tests/table-from.c

   1 /* Copyright (C) 2000-2001 Free Software Foundation, Inc.
   2    This file is part of the GNU LIBICONV Library.
   3
   4    The GNU LIBICONV Library is free software; you can redistribute it
   5    and/or modify it under the terms of the GNU Library General Public
   6    License as published by the Free Software Foundation; either version 2
   7    of the License, or (at your option) any later version.
   8
   9    The GNU LIBICONV Library is distributed in the hope that it will be
  10    useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  12    Library General Public License for more details.
  13
  14    You should have received a copy of the GNU Library General Public
  15    License along with the GNU LIBICONV Library; see the file COPYING.LIB.
  16    If not, write to the Free Software Foundation, Inc., 59 Temple Place -
  17    Suite 330, Boston, MA 02111-1307, USA.  */
  18
  19 /* Create a table from CHARSET to Unicode. */
  20
  21 #include "config.h"
  22
  23 #include <stddef.h>
  24 #include <stdio.h>
  25 #include <stdlib.h>
  26 #include <iconv.h>
  27 #include <errno.h>
  28
  29 /* If nonzero, ignore conversions outside Unicode plane 0. */
  30 static int bmp_only;
  31
  32 static const char* hexbuf (unsigned char buf[], unsigned int buflen)
  33 {
  34   static char msg[50];
  35   switch (buflen) {
  36     case 1: sprintf(msg,"0x%02X",buf[0]); break;
  37     case 2: sprintf(msg,"0x%02X%02X",buf[0],buf[1]); break;
  38     case 3: sprintf(msg,"0x%02X%02X%02X",buf[0],buf[1],buf[2]); break;
  39     case 4: sprintf(msg,"0x%02X%02X%02X%02X",buf[0],buf[1],buf[2],buf[3]); break;
  40     default: abort();
  41   }
  42   return msg;
  43 }
  44
  45 static int try (iconv_t cd, unsigned char buf[], unsigned int buflen, unsigned int* out)
  46 {
  47   const char* inbuf = (const char*) buf;
  48   size_t inbytesleft = buflen;
  49   char* outbuf = (char*) out;
  50   size_t outbytesleft = 3*sizeof(unsigned int);
  51   size_t result;
  52   iconv(cd,NULL,NULL,NULL,NULL);
  53   result = iconv(cd,(ICONV_CONST char**)&inbuf,&inbytesleft,&outbuf,&outbytesleft);
  54   if (result != (size_t)(-1))
  55     result = iconv(cd,NULL,NULL,&outbuf,&outbytesleft);
  56   if (result == (size_t)(-1)) {
  57     if (errno == EILSEQ) {
  58       return -1;
  59     } else if (errno == EINVAL) {
  60       return 0;
  61     } else {
  62       int saved_errno = errno;
  63       fprintf(stderr,"%s: iconv error: ",hexbuf(buf,buflen));
  64       errno = saved_errno;
  65       perror("");
  66       exit(1);
  67     }
  68   } else if (result > 0) /* ignore conversions with transliteration */ {
  69     return -1;
  70   } else {
  71     if (inbytesleft != 0) {
  72       fprintf(stderr,"%s: inbytes = %ld, outbytes = %ld\n",hexbuf(buf,buflen),(long)(buflen-inbytesleft),(long)(3*sizeof(unsigned int)-outbytesleft));
  73       exit(1);
  74     }
  75     return (3*sizeof(unsigned int)-outbytesleft)/sizeof(unsigned int);
  76   }
  77 }
  78
  79 /* Returns the out[] buffer as a Unicode value, formatted as 0x%04X. */
  80 static const char* ucs4_decode (const unsigned int* out, unsigned int outlen)
  81 {
  82   static char hexbuf[21];
  83   char* p = hexbuf;
  84   while (outlen > 0) {
  85     if (p > hexbuf)
  86       *p++ = ' ';
  87     sprintf (p, "0x%04X", out[0]);
  88     out += 1; outlen -= 1;
  89     if (bmp_only && strlen(p) > 6)
  90       return NULL;
  91     p += strlen(p);
  92   }
  93   return hexbuf;
  94 }
  95
  96 int main (int argc, char* argv[])
  97 {
  98   const char* charset;
  99   iconv_t cd;
 100   int search_depth;
 101
 102   if (argc != 2) {
 103     fprintf(stderr,"Usage: table-to charset\n");
 104     exit(1);
 105   }
 106   charset = argv[1];
 107
 108   cd = iconv_open("UCS-4-INTERNAL",charset);
 109   if (cd == (iconv_t)(-1)) {
 110     perror("iconv_open");
 111     exit(1);
 112   }
 113
 114   /* When testing UTF-8 or GB18030, stop at 0x10000, otherwise the output
 115      file gets too big. */
 116   bmp_only = (strcmp(charset,"UTF-8") == 0 || strcmp(charset,"GB18030") == 0);
 117   search_depth = (strcmp(charset,"UTF-8") == 0 ? 3 : 4);
 118
 119   {
 120     unsigned int out[3];
 121     unsigned char buf[4];
 122     unsigned int i0, i1, i2, i3;
 123     int result;
 124     for (i0 = 0; i0 < 0x100; i0++) {
 125       buf[0] = i0;
 126       result = try(cd,buf,1,out);
 127       if (result < 0) {
 128       } else if (result > 0) {
 129         const char* unicode = ucs4_decode(out,result);
 130         if (unicode != NULL)
 131           printf("0x%02X\t%s\n",i0,unicode);
 132       } else {
 133         for (i1 = 0; i1 < 0x100; i1++) {
 134           buf[1] = i1;
 135           result = try(cd,buf,2,out);
 136           if (result < 0) {
 137           } else if (result > 0) {
 138             const char* unicode = ucs4_decode(out,result);
 139             if (unicode != NULL)
 140               printf("0x%02X%02X\t%s\n",i0,i1,unicode);
 141           } else {
 142             for (i2 = 0; i2 < 0x100; i2++) {
 143               buf[2] = i2;
 144               result = try(cd,buf,3,out);
 145               if (result < 0) {
 146               } else if (result > 0) {
 147                 const char* unicode = ucs4_decode(out,result);
 148                 if (unicode != NULL)
 149                   printf("0x%02X%02X%02X\t%s\n",i0,i1,i2,unicode);
 150               } else if (search_depth > 3) {
 151                 for (i3 = 0; i3 < 0x100; i3++) {
 152                   buf[3] = i3;
 153                   result = try(cd,buf,4,out);
 154                   if (result < 0) {
 155                   } else if (result > 0) {
 156                     const char* unicode = ucs4_decode(out,result);
 157                     if (unicode != NULL)
 158                       printf("0x%02X%02X%02X%02X\t%s\n",i0,i1,i2,i3,unicode);
 159                   } else {
 160                     fprintf(stderr,"%s: incomplete byte sequence\n",hexbuf(buf,4));
 161                     exit(1);
 162                   }
 163                 }
 164               }
 165             }
 166           }
 167         }
 168       }
 169     }
 170   }
 171
 172   if (iconv_close(cd) < 0) {
 173     perror("iconv_close");
 174     exit(1);
 175   }
 176
 177   if (ferror(stdin) || ferror(stdout)) {
 178     fprintf(stderr,"I/O error\n");
 179     exit(1);
 180   }
 181
 182   exit(0);
 183 }