexedTokenSource TokenSource(AllTokens);
Line->FirstStartColumn = FirstStartColumn;
do {
LLVM_DEBUG(llvm::dbgs() << "----\n");
reset();
Tokens = &TokenSource;
TokenSource.reset();
readToken();
parseFile();
// If we found an include guard then all preprocessor directives (other than
// the guard) are over-indented by one.
if (IncludeGuard == IG_Found)
for (auto &Line : Lines)
if (Line.InPPDirective && Line.Level > 0)
--Line.Level;
// Create line with eof token.
pushToken(FormatTok);
addUnwrappedLine();
for (SmallVectorImpl<UnwrappedLine>::iterator I = Lines.begin(),
E = Lines.end();
I != E; ++I) {
Callback.consumeUnwrappedLine(*I);
}
Callback.finishRun();
Lines.clear();
while (!PPLevelBranchIndex.empty() &&
PPLevelBranchIndex.back() + 1 >= PPLevelBranchCount.back()) {
PPLevelBranchIndex.resize(PPLevelBranchIndex.size() - 1);
PPLevelBranchCount.resize(PPLevelBranchCount.size() - 1);
}
if (!PPLevelBranchIndex.empty()) {
++PPLevelBranchIndex.back();
assert(PPLevelBranchIndex.size() == PPLevelBranchCount.size());
assert(PPLevelBranchIndex.back() <= PPLevelBranchCount.back());
}
} while (!PPLevelBranchIndex.empty());
}
void UnwrappedLineParser::parseFile() {
// The top-level context in a file always has declarations, except for pre-
// processor directives and JavaScript files.
bool MustBeDeclaration =
!Line->InPPDirective && Style.Language != FormatStyle::LK_JavaScript;
ScopedDeclarationState DeclarationState(*Line, DeclarationScopeStack,
MustBeDeclaration);
if (Style.Language == FormatStyle::LK_TextProto)
parseBracedList();
else
parseLevel(/*HasOpeningBrace=*/false);
// Make sure to format the remaining tokens.
//
// LK_TextProto is special since its top-level is parsed as the body of a
// braced list, which does not necessarily have natural line separators such
// as a semicolon. Comments after the last entry that have been determined to
// not belong to that line, as in:
// key: value
// // endfile comment
// do not have a chance to be put on a line of their own until this point.
// Here we add this newline before end-of-file comments.
if (Style.Language == FormatStyle::LK_TextProto &&
!CommentsBeforeNextToken.empty())
addUnwrappedLine();
flushComments(true);
addUnwrappedLine();
}
void UnwrappedLineParser::parseCSharpGenericTypeConstraint() {
do {
switch (FormatTok->Tok.getKind()) {
case tok::l_brace:
return;
default:
if (FormatTok->is(Keywords.kw_where)) {
addUnwrappedLine();
nextToken();
parseCSharpGenericTypeConstraint();
break;
}
nextToken();
break;
}
} while (!eof());
}
void UnwrappedLineParser::parseCSharpAttribute() {
int UnpairedSquareBrackets = 1;
do {
switch (FormatTok->Tok.getKind()) {
case tok::r_square:
nextToken();
--UnpairedSquareBrackets;
if (UnpairedSquareBrackets == 0) {
addUnwrappedLine();
return;
}
break;
case tok::l_square:
++UnpairedSquareBrackets;
nextToken();
break;
default:
nextToken();
break;
}
} while (!eof());
}
void UnwrappedLineParser::parseLevel(bool HasOpeningBrace) {
bool SwitchLabelEncountered = false;
do {
tok::TokenKind kind = FormatTok->Tok.getKind();
if (FormatTok->getType() == TT_MacroBlockBegin) {
kind = tok::l_brace;
} else if (FormatTok->getType() == TT_MacroBlockEnd) {
kind = tok::r_brace;
}
switch (kind) {
case tok::comment:
nextToken();
addUnwrappedLine();
break;
case tok::l_brace:
// FIXME: Add parameter whether this can happen - if this happens, we must
// be in a non-declaration context.
if (!FormatTok->is(TT_MacroBlockBegin) && tryToParseBracedList())
continue;
parseBlock(/*MustBeDeclaration=*/false);
addUnwrappedLine();
break;
case tok::r_brace:
if (HasOpeningBrace)
return;
nextToken();
addUnwrappedLine();
break;
case tok::kw_default: {
unsigned StoredPosition = Tokens->getPosition();
FormatToken *Next;
do {
Next = Tokens->getNextToken();
} while (Next && Next->is(tok::comment));
FormatTok = Tokens->setPosition(StoredPosition);
if (Next && Next->isNot(tok::colon)) {
// default not followed by ':' is not a case label; treat it like
// an identifier.
parseStructuralElement();
break;
}
// Else, if it is 'default:', fall through to the case handling.
LLVM_FALLTHROUGH;
}
case tok::kw_case:
if (Style.Language == FormatStyle::LK_JavaScript &&
Line->MustBeDeclaration) {
// A 'case: string' style field declaration.
parseStructuralElement();
break;
}
if (!SwitchLabelEncountered &&
(Style.IndentCaseLabels || (Line->InPPDirective && Line->Level == 1)))
++Line->Level;
SwitchLabelEncountered = true;
parseStructuralElement();
break;
case tok::l_square:
if (Style.isCSharp()) {
nextToken();
parseCSharpAttribute();
break;
}
LLVM_FALLTHROUGH;
default:
parseStructuralElement();
break;
}
} while (!eof());
}
void UnwrappedLineParser::calculateBraceTypes(bool ExpectClassBody) {
// We'll parse forward through the tokens until we hit
// a closing brace or eof - note that getNextToken() will
// parse macros, so this will magically work inside macro
// definitions, too.
unsigned StoredPosition = Tokens->getPosition();
FormatToken *Tok = FormatTok;
const FormatToken *PrevTok = Tok->Previous;
// Keep a stack of positions of lbrace tokens. We will
// update information about whether an lbrace starts a
// braced init list or a different block during the loop.
SmallVector<FormatToken *, 8> LBraceStack;
assert(Tok->Tok.is(tok::l_brace));
do {
// Get next non-comment token.
FormatToken *NextTok;
unsigned ReadTokens = 0;
do {
NextTok = Tokens->getNextToken();
++ReadTokens;
} while (NextTok->is(tok::comment));
switch (Tok->Tok.getKind()) {
case tok::l_brace:
if (Style.Language == FormatStyle::LK_JavaScript && PrevTok) {
if (PrevTok->isOneOf(tok::colon, tok::less))
// A ':' indicates this code is in a type, or a braced list
// following a label in an object literal ({a: {b: 1}}).
// A '<' could be an object used in a comparison, but that is nonsense
// code (can never return true), so more likely it is a generic type
// argument (`X<{a: string; b: number}>`).
// The code below could be confused by semicolons between the
// individual members in a type member list, which would normally
// trigger BK_Block. In both cases, this must be parsed as an inline
// braced init.
Tok->setBlockKind(BK_BracedInit);
else if (PrevTok->is(tok::r_paren))
// `) { }` can only occur in function or method declarations in JS.
Tok->setBlockKind(BK_Block);
} else {
Tok->setBlockKind(BK_Unknown);
}
LBraceStack.push_back(Tok);
break;
case tok::r_brace:
if (LBraceStack.empty())
break;
if (LBraceStack.back()->is(BK_Unknown)) {
bool ProbablyBracedList = false;
if (Style.Language == FormatStyle::LK_Proto) {
ProbablyBracedList = NextTok->isOneOf(tok::comma, tok::r_square);
} else {
// Using OriginalColumn to distinguish between ObjC methods and
// binary operators is a bit hacky.
bool NextIsObjCMethod = NextTok->isOneOf(tok::plus, tok::minus) &&
NextTok->OriginalColumn == 0;
// If there is a comma, semicolon or right paren after the closing
// brace, we assume this is a braced initializer list. Note that
// regardless how we mark inner braces here, we will overwrite the
// BlockKind later if we parse a braced list (where all blocks
// inside are by default braced lists), or when we explicitly detect
// blocks (for example while parsing lambdas).
// FIXME: Some of these do not apply to JS, e.g. "} {" can never be a
// braced list in JS.
ProbablyBracedList =
(Style.Language == FormatStyle::LK_JavaScript &&
NextTok->isOneOf(Keywords.kw_of, Keywords.kw_in,
Keywords.kw_as)) ||
(Style.isCpp() && NextTok->is(tok::l_paren)) ||
NextTok->isOneOf(tok::comma, tok::period, tok::colon,
tok::r_paren, tok::r_square, tok::l_brace,
tok::ellipsis) ||
(NextTok->is(tok::identifier) &&
!PrevTok->isOneOf(tok::semi, tok::r_brace, tok::l_brace)) ||
(NextTok->is(tok::semi) &&
(!ExpectClassBody || LBraceStack.size() != 1)) ||
(NextTok->isBinaryOperator() && !NextIsObjCMethod);
if (!Style.isCSharp() && NextTok->is(tok::l_square)) {
// We can have an array subscript after a braced init
// list, but C++11 attributes are expected after blocks.
NextTok = Tokens->getNextToken();
++ReadTokens;
ProbablyBracedList = NextTok->isNot(tok::l_square);
}
}
if (ProbablyBracedList) {
Tok->setBlockKind(BK_BracedInit);
LBraceStack.back()->setBlockKind(BK_BracedInit);
} else {
Tok->setBlockKind(BK_Block);
LBraceStack.back()->setBlockKind(BK_Block);
}
}
LBraceStack.pop_back();
break;
case tok::identifier:
if (!Tok->is(TT_StatementMacro))
break;
LLVM_FALLTHROUGH;
case tok::at:
case tok::semi:
case tok::kw_if:
case tok::kw_while:
case tok::kw_for:
case tok::kw_switch:
case tok::kw_try:
case tok::kw___try:
if (!LBraceStack.empty() && LBraceStack.back()->is(BK_Unknown))
LBraceStack.back()->setBlockKind(BK_Block);
break;
default:
break;
}
PrevTok = Tok;
Tok = NextTok;
} while (Tok->Tok.isNot(tok::eof) && !LBraceStack.empty());
// Assume other blocks for all unclosed opening braces.
for (unsigned i = 0, e = LBraceStack.size(); i != e; ++i) {
if (LBraceStack[i]->is(BK_Unknown))
LBraceStack[i]->setBlockKind(BK_Block);
}
FormatTok = Tokens->setPosition(StoredPosition);
}
template <class T>
static inline void hash_combine(std::size_t &seed, const T &v) {
std::hash<T> hasher;
seed ^= hasher(v) + 0x9e3779b9 + (seed << 6) + (seed >> 2);
}
size_t UnwrappedLineParser::computePPHash() const {
size_t h = 0;
for (const auto &i : PPStack) {
hash_combine(h, size_t(i.Kind));
hash_combine(h, i.Line);
}
return h;
}
void UnwrappedLineParser::parseBlock(bool MustBeDeclaration, unsigned AddLevels,
bool MunchSemi,
bool UnindentWhitesmithsBraces) {
assert(FormatTok->isOneOf(tok::l_brace, TT_MacroBlockBegin) &&
"'{' or macro block token expected");
const bool MacroBlock = FormatTok->is(TT_MacroBlockBegin);
FormatTok->setBlockKind(BK_Block);
// For Whitesmiths mode, jump to the next level prior to skipping over the
// braces.
if (AddLevels > 0 && Style.BreakBeforeBraces == FormatStyle::BS_Whitesmiths)
++Line->Level;
size_t PPStartHash = computePPHash();
unsigned InitialLevel = Line->Level;
nextToken(/*LevelDifference=*/AddLevels);
if (MacroBlock && FormatTok->is(tok::l_paren))
parseParens();
size_t NbPreprocessorDirectives =
CurrentLines == &Lines ? PreprocessorDirectives.size() : 0;
addUnwrappedLine();
size_t OpeningLineIndex =
CurrentLines->empty()
? (UnwrappedLine::kInvalidIndex)
: (CurrentLines->size() - 1 - NbPreprocessorDirectives);
// Whitesmiths is weird here. The brace needs to be indented for the namespace
// block, but the block itself may not be indented depending on the style
// settings. This allows the format to back up one level in those cases.
if (UnindentWhitesmithsBraces)
--Line->Level;
ScopedDeclarationState DeclarationState(*Line, DeclarationScopeStack,
MustBeDeclaration);
if (AddLevels > 0u && Style.BreakBeforeBraces != FormatStyle::BS_Whitesmiths)
Line->Level += AddLevels;
parseLevel(/*HasOpeningBrace=*/true);
if (eof())
return;
if (MacroBlock ? !FormatTok->is(TT_MacroBlockEnd)
: !FormatTok->is(tok::r_brace)) {
Line->Level = InitialLevel;
FormatTok->setBlockKind(BK_Block);
return;
}
size_t PPEndHash = computePPHash();
// Munch the closing brace.
nextToken(/*LevelDifference=*/-AddLevels);
if (MacroBlock && FormatTok->is(tok::l_paren))
parseParens();
if (FormatTok->is(tok::arrow)) {
// Following the } we can find a trailing return type arrow
// as part of an implicit conversion constraint.
nextToken();
parseStructuralElement();
}
if (MunchSemi && FormatTok->Tok.is(tok::semi))
nextToken();
Line->Level = InitialLevel;
if (PPStartHash == PPEndHash) {
Line->MatchingOpeningBlockLineIndex = OpeningLineIndex;
if (OpeningLineIndex != UnwrappedLine::kInvalidIndex) {
// Update the opening line to add the forward reference as well
(*CurrentLines)[OpeningLineIndex].MatchingClosingBlockLineIndex =
CurrentLines->size() - 1;
}
}
}
static bool isGoogScope(const UnwrappedLine &Line) {
// FIXME: Closure-library specific stuff should not be hard-coded but be
// configurable.
if (Line.Tokens.size() < 4)
return false;
auto I = Line.Tokens.begin();
if (I->Tok->TokenText != "goog")
return false;
++I;
if (I->Tok->isNot(tok::period))
return false;
++I;
if (I->Tok->TokenText != "scope")
return false;
++I;
return I->Tok->is(tok::l_paren);
}
static bool isIIFE(const UnwrappedLine &Line,
const AdditionalKeywords &Keywords) {
// Look for the start of an immediately invoked anonymous function.
// https://en.wikipedia.org/wiki/Immediately-invoked_function_expression
// This is commonly done in JavaScript to create a new, anonymous scope.
// Example: (function() { ... })()
if (Line.Tokens.size() < 3)
return false;
auto I = Line.Tokens.begin();
if (I->Tok->isNot(tok::l_paren))
return false;
++I;
if (I->Tok->isNot(Keywords.kw_function))
return false;
++I;
return I->Tok->is(tok::l_paren);
}
static bool ShouldBreakBeforeBrace(const FormatStyle &Style,
const FormatToken &InitialToken) {
if (InitialToken.isOneOf(tok::kw_namespace, TT_NamespaceMacro))
return Style.BraceWrapping.AfterNamespace;
if (InitialToken.is(tok::kw_class))
return Style.BraceWrapping.AfterClass;
if (InitialToken.is(tok::kw_union))
return Style.BraceWrapping.AfterUnion;
if (InitialToken.is(tok::kw_struct))
return Style.BraceWrapping.AfterStruct;
return false;
}
void UnwrappedLineParser::parseChildBlock() {
FormatTok->setBlockKind(BK_Block);
nextToken();
{
bool SkipIndent = (Style.Language == FormatStyle::LK_JavaScript &&
(isGoogScope(*Line) || isIIFE(*Line, Keywords)));
ScopedLineState LineState(*this);
ScopedDeclarationState DeclarationState(*Line, DeclarationScopeStack,
/*MustBeDeclaration=*/false);
Line->Level += SkipIndent ? 0 : 1;
parseLevel(/*HasOpeningBrace=*/true);
flushComments(isOnNewLine(*FormatTok));
Line->Level -= SkipIndent ? 0 : 1;
}
nextToken();
}
void UnwrappedLineParser::parsePPDirective() {
assert(FormatTok->Tok.is(tok::hash) && "'#' expected");
ScopedMacroState MacroState(*Line, Tokens, FormatTok);
nextToken();
if (!FormatTok->Tok.getIdentifierInfo()) {
parsePPUnknown();
return;
}
switch (FormatTok->Tok.getIdentifierInfo()->getPPKeywordID()) {
case tok::pp_define:
parsePPDefine();
return;
case tok::pp_if:
parsePPIf(/*IfDef=*/false);
break;
case tok::pp_ifdef:
case tok::pp_ifndef:
parsePPIf(/*IfDef=*/true);
break;
case tok::pp_else:
parsePPElse();
break;
case tok::pp_elif:
parsePPElIf();
break;
case tok::pp_endif:
parsePPEndIf();
break;
default:
parsePPUnknown();
break;
}
}
void UnwrappedLineParser::conditionalCompilationCondition(bool Unreachable) {
size_t Line = CurrentLines->size();
if (CurrentLines == &PreprocessorDirectives)
Line += Lines.size();
if (Unreachable ||
(!PPStack.empty() && PPStack.back().Kind == PP_Unreachable))
PPStack.push_back({PP_Unreachable, Line});
else
PPStack.push_back({PP_Conditional, Line});
}
void UnwrappedLineParser::conditionalCompilationStart(bool Unreachable) {
++PPBranchLevel;
assert(PPBranchLevel >= 0 && PPBranchLevel <= (int)PPLevelBranchIndex.size());
if (PPBranchLevel == (int)PPLevelBranchIndex.size()) {
PPLevelBranchIndex.push_back(0);
PPLevelBranchCount.push_back(0);
}
PPChainBranchIndex.push(0);
bool Skip = PPLevelBranchIndex[PPBranchLevel] > 0;
conditionalCompilationCondition(Unreachable || Skip);
}
void UnwrappedLineParser::conditionalCompilationAlternative() {
if (!PPStack.empty())
PPStack.pop_back();
assert(PPBranchLevel < (int)PPLevelBranchIndex.size());
if (!PPChainBranchIndex.empty())
++PPChainBranchIndex.top();
conditionalCompilationCondition(
PPBranchLevel >= 0 && !PPChainBranchIndex.empty() &&
PPLevelBranchIndex[PPBranchLevel] != PPChainBranchIndex.top());
}
void UnwrappedLineParser::conditionalCompilationEnd() {
assert(PPBranchLevel < (int)PPLevelBranchIndex.size());
if (PPBranchLevel >= 0 && !PPChainBranchIndex.empty()) {
if (PPChainBranchIndex.top() + 1 > PPLevelBranchCount[PPBranchLevel]) {
PPLevelBranchCount[PPBranchLevel] = PPChainBranchIndex.top() + 1;
}
}
// Guard against #endif's without #if.
if (PPBranchLevel > -1)
--PPBranchLevel;
if (!PPChainBranchIndex.empty())
PPChainBranchIndex.pop();
if (!PPStack.empty())
PPStack.pop_back();
}
void UnwrappedLineParser::parsePPIf(bool IfDef) {
bool IfNDef = FormatTok->is(tok::pp_ifndef);
nextToken();
bool Unreachable = false;
if (!IfDef && (FormatTok->is(tok::kw_false) || FormatTok->TokenText == "0"))
Unreachable = true;
if (IfDef && !IfNDef && FormatTok->TokenText == "SWIG")
Unreachable = true;
conditionalCompilationStart(Unreachable);
FormatToken *IfCondition = FormatTok;
// If there's a #ifndef on the first line, and the only lines before it are
// comments, it could be an include guard.
bool MaybeIncludeGuard = IfNDef;
if (IncludeGuard == IG_Inited && MaybeIncludeGuard)
for (auto &Line : Lines) {
if (!Line.Tokens.front().Tok->is(tok::comment)) {
MaybeIncludeGuard = false;
IncludeGuard = IG_Rejected;
break;
}
}
--PPBranchLevel;
parsePPUnknown();
++PPBranchLevel;
if (IncludeGuard == IG_Inited && MaybeIncludeGuard) {
IncludeGuard = IG_IfNdefed;
IncludeGuardToken = IfCondition;
}
}
void UnwrappedLineParser::parsePPElse() {
// If a potential include guard has an #else, it's not an include guard.
if (IncludeGuard == IG_Defined && PPBranchLevel == 0)
IncludeGuard = IG_Rejected;
conditionalCompilationAlternative();
if (PPBranchLevel > -1)
--PPBranchLevel;
parsePPUnknown();
++PPBranchLevel;
}
void UnwrappedLineParser::parsePPElIf() { parsePPElse(); }
void UnwrappedLineParser::parsePPEndIf() {
conditionalCompilationEnd();
parsePPUnknown();
// If the #endif of a potential include guard is the last thing in the file,
// then we found an include guard.
unsigned TokenPosition = Tokens->getPosition();
FormatToken *PeekNext = AllTokens[TokenPosition];
if (IncludeGuard == IG_Defined && PPBranchLevel == -1 &&
PeekNext->is(tok::eof) &&
Style.IndentPPDirectives != FormatStyle::PPDIS_None)
IncludeGuard = IG_Found;
}
void UnwrappedLineParser::parsePPDefine() {
nextToken();
if (!FormatTok->Tok.getIdentifierInfo()) {
IncludeGuard = IG_Rejected;
IncludeGuardToken = nullptr;
parsePPUnknown();
return;
}
if (IncludeGuard == IG_IfNdefed &&
IncludeGuardToken->TokenText == FormatTok->TokenText) {
IncludeGuard = IG_Defined;
IncludeGuardToken = nullptr;
for (auto &Line : Lines) {
if (!Line.Tokens.front().Tok->isOneOf(tok::comment, tok::hash)) {
IncludeGuard = IG_Rejected;
break;
}
}
}
nextToken();
if (FormatTok->Tok.getKind() == tok::l_paren &&
FormatTok->WhitespaceRange.getBegin() ==
FormatTok->WhitespaceRange.getEnd()) {
parseParens();
}
if (Style.IndentPPDirectives != FormatStyle::PPDIS_None)
Line->Level += PPBranchLevel + 1;
addUnwrappedLine();
++Line->Level;
// Errors during a preprocessor directive can only affect the layout of the
// preprocessor directive, and thus we ignore them. An alternative approach
// would be to use the same approach we use on the file level (no
// re-indentation if there was a structural error) within the macro
// definition.
parseFile();
}
void UnwrappedLineParser::parsePPUnknown() {
do {
nextToken();
} while (!eof());
if (Style.IndentPPDirectives != FormatStyle::PPDIS_None)
Line->Level += PPBranchLevel + 1;
addUnwrappedLine();
}
// Here we exclude certain tokens that are not usually the first token in an
// unwrapped line. This is used in attempt to distinguish macro calls without
// trailing semicolons from other constructs split to several lines.
static bool tokenCanStartNewLine(const FormatToken &Tok) {
// Semicolon can be a null-statement, l_square can be a start of a macro or
// a C++11 attribute, but this doesn't seem to be common.
return Tok.isNot(tok::semi) && Tok.isNot(tok::l_brace) &&
Tok.isNot(TT_AttributeSquare) &&
// Tokens that can only be used as binary operators and a part of
// overloaded operator names.
Tok.isNot(tok::period) && Tok.isNot(tok::periodstar) &&
Tok.isNot(tok::arrow) && Tok.isNot(tok::arrowstar) &&
Tok.isNot(tok::less) && Tok.isNot(tok::greater) &&
Tok.isNot(tok::slash) && Tok.isNot(tok::percent) &&
Tok.isNot(tok::lessless) && Tok.isNot(tok::greatergreater) &&
Tok.isNot(tok::equal) && Tok.isNot(tok::plusequal) &&
Tok.isNot(tok::minusequal) && Tok.isNot(tok::starequal) &&
Tok.isNot(tok::slashequal) && Tok.isNot(tok::percentequal) &&
Tok.isNot(tok::ampequal) && Tok.isNot(tok::pipeequal) &&
Tok.isNot(tok::caretequal) && Tok.isNot(tok::greatergreaterequal) &&
Tok.isNot(tok::lesslessequal) &&
// Colon is used in labels, base class lists, initializer lists,
// range-based for loops, ternary operator, but should never be the
// first token in an unwrapped line.
Tok.isNot(tok::colon) &&
// 'noexcept' is a trailing annotation.
Tok.isNot(tok::kw_noexcept);
}
static bool mustBeJSIdent(const AdditionalKeywords &Keywords,
const FormatToken *FormatTok) {
// FIXME: This returns true for C/C++ keywords like 'struct'.
return FormatTok->is(tok::identifier) &&
(FormatTok->Tok.getIdentifierInfo() == nullptr ||
!FormatTok->isOneOf(
Keywords.kw_in, Keywords.kw_of, Keywords.kw_as, Keywords.kw_async,
Keywords.kw_await, Keywords.kw_yield, Keywords.kw_finally,
Keywords.kw_function, Keywords.kw_import, Keywords.kw_is,
Keywords.kw_let, Keywords.kw_var, tok::kw_const,
Keywords.kw_abstract, Keywords.kw_extends, Keywords.kw_implements,
Keywords.kw_instanceof, Keywords.kw_interface, Keywords.kw_throws,
Keywords.kw_from));
}
static bool mustBeJSIdentOrValue(const AdditionalKeywords &Keywords,
const FormatToken *FormatTok) {
return FormatTok->Tok.isLiteral() ||
FormatTok->isOneOf(tok::kw_true, tok::kw_false) ||
mustBeJSIdent(Keywords, FormatTok);
}
// isJSDeclOrStmt returns true if |FormatTok| starts a declaration or statement
// when encountered after a value (see mustBeJSIdentOrValue).
static bool isJSDeclOrStmt(const AdditionalKeywords &Keywords,
const FormatToken *FormatTok) {
return FormatTok->isOneOf(
tok::kw_return, Keywords.kw_yield,
// conditionals
tok::kw_if, tok::kw_else,
// loops
tok::kw_for, tok::kw_while, tok::kw_do, tok::kw_continue, tok::kw_break,
// switch/case
tok::kw_switch, tok::kw_case,
// exceptions
tok::kw_throw, tok::kw_try, tok::kw_catch, Keywords.kw_finally,
// declaration
tok::kw_const, tok::kw_class, Keywords.kw_var, Keywords.kw_let,
Keywords.kw_async, Keywords.kw_function,
// import/export
Keywords.kw_import, tok::kw_export);
}
// readTokenWithJavaScriptASI reads the next token and terminates the current
// line if JavaScript Automatic Semicolon Insertion must
// happen between the current token and the next token.
//
// This method is conservative - it cannot cover all edge cases of JavaScript,
// but only aims to correctly handle certain well known cases. It *must not*
// return true in speculative cases.
void UnwrappedLineParser::readTokenWithJavaScriptASI() {
FormatToken *Previous = FormatTok;
readToken();
FormatToken *Next = FormatTok;
bool IsOnSameLine =
CommentsBeforeNextToken.empty()
? Next->NewlinesBefore == 0
: CommentsBeforeNextToken.front()->NewlinesBefore == 0;
if (IsOnSameLine)
return;
bool PreviousMustBeValue = mustBeJSIdentOrValue(Keywords, Previous);
bool PreviousStartsTemplateExpr =
Previous->is(TT_TemplateString) && Previous->TokenText.endswith("${");
if (PreviousMustBeValue || Previous->is(tok::r_paren)) {
// If the line contains an '@' sign, the previous token might be an
// annotation, which can precede another identifier/value.
bool HasAt = std::find_if(Line->Tokens.begin(), Line->Tokens.end(),
[](UnwrappedLineNode &LineNode) {
return LineNode.Tok->is(tok::at);
}) != Line->Tokens.end();
if (HasAt)
return;
}
if (Next->is(tok::exclaim) && PreviousMustBeValue)
return addUnwrappedLine();
bool NextMustBeValue = mustBeJSIdentOrValue(Keywords, Next);
bool NextEndsTemplateExpr =
Next->is(TT_TemplateString) && Next->TokenText.startswith("}");
if (NextMustBeValue && !NextEndsTemplateExpr && !PreviousStartsTemplateExpr &&
(PreviousMustBeValue ||
Previous->isOneOf(tok::r_square, tok::r_paren, tok::plusplus,
tok::minusminus)))
return addUnwrappedLine();
if ((PreviousMustBeValue || Previous->is(tok::r_paren)) &&
isJSDeclOrStmt(Keywords, Next))
return addUnwrappedLine();
}
void UnwrappedLineParser::parseStructuralElement() {
assert(!FormatTok->is(tok::l_brace));
if (Style.Language == FormatStyle::LK_TableGen &&
FormatTok->is(tok::pp_include)) {
nextToken();
if (FormatTok->is(tok::string_literal))
nextToken();
addUnwrappedLine();
return;
}
switch (FormatTok->Tok.getKind()) {
case tok::kw_asm:
nextToken();
if (FormatTok->is(tok::l_brace)) {
FormatTok->setType(TT_InlineASMBrace);
nextToken();
while (FormatTok && FormatTok->isNot(tok::eof)) {
if (FormatTok->is(tok::r_brace)) {
FormatTok->setType(TT_InlineASMBrace);
nextToken();
addUnwrappedLine();
break;
}
FormatTok->Finalized = true;
nextToken();
}
}
break;
case tok::kw_namespace:
parseNamespace();
return;
case tok::kw_public:
case tok::kw_protected:
case tok::kw_private:
if (Style.Language == FormatStyle::LK_Java ||
Style.Language == FormatStyle::LK_JavaScript || Style.isCSharp())
nextToken();
else
parseAccessSpecifier();
return;
case tok::kw_if:
if (Style.Language == FormatStyle::LK_JavaScript && Line->MustBeDeclaration)
// field/method declaration.
break;
parseIfThenElse();
return;
case tok::kw_for:
case tok::kw_while:
if (Style.Language == FormatStyle::LK_JavaScript && Line->MustBeDeclaration)
// field/method declaration.
break;
parseForOrWhileLoop();
return;
case tok::kw_do:
if (Style.Language == FormatStyle::LK_JavaScript && Line->MustBeDeclaration)
// field/method declaration.
break;
parseDoWhile();
return;
case tok::kw_switch:
if (Style.Language == FormatStyle::LK_JavaScript && Line->MustBeDeclaration)
// 'switch: string' field declaration.
break;
parseSwitch();
return;
case tok::kw_default:
if (Style.Language == FormatStyle::LK_JavaScript && Line->MustBeDeclaration)
// 'default: string' field declaration.
break;
nextToken();
if (FormatTok->is(tok::colon)) {
parseLabel();
return;
}
// e.g. "default void f() {}" in a Java interface.
break;
case tok::kw_case:
if (Style.Language == FormatStyle::LK_JavaScript && Line->MustBeDeclaration)
// 'case: string' field declaration.
break;
parseCaseLabel();
return;
case tok::kw_try:
case tok::kw___try:
if (Style.Language == FormatStyle::LK_JavaScript && Line->MustBeDeclaration)
// field/method declaration.
break;
parseTryCatch();
return;
case tok::kw_extern:
nextToken();
if (FormatTok->Tok.is(tok::string_literal)) {
nextToken();
if (FormatTok->Tok.is(tok::l_brace)) {
if (!Style.IndentExternBlock) {
if (Style.BraceWrapping.AfterExternBlock) {
addUnwrappedLine();
}
unsigned AddLevels = Style.BraceWrapping.AfterExternBlock ? 1u : 0u;
parseBlock(/*MustBeDeclaration=*/true, AddLevels);
} else {
unsigned AddLevels =
Style.IndentExternBlock == FormatStyle::IEBS_Indent ? 1u : 0u;
parseBlock(/*MustBeDeclaration=*/true, AddLevels);
}
addUnwrappedLine();
return;
}
}
break;
case tok::kw_export:
if (Style.Language == FormatStyle::LK_JavaScript) {
parseJavaScriptEs6ImportExport();
return;
}
if (!Style.isCpp())
break;
// Handle C++ "(inline|export) namespace".
LLVM_FALLTHROUGH;
case tok::kw_inline:
nextToken();
if (FormatTok->Tok.is(tok::kw_namespace)) {
parseNamespace();
return;
}
break;
case tok::identifier:
if (FormatTok->is(TT_ForEachMacro)) {
parseForOrWhileLoop();
return;
}
if (FormatTok->is(TT_MacroBlockBegin)) {
parseBlock(/*MustBeDeclaration=*/false, /*AddLevels=*/1u,
/*MunchSemi=*/false);
return;
}
if (FormatTok->is(Keywords.kw_import)) {
if (Style.Language == FormatStyle::LK_JavaScript) {
parseJavaScriptEs6ImportExport();
return;
}
if (Style.Language == FormatStyle::LK_Proto) {
nextToken();
if (FormatTok->is(tok::kw_public))
nextToken();
if (!FormatTok->is(tok::string_literal))
return;
nextToken();
if (FormatTok->is(tok::semi))
nextToken();
addUnwrappedLine();
return;
}
}
if (Style.isCpp() &&
FormatTok->isOneOf(Keywords.kw_signals, Keywords.kw_qsignals,
Keywords.kw_slots, Keywords.kw_qslots)) {
nextToken();
if (FormatTok->is(tok::colon)) {
nextToken();
addUnwrappedLine();
return;
}
}
if (Style.isCpp() && FormatTok->is(TT_StatementMacro)) {
parseStatementMacro();
return;
}
if (Style.isCpp() && FormatTok->is(TT_NamespaceMacro)) {
parseNamespace();
return;
}
// In all other cases, parse the declaration.
break;
default:
break;
}
do {
const FormatToken *Previous = FormatTok->Previous;
switch (FormatTok->Tok.getKind()) {
case tok::at:
nextToken();
if (FormatTok->Tok.is(tok::l_brace)) {
nextToken();
parseBracedList();
break;
} else if (Style.Language == FormatStyle::LK_Java &&
FormatTok->is(Keywords.kw_interface)) {
nextToken();
break;
}
switch (FormatTok->Tok.getObjCKeywordID()) {
case tok::objc_public:
case tok::objc_protected:
case tok::objc_package:
case tok::objc_private:
return parseAccessSpecifier();
case tok::objc_interface:
case tok::objc_implementation:
return parseObjCInterfaceOrImplementation();
case tok::objc_protocol:
if (parseObjCProtocol())
return;
break;
case tok::objc_end:
return; // Handled by the caller.
case tok::objc_optional:
case tok::objc_required:
nextToken();
addUnwrappedLine();
return;
case tok::objc_autoreleasepool:
nextToken();
if (FormatTok->Tok.is(tok::l_brace)) {
if (Style.BraceWrapping.AfterControlStatement ==
FormatStyle::BWACS_Always)
addUnwrappedLine();
parseBlock(/*MustBeDeclaration=*/false);
}
addUnwrappedLine();
return;
case tok::objc_synchronized:
nextToken();
if (FormatTok->Tok.is(tok::l_paren))
// Skip synchronization object
parseParens();
if (FormatTok->Tok.is(tok::l_brace)) {
if (Style.BraceWrapping.AfterControlStatement ==
FormatStyle::BWACS_Always)
addUnwrappedLine();
parseBlock(/*MustBeDeclaration=*/false);
}
addUnwrappedLine();
return;
case tok::objc_try:
// This branch isn't strictly necessary (the kw_try case below would
// do this too after the tok::at is parsed above). But be explicit.
parseTryCatch();
return;
default:
break;
}
break;
case tok::kw_concept:
parseConcept();
break;
case tok::kw_requires:
parseRequires();
break;
case tok::kw_enum:
// Ignore if this is part of "template <enum ...".
if (Previous && Previous->is(tok::less)) {
nextToken();
break;
}
// parseEnum falls through and does not yet add an unwrapped line as an
// enum definition can start a structural element.
if (!parseEnum())
break;
// This only applies for C++.
if (!Style.isCpp()) {
addUnwrappedLine();
return;
}
break;
case tok::kw_typedef:
nextToken();
if (FormatTok->isOneOf(Keywords.kw_NS_ENUM, Keywords.kw_NS_OPTIONS,
Keywords.kw_CF_ENUM, Keywords.kw_CF_OPTIONS,
Keywords.kw_CF_CLOSED_ENUM,
Keywords.kw_NS_CLOSED_ENUM))
parseEnum();
break;
case tok::kw_struct:
case tok::kw_union:
case tok::kw_class:
// parseRecord falls through and does not yet add an unwrapped line as a
// record declaration or definition can start a structural element.
parseRecord();
// This does not apply for Java, JavaScript and C#.
if (Style.Language == FormatStyle::LK_Java ||
Style.Language == FormatStyle::LK_JavaScript || Style.isCSharp()) {
if (FormatTok->is(tok::semi))
nextToken();
addUnwrappedLine();
return;
}
break;
case tok::period:
nextToken();
// In Java, classes have an implicit static member "class".
if (Style.Language == FormatStyle::LK_Java && FormatTok &&
FormatTok->is(tok::kw_class))
nextToken();
if (Style.Language == FormatStyle::LK_JavaScript && FormatTok &&
FormatTok->Tok.getIdentifierInfo())
// JavaScript only has pseudo keywords, all keywords are allowed to
// appear in "IdentifierName" positions. See http://es5.github.io/#x7.6
nextToken();
break;
case tok::semi:
nextToken();
addUnwrappedLine();
return;
case tok::r_brace:
addUnwrappedLine();
return;
case tok::l_paren:
parseParens();
break;
case tok::kw_operator:
nextToken();
if (FormatTok->isBinaryOperator())
nextToken();
break;
case tok::caret:
nextToken();
if (FormatTok->Tok.isAnyIdentifier() ||
FormatTok->isSimpleTypeSpecifier())
nextToken();
if (FormatTok->is(tok::l_paren))
parseParens();
if (FormatTok->is(tok::l_brace))
parseChildBlock();
break;
case tok::l_brace:
if (!tryToParsePropertyAccessor() && !tryToParseBracedList()) {
// A block outside of parentheses must be the last part of a
// structural element.
// FIXME: Figure out cases where this is not true, and add projections
// for them (the one we know is missing are lambdas).
if (Style.BraceWrapping.AfterFunction)
addUnwrappedLine();
FormatTok->setType(TT_FunctionLBrace);
parseBlock(/*MustBeDeclaration=*/false);
addUnwrappedLine();
return;
}
// Otherwise this was a braced init list, and the structural
// element continues.
break;
case tok::kw_try:
if (Style.Language == FormatStyle::LK_JavaScript &&
Line->MustBeDeclaration) {
// field/method declaration.
nextToken();
break;
}
// We arrive here when parsing function-try blocks.
if (Style.BraceWrapping.AfterFunction)
addUnwrappedLine();
parseTryCatch();
return;
case tok::identifier: {
if (Style.isCSharp() && FormatTok->is(Keywords.kw_where) &&
Line->MustBeDeclaration) {
addUnwrappedLine();
parseCSharpGenericTypeConstraint();
break;
}
if (FormatTok->is(TT_MacroBlockEnd)) {
addUnwrappedLine();
return;
}
// Function declarations (as opposed to function expressions) are parsed
// on their own unwrapped line by continuing this loop. Function
// expressions (functions that are not on their own line) must not create
// a new unwrapped line, so they are special cased below.
size_t TokenCount = Line->Tokens.size();
if (Style.Language == FormatStyle::LK_JavaScript &&
FormatTok->is(Keywords.kw_function) &&
(TokenCount > 1 || (TokenCount == 1 && !Line->Tokens.front().Tok->is(
Keywords.kw_async)))) {
tryToParseJSFunction();
break;
}
if ((Style.Language == FormatStyle::LK_JavaScript ||
Style.Language == FormatStyle::LK_Java) &&
FormatTok->is(Keywords.kw_interface)) {
if (Style.Language == FormatStyle::LK_JavaScript) {
// In JavaScript/TypeScript, "interface" can be used as a standalone
// identifier, e.g. in `var interface = 1;`. If "interface" is
// followed by another identifier, it is very like to be an actual
// interface declaration.
unsigned StoredPosition = Tokens->getPosition();
FormatToken *Next = Tokens->getNextToken();
FormatTok = Tokens->setPosition(StoredPosition);
if (Next && !mustBeJSIdent(Keywords, Next)) {
nextToken();
break;
}
}
parseRecord();
addUnwrappedLine();
return;
}
if (Style.isCpp() && FormatTok->is(TT_StatementMacro)) {
parseStatementMacro();
return;
}
// See if the following token should start a new unwrapped line.
StringRef Text = FormatTok->TokenText;
nextToken();
// JS doesn't have macros, and within classes colons indicate fields, not
// labels.
if (Style.Language == FormatStyle::LK_JavaScript)
break;
TokenCount = Line->Tokens.size();
if (TokenCount == 1 ||
(TokenCount == 2 && Line->Tokens.front().Tok->is(tok::comment))) {
if (FormatTok->Tok.is(tok::colon) && !Line->MustBeDeclaration) {
Line->Tokens.begin()->Tok->MustBreakBefore = true;
parseLabel(!Style.IndentGotoLabels);
return;
}
// Recognize function-like macro usages without trailing semicolon as
// well as free-standing macros like Q_OBJECT.
bool FunctionLike = FormatTok->is(tok::l_paren);
if (FunctionLike)
parseParens();
bool FollowedByNewline =
CommentsBeforeNextToken.empty()
? FormatTok->NewlinesBefore > 0
: CommentsBeforeNextToken.front()->NewlinesBefore > 0;
if (FollowedByNewline && (Text.size() >= 5 || FunctionLike) &&
tokenCanStartNewLine(*FormatTok) && Text == Text.upper()) {
addUnwrappedLine();
return;
}
}
break;
}
case tok::equal:
// Fat arrows (=>) have tok::TokenKind tok::equal but TokenType
// TT_JsFatArrow. The always start an expression or a child block if
// followed by a curly.
if (FormatTok->is(TT_JsFatArrow)) {
nextToken();
if (FormatTok->is(tok::l_brace)) {
// C# may break after => if the next character is a newline.
if (Style.isCSharp() && Style.BraceWrapping.AfterFunction == true) {
// calling `addUnwrappedLine()` here causes odd parsing errors.
FormatTok->MustBreakBefore = true;
}
parseChildBlock();
}
break;
}
nextToken();
if (FormatTok->Tok.is(tok::l_brace)) {
// Block kind should probably be set to BK_BracedInit for any language.
// C# needs this change to ensure that array initialisers and object
// initialisers are indented the same way.
if (Style.isCSharp())
FormatTok->setBlockKind(BK_BracedInit);
nextToken();
parseBracedList();
} else if (Style.Language == FormatStyle::LK_Proto &&
FormatTok->Tok.is(tok::less)) {
nextToken();
parseBracedList(/*ContinueOnSemicolons=*/false, /*IsEnum=*/false,
/*ClosingBraceKind=*/tok::greater);
}
break;
case tok::l_square:
parseSquare();
break;
case tok::kw_new:
parseNew();
break;
default:
nextToken();
break;
}
} while (!eof());
}
bool UnwrappedLineParser::tryToParsePropertyAccessor() {
assert(FormatTok->is(tok::l_brace));
if (!Style.isCSharp())
return false;
// See if it's a property accessor.
if (FormatTok->Previous->isNot(tok::identifier))
return false;
// See if we are inside a property accessor.
//
// Record the current tokenPosition so that we can advance and
// reset the current token. `Next` is not set yet so we need
// another way to advance along the token stream.
unsigned int StoredPosition = Tokens->getPosition();
FormatToken *Tok = Tokens->getNextToken();
// A trivial property accessor is of the form:
// { [ACCESS_SPECIFIER] [get]; [ACCESS_SPECIFIER] [set] }
// Track these as they do not require line breaks to be introduced.
bool HasGetOrSet = false;
bool IsTrivialPropertyAccessor = true;
while (!eof()) {
if (Tok->isOneOf(tok::semi, tok::kw_public, tok::kw_private,
tok::kw_protected, Keywords.kw_internal, Keywords.kw_get,
Keywords.kw_set)) {
if (Tok->isOneOf(Keywords.kw_get, Keywords.kw_set))
HasGetOrSet = true;
Tok = Tokens->getNextToken();
continue;
}
if (Tok->isNot(tok::r_brace))
IsTrivialPropertyAccessor = false;
break;
}
if (!HasGetOrSet) {
Tokens->setPosition(StoredPosition);
return false;
}
// Try to parse the property accessor:
// https://docs.microsoft.com/en-us/dotnet/csharp/programming-guide/classes-and-structs/properties
Tokens->setPosition(StoredPosition);
if (!IsTrivialPropertyAccessor && Style.BraceWrapping.AfterFunction == true)
addUnwrappedLine();
nextToken();
do {
switch (FormatTok->Tok.getKind()) {
case tok::r_brace:
nextToken();
if (FormatTok->is(tok::equal)) {
while (!eof() && FormatTok->isNot(tok::semi))
nextToken();
nextToken();
}
addUnwrappedLine();
return true;
case tok::l_brace:
++Line->Level;
parseBlock(/*MustBeDeclaration=*/true);
addUnwrappedLine();
--Line->Level;
break;
case tok::equal:
if (FormatTok->is(TT_JsFatArrow)) {
++Line->Level;
do {
nextToken();
} while (!eof() && FormatTok->isNot(tok::semi));
nextToken();
addUnwrappedLine();
--Line->Level;
break;
}
nextToken();
break;
default:
if (FormatTok->isOneOf(Keywords.kw_get, Keywords.kw_set) &&
!IsTrivialPropertyAccessor) {
// Non-trivial get/set needs to be on its own line.
addUnwrappedLine();
}
nextToken();
}
} while (!eof());
// Unreachable for well-formed code (paired '{' and '}').
return true;
}
bool UnwrappedLineParser::tryToParseLambda() {
if (!Style.isCpp()) {
nextToken();
return false;
}
assert(FormatTok->is(tok::l_square));
FormatToken &LSquare = *FormatTok;
if (!tryToParseLambdaIntroducer())
return false;
bool SeenArrow = false;
while (FormatTok->isNot(tok::l_brace)) {
if (FormatTok->isSimpleTypeSpecifier()) {
nextToken();
continue;
}
switch (FormatTok->Tok.getKind()) {
case tok::l_brace:
break;
case tok::l_paren:
parseParens();
break;
case tok::amp:
case tok::star:
case tok::kw_const:
case tok::comma:
case tok::less:
case tok::greater:
case tok::identifier:
case tok::numeric_constant:
case tok::coloncolon:
case tok::kw_class:
case tok::kw_mutable:
case tok::kw_noexcept:
case tok::kw_template:
case tok::kw_typename:
nextToken();
break;
// Specialization of a template with an integer parameter can contain
// arithmetic, logical, comparison and ternary operators.
//
// FIXME: This also accepts sequences of operators that are not in the scope
// of a template argument list.
//
// In a C++ lambda a template type can only occur after an arrow. We use
// this as an heuristic to distinguish between Objective-C expressions
// followed by an `a->b` expression, such as:
// ([obj func:arg] + a->b)
// Otherwise the code below would parse as a lambda.
//
// FIXME: This heuristic is incorrect for C++20 generic lambdas with
// explicit template lists: []<bool b = true && false>(U &&u){}
case tok::plus:
case tok::minus:
case tok::exclaim:
case tok::tilde:
case tok::slash:
case tok::percent:
case tok::lessless:
case tok::pipe:
case tok::pipepipe:
case tok::ampamp:
case tok::caret:
case tok::equalequal:
case tok::exclaimequal:
case tok::greaterequal:
case tok::lessequal:
case tok::question:
case tok::colon:
case tok::ellipsis:
case tok::kw_true:
case tok::kw_false:
if (SeenArrow) {
nextToken();
break;
}
return true;
case tok::arrow:
// This might or might not actually be a lambda arrow (this could be an
// ObjC method invocation followed by a dereferencing arrow). We might
// reset this back to TT_Unknown in TokenAnnotator.
FormatTok->setType(TT_LambdaArrow);
SeenArrow = true;
nextToken();
break;
default:
return true;
}
}
FormatTok->setType(TT_LambdaLBrace);
LSquare.setType(TT_LambdaLSquare);
parseChildBlock();
return true;
}
bool UnwrappedLineParser::tryToParseLambdaIntroducer() {
const FormatToken *Previous = FormatTok->Previous;
if (Previous &&
(Previous->isOneOf(tok::identifier, tok::kw_operator, tok::kw_new,
tok::kw_delete, tok::l_square) ||
FormatTok->isCppStructuredBinding(Style) || Previous->closesScope() ||
Previous->isSimpleTypeSpecifier())) {
nextToken();
return false;
}
nextToken();
if (FormatTok->is(tok::l_square)) {
return false;
}
parseSquare(/*LambdaIntroducer=*/true);
return true;
}
void UnwrappedLineParser::tryToParseJSFunction() {
assert(FormatTok->is(Keywords.kw_function) ||
FormatTok->startsSequence(Keywords.kw_async, Keywords.kw_function));
if (FormatTok->is(Keywords.kw_async))
nextToken();
// Consume "function".
nextToken();
// Consume * (generator function). Treat it like C++'s overloaded operators.
if (FormatTok->is(tok::star)) {
FormatTok->setType(TT_OverloadedOperator);
nextToken();
}
// Consume function name.
if (FormatTok->is(tok::identifier))
nextToken();
if (FormatTok->isNot(tok::l_paren))
return;
// Parse formal parameter list.
parseParens();
if (FormatTok->is(tok::colon)) {
// Parse a type definition.
nextToken();
// Eat the type declaration. For braced inline object types, balance braces,
// otherwise just parse until finding an l_brace for the function body.
if (FormatTok->is(tok::l_brace))
tryToParseBracedList();
else
while (!FormatTok->isOneOf(tok::l_brace, tok::semi) && !eof())
nextToken();
}
if (FormatTok->is(tok::semi))
return;
parseChildBlock();
}
bool UnwrappedLineParser::tryToParseBracedList() {
if (FormatTok->is(BK_Unknown))
calculateBraceTypes();
assert(FormatTok->isNot(BK_Unknown));
if (FormatTok->is(BK_Block))
return false;
nextToken();
parseBracedList();
return true;
}
bool UnwrappedLineParser::parseBracedList(bool ContinueOnSemicolons,
bool IsEnum,
tok::TokenKind ClosingBraceKind) {
bool HasError = false;
// FIXME: Once we have an expression parser in the UnwrappedLineParser,
// replace this by using parseAssigmentExpression() inside.
do {
if (Style.isCSharp()) {
if (FormatTok->is(TT_JsFatArrow)) {
nextToken();
// Fat arrows can be followed by simple expressions or by child blocks
// in curly braces.
if (FormatTok->is(tok::l_brace)) {
parseChildBlock();
continue;
}
}
}
if (Style.Language == FormatStyle::LK_JavaScript) {
if (FormatTok->is(Keywords.kw_function) ||
FormatTok->startsSequence(Keywords.kw_async, Keywords.kw_function)) {
tryToParseJSFunction();
continue;
}
if (FormatTok->is(TT_JsFatArrow)) {
nextToken();
// Fat arrows can be followed by simple expressions or by child blocks
// in curly braces.
if (FormatTok->is(tok::l_brace)) {
parseChildBlock();
continue;
}
}
if (FormatTok->is(tok::l_brace)) {
// Could be a method inside of a braced list `{a() { return 1; }}`.
if (tryToParseBracedList())
continue;
parseChildBlock();
}
}
if (FormatTok->Tok.getKind() == ClosingBraceKind) {
if (IsEnum && !Style.AllowShortEnumsOnASingleLine)
addUnwrappedLine();
nextToken();
return !HasError;
}
switch (FormatTok->Tok.getKind()) {
case tok::caret:
nextToken();
if (FormatTok->is(tok::l_brace)) {
parseChildBlock();
}
break;
case tok::l_square:
if (Style.isCSharp())
parseSquare();
else
tryToParseLambda();
break;
case tok::l_paren:
parseParens();
// JavaScript can just have free standing methods and getters/setters in
// object literals. Detect them by a "{" following ")".
if (Style.Language == FormatStyle::LK_JavaScript) {
if (FormatTok->is(tok::l_brace))
parseChildBlock();
break;
}
break;
case tok::l_brace:
// Assume there are no blocks inside a braced init list apart
// from the ones we explicitly parse out (like lambdas).
FormatTok->setBlockKind(BK_BracedInit);
nextToken();
parseBracedList();
break;
case tok::less:
if (Style.Language == FormatStyle::LK_Proto) {
nextToken();
parseBracedList(/*ContinueOnSemicolons=*/false, /*IsEnum=*/false,
/*ClosingBraceKind=*/tok::greater);
} else {
nextToken();
}
break;
case tok::semi:
// JavaScript (or more precisely TypeScript) can have semicolons in braced
// lists (in so-called TypeMemberLists). Thus, the semicolon cannot be
// used for error recovery if we have otherwise determined that this is
// a braced list.
if (Style.Language == FormatStyle::LK_JavaScript) {
nextToken();
break;
}
HasError = true;
if (!ContinueOnSemicolons)
return !HasError;
nextToken();
break;
case tok::comma:
nextToken();
if (IsEnum && !Style.AllowShortEnumsOnASingleLine)
addUnwrappedLine();
break;
default:
nextToken();
break;
}
} while (!eof());
return false;
}
void UnwrappedLineParser::parseParens() {
assert(FormatTok->Tok.is(tok::l_paren) && "'(' expected.");
nextToken();
do {
switch (FormatTok->Tok.getKind()) {
case tok::l_paren:
parseParens();
if (Style.Language == FormatStyle::LK_Java && FormatTok->is(tok::l_brace))
parseChildBlock();
break;
case tok::r_paren:
nextToken();
return;
case tok::r_brace:
// A "}" inside parenthesis is an error if there wasn't a matching "{".
return;
case tok::l_square:
tryToParseLambda();
break;
case tok::l_brace:
if (!tryToParseBracedList())
parseChildBlock();
break;
case tok::at:
nextToken();
if (FormatTok->Tok.is(tok::l_brace)) {
nextToken();
parseBracedList();
}
break;
case tok::kw_class:
if (Style.Language == FormatStyle::LK_JavaScript)
parseRecord(/*ParseAsExpr=*/true);
else
nextToken();
break;
case tok::identifier:
if (Style.Language == FormatStyle::LK_JavaScript &&
(FormatTok->is(Keywords.kw_function) ||
FormatTok->startsSequence(Keywords.kw_async, Keywords.kw_function)))
tryToParseJSFunction();
else
nextToken();
break;
default:
nextToken();
break;
}
} while (!eof());
}
void UnwrappedLineParser::parseSquare(bool LambdaIntroducer) {
if (!LambdaIntroducer) {
assert(FormatTok->Tok.is(tok::l_square) && "'[' expected.");
if (tryToParseLambda())
return;
}
do {
switch (FormatTok->Tok.getKind()) {
case tok::l_paren:
parseParens();
break;
case tok::r_square:
nextToken();
return;
case tok::r_brace:
// A "}" inside parenthesis is an error if there wasn't a matching "{".
return;
case tok::l_square:
parseSquare();
break;
case tok::l_brace: {
if (!tryToParseBracedList())
parseChildBlock();
break;
}
case tok::at:
nextToken();
if (FormatTok->Tok.is(tok::l_brace)) {
nextToken();
parseBracedList();
}
break;
default:
nextToken();
break;
}
} while (!eof());
}
void UnwrappedLineParser::parseIfThenElse() {
assert(FormatTok->Tok.is(tok::kw_if) && "'if' expected");
nextToken();
if (FormatTok->Tok.isOneOf(tok::kw_constexpr, tok::identifier))
nextToken();
if (FormatTok->Tok.is(tok::l_paren))
parseParens();
// handle [[likely]] / [[unlikely]]
if (FormatTok->is(tok::l_square) && tryToParseSimpleAttribute())
parseSquare();
bool NeedsUnwrappedLine = false;
if (FormatTok->Tok.is(tok::l_brace)) {
CompoundStatementIndenter Indenter(this, Style, Line->Level);
parseBlock(/*MustBeDeclaration=*/false);
if (Style.BraceWrapping.BeforeElse)
addUnwrappedLine();
else
NeedsUnwrappedLine = true;
} else {
addUnwrappedLine();
++Line->Level;
parseStructuralElement();
--Line->Level;
}
if (FormatTok->Tok.is(tok::kw_else)) {
nextToken();
// handle [[likely]] / [[unlikely]]
if (FormatTok->Tok.is(tok::l_square) && tryToParseSimpleAttribute())
parseSquare();
if (FormatTok->Tok.is(tok::l_brace)) {
CompoundStatementIndenter Indenter(this, Style, Line->Level);
parseBlock(/*MustBeDeclaration=*/false);
addUnwrappedLine();
} else if (FormatTok->Tok.is(tok::kw_if)) {
parseIfThenElse();
} else {
addUnwrappedLine();
++Line->Level;
parseStructuralElement();
if (FormatTok->is(tok::eof))
addUnwrappedLine();
--Line->Level;
}
} else if (NeedsUnwrappedLine) {
addUnwrappedLine();
}
}
void UnwrappedLineParser::parseTryCatch() {
assert(FormatTok->isOneOf(tok::kw_try, tok::kw___try) && "'try' expected");
nextToken();
bool NeedsUnwrappedLine = false;
if (FormatTok->is(tok::colon)) {
// We are in a function try block, what comes is an initializer list.
nextToken();
// In case identifiers were removed by clang-tidy, what might follow is
// multiple commas in sequence - before the first identifier.
while (FormatTok->is(tok::comma))
nextToken();
while (FormatTok->is(tok::identifier)) {
nextToken();
if (FormatTok->is(tok::l_paren))
parseParens();
if (FormatTok->Previous && FormatTok->Previous->is(tok::identifier) &&
FormatTok->is(tok::l_brace)) {
do {
nextToken();
} while (!FormatTok->is(tok::r_brace));
nextToken();
}
// In case identifiers were removed by clang-tidy, what might follow is
// multiple commas in sequence - after the first identifier.
while (FormatTok->is(tok::comma))
nextToken();
}
}
// Parse try with resource.
if (Style.Language == FormatStyle::LK_Java && FormatTok->is(tok::l_paren)) {
parseParens();
}
if (FormatTok->is(tok::l_brace)) {
CompoundStatementIndenter Indenter(this, Style, Line->Level);
parseBlock(/*MustBeDeclaration=*/false);
if (Style.BraceWrapping.BeforeCatch) {
addUnwrappedLine();
} else {
NeedsUnwrappedLine = true;
}
} else if (!FormatTok->is(tok::kw_catch)) {
// The C++ standard requires a compound-statement after a try.
// If there's none, we try to assume there's a structuralElement
// and try to continue.
addUnwrappedLine();
++Line->Level;
parseStructuralElement();
--Line->Level;
}
while (1) {
if (FormatTok->is(tok::at))
nextToken();
if (!(FormatTok->isOneOf(tok::kw_catch, Keywords.kw___except,
tok::kw___finally) ||
((Style.Language == FormatStyle::LK_Java ||
Style.Language == FormatStyle::LK_JavaScript) &&
FormatTok->is(Keywords.kw_finally)) ||
(FormatTok->Tok.isObjCAtKeyword(tok::objc_catch) ||
FormatTok->Tok.isObjCAtKeyword(tok::objc_finally))))
break;
nextToken();
while (FormatTok->isNot(tok::l_brace)) {
if (FormatTok->is(tok::l_paren)) {
parseParens();
continue;
}
if (FormatTok->isOneOf(tok::semi, tok::r_brace, tok::eof))
return;
nextToken();
}
NeedsUnwrappedLine = false;
CompoundStatementIndenter Indenter(this, Style, Line->Level);
parseBlock(/*MustBeDeclaration=*/false);
if (Style.BraceWrapping.BeforeCatch)
addUnwrappedLine();
else
NeedsUnwrappedLine = true;
}
if (NeedsUnwrappedLine)
addUnwrappedLine();
}
void UnwrappedLineParser::parseNamespace() {
assert(FormatTok->isOneOf(tok::kw_namespace, TT_NamespaceMacro) &&
"'namespace' expected");
const FormatToken &InitialToken = *FormatTok;
nextToken();
if (InitialToken.is(TT_NamespaceMacro)) {
parseParens();
} else {
while (FormatTok->isOneOf(tok::identifier, tok::coloncolon, tok::kw_inline,
tok::l_square)) {
if (FormatTok->is(tok::l_square))
parseSquare();
else
nextToken();
}
}
if (FormatTok->Tok.is(tok::l_brace)) {
if (ShouldBreakBeforeBrace(Style, InitialToken))
addUnwrappedLine();
unsigned AddLevels =
Style.NamespaceIndentation == FormatStyle::NI_All ||
(Style.NamespaceIndentation == FormatStyle::NI_Inner &&
DeclarationScopeStack.size() > 1)
? 1u
: 0u;
bool ManageWhitesmithsBraces =
AddLevels == 0u &&
Style.BreakBeforeBraces == FormatStyle::BS_Whitesmiths;
// If we're in Whitesmiths mode, indent the brace if we're not indenting
// the whole block.
if (ManageWhitesmithsBraces)
++Line->Level;
parseBlock(/*MustBeDeclaration=*/true, AddLevels,
/*MunchSemi=*/true,
/*UnindentWhitesmithsBraces=*/ManageWhitesmithsBraces);
// Munch the semicolon after a namespace. This is more common than one would
// think. Putting the semicolon into its own line is very ugly.
if (FormatTok->Tok.is(tok::semi))
nextToken();
addUnwrappedLine(AddLevels > 0 ? LineLevel::Remove : LineLevel::Keep);
if (ManageWhitesmithsBraces)
--Line->Level;
}
// FIXME: Add error handling.
}
void UnwrappedLineParser::parseNew() {
assert(FormatTok->is(tok::kw_new) && "'new' expected");
nextToken();
if (Style.isCSharp()) {
do {
if (FormatTok->is(tok::l_brace))
parseBracedList();
if (FormatTok->isOneOf(tok::semi, tok::comma))
return;
nextToken();
} while (!eof());
}
if (Style.Language != FormatStyle::LK_Java)
return;
// In Java, we can parse everything up to the parens, which aren't optional.
do {
// There should not be a ;, { or } before the new's open paren.
if (FormatTok->isOneOf(tok::semi, tok::l_brace, tok::r_brace))
return;
// Consume the parens.
if (FormatTok->is(tok::l_paren)) {
parseParens();
// If there is a class body of an anonymous class, consume that as child.
if (FormatTok->is(tok::l_brace))
parseChildBlock();
return;
}
nextToken();
} while (!eof());
}
void UnwrappedLineParser::parseForOrWhileLoop() {
assert(FormatTok->isOneOf(tok::kw_for, tok::kw_while, TT_ForEachMacro) &&
"'for', 'while' or foreach macro expected");
nextToken();
// JS' for await ( ...
if (Style.Language == FormatStyle::LK_JavaScript &&
FormatTok->is(Keywords.kw_await))
nextToken();
if (FormatTok->Tok.is(tok::l_paren))
parseParens();
if (FormatTok->Tok.is(tok::l_brace)) {
CompoundStatementIndenter Indenter(this, Style, Line->Level);
parseBlock(/*MustBeDeclaration=*/false);
addUnwrappedLine();
} else {
addUnwrappedLine();
++Line->Level;
parseStructuralElement();
--Line->Level;
}
}
void UnwrappedLineParser::parseDoWhile() {
assert(FormatTok->Tok.is(tok::kw_do) && "'do' expected");
nextToken();
if (FormatTok->Tok.is(tok::l_brace)) {
CompoundStatementIndenter Indenter(this, Style, Line->Level);
parseBlock(/*MustBeDeclaration=*/false);
if (Style.BraceWrapping.BeforeWhile)
addUnwrappedLine();
} else {
addUnwrappedLine();
++Line->Level;
parseStructuralElement();
--Line->Level;
}
// FIXME: Add error handling.
if (!FormatTok->Tok.is(tok::kw_while)) {
addUnwrappedLine();
return;
}
// If in Whitesmiths mode, the line with the while() needs to be indented
// to the same level as the block.
if (Style.BreakBeforeBraces == FormatStyle::BS_Whitesmiths)
++Line->Level;
nextToken();
parseStructuralElement();
}
void UnwrappedLineParser::parseLabel(bool LeftAlignLabel) {
nextToken();
unsigned OldLineLevel = Line->Level;
if (Line->Level > 1 || (!Line->InPPDirective && Line->Level > 0))
--Line->Level;
if (LeftAlignLabel)
Line->Level = 0;
if (!Style.IndentCaseBlocks && CommentsBeforeNextToken.empty() &&
FormatTok->Tok.is(tok::l_brace)) {
CompoundStatementIndenter Indenter(this, Line->Level,
Style.BraceWrapping.AfterCaseLabel,
Style.BraceWrapping.IndentBraces);
parseBlock(/*MustBeDeclaration=*/false);
if (FormatTok->Tok.is(tok::kw_break)) {
if (Style.BraceWrapping.AfterControlStatement ==
FormatStyle::BWACS_Always) {
addUnwrappedLine();
if (!Style.IndentCaseBlocks &&
Style.BreakBeforeBraces == FormatStyle::BS_Whitesmiths) {
Line->Level++;
}
}
parseStructuralElement();
}
addUnwrappedLine();
} else {
if (FormatTok->is(tok::semi))
nextToken();
addUnwrappedLine();
}
Line->Level = OldLineLevel;
if (FormatTok->isNot(tok::l_brace)) {
parseStructuralElement();
addUnwrappedLine();
}
}
void UnwrappedLineParser::parseCaseLabel() {
assert(FormatTok->Tok.is(tok::kw_case) && "'case' expected");
// FIXME: fix handling of complex expressions here.
do {
nextToken();
} while (!eof() && !FormatTok->Tok.is(tok::colon));
parseLabel();
}
void UnwrappedLineParser::parseSwitch() {
assert(FormatTok->Tok.is(tok::kw_switch) && "'switch' expected");
nextToken();
if (FormatTok->Tok.is(tok::l_paren))
parseParens();
if (FormatTok->Tok.is(tok::l_brace)) {
CompoundStatementIndenter Indenter(this, Style, Line->Level);
parseBlock(/*MustBeDeclaration=*/false);
addUnwrappedLine();
} else {
addUnwrappedLine();
++Line->Level;
parseStructuralElement();
--Line->Level;
}
}
void UnwrappedLineParser::parseAccessSpecifier() {
nextToken();
// Understand Qt's slots.
if (FormatTok->isOneOf(Keywords.kw_slots, Keywords.kw_qslots))
nextToken();
// Otherwise, we don't know what it is, and we'd better keep the next token.
if (FormatTok->Tok.is(tok::colon))
nextToken();
addUnwrappedLine();
}
void UnwrappedLineParser::parseConcept() {
assert(FormatTok->Tok.is(tok::kw_concept) && "'concept' expected");
nextToken();
if (!FormatTok->Tok.is(tok::identifier))
return;
nextToken();
if (!FormatTok->Tok.is(tok::equal))
return;
nextToken();
if (FormatTok->Tok.is(tok::kw_requires)) {
nextToken();
parseRequiresExpression(Line->Level);
} else {
parseConstraintExpression(Line->Level);
}
}
void UnwrappedLineParser::parseRequiresExpression(unsigned int OriginalLevel) {
// requires (R range)
if (FormatTok->Tok.is(tok::l_paren)) {
parseParens();
if (Style.IndentRequires && OriginalLevel != Line->Level) {
addUnwrappedLine();
--Line->Level;
}
}
if (FormatTok->Tok.is(tok::l_brace)) {
if (Style.BraceWrapping.AfterFunction)
addUnwrappedLine();
FormatTok->setType(TT_FunctionLBrace);
parseBlock(/*MustBeDeclaration=*/false);
addUnwrappedLine();
} else {
parseConstraintExpression(OriginalLevel);
}
}
void UnwrappedLineParser::parseConstraintExpression(
unsigned int OriginalLevel) {
// requires Id<T> && Id<T> || Id<T>
while (
FormatTok->isOneOf(tok::identifier, tok::kw_requires, tok::coloncolon)) {
nextToken();
while (FormatTok->isOneOf(tok::identifier, tok::coloncolon, tok::less,
tok::greater, tok::comma, tok::ellipsis)) {
if (FormatTok->Tok.is(tok::less)) {
parseBracedList(/*ContinueOnSemicolons=*/false, /*IsEnum=*/false,
/*ClosingBraceKind=*/tok::greater);
continue;
}
nextToken();
}
if (FormatTok->Tok.is(tok::kw_requires)) {
parseRequiresExpression(OriginalLevel);
}
if (FormatTok->Tok.is(tok::less)) {
parseBracedList(/*ContinueOnSemicolons=*/false, /*IsEnum=*/false,
/*ClosingBraceKind=*/tok::greater);
}
if (FormatTok->Tok.is(tok::l_paren)) {
parseParens();
}
if (FormatTok->Tok.is(tok::l_brace)) {
if (Style.BraceWrapping.AfterFunction)
addUnwrappedLine();
FormatTok->setType(TT_FunctionLBrace);
parseBlock(/*MustBeDeclaration=*/false);
}
if (FormatTok->Tok.is(tok::semi)) {
// Eat any trailing semi.
nextToken();
addUnwrappedLine();
}
if (FormatTok->Tok.is(tok::colon)) {
return;
}
if (!FormatTok->Tok.isOneOf(tok::ampamp, tok::pipepipe)) {
if (FormatTok->Previous &&
!FormatTok->Previous->isOneOf(tok::identifier, tok::kw_requires,
tok::coloncolon)) {
addUnwrappedLine();
}
if (Style.IndentRequires && OriginalLevel != Line->Level) {
--Line->Level;
}
break;
} else {
FormatTok->setType(TT_ConstraintJunctions);
}
nextToken();
}
}
void UnwrappedLineParser::parseRequires() {
assert(FormatTok->Tok.is(tok::kw_requires) && "'requires' expected");
unsigned OriginalLevel = Line->Level;
if (FormatTok->Previous && FormatTok->Previous->is(tok::greater)) {
addUnwrappedLine();
if (Style.IndentRequires) {
Line->Level++;
}
}
nextToken();
parseRequiresExpression(OriginalLevel);
}
bool UnwrappedLineParser::parseEnum() {
// Won't be 'enum' for NS_ENUMs.
if (FormatTok->Tok.is(tok::kw_enum))
nextToken();
// In TypeScript, "enum" can also be used as property name, e.g. in interface
// declarations. An "enum" keyword followed by a colon would be a syntax
// error and thus assume it is just an identifier.
if (Style.Language == FormatStyle::LK_JavaScript &&
FormatTok->isOneOf(tok::colon, tok::question))
return false;
// In protobuf, "enum" can be used as a field name.
if (Style.Language == FormatStyle::LK_Proto && FormatTok->is(tok::equal))
return false;
// Eat up enum class ...
if (FormatTok->Tok.is(tok::kw_class) || FormatTok->Tok.is(tok::kw_struct))
nextToken();
while (FormatTok->Tok.getIdentifierInfo() ||
FormatTok->isOneOf(tok::colon, tok::coloncolon, tok::less,
tok::greater, tok::comma, tok::question)) {
nextToken();
// We can have macros or attributes in between 'enum' and the enum name.
if (FormatTok->is(tok::l_paren))
parseParens();
if (FormatTok->is(tok::identifier)) {
nextToken();
// If there are two identifiers in a row, this is likely an elaborate
// return type. In Java, this can be "implements", etc.
if (Style.isCpp() && FormatTok->is(tok::identifier))
return false;
}
}
// Just a declaration or something is wrong.
if (FormatTok->isNot(tok::l_brace))
return true;
FormatTok->setBlockKind(BK_Block);
if (Style.Language == FormatStyle::LK_Java) {
// Java enums are different.
parseJavaEnumBody();
return true;
}
if (Style.Language == FormatStyle::LK_Proto) {
parseBlock(/*MustBeDeclaration=*/true);
return true;
}
if (!Style.AllowShortEnumsOnASingleLine)
addUnwrappedLine();
// Parse enum body.
nextToken();
if (!Style.AllowShortEnumsOnASingleLine) {
addUnwrappedLine();
Line->Level += 1;
}
bool HasError = !parseBracedList(/*ContinueOnSemicolons=*/true,
/*IsEnum=*/true);
if (!Style.AllowShortEnumsOnASingleLine)
Line->Level -= 1;
if (HasError) {
if (FormatTok->is(tok::semi))
nextToken();
addUnwrappedLine();
}
return true;
// There is no addUnwrappedLine() here so that we fall through to parsing a
// structural element afterwards. Thus, in "enum A {} n, m;",
// "} n, m;" will end up in one unwrapped line.
}
namespace {
// A class used to set and restore the Token position when peeking
// ahead in the token source.
class ScopedTokenPosition {
unsigned StoredPosition;
FormatTokenSource *Tokens;
public:
ScopedTokenPosition(FormatTokenSource *Tokens) : Tokens(Tokens) {
assert(Tokens && "Tokens expected to not be null");
StoredPosition = Tokens->getPosition();
}
~ScopedTokenPosition() { Tokens->setPosition(StoredPosition); }
};
} // namespace
// Look to see if we have [[ by looking ahead, if
// its not then rewind to the original position.
bool UnwrappedLineParser::tryToParseSimpleAttribute() {
ScopedTokenPosition AutoPosition(Tokens);
FormatToken *Tok = Tokens->getNextToken();
// We already read the first [ check for the second.
if (Tok && !Tok->is(tok::l_square)) {
return false;
}
// Double check that the attribute is just something
// fairly simple.
while (Tok) {
if (Tok->is(tok::r_square)) {
break;
}
Tok = Tokens->getNextToken();
}
Tok = Tokens->getNextToken();
if (Tok && !Tok->is(tok::r_square)) {
return false;
}
Tok = Tokens->getNextToken();
if (Tok && Tok->is(tok::semi)) {
return false;
}
return true;
}