Fix assertions and wrong output from StmtPrinter's string literal printing.

String literals (including unicode ones) can contain non-Unicode codepoints
if they were written using \x or similar. Write those out using \x, but be
careful that the following character can't be misinterpreted as part of the
\x escape sequence. Convert UTF-16 surrogate pairs back to codepoints before
rendering them.


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@154069 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 55 insertions, 7 deletions

diff --git a/lib/AST/StmtPrinter.cpp b/lib/AST/StmtPrinter.cpp
index 7ebc1299f0..ef5eefb306 100644
--- a/lib/AST/StmtPrinter.cpp
+++ b/lib/AST/StmtPrinter.cpp
@@ -727,12 +727,40 @@ void StmtPrinter::VisitStringLiteral(StringLiteral *Str) {
   OS << '"';
   static char Hex[] = "0123456789ABCDEF";
 
+  unsigned LastSlashX = Str->getLength();
   for (unsigned I = 0, N = Str->getLength(); I != N; ++I) {
     switch (uint32_t Char = Str->getCodeUnit(I)) {
     default:
-      // FIXME: Is this the best way to print wchar_t?
+      // FIXME: Convert UTF-8 back to codepoints before rendering.
+
+      // Convert UTF-16 surrogate pairs back to codepoints before rendering.
+      // Leave invalid surrogates alone; we'll use \x for those.
+      if (Str->getKind() == StringLiteral::UTF16 && I != N - 1 &&
+          Char >= 0xd800 && Char <= 0xdbff) {
+        uint32_t Trail = Str->getCodeUnit(I + 1);
+        if (Trail >= 0xdc00 && Trail <= 0xdfff) {
+          Char = 0x10000 + ((Char - 0xd800) << 10) + (Trail - 0xdc00);
+          ++I;
+        }
+      }
+
       if (Char > 0xff) {
-        assert(Char <= 0x10ffff && "invalid unicode codepoint");
+        // If this is a wide string, output characters over 0xff using \x
+        // escapes. Otherwise, this is a UTF-16 or UTF-32 string, and Char is a
+        // codepoint: use \x escapes for invalid codepoints.
+        if (Str->getKind() == StringLiteral::Wide ||
+            (Char >= 0xd800 && Char <= 0xdfff) || Char >= 0x110000) {
+          // FIXME: Is this the best way to print wchar_t?
+          OS << "\\x";
+          int Shift = 28;
+          while ((Char >> Shift) == 0)
+            Shift -= 4;
+          for (/**/; Shift >= 0; Shift -= 4)
+            OS << Hex[(Char >> Shift) & 15];
+          LastSlashX = I;
+          break;
+        }
+
         if (Char > 0xffff)
           OS << "\\U00"
              << Hex[(Char >> 20) & 15]
@@ -745,13 +773,26 @@ void StmtPrinter::VisitStringLiteral(StringLiteral *Str) {
            << Hex[(Char >>  0) & 15];
         break;
       }
+
+      // If we used \x... for the previous character, and this character is a
+      // hexadecimal digit, prevent it being slurped as part of the \x.
+      if (LastSlashX + 1 == I) {
+        switch (Char) {
+          case '0': case '1': case '2': case '3': case '4':
+          case '5': case '6': case '7': case '8': case '9':
+          case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
+          case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
+            OS << "\"\"";
+        }
+      }
+
       if (Char <= 0xff && isprint(Char))
         OS << (char)Char;
       else  // Output anything hard as an octal escape.
         OS << '\\'
-        << (char)('0'+ ((Char >> 6) & 7))
-        << (char)('0'+ ((Char >> 3) & 7))
-        << (char)('0'+ ((Char >> 0) & 7));
+           << (char)('0' + ((Char >> 6) & 7))
+           << (char)('0' + ((Char >> 3) & 7))
+           << (char)('0' + ((Char >> 0) & 7));
       break;
     // Handle some common non-printable cases to make dumps prettier.
     case '\\': OS << "\\\\"; break;
diff --git a/test/SemaCXX/constexpr-printing.cpp b/test/SemaCXX/constexpr-printing.cpp
index 4e5bc429db..fc0cce25eb 100644
--- a/test/SemaCXX/constexpr-printing.cpp
+++ b/test/SemaCXX/constexpr-printing.cpp
@@ -85,8 +85,8 @@ constexpr char16_t c16 = get(u"test\0\\\"\t\a\b\234\u1234"); // \
   expected-error {{}} expected-note {{u"test\000\\\"\t\a\b\234\u1234"}}
 constexpr char32_t c32 = get(U"test\0\\\"\t\a\b\234\u1234\U0010ffff"); // \
   expected-error {{}} expected-note {{U"test\000\\\"\t\a\b\234\u1234\U0010FFFF"}}
-constexpr wchar_t wc = get(L"test\0\\\"\t\a\b\234\u1234"); // \
-  expected-error {{}} expected-note {{L"test\000\\\"\t\a\b\234\u1234"}}
+constexpr wchar_t wc = get(L"test\0\\\"\t\a\b\234\u1234\xffffffff"); // \
+  expected-error {{}} expected-note {{L"test\000\\\"\t\a\b\234\x1234\xFFFFFFFF"}}
 
 constexpr char32_t c32_err = get(U"\U00110000"); // expected-error {{invalid universal character}}
 
diff --git a/test/SemaCXX/static-assert.cpp b/test/SemaCXX/static-assert.cpp
index 2b44e81d3e..68ef0183e2 100644
--- a/test/SemaCXX/static-assert.cpp
+++ b/test/SemaCXX/static-assert.cpp
@@ -27,3 +27,10 @@ template<typename T> struct S {
 
 S<char> s1; // expected-note {{in instantiation of template class 'S<char>' requested here}}
 S<int> s2;
+
+static_assert(false, L"\xFFFFFFFF"); // expected-error {{static_assert failed L"\xFFFFFFFF"}}
+static_assert(false, u"\U000317FF"); // expected-error {{static_assert failed u"\U000317FF"}}
+// FIXME: render this as u8"\u03A9"
+static_assert(false, u8"Ω"); // expected-error {{static_assert failed u8"\316\251"}}
+static_assert(false, L"\u1234"); // expected-error {{static_assert failed L"\x1234"}}
+static_assert(false, L"\x1ff" "0\x123" "fx\xfffff" "goop"); // expected-error {{static_assert failed L"\x1FF""0\x123""fx\xFFFFFgoop"}}