Commit f9f0919d authored by Jonathan Coe's avatar Jonathan Coe
Browse files

[clang-format] Improve support for multiline C# strings 

Reviewers: krasimir

Reviewed By: krasimir

Tags: #clang-format

Differential Revision: https://reviews.llvm.org/D73622
parent 8184176e

clang/lib/Format/FormatTokenLexer.cpp

+69 −18
Original line number Diff line number Diff line
@@ -57,6 +57,10 @@ ArrayRef<FormatToken *> FormatTokenLexer::lex() { 
    if (Style.Language == FormatStyle::LK_TextProto)

      tryParsePythonComment();

    tryMergePreviousTokens();

    if (Style.isCSharp())

      // This needs to come after tokens have been merged so that C#

      // string literals are correctly identified.

      handleCSharpVerbatimAndInterpolatedStrings();

    if (Tokens.back()->NewlinesBefore > 0 || Tokens.back()->IsMultiline)

      FirstInLineIndex = Tokens.size() - 1;

  } while (Tokens.back()->Tok.isNot(tok::eof));
@@ -181,12 +185,12 @@ bool FormatTokenLexer::tryMergeJSPrivateIdentifier() { 
// Search for verbatim or interpolated string literals @"ABC" or

// $"aaaaa{abc}aaaaa" i and mark the token as TT_CSharpStringLiteral, and to

// prevent splitting of @, $ and ".

// Merging of multiline verbatim strings with embedded '"' is handled in

// handleCSharpVerbatimAndInterpolatedStrings with lower-level lexing.

bool FormatTokenLexer::tryMergeCSharpStringLiteral() {

  if (Tokens.size() < 2)

    return false;



  auto &CSharpStringLiteral = *(Tokens.end() - 2);



  // Interpolated strings could contain { } with " characters inside.

  // $"{x ?? "null"}"

  // should not be split into $"{x ?? ", null, "}" but should treated as a
@@ -236,27 +240,12 @@ bool FormatTokenLexer::tryMergeCSharpStringLiteral() { 
    }

  }



  // verbatim strings could contain "" which C# sees as an escaped ".

  // @"""Hello""" will have been tokenized as @"" "Hello" "" and needs

  // merging into a single string literal.

  // Look for @"aaaaaa" or $"aaaaaa".

  auto &String = *(Tokens.end() - 1);

  if (!String->is(tok::string_literal))

    return false;



  if (CSharpStringLiteral->Type == TT_CSharpStringLiteral &&

      (CSharpStringLiteral->TokenText.startswith(R"(@")") ||

       CSharpStringLiteral->TokenText.startswith(R"($@")"))) {

    CSharpStringLiteral->TokenText = StringRef(

        CSharpStringLiteral->TokenText.begin(),

        String->TokenText.end() - CSharpStringLiteral->TokenText.begin());

    CSharpStringLiteral->ColumnWidth += String->ColumnWidth;

    Tokens.erase(Tokens.end() - 1);

    return true;

  }



  auto &At = *(Tokens.end() - 2);



  // Look for @"aaaaaa" or $"aaaaaa".

  if (!(At->is(tok::at) || At->TokenText == "$"))

    return false;
@@ -498,6 +487,68 @@ void FormatTokenLexer::tryParseJSRegexLiteral() { 
  resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(Offset)));

}



void FormatTokenLexer::handleCSharpVerbatimAndInterpolatedStrings() {

  FormatToken *CSharpStringLiteral = Tokens.back();



  if (CSharpStringLiteral->Type != TT_CSharpStringLiteral)

    return;



  // Deal with multiline strings.

  if (!(CSharpStringLiteral->TokenText.startswith(R"(@")") ||

        CSharpStringLiteral->TokenText.startswith(R"($@")")))

    return;



  const char *StrBegin =

      Lex->getBufferLocation() - CSharpStringLiteral->TokenText.size();

  const char *Offset = StrBegin;

  if (CSharpStringLiteral->TokenText.startswith(R"(@")"))

    Offset += 2;

  else // CSharpStringLiteral->TokenText.startswith(R"($@")")

    Offset += 3;



  // Look for a terminating '"' in the current file buffer.

  // Make no effort to format code within an interpolated or verbatim string.

  for (; Offset != Lex->getBuffer().end(); ++Offset) {

    if (Offset[0] == '"') {

      // "" within a verbatim string is an escaped double quote: skip it.

      if (Offset + 1 < Lex->getBuffer().end() && Offset[1] == '"')

        ++Offset;

      else

        break;

    }

  }



  // Make no attempt to format code properly if a verbatim string is

  // unterminated.

  if (Offset == Lex->getBuffer().end())

    return;



  StringRef LiteralText(StrBegin, Offset - StrBegin + 1);

  CSharpStringLiteral->TokenText = LiteralText;



  // Adjust width for potentially multiline string literals.

  size_t FirstBreak = LiteralText.find('\n');

  StringRef FirstLineText = FirstBreak == StringRef::npos

                                ? LiteralText

                                : LiteralText.substr(0, FirstBreak);

  CSharpStringLiteral->ColumnWidth = encoding::columnWidthWithTabs(

      FirstLineText, CSharpStringLiteral->OriginalColumn, Style.TabWidth,

      Encoding);

  size_t LastBreak = LiteralText.rfind('\n');

  if (LastBreak != StringRef::npos) {

    CSharpStringLiteral->IsMultiline = true;

    unsigned StartColumn = 0; // The template tail spans the entire line.

    CSharpStringLiteral->LastLineColumnWidth = encoding::columnWidthWithTabs(

        LiteralText.substr(LastBreak + 1, LiteralText.size()), StartColumn,

        Style.TabWidth, Encoding);

  }



  SourceLocation loc = Offset < Lex->getBuffer().end()

                           ? Lex->getSourceLocation(Offset + 1)

                           : SourceMgr.getLocForEndOfFile(ID);

  resetLexer(SourceMgr.getFileOffset(loc));

}



void FormatTokenLexer::handleTemplateStrings() {

  FormatToken *BacktickToken = Tokens.back();

clang/lib/Format/FormatTokenLexer.h

+2 −0
Original line number Diff line number Diff line
@@ -79,6 +79,8 @@ private: 
  // nested template parts by balancing curly braces.

  void handleTemplateStrings();



  void handleCSharpVerbatimAndInterpolatedStrings();



  void tryParsePythonComment();



  bool tryMerge_TMacro();

clang/unittests/Format/FormatTestCSharp.cpp

+35 −3
Original line number Diff line number Diff line
@@ -412,9 +412,9 @@ TEST_F(FormatTestCSharp, CSharpSpaceAfterCStyleCast) { 
TEST_F(FormatTestCSharp, CSharpEscapedQuotesInVerbatimStrings) {

  FormatStyle Style = getGoogleStyle(FormatStyle::LK_CSharp);



  verifyFormat(R"(string str = @"""")", Style);

  verifyFormat(R"(string str = @"""Hello world""")", Style);

  verifyFormat(R"(string str = $@"""Hello {friend}""")", Style);

  verifyFormat(R"(string str = @"""";)", Style);

  verifyFormat(R"(string str = @"""Hello world""";)", Style);

  verifyFormat(R"(string str = $@"""Hello {friend}""";)", Style);

}



TEST_F(FormatTestCSharp, CSharpQuotesInInterpolatedStrings) {
@@ -425,5 +425,37 @@ TEST_F(FormatTestCSharp, CSharpQuotesInInterpolatedStrings) { 
  verifyFormat(R"(string str3 = $"{braceCount}}} braces";)", Style);

}



TEST_F(FormatTestCSharp, CSharpNewlinesInVerbatimStrings) {

  // Use MS style as Google Style inserts a line break before multiline strings.



  // verifyFormat does not understand multiline C# string-literals

  // so check the format explicitly.



  FormatStyle Style = getMicrosoftStyle(FormatStyle::LK_CSharp);



  std::string Code = R"(string s1 = $@"some code:

  class {className} {{

    {className}() {{}}

  }}";)";



  EXPECT_EQ(Code, format(Code, Style));



  // Multiline string in the middle of a function call.

  Code = R"(

var x = foo(className, $@"some code:

  class {className} {{

    {className}() {{}}

  }}",

            y);)"; // y aligned with `className` arg.



  EXPECT_EQ(Code, format(Code, Style));



  // Interpolated string with embedded multiline string.

  Code = R"(Console.WriteLine($"{string.Join(@",

		", values)}");)";



  EXPECT_EQ(Code, format(Code, Style));

}



} // namespace format

} // end namespace clang

clang/lib/Format/ContinuationIndenter.cpp

+1 −1

File changed.

Contains only whitespace changes.