From: Philip Newton Date: Mon, 1 Apr 2002 17:06:18 +0000 (+0200) Subject: BOM, 0xFFFE, 0xFEFF, etc. X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=274085e3d0d92fea31afce1cf16bad209874ec70;p=p5sagit%2Fp5-mst-13.2.git BOM, 0xFFFE, 0xFEFF, etc. Message-ID: p4raw-id: //depot/perl@15656 --- diff --git a/lib/charnames.pm b/lib/charnames.pm index 3209f29..549a8c2 100644 --- a/lib/charnames.pm +++ b/lib/charnames.pm @@ -104,7 +104,7 @@ sub charnames ## ## Now know where in the string the name starts. - ## The code, in hex, is befor that. + ## The code, in hex, is before that. ## ## The code can be 4-6 characters long, so we've got to sort of ## go look for it, just after the newline that comes before $off[0]. @@ -181,7 +181,7 @@ my %viacode; sub viacode { if (@_ != 1) { - carp "charnames::viacode() expects one numeric argument"; + carp "charnames::viacode() expects one argument"; return () } @@ -208,8 +208,6 @@ sub viacode if ($txt =~ m/^$hex\t\t(.+)/m) { return $viacode{$hex} = $1; - } elsif ($hex eq 'FEFF') { - return $viacode{$hex} = "BYTE ORDER MARK"; } else { carp "Unknown charcode '$hex'"; return "\x{FFFD}"; @@ -244,7 +242,7 @@ __END__ =head1 NAME -charnames - define character names for C<\N{named}> string literal escapes. +charnames - define character names for C<\N{named}> string literal escapes =head1 SYNOPSIS @@ -336,9 +334,12 @@ prints "FOUR TEARDROP-SPOKED ASTERISK". Returns undef if no name is known for the code. -This works only for the standard names, and does not yet aply +This works only for the standard names, and does not yet apply to custom translators. +Notice that the name returned for of U+FEFF is "ZERO WIDTH NO-BREAK +SPACE", not "BYTE ORDER MARK". + =head1 charnames::vianame(code) Returns the code point indicated by the name. diff --git a/lib/charnames.t b/lib/charnames.t index 730ce18..1beecf3 100644 --- a/lib/charnames.t +++ b/lib/charnames.t @@ -193,7 +193,7 @@ print "ok 30\n"; print "not " unless "\N{NEL}" =~ $nel; print "ok 31\n"; -print "not " unless "\N{BYTE ORDER MARK}" eq chr(0xFFFE); +print "not " unless "\N{BYTE ORDER MARK}" eq chr(0xFEFF); print "ok 32\n"; print "not " unless "\N{BOM}" eq chr(0xFEFF); @@ -217,6 +217,6 @@ print "ok 33\n"; print "ok 37\n"; } -print "not " unless charnames::viacode(0xFEFF) eq "BYTE ORDER MARK"; +print "not " unless charnames::viacode(0xFEFF) eq "ZERO WIDTH NO-BREAK SPACE"; print "ok 38\n";