gdb/gdb_wchar.h

   1 /* Wide characters for gdb
   2    Copyright (C) 2009-2024 Free Software Foundation, Inc.
   3
   4    This file is part of GDB.
   5
   6    This program is free software; you can redistribute it and/or modify
   7    it under the terms of the GNU General Public License as published by
   8    the Free Software Foundation; either version 3 of the License, or
   9    (at your option) any later version.
  10
  11    This program is distributed in the hope that it will be useful,
  12    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14    GNU General Public License for more details.
  15
  16    You should have received a copy of the GNU General Public License
  17    along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
  18
  19 #ifndef GDB_GDB_WCHAR_H
  20 #define GDB_GDB_WCHAR_H
  21
  22 /* We handle three different modes here.
  23
  24    Capable systems have the full suite: wchar_t support and iconv
  25    (perhaps via GNU libiconv).  On these machines, full functionality
  26    is available.  Note that full functionality is dependent on us
  27    being able to convert from an arbitrary encoding to wchar_t.  In
  28    practice this means we look for __STDC_ISO_10646__ (where we know
  29    the name of the wchar_t encoding) or GNU libiconv, where we can use
  30    "wchar_t".
  31
  32    DJGPP is known to have libiconv but not wchar_t support.  On
  33    systems like this, we use the narrow character functions.  The full
  34    functionality is available to the user, but many characters (those
  35    outside the narrow range) will be displayed as escapes.
  36
  37    Finally, some systems do not have iconv, or are really broken
  38    (e.g., Solaris, which almost has all of this working, but where
  39    just enough is broken to make it too hard to use).  Here we provide
  40    a phony iconv which only handles a single character set, and we
  41    provide wrappers for the wchar_t functionality we use.  */
  42
  43
  44 #if defined (HAVE_ICONV)
  45 #include <iconv.h>
  46 #else
  47 /* This define is used elsewhere so we don't need to duplicate the
  48    same checking logic in multiple places.  */
  49 #define PHONY_ICONV
  50 #endif
  51
  52 #include <wchar.h>
  53 #include <wctype.h>
  54
  55 /* We use "btowc" as a sentinel to detect functioning wchar_t support.
  56    We check for either __STDC_ISO_10646__ or a new-enough libiconv in
  57    order to ensure we can convert to and from wchar_t.  We choose
  58    libiconv version 0x108 because it is the first version with
  59    iconvlist.  */
  60 #if defined (HAVE_ICONV) && defined (HAVE_BTOWC) \
  61   && (defined (__STDC_ISO_10646__) \
  62       || (defined (_LIBICONV_VERSION) && _LIBICONV_VERSION >= 0x108))
  63
  64 typedef wchar_t gdb_wchar_t;
  65 typedef wint_t gdb_wint_t;
  66
  67 #define gdb_wcslen wcslen
  68 #define gdb_iswprint iswprint
  69 #define gdb_iswxdigit iswxdigit
  70 #define gdb_btowc btowc
  71 #define gdb_WEOF WEOF
  72
  73 #define LCST(X) L ## X
  74
  75 /* If __STDC_ISO_10646__ is defined, then the host wchar_t is UCS-4.
  76    We exploit this fact in the hope that there are hosts that define
  77    this but which do not support "wchar_t" as an encoding argument to
  78    iconv_open.  We put the endianness into the encoding name to avoid
  79    hosts that emit a BOM when the unadorned name is used.
  80
  81    Also, on version 14 macOS 'Sonoma', the implementation of iconv was
  82    changed in such a way that breaks the way that gdb was using it.
  83    Specifically, using wchar_t as an intermediate encoding silently
  84    breaks when attempting to do character-by-character encoding.
  85    By using the intermediate_encoding function to choose a suitable
  86    encoding to put in the wchar_t, the iconv implementation behaves as
  87    we expect it to. Strictly speaking, this seems to be a bug in
  88    Sonoma specifically, but it is desirable for binaries built for
  89    older versions of macOS to still work on newer ones such as Sonoma,
  90    so there is no version check here for this workaround.  */
  91 #if defined (__STDC_ISO_10646__) || defined (__APPLE__)
  92 #define USE_INTERMEDIATE_ENCODING_FUNCTION
  93 #define INTERMEDIATE_ENCODING intermediate_encoding ()
  94 const char *intermediate_encoding (void);
  95
  96 #elif defined (_LIBICONV_VERSION) && _LIBICONV_VERSION >= 0x108
  97 #define INTERMEDIATE_ENCODING "wchar_t"
  98 #else
  99 /* This shouldn't happen, because the earlier #if should have filtered
 100    out this case.  */
 101 #error "Neither __STDC_ISO_10646__ nor _LIBICONV_VERSION defined"
 102 #endif
 103
 104 #else
 105
 106 /* If we got here and have wchar_t support, we might be on a system
 107    with some problem.  So, we just disable everything.  */
 108 #if defined (HAVE_BTOWC)
 109 #define PHONY_ICONV
 110 #endif
 111
 112 typedef char gdb_wchar_t;
 113 typedef int gdb_wint_t;
 114
 115 #define gdb_wcslen strlen
 116 #define gdb_iswprint isprint
 117 #define gdb_iswxdigit isxdigit
 118 #define gdb_btowc /* empty */
 119 #define gdb_WEOF EOF
 120
 121 #define LCST(X) X
 122
 123 /* If we are using the narrow character set, we want to use the host
 124    narrow encoding as our intermediate encoding.  However, if we are
 125    also providing a phony iconv, we might as well just stick with
 126    "wchar_t".  */
 127 #ifdef PHONY_ICONV
 128 #define INTERMEDIATE_ENCODING "wchar_t"
 129 #else
 130 #define INTERMEDIATE_ENCODING host_charset ()
 131 #endif
 132
 133 #endif
 134
 135 #endif /* GDB_GDB_WCHAR_H */