Add UTF-32 character literal

test/unicode.c

@@ -25,6 +25,15 @@ int main() {
 
   ASSERT(0, strcmp(STR(u'a'), "u'a'"));
 
+  ASSERT(4, sizeof(U'\0'));
+  ASSERT(1, U'\xffffffff'>>31);
+  ASSERT(97, U'a');
+  ASSERT(946, U'β');
+  ASSERT(12354, U'あ');
+  ASSERT(127843, U'🍣');
+
+  ASSERT(0, strcmp(STR(U'a'), "U'a'"));
+
   printf("OK\n");
   return 0;
 }

tokenize.c

@@ -495,6 +495,13 @@ Token *tokenize(File *file) {
       continue;
     }
 
+    // UTF-32 character literal
+    if (startswith(p, "U'")) {
+      cur = cur->next = read_char_literal(p, p + 1, ty_uint);
+      p += cur->len;
+      continue;
+    }
+
     // Identifier or keyword
     if (is_ident1(*p)) {
       char *start = p;