diff --git a/libstdc++-v3/ChangeLog b/libstdc++-v3/ChangeLog index a703dc729bc4..3c27ef46c4fc 100644 --- a/libstdc++-v3/ChangeLog +++ b/libstdc++-v3/ChangeLog @@ -1,9 +1,22 @@ 2000-08-30 Benjamin Kosnik + * testsuite/22_locale/ctype_wchar_t_members.cc (test01): New file. + + * docs/22_locale/codecvt.html: Re-number. + * docs/22_locale/howto.html: Add entry for ctype + documentation. Add entry for Nathan's introduction to locales + paper. + * docs/22_locale/ctype.html: New file. In progress... + * docs/22_locale/codecvt.html: Formatting cleanups. * src/locale.cc (ctype::do_is): Fix thinko. -2000-08-30 Benjamin Kosnik +2000-08-30 Phil Edwards + + * docs/22_locale/codecvt.html: Behind-the-scenes ASCII->HTML + tweaks for certain browsers. + +2000-08-29 Benjamin Kosnik * bits/locale_facets.h (ctype): Remove __table_type. Add include for bits/std_cwctype.h, for wctype_t. @@ -14,13 +27,8 @@ * config/gnu-linux/ctype.cc: Tweak. * testsuite/22_locale/ctype.cc: Tweak. - * bits/codecvt.h (__enc_traits): Mangle names. + * bits/codecvt.h (__enc_traits): Uglify names. -2000-08-30 Phil Edwards - - * docs/22_locale/codecvt.html: Behind-the-scenes ASCII->HTML - tweaks for certain browsers. - 2000-08-28 Benjamin Kosnik * docs/22_locale/codecvt.html: Add more bits, format. diff --git a/libstdc++-v3/docs/22_locale/codecvt.html b/libstdc++-v3/docs/22_locale/codecvt.html index ee05cd3cad5b..2ce6c95a1e58 100644 --- a/libstdc++-v3/docs/22_locale/codecvt.html +++ b/libstdc++-v3/docs/22_locale/codecvt.html @@ -97,7 +97,7 @@ mcsrtombs and wcsrtombs in particular.

-2. Some thoughts on what would be useful +3. Some thoughts on what would be useful

Probably the most frequently asked question about code conversion is: "So dudes, what's the deal with Unicode strings?" The dude part is @@ -208,7 +208,7 @@ mechanism may be required.

-3. Problems with "C" code conversions : thread safety, global +4. Problems with "C" code conversions : thread safety, global locales, termination.

@@ -251,7 +251,7 @@ LC_CTYPE category implements.

-4. Design +5. Design

The two required specializations are implemented as follows: @@ -370,7 +370,7 @@ codecvt usage.

-5. Examples +6. Examples

    @@ -431,7 +431,7 @@ More information can be found in the following testcases:

    -6. Unresolved Issues +7. Unresolved Issues

    • @@ -474,7 +474,7 @@ More information can be found in the following testcases:

      -7. Acknowledgments +8. Acknowledgments

      Ulrich Drepper for the iconv suggestions and patient answering of late-night questions, Jason Merrill for the template partial @@ -482,7 +482,7 @@ specialization hints, language clarification, and wchar_t fixes.

      -8. Bibliography / Referenced Documents +9. Bibliography / Referenced Documents

      Drepper, Ulrich, GNU libc (glibc) 2.2 manual. In particular, Chapters "6. Character Set Handling" and "7 Locales and Internationalization" diff --git a/libstdc++-v3/docs/22_locale/ctype.html b/libstdc++-v3/docs/22_locale/ctype.html new file mode 100644 index 000000000000..08be102fe266 --- /dev/null +++ b/libstdc++-v3/docs/22_locale/ctype.html @@ -0,0 +1,146 @@ + + +

      + Notes on the ctype implementation. +

      + + +prepared by Benjamin Kosnik (bkoz@redhat.com) on August 30, 2000 + + +

      +

      +1. Abstract +

      +

      +Woe is me. +

      + +

      +

      +2. What the standard says +

      + + +

      +

      +3. Problems with "C" ctype : global locales, termination. +

      + +

      +For the required specialization codecvt<wchar_t, char, mbstate_t> , +conversions are made between the internal character set (always UCS4 +on GNU/Linux) and whatever the currently selected locale for the +LC_CTYPE category implements. + +

      +

      +4. Design +

      +The two required specializations are implemented as follows: + +

      + +ctype<char> + +

      +This is simple specialization. Implementing this was a piece of cake. + +

      + +ctype<wchar_t> + +

      +This specialization, by specifying all the template parameters, pretty +much ties the hands of implementors. As such, the implementation is +straightforward, involving mcsrtombs for the conversions between char +to wchar_t and wcsrtombs for conversions between wchar_t and char. + +

      +Neither of these two required specializations deals with Unicode +characters. As such, libstdc++-v3 implements + + + +

      +

      +5. Examples +

      + +
      +  typedef ctype cctype;
+
      + +More information can be found in the following testcases: +
        +
      • testsuite/22_locale/ctype_char_members.cc +
      • testsuite/22_locale/ctype_wchar_t_members.cc +
      + +

      +

      +6. Unresolved Issues +

      + +
        +
      • how to deal with the global locale issue? + +
      • how to deal with different types than char, wchar_t? + +
      • codecvt/ctype overlap: narrow/widen + +
      • mask typedef in codecvt_base, argument types in codecvt. + what is know about this type? + +
      • why mask* argument in codecvt? + +
      • can this be made (more) generic? is there a simple way to + straighten out the configure-time mess that is a by-product of + this class? + +
      • get the ctype::mask stuff under control. Need to + make some kind of static table, and not do lookup evertime + somebody hits the do_is... functions. Too bad we can't just + redefine mask for ctype + +
      • rename abstract base class. See if just smash-overriding + is a better approach. Clarify, add sanity to naming. + +
      + + +

      +

      +7. Acknowledgments +

      +Ulrich Drepper for patient answering of late-night questions, skeletal +examples, and C language expertise. + +

      +

      +8. Bibliography / Referenced Documents +

      + +Drepper, Ulrich, GNU libc (glibc) 2.2 manual. In particular, Chapters "6. Character Set Handling" and "7 Locales and Internationalization" + +

      +Drepper, Ulrich, Numerous, late-night email correspondence + +

      +ISO/IEC 14882:1998 Programming languages - C++ + +

      +ISO/IEC 9899:1999 Programming languages - C + +

      +Langer, Angelika and Klaus Kreft, Standard C++ IOStreams and Locales, Advanced Programmer's Guide and Reference, Addison Wesley Longman, Inc. 2000 + +

      +Stroustrup, Bjarne, Appendix D, The C++ Programming Language, Special Edition, Addison Wesley, Inc. 2000 + +

      +System Interface Definitions, Issue 6 (IEEE Std. 1003.1-200x) +The Open Group/The Institute of Electrical and Electronics Engineers, Inc. +http://www.opennc.org/austin/docreg.html + + diff --git a/libstdc++-v3/docs/22_locale/howto.html b/libstdc++-v3/docs/22_locale/howto.html index 17295292d10d..c464bf105fae 100644 --- a/libstdc++-v3/docs/22_locale/howto.html +++ b/libstdc++-v3/docs/22_locale/howto.html @@ -9,14 +9,13 @@ libstdc++-v3 HOWTO: Chapter 22 - +

      Chapter 22: Localization

      -

      Chapter 22 deals with the FORTRAN subroutines for automatically - transforming lemmings into gold. +

      Chapter 22 deals with the C++ localization facilities.

      @@ -24,8 +23,10 @@

      Contents

      @@ -45,15 +46,51 @@

      -

      Notes on the codecvt implementation

      -

      This document turned out to be larger than anticipated. As - such, it gets its own page, which can be found - here. +

      Nathan Myers on Locales

      +

      An article entitled "The Standard C++ Locale" was published in + Dr. Dobb's Journal and can be found + here

      Return to top of page or to the FAQ.

      +
      +

      codecvt

      +

      Notes made during the implementation of codecvt can be found + here. +

      + +

      The following is the abstract from the implementation notes: +

      + The standard class codecvt attempts to address conversions +between different character encoding schemes. In particular, the +standard attempts to detail conversions between the +implementation-defined wide characters (hereafter referred to as +wchar_t) and the standard type char that is so beloved in classic +"C" (which can now be referred to as narrow characters.) +This document attempts to describe how the GNU libstdc++-v3 +implementation deals with the conversion between wide and narrow +characters, and also presents a framework for dealing with the huge +number of other encodings that iconv can convert, including Unicode +and UTF8. Design issues and requirements are addressed, and examples +of correct usage for both the required specializations for wide and +narrow characters and the implementation-provided extended +functionality are given. +
      + +

      Return to top of page or + to the FAQ. +

      + +
      +

      ctype

      +

      Notes made during the implementation of ctype can be found + here. +

      +

      Return to top of page or + to the FAQ. +

      @@ -64,7 +101,7 @@ Comments and suggestions are welcome, and may be sent to Phil Edwards or Gabriel Dos Reis. -
      $Id: howto.html,v 1.2 2000/07/11 21:45:07 pme Exp $ +
      $Id: howto.html,v 1.3 2000/08/25 08:52:56 bkoz Exp $

      diff --git a/libstdc++-v3/testsuite/22_locale/ctype_wchar_t_members.cc b/libstdc++-v3/testsuite/22_locale/ctype_wchar_t_members.cc new file mode 100644 index 000000000000..ad8452ac397d --- /dev/null +++ b/libstdc++-v3/testsuite/22_locale/ctype_wchar_t_members.cc @@ -0,0 +1,105 @@ +// 2000-09-01 Benjamin Kosnik + +// Copyright (C) 2000 Free Software Foundation, Inc. +// +// 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. + +// As a special exception, you may use this file as part of a free software +// library without restriction. Specifically, if other files instantiate +// templates or use macros or inline functions from this file, or you compile +// this file and link it with other files to produce an executable, this +// file does not by itself cause the resulting executable to be covered by +// the GNU General Public License. This exception does not however +// invalidate any other reasons why the executable file might be covered by +// the GNU General Public License. + +// 22.2.1.3.2 ctype members + +#include +// NB: Don't include any other headers in this file. +#include + +class gnu_ctype: public std::ctype {}; + +void test01() +{ + bool test = true; + typedef wchar_t char_type; + + const char_type strlit00[] = L"manilla, cebu, tandag PHILIPPINES"; + const char_type strlit01[] = L"MANILLA, CEBU, TANDAG PHILIPPINES"; + const char_type strlit02[] = L"manilla, cebu, tandag philippines"; + const char_type c00 = L'S'; + const char_type c10 = L's'; + const char_type c20 = L'9'; + const char_type c30 = L' '; + const char_type c40 = L'!'; + const char_type c50 = L'F'; + const char_type c60 = L'f'; + const char_type c70 = L'X'; + const char_type c80 = L'x'; + + gnu_ctype gctype; + char_type c100; + int len = std::char_traits::length(strlit00); + char_type c_array[len + 1]; + + // bool is(mask m, char_type c) const; + VERIFY( gctype.is(std::ctype_base::space, c30) ); + VERIFY( gctype.is(std::ctype_base::upper, c00) ); + VERIFY( gctype.is(std::ctype_base::lower, c10) ); + VERIFY( gctype.is(std::ctype_base::digit, c20) ); + VERIFY( gctype.is(std::ctype_base::punct, c40) ); + VERIFY( gctype.is(std::ctype_base::alpha, c50) ); + VERIFY( gctype.is(std::ctype_base::alpha, c60) ); + VERIFY( gctype.is(std::ctype_base::xdigit, c20) ); + VERIFY( !gctype.is(std::ctype_base::xdigit, c80) ); + VERIFY( gctype.is(std::ctype_base::alnum, c50) ); + VERIFY( gctype.is(std::ctype_base::alnum, c20) ); + VERIFY( gctype.is(std::ctype_base::graph, c40) ); + VERIFY( gctype.is(std::ctype_base::graph, c20) ); + + // char_type toupper(char_type c) const + c100 = gctype.toupper(c10); + VERIFY( c100 == c00 ); + + // char_type tolower(char_type c) const + c100 = gctype.tolower(c00); + VERIFY( c100 == c10 ); + + // char_type toupper(char_type* low, const char_type* hi) const + std::char_traits::copy(c_array, strlit02, len + 1); + gctype.toupper(c_array, c_array + len); + VERIFY( !std::char_traits::compare(c_array, strlit01, len - 1) ); + + // char_type tolower(char_type* low, const char_type* hi) const + std::char_traits::copy(c_array, strlit01, len + 1); + gctype.tolower(c_array, c_array + len); + VERIFY( !std::char_traits::compare(c_array, strlit02, len - 1) ); + + +#ifdef DEBUG_ASSERT + assert(test); +#endif +} + +int main() { + test01(); + return 0; +} + +