| line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
|
1
|
|
|
|
|
|
|
package Locale::Maketext::Utils::Phrase::Norm::Grapheme; |
|
2
|
|
|
|
|
|
|
|
|
3
|
4
|
|
|
4
|
|
2241
|
use strict; |
|
|
4
|
|
|
|
|
38
|
|
|
|
4
|
|
|
|
|
128
|
|
|
4
|
4
|
|
|
4
|
|
16
|
use warnings; |
|
|
4
|
|
|
|
|
28
|
|
|
|
4
|
|
|
|
|
691
|
|
|
5
|
|
|
|
|
|
|
|
|
6
|
|
|
|
|
|
|
sub normalize_maketext_string { |
|
7
|
75
|
|
|
75
|
0
|
209
|
my ($filter) = @_; |
|
8
|
|
|
|
|
|
|
|
|
9
|
75
|
|
|
|
|
230
|
my $string_sr = $filter->get_string_sr(); |
|
10
|
|
|
|
|
|
|
|
|
11
|
75
|
100
|
|
|
|
167
|
if ( ${$string_sr} =~ s/((?:\\x[0-9a-fA-F]{2})+)/[comment,grapheme “$1”]/ ) { |
|
|
75
|
|
|
|
|
420
|
|
|
12
|
8
|
|
|
|
|
30
|
$filter->add_violation('Contains grapheme notation'); |
|
13
|
|
|
|
|
|
|
} |
|
14
|
|
|
|
|
|
|
|
|
15
|
75
|
|
|
|
|
233
|
return $filter->return_value; |
|
16
|
|
|
|
|
|
|
} |
|
17
|
|
|
|
|
|
|
|
|
18
|
|
|
|
|
|
|
1; |
|
19
|
|
|
|
|
|
|
|
|
20
|
|
|
|
|
|
|
__END__ |
|
21
|
|
|
|
|
|
|
|
|
22
|
|
|
|
|
|
|
=encoding utf-8 |
|
23
|
|
|
|
|
|
|
|
|
24
|
|
|
|
|
|
|
=head1 Normalization |
|
25
|
|
|
|
|
|
|
|
|
26
|
|
|
|
|
|
|
Graphemes are not very human readable and require interpolation, we can avoid both issues by not using them! |
|
27
|
|
|
|
|
|
|
|
|
28
|
|
|
|
|
|
|
=head2 Rationale |
|
29
|
|
|
|
|
|
|
|
|
30
|
|
|
|
|
|
|
This helps give consistency, clarity, and simplicity. |
|
31
|
|
|
|
|
|
|
|
|
32
|
|
|
|
|
|
|
If we parse a string and find 'Commencing compilation \xe2\x80\xa6' then we have to interpolate that string into 'Commencing compilation …' before we can look it up to see if it exists in a hash. |
|
33
|
|
|
|
|
|
|
|
|
34
|
|
|
|
|
|
|
Graphemes also add a layer of complexity that hinders translators and thus makes room for lower quality translations. |
|
35
|
|
|
|
|
|
|
|
|
36
|
|
|
|
|
|
|
Developers have it slightly better in that they’ll recognize it but it still requires effort to figure out what it is exactly and to determine what sequence they need for a given character. |
|
37
|
|
|
|
|
|
|
|
|
38
|
|
|
|
|
|
|
You can simply use the character itself or a bracket notation method for the handful of markup related or visually special characters |
|
39
|
|
|
|
|
|
|
|
|
40
|
|
|
|
|
|
|
=head1 possible violations |
|
41
|
|
|
|
|
|
|
|
|
42
|
|
|
|
|
|
|
If you get false positives then that only goes to help highlight how ambiguity adds to the reason to avoid non-bytes strings! |
|
43
|
|
|
|
|
|
|
|
|
44
|
|
|
|
|
|
|
=over 4 |
|
45
|
|
|
|
|
|
|
|
|
46
|
|
|
|
|
|
|
=item Contains grapheme notation |
|
47
|
|
|
|
|
|
|
|
|
48
|
|
|
|
|
|
|
A sequence of \xe2\x98\xba\xe2\x80\xa6 will be replaced w/ [comment,grapheme “\xe2\x98\xba\xe2\x80\xa6”] |
|
49
|
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
=back |
|
51
|
|
|
|
|
|
|
|
|
52
|
|
|
|
|
|
|
=head1 possible warnings |
|
53
|
|
|
|
|
|
|
|
|
54
|
|
|
|
|
|
|
None |
|
55
|
|
|
|
|
|
|
|
|
56
|
|
|
|
|
|
|
=head1 Entire filter only runs under extra filter |
|
57
|
|
|
|
|
|
|
|
|
58
|
|
|
|
|
|
|
See L<Locale::Maketext::Utils::Phrase::Norm/extra filters> for more details. |