a2p
accept
access
acct
addftinfo
addr2line
adjtime
afmtodit
after
aio_cancel
aio_error
aio_read
aio_return
aio_suspend
aio_waitcomplete
aio_write
alias
aliases
alloc
anvil
append
apply
apropos
ar
array
as
asa
asn1parse
at
atq
atrm
attemptckalloc
attemptckrealloc
authlib
authtest
autopoint
awk
b64decode
b64encode
basename
batch
bc
bdes
bell
bg
bgerror
biff
big5
binary
bind
bindkey
bindtags
bindtextdomain
bio
bitmap
blowfish
bn
bootparams
bootptab
bounce
brandelf
break
breaksw
brk
bsdiff
bsdtar
bsnmpd
bspatch
bthost
btsockstat
buffer
builtin
builtins
bunzip2
button
byacc
bzcat
bzegrep
bzfgrep
bzgrep
bzip2
c2ph
c89
c99
ca
cal
calendar
canvas
cap_mkdb
case
cat
catch
catman
cc
cd
cdcontrol
chdir
checkbutton
checknr
chflags
chfn
chgrp
chio
chkey
chmod
chown
chpass
chroot
chsh
ci
ciphers
ckalloc
ckdist
ckfree
ckrealloc
cksum
cleanup
clear
clipboard
clock
clock_getres
clock_gettime
clock_settime
close
cmp
co
col
colcrt
colldef
colors
colrm
column
comm
command
compile_et
complete
compress
concat
config
connect
console
continue
core
courierlogger
couriertcpd
cp
cpan
cpio
cpp
creat
crl
crontab
crunchgen
crunchide
crypt
crypto
csh
csplit
ctags
ctm
ctm_dequeue
ctm_rmail
ctm_smail
cu
cursor
cursors
cut
cvs
date
dbiprof
dbiproxy
dc
dcgettext
dcngettext
dd
dde
default
defer
deliverquota
des
destroy
devfs
df
dgettext
dgst
dh
dhparam
dialog
diff
diff3
dig
dir
dirent
dirname
dirs
discard
disktab
dngettext
do
domainname
done
dprofpp
dsa
dsaparam
dtmfdecode
du
dup
dup2
eaccess
ec
ecdsa
echo
echotc
ecparam
ed
edit
editrc
ee
egrep
elf
elfdump
elif
else
enc
enc2xs
encoding
end
endif
endsw
engine
enigma
entry
env
envsubst
eof
eqn
err
errno
error
errstr
esac
ethers
euc
eui64
eval
event
evp
ex
exec
execve
exit
expand
export
exports
expr
extattr
extattr_delete_fd
extattr_delete_file
extattr_get_fd
extattr_get_file
extattr_set_fd
extattr_set_file
f77
false
famm
famx
fblocked
fbtab
fc
fchdir
fchflags
fchmod
fchown
fcntl
fconfigure
fcopy
fdescfs
fdformat
fdread
fdwrite
fetch
fg
fgrep
fhopen
fhstat
fhstatfs
fi
file
file2c
fileevent
filename
filetest
find
find2perl
finger
flex
flock
flush
fmt
focus
fold
font
fontedit
for
foreach
fork
format
forward
fpathconf
frame
from
fs
fstab
fstat
fstatfs
fsync
ftp
ftpchroot
ftpusers
ftruncate
futimes
g711conv
gb2312
gb18030
gbk
gcc
gcore
gcov
gdb
gencat
gendsa
genrsa
gensnmptree
getconf
getdents
getdirentries
getdtablesize
getegid
geteuid
getfacl
getfh
getfsstat
getgid
getgroups
getitimer
getlogin
getopt
getopts
getpeername
getpgid
getpgrp
getpid
getppid
getpriority
getresgid
getresuid
getrlimit
getrusage
gets
getsid
getsockname
getsockopt
gettext
gettextize
gettimeofday
gettytab
getuid
glob
global
gmake
goto
gperf
gprof
grab
grep
grid
grn
grodvi
groff
groff_font
groff_out
groff_tmac
grog
grolbp
grolj4
grops
grotty
group
groups
gunzip
gzcat
gzexe
gzip
h2ph
h2xs
hash
hashstat
hd
head
help2man
hesinfo
hexdump
history
host
hostname
hosts
hosts_access
hosts_options
hpftodit
http
hup
i386_get_ioperm
i386_get_ldt
i386_set_ioperm
i386_set_ldt
i386_vm86
iconv
id
ident
idprio
if
ifnames253
ifnames259
image
imapd
incr
indent
indxbib
info
infokey
inode
install
instmodsh
interp
intro
introduction
ioctl
ipcrm
ipcs
ipf
ipftest
ipnat
ippool
ipresend
issetugid
jail
jail_attach
jobid
jobs
join
jot
kbdcontrol
kbdmap
kcon
kdestroy
kdump
kenv
kevent
keycap
keylogin
keylogout
keymap
keysyms
kgdb
kill
killall
killpg
kinit
kldfind
kldfirstmod
kldload
kldnext
kldstat
kldsym
kldunload
klist
kpasswd
kqueue
kse
kse_create
kse_exit
kse_release
kse_switchin
kse_thr_interrupt
kse_wakeup
ktrace
label
labelframe
lam
lappend
last
lastcomm
lastlog
lchflags
lchmod
lchown
ld
ldap
ldapadd
ldapcompare
ldapdelete
ldapmodify
ldapmodrdn
ldappasswd
ldapsearch
ldapwhoami
ldd
leave
less
lesskey
lex
lgetfh
lhash
libnetcfg
library
limit
limits
lindex
link
linprocfs
linsert
lint
lio_listio
list
listbox
listen
lj4_font
lkbib
llength
lmtp
ln
load
loadfont
local
locale
locate
lock
lockf
log
logger
login
logins
logname
logout
look
lookbib
lorder
lower
lp
lpq
lpr
lprm
lptest
lrange
lreplace
ls
lsearch
lseek
lset
lsort
lstat
lsvfs
lutimes
lynx
m4
madvise
magic
mail
maildiracl
maildirkw
maildirmake
mailq
mailx
make
makeinfo
makewhatis
man
manpath
master
mc
mcedit
mcview
md2
md4
md5
mdc2
memory
menu
menubar
menubutton
merge
mesg
message
mincore
minherit
minigzip
mkdep
mkdir
mkfifo
mkimapdcert
mklocale
mknod
mkpop3dcert
mkstr
mktemp
mlock
mlockall
mmap
mmroff
modfind
modfnext
modnext
modstat
moduli
more
motd
mount
mprotect
mptable
msdos
msdosfs
msgattrib
msgcat
msgcmp
msgcomm
msgconv
msgen
msgexec
msgfilter
msgfmt
msggrep
msginit
msgmerge
msgs
msgunfmt
msguniq
mskanji
msql2mysql
msync
mt
munlock
munlockall
munmap
mv
myisamchk
myisamlog
myisampack
mysql
mysqlaccess
mysqladmin
mysqlbinlog
mysqlcheck
mysqld
mysqldump
mysqld_multi
mysqld_safe
mysqlhotcopy
mysqlimport
mysqlshow
mysql_config
mysql_fix_privilege_tables
mysql_zap
namespace
nanosleep
nawk
nc
ncal
ncplist
ncplogin
ncplogout
neqn
netconfig
netgroup
netid
netstat
networks
newaliases
newgrp
nex
nfsstat
nfssvc
ngettext
nice
nl
nm
nmount
nohup
nologin
notify
nroff
nseq
nslookup
ntp_adjtime
ntp_gettime
nvi
nview
objcopy
objdump
objformat
ocsp
od
onintr
open
openssl
opieaccess
opieinfo
opiekey
opiekeys
opiepasswd
option
options
oqmgr
pack
package
packagens
pagesize
palette
pam_auth
panedwindow
parray
passwd
paste
patch
pathchk
pathconf
pawd
pax
pbm
pcre
pcreapi
pcrebuild
pcrecallout
pcrecompat
pcrecpp
pcregrep
pcrematching
pcrepartial
pcrepattern
pcreperform
pcreposix
pcreprecompile
pcresample
pcretest
perl
perl56delta
perl58delta
perl561delta
perl570delta
perl571delta
perl572delta
perl573delta
perl581delta
perl582delta
perl583delta
perl584delta
perl585delta
perl586delta
perl587delta
perl588delta
perl5004delta
perl5005delta
perlaix
perlamiga
perlapi
perlapio
perlapollo
perlartistic
perlbeos
perlbook
perlboot
perlbot
perlbs2000
perlbug
perlcall
perlcc
perlce
perlcheat
perlclib
perlcn
perlcompile
perlcygwin
perldata
perldbmfilter
perldebguts
perldebtut
perldebug
perldelta
perldgux
perldiag
perldoc
perldos
perldsc
perlebcdic
perlembed
perlepoc
perlfaq
perlfaq1
perlfaq2
perlfaq3
perlfaq4
perlfaq5
perlfaq6
perlfaq7
perlfaq8
perlfaq9
perlfilter
perlfork
perlform
perlfreebsd
perlfunc
perlglossary
perlgpl
perlguts
perlhack
perlhist
perlhpux
perlhurd
perlintern
perlintro
perliol
perlipc
perlirix
perlivp
perljp
perlko
perllexwarn
perllinux
perllocale
perllol
perlmachten
perlmacos
perlmacosx
perlmint
perlmod
perlmodinstall
perlmodlib
perlmodstyle
perlmpeix
perlnetware
perlnewmod
perlnumber
perlobj
perlop
perlopenbsd
perlopentut
perlos2
perlos390
perlos400
perlothrtut
perlpacktut
perlplan9
perlpod
perlpodspec
perlport
perlqnx
perlre
perlref
perlreftut
perlrequick
perlreref
perlretut
perlrun
perlsec
perlsolaris
perlstyle
perlsub
perlsyn
perlthrtut
perltie
perltoc
perltodo
perltooc
perltoot
perltrap
perltru64
perltw
perlunicode
perluniintro
perlutil
perluts
perlvar
perlvmesa
perlvms
perlvos
perlwin32
perlxs
perlxstut
perror
pfbtops
pftp
pgrep
phones
photo
pic
pickup
piconv
pid
pipe
pkcs7
pkcs8
pkcs12
pkg_add
pkg_check
pkg_create
pkg_delete
pkg_info
pkg_sign
pkg_version
pkill
pl2pm
place
pod2html
pod2latex
pod2man
pod2text
pod2usage
podchecker
podselect
poll
popd
popup
posix_madvise
postalias
postcat
postconf
postdrop
postfix
postkick
postlock
postlog
postmap
postqueue
postsuper
pr
pread
preadv
printcap
printenv
printf
proc
procfs
profil
protocols
prove
proxymap
ps
psed
psroff
pstruct
ptrace
publickey
pushd
puts
pwd
pwrite
pwritev
qmgr
qmqpd
quota
quotactl
radiobutton
raise
rand
ranlib
rcp
rcs
rcsclean
rcsdiff
rcsfile
rcsfreeze
rcsintro
rcsmerge
read
readelf
readlink
readonly
readv
realpath
reboot
recv
recvfrom
recvmsg
red
ree
refer
regexp
registry
regsub
rehash
remote
rename
repeat
replace
req
reset
resolver
resource
return
rev
revoke
rfcomm_sppd
rfork
rhosts
ripemd
ripemd160
rlog
rlogin
rm
rmd160
rmdir
rpc
rpcgen
rs
rsa
rsautl
rsh
rtld
rtprio
rup
ruptime
rusers
rwall
rwho
s2p
safe
sasl
sasldblistusers2
saslpasswd2
sbrk
scache
scale
scan
sched
sched_getparam
sched_getscheduler
sched_get_priority_max
sched_get_priority_min
sched_rr_get_interval
sched_setparam
sched_setscheduler
sched_yield
scon
scp
script
scrollbar
sdiff
sed
seek
select
selection
semctl
semget
semop
send
sendbug
sendfile
sendmail
sendmsg
sendto
services
sess_id
set
setegid
setenv
seteuid
setfacl
setgid
setgroups
setitimer
setlogin
setpgid
setpgrp
setpriority
setregid
setresgid
setresuid
setreuid
setrlimit
setsid
setsockopt
settc
settimeofday
setty
setuid
setvar
sftp
sh
sha
sha1
sha256
shar
shells
shift
shmat
shmctl
shmdt
shmget
showq
shutdown
sigaction
sigaltstack
sigblock
sigmask
sigpause
sigpending
sigprocmask
sigreturn
sigsetmask
sigstack
sigsuspend
sigvec
sigwait
size
slapadd
slapcat
slapd
slapdn
slapindex
slappasswd
slaptest
sleep
slogin
slurpd
smbutil
smime
smtp
smtpd
socket
socketpair
sockstat
soelim
sort
source
spawn
speed
spinbox
spkac
splain
split
squid
squid_ldap_auth
squid_ldap_group
squid_unix_group
sscop
ssh
sshd_config
ssh_config
stab
startslip
stat
statfs
stop
string
strings
strip
stty
su
subst
sum
suspend
swapoff
swapon
switch
symlink
sync
sysarch
syscall
sysconftool
sysconftoolcheck
systat
s_client
s_server
s_time
tabs
tail
talk
tar
tbl
tclsh
tcltest
tclvars
tcopy
tcpdump
tcpslice
tcsh
tee
tell
telltc
telnet
term
termcap
terminfo
test
texindex
texinfo
text
textdomain
tfmtodit
tftp
then
threads
time
tip
tk
tkerror
tkvars
tkwait
tlsmgr
tmac
top
toplevel
touch
tput
tr
trace
trafshow
trap
troff
true
truncate
truss
tset
tsort
tty
ttys
type
tzfile
ui
ul
ulimit
umask
unalias
uname
uncomplete
uncompress
undelete
unexpand
unhash
unifdef
unifdefall
uniq
units
unknown
unlimit
unlink
unmount
unset
unsetenv
until
unvis
update
uplevel
uptime
upvar
usbhidaction
usbhidctl
users
utf8
utimes
utmp
utrace
uudecode
uuencode
uuidgen
vacation
variable
verify
version
vfork
vgrind
vgrindefs
vi
vidcontrol
vidfont
view
virtual
vis
vt220keys
vwait
w
wait
wait3
wait4
waitpid
wall
wc
wget
what
whatis
where
whereis
which
while
who
whoami
whois
window
winfo
wish
wm
write
writev
wtmp
x509
xargs
xgettext
xmlwf
xstr
xsubpp
yacc
yes
ypcat
ypchfn
ypchpass
ypchsh
ypmatch
yppasswd
ypwhich
yyfix
zcat
zcmp
zdiff
zegrep
zfgrep
zforce
zgrep
zmore
znew
_exit
__syscall
 
FreeBSD/Linux/UNIX General Commands Manual
Hypertext Man Pages
encoding
 
encoding(3)	       Perl Programmers Reference Guide 	   encoding(3)



NAME
       encoding - allows you to write your script in non-ascii or non-utf8

SYNOPSIS
	 use encoding "greek";	# Perl like Greek to you?
	 use encoding "euc-jp"; # Jperl!

	 # or you can even do this if your shell supports your native encoding

	 perl -Mencoding=latin2 -e '...' # Feeling centrally European?
	 perl -Mencoding=euc-kr -e '...' # Or Korean?

	 # more control

	 # A simple euc-cn => utf-8 converter
	 use encoding "euc-cn", STDOUT => "utf8";  while(<>){print};

	 # "no encoding;" supported (but not scoped!)
	 no encoding;

	 # an alternate way, Filter
	 use encoding "euc-jp", Filter=>1;
	 # now you can use kanji identifiers -- in euc-jp!

	 # switch on locale -
	 # note that this probably means that unless you have a complete control
	 # over the environments the application is ever going to be run, you should
	 # NOT use the feature of encoding pragma allowing you to write your script
	 # in any recognized encoding because changing locale settings will wreck
	 # the script; you can of course still use the other features of the pragma.
	 use encoding ':locale';

ABSTRACT
       Let's start with a bit of history: Perl 5.6.0 introduced Unicode sup-
       port.  You could apply "substr()" and regexes even to complex CJK char-
       acters -- so long as the script was written in UTF-8.  But back then,
       text editors that supported UTF-8 were still rare and many users
       instead chose to write scripts in legacy encodings, giving up a whole
       new feature of Perl 5.6.

       Rewind to the future: starting from perl 5.8.0 with the encoding
       pragma, you can write your script in any encoding you like (so long as
       the "Encode" module supports it) and still enjoy Unicode support.  This
       pragma achieves that by doing the following:

       o   Internally converts all literals ("q//,qq//,qr//,qw///, qx//") from
	   the encoding specified to utf8.  In Perl 5.8.1 and later, literals
	   in "tr///" and "DATA" pseudo-filehandle are also converted.

       o   Changing PerlIO layers of "STDIN" and "STDOUT" to the encoding
	    specified.

       Literal Conversions

       You can write code in EUC-JP as follows:

	 my $Rakuda = "\xF1\xD1\xF1\xCC"; # Camel in Kanji
		      #<-char-><-char->   # 4 octets
	 s/\bCamel\b/$Rakuda/;

       And with "use encoding "euc-jp"" in effect, it is the same thing as the
       code in UTF-8:

	 my $Rakuda = "\x{99F1}\x{99DD}"; # two Unicode Characters
	 s/\bCamel\b/$Rakuda/;

       PerlIO layers for "STD(IN|OUT)"

       The encoding pragma also modifies the filehandle layers of STDIN and
       STDOUT to the specified encoding.  Therefore,

	 use encoding "euc-jp";
	 my $message = "Camel is the symbol of perl.\n";
	 my $Rakuda = "\xF1\xD1\xF1\xCC"; # Camel in Kanji
	 $message =~ s/\bCamel\b/$Rakuda/;
	 print $message;

       Will print "\xF1\xD1\xF1\xCC is the symbol of perl.\n", not
       "\x{99F1}\x{99DD} is the symbol of perl.\n".

       You can override this by giving extra arguments; see below.

       Implicit upgrading for byte strings

       By default, if strings operating under byte semantics and strings with
       Unicode character data are concatenated, the new string will be created
       by decoding the byte strings as ISO 8859-1 (Latin-1).

       The encoding pragma changes this to use the specified encoding instead.
       For example:

	   use encoding 'utf8';
	   my $string = chr(20000); # a Unicode string
	   utf8::encode($string);   # now it's a UTF-8 encoded byte string
	   # concatenate with another Unicode string
	   print length($string . chr(20000));

       Will print 2, because $string is upgraded as UTF-8.  Without "use
       encoding 'utf8';", it will print 4 instead, since $string is three
       octets when interpreted as Latin-1.

FEATURES THAT REQUIRE 5.8.1
       Some of the features offered by this pragma requires perl 5.8.1.  Most
       of these are done by Inaba Hiroto.  Any other features and changes are
       good for 5.8.0.

       "NON-EUC" doublebyte encodings
	   Because perl needs to parse script before applying this pragma,
	   such encodings as Shift_JIS and Big-5 that may contain '\' (BACK-
	   SLASH; \x5c) in the second byte fails because the second byte may
	   accidentally escape the quoting character that follows.  Perl 5.8.1
	   or later fixes this problem.

       tr//
	   "tr//" was overlooked by Perl 5 porters when they released perl
	   5.8.0 See the section below for details.

       DATA pseudo-filehandle
	   Another feature that was overlooked was "DATA".

USAGE
       use encoding [ENCNAME] ;
	   Sets the script encoding to ENCNAME.  And unless ${^UNICODE} exists
	   and non-zero, PerlIO layers of STDIN and STDOUT are set to ":encod-
	   ing(ENCNAME)".

	   Note that STDERR WILL NOT be changed.

	   Also note that non-STD file handles remain unaffected.  Use "use
	   open" or "binmode" to change layers of those.

	   If no encoding is specified, the environment variable PERL_ENCODING
	   is consulted.  If no encoding can be found, the error "Unknown
	   encoding 'ENCNAME'" will be thrown.

       use encoding ENCNAME [ STDIN => ENCNAME_IN ...] ;
	   You can also individually set encodings of STDIN and STDOUT via the
	   "STDIN => ENCNAME" form.  In this case, you cannot omit the first
	   ENCNAME.  "STDIN => undef" turns the IO transcoding completely off.

	   When ${^UNICODE} exists and non-zero, these options will completely
	   ignored.  ${^UNICODE} is a variable introduced in perl 5.8.1.  See
	   perlrun see "${^UNICODE}" in perlvar and "-C" in perlrun for
	   details (perl 5.8.1 and later).

       use encoding ENCNAME Filter=>1;
	   This turns the encoding pragma into a source filter.  While the
	   default approach just decodes interpolated literals (in qq() and
	   qr()), this will apply a source filter to the entire source code.
	   See "The Filter Option" below for details.

       no encoding;
	   Unsets the script encoding. The layers of STDIN, STDOUT are reset
	   to ":raw" (the default unprocessed raw stream of bytes).

The Filter Option
       The magic of "use encoding" is not applied to the names of identifiers.
       In order to make "${"\x{4eba}"}++" ($human++, where human is a single
       Han ideograph) work, you still need to write your script in UTF-8 -- or
       use a source filter.  That's what 'Filter=>1' does.

       What does this mean?  Your source code behaves as if it is written in
       UTF-8 with 'use utf8' in effect.  So even if your editor only supports
       Shift_JIS, for example, you can still try examples in Chapter 15 of
       "Programming Perl, 3rd Ed.".  For instance, you can use UTF-8 identi-
       fiers.

       This option is significantly slower and (as of this writing) non-ASCII
       identifiers are not very stable WITHOUT this option and with the source
       code written in UTF-8.

       Filter-related changes at Encode version 1.87


       o   The Filter option now sets STDIN and STDOUT like non-filter
	   options.  And "STDIN=>ENCODING" and "STDOUT=>ENCODING" work like
	   non-filter version.

       o   "use utf8" is implicitly declared so you no longer have to "use
	   utf8" to "${"\x{4eba}"}++".

CAVEATS
       NOT SCOPED

       The pragma is a per script, not a per block lexical.  Only the last
       "use encoding" or "no encoding" matters, and it affects the whole
       script.	However, the  pragma is supported and use encod-
       ing can appear as many times as you want in a given script.  The multi-
       ple use of this pragma is discouraged.

       By the same reason, the use this pragma inside modules is also discour-
       aged (though not as strongly discouraged as the case above.  See
       below).

       If you still have to write a module with this pragma, be very careful
       of the load order.  See the codes below;

	 # called module
	 package Module_IN_BAR;
	 use encoding "bar";
	 # stuff in "bar" encoding here
	 1;

	 # caller script
	 use encoding "foo"
	 use Module_IN_BAR;
	 # surprise! use encoding "bar" is in effect.

       The best way to avoid this oddity is to use this pragma RIGHT AFTER
       other modules are loaded.  i.e.

	 use Module_IN_BAR;
	 use encoding "foo";

       DO NOT MIX MULTIPLE ENCODINGS

       Notice that only literals (string or regular expression) having only
       legacy code points are affected: if you mix data like this

	       \xDF\x{100}

       the data is assumed to be in (Latin 1 and) Unicode, not in your native
       encoding.  In other words, this will match in "greek":

	       "\xDF" =~ /\x{3af}/

       but this will not

	       "\xDF\x{100}" =~ /\x{3af}\x{100}/

       since the "\xDF" (ISO 8859-7 GREEK SMALL LETTER IOTA WITH TONOS) on the
       left will not be upgraded to "\x{3af}" (Unicode GREEK SMALL LETTER IOTA
       WITH TONOS) because of the "\x{100}" on the left.  You should not be
       mixing your legacy data and Unicode in the same string.

       This pragma also affects encoding of the 0x80..0xFF code point range:
       normally characters in that range are left as eight-bit bytes (unless
       they are combined with characters with code points 0x100 or larger, in
       which case all characters need to become UTF-8 encoded), but if the
       "encoding" pragma is present, even the 0x80..0xFF range always gets
       UTF-8 encoded.

       After all, the best thing about this pragma is that you don't have to
       resort to \x{....} just to spell your name in a native encoding.  So
       feel free to put your strings in your encoding in quotes and regexes.

       tr/// with ranges

       The encoding pragma works by decoding string literals in
       "q//,qq//,qr//,qw///, qx//" and so forth.  In perl 5.8.0, this does not
       apply to "tr///".  Therefore,

	 use encoding 'euc-jp';
	 #....
	 $kana =~ tr/\xA4\xA1-\xA4\xF3/\xA5\xA1-\xA5\xF3/;
	 #	     -------- -------- -------- --------

       Does not work as

	 $kana =~ tr/\x{3041}-\x{3093}/\x{30a1}-\x{30f3}/;

       Legend of characters above
	     utf8     euc-jp   charnames::viacode()
	     -----------------------------------------
	     \x{3041} \xA4\xA1 HIRAGANA LETTER SMALL A
	     \x{3093} \xA4\xF3 HIRAGANA LETTER N
	     \x{30a1} \xA5\xA1 KATAKANA LETTER SMALL A
	     \x{30f3} \xA5\xF3 KATAKANA LETTER N

       This counterintuitive behavior has been fixed in perl 5.8.1.

       workaround to tr///;

       In perl 5.8.0, you can work around as follows;

	 use encoding 'euc-jp';
	 #  ....
	 eval qq{ \$kana =~ tr/\xA4\xA1-\xA4\xF3/\xA5\xA1-\xA5\xF3/ };

       Note the "tr//" expression is surrounded by "qq{}".  The idea behind is
       the same as classic idiom that makes "tr///" 'interpolate'.

	  tr/$from/$to/;	    # wrong!
	  eval qq{ tr/$from/$to/ }; # workaround.

       Nevertheless, in case of encoding pragma even "q//" is affected so
       "tr///" not being decoded was obviously against the will of Perl5
       Porters so it has been fixed in Perl 5.8.1 or later.

EXAMPLE - Greekperl
	   use encoding "iso 8859-7";

	   # \xDF in 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;

	   # ... as are eq and cmp ...

	   print "peta\n" if "\x{3af}" eq  pack("C", 0xdf);
	   print "exa\n"  if "\x{3af}" cmp pack("C", 0xdf) == 0;

	   # ... but pack/unpack C are not affected, in case you still
	   # want to go back to your native encoding

	   print "zetta\n" if unpack("C", (pack("C", 0xdf))) == 0xdf;

KNOWN PROBLEMS
       literals in regex that are longer than 127 bytes
	   For native multibyte encodings (either fixed or variable length),
	   the current implementation of the regular expressions may introduce
	   recoding errors for regular expression literals longer than 127
	   bytes.

       EBCDIC
	   The encoding pragma is not supported on EBCDIC platforms.  (Porters
	   who are willing and able to remove this limitation are welcome.)

       format
	   This pragma doesn't work well with format because PerlIO does not
	   get along very well with it.  When format contains non-ascii char-
	   acters it prints funny or gets "wide character warnings".  To
	   understand it, try the code below.

	     # Save this one in utf8
	     # replace *non-ascii* with a non-ascii string
	     my $camel;
	     format STDOUT =
	     *non-ascii*@>>>>>>>
	     $camel
	     .
	     $camel = "*non-ascii*";
	     binmode(STDOUT=>':encoding(utf8)'); # bang!
	     write;		 # funny
	     print $camel, "\n"; # fine

	   Without binmode this happens to work but without binmode, print()
	   fails instead of write().

	   At any rate, the very use of format is questionable when it comes
	   to unicode characters since you have to consider such things as
	   character width (i.e. double-width for ideographs) and directions
	   (i.e. BIDI for Arabic and Hebrew).

       The Logic of :locale

       The logic of ":locale" is as follows:

       1.  If the platform supports the langinfo(CODESET) interface, the code-
	   set returned is used as the default encoding for the open pragma.

       2.  If 1. didn't work but we are under the locale pragma, the environ-
	   ment variables LC_ALL and LANG (in that order) are matched for
	   encodings (the part after ".", if any), and if any found, that is
	   used as the default encoding for the open pragma.

       3.  If 1. and 2. didn't work, the environment variables LC_ALL and LANG
	   (in that order) are matched for anything looking like UTF-8, and if
	   any found, ":utf8" is used as the default encoding for the open
	   pragma.

       If your locale environment variables (LC_ALL, LC_CTYPE, LANG) contain
       the strings 'UTF-8' or 'UTF8' (case-insensitive matching), the default
       encoding of your STDIN, STDOUT, and STDERR, and of any subsequent file
       open, is UTF-8.

HISTORY
       This pragma first appeared in Perl 5.8.0.  For features that require
       5.8.1 and better, see above.

       The ":locale" subpragma was implemented in 2.01, or Perl 5.8.6.

SEE ALSO
       perlunicode, Encode, open, Filter::Util::Call,

       Ch. 15 of "Programming Perl (3rd Edition)" by Larry Wall, Tom Chris-
       tiansen, Jon Orwant; O'Reilly & Associates; ISBN 0-596-00027-8



perl v5.8.8			  2001-09-21			   encoding(3)
=18836
+154
(66)