gdb/testsuite/gdb.base/charset.c

   1 /* This testcase is part of GDB, the GNU debugger.
   2
   3    Copyright 2001-2020 Free Software Foundation, Inc.
   4
   5    Contributed by Red Hat, originally written by Jim Blandy.
   6
   7    This program is free software; you can redistribute it and/or modify
   8    it under the terms of the GNU General Public License as published by
   9    the Free Software Foundation; either version 3 of the License, or
  10    (at your option) any later version.
  11
  12    This program is distributed in the hope that it will be useful,
  13    but WITHOUT ANY WARRANTY; without even the implied warranty of
  14    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15    GNU General Public License for more details.
  16
  17    You should have received a copy of the GNU General Public License
  18    along with this program.  If not, see <http://www.gnu.org/licenses/>.
  19
  20    Please email any bugs, comments, and/or additions to this file to:
  21    bug-gdb@gnu.org  */
  22
  23 /* X_string is a null-terminated string in the X charset whose
  24    elements are as follows.  X should be the name the `set charset'
  25    command uses for the character set, in lower-case, with any
  26    non-identifier characters replaced with underscores.  Where a
  27    character set doesn't have the given character, the string should
  28    contain the character 'x'.
  29
  30    [0] --- the `alert' character, '\a'
  31    [1] --- the `backspace' character, '\b'
  32    [2] --- the `form feed' character, '\f'
  33    [3] --- the `line feed' character, '\n'
  34    [4] --- the `carriage return' character, '\r'
  35    [5] --- the `horizontal tab' character, '\t'
  36    [6] --- the `vertical tab' character, '\v'
  37    [7  .. 32] --- the uppercase letters A-Z
  38    [33 .. 58] --- the lowercase letters a-z
  39    [59 .. 68] --- the digits 0-9
  40    [69] --- the `cent' character
  41    [70] --- a control character with no defined backslash escape
  42
  43    Feel free to extend these as you like.  */
  44
  45 #define NUM_CHARS (71)
  46
  47 char ascii_string[NUM_CHARS];
  48 char iso_8859_1_string[NUM_CHARS];
  49 char ebcdic_us_string[NUM_CHARS];
  50 char ibm1047_string[NUM_CHARS];
  51
  52 #ifndef __cplusplus
  53
  54 /* We make a phony wchar_t and then pretend that this platform uses
  55    UTF-32 (or UTF-16, depending on the size -- same difference for the
  56    purposes of this test).  */
  57 typedef unsigned int wchar_t;
  58
  59 /* We also define a couple phony types for testing the u'' and U''
  60    support.  It is ok if these have the wrong size on some platforms
  61    -- the test case will skip the tests in that case.  */
  62 typedef unsigned short char16_t;
  63 typedef unsigned int char32_t;
  64
  65 #endif
  66
  67 wchar_t utf_32_string[NUM_CHARS];
  68
  69 /* Make sure to use the typedefs.  */
  70 char16_t uvar;
  71 char32_t Uvar;
  72
  73 char16_t *String16;
  74 char32_t *String32;
  75
  76 /* A typedef to a typedef should also work.  */
  77 typedef wchar_t my_wchar_t;
  78 my_wchar_t myvar;
  79
  80 /* Some arrays for simple assignment tests.  */
  81 short short_array[3];
  82 int int_array[3];
  83 long long_array[3];
  84
  85 /* These are unsigned char so we can pass down characters >127 without
  86    explicit casts or warnings.  */
  87
  88 void
  89 init_string (char string[],
  90              unsigned char x,
  91              unsigned char alert,
  92              unsigned char backspace,
  93              unsigned char form_feed,
  94              unsigned char line_feed,
  95              unsigned char carriage_return,
  96              unsigned char horizontal_tab,
  97              unsigned char vertical_tab,
  98              unsigned char cent,
  99              unsigned char misc_ctrl)
 100 {
 101   int i;
 102
 103   for (i = 0; i < NUM_CHARS; ++i)
 104     string[i] = x;
 105   string[0] = alert;
 106   string[1] = backspace;
 107   string[2] = form_feed;
 108   string[3] = line_feed;
 109   string[4] = carriage_return;
 110   string[5] = horizontal_tab;
 111   string[6] = vertical_tab;
 112   string[69] = cent;
 113   string[70] = misc_ctrl;
 114 }
 115
 116
 117 void
 118 fill_run (char string[], int start, int len, int first)
 119 {
 120   int i;
 121
 122   for (i = 0; i < len; i++)
 123     string[start + i] = first + i;
 124 }
 125
 126
 127 void
 128 init_utf32 ()
 129 {
 130   int i;
 131
 132   for (i = 0; i < NUM_CHARS; ++i)
 133     utf_32_string[i] = iso_8859_1_string[i] & 0xff;
 134 }
 135
 136 extern void malloc_stub (void);
 137
 138 int main ()
 139 {
 140
 141   malloc_stub ();
 142
 143   /* Initialize ascii_string.  */
 144   init_string (ascii_string,
 145                120,
 146                7, 8, 12,
 147                10, 13, 9,
 148                11, 120, 17);
 149   fill_run (ascii_string, 7, 26, 65);
 150   fill_run (ascii_string, 33, 26, 97);
 151   fill_run (ascii_string, 59, 10, 48);
 152
 153   /* Initialize iso_8859_1_string.  */
 154   init_string (iso_8859_1_string,
 155                120,
 156                7, 8, 12,
 157                10, 13, 9,
 158                11, 162, 17);
 159   fill_run (iso_8859_1_string, 7, 26, 65);
 160   fill_run (iso_8859_1_string, 33, 26, 97);
 161   fill_run (iso_8859_1_string, 59, 10, 48);
 162
 163   /* Initialize ebcdic_us_string.  */
 164   init_string (ebcdic_us_string,
 165                167,
 166                47, 22, 12,
 167                37, 13, 5,
 168                11, 74, 17);
 169   /* In EBCDIC, the upper-case letters are broken into three separate runs.  */
 170   fill_run (ebcdic_us_string, 7, 9, 193);
 171   fill_run (ebcdic_us_string, 16, 9, 209);
 172   fill_run (ebcdic_us_string, 25, 8, 226);
 173   /* The lower-case letters are, too.  */
 174   fill_run (ebcdic_us_string, 33, 9, 129);
 175   fill_run (ebcdic_us_string, 42, 9, 145);
 176   fill_run (ebcdic_us_string, 51, 8, 162);
 177   /* The digits, at least, are contiguous.  */
 178   fill_run (ebcdic_us_string, 59, 10, 240);
 179
 180   /* Initialize ibm1047_string.  */
 181   init_string (ibm1047_string,
 182                167,
 183                47, 22, 12,
 184                37, 13, 5,
 185                11, 74, 17);
 186   /* In EBCDIC, the upper-case letters are broken into three separate runs.  */
 187   fill_run (ibm1047_string, 7, 9, 193);
 188   fill_run (ibm1047_string, 16, 9, 209);
 189   fill_run (ibm1047_string, 25, 8, 226);
 190   /* The lower-case letters are, too.  */
 191   fill_run (ibm1047_string, 33, 9, 129);
 192   fill_run (ibm1047_string, 42, 9, 145);
 193   fill_run (ibm1047_string, 51, 8, 162);
 194   /* The digits, at least, are contiguous.  */
 195   fill_run (ibm1047_string, 59, 10, 240);
 196
 197   init_utf32 ();
 198
 199   myvar = utf_32_string[7];
 200
 201   return 0;            /* all strings initialized */
 202 }