pod/perltooc.pod Tom's object-oriented tutorial (more on class data)
pod/perltoot.pod Tom's object-oriented tutorial
pod/perltrap.pod Trap info
-pod/perlunintro.pod Unicode introduction
+pod/perluniintro.pod Unicode introduction
pod/perlunicode.pod Unicode support info
pod/perlutil.pod Accompanying utilities explained
pod/perlvar.pod Variable info
perlport
perllocale
- perlunintro
+ perluniintro
perlunicode
perlebcdic
perlport Perl portability guide
perllocale Perl locale support
- perlunintro Perl Unicode introduction
+ perluniintro Perl Unicode introduction
perlunicode Perl Unicode support
perlebcdic Considerations for running Perl on EBCDIC platforms
NEWSOCKET,GENERICSOCKET, alarm SECONDS, alarm, atan2 Y,X, bind SOCKET,NAME,
binmode FILEHANDLE, DISCIPLINE, binmode FILEHANDLE, bless REF,CLASSNAME,
bless REF, caller EXPR, caller, chdir EXPR, chmod LIST, chomp VARIABLE,
-chomp LIST, chomp, chop VARIABLE, chop LIST, chop, chown LIST, chr NUMBER,
-chr, chroot FILENAME, chroot, close FILEHANDLE, close, closedir DIRHANDLE,
-connect SOCKET,NAME, continue BLOCK, cos EXPR, cos, crypt PLAINTEXT,SALT,
-dbmclose HASH, dbmopen HASH,DBNAME,MASK, defined EXPR, defined, delete
-EXPR, die LIST, do BLOCK, do SUBROUTINE(LIST), do EXPR, dump LABEL, dump,
-each HASH, eof FILEHANDLE, eof (), eof, eval EXPR, eval BLOCK, exec LIST,
-exec PROGRAM LIST, exists EXPR, exit EXPR, exp EXPR, exp, fcntl
-FILEHANDLE,FUNCTION,SCALAR, fileno FILEHANDLE, flock FILEHANDLE,OPERATION,
-fork, format, formline PICTURE,LIST, getc FILEHANDLE, getc, getlogin,
-getpeername SOCKET, getpgrp PID, getppid, getpriority WHICH,WHO, getpwnam
-NAME, getgrnam NAME, gethostbyname NAME, getnetbyname NAME, getprotobyname
-NAME, getpwuid UID, getgrgid GID, getservbyname NAME,PROTO, gethostbyaddr
-ADDR,ADDRTYPE, getnetbyaddr ADDR,ADDRTYPE, getprotobynumber NUMBER,
-getservbyport PORT,PROTO, getpwent, getgrent, gethostent, getnetent,
-getprotoent, getservent, setpwent, setgrent, sethostent STAYOPEN, setnetent
-STAYOPEN, setprotoent STAYOPEN, setservent STAYOPEN, endpwent, endgrent,
-endhostent, endnetent, endprotoent, endservent, getsockname SOCKET,
-getsockopt SOCKET,LEVEL,OPTNAME, glob EXPR, glob, gmtime EXPR, goto LABEL,
-goto EXPR, goto &NAME, grep BLOCK LIST, grep EXPR,LIST, hex EXPR, hex,
-import, index STR,SUBSTR,POSITION, index STR,SUBSTR, int EXPR, int, ioctl
-FILEHANDLE,FUNCTION,SCALAR, join EXPR,LIST, keys HASH, kill SIGNAL, LIST,
-last LABEL, last, lc EXPR, lc, lcfirst EXPR, lcfirst, length EXPR, length,
-link OLDFILE,NEWFILE, listen SOCKET,QUEUESIZE, local EXPR, localtime EXPR,
-lock, log EXPR, log, lstat EXPR, lstat, m//, map BLOCK LIST, map EXPR,LIST,
-mkdir FILENAME,MASK, mkdir FILENAME, msgctl ID,CMD,ARG, msgget KEY,FLAGS,
-msgrcv ID,VAR,SIZE,TYPE,FLAGS, msgsnd ID,MSG,FLAGS, my EXPR, my EXPR :
-ATTRIBUTES, next LABEL, next, no Module LIST, oct EXPR, oct, open
-FILEHANDLE,EXPR, open FILEHANDLE,MODE,EXPR, open FILEHANDLE,MODE,EXPR,LIST,
-open FILEHANDLE, opendir DIRHANDLE,EXPR, ord EXPR, ord, our EXPR, our EXPR
-: ATTRIBUTES, pack TEMPLATE,LIST, package NAMESPACE, package, pipe
+chomp( LIST ), chomp, chop VARIABLE, chop( LIST ), chop, chown LIST, chr
+NUMBER, chr, chroot FILENAME, chroot, close FILEHANDLE, close, closedir
+DIRHANDLE, connect SOCKET,NAME, continue BLOCK, cos EXPR, cos, crypt
+PLAINTEXT,SALT, dbmclose HASH, dbmopen HASH,DBNAME,MASK, defined EXPR,
+defined, delete EXPR, die LIST, do BLOCK, do SUBROUTINE(LIST), do EXPR,
+dump LABEL, dump, each HASH, eof FILEHANDLE, eof (), eof, eval EXPR, eval
+BLOCK, exec LIST, exec PROGRAM LIST, exists EXPR, exit EXPR, exp EXPR, exp,
+fcntl FILEHANDLE,FUNCTION,SCALAR, fileno FILEHANDLE, flock
+FILEHANDLE,OPERATION, fork, format, formline PICTURE,LIST, getc FILEHANDLE,
+getc, getlogin, getpeername SOCKET, getpgrp PID, getppid, getpriority
+WHICH,WHO, getpwnam NAME, getgrnam NAME, gethostbyname NAME, getnetbyname
+NAME, getprotobyname NAME, getpwuid UID, getgrgid GID, getservbyname
+NAME,PROTO, gethostbyaddr ADDR,ADDRTYPE, getnetbyaddr ADDR,ADDRTYPE,
+getprotobynumber NUMBER, getservbyport PORT,PROTO, getpwent, getgrent,
+gethostent, getnetent, getprotoent, getservent, setpwent, setgrent,
+sethostent STAYOPEN, setnetent STAYOPEN, setprotoent STAYOPEN, setservent
+STAYOPEN, endpwent, endgrent, endhostent, endnetent, endprotoent,
+endservent, getsockname SOCKET, getsockopt SOCKET,LEVEL,OPTNAME, glob EXPR,
+glob, gmtime EXPR, goto LABEL, goto EXPR, goto &NAME, grep BLOCK LIST, grep
+EXPR,LIST, hex EXPR, hex, import, index STR,SUBSTR,POSITION, index
+STR,SUBSTR, int EXPR, int, ioctl FILEHANDLE,FUNCTION,SCALAR, join
+EXPR,LIST, keys HASH, kill SIGNAL, LIST, last LABEL, last, lc EXPR, lc,
+lcfirst EXPR, lcfirst, length EXPR, length, link OLDFILE,NEWFILE, listen
+SOCKET,QUEUESIZE, local EXPR, localtime EXPR, lock, log EXPR, log, lstat
+EXPR, lstat, m//, map BLOCK LIST, map EXPR,LIST, mkdir FILENAME,MASK, mkdir
+FILENAME, msgctl ID,CMD,ARG, msgget KEY,FLAGS, msgrcv
+ID,VAR,SIZE,TYPE,FLAGS, msgsnd ID,MSG,FLAGS, my EXPR, my EXPR : ATTRIBUTES,
+next LABEL, next, no Module LIST, oct EXPR, oct, open FILEHANDLE,EXPR, open
+FILEHANDLE,MODE,EXPR, open FILEHANDLE,MODE,EXPR,LIST, open FILEHANDLE,
+opendir DIRHANDLE,EXPR, ord EXPR, ord, our EXPR, our EXPR : ATTRIBUTES,
+pack TEMPLATE,LIST, package NAMESPACE, package, pipe
READHANDLE,WRITEHANDLE, pop ARRAY, pop, pos SCALAR, pos, print FILEHANDLE
LIST, print LIST, print, printf FILEHANDLE FORMAT, LIST, printf FORMAT,
LIST, prototype FUNCTION, push ARRAY,LIST, q/STRING/, qq/STRING/,
=item Parsing Traps
-Parsing, Parsing, Parsing, Parsing
+Parsing, Parsing, Parsing, Parsing, Parsing
=item Numerical Traps
=back
-=head2 perlunintro - Perl Unicode introduction
+=head2 perluniintro - Perl Unicode introduction
=over 4
=item The Typemap
+=item Safely Storing Static Data in XS
+
+MY_CXT_KEY, typedef my_cxt_t, START_MY_CXT, MY_CXT_INIT, dMY_CXT, MY_CXT
+
=back
=item EXAMPLES
mg_find, mg_free, mg_get, mg_length, mg_magical, mg_set, Move, New, newAV,
Newc, newCONSTSUB, newHV, newRV_inc, newRV_noinc, NEWSV, newSV, newSViv,
newSVnv, newSVpv, newSVpvf, newSVpvn, newSVpvn_share, newSVrv, newSVsv,
-newSVuv, newXS, newXSproto, Newz, Nullav, Nullch, Nullcv, Nullhv, Nullsv,
-ORIGMARK, perl_alloc, perl_clone, perl_construct, perl_destruct, perl_free,
-perl_parse, perl_run, PL_modglobal, PL_na, PL_sv_no, PL_sv_undef,
-PL_sv_yes, POPi, POPl, POPn, POPp, POPpbytex, POPpx, POPs, PUSHi, PUSHMARK,
-PUSHn, PUSHp, PUSHs, PUSHu, PUTBACK, Renew, Renewc, require_pv, RETVAL,
-Safefree, savepv, savepvn, SAVETMPS, scan_bin, scan_hex, scan_oct,
-sharedsv_find, sharedsv_init, sharedsv_lock, sharedsv_new,
-sharedsv_thrcnt_dec, sharedsv_thrcnt_inc, sharedsv_unlock, sortsv, SP,
-SPAGAIN, ST, strEQ, strGE, strGT, strLE, strLT, strNE, strnEQ, strnNE,
-StructCopy, SvCUR, SvCUR_set, SvEND, SvGETMAGIC, SvGROW, SvIOK, SvIOKp,
-SvIOK_notUV, SvIOK_off, SvIOK_on, SvIOK_only, SvIOK_only_UV, SvIOK_UV,
-SvIV, SvIVx, SvIVX, SvLEN, SvNIOK, SvNIOKp, SvNIOK_off, SvNOK, SvNOKp,
-SvNOK_off, SvNOK_on, SvNOK_only, SvNV, SvNVX, SvNVx, SvOK, SvOOK, SvPOK,
-SvPOKp, SvPOK_off, SvPOK_on, SvPOK_only, SvPOK_only_UTF8, SvPV, SvPVbyte,
-SvPVbytex, SvPVbytex_force, SvPVbyte_force, SvPVbyte_nolen, SvPVutf8,
-SvPVutf8x, SvPVutf8x_force, SvPVutf8_force, SvPVutf8_nolen, SvPVX, SvPVx,
-SvPV_force, SvPV_force_nomg, SvPV_nolen, SvREFCNT, SvREFCNT_dec,
-SvREFCNT_inc, SvROK, SvROK_off, SvROK_on, SvRV, SvSETMAGIC, SvSetMagicSV,
-SvSetMagicSV_nosteal, SvSetSV, SvSetSV_nosteal, SvSTASH, SvTAINT,
-SvTAINTED, SvTAINTED_off, SvTAINTED_on, SvTRUE, svtype, SvTYPE, SVt_IV,
-SVt_NV, SVt_PV, SVt_PVAV, SVt_PVCV, SVt_PVHV, SVt_PVMG, SvUOK, SvUPGRADE,
-SvUTF8, SvUTF8_off, SvUTF8_on, SvUV, SvUVx, SvUVX, sv_2bool, sv_2cv,
-sv_2io, sv_2iv, sv_2mortal, sv_2nv, sv_2pvbyte, sv_2pvbyte_nolen,
+newSVuv, newXS, newXSproto, Newz, new_vstring, Nullav, Nullch, Nullcv,
+Nullhv, Nullsv, ORIGMARK, perl_alloc, perl_clone, perl_construct,
+perl_destruct, perl_free, perl_parse, perl_run, PL_modglobal, PL_na,
+PL_sv_no, PL_sv_undef, PL_sv_yes, POPi, POPl, POPn, POPp, POPpbytex, POPpx,
+POPs, PUSHi, PUSHMARK, PUSHn, PUSHp, PUSHs, PUSHu, PUTBACK, Renew, Renewc,
+require_pv, RETVAL, Safefree, savepv, savepvn, SAVETMPS, scan_bin,
+scan_hex, scan_oct, sharedsv_find, sharedsv_init, sharedsv_lock,
+sharedsv_new, sharedsv_thrcnt_dec, sharedsv_thrcnt_inc, sharedsv_unlock,
+sortsv, SP, SPAGAIN, ST, strEQ, strGE, strGT, strLE, strLT, strNE, strnEQ,
+strnNE, StructCopy, SvCUR, SvCUR_set, SvEND, SvGETMAGIC, SvGROW, SvIOK,
+SvIOKp, SvIOK_notUV, SvIOK_off, SvIOK_on, SvIOK_only, SvIOK_only_UV,
+SvIOK_UV, SvIV, SvIVX, SvIVx, SvLEN, SvNIOK, SvNIOKp, SvNIOK_off, SvNOK,
+SvNOKp, SvNOK_off, SvNOK_on, SvNOK_only, SvNV, SvNVx, SvNVX, SvOK, SvOOK,
+SvPOK, SvPOKp, SvPOK_off, SvPOK_on, SvPOK_only, SvPOK_only_UTF8, SvPV,
+SvPVbyte, SvPVbytex, SvPVbytex_force, SvPVbyte_force, SvPVbyte_nolen,
+SvPVutf8, SvPVutf8x, SvPVutf8x_force, SvPVutf8_force, SvPVutf8_nolen,
+SvPVX, SvPVx, SvPV_force, SvPV_force_nomg, SvPV_nolen, SvREFCNT,
+SvREFCNT_dec, SvREFCNT_inc, SvROK, SvROK_off, SvROK_on, SvRV, SvSETMAGIC,
+SvSetMagicSV, SvSetMagicSV_nosteal, SvSetSV, SvSetSV_nosteal, SvSTASH,
+SvTAINT, SvTAINTED, SvTAINTED_off, SvTAINTED_on, SvTRUE, svtype, SvTYPE,
+SVt_IV, SVt_NV, SVt_PV, SVt_PVAV, SVt_PVCV, SVt_PVHV, SVt_PVMG, SvUOK,
+SvUPGRADE, SvUTF8, SvUTF8_off, SvUTF8_on, SvUV, SvUVx, SvUVX, sv_2bool,
+sv_2cv, sv_2io, sv_2iv, sv_2mortal, sv_2nv, sv_2pvbyte, sv_2pvbyte_nolen,
sv_2pvutf8, sv_2pvutf8_nolen, sv_2pv_flags, sv_2pv_nolen, sv_2uv,
sv_backoff, sv_bless, sv_catpv, sv_catpvf, sv_catpvf_mg, sv_catpvn,
sv_catpvn_flags, sv_catpvn_mg, sv_catpv_mg, sv_catsv, sv_catsv_flags,
=item Data Structures
-1. The functions and attributes of the "layer class", 2. The per-instance
-data for a particular handle
-
=item Functions and Attributes
=item Per-instance Data
=item Prototypes versus indirect objects
-=item Install HMTL
+=item Install HTML
=item Prototype method calls
=item Cygwin intermittent failures of lib/Memoize/t/expire_file 11 and 12
-=item HP-UX lib/io_multihomed Fails When LP64-Configur
+=item HP-UX lib/io_multihomed Fails When LP64-Configured
=item HP-UX lib/posix Subtest 9 Fails When LP64-Configured
=item NOTE
-=item What's New in Perl ffor MPE/iX
+=item What's New in Perl for MPE/iX
=item Welcome to Perl/iX
=item DESCRIPTION
-new, function, LIST, $thread->join, $thread->detach, threads->self,
-$thread->tid
+$thread = new(function, LIST), $thread->join, $thread->detach,
+threads->self, $thread->tid
=item TODO
=back
+=head2 threads - Perl extension allowing use of interpreter based threads
+from perl
+
+=over 4
+
+=item SYNOPSIS
+
+=item DESCRIPTION
+
+$thread = new(function, LIST), $thread->join, $thread->detach,
+threads->self, $thread->tid
+
+=item TODO
+
+Fix so the return value is returned when you join, Add join_all, Fix memory
+leaks!
+
+=item AUTHOR and COPYRIGHT
+
+=item BUGS
+
+creating a thread from within a thread is unsafe under win32,
+PERL_OLD_SIGNALS are not threadsafe, will not be
+
+=item SEE ALSO
+
+=back
+
+=head2 threadshared, threads::shared - Perl extension for sharing data
+structures between threads
+
+=over 4
+
+=item SYNOPSIS
+
+=item DESCRIPTION
+
+=item EXPORT
+
+=item FUNCTIONS
+
+share VARIABLE, lock VARIABLE, unlock VARIABLE, cond_wait VARIABLE,
+cond_signal VARIABLE, cond_broadcast VARIABLE
+
+=item BUGS
+
+=item AUTHOR
+
+=item SEE ALSO
+
+=back
+
=head2 utf8 - Perl pragma to enable/disable UTF-8 (or UTF-EBCDIC) in source
code
=over 4
+=item Runtime debugging
+
=item Memory footprint debugging
=back
=item All-in-one interface
+=item Filtering only specific components of source code
+
+C<"code">, C<"executable">, C<"quotelike">, C<"string">, C<"regex">,
+C<"all">
+
+=item Filtering only the code parts of source code
+
+Most source code ceases to be grammatically correct when it is broken up
+into the pieces between string literals and regexes. So the C<'code'>
+component filter behaves slightly differently from the other partial
+filters
+described in the previous section.
+
=item Using Filter::Simple and Exporter together
=item How it works
=item DESCRIPTION
-center, date, fixed, fixedbold, fixeditalic, fixedbolditalic, quotes,
+center, date, fixed, fixedbold, fixeditalic, fixedbolditalic, name, quotes,
release, section
=item DIAGNOSTICS
=back
+=head2 Pod::ParseLink -- Parse an L<> formatting code in POD text
+
+=over 4
+
+=item SYNOPSIS
+
+=item DESCRIPTION
+
+=item AUTHOR
+
+=item COPYRIGHT AND LICENSE
+
+=back
+
=head2 Pod::ParseUtils - helpers for POD parsing and conversion
=over 4
=back
-=head2 Thread - manipulate threads in Perl (EXPERIMENTAL, subject to
-change)
+=head2 Thread - manipulate threads in Perl
=over 4
=item FUNCTIONS
-new \&start_sub, new \&start_sub, LIST, lock VARIABLE, async BLOCK;,
-Thread->self, Thread->list, cond_wait VARIABLE, cond_signal VARIABLE,
-cond_broadcast VARIABLE, yield
+$thread = Thread->new(\&start_sub), $thread = Thread->new(\&start_sub,
+LIST), lock VARIABLE, async BLOCK;, Thread->self, cond_wait VARIABLE,
+cond_signal VARIABLE, cond_broadcast VARIABLE, yield
=item METHODS
--- /dev/null
+=head1 NAME
+
+perluniintro - Perl Unicode introduction
+
+=head1 DESCRIPTION
+
+This document gives a general idea of Unicode and how to use Unicode
+in Perl.
+
+=head2 Unicode
+
+Unicode is a character set standard with plans to cover all of the
+writing systems of the world, plus many other symbols.
+
+Unicode and ISO/IEC 10646 are coordinated standards that provide code
+points for the characters in almost all modern character set standards,
+covering more than 30 writing systems and hundreds of languages,
+including all commercially important modern languages. All characters
+in the largest Chinese, Japanese, and Korean dictionaries are also
+encoded. The standards will eventually cover almost all characters in
+more than 250 writing systems and thousands of languages.
+
+A Unicode I<character> is an abstract entity. It is not bound to any
+particular integer width, and especially not to the C language C<char>.
+Unicode is language neutral and display neutral: it doesn't encode the
+language of the text, and it doesn't define fonts or other graphical
+layout details. Unicode operates on characters and on text built from
+those characters.
+
+Unicode defines characters like C<LATIN CAPITAL LETTER A> or C<GREEK
+SMALL LETTER ALPHA>, and then unique numbers for those, hexadecimal
+0x0041 or 0x03B1 for those particular characters. Such unique
+numbers are called I<code points>.
+
+The Unicode standard prefers using hexadecimal notation for the code
+points. (In case this notation, numbers like 0x0041, is unfamiliar to
+you, take a peek at a later section, L</"Hexadecimal Notation">.)
+The Unicode standard uses the notation C<U+0041 LATIN CAPITAL LETTER A>,
+which gives the hexadecimal code point, and the normative name of
+the character.
+
+Unicode also defines various I<properties> for the characters, like
+"uppercase" or "lowercase", "decimal digit", or "punctuation":
+these properties are independent of the names of the characters.
+Furthermore, various operations on the characters like uppercasing,
+lowercasing, and collating (sorting), are defined.
+
+A Unicode character consists either of a single code point, or a
+I<base character> (like C<LATIN CAPITAL LETTER A>), followed by one or
+more I<modifiers> (like C<COMBINING ACUTE ACCENT>). This sequence of
+a base character and modifiers is called a I<combining character
+sequence>.
+
+Whether to call these combining character sequences, as a whole,
+"characters" depends on your point of view. If you are a programmer, you
+probably would tend towards seeing each element in the sequences as one
+unit, one "character", but from the user viewpoint, the sequence as a
+whole is probably considered one "character", since that's probably what
+it looks like in the context of the user's language.
+
+With this "as a whole" view of characters, the number of characters is
+open-ended. But in the programmer's "one unit is one character" point of
+view, the concept of "characters" is more deterministic, and so we take
+that point of view in this document: one "character" is one Unicode
+code point, be it a base character or a combining character.
+
+For some of the combinations there are I<precomposed> characters,
+for example C<LATIN CAPITAL LETTER A WITH ACUTE> is defined as
+a single code point. These precomposed characters are, however,
+often available only for some combinations, and mainly they are
+meant to support round-trip conversions between Unicode and legacy
+standards (like the ISO 8859), and in general case the composing
+method is more extensible. To support conversion between the
+different compositions of the characters, various I<normalization
+forms> are also defined.
+
+Because of backward compatibility with legacy encodings, the "a unique
+number for every character" breaks down a bit: "at least one number
+for every character" is closer to truth. (This happens when the same
+character has been encoded in several legacy encodings.) The converse
+is also not true: not every code point has an assigned character.
+Firstly, there are unallocated code points within otherwise used
+blocks. Secondly, there are special Unicode control characters that
+do not represent true characters.
+
+A common myth about Unicode is that it would be "16-bit", that is,
+0x10000 (or 65536) characters from 0x0000 to 0xFFFF. B<This is untrue.>
+Since Unicode 2.0 Unicode has been defined all the way up to 21 bits
+(0x10FFFF), and since 3.1 characters have been defined beyond 0xFFFF.
+The first 0x10000 characters are called the I<Plane 0>, or the I<Basic
+Multilingual Plane> (BMP). With the Unicode 3.1, 17 planes in all are
+defined (but nowhere near full of defined characters yet).
+
+Another myth is that the 256-character blocks have something to do
+with languages: a block per language. B<Also this is untrue.>
+The division into the blocks exists but it is almost completely
+accidental, an artifact of how the characters have been historically
+allocated. Instead, there is a concept called I<scripts>, which may
+be more useful: there is C<Latin> script, C<Greek> script, and so on.
+Scripts usually span several parts of several blocks. For further
+information see L<Unicode::UCD>.
+
+The Unicode code points are just abstract numbers. To input and
+output these abstract numbers, the numbers must be I<encoded> somehow.
+Unicode defines several I<character encoding forms>, of which I<UTF-8>
+is perhaps the most popular. UTF-8 is a variable length encoding that
+encodes Unicode characters as 1 to 6 bytes (only 4 with the currently
+defined characters). Other encodings are UTF-16 and UTF-32 and their
+big and little endian variants (UTF-8 is byteorder independent).
+The ISO/IEC 10646 defines the UCS-2 and UCS-4 encoding forms.
+
+For more information about encodings, for example to learn what
+I<surrogates> and I<byte order marks> (BOMs) are, see L<perlunicode>.
+
+=head2 Perl's Unicode Support
+
+Starting from Perl 5.6.0, Perl has had the capability of handling
+Unicode natively. The first recommended release for serious Unicode
+work is Perl 5.8.0, however. The maintenance release 5.6.1 fixed many
+of the problems of the initial implementation of Unicode, but for
+example regular expressions didn't really work with Unicode.
+
+B<Starting from Perl 5.8.0, the use of C<use utf8> is no longer
+necessary.> In earlier releases the C<utf8> pragma was used to declare
+that operations in the current block or file would be Unicode-aware.
+This model was found to be wrong, or at least clumsy: the Unicodeness
+is now carried with the data, not attached to the operations. (There
+is one remaining case where an explicit C<use utf8> is needed: if your
+Perl script is in UTF-8, you can use UTF-8 in your variable and
+subroutine names, and in your string and regular expression literals,
+by saying C<use utf8>. This is not the default because that would
+break existing scripts having legacy 8-bit data in them.)
+
+=head2 Perl's Unicode Model
+
+Perl supports both the old, pre-5.6, model of strings of eight-bit
+native bytes, and strings of Unicode characters. The principle is
+that Perl tries to keep its data as eight-bit bytes for as long as
+possible, but as soon as Unicodeness cannot be avoided, the data is
+transparently upgraded to Unicode.
+
+The internal encoding of Unicode in Perl is UTF-8. The internal
+encoding is normally hidden, however, and one need not and should not
+worry about the internal encoding at all: it is all just characters.
+
+Perl 5.8.0 will also support Unicode on EBCDIC platforms. There the
+support is somewhat harder to implement since additional conversions
+are needed at every step. Because of these difficulties the Unicode
+support won't be quite as full as in other, mainly ASCII-based,
+platforms (the Unicode support will be better than in the 5.6 series,
+which didn't work much at all for EBCDIC platform). On EBCDIC
+platforms the internal encoding form used is UTF-EBCDIC.
+
+=head2 Creating Unicode
+
+To create Unicode literals, use the C<\x{...}> notation in
+doublequoted strings:
+
+ my $smiley = "\x{263a}";
+
+Similarly for regular expression literals
+
+ $smiley =~ /\x{263a}/;
+
+At run-time you can use C<chr()>:
+
+ my $hebrew_alef = chr(0x05d0);
+
+(See L</"Further Resources"> for how to find all these numeric codes.)
+
+Naturally, C<ord()> will do the reverse: turn a character to a code point.
+
+Note that C<\x..>, C<\x{..}> and C<chr(...)> for arguments less than
+0x100 (decimal 256) will generate an eight-bit character for backward
+compatibility with older Perls. For arguments of 0x100 or more,
+Unicode will always be produced. If you want UTF-8 always, use
+C<pack("U", ...)> instead of C<\x..>, C<\x{..}>, or C<chr()>.
+
+You can also use the C<charnames> pragma to invoke characters
+by name in doublequoted strings:
+
+ use charnames ':full';
+ my $arabic_alef = "\N{ARABIC LETTER ALEF}";
+
+And, as mentioned above, you can also C<pack()> numbers into Unicode
+characters:
+
+ my $georgian_an = pack("U", 0x10a0);
+
+=head2 Handling Unicode
+
+Handling Unicode is for the most part transparent: just use the
+strings as usual. Functions like C<index()>, C<length()>, and
+C<substr()> will work on the Unicode characters; regular expressions
+will work on the Unicode characters (see L<perlunicode> and L<perlretut>).
+
+Note that Perl does B<not> consider combining character sequences
+to be characters, such for example
+
+ use charnames ':full';
+ print length("\N{LATIN CAPITAL LETTER A}\N{COMBINING ACUTE ACCENT}"), "\n";
+
+will print 2, not 1. The only exception is that regular expressions
+have C<\X> for matching a combining character sequence.
+
+When life is not quite so transparent is working with legacy
+encodings, and I/O, and certain special cases.
+
+=head2 Legacy Encodings
+
+When you combine legacy data and Unicode the legacy data needs
+to be upgraded to Unicode. Normally ISO 8859-1 (or EBCDIC, if
+applicable) is assumed. You can override this assumption by
+using the C<encoding> pragma, for example
+
+ use encoding 'latin2'; # ISO 8859-2
+
+in which case literals (string or regular expression) and chr/ord
+in your whole script are assumed to produce Unicode characters from
+ISO 8859-2 code points. Note that the matching for the encoding
+names is forgiving: instead of C<latin2> you could have said
+C<Latin 2>, or C<iso8859-2>, and so forth. With just
+
+ use encoding;
+
+first the environment variable C<PERL_ENCODING> will be consulted,
+and if that doesn't exist, ISO 8859-1 (Latin 1) will be assumed.
+
+The C<Encode> module knows about many encodings and it has interfaces
+for doing conversions between those encodings:
+
+ use Encode 'from_to';
+ from_to($data, "iso-8859-3", "utf-8"); # from legacy to utf-8
+
+=head2 Unicode I/O
+
+Normally writing out Unicode data
+
+ print chr(0x100), "\n";
+
+will print out the raw UTF-8 bytes.
+
+But reading in correctly formed UTF-8 data will not magically turn
+the data into Unicode in Perl's eyes.
+
+You can use either the C<':utf8'> I/O discipline when opening files
+
+ open(my $fh,'<:utf8', 'anything');
+ my $line_of_utf8 = <$fh>;
+
+The I/O disciplines can also be specified more flexibly with
+the C<open> pragma; see L<open>:
+
+ use open ':utf8'; # input and output will be UTF-8
+ open X, ">utf8";
+ print X chr(0x100), "\n"; # this would have been UTF-8 without the pragma
+ close X;
+ open Y, "<utf8";
+ printf "%#x\n", ord(<Y>); # this should print 0x100
+ close Y;
+
+With the C<open> pragma you can use the C<:locale> discipline
+
+ $ENV{LANG} = 'ru_RU.KOI8-R';
+ # the :locale will probe the locale environment variables like LANG
+ use open OUT => ':locale'; # russki parusski
+ open(O, ">koi8");
+ print O chr(0x430); # Unicode CYRILLIC SMALL LETTER A = KOI8-R 0xc1
+ close O;
+ open(I, "<koi8");
+ printf "%#x\n", ord(<I>), "\n"; # this should print 0xc1
+ close I;
+
+or you can also use the C<':encoding(...)'> discipline
+
+ open(my $epic,'<:encoding(iso-8859-7)','iliad.greek');
+ my $line_of_iliad = <$epic>;
+
+Both of these methods install a transparent filter on the I/O stream that
+will convert data from the specified encoding when it is read in from the
+stream. In the first example the F<anything> file is assumed to be UTF-8
+encoded Unicode, in the second example the F<iliad.greek> file is assumed
+to be ISO-8858-7 encoded Greek, but the lines read in will be in both
+cases Unicode.
+
+The L<open> pragma affects all the C<open()> calls after the pragma by
+setting default disciplines. If you want to affect only certain
+streams, use explicit disciplines directly in the C<open()> call.
+
+You can switch encodings on an already opened stream by using
+C<binmode()>, see L<perlfunc/binmode>.
+
+The C<:locale> does not currently work with C<open()> and
+C<binmode()>, only with the C<open> pragma. The C<:utf8> and
+C<:encoding(...)> do work with all of C<open()>, C<binmode()>,
+and the C<open> pragma.
+
+Similarly, you may use these I/O disciplines on input streams to
+automatically convert data from the specified encoding when it is
+written to the stream.
+
+ open(my $unicode, '<:utf8', 'japanese.uni');
+ open(my $nihongo, '>:encoding(iso2022-jp)', 'japanese.jp');
+ while (<$unicode>) { print $nihongo }
+
+The naming of encodings, both by the C<open()> and by the C<open>
+pragma, is similarly understanding as with the C<encoding> pragma:
+C<koi8-r> and C<KOI8R> will both be understood.
+
+Common encodings recognized by ISO, MIME, IANA, and various other
+standardisation organisations are recognised, for a more detailed
+list see L<Encode>.
+
+C<read()> reads characters and returns the number of characters.
+C<seek()> and C<tell()> operate on byte counts, as do C<sysread()>
+and C<sysseek()>.
+
+Notice that because of the default behaviour "input is not UTF-8"
+it is easy to mistakenly write code that keeps on expanding a file
+by repeatedly encoding it in UTF-8:
+
+ # BAD CODE WARNING
+ open F, "file";
+ local $/; # read in the whole file
+ $t = <F>;
+ close F;
+ open F, ">:utf8", "file";
+ print F $t;
+ close F;
+
+If you run this code twice, the contents of the F<file> will be twice
+UTF-8 encoded. A C<use open ':utf8'> would have avoided the bug.
+
+=head2 Special Cases
+
+=over 4
+
+=item *
+
+Bit Complement Operator ~ And vec()
+
+The bit complement operator C<~> will produce surprising results if
+used on strings containing Unicode characters. The results are
+consistent with the internal UTF-8 encoding of the characters, but not
+with much else. So don't do that. Similarly for vec(): you will be
+operating on the UTF-8 bit patterns of the Unicode characters, not on
+the bytes, which is very probably not what you want.
+
+=item *
+
+Peeking At UTF-8
+
+One way of peeking inside the internal encoding of Unicode characters
+is to use C<unpack("C*", ...> to get the bytes, or C<unpack("H*", ...)>
+to display the bytes:
+
+ # this will print c4 80 for the UTF-8 bytes 0xc4 0x80
+ print join(" ", unpack("H*", pack("U", 0x100))), "\n";
+
+Yet another way would be to use the Devel::Peek module:
+
+ perl -MDevel::Peek -e 'Dump(chr(0x100))'
+
+That will show the UTF8 flag in FLAGS and both the UTF-8 bytes
+and Unicode characters in PV. See also later in this document
+the discussion about the C<is_utf8> function of the C<Encode> module.
+
+=back
+
+=head2 Advanced Topics
+
+=over 4
+
+=item *
+
+String Equivalence
+
+The question of string equivalence turns somewhat complicated
+in Unicode: what do you mean by equal?
+
+ Is C<LATIN CAPITAL LETTER A WITH ACUTE> equal to
+ C<LATIN CAPITAL LETTER A>?
+
+The short answer is that by default Perl compares equivalence
+(C<eq>, C<ne>) based only on code points of the characters.
+In the above case, no (because 0x00C1 != 0x0041). But sometimes any
+CAPITAL LETTER As being considered equal, or even any As of any case,
+would be desirable.
+
+The long answer is that you need to consider character normalization
+and casing issues: see L<Unicode::Normalize>, and Unicode Technical
+Reports #15 and #21, I<Unicode Normalization Forms> and I<Case
+Mappings>, http://www.unicode.org/unicode/reports/tr15/
+http://www.unicode.org/unicode/reports/tr21/
+
+As of Perl 5.8.0, the's regular expression case-ignoring matching
+implements only 1:1 semantics: one character matches one character.
+In I<Case Mappings> both 1:N and N:1 matches are defined.
+
+=item *
+
+String Collation
+
+People like to see their strings nicely sorted, or as Unicode
+parlance goes, collated. But again, what do you mean by collate?
+
+ Does C<LATIN CAPITAL LETTER A WITH ACUTE> come before or after
+ C<LATIN CAPITAL LETTER A WITH GRAVE>?
+
+The short answer is that by default Perl compares strings (C<lt>,
+C<le>, C<cmp>, C<ge>, C<gt>) based only on the code points of the
+characters. In the above case, after, since 0x00C1 > 0x00C0.
+
+The long answer is that "it depends", and a good answer cannot be
+given without knowing (at the very least) the language context.
+See L<Unicode::Collate>, and I<Unicode Collation Algorithm>
+http://www.unicode.org/unicode/reports/tr10/
+
+=back
+
+=head2 Miscellaneous
+
+=over 4
+
+=item *
+
+Character Ranges
+
+Character ranges in regular expression character classes (C</[a-z]/>)
+and in the C<tr///> (also known as C<y///>) operator are not magically
+Unicode-aware. What this means that C<[a-z]> will not magically start
+to mean "all alphabetic letters" (not that it does mean that even for
+8-bit characters, you should be using C</[[:alpha]]/> for that).
+
+For specifying things like that in regular expressions you can use the
+various Unicode properties, C<\pL> in this particular case. You can
+use Unicode code points as the end points of character ranges, but
+that means that particular code point range, nothing more. For
+further information, see L<perlunicode>.
+
+=item *
+
+String-To-Number Conversions
+
+Unicode does define several other decimal (and numeric) characters
+than just the familiar 0 to 9, such as the Arabic and Indic digits.
+Perl does not support string-to-number conversion for digits other
+than the 0 to 9 (and a to f for hexadecimal).
+
+=back
+
+=head2 Questions With Answers
+
+=over 4
+
+=item Will My Old Scripts Break?
+
+Very probably not. Unless you are generating Unicode characters
+somehow, any old behaviour should be preserved. About the only
+behaviour that has changed and which could start generating Unicode
+is the old behaviour of C<chr()> where supplying an argument more
+than 255 produced a character modulo 255 (for example, C<chr(300)>
+was equal to C<chr(45)>).
+
+=item How Do I Make My Scripts Work With Unicode?
+
+Very little work should be needed since nothing changes until you
+somehow generate Unicode data. The greatest trick will be getting
+input as Unicode, and for that see the earlier I/O discussion.
+
+=item How Do I Know Whether My String Is In Unicode?
+
+You shouldn't care. No, you really shouldn't. If you have
+to care (beyond the cases described above), it means that we
+didn't get the transparency of Unicode quite right.
+
+Okay, if you insist:
+
+ use Encode 'is_utf8';
+ print is_utf8($string) ? 1 : 0, "\n";
+
+But note that this doesn't mean that any of the characters in the
+string are necessary UTF-8 encoded, or that any of the characters have
+code points greater than 0xFF (255) or even 0x80 (128), or that the
+string has any characters at all. All the C<is_utf8()> does is to
+return the value of the internal "utf8ness" flag attached to the
+$string. If the flag is on, characters added to that string will be
+automatically upgraded to UTF-8 (and even then only if they really
+need to be upgraded, that is, if their code point is greater than 0xFF).
+
+Sometimes you might really need to know the byte length of a string
+instead of the character length. For that use the C<bytes> pragma
+and its only defined function C<length()>:
+
+ my $unicode = chr(0x100);
+ print length($unicode), "\n"; # will print 1
+ use bytes;
+ print length($unicode), "\n"; # will print 2 (the 0xC4 0x80 of the UTF-8)
+
+=item How Do I Detect Invalid UTF-8?
+
+Either
+
+ use Encode 'encode_utf8';
+ if (encode_utf8($string)) {
+ # valid
+ } else {
+ # invalid
+ }
+
+or
+
+ use warnings;
+ @chars = unpack("U0U*", "\xFF"); # will warn
+
+The warning will be C<Malformed UTF-8 character (byte 0xff) in
+unpack>. The "U0" means "expect strictly UTF-8 encoded Unicode".
+Without that the C<unpack("U*", ...)> would accept also data like
+C<chr(0xFF>).
+
+=item How Do I Convert Data Into UTF-8? Or Vice Versa?
+
+This probably isn't as useful (or simple) as you might think.
+Also, normally you shouldn't need to.
+
+In one sense what you are asking doesn't make much sense: UTF-8 is
+(intended as an) Unicode encoding, so converting "data" into UTF-8
+isn't meaningful unless you know in what character set and encoding
+the binary data is in, and in this case you can use C<Encode>.
+
+ use Encode 'from_to';
+ from_to($data, "iso-8859-1", "utf-8"); # from latin-1 to utf-8
+
+If you have ASCII (really 7-bit US-ASCII), you already have valid
+UTF-8, the lowest 128 characters of UTF-8 encoded Unicode and US-ASCII
+are equivalent.
+
+If you have Latin-1 (or want Latin-1), you can just use pack/unpack:
+
+ $latin1 = pack("C*", unpack("U*", $utf8));
+ $utf8 = pack("U*", unpack("C*", $latin1));
+
+(The same works for EBCDIC.)
+
+If you have a sequence of bytes you B<know> is valid UTF-8,
+but Perl doesn't know it yet, you can make Perl a believer, too:
+
+ use Encode 'decode_utf8';
+ $utf8 = decode_utf8($bytes);
+
+You can convert well-formed UTF-8 to a sequence of bytes, but if
+you just want to convert random binary data into UTF-8, you can't.
+Any random collection of bytes isn't well-formed UTF-8. You can
+use C<unpack("C*", $string)> for the former, and you can create
+well-formed Unicode/UTF-8 data by C<pack("U*", 0xff, ...)>.
+
+=item How Do I Display Unicode? How Do I Input Unicode?
+
+See http://www.hclrss.demon.co.uk/unicode/ and
+http://www.cl.cam.ac.uk/~mgk25/unicode.html
+
+=item How Does Unicode Work With Traditional Locales?
+
+In Perl, not very well. Avoid using locales through the C<locale>
+pragma. Use only one or the other.
+
+=back
+
+=head2 Hexadecimal Notation
+
+The Unicode standard prefers using hexadecimal notation because that
+shows better the division of Unicode into blocks of 256 characters.
+Hexadecimal is also simply shorter than decimal. You can use decimal
+notation, too, but learning to use hexadecimal just makes life easier
+with the Unicode standard.
+
+The C<0x> prefix means a hexadecimal number, the digits are 0-9 I<and>
+a-f (or A-F, case doesn't matter). Each hexadecimal digit represents
+four bits, or half a byte. C<print 0x..., "\n"> will show a
+hexadecimal number in decimal, and C<printf "%x\n", $decimal> will
+show a decimal number in hexadecimal. If you have just the
+"hexdigits" of a hexadecimal number, you can use the C<hex()>
+function.
+
+ print 0x0009, "\n"; # 9
+ print 0x000a, "\n"; # 10
+ print 0x000f, "\n"; # 15
+ print 0x0010, "\n"; # 16
+ print 0x0011, "\n"; # 17
+ print 0x0100, "\n"; # 256
+
+ print 0x0041, "\n"; # 65
+
+ printf "%x\n", 65; # 41
+ printf "%#x\n", 65; # 0x41
+
+ print hex("41"), "\n"; # 65
+
+=head2 Further Resources
+
+=over 4
+
+=item *
+
+Unicode Consortium
+
+ http://www.unicode.org/
+
+=item *
+
+Unicode FAQ
+
+ http://www.unicode.org/unicode/faq/
+
+=item *
+
+Unicode Glossary
+
+ http://www.unicode.org/glossary/
+
+=item *
+
+Unicode Useful Resources
+
+ http://www.unicode.org/unicode/onlinedat/resources.html
+
+=item *
+
+Unicode and Multilingual Support in HTML, Fonts, Web Browsers and Other Applications
+
+ http://www.hclrss.demon.co.uk/unicode/
+
+=item *
+
+UTF-8 and Unicode FAQ for Unix/Linux
+
+ http://www.cl.cam.ac.uk/~mgk25/unicode.html
+
+=item *
+
+Legacy Character Sets
+
+ http://www.czyborra.com/
+ http://www.eki.ee/letter/
+
+=item *
+
+The Unicode support files live within the Perl installation in the
+directory
+
+ $Config{installprivlib}/unicore
+
+in Perl 5.8.0 or newer, and
+
+ $Config{installprivlib}/unicode
+
+in the Perl 5.6 series. (The renaming to F<lib/unicore> was done to
+avoid naming conflicts with lib/Unicode in case-insensitive filesystems.)
+The main Unicode data file is F<Unicode.txt> (or F<Unicode.301> in
+Perl 5.6.1.) You can find the C<$Config{installprivlib}> by
+
+ perl "-V:installprivlib"
+
+Note that some of the files have been renamed from the Unicode
+standard since the Perl installation tries to live by the "8.3"
+filenaming restrictions. The renamings are shown in the
+accompanying F<rename> file.
+
+You can explore various information from the Unicode data files using
+the C<Unicode::UCD> module.
+
+=back
+
+=head1 SEE ALSO
+
+L<perlunicode>, L<Encode>, L<encoding>, L<open>, L<utf8>, L<bytes>,
+L<perlretut>, L<Unicode::Collate>, L<Unicode::Normalize>, L<Unicode::UCD>
+
+=head1 ACKNOWLEDGEMENTS
+
+Thanks to the kind readers of the perl5-porters@perl.org,
+perl-unicode@perl.org, linux-utf8@nl.linux.org, and unicore@unicode.org
+mailing lists for their valuable feedback.
+
+=head1 AUTHOR, COPYRIGHT, AND LICENSE
+
+Copyright 2001 Jarkko Hietaniemi <jhi@iki.fi>
+
+This document may be distributed under the same terms as Perl itself.
+++ /dev/null
-=head1 NAME
-
-perlunintro - Perl Unicode introduction
-
-=head1 DESCRIPTION
-
-This document gives a general idea of Unicode and how to use Unicode
-in Perl.
-
-=head2 Unicode
-
-Unicode is a character set standard with plans to cover all of the
-writing systems of the world, plus many other symbols.
-
-Unicode and ISO/IEC 10646 are coordinated standards that provide code
-points for the characters in almost all modern character set standards,
-covering more than 30 writing systems and hundreds of languages,
-including all commercially important modern languages. All characters
-in the largest Chinese, Japanese, and Korean dictionaries are also
-encoded. The standards will eventually cover almost all characters in
-more than 250 writing systems and thousands of languages.
-
-A Unicode I<character> is an abstract entity. It is not bound to any
-particular integer width, and especially not to the C language C<char>.
-Unicode is language neutral and display neutral: it doesn't encode the
-language of the text, and it doesn't define fonts or other graphical
-layout details. Unicode operates on characters and on text built from
-those characters.
-
-Unicode defines characters like C<LATIN CAPITAL LETTER A> or C<GREEK
-SMALL LETTER ALPHA>, and then unique numbers for those, hexadecimal
-0x0041 or 0x03B1 for those particular characters. Such unique
-numbers are called I<code points>.
-
-The Unicode standard prefers using hexadecimal notation for the code
-points. (In case this notation, numbers like 0x0041, is unfamiliar to
-you, take a peek at a later section, L</"Hexadecimal Notation">.)
-The Unicode standard uses the notation C<U+0041 LATIN CAPITAL LETTER A>,
-which gives the hexadecimal code point, and the normative name of
-the character.
-
-Unicode also defines various I<properties> for the characters, like
-"uppercase" or "lowercase", "decimal digit", or "punctuation":
-these properties are independent of the names of the characters.
-Furthermore, various operations on the characters like uppercasing,
-lowercasing, and collating (sorting), are defined.
-
-A Unicode character consists either of a single code point, or a
-I<base character> (like C<LATIN CAPITAL LETTER A>), followed by one or
-more I<modifiers> (like C<COMBINING ACUTE ACCENT>). This sequence of
-a base character and modifiers is called a I<combining character
-sequence>.
-
-Whether to call these combining character sequences, as a whole,
-"characters" depends on your point of view. If you are a programmer, you
-probably would tend towards seeing each element in the sequences as one
-unit, one "character", but from the user viewpoint, the sequence as a
-whole is probably considered one "character", since that's probably what
-it looks like in the context of the user's language.
-
-With this "as a whole" view of characters, the number of characters is
-open-ended. But in the programmer's "one unit is one character" point of
-view, the concept of "characters" is more deterministic, and so we take
-that point of view in this document: one "character" is one Unicode
-code point, be it a base character or a combining character.
-
-For some of the combinations there are I<precomposed> characters,
-for example C<LATIN CAPITAL LETTER A WITH ACUTE> is defined as
-a single code point. These precomposed characters are, however,
-often available only for some combinations, and mainly they are
-meant to support round-trip conversions between Unicode and legacy
-standards (like the ISO 8859), and in general case the composing
-method is more extensible. To support conversion between the
-different compositions of the characters, various I<normalization
-forms> are also defined.
-
-Because of backward compatibility with legacy encodings, the "a unique
-number for every character" breaks down a bit: "at least one number
-for every character" is closer to truth. (This happens when the same
-character has been encoded in several legacy encodings.) The converse
-is also not true: not every code point has an assigned character.
-Firstly, there are unallocated code points within otherwise used
-blocks. Secondly, there are special Unicode control characters that
-do not represent true characters.
-
-A common myth about Unicode is that it would be "16-bit", that is,
-0x10000 (or 65536) characters from 0x0000 to 0xFFFF. B<This is untrue.>
-Since Unicode 2.0 Unicode has been defined all the way up to 21 bits
-(0x10FFFF), and since 3.1 characters have been defined beyond 0xFFFF.
-The first 0x10000 characters are called the I<Plane 0>, or the I<Basic
-Multilingual Plane> (BMP). With the Unicode 3.1, 17 planes in all are
-defined (but nowhere near full of defined characters yet).
-
-Another myth is that the 256-character blocks have something to do
-with languages: a block per language. B<Also this is untrue.>
-The division into the blocks exists but it is almost completely
-accidental, an artifact of how the characters have been historically
-allocated. Instead, there is a concept called I<scripts>, which may
-be more useful: there is C<Latin> script, C<Greek> script, and so on.
-Scripts usually span several parts of several blocks. For further
-information see L<Unicode::UCD>.
-
-The Unicode code points are just abstract numbers. To input and
-output these abstract numbers, the numbers must be I<encoded> somehow.
-Unicode defines several I<character encoding forms>, of which I<UTF-8>
-is perhaps the most popular. UTF-8 is a variable length encoding that
-encodes Unicode characters as 1 to 6 bytes (only 4 with the currently
-defined characters). Other encodings are UTF-16 and UTF-32 and their
-big and little endian variants (UTF-8 is byteorder independent).
-The ISO/IEC 10646 defines the UCS-2 and UCS-4 encoding forms.
-
-For more information about encodings, for example to learn what
-I<surrogates> and I<byte order marks> (BOMs) are, see L<perlunicode>.
-
-=head2 Perl's Unicode Support
-
-Starting from Perl 5.6.0, Perl has had the capability of handling
-Unicode natively. The first recommended release for serious Unicode
-work is Perl 5.8.0, however. The maintenance release 5.6.1 fixed many
-of the problems of the initial implementation of Unicode, but for
-example regular expressions didn't really work with Unicode.
-
-B<Starting from Perl 5.8.0, the use of C<use utf8> is no longer
-necessary.> In earlier releases the C<utf8> pragma was used to declare
-that operations in the current block or file would be Unicode-aware.
-This model was found to be wrong, or at least clumsy: the Unicodeness
-is now carried with the data, not attached to the operations. (There
-is one remaining case where an explicit C<use utf8> is needed: if your
-Perl script is in UTF-8, you can use UTF-8 in your variable and
-subroutine names, and in your string and regular expression literals,
-by saying C<use utf8>. This is not the default because that would
-break existing scripts having legacy 8-bit data in them.)
-
-=head2 Perl's Unicode Model
-
-Perl supports both the old, pre-5.6, model of strings of eight-bit
-native bytes, and strings of Unicode characters. The principle is
-that Perl tries to keep its data as eight-bit bytes for as long as
-possible, but as soon as Unicodeness cannot be avoided, the data is
-transparently upgraded to Unicode.
-
-The internal encoding of Unicode in Perl is UTF-8. The internal
-encoding is normally hidden, however, and one need not and should not
-worry about the internal encoding at all: it is all just characters.
-
-Perl 5.8.0 will also support Unicode on EBCDIC platforms. There the
-support is somewhat harder to implement since additional conversions
-are needed at every step. Because of these difficulties the Unicode
-support won't be quite as full as in other, mainly ASCII-based,
-platforms (the Unicode support will be better than in the 5.6 series,
-which didn't work much at all for EBCDIC platform). On EBCDIC
-platforms the internal encoding form used is UTF-EBCDIC.
-
-=head2 Creating Unicode
-
-To create Unicode literals, use the C<\x{...}> notation in
-doublequoted strings:
-
- my $smiley = "\x{263a}";
-
-Similarly for regular expression literals
-
- $smiley =~ /\x{263a}/;
-
-At run-time you can use C<chr()>:
-
- my $hebrew_alef = chr(0x05d0);
-
-(See L</"Further Resources"> for how to find all these numeric codes.)
-
-Naturally, C<ord()> will do the reverse: turn a character to a code point.
-
-Note that C<\x..>, C<\x{..}> and C<chr(...)> for arguments less than
-0x100 (decimal 256) will generate an eight-bit character for backward
-compatibility with older Perls. For arguments of 0x100 or more,
-Unicode will always be produced. If you want UTF-8 always, use
-C<pack("U", ...)> instead of C<\x..>, C<\x{..}>, or C<chr()>.
-
-You can also use the C<charnames> pragma to invoke characters
-by name in doublequoted strings:
-
- use charnames ':full';
- my $arabic_alef = "\N{ARABIC LETTER ALEF}";
-
-And, as mentioned above, you can also C<pack()> numbers into Unicode
-characters:
-
- my $georgian_an = pack("U", 0x10a0);
-
-=head2 Handling Unicode
-
-Handling Unicode is for the most part transparent: just use the
-strings as usual. Functions like C<index()>, C<length()>, and
-C<substr()> will work on the Unicode characters; regular expressions
-will work on the Unicode characters (see L<perlunicode> and L<perlretut>).
-
-Note that Perl does B<not> consider combining character sequences
-to be characters, such for example
-
- use charnames ':full';
- print length("\N{LATIN CAPITAL LETTER A}\N{COMBINING ACUTE ACCENT}"), "\n";
-
-will print 2, not 1. The only exception is that regular expressions
-have C<\X> for matching a combining character sequence.
-
-When life is not quite so transparent is working with legacy
-encodings, and I/O, and certain special cases.
-
-=head2 Legacy Encodings
-
-When you combine legacy data and Unicode the legacy data needs
-to be upgraded to Unicode. Normally ISO 8859-1 (or EBCDIC, if
-applicable) is assumed. You can override this assumption by
-using the C<encoding> pragma, for example
-
- use encoding 'latin2'; # ISO 8859-2
-
-in which case literals (string or regular expression) and chr/ord
-in your whole script are assumed to produce Unicode characters from
-ISO 8859-2 code points. Note that the matching for the encoding
-names is forgiving: instead of C<latin2> you could have said
-C<Latin 2>, or C<iso8859-2>, and so forth. With just
-
- use encoding;
-
-first the environment variable C<PERL_ENCODING> will be consulted,
-and if that doesn't exist, ISO 8859-1 (Latin 1) will be assumed.
-
-The C<Encode> module knows about many encodings and it has interfaces
-for doing conversions between those encodings:
-
- use Encode 'from_to';
- from_to($data, "iso-8859-3", "utf-8"); # from legacy to utf-8
-
-=head2 Unicode I/O
-
-Normally writing out Unicode data
-
- print chr(0x100), "\n";
-
-will print out the raw UTF-8 bytes.
-
-But reading in correctly formed UTF-8 data will not magically turn
-the data into Unicode in Perl's eyes.
-
-You can use either the C<':utf8'> I/O discipline when opening files
-
- open(my $fh,'<:utf8', 'anything');
- my $line_of_utf8 = <$fh>;
-
-The I/O disciplines can also be specified more flexibly with
-the C<open> pragma; see L<open>:
-
- use open ':utf8'; # input and output will be UTF-8
- open X, ">utf8";
- print X chr(0x100), "\n"; # this would have been UTF-8 without the pragma
- close X;
- open Y, "<utf8";
- printf "%#x\n", ord(<Y>); # this should print 0x100
- close Y;
-
-With the C<open> pragma you can use the C<:locale> discipline
-
- $ENV{LANG} = 'ru_RU.KOI8-R';
- # the :locale will probe the locale environment variables like LANG
- use open OUT => ':locale'; # russki parusski
- open(O, ">koi8");
- print O chr(0x430); # Unicode CYRILLIC SMALL LETTER A = KOI8-R 0xc1
- close O;
- open(I, "<koi8");
- printf "%#x\n", ord(<I>), "\n"; # this should print 0xc1
- close I;
-
-or you can also use the C<':encoding(...)'> discipline
-
- open(my $epic,'<:encoding(iso-8859-7)','iliad.greek');
- my $line_of_iliad = <$epic>;
-
-Both of these methods install a transparent filter on the I/O stream that
-will convert data from the specified encoding when it is read in from the
-stream. In the first example the F<anything> file is assumed to be UTF-8
-encoded Unicode, in the second example the F<iliad.greek> file is assumed
-to be ISO-8858-7 encoded Greek, but the lines read in will be in both
-cases Unicode.
-
-The L<open> pragma affects all the C<open()> calls after the pragma by
-setting default disciplines. If you want to affect only certain
-streams, use explicit disciplines directly in the C<open()> call.
-
-You can switch encodings on an already opened stream by using
-C<binmode()>, see L<perlfunc/binmode>.
-
-The C<:locale> does not currently work with C<open()> and
-C<binmode()>, only with the C<open> pragma. The C<:utf8> and
-C<:encoding(...)> do work with all of C<open()>, C<binmode()>,
-and the C<open> pragma.
-
-Similarly, you may use these I/O disciplines on input streams to
-automatically convert data from the specified encoding when it is
-written to the stream.
-
- open(my $unicode, '<:utf8', 'japanese.uni');
- open(my $nihongo, '>:encoding(iso2022-jp)', 'japanese.jp');
- while (<$unicode>) { print $nihongo }
-
-The naming of encodings, both by the C<open()> and by the C<open>
-pragma, is similarly understanding as with the C<encoding> pragma:
-C<koi8-r> and C<KOI8R> will both be understood.
-
-Common encodings recognized by ISO, MIME, IANA, and various other
-standardisation organisations are recognised, for a more detailed
-list see L<Encode>.
-
-C<read()> reads characters and returns the number of characters.
-C<seek()> and C<tell()> operate on byte counts, as do C<sysread()>
-and C<sysseek()>.
-
-Notice that because of the default behaviour "input is not UTF-8"
-it is easy to mistakenly write code that keeps on expanding a file
-by repeatedly encoding it in UTF-8:
-
- # BAD CODE WARNING
- open F, "file";
- local $/; # read in the whole file
- $t = <F>;
- close F;
- open F, ">:utf8", "file";
- print F $t;
- close F;
-
-If you run this code twice, the contents of the F<file> will be twice
-UTF-8 encoded. A C<use open ':utf8'> would have avoided the bug.
-
-=head2 Special Cases
-
-=over 4
-
-=item *
-
-Bit Complement Operator ~ And vec()
-
-The bit complement operator C<~> will produce surprising results if
-used on strings containing Unicode characters. The results are
-consistent with the internal UTF-8 encoding of the characters, but not
-with much else. So don't do that. Similarly for vec(): you will be
-operating on the UTF-8 bit patterns of the Unicode characters, not on
-the bytes, which is very probably not what you want.
-
-=item *
-
-Peeking At UTF-8
-
-One way of peeking inside the internal encoding of Unicode characters
-is to use C<unpack("C*", ...> to get the bytes, or C<unpack("H*", ...)>
-to display the bytes:
-
- # this will print c4 80 for the UTF-8 bytes 0xc4 0x80
- print join(" ", unpack("H*", pack("U", 0x100))), "\n";
-
-Yet another way would be to use the Devel::Peek module:
-
- perl -MDevel::Peek -e 'Dump(chr(0x100))'
-
-That will show the UTF8 flag in FLAGS and both the UTF-8 bytes
-and Unicode characters in PV. See also later in this document
-the discussion about the C<is_utf8> function of the C<Encode> module.
-
-=back
-
-=head2 Advanced Topics
-
-=over 4
-
-=item *
-
-String Equivalence
-
-The question of string equivalence turns somewhat complicated
-in Unicode: what do you mean by equal?
-
- Is C<LATIN CAPITAL LETTER A WITH ACUTE> equal to
- C<LATIN CAPITAL LETTER A>?
-
-The short answer is that by default Perl compares equivalence
-(C<eq>, C<ne>) based only on code points of the characters.
-In the above case, no (because 0x00C1 != 0x0041). But sometimes any
-CAPITAL LETTER As being considered equal, or even any As of any case,
-would be desirable.
-
-The long answer is that you need to consider character normalization
-and casing issues: see L<Unicode::Normalize>, and Unicode Technical
-Reports #15 and #21, I<Unicode Normalization Forms> and I<Case
-Mappings>, http://www.unicode.org/unicode/reports/tr15/
-http://www.unicode.org/unicode/reports/tr21/
-
-As of Perl 5.8.0, the's regular expression case-ignoring matching
-implements only 1:1 semantics: one character matches one character.
-In I<Case Mappings> both 1:N and N:1 matches are defined.
-
-=item *
-
-String Collation
-
-People like to see their strings nicely sorted, or as Unicode
-parlance goes, collated. But again, what do you mean by collate?
-
- Does C<LATIN CAPITAL LETTER A WITH ACUTE> come before or after
- C<LATIN CAPITAL LETTER A WITH GRAVE>?
-
-The short answer is that by default Perl compares strings (C<lt>,
-C<le>, C<cmp>, C<ge>, C<gt>) based only on the code points of the
-characters. In the above case, after, since 0x00C1 > 0x00C0.
-
-The long answer is that "it depends", and a good answer cannot be
-given without knowing (at the very least) the language context.
-See L<Unicode::Collate>, and I<Unicode Collation Algorithm>
-http://www.unicode.org/unicode/reports/tr10/
-
-=back
-
-=head2 Miscellaneous
-
-=over 4
-
-=item *
-
-Character Ranges
-
-Character ranges in regular expression character classes (C</[a-z]/>)
-and in the C<tr///> (also known as C<y///>) operator are not magically
-Unicode-aware. What this means that C<[a-z]> will not magically start
-to mean "all alphabetic letters" (not that it does mean that even for
-8-bit characters, you should be using C</[[:alpha]]/> for that).
-
-For specifying things like that in regular expressions you can use the
-various Unicode properties, C<\pL> in this particular case. You can
-use Unicode code points as the end points of character ranges, but
-that means that particular code point range, nothing more. For
-further information, see L<perlunicode>.
-
-=item *
-
-String-To-Number Conversions
-
-Unicode does define several other decimal (and numeric) characters
-than just the familiar 0 to 9, such as the Arabic and Indic digits.
-Perl does not support string-to-number conversion for digits other
-than the 0 to 9 (and a to f for hexadecimal).
-
-=back
-
-=head2 Questions With Answers
-
-=over 4
-
-=item Will My Old Scripts Break?
-
-Very probably not. Unless you are generating Unicode characters
-somehow, any old behaviour should be preserved. About the only
-behaviour that has changed and which could start generating Unicode
-is the old behaviour of C<chr()> where supplying an argument more
-than 255 produced a character modulo 255 (for example, C<chr(300)>
-was equal to C<chr(45)>).
-
-=item How Do I Make My Scripts Work With Unicode?
-
-Very little work should be needed since nothing changes until you
-somehow generate Unicode data. The greatest trick will be getting
-input as Unicode, and for that see the earlier I/O discussion.
-
-=item How Do I Know Whether My String Is In Unicode?
-
-You shouldn't care. No, you really shouldn't. If you have
-to care (beyond the cases described above), it means that we
-didn't get the transparency of Unicode quite right.
-
-Okay, if you insist:
-
- use Encode 'is_utf8';
- print is_utf8($string) ? 1 : 0, "\n";
-
-But note that this doesn't mean that any of the characters in the
-string are necessary UTF-8 encoded, or that any of the characters have
-code points greater than 0xFF (255) or even 0x80 (128), or that the
-string has any characters at all. All the C<is_utf8()> does is to
-return the value of the internal "utf8ness" flag attached to the
-$string. If the flag is on, characters added to that string will be
-automatically upgraded to UTF-8 (and even then only if they really
-need to be upgraded, that is, if their code point is greater than 0xFF).
-
-Sometimes you might really need to know the byte length of a string
-instead of the character length. For that use the C<bytes> pragma
-and its only defined function C<length()>:
-
- my $unicode = chr(0x100);
- print length($unicode), "\n"; # will print 1
- use bytes;
- print length($unicode), "\n"; # will print 2 (the 0xC4 0x80 of the UTF-8)
-
-=item How Do I Detect Invalid UTF-8?
-
-Either
-
- use Encode 'encode_utf8';
- if (encode_utf8($string)) {
- # valid
- } else {
- # invalid
- }
-
-or
-
- use warnings;
- @chars = unpack("U0U*", "\xFF"); # will warn
-
-The warning will be C<Malformed UTF-8 character (byte 0xff) in
-unpack>. The "U0" means "expect strictly UTF-8 encoded Unicode".
-Without that the C<unpack("U*", ...)> would accept also data like
-C<chr(0xFF>).
-
-=item How Do I Convert Data Into UTF-8? Or Vice Versa?
-
-This probably isn't as useful (or simple) as you might think.
-Also, normally you shouldn't need to.
-
-In one sense what you are asking doesn't make much sense: UTF-8 is
-(intended as an) Unicode encoding, so converting "data" into UTF-8
-isn't meaningful unless you know in what character set and encoding
-the binary data is in, and in this case you can use C<Encode>.
-
- use Encode 'from_to';
- from_to($data, "iso-8859-1", "utf-8"); # from latin-1 to utf-8
-
-If you have ASCII (really 7-bit US-ASCII), you already have valid
-UTF-8, the lowest 128 characters of UTF-8 encoded Unicode and US-ASCII
-are equivalent.
-
-If you have Latin-1 (or want Latin-1), you can just use pack/unpack:
-
- $latin1 = pack("C*", unpack("U*", $utf8));
- $utf8 = pack("U*", unpack("C*", $latin1));
-
-(The same works for EBCDIC.)
-
-If you have a sequence of bytes you B<know> is valid UTF-8,
-but Perl doesn't know it yet, you can make Perl a believer, too:
-
- use Encode 'decode_utf8';
- $utf8 = decode_utf8($bytes);
-
-You can convert well-formed UTF-8 to a sequence of bytes, but if
-you just want to convert random binary data into UTF-8, you can't.
-Any random collection of bytes isn't well-formed UTF-8. You can
-use C<unpack("C*", $string)> for the former, and you can create
-well-formed Unicode/UTF-8 data by C<pack("U*", 0xff, ...)>.
-
-=item How Do I Display Unicode? How Do I Input Unicode?
-
-See http://www.hclrss.demon.co.uk/unicode/ and
-http://www.cl.cam.ac.uk/~mgk25/unicode.html
-
-=item How Does Unicode Work With Traditional Locales?
-
-In Perl, not very well. Avoid using locales through the C<locale>
-pragma. Use only one or the other.
-
-=back
-
-=head2 Hexadecimal Notation
-
-The Unicode standard prefers using hexadecimal notation because that
-shows better the division of Unicode into blocks of 256 characters.
-Hexadecimal is also simply shorter than decimal. You can use decimal
-notation, too, but learning to use hexadecimal just makes life easier
-with the Unicode standard.
-
-The C<0x> prefix means a hexadecimal number, the digits are 0-9 I<and>
-a-f (or A-F, case doesn't matter). Each hexadecimal digit represents
-four bits, or half a byte. C<print 0x..., "\n"> will show a
-hexadecimal number in decimal, and C<printf "%x\n", $decimal> will
-show a decimal number in hexadecimal. If you have just the
-"hexdigits" of a hexadecimal number, you can use the C<hex()>
-function.
-
- print 0x0009, "\n"; # 9
- print 0x000a, "\n"; # 10
- print 0x000f, "\n"; # 15
- print 0x0010, "\n"; # 16
- print 0x0011, "\n"; # 17
- print 0x0100, "\n"; # 256
-
- print 0x0041, "\n"; # 65
-
- printf "%x\n", 65; # 41
- printf "%#x\n", 65; # 0x41
-
- print hex("41"), "\n"; # 65
-
-=head2 Further Resources
-
-=over 4
-
-=item *
-
-Unicode Consortium
-
- http://www.unicode.org/
-
-=item *
-
-Unicode FAQ
-
- http://www.unicode.org/unicode/faq/
-
-=item *
-
-Unicode Glossary
-
- http://www.unicode.org/glossary/
-
-=item *
-
-Unicode Useful Resources
-
- http://www.unicode.org/unicode/onlinedat/resources.html
-
-=item *
-
-Unicode and Multilingual Support in HTML, Fonts, Web Browsers and Other Applications
-
- http://www.hclrss.demon.co.uk/unicode/
-
-=item *
-
-UTF-8 and Unicode FAQ for Unix/Linux
-
- http://www.cl.cam.ac.uk/~mgk25/unicode.html
-
-=item *
-
-Legacy Character Sets
-
- http://www.czyborra.com/
- http://www.eki.ee/letter/
-
-=item *
-
-The Unicode support files live within the Perl installation in the
-directory
-
- $Config{installprivlib}/unicore
-
-in Perl 5.8.0 or newer, and
-
- $Config{installprivlib}/unicode
-
-in the Perl 5.6 series. (The renaming to F<lib/unicore> was done to
-avoid naming conflicts with lib/Unicode in case-insensitive filesystems.)
-The main Unicode data file is F<Unicode.txt> (or F<Unicode.301> in
-Perl 5.6.1.) You can find the C<$Config{installprivlib}> by
-
- perl "-V:installprivlib"
-
-Note that some of the files have been renamed from the Unicode
-standard since the Perl installation tries to live by the "8.3"
-filenaming restrictions. The renamings are shown in the
-accompanying F<rename> file.
-
-You can explore various information from the Unicode data files using
-the C<Unicode::UCD> module.
-
-=back
-
-=head1 SEE ALSO
-
-L<perlunicode>, L<Encode>, L<encoding>, L<open>, L<utf8>, L<bytes>,
-L<perlretut>, L<Unicode::Collate>, L<Unicode::Normalize>, L<Unicode::UCD>
-
-=head1 ACKNOWLEDGEMENTS
-
-Thanks to the kind readers of the perl5-porters@perl.org,
-perl-unicode@perl.org, linux-utf8@nl.linux.org, and unicore@unicode.org
-mailing lists for their valuable feedback.
-
-=head1 AUTHOR, COPYRIGHT, AND LICENSE
-
-Copyright 2001 Jarkko Hietaniemi <jhi@iki.fi>
-
-This document may be distributed under the same terms as Perl itself.
projects / platform / upstream / perl.git / commitdiff