summaryrefslogtreecommitdiffstats
path: root/lib/Format/TokenAnnotator.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'lib/Format/TokenAnnotator.cpp')
-rw-r--r--lib/Format/TokenAnnotator.cpp195
1 files changed, 148 insertions, 47 deletions
diff --git a/lib/Format/TokenAnnotator.cpp b/lib/Format/TokenAnnotator.cpp
index 24c2f998c3..ddaacaab77 100644
--- a/lib/Format/TokenAnnotator.cpp
+++ b/lib/Format/TokenAnnotator.cpp
@@ -1,9 +1,8 @@
//===--- TokenAnnotator.cpp - Format C++ code -----------------------------===//
//
-// The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
+// 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
//
//===----------------------------------------------------------------------===//
///
@@ -14,6 +13,7 @@
//===----------------------------------------------------------------------===//
#include "TokenAnnotator.h"
+#include "FormatToken.h"
#include "clang/Basic/SourceManager.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/Support/Debug.h"
@@ -62,7 +62,7 @@ private:
if (NonTemplateLess.count(CurrentToken->Previous))
return false;
- const FormatToken &Previous = *CurrentToken->Previous; // The '<'.
+ const FormatToken &Previous = *CurrentToken->Previous; // The '<'.
if (Previous.Previous) {
if (Previous.Previous->Tok.isLiteral())
return false;
@@ -299,6 +299,8 @@ private:
CurrentToken->Type = TT_JavaAnnotation;
if (Left->Previous && Left->Previous->is(TT_LeadingJavaAnnotation))
CurrentToken->Type = TT_LeadingJavaAnnotation;
+ if (Left->Previous && Left->Previous->is(TT_AttributeSquare))
+ CurrentToken->Type = TT_AttributeSquare;
if (!HasMultipleLines)
Left->PackingKind = PPK_Inconclusive;
@@ -349,6 +351,40 @@ private:
return false;
}
+ bool isCSharpAttributeSpecifier(const FormatToken &Tok) {
+ if (!Style.isCSharp())
+ return false;
+
+ const FormatToken *AttrTok = Tok.Next;
+ if (!AttrTok)
+ return false;
+
+ // Just an empty declaration e.g. string [].
+ if (AttrTok->is(tok::r_square))
+ return false;
+
+ // Move along the tokens inbetween the '[' and ']' e.g. [STAThread].
+ while (AttrTok && AttrTok->isNot(tok::r_square)) {
+ AttrTok = AttrTok->Next;
+ }
+
+ if (!AttrTok)
+ return false;
+
+ // Move past the end of ']'.
+ AttrTok = AttrTok->Next;
+ if (!AttrTok)
+ return false;
+
+ // Limit this to being an access modifier that follows.
+ if (AttrTok->isOneOf(tok::kw_public, tok::kw_private, tok::kw_protected,
+ tok::kw_class, tok::kw_static, tok::l_square,
+ Keywords.kw_internal)) {
+ return true;
+ }
+ return false;
+ }
+
bool isCpp11AttributeSpecifier(const FormatToken &Tok) {
if (!Style.isCpp() || !Tok.startsSequence(tok::l_square, tok::l_square))
return false;
@@ -366,7 +402,7 @@ private:
// specifier parameter, although this is technically valid:
// [[foo(:)]]
if (AttrTok->is(tok::colon) ||
- AttrTok->startsSequence(tok::identifier, tok::identifier) ||
+ AttrTok->startsSequence(tok::identifier, tok::identifier) ||
AttrTok->startsSequence(tok::r_paren, tok::identifier))
return false;
if (AttrTok->is(tok::ellipsis))
@@ -399,11 +435,17 @@ private:
bool IsCpp11AttributeSpecifier = isCpp11AttributeSpecifier(*Left) ||
Contexts.back().InCpp11AttributeSpecifier;
+ // Treat C# Attributes [STAThread] much like C++ attributes [[...]].
+ bool IsCSharp11AttributeSpecifier =
+ isCSharpAttributeSpecifier(*Left) ||
+ Contexts.back().InCSharpAttributeSpecifier;
+
bool InsideInlineASM = Line.startsWith(tok::kw_asm);
+ bool IsCppStructuredBinding = Left->isCppStructuredBinding(Style);
bool StartsObjCMethodExpr =
- !InsideInlineASM && !CppArrayTemplates && Style.isCpp() &&
- !IsCpp11AttributeSpecifier && Contexts.back().CanBeExpression &&
- Left->isNot(TT_LambdaLSquare) &&
+ !IsCppStructuredBinding && !InsideInlineASM && !CppArrayTemplates &&
+ Style.isCpp() && !IsCpp11AttributeSpecifier &&
+ Contexts.back().CanBeExpression && Left->isNot(TT_LambdaLSquare) &&
!CurrentToken->isOneOf(tok::l_brace, tok::r_square) &&
(!Parent ||
Parent->isOneOf(tok::colon, tok::l_square, tok::l_paren,
@@ -411,11 +453,12 @@ private:
Parent->isUnaryOperator() ||
// FIXME(bug 36976): ObjC return types shouldn't use TT_CastRParen.
Parent->isOneOf(TT_ObjCForIn, TT_CastRParen) ||
- getBinOpPrecedence(Parent->Tok.getKind(), true, true) > prec::Unknown);
+ (getBinOpPrecedence(Parent->Tok.getKind(), true, true) >
+ prec::Unknown));
bool ColonFound = false;
unsigned BindingIncrease = 1;
- if (Left->isCppStructuredBinding(Style)) {
+ if (IsCppStructuredBinding) {
Left->Type = TT_StructuredBindingLSquare;
} else if (Left->is(TT_Unknown)) {
if (StartsObjCMethodExpr) {
@@ -476,6 +519,8 @@ private:
// Should only be relevant to JavaScript:
tok::kw_default)) {
Left->Type = TT_ArrayInitializerLSquare;
+ } else if (IsCSharp11AttributeSpecifier) {
+ Left->Type = TT_AttributeSquare;
} else {
BindingIncrease = 10;
Left->Type = TT_ArraySubscriptLSquare;
@@ -490,14 +535,22 @@ private:
Contexts.back().ColonIsObjCMethodExpr = StartsObjCMethodExpr;
Contexts.back().InCpp11AttributeSpecifier = IsCpp11AttributeSpecifier;
+ Contexts.back().InCSharpAttributeSpecifier = IsCSharp11AttributeSpecifier;
while (CurrentToken) {
if (CurrentToken->is(tok::r_square)) {
if (IsCpp11AttributeSpecifier)
CurrentToken->Type = TT_AttributeSquare;
- else if (CurrentToken->Next && CurrentToken->Next->is(tok::l_paren) &&
+ if (IsCSharp11AttributeSpecifier)
+ CurrentToken->Type = TT_AttributeSquare;
+ else if (((CurrentToken->Next &&
+ CurrentToken->Next->is(tok::l_paren)) ||
+ (CurrentToken->Previous &&
+ CurrentToken->Previous->Previous == Left)) &&
Left->is(TT_ObjCMethodExpr)) {
- // An ObjC method call is rarely followed by an open parenthesis.
+ // An ObjC method call is rarely followed by an open parenthesis. It
+ // also can't be composed of just one token, unless it's a macro that
+ // will be expanded to more tokens.
// FIXME: Do we incorrectly label ":" with this?
StartsObjCMethodExpr = false;
Left->Type = TT_Unknown;
@@ -516,6 +569,10 @@ private:
if (Parent && Parent->is(TT_PointerOrReference))
Parent->Type = TT_BinaryOperator;
}
+ // An arrow after an ObjC method expression is not a lambda arrow.
+ if (CurrentToken->Type == TT_ObjCMethodExpr && CurrentToken->Next &&
+ CurrentToken->Next->is(TT_LambdaArrow))
+ CurrentToken->Next->Type = TT_Unknown;
Left->MatchingParen = CurrentToken;
CurrentToken->MatchingParen = Left;
// FirstObjCSelectorName is set when a colon is found. This does
@@ -523,11 +580,11 @@ private:
// Here, we set FirstObjCSelectorName when the end of the method call is
// reached, in case it was not set already.
if (!Contexts.back().FirstObjCSelectorName) {
- FormatToken* Previous = CurrentToken->getPreviousNonComment();
- if (Previous && Previous->is(TT_SelectorName)) {
- Previous->ObjCSelectorNameParts = 1;
- Contexts.back().FirstObjCSelectorName = Previous;
- }
+ FormatToken *Previous = CurrentToken->getPreviousNonComment();
+ if (Previous && Previous->is(TT_SelectorName)) {
+ Previous->ObjCSelectorNameParts = 1;
+ Contexts.back().FirstObjCSelectorName = Previous;
+ }
} else {
Left->ParameterCount =
Contexts.back().FirstObjCSelectorName->ObjCSelectorNameParts;
@@ -1067,8 +1124,11 @@ public:
if (Style.Language == FormatStyle::LK_Proto && Line.Level == 0 &&
CurrentToken->is(Keywords.kw_option)) {
next();
- if (CurrentToken && CurrentToken->is(tok::identifier))
+ if (CurrentToken && CurrentToken->is(tok::identifier)) {
+ while (CurrentToken)
+ next();
return LT_ImportStatement;
+ }
}
bool KeywordVirtualFound = false;
@@ -1134,11 +1194,11 @@ private:
// Reset token type in case we have already looked at it and then
// recovered from an error (e.g. failure to find the matching >).
- if (!CurrentToken->isOneOf(TT_LambdaLSquare, TT_ForEachMacro,
- TT_FunctionLBrace, TT_ImplicitStringLiteral,
- TT_InlineASMBrace, TT_JsFatArrow, TT_LambdaArrow,
- TT_OverloadedOperator, TT_RegexLiteral,
- TT_TemplateString, TT_ObjCStringLiteral))
+ if (!CurrentToken->isOneOf(
+ TT_LambdaLSquare, TT_LambdaLBrace, TT_ForEachMacro,
+ TT_FunctionLBrace, TT_ImplicitStringLiteral, TT_InlineASMBrace,
+ TT_JsFatArrow, TT_LambdaArrow, TT_OverloadedOperator,
+ TT_RegexLiteral, TT_TemplateString, TT_ObjCStringLiteral))
CurrentToken->Type = TT_Unknown;
CurrentToken->Role.reset();
CurrentToken->MatchingParen = nullptr;
@@ -1182,6 +1242,7 @@ private:
bool CaretFound = false;
bool IsForEachMacro = false;
bool InCpp11AttributeSpecifier = false;
+ bool InCSharpAttributeSpecifier = false;
};
/// Puts a new \c Context onto the stack \c Contexts for the lifetime
@@ -1389,7 +1450,8 @@ private:
Current.Type = Current.Previous->Type;
}
} else if (canBeObjCSelectorComponent(Current) &&
- // FIXME(bug 36976): ObjC return types shouldn't use TT_CastRParen.
+ // FIXME(bug 36976): ObjC return types shouldn't use
+ // TT_CastRParen.
Current.Previous && Current.Previous->is(TT_CastRParen) &&
Current.Previous->MatchingParen &&
Current.Previous->MatchingParen->Previous &&
@@ -1912,12 +1974,15 @@ void TokenAnnotator::setCommentLineLevels(
NextNonCommentLine->First->NewlinesBefore <= 1 &&
NextNonCommentLine->First->OriginalColumn ==
(*I)->First->OriginalColumn) {
- // Align comments for preprocessor lines with the # in column 0.
- // Otherwise, align with the next line.
- (*I)->Level = (NextNonCommentLine->Type == LT_PreprocessorDirective ||
- NextNonCommentLine->Type == LT_ImportStatement)
- ? 0
- : NextNonCommentLine->Level;
+ // Align comments for preprocessor lines with the # in column 0 if
+ // preprocessor lines are not indented. Otherwise, align with the next
+ // line.
+ (*I)->Level =
+ (Style.IndentPPDirectives != FormatStyle::PPDIS_BeforeHash &&
+ (NextNonCommentLine->Type == LT_PreprocessorDirective ||
+ NextNonCommentLine->Type == LT_ImportStatement))
+ ? 0
+ : NextNonCommentLine->Level;
} else {
NextNonCommentLine = (*I)->First->isNot(tok::r_brace) ? (*I) : nullptr;
}
@@ -2033,7 +2098,7 @@ static bool isFunctionDeclarationName(const FormatToken &Current,
return true;
for (const FormatToken *Tok = Next->Next; Tok && Tok != Next->MatchingParen;
Tok = Tok->Next) {
- if (Tok->is(tok::l_paren) && Tok->MatchingParen) {
+ if (Tok->isOneOf(tok::l_paren, TT_TemplateOpener) && Tok->MatchingParen) {
Tok = Tok->MatchingParen;
continue;
}
@@ -2245,6 +2310,9 @@ unsigned TokenAnnotator::splitPenalty(const AnnotatedLine &Line,
return 500;
}
+ if (Left.is(tok::coloncolon) ||
+ (Right.is(tok::period) && Style.Language == FormatStyle::LK_Proto))
+ return 500;
if (Right.isOneOf(TT_StartOfName, TT_FunctionDeclarationName) ||
Right.is(tok::kw_operator)) {
if (Line.startsWith(tok::kw_for) && Right.PartOfMultiVariableDeclStmt)
@@ -2263,9 +2331,6 @@ unsigned TokenAnnotator::splitPenalty(const AnnotatedLine &Line,
return 160;
if (Left.is(TT_CastRParen))
return 100;
- if (Left.is(tok::coloncolon) ||
- (Right.is(tok::period) && Style.Language == FormatStyle::LK_Proto))
- return 500;
if (Left.isOneOf(tok::kw_class, tok::kw_struct))
return 5000;
if (Left.is(tok::comment))
@@ -2391,6 +2456,12 @@ unsigned TokenAnnotator::splitPenalty(const AnnotatedLine &Line,
return 3;
}
+bool TokenAnnotator::spaceRequiredBeforeParens(const FormatToken &Right) const {
+ return Style.SpaceBeforeParens == FormatStyle::SBPO_Always ||
+ (Style.SpaceBeforeParens == FormatStyle::SBPO_NonEmptyParentheses &&
+ Right.ParameterCount > 0);
+}
+
bool TokenAnnotator::spaceRequiredBetween(const AnnotatedLine &Line,
const FormatToken &Left,
const FormatToken &Right) {
@@ -2415,9 +2486,9 @@ bool TokenAnnotator::spaceRequiredBetween(const AnnotatedLine &Line,
if (Right.isOneOf(tok::semi, tok::comma))
return false;
if (Right.is(tok::less) && Line.Type == LT_ObjCDecl) {
- bool IsLightweightGeneric =
- Right.MatchingParen && Right.MatchingParen->Next &&
- Right.MatchingParen->Next->is(tok::colon);
+ bool IsLightweightGeneric = Right.MatchingParen &&
+ Right.MatchingParen->Next &&
+ Right.MatchingParen->Next->is(tok::colon);
return !IsLightweightGeneric && Style.ObjCSpaceBeforeProtocolList;
}
if (Right.is(tok::less) && Left.is(tok::kw_template))
@@ -2537,9 +2608,11 @@ bool TokenAnnotator::spaceRequiredBetween(const AnnotatedLine &Line,
(Left.isOneOf(tok::kw_try, Keywords.kw___except, tok::kw_catch,
tok::kw_new, tok::kw_delete) &&
(!Left.Previous || Left.Previous->isNot(tok::period))))) ||
- (Style.SpaceBeforeParens == FormatStyle::SBPO_Always &&
+ (spaceRequiredBeforeParens(Right) &&
(Left.is(tok::identifier) || Left.isFunctionLikeKeyword() ||
- Left.is(tok::r_paren)) &&
+ Left.is(tok::r_paren) || Left.isSimpleTypeSpecifier() ||
+ (Left.is(tok::r_square) && Left.MatchingParen &&
+ Left.MatchingParen->is(TT_LambdaLSquare))) &&
Line.Type != LT_PreprocessorDirective);
}
if (Left.is(tok::at) && Right.Tok.getObjCKeywordID() != tok::objc_not_keyword)
@@ -2602,7 +2675,8 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
// Slashes occur in text protocol extension syntax: [type/type] { ... }.
if (Left.is(tok::slash) || Right.is(tok::slash))
return false;
- if (Left.MatchingParen && Left.MatchingParen->is(TT_ProtoExtensionLSquare) &&
+ if (Left.MatchingParen &&
+ Left.MatchingParen->is(TT_ProtoExtensionLSquare) &&
Right.isOneOf(tok::l_brace, tok::less))
return !Style.Cpp11BracedListStyle;
// A percent is probably part of a formatting specification, such as %lld.
@@ -2612,7 +2686,7 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
// and "%d %d"
if (Left.is(tok::numeric_constant) && Right.is(tok::percent))
return Right.WhitespaceRange.getEnd() != Right.WhitespaceRange.getBegin();
- } else if (Style.Language == FormatStyle::LK_JavaScript) {
+ } else if (Style.Language == FormatStyle::LK_JavaScript || Style.isCSharp()) {
if (Left.is(TT_JsFatArrow))
return true;
// for await ( ...
@@ -2730,7 +2804,7 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
Left.isOneOf(TT_TrailingReturnArrow, TT_LambdaArrow))
return true;
if (Right.is(TT_OverloadedOperatorLParen))
- return Style.SpaceBeforeParens == FormatStyle::SBPO_Always;
+ return spaceRequiredBeforeParens(Right);
if (Left.is(tok::comma))
return true;
if (Right.is(tok::comma))
@@ -2761,7 +2835,8 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
return true;
}
if (Left.is(TT_UnaryOperator))
- return Right.is(TT_BinaryOperator);
+ return (Style.SpaceAfterLogicalNot && Left.is(tok::exclaim)) ||
+ Right.is(TT_BinaryOperator);
// If the next token is a binary operator or a selector name, we have
// incorrectly classified the parenthesis as a cast. FIXME: Detect correctly.
@@ -2814,7 +2889,7 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
return true;
if (Left.is(TT_TemplateCloser) && Right.is(tok::l_paren) &&
Right.isNot(TT_FunctionTypeLParen))
- return Style.SpaceBeforeParens == FormatStyle::SBPO_Always;
+ return spaceRequiredBeforeParens(Right);
if (Right.is(TT_TemplateOpener) && Left.is(tok::r_paren) &&
Left.MatchingParen && Left.MatchingParen->is(TT_OverloadedOperatorLParen))
return false;
@@ -2831,7 +2906,7 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
// Returns 'true' if 'Tok' is a brace we'd want to break before in Allman style.
static bool isAllmanBrace(const FormatToken &Tok) {
return Tok.is(tok::l_brace) && Tok.BlockKind == BK_Block &&
- !Tok.isOneOf(TT_ObjCBlockLBrace, TT_DictLiteral);
+ !Tok.isOneOf(TT_ObjCBlockLBrace, TT_LambdaLBrace, TT_DictLiteral);
}
bool TokenAnnotator::mustBreakBefore(const AnnotatedLine &Line,
@@ -2959,6 +3034,27 @@ bool TokenAnnotator::mustBreakBefore(const AnnotatedLine &Line,
if (Left.is(TT_ObjCBlockLBrace) && !Style.AllowShortBlocksOnASingleLine)
return true;
+ if (Left.is(TT_LambdaLBrace)) {
+ if (Left.MatchingParen && Left.MatchingParen->Next &&
+ Left.MatchingParen->Next->isOneOf(tok::comma, tok::r_paren) &&
+ Style.AllowShortLambdasOnASingleLine == FormatStyle::SLS_Inline)
+ return false;
+
+ if (Style.AllowShortLambdasOnASingleLine == FormatStyle::SLS_None ||
+ Style.AllowShortLambdasOnASingleLine == FormatStyle::SLS_Inline ||
+ (!Left.Children.empty() &&
+ Style.AllowShortLambdasOnASingleLine == FormatStyle::SLS_Empty))
+ return true;
+ }
+
+ // Put multiple C# attributes on a new line.
+ if (Style.isCSharp() &&
+ ((Left.is(TT_AttributeSquare) && Left.is(tok::r_square)) ||
+ (Left.is(tok::r_square) && Right.is(TT_AttributeSquare) &&
+ Right.is(tok::l_square))))
+ return true;
+
+ // Put multiple Java annotation on a new line.
if ((Style.Language == FormatStyle::LK_Java ||
Style.Language == FormatStyle::LK_JavaScript) &&
Left.is(TT_LeadingJavaAnnotation) &&
@@ -3119,7 +3215,7 @@ bool TokenAnnotator::canBreakBefore(const AnnotatedLine &Line,
// function f(): a is B { ... }
// Do not break before is in these cases.
if (Right.is(Keywords.kw_is)) {
- const FormatToken* Next = Right.getNextNonComment();
+ const FormatToken *Next = Right.getNextNonComment();
// If `is` is followed by a colon, it's likely that it's a dict key, so
// ignore it for this check.
// For example this is common in Polymer:
@@ -3159,6 +3255,11 @@ bool TokenAnnotator::canBreakBefore(const AnnotatedLine &Line,
return false; // must not break in "module foo { ...}"
if (Right.is(TT_TemplateString) && Right.closesScope())
return false;
+ // Don't split tagged template literal so there is a break between the tag
+ // identifier and template string.
+ if (Left.is(tok::identifier) && Right.is(TT_TemplateString)) {
+ return false;
+ }
if (Left.is(TT_TemplateString) && Left.opensScope())
return true;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-24 18:07:56 +0000