On Thu, Sep 01, 2022 at 03:00:28PM -0400, Jason Merrill wrote:
> We might as well use the same flag name, and document it to mean what it
> currently means for GCC.
Ok, following patch introduces -Wunicode (on by default).
> It looks like this is handling \N{abc}, for which "incomplete" seems like
> the wrong description; it's complete, just wrong, and the diagnostic doesn't
> help correct it.
And also will emit the is not a valid universal character with did you mean
if it matches loosely, otherwise will use the not terminated with } after
... wording.
Ok if it passes bootstrap/regtest?
2022-09-03 Jakub Jelinek <ja...@redhat.com>
libcpp/
* include/cpplib.h (struct cpp_options): Add cpp_warn_unicode member.
(enum cpp_warning_reason): Add CPP_W_UNICODE.
* init.cc (cpp_create_reader): Initialize cpp_warn_unicode.
* charset.cc (_cpp_valid_ucn): In possible identifier contexts, don't
handle \u{ or \N{ specially in -std=c* modes except -std=c++2{3,b}.
In possible identifier contexts, don't emit an error and punt
if \N isn't followed by {, or if \N{} surrounds some lower case
letters or _. In possible identifier contexts when not C++23, don't
emit an error but warning about unknown character names and treat as
separate tokens. When treating as separate tokens \u{ or \N{, emit
warnings.
gcc/
* doc/invoke.texi (-Wno-unicode): Document.
gcc/c-family/
* c.opt (Winvalid-utf8): Use ObjC instead of objC. Remove
" in comments" from description.
(Wunicode): New option.
gcc/testsuite/
* c-c++-common/cpp/delimited-escape-seq-4.c: New test.
* c-c++-common/cpp/delimited-escape-seq-5.c: New test.
* c-c++-common/cpp/delimited-escape-seq-6.c: New test.
* c-c++-common/cpp/delimited-escape-seq-7.c: New test.
* c-c++-common/cpp/named-universal-char-escape-5.c: New test.
* c-c++-common/cpp/named-universal-char-escape-6.c: New test.
* c-c++-common/cpp/named-universal-char-escape-7.c: New test.
* g++.dg/cpp23/named-universal-char-escape1.C: New test.
* g++.dg/cpp23/named-universal-char-escape2.C: New test.
--- libcpp/include/cpplib.h.jj 2022-09-03 09:35:41.465984642 +0200
+++ libcpp/include/cpplib.h 2022-09-03 11:30:57.250677870 +0200
@@ -565,6 +565,10 @@ struct cpp_options
2 if it should be a pedwarn. */
unsigned char cpp_warn_invalid_utf8;
+ /* True if libcpp should warn about invalid forms of delimited or named
+ escape sequences. */
+ bool cpp_warn_unicode;
+
/* True if -finput-charset= option has been used explicitly. */
bool cpp_input_charset_explicit;
@@ -675,7 +679,8 @@ enum cpp_warning_reason {
CPP_W_CXX20_COMPAT,
CPP_W_EXPANSION_TO_DEFINED,
CPP_W_BIDIRECTIONAL,
- CPP_W_INVALID_UTF8
+ CPP_W_INVALID_UTF8,
+ CPP_W_UNICODE
};
/* Callback for header lookup for HEADER, which is the name of a
--- libcpp/init.cc.jj 2022-09-01 09:47:23.729892618 +0200
+++ libcpp/init.cc 2022-09-03 11:19:10.954452329 +0200
@@ -228,6 +228,7 @@ cpp_create_reader (enum c_lang lang, cpp
CPP_OPTION (pfile, warn_date_time) = 0;
CPP_OPTION (pfile, cpp_warn_bidirectional) = bidirectional_unpaired;
CPP_OPTION (pfile, cpp_warn_invalid_utf8) = 0;
+ CPP_OPTION (pfile, cpp_warn_unicode) = 1;
CPP_OPTION (pfile, cpp_input_charset_explicit) = 0;
/* Default CPP arithmetic to something sensible for the host for the
--- libcpp/charset.cc.jj 2022-09-01 14:19:47.462235851 +0200
+++ libcpp/charset.cc 2022-09-03 11:26:14.858585905 +0200
@@ -1448,7 +1448,11 @@ _cpp_valid_ucn (cpp_reader *pfile, const
if (str[-1] == 'u')
{
length = 4;
- if (str < limit && *str == '{')
+ if (str < limit
+ && *str == '{'
+ && (!identifier_pos
+ || CPP_OPTION (pfile, delimited_escape_seqs)
+ || !CPP_OPTION (pfile, std)))
{
str++;
/* Magic value to indicate no digits seen. */
@@ -1462,8 +1466,22 @@ _cpp_valid_ucn (cpp_reader *pfile, const
else if (str[-1] == 'N')
{
length = 4;
+ if (identifier_pos
+ && !CPP_OPTION (pfile, delimited_escape_seqs)
+ && CPP_OPTION (pfile, std))
+ {
+ *cp = 0;
+ return false;
+ }
if (str == limit || *str != '{')
- cpp_error (pfile, CPP_DL_ERROR, "'\\N' not followed by '{'");
+ {
+ if (identifier_pos)
+ {
+ *cp = 0;
+ return false;
+ }
+ cpp_error (pfile, CPP_DL_ERROR, "'\\N' not followed by '{'");
+ }
else
{
str++;
@@ -1472,6 +1490,7 @@ _cpp_valid_ucn (cpp_reader *pfile, const
length = 0;
const uchar *name = str;
bool strict = true;
+ const uchar *strict_end = name;
do
{
@@ -1481,7 +1500,11 @@ _cpp_valid_ucn (cpp_reader *pfile, const
if (!ISIDNUM (c) && c != ' ' && c != '-')
break;
if (ISLOWER (c) || c == '_')
- strict = false;
+ {
+ if (strict)
+ strict_end = str;
+ strict = false;
+ }
str++;
extend_char_range (char_range, loc_reader);
}
@@ -1489,8 +1512,35 @@ _cpp_valid_ucn (cpp_reader *pfile, const
if (str < limit && *str == '}')
{
- if (name == str && identifier_pos)
+ if (identifier_pos && (name == str || !strict))
{
+ if (name == str)
+ cpp_warning (pfile, CPP_W_UNICODE,
+ "empty named universal character escape "
+ "sequence; treating it as separate tokens");
+ else
+ {
+ char canon_name[uname2c_max_name_len + 1];
+ result = _cpp_uname2c_uax44_lm2 ((const char *) name,
+ str - name, canon_name);
+ if (result == (cppchar_t) -1)
+ cpp_warning (pfile, CPP_W_UNICODE,
+ "'\\N{' not terminated with '}' after "
+ "%.*s; treating it as separate tokens",
+ (int) (strict_end - base), base);
+ else
+ {
+ bool ret
+ = cpp_warning (pfile, CPP_W_UNICODE,
+ "\\N{%.*s} is not a valid "
+ "universal character; treating it "
+ "as separate tokens",
+ (int) (str - name), name);
+ if (ret)
+ cpp_error (pfile, CPP_DL_NOTE,
+ "did you mean \\N{%s}?", canon_name);
+ }
+ }
*cp = 0;
return false;
}
@@ -1515,27 +1565,49 @@ _cpp_valid_ucn (cpp_reader *pfile, const
uname2c_tree, NULL);
if (result == (cppchar_t) -1)
{
- cpp_error (pfile, CPP_DL_ERROR,
- "\\N{%.*s} is not a valid universal "
- "character", (int) (str - name), name);
+ bool ret = true;
+ if (identifier_pos
+ && !CPP_OPTION (pfile, delimited_escape_seqs))
+ ret = cpp_warning (pfile, CPP_W_UNICODE,
+ "\\N{%.*s} is not a valid "
+ "universal character; treating it "
+ "as separate tokens",
+ (int) (str - name), name);
+ else
+ cpp_error (pfile, CPP_DL_ERROR,
+ "\\N{%.*s} is not a valid universal "
+ "character", (int) (str - name), name);
/* Try to do a loose name lookup according to
Unicode loose matching rule UAX44-LM2. */
char canon_name[uname2c_max_name_len + 1];
result = _cpp_uname2c_uax44_lm2 ((const char *) name,
str - name, canon_name);
- if (result != (cppchar_t) -1)
+ if (result != (cppchar_t) -1 && ret)
cpp_error (pfile, CPP_DL_NOTE,
"did you mean \\N{%s}?", canon_name);
else
- result = 0x40;
+ result = 0xC0;
+ if (identifier_pos
+ && !CPP_OPTION (pfile, delimited_escape_seqs))
+ {
+ *cp = 0;
+ return false;
+ }
}
}
str++;
extend_char_range (char_range, loc_reader);
}
else if (identifier_pos)
- length = 1;
+ {
+ cpp_warning (pfile, CPP_W_UNICODE,
+ "'\\N{' not terminated with '}' after %.*s; "
+ "treating it as separate tokens",
+ (int) (str - base), base);
+ *cp = 0;
+ return false;
+ }
else
{
cpp_error (pfile, CPP_DL_ERROR,
@@ -1584,12 +1656,17 @@ _cpp_valid_ucn (cpp_reader *pfile, const
}
while (--length);
- if (delimited
- && str < limit
- && *str == '}'
- && (length != 32 || !identifier_pos))
+ if (delimited && str < limit && *str == '}')
{
- if (length == 32)
+ if (length == 32 && identifier_pos)
+ {
+ cpp_warning (pfile, CPP_W_UNICODE,
+ "empty delimited escape sequence; "
+ "treating it as separate tokens");
+ *cp = 0;
+ return false;
+ }
+ else if (length == 32)
cpp_error (pfile, CPP_DL_ERROR,
"empty delimited escape sequence");
else if (!CPP_OPTION (pfile, delimited_escape_seqs)
@@ -1607,6 +1684,11 @@ _cpp_valid_ucn (cpp_reader *pfile, const
error message in that case. */
if (length && identifier_pos)
{
+ if (delimited)
+ cpp_warning (pfile, CPP_W_UNICODE,
+ "'\\u{' not terminated with '}' after %.*s; "
+ "treating it as separate tokens",
+ (int) (str - base), base);
*cp = 0;
return false;
}
--- gcc/doc/invoke.texi.jj 2022-09-03 09:35:40.966991672 +0200
+++ gcc/doc/invoke.texi 2022-09-03 11:39:03.875914845 +0200
@@ -365,7 +365,7 @@ Objective-C and Objective-C++ Dialects}.
-Winfinite-recursion @gol
-Winit-self -Winline -Wno-int-conversion -Wint-in-bool-context @gol
-Wno-int-to-pointer-cast -Wno-invalid-memory-model @gol
--Winvalid-pch -Winvalid-utf8 -Wjump-misses-init @gol
+-Winvalid-pch -Winvalid-utf8 -Wno-unicode -Wjump-misses-init @gol
-Wlarger-than=@var{byte-size} -Wlogical-not-parentheses -Wlogical-op @gol
-Wlong-long -Wno-lto-type-mismatch -Wmain -Wmaybe-uninitialized @gol
-Wmemset-elt-size -Wmemset-transposed-args @gol
@@ -9577,6 +9577,12 @@ Warn if an invalid UTF-8 character is fo
This warning is on by default for C++23 if @option{-finput-charset=UTF-8}
is used and turned into error with @option{-pedantic-errors}.
+@item -Wno-unicode
+@opindex Wunicode
+@opindex Wno-unicode
+Don't diagnose invalid forms of delimited or named escape sequences which are
+treated as separate tokens. @option{Wunicode} is enabled by default.
+
@item -Wlong-long
@opindex Wlong-long
@opindex Wno-long-long
--- gcc/c-family/c.opt.jj 2022-09-03 09:35:40.206002393 +0200
+++ gcc/c-family/c.opt 2022-09-03 11:17:04.529201926 +0200
@@ -822,8 +822,8 @@ C ObjC C++ ObjC++ CPP(warn_invalid_pch)
Warn about PCH files that are found but not used.
Winvalid-utf8
-C objC C++ ObjC++ CPP(cpp_warn_invalid_utf8) CppReason(CPP_W_INVALID_UTF8)
Var(warn_invalid_utf8) Init(0) Warning
-Warn about invalid UTF-8 characters in comments.
+C ObjC C++ ObjC++ CPP(cpp_warn_invalid_utf8) CppReason(CPP_W_INVALID_UTF8)
Var(warn_invalid_utf8) Init(0) Warning
+Warn about invalid UTF-8 characters.
Wjump-misses-init
C ObjC Var(warn_jump_misses_init) Warning LangEnabledby(C ObjC,Wc++-compat)
@@ -1345,6 +1345,10 @@ Wundef
C ObjC C++ ObjC++ CPP(warn_undef) CppReason(CPP_W_UNDEF) Var(cpp_warn_undef)
Init(0) Warning
Warn if an undefined macro is used in an #if directive.
+Wunicode
+C ObjC C++ ObjC++ CPP(cpp_warn_unicode) CppReason(CPP_W_UNICODE)
Var(warn_unicode) Init(1) Warning
+Warn about invalid forms of delimited or named escape sequences.
+
Wuninitialized
C ObjC C++ ObjC++ LTO LangEnabledBy(C ObjC C++ ObjC++ LTO,Wall)
;
--- gcc/testsuite/c-c++-common/cpp/delimited-escape-seq-4.c.jj 2022-09-03
11:13:37.570068845 +0200
+++ gcc/testsuite/c-c++-common/cpp/delimited-escape-seq-4.c 2022-09-03
11:56:52.818054420 +0200
@@ -0,0 +1,13 @@
+/* P2290R3 - Delimited escape sequences */
+/* { dg-do compile } */
+/* { dg-require-effective-target wchar } */
+/* { dg-options "-std=gnu99 -Wno-c++-compat" { target c } } */
+/* { dg-options "-std=gnu++20" { target c++ } } */
+
+#define z(x) 0
+#define a z(
+int b = a\u{}); /* { dg-warning "empty delimited escape
sequence; treating it as separate tokens" } */
+int c = a\u{); /* { dg-warning "'\\\\u\\\{' not terminated with '\\\}'
after \\\\u\\\{; treating it as separate tokens" } */
+int d = a\u{12XYZ}); /* { dg-warning "'\\\\u\\\{' not terminated with '\\\}'
after \\\\u\\\{12; treating it as separate tokens" } */
+int e = a\u123);
+int f = a\U1234567);
--- gcc/testsuite/c-c++-common/cpp/delimited-escape-seq-5.c.jj 2022-09-03
11:13:37.570068845 +0200
+++ gcc/testsuite/c-c++-common/cpp/delimited-escape-seq-5.c 2022-09-03
12:01:35.618124647 +0200
@@ -0,0 +1,13 @@
+/* P2290R3 - Delimited escape sequences */
+/* { dg-do compile } */
+/* { dg-require-effective-target wchar } */
+/* { dg-options "-std=c17 -Wno-c++-compat" { target c } } */
+/* { dg-options "-std=c++23" { target c++ } } */
+
+#define z(x) 0
+#define a z(
+int b = a\u{}); /* { dg-warning "empty delimited escape
sequence; treating it as separate tokens" "" { target c++23 } } */
+int c = a\u{); /* { dg-warning "'\\\\u\\\{' not terminated with '\\\}'
after \\\\u\\\{; treating it as separate tokens" "" { target c++23 } } */
+int d = a\u{12XYZ}); /* { dg-warning "'\\\\u\\\{' not terminated with '\\\}'
after \\\\u\\\{12; treating it as separate tokens" "" { target c++23 } } */
+int e = a\u123);
+int f = a\U1234567);
--- gcc/testsuite/c-c++-common/cpp/delimited-escape-seq-6.c.jj 2022-09-03
11:59:36.573778876 +0200
+++ gcc/testsuite/c-c++-common/cpp/delimited-escape-seq-6.c 2022-09-03
11:59:55.808511591 +0200
@@ -0,0 +1,13 @@
+/* P2290R3 - Delimited escape sequences */
+/* { dg-do compile } */
+/* { dg-require-effective-target wchar } */
+/* { dg-options "-std=gnu99 -Wno-c++-compat -Wno-unicode" { target c } } */
+/* { dg-options "-std=gnu++20 -Wno-unicode" { target c++ } } */
+
+#define z(x) 0
+#define a z(
+int b = a\u{}); /* { dg-bogus "empty delimited escape sequence;
treating it as separate tokens" } */
+int c = a\u{); /* { dg-bogus "'\\\\u\\\{' not terminated with '\\\}'
after \\\\u\\\{; treating it as separate tokens" } */
+int d = a\u{12XYZ}); /* { dg-bogus "'\\\\u\\\{' not terminated with '\\\}'
after \\\\u\\\{12; treating it as separate tokens" } */
+int e = a\u123);
+int f = a\U1234567);
--- gcc/testsuite/c-c++-common/cpp/delimited-escape-seq-7.c.jj 2022-09-03
12:01:48.958939255 +0200
+++ gcc/testsuite/c-c++-common/cpp/delimited-escape-seq-7.c 2022-09-03
12:02:16.765552854 +0200
@@ -0,0 +1,13 @@
+/* P2290R3 - Delimited escape sequences */
+/* { dg-do compile } */
+/* { dg-require-effective-target wchar } */
+/* { dg-options "-std=c17 -Wno-c++-compat -Wno-unicode" { target c } } */
+/* { dg-options "-std=c++23 -Wno-unicode" { target c++ } } */
+
+#define z(x) 0
+#define a z(
+int b = a\u{}); /* { dg-bogus "empty delimited escape sequence;
treating it as separate tokens" } */
+int c = a\u{); /* { dg-bogus "'\\\\u\\\{' not terminated with '\\\}'
after \\\\u\\\{; treating it as separate tokens" } */
+int d = a\u{12XYZ}); /* { dg-bogus "'\\\\u\\\{' not terminated with '\\\}'
after \\\\u\\\{12; treating it as separate tokens" } */
+int e = a\u123);
+int f = a\U1234567);
--- gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-5.c.jj
2022-09-03 11:13:37.570068845 +0200
+++ gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-5.c
2022-09-03 12:12:29.596042747 +0200
@@ -0,0 +1,17 @@
+/* P2071R2 - Named universal character escapes */
+/* { dg-do compile } */
+/* { dg-require-effective-target wchar } */
+/* { dg-options "-std=gnu99 -Wno-c++-compat" { target c } } */
+/* { dg-options "-std=gnu++20" { target c++ } } */
+
+#define z(x) 0
+#define a z(
+int b = a\N{}); /* { dg-warning "empty named
universal character escape sequence; treating it as separate tokens" } */
+int c = a\N{); /* { dg-warning "'\\\\N\\\{' not
terminated with '\\\}' after \\\\N\\\{; treating it as separate tokens" } */
+int d = a\N);
+int e = a\NARG);
+int f = a\N{abc}); /* { dg-warning "'\\\\N\\\{'
not terminated with '\\\}' after \\\\N\\\{; treating it as separate tokens" } */
+int g = a\N{ABC.123}); /* { dg-warning "'\\\\N\\\{'
not terminated with '\\\}' after \\\\N\\\{ABC; treating it as separate tokens"
} */
+int h = a\N{NON-EXISTENT CHAR}); /* { dg-warning "\\\\N\\\{NON-EXISTENT
CHAR\\\} is not a valid universal character; treating it as separate tokens" }
*/
+int i = a\N{Latin_Small_Letter_A_With_Acute}); /* { dg-warning
"\\\\N\\\{Latin_Small_Letter_A_With_Acute\\\} is not a valid universal
character; treating it as separate tokens" } */
+ /* { dg-message "did you mean
\\\\N\\\{LATIN SMALL LETTER A WITH ACUTE\\\}\\?" "" { target *-*-* } .-1 } */
--- gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-6.c.jj
2022-09-03 11:13:37.570068845 +0200
+++ gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-6.c
2022-09-03 11:44:34.558316155 +0200
@@ -0,0 +1,17 @@
+/* P2071R2 - Named universal character escapes */
+/* { dg-do compile } */
+/* { dg-require-effective-target wchar } */
+/* { dg-options "-std=c17 -Wno-c++-compat" { target c } } */
+/* { dg-options "-std=c++20" { target c++ } } */
+
+#define z(x) 0
+#define a z(
+int b = a\N{});
+int c = a\N{);
+int d = a\N);
+int e = a\NARG);
+int f = a\N{abc});
+int g = a\N{ABC.123});
+int h = a\N{NON-EXISTENT CHAR}); /* { dg-bogus "is not a valid universal
character" } */
+int i = a\N{Latin_Small_Letter_A_With_Acute});
+int j = a\N{LATIN SMALL LETTER A WITH ACUTE});
--- gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-7.c.jj
2022-09-03 12:18:31.296022384 +0200
+++ gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-7.c
2022-09-03 12:19:00.956610699 +0200
@@ -0,0 +1,17 @@
+/* P2071R2 - Named universal character escapes */
+/* { dg-do compile } */
+/* { dg-require-effective-target wchar } */
+/* { dg-options "-std=gnu99 -Wno-c++-compat -Wno-unicode" { target c } } */
+/* { dg-options "-std=gnu++20 -Wno-unicode" { target c++ } } */
+
+#define z(x) 0
+#define a z(
+int b = a\N{}); /* { dg-bogus "empty named
universal character escape sequence; treating it as separate tokens" } */
+int c = a\N{); /* { dg-bogus "'\\\\N\\\{' not
terminated with '\\\}' after \\\\N\\\{; treating it as separate tokens" } */
+int d = a\N);
+int e = a\NARG);
+int f = a\N{abc}); /* { dg-bogus "'\\\\N\\\{' not
terminated with '\\\}' after \\\\N\\\{; treating it as separate tokens" } */
+int g = a\N{ABC.123}); /* { dg-bogus "'\\\\N\\\{' not
terminated with '\\\}' after \\\\N\\\{ABC; treating it as separate tokens" } */
+int h = a\N{NON-EXISTENT CHAR}); /* { dg-bogus "\\\\N\\\{NON-EXISTENT
CHAR\\\} is not a valid universal character; treating it as separate tokens" }
*/
+int i = a\N{Latin_Small_Letter_A_With_Acute}); /* { dg-bogus
"\\\\N\\\{Latin_Small_Letter_A_With_Acute\\\} is not a valid universal
character; treating it as separate tokens" } */
+ /* { dg-bogus "did you mean
\\\\N\\\{LATIN SMALL LETTER A WITH ACUTE\\\}\\?" "" { target *-*-* } .-1 } */
--- gcc/testsuite/g++.dg/cpp23/named-universal-char-escape1.C.jj
2022-09-03 11:13:37.571068831 +0200
+++ gcc/testsuite/g++.dg/cpp23/named-universal-char-escape1.C 2022-09-03
12:16:49.010442096 +0200
@@ -0,0 +1,16 @@
+// P2071R2 - Named universal character escapes
+// { dg-do compile }
+// { dg-require-effective-target wchar }
+
+#define z(x) 0
+#define a z(
+int b = a\N{}); // { dg-warning "empty named
universal character escape sequence; treating it as separate tokens" "" {
target c++23 } }
+int c = a\N{); // { dg-warning "'\\\\N\\\{' not
terminated with '\\\}' after \\\\N\\\{; treating it as separate tokens" "" {
target c++23 } }
+int d = a\N);
+int e = a\NARG);
+int f = a\N{abc}); // { dg-warning "'\\\\N\\\{' not
terminated with '\\\}' after \\\\N\\\{; treating it as separate tokens" "" {
target c++23 } }
+int g = a\N{ABC.123}); // { dg-warning "'\\\\N\\\{' not
terminated with '\\\}' after \\\\N\\\{ABC; treating it as separate tokens" "" {
target c++23 } }
+int h = a\N{NON-EXISTENT CHAR}); // { dg-error "is not a valid universal
character" "" { target c++23 } }
+ // { dg-error "was not declared in this
scope" "" { target c++23 } .-1 }
+int i = a\N{Latin_Small_Letter_A_With_Acute}); // { dg-warning
"\\\\N\\\{Latin_Small_Letter_A_With_Acute\\\} is not a valid universal
character; treating it as separate tokens" "" { target c++23 } }
+ // { dg-message "did you mean
\\\\N\\\{LATIN SMALL LETTER A WITH ACUTE\\\}\\?" "" { target c++23 } .-1 }
--- gcc/testsuite/g++.dg/cpp23/named-universal-char-escape2.C.jj
2022-09-03 11:13:37.571068831 +0200
+++ gcc/testsuite/g++.dg/cpp23/named-universal-char-escape2.C 2022-09-03
12:18:03.567407252 +0200
@@ -0,0 +1,18 @@
+// P2071R2 - Named universal character escapes
+// { dg-do compile }
+// { dg-require-effective-target wchar }
+// { dg-options "" }
+
+#define z(x) 0
+#define a z(
+int b = a\N{}); // { dg-warning "empty named
universal character escape sequence; treating it as separate tokens" }
+int c = a\N{); // { dg-warning "'\\\\N\\\{' not
terminated with '\\\}' after \\\\N\\\{; treating it as separate tokens" }
+int d = a\N);
+int e = a\NARG);
+int f = a\N{abc}); // { dg-warning "'\\\\N\\\{' not
terminated with '\\\}' after \\\\N\\\{; treating it as separate tokens" }
+int g = a\N{ABC.123}); // { dg-warning "'\\\\N\\\{' not
terminated with '\\\}' after \\\\N\\\{ABC; treating it as separate tokens" }
+int h = a\N{NON-EXISTENT CHAR}); // { dg-error "is not a valid universal
character" "" { target c++23 } }
+ // { dg-error "was not declared in this
scope" "" { target c++23 } .-1 }
+ // { dg-warning "\\\\N\\\{NON-EXISTENT
CHAR\\\} is not a valid universal character; treating it as separate tokens" ""
{ target c++20_down } .-2 }
+int i = a\N{Latin_Small_Letter_A_With_Acute}); // { dg-warning
"\\\\N\\\{Latin_Small_Letter_A_With_Acute\\\} is not a valid universal
character; treating it as separate tokens" }
+ // { dg-message "did you mean
\\\\N\\\{LATIN SMALL LETTER A WITH ACUTE\\\}\\?" "" { target *-*-* } .-1 }
Jakub
