[clang-format] Fix raw string prefix penalty

[krasimir]

Summary

We weren't penalizing cases where the raw string prefix goes over the column limit.

lib/Format/ContinuationIndenter.cpp

for (const tooling::Replacement &Fix : Fixes.first) {
         llvm::errs() << "Failed to reformat raw string: "
                      << llvm::toString(std::move(Err)) << "\n";
       }
     }
   }
   unsigned RawLastLineEndColumn = getLastLineEndColumn(
       *NewCode, FirstStartColumn, Style.TabWidth, Encoding);
   State.Column = RawLastLineEndColumn + NewSuffixSize;
-  return Fixes.second;
+  // Since we're updating the column to after the raw string literal here, we
+  // have to manually add the penalty for the prefix R"delim( over the column
+  // limit.
+  unsigned PrefixExcessCharacters =
+      StartColumn + NewPrefixSize > Style.ColumnLimit ?
+      StartColumn + NewPrefixSize - Style.ColumnLimit : 0;
+  return Fixes.second + PrefixExcessCharacters * Style.PenaltyExcessCharacter;
 }
 
 unsigned ContinuationIndenter::addMultilineToken(const FormatToken &Current,
                                                  LineState &State) {
   // Break before further function parameters on all levels.
   for (unsigned i = 0, e = State.Stack.size(); i != e; ++i)
     State.Stack[i].BreakBeforeParameter = true;
 

unittests/Format/FormatTestRawStrings.cpp

expect_eq(R"test(a = R"proto(key: value)proto";)test",
             format(R"test(a = R"pb(key:value)pb";)test", Style));
 
   // Don't update to canonical delimiter if it occurs as a raw string suffix in
   // the raw string content.
   expect_eq(R"test(a = R"pb(key: ")proto")pb";)test",
             format(R"test(a = R"pb(key:")proto")pb";)test", Style));
 }
 
+TEST_F(FormatTestRawStrings, PenalizesPrefixExcessChars) {
+  FormatStyle Style = getRawStringPbStyleWithColumns(60);
+
+  // The '(' in R"pb is at column 60, no break.
+  expect_eq(R"test(
+xxxxxxxaaaaax wwwwwww = _Verxrrrrrrrr(PARSE_TEXT_PROTO(R"pb(
+  Category: aaaaaaaaaaaaaaaaaaaaaaaaaa
+)pb"));
+)test",
+            format(R"test(
+xxxxxxxaaaaax wwwwwww = _Verxrrrrrrrr(PARSE_TEXT_PROTO(R"pb(
+  Category: aaaaaaaaaaaaaaaaaaaaaaaaaa
+)pb"));
+)test", Style));
+  // The '(' in R"pb is at column 61, break.
+  expect_eq(R"test(
+xxxxxxxaaaaax wwwwwww =
+    _Verxrrrrrrrrr(PARSE_TEXT_PROTO(R"pb(
+      Category: aaaaaaaaaaaaaaaaaaaaaaaaaa
+    )pb"));
+)test",
+            format(R"test(
+xxxxxxxaaaaax wwwwwww = _Verxrrrrrrrrr(PARSE_TEXT_PROTO(R"pb(
+      Category: aaaaaaaaaaaaaaaaaaaaaaaaaa
+)pb"));
+)test", Style));
+}
+
 } // end namespace
 } // end namespace format
 } // end namespace clang