diff --git a/libstdc++-v3/ChangeLog b/libstdc++-v3/ChangeLog index 93707882ee9..d6f6855bc0a 100644 --- a/libstdc++-v3/ChangeLog +++ b/libstdc++-v3/ChangeLog @@ -1,3 +1,90 @@ +2003-02-06 Benjamin Kosnik + + * testsuite/22_locale/codecvt/encoding/wchar_t/1.cc (test01): + Explicitly use the "C" locale. + * testsuite/22_locale/codecvt/max_length/wchar_t/1.cc (test01): Same. + +2003-02-06 Petur Runolfsson + + DR 75 + DR 305 + PR libstdc++/9028 (partial) + PR libstdc++/9224 + PR libstdc++/9246 + PR libstdc++/9247 + + * src/codecvt.cc + (codecvt::do_encoding, + codecvt::do_length, + codecvt::do_max_length): + Move... + * config/locale/generic/codecvt_members.cc: ...here. + * config/locale/gnu/codecvt_members.cc: ...and here. + + * config/locale/generic/codecvt_members.cc, + * config/locale/gnu/codecvt_members.cc + (codecvt::do_encoding + codecvt::do_in, + codecvt::do_length, + codecvt::do_max_length, + codecvt::do_out): + New implementation that handles stateless encodings, + including UTF-8. + + * config/locale/generic/codecvt_members.cc, + * config/locale/gnu/codecvt_members.cc, + * config/locale/ieee_1003.1-2001/codecvt_specializations.h, + * include/bits/codecvt.h, + * src/codecvt.cc + (codecvt::length, codecvt::do_length): + Change type of first argument of length and do_length from + 'const state_type&' to 'state_type&' according to DR 75. + + * testsuite/22_locale/codecvt/always_noconv/wchar_t/1.cc: Cleanup. + * testsuite/22_locale/codecvt/always_noconv/wchar_t/2.cc: New test. + * testsuite/22_locale/codecvt/always_noconv/wchar_t/3.cc: New test. + * testsuite/22_locale/codecvt/always_noconv/wchar_t/4.cc: New test. + * testsuite/22_locale/codecvt/encoding/wchar_t/1.cc: + Cleanup and check for correct return value from encoding + for "C" locale. + * testsuite/22_locale/codecvt/encoding/wchar_t/2.cc: New test. + * testsuite/22_locale/codecvt/encoding/wchar_t/3.cc: New test. + * testsuite/22_locale/codecvt/encoding/wchar_t/4.cc: New test. + * testsuite/22_locale/codecvt/in/wchar_t/1.cc: Cleanup. + * testsuite/22_locale/codecvt/in/wchar_t/2.cc: New test. + * testsuite/22_locale/codecvt/in/wchar_t/3.cc: New test. + * testsuite/22_locale/codecvt/in/wchar_t/4.cc: New test. + * testsuite/22_locale/codecvt/in/wchar_t/5.cc: New test. + * testsuite/22_locale/codecvt/in/wchar_t/6.cc: New test. + * testsuite/22_locale/codecvt/in/wchar_t/7.cc: New test. + * testsuite/22_locale/codecvt/in/wchar_t/8.cc: New test. + * testsuite/22_locale/codecvt/in/wchar_t/9.cc: New test. + * testsuite/22_locale/codecvt/length/char/1.cc: Cleanup. + * testsuite/22_locale/codecvt/length/char/2.cc: New test. + * testsuite/22_locale/codecvt/length/wchar_t/1.cc: Cleanup. + * testsuite/22_locale/codecvt/length/wchar_t/2.cc: New test. + * testsuite/22_locale/codecvt/length/wchar_t/3.cc: New test. + * testsuite/22_locale/codecvt/length/wchar_t/4.cc: New test. + * testsuite/22_locale/codecvt/length/wchar_t/5.cc: New test. + * testsuite/22_locale/codecvt/length/wchar_t/6.cc: New test. + * testsuite/22_locale/codecvt/length/wchar_t/7.cc: New test. + * testsuite/22_locale/codecvt/max_length/wchar_t/1.cc: Cleanup. + * testsuite/22_locale/codecvt/max_length/wchar_t/2.cc: New test. + * testsuite/22_locale/codecvt/max_length/wchar_t/3.cc: New test. + * testsuite/22_locale/codecvt/max_length/wchar_t/4.cc: New test. + * testsuite/22_locale/codecvt/out/wchar_t/1.cc: Cleanup. + * testsuite/22_locale/codecvt/out/wchar_t/2.cc: New test. + * testsuite/22_locale/codecvt/out/wchar_t/3.cc: New test. + * testsuite/22_locale/codecvt/out/wchar_t/4.cc: New test. + * testsuite/22_locale/codecvt/out/wchar_t/5.cc: New test. + * testsuite/22_locale/codecvt/out/wchar_t/6.cc: New test. + * testsuite/22_locale/codecvt/out/wchar_t/7.cc: New test. + * testsuite/22_locale/codecvt/unicode/1.cc: New test. + * testsuite/22_locale/codecvt/unshift/wchar_t/1.cc: Cleanup. + * testsuite/22_locale/codecvt/unshift/wchar_t/2.cc: New test. + * testsuite/22_locale/codecvt/unshift/wchar_t/3.cc: New test. + * testsuite/22_locale/codecvt/unshfit/wchar_t/4.cc: New test. + 2003-02-05 Benjamin Kosnik * include/bits/locale_facets.tcc (time_put::do_put): Use __write. diff --git a/libstdc++-v3/config/locale/generic/codecvt_members.cc b/libstdc++-v3/config/locale/generic/codecvt_members.cc index 0abe542883b..bd685107533 100644 --- a/libstdc++-v3/config/locale/generic/codecvt_members.cc +++ b/libstdc++-v3/config/locale/generic/codecvt_members.cc @@ -46,25 +46,42 @@ namespace std extern_type* __to, extern_type* __to_end, extern_type*& __to_next) const { - result __ret = error; - size_t __len = std::min(__from_end - __from, __to_end - __to); - size_t __conv = wcsrtombs(__to, &__from, __len, &__state); + result __ret = ok; + // The conversion must be done using a temporary destination buffer + // since it is not possible to pass the size of the buffer to wcrtomb + extern_type __buf[MB_LEN_MAX]; + // A temporary state must be used since the result of the last + // conversion may be thrown away. + state_type __tmp_state(__state); + + // The conversion must be done by calling wcrtomb in a loop rather + // than using wcsrtombs because wcsrtombs assumes that the input is + // zero-terminated. + while (__from < __from_end && __to < __to_end) + { + size_t __conv = wcrtomb(__buf, *__from, &__tmp_state); + if (__conv == static_cast(-1)) + { + __ret = error; + break; + } + else if (__conv > static_cast(__to_end - __to)) + { + __ret = partial; + break; + } - if (__conv == __len) - { - __from_next = __from; - __to_next = __to + __conv; - __ret = ok; + memcpy(__to, __buf, __conv); + __state = __tmp_state; + __to += __conv; + __from++; } - else if (__conv > 0 && __conv < __len) - { - __from_next = __from; - __to_next = __to + __conv; - __ret = partial; - } - else - __ret = error; - + + if (__ret == ok && __from < __from_end) + __ret = partial; + + __from_next = __from; + __to_next = __to; return __ret; } @@ -75,25 +92,106 @@ namespace std intern_type* __to, intern_type* __to_end, intern_type*& __to_next) const { - result __ret = error; - size_t __len = std::min(__from_end - __from, __to_end - __to); - size_t __conv = mbsrtowcs(__to, &__from, __len, &__state); + result __ret = ok; + // This temporary state object is neccessary so __state won't be modified + // if [__from, __from_end) is a partial multibyte character. + state_type __tmp_state(__state); - if (__conv == __len) + // Conversion must be done by calling mbrtowc in a loop rather than + // by calling mbsrtowcs because mbsrtowcs assumes that the input + // sequence is zero-terminated. + while (__from < __from_end && __to < __to_end) { - __from_next = __from; - __to_next = __to + __conv; - __ret = ok; + size_t __conv = mbrtowc(__to, __from, __from_end - __from, + &__tmp_state); + if (__conv == static_cast(-1)) + { + __ret = error; + break; + } + else if (__conv == static_cast(-2)) + { + // It is unclear what to return in this case (see DR 382). + __ret = partial; + break; + } + else if (__conv == 0) + { + // XXX Probably wrong for stateful encodings + __conv = 1; + *__to = L'\0'; + } + + __state = __tmp_state; + __to++; + __from += __conv; } - else if (__conv > 0 && __conv < __len) + + // It is not clear that __from < __from_end implies __ret != ok + // (see DR 382). + if (__ret == ok && __from < __from_end) + __ret = partial; + + __from_next = __from; + __to_next = __to; + return __ret; + } + + int + codecvt:: + do_encoding() const throw() + { + // XXX This implementation assumes that the encoding is + // stateless and is either single-byte or variable-width. + int __ret = 0; + if (MB_CUR_MAX == 1) + __ret = 1; + return __ret; + } + + int + codecvt:: + do_max_length() const throw() + { + // XXX Probably wrong for stateful encodings. + int __ret = MB_CUR_MAX; + return __ret; + } + + int + codecvt:: + do_length(state_type& __state, const extern_type* __from, + const extern_type* __end, size_t __max) const + { + int __ret = 0; + state_type __tmp_state(__state); + + while (__from < __end && __max) { - __from_next = __from; - __to_next = __to + __conv; - __ret = partial; + size_t __conv = mbrtowc(NULL, __from, __end - __from, &__tmp_state); + if (__conv == static_cast(-1)) + { + // Invalid source character + break; + } + else if (__conv == static_cast(-2)) + { + // Remainder of input does not form a complete destination + // character. + break; + } + else if (__conv == 0) + { + // XXX Probably wrong for stateful encodings + __conv = 1; + } + + __state = __tmp_state; + __from += __conv; + __ret += __conv; + __max--; } - else - __ret = error; - + return __ret; } #endif diff --git a/libstdc++-v3/config/locale/gnu/codecvt_members.cc b/libstdc++-v3/config/locale/gnu/codecvt_members.cc index 2e71a326d1c..b093385a586 100644 --- a/libstdc++-v3/config/locale/gnu/codecvt_members.cc +++ b/libstdc++-v3/config/locale/gnu/codecvt_members.cc @@ -47,31 +47,50 @@ namespace std extern_type* __to, extern_type* __to_end, extern_type*& __to_next) const { - result __ret = error; - size_t __len = std::min(__from_end - __from, __to_end - __to); + result __ret = ok; + // The conversion must be done using a temporary destination buffer + // since it is not possible to pass the size of the buffer to wcrtomb + extern_type __buf[MB_LEN_MAX]; + // A temporary state must be used since the result of the last + // conversion may be thrown away. + state_type __tmp_state(__state); + #if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) __c_locale __old = __uselocale(_M_c_locale_codecvt); #endif - size_t __conv = wcsrtombs(__to, &__from, __len, &__state); + + // The conversion must be done by calling wcrtomb in a loop rather + // than using wcsrtombs because wcsrtombs assumes that the input is + // zero-terminated. + while (__from < __from_end && __to < __to_end) + { + size_t __conv = wcrtomb(__buf, *__from, &__tmp_state); + if (__conv == static_cast(-1)) + { + __ret = error; + break; + } + else if (__conv > static_cast(__to_end - __to)) + { + __ret = partial; + break; + } + + memcpy(__to, __buf, __conv); + __state = __tmp_state; + __to += __conv; + __from++; + } + #if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) __uselocale(__old); #endif - if (__conv == __len) - { - __from_next = __from; - __to_next = __to + __conv; - __ret = ok; - } - else if (__conv > 0 && __conv < __len) - { - __from_next = __from; - __to_next = __to + __conv; - __ret = partial; - } - else - __ret = error; - + if (__ret == ok && __from < __from_end) + __ret = partial; + + __from_next = __from; + __to_next = __to; return __ret; } @@ -82,31 +101,131 @@ namespace std intern_type* __to, intern_type* __to_end, intern_type*& __to_next) const { - result __ret = error; - size_t __len = std::min(__from_end - __from, __to_end - __to); + result __ret = ok; + // This temporary state object is neccessary so __state won't be modified + // if [__from, __from_end) is a partial multibyte character. + state_type __tmp_state(__state); #if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) __c_locale __old = __uselocale(_M_c_locale_codecvt); #endif - size_t __conv = mbsrtowcs(__to, &__from, __len, &__state); + + // Conversion must be done by calling mbrtowc in a loop rather than + // by calling mbsrtowcs because mbsrtowcs assumes that the input + // sequence is zero-terminated. + while (__from < __from_end && __to < __to_end) + { + size_t __conv = mbrtowc(__to, __from, __from_end - __from, + &__tmp_state); + if (__conv == static_cast(-1)) + { + __ret = error; + break; + } + else if (__conv == static_cast(-2)) + { + // It is unclear what to return in this case (see DR 382). + __ret = partial; + break; + } + else if (__conv == 0) + { + // XXX Probably wrong for stateful encodings + __conv = 1; + *__to = L'\0'; + } + + __state = __tmp_state; + __to++; + __from += __conv; + } + #if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) __uselocale(__old); #endif - if (__conv == __len) + // It is not clear that __from < __from_end implies __ret != ok + // (see DR 382). + if (__ret == ok && __from < __from_end) + __ret = partial; + + __from_next = __from; + __to_next = __to; + return __ret; + } + + int + codecvt:: + do_encoding() const throw() + { + // XXX This implementation assumes that the encoding is + // stateless and is either single-byte or variable-width. + int __ret = 0; +#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) + __c_locale __old = __uselocale(_M_c_locale_codecvt); +#endif + if (MB_CUR_MAX == 1) + __ret = 1; +#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) + __uselocale(__old); +#endif + return __ret; + } + + int + codecvt:: + do_max_length() const throw() + { +#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) + __c_locale __old = __uselocale(_M_c_locale_codecvt); +#endif + // XXX Probably wrong for stateful encodings. + int __ret = MB_CUR_MAX; +#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) + __uselocale(__old); +#endif + return __ret; + } + + int + codecvt:: + do_length(state_type& __state, const extern_type* __from, + const extern_type* __end, size_t __max) const + { + int __ret = 0; + state_type __tmp_state(__state); +#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) + __c_locale __old = __uselocale(_M_c_locale_codecvt); +#endif + + while (__from < __end && __max) { - __from_next = __from; - __to_next = __to + __conv; - __ret = ok; + size_t __conv = mbrtowc(NULL, __from, __end - __from, &__tmp_state); + if (__conv == static_cast(-1)) + { + // Invalid source character + break; + } + else if (__conv == static_cast(-2)) + { + // Remainder of input does not form a complete destination + // character. + break; + } + else if (__conv == 0) + { + // XXX Probably wrong for stateful encodings + __conv = 1; + } + + __state = __tmp_state; + __from += __conv; + __ret += __conv; + __max--; } - else if (__conv > 0 && __conv < __len) - { - __from_next = __from; - __to_next = __to + __conv; - __ret = partial; - } - else - __ret = error; - + +#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) + __uselocale(__old); +#endif return __ret; } #endif diff --git a/libstdc++-v3/config/locale/ieee_1003.1-2001/codecvt_specializations.h b/libstdc++-v3/config/locale/ieee_1003.1-2001/codecvt_specializations.h index 1921905dfe5..45c069d342e 100644 --- a/libstdc++-v3/config/locale/ieee_1003.1-2001/codecvt_specializations.h +++ b/libstdc++-v3/config/locale/ieee_1003.1-2001/codecvt_specializations.h @@ -230,7 +230,7 @@ do_always_noconv() const throw(); virtual int - do_length(const state_type&, const extern_type* __from, + do_length(state_type&, const extern_type* __from, const extern_type* __end, size_t __max) const; virtual int @@ -447,7 +447,7 @@ template int codecvt<_InternT, _ExternT, __enc_traits>:: - do_length(const state_type&, const extern_type* __from, + do_length(state_type&, const extern_type* __from, const extern_type* __end, size_t __max) const { return std::min(__max, static_cast(__end - __from)); } diff --git a/libstdc++-v3/include/bits/codecvt.h b/libstdc++-v3/include/bits/codecvt.h index c88c29d2cd0..45d5f3a2915 100644 --- a/libstdc++-v3/include/bits/codecvt.h +++ b/libstdc++-v3/include/bits/codecvt.h @@ -106,7 +106,7 @@ { return this->do_always_noconv(); } int - length(const state_type& __state, const extern_type* __from, + length(state_type& __state, const extern_type* __from, const extern_type* __end, size_t __max) const { return this->do_length(__state, __from, __end, __max); } @@ -144,7 +144,7 @@ do_always_noconv() const throw() = 0; virtual int - do_length(const state_type&, const extern_type* __from, + do_length(state_type&, const extern_type* __from, const extern_type* __end, size_t __max) const = 0; virtual int @@ -204,7 +204,7 @@ do_always_noconv() const throw(); virtual int - do_length(const state_type&, const extern_type* __from, + do_length(state_type&, const extern_type* __from, const extern_type* __end, size_t __max) const; virtual int @@ -264,7 +264,7 @@ do_always_noconv() const throw(); virtual int - do_length(const state_type&, const extern_type* __from, + do_length(state_type&, const extern_type* __from, const extern_type* __end, size_t __max) const; virtual int @@ -324,7 +324,7 @@ bool do_always_noconv() const throw(); virtual - int do_length(const state_type&, const extern_type* __from, + int do_length(state_type&, const extern_type* __from, const extern_type* __end, size_t __max) const; virtual int diff --git a/libstdc++-v3/src/codecvt.cc b/libstdc++-v3/src/codecvt.cc index a436dc64d8c..a44256d5f7a 100644 --- a/libstdc++-v3/src/codecvt.cc +++ b/libstdc++-v3/src/codecvt.cc @@ -108,7 +108,7 @@ namespace std int codecvt:: - do_length (const state_type&, const extern_type* __from, + do_length (state_type&, const extern_type* __from, const extern_type* __end, size_t __max) const { return std::min(__max, static_cast(__end - __from)); } @@ -138,29 +138,14 @@ namespace std do_unshift(state_type&, extern_type* __to, extern_type*, extern_type*& __to_next) const { + // XXX Probably wrong for stateful encodings __to_next = __to; return noconv; } - int - codecvt:: - do_encoding() const throw() - { return sizeof(wchar_t); } - bool codecvt:: do_always_noconv() const throw() { return false; } - - int - codecvt:: - do_length(const state_type&, const extern_type* __from, - const extern_type* __end, size_t __max) const - { return std::min(__max, static_cast(__end - __from)); } - - int - codecvt:: - do_max_length() const throw() - { return 1; } #endif // _GLIBCPP_USE_WCHAR_T } // namespace std diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/1.cc b/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/1.cc index fb267410804..25d66af0d68 100644 --- a/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/1.cc +++ b/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/1.cc @@ -23,49 +23,17 @@ #include #include -// Need to explicitly set the state(mbstate_t) to zero. -// How to do this is not specified by the ISO C99 standard, so we -// might need to add some operators to make the intuiative case -// work: -// w_codecvt::state_type state00; -// state00 = 0; -// or, can use this explicit "C" initialization: -// w_codecvt::state_type state01 = {0, 0}; -// .. except Ulrich says: Use memset. Always use memset. Feel the force... -void -zero_state(std::mbstate_t& state) -{ std::memset(&state, 0, sizeof(std::mbstate_t)); } - // Required instantiation // codecvt void test01() { using namespace std; typedef codecvt w_codecvt; - typedef codecvt_base::result result; - typedef wchar_t int_type; - typedef char ext_type; - typedef char_traits int_traits; - typedef char_traits ext_traits; - - bool test = true; - const ext_type* e_lit = "black pearl jasmine tea"; - const ext_type* efrom_next; - const int_type* i_lit = L"black pearl jasmine tea"; - const int_type* ifrom_next; - int size = strlen(e_lit); - ext_type* e_arr = new ext_type[size + 1]; - ext_type* eto_next; - int_type* i_arr = new int_type[size + 1]; - int_type* ito_next; locale loc; const w_codecvt* cvt = &use_facet(loc); VERIFY( !cvt->always_noconv() ); - - delete [] e_arr; - delete [] i_arr; } int main () diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/2.cc b/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/2.cc new file mode 100644 index 00000000000..19e73985f19 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/2.cc @@ -0,0 +1,46 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Required instantiation +// codecvt +// +// Baseline test in ISO-8859-1 locale +void test02() +{ + using namespace std; + typedef codecvt w_codecvt; + + locale loc ("en_US.ISO-8859-1"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + VERIFY( !cvt->always_noconv() ); +} + +int main () +{ + test02(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/3.cc b/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/3.cc new file mode 100644 index 00000000000..8681276f6b1 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/3.cc @@ -0,0 +1,46 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Required instantiation +// codecvt +// +// Baseline test in ISO-8859-15 locale +void test03() +{ + using namespace std; + typedef codecvt w_codecvt; + + locale loc ("en_US.ISO-8859-15"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + VERIFY( !cvt->always_noconv() ); +} + +int main () +{ + test03(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/4.cc b/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/4.cc new file mode 100644 index 00000000000..36bc3a183bd --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/always_noconv/wchar_t/4.cc @@ -0,0 +1,46 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Required instantiation +// codecvt +// +// Baseline test in UTF-8 locale +void test04() +{ + using namespace std; + typedef codecvt w_codecvt; + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + VERIFY( !cvt->always_noconv() ); +} + +int main () +{ + test04(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/1.cc b/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/1.cc index 0aefff30397..d2fa938e892 100644 --- a/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/1.cc +++ b/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/1.cc @@ -23,50 +23,19 @@ #include #include -// Need to explicitly set the state(mbstate_t) to zero. -// How to do this is not specified by the ISO C99 standard, so we -// might need to add some operators to make the intuiative case -// work: -// w_codecvt::state_type state00; -// state00 = 0; -// or, can use this explicit "C" initialization: -// w_codecvt::state_type state01 = {0, 0}; -// .. except Ulrich says: Use memset. Always use memset. Feel the force... -void -zero_state(std::mbstate_t& state) -{ std::memset(&state, 0, sizeof(std::mbstate_t)); } - // Required instantiation // codecvt void test01() { using namespace std; typedef codecvt w_codecvt; - typedef codecvt_base::result result; - typedef wchar_t int_type; - typedef char ext_type; - typedef char_traits int_traits; - typedef char_traits ext_traits; - bool test = true; - const ext_type* e_lit = "black pearl jasmine tea"; - const ext_type* efrom_next; - const int_type* i_lit = L"black pearl jasmine tea"; - const int_type* ifrom_next; - int size = strlen(e_lit); - ext_type* e_arr = new ext_type[size + 1]; - ext_type* eto_next; - int_type* i_arr = new int_type[size + 1]; - int_type* ito_next; - locale loc; - const w_codecvt* cvt = &use_facet(loc); + locale loc_c = locale::classic(); + const w_codecvt* cvt = &use_facet(loc_c); int i = cvt->encoding(); - VERIFY( i == 4 ); // Target-dependent. - - delete [] e_arr; - delete [] i_arr; + VERIFY( i == 1 ); // Depends both on target and locale. } int main () diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/2.cc b/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/2.cc new file mode 100644 index 00000000000..9c7f5d040e6 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/2.cc @@ -0,0 +1,48 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Required instantiation +// codecvt +// +// Test do_encoding with ISO-8859-1 locale. +void test02() +{ + using namespace std; + typedef codecvt w_codecvt; + bool test = true; + + locale loc ("en_US.ISO-8859-1"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + int i = cvt->encoding(); + VERIFY( i == 1 ); // ISO-8859-1 is a single-byte encoding +} + +int main () +{ + test02(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/3.cc b/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/3.cc new file mode 100644 index 00000000000..98a8961113e --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/3.cc @@ -0,0 +1,48 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Required instantiation +// codecvt +// +// Test do_encoding with ISO-8859-15 locale. +void test03() +{ + using namespace std; + typedef codecvt w_codecvt; + bool test = true; + + locale loc ("en_US.ISO-8859-15"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + int i = cvt->encoding(); + VERIFY( i == 1 ); // ISO-8859-15 is a single-byte encoding +} + +int main () +{ + test03(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/4.cc b/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/4.cc new file mode 100644 index 00000000000..f2ada106694 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/encoding/wchar_t/4.cc @@ -0,0 +1,48 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Required instantiation +// codecvt +// +// Test do_encoding with UTF-8 locale. +void test04() +{ + using namespace std; + typedef codecvt w_codecvt; + bool test = true; + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + int i = cvt->encoding(); + VERIFY( i == 0 ); // UTF-8 is a stateless multibyte encoding +} + +int main () +{ + test04(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/1.cc b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/1.cc index 7340d418209..d5a410a7741 100644 --- a/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/1.cc +++ b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/1.cc @@ -38,6 +38,8 @@ zero_state(std::mbstate_t& state) // Required instantiation // codecvt +// +// Baseline test for "C" locale void test01() { using namespace std; @@ -46,17 +48,16 @@ void test01() typedef wchar_t int_type; typedef char ext_type; typedef char_traits int_traits; - typedef char_traits ext_traits; bool test = true; const ext_type* e_lit = "black pearl jasmine tea"; const ext_type* efrom_next; const int_type* i_lit = L"black pearl jasmine tea"; - const int_type* ifrom_next; int size = strlen(e_lit); - ext_type* e_arr = new ext_type[size + 1]; - ext_type* eto_next; int_type* i_arr = new int_type[size + 1]; + int_type* i_ref = new int_type[size + 1]; + wmemset(i_arr, 0xdeadbeef, size + 1); + wmemset(i_ref, 0xdeadbeef, size + 1); int_type* ito_next; locale loc; @@ -68,12 +69,13 @@ void test01() result r1 = cvt->in(state01, e_lit, e_lit + size, efrom_next, i_arr, i_arr + size, ito_next); VERIFY( r1 == codecvt_base::ok ); - VERIFY( !int_traits::compare(i_arr, i_lit, size) ); VERIFY( efrom_next == e_lit + size ); VERIFY( ito_next == i_arr + size ); + VERIFY( !int_traits::compare(i_arr, i_lit, size) ); + VERIFY( !int_traits::compare(ito_next, i_ref, 1) ); - delete [] e_arr; delete [] i_arr; + delete [] i_ref; } int main () diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/2.cc b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/2.cc new file mode 100644 index 00000000000..d9e55ef3858 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/2.cc @@ -0,0 +1,114 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Baseline test for ISO-8859-1. Converts entire charset. +void test02() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits int_traits; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + "abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86" + "\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95" + "\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4" + "\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3" + "\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2" + "\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1" + "\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0" + "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe" + "\xff"; + + const ext_type* efrom_next; + const int_type* i_lit = + L"\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + L"\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + L"'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + L"abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86" + L"\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95" + L"\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4" + L"\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3" + L"\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2" + L"\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1" + L"\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0" + L"\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + L"\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe" + L"\xff"; + + int size = strlen(e_lit); + int_type* i_arr = new int_type[size + 1]; + int_type* i_ref = new int_type[size + 1]; + wmemset(i_arr, 0xdeadbeef, size + 1); + wmemset(i_ref, 0xdeadbeef, size + 1); + int_type* ito_next; + + locale loc ("en_US.ISO-8859-1"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // in + w_codecvt::state_type state01; + zero_state(state01); + result r1 = cvt->in(state01, e_lit, e_lit + size, efrom_next, + i_arr, i_arr + size, ito_next); + VERIFY( r1 == codecvt_base::ok ); + VERIFY( efrom_next == e_lit + size ); + VERIFY( ito_next == i_arr + size ); + VERIFY( !int_traits::compare(i_arr, i_lit, size) ); + VERIFY( !int_traits::compare(ito_next, i_ref, 1) ); + + delete [] i_arr; + delete [] i_ref; +} + +int main () +{ + test02(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/3.cc b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/3.cc new file mode 100644 index 00000000000..152e7e9fe4f --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/3.cc @@ -0,0 +1,128 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Baseline test for ISO-8859-15. Converts entire charset. +void test03() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits int_traits; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + "abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86" + "\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95" + "\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4" + "\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3" + "\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2" + "\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1" + "\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0" + "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe" + "\xff"; + + const ext_type* efrom_next; + const int_type i_lit[] = { + 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, + 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, L'!', + L'"', L'#', L'$', L'%', L'&', L'\'', L'(', L')', L'*', L'+', + L',', L'-', L'.', L'/', L'0', L'1', L'2', L'3', L'4', L'5', + L'6', L'7', L'8', L'9', L':', L';', L'<', L'=', L'>', L'?', + L'@', L'A', L'B', L'C', L'D', L'E', L'F', L'G', L'H', L'I', + L'J', L'K', L'L', L'M', L'N', L'O', L'P', L'Q', L'R', L'S', + L'T', L'U', L'V', L'W', L'X', L'Y', L'Z', L'[', L'\\', L']', + L'^', L'_', L'`', L'a', L'b', L'c', L'd', L'e', L'f', L'g', + L'h', L'i', L'j', L'k', L'l', L'm', L'n', L'o', L'p', L'q', + L'r', L's', L't', L'u', L'v', L'w', L'x', L'y', L'z', L'{', + L'|', L'}', L'~', 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, + 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, + 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, 0xa0, 0xa1, 0xa2, 0xa3, + 0x20ac, 0xa5, 0x160, 0xa7, 0x161, 0xa9, 0xaa, 0xab, 0xac, 0xad, + 0xae, 0xaf, 0xb0, 0xb1, 0xb2, 0xb3, 0x17d, 0xb5, 0xb6, 0xb7, + 0x17e, 0xb9, 0xba, 0xbb, 0x152, 0x153, 0x178, 0xbf, 0xc0, 0xc1, + 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, + 0xcc, 0xcd, 0xce, 0xcf, 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, + 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, + 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, + 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, + 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, + 0xfe, 0xff, 0x0 + }; + + int size = strlen(e_lit); + int_type* i_arr = new int_type[size + 1]; + int_type* i_ref = new int_type[size + 1]; + wmemset(i_arr, 0xdeadbeef, size + 1); + wmemset(i_ref, 0xdeadbeef, size + 1); + int_type* ito_next; + + locale loc ("en_US.ISO-8859-15"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // in + w_codecvt::state_type state01; + zero_state(state01); + result r1 = cvt->in(state01, e_lit, e_lit + size, efrom_next, + i_arr, i_arr + size, ito_next); + VERIFY( r1 == codecvt_base::ok ); + VERIFY( efrom_next == e_lit + size ); + VERIFY( ito_next == i_arr + size ); + VERIFY( !int_traits::compare(i_arr, i_lit, size) ); + VERIFY( !int_traits::compare(ito_next, i_ref, 1) ); + + delete [] i_arr; + delete [] i_ref; +} + +int main () +{ + test03(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/4.cc b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/4.cc new file mode 100644 index 00000000000..c916a16b6c9 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/4.cc @@ -0,0 +1,136 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Baseline test for UTF-8. Converts a selection of characters into +// an array that is known to be of the exact needed size. +void test04() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits int_traits; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@}~\x7f\xc2\x80\xc2\x81\xc2\x82\xc2" + "\x83\xc2\x84\xc2\x85\xc2\x86\xc2\x87\xc2\x88\xc2\x89\xc2\x8a" + "\xc2\x8b\xc2\x8c\xc2\x8d\xc2\x8e\xc2\x8f\xc2\x90\xc2\x91\xc2" + "\x92\xc2\x93\xc2\x94\xc2\x95\xc2\x96\xc2\x97\xc2\x98\xc2\x99" + "\xc2\x9a\xc2\x9b\xc2\x9c\xc3\xba\xc3\xbb\xc3\xbc\xc3\xbd\xc3" + "\xbe\xc3\xbf\xc4\x80\xc4\x81\xc4\x82\xc4\x83\xc4\x84\xc4\x85" + "\xc4\x86\xc4\x87\xc4\x88\xc4\x89\xc4\x8a\xc4\x8b\xc4\x8c\xc4" + "\x8d\xc4\x8e\xc4\x8f\xc4\x90\xc4\x91\xc4\x92\xc4\x93\xc4\x94" + "\xc4\x95\xc4\x96\xc4\x97\xc4\x98\xc4\x99\xdf\xb8\xdf\xb9\xdf" + "\xba\xdf\xbb\xdf\xbc\xdf\xbd\xdf\xbe\xdf\xbf\xe0\xa0\x80\xe0" + "\xa0\x81\xe0\xa0\x82\xe0\xa0\x83\xe0\xa0\x84\xe0\xa0\x85\xe0" + "\xa0\x86\xe0\xa0\x87\xe0\xa0\x88\xe0\xa0\x89\xe0\xa0\x8a\xe0" + "\xa0\x8b\xe0\xa0\x8c\xe0\xa0\x8d\xe0\xa0\x8e\xe0\xa0\x8f\xe0" + "\xa0\x90\xe0\xa0\x91\xe0\xa0\x92\xe0\xa0\x93\xe0\xa0\x94\xe0" + "\xa0\x95\xe0\xa0\x96\xe0\xa0\x97\x1\x2\x4\x8\x10\x20@\xc2\x80" + "\xc4\x80\xc8\x80\xd0\x80\xe0\xa0\x80\xe1\x80\x80\xe2\x80\x80" + "\xe4\x80\x80\xe8\x80\x80\xf0\x90\x80\x80\xf0\xa0\x80\x80\xf1" + "\x80\x80\x80\xf2\x80\x80\x80\xf4\x80\x80\x80\xf8\x88\x80\x80" + "\x80\xf8\x90\x80\x80\x80\xf8\xa0\x80\x80\x80\xf9\x80\x80\x80" + "\x80\xfa\x80\x80\x80\x80\xfc\x84\x80\x80\x80\x80\xfc\x88\x80" + "\x80\x80\x80\xfc\x90\x80\x80\x80\x80\xfc\xa0\x80\x80\x80\x80" + "\xfd\x80\x80\x80\x80\x80"; + + const ext_type* efrom_next; + const int_type i_lit[] = { + 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, + 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, L'!', + L'"', L'#', L'$', L'%', L'&', L'\'', L'(', L')', L'*', L'+', + L',', L'-', L'.', L'/', L'0', L'1', L'2', L'3', L'4', L'5', + L'6', L'7', L'8', L'9', L':', L';', L'<', L'=', L'>', L'?', + L'@', L'}', L'~', 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, + 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, + 0x9a, 0x9b, 0x9c, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x100, + 0x101, 0x102, 0x103, 0x104, 0x105, 0x106, 0x107, 0x108, 0x109, + 0x10a, 0x10b, 0x10c, 0x10d, 0x10e, 0x10f, 0x110, 0x111, 0x112, + 0x113, 0x114, 0x115, 0x116, 0x117, 0x118, 0x119, 0x7f8, 0x7f9, + 0x7fa, 0x7fb, 0x7fc, 0x7fd, 0x7fe, 0x7ff, 0x800, 0x801, 0x802, + 0x803, 0x804, 0x805, 0x806, 0x807, 0x808, 0x809, 0x80a, 0x80b, + 0x80c, 0x80d, 0x80e, 0x80f, 0x810, 0x811, 0x812, 0x813, 0x814, + 0x815, 0x816, 0x817, 0x1, 0x2, 0x4, 0x8, 0x10, 0x20, L'@', + 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, + 0x10000, 0x20000, 0x40000, 0x80000, 0x100000, 0x200000, 0x400000, + 0x800000, 0x1000000, 0x2000000, 0x4000000, 0x8000000, 0x10000000, + 0x20000000, 0x40000000, 0x0 + }; + + int esize = strlen(e_lit); + int isize = wcslen(i_lit); + int_type* i_arr = new int_type[esize + 1]; + int_type* i_ref = new int_type[esize + 1]; + wmemset(i_arr, 0xdeadbeef, esize + 1); + wmemset(i_ref, 0xdeadbeef, esize + 1); + int_type* ito_next; + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // in + w_codecvt::state_type state01; + zero_state(state01); + result r1 = cvt->in(state01, e_lit, e_lit + esize, efrom_next, + i_arr, i_arr + isize, ito_next); + VERIFY( r1 == codecvt_base::ok ); + VERIFY( efrom_next == e_lit + esize ); + VERIFY( ito_next == i_arr + isize ); + VERIFY( !int_traits::compare(i_arr, i_lit, isize) ); + VERIFY( !int_traits::compare(ito_next, i_ref, esize + 1 - isize) ); + + delete [] i_arr; + delete [] i_ref; +} + +int main () +{ + test04(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/5.cc b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/5.cc new file mode 100644 index 00000000000..ec65f60c692 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/5.cc @@ -0,0 +1,86 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Test handling of '\0' characters in input +// libstdc++/9246 +void test05() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits int_traits; + + bool test = true; + const ext_type e_lit[] = { '\0', '\0', 'f', '\0' }; + const ext_type* efrom_next; + const int_type i_lit[] = { L'\0', L'\0', L'f', L'\0' }; + int size = sizeof(e_lit); + int_type* i_arr = new int_type[size + 1]; + int_type* i_ref = new int_type[size + 1]; + wmemset(i_arr, 0xdeadbeef, size + 1); + wmemset(i_ref, 0xdeadbeef, size + 1); + int_type* ito_next; + + locale loc; + const w_codecvt* cvt = &use_facet(loc); + + // in + w_codecvt::state_type state01; + zero_state(state01); + result r1 = cvt->in(state01, e_lit, e_lit + size, efrom_next, + i_arr, i_arr + size, ito_next); + VERIFY( r1 == codecvt_base::ok ); + VERIFY( efrom_next == e_lit + size ); + VERIFY( ito_next == i_arr + size ); + VERIFY( !int_traits::compare(i_arr, i_lit, size) ); + VERIFY( !int_traits::compare(ito_next, i_ref, 1) ); + + delete [] i_arr; + delete [] i_ref; +} + +int main () +{ + test05(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/6.cc b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/6.cc new file mode 100644 index 00000000000..1be30323b8b --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/6.cc @@ -0,0 +1,86 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Test handling of output buffer that is too small. +// libstdc++/9247 +void test06() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits int_traits; + + bool test = true; + const ext_type* e_lit = "black pearl jasmine tea"; + const ext_type* efrom_next; + const int_type* i_lit = L"black pearl jasmine tea"; + int size = strlen(e_lit); + int_type* i_arr = new int_type[size + 1]; + int_type* i_ref = new int_type[size + 1]; + wmemset(i_arr, 0xdeadbeef, size + 1); + wmemset(i_ref, 0xdeadbeef, size + 1); + int_type* ito_next; + + locale loc; + const w_codecvt* cvt = &use_facet(loc); + + // in + w_codecvt::state_type state01; + zero_state(state01); + result r1 = cvt->in(state01, e_lit, e_lit + size, efrom_next, + i_arr, i_arr + 1, ito_next); + VERIFY( r1 == codecvt_base::partial ); + VERIFY( efrom_next == e_lit + 1 ); + VERIFY( ito_next == i_arr + 1 ); + VERIFY( !int_traits::compare(i_arr, i_lit, 1) ); + VERIFY( !int_traits::compare(ito_next, i_ref, size) ); + + delete [] i_arr; + delete [] i_ref; +} + +int main () +{ + test06(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/7.cc b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/7.cc new file mode 100644 index 00000000000..f692e9cee6e --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/7.cc @@ -0,0 +1,86 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Test handling of illegal input sequence in UTF-8. +void test07() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits int_traits; + + bool test = true; + const ext_type* e_lit = "a\xc0\xff"; + const ext_type* efrom_next; + const int_type* i_lit = L"a"; + int size = strlen(e_lit); + int_type* i_arr = new int_type[size + 1]; + int_type* i_ref = new int_type[size + 1]; + wmemset(i_arr, 0xdeadbeef, size + 1); + wmemset(i_ref, 0xdeadbeef, size + 1); + int_type* ito_next; + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // in + w_codecvt::state_type state01; + zero_state(state01); + result r1 = cvt->in(state01, e_lit, e_lit + size, efrom_next, + i_arr, i_arr + size, ito_next); + VERIFY( r1 == codecvt_base::error ); + VERIFY( efrom_next == e_lit + 1 ); + VERIFY( ito_next == i_arr + 1 ); + VERIFY( !int_traits::compare(i_arr, i_lit, 1) ); + VERIFY( !int_traits::compare(ito_next, i_ref, size) ); + + delete [] i_arr; + delete [] i_ref; +} + +int main () +{ + test07(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/8.cc b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/8.cc new file mode 100644 index 00000000000..28b1fa04f80 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/8.cc @@ -0,0 +1,135 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Test UTF-8 with output buffer larger than needed. +void test08() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits int_traits; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@}~\x7f\xc2\x80\xc2\x81\xc2\x82\xc2" + "\x83\xc2\x84\xc2\x85\xc2\x86\xc2\x87\xc2\x88\xc2\x89\xc2\x8a" + "\xc2\x8b\xc2\x8c\xc2\x8d\xc2\x8e\xc2\x8f\xc2\x90\xc2\x91\xc2" + "\x92\xc2\x93\xc2\x94\xc2\x95\xc2\x96\xc2\x97\xc2\x98\xc2\x99" + "\xc2\x9a\xc2\x9b\xc2\x9c\xc3\xba\xc3\xbb\xc3\xbc\xc3\xbd\xc3" + "\xbe\xc3\xbf\xc4\x80\xc4\x81\xc4\x82\xc4\x83\xc4\x84\xc4\x85" + "\xc4\x86\xc4\x87\xc4\x88\xc4\x89\xc4\x8a\xc4\x8b\xc4\x8c\xc4" + "\x8d\xc4\x8e\xc4\x8f\xc4\x90\xc4\x91\xc4\x92\xc4\x93\xc4\x94" + "\xc4\x95\xc4\x96\xc4\x97\xc4\x98\xc4\x99\xdf\xb8\xdf\xb9\xdf" + "\xba\xdf\xbb\xdf\xbc\xdf\xbd\xdf\xbe\xdf\xbf\xe0\xa0\x80\xe0" + "\xa0\x81\xe0\xa0\x82\xe0\xa0\x83\xe0\xa0\x84\xe0\xa0\x85\xe0" + "\xa0\x86\xe0\xa0\x87\xe0\xa0\x88\xe0\xa0\x89\xe0\xa0\x8a\xe0" + "\xa0\x8b\xe0\xa0\x8c\xe0\xa0\x8d\xe0\xa0\x8e\xe0\xa0\x8f\xe0" + "\xa0\x90\xe0\xa0\x91\xe0\xa0\x92\xe0\xa0\x93\xe0\xa0\x94\xe0" + "\xa0\x95\xe0\xa0\x96\xe0\xa0\x97\x1\x2\x4\x8\x10\x20@\xc2\x80" + "\xc4\x80\xc8\x80\xd0\x80\xe0\xa0\x80\xe1\x80\x80\xe2\x80\x80" + "\xe4\x80\x80\xe8\x80\x80\xf0\x90\x80\x80\xf0\xa0\x80\x80\xf1" + "\x80\x80\x80\xf2\x80\x80\x80\xf4\x80\x80\x80\xf8\x88\x80\x80" + "\x80\xf8\x90\x80\x80\x80\xf8\xa0\x80\x80\x80\xf9\x80\x80\x80" + "\x80\xfa\x80\x80\x80\x80\xfc\x84\x80\x80\x80\x80\xfc\x88\x80" + "\x80\x80\x80\xfc\x90\x80\x80\x80\x80\xfc\xa0\x80\x80\x80\x80" + "\xfd\x80\x80\x80\x80\x80"; + + const ext_type* efrom_next; + const int_type i_lit[] = { + 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, + 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, L'!', + L'"', L'#', L'$', L'%', L'&', L'\'', L'(', L')', L'*', L'+', + L',', L'-', L'.', L'/', L'0', L'1', L'2', L'3', L'4', L'5', + L'6', L'7', L'8', L'9', L':', L';', L'<', L'=', L'>', L'?', + L'@', L'}', L'~', 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, + 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, + 0x9a, 0x9b, 0x9c, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x100, + 0x101, 0x102, 0x103, 0x104, 0x105, 0x106, 0x107, 0x108, 0x109, + 0x10a, 0x10b, 0x10c, 0x10d, 0x10e, 0x10f, 0x110, 0x111, 0x112, + 0x113, 0x114, 0x115, 0x116, 0x117, 0x118, 0x119, 0x7f8, 0x7f9, + 0x7fa, 0x7fb, 0x7fc, 0x7fd, 0x7fe, 0x7ff, 0x800, 0x801, 0x802, + 0x803, 0x804, 0x805, 0x806, 0x807, 0x808, 0x809, 0x80a, 0x80b, + 0x80c, 0x80d, 0x80e, 0x80f, 0x810, 0x811, 0x812, 0x813, 0x814, + 0x815, 0x816, 0x817, 0x1, 0x2, 0x4, 0x8, 0x10, 0x20, L'@', + 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, + 0x10000, 0x20000, 0x40000, 0x80000, 0x100000, 0x200000, 0x400000, + 0x800000, 0x1000000, 0x2000000, 0x4000000, 0x8000000, 0x10000000, + 0x20000000, 0x40000000, 0x0 + }; + + int esize = strlen(e_lit); + int isize = wcslen(i_lit); + int_type* i_arr = new int_type[esize + 1]; + int_type* i_ref = new int_type[esize + 1]; + wmemset(i_arr, 0xdeadbeef, esize + 1); + wmemset(i_ref, 0xdeadbeef, esize + 1); + int_type* ito_next; + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // in + w_codecvt::state_type state01; + zero_state(state01); + result r1 = cvt->in(state01, e_lit, e_lit + esize, efrom_next, + i_arr, i_arr + esize, ito_next); + VERIFY( r1 == codecvt_base::ok ); + VERIFY( efrom_next == e_lit + esize ); + VERIFY( ito_next == i_arr + isize ); + VERIFY( !int_traits::compare(i_arr, i_lit, isize) ); + VERIFY( !int_traits::compare(ito_next, i_ref, esize + 1 - isize) ); + + delete [] i_arr; + delete [] i_ref; +} + +int main () +{ + test08(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/9.cc b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/9.cc new file mode 100644 index 00000000000..0ddebc771a9 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/in/wchar_t/9.cc @@ -0,0 +1,158 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Test one source character at a time for UTF-8 +void test09() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits int_traits; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@}~\x7f\xc2\x80\xc2\x81\xc2\x82\xc2" + "\x83\xc2\x84\xc2\x85\xc2\x86\xc2\x87\xc2\x88\xc2\x89\xc2\x8a" + "\xc2\x8b\xc2\x8c\xc2\x8d\xc2\x8e\xc2\x8f\xc2\x90\xc2\x91\xc2" + "\x92\xc2\x93\xc2\x94\xc2\x95\xc2\x96\xc2\x97\xc2\x98\xc2\x99" + "\xc2\x9a\xc2\x9b\xc2\x9c\xc3\xba\xc3\xbb\xc3\xbc\xc3\xbd\xc3" + "\xbe\xc3\xbf\xc4\x80\xc4\x81\xc4\x82\xc4\x83\xc4\x84\xc4\x85" + "\xc4\x86\xc4\x87\xc4\x88\xc4\x89\xc4\x8a\xc4\x8b\xc4\x8c\xc4" + "\x8d\xc4\x8e\xc4\x8f\xc4\x90\xc4\x91\xc4\x92\xc4\x93\xc4\x94" + "\xc4\x95\xc4\x96\xc4\x97\xc4\x98\xc4\x99\xdf\xb8\xdf\xb9\xdf" + "\xba\xdf\xbb\xdf\xbc\xdf\xbd\xdf\xbe\xdf\xbf\xe0\xa0\x80\xe0" + "\xa0\x81\xe0\xa0\x82\xe0\xa0\x83\xe0\xa0\x84\xe0\xa0\x85\xe0" + "\xa0\x86\xe0\xa0\x87\xe0\xa0\x88\xe0\xa0\x89\xe0\xa0\x8a\xe0" + "\xa0\x8b\xe0\xa0\x8c\xe0\xa0\x8d\xe0\xa0\x8e\xe0\xa0\x8f\xe0" + "\xa0\x90\xe0\xa0\x91\xe0\xa0\x92\xe0\xa0\x93\xe0\xa0\x94\xe0" + "\xa0\x95\xe0\xa0\x96\xe0\xa0\x97\x1\x2\x4\x8\x10\x20@\xc2\x80" + "\xc4\x80\xc8\x80\xd0\x80\xe0\xa0\x80\xe1\x80\x80\xe2\x80\x80" + "\xe4\x80\x80\xe8\x80\x80\xf0\x90\x80\x80\xf0\xa0\x80\x80\xf1" + "\x80\x80\x80\xf2\x80\x80\x80\xf4\x80\x80\x80\xf8\x88\x80\x80" + "\x80\xf8\x90\x80\x80\x80\xf8\xa0\x80\x80\x80\xf9\x80\x80\x80" + "\x80\xfa\x80\x80\x80\x80\xfc\x84\x80\x80\x80\x80\xfc\x88\x80" + "\x80\x80\x80\xfc\x90\x80\x80\x80\x80\xfc\xa0\x80\x80\x80\x80" + "\xfd\x80\x80\x80\x80\x80"; + + const ext_type* efrom = e_lit; + const ext_type* efrom_next; + const int_type i_lit[] = { + 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, + 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, L'!', + L'"', L'#', L'$', L'%', L'&', L'\'', L'(', L')', L'*', L'+', + L',', L'-', L'.', L'/', L'0', L'1', L'2', L'3', L'4', L'5', + L'6', L'7', L'8', L'9', L':', L';', L'<', L'=', L'>', L'?', + L'@', L'}', L'~', 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, + 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, + 0x9a, 0x9b, 0x9c, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x100, + 0x101, 0x102, 0x103, 0x104, 0x105, 0x106, 0x107, 0x108, 0x109, + 0x10a, 0x10b, 0x10c, 0x10d, 0x10e, 0x10f, 0x110, 0x111, 0x112, + 0x113, 0x114, 0x115, 0x116, 0x117, 0x118, 0x119, 0x7f8, 0x7f9, + 0x7fa, 0x7fb, 0x7fc, 0x7fd, 0x7fe, 0x7ff, 0x800, 0x801, 0x802, + 0x803, 0x804, 0x805, 0x806, 0x807, 0x808, 0x809, 0x80a, 0x80b, + 0x80c, 0x80d, 0x80e, 0x80f, 0x810, 0x811, 0x812, 0x813, 0x814, + 0x815, 0x816, 0x817, 0x1, 0x2, 0x4, 0x8, 0x10, 0x20, L'@', + 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, + 0x10000, 0x20000, 0x40000, 0x80000, 0x100000, 0x200000, 0x400000, + 0x800000, 0x1000000, 0x2000000, 0x4000000, 0x8000000, 0x10000000, + 0x20000000, 0x40000000, 0x0 + }; + + int esize = strlen(e_lit); + int isize = wcslen(i_lit); + int_type* i_arr = new int_type[esize + 1]; + int_type* i_ref = new int_type[esize + 1]; + wmemset(i_arr, 0xdeadbeef, esize + 1); + wmemset(i_ref, 0xdeadbeef, esize + 1); + int_type* ito = i_arr; + int_type* ito_next; + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // in + w_codecvt::state_type state01; + zero_state(state01); + result r1; + + for (int i = 0; i <= esize; ++i) + { + r1 = cvt->in(state01, efrom, e_lit + i, efrom_next, + ito, i_arr + esize, ito_next); + + printf("%d %d %d %x %x\n", efrom - e_lit, i, efrom_next - e_lit, + efrom[-1], ito[-1]); + + // It it not clear if partial should ever be returned here + // (see DR 382). + VERIFY( r1 == codecvt_base::ok || r1 == codecvt_base::partial ); + VERIFY( efrom_next >= efrom ); + VERIFY( efrom_next <= e_lit + i ); + VERIFY( ito_next >= ito ); + VERIFY( ito_next <= i_arr + isize ); + VERIFY( !int_traits::compare(i_arr, i_lit, ito_next - i_arr) ); + VERIFY( !int_traits::compare(ito_next, i_ref, + i_arr + esize + 1 - ito_next) ); + + efrom = efrom_next; + ito = ito_next; + } + + VERIFY( r1 == codecvt_base::ok ); + VERIFY( efrom_next == e_lit + esize ); + VERIFY( ito_next == i_arr + isize ); + + delete [] i_arr; + delete [] i_ref; +} + +int main () +{ + test09(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/length/char/1.cc b/libstdc++-v3/testsuite/22_locale/codecvt/length/char/1.cc index 1ef0f267c01..3ea244dcbb0 100644 --- a/libstdc++-v3/testsuite/22_locale/codecvt/length/char/1.cc +++ b/libstdc++-v3/testsuite/22_locale/codecvt/length/char/1.cc @@ -33,26 +33,14 @@ void test01() bool test = true; const char* c_lit = "black pearl jasmine tea"; - const char* from_next; int size = 25; - char* c_arr = new char[size]; - char* c_ref = new char[size]; - char* to_next; locale loc = locale::classic(); c_codecvt::state_type state; const c_codecvt* cvt = &use_facet(loc); - // According to the resolution of DR19 (see also libstd++/9168), in - // case of degenerate conversion ('noconv'), "there are no changes to - // the values in [to, to_limit)." - memset(c_ref, 'X', size); - int j = cvt->length(state, c_lit, c_lit + size, 5); VERIFY( j == 5 ); - - delete [] c_arr; - delete [] c_ref; } int main () diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/length/char/2.cc b/libstdc++-v3/testsuite/22_locale/codecvt/length/char/2.cc new file mode 100644 index 00000000000..6e0a7e96f2e --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/length/char/2.cc @@ -0,0 +1,69 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +bool length_called = false; + +class length_codecvt : public std::codecvt +{ + typedef std::codecvt c_codecvt; + +public: + // DR75: type of first argument of do_length is state_type& + virtual int do_length(state_type& state, const extern_type* from, + const extern_type* end, std::size_t max) const + { + length_called = true; + return c_codecvt::do_length(state, from, end, max); + } +}; + +// Required instantiation, degenerate conversion. +// codecvt +// +// libstdc++/9224 +void test02() +{ + using namespace std; + typedef codecvt_base::result result; + typedef codecvt c_codecvt; + + bool test = true; + const char* c_lit = "black pearl jasmine tea"; + int size = 25; + + locale loc (locale::classic(), new length_codecvt); + c_codecvt::state_type state; + const c_codecvt* cvt = &use_facet(loc); + + length_called = false; + cvt->length(state, c_lit, c_lit + size, 5); + VERIFY( length_called ); +} + +int main () +{ + test02(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/1.cc b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/1.cc index ca673240f46..100de8567fc 100644 --- a/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/1.cc +++ b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/1.cc @@ -42,22 +42,11 @@ void test01() { using namespace std; typedef codecvt w_codecvt; - typedef codecvt_base::result result; - typedef wchar_t int_type; typedef char ext_type; - typedef char_traits int_traits; - typedef char_traits ext_traits; bool test = true; const ext_type* e_lit = "black pearl jasmine tea"; - const ext_type* efrom_next; - const int_type* i_lit = L"black pearl jasmine tea"; - const int_type* ifrom_next; int size = strlen(e_lit); - ext_type* e_arr = new ext_type[size + 1]; - ext_type* eto_next; - int_type* i_arr = new int_type[size + 1]; - int_type* ito_next; locale loc; const w_codecvt* cvt = &use_facet(loc); @@ -66,9 +55,6 @@ void test01() zero_state(state04); int j = cvt->length(state04, e_lit, e_lit + size, 5); VERIFY( j == 5 ); - - delete [] e_arr; - delete [] i_arr; } int main () diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/2.cc b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/2.cc new file mode 100644 index 00000000000..0e90fbdc833 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/2.cc @@ -0,0 +1,88 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test02() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef char ext_type; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + "abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86" + "\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95" + "\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4" + "\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3" + "\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2" + "\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1" + "\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0" + "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe" + "\xff"; + int size = strlen(e_lit); + + locale loc ("en_US.ISO-8859-1"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + w_codecvt::state_type state01; + zero_state(state01); + int i = cvt->length(state01, e_lit, e_lit + size, 5); + VERIFY( i == 5 ); + + w_codecvt::state_type state02; + zero_state(state02); + int j = cvt->length(state02, e_lit, e_lit + size, size); + VERIFY( j == size ); + + w_codecvt::state_type state03; + zero_state(state03); + int k = cvt->length(state03, e_lit, e_lit + size, size * 2); + VERIFY( k == size ); +} + +int main () +{ + test02(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/3.cc b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/3.cc new file mode 100644 index 00000000000..8031c3edee0 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/3.cc @@ -0,0 +1,88 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test03() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef char ext_type; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + "abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86" + "\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95" + "\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4" + "\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3" + "\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2" + "\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1" + "\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0" + "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe" + "\xff"; + int size = strlen(e_lit); + + locale loc ("en_US.ISO-8859-15"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + w_codecvt::state_type state01; + zero_state(state01); + int i = cvt->length(state01, e_lit, e_lit + size, 5); + VERIFY( i == 5 ); + + w_codecvt::state_type state02; + zero_state(state02); + int j = cvt->length(state02, e_lit, e_lit + size, size); + VERIFY( j == size ); + + w_codecvt::state_type state03; + zero_state(state03); + int k = cvt->length(state03, e_lit, e_lit + size, size * 2); + VERIFY( k == size ); +} + +int main () +{ + test03(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/4.cc b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/4.cc new file mode 100644 index 00000000000..6a802bd2856 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/4.cc @@ -0,0 +1,127 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test04() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef wchar_t int_type; + typedef char ext_type; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@}~\x7f\xc2\x80\xc2\x81\xc2\x82\xc2" + "\x83\xc2\x84\xc2\x85\xc2\x86\xc2\x87\xc2\x88\xc2\x89\xc2\x8a" + "\xc2\x8b\xc2\x8c\xc2\x8d\xc2\x8e\xc2\x8f\xc2\x90\xc2\x91\xc2" + "\x92\xc2\x93\xc2\x94\xc2\x95\xc2\x96\xc2\x97\xc2\x98\xc2\x99" + "\xc2\x9a\xc2\x9b\xc2\x9c\xc3\xba\xc3\xbb\xc3\xbc\xc3\xbd\xc3" + "\xbe\xc3\xbf\xc4\x80\xc4\x81\xc4\x82\xc4\x83\xc4\x84\xc4\x85" + "\xc4\x86\xc4\x87\xc4\x88\xc4\x89\xc4\x8a\xc4\x8b\xc4\x8c\xc4" + "\x8d\xc4\x8e\xc4\x8f\xc4\x90\xc4\x91\xc4\x92\xc4\x93\xc4\x94" + "\xc4\x95\xc4\x96\xc4\x97\xc4\x98\xc4\x99\xdf\xb8\xdf\xb9\xdf" + "\xba\xdf\xbb\xdf\xbc\xdf\xbd\xdf\xbe\xdf\xbf\xe0\xa0\x80\xe0" + "\xa0\x81\xe0\xa0\x82\xe0\xa0\x83\xe0\xa0\x84\xe0\xa0\x85\xe0" + "\xa0\x86\xe0\xa0\x87\xe0\xa0\x88\xe0\xa0\x89\xe0\xa0\x8a\xe0" + "\xa0\x8b\xe0\xa0\x8c\xe0\xa0\x8d\xe0\xa0\x8e\xe0\xa0\x8f\xe0" + "\xa0\x90\xe0\xa0\x91\xe0\xa0\x92\xe0\xa0\x93\xe0\xa0\x94\xe0" + "\xa0\x95\xe0\xa0\x96\xe0\xa0\x97\x1\x2\x4\x8\x10\x20@\xc2\x80" + "\xc4\x80\xc8\x80\xd0\x80\xe0\xa0\x80\xe1\x80\x80\xe2\x80\x80" + "\xe4\x80\x80\xe8\x80\x80\xf0\x90\x80\x80\xf0\xa0\x80\x80\xf1" + "\x80\x80\x80\xf2\x80\x80\x80\xf4\x80\x80\x80\xf8\x88\x80\x80" + "\x80\xf8\x90\x80\x80\x80\xf8\xa0\x80\x80\x80\xf9\x80\x80\x80" + "\x80\xfa\x80\x80\x80\x80\xfc\x84\x80\x80\x80\x80\xfc\x88\x80" + "\x80\x80\x80\xfc\x90\x80\x80\x80\x80\xfc\xa0\x80\x80\x80\x80" + "\xfd\x80\x80\x80\x80\x80"; + + const ext_type* efrom_next; + const int_type i_lit[] = { + 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, + 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, L'!', + L'"', L'#', L'$', L'%', L'&', L'\'', L'(', L')', L'*', L'+', + L',', L'-', L'.', L'/', L'0', L'1', L'2', L'3', L'4', L'5', + L'6', L'7', L'8', L'9', L':', L';', L'<', L'=', L'>', L'?', + L'@', L'}', L'~', 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, + 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, + 0x9a, 0x9b, 0x9c, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x100, + 0x101, 0x102, 0x103, 0x104, 0x105, 0x106, 0x107, 0x108, 0x109, + 0x10a, 0x10b, 0x10c, 0x10d, 0x10e, 0x10f, 0x110, 0x111, 0x112, + 0x113, 0x114, 0x115, 0x116, 0x117, 0x118, 0x119, 0x7f8, 0x7f9, + 0x7fa, 0x7fb, 0x7fc, 0x7fd, 0x7fe, 0x7ff, 0x800, 0x801, 0x802, + 0x803, 0x804, 0x805, 0x806, 0x807, 0x808, 0x809, 0x80a, 0x80b, + 0x80c, 0x80d, 0x80e, 0x80f, 0x810, 0x811, 0x812, 0x813, 0x814, + 0x815, 0x816, 0x817, 0x1, 0x2, 0x4, 0x8, 0x10, 0x20, L'@', + 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, + 0x10000, 0x20000, 0x40000, 0x80000, 0x100000, 0x200000, 0x400000, + 0x800000, 0x1000000, 0x2000000, 0x4000000, 0x8000000, 0x10000000, + 0x20000000, 0x40000000, 0x0 + }; + + int esize = strlen(e_lit); + int isize = wcslen(i_lit); + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + w_codecvt::state_type state01; + zero_state(state01); + int i = cvt->length(state01, e_lit, e_lit + esize, 5); + VERIFY( i == 5 ); + + w_codecvt::state_type state02; + zero_state(state02); + int j = cvt->length(state02, e_lit, e_lit + esize, isize); + VERIFY( j == esize ); + + w_codecvt::state_type state03; + zero_state(state03); + int k = cvt->length(state03, e_lit, e_lit + esize, esize * 2); + VERIFY( k == esize ); +} + +int main () +{ + test04(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/5.cc b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/5.cc new file mode 100644 index 00000000000..284233e7b6b --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/5.cc @@ -0,0 +1,64 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test05() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef char ext_type; + + bool test = true; + const ext_type e_lit[] = { '\0', '\0', 'f', '\0' }; + int size = sizeof(e_lit); + + locale loc; + const w_codecvt* cvt = &use_facet(loc); + + w_codecvt::state_type state04; + zero_state(state04); + int j = cvt->length(state04, e_lit, e_lit + size, 5); + VERIFY( j == size ); +} + +int main () +{ + test05(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/6.cc b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/6.cc new file mode 100644 index 00000000000..76c151edf05 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/6.cc @@ -0,0 +1,84 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +bool length_called = false; + +class length_codecvt : public std::codecvt +{ + typedef std::codecvt w_codecvt; + +public: + // DR75: type of first argument of do_length is state_type& + virtual int do_length(state_type& state, const extern_type* from, + const extern_type* end, std::size_t max) const + { + length_called = true; + return w_codecvt::do_length(state, from, end, max); + } +}; + +// Required instantiation +// codecvt +// +// libstdc++/9224 +void test06() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef char ext_type; + + bool test = true; + const ext_type* e_lit = "black pearl jasmine tea"; + int size = strlen(e_lit); + + locale loc; + loc = locale(loc, new length_codecvt); + const w_codecvt* cvt = &use_facet(loc); + + w_codecvt::state_type state04; + zero_state(state04); + length_called = false; + cvt->length(state04, e_lit, e_lit + size, 5); + VERIFY( length_called ); +} + +int main () +{ + test06(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/7.cc b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/7.cc new file mode 100644 index 00000000000..8a275e35a37 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/length/wchar_t/7.cc @@ -0,0 +1,79 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Test handling of illegal input sequence in UTF-8. +void test07() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef wchar_t int_type; + typedef char ext_type; + + bool test = true; + const ext_type* e_lit = "a\xc0\xff"; + const ext_type* efrom_next; + int size = strlen(e_lit); + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + w_codecvt::state_type state01; + zero_state(state01); + int i = cvt->length(state01, e_lit, e_lit + size, 1); + VERIFY( i == 1 ); + + w_codecvt::state_type state02; + zero_state(state02); + int j = cvt->length(state02, e_lit, e_lit + size, size); + VERIFY( j == 1 ); + + w_codecvt::state_type state03; + zero_state(state03); + int k = cvt->length(state03, e_lit, e_lit + size, size * 2); + VERIFY( k == 1 ); +} + +int main () +{ + test07(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/1.cc b/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/1.cc index 028756c897c..b2995e3b2fb 100644 --- a/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/1.cc +++ b/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/1.cc @@ -23,51 +23,18 @@ #include #include - -// Need to explicitly set the state(mbstate_t) to zero. -// How to do this is not specified by the ISO C99 standard, so we -// might need to add some operators to make the intuiative case -// work: -// w_codecvt::state_type state00; -// state00 = 0; -// or, can use this explicit "C" initialization: -// w_codecvt::state_type state01 = {0, 0}; -// .. except Ulrich says: Use memset. Always use memset. Feel the force... -void -zero_state(std::mbstate_t& state) -{ std::memset(&state, 0, sizeof(std::mbstate_t)); } - // Required instantiation // codecvt void test01() { using namespace std; typedef codecvt w_codecvt; - typedef codecvt_base::result result; - typedef wchar_t int_type; - typedef char ext_type; - typedef char_traits int_traits; - typedef char_traits ext_traits; - bool test = true; - const ext_type* e_lit = "black pearl jasmine tea"; - const ext_type* efrom_next; - const int_type* i_lit = L"black pearl jasmine tea"; - const int_type* ifrom_next; - int size = strlen(e_lit); - ext_type* e_arr = new ext_type[size + 1]; - ext_type* eto_next; - int_type* i_arr = new int_type[size + 1]; - int_type* ito_next; - - locale loc; - const w_codecvt* cvt = &use_facet(loc); + locale loc_c = locale::classic(); + const w_codecvt* cvt = &use_facet(loc_c); int k = cvt->max_length(); VERIFY( k == 1 ); - - delete [] e_arr; - delete [] i_arr; } int main () diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/2.cc b/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/2.cc new file mode 100644 index 00000000000..37fdf544449 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/2.cc @@ -0,0 +1,45 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Required instantiation +// codecvt +void test02() +{ + using namespace std; + typedef codecvt w_codecvt; + + locale loc ("en_US.ISO-8859-1"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + int k = cvt->max_length(); + VERIFY( k == 1 ); // ISO-8859-1 is a single-byte encoding +} + +int main () +{ + test02(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/3.cc b/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/3.cc new file mode 100644 index 00000000000..d6778d18a07 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/3.cc @@ -0,0 +1,45 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Required instantiation +// codecvt +void test03() +{ + using namespace std; + typedef codecvt w_codecvt; + + locale loc ("en_US.ISO-8859-15"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + int k = cvt->max_length(); + VERIFY( k == 1 ); // ISO-8859-15 is a single-byte encoding +} + +int main () +{ + test03(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/4.cc b/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/4.cc new file mode 100644 index 00000000000..fd85941ab37 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/max_length/wchar_t/4.cc @@ -0,0 +1,47 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Required instantiation +// codecvt +void test04() +{ + using namespace std; + typedef codecvt w_codecvt; + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + int k = cvt->max_length(); + // Each UCS-4 wide character can be converted to at most 6 narrow + // characters in the UTF-8 encoding. + VERIFY( k == 6 ); +} + +int main () +{ + test04(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/1.cc b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/1.cc index 3727044ae38..82a57c6fdbd 100644 --- a/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/1.cc +++ b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/1.cc @@ -45,19 +45,18 @@ void test01() typedef codecvt_base::result result; typedef wchar_t int_type; typedef char ext_type; - typedef char_traits int_traits; typedef char_traits ext_traits; bool test = true; const ext_type* e_lit = "black pearl jasmine tea"; - const ext_type* efrom_next; const int_type* i_lit = L"black pearl jasmine tea"; const int_type* ifrom_next; int size = strlen(e_lit); ext_type* e_arr = new ext_type[size + 1]; + ext_type* e_ref = new ext_type[size + 1]; + memset(e_arr, 0xf0, size + 1); + memset(e_ref, 0xf0, size + 1); ext_type* eto_next; - int_type* i_arr = new int_type[size + 1]; - int_type* ito_next; locale loc; const w_codecvt* cvt = &use_facet(loc); @@ -68,12 +67,13 @@ void test01() result r2 = cvt->out(state02, i_lit, i_lit + size, ifrom_next, e_arr, e_arr + size, eto_next); VERIFY( r2 == codecvt_base::ok ); - VERIFY( !ext_traits::compare(e_arr, e_lit, size) ); VERIFY( ifrom_next == i_lit + size ); VERIFY( eto_next == e_arr + size ); + VERIFY( !ext_traits::compare(e_arr, e_lit, size) ); + VERIFY( !ext_traits::compare(eto_next, e_ref, 1) ); delete [] e_arr; - delete [] i_arr; + delete [] e_ref; } int main () diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/2.cc b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/2.cc new file mode 100644 index 00000000000..c2e807da594 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/2.cc @@ -0,0 +1,112 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test02() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits ext_traits; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + "abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86" + "\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95" + "\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4" + "\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3" + "\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2" + "\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1" + "\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0" + "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe" + "\xff"; + + const int_type* i_lit = + L"\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + L"\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + L"'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + L"abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86" + L"\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95" + L"\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4" + L"\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3" + L"\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2" + L"\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1" + L"\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0" + L"\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + L"\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe" + L"\xff"; + + const int_type* ifrom_next; + int size = strlen(e_lit); + ext_type* e_arr = new ext_type[size + 1]; + ext_type* e_ref = new ext_type[size + 1]; + memset(e_arr, 0xf0, size + 1); + memset(e_ref, 0xf0, size + 1); + ext_type* eto_next; + + locale loc ("en_US.ISO-8859-1"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // out + w_codecvt::state_type state02; + zero_state(state02); + result r2 = cvt->out(state02, i_lit, i_lit + size, ifrom_next, + e_arr, e_arr + size, eto_next); + VERIFY( r2 == codecvt_base::ok ); + VERIFY( ifrom_next == i_lit + size ); + VERIFY( eto_next == e_arr + size ); + VERIFY( !ext_traits::compare(e_arr, e_lit, size) ); + VERIFY( !ext_traits::compare(eto_next, e_ref, 1) ); + + delete [] e_arr; + delete [] e_ref; +} + +int main () +{ + test02(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/3.cc b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/3.cc new file mode 100644 index 00000000000..d92e01c7d2b --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/3.cc @@ -0,0 +1,126 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test03() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits ext_traits; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + "abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86" + "\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95" + "\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4" + "\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3" + "\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2" + "\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1" + "\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0" + "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe" + "\xff"; + + const int_type i_lit[] = { + 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, + 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, L'!', + L'"', L'#', L'$', L'%', L'&', L'\'', L'(', L')', L'*', L'+', + L',', L'-', L'.', L'/', L'0', L'1', L'2', L'3', L'4', L'5', + L'6', L'7', L'8', L'9', L':', L';', L'<', L'=', L'>', L'?', + L'@', L'A', L'B', L'C', L'D', L'E', L'F', L'G', L'H', L'I', + L'J', L'K', L'L', L'M', L'N', L'O', L'P', L'Q', L'R', L'S', + L'T', L'U', L'V', L'W', L'X', L'Y', L'Z', L'[', L'\\', L']', + L'^', L'_', L'`', L'a', L'b', L'c', L'd', L'e', L'f', L'g', + L'h', L'i', L'j', L'k', L'l', L'm', L'n', L'o', L'p', L'q', + L'r', L's', L't', L'u', L'v', L'w', L'x', L'y', L'z', L'{', + L'|', L'}', L'~', 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, + 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, + 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, 0xa0, 0xa1, 0xa2, 0xa3, + 0x20ac, 0xa5, 0x160, 0xa7, 0x161, 0xa9, 0xaa, 0xab, 0xac, 0xad, + 0xae, 0xaf, 0xb0, 0xb1, 0xb2, 0xb3, 0x17d, 0xb5, 0xb6, 0xb7, + 0x17e, 0xb9, 0xba, 0xbb, 0x152, 0x153, 0x178, 0xbf, 0xc0, 0xc1, + 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, + 0xcc, 0xcd, 0xce, 0xcf, 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, + 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, + 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, + 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, + 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, + 0xfe, 0xff, 0x0 + }; + + const int_type* ifrom_next; + int size = strlen(e_lit); + ext_type* e_arr = new ext_type[size + 1]; + ext_type* e_ref = new ext_type[size + 1]; + memset(e_arr, 0xf0, size + 1); + memset(e_ref, 0xf0, size + 1); + ext_type* eto_next; + + locale loc ("en_US.ISO-8859-15"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // out + w_codecvt::state_type state02; + zero_state(state02); + result r2 = cvt->out(state02, i_lit, i_lit + size, ifrom_next, + e_arr, e_arr + size, eto_next); + VERIFY( r2 == codecvt_base::ok ); + VERIFY( ifrom_next == i_lit + size ); + VERIFY( eto_next == e_arr + size ); + VERIFY( !ext_traits::compare(e_arr, e_lit, size) ); + VERIFY( !ext_traits::compare(eto_next, e_ref, 1) ); + + delete [] e_arr; + delete [] e_ref; +} + +int main () +{ + test03(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/4.cc b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/4.cc new file mode 100644 index 00000000000..626ff70efe4 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/4.cc @@ -0,0 +1,133 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test04() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits ext_traits; + + bool test = true; + const ext_type* e_lit = + "\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + "'()*+,-./0123456789:;<=>?@}~\x7f\xc2\x80\xc2\x81\xc2\x82\xc2" + "\x83\xc2\x84\xc2\x85\xc2\x86\xc2\x87\xc2\x88\xc2\x89\xc2\x8a" + "\xc2\x8b\xc2\x8c\xc2\x8d\xc2\x8e\xc2\x8f\xc2\x90\xc2\x91\xc2" + "\x92\xc2\x93\xc2\x94\xc2\x95\xc2\x96\xc2\x97\xc2\x98\xc2\x99" + "\xc2\x9a\xc2\x9b\xc2\x9c\xc3\xba\xc3\xbb\xc3\xbc\xc3\xbd\xc3" + "\xbe\xc3\xbf\xc4\x80\xc4\x81\xc4\x82\xc4\x83\xc4\x84\xc4\x85" + "\xc4\x86\xc4\x87\xc4\x88\xc4\x89\xc4\x8a\xc4\x8b\xc4\x8c\xc4" + "\x8d\xc4\x8e\xc4\x8f\xc4\x90\xc4\x91\xc4\x92\xc4\x93\xc4\x94" + "\xc4\x95\xc4\x96\xc4\x97\xc4\x98\xc4\x99\xdf\xb8\xdf\xb9\xdf" + "\xba\xdf\xbb\xdf\xbc\xdf\xbd\xdf\xbe\xdf\xbf\xe0\xa0\x80\xe0" + "\xa0\x81\xe0\xa0\x82\xe0\xa0\x83\xe0\xa0\x84\xe0\xa0\x85\xe0" + "\xa0\x86\xe0\xa0\x87\xe0\xa0\x88\xe0\xa0\x89\xe0\xa0\x8a\xe0" + "\xa0\x8b\xe0\xa0\x8c\xe0\xa0\x8d\xe0\xa0\x8e\xe0\xa0\x8f\xe0" + "\xa0\x90\xe0\xa0\x91\xe0\xa0\x92\xe0\xa0\x93\xe0\xa0\x94\xe0" + "\xa0\x95\xe0\xa0\x96\xe0\xa0\x97\x1\x2\x4\x8\x10\x20@\xc2\x80" + "\xc4\x80\xc8\x80\xd0\x80\xe0\xa0\x80\xe1\x80\x80\xe2\x80\x80" + "\xe4\x80\x80\xe8\x80\x80\xf0\x90\x80\x80\xf0\xa0\x80\x80\xf1" + "\x80\x80\x80\xf2\x80\x80\x80\xf4\x80\x80\x80\xf8\x88\x80\x80" + "\x80\xf8\x90\x80\x80\x80\xf8\xa0\x80\x80\x80\xf9\x80\x80\x80" + "\x80\xfa\x80\x80\x80\x80\xfc\x84\x80\x80\x80\x80\xfc\x88\x80" + "\x80\x80\x80\xfc\x90\x80\x80\x80\x80\xfc\xa0\x80\x80\x80\x80" + "\xfd\x80\x80\x80\x80\x80"; + + const int_type i_lit[] = { + 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, + 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, L'!', + L'"', L'#', L'$', L'%', L'&', L'\'', L'(', L')', L'*', L'+', + L',', L'-', L'.', L'/', L'0', L'1', L'2', L'3', L'4', L'5', + L'6', L'7', L'8', L'9', L':', L';', L'<', L'=', L'>', L'?', + L'@', L'}', L'~', 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, + 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, + 0x9a, 0x9b, 0x9c, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x100, + 0x101, 0x102, 0x103, 0x104, 0x105, 0x106, 0x107, 0x108, 0x109, + 0x10a, 0x10b, 0x10c, 0x10d, 0x10e, 0x10f, 0x110, 0x111, 0x112, + 0x113, 0x114, 0x115, 0x116, 0x117, 0x118, 0x119, 0x7f8, 0x7f9, + 0x7fa, 0x7fb, 0x7fc, 0x7fd, 0x7fe, 0x7ff, 0x800, 0x801, 0x802, + 0x803, 0x804, 0x805, 0x806, 0x807, 0x808, 0x809, 0x80a, 0x80b, + 0x80c, 0x80d, 0x80e, 0x80f, 0x810, 0x811, 0x812, 0x813, 0x814, + 0x815, 0x816, 0x817, 0x1, 0x2, 0x4, 0x8, 0x10, 0x20, L'@', + 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, + 0x10000, 0x20000, 0x40000, 0x80000, 0x100000, 0x200000, 0x400000, + 0x800000, 0x1000000, 0x2000000, 0x4000000, 0x8000000, 0x10000000, + 0x20000000, 0x40000000, 0x0 + }; + + const int_type* ifrom_next; + int esize = strlen(e_lit); + int isize = wcslen(i_lit); + ext_type* e_arr = new ext_type[esize + 1]; + ext_type* e_ref = new ext_type[esize + 1]; + memset(e_arr, 0xf0, esize + 1); + memset(e_ref, 0xf0, esize + 1); + ext_type* eto_next; + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // out + w_codecvt::state_type state02; + zero_state(state02); + result r2 = cvt->out(state02, i_lit, i_lit + isize, ifrom_next, + e_arr, e_arr + esize, eto_next); + VERIFY( r2 == codecvt_base::ok ); + VERIFY( ifrom_next == i_lit + isize ); + VERIFY( eto_next == e_arr + esize ); + VERIFY( !ext_traits::compare(e_arr, e_lit, esize) ); + VERIFY( !ext_traits::compare(eto_next, e_ref, 1) ); + + delete [] e_arr; + delete [] e_ref; +} + +int main () +{ + test04(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/5.cc b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/5.cc new file mode 100644 index 00000000000..13ca4b28719 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/5.cc @@ -0,0 +1,86 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Test handling of '\0' characters in input +// libstdc++/9246 +void test05() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits ext_traits; + + bool test = true; + const ext_type e_lit[] = { '\0', '\0', 'f', '\0' }; + const int_type i_lit[] = { L'\0', L'\0', L'f', L'\0' }; + const int_type* ifrom_next; + int size = sizeof(e_lit); + ext_type* e_arr = new ext_type[size + 1]; + ext_type* e_ref = new ext_type[size + 1]; + memset(e_arr, 0xf0, size + 1); + memset(e_ref, 0xf0, size + 1); + ext_type* eto_next; + + locale loc; + const w_codecvt* cvt = &use_facet(loc); + + // out + w_codecvt::state_type state02; + zero_state(state02); + result r2 = cvt->out(state02, i_lit, i_lit + size, ifrom_next, + e_arr, e_arr + size, eto_next); + VERIFY( r2 == codecvt_base::ok ); + VERIFY( ifrom_next == i_lit + size ); + VERIFY( eto_next == e_arr + size ); + VERIFY( !ext_traits::compare(e_arr, e_lit, size) ); + VERIFY( !ext_traits::compare(eto_next, e_ref, 1) ); + + delete [] e_arr; + delete [] e_ref; +} + +int main () +{ + test05(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/6.cc b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/6.cc new file mode 100644 index 00000000000..9ee2770bafd --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/6.cc @@ -0,0 +1,86 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +// +// Test handling of output buffer that is too small. +// libstdc++/9247 +void test06() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits ext_traits; + + bool test = true; + const ext_type* e_lit = "black pearl jasmine tea"; + const int_type* i_lit = L"black pearl jasmine tea"; + const int_type* ifrom_next; + int size = strlen(e_lit); + ext_type* e_arr = new ext_type[size + 1]; + ext_type* e_ref = new ext_type[size + 1]; + memset(e_arr, 0xf0, size + 1); + memset(e_ref, 0xf0, size + 1); + ext_type* eto_next; + + locale loc; + const w_codecvt* cvt = &use_facet(loc); + + // out + w_codecvt::state_type state02; + zero_state(state02); + result r2 = cvt->out(state02, i_lit, i_lit + size, ifrom_next, + e_arr, e_arr + 1, eto_next); + VERIFY( r2 == codecvt_base::partial ); + VERIFY( ifrom_next == i_lit + 1 ); + VERIFY( eto_next == e_arr + 1 ); + VERIFY( !ext_traits::compare(e_arr, e_lit, 1) ); + VERIFY( !ext_traits::compare(eto_next, e_ref, size) ); + + delete [] e_arr; + delete [] e_ref; +} + +int main () +{ + test06(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/7.cc b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/7.cc new file mode 100644 index 00000000000..3ea57c05c03 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/out/wchar_t/7.cc @@ -0,0 +1,84 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test03() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits ext_traits; + + bool test = true; + const ext_type* e_lit = "a"; + const int_type i_lit[] = { L'a', 0x20ac, 0x0 }; + const int_type* ifrom_next; + int size = wcslen(i_lit); + ext_type* e_arr = new ext_type[size + 1]; + ext_type* e_ref = new ext_type[size + 1]; + memset(e_arr, 0xf0, size + 1); + memset(e_ref, 0xf0, size + 1); + ext_type* eto_next; + + locale loc ("en_US.ISO-8859-1"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // out + w_codecvt::state_type state02; + zero_state(state02); + result r2 = cvt->out(state02, i_lit, i_lit + size, ifrom_next, + e_arr, e_arr + size, eto_next); + VERIFY( r2 == codecvt_base::error ); + VERIFY( ifrom_next == i_lit + 1 ); + VERIFY( eto_next == e_arr + 1 ); + VERIFY( !ext_traits::compare(e_arr, e_lit, 1) ); + VERIFY( !ext_traits::compare(eto_next, e_ref, size) ); + + delete [] e_arr; + delete [] e_ref; +} + +int main () +{ + test03(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/unicode/1.cc b/libstdc++-v3/testsuite/22_locale/codecvt/unicode/1.cc new file mode 100644 index 00000000000..b96b22c5991 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/unicode/1.cc @@ -0,0 +1,147 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + + + +#ifdef _GLIBCPP_USE___ENC_TRAITS + +// Need some char_traits specializations for this to work. +typedef unsigned short unicode_t; + +namespace std +{ + template<> + struct char_traits + { + typedef unicode_t char_type; + // Unsigned as wint_t is unsigned. + typedef unsigned long int_type; + typedef streampos pos_type; + typedef streamoff off_type; + typedef mbstate_t state_type; + + static void + assign(char_type& __c1, const char_type& __c2); + + static bool + eq(const char_type& __c1, const char_type& __c2); + + static bool + lt(const char_type& __c1, const char_type& __c2); + + static int + compare(const char_type* __s1, const char_type* __s2, size_t __n) + { return memcmp(__s1, __s2, __n); } + + static size_t + length(const char_type* __s); + + static const char_type* + find(const char_type* __s, size_t __n, const char_type& __a); + + static char_type* + move(char_type* __s1, const char_type* __s2, size_t __n); + + static char_type* + copy(char_type* __s1, const char_type* __s2, size_t __n) + { return static_cast(memcpy(__s1, __s2, __n)); } + + static char_type* + assign(char_type* __s, size_t __n, char_type __a); + + static char_type + to_char_type(const int_type& __c); + + static int_type + to_int_type(const char_type& __c); + + static bool + eq_int_type(const int_type& __c1, const int_type& __c2); + + static int_type + eof(); + + static int_type + not_eof(const int_type& __c); + }; +} + +void +initialize_state(std::__enc_traits& state) +{ state._M_init(); } + +bool length_called = false; + +class length_codecvt : public std::codecvt +{ + typedef std::codecvt unicode_codecvt; + +public: + // DR75: type of first argument of do_length is state_type& + virtual int do_length(state_type& state, const extern_type* from, + const extern_type* end, std::size_t max) const + { + length_called = true; + return unicode_codecvt::do_length(state, from, end, max); + } +}; + +// Partial specialization using __enc_traits. +// codecvt +// UNICODE - UCS2 (big endian) +void test01() +{ + using namespace std; + typedef unicode_t int_type; + typedef char ext_type; + typedef __enc_traits enc_type; + typedef codecvt unicode_codecvt; + + bool test = true; + const ext_type* e_lit = "black pearl jasmine tea"; + int size = strlen(e_lit); + + // construct a locale object with the specialized facet. + locale loc(locale::classic(), new length_codecvt); + // sanity check the constructed locale has the specialized facet. + VERIFY( has_facet(loc) ); + const unicode_codecvt& cvt = use_facet(loc); + + unicode_codecvt::state_type state04("UCS-2BE", "ISO-8859-15", 0xfeff, 0); + initialize_state(state04); + length_called = false; + cvt.length(state04, e_lit, e_lit + size, 5); + VERIFY( length_called ); +} +#endif // _GLIBCPP_USE___ENC_TRAITS + +int main () +{ +#if _GLIBCPP_USE___ENC_TRAITS + test01(); +#endif + + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/1.cc b/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/1.cc index 2f31670e4c7..65aaea05056 100644 --- a/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/1.cc +++ b/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/1.cc @@ -45,43 +45,16 @@ void test01() typedef codecvt_base::result result; typedef wchar_t int_type; typedef char ext_type; - typedef char_traits int_traits; - typedef char_traits ext_traits; bool test = true; const ext_type* e_lit = "black pearl jasmine tea"; - const ext_type* efrom_next; - const int_type* i_lit = L"black pearl jasmine tea"; - const int_type* ifrom_next; int size = strlen(e_lit); ext_type* e_arr = new ext_type[size + 1]; ext_type* eto_next; - int_type* i_arr = new int_type[size + 1]; - int_type* ito_next; locale loc; const w_codecvt* cvt = &use_facet(loc); - // in - w_codecvt::state_type state01; - zero_state(state01); - result r1 = cvt->in(state01, e_lit, e_lit + size, efrom_next, - i_arr, i_arr + size, ito_next); - VERIFY( r1 == codecvt_base::ok ); - VERIFY( !int_traits::compare(i_arr, i_lit, size) ); - VERIFY( efrom_next == e_lit + size ); - VERIFY( ito_next == i_arr + size ); - - // out - w_codecvt::state_type state02; - zero_state(state02); - result r2 = cvt->out(state02, i_lit, i_lit + size, ifrom_next, - e_arr, e_arr + size, eto_next); - VERIFY( r2 == codecvt_base::ok ); - VERIFY( !ext_traits::compare(e_arr, e_lit, size) ); - VERIFY( ifrom_next == i_lit + size ); - VERIFY( eto_next == e_arr + size ); - // unshift strcpy(e_arr, e_lit); w_codecvt::state_type state03; @@ -90,6 +63,8 @@ void test01() VERIFY( r3 == codecvt_base::noconv ); VERIFY( !strcmp(e_arr, e_lit) ); VERIFY( eto_next == e_arr ); + + delete [] e_arr; } int main () diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/2.cc b/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/2.cc new file mode 100644 index 00000000000..77e3b9292dd --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/2.cc @@ -0,0 +1,107 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test02() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits ext_traits; + + bool test = true; + const int_type* i_lit = + L"\x1\x2\x3\x4\x5\x6\x7\x8\x9\xa\xb\xc\xd\xe\xf\x10\x11\x12\x13" + L"\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20!\"#$%&" + L"'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + L"abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86" + L"\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95" + L"\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4" + L"\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3" + L"\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2" + L"\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1" + L"\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0" + L"\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + L"\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe" + L"\xff"; + + const int_type* ifrom_next; + int size = wcslen(i_lit); + ext_type* e_arr = new ext_type[size + 1]; + ext_type* e_ref = new ext_type[size + 1]; + memset(e_arr, 0xf0, size + 1); + memset(e_ref, 0xf0, size + 1); + ext_type* eto_next; + + locale loc ("en_US.ISO-8859-1"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // unshift + w_codecvt::state_type state01; + zero_state(state01); + result r1 = cvt->unshift(state01, e_arr, e_arr + size, eto_next); + VERIFY( r1 == codecvt_base::noconv ); + VERIFY( !ext_traits::compare(e_arr, e_ref, size + 1) ); + VERIFY( eto_next == e_arr ); + + for (int i = 0; i < size; ++i) + { + w_codecvt::state_type state02; + zero_state(state02); + cvt->out(state02, i_lit + i, i_lit + i + 1, ifrom_next, + e_arr, e_arr + size, eto_next); + memset(e_arr, 0xf0, size + 1); + result r2 = cvt->unshift(state02, e_arr, e_arr + size, eto_next); + VERIFY( r2 == codecvt_base::noconv ); + VERIFY( !ext_traits::compare(e_arr, e_ref, size + 1) ); + VERIFY( eto_next == e_arr ); + } + + delete [] e_arr; + delete [] e_ref; +} + +int main () +{ + test02(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/3.cc b/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/3.cc new file mode 100644 index 00000000000..a828090b14d --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/3.cc @@ -0,0 +1,121 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test03() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits ext_traits; + + bool test = true; + const int_type i_lit[] = { + 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, + 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, L'!', + L'"', L'#', L'$', L'%', L'&', L'\'', L'(', L')', L'*', L'+', + L',', L'-', L'.', L'/', L'0', L'1', L'2', L'3', L'4', L'5', + L'6', L'7', L'8', L'9', L':', L';', L'<', L'=', L'>', L'?', + L'@', L'A', L'B', L'C', L'D', L'E', L'F', L'G', L'H', L'I', + L'J', L'K', L'L', L'M', L'N', L'O', L'P', L'Q', L'R', L'S', + L'T', L'U', L'V', L'W', L'X', L'Y', L'Z', L'[', L'\\', L']', + L'^', L'_', L'`', L'a', L'b', L'c', L'd', L'e', L'f', L'g', + L'h', L'i', L'j', L'k', L'l', L'm', L'n', L'o', L'p', L'q', + L'r', L's', L't', L'u', L'v', L'w', L'x', L'y', L'z', L'{', + L'|', L'}', L'~', 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, + 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, + 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, 0xa0, 0xa1, 0xa2, 0xa3, + 0x20ac, 0xa5, 0x160, 0xa7, 0x161, 0xa9, 0xaa, 0xab, 0xac, 0xad, + 0xae, 0xaf, 0xb0, 0xb1, 0xb2, 0xb3, 0x17d, 0xb5, 0xb6, 0xb7, + 0x17e, 0xb9, 0xba, 0xbb, 0x152, 0x153, 0x178, 0xbf, 0xc0, 0xc1, + 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, + 0xcc, 0xcd, 0xce, 0xcf, 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, + 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, + 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, + 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, + 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, + 0xfe, 0xff, 0x0 + }; + + const int_type* ifrom_next; + int size = wcslen(i_lit); + ext_type* e_arr = new ext_type[size + 1]; + ext_type* e_ref = new ext_type[size + 1]; + memset(e_arr, 0xf0, size + 1); + memset(e_ref, 0xf0, size + 1); + ext_type* eto_next; + + locale loc ("en_US.ISO-8859-15"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // unshift + w_codecvt::state_type state01; + zero_state(state01); + result r1 = cvt->unshift(state01, e_arr, e_arr + size, eto_next); + VERIFY( r1 == codecvt_base::noconv ); + VERIFY( !ext_traits::compare(e_arr, e_ref, size + 1) ); + VERIFY( eto_next == e_arr ); + + for (int i = 0; i < size; ++i) + { + w_codecvt::state_type state02; + zero_state(state02); + cvt->out(state02, i_lit + i, i_lit + i + 1, ifrom_next, + e_arr, e_arr + size, eto_next); + memset(e_arr, 0xf0, size + 1); + result r2 = cvt->unshift(state02, e_arr, e_arr + size, eto_next); + VERIFY( r2 == codecvt_base::noconv ); + VERIFY( !ext_traits::compare(e_arr, e_ref, size + 1) ); + VERIFY( eto_next == e_arr ); + } + + delete [] e_arr; + delete [] e_ref; +} + +int main () +{ + test03(); + return 0; +} diff --git a/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/4.cc b/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/4.cc new file mode 100644 index 00000000000..09a91ed5597 --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/codecvt/unshift/wchar_t/4.cc @@ -0,0 +1,116 @@ +// 2003-02-06 Petur Runolfsson + +// Copyright (C) 2003 Free Software Foundation +// +// This file is part of the GNU ISO C++ Library. This library is free +// software; you can redistribute it and/or modify it under the +// terms of the GNU General Public License as published by the +// Free Software Foundation; either version 2, or (at your option) +// any later version. + +// This library is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License along +// with this library; see the file COPYING. If not, write to the Free +// Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, +// USA. + +// 22.2.1.5 - Template class codecvt [lib.locale.codecvt] + +#include +#include + +// Need to explicitly set the state(mbstate_t) to zero. +// How to do this is not specified by the ISO C99 standard, so we +// might need to add some operators to make the intuiative case +// work: +// w_codecvt::state_type state00; +// state00 = 0; +// or, can use this explicit "C" initialization: +// w_codecvt::state_type state01 = {0, 0}; +// .. except Ulrich says: Use memset. Always use memset. Feel the force... +void +zero_state(std::mbstate_t& state) +{ std::memset(&state, 0, sizeof(std::mbstate_t)); } + +// Required instantiation +// codecvt +void test04() +{ + using namespace std; + typedef codecvt w_codecvt; + typedef codecvt_base::result result; + typedef wchar_t int_type; + typedef char ext_type; + typedef char_traits ext_traits; + + bool test = true; + const int_type i_lit[] = { + 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, + 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, L'!', + L'"', L'#', L'$', L'%', L'&', L'\'', L'(', L')', L'*', L'+', + L',', L'-', L'.', L'/', L'0', L'1', L'2', L'3', L'4', L'5', + L'6', L'7', L'8', L'9', L':', L';', L'<', L'=', L'>', L'?', + L'@', L'}', L'~', 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, + 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, + 0x9a, 0x9b, 0x9c, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x100, + 0x101, 0x102, 0x103, 0x104, 0x105, 0x106, 0x107, 0x108, 0x109, + 0x10a, 0x10b, 0x10c, 0x10d, 0x10e, 0x10f, 0x110, 0x111, 0x112, + 0x113, 0x114, 0x115, 0x116, 0x117, 0x118, 0x119, 0x7f8, 0x7f9, + 0x7fa, 0x7fb, 0x7fc, 0x7fd, 0x7fe, 0x7ff, 0x800, 0x801, 0x802, + 0x803, 0x804, 0x805, 0x806, 0x807, 0x808, 0x809, 0x80a, 0x80b, + 0x80c, 0x80d, 0x80e, 0x80f, 0x810, 0x811, 0x812, 0x813, 0x814, + 0x815, 0x816, 0x817, 0x1, 0x2, 0x4, 0x8, 0x10, 0x20, L'@', + 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, + 0x10000, 0x20000, 0x40000, 0x80000, 0x100000, 0x200000, 0x400000, + 0x800000, 0x1000000, 0x2000000, 0x4000000, 0x8000000, 0x10000000, + 0x20000000, 0x40000000, 0x0 + }; + + const int_type* ifrom_next; + int size = wcslen(i_lit); + ext_type* e_arr = new ext_type[size + 1]; + ext_type* e_ref = new ext_type[size + 1]; + memset(e_arr, 0xf0, size + 1); + memset(e_ref, 0xf0, size + 1); + ext_type* eto_next; + + locale loc ("en_US.UTF-8"); + locale::global(loc); + const w_codecvt* cvt = &use_facet(loc); + + // unshift + w_codecvt::state_type state01; + zero_state(state01); + result r1 = cvt->unshift(state01, e_arr, e_arr + size, eto_next); + VERIFY( r1 == codecvt_base::noconv ); + VERIFY( !ext_traits::compare(e_arr, e_ref, size + 1) ); + VERIFY( eto_next == e_arr ); + + for (int i = 0; i < size; ++i) + { + w_codecvt::state_type state02; + zero_state(state02); + cvt->out(state02, i_lit + i, i_lit + i + 1, ifrom_next, + e_arr, e_arr + size, eto_next); + memset(e_arr, 0xf0, size + 1); + result r2 = cvt->unshift(state02, e_arr, e_arr + size, eto_next); + VERIFY( r2 == codecvt_base::noconv ); + VERIFY( !ext_traits::compare(e_arr, e_ref, size + 1) ); + VERIFY( eto_next == e_arr ); + } + + delete [] e_arr; + delete [] e_ref; +} + +int main () +{ + test04(); + return 0; +}