X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/393fec973b1b95a178b4b9600173880d9f93debf..288837b92d17bacae078dc0122755b34ca019ac6:/lib/utf8.pm diff --git a/lib/utf8.pm b/lib/utf8.pm index be7cc0b..43c7277 100644 --- a/lib/utf8.pm +++ b/lib/utf8.pm @@ -1,20 +1,22 @@ package utf8; -$^U = 1 if caller and caller eq 'main'; # they are unicode aware - # XXX split this out? +$utf8::hint_bits = 0x00800000; + +our $VERSION = '1.13'; sub import { - $^H |= 0x00800000; - $enc{caller()} = $_[1] if $_[1]; + $^H |= $utf8::hint_bits; } sub unimport { - $^H &= ~0x00800000; + $^H &= ~$utf8::hint_bits; } sub AUTOLOAD { require "utf8_heavy.pl"; - goto &$AUTOLOAD; + goto &$AUTOLOAD if defined &$AUTOLOAD; + require Carp; + Carp::croak("Undefined subroutine $AUTOLOAD called"); } 1; @@ -22,69 +24,192 @@ __END__ =head1 NAME -utf8 - Perl pragma to enable/disable UTF-8 in source code +utf8 - Perl pragma to enable/disable UTF-8 (or UTF-EBCDIC) in source code =head1 SYNOPSIS - use utf8; - no utf8; + use utf8; + no utf8; -=head1 DESCRIPTION + # Convert the internal representation of a Perl scalar to/from UTF-8. -WARNING: The implementation of Unicode support in Perl is incomplete. -Expect sudden and unannounced changes! + $num_octets = utf8::upgrade($string); + $success = utf8::downgrade($string[, $fail_ok]); -The C pragma tells the Perl parser to allow UTF-8 in the -program text in the current lexical scope. The C pragma -tells Perl to switch back to treating the source text as literal -bytes in the current lexical scope. - -This pragma is primarily a compatibility device. Perl versions -earlier than 5.6 allowed arbitrary bytes in source code, whereas -in future we would like to standardize on the UTF-8 encoding for -source text. Until UTF-8 becomes the default format for source -text, this pragma should be used to recognize UTF-8 in the source. -When UTF-8 becomes the standard source format, this pragma will -effectively become a no-op. + # Change each character of a Perl scalar to/from a series of + # characters that represent the UTF-8 bytes of each original character. -Enabling the C pragma has the following effects: + utf8::encode($string); # "\x{100}" becomes "\xc4\x80" + utf8::decode($string); # "\xc4\x80" becomes "\x{100}" -=over + $flag = utf8::is_utf8($string); # since Perl 5.8.1 + $flag = utf8::valid($string); -=item * +=head1 DESCRIPTION -Bytes in the source text that have their high-bit set will be treated -as being part of a literal UTF-8 character. This includes most literals -such as identifiers, string constants, constant regular expression patterns -and package names. +The C pragma tells the Perl parser to allow UTF-8 in the +program text in the current lexical scope (allow UTF-EBCDIC on EBCDIC based +platforms). The C pragma tells Perl to switch back to treating +the source text as literal bytes in the current lexical scope. -=item * +B The utility functions described below are +directly usable without C. + +Because it is not possible to reliably tell UTF-8 from native 8 bit +encodings, you need either a Byte Order Mark at the beginning of your +source code, or C, to instruct perl. + +When UTF-8 becomes the standard source format, this pragma will +effectively become a no-op. For convenience in what follows the term +I is used to refer to UTF-8 on ASCII and ISO Latin based +platforms and UTF-EBCDIC on EBCDIC based platforms. -As a side effect, when this pragma is used within the main package, -it also enables Unicode character semantics for the entire program. -See L for more on that. +See also the effects of the C<-C> switch and its cousin, the +C<$ENV{PERL_UNICODE}>, in L. -[XXX: split this out into separate "pragma" and/or -C command-line -switch?] +Enabling the C pragma has the following effect: + +=over 4 =item * -In the absence of inputs marked as UTF-8, regular expressions within the -scope of this pragma will default to using character semantics instead -of byte semantics. +Bytes in the source text that have their high-bit set will be treated +as being part of a literal UTF-X sequence. This includes most +literals such as identifier names, string constants, and constant +regular expression patterns. + +On EBCDIC platforms characters in the Latin 1 character set are +treated as being part of a literal UTF-EBCDIC character. + +=back - @bytes_or_chars = split //, $data; # may split to bytes if data - # $data isn't UTF-8 - { - use utf8; # force char semantics - @chars = split //, $data; # splits characters - } +Note that if you have bytes with the eighth bit on in your script +(for example embedded Latin-1 in your string literals), C +will be unhappy since the bytes are most probably not well-formed +UTF-X. If you want to have such bytes under C, you can disable +this pragma until the end the block (or file, if at top level) by +C. + +=head2 Utility functions + +The following functions are defined in the C package by the +Perl core. You do not need to say C to use these and in fact +you should not say that unless you really want to have UTF-8 source code. -[XXX: Should this should be enabled like chr()/sprintf("%c") by looking -at $^U instead?] +=over 4 + +=item * $num_octets = utf8::upgrade($string) + +Converts in-place the internal representation of the string from an octet +sequence in the native encoding (Latin-1 or EBCDIC) to I. The +logical character sequence itself is unchanged. If I<$string> is already +stored as I, then this is a no-op. Returns the +number of octets necessary to represent the string as I. Can be +used to make sure that the UTF-8 flag is on, so that C<\w> or C +work as Unicode on strings containing characters in the range 0x80-0xFF +(on ASCII and derivatives). + +B +Therefore Encode is recommended for the general purposes; see also +L. + +=item * $success = utf8::downgrade($string[, $fail_ok]) + +Converts in-place the internal representation of the string from +I to the equivalent octet sequence in the native encoding (Latin-1 +or EBCDIC). The logical character sequence itself is unchanged. If +I<$string> is already stored as native 8 bit, then this is a no-op. Can +be used to +make sure that the UTF-8 flag is off, e.g. when you want to make sure +that the substr() or length() function works with the usually faster +byte algorithm. + +Fails if the original I sequence cannot be represented in the +native 8 bit encoding. On failure dies or, if the value of I<$fail_ok> is +true, returns false. + +Returns true on success. + +B +Therefore Encode is recommended for the general purposes; see also +L. + +=item * utf8::encode($string) + +Converts in-place the character sequence to the corresponding octet +sequence in I. That is, every (possibly wide) character gets +replaced with a sequence of one or more characters that represent the +individual I bytes of the character. The UTF8 flag is turned off. +Returns nothing. + + my $a = "\x{100}"; # $a contains one character, with ord 0x100 + utf8::encode($a); # $a contains two characters, with ords 0xc4 and + # 0x80 + +B +Therefore Encode is recommended for the general purposes; see also +L. + +=item * $success = utf8::decode($string) + +Attempts to convert in-place the octet sequence encoded as I to the +corresponding character sequence. That is, it replaces each sequence of +characters in the string whose ords represent a valid UTF-X byte +sequence, with the corresponding single character. The UTF-8 flag is +turned on only if the source string contains multiple-byte I +characters. If I<$string> is invalid as I, returns false; +otherwise returns true. + + my $a = "\xc4\x80"; # $a contains two characters, with ords + # 0xc4 and 0x80 + utf8::decode($a); # $a contains one character, with ord 0x100 + +B +Therefore Encode is recommended for the general purposes; see also +L. + +=item * $flag = utf8::is_utf8($string) + +(Since Perl 5.8.1) Test whether I<$string> is marked internally as encoded in +UTF-8. Functionally the same as Encode::is_utf8(). + +=item * $flag = utf8::valid($string) + +[INTERNAL] Test whether I<$string> is in a consistent state regarding +UTF-8. Will return true if it is well-formed UTF-8 and has the UTF-8 flag +on B if I<$string> is held as bytes (both these states are 'consistent'). +Main reason for this routine is to allow Perl's test suite to check +that operations have left strings in a consistent state. You most +probably want to use utf8::is_utf8() instead. + +=back + +C is like C, but the UTF8 flag is +cleared. See L for more on the UTF8 flag and the C API +functions C, C, C, +and C, which are wrapped by the Perl functions +C, C, C and +C. Also, the functions utf8::is_utf8, utf8::valid, +utf8::encode, utf8::decode, utf8::upgrade, and utf8::downgrade are +actually internal, and thus always available, without a C +statement. + +=head1 BUGS + +One can have Unicode in identifier names, but not in package/class or +subroutine names. While some limited functionality towards this does +exist as of Perl 5.8.0, that is more accidental than designed; use of +Unicode for the said purposes is unsupported. + +One reason of this unfinishedness is its (currently) inherent +unportability: since both package names and subroutine names may need +to be mapped to file and directory names, the Unicode capability of +the filesystem becomes important-- and there unfortunately aren't +portable answers. =head1 SEE ALSO -L, L +L, L, L, L, L =cut