From 2c03d73667df53165834e9bcb5d09243db414ec3 Mon Sep 17 00:00:00 2001 From: Jakub Jelinek Date: Thu, 7 Nov 2019 21:24:38 +0100 Subject: PR c++/91370 - Implement P1041R4 and P1139R2 - Stronger Unicode reqs 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. From-SVN: r277929 --- libcpp/ChangeLog | 11 +++++++++++ libcpp/charset.c | 16 +++++++++++----- 2 files changed, 22 insertions(+), 5 deletions(-) (limited to 'libcpp') diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog index 8be8438..b57f265 100644 --- a/libcpp/ChangeLog +++ b/libcpp/ChangeLog @@ -1,3 +1,14 @@ +2019-11-07 Jakub Jelinek + + 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. + 2019-11-05 Tim van Deurzen * cpplib.h: Add spaceship operator for C++. diff --git a/libcpp/charset.c b/libcpp/charset.c index 39af77a..0b8815a 100644 --- a/libcpp/charset.c +++ b/libcpp/charset.c @@ -1881,10 +1881,11 @@ cpp_interpret_string_notranslate (cpp_reader *pfile, const cpp_string *from, /* 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 *pfile, cpp_string str, 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, cpp_string str, 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 *pfile, const cpp_token *token, 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); -- cgit v1.1