• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
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 using icu::LocalUConverterPointer;
10 using icu::UnicodeSet;
11 
12 static const char *kConverter = "ibm-1047";
13 
main(int argc,const char * argv[])14 int main(int argc, const char *argv[]) {
15   printf("// %s\n", U_COPYRIGHT_STRING);
16   printf("// generated by tblgen. You weren't going to edit it by hand, were you?\n");
17   printf("\n");
18 
19   UErrorCode status = U_ZERO_ERROR;
20   LocalUConverterPointer cnv(ucnv_open(kConverter, &status));
21 
22   if(U_FAILURE(status)) {
23     fprintf(stderr, "Failed to open %s: %s\n", kConverter, u_errorName(status));
24     return 1;
25   }
26 
27   printf("static const char cp1047_8859_1[256] = { \n");
28   for(int i=0x00; i<0x100; i++) {
29     char cp1047[1];
30     cp1047[0] = i;
31     char16_t u[1];
32     char16_t *target = u;
33     const char *source = cp1047;
34     ucnv_toUnicode(cnv.getAlias(), &target, u+1, &source, cp1047+1, nullptr, true, &status);
35     if(U_FAILURE(status)) {
36       fprintf(stderr, "Conversion failure at #%X: %s\n", i, u_errorName(status));
37       return 2;
38     }
39     printf(" (char)0x%02X, /* %02X */\n", u[0], i);
40   }
41   printf("};\n\n");
42 
43   //
44   //  UnicodeSet oldIllegal("[:print:]", status); // [a-zA-Z0-9_}{#)(><%:;.?*+-/^&|~!=,\\u005b\\u005d\\u005c]", status);
45   UnicodeSet oldIllegal("[0-9 a-z A-Z "
46                         "_ \\{ \\} \\[ \\] # \\( \\) < > % \\: ; . "
47                         "? * + \\- / \\^ \\& | ~ ! = , \\ \" ' ]", status);
48 
49   /*
50 
51 http://www.lirmm.fr/~ducour/Doc-objets/ISO+IEC+14882-1998.pdf ( note: 1998 )   page 10, section 2.2 says:
52 
53 1 The basic source character set consists of 96 characters: the space character, the control characters repre- 15)
54 senting horizontal tab, vertical tab, form feed, and new-line, plus the following 91 graphical characters:
55 a b c d e f g h i j k l m n opqrstuvwxyz
56 A B C D E F G H I J K L M N OPQRSTUVWXYZ
57 0 12 3 4 5 6 7 8 9
58  _ { } [ ] # ( ) < > % : ; . ?*+-/^&|~!=,\"
59 2 The universal-character-name construct provides a way to name other characters. hex-quad:
60 hexadecimal-digit hexadecimal-digit hexadecimal-digit hexadecimal-digit
61 universal-character-name: \u hex-quad
62 \U hex-quad hex-quad
63 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.
64 
65 
66 So basically:  printable ASCII plus  0x00-0x1F,  0x7F-0x9F, was all illegal.
67 
68 Some discussion at http://unicode.org/mail-arch/unicode-ml/y2003-m10/0471.html
69 
70    */
71 
72 
73 
74   printf("static const bool oldIllegal[256] = { \n");
75   for(char16_t i=0x00; i<0x100;i++) {
76     printf(" %s, /* U+%04X */\n",
77            (oldIllegal.contains(i))?" true":"false",
78            i);
79   }
80   printf("};\n\n");
81 
82   return 0;
83 }
84