line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package XML::Char; |
2
|
|
|
|
|
|
|
|
3
|
2
|
|
|
2
|
|
33260
|
use utf8; |
|
2
|
|
|
|
|
4
|
|
|
2
|
|
|
|
|
12
|
|
4
|
|
|
|
|
|
|
|
5
|
|
|
|
|
|
|
=encoding UTF-8 |
6
|
|
|
|
|
|
|
|
7
|
|
|
|
|
|
|
=head1 NAME |
8
|
|
|
|
|
|
|
|
9
|
|
|
|
|
|
|
XML::Char - validate characters for XML |
10
|
|
|
|
|
|
|
|
11
|
|
|
|
|
|
|
=head1 SYNOPSIS |
12
|
|
|
|
|
|
|
|
13
|
|
|
|
|
|
|
use XML::Char; |
14
|
|
|
|
|
|
|
if (not XML::Char->valid("bell ".chr(7))) { |
15
|
|
|
|
|
|
|
die 'no way to store this string directly to XML'; |
16
|
|
|
|
|
|
|
} |
17
|
|
|
|
|
|
|
|
18
|
|
|
|
|
|
|
use utf8; |
19
|
|
|
|
|
|
|
use XML::Char; |
20
|
|
|
|
|
|
|
if (XML::Char->valid("UTF8 je pořádný peklo")) { |
21
|
|
|
|
|
|
|
print "fuf, we are fine\n"; |
22
|
|
|
|
|
|
|
} |
23
|
|
|
|
|
|
|
|
24
|
|
|
|
|
|
|
=head1 DESCRIPTION |
25
|
|
|
|
|
|
|
|
26
|
|
|
|
|
|
|
For me it was kind of a surprised to learn that C is a valid UTF-8 |
27
|
|
|
|
|
|
|
character. All of the 0-0x7F are... |
28
|
|
|
|
|
|
|
|
29
|
|
|
|
|
|
|
Emo: well it's not because that they are valid utf-8 characters that you have to expect XML to accept them |
30
|
|
|
|
|
|
|
|
31
|
|
|
|
|
|
|
Well of course not, now I know :-) |
32
|
|
|
|
|
|
|
|
33
|
|
|
|
|
|
|
L defines which characters XML processors MUST accept: |
34
|
|
|
|
|
|
|
|
35
|
|
|
|
|
|
|
[2] Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF] |
36
|
|
|
|
|
|
|
/* any Unicode character, excluding the surrogate blocks, FFFE, and FFFF. */ |
37
|
|
|
|
|
|
|
|
38
|
|
|
|
|
|
|
This module validates if a given string meets this criteria. In addition |
39
|
|
|
|
|
|
|
the string has to be a Perl UTF-8 string (C - see L). |
40
|
|
|
|
|
|
|
|
41
|
|
|
|
|
|
|
=cut |
42
|
|
|
|
|
|
|
|
43
|
2
|
|
|
2
|
|
89
|
use 5.006; |
|
2
|
|
|
|
|
5
|
|
|
2
|
|
|
|
|
65
|
|
44
|
2
|
|
|
2
|
|
7
|
use strict; |
|
2
|
|
|
|
|
6
|
|
|
2
|
|
|
|
|
54
|
|
45
|
2
|
|
|
2
|
|
6
|
use warnings; |
|
2
|
|
|
|
|
7
|
|
|
2
|
|
|
|
|
89
|
|
46
|
|
|
|
|
|
|
|
47
|
|
|
|
|
|
|
our $VERSION = '0.03'; |
48
|
|
|
|
|
|
|
|
49
|
2
|
|
|
2
|
|
900
|
use parent qw(DynaLoader); |
|
2
|
|
|
|
|
480
|
|
|
2
|
|
|
|
|
6
|
|
50
|
|
|
|
|
|
|
|
51
|
2
|
|
|
2
|
|
89
|
use Exporter 'import'; |
|
2
|
|
|
|
|
3
|
|
|
2
|
|
|
|
|
320
|
|
52
|
|
|
|
|
|
|
our @EXPORT_OK = qw( |
53
|
|
|
|
|
|
|
); |
54
|
|
|
|
|
|
|
|
55
|
|
|
|
|
|
|
__PACKAGE__->bootstrap; |
56
|
|
|
|
|
|
|
|
57
|
|
|
|
|
|
|
=head2 valid($value) |
58
|
|
|
|
|
|
|
|
59
|
|
|
|
|
|
|
Returns true or false if C<$value> consists of valid UTF-8 XML characters. |
60
|
|
|
|
|
|
|
|
61
|
|
|
|
|
|
|
=cut |
62
|
|
|
|
|
|
|
|
63
|
|
|
|
|
|
|
sub valid { |
64
|
26
|
|
|
26
|
1
|
20247
|
my ($self, $value); |
65
|
26
|
100
|
|
|
|
55
|
if (@_ < 2) { |
66
|
2
|
|
|
|
|
3
|
$self = __PACKAGE__; |
67
|
2
|
|
|
|
|
3
|
$value = shift @_; |
68
|
|
|
|
|
|
|
} |
69
|
|
|
|
|
|
|
else { |
70
|
24
|
|
|
|
|
28
|
$self = shift @_; |
71
|
24
|
|
|
|
|
25
|
$value = shift @_; |
72
|
|
|
|
|
|
|
} |
73
|
|
|
|
|
|
|
|
74
|
|
|
|
|
|
|
die 'bad usage' |
75
|
26
|
50
|
|
|
|
31
|
if not eval { $self->can('valid') }; |
|
26
|
|
|
|
|
132
|
|
76
|
|
|
|
|
|
|
|
77
|
|
|
|
|
|
|
# undef is valid |
78
|
26
|
100
|
|
|
|
60
|
return 1 |
79
|
|
|
|
|
|
|
if not defined $value; |
80
|
|
|
|
|
|
|
|
81
|
25
|
|
|
|
|
119
|
return _valid_xml_string($value); |
82
|
|
|
|
|
|
|
} |
83
|
|
|
|
|
|
|
|
84
|
|
|
|
|
|
|
1; |
85
|
|
|
|
|
|
|
|
86
|
|
|
|
|
|
|
__END__ |