Gecko [ edgpens.lpkmn.gov.my ]

Name	Size	Permission
App	[ DIR ]	drwxrwxrwx
Archive	[ DIR ]	drwxrwxrwx
Attribute	[ DIR ]	drwxrwxrwx
B	[ DIR ]	drwxrwxrwx
CORE	[ DIR ]	drwxrwxrwx
CPAN	[ DIR ]	drwxrwxrwx
Carp	[ DIR ]	drwxrwxrwx
Class	[ DIR ]	drwxrwxrwx
Compress	[ DIR ]	drwxrwxrwx
Config	[ DIR ]	drwxrwxrwx
DBM_Filter	[ DIR ]	drwxrwxrwx
Data	[ DIR ]	drwxrwxrwx
Devel	[ DIR ]	drwxrwxrwx
Digest	[ DIR ]	drwxrwxrwx
Encode	[ DIR ]	drwxrwxrwx
Exporter	[ DIR ]	drwxrwxrwx
ExtUtils	[ DIR ]	drwxrwxrwx
File	[ DIR ]	drwxrwxrwx
Filter	[ DIR ]	drwxrwxrwx
Getopt	[ DIR ]	drwxrwxrwx
HTML	[ DIR ]	drwxrwxrwx
HTTP	[ DIR ]	drwxrwxrwx
Hash	[ DIR ]	drwxrwxrwx
I18N	[ DIR ]	drwxrwxrwx
IO	[ DIR ]	drwxrwxrwx
IPC	[ DIR ]	drwxrwxrwx
JSON	[ DIR ]	drwxrwxrwx
List	[ DIR ]	drwxrwxrwx
Locale	[ DIR ]	drwxrwxrwx
MIME	[ DIR ]	drwxrwxrwx
Math	[ DIR ]	drwxrwxrwx
Memoize	[ DIR ]	drwxrwxrwx
Module	[ DIR ]	drwxrwxrwx
Net	[ DIR ]	drwxrwxrwx
Params	[ DIR ]	drwxrwxrwx
Parse	[ DIR ]	drwxrwxrwx
Perl	[ DIR ]	drwxrwxrwx
PerlIO	[ DIR ]	drwxrwxrwx
Pod	[ DIR ]	drwxrwxrwx
Scalar	[ DIR ]	drwxrwxrwx
Search	[ DIR ]	drwxrwxrwx
Sub	[ DIR ]	drwxrwxrwx
Sys	[ DIR ]	drwxrwxrwx
TAP	[ DIR ]	drwxrwxrwx
Term	[ DIR ]	drwxrwxrwx
Test	[ DIR ]	drwxrwxrwx
Test2	[ DIR ]	drwxrwxrwx
Text	[ DIR ]	drwxrwxrwx
Thread	[ DIR ]	drwxrwxrwx
Tie	[ DIR ]	drwxrwxrwx
Time	[ DIR ]	drwxrwxrwx
Unicode	[ DIR ]	drwxrwxrwx
User	[ DIR ]	drwxrwxrwx
Win32API	[ DIR ]	drwxrwxrwx
auto	[ DIR ]	drwxrwxrwx
autodie	[ DIR ]	drwxrwxrwx
encoding	[ DIR ]	drwxrwxrwx
overload	[ DIR ]	drwxrwxrwx
pods	[ DIR ]	drwxrwxrwx
threads	[ DIR ]	drwxrwxrwx
unicore	[ DIR ]	drwxrwxrwx
version	[ DIR ]	drwxrwxrwx
warnings	[ DIR ]	drwxrwxrwx
.packlist	90.13 KB	-rw-rw-rw-
AnyDBM_File.pm	2.56 KB	-rw-rw-rw-
AutoLoader.pm	15.43 KB	-rw-rw-rw-
AutoSplit.pm	19.18 KB	-rw-rw-rw-
B.pm	28.78 KB	-rw-rw-rw-
Benchmark.pm	30.3 KB	-rw-rw-rw-
CORE.pod	3.11 KB	-rw-rw-rw-
CPAN.pm	142.98 KB	-rw-rw-rw-
Carp.pm	35.12 KB	-rw-rw-rw-
Config.pm	3.3 KB	-rw-rw-rw-
Config.pod	258.26 KB	-rw-rw-rw-
Config_git.pl	421 B	-rw-rw-rw-
Config_heavy.pl	37.27 KB	-rw-rw-rw-
Cwd.pm	21.43 KB	-rw-rw-rw-
DB.pm	18.48 KB	-rw-rw-rw-
DBM_Filter.pm	14.05 KB	-rw-rw-rw-
Digest.pm	10.45 KB	-rw-rw-rw-
DirHandle.pm	2.04 KB	-rw-rw-rw-
Dumpvalue.pm	17.25 KB	-rw-rw-rw-
DynaLoader.pm	25.33 KB	-rw-rw-rw-
Encode.pm	31.33 KB	-rw-rw-rw-
English.pm	4.65 KB	-rw-rw-rw-
Env.pm	5.39 KB	-rw-rw-rw-
Errno.pm	92.68 KB	-rw-rw-rw-
Exporter.pm	18.36 KB	-rw-rw-rw-
Fatal.pm	57.64 KB	-rw-rw-rw-
Fcntl.pm	3.95 KB	-rw-rw-rw-
FileCache.pm	5.42 KB	-rw-rw-rw-
FileHandle.pm	6.63 KB	-rw-rw-rw-
FindBin.pm	4.45 KB	-rw-rw-rw-
GDBM_File.pm	2.03 KB	-rw-rw-rw-
IO.pm	1.42 KB	-rw-rw-rw-
Internals.pod	2.51 KB	-rw-rw-rw-
Memoize.pm	35.34 KB	-rw-rw-rw-
NDBM_File.pm	3.01 KB	-rw-rw-rw-
NEXT.pm	18.54 KB	-rw-rw-rw-
O.pm	4.19 KB	-rw-rw-rw-
ODBM_File.pm	2.9 KB	-rw-rw-rw-
Opcode.pm	15.57 KB	-rw-rw-rw-
POSIX.pm	19.87 KB	-rw-rw-rw-
POSIX.pod	78.81 KB	-rw-rw-rw-
PerlIO.pm	14.1 KB	-rw-rw-rw-
SDBM_File.pm	3.72 KB	-rw-rw-rw-
Safe.pm	24.5 KB	-rw-rw-rw-
SelectSaver.pm	1.05 KB	-rw-rw-rw-
SelfLoader.pm	17.27 KB	-rw-rw-rw-
Socket.pm	36.19 KB	-rw-rw-rw-
Storable.pm	48.75 KB	-rw-rw-rw-
Symbol.pm	4.69 KB	-rw-rw-rw-
Test.pm	29.34 KB	-rw-rw-rw-
Test2.pm	6.24 KB	-rw-rw-rw-
Thread.pm	8.09 KB	-rw-rw-rw-
UNIVERSAL.pm	6.44 KB	-rw-rw-rw-
Win32.pm	57.28 KB	-rw-rw-rw-
Win32CORE.pm	1.27 KB	-rw-rw-rw-
XSLoader.pm	11.37 KB	-rw-rw-rw-
_charnames.pm	33.35 KB	-rw-rw-rw-
attributes.pm	15.97 KB	-rw-rw-rw-
autodie.pm	12.23 KB	-rw-rw-rw-
autouse.pm	4.14 KB	-rw-rw-rw-
base.pm	10.7 KB	-rw-rw-rw-
bigint.pm	22.85 KB	-rw-rw-rw-
bignum.pm	20.64 KB	-rw-rw-rw-
bigrat.pm	15.78 KB	-rw-rw-rw-
blib.pm	2.01 KB	-rw-rw-rw-
bytes.pm	3.65 KB	-rw-rw-rw-
bytes_heavy.pl	758 B	-rw-rw-rw-
charnames.pm	20.44 KB	-rw-rw-rw-
constant.pm	14.38 KB	-rw-rw-rw-
deprecate.pm	4.5 KB	-rw-rw-rw-
diagnostics.pm	18.85 KB	-rw-rw-rw-
dumpvar.pl	15.19 KB	-rw-rw-rw-
encoding.pm	22.41 KB	-rw-rw-rw-
experimental.pm	7.39 KB	-rw-rw-rw-
feature.pm	18.56 KB	-rw-rw-rw-
fields.pm	9.25 KB	-rw-rw-rw-
filetest.pm	3.91 KB	-rw-rw-rw-
if.pm	3.53 KB	-rw-rw-rw-
integer.pm	3.18 KB	-rw-rw-rw-
less.pm	3.13 KB	-rw-rw-rw-
lib.pm	6.2 KB	-rw-rw-rw-
locale.pm	4.74 KB	-rw-rw-rw-
meta_notation.pm	2.07 KB	-rw-rw-rw-
mro.pm	9.66 KB	-rw-rw-rw-
ok.pm	967 B	-rw-rw-rw-
open.pm	8.31 KB	-rw-rw-rw-
ops.pm	997 B	-rw-rw-rw-
overload.pm	52.05 KB	-rw-rw-rw-
overloading.pm	1.77 KB	-rw-rw-rw-
parent.pm	2.64 KB	-rw-rw-rw-
perl5db.pl	309.69 KB	-rw-rw-rw-
perlfaq.pm	77 B	-rw-rw-rw-
perllocal.pod	104.69 KB	-rw-rw-rw-
re.pm	24.8 KB	-rw-rw-rw-
sigtrap.pm	8.53 KB	-rw-rw-rw-
sort.pm	3.82 KB	-rw-rw-rw-
strict.pm	4.63 KB	-rw-rw-rw-
subs.pm	901 B	-rw-rw-rw-
threads.pm	37.06 KB	-rw-rw-rw-
utf8.pm	10.18 KB	-rw-rw-rw-
vars.pm	2.4 KB	-rw-rw-rw-
version.pm	1.93 KB	-rw-rw-rw-
version.pod	9.6 KB	-rw-rw-rw-
vmsish.pm	4.21 KB	-rw-rw-rw-
warnings.pm	49.35 KB	-rw-rw-rw-

Code Editor : utf8.pm

package utf8;

$utf8::hint_bits = 0x00800000;

our $VERSION = '1.22';

sub import {
    $^H |= $utf8::hint_bits;
}

sub unimport {
    $^H &= ~$utf8::hint_bits;
}

sub AUTOLOAD {
    goto &$AUTOLOAD if defined &$AUTOLOAD;
    require Carp;
    Carp::croak("Undefined subroutine $AUTOLOAD called");
}

1;
__END__

=head1 NAME

utf8 - Perl pragma to enable/disable UTF-8 (or UTF-EBCDIC) in source code

=head1 SYNOPSIS

use utf8;
 no utf8;

# Convert the internal representation of a Perl scalar to/from UTF-8.

$num_octets = utf8::upgrade($string);
 $success    = utf8::downgrade($string[, $fail_ok]);

# Change each character of a Perl scalar to/from a series of
 # characters that represent the UTF-8 bytes of each original character.

utf8::encode($string);  # "\x{100}"  becomes "\xc4\x80"
 utf8::decode($string);  # "\xc4\x80" becomes "\x{100}"

# Convert a code point from the platform native character set to
 # Unicode, and vice-versa.
 $unicode = utf8::native_to_unicode(ord('A')); # returns 65 on both
                                               # ASCII and EBCDIC
                                               # platforms
 $native = utf8::unicode_to_native(65);        # returns 65 on ASCII
                                               # platforms; 193 on
                                               # EBCDIC

$flag = utf8::is_utf8($string); # since Perl 5.8.1
 $flag = utf8::valid($string);

=head1 DESCRIPTION

The C<use utf8> pragma tells the Perl parser to allow UTF-8 in the
program text in the current lexical scope.  The C<no utf8> pragma tells Perl
to switch back to treating the source text as literal bytes in the current
lexical scope.  (On EBCDIC platforms, technically it is allowing UTF-EBCDIC,
and not UTF-8, but this distinction is academic, so in this document the term
UTF-8 is used to mean both).

B<Do not use this pragma for anything else than telling Perl that your
script is written in UTF-8.> The utility functions described below are
directly usable without C<use utf8;>.

Because it is not possible to reliably tell UTF-8 from native 8 bit
encodings, you need either a Byte Order Mark at the beginning of your
source code, or C<use utf8;>, to instruct perl.

When UTF-8 becomes the standard source format, this pragma will
effectively become a no-op.

See also the effects of the C<-C> switch and its cousin, the
C<PERL_UNICODE> environment variable, in L<perlrun>.

Enabling the C<utf8> pragma has the following effect:

=over 4

=item *

Bytes in the source text that are not in the ASCII character set will be
treated as being part of a literal UTF-8 sequence.  This includes most
literals such as identifier names, string constants, and constant
regular expression patterns.

=back

Note that if you have non-ASCII, non-UTF-8 bytes in your script (for example
embedded Latin-1 in your string literals), C<use utf8> will be unhappy.  If
you want to have such bytes under C<use utf8>, you can disable this pragma
until the end the block (or file, if at top level) by C<no utf8;>.

=head2 Utility functions

The following functions are defined in the C<utf8::> package by the
Perl core.  You do not need to say C<use utf8> to use these and in fact
you should not say that unless you really want to have UTF-8 source code.

=over 4

=item * C<$num_octets = utf8::upgrade($string)>

(Since Perl v5.8.0)
Converts in-place the internal representation of the string from an octet
sequence in the native encoding (Latin-1 or EBCDIC) to UTF-8. The
logical character sequence itself is unchanged.  If I<$string> is already
upgraded, then this is a no-op. Returns the
number of octets necessary to represent the string as UTF-8.

If your code needs to be compatible with versions of perl without
C<use feature 'unicode_strings';>, you can force Unicode semantics on
a given string:

# force unicode semantics for $string without the
  # "unicode_strings" feature
  utf8::upgrade($string);

For example:

# without explicit or implicit use feature 'unicode_strings'
  my $x = "\xDF";    # LATIN SMALL LETTER SHARP S
  $x =~ /ss/i;       # won't match
  my $y = uc($x);    # won't convert
  utf8::upgrade($x);
  $x =~ /ss/i;       # matches
  my $z = uc($x);    # converts to "SS"

B<Note that this function does not handle arbitrary encodings>;
use L<Encode> instead.

=item * C<$success = utf8::downgrade($string[, $fail_ok])>

(Since Perl v5.8.0)
Converts in-place the internal representation of the string from UTF-8 to the
equivalent octet sequence in the native encoding (Latin-1 or EBCDIC). The
logical character sequence itself is unchanged. If I<$string> is already
stored as native 8 bit, then this is a no-op.  Can be used to make sure that
the UTF-8 flag is off, e.g. when you want to make sure that the substr() or
length() function works with the usually faster byte algorithm.

Fails if the original UTF-8 sequence cannot be represented in the
native 8 bit encoding. On failure dies or, if the value of I<$fail_ok> is
true, returns false.

Returns true on success.

If your code expects an octet sequence this can be used to validate
that you've received one:

# throw an exception if not representable as octets
  utf8::downgrade($string)

# or do your own error handling
  utf8::downgrade($string, 1) or die "string must be octets";

B<Note that this function does not handle arbitrary encodings>;
use L<Encode> instead.

=item * C<utf8::encode($string)>

(Since Perl v5.8.0)
Converts in-place the character sequence to the corresponding octet
sequence in Perl's extended UTF-8. That is, every (possibly wide) character
gets replaced with a sequence of one or more characters that represent the
individual UTF-8 bytes of the character.  The UTF8 flag is turned off.
Returns nothing.

my $x = "\x{100}"; # $x contains one character, with ord 0x100
 utf8::encode($x);  # $x contains two characters, with ords (on
                    # ASCII platforms) 0xc4 and 0x80.  On EBCDIC
                    # 1047, this would instead be 0x8C and 0x41.

Similar to:

use Encode;
  $x = Encode::encode("utf8", $x);

B<Note that this function does not handle arbitrary encodings>;
use L<Encode> instead.

=item * C<$success = utf8::decode($string)>

(Since Perl v5.8.0)
Attempts to convert in-place the octet sequence encoded in Perl's extended
UTF-8 to the corresponding character sequence. That is, it replaces each
sequence of characters in the string whose ords represent a valid (extended)
UTF-8 byte sequence, with the corresponding single character.  The UTF-8 flag
is turned on only if the source string contains multiple-byte UTF-8
characters.  If I<$string> is invalid as extended UTF-8, returns false;
otherwise returns true.

my $x = "\xc4\x80"; # $x contains two characters, with ords
                     # 0xc4 and 0x80
 utf8::decode($x);   # On ASCII platforms, $x contains one char,
                     # with ord 0x100.   Since these bytes aren't
                     # legal UTF-EBCDIC, on EBCDIC platforms, $x is
                     # unchanged and the function returns FALSE.

B<Note that this function does not handle arbitrary encodings>;
use L<Encode> instead.

=item * C<$unicode = utf8::native_to_unicode($code_point)>

(Since Perl v5.8.0)
This takes an unsigned integer (which represents the ordinal number of a
character (or a code point) on the platform the program is being run on) and
returns its Unicode equivalent value.  Since ASCII platforms natively use the
Unicode code points, this function returns its input on them.  On EBCDIC
platforms it converts from EBCDIC to Unicode.

A meaningless value will currently be returned if the input is not an unsigned
integer.

Since Perl v5.22.0, calls to this function are optimized out on ASCII
platforms, so there is no performance hit in using it there.

=item * C<$native = utf8::unicode_to_native($code_point)>

(Since Perl v5.8.0)
This is the inverse of C<utf8::native_to_unicode()>, converting the other
direction.  Again, on ASCII platforms, this returns its input, but on EBCDIC
platforms it will find the native platform code point, given any Unicode one.

A meaningless value will currently be returned if the input is not an unsigned
integer.

Since Perl v5.22.0, calls to this function are optimized out on ASCII
platforms, so there is no performance hit in using it there.

=item * C<$flag = utf8::is_utf8($string)>

(Since Perl 5.8.1)  Test whether I<$string> is marked internally as encoded in
UTF-8.  Functionally the same as C<Encode::is_utf8($string)>.

Typically only necessary for debugging and testing, if you need to
dump the internals of an SV, L<Devel::Peek's|Devel::Peek> Dump()
provides more detail in a compact form.

If you still think you need this outside of debugging, testing or
dealing with filenames, you should probably read L<perlunitut> and
L<perlunifaq/What is "the UTF8 flag"?>.

Don't use this flag as a marker to distinguish character and binary
data: that should be decided for each variable when you write your
code.

To force unicode semantics in code portable to perl 5.8 and 5.10, call
C<utf8::upgrade($string)> unconditionally.

=item * C<$flag = utf8::valid($string)>

[INTERNAL] Test whether I<$string> is in a consistent state regarding
UTF-8.  Will return true if it is well-formed Perl extended UTF-8 and has the
UTF-8 flag
on B<or> if I<$string> is held as bytes (both these states are 'consistent').
The main reason for this routine is to allow Perl's test suite to check
that operations have left strings in a consistent state.

=back

C<utf8::encode> is like C<utf8::upgrade>, but the UTF8 flag is
cleared.  See L<perlunicode>, and the C API
functions C<L<sv_utf8_upgrade|perlapi/sv_utf8_upgrade>>,
C<L<perlapi/sv_utf8_downgrade>>, C<L<perlapi/sv_utf8_encode>>,
and C<L<perlapi/sv_utf8_decode>>, which are wrapped by the Perl functions
C<utf8::upgrade>, C<utf8::downgrade>, C<utf8::encode> and
C<utf8::decode>.  Also, the functions C<utf8::is_utf8>, C<utf8::valid>,
C<utf8::encode>, C<utf8::decode>, C<utf8::upgrade>, and C<utf8::downgrade> are
actually internal, and thus always available, without a C<require utf8>
statement.

=head1 BUGS

Some filesystems may not support UTF-8 file names, or they may be supported
incompatibly with Perl.  Therefore UTF-8 names that are visible to the
filesystem, such as module names may not work.

=head1 SEE ALSO

L<perlunitut>, L<perluniintro>, L<perlrun>, L<bytes>, L<perlunicode>

=cut

${this.title}

Code Editor : utf8.pm