locale/lc-ctype.c

   1 /* Define current locale data for LC_CTYPE category.
   2    Copyright (C) 1995-2024 Free Software Foundation, Inc.
   3    This file is part of the GNU C Library.
   4
   5    The GNU C Library is free software; you can redistribute it and/or
   6    modify it under the terms of the GNU Lesser General Public
   7    License as published by the Free Software Foundation; either
   8    version 2.1 of the License, or (at your option) any later version.
   9
  10    The GNU C Library is distributed in the hope that it will be useful,
  11    but WITHOUT ANY WARRANTY; without even the implied warranty of
  12    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  13    Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public
  16    License along with the GNU C Library; if not, see
  17    <https://www.gnu.org/licenses/>.  */
  18
  19 #include "localeinfo.h"
  20 #include <ctype.h>
  21 #include <endian.h>
  22 #include <stdint.h>
  23
  24 _NL_CURRENT_DEFINE (LC_CTYPE);
  25
  26 /* We are called after loading LC_CTYPE data to load it into
  27    the variables used by the ctype.h macros.  */
  28
  29
  30
  31 void
  32 _nl_postload_ctype (void)
  33 {
  34 #define current(type,x,offset) \
  35   ((const type *) _NL_CURRENT (LC_CTYPE, _NL_CTYPE_##x) + offset)
  36
  37   const union locale_data_value *const ctypes
  38     = _nl_global_locale.__locales[LC_CTYPE]->values;
  39
  40 /* These thread-local variables are defined in ctype-info.c.
  41    The declarations here must match those in localeinfo.h.
  42
  43    These point into arrays of 384, so they can be indexed by any `unsigned
  44    char' value [0,255]; by EOF (-1); or by any `signed char' value
  45    [-128,-1).  ISO C requires that the ctype functions work for `unsigned
  46    char' values and for EOF; we also support negative `signed char' values
  47    for broken old programs.  The case conversion arrays are of `int's
  48    rather than `unsigned char's because tolower (EOF) must be EOF, which
  49    doesn't fit into an `unsigned char'.  But today more important is that
  50    the arrays are also used for multi-byte character sets.
  51
  52    First we update the special members of _nl_global_locale as newlocale
  53    would.  This is necessary for uselocale (LC_GLOBAL_LOCALE) to find these
  54    values properly.  */
  55
  56   _nl_global_locale.__ctype_b = (const unsigned short int *)
  57     ctypes[_NL_ITEM_INDEX (_NL_CTYPE_CLASS)].string + 128;
  58   _nl_global_locale.__ctype_tolower = (const int *)
  59     ctypes[_NL_ITEM_INDEX (_NL_CTYPE_TOLOWER)].string + 128;
  60   _nl_global_locale.__ctype_toupper = (const int *)
  61     ctypes[_NL_ITEM_INDEX (_NL_CTYPE_TOUPPER)].string + 128;
  62
  63   /* Next we must set the thread-local caches if and only if this thread is
  64      in fact using the global locale.  */
  65   if (_NL_CURRENT_LOCALE == &_nl_global_locale)
  66     {
  67       __libc_tsd_set (const uint16_t *, CTYPE_B,
  68                       (void *) _nl_global_locale.__ctype_b);
  69       __libc_tsd_set (const int32_t *, CTYPE_TOUPPER,
  70                       (void *) _nl_global_locale.__ctype_toupper);
  71       __libc_tsd_set (const int32_t *, CTYPE_TOLOWER,
  72                       (void *) _nl_global_locale.__ctype_tolower);
  73     }
  74
  75 #include <shlib-compat.h>
  76 #if SHLIB_COMPAT (libc, GLIBC_2_0, GLIBC_2_3)
  77   /* We must use the exported names to access these so we are sure to
  78      be accessing the main executable's copy if it has COPY relocs.  */
  79
  80   extern const unsigned short int *__ctype_b; /* Characteristics.  */
  81   extern const __int32_t *__ctype_tolower; /* Case conversions.  */
  82   extern const __int32_t *__ctype_toupper; /* Case conversions.  */
  83
  84   extern const uint32_t *__ctype32_b;
  85   extern const uint32_t *__ctype32_toupper;
  86   extern const uint32_t *__ctype32_tolower;
  87
  88   /* We need the .symver declarations these macros generate so that
  89      our references are explicitly bound to the versioned symbol names
  90      rather than the unadorned names that are not exported.  When the
  91      linker sees these bound to local symbols (as the unexported names are)
  92      then it doesn't generate a proper relocation to the global symbols.
  93      We need those relocations so that a versioned definition with a COPY
  94      reloc in an executable will override the libc.so definition.  */
  95
  96 compat_symbol_reference (libc, __ctype_b, __ctype_b, GLIBC_2_0);
  97 compat_symbol_reference (libc, __ctype_tolower, __ctype_tolower, GLIBC_2_0);
  98 compat_symbol_reference (libc, __ctype_toupper, __ctype_toupper, GLIBC_2_0);
  99 compat_symbol_reference (libc, __ctype32_b, __ctype32_b, GLIBC_2_0);
 100 compat_symbol_reference (libc, __ctype32_tolower, __ctype32_tolower,
 101                           GLIBC_2_2);
 102 compat_symbol_reference (libc, __ctype32_toupper, __ctype32_toupper,
 103                          GLIBC_2_2);
 104
 105   __ctype_b = current (uint16_t, CLASS, 128);
 106   __ctype_toupper = current (int32_t, TOUPPER, 128);
 107   __ctype_tolower = current (int32_t, TOLOWER, 128);
 108   __ctype32_b = current (uint32_t, CLASS32, 0);
 109   __ctype32_toupper = current (uint32_t, TOUPPER32, 0);
 110   __ctype32_tolower = current (uint32_t, TOLOWER32, 0);
 111 #endif
 112 }