clang/test/Lexer/utf8-char-literal.cpp

   1 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c11 -x c -fsyntax-only -verify %s
   2 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c2x -x c -fsyntax-only -verify %s
   3 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -fsyntax-only -verify %s
   4 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++17 -fsyntax-only -verify %s
   5 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++17 -fsyntax-only -fchar8_t -verify %s
   6 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++20 -fsyntax-only -verify %s
   7 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++20 -fsyntax-only -fno-char8_t -verify %s
   8
   9 int array0[u'ñ' == u'\xf1'? 1 : -1];
  10 int array1['\xF1' !=  u'\xf1'? 1 : -1];
  11 int array1['ñ' !=  u'\xf1'? 1 : -1]; // expected-error {{character too large for enclosing character literal type}}
  12 #if __cplusplus > 201402L
  13 char a = u8'ñ'; // expected-error {{character too large for enclosing character literal type}}
  14 char b = u8'\x80'; // ok
  15 char c = u8'\u0080'; // expected-error {{character too large for enclosing character literal type}}
  16 char d = u8'\u1234'; // expected-error {{character too large for enclosing character literal type}}
  17 char e = u8'ሴ'; // expected-error {{character too large for enclosing character literal type}}
  18 char f = u8'ab'; // expected-error {{Unicode character literals may not contain multiple characters}}
  19 #elif __STDC_VERSION__ >= 202311L
  20 char a = u8'ñ';      // expected-error {{character too large for enclosing character literal type}}
  21 char b = u8'\x80';   // ok
  22 char c = u8'\u0000'; // ok
  23 char d = u8'\u1234'; // expected-error {{character too large for enclosing character literal type}}
  24 char e = u8'ሴ';      // expected-error {{character too large for enclosing character literal type}}
  25 char f = u8'ab';     // expected-error {{Unicode character literals may not contain multiple characters}}
  26 _Static_assert(
  27     _Generic(u8'a',
  28              default : 0,
  29              unsigned char : 1),
  30     "Surprise!");
  31 #endif
  32
  33
  34 // UTF-8 character literals are enabled in C++17 and later. If `-fchar8_t` is not enabled
  35 // (as is the case in C++17), then UTF-8 character literals may produce signed or
  36 // unsigned values depending on whether char is a signed type. If `-fchar8_t` is enabled
  37 // (which is the default behavior for C++20), then UTF-8 character literals always
  38 // produce unsigned values. The tests below depend on the target having a signed
  39 // 8-bit char so that '\xff' produces a negative value.
  40 #if __cplusplus >= 201703L
  41 #  if !defined(__cpp_char8_t)
  42 #    if !(u8'\xff' == '\xff')
  43 #      error UTF-8 character value did not match ordinary character literal; this is unexpected
  44 #    endif
  45 #  else
  46 #    if u8'\xff' == '\xff' // expected-warning {{right side of operator converted from negative value to unsigned}}
  47 #      error UTF-8 character value matched ordinary character literal; this is unexpected
  48 #    endif
  49 #  endif
  50 #endif
  51
  52 /// In C23, u8 char literals are always unsigned.
  53 #if __STDC_VERSION__ >= 202311L
  54 #  if u8'\xff' == '\xff'// expected-warning {{right side of operator converted from negative value to unsigned}}
  55 #    error u8 char literal is not unsigned
  56 #  endif
  57 #endif