draft-ietf-idn-dude-02.txt

bind-3.2.

  char output[] )
{
  unsigned int max_out, in, out, k, j;
  u_code_point prev, codept, diff, tmp;
  char shift;

  prev = 0x60;
  max_out = *output_size;

  for (in = out = 0;  in < input_length;  ++in) {

    /* At the start of each iteration, in and out are the number of */
    /* items already input/output, or equivalently, the indices of  */
    /* the next items to be input/output.                           */

    codept = input[in];

    if (codept == 0x2D) {
      /* Hyphen-minus stands for itself. */
      if (max_out - out < 1) return dude_big_output;
      output[out++] = 0x2D;
      continue;
    }

    diff = prev ^ codept;

    /* Compute the number of base-32 characters (k): */
    for (tmp = diff >> 4, k = 1;  tmp != 0;  ++k, tmp >>= 4);

    if (max_out - out < k) return dude_big_output;
    shift = uppercase_flags && uppercase_flags[in] ? 32 : 0;
    /* shift controls the case of the last base-32 digit. */

    /* Each quintet has the form 1xxxx except the last is 0xxxx. */
    /* Computing the base-32 digits in reverse order is easiest. */

    out += k;
    output[out - 1] = base32[diff & 0xF] - shift;

    for (j = 2;  j <= k;  ++j) {
      diff >>= 4;
      output[out - j] = base32[0x10 | (diff & 0xF)];
    }

    prev = codept;
  }

  /* Append the null terminator: */
  if (max_out - out < 1) return dude_big_output;
  output[out++] = 0;

  *output_size = out;
  return dude_success;
}


/* Decoder: */

enum dude_status dude_decode(
  enum case_sensitivity case_sensitivity,
  char scratch_space[],
  const char input[],
  unsigned int *output_length,
  u_code_point output[],
  unsigned char uppercase_flags[] )
{
  u_code_point prev, q, diff;
  char c;
  unsigned int max_out, in, out, scratch_size;
  enum dude_status status;

  prev = 0x60;
  max_out = *output_length;

  for (c = input[in = 0], out = 0;  c != 0;  c = input[++in], ++out) {

    /* At the start of each iteration, in and out are the number of */
    /* items already input/output, or equivalently, the indices of  */
    /* the next items to be input/output.                           */

    if (max_out - out < 1) return dude_big_output;

    if (c == 0x2D) output[out] = c;  /* hyphen-minus is literal */
    else {
      /* Base-32 sequence.  Decode quintets until 0xxxx is found: */

      for (diff = 0;  ;  c = input[++in]) {
        q = base32_decode(c);
        if (q == base32_invalid) return dude_bad_input;
        diff = (diff << 4) | (q & 0xF);
        if (q >> 4 == 0) break;
      }

      prev = output[out] = prev ^ diff;
    }

    /* Case of last character determines uppercase flag: */
    if (uppercase_flags) uppercase_flags[out] = c >= 65 && c <= 90;
  }

  /* Enforce the uniqueness of the encoding by re-encoding */
  /* the output and comparing the result to the input:     */

  scratch_size = ++in;
  status = dude_encode(out, output, uppercase_flags,
                       &scratch_size, scratch_space);
  if (status != dude_success || scratch_size != in ||
      unequal(case_sensitivity, scratch_space, input)
     ) return dude_bad_input;

  *output_length = out;
  return dude_success;
}


/******************************************************************/
/* Wrapper for testing (would normally go in a separate .c file): */

#include <assert.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

/* For testing, we'll just set some compile-time limits rather than */
/* use malloc(), and set a compile-time option rather than using a  */
/* command-line option.                                             */

enum {
  unicode_max_length = 256,
  ace_max_size = 256,
  test_case_sensitivity = case_insensitive
                          /* suitable for host names */
};


static void usage(char **argv)
{
  fprintf(stderr,
    "%s -e reads code points and writes a DUDE string.\n"
    "%s -d reads a DUDE string and writes code points.\n"
    "Input and output are plain text in the native character set.\n"
    "Code points are in the form u+hex separated by whitespace.\n"
    "A DUDE string is a newline-terminated sequence of LDH characters\n"
    "(without any signature).\n"
    "The case of the u in u+hex is the force-to-uppercase flag.\n"
    , argv[0], argv[0]);
  exit(EXIT_FAILURE);
}


static void fail(const char *msg)
{
  fputs(msg,stderr);
  exit(EXIT_FAILURE);
}

static const char too_big[] =
  "input or output is too large, recompile with larger limits\n";
static const char invalid_input[] = "invalid input\n";
static const char io_error[] = "I/O error\n";


/* The following string is used to convert LDH      */
/* characters between ASCII and the native charset: */

static const char ldh_ascii[] =
  "................"
  "................"
  ".............-.."
  "0123456789......"
  ".ABCDEFGHIJKLMNO"
  "PQRSTUVWXYZ....."
  ".abcdefghijklmno"
  "pqrstuvwxyz";


int main(int argc, char **argv)
{
  enum dude_status status;
  int r;
  char *p;

  if (argc != 2) usage(argv);
  if (argv[1][0] != '-') usage(argv);
  if (argv[1][2] != 0) usage(argv);

  if (argv[1][1] == 'e') {
    u_code_point input[unicode_max_length];
    unsigned long codept;
    unsigned char uppercase_flags[unicode_max_length];
    char output[ace_max_size], uplus[3];
    unsigned int input_length, output_size, i;

    /* Read the input code points: */

    input_length = 0;

    for (;;) {
      r = scanf("%2s%lx", uplus, &codept);
      if (ferror(stdin)) fail(io_error);
      if (r == EOF || r == 0) break;

      if (r != 2 || uplus[1] != '+' || codept > (u_code_point)-1) {
        fail(invalid_input);
      }

      if (input_length == unicode_max_length) fail(too_big);

      if (uplus[0] == 'u') uppercase_flags[input_length] = 0;
      else if (uplus[0] == 'U') uppercase_flags[input_length] = 1;
      else fail(invalid_input);

      input[input_length++] = codept;
    }

    /* Encode: */

    output_size = ace_max_size;
    status = dude_encode(input_length, input, uppercase_flags,
                         &output_size, output);
    if (status == dude_bad_input) fail(invalid_input);
    if (status == dude_big_output) fail(too_big);
    assert(status == dude_success);

    /* Convert to native charset and output: */

    for (p = output;  *p != 0;  ++p) {
      i = *p;
      assert(i <= 122 && ldh_ascii[i] != '.');
      *p = ldh_ascii[i];
    }

    r = puts(output);
    if (r == EOF) fail(io_error);
    return EXIT_SUCCESS;
  }

  if (argv[1][1] == 'd') {
    char input[ace_max_size], scratch[ace_max_size], *pp;
    u_code_point output[unicode_max_length];
    unsigned char uppercase_flags[unicode_max_length];
    unsigned int input_length, output_length, i;

    /* Read the DUDE input string and convert to ASCII: */

    fgets(input, ace_max_size, stdin);
    if (ferror(stdin)) fail(io_error);
    if (feof(stdin)) fail(invalid_input);
    input_length = strlen(input);
    if (input[input_length - 1] != '\n') fail(too_big);
    input[--input_length] = 0;

    for (p = input;  *p != 0;  ++p) {
      pp = strchr(ldh_ascii, *p);
      if (pp == 0) fail(invalid_input);
      *p = pp - ldh_ascii;
    }

    /* Decode: */

    output_length = unicode_max_length;
    status = dude_decode(test_case_sensitivity, scratch, input,
                         &output_length, output, uppercase_flags);
    if (status == dude_bad_input) fail(invalid_input);
    if (status == dude_big_output) fail(too_big);
    assert(status == dude_success);

    /* Output the result: */

    for (i = 0;  i < output_length;  ++i) {
      r = printf("%s+%04lX\n",
                 uppercase_flags[i] ? "U" : "u",
                 (unsigned long) output[i] );
      if (r < 0) fail(io_error);
    }

    return EXIT_SUCCESS;
  }

  usage(argv);
  return EXIT_SUCCESS;  /* not reached, but quiets compiler warning */
}



                   INTERNET-DRAFT expires 2001-Dec-07