Skip to content

Commit

Permalink
parse: do not escape all non-ascii bytes
Browse files Browse the repository at this point in the history
g_strescape will transform utf-8 strings in a sequence of escaped octal
numbers in form of a string. That happens because g_strescape will
escape the range from 0x7f to 0xff.

For example, "áéí" will become "\\303\\241\\303\\251\\303\\255". Pure
ASCII strings are not affected by it.

Add all the range 0x7f-0xff to the exception list.
  • Loading branch information
daniloegea committed Jul 3, 2024
1 parent 2945ea3 commit 2fda0a0
Show file tree
Hide file tree
Showing 2 changed files with 63 additions and 1 deletion.
14 changes: 13 additions & 1 deletion src/parse.c
Original file line number Diff line number Diff line change
Expand Up @@ -59,8 +59,20 @@
* Quotes are escaped at configuration generation time as needed, as they might be part of passwords for example.
* Escaping backslashes in the parser affects "netplan set" as it will always escape \'s from
* the input and update YAMLs with all the \'s escaped again.
*
* g_strescape will also escape all the non-ascii chars in the range 0x7f-0xff. This affects non-ascii
* strings and will break utf-8 strings for example. So we add the entire range to the list of exceptions.
*/
static char* STRESCAPE_EXCEPTIONS = "\"\\";
static char* STRESCAPE_EXCEPTIONS =
"\"\\"
"\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91"
"\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3"
"\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5"
"\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
"\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9"
"\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb"
"\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd"
"\xfe\xff";

STATIC gboolean
insert_kv_into_hash(void *key, void *value, void *hash);
Expand Down
50 changes: 50 additions & 0 deletions tests/ctests/test_netplan_parser.c
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
#include <stddef.h>
#include <setjmp.h>
#include <sys/stat.h>
#include <sys/mman.h>

#include <cmocka.h>
#include <yaml.h>
Expand Down Expand Up @@ -383,6 +384,54 @@ test_parser_flags_ignore_errors(__unused void** state)
rmdir(tempdir);
}

void
test_parse_utf8_characters(__unused void** state)
{
NetplanState *np_state = NULL;
int fd;
int size;
int res;

char* yaml =
"network:\n"
" version: 2\n"
" wifis:\n"
" wlan0:\n"
" access-points:\n"
" \"áéíóúÁÉÍÓÚ\":\n"
" password: \"áéíóúÁÉÍÓÚ\"\n";

char* expected =
"network:\n"
" version: 2\n"
" wifis:\n"
" wlan0:\n"
" access-points:\n"
" \"áéíóúÁÉÍÓÚ\":\n"
" auth:\n"
" key-management: \"psk\"\n"
" password: \"áéíóúÁÉÍÓÚ\"\n";

np_state = load_string_to_netplan_state(yaml);

fd = memfd_create("netplan-tests", 0);

netplan_state_dump_yaml(np_state, fd, NULL);

size = lseek(fd, 0, SEEK_CUR) + 1;
yaml = malloc(size);
memset(yaml, 0, size);
lseek(fd, 0, SEEK_SET);
res = read(fd, yaml, size - 1);
assert_true(res > 0);

assert_string_equal(yaml, expected);

netplan_state_clear(&np_state);
close(fd);
free(yaml);
}

int
setup(__unused void** state)
{
Expand Down Expand Up @@ -415,6 +464,7 @@ main()
cmocka_unit_test(test_parser_flags),
cmocka_unit_test(test_parser_flags_bad_flags),
cmocka_unit_test(test_parser_flags_ignore_errors),
cmocka_unit_test(test_parse_utf8_characters),
};

return cmocka_run_group_tests(tests, setup, tear_down);
Expand Down

0 comments on commit 2fda0a0

Please sign in to comment.