clang/test/Lexer/unicode.c

   1 // RUN: %clang_cc1 -fsyntax-only -verify -x c -std=c11 %s
   2 // RUN: %clang_cc1 -fsyntax-only -verify=expected,c2x -x c -std=c2x %s
   3 // RUN: %clang_cc1 -fsyntax-only -verify=expected,cxx -x c++ -std=c++11 %s
   4 // RUN: %clang_cc1 -std=c99 -E -DPP_ONLY=1 %s | FileCheck %s --strict-whitespace
   5 // RUN: %clang_cc1 -E -DPP_ONLY=1 %s | FileCheck %s --strict-whitespace
   6
   7 // This file contains Unicode characters; please do not "fix" them!
   8
   9 extern int x; // expected-warning {{treating Unicode character as whitespace}}
  10 extern int　x; // expected-warning {{treating Unicode character as whitespace}}
  11
  12 // CHECK: extern int {{x}}
  13 // CHECK: extern int　{{x}}
  14
  15 #pragma mark ¡Unicode!
  16
  17 #define COPYRIGHT Copyright © 2012
  18 #define XSTR(X) #X
  19 #define STR(X) XSTR(X)
  20
  21 static const char *copyright = STR(COPYRIGHT); // no-warning
  22 // CHECK: static const char *copyright = "Copyright © {{2012}}";
  23
  24 #if PP_ONLY
  25 COPYRIGHT
  26 // CHECK: Copyright © {{2012}}
  27 CHECK : The preprocessor should not complain about Unicode characters like ©.
  28 #endif
  29
  30 int a;
  31
  32 extern int X\UAAAAAAAA; // expected-error {{not allowed in an identifier}}
  33 int Y = '\UAAAAAAAA'; // expected-error {{invalid universal character}}
  34
  35 #if defined(__cplusplus) || (defined(__STDC_VERSION__) && __STDC_VERSION__ >= 202311L)
  36
  37 extern int ༀ;
  38 extern int 𑩐;
  39 extern int 𐠈;
  40 extern int ꙮ;
  41 extern int  \u1B4C;     // BALINESE LETTER ARCHAIC JNYA - Added in Unicode 14
  42 extern int  \U00016AA2; // TANGSA LETTER GA - Added in Unicode 14
  43 extern int  \U0001E4D0; // 𞓐 NAG MUNDARI LETTER O - Added in Unicode 15
  44 extern int a\N{TANGSA LETTER GA};
  45 extern int a\N{TANGSALETTERGA}; // expected-error {{'TANGSALETTERGA' is not a valid Unicode character name}} \
  46                                 // expected-error {{expected ';' after top level declarator}} \
  47                                 // expected-note {{characters names in Unicode escape sequences are sensitive to case and whitespace}}
  48
  49 extern int 𝛛; // expected-warning {{mathematical notation character <U+1D6DB> in an identifier is a Clang extension}}
  50 extern int ₉; // expected-error {{character <U+2089> not allowed at the start of an identifier}} \\
  51                  expected-warning {{declaration does not declare anything}}
  52
  53 int a¹b₍₄₂₎∇; // expected-warning 6{{mathematical notation character}}
  54
  55 int \u{221E} = 1; // expected-warning {{mathematical notation character}}
  56 int \N{MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL} = 1;
  57                  // expected-warning@-1 {{mathematical notation character}}
  58
  59 int a\N{SUBSCRIPT EQUALS SIGN} = 1; // expected-warning {{mathematical notation character}}
  60
  61 // This character doesn't have the XID_Start property
  62 extern int  \U00016AC0; // TANGSA DIGIT ZERO  // cxx-error {{expected unqualified-id}} \
  63                                               // c2x-error {{expected identifier or '('}}
  64
  65 extern int 🌹; // expected-error {{unexpected character <U+1F339>}} \
  66                   expected-warning {{declaration does not declare anything}}
  67
  68 extern int 🫎;   // MOOSE (Unicode 15) \
  69                 // expected-error {{unexpected character <U+1FACE>}} \
  70                    expected-warning {{declaration does not declare anything}}
  71
  72 extern int 👷; // expected-error {{unexpected character <U+1F477>}} \
  73                   expected-warning {{declaration does not declare anything}}
  74
  75 extern int 👷‍♀; // expected-warning {{declaration does not declare anything}} \
  76                   expected-error {{unexpected character <U+1F477>}} \
  77                   expected-error {{unexpected character <U+200D>}} \
  78                   expected-error {{unexpected character <U+2640>}}
  79 #else
  80
  81 // A 🌹 by any other name....
  82 extern int 🌹;
  83 int 🌵(int 🌻) { return 🌻+ 1; }
  84 int main (void) {
  85   int 🌷 = 🌵(🌹);
  86   return 🌷;
  87 }
  88
  89 int n; = 3; // expected-warning {{treating Unicode character <U+037E> as an identifier character rather than as ';' symbol}}
  90 int *n꞉꞉v = &n;; // expected-warning 2{{treating Unicode character <U+A789> as an identifier character rather than as ':' symbol}}
  91                  // expected-warning@-1 {{treating Unicode character <U+037E> as an identifier character rather than as ';' symbol}}
  92 int v＝［＝］（auto）｛return～x；｝（）; // expected-warning 12{{treating Unicode character}}
  93
  94 int ⁠xx‍;
  95 // expected-warning@-1 {{identifier contains Unicode character <U+2060> that is invisible in some environments}}
  96 // expected-warning@-2 {{identifier contains Unicode character <U+FEFF> that is invisible in some environments}}
  97 // expected-warning@-3 {{identifier contains Unicode character <U+200D> that is invisible in some environments}}
  98 int foobar = 0; // expected-warning {{identifier contains Unicode character <U+200B> that is invisible in some environments}}
  99 int x = foobar; // expected-error {{undeclared identifier}}
 100
 101 int ∣foo; // expected-error {{unexpected character <U+2223>}}
 102 #ifndef PP_ONLY
 103 #define ∶ x // expected-error {{macro name must be an identifier}}
 104 #endif
 105
 106 #endif