tblgen.cpp   [plain text]

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html

#include "unicode/utypes.h"
#include "unicode/ucnv.h"
#include "unicode/uniset.h"
#include <stdio.h>

static const char *kConverter = "ibm-1047";

int main(int argc, const char *argv[]) {
  printf("// %s\n", U_COPYRIGHT_STRING);
  printf("// generated by tblgen. You weren't going to edit it by hand, were you?\n");
  printf("\n");

  UErrorCode status = U_ZERO_ERROR;
  LocalUConverterPointer cnv(ucnv_open(kConverter, &status));

  if(U_FAILURE(status)) {
    fprintf(stderr, "Failed to open %s: %s\n", kConverter, u_errorName(status));
    return 1;
  }

  printf("static const char cp1047_8859_1[256] = { \n");
  for(int i=0x00; i<0x100; i++) {
    char cp1047[1];
    cp1047[0] = i;
    UChar u[1];
    UChar *target = u;
    const char *source = cp1047;
    ucnv_toUnicode(cnv.getAlias(), &target, u+1, &source, cp1047+1, nullptr, true, &status);
    if(U_FAILURE(status)) {
      fprintf(stderr, "Conversion failure at #%X: %s\n", i, u_errorName(status));
      return 2;
    }
    printf(" (char)0x%02X, /* %02X */\n", u[0], i);
  }
  printf("};\n\n");

  // 
  //  UnicodeSet oldIllegal("[:print:]", status); // [a-zA-Z0-9_}{#)(><%:;.?*+-/^&|~!=,\\u005b\\u005d\\u005c]", status);
  UnicodeSet oldIllegal("[0-9 a-z A-Z "
                        "_ \\{ \\} \\[ \\] # \\( \\) < > % \\: ; . "
                        "? * + \\- / \\^ \\& | ~ ! = , \\ \" ' ]", status);
  
  /*

http://www.lirmm.fr/~ducour/Doc-objets/ISO+IEC+14882-1998.pdf ( note: 1998 )   page 10, section 2.2 says:

1 The basic source character set consists of 96 characters: the space character, the control characters repre- 15)
senting horizontal tab, vertical tab, form feed, and new-line, plus the following 91 graphical characters:
a b c d e f g h i j k l m n opqrstuvwxyz
A B C D E F G H I J K L M N OPQRSTUVWXYZ
0 12 3 4 5 6 7 8 9
 _ { } [ ] # ( ) < > % : ; . ?*+-/^&|~!=,\"
2 The universal-character-name construct provides a way to name other characters. hex-quad:
hexadecimal-digit hexadecimal-digit hexadecimal-digit hexadecimal-digit
universal-character-name: \u hex-quad
\U hex-quad hex-quad
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.


So basically:  printable ASCII plus  0x00-0x1F,  0x7F-0x9F, was all illegal.

Some discussion at http://unicode.org/mail-arch/unicode-ml/y2003-m10/0471.html

   */
  


  printf("static const bool oldIllegal[256] = { \n");
  for(UChar i=0x00; i<0x100;i++) {
    printf(" %s, /* U+%04X */\n",
           (oldIllegal.contains(i))?" true":"false",
           i);
  }
  printf("};\n\n");
  
  return 0;
}