| 1 |
.\" -*- mode: troff; coding: utf-8 -*- |
| 2 |
.\" Automatically generated by Pod::Man 5.0102 (Pod::Simple 3.45) |
| 3 |
.\" |
| 4 |
.\" Standard preamble: |
| 5 |
.\" ======================================================================== |
| 6 |
.de Sp \" Vertical space (when we can't use .PP) |
| 7 |
.if t .sp .5v |
| 8 |
.if n .sp |
| 9 |
.. |
| 10 |
.de Vb \" Begin verbatim text |
| 11 |
.ft CW |
| 12 |
.nf |
| 13 |
.ne \\$1 |
| 14 |
.. |
| 15 |
.de Ve \" End verbatim text |
| 16 |
.ft R |
| 17 |
.fi |
| 18 |
.. |
| 19 |
.\" \*(C` and \*(C' are quotes in nroff, nothing in troff, for use with C<>. |
| 20 |
.ie n \{\ |
| 21 |
. ds C` "" |
| 22 |
. ds C' "" |
| 23 |
'br\} |
| 24 |
.el\{\ |
| 25 |
. ds C` |
| 26 |
. ds C' |
| 27 |
'br\} |
| 28 |
.\" |
| 29 |
.\" Escape single quotes in literal strings from groff's Unicode transform. |
| 30 |
.ie \n(.g .ds Aq \(aq |
| 31 |
.el .ds Aq ' |
| 32 |
.\" |
| 33 |
.\" If the F register is >0, we'll generate index entries on stderr for |
| 34 |
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index |
| 35 |
.\" entries marked with X<> in POD. Of course, you'll have to process the |
| 36 |
.\" output yourself in some meaningful fashion. |
| 37 |
.\" |
| 38 |
.\" Avoid warning from groff about undefined register 'F'. |
| 39 |
.de IX |
| 40 |
.. |
| 41 |
.nr rF 0 |
| 42 |
.if \n(.g .if rF .nr rF 1 |
| 43 |
.if (\n(rF:(\n(.g==0)) \{\ |
| 44 |
. if \nF \{\ |
| 45 |
. de IX |
| 46 |
. tm Index:\\$1\t\\n%\t"\\$2" |
| 47 |
.. |
| 48 |
. if !\nF==2 \{\ |
| 49 |
. nr % 0 |
| 50 |
. nr F 2 |
| 51 |
. \} |
| 52 |
. \} |
| 53 |
.\} |
| 54 |
.rr rF |
| 55 |
.\" ======================================================================== |
| 56 |
.\" |
| 57 |
.IX Title "bytes 3perl" |
| 58 |
.TH bytes 3perl 2025-11-16 "perl v5.40.1" "Perl Programmers Reference Guide" |
| 59 |
.\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 60 |
.\" way too many mistakes in technical documents. |
| 61 |
.if n .ad l |
| 62 |
.nh |
| 63 |
.SH NAME |
| 64 |
bytes \- Perl pragma to expose the individual bytes of characters |
| 65 |
.SH NOTICE |
| 66 |
.IX Header "NOTICE" |
| 67 |
Because the bytes pragma breaks encapsulation (i.e. it exposes the innards of |
| 68 |
how the perl executable currently happens to store a string), the byte values |
| 69 |
that result are in an unspecified encoding. |
| 70 |
.PP |
| 71 |
\&\fBUse of this module for anything other than debugging purposes is |
| 72 |
strongly discouraged.\fR If you feel that the functions here within |
| 73 |
might be useful for your application, this possibly indicates a |
| 74 |
mismatch between your mental model of Perl Unicode and the current |
| 75 |
reality. In that case, you may wish to read some of the perl Unicode |
| 76 |
documentation: perluniintro, perlunitut, perlunifaq and |
| 77 |
perlunicode. |
| 78 |
.SH SYNOPSIS |
| 79 |
.IX Header "SYNOPSIS" |
| 80 |
.Vb 8 |
| 81 |
\& use bytes; |
| 82 |
\& ... chr(...); # or bytes::chr |
| 83 |
\& ... index(...); # or bytes::index |
| 84 |
\& ... length(...); # or bytes::length |
| 85 |
\& ... ord(...); # or bytes::ord |
| 86 |
\& ... rindex(...); # or bytes::rindex |
| 87 |
\& ... substr(...); # or bytes::substr |
| 88 |
\& no bytes; |
| 89 |
.Ve |
| 90 |
.SH DESCRIPTION |
| 91 |
.IX Header "DESCRIPTION" |
| 92 |
Perl's characters are stored internally as sequences of one or more bytes. |
| 93 |
This pragma allows for the examination of the individual bytes that together |
| 94 |
comprise a character. |
| 95 |
.PP |
| 96 |
Originally the pragma was designed for the loftier goal of helping incorporate |
| 97 |
Unicode into Perl, but the approach that used it was found to be defective, |
| 98 |
and the one remaining legitimate use is for debugging when you need to |
| 99 |
non-destructively examine characters' individual bytes. Just insert this |
| 100 |
pragma temporarily, and remove it after the debugging is finished. |
| 101 |
.PP |
| 102 |
The original usage can be accomplished by explicit (rather than this pragma's |
| 103 |
implicit) encoding using the Encode module: |
| 104 |
.PP |
| 105 |
.Vb 1 |
| 106 |
\& use Encode qw/encode/; |
| 107 |
\& |
| 108 |
\& my $utf8_byte_string = encode "UTF8", $string; |
| 109 |
\& my $latin1_byte_string = encode "Latin1", $string; |
| 110 |
.Ve |
| 111 |
.PP |
| 112 |
Or, if performance is needed and you are only interested in the UTF\-8 |
| 113 |
representation: |
| 114 |
.PP |
| 115 |
.Vb 1 |
| 116 |
\& utf8::encode(my $utf8_byte_string = $string); |
| 117 |
.Ve |
| 118 |
.PP |
| 119 |
\&\f(CW\*(C`no bytes\*(C'\fR can be used to reverse the effect of \f(CW\*(C`use bytes\*(C'\fR within the |
| 120 |
current lexical scope. |
| 121 |
.PP |
| 122 |
As an example, when Perl sees \f(CW\*(C`$x = chr(400)\*(C'\fR, it encodes the character |
| 123 |
in UTF\-8 and stores it in \f(CW$x\fR. Then it is marked as character data, so, |
| 124 |
for instance, \f(CW\*(C`length $x\*(C'\fR returns \f(CW1\fR. However, in the scope of the |
| 125 |
\&\f(CW\*(C`bytes\*(C'\fR pragma, \f(CW$x\fR is treated as a series of bytes \- the bytes that make |
| 126 |
up the UTF8 encoding \- and \f(CW\*(C`length $x\*(C'\fR returns \f(CW2\fR: |
| 127 |
.PP |
| 128 |
.Vb 9 |
| 129 |
\& $x = chr(400); |
| 130 |
\& print "Length is ", length $x, "\en"; # "Length is 1" |
| 131 |
\& printf "Contents are %vd\en", $x; # "Contents are 400" |
| 132 |
\& { |
| 133 |
\& use bytes; # or "require bytes; bytes::length()" |
| 134 |
\& print "Length is ", length $x, "\en"; # "Length is 2" |
| 135 |
\& printf "Contents are %vd\en", $x; # "Contents are 198.144 (on |
| 136 |
\& # ASCII platforms)" |
| 137 |
\& } |
| 138 |
.Ve |
| 139 |
.PP |
| 140 |
\&\f(CWchr()\fR, \f(CWord()\fR, \f(CWsubstr()\fR, \f(CWindex()\fR and \f(CWrindex()\fR behave similarly. |
| 141 |
.PP |
| 142 |
For more on the implications, see perluniintro and perlunicode. |
| 143 |
.PP |
| 144 |
\&\f(CWbytes::length()\fR is admittedly handy if you need to know the |
| 145 |
\&\fBbyte length\fR of a Perl scalar. But a more modern way is: |
| 146 |
.PP |
| 147 |
.Vb 2 |
| 148 |
\& use Encode \*(Aqencode\*(Aq; |
| 149 |
\& length(encode(\*(AqUTF\-8\*(Aq, $scalar)) |
| 150 |
.Ve |
| 151 |
.SH LIMITATIONS |
| 152 |
.IX Header "LIMITATIONS" |
| 153 |
\&\f(CWbytes::substr()\fR does not work as an \fR\f(BIlvalue()\fR\fI\fR. |
| 154 |
.SH "SEE ALSO" |
| 155 |
.IX Header "SEE ALSO" |
| 156 |
perluniintro, perlunicode, utf8, Encode |