gdb/charset.h

   1 /* Character set conversion support for GDB.
   2    Copyright (C) 2001, 2007 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 2 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, write to the Free Software
  18    Foundation, Inc., 51 Franklin Street, Fifth Floor,
  19    Boston, MA 02110-1301, USA.  */
  20
  21 #ifndef CHARSET_H
  22 #define CHARSET_H
  23
  24
  25 /* If the target program uses a different character set than the host,
  26    GDB has some support for translating between the two; GDB converts
  27    characters and strings to the host character set before displaying
  28    them, and converts characters and strings appearing in expressions
  29    entered by the user to the target character set.
  30
  31    At the moment, GDB only supports single-byte, stateless character
  32    sets.  This includes the ISO-8859 family (ASCII extended with
  33    accented characters, and (I think) Cyrillic, for European
  34    languages), and the EBCDIC family (used on IBM's mainframes).
  35    Unfortunately, it excludes many Asian scripts, the fixed- and
  36    variable-width Unicode encodings, and other desireable things.
  37    Patches are welcome!  (For example, it would be nice if the Java
  38    string support could simply get absorbed into some more general
  39    multi-byte encoding support.)
  40
  41    Furthermore, GDB's code pretty much assumes that the host character
  42    set is some superset of ASCII; there are plenty if ('0' + n)
  43    expressions and the like.
  44
  45    When the `iconv' library routine supports a character set meeting
  46    the requirements above, it's easy to plug an entry into GDB's table
  47    that uses iconv to handle the details.  */
  48
  49 /* Return the name of the current host/target character set.  The
  50    result is owned by the charset module; the caller should not free
  51    it.  */
  52 const char *host_charset (void);
  53 const char *target_charset (void);
  54
  55 /* In general, the set of C backslash escapes (\n, \f) is specific to
  56    the character set.  Not all character sets will have form feed
  57    characters, for example.
  58
  59    The following functions allow GDB to parse and print control
  60    characters in a character-set-independent way.  They are both
  61    language-specific (to C and C++) and character-set-specific.
  62    Putting them here is a compromise.  */
  63
  64
  65 /* If the target character TARGET_CHAR have a backslash escape in the
  66    C language (i.e., a character like 'n' or 't'), return the host
  67    character string that should follow the backslash.  Otherwise,
  68    return zero.
  69
  70    When this function returns non-zero, the string it returns is
  71    statically allocated; the caller is not responsible for freeing it.  */
  72 const char *c_target_char_has_backslash_escape (int target_char);
  73
  74
  75 /* If the host character HOST_CHAR is a valid backslash escape in the
  76    C language for the target character set, return non-zero, and set
  77    *TARGET_CHAR to the target character the backslash escape represents.
  78    Otherwise, return zero.  */
  79 int c_parse_backslash (int host_char, int *target_char);
  80
  81
  82 /* Return non-zero if the host character HOST_CHAR can be printed
  83    literally --- that is, if it can be readably printed as itself in a
  84    character or string constant.  Return zero if it should be printed
  85    using some kind of numeric escape, like '\031' in C, '^(25)' in
  86    Chill, or #25 in Pascal.  */
  87 int host_char_print_literally (int host_char);
  88
  89
  90 /* If the host character HOST_CHAR has an equivalent in the target
  91    character set, set *TARGET_CHAR to that equivalent, and return
  92    non-zero.  Otherwise, return zero.  */
  93 int host_char_to_target (int host_char, int *target_char);
  94
  95
  96 /* If the target character TARGET_CHAR has an equivalent in the host
  97    character set, set *HOST_CHAR to that equivalent, and return
  98    non-zero.  Otherwise, return zero.  */
  99 int target_char_to_host (int target_char, int *host_char);
 100
 101
 102 /* If the target character TARGET_CHAR has a corresponding control
 103    character (also in the target character set), set *TARGET_CTRL_CHAR
 104    to the control character, and return non-zero.  Otherwise, return
 105    zero.  */
 106 int target_char_to_control_char (int target_char, int *target_ctrl_char);
 107
 108
 109 #endif /* CHARSET_H */