X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2Fopen.pm;h=c2940931b77f39b837739c725031d6c92b22d5c2;hb=5fef21a34e2a36dc7c83d55110ccc5c57cc7d14d;hp=b535d88239a75507a773fb5db1e6546441ffc3f6;hpb=725d232a70026302b7898692e2e17c43b9ad4e76;p=p5sagit%2Fp5-mst-13.2.git diff --git a/lib/open.pm b/lib/open.pm index b535d88..c294093 100644 --- a/lib/open.pm +++ b/lib/open.pm @@ -1,12 +1,13 @@ package open; +use warnings; use Carp; -$open::hint_bits = 0x20000; +$open::hint_bits = 0x20000; # HINT_LOCALIZE_HH our $VERSION = '1.01'; my $locale_encoding; -sub in_locale { $^H & $locale::hint_bits } +sub in_locale { $^H & ($locale::hint_bits || 0)} sub _get_locale_encoding { unless (defined $locale_encoding) { @@ -16,16 +17,17 @@ sub _get_locale_encoding { I18N::Langinfo->import(qw(langinfo CODESET)); $locale_encoding = langinfo(CODESET()); }; - unless ($@) { - print "# locale_encoding = $locale_encoding\n"; - } my $country_language; + + no warnings 'uninitialized'; + if (not $locale_encoding && in_locale()) { if ($ENV{LC_ALL} =~ /^([^.]+)\.([^.]+)$/) { ($country_language, $locale_encoding) = ($1, $2); } elsif ($ENV{LANG} =~ /^([^.]+)\.([^.]+)$/) { ($country_language, $locale_encoding) = ($1, $2); } + # LANGUAGE affects only LC_MESSAGES only on glibc } elsif (not $locale_encoding) { if ($ENV{LC_ALL} =~ /\butf-?8\b/i || $ENV{LANG} =~ /\butf-?8\b/i) { @@ -45,6 +47,8 @@ sub _get_locale_encoding { $locale_encoding = 'euc-jp'; } elsif ($country_language =~ /^ko_KR|korean?$/i) { $locale_encoding = 'euc-kr'; + } elsif ($country_language =~ /^zh_CN|chin(?:a|ese)?$/i) { + $locale_encoding = 'euc-cn'; } elsif ($country_language =~ /^zh_TW|taiwan(?:ese)?$/i) { $locale_encoding = 'euc-tw'; } @@ -56,7 +60,8 @@ sub _get_locale_encoding { sub import { my ($class,@args) = @_; - croak("`use open' needs explicit list of disciplines") unless @args; + croak("`use open' needs explicit list of PerlIO layers") unless @args; + my $std; $^H |= $open::hint_bits; my ($in,$out) = split(/\0/,(${^OPEN} || "\0"), -1); while (@args) { @@ -65,6 +70,9 @@ sub import { if ($type =~ /^:?(utf8|locale|encoding\(.+\))$/) { $type = 'IO'; $dscp = ":$1"; + } elsif ($type eq ':std') { + $std = 1; + next; } else { $dscp = shift(@args) || ''; } @@ -75,16 +83,20 @@ sub import { use Encode; _get_locale_encoding() unless defined $locale_encoding; - croak "Cannot figure out an encoding to use" + (warnings::warnif("layer", "Cannot figure out an encoding to use"), last) unless defined $locale_encoding; if ($locale_encoding =~ /^utf-?8$/i) { $layer = "utf8"; } else { $layer = "encoding($locale_encoding)"; } + $std = 1; } else { - unless(PerlIO::Layer::->find($layer)) { - carp("Unknown discipline layer '$layer'"); + my $target = $layer; # the layer name itself + $target =~ s/^(\w+)\(.+\)$/$1/; # strip parameters + + unless(PerlIO::Layer::->find($target,1)) { + warnings::warnif("layer", "Unknown PerlIO layer '$target'"); } } push(@val,":$layer"); @@ -92,7 +104,6 @@ sub import { $^H{"open_$type"} = $layer; } } - # print "# type = $type, val = @val\n"; if ($type eq 'IN') { $in = join(' ',@val); } @@ -103,10 +114,28 @@ sub import { $in = $out = join(' ',@val); } else { - croak "Unknown discipline class '$type'"; + croak "Unknown PerlIO layer class '$type'"; + } + } + ${^OPEN} = join("\0",$in,$out) if $in or $out; + if ($std) { + if ($in) { + if ($in =~ /:utf8\b/) { + binmode(STDIN, ":utf8"); + } elsif ($in =~ /(\w+\(.+\))/) { + binmode(STDIN, ":$1"); + } + } + if ($out) { + if ($out =~ /:utf8\b/) { + binmode(STDOUT, ":utf8"); + binmode(STDERR, ":utf8"); + } elsif ($out =~ /(\w+\(.+\))/) { + binmode(STDOUT, ":$1"); + binmode(STDERR, ":$1"); + } } } - ${^OPEN} = join("\0",$in,$out); } 1; @@ -114,11 +143,11 @@ __END__ =head1 NAME -open - perl pragma to set default disciplines for input and output +open - perl pragma to set default PerlIO layers for input and output =head1 SYNOPSIS - use open IN => ":crlf", OUT => ":raw"; + use open IN => ":crlf", OUT => ":bytes"; use open OUT => ':utf8'; use open IO => ":encoding(iso-8859-7)"; @@ -128,19 +157,18 @@ open - perl pragma to set default disciplines for input and output use open ':locale'; use open ':encoding(iso-8859-7)'; + use open ':std'; + =head1 DESCRIPTION -Full-fledged support for I/O disciplines is now implemented provided +Full-fledged support for I/O layers is now implemented provided Perl is configured to use PerlIO as its IO system (which is now the default). The C pragma serves as one of the interfaces to declare default -"layers" (aka disciplines) for all I/O. - -The C pragma is used to declare one or more default layers for -I/O operations. Any open(), readpipe() (aka qx//) and similar -operators found within the lexical scope of this pragma will use the -declared defaults. +"layers" (also known as "disciplines") for all I/O. Any open(), +readpipe() (aka qx//) and similar operators found within the lexical +scope of this pragma will use the declared defaults. With the C subpragma you can declare the default layers of input streams, and with the C subpragma you can declare @@ -149,7 +177,7 @@ you can control both input and output streams simultaneously. If you have a legacy encoding, you can use the C<:encoding(...)> tag. -if you want to set your encoding disciplines based on your +if you want to set your encoding layers based on your locale environment variables, you can use the C<:locale> tag. For example: @@ -178,20 +206,67 @@ and these use open ':encoding(iso-8859-7)'; use open IO => ':encoding(iso-8859-7)'; +The matching of encoding names is loose: case does not matter, and +many encodings have several aliases. See L for +details and the list of supported locales. + +Note that C<:utf8> PerlIO layer must always be specified exactly like +that, it is not subject to the loose matching of encoding names. + When open() is given an explicit list of layers they are appended to the list declared using this pragma. -Directory handles may also support disciplines in future. +The C<:std> subpragma on its own has no effect, but if combined with +the C<:utf8> or C<:encoding> subpragmas, it converts the standard +filehandles (STDIN, STDOUT, STDERR) to comply with encoding selected +for input/output handles. For example, if both input and out are +chosen to be C<:utf8>, a C<:std> will mean that STDIN, STDOUT, and +STDERR are also in C<:utf8>. On the other hand, if only output is +chosen to be in C<< :encoding(koi8r) >>, a C<:std> will cause only the +STDOUT and STDERR to be in C. The C<:locale> subpragma +implicitly turns on C<:std>. + +The logic of C<:locale> is as follows: + +=over 4 + +=item 1. + +If the platform supports the langinfo(CODESET) interface, the codeset +returned is used as the default encoding for the open pragma. + +=item 2. + +If 1. didn't work but we are under the locale pragma, the environment +variables LC_ALL and LANG (in that order) are matched for encodings +(the part after C<.>, if any), and if any found, that is used +as the default encoding for the open pragma. + +=item 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, C<:utf8> is used as the default encoding for the open +pragma. + +=back + +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 +B, is UTF-8. + +Directory handles may also support PerlIO layers in the future. =head1 NONPERLIO FUNCTIONALITY If Perl is not built to use PerlIO as its IO system then only the two -pseudo-disciplines ":raw" and ":crlf" are available. +pseudo-layers C<:bytes> and C<:crlf> are available. -The ":raw" discipline corresponds to "binary mode" and the ":crlf" -discipline corresponds to "text mode" on platforms that distinguish +The C<:bytes> layer corresponds to "binary mode" and the C<:crlf> +layer corresponds to "text mode" on platforms that distinguish between the two modes when opening files (which is many DOS-like -platforms, including Windows). These two disciplines are no-ops on +platforms, including Windows). These two layers are no-ops on platforms where binmode() is a no-op, but perform their functions everywhere if PerlIO is enabled.