From 053876cdbe8057210e6f4da4eec2df58f92ccd4c Mon Sep 17 00:00:00 2001 From: Tom Honermann Date: Tue, 2 Aug 2022 14:36:02 -0400 Subject: preprocessor/106426: Treat u8 character literals as unsigned in char8_t modes. This patch corrects handling of UTF-8 character literals in preprocessing directives so that they are treated as unsigned types in char8_t enabled C++ modes (C++17 with -fchar8_t or C++20 without -fno-char8_t). Previously, UTF-8 character literals were always treated as having the same type as ordinary character literals (signed or unsigned dependent on target or use of the -fsigned-char or -funsigned char options). PR preprocessor/106426 gcc/c-family/ChangeLog: * c-opts.cc (c_common_post_options): Assign cpp_opts->unsigned_utf8char subject to -fchar8_t, -fsigned-char, and/or -funsigned-char. gcc/testsuite/ChangeLog: * g++.dg/ext/char8_t-char-literal-1.C: Check signedness of u8 literals. * g++.dg/ext/char8_t-char-literal-2.C: Check signedness of u8 literals. libcpp/ChangeLog: * charset.cc (narrow_str_to_charconst): Set signedness of CPP_UTF8CHAR literals based on unsigned_utf8char. * include/cpplib.h (cpp_options): Add unsigned_utf8char. * init.cc (cpp_create_reader): Initialize unsigned_utf8char. --- libcpp/include/cpplib.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'libcpp/include/cpplib.h') diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index 3eba6f7..f9c042d 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -581,8 +581,8 @@ struct cpp_options ints and target wide characters, respectively. */ size_t precision, char_precision, int_precision, wchar_precision; - /* True means chars (wide chars) are unsigned. */ - bool unsigned_char, unsigned_wchar; + /* True means chars (wide chars, UTF-8 chars) are unsigned. */ + bool unsigned_char, unsigned_wchar, unsigned_utf8char; /* True if the most significant byte in a word has the lowest address in memory. */ -- cgit v1.1 From 60468d6cd46a3bd3afe8ff856f82afcd4c65a217 Mon Sep 17 00:00:00 2001 From: Tom Honermann Date: Mon, 1 Aug 2022 14:49:00 -0400 Subject: c++: Fix pragma suppression of -Wc++20-compat diagnostics [PR106423] MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Gcc's '#pragma GCC diagnostic' directives are processed in "early mode" (see handle_pragma_diagnostic_early) for the C++ frontend and, as such, require that the target diagnostic option be enabled for the preprocessor (see c_option_is_from_cpp_diagnostics). This change modifies the -Wc++20-compat option definition to register it as a preprocessor option so that its associated diagnostics can be suppressed. The changes also implicitly disable the option in C++20 and later modes. These changes are consistent with the definition of the -Wc++11-compat option. This support is motivated by the need to suppress the following diagnostic otherwise issued in C++17 and earlier modes due to the char8_t typedef present in the uchar.h header file in glibc 2.36. warning: identifier ‘char8_t’ is a keyword in C++20 [-Wc++20-compat] Tests are added to validate suppression of both -Wc++11-compat and -Wc++20-compat related diagnostics (fixes were only needed for the C++20 case). PR c++/106423 gcc/c-family/ChangeLog: * c-opts.cc (c_common_post_options): Disable -Wc++20-compat diagnostics in C++20 and later. * c.opt (Wc++20-compat): Enable hooks for the preprocessor. gcc/cp/ChangeLog: * parser.cc (cp_lexer_saving_tokens): Add comment regarding diagnostic requirements. gcc/testsuite/ChangeLog: * g++.dg/cpp0x/keywords2.C: New test. * g++.dg/cpp2a/keywords2.C: New test. libcpp/ChangeLog: * include/cpplib.h (cpp_warning_reason): Add CPP_W_CXX20_COMPAT. * init.cc (cpp_create_reader): Add cpp_warn_cxx20_compat. --- libcpp/include/cpplib.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'libcpp/include/cpplib.h') diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index f9c042d..26e2b4c 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -547,6 +547,9 @@ struct cpp_options /* True if warn about differences between C++98 and C++11. */ bool cpp_warn_cxx11_compat; + /* True if warn about differences between C++17 and C++20. */ + bool cpp_warn_cxx20_compat; + /* Nonzero if bidirectional control characters checking is on. See enum cpp_bidirectional_level. */ unsigned char cpp_warn_bidirectional; @@ -655,6 +658,7 @@ enum cpp_warning_reason { CPP_W_C90_C99_COMPAT, CPP_W_C11_C2X_COMPAT, CPP_W_CXX11_COMPAT, + CPP_W_CXX20_COMPAT, CPP_W_EXPANSION_TO_DEFINED, CPP_W_BIDIRECTIONAL }; -- cgit v1.1 From d7c3000147c1d8090f66a2baf4623d2c0dfe8eb6 Mon Sep 17 00:00:00 2001 From: Joseph Myers Date: Thu, 18 Aug 2022 23:01:01 +0000 Subject: preprocessor: Support #warning for standard C2x ISO C2x standardizes the existing #warning extension. Arrange accordingly for it not to be diagnosed with -std=c2x -pedantic, but to be diagnosed with -Wc11-c2x-compat. Bootstrapped with no regressions for x86_64-pc-linux-gnu. gcc/testsuite/ * gcc.dg/cpp/c11-warning-1.c, gcc.dg/cpp/c11-warning-2.c, gcc.dg/cpp/c11-warning-3.c, gcc.dg/cpp/c11-warning-4.c, gcc.dg/cpp/c2x-warning-1.c, gcc.dg/cpp/c2x-warning-2.c, gcc.dg/cpp/gnu11-warning-1.c, gcc.dg/cpp/gnu11-warning-2.c, gcc.dg/cpp/gnu11-warning-3.c, gcc.dg/cpp/gnu11-warning-4.c, gcc.dg/cpp/gnu2x-warning-1.c, gcc.dg/cpp/gnu2x-warning-2.c: New tests. libcpp/ * include/cpplib.h (struct cpp_options): Add warning_directive. * init.cc (struct lang_flags, lang_defaults): Add warning_directive. * directives.cc (DIRECTIVE_TABLE): Mark #warning as STDC2X not EXTENSION. (directive_diagnostics): Diagnose #warning with -Wc11-c2x-compat, or with -pedantic for a standard not supporting #warning. --- libcpp/include/cpplib.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'libcpp/include/cpplib.h') diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index 26e2b4c..58ed51d 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -513,6 +513,9 @@ struct cpp_options /* Nonzero for the '#elifdef' and '#elifndef' directives. */ unsigned char elifdef; + /* Nonzero for the '#warning' directive. */ + unsigned char warning_directive; + /* Nonzero means tokenize C++20 module directives. */ unsigned char module_directives; -- cgit v1.1 From e9dd050e0ccd644c3bb6d6538dc6187157f6b3e8 Mon Sep 17 00:00:00 2001 From: Jakub Jelinek Date: Sat, 20 Aug 2022 10:26:55 +0200 Subject: libcpp: Implement C++23 P2290R3 - Delimited escape sequences [PR106645] The following patch implements the C++23 P2290R3 paper. 2022-08-20 Jakub Jelinek PR c++/106645 libcpp/ * include/cpplib.h (struct cpp_options): Implement P2290R3 - Delimited escape sequences. Add delimite_escape_seqs member. * init.cc (struct lang_flags): Likewise. (lang_defaults): Add delim column. (cpp_set_lang): Copy over delimite_escape_seqs. * charset.cc (extend_char_range): New function. (_cpp_valid_ucn): Use it. Handle delimited escape sequences. (convert_hex): Likewise. (convert_oct): Likewise. (convert_ucn): Use extend_char_range. (convert_escape): Call convert_oct even for \o. (_cpp_interpret_identifier): Handle delimited escape sequences. * lex.cc (get_bidi_ucn_1): Likewise. Add end argument, fill it in. (get_bidi_ucn): Adjust get_bidi_ucn_1 caller. Use end argument to compute num_bytes. gcc/testsuite/ * c-c++-common/cpp/delimited-escape-seq-1.c: New test. * c-c++-common/cpp/delimited-escape-seq-2.c: New test. * c-c++-common/cpp/delimited-escape-seq-3.c: New test. * c-c++-common/Wbidi-chars-24.c: New test. * gcc.dg/cpp/delimited-escape-seq-1.c: New test. * gcc.dg/cpp/delimited-escape-seq-2.c: New test. * g++.dg/cpp/delimited-escape-seq-1.C: New test. * g++.dg/cpp/delimited-escape-seq-2.C: New test. --- libcpp/include/cpplib.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'libcpp/include/cpplib.h') diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index 58ed51d..810203d 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -522,6 +522,9 @@ struct cpp_options /* Nonzero for C++23 size_t literals. */ unsigned char size_t_literals; + /* Nonzero for C++23 delimited escape sequences. */ + unsigned char delimited_escape_seqs; + /* Holds the name of the target (execution) character set. */ const char *narrow_charset; -- cgit v1.1 From 0b8c57ed40f19086e30ce54faec3222ac21cc0df Mon Sep 17 00:00:00 2001 From: Jakub Jelinek Date: Thu, 1 Sep 2022 09:48:01 +0200 Subject: libcpp: Add -Winvalid-utf8 warning [PR106655] The following patch introduces a new warning - -Winvalid-utf8 similarly to what clang now has - to diagnose invalid UTF-8 byte sequences in comments, but not just in those, but also in string/character literals and outside of them. The warning is on by default when explicit -finput-charset=UTF-8 is used and C++23 compilation is requested and if -{,W}pedantic or -pedantic-errors it is actually a pedwarn. The reason it is on by default only for -finput-charset=UTF-8 is that the sources often are UTF-8, but sometimes could be some ASCII compatible single byte encoding where non-ASCII characters only appear in comments. So having the warning off by default is IMO desirable. The C++23 pedantic mode for when the source code is UTF-8 is -std=c++23 -pedantic-errors -finput-charset=UTF-8. 2022-09-01 Jakub Jelinek PR c++/106655 libcpp/ * include/cpplib.h (struct cpp_options): Implement C++23 P2295R6 - Support for UTF-8 as a portable source file encoding. Add cpp_warn_invalid_utf8 and cpp_input_charset_explicit fields. (enum cpp_warning_reason): Add CPP_W_INVALID_UTF8 enumerator. * init.cc (cpp_create_reader): Initialize cpp_warn_invalid_utf8 and cpp_input_charset_explicit. * charset.cc (_cpp_valid_utf8): Adjust function comment. * lex.cc (UCS_LIMIT): Define. (utf8_continuation): New const variable. (utf8_signifier): Move earlier in the file. (_cpp_warn_invalid_utf8, _cpp_handle_multibyte_utf8): New functions. (_cpp_skip_block_comment): Handle -Winvalid-utf8 warning. (skip_line_comment): Likewise. (lex_raw_string, lex_string): Likewise. (_cpp_lex_direct): Likewise. gcc/ * doc/invoke.texi (-Winvalid-utf8): Document it. gcc/c-family/ * c.opt (-Winvalid-utf8): New warning. * c-opts.cc (c_common_handle_option) : Set cpp_opts->cpp_input_charset_explicit. (c_common_post_options): If -finput-charset=UTF-8 is explicit in C++23, enable -Winvalid-utf8 by default and if -pedantic or -pedantic-errors, make it a pedwarn. gcc/testsuite/ * c-c++-common/cpp/Winvalid-utf8-1.c: New test. * c-c++-common/cpp/Winvalid-utf8-2.c: New test. * c-c++-common/cpp/Winvalid-utf8-3.c: New test. * g++.dg/cpp23/Winvalid-utf8-1.C: New test. * g++.dg/cpp23/Winvalid-utf8-2.C: New test. * g++.dg/cpp23/Winvalid-utf8-3.C: New test. * g++.dg/cpp23/Winvalid-utf8-4.C: New test. * g++.dg/cpp23/Winvalid-utf8-5.C: New test. * g++.dg/cpp23/Winvalid-utf8-6.C: New test. * g++.dg/cpp23/Winvalid-utf8-7.C: New test. * g++.dg/cpp23/Winvalid-utf8-8.C: New test. * g++.dg/cpp23/Winvalid-utf8-9.C: New test. * g++.dg/cpp23/Winvalid-utf8-10.C: New test. * g++.dg/cpp23/Winvalid-utf8-11.C: New test. * g++.dg/cpp23/Winvalid-utf8-12.C: New test. --- libcpp/include/cpplib.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'libcpp/include/cpplib.h') diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index 810203d..a7600de 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -560,6 +560,13 @@ struct cpp_options cpp_bidirectional_level. */ unsigned char cpp_warn_bidirectional; + /* True if libcpp should warn about invalid UTF-8 characters in comments. + 2 if it should be a pedwarn. */ + unsigned char cpp_warn_invalid_utf8; + + /* True if -finput-charset= option has been used explicitly. */ + bool cpp_input_charset_explicit; + /* Dependency generation. */ struct { @@ -666,7 +673,8 @@ enum cpp_warning_reason { CPP_W_CXX11_COMPAT, CPP_W_CXX20_COMPAT, CPP_W_EXPANSION_TO_DEFINED, - CPP_W_BIDIRECTIONAL + CPP_W_BIDIRECTIONAL, + CPP_W_INVALID_UTF8 }; /* Callback for header lookup for HEADER, which is the name of a -- cgit v1.1 From bedfca647a9e9c1adadd8924f3ee0ab4189424e0 Mon Sep 17 00:00:00 2001 From: David Malcolm Date: Fri, 2 Sep 2022 18:29:33 -0400 Subject: c/c++: new warning: -Wxor-used-as-pow [PR90885] PR c/90885 notes various places in real-world code where people have written C/C++ code that uses ^ (exclusive or) where presumbably they meant exponentiation. For example https://codesearch.isocpp.org/cgi-bin/cgi_ppsearch?q=2%5E32&search=Search currently finds 11 places using "2^32", and all of them appear to be places where the user means 2 to the power of 32, rather than 2 exclusive-orred with 32 (which is 34). This patch adds a new -Wxor-used-as-pow warning to the C and C++ frontends to complain about ^ when the left-hand side is the decimal constant 2 or the decimal constant 10. This is the same name as the corresponding clang warning: https://clang.llvm.org/docs/DiagnosticsReference.html#wxor-used-as-pow As per the clang warning, the warning suggests converting the left-hand side to a hexadecimal constant if you really mean xor, which suppresses the warning (though this patch implements a fix-it hint for that, whereas the clang implementation only has a fix-it hint for the initial suggestion of exponentiation). I initially tried implementing this without checking for decimals, but this version had lots of false positives. Checking for decimals requires extending the lexer to capture whether or not a CPP_NUMBER token was decimal. I added a new DECIMAL_INT flag to cpplib.h for this. Unfortunately, c_token and cp_tokens both have only an unsigned char for their flags (as captured by c_lex_with_flags), whereas this would add the 12th flag to cpp_tokens. Of the first 8 flags, all but BOL are used in the C or C++ frontends, but BOL is not, so I moved that to a higher position, using its old value for the new DECIMAL_INT flag, so that it is representable within an unsigned char. Example output: demo.c:5:13: warning: result of '2^8' is 10; did you mean '1 << 8' (256)? [-Wxor-used-as-pow] 5 | int t2_8 = 2^8; | ^ | -- | 1<< demo.c:5:12: note: you can silence this warning by using a hexadecimal constant (0x2 rather than 2) 5 | int t2_8 = 2^8; | ^ | 0x2 demo.c:21:15: warning: result of '10^6' is 12; did you mean '1e6'? [-Wxor-used-as-pow] 21 | int t10_6 = 10^6; | ^ | --- | 1e demo.c:21:13: note: you can silence this warning by using a hexadecimal constant (0xa rather than 10) 21 | int t10_6 = 10^6; | ^~ | 0xa gcc/c-family/ChangeLog: PR c/90885 * c-common.h (check_for_xor_used_as_pow): New decl. * c-lex.cc (c_lex_with_flags): Add DECIMAL_INT to flags as appropriate. * c-warn.cc (check_for_xor_used_as_pow): New. * c.opt (Wxor-used-as-pow): New. gcc/c/ChangeLog: PR c/90885 * c-parser.cc (c_parser_string_literal): Clear ret.m_decimal. (c_parser_expr_no_commas): Likewise. (c_parser_conditional_expression): Likewise. (c_parser_binary_expression): Clear m_decimal when popping the stack. (c_parser_unary_expression): Clear ret.m_decimal. (c_parser_has_attribute_expression): Likewise for result. (c_parser_predefined_identifier): Likewise for expr. (c_parser_postfix_expression): Likewise for expr. Set expr.m_decimal when handling a CPP_NUMBER that was a decimal token. * c-tree.h (c_expr::m_decimal): New bitfield. * c-typeck.cc (parser_build_binary_op): Clear result.m_decimal. (parser_build_binary_op): Call check_for_xor_used_as_pow. gcc/cp/ChangeLog: PR c/90885 * cp-tree.h (class cp_expr): Add bitfield m_decimal. Clear it in existing ctors. Add ctor that allows specifying its value. (cp_expr::decimal_p): New accessor. * parser.cc (cp_parser_expression_stack_entry::flags): New field. (cp_parser_primary_expression): Set m_decimal of cp_expr when handling numbers. (cp_parser_binary_expression): Extract flags from token when populating stack. Call check_for_xor_used_as_pow. gcc/ChangeLog: PR c/90885 * doc/invoke.texi (Warning Options): Add -Wxor-used-as-pow. gcc/testsuite/ChangeLog: PR c/90885 * c-c++-common/Wxor-used-as-pow-1.c: New test. * c-c++-common/Wxor-used-as-pow-fixits.c: New test. * g++.dg/parse/expr3.C: Convert 2 to 0x2 to suppress -Wxor-used-as-pow. * g++.dg/warn/Wparentheses-10.C: Likewise. * g++.dg/warn/Wparentheses-18.C: Likewise. * g++.dg/warn/Wparentheses-19.C: Likewise. * g++.dg/warn/Wparentheses-9.C: Likewise. * g++.dg/warn/Wxor-used-as-pow-named-op.C: New test. * gcc.dg/Wparentheses-6.c: Convert 2 to 0x2 to suppress -Wxor-used-as-pow. * gcc.dg/Wparentheses-7.c: Likewise. * gcc.dg/precedence-1.c: Likewise. libcpp/ChangeLog: PR c/90885 * include/cpplib.h (BOL): Move macro to 1 << 12 since it is not used by C/C++'s unsigned char token flags. (DECIMAL_INT): New, using 1 << 6, so that it is visible as part of C/C++'s 8 bits of token flags. Signed-off-by: David Malcolm --- libcpp/include/cpplib.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'libcpp/include/cpplib.h') diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index a7600de..1a3fb19 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -190,7 +190,7 @@ struct GTY(()) cpp_string { #define NAMED_OP (1 << 4) /* C++ named operators. */ #define PREV_FALLTHROUGH (1 << 5) /* On a token preceeded by FALLTHROUGH comment. */ -#define BOL (1 << 6) /* Token at beginning of line. */ +#define DECIMAL_INT (1 << 6) /* Decimal integer, set in c-lex.cc. */ #define PURE_ZERO (1 << 7) /* Single 0 digit, used by the C++ frontend, set in c-lex.cc. */ #define SP_DIGRAPH (1 << 8) /* # or ## token was a digraph. */ @@ -199,6 +199,7 @@ struct GTY(()) cpp_string { after a # operator. */ #define NO_EXPAND (1 << 10) /* Do not macro-expand this token. */ #define PRAGMA_OP (1 << 11) /* _Pragma token. */ +#define BOL (1 << 12) /* Token at beginning of line. */ /* Specify which field, if any, of the cpp_token union is used. */ -- cgit v1.1 From 572f5e1bc68e131b25cd2d5ba231e932f5038904 Mon Sep 17 00:00:00 2001 From: Jakub Jelinek Date: Wed, 7 Sep 2022 08:44:38 +0200 Subject: libcpp: Named universal character escapes and delimited escape sequence tweaks On Tue, Aug 30, 2022 at 09:10:37PM +0000, Joseph Myers wrote: > I'm seeing build failures of glibc for powerpc64, as illustrated by the > following C code: > > #if 0 > \NARG > #endif > > (the actual sysdeps/powerpc/powerpc64/sysdep.h code is inside #ifdef > __ASSEMBLER__). > > This shows some problems with this feature - and with delimited escape > sequences - as it affects C. It's fine to accept it as an extension > inside string and character literals, because \N or \u{...} would be > invalid in the absence of the feature (i.e. the syntax for such literals > fails to match, meaning that the rule about undefined behavior for a > single ' or " as a pp-token applies). But outside string and character > literals, the usual lexing rules apply, the \ is a pp-token on its own and > the code is valid at the preprocessing level, and with expansion of macros > appearing before or after the \ (e.g. u defined as a macro in the \u{...} > case) it may be valid code at the language level as well. I don't know > what older C++ versions say about this, but for C this means e.g. > > #define z(x) 0 > #define a z( > int x = a\NARG); > > needs to be accepted as expanding to "int x = 0;", not interpreted as > using the \N feature in an identifier and produce an error. The following patch changes this, so that: 1) outside of string/character literals, \N without following { is never treated as an error nor warning, it is silently treated as \ separate token followed by whatever is after it 2) \u{123} and \N{LATIN SMALL LETTER A WITH ACUTE} are not handled as extension at all outside of string/character literals in the strict standard modes (-std=c*) except for -std=c++{23,2b}, only in the -std=gnu* modes, because it changes behavior on valid sources, e.g. #define z(x) 0 #define a z( int x = a\u{123}); int y = a\N{LATIN SMALL LETTER A WITH ACUTE}); 3) introduces -Wunicode warning (on by default) and warns for cases of what looks like invalid delimited escape sequence or named universal character escape outside of string/character literals and is treated as separate tokens 2022-09-07 Jakub Jelinek 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 | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'libcpp/include/cpplib.h') diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index 1a3fb19..c25bcf2 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -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 -- cgit v1.1 From 0a91bdaf177409a2a5e7895bce4f0e7091b4b3ca Mon Sep 17 00:00:00 2001 From: Joseph Myers Date: Wed, 7 Sep 2022 13:56:25 +0000 Subject: c: New C2x keywords C2x follows C++ in making alignas, alignof, bool, false, static_assert, thread_local and true keywords; implement this accordingly. This implementation makes them normal keywords in C2x mode just like any other keyword (C2x leaves open the possibility of implementation using predefined macros instead - thus, there aren't any testcases asserting that they aren't macros). As in C++ and previous versions of C, true and false are handled like signed 1 and 0 in #if (there was an intermediate state in some C2x drafts where they had different macro expansions that were unsigned in #if). Bootstrapped with no regressions for x86_64-pc-linux-gnu. As with the removal of unprototyped functions, this change has a high risk of breaking some old code and people doing GNU/Linux distribution builds may wish to see how much is broken in a build with a -std=gnu2x default. gcc/ * ginclude/stdalign.h [defined __STDC_VERSION__ && __STDC_VERSION__ > 201710L]: Disable all content. * ginclude/stdbool.h [defined __STDC_VERSION__ && __STDC_VERSION__ > 201710L] (bool, true, false): Do not define. gcc/c-family/ * c-common.cc (c_common_reswords): Use D_C2X instead of D_CXXONLY for alignas, alignof, bool, false, static_assert, thread_local and true. gcc/c/ * c-parser.cc (c_parser_static_assert_declaration_no_semi) (c_parser_alignas_specifier, c_parser_alignof_expression): Allow for C2x spellings of keywords. (c_parser_postfix_expression): Handle RID_TRUE and RID_FALSE. gcc/testsuite/ * gcc.dg/c11-keywords-1.c, gcc.dg/c2x-align-1.c, gcc.dg/c2x-align-6.c, gcc.dg/c2x-bool-2.c, gcc.dg/c2x-static-assert-3.c, gcc.dg/c2x-static-assert-4.c, gcc.dg/c2x-thread-local-1.c: New tests. * gcc.dg/c2x-bool-1.c: Update expectations. libcpp/ * include/cpplib.h (struct cpp_options): Add true_false. * expr.cc (eval_token): Check true_false not cplusplus to determine whether to handle true and false keywords. * init.cc (struct lang_flags): Add true_false. (lang_defaults): Update. (cpp_set_lang): Set true_false. --- libcpp/include/cpplib.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'libcpp/include/cpplib.h') diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index c25bcf2..2db1e9c 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -526,6 +526,9 @@ struct cpp_options /* Nonzero for C++23 delimited escape sequences. */ unsigned char delimited_escape_seqs; + /* Nonzero for 'true' and 'false' in #if expressions. */ + unsigned char true_false; + /* Holds the name of the target (execution) character set. */ const char *narrow_charset; -- cgit v1.1