ioeric updated this revision to Diff 54476.
ioeric added a comment.
- Added comments for endsWithInternal().
http://reviews.llvm.org/D18551
Files:
include/clang/Format/Format.h
lib/Format/AffectedRangeManager.cpp
lib/Format/AffectedRangeManager.h
lib/Format/CMakeLists.txt
lib/Format/Format.cpp
lib/Format/TokenAnnotator.h
unittests/Format/CMakeLists.txt
unittests/Format/CleanupTest.cpp
unittests/Format/FormatTest.cpp
Index: unittests/Format/FormatTest.cpp
===================================================================
--- unittests/Format/FormatTest.cpp
+++ unittests/Format/FormatTest.cpp
@@ -11526,6 +11526,35 @@
Code, formatReplacements(Code, Replaces, Style)));
}
+TEST_F(ReplacementTest, FixOnlyAffectedCodeAfterReplacements) {
+ std::string Code = "namespace A {\n"
+ "namespace B {\n"
+ " int x;\n"
+ "} // namespace B\n"
+ "} // namespace A\n"
+ "\n"
+ "namespace C {\n"
+ "namespace D { int i; }\n"
+ "inline namespace E { namespace { int y; } }\n"
+ "int x= 0;"
+ "}";
+ std::string Expected = "\n\nnamespace C {\n"
+ "namespace D { int i; }\n\n"
+ "int x= 0;"
+ "}";
+ FileID ID = Context.createInMemoryFile("fix.cpp", Code);
+ tooling::Replacements Replaces;
+ Replaces.insert(tooling::Replacement(
+ Context.Sources, Context.getLocation(ID, 3, 3), 6, ""));
+ Replaces.insert(tooling::Replacement(
+ Context.Sources, Context.getLocation(ID, 9, 34), 6, ""));
+
+ format::FormatStyle Style = format::getLLVMStyle();
+ auto FinalReplaces = formatReplacements(
+ Code, cleanupAroundReplacements(Code, Replaces, Style), Style);
+ EXPECT_EQ(Expected, applyAllReplacements(Code, FinalReplaces));
+}
+
} // end namespace
} // end namespace format
} // end namespace clang
Index: unittests/Format/CleanupTest.cpp
===================================================================
--- /dev/null
+++ unittests/Format/CleanupTest.cpp
@@ -0,0 +1,118 @@
+//===- unittest/Format/CleanupTest.cpp - Code cleanup unit tests ----------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "clang/Format/Format.h"
+
+#include "clang/Tooling/Core/Replacement.h"
+
+#include "gtest/gtest.h"
+
+namespace clang {
+namespace format {
+namespace {
+
+class CleanupTest : public ::testing::Test {
+protected:
+ std::string cleanup(llvm::StringRef Code,
+ const std::vector<tooling::Range> &Ranges,
+ const FormatStyle &Style = getLLVMStyle()) {
+ tooling::Replacements Replaces = format::cleanup(Style, Code, Ranges);
+
+ std::string Result = applyAllReplacements(Code, Replaces);
+ EXPECT_NE("", Result);
+ return Result;
+ }
+};
+
+TEST_F(CleanupTest, DeleteEmptyNamespaces) {
+ std::string Code = "namespace A {\n"
+ "namespace B {\n"
+ "} // namespace B\n"
+ "} // namespace A\n\n"
+ "namespace C {\n"
+ "namespace D { int i; }\n"
+ "inline namespace E { namespace { } }\n"
+ "}";
+ std::string Expected = "\n\n\n\n\nnamespace C {\n"
+ "namespace D { int i; }\n \n"
+ "}";
+ std::vector<tooling::Range> Ranges;
+ Ranges.push_back(tooling::Range(28, 0));
+ Ranges.push_back(tooling::Range(91, 6));
+ Ranges.push_back(tooling::Range(132, 0));
+ std::string Result = cleanup(Code, Ranges);
+ EXPECT_EQ(Expected, Result);
+}
+
+TEST_F(CleanupTest, NamespaceWithSyntaxError) {
+ std::string Code = "namespace A {\n"
+ "namespace B {\n" // missing r_brace
+ "} // namespace A\n\n"
+ "namespace C {\n"
+ "namespace D int i; }\n"
+ "inline namespace E { namespace { } }\n"
+ "}";
+ std::string Expected = "namespace A {\n"
+ "\n\n\nnamespace C {\n"
+ "namespace D int i; }\n \n"
+ "}";
+ std::vector<tooling::Range> Ranges(1, tooling::Range(0, Code.size()));
+ std::string Result = cleanup(Code, Ranges);
+ EXPECT_EQ(Expected, Result);
+}
+
+TEST_F(CleanupTest, EmptyNamespaceNotAffected) {
+ std::string Code = "namespace A {\n\n"
+ "namespace {\n\n}}";
+ // Even though the namespaces are empty, but the inner most empty namespace
+ // block is not affected by the changed ranges.
+ std::string Expected = "namespace A {\n\n"
+ "namespace {\n\n}}";
+ // Set the changed range to be the second "\n".
+ std::vector<tooling::Range> Ranges(1, tooling::Range(14, 0));
+ std::string Result = cleanup(Code, Ranges);
+ EXPECT_EQ(Expected, Result);
+}
+
+TEST_F(CleanupTest, EmptyNamespaceWithCommentsNoBreakBeforeBrace) {
+ std::string Code = "namespace A {\n"
+ "namespace B {\n"
+ "// Yo\n"
+ "} // namespace B\n"
+ "} // namespace A\n"
+ "namespace C { // Yo\n"
+ "}";
+ std::string Expected = "\n\n\n\n\n\n";
+ std::vector<tooling::Range> Ranges(1, tooling::Range(0, Code.size()));
+ std::string Result = cleanup(Code, Ranges);
+ EXPECT_EQ(Expected, Result);
+}
+
+TEST_F(CleanupTest, EmptyNamespaceWithCommentsBreakBeforeBrace) {
+ std::string Code = "namespace A\n"
+ "/* Yo */ {\n"
+ "namespace B\n"
+ "{\n"
+ "// Yo\n"
+ "} // namespace B\n"
+ "} // namespace A\n"
+ "namespace C\n"
+ "{ // Yo\n"
+ "}\n";
+ std::string Expected = "\n\n\n\n\n\n\n\n\n\n";
+ std::vector<tooling::Range> Ranges(1, tooling::Range(0, Code.size()));
+ FormatStyle Style = getLLVMStyle();
+ Style.BraceWrapping.AfterNamespace = true;
+ std::string Result = cleanup(Code, Ranges, Style);
+ EXPECT_EQ(Expected, Result);
+}
+
+} // end namespace
+} // end namespace format
+} // end namespace clang
Index: unittests/Format/CMakeLists.txt
===================================================================
--- unittests/Format/CMakeLists.txt
+++ unittests/Format/CMakeLists.txt
@@ -3,6 +3,7 @@
)
add_clang_unittest(FormatTests
+ CleanupTest.cpp
FormatTest.cpp
FormatTestJava.cpp
FormatTestJS.cpp
Index: lib/Format/TokenAnnotator.h
===================================================================
--- lib/Format/TokenAnnotator.h
+++ lib/Format/TokenAnnotator.h
@@ -86,6 +86,14 @@
return startsWithInternal(First, Tokens...);
}
+ /// \c true if this line ends with the given tokens in reversed order,
+ /// ignoring comments.
+ /// For example, given tokens [T1, T2, T3, ...], the function returns true if
+ /// this line is like "... T3 T2 T1".
+ template <typename... Ts> bool endsWith(Ts... Tokens) const {
+ return endsWithInternal(Last, Tokens...);
+ }
+
/// \c true if this line looks like a function definition instead of a
/// function declaration. Asserts MightBeFunctionDecl.
bool mightBeFunctionDefinition() const {
@@ -143,6 +151,23 @@
return Tok && startsWithInternal(Tok, K1) &&
startsWithInternal(Tok->Next, Tokens...);
}
+
+ template <typename A, typename... Ts>
+ bool endsWithInternal(const FormatToken *Tok, A K1) const {
+ // See the comments above in `startsWithInternal(Tok, K1)`.
+ while (Tok && Tok->is(tok::comment))
+ Tok = Tok->Previous;
+ return Tok && Tok->is(K1);
+ }
+
+ template <typename A, typename... Ts>
+ bool endsWithInternal(const FormatToken *Tok, A K1, Ts... Tokens) const {
+ // See the comments above in `startsWithInternal(Tok, K1, Tokens)`.
+ while (Tok && Tok->is(tok::comment))
+ Tok = Tok->Previous;
+ return Tok && endsWithInternal(Tok, K1) &&
+ endsWithInternal(Tok->Previous, Tokens...);
+ }
};
/// \brief Determines extra information about the tokens comprising an
Index: lib/Format/Format.cpp
===================================================================
--- lib/Format/Format.cpp
+++ lib/Format/Format.cpp
@@ -14,6 +14,7 @@
//===----------------------------------------------------------------------===//
#include "clang/Format/Format.h"
+#include "AffectedRangeManager.h"
#include "ContinuationIndenter.h"
#include "TokenAnnotator.h"
#include "UnwrappedLineFormatter.h"
@@ -782,8 +783,8 @@
class FormatTokenLexer {
public:
- FormatTokenLexer(SourceManager &SourceMgr, FileID ID, FormatStyle &Style,
- encoding::Encoding Encoding)
+ FormatTokenLexer(SourceManager &SourceMgr, FileID ID,
+ const FormatStyle &Style, encoding::Encoding Encoding)
: FormatTok(nullptr), IsFirstToken(true), GreaterStashed(false),
LessStashed(false), Column(0), TrailingWhitespace(0),
SourceMgr(SourceMgr), ID(ID), Style(Style),
@@ -1350,7 +1351,8 @@
Tokens.back()->Tok.getIdentifierInfo()->getPPKeywordID() ==
tok::pp_define) &&
std::find(ForEachMacros.begin(), ForEachMacros.end(),
- FormatTok->Tok.getIdentifierInfo()) != ForEachMacros.end()) {
+ FormatTok->Tok.getIdentifierInfo()) !=
+ ForEachMacros.end()) {
FormatTok->Type = TT_ForEachMacro;
} else if (FormatTok->is(tok::identifier)) {
if (MacroBlockBeginRegex.match(Text)) {
@@ -1372,7 +1374,7 @@
std::unique_ptr<Lexer> Lex;
SourceManager &SourceMgr;
FileID ID;
- FormatStyle &Style;
+ const FormatStyle &Style;
IdentifierTable IdentTable;
AdditionalKeywords Keywords;
encoding::Encoding Encoding;
@@ -1446,14 +1448,14 @@
}
}
-class Formatter : public UnwrappedLineConsumer {
+class TokenAnalyzer : public UnwrappedLineConsumer {
public:
- Formatter(const FormatStyle &Style, SourceManager &SourceMgr, FileID ID,
- ArrayRef<CharSourceRange> Ranges)
+ TokenAnalyzer(const FormatStyle &Style, SourceManager &SourceMgr, FileID ID,
+ ArrayRef<CharSourceRange> Ranges)
: Style(Style), ID(ID), SourceMgr(SourceMgr),
- Whitespaces(SourceMgr, Style,
- inputUsesCRLF(SourceMgr.getBufferData(ID))),
- Ranges(Ranges.begin(), Ranges.end()), UnwrappedLines(1),
+ AffectedRangeMgr(SourceMgr, SmallVector<CharSourceRange, 8>(
+ Ranges.begin(), Ranges.end())),
+ UnwrappedLines(1),
Encoding(encoding::detectEncoding(SourceMgr.getBufferData(ID))) {
DEBUG(llvm::dbgs() << "File encoding: "
<< (Encoding == encoding::Encoding_UTF8 ? "UTF8"
@@ -1463,7 +1465,7 @@
<< "\n");
}
- tooling::Replacements format(bool *IncompleteFormat) {
+ tooling::Replacements process(bool *IncompleteFormat) {
tooling::Replacements Result;
FormatTokenLexer Tokens(SourceMgr, ID, Style, Encoding);
@@ -1475,11 +1477,16 @@
++Run) {
DEBUG(llvm::dbgs() << "Run " << Run << "...\n");
SmallVector<AnnotatedLine *, 16> AnnotatedLines;
+
+ TokenAnnotator Annotator(Style, Tokens.getKeywords());
for (unsigned i = 0, e = UnwrappedLines[Run].size(); i != e; ++i) {
AnnotatedLines.push_back(new AnnotatedLine(UnwrappedLines[Run][i]));
+ Annotator.annotate(*AnnotatedLines.back());
}
+
tooling::Replacements RunResult =
- format(AnnotatedLines, Tokens, Result, IncompleteFormat);
+ analyze(Annotator, AnnotatedLines, Tokens, Result, IncompleteFormat);
+
DEBUG({
llvm::dbgs() << "Replacements for run " << Run << ":\n";
for (tooling::Replacements::iterator I = RunResult.begin(),
@@ -1492,21 +1499,51 @@
delete AnnotatedLines[i];
}
Result.insert(RunResult.begin(), RunResult.end());
- Whitespaces.reset();
}
return Result;
}
- tooling::Replacements format(SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
- FormatTokenLexer &Tokens,
- tooling::Replacements &Result,
- bool *IncompleteFormat) {
- TokenAnnotator Annotator(Style, Tokens.getKeywords());
- for (unsigned i = 0, e = AnnotatedLines.size(); i != e; ++i) {
- Annotator.annotate(*AnnotatedLines[i]);
- }
+protected:
+ virtual tooling::Replacements
+ analyze(TokenAnnotator &Annotator,
+ SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
+ FormatTokenLexer &Tokens, tooling::Replacements &Result,
+ bool *IncompleteFormat) = 0;
+
+ void consumeUnwrappedLine(const UnwrappedLine &TheLine) override {
+ assert(!UnwrappedLines.empty());
+ UnwrappedLines.back().push_back(TheLine);
+ }
+
+ void finishRun() override {
+ UnwrappedLines.push_back(SmallVector<UnwrappedLine, 16>());
+ }
+
+ FormatStyle Style;
+ FileID ID;
+ SourceManager &SourceMgr;
+ // AffectedRangeMgr stores ranges to be fixed.
+ AffectedRangeManager AffectedRangeMgr;
+ SmallVector<SmallVector<UnwrappedLine, 16>, 2> UnwrappedLines;
+
+ encoding::Encoding Encoding;
+};
+
+class Formatter : public TokenAnalyzer {
+public:
+ Formatter(const FormatStyle &Style, SourceManager &SourceMgr, FileID ID,
+ ArrayRef<CharSourceRange> Ranges)
+ : TokenAnalyzer(Style, SourceMgr, ID, Ranges) {}
+
+ tooling::Replacements
+ analyze(TokenAnnotator &Annotator,
+ SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
+ FormatTokenLexer &Tokens, tooling::Replacements &Result,
+ bool *IncompleteFormat) override {
deriveLocalStyle(AnnotatedLines);
- computeAffectedLines(AnnotatedLines.begin(), AnnotatedLines.end());
+ AffectedRangeMgr.computeAffectedLines(AnnotatedLines.begin(),
+ AnnotatedLines.end());
+
if (Style.Language == FormatStyle::LK_JavaScript &&
Style.JavaScriptQuotes != FormatStyle::JSQS_Leave)
requoteJSStringLiteral(AnnotatedLines, Result);
@@ -1516,6 +1553,9 @@
}
Annotator.setCommentLineLevels(AnnotatedLines);
+
+ WhitespaceManager Whitespaces(SourceMgr, Style,
+ inputUsesCRLF(SourceMgr.getBufferData(ID)));
ContinuationIndenter Indenter(Style, Tokens.getKeywords(), SourceMgr,
Whitespaces, Encoding,
BinPackInconclusiveFunctions);
@@ -1526,50 +1566,11 @@
}
private:
- // Determines which lines are affected by the SourceRanges given as input.
- // Returns \c true if at least one line between I and E or one of their
- // children is affected.
- bool computeAffectedLines(SmallVectorImpl<AnnotatedLine *>::iterator I,
- SmallVectorImpl<AnnotatedLine *>::iterator E) {
- bool SomeLineAffected = false;
- const AnnotatedLine *PreviousLine = nullptr;
- while (I != E) {
- AnnotatedLine *Line = *I;
- Line->LeadingEmptyLinesAffected = affectsLeadingEmptyLines(*Line->First);
-
- // If a line is part of a preprocessor directive, it needs to be formatted
- // if any token within the directive is affected.
- if (Line->InPPDirective) {
- FormatToken *Last = Line->Last;
- SmallVectorImpl<AnnotatedLine *>::iterator PPEnd = I + 1;
- while (PPEnd != E && !(*PPEnd)->First->HasUnescapedNewline) {
- Last = (*PPEnd)->Last;
- ++PPEnd;
- }
-
- if (affectsTokenRange(*Line->First, *Last,
- /*IncludeLeadingNewlines=*/false)) {
- SomeLineAffected = true;
- markAllAsAffected(I, PPEnd);
- }
- I = PPEnd;
- continue;
- }
-
- if (nonPPLineAffected(Line, PreviousLine))
- SomeLineAffected = true;
-
- PreviousLine = Line;
- ++I;
- }
- return SomeLineAffected;
- }
-
// If the last token is a double/single-quoted string literal, generates a
// replacement with a single/double quoted string literal, re-escaping the
// contents in the process.
void requoteJSStringLiteral(SmallVectorImpl<AnnotatedLine *> &Lines,
- tooling::Replacements &Result) {
+ tooling::Replacements &Result) {
for (AnnotatedLine *Line : Lines) {
requoteJSStringLiteral(Line->Children, Result);
if (!Line->Affected)
@@ -1604,145 +1605,50 @@
bool Escaped = false;
for (size_t i = 1; i < Input.size() - 1; i++) {
switch (Input[i]) {
- case '\\':
- if (!Escaped && i + 1 < Input.size() &&
- ((IsSingle && Input[i + 1] == '"') ||
- (!IsSingle && Input[i + 1] == '\''))) {
- // Remove this \, it's escaping a " or ' that no longer needs
- // escaping
- ColumnWidth--;
- Replace(Start.getLocWithOffset(i), 1, "");
- continue;
- }
- Escaped = !Escaped;
- break;
- case '\"':
- case '\'':
- if (!Escaped && IsSingle == (Input[i] == '\'')) {
- // Escape the quote.
- Replace(Start.getLocWithOffset(i), 0, "\\");
- ColumnWidth++;
- }
- Escaped = false;
- break;
- default:
- Escaped = false;
- break;
+ case '\\':
+ if (!Escaped && i + 1 < Input.size() &&
+ ((IsSingle && Input[i + 1] == '"') ||
+ (!IsSingle && Input[i + 1] == '\''))) {
+ // Remove this \, it's escaping a " or ' that no longer needs
+ // escaping
+ ColumnWidth--;
+ Replace(Start.getLocWithOffset(i), 1, "");
+ continue;
+ }
+ Escaped = !Escaped;
+ break;
+ case '\"':
+ case '\'':
+ if (!Escaped && IsSingle == (Input[i] == '\'')) {
+ // Escape the quote.
+ Replace(Start.getLocWithOffset(i), 0, "\\");
+ ColumnWidth++;
+ }
+ Escaped = false;
+ break;
+ default:
+ Escaped = false;
+ break;
}
}
// For formatting, count the number of non-escaped single quotes in them
// and adjust ColumnWidth to take the added escapes into account.
- // FIXME(martinprobst): this might conflict with code breaking a long string
- // literal (which clang-format doesn't do, yet). For that to work, this code
- // would have to modify TokenText directly.
+ // FIXME(martinprobst): this might conflict with code breaking a long
+ // string literal (which clang-format doesn't do, yet). For that to
+ // work, this code would have to modify TokenText directly.
FormatTok->ColumnWidth = ColumnWidth;
}
}
}
-
- // Determines whether 'Line' is affected by the SourceRanges given as input.
- // Returns \c true if line or one if its children is affected.
- bool nonPPLineAffected(AnnotatedLine *Line,
- const AnnotatedLine *PreviousLine) {
- bool SomeLineAffected = false;
- Line->ChildrenAffected =
- computeAffectedLines(Line->Children.begin(), Line->Children.end());
- if (Line->ChildrenAffected)
- SomeLineAffected = true;
-
- // Stores whether one of the line's tokens is directly affected.
- bool SomeTokenAffected = false;
- // Stores whether we need to look at the leading newlines of the next token
- // in order to determine whether it was affected.
- bool IncludeLeadingNewlines = false;
-
- // Stores whether the first child line of any of this line's tokens is
- // affected.
- bool SomeFirstChildAffected = false;
-
- for (FormatToken *Tok = Line->First; Tok; Tok = Tok->Next) {
- // Determine whether 'Tok' was affected.
- if (affectsTokenRange(*Tok, *Tok, IncludeLeadingNewlines))
- SomeTokenAffected = true;
-
- // Determine whether the first child of 'Tok' was affected.
- if (!Tok->Children.empty() && Tok->Children.front()->Affected)
- SomeFirstChildAffected = true;
-
- IncludeLeadingNewlines = Tok->Children.empty();
- }
-
- // Was this line moved, i.e. has it previously been on the same line as an
- // affected line?
- bool LineMoved = PreviousLine && PreviousLine->Affected &&
- Line->First->NewlinesBefore == 0;
-
- bool IsContinuedComment =
- Line->First->is(tok::comment) && Line->First->Next == nullptr &&
- Line->First->NewlinesBefore < 2 && PreviousLine &&
- PreviousLine->Affected && PreviousLine->Last->is(tok::comment);
-
- if (SomeTokenAffected || SomeFirstChildAffected || LineMoved ||
- IsContinuedComment) {
- Line->Affected = true;
- SomeLineAffected = true;
- }
- return SomeLineAffected;
- }
-
- // Marks all lines between I and E as well as all their children as affected.
- void markAllAsAffected(SmallVectorImpl<AnnotatedLine *>::iterator I,
- SmallVectorImpl<AnnotatedLine *>::iterator E) {
- while (I != E) {
- (*I)->Affected = true;
- markAllAsAffected((*I)->Children.begin(), (*I)->Children.end());
- ++I;
- }
- }
-
- // Returns true if the range from 'First' to 'Last' intersects with one of the
- // input ranges.
- bool affectsTokenRange(const FormatToken &First, const FormatToken &Last,
- bool IncludeLeadingNewlines) {
- SourceLocation Start = First.WhitespaceRange.getBegin();
- if (!IncludeLeadingNewlines)
- Start = Start.getLocWithOffset(First.LastNewlineOffset);
- SourceLocation End = Last.getStartOfNonWhitespace();
- End = End.getLocWithOffset(Last.TokenText.size());
- CharSourceRange Range = CharSourceRange::getCharRange(Start, End);
- return affectsCharSourceRange(Range);
- }
-
- // Returns true if one of the input ranges intersect the leading empty lines
- // before 'Tok'.
- bool affectsLeadingEmptyLines(const FormatToken &Tok) {
- CharSourceRange EmptyLineRange = CharSourceRange::getCharRange(
- Tok.WhitespaceRange.getBegin(),
- Tok.WhitespaceRange.getBegin().getLocWithOffset(Tok.LastNewlineOffset));
- return affectsCharSourceRange(EmptyLineRange);
- }
-
- // Returns true if 'Range' intersects with one of the input ranges.
- bool affectsCharSourceRange(const CharSourceRange &Range) {
- for (SmallVectorImpl<CharSourceRange>::const_iterator I = Ranges.begin(),
- E = Ranges.end();
- I != E; ++I) {
- if (!SourceMgr.isBeforeInTranslationUnit(Range.getEnd(), I->getBegin()) &&
- !SourceMgr.isBeforeInTranslationUnit(I->getEnd(), Range.getBegin()))
- return true;
- }
- return false;
- }
-
static bool inputUsesCRLF(StringRef Text) {
return Text.count('\r') * 2 > Text.count('\n');
}
bool
hasCpp03IncompatibleFormat(const SmallVectorImpl<AnnotatedLine *> &Lines) {
- for (const AnnotatedLine* Line : Lines) {
+ for (const AnnotatedLine *Line : Lines) {
if (hasCpp03IncompatibleFormat(Line->Children))
return true;
for (FormatToken *Tok = Line->First->Next; Tok; Tok = Tok->Next) {
@@ -1760,7 +1666,7 @@
int countVariableAlignments(const SmallVectorImpl<AnnotatedLine *> &Lines) {
int AlignmentDiff = 0;
- for (const AnnotatedLine* Line : Lines) {
+ for (const AnnotatedLine *Line : Lines) {
AlignmentDiff += countVariableAlignments(Line->Children);
for (FormatToken *Tok = Line->First; Tok && Tok->Next; Tok = Tok->Next) {
if (!Tok->is(TT_PointerOrReference))
@@ -1807,24 +1713,172 @@
HasBinPackedFunction || !HasOnePerLineFunction;
}
- void consumeUnwrappedLine(const UnwrappedLine &TheLine) override {
- assert(!UnwrappedLines.empty());
- UnwrappedLines.back().push_back(TheLine);
+ bool BinPackInconclusiveFunctions;
+};
+
+// This class clean up the erroneous/redundant code around the given ranges in
+// file.
+class Cleaner : public TokenAnalyzer {
+public:
+ Cleaner(const FormatStyle &Style, SourceManager &SourceMgr, FileID ID,
+ ArrayRef<CharSourceRange> Ranges)
+ : TokenAnalyzer(Style, SourceMgr, ID, Ranges),
+ DeletedTokens(FormatTokenLess(SourceMgr)) {}
+
+ // FIXME: eliminate unused parameters.
+ tooling::Replacements
+ analyze(TokenAnnotator &Annotator,
+ SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
+ FormatTokenLexer &Tokens, tooling::Replacements &Result,
+ bool *IncompleteFormat) override {
+ // FIXME: in the current implementation the granularity of affected range
+ // is an annotated line. However, this is not sufficient. Furthermore,
+ // redundant code introduced by replacements does not necessarily
+ // intercept with ranges of replacements that result in the redundancy.
+ // To determine if some redundant code is actually introduced by
+ // replacements(e.g. deletions), we need to come up with a more
+ // sophisticated way of computing affected ranges.
+ AffectedRangeMgr.computeAffectedLines(AnnotatedLines.begin(),
+ AnnotatedLines.end());
+
+ checkEmptyNamespace(AnnotatedLines);
+
+ return generateFixes();
}
- void finishRun() override {
- UnwrappedLines.push_back(SmallVector<UnwrappedLine, 16>());
+private:
+ bool containsOnlyComments(const AnnotatedLine &Line) {
+ for (FormatToken *Tok = Line.First; Tok != nullptr; Tok = Tok->Next) {
+ if (Tok->isNot(tok::comment))
+ return false;
+ }
+ return true;
}
- FormatStyle Style;
- FileID ID;
- SourceManager &SourceMgr;
- WhitespaceManager Whitespaces;
- SmallVector<CharSourceRange, 8> Ranges;
- SmallVector<SmallVector<UnwrappedLine, 16>, 2> UnwrappedLines;
+ // Iterate through all lines and remove any empty (nested) namespaces.
+ void checkEmptyNamespace(SmallVectorImpl<AnnotatedLine *> &AnnotatedLines) {
+ 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)) {
+ checkEmptyNamespace(AnnotatedLines, i, i);
+ }
+ }
- encoding::Encoding Encoding;
- bool BinPackInconclusiveFunctions;
+ for (auto Line : DeletedLines) {
+ FormatToken *Tok = AnnotatedLines[Line]->First;
+ while (Tok) {
+ deleteToken(Tok);
+ Tok = Tok->Next;
+ }
+ }
+ }
+
+ // The function checks if the namespace, which starts from \p CurrentLine, and
+ // its nested namespaces are empty and delete them if they are empty. It also
+ // sets \p NewLine to the last line checked.
+ // Returns true if the current namespace is empty.
+ bool checkEmptyNamespace(SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
+ unsigned CurrentLine, unsigned &NewLine) {
+ unsigned InitLine = CurrentLine, End = AnnotatedLines.size();
+ if (Style.BraceWrapping.AfterNamespace) {
+ // If the left brace is in a new line, we should consume it first so that
+ // it does not make the namespace non-empty.
+ // TODO: error handling if there is no left brace.
+ if (!AnnotatedLines[++CurrentLine]->startsWith(tok::l_brace)) {
+ NewLine = CurrentLine;
+ return false;
+ }
+ } else if (!AnnotatedLines[CurrentLine]->endsWith(tok::l_brace)) {
+ return false;
+ }
+ while (++CurrentLine < End) {
+ 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 (!checkEmptyNamespace(AnnotatedLines, CurrentLine, NewLine))
+ return false;
+ CurrentLine = NewLine;
+ continue;
+ }
+
+ if (containsOnlyComments(*AnnotatedLines[CurrentLine]))
+ continue;
+
+ // If there is anything other than comments or nested namespaces in the
+ // current namespace, the namespace cannot be empty.
+ NewLine = CurrentLine;
+ return false;
+ }
+
+ NewLine = CurrentLine;
+ if (CurrentLine >= End)
+ return false;
+
+ // Check if the empty namespace is actually affected by changed ranges.
+ if (!AffectedRangeMgr.affectsCharSourceRange(CharSourceRange::getCharRange(
+ AnnotatedLines[InitLine]->First->Tok.getLocation(),
+ AnnotatedLines[CurrentLine]->Last->Tok.getEndLoc())))
+ return false;
+
+ for (unsigned i = InitLine; i <= CurrentLine; ++i) {
+ DeletedLines.insert(i);
+ }
+
+ return true;
+ }
+
+ // Delete the given token.
+ inline void deleteToken(FormatToken *Tok) {
+ if (Tok)
+ DeletedTokens.insert(Tok);
+ }
+
+ tooling::Replacements generateFixes() {
+ tooling::Replacements Fixes;
+ std::vector<FormatToken *> Tokens;
+ std::copy(DeletedTokens.begin(), DeletedTokens.end(),
+ std::back_inserter(Tokens));
+
+ // Merge multiple continuous token deletions into one big deletion so that
+ // the number of replacements can be reduced. This makes computing affected
+ // ranges more efficient when we run reformat on the changed code.
+ unsigned Idx = 0;
+ while (Idx < Tokens.size()) {
+ unsigned St = Idx, End = Idx;
+ while ((End + 1) < Tokens.size() &&
+ Tokens[End]->Next == Tokens[End + 1]) {
+ End++;
+ }
+ auto SR = CharSourceRange::getCharRange(Tokens[St]->Tok.getLocation(),
+ Tokens[End]->Tok.getEndLoc());
+ Fixes.insert(tooling::Replacement(SourceMgr, SR, ""));
+ Idx = End + 1;
+ }
+
+ return Fixes;
+ }
+
+ // Class for less-than inequality comparason for the set `RedundantTokens`.
+ // We store tokens in the order they appear in the translation unit so that
+ // we do not need to sort them in `generateFixes()`.
+ struct FormatTokenLess {
+ FormatTokenLess(SourceManager &SM) : SM(SM) {}
+
+ bool operator()(const FormatToken *LHS, const FormatToken *RHS) {
+ return SM.isBeforeInTranslationUnit(LHS->Tok.getLocation(),
+ RHS->Tok.getLocation());
+ }
+ SourceManager &SM;
+ };
+
+ // Tokens to be deleted.
+ std::set<FormatToken *, FormatTokenLess> DeletedTokens;
+ // The line numbers of lines to be deleted.
+ std::set<unsigned> DeletedLines;
};
struct IncludeDirective {
@@ -1993,39 +2047,56 @@
return Replaces;
}
-tooling::Replacements formatReplacements(StringRef Code,
- const tooling::Replacements &Replaces,
- const FormatStyle &Style) {
+template <typename T>
+static tooling::Replacements
+processReplacements(T ProcessFunc, StringRef Code,
+ const tooling::Replacements &Replaces,
+ const FormatStyle &Style) {
if (Replaces.empty())
return tooling::Replacements();
std::string NewCode = applyAllReplacements(Code, Replaces);
std::vector<tooling::Range> ChangedRanges =
tooling::calculateChangedRanges(Replaces);
StringRef FileName = Replaces.begin()->getFilePath();
+
tooling::Replacements FormatReplaces =
- reformat(Style, NewCode, ChangedRanges, FileName);
+ ProcessFunc(Style, NewCode, ChangedRanges, FileName);
- tooling::Replacements MergedReplacements =
- mergeReplacements(Replaces, FormatReplaces);
+ return mergeReplacements(Replaces, FormatReplaces);
+}
- return MergedReplacements;
+tooling::Replacements formatReplacements(StringRef Code,
+ const tooling::Replacements &Replaces,
+ const FormatStyle &Style) {
+ // We need to use lambda function here since there are two versions of
+ // `reformat`.
+ auto Reformat = [](const FormatStyle &Style, StringRef Code,
+ std::vector<tooling::Range> Ranges,
+ StringRef FileName) -> tooling::Replacements {
+ return reformat(Style, Code, Ranges, FileName);
+ };
+ return processReplacements(Reformat, Code, Replaces, Style);
}
-tooling::Replacements reformat(const FormatStyle &Style,
- SourceManager &SourceMgr, FileID ID,
- ArrayRef<CharSourceRange> Ranges,
- bool *IncompleteFormat) {
- FormatStyle Expanded = expandPresets(Style);
- if (Expanded.DisableFormat)
- return tooling::Replacements();
- Formatter formatter(Expanded, SourceMgr, ID, Ranges);
- return formatter.format(IncompleteFormat);
+tooling::Replacements
+cleanupAroundReplacements(StringRef Code, const tooling::Replacements &Replaces,
+ const FormatStyle &Style) {
+ // We need to use lambda function here since there are two versions of
+ // `cleanup`.
+ auto Cleanup = [](const FormatStyle &Style, StringRef Code,
+ std::vector<tooling::Range> Ranges,
+ StringRef FileName) -> tooling::Replacements {
+ return cleanup(Style, Code, Ranges, FileName);
+ };
+ return processReplacements(Cleanup, Code, Replaces, Style);
}
-tooling::Replacements reformat(const FormatStyle &Style, StringRef Code,
- ArrayRef<tooling::Range> Ranges,
- StringRef FileName, bool *IncompleteFormat) {
+template <typename T>
+static tooling::Replacements
+setupEnvironmentAndProcess(T Callback, const FormatStyle &Style, StringRef Code,
+ ArrayRef<tooling::Range> Ranges, StringRef FileName,
+ bool *IncompleteFormat) {
if (Style.DisableFormat)
return tooling::Replacements();
@@ -2048,7 +2119,55 @@
SourceLocation End = Start.getLocWithOffset(Range.getLength());
CharRanges.push_back(CharSourceRange::getCharRange(Start, End));
}
- return reformat(Style, SourceMgr, ID, CharRanges, IncompleteFormat);
+
+ return Callback(Style, SourceMgr, ID, CharRanges, IncompleteFormat);
+}
+
+tooling::Replacements reformat(const FormatStyle &Style,
+ SourceManager &SourceMgr, FileID ID,
+ ArrayRef<CharSourceRange> Ranges,
+ bool *IncompleteFormat) {
+ FormatStyle Expanded = expandPresets(Style);
+ if (Expanded.DisableFormat)
+ return tooling::Replacements();
+
+ Formatter Format(Expanded, SourceMgr, ID, Ranges);
+ return Format.process(IncompleteFormat);
+}
+
+tooling::Replacements reformat(const FormatStyle &Style, StringRef Code,
+ ArrayRef<tooling::Range> Ranges,
+ StringRef FileName, bool *IncompleteFormat) {
+ // We need to use lambda here since there are two versions of `reformat`.
+ auto Format = [](const FormatStyle &Style, SourceManager &SourceMgr,
+ FileID ID, ArrayRef<CharSourceRange> Ranges,
+ bool *IncompleteFormat) -> tooling::Replacements {
+ return reformat(Style, SourceMgr, ID, Ranges, IncompleteFormat);
+ };
+ return setupEnvironmentAndProcess(Format, Style, Code, Ranges, FileName,
+ IncompleteFormat);
+}
+
+tooling::Replacements cleanup(const FormatStyle &Style,
+ SourceManager &SourceMgr, FileID ID,
+ ArrayRef<CharSourceRange> Ranges) {
+ Cleaner Clean(Style, SourceMgr, ID, Ranges);
+ return Clean.process(nullptr);
+}
+
+tooling::Replacements cleanup(const FormatStyle &Style, StringRef Code,
+ ArrayRef<tooling::Range> Ranges,
+ StringRef FileName) {
+ // We need to use lambda here since there are two versions of `cleanup`.
+ auto Cleanup = [](const FormatStyle &Style, SourceManager &SourceMgr,
+ FileID ID, ArrayRef<CharSourceRange> Ranges,
+ bool *IncompleteFormat) -> tooling::Replacements {
+
+ return cleanup(Style, SourceMgr, ID, Ranges);
+ };
+
+ return setupEnvironmentAndProcess(Cleanup, Style, Code, Ranges, FileName,
+ nullptr);
}
LangOptions getFormattingLangOpts(const FormatStyle &Style) {
@@ -2062,7 +2181,7 @@
LangOpts.Bool = 1;
LangOpts.ObjC1 = 1;
LangOpts.ObjC2 = 1;
- LangOpts.MicrosoftExt = 1; // To get kw___try, kw___finally.
+ LangOpts.MicrosoftExt = 1; // To get kw___try, kw___finally.
LangOpts.DeclSpecKeyword = 1; // To get __declspec.
return LangOpts;
}
Index: lib/Format/CMakeLists.txt
===================================================================
--- lib/Format/CMakeLists.txt
+++ lib/Format/CMakeLists.txt
@@ -1,6 +1,7 @@
set(LLVM_LINK_COMPONENTS support)
add_clang_library(clangFormat
+ AffectedRangeManager.cpp
BreakableToken.cpp
ContinuationIndenter.cpp
Format.cpp
Index: lib/Format/AffectedRangeManager.h
===================================================================
--- /dev/null
+++ lib/Format/AffectedRangeManager.h
@@ -0,0 +1,66 @@
+//===--- AffectedRangeManager.h - Format C++ code ---------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// \brief AffectedRangeManager class manages affected ranges in the code.
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_LIB_FORMAT_AFFECTEDRANGEMANAGER_H
+#define LLVM_CLANG_LIB_FORMAT_AFFECTEDRANGEMANAGER_H
+
+#include "clang/Basic/SourceManager.h"
+
+namespace clang {
+namespace format {
+
+struct FormatToken;
+class AnnotatedLine;
+
+class AffectedRangeManager {
+public:
+ AffectedRangeManager(SourceManager &SourceMgr,
+ const SmallVector<CharSourceRange, 8> &Ranges)
+ : SourceMgr(SourceMgr), Ranges(Ranges) {}
+
+ // Determines which lines are affected by the SourceRanges given as input.
+ // Returns \c true if at least one line between I and E or one of their
+ // children is affected.
+ bool computeAffectedLines(SmallVectorImpl<AnnotatedLine *>::iterator I,
+ SmallVectorImpl<AnnotatedLine *>::iterator E);
+
+ // Returns true if 'Range' intersects with one of the input ranges.
+ bool affectsCharSourceRange(const CharSourceRange &Range);
+
+private:
+ // Returns true if the range from 'First' to 'Last' intersects with one of the
+ // input ranges.
+ bool affectsTokenRange(const FormatToken &First, const FormatToken &Last,
+ bool IncludeLeadingNewlines);
+
+ // Returns true if one of the input ranges intersect the leading empty lines
+ // before 'Tok'.
+ bool affectsLeadingEmptyLines(const FormatToken &Tok);
+
+ // Marks all lines between I and E as well as all their children as affected.
+ void markAllAsAffected(SmallVectorImpl<AnnotatedLine *>::iterator I,
+ SmallVectorImpl<AnnotatedLine *>::iterator E);
+
+ // Determines whether 'Line' is affected by the SourceRanges given as input.
+ // Returns \c true if line or one if its children is affected.
+ bool nonPPLineAffected(AnnotatedLine *Line,
+ const AnnotatedLine *PreviousLine);
+ SourceManager &SourceMgr;
+ const SmallVector<CharSourceRange, 8> Ranges;
+};
+
+} // namespace format
+} // namespace clang
+
+#endif // LLVM_CLANG_LIB_FORMAT_WHITESPACEMANAGER_H
Index: lib/Format/AffectedRangeManager.cpp
===================================================================
--- /dev/null
+++ lib/Format/AffectedRangeManager.cpp
@@ -0,0 +1,150 @@
+//===--- AffectedRangeManager.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.
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// \brief This file implements AffectRangeManager class.
+///
+//===----------------------------------------------------------------------===//
+
+#include "AffectedRangeManager.h"
+
+#include "FormatToken.h"
+#include "TokenAnnotator.h"
+
+namespace clang {
+namespace format {
+
+bool AffectedRangeManager::computeAffectedLines(
+ SmallVectorImpl<AnnotatedLine *>::iterator I,
+ SmallVectorImpl<AnnotatedLine *>::iterator E) {
+ bool SomeLineAffected = false;
+ const AnnotatedLine *PreviousLine = nullptr;
+ while (I != E) {
+ AnnotatedLine *Line = *I;
+ Line->LeadingEmptyLinesAffected = affectsLeadingEmptyLines(*Line->First);
+
+ // If a line is part of a preprocessor directive, it needs to be formatted
+ // if any token within the directive is affected.
+ if (Line->InPPDirective) {
+ FormatToken *Last = Line->Last;
+ SmallVectorImpl<AnnotatedLine *>::iterator PPEnd = I + 1;
+ while (PPEnd != E && !(*PPEnd)->First->HasUnescapedNewline) {
+ Last = (*PPEnd)->Last;
+ ++PPEnd;
+ }
+
+ if (affectsTokenRange(*Line->First, *Last,
+ /*IncludeLeadingNewlines=*/false)) {
+ SomeLineAffected = true;
+ markAllAsAffected(I, PPEnd);
+ }
+ I = PPEnd;
+ continue;
+ }
+
+ if (nonPPLineAffected(Line, PreviousLine))
+ SomeLineAffected = true;
+
+ PreviousLine = Line;
+ ++I;
+ }
+ return SomeLineAffected;
+}
+
+bool AffectedRangeManager::affectsCharSourceRange(
+ const CharSourceRange &Range) {
+ for (SmallVectorImpl<CharSourceRange>::const_iterator I = Ranges.begin(),
+ E = Ranges.end();
+ I != E; ++I) {
+ if (!SourceMgr.isBeforeInTranslationUnit(Range.getEnd(), I->getBegin()) &&
+ !SourceMgr.isBeforeInTranslationUnit(I->getEnd(), Range.getBegin()))
+ return true;
+ }
+ return false;
+}
+
+bool AffectedRangeManager::affectsTokenRange(const FormatToken &First,
+ const FormatToken &Last,
+ bool IncludeLeadingNewlines) {
+ SourceLocation Start = First.WhitespaceRange.getBegin();
+ if (!IncludeLeadingNewlines)
+ Start = Start.getLocWithOffset(First.LastNewlineOffset);
+ SourceLocation End = Last.getStartOfNonWhitespace();
+ End = End.getLocWithOffset(Last.TokenText.size());
+ CharSourceRange Range = CharSourceRange::getCharRange(Start, End);
+ return affectsCharSourceRange(Range);
+}
+
+bool AffectedRangeManager::affectsLeadingEmptyLines(const FormatToken &Tok) {
+ CharSourceRange EmptyLineRange = CharSourceRange::getCharRange(
+ Tok.WhitespaceRange.getBegin(),
+ Tok.WhitespaceRange.getBegin().getLocWithOffset(Tok.LastNewlineOffset));
+ return affectsCharSourceRange(EmptyLineRange);
+}
+
+void AffectedRangeManager::markAllAsAffected(
+ SmallVectorImpl<AnnotatedLine *>::iterator I,
+ SmallVectorImpl<AnnotatedLine *>::iterator E) {
+ while (I != E) {
+ (*I)->Affected = true;
+ markAllAsAffected((*I)->Children.begin(), (*I)->Children.end());
+ ++I;
+ }
+}
+
+bool AffectedRangeManager::nonPPLineAffected(
+ AnnotatedLine *Line, const AnnotatedLine *PreviousLine) {
+ bool SomeLineAffected = false;
+ Line->ChildrenAffected =
+ computeAffectedLines(Line->Children.begin(), Line->Children.end());
+ if (Line->ChildrenAffected)
+ SomeLineAffected = true;
+
+ // Stores whether one of the line's tokens is directly affected.
+ bool SomeTokenAffected = false;
+ // Stores whether we need to look at the leading newlines of the next token
+ // in order to determine whether it was affected.
+ bool IncludeLeadingNewlines = false;
+
+ // Stores whether the first child line of any of this line's tokens is
+ // affected.
+ bool SomeFirstChildAffected = false;
+
+ for (FormatToken *Tok = Line->First; Tok; Tok = Tok->Next) {
+ // Determine whether 'Tok' was affected.
+ if (affectsTokenRange(*Tok, *Tok, IncludeLeadingNewlines))
+ SomeTokenAffected = true;
+
+ // Determine whether the first child of 'Tok' was affected.
+ if (!Tok->Children.empty() && Tok->Children.front()->Affected)
+ SomeFirstChildAffected = true;
+
+ IncludeLeadingNewlines = Tok->Children.empty();
+ }
+
+ // Was this line moved, i.e. has it previously been on the same line as an
+ // affected line?
+ bool LineMoved = PreviousLine && PreviousLine->Affected &&
+ Line->First->NewlinesBefore == 0;
+
+ bool IsContinuedComment =
+ Line->First->is(tok::comment) && Line->First->Next == nullptr &&
+ Line->First->NewlinesBefore < 2 && PreviousLine &&
+ PreviousLine->Affected && PreviousLine->Last->is(tok::comment);
+
+ if (SomeTokenAffected || SomeFirstChildAffected || LineMoved ||
+ IsContinuedComment) {
+ Line->Affected = true;
+ SomeLineAffected = true;
+ }
+ return SomeLineAffected;
+}
+
+} // namespace format
+} // namespace clang
Index: include/clang/Format/Format.h
===================================================================
--- include/clang/Format/Format.h
+++ include/clang/Format/Format.h
@@ -771,6 +771,12 @@
const tooling::Replacements &Replaces,
const FormatStyle &Style);
+/// \brief Returns the replacements corresponding to applying \p Replaces and
+/// cleaning up the code after that.
+tooling::Replacements
+cleanupAroundReplacements(StringRef Code, const tooling::Replacements &Replaces,
+ const FormatStyle &Style);
+
/// \brief Reformats the given \p Ranges in the file \p ID.
///
/// Each range is extended on either end to its next bigger logic unit, i.e.
@@ -796,6 +802,22 @@
StringRef FileName = "<stdin>",
bool *IncompleteFormat = nullptr);
+/// \brief Clean up any erroneous/redundant code in the given \p Ranges in the
+/// file \p ID.
+///
+/// Returns the ``Replacements`` that clean up all \p Ranges in the file \p ID.
+tooling::Replacements cleanup(const FormatStyle &Style,
+ SourceManager &SourceMgr, FileID ID,
+ ArrayRef<CharSourceRange> Ranges);
+
+/// \brief Clean up any erroneous/redundant code in the given \p Ranges in \p
+/// Code.
+///
+/// Otherwise identical to the cleanup() function using a file ID.
+tooling::Replacements cleanup(const FormatStyle &Style, StringRef Code,
+ ArrayRef<tooling::Range> Ranges,
+ StringRef FileName = "<stdin>");
+
/// \brief Returns the ``LangOpts`` that the formatter expects you to set.
///
/// \param Style determines specific settings for lexing mode.
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
