summaryrefslogtreecommitdiff
path: root/Master/tlpkg/tlperl/lib/utf8.pm
diff options
context:
space:
mode:
Diffstat (limited to 'Master/tlpkg/tlperl/lib/utf8.pm')
-rw-r--r--Master/tlpkg/tlperl/lib/utf8.pm61
1 files changed, 31 insertions, 30 deletions
diff --git a/Master/tlpkg/tlperl/lib/utf8.pm b/Master/tlpkg/tlperl/lib/utf8.pm
index 1d6992ccf03..6a979f147b3 100644
--- a/Master/tlpkg/tlperl/lib/utf8.pm
+++ b/Master/tlpkg/tlperl/lib/utf8.pm
@@ -2,11 +2,10 @@ package utf8;
$utf8::hint_bits = 0x00800000;
-our $VERSION = '1.10';
+our $VERSION = '1.13_01';
sub import {
$^H |= $utf8::hint_bits;
- $enc{caller()} = $_[1] if $_[1];
}
sub unimport {
@@ -29,22 +28,22 @@ utf8 - Perl pragma to enable/disable UTF-8 (or UTF-EBCDIC) in source code
=head1 SYNOPSIS
- use utf8;
- no utf8;
+ use utf8;
+ no utf8;
- # Convert the internal representation of a Perl scalar to/from UTF-8.
+ # Convert the internal representation of a Perl scalar to/from UTF-8.
- $num_octets = utf8::upgrade($string);
- $success = utf8::downgrade($string[, FAIL_OK]);
+ $num_octets = utf8::upgrade($string);
+ $success = utf8::downgrade($string[, $fail_ok]);
- # Change each character of a Perl scalar to/from a series of
- # characters that represent the UTF-8 bytes of each original character.
+ # Change each character of a Perl scalar to/from a series of
+ # characters that represent the UTF-8 bytes of each original character.
- utf8::encode($string); # "\x{100}" becomes "\xc4\x80"
- utf8::decode($string); # "\xc4\x80" becomes "\x{100}"
+ utf8::encode($string); # "\x{100}" becomes "\xc4\x80"
+ utf8::decode($string); # "\xc4\x80" becomes "\x{100}"
- $flag = utf8::is_utf8(STRING); # since Perl 5.8.1
- $flag = utf8::valid(STRING);
+ $flag = utf8::is_utf8($string); # since Perl 5.8.1
+ $flag = utf8::valid($string);
=head1 DESCRIPTION
@@ -96,11 +95,11 @@ C<no utf8;>.
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.
+you should not say that unless you really want to have UTF-8 source code.
=over 4
-=item * $num_octets = utf8::upgrade($string)
+=item * C<$num_octets = utf8::upgrade($string)>
Converts in-place the internal representation of the string from an octet
sequence in the native encoding (Latin-1 or EBCDIC) to I<UTF-X>. The
@@ -115,7 +114,7 @@ B<Note that this function does not handle arbitrary encodings.>
Therefore Encode is recommended for the general purposes; see also
L<Encode>.
-=item * $success = utf8::downgrade($string[, FAIL_OK])
+=item * C<$success = utf8::downgrade($string[, $fail_ok])>
Converts in-place the internal representation of the string from
I<UTF-X> to the equivalent octet sequence in the native encoding (Latin-1
@@ -127,7 +126,7 @@ that the substr() or length() function works with the usually faster
byte algorithm.
Fails if the original I<UTF-X> sequence cannot be represented in the
-native 8 bit encoding. On failure dies or, if the value of C<FAIL_OK> is
+native 8 bit encoding. On failure dies or, if the value of I<$fail_ok> is
true, returns false.
Returns true on success.
@@ -136,7 +135,7 @@ B<Note that this function does not handle arbitrary encodings.>
Therefore Encode is recommended for the general purposes; see also
L<Encode>.
-=item * utf8::encode($string)
+=item * C<utf8::encode($string)>
Converts in-place the character sequence to the corresponding octet
sequence in I<UTF-X>. That is, every (possibly wide) character gets
@@ -144,16 +143,17 @@ replaced with a sequence of one or more characters that represent the
individual I<UTF-X> bytes of the character. The UTF8 flag is turned off.
Returns nothing.
- my $a = "\x{100}"; # $a contains one character, with ord 0x100
- utf8::encode($a); # $a contains two characters, with ords 0xc4 and 0x80
+ my $a = "\x{100}"; # $a contains one character, with ord 0x100
+ utf8::encode($a); # $a contains two characters, with ords 0xc4 and
+ # 0x80
B<Note that this function does not handle arbitrary encodings.>
Therefore Encode is recommended for the general purposes; see also
L<Encode>.
-=item * $success = utf8::decode($string)
+=item * C<$success = utf8::decode($string)>
-Attempts to convert in-place the octet sequence in I<UTF-X> to the
+Attempts to convert in-place the octet sequence encoded as I<UTF-X> to the
corresponding character sequence. That is, it replaces each sequence of
characters in the string whose ords represent a valid UTF-X byte
sequence, with the corresponding single character. The UTF-8 flag is
@@ -161,24 +161,25 @@ turned on only if the source string contains multiple-byte I<UTF-X>
characters. If I<$string> is invalid as I<UTF-X>, returns false;
otherwise returns true.
- my $a = "\xc4\x80"; # $a contains two characters, with ords 0xc4 and 0x80
+ my $a = "\xc4\x80"; # $a contains two characters, with ords
+ # 0xc4 and 0x80
utf8::decode($a); # $a contains one character, with ord 0x100
B<Note that this function does not handle arbitrary encodings.>
Therefore Encode is recommended for the general purposes; see also
L<Encode>.
-=item * $flag = utf8::is_utf8(STRING)
+=item * C<$flag = utf8::is_utf8($string)>
-(Since Perl 5.8.1) Test whether STRING is encoded internally in UTF-8.
-Functionally the same as Encode::is_utf8().
+(Since Perl 5.8.1) Test whether I<$string> is marked internally as encoded in
+UTF-8. Functionally the same as Encode::is_utf8().
-=item * $flag = utf8::valid(STRING)
+=item * C<$flag = utf8::valid($string)>
-[INTERNAL] Test whether STRING is in a consistent state regarding
+[INTERNAL] Test whether I<$string> is in a consistent state regarding
UTF-8. Will return true if it is well-formed UTF-8 and has the UTF-8 flag
-on B<or> if STRING is held as bytes (both these states are 'consistent').
-Main reason for this routine is to allow Perl's testsuite to check
+on B<or> if I<$string> is held as bytes (both these states are 'consistent').
+Main reason for this routine is to allow Perl's test suite to check
that operations have left strings in a consistent state. You most
probably want to use utf8::is_utf8() instead.