[clang-format] Add a NamespaceEndCommentsFixer

Summary:
This patch adds a NamespaceEndCommentsFixer TokenAnalyzer for clang-format,
which fixes end namespace comments.
It currently supports inserting and updating existing wrong comments.

Example source:
```
namespace A {
int i;
}

namespace B {
int j;
} // namespace A
```

after formatting:
```
namespace A {
int i;
} // namespace A

namespace B {
int j;
} // namespace B
```

Reviewers: klimek, djasper

Reviewed By: djasper

Subscribers: klimek, mgorny

Differential Revision: https://reviews.llvm.org/D30269

llvm-svn: 296341

7 files changed, 229 insertions, 2 deletions

diff --git a/clang/lib/Format/CMakeLists.txt b/clang/lib/Format/CMakeLists.txt
index cb46b9f255d..0c7511c1bb0 100644
--- a/clang/lib/Format/CMakeLists.txt
+++ b/clang/lib/Format/CMakeLists.txt
@@ -7,6 +7,7 @@ add_clang_library(clangFormat
   Format.cpp
   FormatToken.cpp
   FormatTokenLexer.cpp
+  NamespaceEndCommentsFixer.cpp
   SortJavaScriptImports.cpp
   TokenAnalyzer.cpp
   TokenAnnotator.cpp
diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index a48bd37d4d9..99787408133 100644
--- a/clang/lib/Format/Format.cpp
+++ b/clang/lib/Format/Format.cpp
@@ -17,6 +17,7 @@
 #include "AffectedRangeManager.h"
 #include "ContinuationIndenter.h"
 #include "FormatTokenLexer.h"
+#include "NamespaceEndCommentsFixer.h"
 #include "SortJavaScriptImports.h"
 #include "TokenAnalyzer.h"
 #include "TokenAnnotator.h"
@@ -1857,6 +1858,16 @@ tooling::Replacements cleanup(const FormatStyle &Style, StringRef Code,
   return Clean.process();
 }
 
+tooling::Replacements fixNamespaceEndComments(const FormatStyle &Style,
+                                              StringRef Code,
+                                              ArrayRef<tooling::Range> Ranges,
+                                              StringRef FileName) {
+  std::unique_ptr<Environment> Env =
+      Environment::CreateVirtualEnvironment(Code, FileName, Ranges);
+  NamespaceEndCommentsFixer Fix(*Env, Style);
+  return Fix.process();
+}
+
 LangOptions getFormattingLangOpts(const FormatStyle &Style) {
   LangOptions LangOpts;
   LangOpts.CPlusPlus = 1;
diff --git a/clang/lib/Format/NamespaceEndCommentsFixer.cpp b/clang/lib/Format/NamespaceEndCommentsFixer.cpp
new file mode 100644
index 00000000000..495c34db754
--- /dev/null
+++ b/clang/lib/Format/NamespaceEndCommentsFixer.cpp
@@ -0,0 +1,165 @@
+//===--- NamespaceEndCommentsFixer.cpp --------------------------*- C++ -*-===//
+//
+//                     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 NamespaceEndCommentsFixer, a TokenAnalyzer that
+/// fixes namespace end comments.
+///
+//===----------------------------------------------------------------------===//
+
+#include "NamespaceEndCommentsFixer.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/Regex.h"
+
+#define DEBUG_TYPE "namespace-end-comments-fixer"
+
+namespace clang {
+namespace format {
+
+namespace {
+// The maximal number of lines that a short namespace spans.
+// Short namespaces don't need an end comment.
+static const int kShortNamespaceMaxLines = 1;
+
+// Matches a valid namespace end comment.
+// Valid namespace end comments don't need to be edited.
+static llvm::Regex kNamespaceCommentPattern =
+    llvm::Regex("^/[/*] *(end (of )?)? *(anonymous|unnamed)? *"
+                "namespace( +([a-zA-Z0-9:_]+))?\\.? *(\\*/)?$",
+                llvm::Regex::IgnoreCase);
+
+// Computes the name of a namespace given the namespace token.
+// Returns "" for anonymous namespace.
+std::string computeName(const FormatToken *NamespaceTok) {
+  assert(NamespaceTok && NamespaceTok->is(tok::kw_namespace) &&
+         "expecting a namespace token");
+  std::string name = "";
+  // Collects all the non-comment tokens between 'namespace' and '{'.
+  const FormatToken *Tok = NamespaceTok->getNextNonComment();
+  while (Tok && !Tok->is(tok::l_brace)) {
+    name += Tok->TokenText;
+    Tok = Tok->getNextNonComment();
+  }
+  return name;
+}
+
+std::string computeEndCommentText(StringRef NamespaceName, bool AddNewline) {
+  std::string text = "// namespace";
+  if (!NamespaceName.empty()) {
+    text += ' ';
+    text += NamespaceName;
+  }
+  if (AddNewline)
+    text += '\n';
+  return text;
+}
+
+bool isShort(const FormatToken *NamespaceTok, const FormatToken *RBraceTok,
+             const SourceManager &SourceMgr) {
+  int StartLine =
+      SourceMgr.getSpellingLineNumber(NamespaceTok->Tok.getLocation());
+  int EndLine = SourceMgr.getSpellingLineNumber(RBraceTok->Tok.getLocation());
+  return EndLine - StartLine + 1 <= kShortNamespaceMaxLines;
+}
+
+bool hasEndComment(const FormatToken *RBraceTok) {
+  return RBraceTok->Next && RBraceTok->Next->is(tok::comment);
+}
+
+bool validEndComment(const FormatToken *RBraceTok, StringRef NamespaceName) {
+  assert(hasEndComment(RBraceTok));
+  const FormatToken *Comment = RBraceTok->Next;
+  SmallVector<StringRef, 7> Groups;
+  if (kNamespaceCommentPattern.match(Comment->TokenText, &Groups)) {
+    StringRef NamespaceNameInComment = Groups.size() > 5 ? Groups[5] : "";
+    // Anonymous namespace comments must not mention a namespace name.
+    if (NamespaceName.empty() && !NamespaceNameInComment.empty())
+      return false;
+    StringRef AnonymousInComment = Groups.size() > 3 ? Groups[3] : "";
+    // Named namespace comments must not mention anonymous namespace.
+    if (!NamespaceName.empty() && !AnonymousInComment.empty())
+      return false;
+    return NamespaceNameInComment == NamespaceName;
+  }
+  return false;
+}
+
+void addEndComment(const FormatToken *RBraceTok, StringRef EndCommentText,
+                   const SourceManager &SourceMgr,
+                   tooling::Replacements *Fixes) {
+  auto EndLoc = RBraceTok->Tok.getEndLoc();
+  auto Range = CharSourceRange::getCharRange(EndLoc, EndLoc);
+  auto Err = Fixes->add(tooling::Replacement(SourceMgr, Range, EndCommentText));
+  if (Err) {
+    llvm::errs() << "Error while adding namespace end comment: "
+                 << llvm::toString(std::move(Err)) << "\n";
+  }
+}
+
+void updateEndComment(const FormatToken *RBraceTok, StringRef EndCommentText,
+                      const SourceManager &SourceMgr,
+                      tooling::Replacements *Fixes) {
+  assert(hasEndComment(RBraceTok));
+  const FormatToken *Comment = RBraceTok->Next;
+  auto Range = CharSourceRange::getCharRange(Comment->getStartOfNonWhitespace(),
+                                             Comment->Tok.getEndLoc());
+  auto Err = Fixes->add(tooling::Replacement(SourceMgr, Range, EndCommentText));
+  if (Err) {
+    llvm::errs() << "Error while updating namespace end comment: "
+                 << llvm::toString(std::move(Err)) << "\n";
+  }
+}
+} // namespace
+
+NamespaceEndCommentsFixer::NamespaceEndCommentsFixer(const Environment &Env,
+                                                     const FormatStyle &Style)
+    : TokenAnalyzer(Env, Style) {}
+
+tooling::Replacements NamespaceEndCommentsFixer::analyze(
+    TokenAnnotator &Annotator, SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
+    FormatTokenLexer &Tokens) {
+  const SourceManager &SourceMgr = Env.getSourceManager();
+  AffectedRangeMgr.computeAffectedLines(AnnotatedLines.begin(),
+                                        AnnotatedLines.end());
+  tooling::Replacements Fixes;
+  for (size_t I = 0, E = AnnotatedLines.size(); I != E; ++I) {
+    if (!AnnotatedLines[I]->Affected || AnnotatedLines[I]->InPPDirective ||
+        !AnnotatedLines[I]->startsWith(tok::r_brace))
+      continue;
+    const AnnotatedLine *EndLine = AnnotatedLines[I];
+    size_t StartLineIndex = EndLine->MatchingOpeningBlockLineIndex;
+    if (StartLineIndex == UnwrappedLine::kInvalidIndex)
+      continue;
+    assert(StartLineIndex < E);
+    const FormatToken *NamespaceTok = AnnotatedLines[StartLineIndex]->First;
+    // Detect "(inline)? namespace" in the beginning of a line.
+    if (NamespaceTok->is(tok::kw_inline))
+      NamespaceTok = NamespaceTok->getNextNonComment();
+    if (NamespaceTok->isNot(tok::kw_namespace))
+      continue;
+    const FormatToken *RBraceTok = EndLine->First;
+    const std::string NamespaceName = computeName(NamespaceTok);
+    bool AddNewline = (I + 1 < E) &&
+                      AnnotatedLines[I + 1]->First->NewlinesBefore == 0 &&
+                      AnnotatedLines[I + 1]->First->isNot(tok::eof);
+    const std::string EndCommentText =
+        computeEndCommentText(NamespaceName, AddNewline);
+    if (!hasEndComment(RBraceTok)) {
+      if (!isShort(NamespaceTok, RBraceTok, SourceMgr))
+        addEndComment(RBraceTok, EndCommentText, SourceMgr, &Fixes);
+      continue;
+    }
+    if (!validEndComment(RBraceTok, NamespaceName))
+      updateEndComment(RBraceTok, EndCommentText, SourceMgr, &Fixes);
+  }
+  return Fixes;
+}
+
+} // namespace format
+} // namespace clang
diff --git a/clang/lib/Format/NamespaceEndCommentsFixer.h b/clang/lib/Format/NamespaceEndCommentsFixer.h
new file mode 100644
index 00000000000..7790668a2e8
--- /dev/null
+++ b/clang/lib/Format/NamespaceEndCommentsFixer.h
@@ -0,0 +1,37 @@
+//===--- NamespaceEndCommentsFixer.h ----------------------------*- C++ -*-===//
+//
+//                     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 declares NamespaceEndCommentsFixer, a TokenAnalyzer that
+/// fixes namespace end comments.
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_LIB_FORMAT_NAMESPACEENDCOMMENTSFIXER_H
+#define LLVM_CLANG_LIB_FORMAT_NAMESPACEENDCOMMENTSFIXER_H
+
+#include "TokenAnalyzer.h"
+
+namespace clang {
+namespace format {
+
+class NamespaceEndCommentsFixer : public TokenAnalyzer {
+public:
+  NamespaceEndCommentsFixer(const Environment &Env, const FormatStyle &Style);
+
+  tooling::Replacements
+  analyze(TokenAnnotator &Annotator,
+          SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
+          FormatTokenLexer &Tokens) override;
+};
+
+} // end namespace format
+} // end namespace clang
+
+#endif
diff --git a/clang/lib/Format/TokenAnnotator.h b/clang/lib/Format/TokenAnnotator.h
index 09b25958b3d..805509533bf 100644
--- a/clang/lib/Format/TokenAnnotator.h
+++ b/clang/lib/Format/TokenAnnotator.h
@@ -39,6 +39,7 @@ class AnnotatedLine {
 public:
   AnnotatedLine(const UnwrappedLine &Line)
       : First(Line.Tokens.front().Tok), Level(Line.Level),
+        MatchingOpeningBlockLineIndex(Line.MatchingOpeningBlockLineIndex),
         InPPDirective(Line.InPPDirective),
         MustBeDeclaration(Line.MustBeDeclaration), MightBeFunctionDecl(false),
         IsMultiVariableDeclStmt(false), Affected(false),
@@ -109,6 +110,7 @@ public:
 
   LineType Type;
   unsigned Level;
+  size_t MatchingOpeningBlockLineIndex;
   bool InPPDirective;
   bool MustBeDeclaration;
   bool MightBeFunctionDecl;
diff --git a/clang/lib/Format/UnwrappedLineParser.cpp b/clang/lib/Format/UnwrappedLineParser.cpp
index ab343d8bbed..9a536ad6019 100644
--- a/clang/lib/Format/UnwrappedLineParser.cpp
+++ b/clang/lib/Format/UnwrappedLineParser.cpp
@@ -428,6 +428,8 @@ void UnwrappedLineParser::parseBlock(bool MustBeDeclaration, bool AddLevel,
     parseParens();
 
   addUnwrappedLine();
+  size_t OpeningLineIndex =
+      Lines.empty() ? (UnwrappedLine::kInvalidIndex) : (Lines.size() - 1);
 
   ScopedDeclarationState DeclarationState(*Line, DeclarationScopeStack,
                                           MustBeDeclaration);
@@ -453,6 +455,7 @@ void UnwrappedLineParser::parseBlock(bool MustBeDeclaration, bool AddLevel,
   if (MunchSemi && FormatTok->Tok.is(tok::semi))
     nextToken();
   Line->Level = InitialLevel;
+  Line->MatchingOpeningBlockLineIndex = OpeningLineIndex;
 }
 
 static bool isGoogScope(const UnwrappedLine &Line) {
diff --git a/clang/lib/Format/UnwrappedLineParser.h b/clang/lib/Format/UnwrappedLineParser.h
index 6cea8cdc036..15d1d9cda7a 100644
--- a/clang/lib/Format/UnwrappedLineParser.h
+++ b/clang/lib/Format/UnwrappedLineParser.h
@@ -48,6 +48,14 @@ struct UnwrappedLine {
   bool InPPDirective;
 
   bool MustBeDeclaration;
+
+  /// \brief If this \c UnwrappedLine closes a block in a sequence of lines,
+  /// \c MatchingOpeningBlockLineIndex stores the index of the corresponding
+  /// opening line. Otherwise, \c MatchingOpeningBlockLineIndex must be
+  /// \c kInvalidIndex.
+  size_t MatchingOpeningBlockLineIndex;
+
+  static const size_t kInvalidIndex = -1;
 };
 
 class UnwrappedLineConsumer {
@@ -234,8 +242,8 @@ struct UnwrappedLineNode {
   SmallVector<UnwrappedLine, 0> Children;
 };
 
-inline UnwrappedLine::UnwrappedLine()
-    : Level(0), InPPDirective(false), MustBeDeclaration(false) {}
+inline UnwrappedLine::UnwrappedLine() : Level(0), InPPDirective(false),
+  MustBeDeclaration(false), MatchingOpeningBlockLineIndex(kInvalidIndex) {}
 
 } // end namespace format
 } // end namespace clang