.\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.16)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  \*(C+ will
.\" give a nicer C++.  Capital omega is used to do unbreakable dashes and
.\" therefore won't be available.  \*(C` and \*(C' expand to `' in nroff,
.\" nothing in troff, for use with C<>.
.tr \(*W-
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\"
.\" If the F register is turned on, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.ie \nF \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    nr % 0
.    rr F
.\}
.el \{\
.    de IX
..
.\}
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "bytes 3perl"
.TH bytes 3perl "2010-12-30" "perl v5.14.2" "Perl Programmers Reference Guide"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.SH "NAME"
bytes \- Perl pragma to force byte semantics rather than character semantics
.SH "NOTICE"
.IX Header "NOTICE"
This pragma reflects early attempts to incorporate Unicode into perl and
has since been superseded. It breaks encapsulation (i.e. it exposes the
innards of how the perl executable currently happens to store a string),
and use of this module for anything other than debugging purposes is
strongly discouraged. If you feel that the functions here within might be
useful for your application, this possibly indicates a mismatch between
your mental model of Perl Unicode and the current reality. In that case,
you may wish to read some of the perl Unicode documentation:
perluniintro, perlunitut, perlunifaq and perlunicode.
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 8
\&    use bytes;
\&    ... chr(...);       # or bytes::chr
\&    ... index(...);     # or bytes::index
\&    ... length(...);    # or bytes::length
\&    ... ord(...);       # or bytes::ord
\&    ... rindex(...);    # or bytes::rindex
\&    ... substr(...);    # or bytes::substr
\&    no bytes;
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
The \f(CW\*(C`use bytes\*(C'\fR pragma disables character semantics for the rest of the
lexical scope in which it appears.  \f(CW\*(C`no bytes\*(C'\fR can be used to reverse
the effect of \f(CW\*(C`use bytes\*(C'\fR within the current lexical scope.
.PP
Perl normally assumes character semantics in the presence of character
data (i.e. data that has come from a source that has been marked as
being of a particular character encoding). When \f(CW\*(C`use bytes\*(C'\fR is in
effect, the encoding is temporarily ignored, and each string is treated
as a series of bytes.
.PP
As an example, when Perl sees \f(CW\*(C`$x = chr(400)\*(C'\fR, it encodes the character
in \s-1UTF\-8\s0 and stores it in \f(CW$x\fR. Then it is marked as character data, so,
for instance, \f(CW\*(C`length $x\*(C'\fR returns \f(CW1\fR. However, in the scope of the
\&\f(CW\*(C`bytes\*(C'\fR pragma, \f(CW$x\fR is treated as a series of bytes \- the bytes that make
up the \s-1UTF8\s0 encoding \- and \f(CW\*(C`length $x\*(C'\fR returns \f(CW2\fR:
.PP
.Vb 8
\&    $x = chr(400);
\&    print "Length is ", length $x, "\en";     # "Length is 1"
\&    printf "Contents are %vd\en", $x;         # "Contents are 400"
\&    { 
\&        use bytes; # or "require bytes; bytes::length()"
\&        print "Length is ", length $x, "\en"; # "Length is 2"
\&        printf "Contents are %vd\en", $x;     # "Contents are 198.144"
\&    }
.Ve
.PP
\&\fIchr()\fR, \fIord()\fR, \fIsubstr()\fR, \fIindex()\fR and \fIrindex()\fR behave similarly.
.PP
For more on the implications and differences between character
semantics and byte semantics, see perluniintro and perlunicode.
.SH "LIMITATIONS"
.IX Header "LIMITATIONS"
\&\fIbytes::substr()\fR does not work as an \fIlvalue()\fR.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
perluniintro, perlunicode, utf8