Hi!
GCC does use UTF-16 and UTF-32 for char16_t and char32_t string literals
already, so P1041R4 is I believe already implemented with no changes needed.
While going through P1139R2, I've realized that we weren't handling
"If the value is not representable within 16 bits, the program is ill-formed. A
char16_t
literal containing multiple c-chars is ill-formed."
and
"A char32_t literal containing multiple c-chars is ill-formed."
already from C++11 correctly, we were just warning about it, rather than
emitting an error. This is different from C11, where the standard
makes it implementation-defined what happens.
Furthermore, the C++17:
"If the value is not representable with a single UTF-8 code unit,
the program is ill-formed. A UTF-8 character literal containing multiple
c-chars is
ill-formed."
wasn't handled as an error, but instead u8'ab' would be an int with a
warning, similarly u8'\u00c0' etc. u8 char literals are only in C++17+,
not in C, so no need to worry about C at this point.
And lastly, P1139R2 makes it clear that code points above U+10FFFF are
ill-formed, but that is something Eric already implemented in r276167.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
I believe we can now claim to have both P1041R4 and P1139R2 implemented.
2019-11-07 Jakub Jelinek <ja...@redhat.com>
PR c++/91370 - Implement P1041R4 and P1139R2 - Stronger Unicode reqs
* charset.c (narrow_str_to_charconst): Add TYPE argument. For
CPP_UTF8CHAR diagnose whenever number of chars is > 1, using
CPP_DL_ERROR instead of CPP_DL_WARNING.
(wide_str_to_charconst): For CPP_CHAR16 or CPP_CHAR32, use
CPP_DL_ERROR instead of CPP_DL_WARNING when multiple char16_t
or char32_t chars are needed.
(cpp_interpret_charconst): Adjust narrow_str_to_charconst caller.
* g++.dg/cpp1z/utf8-neg.C: Expect errors rather than -Wmultichar
warnings.
* g++.dg/ext/utf16-4.C: Expect errors rather than warnings.
* g++.dg/ext/utf32-4.C: Likewise.
* g++.dg/cpp2a/ucn2.C: New test.
--- libcpp/charset.c.jj 2019-09-27 10:32:17.127641484 +0200
+++ libcpp/charset.c 2019-11-07 13:40:19.616040925 +0100
@@ -1881,10 +1881,11 @@ cpp_interpret_string_notranslate (cpp_re
/* Subroutine of cpp_interpret_charconst which performs the conversion
to a number, for narrow strings. STR is the string structure returned
by cpp_interpret_string. PCHARS_SEEN and UNSIGNEDP are as for
- cpp_interpret_charconst. */
+ cpp_interpret_charconst. TYPE is the token type. */
static cppchar_t
narrow_str_to_charconst (cpp_reader *pfile, cpp_string str,
- unsigned int *pchars_seen, int *unsignedp)
+ unsigned int *pchars_seen, int *unsignedp,
+ enum cpp_ttype type)
{
size_t width = CPP_OPTION (pfile, char_precision);
size_t max_chars = CPP_OPTION (pfile, int_precision) / width;
@@ -1913,10 +1914,12 @@ narrow_str_to_charconst (cpp_reader *pfi
result = c;
}
+ if (type == CPP_UTF8CHAR)
+ max_chars = 1;
if (i > max_chars)
{
i = max_chars;
- cpp_error (pfile, CPP_DL_WARNING,
+ cpp_error (pfile, type == CPP_UTF8CHAR ? CPP_DL_ERROR : CPP_DL_WARNING,
"character constant too long for its type");
}
else if (i > 1 && CPP_OPTION (pfile, warn_multichar))
@@ -1980,7 +1983,9 @@ wide_str_to_charconst (cpp_reader *pfile
character exactly fills a wchar_t, so a multi-character wide
character constant is guaranteed to overflow. */
if (str.len > nbwc * 2)
- cpp_error (pfile, CPP_DL_WARNING,
+ cpp_error (pfile, (CPP_OPTION (pfile, cplusplus)
+ && (type == CPP_CHAR16 || type == CPP_CHAR32))
+ ? CPP_DL_ERROR : CPP_DL_WARNING,
"character constant too long for its type");
/* Truncate the constant to its natural width, and simultaneously
@@ -2038,7 +2043,8 @@ cpp_interpret_charconst (cpp_reader *pfi
result = wide_str_to_charconst (pfile, str, pchars_seen, unsignedp,
token->type);
else
- result = narrow_str_to_charconst (pfile, str, pchars_seen, unsignedp);
+ result = narrow_str_to_charconst (pfile, str, pchars_seen, unsignedp,
+ token->type);
if (str.text != token->val.str.text)
free ((void *)str.text);
--- gcc/testsuite/g++.dg/cpp1z/utf8-neg.C.jj 2018-10-22 09:28:06.380657152
+0200
+++ gcc/testsuite/g++.dg/cpp1z/utf8-neg.C 2019-11-07 14:34:23.929317534
+0100
@@ -1,6 +1,6 @@
/* { dg-do compile { target c++17 } } */
const static char c0 = u8''; // { dg-error "empty character" }
-const static char c1 = u8'ab'; // { dg-warning "multi-character
character constant" }
-const static char c2 = u8'\u0124'; // { dg-warning "multi-character
character constant" }
-const static char c3 = u8'\U00064321'; // { dg-warning "multi-character
character constant" }
+const static char c1 = u8'ab'; // { dg-error "character constant too
long for its type" }
+const static char c2 = u8'\u0124'; // { dg-error "character constant too
long for its type" }
+const static char c3 = u8'\U00064321'; // { dg-error "character constant too
long for its type" }
--- gcc/testsuite/g++.dg/ext/utf16-4.C.jj 2017-06-02 09:01:16.403322989
+0200
+++ gcc/testsuite/g++.dg/ext/utf16-4.C 2019-11-07 14:30:42.433643404 +0100
@@ -4,8 +4,8 @@
const static char16_t c0 = u''; /* { dg-error "empty character"
} */
-const static char16_t c1 = u'ab'; /* { dg-warning "constant too
long" } */
-const static char16_t c2 = u'\U00064321'; /* { dg-warning "constant too
long" } */
+const static char16_t c1 = u'ab'; /* { dg-error "constant too
long" } */
+const static char16_t c2 = u'\U00064321'; /* { dg-error "constant too
long" } */
const static char16_t c3 = 'a';
const static char16_t c4 = U'a';
--- gcc/testsuite/g++.dg/ext/utf32-4.C.jj 2014-03-10 10:49:55.292085832
+0100
+++ gcc/testsuite/g++.dg/ext/utf32-4.C 2019-11-07 14:31:19.745083152 +0100
@@ -3,13 +3,13 @@
/* { dg-do compile { target c++11 } } */
const static char32_t c0 = U''; /* { dg-error "empty character"
} */
-const static char32_t c1 = U'ab'; /* { dg-warning "constant too
long" } */
+const static char32_t c1 = U'ab'; /* { dg-error "constant too
long" } */
const static char32_t c2 = U'\U00064321';
const static char32_t c3 = 'a';
const static char32_t c4 = u'a';
const static char32_t c5 = u'\u2029';
-const static char32_t c6 = u'\U00064321'; /* { dg-warning "constant too
long" } */
+const static char32_t c6 = u'\U00064321'; /* { dg-error "constant too
long" } */
const static char32_t c7 = L'a';
const static char32_t c8 = L'\u2029';
const static char32_t c9 = L'\U00064321'; /* { dg-warning "constant too
long" "" { target { ! 4byte_wchar_t } } } */
--- gcc/testsuite/g++.dg/cpp2a/ucn2.C.jj 2019-11-07 13:56:46.356219953
+0100
+++ gcc/testsuite/g++.dg/cpp2a/ucn2.C 2019-11-07 14:21:34.488871186 +0100
@@ -0,0 +1,30 @@
+// P1139R2
+// { dg-do compile { target c++11 } }
+// { dg-additional-options "-fchar8_t" { target c++17_down } }
+
+const char16_t *a = u"\U0001F914\u2753";
+const char32_t *b = U"\U0001F914\u2753";
+const char16_t *c = u"\uD802"; // { dg-error "is not a valid universal
character" }
+const char16_t *d = u"\U0000DFF0"; // { dg-error "is not a valid universal
character" }
+const char16_t *e = u"\U00110000"; // { dg-error "is outside the UCS
codespace" "" { target c++2a } }
+ // { dg-error "converting UCN to
execution character set" "" { target *-*-* } .-1 }
+const char32_t *f = U"\uD802"; // { dg-error "is not a valid universal
character" }
+const char32_t *g = U"\U0000DFF0"; // { dg-error "is not a valid universal
character" }
+const char32_t *h = U"\U00110001"; // { dg-error "is outside the UCS
codespace" "" { target c++2a } }
+#if __cpp_unicode_characters >= 201411
+const char8_t i = u8'\u00C0'; // { dg-error "character constant too
long for its type" "" { target c++17 } }
+#endif
+const char16_t j = u'\U0001F914'; // { dg-error "character constant too
long for its type" }
+const char32_t k = U'\U0001F914';
+#if __cpp_unicode_characters >= 201411
+const char8_t l = u8'ab'; // { dg-error "character constant too
long for its type" "" { target c++17 } }
+#endif
+const char16_t m = u'ab'; // { dg-error "character constant too
long for its type" }
+const char32_t n = U'ab'; // { dg-error "character constant too
long for its type" }
+#if __cpp_unicode_characters >= 201411
+const char8_t o = u8'\U00110002'; // { dg-error "is outside the UCS
codespace" "" { target c++2a } }
+ // { dg-error "character constant too
long for its type" "" { target c++17 } .-1 }
+#endif
+const char16_t p = u'\U00110003'; // { dg-error "is outside the UCS
codespace" "" { target c++2a } }
+ // { dg-error "converting UCN to
execution character set" "" { target *-*-* } .-1 }
+const char32_t q = U'\U00110004'; // { dg-error "is outside the UCS
codespace" "" { target c++2a } }
Jakub
