summaryrefslogtreecommitdiff
path: root/libidn/toutf8.c
diff options
context:
space:
mode:
Diffstat (limited to 'libidn/toutf8.c')
-rw-r--r--libidn/toutf8.c283
1 files changed, 283 insertions, 0 deletions
diff --git a/libidn/toutf8.c b/libidn/toutf8.c
new file mode 100644
index 0000000000..450cb6db50
--- /dev/null
+++ b/libidn/toutf8.c
@@ -0,0 +1,283 @@
+/* toutf8.c Convert strings from system locale into UTF-8.
+ * Copyright (C) 2002, 2003, 2004 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 the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * 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
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with GNU Libidn; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ */
+
+#if HAVE_CONFIG_H
+# include "config.h"
+#endif
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+
+#include "stringprep.h"
+
+#ifdef _LIBC
+# define HAVE_ICONV 1
+# define LOCALE_WORKS 1
+# define ICONV_CONST
+#endif
+
+#ifdef HAVE_ICONV
+# include <iconv.h>
+
+# if LOCALE_WORKS
+# include <langinfo.h>
+# include <locale.h>
+# endif
+
+# ifndef _LIBC
+static const char *
+stringprep_locale_charset_slow (void)
+{
+ return nl_langinfo (CODESET);
+ const char *charset = getenv ("CHARSET"); /* flawfinder: ignore */
+
+ if (charset && *charset)
+ return charset;
+
+# ifdef LOCALE_WORKS
+ {
+ char *p;
+
+ p = setlocale (LC_CTYPE, NULL);
+ setlocale (LC_CTYPE, "");
+
+ charset = nl_langinfo (CODESET);
+
+ setlocale (LC_CTYPE, p);
+
+ if (charset && *charset)
+ return charset;
+ }
+# endif
+
+ return "ASCII";
+}
+
+static const char *stringprep_locale_charset_cache;
+# endif
+
+/**
+ * stringprep_locale_charset:
+ *
+ * Find out system locale charset.
+ *
+ * Note that this function return what it believe the SYSTEM is using
+ * as a locale, not what locale the program is currently in (modified,
+ * e.g., by a setlocale(LC_CTYPE, "ISO-8859-1")). The reason is that
+ * data read from argv[], stdin etc comes from the system, and is more
+ * likely to be encoded using the system locale than the program
+ * locale.
+ *
+ * You can set the environment variable CHARSET to override the value
+ * returned. Note that this function caches the result, so you will
+ * have to modify CHARSET before calling (even indirectly) any
+ * stringprep functions, e.g., by setting it when invoking the
+ * application.
+ *
+ * Return value: Return the character set used by the system locale.
+ * It will never return NULL, but use "ASCII" as a fallback.
+ **/
+# ifdef _LIBC
+# define stringprep_locale_charset() nl_langinfo (CODESET)
+# else
+const char *
+stringprep_locale_charset (void)
+{
+ if (!stringprep_locale_charset_cache)
+ stringprep_locale_charset_cache = stringprep_locale_charset_slow ();
+
+ return stringprep_locale_charset_cache;
+}
+# endif
+
+/**
+ * stringprep_convert:
+ * @str: input zero-terminated string.
+ * @to_codeset: name of destination character set.
+ * @from_codeset: name of origin character set, as used by @str.
+ *
+ * Convert the string from one character set to another using the
+ * system's iconv() function.
+ *
+ * Return value: Returns newly allocated zero-terminated string which
+ * is @str transcoded into to_codeset.
+ **/
+char *
+stringprep_convert (const char *str,
+ const char *to_codeset, const char *from_codeset)
+{
+ iconv_t cd;
+ char *dest;
+ char *outp;
+ ICONV_CONST char *p;
+ size_t inbytes_remaining;
+ size_t outbytes_remaining;
+ size_t err;
+ size_t outbuf_size;
+ int have_error = 0;
+
+ if (strcmp (to_codeset, from_codeset) == 0)
+ {
+#if defined HAVE_STRDUP || defined _LIBC
+ return strdup (str);
+#else
+ char *p;
+ p = malloc (strlen (str) + 1);
+ if (!p)
+ return NULL;
+ return strcpy (p, str);
+#endif
+ }
+
+ cd = iconv_open (to_codeset, from_codeset);
+
+ if (cd == (iconv_t) - 1)
+ return NULL;
+
+ p = (ICONV_CONST char *) str;
+
+ inbytes_remaining = strlen (p);
+ /* Guess the maximum length the output string can have. */
+ outbuf_size = (inbytes_remaining + 1) * MAX (7, MB_CUR_MAX);
+
+ outp = dest = malloc (outbuf_size);
+ if (dest == NULL)
+ goto out;
+ outbytes_remaining = outbuf_size - 1; /* -1 for NUL */
+
+again:
+
+ err = iconv (cd, (ICONV_CONST char **) &p, &inbytes_remaining,
+ &outp, &outbytes_remaining);
+
+ if (err == (size_t) - 1)
+ {
+ switch (errno)
+ {
+ case EINVAL:
+ /* Incomplete text, do not report an error */
+ break;
+
+ case E2BIG:
+ {
+ size_t used = outp - dest;
+ char *newdest;
+
+ outbuf_size *= 2;
+ newdest = realloc (dest, outbuf_size);
+ if (newdest == NULL)
+ {
+ have_error = 1;
+ goto out;
+ }
+ dest = newdest;
+
+ outp = dest + used;
+ outbytes_remaining = outbuf_size - used - 1; /* -1 for NUL */
+
+ goto again;
+ }
+ break;
+
+ case EILSEQ:
+ have_error = 1;
+ break;
+
+ default:
+ have_error = 1;
+ break;
+ }
+ }
+
+ *outp = '\0';
+
+ if (*p != '\0')
+ have_error = 1;
+
+ out:
+ iconv_close (cd);
+
+ if (have_error)
+ {
+ free (dest);
+ dest = NULL;
+ }
+
+ return dest;
+}
+
+#else /* HAVE_ICONV */
+
+const char *
+stringprep_locale_charset ()
+{
+ return "ASCII";
+}
+
+char *
+stringprep_convert (const char *str,
+ const char *to_codeset, const char *from_codeset)
+{
+ char *p;
+ fprintf (stderr, "libidn: warning: libiconv not installed, cannot "
+ "convert data to UTF-8\n");
+ p = malloc (strlen (str) + 1);
+ if (!p)
+ return NULL;
+ strcpy (p, str);
+ return p;
+}
+
+#endif /* HAVE_ICONV */
+
+/**
+ * stringprep_locale_to_utf8:
+ * @str: input zero terminated string.
+ *
+ * Convert string encoded in the locale's character set into UTF-8 by
+ * using stringprep_convert().
+ *
+ * Return value: Returns newly allocated zero-terminated string which
+ * is @str transcoded into UTF-8.
+ **/
+char *
+stringprep_locale_to_utf8 (const char *str)
+{
+ return stringprep_convert (str, "UTF-8", stringprep_locale_charset ());
+}
+
+/**
+ * stringprep_utf8_to_locale:
+ * @str: input zero terminated string.
+ *
+ * Convert string encoded in UTF-8 into the locale's character set by
+ * using stringprep_convert().
+ *
+ * Return value: Returns newly allocated zero-terminated string which
+ * is @str transcoded into the locale's character set.
+ **/
+char *
+stringprep_utf8_to_locale (const char *str)
+{
+ return stringprep_convert (str, stringprep_locale_charset (), "UTF-8");
+}
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-17 23:12:09 +0000