[clang-format] Emit absolute splits before lines for comments, try 2

[krasimir]

Summary

This recommits https://reviews.llvm.org/D36956 with an update to the added test
case to not use raw string literals, since this makes gcc unhappy.

[djasper]

Does the test still test the same thing if you set the column limit to 60 and remove 20 spaces? If not, this is fine.

[krasimir]

@djasper: No. The test case is a special constellation.

lib/Format/BreakableToken.cpp

void BreakableBlockComment::insertBreak(unsigned LineIndex, unsigned TailOffset,
   assert(LocalIndentAtLineBreak >= Prefix.size());
   Whitespaces.replaceWhitespaceInToken(
       tokenAt(LineIndex), BreakOffsetInToken, CharsToRemove, "", Prefix,
       InPPDirective, /*Newlines=*/1,
       /*Spaces=*/LocalIndentAtLineBreak - Prefix.size());
 }
 
 BreakableToken::Split BreakableBlockComment::getSplitBefore(
-    unsigned LineIndex,
-    unsigned PreviousEndColumn,
-    unsigned ColumnLimit,
+    unsigned LineIndex, unsigned PreviousEndColumn, unsigned ColumnLimit,
     llvm::Regex &CommentPragmasRegex) const {
   if (!mayReflow(LineIndex, CommentPragmasRegex))
     return Split(StringRef::npos, 0);
   StringRef TrimmedContent = Content[LineIndex].ltrim(Blanks);
-  return getReflowSplit(TrimmedContent, ReflowPrefix, PreviousEndColumn,
+  Split Result = getReflowSplit(TrimmedContent, ReflowPrefix, PreviousEndColumn,
                                 ColumnLimit);
+  // Result is relative to TrimmedContent. Adapt it relative to
+  // Content[LineIndex].
+  if (Result.first != StringRef::npos)
+    Result.first += Content[LineIndex].size() - TrimmedContent.size();
+  return Result;
 }
 
 unsigned BreakableBlockComment::getReflownColumn(
     StringRef Content,
     unsigned LineIndex,
     unsigned PreviousEndColumn) const {
     unsigned StartColumn = PreviousEndColumn + ReflowPrefix.size();
     // If this is the last line, it will carry around its '*/' postfix.
unsigned WhitespaceLength = TrimmedContent.data() -
         tokenAt(LineIndex).TokenText.data() -
         WhitespaceOffsetInToken;
     Whitespaces.replaceWhitespaceInToken(
         tokenAt(LineIndex), WhitespaceOffsetInToken,
         /*ReplaceChars=*/WhitespaceLength, /*PreviousPostfix=*/"",
         /*CurrentPrefix=*/ReflowPrefix, InPPDirective, /*Newlines=*/0,
         /*Spaces=*/0);
     // Check if we need to also insert a break at the whitespace range.
-    // For this we first adapt the reflow split relative to the beginning of the
-    // content.
     // Note that we don't need a penalty for this break, since it doesn't change
     // the total number of lines.
-    Split BreakSplit = SplitBefore;
-    BreakSplit.first += TrimmedContent.data() - Content[LineIndex].data();
     unsigned ReflownColumn =
         getReflownColumn(TrimmedContent, LineIndex, PreviousEndColumn);
-    if (ReflownColumn > ColumnLimit) {
-      insertBreak(LineIndex, 0, BreakSplit, Whitespaces);
-    }
+    if (ReflownColumn > ColumnLimit)
+      insertBreak(LineIndex, 0, SplitBefore, Whitespaces);
     return;
   }
 
   // Here no reflow with the previous line will happen.
   // Fix the decoration of the line at LineIndex.
   StringRef Prefix = Decoration;
   if (Content[LineIndex].empty()) {
     if (LineIndex + 1 == Lines.size()) {

unittests/Format/FormatTestComments.cpp

EXPECT_EQ("/*\n"
             " * long */",
             format("/*\n"
                    " * long long long long\n"
                    " * long\n"
                    "  *\n"
                    "* long */",
                    getLLVMStyleWithColumns(20)));
 }
+
+TEST_F(FormatTestComments, NoCrush_Bug34236) {
+  // This is a test case from a crasher reported in:
+  // https://bugs.llvm.org/show_bug.cgi?id=34236
+  // Temporarily disable formatting for readability.
+  // clang-format off
+  EXPECT_EQ(
+"/*                                                                */ /*\n"
+"                                                                      *       a\n"
+"                                                                      * b c\n"
+"                                                                      * d*/",
+      format(
+"/*                                                                */ /*\n"
+" *       a b\n"
+" *       c     d*/",
+          getLLVMStyleWithColumns(80)));
+  // clang-format on
+}
 } // end namespace
 } // end namespace format
 } // end namespace clang