Make clang-format cleaner remove redundant commas in list and redundant colon in constructor initializer.

Summary: Make clang-format cleaner remove redundant commas/colons in constructor initializer list.

Reviewers: klimek, djasper

Subscribers: cfe-commits, klimek

Differential Revision: http://reviews.llvm.org/D19804

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@269888 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Format/Format.cpp

@@ -1765,6 +1765,15 @@ public:
 
     checkEmptyNamespace(AnnotatedLines);
 
+    for (auto &Line : AnnotatedLines) {
+      if (Line->Affected) {
+        cleanupRight(Line->First, tok::comma, tok::comma);
+        cleanupRight(Line->First, TT_CtorInitializerColon, tok::comma);
+        cleanupLeft(Line->First, TT_CtorInitializerComma, tok::l_brace);
+        cleanupLeft(Line->First, TT_CtorInitializerColon, tok::l_brace);
+      }
+    }
+
     return generateFixes();
   }
 
@@ -1853,6 +1862,45 @@ private:
     return true;
   }
 
+  // Checks pairs {start, start->next},..., {end->previous, end} and deletes one
+  // of the token in the pair if the left token has \p LK token kind and the
+  // right token has \p RK token kind. If \p DeleteLeft is true, the left token
+  // is deleted on match; otherwise, the right token is deleted.
+  template <typename LeftKind, typename RightKind>
+  void cleanupPair(FormatToken *Start, LeftKind LK, RightKind RK,
+                   bool DeleteLeft) {
+    auto NextNotDeleted = [this](const FormatToken &Tok) -> FormatToken * {
+      for (auto *Res = Tok.Next; Res; Res = Res->Next)
+        if (!Res->is(tok::comment) &&
+            DeletedTokens.find(Res) == DeletedTokens.end())
+          return Res;
+      return nullptr;
+    };
+    for (auto *Left = Start; Left;) {
+      auto *Right = NextNotDeleted(*Left);
+      if (!Right)
+        break;
+      if (Left->is(LK) && Right->is(RK)) {
+        deleteToken(DeleteLeft ? Left : Right);
+        // If the right token is deleted, we should keep the left token
+        // unchanged and pair it with the new right token.
+        if (!DeleteLeft)
+          continue;
+      }
+      Left = Right;
+    }
+  }
+
+  template <typename LeftKind, typename RightKind>
+  void cleanupLeft(FormatToken *Start, LeftKind LK, RightKind RK) {
+    cleanupPair(Start, LK, RK, /*DeleteLeft=*/true);
+  }
+
+  template <typename LeftKind, typename RightKind>
+  void cleanupRight(FormatToken *Start, LeftKind LK, RightKind RK) {
+    cleanupPair(Start, LK, RK, /*DeleteLeft=*/false);
+  }
+
   // Delete the given token.
   inline void deleteToken(FormatToken *Tok) {
     if (Tok)

lib/Format/TokenAnnotator.cpp

@@ -920,6 +920,10 @@ private:
       Contexts.back().IsExpression = false;
     } else if (Current.is(TT_LambdaArrow) || Current.is(Keywords.kw_assert)) {
       Contexts.back().IsExpression = Style.Language == FormatStyle::LK_Java;
+    } else if (Current.Previous &&
+               Current.Previous->is(TT_CtorInitializerColon)) {
+      Contexts.back().IsExpression = true;
+      Contexts.back().InCtorInitializer = true;
     } else if (Current.isOneOf(tok::r_paren, tok::greater, tok::comma)) {
       for (FormatToken *Previous = Current.Previous;
            Previous && Previous->isOneOf(tok::star, tok::amp);
@@ -927,10 +931,6 @@ private:
         Previous->Type = TT_PointerOrReference;
       if (Line.MustBeDeclaration && !Contexts.front().InCtorInitializer)
         Contexts.back().IsExpression = false;
-    } else if (Current.Previous &&
-               Current.Previous->is(TT_CtorInitializerColon)) {
-      Contexts.back().IsExpression = true;
-      Contexts.back().InCtorInitializer = true;
     } else if (Current.is(tok::kw_new)) {
       Contexts.back().CanBeExpression = false;
     } else if (Current.isOneOf(tok::semi, tok::exclaim)) {

unittests/Format/CleanupTest.cpp

@@ -113,6 +113,133 @@ TEST_F(CleanupTest, EmptyNamespaceWithCommentsBreakBeforeBrace) {
   EXPECT_EQ(Expected, Result);
 }
 
+TEST_F(CleanupTest, CtorInitializationSimpleRedundantComma) {
+  std::string Code = "class A {\nA() : , {} };";
+  std::string Expected = "class A {\nA()  {} };";
+  std::vector<tooling::Range> Ranges;
+  Ranges.push_back(tooling::Range(17, 0));
+  Ranges.push_back(tooling::Range(19, 0));
+  std::string Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+
+  Code = "class A {\nA() : x(1), {} };";
+  Expected = "class A {\nA() : x(1) {} };";
+  Ranges.clear();
+  Ranges.push_back(tooling::Range(23, 0));
+  Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+
+  Code = "class A {\nA() :,,,,{} };";
+  Expected = "class A {\nA() {} };";
+  Ranges.clear();
+  Ranges.push_back(tooling::Range(15, 0));
+  Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+}
+
+TEST_F(CleanupTest, ListSimpleRedundantComma) {
+  std::string Code = "void f() { std::vector<int> v = {1,2,,,3,{4,5}}; }";
+  std::string Expected = "void f() { std::vector<int> v = {1,2,3,{4,5}}; }";
+  std::vector<tooling::Range> Ranges;
+  Ranges.push_back(tooling::Range(40, 0));
+  std::string Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+
+  Code = "int main() { f(1,,2,3,,4);}";
+  Expected = "int main() { f(1,2,3,4);}";
+  Ranges.clear();
+  Ranges.push_back(tooling::Range(17, 0));
+  Ranges.push_back(tooling::Range(22, 0));
+  Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+}
+
+TEST_F(CleanupTest, CtorInitializationBracesInParens) {
+  std::string Code = "class A {\nA() : x({1}),, {} };";
+  std::string Expected = "class A {\nA() : x({1}) {} };";
+  std::vector<tooling::Range> Ranges;
+  Ranges.push_back(tooling::Range(24, 0));
+  Ranges.push_back(tooling::Range(26, 0));
+  std::string Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+}
+
+TEST_F(CleanupTest, RedundantCommaNotInAffectedRanges) {
+  std::string Code =
+      "class A {\nA() : x({1}), /* comment */, { int x = 0; } };";
+  std::string Expected =
+      "class A {\nA() : x({1}), /* comment */, { int x = 0; } };";
+  // Set the affected range to be "int x = 0", which does not intercept the
+  // constructor initialization list.
+  std::vector<tooling::Range> Ranges(1, tooling::Range(42, 9));
+  std::string Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+
+  Code = "class A {\nA() : x(1), {} };";
+  Expected = "class A {\nA() : x(1), {} };";
+  // No range. Fixer should do nothing.
+  Ranges.clear();
+  Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+}
+
+// FIXME: delete comments too.
+TEST_F(CleanupTest, CtorInitializationCommentAroundCommas) {
+  // Remove redundant commas around comment.
+  std::string Code = "class A {\nA() : x({1}), /* comment */, {} };";
+  std::string Expected = "class A {\nA() : x({1}) /* comment */ {} };";
+  std::vector<tooling::Range> Ranges;
+  Ranges.push_back(tooling::Range(25, 0));
+  Ranges.push_back(tooling::Range(40, 0));
+  std::string Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+
+  // Remove trailing comma and ignore comment.
+  Code = "class A {\nA() : x({1}), // comment\n{} };";
+  Expected = "class A {\nA() : x({1}) // comment\n{} };";
+  Ranges = std::vector<tooling::Range>(1, tooling::Range(25, 0));
+  Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+
+  // Remove trailing comma and ignore comment.
+  Code = "class A {\nA() : x({1}), // comment\n , y(1),{} };";
+  Expected = "class A {\nA() : x({1}), // comment\n  y(1){} };";
+  Ranges = std::vector<tooling::Range>(1, tooling::Range(38, 0));
+  Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+
+  // Remove trailing comma and ignore comment.
+  Code = "class A {\nA() : x({1}), \n/* comment */, y(1),{} };";
+  Expected = "class A {\nA() : x({1}), \n/* comment */ y(1){} };";
+  Ranges = std::vector<tooling::Range>(1, tooling::Range(40, 0));
+  Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+
+  // Remove trailing comma and ignore comment.
+  Code = "class A {\nA() : , // comment\n y(1),{} };";
+  Expected = "class A {\nA() :  // comment\n y(1){} };";
+  Ranges = std::vector<tooling::Range>(1, tooling::Range(17, 0));
+  Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+}
+
+TEST_F(CleanupTest, CtorInitializerInNamespace) {
+  std::string Code = "namespace A {\n"
+                     "namespace B {\n" // missing r_brace
+                     "} // namespace A\n\n"
+                     "namespace C {\n"
+                     "class A { A() : x(0),, {} };\n"
+                     "inline namespace E { namespace { } }\n"
+                     "}";
+  std::string Expected = "namespace A {\n"
+                         "\n\n\nnamespace C {\n"
+                         "class A { A() : x(0) {} };\n   \n"
+                         "}";
+  std::vector<tooling::Range> Ranges(1, tooling::Range(0, Code.size()));
+  std::string Result = cleanup(Code, Ranges);
+  EXPECT_EQ(Expected, Result);
+}
+
 } // end namespace
 } // end namespace format
 } // end namespace clang