icuSources/tools/escapesrc/tblgen.cpp

   1 // © 2016 and later: Unicode, Inc. and others.
   2 // License & terms of use: http://www.unicode.org/copyright.html
   3
   4 #include "unicode/utypes.h"
   5 #include "unicode/ucnv.h"
   6 #include "unicode/uniset.h"
   7 #include <stdio.h>
   8
   9 static const char *kConverter = "ibm-1047";
  10
  11 int main(int argc, const char *argv[]) {
  12   printf("// %s\n", U_COPYRIGHT_STRING);
  13   printf("// generated by tblgen. You weren't going to edit it by hand, were you?\n");
  14   printf("\n");
  15
  16   UErrorCode status = U_ZERO_ERROR;
  17   LocalUConverterPointer cnv(ucnv_open(kConverter, &status));
  18
  19   if(U_FAILURE(status)) {
  20     fprintf(stderr, "Failed to open %s: %s\n", kConverter, u_errorName(status));
  21     return 1;
  22   }
  23
  24   printf("static const char cp1047_8859_1[256] = { \n");
  25   for(int i=0x00; i<0x100; i++) {
  26     char cp1047[1];
  27     cp1047[0] = i;
  28     UChar u[1];
  29     UChar *target = u;
  30     const char *source = cp1047;
  31     ucnv_toUnicode(cnv.getAlias(), &target, u+1, &source, cp1047+1, nullptr, true, &status);
  32     if(U_FAILURE(status)) {
  33       fprintf(stderr, "Conversion failure at #%X: %s\n", i, u_errorName(status));
  34       return 2;
  35     }
  36     printf(" (char)0x%02X, /* %02X */\n", u[0], i);
  37   }
  38   printf("};\n\n");
  39
  40   //
  41   //  UnicodeSet oldIllegal("[:print:]", status); // [a-zA-Z0-9_}{#)(><%:;.?*+-/^&|~!=,\\u005b\\u005d\\u005c]", status);
  42   UnicodeSet oldIllegal("[0-9 a-z A-Z "
  43                         "_ \\{ \\} \\[ \\] # \\( \\) < > % \\: ; . "
  44                         "? * + \\- / \\^ \\& | ~ ! = , \\ \" ' ]", status);
  45
  46   /*
  47
  48 http://www.lirmm.fr/~ducour/Doc-objets/ISO+IEC+14882-1998.pdf ( note: 1998 )   page 10, section 2.2 says:
  49
  50 1 The basic source character set consists of 96 characters: the space character, the control characters repre- 15)
  51 senting horizontal tab, vertical tab, form feed, and new-line, plus the following 91 graphical characters:
  52 a b c d e f g h i j k l m n opqrstuvwxyz
  53 A B C D E F G H I J K L M N OPQRSTUVWXYZ
  54 0 12 3 4 5 6 7 8 9
  55  _ { } [ ] # ( ) < > % : ; . ?*+-/^&|~!=,\"
  56 2 The universal-character-name construct provides a way to name other characters. hex-quad:
  57 hexadecimal-digit hexadecimal-digit hexadecimal-digit hexadecimal-digit
  58 universal-character-name: \u hex-quad
  59 \U hex-quad hex-quad
  60 The character designated by the universal-character-name \UNNNNNNNN is that character whose character short name in ISO/IEC 10646 is NNNNNNNN; the character designated by the universal-character-name \uNNNN is that character whose character short name in ISO/IEC 10646 is 0000NNNN. If the hexadecimal value for a universal character name is less than 0x20 or in the range 0x7F-0x9F (inclusive), or if the uni- versal character name designates a character in the basic source character set, then the program is ill- formed.
  61
  62
  63 So basically:  printable ASCII plus  0x00-0x1F,  0x7F-0x9F, was all illegal.
  64
  65 Some discussion at http://unicode.org/mail-arch/unicode-ml/y2003-m10/0471.html
  66
  67    */
  68
  69
  70
  71   printf("static const bool oldIllegal[256] = { \n");
  72   for(UChar i=0x00; i<0x100;i++) {
  73     printf(" %s, /* U+%04X */\n",
  74            (oldIllegal.contains(i))?" true":"false",
  75            i);
  76   }
  77   printf("};\n\n");
  78
  79   return 0;
  80 }