idna.c

Go to the documentation of this file.

/* idna.c --- Prototypes for Internationalized Domain Name library.
   Copyright (C) 2002-2025 Simon Josefsson
 
   This file is part of GNU Libidn.
 
   GNU Libidn is free software: you can redistribute it and/or
   modify it under the terms of either:
 
     * the GNU Lesser General Public License as published by the Free
       Software Foundation; either version 3 of the License, or (at
       your option) any later version.
 
   or
 
     * the GNU General Public License as published by the Free
       Software Foundation; either version 2 of the License, or (at
       your option) any later version.
 
   or both in parallel, as here.
 
   GNU Libidn is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   General Public License for more details.
 
   You should have received copies of the GNU General Public License and
   the GNU Lesser General Public License along with this program.  If
   not, see <https://www.gnu.org/licenses/>. */
 
#ifdef HAVE_CONFIG_H
# include "config.h"
#endif
 
#include <stdlib.h>
#include <string.h>
#include <stringprep.h>
#include <punycode.h>
 
#include "idna.h"
 
/* Get c_strcasecmp. */
#include <c-strcase.h>
 
#define DOTP(c) ((c) == 0x002E || (c) == 0x3002 ||      \
                 (c) == 0xFF0E || (c) == 0xFF61)
 
/* Core functions */
 
int
idna_to_ascii_4i (const uint32_t *in, size_t inlen, char *out, int flags)
{
  size_t len, outlen;
  uint32_t *src;                /* XXX don't need to copy data? */
  int rc;
 
  /*
   * ToASCII consists of the following steps:
   *
   * 1. If all code points in the sequence are in the ASCII range (0..7F)
   * then skip to step 3.
   */
 
  {
    size_t i;
    int inasciirange;
 
    inasciirange = 1;
    for (i = 0; i < inlen; i++)
      if (in[i] > 0x7F)
        inasciirange = 0;
    if (inasciirange)
      {
        src = malloc (sizeof (in[0]) * (inlen + 1));
        if (src == NULL)
          return IDNA_MALLOC_ERROR;
 
        memcpy (src, in, sizeof (in[0]) * inlen);
        src[inlen] = 0;
 
        goto step3;
      }
  }
 
  /*
   * 2. Perform the steps specified in [NAMEPREP] and fail if there is
   * an error. The AllowUnassigned flag is used in [NAMEPREP].
   */
 
  {
    char *p;
 
    p = stringprep_ucs4_to_utf8 (in, (ssize_t) inlen, NULL, NULL);
    if (p == NULL)
      return IDNA_MALLOC_ERROR;
 
    len = strlen (p);
    do
      {
        char *newp;
 
        len = 2 * len + 10;     /* XXX better guess? */
        newp = realloc (p, len);
        if (newp == NULL)
          {
            free (p);
            return IDNA_MALLOC_ERROR;
          }
        p = newp;
 
        if (flags & IDNA_ALLOW_UNASSIGNED)
          rc = stringprep_nameprep (p, len);
        else
          rc = stringprep_nameprep_no_unassigned (p, len);
      }
    while (rc == STRINGPREP_TOO_SMALL_BUFFER);
 
    if (rc != STRINGPREP_OK)
      {
        free (p);
        return IDNA_STRINGPREP_ERROR;
      }
 
    src = stringprep_utf8_to_ucs4 (p, -1, NULL);
 
    free (p);
 
    if (!src)
      return IDNA_MALLOC_ERROR;
  }
 
step3:
  /*
   * 3. If the UseSTD3ASCIIRules flag is set, then perform these checks:
   *
   * (a) Verify the absence of non-LDH ASCII code points; that is,
   * the absence of 0..2C, 2E..2F, 3A..40, 5B..60, and 7B..7F.
   *
   * (b) Verify the absence of leading and trailing hyphen-minus;
   * that is, the absence of U+002D at the beginning and end of
   * the sequence.
   */
 
  if (flags & IDNA_USE_STD3_ASCII_RULES)
    {
      size_t i;
 
      for (i = 0; src[i]; i++)
        if (src[i] <= 0x2C || src[i] == 0x2E || src[i] == 0x2F ||
            (src[i] >= 0x3A && src[i] <= 0x40) ||
            (src[i] >= 0x5B && src[i] <= 0x60) ||
            (src[i] >= 0x7B && src[i] <= 0x7F))
          {
            free (src);
            return IDNA_CONTAINS_NON_LDH;
          }
 
      if (src[0] == 0x002D || (i > 0 && src[i - 1] == 0x002D))
        {
          free (src);
          return IDNA_CONTAINS_MINUS;
        }
    }
 
  /*
   * 4. If all code points in the sequence are in the ASCII range
   * (0..7F), then skip to step 8.
   */
 
  {
    size_t i;
    int inasciirange;
 
    inasciirange = 1;
    for (i = 0; src[i]; i++)
      {
        if (src[i] > 0x7F)
          inasciirange = 0;
        /* copy string to output buffer if we are about to skip to step8 */
        if (i < 64)
          out[i] = src[i];
      }
    if (i < 64)
      out[i] = '\0';
    else
      {
        free (src);
        return IDNA_INVALID_LENGTH;
      }
    if (inasciirange)
      goto step8;
  }
 
  /*
   * 5. Verify that the sequence does NOT begin with the ACE prefix.
   *
   */
 
  {
    size_t i;
    int match;
 
    match = 1;
    for (i = 0; match && i < strlen (IDNA_ACE_PREFIX); i++)
      if (((uint32_t) IDNA_ACE_PREFIX[i] & 0xFF) != src[i])
        match = 0;
    if (match)
      {
        free (src);
        return IDNA_CONTAINS_ACE_PREFIX;
      }
  }
 
  /*
   * 6. Encode the sequence using the encoding algorithm in [PUNYCODE]
   * and fail if there is an error.
   */
  for (len = 0; src[len]; len++)
    ;
  src[len] = '\0';
  outlen = 63 - strlen (IDNA_ACE_PREFIX);
  rc = punycode_encode (len, src, NULL,
                        &outlen, &out[strlen (IDNA_ACE_PREFIX)]);
  if (rc != PUNYCODE_SUCCESS)
    {
      free (src);
      return IDNA_PUNYCODE_ERROR;
    }
  out[strlen (IDNA_ACE_PREFIX) + outlen] = '\0';
 
  /*
   * 7. Prepend the ACE prefix.
   */
 
  memcpy (out, IDNA_ACE_PREFIX, strlen (IDNA_ACE_PREFIX));
 
  /*
   * 8. Verify that the number of code points is in the range 1 to 63
   * inclusive (0 is excluded).
   */
 
step8:
  free (src);
  if (strlen (out) < 1)
    return IDNA_INVALID_LENGTH;
 
  return IDNA_SUCCESS;
}
 
/* ToUnicode().  May realloc() utf8in.  Will free utf8in unconditionally. */
static int
idna_to_unicode_internal (char *utf8in,
                          uint32_t *out, size_t *outlen, int flags)
{
  int rc;
  char tmpout[64];
  size_t utf8len = strlen (utf8in) + 1;
  size_t addlen = 0, addinc = utf8len / 10 + 1;
 
  /*
   * ToUnicode consists of the following steps:
   *
   * 1. If the sequence contains any code points outside the ASCII range
   * (0..7F) then proceed to step 2, otherwise skip to step 3.
   */
 
  {
    size_t i;
    int inasciirange;
 
    inasciirange = 1;
    for (i = 0; utf8in[i]; i++)
      if (utf8in[i] & ~0x7F)
        inasciirange = 0;
    if (inasciirange)
      goto step3;
  }
 
  /*
   * 2. Perform the steps specified in [NAMEPREP] and fail if there is an
   * error. (If step 3 of ToASCII is also performed here, it will not
   * affect the overall behavior of ToUnicode, but it is not
   * necessary.) The AllowUnassigned flag is used in [NAMEPREP].
   */
  do
    {
      char *newp = realloc (utf8in, utf8len + addlen);
      if (newp == NULL)
        {
          free (utf8in);
          return IDNA_MALLOC_ERROR;
        }
      utf8in = newp;
      if (flags & IDNA_ALLOW_UNASSIGNED)
        rc = stringprep_nameprep (utf8in, utf8len + addlen);
      else
        rc = stringprep_nameprep_no_unassigned (utf8in, utf8len + addlen);
      addlen += addinc;
      addinc *= 2;
    }
  while (rc == STRINGPREP_TOO_SMALL_BUFFER);
 
  if (rc != STRINGPREP_OK)
    {
      free (utf8in);
      return IDNA_STRINGPREP_ERROR;
    }
 
  /* 3. Verify that the sequence begins with the ACE prefix, and save a
   * copy of the sequence.
   * ... The ToASCII and ToUnicode operations MUST recognize the ACE
   prefix in a case-insensitive manner.
   */
 
step3:
  if (c_strncasecmp (utf8in, IDNA_ACE_PREFIX, strlen (IDNA_ACE_PREFIX)) != 0)
    {
      free (utf8in);
      return IDNA_NO_ACE_PREFIX;
    }
 
  /* 4. Remove the ACE prefix.
   */
 
  memmove (utf8in, &utf8in[strlen (IDNA_ACE_PREFIX)],
           strlen (utf8in) - strlen (IDNA_ACE_PREFIX) + 1);
 
  /* 5. Decode the sequence using the decoding algorithm in [PUNYCODE]
   * and fail if there is an error. Save a copy of the result of
   * this step.
   */
 
  (*outlen)--;                  /* reserve one for the zero */
 
  rc = punycode_decode (strlen (utf8in), utf8in, outlen, out, NULL);
  if (rc != PUNYCODE_SUCCESS)
    {
      free (utf8in);
      return IDNA_PUNYCODE_ERROR;
    }
 
  out[*outlen] = 0;             /* add zero */
 
  /* 6. Apply ToASCII.
   */
 
  rc = idna_to_ascii_4i (out, *outlen, tmpout, flags);
  if (rc != IDNA_SUCCESS)
    {
      free (utf8in);
      return rc;
    }
 
  /* 7. Verify that the result of step 6 matches the saved copy from
   * step 3, using a case-insensitive ASCII comparison.
   */
 
  if (c_strcasecmp (utf8in, tmpout + strlen (IDNA_ACE_PREFIX)) != 0)
    {
      free (utf8in);
      return IDNA_ROUNDTRIP_VERIFY_ERROR;
    }
 
  /* 8. Return the saved copy from step 5.
   */
 
  free (utf8in);
  return IDNA_SUCCESS;
}
 
int
idna_to_unicode_44i (const uint32_t *in, size_t inlen,
                     uint32_t *out, size_t *outlen, int flags)
{
  int rc;
  size_t outlensave = *outlen;
  char *p;
 
  p = stringprep_ucs4_to_utf8 (in, (ssize_t) inlen, NULL, NULL);
  if (p == NULL)
    return IDNA_MALLOC_ERROR;
 
  rc = idna_to_unicode_internal (p, out, outlen, flags);
  if (rc != IDNA_SUCCESS)
    {
      memcpy (out, in, sizeof (in[0]) * (inlen < outlensave ?
                                         inlen : outlensave));
      *outlen = inlen;
    }
 
  /* p is freed in idna_to_unicode_internal.  */
 
  return rc;
}
 
/* Wrappers that handle several labels */
 
int
idna_to_ascii_4z (const uint32_t *input, char **output, int flags)
{
  const uint32_t *start = input;
  const uint32_t *end;
  char buf[64];
  char *out = NULL;
  int rc;
 
  /* 1) Whenever dots are used as label separators, the following
     characters MUST be recognized as dots: U+002E (full stop),
     U+3002 (ideographic full stop), U+FF0E (fullwidth full stop),
     U+FF61 (halfwidth ideographic full stop). */
 
  if (input[0] == 0)
    {
      /* Handle implicit zero-length root label. */
      *output = malloc (1);
      if (!*output)
        return IDNA_MALLOC_ERROR;
      strcpy (*output, "");
      return IDNA_SUCCESS;
    }
 
  if (DOTP (input[0]) && input[1] == 0)
    {
      /* Handle explicit zero-length root label. */
      *output = malloc (2);
      if (!*output)
        return IDNA_MALLOC_ERROR;
      strcpy (*output, ".");
      return IDNA_SUCCESS;
    }
 
  *output = NULL;
  do
    {
      end = start;
 
      for (; *end && !DOTP (*end); end++)
        ;
 
      if (*end == '\0' && start == end)
        {
          /* Handle explicit zero-length root label. */
          buf[0] = '\0';
        }
      else
        {
          rc = idna_to_ascii_4i (start, (size_t) (end - start), buf, flags);
          if (rc != IDNA_SUCCESS)
            {
              free (out);
              return rc;
            }
        }
 
      if (out)
        {
          size_t l = strlen (out) + 1 + strlen (buf) + 1;
          char *newp = realloc (out, l);
          if (!newp)
            {
              free (out);
              return IDNA_MALLOC_ERROR;
            }
          out = newp;
          strcat (out, ".");
          strcat (out, buf);
        }
      else
        {
          out = strdup (buf);
          if (!out)
            return IDNA_MALLOC_ERROR;
        }
 
      start = end + 1;
    }
  while (*end);
 
  *output = out;
 
  return IDNA_SUCCESS;
}
 
int
idna_to_ascii_8z (const char *input, char **output, int flags)
{
  uint32_t *ucs4;
  size_t ucs4len;
  int rc;
 
  ucs4 = stringprep_utf8_to_ucs4 (input, -1, &ucs4len);
  if (!ucs4)
    return IDNA_ICONV_ERROR;
 
  rc = idna_to_ascii_4z (ucs4, output, flags);
 
  free (ucs4);
 
  return rc;
 
}
 
int
idna_to_ascii_lz (const char *input, char **output, int flags)
{
  char *utf8;
  int rc;
 
  utf8 = stringprep_locale_to_utf8 (input);
  if (!utf8)
    return IDNA_ICONV_ERROR;
 
  rc = idna_to_ascii_8z (utf8, output, flags);
 
  free (utf8);
 
  return rc;
}
 
int
idna_to_unicode_4z4z (const uint32_t *input, uint32_t **output, int flags)
{
  const uint32_t *start = input;
  const uint32_t *end;
  uint32_t *buf;
  size_t buflen;
  uint32_t *out = NULL;
  size_t outlen = 0;
  int rc;
 
  *output = NULL;
 
  do
    {
      end = start;
 
      for (; *end && !DOTP (*end); end++)
        ;
 
      buflen = (size_t) (end - start);
      buf = malloc (sizeof (buf[0]) * (buflen + 1));
      if (!buf)
        {
          free (out);
          return IDNA_MALLOC_ERROR;
        }
 
      /* don't check for non-malloc return codes as per
         specification! */
      rc = idna_to_unicode_44i (start, (size_t) (end - start),
                                buf, &buflen, flags);
      if (rc == IDNA_MALLOC_ERROR)
        {
          free (out);
          return IDNA_MALLOC_ERROR;
        }
 
      if (out)
        {
          uint32_t *newp = realloc (out,
                                    sizeof (out[0])
                                    * (outlen + 1 + buflen + 1));
          if (!newp)
            {
              free (buf);
              free (out);
              return IDNA_MALLOC_ERROR;
            }
          out = newp;
          out[outlen++] = 0x002E;       /* '.' (full stop) */
          memcpy (out + outlen, buf, sizeof (buf[0]) * buflen);
          outlen += buflen;
          out[outlen] = 0x0;
          free (buf);
        }
      else
        {
          out = buf;
          outlen = buflen;
          out[outlen] = 0x0;
        }
 
      start = end + 1;
    }
  while (*end);
 
  *output = out;
 
  return IDNA_SUCCESS;
}
 
int
idna_to_unicode_8z4z (const char *input, uint32_t **output, int flags)
{
  uint32_t *ucs4;
  size_t ucs4len;
  int rc;
 
  ucs4 = stringprep_utf8_to_ucs4 (input, -1, &ucs4len);
  if (!ucs4)
    return IDNA_ICONV_ERROR;
 
  rc = idna_to_unicode_4z4z (ucs4, output, flags);
  free (ucs4);
 
  return rc;
}
 
int
idna_to_unicode_8z8z (const char *input, char **output, int flags)
{
  uint32_t *ucs4;
  int rc;
 
  rc = idna_to_unicode_8z4z (input, &ucs4, flags);
  if (rc != IDNA_SUCCESS)
    return rc;
 
  *output = stringprep_ucs4_to_utf8 (ucs4, -1, NULL, NULL);
  free (ucs4);
 
  if (!*output)
    return IDNA_ICONV_ERROR;
 
  return IDNA_SUCCESS;
}
 
int
idna_to_unicode_8zlz (const char *input, char **output, int flags)
{
  char *utf8;
  int rc;
 
  rc = idna_to_unicode_8z8z (input, &utf8, flags);
  if (rc != IDNA_SUCCESS)
    return rc;
 
  *output = stringprep_utf8_to_locale (utf8);
  free (utf8);
 
  if (!*output)
    return IDNA_ICONV_ERROR;
 
  return IDNA_SUCCESS;
}
 
int
idna_to_unicode_lzlz (const char *input, char **output, int flags)
{
  char *utf8;
  int rc;
 
  utf8 = stringprep_locale_to_utf8 (input);
  if (!utf8)
    return IDNA_ICONV_ERROR;
 
  rc = idna_to_unicode_8zlz (utf8, output, flags);
  free (utf8);
 
  return rc;
}