summaryrefslogtreecommitdiff
path: root/lib/Format
diff options
context:
space:
mode:
authorDimitry Andric <dim@FreeBSD.org>2019-01-19 10:04:05 +0000
committerDimitry Andric <dim@FreeBSD.org>2019-01-19 10:04:05 +0000
commit676fbe8105eeb6ff4bb2ed261cb212fcfdbe7b63 (patch)
tree02a1ac369cb734d0abfa5000dd86e5b7797e6a74 /lib/Format
parentc7e70c433efc6953dc3888b9fbf9f3512d7da2b0 (diff)
Diffstat (limited to 'lib/Format')
-rw-r--r--lib/Format/BreakableToken.cpp38
-rw-r--r--lib/Format/ContinuationIndenter.cpp54
-rw-r--r--lib/Format/Format.cpp216
-rw-r--r--lib/Format/FormatToken.h29
-rw-r--r--lib/Format/FormatTokenLexer.cpp11
-rw-r--r--lib/Format/FormatTokenLexer.h4
-rw-r--r--lib/Format/NamespaceEndCommentsFixer.cpp7
-rw-r--r--lib/Format/TokenAnnotator.cpp70
-rw-r--r--lib/Format/TokenAnnotator.h7
-rw-r--r--lib/Format/UnwrappedLineFormatter.cpp23
-rw-r--r--lib/Format/UnwrappedLineParser.cpp53
-rw-r--r--lib/Format/UnwrappedLineParser.h1
-rw-r--r--lib/Format/WhitespaceManager.cpp10
13 files changed, 441 insertions, 82 deletions
diff --git a/lib/Format/BreakableToken.cpp b/lib/Format/BreakableToken.cpp
index fc2f891e0857e..e6ce01b520b5a 100644
--- a/lib/Format/BreakableToken.cpp
+++ b/lib/Format/BreakableToken.cpp
@@ -67,10 +67,11 @@ static BreakableToken::Split getCommentSplit(StringRef Text,
unsigned ContentStartColumn,
unsigned ColumnLimit,
unsigned TabWidth,
- encoding::Encoding Encoding) {
- LLVM_DEBUG(llvm::dbgs() << "Comment split: \"" << Text << ", " << ColumnLimit
- << "\", Content start: " << ContentStartColumn
- << "\n");
+ encoding::Encoding Encoding,
+ const FormatStyle &Style) {
+ LLVM_DEBUG(llvm::dbgs() << "Comment split: \"" << Text
+ << "\", Column limit: " << ColumnLimit
+ << ", Content start: " << ContentStartColumn << "\n");
if (ColumnLimit <= ContentStartColumn + 1)
return BreakableToken::Split(StringRef::npos, 0);
@@ -89,12 +90,21 @@ static BreakableToken::Split getCommentSplit(StringRef Text,
StringRef::size_type SpaceOffset = Text.find_last_of(Blanks, MaxSplitBytes);
- // Do not split before a number followed by a dot: this would be interpreted
- // as a numbered list, which would prevent re-flowing in subsequent passes.
static auto *const kNumberedListRegexp = new llvm::Regex("^[1-9][0-9]?\\.");
- if (SpaceOffset != StringRef::npos &&
- kNumberedListRegexp->match(Text.substr(SpaceOffset).ltrim(Blanks)))
- SpaceOffset = Text.find_last_of(Blanks, SpaceOffset);
+ while (SpaceOffset != StringRef::npos) {
+ // Do not split before a number followed by a dot: this would be interpreted
+ // as a numbered list, which would prevent re-flowing in subsequent passes.
+ if (kNumberedListRegexp->match(Text.substr(SpaceOffset).ltrim(Blanks)))
+ SpaceOffset = Text.find_last_of(Blanks, SpaceOffset);
+ // In JavaScript, some @tags can be followed by {, and machinery that parses
+ // these comments will fail to understand the comment if followed by a line
+ // break. So avoid ever breaking before a {.
+ else if (Style.Language == FormatStyle::LK_JavaScript &&
+ SpaceOffset + 1 < Text.size() && Text[SpaceOffset + 1] == '{')
+ SpaceOffset = Text.find_last_of(Blanks, SpaceOffset);
+ else
+ break;
+ }
if (SpaceOffset == StringRef::npos ||
// Don't break at leading whitespace.
@@ -109,6 +119,12 @@ static BreakableToken::Split getCommentSplit(StringRef Text,
Blanks, std::max<unsigned>(MaxSplitBytes, FirstNonWhitespace));
}
if (SpaceOffset != StringRef::npos && SpaceOffset != 0) {
+ // adaptStartOfLine will break after lines starting with /** if the comment
+ // is broken anywhere. Avoid emitting this break twice here.
+ // Example: in /** longtextcomesherethatbreaks */ (with ColumnLimit 20) will
+ // insert a break after /**, so this code must not insert the same break.
+ if (SpaceOffset == 1 && Text[SpaceOffset - 1] == '*')
+ return BreakableToken::Split(StringRef::npos, 0);
StringRef BeforeCut = Text.substr(0, SpaceOffset).rtrim(Blanks);
StringRef AfterCut = Text.substr(SpaceOffset).ltrim(Blanks);
return BreakableToken::Split(BeforeCut.size(),
@@ -260,7 +276,7 @@ BreakableComment::getSplit(unsigned LineIndex, unsigned TailOffset,
return Split(StringRef::npos, 0);
return getCommentSplit(Content[LineIndex].substr(TailOffset),
ContentStartColumn, ColumnLimit, Style.TabWidth,
- Encoding);
+ Encoding, Style);
}
void BreakableComment::compressWhitespace(
@@ -620,6 +636,8 @@ void BreakableBlockComment::adaptStartOfLine(
if (DelimitersOnNewline) {
// Since we're breaking at index 1 below, the break position and the
// break length are the same.
+ // Note: this works because getCommentSplit is careful never to split at
+ // the beginning of a line.
size_t BreakLength = Lines[0].substr(1).find_first_not_of(Blanks);
if (BreakLength != StringRef::npos)
insertBreak(LineIndex, 0, Split(1, BreakLength), /*ContentIndent=*/0,
diff --git a/lib/Format/ContinuationIndenter.cpp b/lib/Format/ContinuationIndenter.cpp
index 7ca588a675b5a..c369b94b99878 100644
--- a/lib/Format/ContinuationIndenter.cpp
+++ b/lib/Format/ContinuationIndenter.cpp
@@ -403,7 +403,9 @@ bool ContinuationIndenter::mustBreak(const LineState &State) {
// }.bind(...));
// FIXME: We should find a more generic solution to this problem.
!(State.Column <= NewLineColumn &&
- Style.Language == FormatStyle::LK_JavaScript))
+ Style.Language == FormatStyle::LK_JavaScript) &&
+ !(Previous.closesScopeAfterBlock() &&
+ State.Column <= NewLineColumn))
return true;
// If the template declaration spans multiple lines, force wrap before the
@@ -700,7 +702,8 @@ void ContinuationIndenter::addTokenOnCurrentLine(LineState &State, bool DryRun,
// Indent relative to the RHS of the expression unless this is a simple
// assignment without binary expression on the RHS. Also indent relative to
// unary operators and the colons of constructor initializers.
- State.Stack.back().LastSpace = State.Column;
+ if (Style.BreakBeforeBinaryOperators == FormatStyle::BOS_None)
+ State.Stack.back().LastSpace = State.Column;
} else if (Previous.is(TT_InheritanceColon)) {
State.Stack.back().Indent = State.Column;
State.Stack.back().LastSpace = State.Column;
@@ -1132,7 +1135,8 @@ unsigned ContinuationIndenter::moveStateToNextToken(LineState &State,
// }, a, b, c);
if (Current.isNot(tok::comment) && Previous &&
Previous->isOneOf(tok::l_brace, TT_ArrayInitializerLSquare) &&
- !Previous->is(TT_DictLiteral) && State.Stack.size() > 1) {
+ !Previous->is(TT_DictLiteral) && State.Stack.size() > 1 &&
+ !State.Stack.back().HasMultipleNestedBlocks) {
if (State.Stack[State.Stack.size() - 2].NestedBlockInlined && Newline)
for (unsigned i = 0, e = State.Stack.size() - 1; i != e; ++i)
State.Stack[i].NoLineBreak = true;
@@ -1499,10 +1503,25 @@ unsigned ContinuationIndenter::reformatRawStringLiteral(
// violate the rectangle rule and visually flows within the surrounding
// source.
bool ContentStartsOnNewline = Current.TokenText[OldPrefixSize] == '\n';
- unsigned NextStartColumn =
- ContentStartsOnNewline
- ? State.Stack.back().NestedBlockIndent + Style.IndentWidth
- : FirstStartColumn;
+ // If this token is the last parameter (checked by looking if it's followed by
+ // `)`, the base the indent off the line's nested block indent. Otherwise,
+ // base the indent off the arguments indent, so we can achieve:
+ // fffffffffff(1, 2, 3, R"pb(
+ // key1: 1 #
+ // key2: 2)pb");
+ //
+ // fffffffffff(1, 2, 3,
+ // R"pb(
+ // key1: 1 #
+ // key2: 2
+ // )pb",
+ // 5);
+ unsigned CurrentIndent = (Current.Next && Current.Next->is(tok::r_paren))
+ ? State.Stack.back().NestedBlockIndent
+ : State.Stack.back().Indent;
+ unsigned NextStartColumn = ContentStartsOnNewline
+ ? CurrentIndent + Style.IndentWidth
+ : FirstStartColumn;
// The last start column is the column the raw string suffix starts if it is
// put on a newline.
@@ -1514,7 +1533,7 @@ unsigned ContinuationIndenter::reformatRawStringLiteral(
// indent.
unsigned LastStartColumn = Current.NewlinesBefore
? FirstStartColumn - NewPrefixSize
- : State.Stack.back().NestedBlockIndent;
+ : CurrentIndent;
std::pair<tooling::Replacements, unsigned> Fixes = internal::reformat(
RawStringStyle, RawText, {tooling::Range(0, RawText.size())},
@@ -1524,8 +1543,7 @@ unsigned ContinuationIndenter::reformatRawStringLiteral(
auto NewCode = applyAllReplacements(RawText, Fixes.first);
tooling::Replacements NoFixes;
if (!NewCode) {
- State.Column += Current.ColumnWidth;
- return 0;
+ return addMultilineToken(Current, State);
}
if (!DryRun) {
if (NewDelimiter != OldDelimiter) {
@@ -1574,6 +1592,13 @@ unsigned ContinuationIndenter::reformatRawStringLiteral(
unsigned PrefixExcessCharacters =
StartColumn + NewPrefixSize > Style.ColumnLimit ?
StartColumn + NewPrefixSize - Style.ColumnLimit : 0;
+ bool IsMultiline =
+ ContentStartsOnNewline || (NewCode->find('\n') != std::string::npos);
+ if (IsMultiline) {
+ // Break before further function parameters on all levels.
+ for (unsigned i = 0, e = State.Stack.size(); i != e; ++i)
+ State.Stack[i].BreakBeforeParameter = true;
+ }
return Fixes.second + PrefixExcessCharacters * Style.PenaltyExcessCharacter;
}
@@ -1840,7 +1865,8 @@ ContinuationIndenter::breakProtrudingToken(const FormatToken &Current,
// No break opportunity - update the penalty and continue with the next
// logical line.
if (LineIndex < EndIndex - 1)
- // The last line's penalty is handled in addNextStateToQueue().
+ // The last line's penalty is handled in addNextStateToQueue() or when
+ // calling replaceWhitespaceAfterLastLine below.
Penalty += Style.PenaltyExcessCharacter *
(ContentStartColumn + RemainingTokenColumns - ColumnLimit);
LLVM_DEBUG(llvm::dbgs() << " No break opportunity.\n");
@@ -2095,6 +2121,12 @@ ContinuationIndenter::breakProtrudingToken(const FormatToken &Current,
Token->getSplitAfterLastLine(TailOffset);
if (SplitAfterLastLine.first != StringRef::npos) {
LLVM_DEBUG(llvm::dbgs() << "Replacing whitespace after last line.\n");
+
+ // We add the last line's penalty here, since that line is going to be split
+ // now.
+ Penalty += Style.PenaltyExcessCharacter *
+ (ContentStartColumn + RemainingTokenColumns - ColumnLimit);
+
if (!DryRun)
Token->replaceWhitespaceAfterLastLine(TailOffset, SplitAfterLastLine,
Whitespaces);
diff --git a/lib/Format/Format.cpp b/lib/Format/Format.cpp
index 9a2da69e89b1f..2c4f8760540a4 100644
--- a/lib/Format/Format.cpp
+++ b/lib/Format/Format.cpp
@@ -29,7 +29,6 @@
#include "clang/Basic/Diagnostic.h"
#include "clang/Basic/DiagnosticOptions.h"
#include "clang/Basic/SourceManager.h"
-#include "clang/Basic/VirtualFileSystem.h"
#include "clang/Lex/Lexer.h"
#include "clang/Tooling/Inclusions/HeaderIncludes.h"
#include "llvm/ADT/STLExtras.h"
@@ -38,6 +37,7 @@
#include "llvm/Support/Debug.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/Regex.h"
+#include "llvm/Support/VirtualFileSystem.h"
#include "llvm/Support/YAMLTraits.h"
#include <algorithm>
#include <memory>
@@ -414,6 +414,7 @@ template <> struct MappingTraits<FormatStyle> {
IO.mapOptional("IndentWidth", Style.IndentWidth);
IO.mapOptional("IndentWrappedFunctionNames",
Style.IndentWrappedFunctionNames);
+ IO.mapOptional("JavaImportGroups", Style.JavaImportGroups);
IO.mapOptional("JavaScriptQuotes", Style.JavaScriptQuotes);
IO.mapOptional("JavaScriptWrapImports", Style.JavaScriptWrapImports);
IO.mapOptional("KeepEmptyLinesAtTheStartOfBlocks",
@@ -469,6 +470,7 @@ template <> struct MappingTraits<FormatStyle> {
IO.mapOptional("SpacesInParentheses", Style.SpacesInParentheses);
IO.mapOptional("SpacesInSquareBrackets", Style.SpacesInSquareBrackets);
IO.mapOptional("Standard", Style.Standard);
+ IO.mapOptional("StatementMacros", Style.StatementMacros);
IO.mapOptional("TabWidth", Style.TabWidth);
IO.mapOptional("UseTab", Style.UseTab);
}
@@ -714,6 +716,8 @@ FormatStyle getLLVMStyle() {
LLVMStyle.DisableFormat = false;
LLVMStyle.SortIncludes = true;
LLVMStyle.SortUsingDeclarations = true;
+ LLVMStyle.StatementMacros.push_back("Q_UNUSED");
+ LLVMStyle.StatementMacros.push_back("QT_REQUIRE_VERSION");
return LLVMStyle;
}
@@ -819,7 +823,7 @@ FormatStyle getGoogleStyle(FormatStyle::LanguageKind Language) {
GoogleStyle.JavaScriptQuotes = FormatStyle::JSQS_Single;
GoogleStyle.JavaScriptWrapImports = false;
} else if (Language == FormatStyle::LK_Proto) {
- GoogleStyle.AllowShortFunctionsOnASingleLine = FormatStyle::SFS_None;
+ GoogleStyle.AllowShortFunctionsOnASingleLine = FormatStyle::SFS_Empty;
GoogleStyle.AlwaysBreakBeforeMultilineStrings = false;
GoogleStyle.SpacesInContainerLiterals = false;
GoogleStyle.Cpp11BracedListStyle = false;
@@ -844,6 +848,20 @@ FormatStyle getChromiumStyle(FormatStyle::LanguageKind Language) {
ChromiumStyle.BreakAfterJavaFieldAnnotations = true;
ChromiumStyle.ContinuationIndentWidth = 8;
ChromiumStyle.IndentWidth = 4;
+ // See styleguide for import groups:
+ // https://chromium.googlesource.com/chromium/src/+/master/styleguide/java/java.md#Import-Order
+ ChromiumStyle.JavaImportGroups = {
+ "android",
+ "com",
+ "dalvik",
+ "junit",
+ "org",
+ "com.google.android.apps.chrome",
+ "org.chromium",
+ "java",
+ "javax",
+ };
+ ChromiumStyle.SortIncludes = true;
} else if (Language == FormatStyle::LK_JavaScript) {
ChromiumStyle.AllowShortIfStatementsOnASingleLine = false;
ChromiumStyle.AllowShortLoopsOnASingleLine = false;
@@ -1309,8 +1327,7 @@ private:
std::set<unsigned> DeletedLines;
for (unsigned i = 0, e = AnnotatedLines.size(); i != e; ++i) {
auto &Line = *AnnotatedLines[i];
- if (Line.startsWith(tok::kw_namespace) ||
- Line.startsWith(tok::kw_inline, tok::kw_namespace)) {
+ if (Line.startsWithNamespace()) {
checkEmptyNamespace(AnnotatedLines, i, i, DeletedLines);
}
}
@@ -1347,9 +1364,7 @@ private:
if (AnnotatedLines[CurrentLine]->startsWith(tok::r_brace))
break;
- if (AnnotatedLines[CurrentLine]->startsWith(tok::kw_namespace) ||
- AnnotatedLines[CurrentLine]->startsWith(tok::kw_inline,
- tok::kw_namespace)) {
+ if (AnnotatedLines[CurrentLine]->startsWithNamespace()) {
if (!checkEmptyNamespace(AnnotatedLines, CurrentLine, NewLine,
DeletedLines))
return false;
@@ -1489,7 +1504,8 @@ public:
SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
FormatTokenLexer &Tokens) override {
assert(Style.Language == FormatStyle::LK_Cpp);
- IsObjC = guessIsObjC(AnnotatedLines, Tokens.getKeywords());
+ IsObjC = guessIsObjC(Env.getSourceManager(), AnnotatedLines,
+ Tokens.getKeywords());
tooling::Replacements Result;
return {Result, 0};
}
@@ -1497,8 +1513,10 @@ public:
bool isObjC() { return IsObjC; }
private:
- static bool guessIsObjC(const SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
- const AdditionalKeywords &Keywords) {
+ static bool
+ guessIsObjC(const SourceManager &SourceManager,
+ const SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
+ const AdditionalKeywords &Keywords) {
// Keep this array sorted, since we are binary searching over it.
static constexpr llvm::StringLiteral FoundationIdentifiers[] = {
"CGFloat",
@@ -1589,9 +1607,15 @@ private:
TT_ObjCBlockLBrace, TT_ObjCBlockLParen,
TT_ObjCDecl, TT_ObjCForIn, TT_ObjCMethodExpr,
TT_ObjCMethodSpecifier, TT_ObjCProperty)) {
+ LLVM_DEBUG(llvm::dbgs()
+ << "Detected ObjC at location "
+ << FormatTok->Tok.getLocation().printToString(
+ SourceManager)
+ << " token: " << FormatTok->TokenText << " token type: "
+ << getTokenTypeName(FormatTok->Type) << "\n");
return true;
}
- if (guessIsObjC(Line->Children, Keywords))
+ if (guessIsObjC(SourceManager, Line->Children, Keywords))
return true;
}
}
@@ -1608,6 +1632,14 @@ struct IncludeDirective {
int Category;
};
+struct JavaImportDirective {
+ StringRef Identifier;
+ StringRef Text;
+ unsigned Offset;
+ std::vector<StringRef> AssociatedCommentLines;
+ bool IsStatic;
+};
+
} // end anonymous namespace
// Determines whether 'Ranges' intersects with ('Start', 'End').
@@ -1726,7 +1758,7 @@ static void sortCppIncludes(const FormatStyle &Style,
namespace {
-const char IncludeRegexPattern[] =
+const char CppIncludeRegexPattern[] =
R"(^[\t\ ]*#[\t\ ]*(import|include)[^"<]*(["<][^">]*[">]))";
} // anonymous namespace
@@ -1738,7 +1770,7 @@ tooling::Replacements sortCppIncludes(const FormatStyle &Style, StringRef Code,
unsigned *Cursor) {
unsigned Prev = 0;
unsigned SearchFrom = 0;
- llvm::Regex IncludeRegex(IncludeRegexPattern);
+ llvm::Regex IncludeRegex(CppIncludeRegexPattern);
SmallVector<StringRef, 4> Matches;
SmallVector<IncludeDirective, 16> IncludesInBlock;
@@ -1797,6 +1829,149 @@ tooling::Replacements sortCppIncludes(const FormatStyle &Style, StringRef Code,
return Replaces;
}
+// Returns group number to use as a first order sort on imports. Gives UINT_MAX
+// if the import does not match any given groups.
+static unsigned findJavaImportGroup(const FormatStyle &Style,
+ StringRef ImportIdentifier) {
+ unsigned LongestMatchIndex = UINT_MAX;
+ unsigned LongestMatchLength = 0;
+ for (unsigned I = 0; I < Style.JavaImportGroups.size(); I++) {
+ std::string GroupPrefix = Style.JavaImportGroups[I];
+ if (ImportIdentifier.startswith(GroupPrefix) &&
+ GroupPrefix.length() > LongestMatchLength) {
+ LongestMatchIndex = I;
+ LongestMatchLength = GroupPrefix.length();
+ }
+ }
+ return LongestMatchIndex;
+}
+
+// Sorts and deduplicates a block of includes given by 'Imports' based on
+// JavaImportGroups, then adding the necessary replacement to 'Replaces'.
+// Import declarations with the same text will be deduplicated. Between each
+// import group, a newline is inserted, and within each import group, a
+// lexicographic sort based on ASCII value is performed.
+static void sortJavaImports(const FormatStyle &Style,
+ const SmallVectorImpl<JavaImportDirective> &Imports,
+ ArrayRef<tooling::Range> Ranges, StringRef FileName,
+ tooling::Replacements &Replaces) {
+ unsigned ImportsBeginOffset = Imports.front().Offset;
+ unsigned ImportsEndOffset =
+ Imports.back().Offset + Imports.back().Text.size();
+ unsigned ImportsBlockSize = ImportsEndOffset - ImportsBeginOffset;
+ if (!affectsRange(Ranges, ImportsBeginOffset, ImportsEndOffset))
+ return;
+ SmallVector<unsigned, 16> Indices;
+ SmallVector<unsigned, 16> JavaImportGroups;
+ for (unsigned i = 0, e = Imports.size(); i != e; ++i) {
+ Indices.push_back(i);
+ JavaImportGroups.push_back(
+ findJavaImportGroup(Style, Imports[i].Identifier));
+ }
+ llvm::sort(Indices.begin(), Indices.end(), [&](unsigned LHSI, unsigned RHSI) {
+ // Negating IsStatic to push static imports above non-static imports.
+ return std::make_tuple(!Imports[LHSI].IsStatic, JavaImportGroups[LHSI],
+ Imports[LHSI].Identifier) <
+ std::make_tuple(!Imports[RHSI].IsStatic, JavaImportGroups[RHSI],
+ Imports[RHSI].Identifier);
+ });
+
+ // Deduplicate imports.
+ Indices.erase(std::unique(Indices.begin(), Indices.end(),
+ [&](unsigned LHSI, unsigned RHSI) {
+ return Imports[LHSI].Text == Imports[RHSI].Text;
+ }),
+ Indices.end());
+
+ bool CurrentIsStatic = Imports[Indices.front()].IsStatic;
+ unsigned CurrentImportGroup = JavaImportGroups[Indices.front()];
+
+ std::string result;
+ for (unsigned Index : Indices) {
+ if (!result.empty()) {
+ result += "\n";
+ if (CurrentIsStatic != Imports[Index].IsStatic ||
+ CurrentImportGroup != JavaImportGroups[Index])
+ result += "\n";
+ }
+ for (StringRef CommentLine : Imports[Index].AssociatedCommentLines) {
+ result += CommentLine;
+ result += "\n";
+ }
+ result += Imports[Index].Text;
+ CurrentIsStatic = Imports[Index].IsStatic;
+ CurrentImportGroup = JavaImportGroups[Index];
+ }
+
+ auto Err = Replaces.add(tooling::Replacement(FileName, Imports.front().Offset,
+ ImportsBlockSize, result));
+ // FIXME: better error handling. For now, just skip the replacement for the
+ // release version.
+ if (Err) {
+ llvm::errs() << llvm::toString(std::move(Err)) << "\n";
+ assert(false);
+ }
+}
+
+namespace {
+
+const char JavaImportRegexPattern[] =
+ "^[\t ]*import[\t ]*(static[\t ]*)?([^\t ]*)[\t ]*;";
+
+} // anonymous namespace
+
+tooling::Replacements sortJavaImports(const FormatStyle &Style, StringRef Code,
+ ArrayRef<tooling::Range> Ranges,
+ StringRef FileName,
+ tooling::Replacements &Replaces) {
+ unsigned Prev = 0;
+ unsigned SearchFrom = 0;
+ llvm::Regex ImportRegex(JavaImportRegexPattern);
+ SmallVector<StringRef, 4> Matches;
+ SmallVector<JavaImportDirective, 16> ImportsInBlock;
+ std::vector<StringRef> AssociatedCommentLines;
+
+ bool FormattingOff = false;
+
+ for (;;) {
+ auto Pos = Code.find('\n', SearchFrom);
+ StringRef Line =
+ Code.substr(Prev, (Pos != StringRef::npos ? Pos : Code.size()) - Prev);
+
+ StringRef Trimmed = Line.trim();
+ if (Trimmed == "// clang-format off")
+ FormattingOff = true;
+ else if (Trimmed == "// clang-format on")
+ FormattingOff = false;
+
+ if (ImportRegex.match(Line, &Matches)) {
+ if (FormattingOff) {
+ // If at least one import line has formatting turned off, turn off
+ // formatting entirely.
+ return Replaces;
+ }
+ StringRef Static = Matches[1];
+ StringRef Identifier = Matches[2];
+ bool IsStatic = false;
+ if (Static.contains("static")) {
+ IsStatic = true;
+ }
+ ImportsInBlock.push_back({Identifier, Line, Prev, AssociatedCommentLines, IsStatic});
+ AssociatedCommentLines.clear();
+ } else if (Trimmed.size() > 0 && !ImportsInBlock.empty()) {
+ // Associating comments within the imports with the nearest import below
+ AssociatedCommentLines.push_back(Line);
+ }
+ Prev = Pos + 1;
+ if (Pos == StringRef::npos || Pos + 1 == Code.size())
+ break;
+ SearchFrom = Pos + 1;
+ }
+ if (!ImportsInBlock.empty())
+ sortJavaImports(Style, ImportsInBlock, Ranges, FileName, Replaces);
+ return Replaces;
+}
+
bool isMpegTS(StringRef Code) {
// MPEG transport streams use the ".ts" file extension. clang-format should
// not attempt to format those. MPEG TS' frame format starts with 0x47 every
@@ -1819,6 +1994,8 @@ tooling::Replacements sortIncludes(const FormatStyle &Style, StringRef Code,
return Replaces;
if (Style.Language == FormatStyle::LanguageKind::LK_JavaScript)
return sortJavaScriptImports(Style, Code, Ranges, FileName);
+ if (Style.Language == FormatStyle::LanguageKind::LK_Java)
+ return sortJavaImports(Style, Code, Ranges, FileName, Replaces);
sortCppIncludes(Style, Code, Ranges, FileName, Replaces, Cursor);
return Replaces;
}
@@ -1872,7 +2049,8 @@ namespace {
inline bool isHeaderInsertion(const tooling::Replacement &Replace) {
return Replace.getOffset() == UINT_MAX && Replace.getLength() == 0 &&
- llvm::Regex(IncludeRegexPattern).match(Replace.getReplacementText());
+ llvm::Regex(CppIncludeRegexPattern)
+ .match(Replace.getReplacementText());
}
inline bool isHeaderDeletion(const tooling::Replacement &Replace) {
@@ -1925,7 +2103,7 @@ fixCppIncludeInsertions(StringRef Code, const tooling::Replacements &Replaces,
}
}
- llvm::Regex IncludeRegex = llvm::Regex(IncludeRegexPattern);
+ llvm::Regex IncludeRegex = llvm::Regex(CppIncludeRegexPattern);
llvm::SmallVector<StringRef, 4> Matches;
for (const auto &R : HeaderInsertions) {
auto IncludeDirective = R.getReplacementText();
@@ -2095,8 +2273,7 @@ LangOptions getFormattingLangOpts(const FormatStyle &Style) {
bool AlternativeOperators = Style.isCpp();
LangOpts.CXXOperatorNames = AlternativeOperators ? 1 : 0;
LangOpts.Bool = 1;
- LangOpts.ObjC1 = 1;
- LangOpts.ObjC2 = 1;
+ LangOpts.ObjC = 1;
LangOpts.MicrosoftExt = 1; // To get kw___try, kw___finally.
LangOpts.DeclSpecKeyword = 1; // To get __declspec.
return LangOpts;
@@ -2157,9 +2334,10 @@ const char *DefaultFallbackStyle = "LLVM";
llvm::Expected<FormatStyle> getStyle(StringRef StyleName, StringRef FileName,
StringRef FallbackStyleName,
- StringRef Code, vfs::FileSystem *FS) {
+ StringRef Code,
+ llvm::vfs::FileSystem *FS) {
if (!FS) {
- FS = vfs::getRealFileSystem().get();
+ FS = llvm::vfs::getRealFileSystem().get();
}
FormatStyle Style = getLLVMStyle();
Style.Language = guessLanguage(FileName, Code);
diff --git a/lib/Format/FormatToken.h b/lib/Format/FormatToken.h
index 9094e7689e1de..10390c42911b8 100644
--- a/lib/Format/FormatToken.h
+++ b/lib/Format/FormatToken.h
@@ -86,6 +86,7 @@ namespace format {
TYPE(RegexLiteral) \
TYPE(SelectorName) \
TYPE(StartOfName) \
+ TYPE(StatementMacro) \
TYPE(StructuredBindingLSquare) \
TYPE(TemplateCloser) \
TYPE(TemplateOpener) \
@@ -188,10 +189,6 @@ struct FormatToken {
bool ClosesTemplateDeclaration = false;
/// Number of parameters, if this is "(", "[" or "<".
- ///
- /// This is initialized to 1 as we don't need to distinguish functions with
- /// 0 parameters from functions with 1 parameter. Thus, we can simply count
- /// the number of commas.
unsigned ParameterCount = 0;
/// Number of parameters that are nested blocks,
@@ -268,7 +265,7 @@ struct FormatToken {
/// \c true if this token ends a binary expression.
bool EndsBinaryExpression = false;
- /// Is this is an operator (or "."/"->") in a sequence of operators
+ /// If this is an operator (or "."/"->") in a sequence of operators
/// with the same precedence, contains the 0-based operator index.
unsigned OperatorIndex = 0;
@@ -325,6 +322,14 @@ struct FormatToken {
}
template <typename T> bool isNot(T Kind) const { return !is(Kind); }
+ bool closesScopeAfterBlock() const {
+ if (BlockKind == BK_Block)
+ return true;
+ if (closesScope())
+ return Previous->closesScopeAfterBlock();
+ return false;
+ }
+
/// \c true if this token starts a sequence with the given tokens in order,
/// following the ``Next`` pointers, ignoring comments.
template <typename A, typename... Ts>
@@ -520,8 +525,8 @@ struct FormatToken {
const FormatToken *NamespaceTok = this;
if (is(tok::comment))
NamespaceTok = NamespaceTok->getNextNonComment();
- // Detect "(inline)? namespace" in the beginning of a line.
- if (NamespaceTok && NamespaceTok->is(tok::kw_inline))
+ // Detect "(inline|export)? namespace" in the beginning of a line.
+ if (NamespaceTok && NamespaceTok->isOneOf(tok::kw_inline, tok::kw_export))
NamespaceTok = NamespaceTok->getNextNonComment();
return NamespaceTok && NamespaceTok->is(tok::kw_namespace) ? NamespaceTok
: nullptr;
@@ -594,6 +599,8 @@ public:
/// Notifies the \c Role that a comma was found.
virtual void CommaFound(const FormatToken *Token) {}
+ virtual const FormatToken *lastComma() { return nullptr; }
+
protected:
const FormatStyle &Style;
};
@@ -616,6 +623,12 @@ public:
Commas.push_back(Token);
}
+ const FormatToken *lastComma() override {
+ if (Commas.empty())
+ return nullptr;
+ return Commas.back();
+ }
+
private:
/// A struct that holds information on how to format a given list with
/// a specific number of columns.
@@ -672,6 +685,7 @@ struct AdditionalKeywords {
kw_function = &IdentTable.get("function");
kw_get = &IdentTable.get("get");
kw_import = &IdentTable.get("import");
+ kw_infer = &IdentTable.get("infer");
kw_is = &IdentTable.get("is");
kw_let = &IdentTable.get("let");
kw_module = &IdentTable.get("module");
@@ -743,6 +757,7 @@ struct AdditionalKeywords {
IdentifierInfo *kw_function;
IdentifierInfo *kw_get;
IdentifierInfo *kw_import;
+ IdentifierInfo *kw_infer;
IdentifierInfo *kw_is;
IdentifierInfo *kw_let;
IdentifierInfo *kw_module;
diff --git a/lib/Format/FormatTokenLexer.cpp b/lib/Format/FormatTokenLexer.cpp
index c7f720a443d35..146f5d68b559f 100644
--- a/lib/Format/FormatTokenLexer.cpp
+++ b/lib/Format/FormatTokenLexer.cpp
@@ -37,8 +37,9 @@ FormatTokenLexer::FormatTokenLexer(const SourceManager &SourceMgr, FileID ID,
Lex->SetKeepWhitespaceMode(true);
for (const std::string &ForEachMacro : Style.ForEachMacros)
- ForEachMacros.push_back(&IdentTable.get(ForEachMacro));
- llvm::sort(ForEachMacros.begin(), ForEachMacros.end());
+ Macros.insert({&IdentTable.get(ForEachMacro), TT_ForEachMacro});
+ for (const std::string &StatementMacro : Style.StatementMacros)
+ Macros.insert({&IdentTable.get(StatementMacro), TT_StatementMacro});
}
ArrayRef<FormatToken *> FormatTokenLexer::lex() {
@@ -657,12 +658,12 @@ FormatToken *FormatTokenLexer::getNextToken() {
}
if (Style.isCpp()) {
+ auto it = Macros.find(FormatTok->Tok.getIdentifierInfo());
if (!(Tokens.size() > 0 && Tokens.back()->Tok.getIdentifierInfo() &&
Tokens.back()->Tok.getIdentifierInfo()->getPPKeywordID() ==
tok::pp_define) &&
- std::find(ForEachMacros.begin(), ForEachMacros.end(),
- FormatTok->Tok.getIdentifierInfo()) != ForEachMacros.end()) {
- FormatTok->Type = TT_ForEachMacro;
+ it != Macros.end()) {
+ FormatTok->Type = it->second;
} else if (FormatTok->is(tok::identifier)) {
if (MacroBlockBeginRegex.match(Text)) {
FormatTok->Type = TT_MacroBlockBegin;
diff --git a/lib/Format/FormatTokenLexer.h b/lib/Format/FormatTokenLexer.h
index 3b79d27480e34..0cf357c85f3b1 100644
--- a/lib/Format/FormatTokenLexer.h
+++ b/lib/Format/FormatTokenLexer.h
@@ -22,6 +22,7 @@
#include "clang/Basic/SourceManager.h"
#include "clang/Format/Format.h"
#include "llvm/Support/Regex.h"
+#include "llvm/ADT/MapVector.h"
#include <stack>
@@ -99,7 +100,8 @@ private:
// Index (in 'Tokens') of the last token that starts a new line.
unsigned FirstInLineIndex;
SmallVector<FormatToken *, 16> Tokens;
- SmallVector<IdentifierInfo *, 8> ForEachMacros;
+
+ llvm::SmallMapVector<IdentifierInfo *, TokenType, 8> Macros;
bool FormattingDisabled;
diff --git a/lib/Format/NamespaceEndCommentsFixer.cpp b/lib/Format/NamespaceEndCommentsFixer.cpp
index 995b3219a1f4a..dd364866d1ceb 100644
--- a/lib/Format/NamespaceEndCommentsFixer.cpp
+++ b/lib/Format/NamespaceEndCommentsFixer.cpp
@@ -125,12 +125,7 @@ getNamespaceToken(const AnnotatedLine *Line,
if (StartLineIndex > 0)
NamespaceTok = AnnotatedLines[StartLineIndex - 1]->First;
}
- // Detect "(inline)? namespace" in the beginning of a line.
- if (NamespaceTok->is(tok::kw_inline))
- NamespaceTok = NamespaceTok->getNextNonComment();
- if (!NamespaceTok || NamespaceTok->isNot(tok::kw_namespace))
- return nullptr;
- return NamespaceTok;
+ return NamespaceTok->getNamespaceToken();
}
NamespaceEndCommentsFixer::NamespaceEndCommentsFixer(const Environment &Env,
diff --git a/lib/Format/TokenAnnotator.cpp b/lib/Format/TokenAnnotator.cpp
index 3a19215e18037..24c2f998c388a 100644
--- a/lib/Format/TokenAnnotator.cpp
+++ b/lib/Format/TokenAnnotator.cpp
@@ -366,7 +366,8 @@ 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))
return true;
@@ -398,9 +399,11 @@ private:
bool IsCpp11AttributeSpecifier = isCpp11AttributeSpecifier(*Left) ||
Contexts.back().InCpp11AttributeSpecifier;
+ bool InsideInlineASM = Line.startsWith(tok::kw_asm);
bool StartsObjCMethodExpr =
- !CppArrayTemplates && Style.isCpp() && !IsCpp11AttributeSpecifier &&
- Contexts.back().CanBeExpression && Left->isNot(TT_LambdaLSquare) &&
+ !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,
@@ -1120,6 +1123,7 @@ private:
(Tok.Next->Next->TokenText == "module" ||
Tok.Next->Next->TokenText == "provide" ||
Tok.Next->Next->TokenText == "require" ||
+ Tok.Next->Next->TokenText == "requireType" ||
Tok.Next->Next->TokenText == "forwardDeclare") &&
Tok.Next->Next->Next && Tok.Next->Next->Next->is(tok::l_paren);
}
@@ -2517,7 +2521,9 @@ bool TokenAnnotator::spaceRequiredBetween(const AnnotatedLine &Line,
Right.MatchingParen->BlockKind != BK_Block))
return !Style.Cpp11BracedListStyle;
if (Left.is(TT_BlockComment))
- return !Left.TokenText.endswith("=*/");
+ // No whitespace in x(/*foo=*/1), except for JavaScript.
+ return Style.Language == FormatStyle::LK_JavaScript ||
+ !Left.TokenText.endswith("=*/");
if (Right.is(tok::l_paren)) {
if ((Left.is(tok::r_paren) && Left.is(TT_AttributeParen)) ||
(Left.is(tok::r_square) && Left.is(TT_AttributeSquare)))
@@ -2553,8 +2559,11 @@ bool TokenAnnotator::spaceRequiredBetween(const AnnotatedLine &Line,
return false;
if (Left.is(TT_TemplateCloser) && Left.MatchingParen &&
Left.MatchingParen->Previous &&
- Left.MatchingParen->Previous->is(tok::period))
+ (Left.MatchingParen->Previous->is(tok::period) ||
+ Left.MatchingParen->Previous->is(tok::coloncolon)))
+ // Java call to generic function with explicit type:
// A.<B<C<...>>>DoSomething();
+ // A::<B<C<...>>>DoSomething(); // With a Java 8 method reference.
return false;
if (Left.is(TT_TemplateCloser) && Right.is(tok::l_square))
return false;
@@ -2774,6 +2783,9 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
if (!Style.SpaceBeforeAssignmentOperators &&
Right.getPrecedence() == prec::Assignment)
return false;
+ if (Style.Language == FormatStyle::LK_Java && Right.is(tok::coloncolon) &&
+ (Left.is(tok::identifier) || Left.is(tok::kw_this)))
+ return false;
if (Right.is(tok::coloncolon) && Left.is(tok::identifier))
// Generally don't remove existing spaces between an identifier and "::".
// The identifier might actually be a macro name such as ALWAYS_INLINE. If
@@ -2866,6 +2878,7 @@ bool TokenAnnotator::mustBreakBefore(const AnnotatedLine &Line,
} else if (Style.Language == FormatStyle::LK_Cpp ||
Style.Language == FormatStyle::LK_ObjC ||
Style.Language == FormatStyle::LK_Proto ||
+ Style.Language == FormatStyle::LK_TableGen ||
Style.Language == FormatStyle::LK_TextProto) {
if (Left.isStringLiteral() && Right.isStringLiteral())
return true;
@@ -3041,6 +3054,30 @@ bool TokenAnnotator::mustBreakBefore(const AnnotatedLine &Line,
return true;
}
+ // Deal with lambda arguments in C++ - we want consistent line breaks whether
+ // they happen to be at arg0, arg1 or argN. The selection is a bit nuanced
+ // as aggressive line breaks are placed when the lambda is not the last arg.
+ if ((Style.Language == FormatStyle::LK_Cpp ||
+ Style.Language == FormatStyle::LK_ObjC) &&
+ Left.is(tok::l_paren) && Left.BlockParameterCount > 0 &&
+ !Right.isOneOf(tok::l_paren, TT_LambdaLSquare)) {
+ // Multiple lambdas in the same function call force line breaks.
+ if (Left.BlockParameterCount > 1)
+ return true;
+
+ // A lambda followed by another arg forces a line break.
+ if (!Left.Role)
+ return false;
+ auto Comma = Left.Role->lastComma();
+ if (!Comma)
+ return false;
+ auto Next = Comma->getNextNonComment();
+ if (!Next)
+ return false;
+ if (!Next->isOneOf(TT_LambdaLSquare, tok::l_brace, tok::caret))
+ return true;
+ }
+
return false;
}
@@ -3078,14 +3115,33 @@ bool TokenAnnotator::canBreakBefore(const AnnotatedLine &Line,
// Don't wrap between ":" and "!" of a strict prop init ("field!: type;").
if (Left.is(tok::exclaim) && Right.is(tok::colon))
return false;
- if (Right.is(Keywords.kw_is))
- return false;
+ // Look for is type annotations like:
+ // function f(): a is B { ... }
+ // Do not break before is in these cases.
+ if (Right.is(Keywords.kw_is)) {
+ 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:
+ // Polymer({
+ // is: 'name',
+ // ...
+ // });
+ if (!Next || !Next->is(tok::colon))
+ return false;
+ }
if (Left.is(Keywords.kw_in))
return Style.BreakBeforeBinaryOperators == FormatStyle::BOS_None;
if (Right.is(Keywords.kw_in))
return Style.BreakBeforeBinaryOperators != FormatStyle::BOS_None;
if (Right.is(Keywords.kw_as))
return false; // must not break before as in 'x as type' casts
+ if (Right.isOneOf(Keywords.kw_extends, Keywords.kw_infer)) {
+ // extends and infer can appear as keywords in conditional types:
+ // https://www.typescriptlang.org/docs/handbook/release-notes/typescript-2-8.html#conditional-types
+ // do not break before them, as the expressions are subject to ASI.
+ return false;
+ }
if (Left.is(Keywords.kw_as))
return true;
if (Left.is(TT_JsNonNullAssertion))
diff --git a/lib/Format/TokenAnnotator.h b/lib/Format/TokenAnnotator.h
index a3124fcb3d65b..e2f2c469d2675 100644
--- a/lib/Format/TokenAnnotator.h
+++ b/lib/Format/TokenAnnotator.h
@@ -105,6 +105,13 @@ public:
return !Last->isOneOf(tok::semi, tok::comment);
}
+ /// \c true if this line starts a namespace definition.
+ bool startsWithNamespace() const {
+ return startsWith(tok::kw_namespace) ||
+ startsWith(tok::kw_inline, tok::kw_namespace) ||
+ startsWith(tok::kw_export, tok::kw_namespace);
+ }
+
FormatToken *First;
FormatToken *Last;
diff --git a/lib/Format/UnwrappedLineFormatter.cpp b/lib/Format/UnwrappedLineFormatter.cpp
index 906dae40cbee7..6b6a9aff461ab 100644
--- a/lib/Format/UnwrappedLineFormatter.cpp
+++ b/lib/Format/UnwrappedLineFormatter.cpp
@@ -323,6 +323,10 @@ private:
kwId == clang::tok::objc_synchronized)
return 0;
}
+ // Don't merge block with left brace wrapped after case labels
+ if (TheLine->First->is(tok::l_brace) && I != AnnotatedLines.begin() &&
+ I[-1]->First->isOneOf(tok::kw_case, tok::kw_default))
+ return 0;
// Try to merge a block with left brace wrapped that wasn't yet covered
if (TheLine->Last->is(tok::l_brace)) {
return !Style.BraceWrapping.AfterFunction ||
@@ -424,6 +428,8 @@ private:
if (Limit == 0 || I + 1 == E ||
I[1]->First->isOneOf(tok::kw_case, tok::kw_default))
return 0;
+ if (I[0]->Last->is(tok::l_brace) || I[1]->First->is(tok::l_brace))
+ return 0;
unsigned NumStmts = 0;
unsigned Length = 0;
bool EndsWithComment = false;
@@ -483,6 +489,12 @@ private:
if (Line.First->isOneOf(tok::kw_else, tok::kw_case) ||
(Line.First->Next && Line.First->Next->is(tok::kw_else)))
return 0;
+ // default: in switch statement
+ if (Line.First->is(tok::kw_default)) {
+ const FormatToken *Tok = Line.First->getNextNonComment();
+ if (Tok && Tok->is(tok::colon))
+ return 0;
+ }
if (Line.First->isOneOf(tok::kw_if, tok::kw_while, tok::kw_do, tok::kw_try,
tok::kw___try, tok::kw_catch, tok::kw___finally,
tok::kw_for, tok::r_brace, Keywords.kw___except)) {
@@ -529,7 +541,7 @@ private:
Tok->SpacesRequiredBefore = 0;
Tok->CanBreakBefore = true;
return 1;
- } else if (Limit != 0 && !Line.startsWith(tok::kw_namespace) &&
+ } else if (Limit != 0 && !Line.startsWithNamespace() &&
!startsExternCBlock(Line)) {
// We don't merge short records.
FormatToken *RecordTok = Line.First;
@@ -976,8 +988,7 @@ private:
Path.push_front(Best);
Best = Best->Previous;
}
- for (std::deque<StateNode *>::iterator I = Path.begin(), E = Path.end();
- I != E; ++I) {
+ for (auto I = Path.begin(), E = Path.end(); I != E; ++I) {
unsigned Penalty = 0;
formatChildren(State, (*I)->NewLine, /*DryRun=*/false, Penalty);
Penalty += Indenter->addTokenToState(State, (*I)->NewLine, false);
@@ -986,8 +997,8 @@ private:
printLineState((*I)->Previous->State);
if ((*I)->NewLine) {
llvm::dbgs() << "Penalty for placing "
- << (*I)->Previous->State.NextToken->Tok.getName() << ": "
- << Penalty << "\n";
+ << (*I)->Previous->State.NextToken->Tok.getName()
+ << " on a new line: " << Penalty << "\n";
}
});
}
@@ -1154,7 +1165,7 @@ void UnwrappedLineFormatter::formatFirstToken(
// Remove empty lines after "{".
if (!Style.KeepEmptyLinesAtTheStartOfBlocks && PreviousLine &&
PreviousLine->Last->is(tok::l_brace) &&
- PreviousLine->First->isNot(tok::kw_namespace) &&
+ !PreviousLine->startsWithNamespace() &&
!startsExternCBlock(*PreviousLine))
Newlines = 1;
diff --git a/lib/Format/UnwrappedLineParser.cpp b/lib/Format/UnwrappedLineParser.cpp
index e5afa1264abb5..3cd3c8f9cdf69 100644
--- a/lib/Format/UnwrappedLineParser.cpp
+++ b/lib/Format/UnwrappedLineParser.cpp
@@ -350,7 +350,10 @@ void UnwrappedLineParser::parseLevel(bool HasOpeningBrace) {
break;
case tok::kw_default: {
unsigned StoredPosition = Tokens->getPosition();
- FormatToken *Next = Tokens->getNextToken();
+ 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
@@ -477,6 +480,10 @@ void UnwrappedLineParser::calculateBraceTypes(bool ExpectClassBody) {
}
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:
@@ -989,13 +996,6 @@ void UnwrappedLineParser::parseStructuralElement() {
case tok::kw_namespace:
parseNamespace();
return;
- case tok::kw_inline:
- nextToken();
- if (FormatTok->Tok.is(tok::kw_namespace)) {
- parseNamespace();
- return;
- }
- break;
case tok::kw_public:
case tok::kw_protected:
case tok::kw_private:
@@ -1063,6 +1063,16 @@ void UnwrappedLineParser::parseStructuralElement() {
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)) {
@@ -1102,6 +1112,10 @@ void UnwrappedLineParser::parseStructuralElement() {
return;
}
}
+ if (Style.isCpp() && FormatTok->is(TT_StatementMacro)) {
+ parseStatementMacro();
+ return;
+ }
// In all other cases, parse the declaration.
break;
default:
@@ -1116,6 +1130,10 @@ void UnwrappedLineParser::parseStructuralElement() {
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:
@@ -1260,6 +1278,8 @@ void UnwrappedLineParser::parseStructuralElement() {
break;
case tok::kw_try:
// We arrive here when parsing function-try blocks.
+ if (Style.BraceWrapping.AfterFunction)
+ addUnwrappedLine();
parseTryCatch();
return;
case tok::identifier: {
@@ -1301,6 +1321,11 @@ void UnwrappedLineParser::parseStructuralElement() {
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();
@@ -2143,6 +2168,8 @@ void UnwrappedLineParser::parseObjCMethod() {
addUnwrappedLine();
return;
} else if (FormatTok->Tok.is(tok::l_brace)) {
+ if (Style.BraceWrapping.AfterFunction)
+ addUnwrappedLine();
parseBlock(/*MustBeDeclaration=*/false);
addUnwrappedLine();
return;
@@ -2320,6 +2347,16 @@ void UnwrappedLineParser::parseJavaScriptEs6ImportExport() {
}
}
+void UnwrappedLineParser::parseStatementMacro()
+{
+ nextToken();
+ if (FormatTok->is(tok::l_paren))
+ parseParens();
+ if (FormatTok->is(tok::semi))
+ nextToken();
+ addUnwrappedLine();
+}
+
LLVM_ATTRIBUTE_UNUSED static void printDebugInfo(const UnwrappedLine &Line,
StringRef Prefix = "") {
llvm::dbgs() << Prefix << "Line(" << Line.Level
diff --git a/lib/Format/UnwrappedLineParser.h b/lib/Format/UnwrappedLineParser.h
index 87254832c635e..55d60dff91523 100644
--- a/lib/Format/UnwrappedLineParser.h
+++ b/lib/Format/UnwrappedLineParser.h
@@ -126,6 +126,7 @@ private:
void parseObjCInterfaceOrImplementation();
bool parseObjCProtocol();
void parseJavaScriptEs6ImportExport();
+ void parseStatementMacro();
bool tryToParseLambda();
bool tryToParseLambdaIntroducer();
void tryToParseJSFunction();
diff --git a/lib/Format/WhitespaceManager.cpp b/lib/Format/WhitespaceManager.cpp
index 7070ce03c864e..032b1333322d1 100644
--- a/lib/Format/WhitespaceManager.cpp
+++ b/lib/Format/WhitespaceManager.cpp
@@ -90,7 +90,7 @@ const tooling::Replacements &WhitespaceManager::generateReplacements() {
if (Changes.empty())
return Replaces;
- llvm::sort(Changes.begin(), Changes.end(), Change::IsBeforeInFile(SourceMgr));
+ llvm::sort(Changes, Change::IsBeforeInFile(SourceMgr));
calculateLineBreakInformation();
alignConsecutiveDeclarations();
alignConsecutiveAssignments();
@@ -255,8 +255,14 @@ AlignTokenSequence(unsigned Start, unsigned End, unsigned Column, F &&Matches,
Changes[ScopeStack.back()].indentAndNestingLevel())
ScopeStack.pop_back();
+ // Compare current token to previous non-comment token to ensure whether
+ // it is in a deeper scope or not.
+ unsigned PreviousNonComment = i - 1;
+ while (PreviousNonComment > Start &&
+ Changes[PreviousNonComment].Tok->is(tok::comment))
+ PreviousNonComment--;
if (i != Start && Changes[i].indentAndNestingLevel() >
- Changes[i - 1].indentAndNestingLevel())
+ Changes[PreviousNonComment].indentAndNestingLevel())
ScopeStack.push_back(i);
bool InsideNestedScope = ScopeStack.size() != 0;