Support UTF-8 character constants for C2x.

C2x adds u8'' character constants to C.  This patch adds the
corresponding GCC support.

Most of the support was already present for C++ and just needed
enabling for C2x.  However, in C2x these constants have type unsigned
char, which required corresponding adjustments in the compiler and the
preprocessor to give them that type for C.

For C, it seems clear to me that having type unsigned char means the
constants are unsigned in the preprocessor (and thus treated as having
type uintmax_t in #if conditionals), so this patch implements that.  I
included a conditional in the libcpp change to avoid affecting
signedness for C++, but I'm not sure if in fact these constants should
also be unsigned in the preprocessor for C++ in which case that
!CPP_OPTION (pfile, cplusplus) conditional would not be needed.

Bootstrapped with no regressions on x86_64-pc-linux-gnu.

gcc/c:
	* c-parser.c (c_parser_postfix_expression)
	(c_parser_check_literal_zero): Handle CPP_UTF8CHAR.
	* gimple-parser.c (c_parser_gimple_postfix_expression): Likewise.

gcc/c-family:
	* c-lex.c (lex_charconst): Make CPP_UTF8CHAR constants unsigned
	char for C.

gcc/testsuite:
	* gcc.dg/c11-utf8char-1.c, gcc.dg/c2x-utf8char-1.c,
	gcc.dg/c2x-utf8char-2.c, gcc.dg/c2x-utf8char-3.c,
	gcc.dg/gnu2x-utf8char-1.c: New tests.

libcpp:
	* charset.c (narrow_str_to_charconst): Make CPP_UTF8CHAR constants
	unsigned for C.
	* init.c (lang_defaults): Set utf8_char_literals for GNUC2X and
	STDC2X.

From-SVN: r278265

diff --git a/gcc/c-family/ChangeLog b/gcc/c-family/ChangeLog
index 336159d79f64c9b705245b4dbf1f708a2b0045e6..f4fdccc448afa28a5d4e0c5d685fd949c2824cdd 100644 (file)
--- a/gcc/c-family/ChangeLog
+++ b/gcc/c-family/ChangeLog
@@ -1,3 +1,8 @@
+2019-11-14  Joseph Myers  <joseph@codesourcery.com>
+
+       * c-lex.c (lex_charconst): Make CPP_UTF8CHAR constants unsigned
+       char for C.
+
 2019-11-14  Jakub Jelinek  <jakub@redhat.com>
 
        * c-omp.c (c_omp_check_context_selector): Add nvidia to the list of

diff --git a/gcc/c-family/c-lex.c b/gcc/c-family/c-lex.c
index 42010a762a62e8d8d06578a0f32aeeed27db135e..d446633f8145cfa1e112a4f68e472fdd405466d5 100644 (file)
--- a/gcc/c-family/c-lex.c
+++ b/gcc/c-family/c-lex.c
@@ -1376,7 +1376,9 @@ lex_charconst (const cpp_token *token)
     type = char16_type_node;
   else if (token->type == CPP_UTF8CHAR)
     {
-      if (flag_char8_t)
+      if (!c_dialect_cxx ())
+       type = unsigned_char_type_node;
+      else if (flag_char8_t)
         type = char8_type_node;
       else
         type = char_type_node;

diff --git a/gcc/c/ChangeLog b/gcc/c/ChangeLog
index 04dce4b45ceab01259a33957925ce2d2ed8b0cca..b881cab75ded4a2055ef3452034d567fda293a3e 100644 (file)
--- a/gcc/c/ChangeLog
+++ b/gcc/c/ChangeLog
@@ -1,3 +1,9 @@
+2019-11-14  Joseph Myers  <joseph@codesourcery.com>
+
+       * c-parser.c (c_parser_postfix_expression)
+       (c_parser_check_literal_zero): Handle CPP_UTF8CHAR.
+       * gimple-parser.c (c_parser_gimple_postfix_expression): Likewise.
+
 2019-11-14  Richard Sandiford  <richard.sandiford@arm.com>
 
        * c-typeck.c (build_conditional_expr): Use truth_type_for instead

diff --git a/gcc/c/c-parser.c b/gcc/c/c-parser.c
index 5e30a7f19168bb11f85b93dfee7ca7d6c23f7c01..8ce4e70a0fc0d224c6c0a5978d5fd359713381b4 100644 (file)
--- a/gcc/c/c-parser.c
+++ b/gcc/c/c-parser.c
@@ -8783,6 +8783,7 @@ c_parser_postfix_expression (c_parser *parser)
     case CPP_CHAR:
     case CPP_CHAR16:
     case CPP_CHAR32:
+    case CPP_UTF8CHAR:
     case CPP_WCHAR:
       expr.value = c_parser_peek_token (parser)->value;
       /* For the purpose of warning when a pointer is compared with
@@ -10459,6 +10460,7 @@ c_parser_check_literal_zero (c_parser *parser, unsigned *literal_zero_mask,
     case CPP_WCHAR:
     case CPP_CHAR16:
     case CPP_CHAR32:
+    case CPP_UTF8CHAR:
       /* If a parameter is literal zero alone, remember it
         for -Wmemset-transposed-args warning.  */
       if (integer_zerop (tok->value)

diff --git a/gcc/c/gimple-parser.c b/gcc/c/gimple-parser.c
index 6fdb83c1abe169dd85a540bbf99d71b2bfcb82c2..c16d0dfb88eaee99e2a97a4fb9129f05edb9c927 100644 (file)
--- a/gcc/c/gimple-parser.c
+++ b/gcc/c/gimple-parser.c
@@ -1395,6 +1395,7 @@ c_parser_gimple_postfix_expression (gimple_parser &parser)
     case CPP_CHAR:
     case CPP_CHAR16:
     case CPP_CHAR32:
+    case CPP_UTF8CHAR:
     case CPP_WCHAR:
       expr.value = c_parser_peek_token (parser)->value;
       set_c_expr_source_range (&expr, tok_range);

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 668444818f2b63fff93db31aa692d57bb538791a..51624b7212e42b5e963ac14c6834e761695d5c9e 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2019-11-14  Joseph Myers  <joseph@codesourcery.com>
+
+       * gcc.dg/c11-utf8char-1.c, gcc.dg/c2x-utf8char-1.c,
+       gcc.dg/c2x-utf8char-2.c, gcc.dg/c2x-utf8char-3.c,
+       gcc.dg/gnu2x-utf8char-1.c: New tests.
+
 2019-11-14  Richard Sandiford  <richard.sandiford@arm.com>
 
        PR testsuite/92366

diff --git a/gcc/testsuite/gcc.dg/c11-utf8char-1.c b/gcc/testsuite/gcc.dg/c11-utf8char-1.c
new file mode 100644 (file)
index 0000000..26dbd92
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/c11-utf8char-1.c
@@ -0,0 +1,7 @@
+/* Test C2x UTF-8 characters.  Test not accepted for C11.  */
+/* { dg-do compile } */
+/* { dg-options "-std=c11 -pedantic-errors" } */
+
+#define z(x) 0
+#define u8 z(
+unsigned char a = u8'a');

diff --git a/gcc/testsuite/gcc.dg/c2x-utf8char-1.c b/gcc/testsuite/gcc.dg/c2x-utf8char-1.c
new file mode 100644 (file)
index 0000000..76543af
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/c2x-utf8char-1.c
@@ -0,0 +1,29 @@
+/* Test C2x UTF-8 characters.  Test valid usages.  */
+/* { dg-do compile } */
+/* { dg-options "-std=c2x -pedantic-errors" } */
+
+unsigned char a = u8'a';
+_Static_assert (u8'a' == 97);
+
+unsigned char b = u8'\0';
+_Static_assert (u8'\0' == 0);
+
+unsigned char c = u8'\xff';
+_Static_assert (u8'\xff' == 255);
+
+unsigned char d = u8'\377';
+_Static_assert (u8'\377' == 255);
+
+_Static_assert (sizeof (u8'a') == 1);
+_Static_assert (sizeof (u8'\0') == 1);
+_Static_assert (sizeof (u8'\xff') == 1);
+_Static_assert (sizeof (u8'\377') == 1);
+
+_Static_assert (_Generic (u8'a', unsigned char: 1, default: 2) == 1);
+_Static_assert (_Generic (u8'\0', unsigned char: 1, default: 2) == 1);
+_Static_assert (_Generic (u8'\xff', unsigned char: 1, default: 2) == 1);
+_Static_assert (_Generic (u8'\377', unsigned char: 1, default: 2) == 1);
+
+#if u8'\0' - 1 < 0
+#error "UTF-8 constants not unsigned in preprocessor"
+#endif

diff --git a/gcc/testsuite/gcc.dg/c2x-utf8char-2.c b/gcc/testsuite/gcc.dg/c2x-utf8char-2.c
new file mode 100644 (file)
index 0000000..4e6a2f6
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/c2x-utf8char-2.c
@@ -0,0 +1,8 @@
+/* Test C2x UTF-8 characters.  Character values not affected by
+   different execution character set.  */
+/* { dg-do compile } */
+/* { dg-require-iconv "IBM1047" } */
+/* { dg-options "-std=c2x -pedantic-errors -fexec-charset=IBM1047" } */
+
+_Static_assert (u8'a' == 97);
+_Static_assert (u8'a' != (unsigned char) 'a');

diff --git a/gcc/testsuite/gcc.dg/c2x-utf8char-3.c b/gcc/testsuite/gcc.dg/c2x-utf8char-3.c
new file mode 100644 (file)
index 0000000..7c48983
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/c2x-utf8char-3.c
@@ -0,0 +1,8 @@
+/* Test C2x UTF-8 characters.  Test errors for invalid code.  */
+/* { dg-do compile } */
+/* { dg-options "-std=c2x -pedantic-errors" } */
+
+unsigned char a = u8''; /* { dg-error "empty character constant" } */
+unsigned char b = u8'ab'; /* { dg-error "character constant too long for its type" } */
+unsigned char c = u8'\u00ff'; /* { dg-error "character constant too long for its type" } */
+unsigned char d = u8'\x100'; /* { dg-error "hex escape sequence out of range" } */

diff --git a/gcc/testsuite/gcc.dg/gnu2x-utf8char-1.c b/gcc/testsuite/gcc.dg/gnu2x-utf8char-1.c
new file mode 100644 (file)
index 0000000..9c3add2
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/gnu2x-utf8char-1.c
@@ -0,0 +1,5 @@
+/* Test C2x UTF-8 characters.  Test accepted with -std=gnu2x.  */
+/* { dg-do compile } */
+/* { dg-options "-std=gnu2x" } */
+
+#include "c2x-utf8char-1.c"

diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index b57f26584a150d892f6d03209d69e532d4593729..448f954d2ee15204c635f3dea4480cb7fbb37e0e 100644 (file)
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,10 @@
+2019-11-14  Joseph Myers  <joseph@codesourcery.com>
+
+       * charset.c (narrow_str_to_charconst): Make CPP_UTF8CHAR constants
+       unsigned for C.
+       * init.c (lang_defaults): Set utf8_char_literals for GNUC2X and
+       STDC2X.
+
 2019-11-07  Jakub Jelinek  <jakub@redhat.com>
 
        PR c++/91370 - Implement P1041R4 and P1139R2 - Stronger Unicode reqs

diff --git a/libcpp/charset.c b/libcpp/charset.c
index 0b8815af46bceaadfd7837f7a31befd6371fb29c..d4574415ac168d85fb0b1411015500b0e9fb1ecc 100644 (file)
--- a/libcpp/charset.c
+++ b/libcpp/charset.c
@@ -1928,6 +1928,8 @@ narrow_str_to_charconst (cpp_reader *pfile, cpp_string str,
   /* Multichar constants are of type int and therefore signed.  */
   if (i > 1)
     unsigned_p = 0;
+  else if (type == CPP_UTF8CHAR && !CPP_OPTION (pfile, cplusplus))
+    unsigned_p = 1;
   else
     unsigned_p = CPP_OPTION (pfile, unsigned_char);
 

diff --git a/libcpp/init.c b/libcpp/init.c
index 32b0e70a2107beab98485c4178a358c5e537c413..f5f41b012f89440d5d695c76e9568d3faae82b33 100644 (file)
--- a/libcpp/init.c
+++ b/libcpp/init.c
@@ -102,13 +102,13 @@ static const struct lang_flags lang_defaults[] =
   /* GNUC99   */  { 1,  0,  1,  1,  0,  0,  1,   1,   1,   0,    0,     0,     0,   0,      1,   1,     0 },
   /* GNUC11   */  { 1,  0,  1,  1,  1,  0,  1,   1,   1,   0,    0,     0,     0,   0,      1,   1,     0 },
   /* GNUC17   */  { 1,  0,  1,  1,  1,  0,  1,   1,   1,   0,    0,     0,     0,   0,      1,   1,     0 },
-  /* GNUC2X   */  { 1,  0,  1,  1,  1,  0,  1,   1,   1,   0,    0,     0,     0,   0,      1,   1,     1 },
+  /* GNUC2X   */  { 1,  0,  1,  1,  1,  0,  1,   1,   1,   0,    0,     0,     0,   1,      1,   1,     1 },
   /* STDC89   */  { 0,  0,  0,  0,  0,  1,  0,   0,   0,   0,    0,     0,     1,   0,      0,   0,     0 },
   /* STDC94   */  { 0,  0,  0,  0,  0,  1,  1,   0,   0,   0,    0,     0,     1,   0,      0,   0,     0 },
   /* STDC99   */  { 1,  0,  1,  1,  0,  1,  1,   0,   0,   0,    0,     0,     1,   0,      0,   0,     0 },
   /* STDC11   */  { 1,  0,  1,  1,  1,  1,  1,   1,   0,   0,    0,     0,     1,   0,      0,   0,     0 },
   /* STDC17   */  { 1,  0,  1,  1,  1,  1,  1,   1,   0,   0,    0,     0,     1,   0,      0,   0,     0 },
-  /* STDC2X   */  { 1,  0,  1,  1,  1,  1,  1,   1,   0,   0,    0,     0,     1,   0,      0,   1,     1 },
+  /* STDC2X   */  { 1,  0,  1,  1,  1,  1,  1,   1,   0,   0,    0,     0,     1,   1,      0,   1,     1 },
   /* GNUCXX   */  { 0,  1,  1,  1,  0,  0,  1,   0,   0,   0,    0,     0,     0,   0,      1,   1,     0 },
   /* CXX98    */  { 0,  1,  0,  1,  0,  1,  1,   0,   0,   0,    0,     0,     1,   0,      0,   1,     0 },
   /* GNUCXX11 */  { 1,  1,  1,  1,  1,  0,  1,   1,   1,   1,    0,     0,     0,   0,      1,   1,     0 },