[clang-format] Indent after breaking Javadoc annotated line

Summary:
This patch makes clang-format indent the subsequent lines created by breaking a
long javadoc annotated line.

Reviewers: mprobst

Reviewed By: mprobst

Subscribers: acoomans, cfe-commits

Differential Revision: https://reviews.llvm.org/D49797

llvm-svn: 338232

4 files changed, 96 insertions, 15 deletions

diff --git a/clang/lib/Format/BreakableToken.cpp b/clang/lib/Format/BreakableToken.cpp
index cc68f70100e..9974ed0a518 100644
--- a/clang/lib/Format/BreakableToken.cpp
+++ b/clang/lib/Format/BreakableToken.cpp
@@ -235,6 +235,7 @@ BreakableToken::Split BreakableStringLiteral::getSplit(
 
 void BreakableStringLiteral::insertBreak(unsigned LineIndex,
                                          unsigned TailOffset, Split Split,
+                                         unsigned ContentIndent,
                                          WhitespaceManager &Whitespaces) const {
   Whitespaces.replaceWhitespaceInToken(
       Tok, Prefix.size() + TailOffset + Split.first, Split.second, Postfix,
@@ -510,8 +511,33 @@ unsigned BreakableBlockComment::getContentStartColumn(unsigned LineIndex,
   return std::max(0, ContentColumn[LineIndex]);
 }
 
+const llvm::StringSet<>
+    BreakableBlockComment::ContentIndentingJavadocAnnotations = {
+        "@param", "@return",     "@returns", "@throws",  "@type", "@template",
+        "@see",   "@deprecated", "@define",  "@exports", "@mods",
+};
+
+unsigned BreakableBlockComment::getContentIndent(unsigned LineIndex) const {
+  if (Style.Language != FormatStyle::LK_Java &&
+      Style.Language != FormatStyle::LK_JavaScript)
+    return 0;
+  // The content at LineIndex 0 of a comment like:
+  // /** line 0 */
+  // is "* line 0", so we need to skip over the decoration in that case.
+  StringRef ContentWithNoDecoration = Content[LineIndex];
+  if (LineIndex == 0 && ContentWithNoDecoration.startswith("*")) {
+    ContentWithNoDecoration = ContentWithNoDecoration.substr(1).ltrim(Blanks);
+  }
+  StringRef FirstWord = ContentWithNoDecoration.substr(
+      0, ContentWithNoDecoration.find_first_of(Blanks));
+  if (ContentIndentingJavadocAnnotations.find(FirstWord) !=
+      ContentIndentingJavadocAnnotations.end())
+    return Style.ContinuationIndentWidth;
+  return 0;
+}
+
 void BreakableBlockComment::insertBreak(unsigned LineIndex, unsigned TailOffset,
-                                        Split Split,
+                                        Split Split, unsigned ContentIndent,
                                         WhitespaceManager &Whitespaces) const {
   StringRef Text = Content[LineIndex].substr(TailOffset);
   StringRef Prefix = Decoration;
@@ -532,10 +558,14 @@ void BreakableBlockComment::insertBreak(unsigned LineIndex, unsigned TailOffset,
       Text.data() - tokenAt(LineIndex).TokenText.data() + Split.first;
   unsigned CharsToRemove = Split.second;
   assert(LocalIndentAtLineBreak >= Prefix.size());
+  std::string PrefixWithTrailingIndent = Prefix;
+  for (unsigned I = 0; I < ContentIndent; ++I)
+    PrefixWithTrailingIndent += " ";
   Whitespaces.replaceWhitespaceInToken(
-      tokenAt(LineIndex), BreakOffsetInToken, CharsToRemove, "", Prefix,
-      InPPDirective, /*Newlines=*/1,
-      /*Spaces=*/LocalIndentAtLineBreak - Prefix.size());
+      tokenAt(LineIndex), BreakOffsetInToken, CharsToRemove, "",
+      PrefixWithTrailingIndent, InPPDirective, /*Newlines=*/1,
+      /*Spaces=*/LocalIndentAtLineBreak + ContentIndent -
+          PrefixWithTrailingIndent.size());
 }
 
 BreakableToken::Split
@@ -543,8 +573,17 @@ BreakableBlockComment::getReflowSplit(unsigned LineIndex,
                                       llvm::Regex &CommentPragmasRegex) const {
   if (!mayReflow(LineIndex, CommentPragmasRegex))
     return Split(StringRef::npos, 0);
-
+  
+  // If we're reflowing into a line with content indent, only reflow the next
+  // line if its starting whitespace matches the content indent.
   size_t Trimmed = Content[LineIndex].find_first_not_of(Blanks);
+  if (LineIndex) {
+    unsigned PreviousContentIndent = getContentIndent(LineIndex - 1);
+    if (PreviousContentIndent && Trimmed != StringRef::npos &&
+        Trimmed != PreviousContentIndent)
+      return Split(StringRef::npos, 0);
+  }
+
   return Split(0, Trimmed != StringRef::npos ? Trimmed : 0);
 }
 
@@ -583,7 +622,8 @@ void BreakableBlockComment::adaptStartOfLine(
       // break length are the same.
       size_t BreakLength = Lines[0].substr(1).find_first_not_of(Blanks);
       if (BreakLength != StringRef::npos)
-        insertBreak(LineIndex, 0, Split(1, BreakLength), Whitespaces);
+        insertBreak(LineIndex, 0, Split(1, BreakLength), /*ContentIndent=*/0,
+                    Whitespaces);
     }
     return;
   }
@@ -754,7 +794,7 @@ unsigned BreakableLineCommentSection::getContentStartColumn(unsigned LineIndex,
 
 void BreakableLineCommentSection::insertBreak(
     unsigned LineIndex, unsigned TailOffset, Split Split,
-    WhitespaceManager &Whitespaces) const {
+    unsigned ContentIndent, WhitespaceManager &Whitespaces) const {
   StringRef Text = Content[LineIndex].substr(TailOffset);
   // Compute the offset of the split relative to the beginning of the token
   // text.
diff --git a/clang/lib/Format/BreakableToken.h b/clang/lib/Format/BreakableToken.h
index 0fac8f08c02..a2a818f9114 100644
--- a/clang/lib/Format/BreakableToken.h
+++ b/clang/lib/Format/BreakableToken.h
@@ -21,6 +21,7 @@
 #include "Encoding.h"
 #include "TokenAnnotator.h"
 #include "WhitespaceManager.h"
+#include "llvm/ADT/StringSet.h"
 #include "llvm/Support/Regex.h"
 #include <utility>
 
@@ -135,6 +136,19 @@ public:
   virtual unsigned getContentStartColumn(unsigned LineIndex,
                                          bool Break) const = 0;
 
+  /// Returns additional content indent required for the second line after the
+  /// content at line \p LineIndex is broken.
+  ///
+  /// For example, Javadoc @param annotations require and indent of 4 spaces and
+  /// in this example getContentIndex(1) returns 4.
+  /// /**
+  ///  * @param loooooooooooooong line
+  ///  *     continuation
+  ///  */
+  virtual unsigned getContentIndent(unsigned LineIndex) const {
+    return 0;
+  }
+
   /// Returns a range (offset, length) at which to break the line at
   /// \p LineIndex, if previously broken at \p TailOffset. If possible, do not
   /// violate \p ColumnLimit, assuming the text starting at \p TailOffset in
@@ -146,6 +160,7 @@ public:
 
   /// Emits the previously retrieved \p Split via \p Whitespaces.
   virtual void insertBreak(unsigned LineIndex, unsigned TailOffset, Split Split,
+                           unsigned ContentIndent,
                            WhitespaceManager &Whitespaces) const = 0;
 
   /// Returns the number of columns needed to format
@@ -210,7 +225,7 @@ public:
                                       Split SplitAfterLastLine,
                                       WhitespaceManager &Whitespaces) const {
     insertBreak(getLineCount() - 1, TailOffset, SplitAfterLastLine,
-                Whitespaces);
+                /*ContentIndent=*/0, Whitespaces);
   }
 
   /// Updates the next token of \p State to the next token after this
@@ -245,6 +260,7 @@ public:
                  unsigned ContentStartColumn,
                  llvm::Regex &CommentPragmasRegex) const override;
   void insertBreak(unsigned LineIndex, unsigned TailOffset, Split Split,
+                   unsigned ContentIndent,
                    WhitespaceManager &Whitespaces) const override;
   void compressWhitespace(unsigned LineIndex, unsigned TailOffset, Split Split,
                           WhitespaceManager &Whitespaces) const override {}
@@ -354,7 +370,9 @@ public:
   unsigned getRemainingLength(unsigned LineIndex, unsigned Offset,
                               unsigned StartColumn) const override;
   unsigned getContentStartColumn(unsigned LineIndex, bool Break) const override;
+  unsigned getContentIndent(unsigned LineIndex) const override;
   void insertBreak(unsigned LineIndex, unsigned TailOffset, Split Split,
+                   unsigned ContentIndent,
                    WhitespaceManager &Whitespaces) const override;
   Split getReflowSplit(unsigned LineIndex,
                        llvm::Regex &CommentPragmasRegex) const override;
@@ -368,6 +386,10 @@ public:
   bool mayReflow(unsigned LineIndex,
                  llvm::Regex &CommentPragmasRegex) const override;
 
+  // Contains Javadoc annotations that require additional indent when continued
+  // on multiple lines.
+  static const llvm::StringSet<> ContentIndentingJavadocAnnotations;
+
 private:
   // Rearranges the whitespace between Lines[LineIndex-1] and Lines[LineIndex].
   //
@@ -423,6 +445,7 @@ public:
                           unsigned StartColumn) const override;
   unsigned getContentStartColumn(unsigned LineIndex, bool Break) const override;
   void insertBreak(unsigned LineIndex, unsigned TailOffset, Split Split,
+                   unsigned ContentIndent,
                    WhitespaceManager &Whitespaces) const override;
   Split getReflowSplit(unsigned LineIndex,
                        llvm::Regex &CommentPragmasRegex) const override;
diff --git a/clang/lib/Format/ContinuationIndenter.cpp b/clang/lib/Format/ContinuationIndenter.cpp
index 90d2a999711..7ca588a675b 100644
--- a/clang/lib/Format/ContinuationIndenter.cpp
+++ b/clang/lib/Format/ContinuationIndenter.cpp
@@ -1809,6 +1809,7 @@ ContinuationIndenter::breakProtrudingToken(const FormatToken &Current,
   if (!DryRun)
     Token->adaptStartOfLine(0, Whitespaces);
 
+  unsigned ContentIndent = 0;
   unsigned Penalty = 0;
   LLVM_DEBUG(llvm::dbgs() << "Breaking protruding token at column "
                           << StartColumn << ".\n");
@@ -1930,11 +1931,28 @@ ContinuationIndenter::breakProtrudingToken(const FormatToken &Current,
         }
       }
       LLVM_DEBUG(llvm::dbgs() << "    Breaking...\n");
-      ContentStartColumn =
-          Token->getContentStartColumn(LineIndex, /*Break=*/true);
+      // Update the ContentIndent only if the current line was not reflown with
+      // the previous line, since in that case the previous line should still
+      // determine the ContentIndent. Also never intent the last line.
+      if (!Reflow)
+        ContentIndent = Token->getContentIndent(LineIndex);
+      LLVM_DEBUG(llvm::dbgs()
+                 << "    ContentIndent: " << ContentIndent << "\n");
+      ContentStartColumn = ContentIndent + Token->getContentStartColumn(
+                                               LineIndex, /*Break=*/true);
+
       unsigned NewRemainingTokenColumns = Token->getRemainingLength(
           LineIndex, TailOffset + Split.first + Split.second,
           ContentStartColumn);
+      if (NewRemainingTokenColumns == 0) {
+        // No content to indent.
+        ContentIndent = 0;
+        ContentStartColumn =
+            Token->getContentStartColumn(LineIndex, /*Break=*/true);
+        NewRemainingTokenColumns = Token->getRemainingLength(
+            LineIndex, TailOffset + Split.first + Split.second,
+            ContentStartColumn);
+      }
 
       // When breaking before a tab character, it may be moved by a few columns,
       // but will still be expanded to the next tab stop, so we don't save any
@@ -1948,7 +1966,8 @@ ContinuationIndenter::breakProtrudingToken(const FormatToken &Current,
       LLVM_DEBUG(llvm::dbgs() << "    Breaking at: " << TailOffset + Split.first
                               << ", " << Split.second << "\n");
       if (!DryRun)
-        Token->insertBreak(LineIndex, TailOffset, Split, Whitespaces);
+        Token->insertBreak(LineIndex, TailOffset, Split, ContentIndent,
+                           Whitespaces);
 
       Penalty += NewBreakPenalty;
       TailOffset += Split.first + Split.second;
diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index 59d34308c0a..ec96eaa98d0 100644
--- a/clang/lib/Format/Format.cpp
+++ b/clang/lib/Format/Format.cpp
@@ -808,10 +808,9 @@ FormatStyle getGoogleStyle(FormatStyle::LanguageKind Language) {
     GoogleStyle.AllowShortFunctionsOnASingleLine = FormatStyle::SFS_Empty;
     GoogleStyle.AlwaysBreakBeforeMultilineStrings = false;
     GoogleStyle.BreakBeforeTernaryOperators = false;
-    // taze:, triple slash directives (`/// <...`), @tag followed by { for a lot
-    // of JSDoc tags, and @see, which is commonly followed by overlong URLs.
-    GoogleStyle.CommentPragmas =
-        "(taze:|^/[ \t]*<|(@[A-Za-z_0-9-]+[ \\t]*{)|@see)";
+    // taze:, triple slash directives (`/// <...`), @see, which is commonly
+    // followed by overlong URLs.
+    GoogleStyle.CommentPragmas = "(taze:|^/[ \t]*<|@see)";
     GoogleStyle.MaxEmptyLinesToKeep = 3;
     GoogleStyle.NamespaceIndentation = FormatStyle::NI_All;
     GoogleStyle.SpacesInContainerLiterals = false;