GNU Libidn

Simon Josefsson Datakonsult
Hagagatan 24
113 47 Stockholm
Sweden

E-mail: simon@josefsson.org

     $ wget -q ftp://alpha.gnu.org/pub/gnu/libidn/libidn-1.10.tar.gz
     $ tar xfz libidn-1.10.tar.gz
     $ cd libidn-1.10/
     $ ./configure
     ...
     $ make
     ...
     $ make install
     ...

     #include <stringprep.h>

       if (!stringprep_check_version (STRINGPREP_VERSION))
         {
           printf ("stringprep_check_version() failed:\n"
                   "Header file incompatible with shared library.\n");
           exit(1);
         }

     gcc -c foo.c `pkg-config libidn --cflags`

     gcc -o foo foo.o `pkg-config libidn --libs`

     gcc -o foo foo.c `pkg-config libidn --cflags --libs`

     AC_ARG_WITH(libidn, AC_HELP_STRING([--with-libidn=[DIR]],
                                     [Support IDN (needs GNU Libidn)]),
       libidn=$withval, libidn=yes)
     if test "$libidn" != "no"; then
       if test "$libidn" != "yes"; then
         LDFLAGS="${LDFLAGS} -L$libidn/lib"
         CPPFLAGS="${CPPFLAGS} -I$libidn/include"
       fi
       AC_CHECK_HEADER(idna.h,
         AC_CHECK_LIB(idn, stringprep_check_version,
           [libidn=yes LIBS="${LIBS} -lidn"], libidn=no),
         libidn=no)
     fi
     if test "$libidn" != "no" ; then
       AC_DEFINE(LIBIDN, 1, [Define to 1 if you want IDN support.])
     else
       AC_MSG_WARN([Libidn not found])
     fi
     AC_MSG_CHECKING([if Libidn should be used])
     AC_MSG_RESULT($libidn)

     AC_ARG_WITH(libidn, AC_HELP_STRING([--with-libidn=[DIR]],
                                     [Support IDN (needs GNU Libidn)]),
       libidn=$withval, libidn=yes)
     if test "$libidn" != "no" ; then
       PKG_CHECK_MODULES(LIBIDN, libidn >= 0.0.0, [libidn=yes], [libidn=no])
       if test "$libidn" != "yes" ; then
         libidn=no
         AC_MSG_WARN([Libidn not found])
       else
         libidn=yes
         AC_DEFINE(LIBIDN, 1, [Define to 1 if you want Libidn.])
       fi
     fi
     AC_MSG_CHECKING([if Libidn should be used])
     AC_MSG_RESULT($libidn)

     #include <stringprep.h>

     #include <stringprep.h>

     #include <punycode.h>

     #include <idna.h>

     #include <tld.h>

     #include <pr29.h>

/* example.c --- Example code showing how to use stringprep().
 * Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007, 2008  Simon Josefsson
 *
 * This file is part of GNU Libidn.
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program 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 a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 *
 */

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <locale.h>		/* setlocale() */
#include <stringprep.h>

/*
 * Compiling using libtool and pkg-config is recommended:
 *
 * $ libtool cc -o example example.c `pkg-config --cflags --libs libidn`
 * $ ./example
 * Input string encoded as `ISO-8859-1': ª
 * Before locale2utf8 (length 2): aa 0a
 * Before stringprep (length 3): c2 aa 0a
 * After stringprep (length 2): 61 0a
 * $
 *
 */

int
main (int argc, char *argv[])
{
  char buf[BUFSIZ];
  char *p;
  int rc;
  size_t i;

  setlocale (LC_ALL, "");

  printf ("Input string encoded as `%s': ", stringprep_locale_charset ());
  fflush (stdout);
  fgets (buf, BUFSIZ, stdin);

  printf ("Before locale2utf8 (length %d): ", strlen (buf));
  for (i = 0; i < strlen (buf); i++)
    printf ("%02x ", buf[i] & 0xFF);
  printf ("\n");

  p = stringprep_locale_to_utf8 (buf);
  if (p)
    {
      strcpy (buf, p);
      free (p);
    }
  else
    printf ("Could not convert string to UTF-8, continuing anyway...\n");

  printf ("Before stringprep (length %d): ", strlen (buf));
  for (i = 0; i < strlen (buf); i++)
    printf ("%02x ", buf[i] & 0xFF);
  printf ("\n");

  rc = stringprep (buf, BUFSIZ, 0, stringprep_nameprep);
  if (rc != STRINGPREP_OK)
    printf ("Stringprep failed (%d): %s\n", rc, stringprep_strerror (rc));
  else
    {
      printf ("After stringprep (length %d): ", strlen (buf));
      for (i = 0; i < strlen (buf); i++)
	printf ("%02x ", buf[i] & 0xFF);
      printf ("\n");
    }

  return 0;
}

/* example2.c --- Example code showing how to use punycode.
 * Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007  Simon Josefsson
 * Copyright (C) 2002  Adam M. Costello
 *
 * This file is part of GNU Libidn.
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program 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 a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 *
 */

#include <locale.h>		/* setlocale() */

/*
 * This file is derived from RFC 3492 written by Adam M. Costello.
 *
 * Disclaimer and license: Regarding this entire document or any
 * portion of it (including the pseudocode and C code), the author
 * makes no guarantees and is not responsible for any damage resulting
 * from its use.  The author grants irrevocable permission to anyone
 * to use, modify, and distribute it in any way that does not diminish
 * the rights of anyone else to use, modify, and distribute it,
 * provided that redistributed derivative works do not contain
 * misleading author or version information.  Derivative works need
 * not be licensed under similar terms.
 *
 */

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

#include <punycode.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_length = 256
};

static void
usage (char **argv)
{
  fprintf (stderr,
	   "\n"
	   "%s -e reads code points and writes a Punycode string.\n"
	   "%s -d reads a Punycode string and writes code points.\n"
	   "\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"
	   "Although the specification allows Punycode strings to contain\n"
	   "any characters from the ASCII repertoire, this test code\n"
	   "supports only the printable characters, and needs the Punycode\n"
	   "string to be followed by a newline.\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 overflow[] = "arithmetic overflow\n";
static const char io_error[] = "I/O error\n";

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

static const char print_ascii[] = "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n" "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n" " !\"#$%&'()*+,-./" "0123456789:;<=>?" "\0x40"	/* at sign */
  "ABCDEFGHIJKLMNO"
  "PQRSTUVWXYZ[\\]^_" "`abcdefghijklmno" "pqrstuvwxyz{|}~\n";

int
main (int argc, char **argv)
{
  enum punycode_status status;
  int r;
  size_t input_length, output_length, j;
  unsigned char case_flags[unicode_max_length];

  setlocale (LC_ALL, "");

  if (argc != 2)
    usage (argv);
  if (argv[1][0] != '-')
    usage (argv);
  if (argv[1][2] != 0)
    usage (argv);

  if (argv[1][1] == 'e')
    {
      uint32_t input[unicode_max_length];
      unsigned long codept;
      char output[ace_max_length + 1], uplus[3];
      int c;

      /* 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 > (uint32_t) - 1)
	    {
	      fail (invalid_input);
	    }

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

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

	  input[input_length++] = codept;
	}

      /* Encode: */

      output_length = ace_max_length;
      status = punycode_encode (input_length, input, case_flags,
				&output_length, output);
      if (status == punycode_bad_input)
	fail (invalid_input);
      if (status == punycode_big_output)
	fail (too_big);
      if (status 

GNU Libidn

Table of Contents

GNU Libidn

1 Introduction

1.1 Getting Started

1.2 Features

1.3 Library Overview

1.4 Supported Platforms

1.5 Getting help

1.6 Commercial Support

1.7 Downloading and Installing

1.7.1 Installing under Windows

1.8 Bug Reports

1.9 Contributing

2 Preparation

2.1 Header

2.2 Initialization

2.3 Version Check

stringprep_check_version

2.4 Building the source

2.5 Autoconf tests

3 Utility Functions

3.1 Header file stringprep.h

3.2 Unicode Encoding Transformation

stringprep_unichar_to_utf8

stringprep_utf8_to_unichar

stringprep_ucs4_to_utf8

stringprep_utf8_to_ucs4

3.3 Unicode Normalization

stringprep_ucs4_nfkc_normalize

stringprep_utf8_nfkc_normalize

3.4 Character Set Conversion

stringprep_locale_charset

stringprep_convert

stringprep_locale_to_utf8

stringprep_utf8_to_locale

4 Stringprep Functions

4.1 Header file stringprep.h

4.2 Defining A Stringprep Profile

4.3 Control Flags

4.4 Core Functions

stringprep_4i

stringprep_4zi

stringprep

stringprep_profile

4.5 Error Handling

stringprep_strerror

4.6 Stringprep Profile Macros

5 Punycode Functions

5.1 Header file punycode.h

5.2 Unicode Code Point Data Type

5.3 Core Functions

punycode_encode

punycode_decode

5.4 Error Handling

punycode_strerror

6 IDNA Functions

6.1 Header file idna.h

6.2 Control Flags

6.3 Prefix String

6.4 Core Functions

idna_to_ascii_4i

idna_to_unicode_44i

6.5 Simplified ToASCII Interface

idna_to_ascii_4z

idna_to_ascii_8z

idna_to_ascii_lz

6.6 Simplified ToUnicode Interface

idna_to_unicode_4z4z

idna_to_unicode_8z4z

idna_to_unicode_8z8z

idna_to_unicode_8zlz

idna_to_unicode_lzlz

6.7 Error Handling

idna_strerror

7 TLD Functions

7.1 Header file tld.h

7.2 Core Functions

tld_check_4t

tld_check_4tz

3.1 Header file `stringprep.h`

4.1 Header file `stringprep.h`

5.1 Header file `punycode.h`

6.1 Header file `idna.h`

7.1 Header file `tld.h`

8.1 Header file `pr29.h`