[clang-format] Add the KeepEmptyLinesAtEOF option

[owenpan]

Summary

Adds an option KeepEmptyLinesAtEOF to keep empty lines (up to MaxEmptyLinesToKeep) before EOF. This remedies the probably unintentional change in behavior introduced in rG3d3ea8, which started to always remove empty lines before EOF.

Fixes https://github.com/llvm/llvm-project/issues/56054 and https://github.com/llvm/llvm-project/issues/63150.

[MyDeveloperDay]

LGTM

clang/docs/ClangFormatStyleOptions.rst

import {
          VeryLongImportsAreAnnoying,
          VeryLongImportsAreAnnoying,
          VeryLongImportsAreAnnoying,
      } from 'some/module.js'
 
      false:
      import {VeryLongImportsAreAnnoying, VeryLongImportsAreAnnoying, VeryLongImportsAreAnnoying,} from "some/module.js"
 
+.. _KeepEmptyLinesAtEOF:
+
+**KeepEmptyLinesAtEOF** (``Boolean``) :versionbadge:`clang-format 17` :ref:`¶ <KeepEmptyLinesAtEOF>`
+  Keep empty lines (up to ``MaxEmptyLinesToKeep``) at end of file.
+
 .. _KeepEmptyLinesAtTheStartOfBlocks:
 
 **KeepEmptyLinesAtTheStartOfBlocks** (``Boolean``) :versionbadge:`clang-format 3.7` :ref:`¶ <KeepEmptyLinesAtTheStartOfBlocks>`
   If true, the empty line at the start of blocks is kept.
 
   .. code-block:: c++
 
      true:                                  false:

clang/docs/ReleaseNotes.rst

- Add ``NextLineOnly`` style to option ``PackConstructorInitializers``.
   Compared to ``NextLine`` style, ``NextLineOnly`` style will not try to
   put the initializers on the current line first, instead, it will try to
   put the initializers on the next line only.
 - Add additional Qualifier Ordering support for special cases such
   as templates, requires clauses, long qualified names.
 - Fix all known issues associated with ``LambdaBodyIndentation: OuterScope``.
 - Add ``BracedInitializerIndentWidth`` which can be used to configure
   the indentation level of the contents of braced init lists.
+- Add ``KeepEmptyLinesAtEOF`` to keep empty lines at end of file.
 
 libclang
 --------
 
 - Introduced the new function ``clang_CXXMethod_isExplicit``,
   which identifies whether a constructor or conversion function cursor
   was marked with the explicit identifier.
 

clang/include/clang/Format/Format.h

   ///
   ///    false:
   ///    import {VeryLongImportsAreAnnoying, VeryLongImportsAreAnnoying, VeryLongImportsAreAnnoying,} from "some/module.js"
   /// \endcode
   /// \version 3.9
   bool JavaScriptWrapImports;
   // clang-format on
 
+  /// Keep empty lines (up to ``MaxEmptyLinesToKeep``) at end of file.
+  /// \version 17
+  bool KeepEmptyLinesAtEOF;
+
   /// If true, the empty line at the start of blocks is kept.
   /// \code
   ///    true:                                  false:
   ///    if (foo) {                     vs.     if (foo) {
   ///                                             bar();
   ///      bar();                               }
   ///    }
   /// \endcode
return AccessModifierOffset == R.AccessModifierOffset &&
            IndentWidth == R.IndentWidth &&
            IndentWrappedFunctionNames == R.IndentWrappedFunctionNames &&
            InsertBraces == R.InsertBraces &&
            InsertNewlineAtEOF == R.InsertNewlineAtEOF &&
            IntegerLiteralSeparator == R.IntegerLiteralSeparator &&
            JavaImportGroups == R.JavaImportGroups &&
            JavaScriptQuotes == R.JavaScriptQuotes &&
            JavaScriptWrapImports == R.JavaScriptWrapImports &&
+           KeepEmptyLinesAtEOF == R.KeepEmptyLinesAtEOF &&
            KeepEmptyLinesAtTheStartOfBlocks ==
                R.KeepEmptyLinesAtTheStartOfBlocks &&
            Language == R.Language &&
            LambdaBodyIndentation == R.LambdaBodyIndentation &&
            LineEnding == R.LineEnding && MacroBlockBegin == R.MacroBlockBegin &&
            MacroBlockEnd == R.MacroBlockEnd && Macros == R.Macros &&
            MaxEmptyLinesToKeep == R.MaxEmptyLinesToKeep &&
            NamespaceIndentation == R.NamespaceIndentation &&

clang/lib/Format/Format.cpp

static void mapping(IO &IO, FormatStyle &Style) {
     IO.mapOptional("InsertNewlineAtEOF", Style.InsertNewlineAtEOF);
     IO.mapOptional("InsertTrailingCommas", Style.InsertTrailingCommas);
     IO.mapOptional("IntegerLiteralSeparator", Style.IntegerLiteralSeparator);
     IO.mapOptional("JavaImportGroups", Style.JavaImportGroups);
     IO.mapOptional("JavaScriptQuotes", Style.JavaScriptQuotes);
     IO.mapOptional("JavaScriptWrapImports", Style.JavaScriptWrapImports);
     IO.mapOptional("KeepEmptyLinesAtTheStartOfBlocks",
                    Style.KeepEmptyLinesAtTheStartOfBlocks);
+    IO.mapOptional("KeepEmptyLinesAtEOF", Style.KeepEmptyLinesAtEOF);
     IO.mapOptional("LambdaBodyIndentation", Style.LambdaBodyIndentation);
     IO.mapOptional("LineEnding", Style.LineEnding);
     IO.mapOptional("MacroBlockBegin", Style.MacroBlockBegin);
     IO.mapOptional("MacroBlockEnd", Style.MacroBlockEnd);
     IO.mapOptional("MaxEmptyLinesToKeep", Style.MaxEmptyLinesToKeep);
     IO.mapOptional("NamespaceIndentation", Style.NamespaceIndentation);
     IO.mapOptional("NamespaceMacros", Style.NamespaceMacros);
     IO.mapOptional("ObjCBinPackProtocolList", Style.ObjCBinPackProtocolList);
FormatStyle getLLVMStyle(FormatStyle::LanguageKind Language) {
   LLVMStyle.InsertNewlineAtEOF = false;
   LLVMStyle.InsertTrailingCommas = FormatStyle::TCS_None;
   LLVMStyle.IntegerLiteralSeparator = {
       /*Binary=*/0,  /*BinaryMinDigits=*/0,
       /*Decimal=*/0, /*DecimalMinDigits=*/0,
       /*Hex=*/0,     /*HexMinDigits=*/0};
   LLVMStyle.JavaScriptQuotes = FormatStyle::JSQS_Leave;
   LLVMStyle.JavaScriptWrapImports = true;
+  LLVMStyle.KeepEmptyLinesAtEOF = false;
   LLVMStyle.KeepEmptyLinesAtTheStartOfBlocks = true;
   LLVMStyle.LambdaBodyIndentation = FormatStyle::LBI_Signature;
   LLVMStyle.LineEnding = FormatStyle::LE_DeriveLF;
   LLVMStyle.MaxEmptyLinesToKeep = 1;
   LLVMStyle.NamespaceIndentation = FormatStyle::NI_None;
   LLVMStyle.ObjCBinPackProtocolList = FormatStyle::BPS_Auto;
   LLVMStyle.ObjCBlockIndentWidth = 2;
   LLVMStyle.ObjCBreakBeforeNestedBlockParam = true;

clang/lib/Format/UnwrappedLineFormatter.cpp

 
 void UnwrappedLineFormatter::formatFirstToken(
     const AnnotatedLine &Line, const AnnotatedLine *PreviousLine,
     const AnnotatedLine *PrevPrevLine,
     const SmallVectorImpl<AnnotatedLine *> &Lines, unsigned Indent,
     unsigned NewlineIndent) {
   FormatToken &RootToken = *Line.First;
   if (RootToken.is(tok::eof)) {
-    unsigned Newlines = std::min(RootToken.NewlinesBefore, 1u);
+    unsigned Newlines =
+        std::min(RootToken.NewlinesBefore,
+                 Style.KeepEmptyLinesAtEOF ? Style.MaxEmptyLinesToKeep + 1 : 1);
     unsigned TokenIndent = Newlines ? NewlineIndent : 0;
     Whitespaces->replaceWhitespace(RootToken, Newlines, TokenIndent,
                                    TokenIndent);
     return;
   }
 
   const auto Newlines =
       RootToken.Finalized

clang/unittests/Format/ConfigParseTest.cpp

TEST(ConfigParseTest, ParsesConfigurationBools) {
   CHECK_PARSE_BOOL(IndentCaseLabels);
   CHECK_PARSE_BOOL(IndentCaseBlocks);
   CHECK_PARSE_BOOL(IndentGotoLabels);
   CHECK_PARSE_BOOL_FIELD(IndentRequiresClause, "IndentRequires");
   CHECK_PARSE_BOOL(IndentRequiresClause);
   CHECK_PARSE_BOOL(IndentWrappedFunctionNames);
   CHECK_PARSE_BOOL(InsertBraces);
   CHECK_PARSE_BOOL(InsertNewlineAtEOF);
+  CHECK_PARSE_BOOL(KeepEmptyLinesAtEOF);
   CHECK_PARSE_BOOL(KeepEmptyLinesAtTheStartOfBlocks);
   CHECK_PARSE_BOOL(ObjCSpaceAfterProperty);
   CHECK_PARSE_BOOL(ObjCSpaceBeforeProtocolList);
   CHECK_PARSE_BOOL(Cpp11BracedListStyle);
   CHECK_PARSE_BOOL(ReflowComments);
   CHECK_PARSE_BOOL(RemoveBracesLLVM);
   CHECK_PARSE_BOOL(RemoveSemicolon);
   CHECK_PARSE_BOOL(SpacesInParentheses);

clang/unittests/Format/FormatTest.cpp

 TEST_F(FormatTest, InsertNewlineAtEOF) {
   FormatStyle Style = getLLVMStyle();
   Style.InsertNewlineAtEOF = true;
 
   verifyFormat("int i;\n", Style);
   verifyFormat("int i;\n", "int i;", Style);
 }
 
+TEST_F(FormatTest, KeepEmptyLinesAtEOF) {
+  FormatStyle Style = getLLVMStyle();
+  Style.KeepEmptyLinesAtEOF = true;
+
+  const StringRef Code{"int i;\n\n"};
+  verifyFormat(Code, Code, Style);
+  verifyFormat(Code, "int i;\n\n\n", Style);
+}
+
 TEST_F(FormatTest, SpaceAfterUDL) {
   verifyFormat("auto c = (4s).count();");
   verifyFormat("auto x = 5s .count() == 5;");
 }
 
 TEST_F(FormatTest, InterfaceAsClassMemberName) {
   verifyFormat("class Foo {\n"
                "  int interface;\n"
                "  Foo::Foo(int iface) : interface{iface} {}\n"
                "}");
 }
 
 } // namespace
 } // namespace test
 } // namespace format
 } // namespace clang