summaryrefslogtreecommitdiff
path: root/lib/localcharset.c
diff options
context:
space:
mode:
Diffstat (limited to 'lib/localcharset.c')
-rw-r--r--lib/localcharset.c482
1 files changed, 266 insertions, 216 deletions
diff --git a/lib/localcharset.c b/lib/localcharset.c
index 93da1707..29de23d6 100644
--- a/lib/localcharset.c
+++ b/lib/localcharset.c
@@ -1,6 +1,6 @@
/* Determine a canonical name for the current locale's character encoding.
- Copyright (C) 2000-2006, 2008-2009 Free Software Foundation, Inc.
+ Copyright (C) 2000-2006, 2008-2010 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
@@ -23,6 +23,7 @@
/* Specification. */
#include "localcharset.h"
+#include <fcntl.h>
#include <stddef.h>
#include <stdio.h>
#include <string.h>
@@ -44,6 +45,7 @@
#endif
#if !defined WIN32_NATIVE
+# include <unistd.h>
# if HAVE_LANGINFO_CODESET
# include <langinfo.h>
# else
@@ -75,6 +77,11 @@
# 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) == '\\')
@@ -117,192 +124,219 @@ get_charset_aliases (void)
if (cp == NULL)
{
#if !(defined DARWIN7 || defined VMS || defined WIN32_NATIVE || defined __CYGWIN__)
- FILE *fp;
const char *dir;
const char *base = "charset.alias";
char *file_name;
/* Make it possible to override the charset.alias location. This is
- necessary for running the testsuite before "make install". */
+ necessary for running the testsuite before "make install". */
dir = getenv ("CHARSETALIASDIR");
if (dir == NULL || dir[0] == '\0')
- dir = relocate (LIBDIR);
+ dir = relocate (LIBDIR);
/* Concatenate dir and base into freshly allocated file_name. */
{
- size_t dir_len = strlen (dir);
- size_t base_len = strlen (base);
- int add_slash = (dir_len > 0 && !ISSLASH (dir[dir_len - 1]));
- file_name = (char *) malloc (dir_len + add_slash + base_len + 1);
- if (file_name != NULL)
- {
- memcpy (file_name, dir, dir_len);
- if (add_slash)
- file_name[dir_len] = DIRECTORY_SEPARATOR;
- memcpy (file_name + dir_len + add_slash, base, base_len + 1);
- }
+ size_t dir_len = strlen (dir);
+ size_t base_len = strlen (base);
+ int add_slash = (dir_len > 0 && !ISSLASH (dir[dir_len - 1]));
+ file_name = (char *) malloc (dir_len + add_slash + base_len + 1);
+ if (file_name != NULL)
+ {
+ memcpy (file_name, dir, dir_len);
+ if (add_slash)
+ file_name[dir_len] = DIRECTORY_SEPARATOR;
+ memcpy (file_name + dir_len + add_slash, base, base_len + 1);
+ }
}
- if (file_name == NULL || (fp = fopen (file_name, "r")) == NULL)
- /* Out of memory or file not found, treat it as empty. */
- cp = "";
+ 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 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 (file_name != NULL)
- free (file_name);
+ {
+ 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
+ {
+ FILE *fp;
+
+ fp = fdopen (fd, "r");
+ if (fp == NULL)
+ {
+ /* Out of memory. Treat the file as empty. */
+ close (fd);
+ cp = "";
+ }
+ else
+ {
+ /* 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;
+ }
+ }
+ }
+
+ 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. */
+ 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";
+ "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. */
+ sources of many GNU packages, simply inline the aliases here. */
/* The list of encodings is taken from the OpenVMS 7.3-1 documentation
- "Compaq C Run-Time Library Reference Manual for OpenVMS systems"
- section 10.7 "Handling Different Character Sets". */
+ "Compaq C Run-Time Library Reference Manual for OpenVMS systems"
+ section 10.7 "Handling Different Character Sets". */
cp = "ISO8859-1" "\0" "ISO-8859-1" "\0"
- "ISO8859-2" "\0" "ISO-8859-2" "\0"
- "ISO8859-5" "\0" "ISO-8859-5" "\0"
- "ISO8859-7" "\0" "ISO-8859-7" "\0"
- "ISO8859-8" "\0" "ISO-8859-8" "\0"
- "ISO8859-9" "\0" "ISO-8859-9" "\0"
- /* Japanese */
- "eucJP" "\0" "EUC-JP" "\0"
- "SJIS" "\0" "SHIFT_JIS" "\0"
- "DECKANJI" "\0" "DEC-KANJI" "\0"
- "SDECKANJI" "\0" "EUC-JP" "\0"
- /* Chinese */
- "eucTW" "\0" "EUC-TW" "\0"
- "DECHANYU" "\0" "DEC-HANYU" "\0"
- "DECHANZI" "\0" "GB2312" "\0"
- /* Korean */
- "DECKOREAN" "\0" "EUC-KR" "\0";
+ "ISO8859-2" "\0" "ISO-8859-2" "\0"
+ "ISO8859-5" "\0" "ISO-8859-5" "\0"
+ "ISO8859-7" "\0" "ISO-8859-7" "\0"
+ "ISO8859-8" "\0" "ISO-8859-8" "\0"
+ "ISO8859-9" "\0" "ISO-8859-9" "\0"
+ /* Japanese */
+ "eucJP" "\0" "EUC-JP" "\0"
+ "SJIS" "\0" "SHIFT_JIS" "\0"
+ "DECKANJI" "\0" "DEC-KANJI" "\0"
+ "SDECKANJI" "\0" "EUC-JP" "\0"
+ /* Chinese */
+ "eucTW" "\0" "EUC-TW" "\0"
+ "DECHANYU" "\0" "DEC-HANYU" "\0"
+ "DECHANZI" "\0" "GB2312" "\0"
+ /* Korean */
+ "DECKOREAN" "\0" "EUC-KR" "\0";
# endif
# if defined WIN32_NATIVE || defined __CYGWIN__
/* To avoid the troubles of installing a separate file in the same
- directory as the DLL and of retrieving the DLL's directory at
- runtime, simply inline the aliases here. */
+ directory as the DLL and of retrieving the DLL's directory at
+ runtime, simply inline the aliases here. */
cp = "CP936" "\0" "GBK" "\0"
- "CP1361" "\0" "JOHAB" "\0"
- "CP20127" "\0" "ASCII" "\0"
- "CP20866" "\0" "KOI8-R" "\0"
- "CP20936" "\0" "GB2312" "\0"
- "CP21866" "\0" "KOI8-RU" "\0"
- "CP28591" "\0" "ISO-8859-1" "\0"
- "CP28592" "\0" "ISO-8859-2" "\0"
- "CP28593" "\0" "ISO-8859-3" "\0"
- "CP28594" "\0" "ISO-8859-4" "\0"
- "CP28595" "\0" "ISO-8859-5" "\0"
- "CP28596" "\0" "ISO-8859-6" "\0"
- "CP28597" "\0" "ISO-8859-7" "\0"
- "CP28598" "\0" "ISO-8859-8" "\0"
- "CP28599" "\0" "ISO-8859-9" "\0"
- "CP28605" "\0" "ISO-8859-15" "\0"
- "CP38598" "\0" "ISO-8859-8" "\0"
- "CP51932" "\0" "EUC-JP" "\0"
- "CP51936" "\0" "GB2312" "\0"
- "CP51949" "\0" "EUC-KR" "\0"
- "CP51950" "\0" "EUC-TW" "\0"
- "CP54936" "\0" "GB18030" "\0"
- "CP65001" "\0" "UTF-8" "\0";
+ "CP1361" "\0" "JOHAB" "\0"
+ "CP20127" "\0" "ASCII" "\0"
+ "CP20866" "\0" "KOI8-R" "\0"
+ "CP20936" "\0" "GB2312" "\0"
+ "CP21866" "\0" "KOI8-RU" "\0"
+ "CP28591" "\0" "ISO-8859-1" "\0"
+ "CP28592" "\0" "ISO-8859-2" "\0"
+ "CP28593" "\0" "ISO-8859-3" "\0"
+ "CP28594" "\0" "ISO-8859-4" "\0"
+ "CP28595" "\0" "ISO-8859-5" "\0"
+ "CP28596" "\0" "ISO-8859-6" "\0"
+ "CP28597" "\0" "ISO-8859-7" "\0"
+ "CP28598" "\0" "ISO-8859-8" "\0"
+ "CP28599" "\0" "ISO-8859-9" "\0"
+ "CP28605" "\0" "ISO-8859-15" "\0"
+ "CP38598" "\0" "ISO-8859-8" "\0"
+ "CP51932" "\0" "EUC-JP" "\0"
+ "CP51936" "\0" "GB2312" "\0"
+ "CP51949" "\0" "EUC-KR" "\0"
+ "CP51950" "\0" "EUC-TW" "\0"
+ "CP54936" "\0" "GB18030" "\0"
+ "CP65001" "\0" "UTF-8" "\0";
# endif
#endif
@@ -335,7 +369,7 @@ locale_charset (void)
codeset = nl_langinfo (CODESET);
# ifdef __CYGWIN__
- /* Cygwin 2006 does not have locales. nl_langinfo (CODESET) always
+ /* Cygwin 1.5.x does not have locales. nl_langinfo (CODESET) always
returns "US-ASCII". As long as this is not fixed, return the suffix
of the locale name from the environment variables (if present) or
the codepage as a number. */
@@ -346,36 +380,46 @@ locale_charset (void)
locale = getenv ("LC_ALL");
if (locale == NULL || locale[0] == '\0')
- {
- locale = getenv ("LC_CTYPE");
- if (locale == NULL || locale[0] == '\0')
- locale = getenv ("LANG");
- }
+ {
+ locale = getenv ("LC_CTYPE");
+ if (locale == NULL || locale[0] == '\0')
+ locale = getenv ("LANG");
+ }
if (locale != NULL && locale[0] != '\0')
- {
- /* If the locale name contains an encoding after the dot, return
- it. */
- const char *dot = strchr (locale, '.');
-
- if (dot != NULL)
- {
- const char *modifier;
-
- dot++;
- /* Look for the possible @... trailer and remove it, if any. */
- modifier = strchr (dot, '@');
- if (modifier == NULL)
- return dot;
- if (modifier - dot < sizeof (buf))
- {
- memcpy (buf, dot, modifier - dot);
- buf [modifier - dot] = '\0';
- return buf;
- }
- }
- }
-
- /* Woe32 has a function returning the locale's codepage as a number. */
+ {
+ /* If the locale name contains an encoding after the dot, return
+ it. */
+ const char *dot = strchr (locale, '.');
+
+ if (dot != NULL)
+ {
+ const char *modifier;
+
+ dot++;
+ /* Look for the possible @... trailer and remove it, if any. */
+ modifier = strchr (dot, '@');
+ if (modifier == NULL)
+ return dot;
+ if (modifier - dot < sizeof (buf))
+ {
+ memcpy (buf, dot, modifier - dot);
+ buf [modifier - dot] = '\0';
+ return buf;
+ }
+ }
+ }
+
+ /* Woe32 has a function returning the locale's codepage as a number:
+ GetACP(). This encoding is used by Cygwin, unless the user has set
+ the environment variable CYGWIN=codepage:oem (which very few people
+ do).
+ Output directed to console windows needs to be converted (to
+ GetOEMCP() if the console is using a raster font, or to
+ GetConsoleOutputCP() if it is using a TrueType font). Cygwin does
+ this conversion transparently (see winsup/cygwin/fhandler_console.cc),
+ converting to GetConsoleOutputCP(). This leads to correct results,
+ except when SetConsoleOutputCP has been called and a raster font is
+ in use. */
sprintf (buf, "CP%u", GetACP ());
codeset = buf;
}
@@ -397,11 +441,11 @@ locale_charset (void)
{
locale = getenv ("LC_ALL");
if (locale == NULL || locale[0] == '\0')
- {
- locale = getenv ("LC_CTYPE");
- if (locale == NULL || locale[0] == '\0')
- locale = getenv ("LANG");
- }
+ {
+ locale = getenv ("LC_CTYPE");
+ if (locale == NULL || locale[0] == '\0')
+ locale = getenv ("LANG");
+ }
}
/* On some old systems, one used to set locale = "iso8859_1". On others,
@@ -415,7 +459,13 @@ locale_charset (void)
static char buf[2 + 10 + 1];
- /* Woe32 has a function returning the locale's codepage as a number. */
+ /* Woe32 has a function returning the locale's codepage as a number:
+ GetACP().
+ When the output goes to a console window, it needs to be provided in
+ GetOEMCP() encoding if the console is using a raster font, or in
+ GetConsoleOutputCP() encoding if it is using a TrueType font.
+ But in GUI programs and for output sent to files and pipes, GetACP()
+ encoding is the best bet. */
sprintf (buf, "CP%u", GetACP ());
codeset = buf;
@@ -433,7 +483,7 @@ locale_charset (void)
{
locale = getenv ("LC_CTYPE");
if (locale == NULL || locale[0] == '\0')
- locale = getenv ("LANG");
+ locale = getenv ("LANG");
}
if (locale != NULL && locale[0] != '\0')
{
@@ -441,21 +491,21 @@ locale_charset (void)
const char *dot = strchr (locale, '.');
if (dot != NULL)
- {
- const char *modifier;
-
- dot++;
- /* Look for the possible @... trailer and remove it, if any. */
- modifier = strchr (dot, '@');
- if (modifier == NULL)
- return dot;
- if (modifier - dot < sizeof (buf))
- {
- memcpy (buf, dot, modifier - dot);
- buf [modifier - dot] = '\0';
- return buf;
- }
- }
+ {
+ const char *modifier;
+
+ dot++;
+ /* Look for the possible @... trailer and remove it, if any. */
+ modifier = strchr (dot, '@');
+ if (modifier == NULL)
+ return dot;
+ if (modifier - dot < sizeof (buf))
+ {
+ memcpy (buf, dot, modifier - dot);
+ buf [modifier - dot] = '\0';
+ return buf;
+ }
+ }
/* Resolve through the charset.alias file. */
codeset = locale;
@@ -464,12 +514,12 @@ locale_charset (void)
{
/* OS/2 has a function returning the locale's codepage as a number. */
if (DosQueryCp (sizeof (cp), cp, &cplen))
- codeset = "";
+ codeset = "";
else
- {
- sprintf (buf, "CP%u", cp[0]);
- codeset = buf;
- }
+ {
+ sprintf (buf, "CP%u", cp[0]);
+ codeset = buf;
+ }
}
#endif
@@ -483,10 +533,10 @@ locale_charset (void)
*aliases != '\0';
aliases += strlen (aliases) + 1, aliases += strlen (aliases) + 1)
if (strcmp (codeset, aliases) == 0
- || (aliases[0] == '*' && aliases[1] == '\0'))
+ || (aliases[0] == '*' && aliases[1] == '\0'))
{
- codeset = aliases + strlen (aliases) + 1;
- break;
+ codeset = aliases + strlen (aliases) + 1;
+ break;
}
/* Don't return an empty string. GNU libc and GNU libiconv interpret