VHD: Fix locale aware character encoding handling

ASCII is 7 bit only, which does not work in UTF-8 environments:
> failed to read parent name

Setup locale in vhd-util to parse LC_CTYPE and use the right codeset
when doing file name encoding and decoding.

Increase allocation for UTF-8 buffer as one UTF-16 character might use
twice as much space in UTF-8 (or more).

Don't check outbytesleft==0 as one UTF-8 characters get encoded into
1..8 bytes, so it's perfectly fine (and expected) for the output to have
remaining bytes left.

Test-case:
$ ./vhd-util create -n ä.vhd -s 1
$ ./vhd-util snapshot -n snap.vhd -p ä.vhd ; echo $?

See
<http://unix.stackexchange.com/questions/48689/effect-of-lang-on-terminal>
for more information about the details of handling the encoding right.

Signed-off-by: Philipp Hahn <hahn@univention.de>
Acked-by: Ian Campbell <ian.campbell@citrix.com>

diff --git a/tools/blktap2/vhd/lib/libvhd.c b/tools/blktap2/vhd/lib/libvhd.c
index 95eb5d66907e3e5cc138fe232964c677ee870f8b..1fd5b4eb9d17933e8a97ad63890ac0d7132cb84e 100644 (file)
--- a/tools/blktap2/vhd/lib/libvhd.c
+++ b/tools/blktap2/vhd/lib/libvhd.c
@@ -37,6 +37,7 @@
 #include <iconv.h>
 #include <sys/mman.h>
 #include <sys/stat.h>
+#include <langinfo.h>
 
 #include "libvhd.h"
 #include "relative-path.h"
@@ -1296,6 +1297,7 @@ vhd_macx_encode_location(char *name, char **out, int *outlen)
        size_t ibl, obl;
        char *uri, *uri_utf8, *uri_utf8p, *ret;
        const char *urip;
+       char *codeset;
 
        err     = 0;
        ret     = NULL;
@@ -1304,7 +1306,7 @@ vhd_macx_encode_location(char *name, char **out, int *outlen)
        len     = strlen(name) + strlen("file://");
 
        ibl     = len;
-       obl     = len;
+       obl     = len * 2;
 
        urip = uri = malloc(ibl + 1);
        uri_utf8 = uri_utf8p = malloc(obl);
@@ -1312,7 +1314,8 @@ vhd_macx_encode_location(char *name, char **out, int *outlen)
        if (!uri || !uri_utf8)
                return -ENOMEM;
 
-       cd = iconv_open("UTF-8", "ASCII");
+       codeset = nl_langinfo(CODESET);
+       cd = iconv_open("UTF-8", codeset);
        if (cd == (iconv_t)-1) {
                err = -errno;
                goto out;
@@ -1325,7 +1328,7 @@ vhd_macx_encode_location(char *name, char **out, int *outlen)
            (char **)
 #endif
            &urip, &ibl, &uri_utf8p, &obl) == (size_t)-1 ||
-           ibl || obl) {
+           ibl) {
                err = (errno ? -errno : -EIO);
                goto out;
        }
@@ -1357,6 +1360,7 @@ vhd_w2u_encode_location(char *name, char **out, int *outlen)
        size_t ibl, obl;
        char *uri, *uri_utf16, *uri_utf16p, *tmp, *ret;
        const char *urip;
+       char *codeset;
 
        err     = 0;
        ret     = NULL;
@@ -1404,7 +1408,8 @@ vhd_w2u_encode_location(char *name, char **out, int *outlen)
         * MICROSOFT_COMPAT
         * little endian unicode here 
         */
-       cd = iconv_open("UTF-16LE", "ASCII");
+       codeset = nl_langinfo(CODESET);
+       cd = iconv_open("UTF-16LE", codeset);
        if (cd == (iconv_t)-1) {
                err = -errno;
                goto out;
@@ -1415,7 +1420,7 @@ vhd_w2u_encode_location(char *name, char **out, int *outlen)
            (char **)
 #endif
            &urip, &ibl, &uri_utf16p, &obl) == (size_t)-1 ||
-           ibl || obl) {
+           ibl) {
                err = (errno ? -errno : -EIO);
                goto out;
        }
@@ -1447,11 +1452,13 @@ vhd_macx_decode_location(const char *in, char *out, int len)
        iconv_t cd;
        char *name;
        size_t ibl, obl;
+       char *codeset;
 
        name = out;
        ibl  = obl = len;
 
-       cd = iconv_open("ASCII", "UTF-8");
+       codeset = nl_langinfo(CODESET);
+       cd = iconv_open(codeset, "UTF-8");
        if (cd == (iconv_t)-1) 
                return NULL;
 
@@ -1479,11 +1486,13 @@ vhd_w2u_decode_location(const char *in, char *out, int len, char *utf_type)
        iconv_t cd;
        char *name, *tmp;
        size_t ibl, obl;
+       char *codeset;
 
        tmp = name = out;
        ibl = obl  = len;
 
-       cd = iconv_open("ASCII", utf_type);
+       codeset = nl_langinfo(CODESET);
+       cd = iconv_open(codeset, utf_type);
        if (cd == (iconv_t)-1) 
                return NULL;
 
@@ -2450,6 +2459,7 @@ vhd_initialize_header_parent_name(vhd_context_t *ctx, const char *parent_path)
        size_t ibl, obl;
        char *ppath, *dst;
        const char *pname;
+       char *codeset;
 
        err   = 0;
        pname = NULL;
@@ -2459,7 +2469,8 @@ vhd_initialize_header_parent_name(vhd_context_t *ctx, const char *parent_path)
         * MICROSOFT_COMPAT
         * big endian unicode here 
         */
-       cd = iconv_open(UTF_16BE, "ASCII");
+       codeset = nl_langinfo(CODESET);
+       cd = iconv_open(UTF_16BE, codeset);
        if (cd == (iconv_t)-1) {
                err = -errno;
                goto out;

diff --git a/tools/blktap2/vhd/vhd-util.c b/tools/blktap2/vhd/vhd-util.c
index 944a59e395dd0e8c2d52f2e615bb01433537adde..13f1835f37c9de692ec6608c8f024c46829869aa 100644 (file)
--- a/tools/blktap2/vhd/vhd-util.c
+++ b/tools/blktap2/vhd/vhd-util.c
@@ -28,6 +28,8 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <langinfo.h>
+#include <locale.h>
 
 #include "libvhd.h"
 #include "vhd-util.h"
@@ -114,6 +116,7 @@ main(int argc, char *argv[])
        if (setrlimit(RLIMIT_CORE, &rlim) < 0)
                fprintf(stderr, "setrlimit failed: %d\n", errno);
 #endif
+       setlocale(LC_CTYPE, "");
 
        ret = 0;