1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
|
package encoding;
use Encode;
sub import {
my ($class, $name) = @_;
$name = $ENV{PERL_ENCODING} if @_ < 2;
$name = "latin1" unless defined $name;
my $enc = find_encoding($name);
unless (defined $enc) {
require Carp;
Carp::croak "Unknown encoding '$name'";
}
${^ENCODING} = $enc;
}
=pod
=head1 NAME
encoding - pragma to control the conversion of legacy data into Unicode
=head1 SYNOPSIS
use encoding "iso 8859-7";
# The \xDF of ISO 8859-7 (Greek) is \x{3af} in Unicode.
$a = "\xDF";
$b = "\x{100}";
printf "%#x\n", ord($a); # will print 0x3af, not 0xdf
$c = $a . $b;
# $c will be "\x{3af}\x{100}", not "\x{df}\x{100}".
# chr() is affected, and ...
print "mega\n" if ord(chr(0xdf)) == 0x3af;
# ... ord() is affected by the encoding pragma ...
print "tera\n" if ord(pack("C", 0xdf)) == 0x3af;
# but pack/unpack are not affected, in case you still
# want back to your native encoding
print "peta\n" if unpack("C", (pack("C", 0xdf))) == 0xdf;
=head1 DESCRIPTION
Normally when legacy 8-bit data is converted to Unicode the data is
expected to be Latin-1 (or EBCDIC in EBCDIC platforms). With the
encoding pragma you can change this default.
The pragma is a per script, not a per block lexical. Only the last
C<use encoding> matters, and it affects B<the whole script>.
If no encoding is specified, the environment variable L<PERL_ENCODING>
is consulted. If that fails, "latin1" (ISO 8859-1) is assumed. If no
encoding can be found, C<Unknown encoding '...'> error will be thrown.
=head1 KNOWN PROBLEMS
Literals in regular expressions are not affected by this pragma.
They very probably should.
=head1 SEE ALSO
L<perlunicode>, L<Encode>
=cut
1;
|
