/* Determine a canonical name for the current locale's character encoding.
- Copyright (C) 2000-2006, 2008 Free Software Foundation, Inc.
+ Copyright (C) 2000-2006, 2008-2009 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
/* Specification. */
#include "localcharset.h"
+#include <fcntl.h>
#include <stddef.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
+#if defined __APPLE__ && defined __MACH__ && HAVE_LANGINFO_CODESET
+# define DARWIN7 /* Darwin 7 or newer, i.e. MacOS X 10.3 or newer */
+#endif
+
#if defined _WIN32 || defined __WIN32__
# define WIN32_NATIVE
#endif
#endif
#if !defined WIN32_NATIVE
+# include <unistd.h>
# if HAVE_LANGINFO_CODESET
# include <langinfo.h>
# else
# include "configmake.h"
#endif
+/* Define O_NOFOLLOW to 0 on platforms where it does not exist. */
+#ifndef O_NOFOLLOW
+# define O_NOFOLLOW 0
+#endif
+
#if defined _WIN32 || defined __WIN32__ || defined __CYGWIN__ || defined __EMX__ || defined __DJGPP__
/* Win32, Cygwin, OS/2, DOS */
# define ISSLASH(C) ((C) == '/' || (C) == '\\')
cp = charset_aliases;
if (cp == NULL)
{
-#if !(defined VMS || defined WIN32_NATIVE || defined __CYGWIN__)
- FILE *fp;
+#if !(defined DARWIN7 || defined VMS || defined WIN32_NATIVE || defined __CYGWIN__)
const char *dir;
const char *base = "charset.alias";
char *file_name;
}
}
- if (file_name == NULL || (fp = fopen (file_name, "r")) == NULL)
- /* Out of memory or file not found, treat it as empty. */
+ if (file_name == NULL)
+ /* Out of memory. Treat the file as empty. */
cp = "";
else
{
- /* Parse the file's contents. */
- char *res_ptr = NULL;
- size_t res_size = 0;
-
- for (;;)
+ int fd;
+
+ /* Open the file. Reject symbolic links on platforms that support
+ O_NOFOLLOW. This is a security feature. Without it, an attacker
+ could retrieve parts of the contents (namely, the tail of the
+ first line that starts with "* ") of an arbitrary file by placing
+ a symbolic link to that file under the name "charset.alias" in
+ some writable directory and defining the environment variable
+ CHARSETALIASDIR to point to that directory. */
+ fd = open (file_name,
+ O_RDONLY | (HAVE_WORKING_O_NOFOLLOW ? O_NOFOLLOW : 0));
+ if (fd < 0)
+ /* File not found. Treat it as empty. */
+ cp = "";
+ else
{
- int c;
- char buf1[50+1];
- char buf2[50+1];
- size_t l1, l2;
- char *old_res_ptr;
-
- c = getc (fp);
- if (c == EOF)
- break;
- if (c == '\n' || c == ' ' || c == '\t')
- continue;
- if (c == '#')
- {
- /* Skip comment, to end of line. */
- do
- c = getc (fp);
- while (!(c == EOF || c == '\n'));
- if (c == EOF)
- break;
- continue;
- }
- ungetc (c, fp);
- if (fscanf (fp, "%50s %50s", buf1, buf2) < 2)
- break;
- l1 = strlen (buf1);
- l2 = strlen (buf2);
- old_res_ptr = res_ptr;
- if (res_size == 0)
+ FILE *fp;
+
+ fp = fdopen (fd, "r");
+ if (fp == NULL)
{
- res_size = l1 + 1 + l2 + 1;
- res_ptr = (char *) malloc (res_size + 1);
+ /* Out of memory. Treat the file as empty. */
+ close (fd);
+ cp = "";
}
else
{
- res_size += l1 + 1 + l2 + 1;
- res_ptr = (char *) realloc (res_ptr, res_size + 1);
+ /* Parse the file's contents. */
+ char *res_ptr = NULL;
+ size_t res_size = 0;
+
+ for (;;)
+ {
+ int c;
+ char buf1[50+1];
+ char buf2[50+1];
+ size_t l1, l2;
+ char *old_res_ptr;
+
+ c = getc (fp);
+ if (c == EOF)
+ break;
+ if (c == '\n' || c == ' ' || c == '\t')
+ continue;
+ if (c == '#')
+ {
+ /* Skip comment, to end of line. */
+ do
+ c = getc (fp);
+ while (!(c == EOF || c == '\n'));
+ if (c == EOF)
+ break;
+ continue;
+ }
+ ungetc (c, fp);
+ if (fscanf (fp, "%50s %50s", buf1, buf2) < 2)
+ break;
+ l1 = strlen (buf1);
+ l2 = strlen (buf2);
+ old_res_ptr = res_ptr;
+ if (res_size == 0)
+ {
+ res_size = l1 + 1 + l2 + 1;
+ res_ptr = (char *) malloc (res_size + 1);
+ }
+ else
+ {
+ res_size += l1 + 1 + l2 + 1;
+ res_ptr = (char *) realloc (res_ptr, res_size + 1);
+ }
+ if (res_ptr == NULL)
+ {
+ /* Out of memory. */
+ res_size = 0;
+ if (old_res_ptr != NULL)
+ free (old_res_ptr);
+ break;
+ }
+ strcpy (res_ptr + res_size - (l2 + 1) - (l1 + 1), buf1);
+ strcpy (res_ptr + res_size - (l2 + 1), buf2);
+ }
+ fclose (fp);
+ if (res_size == 0)
+ cp = "";
+ else
+ {
+ *(res_ptr + res_size) = '\0';
+ cp = res_ptr;
+ }
}
- if (res_ptr == NULL)
- {
- /* Out of memory. */
- res_size = 0;
- if (old_res_ptr != NULL)
- free (old_res_ptr);
- break;
- }
- strcpy (res_ptr + res_size - (l2 + 1) - (l1 + 1), buf1);
- strcpy (res_ptr + res_size - (l2 + 1), buf2);
}
- fclose (fp);
- if (res_size == 0)
- cp = "";
- else
- {
- *(res_ptr + res_size) = '\0';
- cp = res_ptr;
- }
- }
- if (file_name != NULL)
- free (file_name);
+ free (file_name);
+ }
#else
+# if defined DARWIN7
+ /* To avoid the trouble of installing a file that is shared by many
+ GNU packages -- many packaging systems have problems with this --,
+ simply inline the aliases here. */
+ cp = "ISO8859-1" "\0" "ISO-8859-1" "\0"
+ "ISO8859-2" "\0" "ISO-8859-2" "\0"
+ "ISO8859-4" "\0" "ISO-8859-4" "\0"
+ "ISO8859-5" "\0" "ISO-8859-5" "\0"
+ "ISO8859-7" "\0" "ISO-8859-7" "\0"
+ "ISO8859-9" "\0" "ISO-8859-9" "\0"
+ "ISO8859-13" "\0" "ISO-8859-13" "\0"
+ "ISO8859-15" "\0" "ISO-8859-15" "\0"
+ "KOI8-R" "\0" "KOI8-R" "\0"
+ "KOI8-U" "\0" "KOI8-U" "\0"
+ "CP866" "\0" "CP866" "\0"
+ "CP949" "\0" "CP949" "\0"
+ "CP1131" "\0" "CP1131" "\0"
+ "CP1251" "\0" "CP1251" "\0"
+ "eucCN" "\0" "GB2312" "\0"
+ "GB2312" "\0" "GB2312" "\0"
+ "eucJP" "\0" "EUC-JP" "\0"
+ "eucKR" "\0" "EUC-KR" "\0"
+ "Big5" "\0" "BIG5" "\0"
+ "Big5HKSCS" "\0" "BIG5-HKSCS" "\0"
+ "GBK" "\0" "GBK" "\0"
+ "GB18030" "\0" "GB18030" "\0"
+ "SJIS" "\0" "SHIFT_JIS" "\0"
+ "ARMSCII-8" "\0" "ARMSCII-8" "\0"
+ "PT154" "\0" "PT154" "\0"
+ /*"ISCII-DEV" "\0" "?" "\0"*/
+ "*" "\0" "UTF-8" "\0";
+# endif
+
# if defined VMS
/* To avoid the troubles of an extra file charset.alias_vms in the
sources of many GNU packages, simply inline the aliases here. */