forked from mirrors/nixpkgs
nixos/test-driver/Logger: Replace invalid UTF-8
Regression introduced by d84741a4bf
.
The mentioned commit actually is a good thing, because we now get the
output from the X session.
Unfortunately, for the i3wm test, the i3-config-wizard prints out the
raw keyboard symbols directly coming from xcb, so the output isn't
necessarily proper UTF-8.
As the XML::Writer already expects valid UTF-8 input, we assume that
everything that comes into sanitise() will be UTF-8 from the start. So
we just decode() it using FB_DEFAULT as the check argument so that
every invalid character is replaced by the unicode replacement
character:
https://en.wikipedia.org/wiki/Specials_(Unicode_block)#Replacement_character
We simply re-oncode it again afterwards and return it, so we should
always get out valid UTF-8 in the log XML.
For more information about FB_DEFAULT and FB_CROAK, have a look at:
http://search.cpan.org/~dankogai/Encode-2.84/Encode.pm#Handling_Malformed_Data
Signed-off-by: aszlig <aszlig@redmoonstudios.org>
This commit is contained in:
parent
8de756d4d1
commit
cb796ccd09
|
@ -3,6 +3,7 @@ package Logger;
|
|||
use strict;
|
||||
use Thread::Queue;
|
||||
use XML::Writer;
|
||||
use Encode qw(decode encode);
|
||||
|
||||
sub new {
|
||||
my ($class) = @_;
|
||||
|
@ -56,7 +57,8 @@ sub nest {
|
|||
sub sanitise {
|
||||
my ($s) = @_;
|
||||
$s =~ s/[[:cntrl:]\xff]//g;
|
||||
return $s;
|
||||
$s = decode('UTF-8', $s, Encode::FB_DEFAULT);
|
||||
return encode('UTF-8', $s, Encode::FB_CROAK);
|
||||
}
|
||||
|
||||
sub log {
|
||||
|
|
Loading…
Reference in a new issue