diff options
| -rw-r--r-- | lib/utf8.pm | 20 | ||||
| -rw-r--r-- | pod/perldelta.pod | 13 | ||||
| -rw-r--r-- | pod/perltodo.pod | 20 | ||||
| -rw-r--r-- | pod/perlunicode.pod | 2 | ||||
| -rw-r--r-- | pod/perluniintro.pod | 2 | ||||
| -rw-r--r-- | toke.c | 6 |
6 files changed, 56 insertions, 7 deletions
diff --git a/lib/utf8.pm b/lib/utf8.pm index e0c4ac1966..5a37aecba8 100644 --- a/lib/utf8.pm +++ b/lib/utf8.pm @@ -57,9 +57,10 @@ Enabling the C<utf8> pragma has the following effect: 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 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. +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 @@ -131,6 +132,19 @@ functions utf8::valid, utf8::encode, utf8::decode, utf8::upgrade, and utf8::downgrade are always available, without a C<require utf8> statement-- this may change in future releases. +=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<perlunicode>, L<bytes> diff --git a/pod/perldelta.pod b/pod/perldelta.pod index e6a4fe38d3..67806a92c1 100644 --- a/pod/perldelta.pod +++ b/pod/perldelta.pod @@ -3284,6 +3284,19 @@ In case of failure please try running them manually, for example ./perl -Ilib ext/Time/HiRes/HiRes.t +=head2 Unicode in package/class and subroutine names does not work + +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. + =head2 UNICOS/mk =over 4 diff --git a/pod/perltodo.pod b/pod/perltodo.pod index 0e5d8a74ef..5f9a6cf2d0 100644 --- a/pod/perltodo.pod +++ b/pod/perltodo.pod @@ -98,7 +98,25 @@ UTF-8 identifier names should probably be canonicalized: NFC? UTF-8 in package names and sub names? The first is problematic because of the mapping to pathnames, ditto for the second one if -one does autosplitting, for example. +one does autosplitting, for example. Some of this works already +in 5.8.0, but essentially it is unsupported. Constructs to consider, +at the very least: + + use utf8; + package UnicodePackage; + sub new { bless {}, shift }; + sub UnicodeMethod1 { ... $_[0]->UnicodeMethod2(...) ... } + sub UnicodeMethod2 { ... } # in here caller(0) should contain Unicode + ... + package main; + my $x = UnicodePackage->new; + print ref $x, "\n"; # should be Unicode + $x->UnicodeMethod1(...); + my $y = UnicodeMethod3 UnicodePackage ...; + +In the above all I<UnicodeXxx> contain (identifier-worthy) characters +beyond the code point 255, for example 256. Wherever package/class or +subroutine names can be returned needs to be checked for Unicodeness. =back diff --git a/pod/perlunicode.pod b/pod/perlunicode.pod index 25d512e70e..0aec6fee11 100644 --- a/pod/perlunicode.pod +++ b/pod/perlunicode.pod @@ -37,7 +37,7 @@ included to enable recognition of UTF-8 in the Perl scripts themselves (in string or regular expression literals, or in identifier names) on ASCII-based machines or to recognize UTF-EBCDIC on EBCDIC-based machines. B<These are the only times when an explicit C<use utf8> -is needed.> +is needed.> See L<utf8>. You can also use the C<encoding> pragma to change the default encoding of the data in your script; see L<encoding>. diff --git a/pod/perluniintro.pod b/pod/perluniintro.pod index 1468ae3282..cc11dde928 100644 --- a/pod/perluniintro.pod +++ b/pod/perluniintro.pod @@ -132,7 +132,7 @@ operations. Only one case remains where an explicit C<use utf8> is needed: if your Perl script itself is encoded in UTF-8, you can use UTF-8 in your identifier names, and in string and regular expression literals, by saying C<use utf8>. This is not the default because -scripts with legacy 8-bit data in them would break. +scripts with legacy 8-bit data in them would break. See L<utf8>. =head2 Perl's Unicode Model @@ -1870,7 +1870,7 @@ S_intuit_more(pTHX_ register char *s) * Method if it's "foo $bar" * Not a method if it's really "print foo $bar" * Method if it's really "foo package::" (interpreted as package->foo) - * Not a method if bar is known to be a subroutne ("sub bar; foo bar") + * Not a method if bar is known to be a subroutine ("sub bar; foo bar") * Not a method if bar is a filehandle or package, but is quoted with * => */ @@ -3913,6 +3913,10 @@ Perl_yylex(pTHX) CLINE; yylval.opval = (OP*)newSVOP(OP_CONST, 0, sv); yylval.opval->op_private = OPpCONST_BARE; + /* UTF-8 package name? */ + if (UTF && !IN_BYTES && + is_utf8_string((U8*)SvPVX(sv), SvCUR(sv))) + SvUTF8_on(sv); /* And if "Foo::", then that's what it certainly is. */ |