package charnames;
use strict;
use warnings;
-use Carp;
-use File::Spec;
-our $VERSION = '1.02';
-
-use bytes (); # for $bytes::hint_bits
-$charnames::hint_bits = 0x20000; # HINT_LOCALIZE_HH
-
-my %alias1 = (
- # Icky 3.2 names with parentheses.
- 'LINE FEED' => 'LINE FEED (LF)',
- 'FORM FEED' => 'FORM FEED (FF)',
- 'CARRIAGE RETURN' => 'CARRIAGE RETURN (CR)',
- 'NEXT LINE' => 'NEXT LINE (NEL)',
- # Convenience.
- 'LF' => 'LINE FEED (LF)',
- 'FF' => 'FORM FEED (FF)',
- 'CR' => 'CARRIAGE RETURN (CR)',
- 'NEL' => 'NEXT LINE (NEL)',
- # More convenience. For futher convencience,
- # it is suggested some way using using the NamesList
- # aliases is implemented.
- 'ZWNJ' => 'ZERO WIDTH NON-JOINER',
- 'ZWJ' => 'ZERO WIDTH JOINER',
- 'BOM' => 'BYTE ORDER MARK',
- );
-
-my %alias2 = (
- # Pre-3.2 compatibility (only for the first 256 characters).
- 'HORIZONTAL TABULATION' => 'CHARACTER TABULATION',
- 'VERTICAL TABULATION' => 'LINE TABULATION',
- 'FILE SEPARATOR' => 'INFORMATION SEPARATOR FOUR',
- 'GROUP SEPARATOR' => 'INFORMATION SEPARATOR THREE',
- 'RECORD SEPARATOR' => 'INFORMATION SEPARATOR TWO',
- 'UNIT SEPARATOR' => 'INFORMATION SEPARATOR ONE',
- 'PARTIAL LINE DOWN' => 'PARTIAL LINE FORWARD',
- 'PARTIAL LINE UP' => 'PARTIAL LINE BACKWARD',
- );
-
-my %alias3 = (
- # User defined aliasses. Even more convenient :)
- );
-my $txt;
-
-sub alias (@)
-{
- @_ or return %alias3;
- my $alias = ref $_[0] ? $_[0] : { @_ };
- @alias3{keys %$alias} = values %$alias;
-} # alias
-
-sub alias_file ($)
-{
- my ($arg, $file) = @_;
- if (-f $arg && File::Spec->file_name_is_absolute ($arg)) {
- $file = $arg;
- }
- elsif ($arg =~ m/^\w+$/) {
- $file = "unicore/${arg}_alias.pl";
- }
- else {
- croak "Charnames alias files can only have identifier characters";
- }
- if (my @alias = do $file) {
- @alias == 1 && !defined $alias[0] and
- croak "$file cannot be used as alias file for charnames";
- @alias % 2 and
- croak "$file did not return a (valid) list of alias pairs";
- alias (@alias);
- return (1);
- }
- 0;
-} # alias_file
-
-# This is not optimized in any way yet
-sub charnames
-{
- my $name = shift;
-
- if (exists $alias1{$name}) {
- $name = $alias1{$name};
- }
- elsif (exists $alias2{$name}) {
- require warnings;
- warnings::warnif('deprecated', qq{Unicode character name "$name" is deprecated, use "$alias2{$name}" instead});
- $name = $alias2{$name};
- }
- elsif (exists $alias3{$name}) {
- $name = $alias3{$name};
- }
-
- my $ord;
- my @off;
- my $fname;
-
- if ($name eq "BYTE ORDER MARK") {
- $fname = $name;
- $ord = 0xFEFF;
- } else {
- ## Suck in the code/name list as a big string.
- ## Lines look like:
- ## "0052\t\tLATIN CAPITAL LETTER R\n"
- $txt = do "unicore/Name.pl" unless $txt;
-
- ## @off will hold the index into the code/name string of the start and
- ## end of the name as we find it.
-
- ## If :full, look for the name exactly
- if ($^H{charnames_full} and $txt =~ /\t\t\Q$name\E$/m) {
- @off = ($-[0], $+[0]);
- }
-
- ## If we didn't get above, and :short allowed, look for the short name.
- ## The short name is like "greek:Sigma"
- unless (@off) {
- if ($^H{charnames_short} and $name =~ /^(.+?):(.+)/s) {
- my ($script, $cname) = ($1, $2);
- my $case = $cname =~ /[[:upper:]]/ ? "CAPITAL" : "SMALL";
- if ($txt =~ m/\t\t\U$script\E (?:$case )?LETTER \U\Q$cname\E$/m) {
- @off = ($-[0], $+[0]);
- }
- }
- }
-
- ## If we still don't have it, check for the name among the loaded
- ## scripts.
- if (not @off) {
- my $case = $name =~ /[[:upper:]]/ ? "CAPITAL" : "SMALL";
- for my $script (@{$^H{charnames_scripts}}) {
- if ($txt =~ m/\t\t$script (?:$case )?LETTER \U\Q$name\E$/m) {
- @off = ($-[0], $+[0]);
- last;
- }
- }
- }
-
- ## If we don't have it by now, give up.
- unless (@off) {
- carp "Unknown charname '$name'";
- return "\x{FFFD}";
- }
+our $VERSION = '1.30';
+use unicore::Name; # mktables-generated algorithmically-defined names
+use _charnames (); # The submodule for this where most of the work gets done
- ##
- ## Now know where in the string the name starts.
- ## 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].
- ##
- ## This would be much easier if unicore/Name.pl had info in
- ## a name/code order, instead of code/name order.
- ##
- ## The +1 after the rindex() is to skip past the newline we're finding,
- ## or, if the rindex() fails, to put us to an offset of zero.
- ##
- my $hexstart = rindex($txt, "\n", $off[0]) + 1;
-
- ## we know where it starts, so turn into number -
- ## the ordinal for the char.
- $ord = hex substr($txt, $hexstart, $off[0] - $hexstart);
- }
+use bytes (); # for $bytes::hint_bits
+use re "/aa"; # Everything in here should be ASCII
- if ($^H & $bytes::hint_bits) { # "use bytes" in effect?
- use bytes;
- return chr $ord if $ord <= 255;
- my $hex = sprintf "%04x", $ord;
- if (not defined $fname) {
- $fname = substr $txt, $off[0] + 2, $off[1] - $off[0] - 2;
- }
- croak "Character 0x$hex with name '$fname' is above 0xFF";
- }
+# Translate between Unicode character names and their code points.
+# This is a wrapper around the submodule C<_charnames>. This design allows
+# C<_charnames> to be autoloaded to enable use of \N{...}, but requires this
+# module to be explicitly requested for the functions API.
- no warnings 'utf8'; # allow even illegal characters
- return pack "U", $ord;
-} # charnames
+$Carp::Internal{ (__PACKAGE__) } = 1;
sub import
{
shift; ## ignore class name
+ _charnames->import(@_);
+}
- if (not @_) {
- carp("`use charnames' needs explicit imports list");
- }
- $^H |= $charnames::hint_bits;
- $^H{charnames} = \&charnames ;
-
- ##
- ## fill %h keys with our @_ args.
- ##
- my ($promote, %h, @args) = (0);
- while (@_ and $_ = shift) {
- if ($_ eq ":alias") {
- @_ or
- croak ":alias needs an argument in charnames";
- my $alias = shift;
- if (ref $alias) {
- ref $alias eq "HASH" or
- croak "Only HASH reference supported as argument to :alias";
- alias ($alias);
- next;
- }
- if ($alias =~ m{:(\w+)$}) {
- $1 eq "full" || $1 eq "short" and
- croak ":alias cannot use existing pragma :$1 (reversed order?)";
- alias_file ($1) and $promote = 1;
- next;
- }
- alias_file ($alias);
- next;
- }
- if (m/^:/ and ! ($_ eq ":full" || $_ eq ":short")) {
- warn "unsupported special '$_' in charnames";
- next;
- }
- push @args, $_;
- }
- @args == 0 && $promote and @args = (":full");
- @h{@args} = (1) x @args;
-
- $^H{charnames_full} = delete $h{':full'};
- $^H{charnames_short} = delete $h{':short'};
- $^H{charnames_scripts} = [map uc, keys %h];
-
- ##
- ## If utf8? warnings are enabled, and some scripts were given,
- ## see if at least we can find one letter of each script.
- ##
- if (warnings::enabled('utf8') && @{$^H{charnames_scripts}}) {
- $txt = do "unicore/Name.pl" unless $txt;
-
- for my $script (@{$^H{charnames_scripts}}) {
- if (not $txt =~ m/\t\t$script (?:CAPITAL |SMALL )?LETTER /) {
- warnings::warn('utf8', "No such script: '$script'");
- }
- }
- }
-} # import
-
-require Unicode::UCD; # for Unicode::UCD::_getcode()
-
+# Cache of already looked-up values. This is set to only contain
+# official values, and user aliases can't override them, so scoping is
+# not an issue.
my %viacode;
-sub viacode
+sub viacode {
+ return _charnames::viacode(@_);
+}
+
+sub vianame
{
if (@_ != 1) {
- carp "charnames::viacode() expects one argument";
+ _charnames::carp "charnames::vianame() expects one name argument";
return ()
}
- my $arg = shift;
- my $code = Unicode::UCD::_getcode($arg);
+ # Looks up the character name and returns its ordinal if
+ # found, undef otherwise.
- my $hex;
+ my $arg = shift;
- if (defined $code) {
- $hex = sprintf "%04X", $arg;
- } else {
- carp("unexpected arg \"$arg\" to charnames::viacode()");
- return;
- }
+ if ($arg =~ /^U\+([0-9a-fA-F]+)$/) {
- if ($code > 0x10FFFF) {
- carp sprintf "Unicode characters only allocated up to U+10FFFF (you asked for U+%X)", $hex;
+ # khw claims that this is poor interface design. The function should
+ # return either a an ord or a chr for all inputs; not be bipolar. But
+ # can't change it because of backward compatibility. New code can use
+ # string_vianame() instead.
+ my $ord = CORE::hex $1;
+ return chr $ord if $ord <= 255 || ! ((caller 0)[8] & $bytes::hint_bits);
+ _charnames::carp _charnames::not_legal_use_bytes_msg($arg, chr $ord);
return;
}
- return $viacode{$hex} if exists $viacode{$hex};
-
- $txt = do "unicore/Name.pl" unless $txt;
+ # The first 1 arg means wants an ord returned; the second that we are in
+ # runtime, and this is the first level routine called from the user
+ return _charnames::lookup_name($arg, 1, 1);
+} # vianame
- if ($txt =~ m/^$hex\t\t(.+)/m) {
- return $viacode{$hex} = $1;
- } else {
- return;
- }
-} # viacode
+sub string_vianame {
-my %vianame;
+ # Looks up the character name and returns its string representation if
+ # found, undef otherwise.
-sub vianame
-{
if (@_ != 1) {
- carp "charnames::vianame() expects one name argument";
- return ()
+ _charnames::carp "charnames::string_vianame() expects one name argument";
+ return;
}
my $arg = shift;
- return chr hex $1 if $arg =~ /^U\+([0-9a-fA-F]+)$/;
+ if ($arg =~ /^U\+([0-9a-fA-F]+)$/) {
- return $vianame{$arg} if exists $vianame{$arg};
+ my $ord = CORE::hex $1;
+ return chr $ord if $ord <= 255 || ! ((caller 0)[8] & $bytes::hint_bits);
- $txt = do "unicore/Name.pl" unless $txt;
-
- my $pos = index $txt, "\t\t$arg\n";
- if ($[ <= $pos) {
- my $posLF = rindex $txt, "\n", $pos;
- (my $code = substr $txt, $posLF + 1, 6) =~ tr/\t//d;
- return $vianame{$arg} = hex $code;
-
- # If $pos is at the 1st line, $posLF must be $[ - 1 (not found);
- # then $posLF + 1 equals to $[ (at the beginning of $txt).
- # Otherwise $posLF is the position of "\n";
- # then $posLF + 1 must be the position of the next to "\n"
- # (the beginning of the line).
- # substr($txt, $posLF + 1, 6) may be "0000\t\t", "00A1\t\t",
- # "10300\t", "100000", etc. So we can get the code via removing TAB.
- } else {
+ _charnames::carp _charnames::not_legal_use_bytes_msg($arg, chr $ord);
return;
}
-} # vianame
+ # The 0 arg means wants a string returned; the 1 arg means that we are in
+ # runtime, and this is the first level routine called from the user
+ return _charnames::lookup_name($arg, 0, 1);
+} # string_vianame
1;
__END__
=head1 NAME
-charnames - define character names for C<\N{named}> string literal escapes
+charnames - access to Unicode character names and named character sequences; also define character names
=head1 SYNOPSIS
- use charnames ':full';
- print "\N{GREEK SMALL LETTER SIGMA} is called sigma.\n";
+ use charnames ':full';
+ print "\N{GREEK SMALL LETTER SIGMA} is called sigma.\n";
+ print "\N{LATIN CAPITAL LETTER E WITH VERTICAL LINE BELOW}",
+ " is an officially named sequence of two Unicode characters\n";
+
+ use charnames ':loose';
+ print "\N{Greek small-letter sigma}",
+ "can be used to ignore case, underscores, most blanks,"
+ "and when you aren't sure if the official name has hyphens\n";
+
+ use charnames ':short';
+ print "\N{greek:Sigma} is an upper-case sigma.\n";
+
+ use charnames qw(cyrillic greek);
+ print "\N{sigma} is Greek sigma, and \N{be} is Cyrillic b.\n";
+
+ use charnames ":full", ":alias" => {
+ e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE",
+ mychar => 0xE8000, # Private use area
+ };
+ print "\N{e_ACUTE} is a small letter e with an acute.\n";
+ print "\N{mychar} allows me to name private use characters.\n";
+
+ use charnames ();
+ print charnames::viacode(0x1234); # prints "ETHIOPIC SYLLABLE SEE"
+ printf "%04X", charnames::vianame("GOTHIC LETTER AHSA"); # prints
+ # "10330"
+ print charnames::vianame("LATIN CAPITAL LETTER A"); # prints 65 on
+ # ASCII platforms;
+ # 193 on EBCDIC
+ print charnames::string_vianame("LATIN CAPITAL LETTER A"); # prints "A"
- use charnames ':short';
- print "\N{greek:Sigma} is an upper-case sigma.\n";
+=head1 DESCRIPTION
- use charnames qw(cyrillic greek);
- print "\N{sigma} is Greek sigma, and \N{be} is Cyrillic b.\n";
+Pragma C<use charnames> is used to gain access to the names of the
+Unicode characters and named character sequences, and to allow you to define
+your own character and character sequence names.
- use charnames ":full", ":alias" => {
- e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE",
- };
- print "\N{e_ACUTE} is a small letter e with an acute.\n";
+All forms of the pragma enable use of the following 3 functions:
- print charnames::viacode(0x1234); # prints "ETHIOPIC SYLLABLE SEE"
- printf "%04X", charnames::vianame("GOTHIC LETTER AHSA"); # prints "10330"
+=over
-=head1 DESCRIPTION
+=item *
-Pragma C<use charnames> supports arguments C<:full>, C<:short>, script
-names and customized aliases. If C<:full> is present, for expansion of
-C<\N{CHARNAME}> string C<CHARNAME> is first looked in the list of
-standard Unicode names of chars. If C<:short> is present, and
-C<CHARNAME> has the form C<SCRIPT:CNAME>, then C<CNAME> is looked up
-as a letter in script C<SCRIPT>. If pragma C<use charnames> is used
-with script name arguments, then for C<\N{CHARNAME}> the name
-C<CHARNAME> is looked up as a letter in the given scripts (in the
-specified order). Customized aliases are explained in L</CUSTOM ALIASES>.
+L</charnames::string_vianame(I<name>)> for run-time lookup of a
+either a character name or a named character sequence, returning its string
+representation
-For lookup of C<CHARNAME> inside a given script C<SCRIPTNAME>
-this pragma looks for the names
+=item *
- SCRIPTNAME CAPITAL LETTER CHARNAME
- SCRIPTNAME SMALL LETTER CHARNAME
- SCRIPTNAME LETTER CHARNAME
+L</charnames::vianame(I<name>)> for run-time lookup of a
+character name (but not a named character sequence) to get its ordinal value
+(code point)
-in the table of standard Unicode names. If C<CHARNAME> is lowercase,
-then the C<CAPITAL> variant is ignored, otherwise the C<SMALL> variant
-is ignored.
+=item *
-Note that C<\N{...}> is compile-time, it's a special form of string
-constant used inside double-quoted strings: in other words, you cannot
-use variables inside the C<\N{...}>. If you want similar run-time
-functionality, use charnames::vianame().
+L</charnames::viacode(I<code>)> for run-time lookup of a code point to get its
+Unicode name.
-For the C0 and C1 control characters (U+0000..U+001F, U+0080..U+009F)
-as of Unicode 3.1, there are no official Unicode names but you can use
-instead the ISO 6429 names (LINE FEED, ESCAPE, and so forth). In
-Unicode 3.2 (as of Perl 5.8) some naming changes take place ISO 6429
-has been updated, see L</ALIASES>. Also note that the U+UU80, U+0081,
-U+0084, and U+0099 do not have names even in ISO 6429.
+=back
-Since the Unicode standard uses "U+HHHH", so can you: "\N{U+263a}"
-is the Unicode smiley face, or "\N{WHITE SMILING FACE}".
+Starting in Perl v5.16, any occurrence of C<\N{I<CHARNAME>}> sequences
+in a double-quotish string automatically loads this module with arguments
+C<:full> and C<:short> (described below) if it hasn't already been loaded with
+different arguments, in order to compile the named Unicode character into
+position in the string. Prior to v5.16, an explicit S<C<use charnames>> was
+required to enable this usage. (However, prior to v5.16, the form C<S<"use
+charnames ();">> did not enable C<\N{I<CHARNAME>}>.)
-=head1 CUSTOM TRANSLATORS
+Note that C<\N{U+I<...>}>, where the I<...> is a hexadecimal number,
+also inserts a character into a string.
+The character it inserts is the one whose code point
+(ordinal value) is equal to the number. For example, C<"\N{U+263a}"> is
+the Unicode (white background, black foreground) smiley face
+equivalent to C<"\N{WHITE SMILING FACE}">.
+Also note, C<\N{I<...>}> can mean a regex quantifier instead of a character
+name, when the I<...> is a number (or comma separated pair of numbers
+(see L<perlreref/QUANTIFIERS>), and is not related to this pragma.
-The mechanism of translation of C<\N{...}> escapes is general and not
-hardwired into F<charnames.pm>. A module can install custom
-translations (inside the scope which C<use>s the module) with the
-following magic incantation:
+The C<charnames> pragma supports arguments C<:full>, C<:loose>, C<:short>,
+script names and L<customized aliases|/CUSTOM ALIASES>.
- use charnames (); # for $charnames::hint_bits
- sub import {
- shift;
- $^H |= $charnames::hint_bits;
- $^H{charnames} = \&translator;
- }
+If C<:full> is present, for expansion of
+C<\N{I<CHARNAME>}>, the string I<CHARNAME> is first looked up in the list of
+standard Unicode character names.
-Here translator() is a subroutine which takes C<CHARNAME> as an
-argument, and returns text to insert into the string instead of the
-C<\N{CHARNAME}> escape. Since the text to insert should be different
-in C<bytes> mode and out of it, the function should check the current
-state of C<bytes>-flag as in:
+C<:loose> is a variant of C<:full> which allows I<CHARNAME> to be less
+precisely specified. Details are in L</LOOSE MATCHES>.
- use bytes (); # for $bytes::hint_bits
- sub translator {
- if ($^H & $bytes::hint_bits) {
- return bytes_translator(@_);
- }
- else {
- return utf8_translator(@_);
- }
- }
+If C<:short> is present, and
+I<CHARNAME> has the form C<I<SCRIPT>:I<CNAME>>, then I<CNAME> is looked up
+as a letter in script I<SCRIPT>, as described in the next paragraph.
+Or, if C<use charnames> is used
+with script name arguments, then for C<\N{I<CHARNAME>}> the name
+I<CHARNAME> is looked up as a letter in the given scripts (in the
+specified order). Customized aliases can override these, and are explained in
+L</CUSTOM ALIASES>.
-=head1 CUSTOM ALIASES
+For lookup of I<CHARNAME> inside a given script I<SCRIPTNAME>,
+this pragma looks in the table of standard Unicode names for the names
-This version of charnames supports three mechanisms of adding local
-or customized aliases to standard Unicode naming conventions (:full)
+ SCRIPTNAME CAPITAL LETTER CHARNAME
+ SCRIPTNAME SMALL LETTER CHARNAME
+ SCRIPTNAME LETTER CHARNAME
-=head2 Anonymous hashes
+If I<CHARNAME> is all lowercase,
+then the C<CAPITAL> variant is ignored, otherwise the C<SMALL> variant
+is ignored, and both I<CHARNAME> and I<SCRIPTNAME> are converted to all
+uppercase for look-up. Other than that, both of them follow L<loose|/LOOSE
+MATCHES> rules if C<:loose> is also specified; strict otherwise.
- use charnames ":full", ":alias" => {
+Note that C<\N{...}> is compile-time; it's a special form of string
+constant used inside double-quotish strings; this means that you cannot
+use variables inside the C<\N{...}>. If you want similar run-time
+functionality, use
+L<charnames::string_vianame()|/charnames::string_vianame(I<name>)>.
+
+Since Unicode 6.0, it is deprecated to use C<BELL>. Instead use C<ALERT> (but
+C<BEL> will continue to work).
+
+If the input name is unknown, C<\N{NAME}> raises a warning and
+substitutes the Unicode REPLACEMENT CHARACTER (U+FFFD).
+
+For C<\N{NAME}>, it is a fatal error if C<use bytes> is in effect and the
+input name is that of a character that won't fit into a byte (i.e., whose
+ordinal is above 255).
+
+Otherwise, any string that includes a C<\N{I<charname>}> or
+C<S<\N{U+I<code point>}>> will automatically have Unicode semantics (see
+L<perlunicode/Byte and Character Semantics>).
+
+=head1 LOOSE MATCHES
+
+By specifying C<:loose>, Unicode's L<loose character name
+matching|http://www.unicode.org/reports/tr44#Matching_Rules> rules are
+selected instead of the strict exact match used otherwise.
+That means that I<CHARNAME> doesn't have to be so precisely specified.
+Upper/lower case doesn't matter (except with scripts as mentioned above), nor
+do any underscores, and the only hyphens that matter are those at the
+beginning or end of a word in the name (with one exception: the hyphen in
+U+1180 C<HANGUL JUNGSEONG O-E> does matter).
+Also, blanks not adjacent to hyphens don't matter.
+The official Unicode names are quite variable as to where they use hyphens
+versus spaces to separate word-like units, and this option allows you to not
+have to care as much.
+The reason non-medial hyphens matter is because of cases like
+U+0F60 C<TIBETAN LETTER -A> versus U+0F68 C<TIBETAN LETTER A>.
+The hyphen here is significant, as is the space before it, and so both must be
+included.
+
+C<:loose> slows down look-ups by a factor of 2 to 3 versus
+C<:full>, but the trade-off may be worth it to you. Each individual look-up
+takes very little time, and the results are cached, so the speed difference
+would become a factor only in programs that do look-ups of many different
+spellings, and probably only when those look-ups are through vianame() and
+string_vianame(), since C<\N{...}> look-ups are done at compile time.
+
+=head1 ALIASES
+
+Starting in Unicode 6.1 and Perl v5.16, Unicode defines many abbreviations and
+names that were formerly Perl extensions, and some additional ones that Perl
+did not previously accept. The list is getting too long to reproduce here,
+but you can get the complete list from the Unicode web site:
+L<http://www.unicode.org/Public/UNIDATA/NameAliases.txt>.
+
+Earlier versions of Perl accepted almost all the 6.1 names. These were most
+extensively documented in the v5.14 version of this pod:
+L<http://perldoc.perl.org/5.14.0/charnames.html#ALIASES>.
+
+=head1 CUSTOM ALIASES
+
+You can add customized aliases to standard (C<:full>) Unicode naming
+conventions. The aliases override any standard definitions, so, if
+you're twisted enough, you can change C<"\N{LATIN CAPITAL LETTER A}"> to
+mean C<"B">, etc.
+
+Note that an alias should not be something that is a legal curly
+brace-enclosed quantifier (see L<perlreref/QUANTIFIERS>). For example
+C<\N{123}> means to match 123 non-newline characters, and is not treated as a
+charnames alias. Aliases are discouraged from beginning with anything
+other than an alphabetic character and from containing anything other
+than alphanumerics, spaces, dashes, parentheses, and underscores.
+Currently they must be ASCII.
+
+An alias can map to either an official Unicode character name (not a loose
+matched name) or to a
+numeric code point (ordinal). The latter is useful for assigning names
+to code points in Unicode private use areas such as U+E800 through
+U+F8FF.
+A numeric code point must be a non-negative integer or a string beginning
+with C<"U+"> or C<"0x"> with the remainder considered to be a
+hexadecimal integer. A literal numeric constant must be unsigned; it
+will be interpreted as hex if it has a leading zero or contains
+non-decimal hex digits; otherwise it will be interpreted as decimal.
+
+Aliases are added either by the use of anonymous hashes:
+
+ use charnames ":alias" => {
e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE",
+ mychar1 => 0xE8000,
};
my $str = "\N{e_ACUTE}";
-=head2 Alias file
+or by using a file containing aliases:
- use charnames ":full", ":alias" => "pro";
+ use charnames ":alias" => "pro";
- will try to read "unicore/pro_alias.pl" from the @INC path. This
- file should return a list in plain perl:
+This will try to read C<"unicore/pro_alias.pl"> from the C<@INC> path. This
+file should return a list in plain perl:
(
A_GRAVE => "LATIN CAPITAL LETTER A WITH GRAVE",
A_BREVE => "LATIN CAPITAL LETTER A WITH BREVE",
A_RING => "LATIN CAPITAL LETTER A WITH RING ABOVE",
A_MACRON => "LATIN CAPITAL LETTER A WITH MACRON",
+ mychar2 => "U+E8001",
);
-=head2 Alias shortcut
+Both these methods insert C<":full"> automatically as the first argument (if no
+other argument is given), and you can give the C<":full"> explicitly as
+well, like
- use charnames ":alias" => ":pro";
-
- works exactly the same as the alias pairs, only this time,
- ":full" is inserted automatically as first argument (if no
- other argument is given).
-
-=head1 charnames::viacode(code)
-
-Returns the full name of the character indicated by the numeric code.
-The example
-
- print charnames::viacode(0x2722);
+ use charnames ":full", ":alias" => "pro";
-prints "FOUR TEARDROP-SPOKED ASTERISK".
+C<":loose"> has no effect with these. Input names must match exactly, using
+C<":full"> rules.
-Returns undef if no name is known for the code.
+Also, both these methods currently allow only single characters to be named.
+To name a sequence of characters, use a
+L<custom translator|/CUSTOM TRANSLATORS> (described below).
-This works only for the standard names, and does not yet apply
-to custom translators.
+=head1 charnames::string_vianame(I<name>)
-Notice that the name returned for of U+FEFF is "ZERO WIDTH NO-BREAK
-SPACE", not "BYTE ORDER MARK".
+This is a runtime equivalent to C<\N{...}>. I<name> can be any expression
+that evaluates to a name accepted by C<\N{...}> under the L<C<:full>
+option|/DESCRIPTION> to C<charnames>. In addition, any other options for the
+controlling C<"use charnames"> in the same scope apply, like C<:loose> or any
+L<script list, C<:short> option|/DESCRIPTION>, or L<custom aliases|/CUSTOM
+ALIASES> you may have defined.
-=head1 charnames::vianame(name)
+The only difference is that if the input name is unknown, C<string_vianame>
+returns C<undef> instead of the REPLACEMENT CHARACTER and does not raise a
+warning message.
-Returns the code point indicated by the name.
-The example
+=head1 charnames::vianame(I<name>)
- printf "%04X", charnames::vianame("FOUR TEARDROP-SPOKED ASTERISK");
+This is similar to C<string_vianame>. The main difference is that under most
+circumstances, vianame returns an ordinal code
+point, whereas C<string_vianame> returns a string. For example,
-prints "2722".
+ printf "U+%04X", charnames::vianame("FOUR TEARDROP-SPOKED ASTERISK");
-Returns undef if the name is unknown.
+prints "U+2722".
-This works only for the standard names, and does not yet apply
-to custom translators.
+This leads to the other two differences. Since a single code point is
+returned, the function can't handle named character sequences, as these are
+composed of multiple characters (it returns C<undef> for these. And, the code
+point can be that of any
+character, even ones that aren't legal under the C<S<use bytes>> pragma,
-=head1 ALIASES
+See L</BUGS> for the circumstances in which the behavior differs
+from that described above.
-A few aliases have been defined for convenience: instead of having
-to use the official names
+=head1 charnames::viacode(I<code>)
- LINE FEED (LF)
- FORM FEED (FF)
- CARRIAGE RETURN (CR)
- NEXT LINE (NEL)
+Returns the full name of the character indicated by the numeric code.
+For example,
-(yes, with parentheses) one can use
+ print charnames::viacode(0x2722);
- LINE FEED
- FORM FEED
- CARRIAGE RETURN
- NEXT LINE
- LF
- FF
- CR
- NEL
+prints "FOUR TEARDROP-SPOKED ASTERISK".
-One can also use
+The name returned is the "best" (defined below) official name or alias
+for the code point, if
+available; otherwise your custom alias for it, if defined; otherwise C<undef>.
+This means that your alias will only be returned for code points that don't
+have an official Unicode name (nor alias) such as private use code points.
+
+If you define more than one name for the code point, it is indeterminate
+which one will be returned.
+
+As mentioned, the function returns C<undef> if no name is known for the code
+point. In Unicode the proper name of these is the empty string, which
+C<undef> stringifies to. (If you ask for a code point past the legal
+Unicode maximum of U+10FFFF that you haven't assigned an alias to, you
+get C<undef> plus a warning.)
+
+The input number must be a non-negative integer, or a string beginning
+with C<"U+"> or C<"0x"> with the remainder considered to be a
+hexadecimal integer. A literal numeric constant must be unsigned; it
+will be interpreted as hex if it has a leading zero or contains
+non-decimal hex digits; otherwise it will be interpreted as decimal.
+
+As mentioned above under L</ALIASES>, Unicode 6.1 defines extra names
+(synonyms or aliases) for some code points, most of which were already
+available as Perl extensions. All these are accepted by C<\N{...}> and the
+other functions in this module, but C<viacode> has to choose which one
+name to return for a given input code point, so it returns the "best" name.
+To understand how this works, it is helpful to know more about the Unicode
+name properties. All code points actually have only a single name, which
+(starting in Unicode 2.0) can never change once a character has been assigned
+to the code point. But mistakes have been made in assigning names, for
+example sometimes a clerical error was made during the publishing of the
+Standard which caused words to be misspelled, and there was no way to correct
+those. The Name_Alias property was eventually created to handle these
+situations. If a name was wrong, a corrected synonym would be published for
+it, using Name_Alias. C<viacode> will return that corrected synonym as the
+"best" name for a code point. (It is even possible, though it hasn't happened
+yet, that the correction itself will need to be corrected, and so another
+Name_Alias can be created for that code point; C<viacode> will return the
+most recent correction.)
+
+The Unicode name for each of the control characters (such as LINE FEED) is the
+empty string. However almost all had names assigned by other standards, such
+as the ASCII Standard, or were in common use. C<viacode> returns these names
+as the "best" ones available. Unicode 6.1 has created Name_Aliases for each
+of them, including alternate names, like NEW LINE. C<viacode> uses the
+original name, "LINE FEED" in preference to the alternate. Similarly the
+name returned for U+FEFF is "ZERO WIDTH NO-BREAK SPACE", not "BYTE ORDER
+MARK".
+
+Until Unicode 6.1, the 4 control characters U+0080, U+0081, U+0084, and U+0099
+did not have names nor aliases.
+To preserve backwards compatibility, any alias you define for these code
+points will be returned by this function, in preference to the official name.
+
+Some code points also have abbreviated names, such as "LF" or "NL".
+C<viacode> never returns these.
+
+Because a name correction may be added in future Unicode releases, the name
+that C<viacode> returns may change as a result. This is a rare event, but it
+does happen.
- BYTE ORDER MARK
- BOM
+=head1 CUSTOM TRANSLATORS
-and
+The mechanism of translation of C<\N{...}> escapes is general and not
+hardwired into F<charnames.pm>. A module can install custom
+translations (inside the scope which C<use>s the module) with the
+following magic incantation:
- ZWNJ
- ZWJ
+ sub import {
+ shift;
+ $^H{charnames} = \&translator;
+ }
-for ZERO WIDTH NON-JOINER and ZERO WIDTH JOINER.
+Here translator() is a subroutine which takes I<CHARNAME> as an
+argument, and returns text to insert into the string instead of the
+C<\N{I<CHARNAME>}> escape.
-For backward compatibility one can use the old names for
-certain C0 and C1 controls
+This is the only way you can create a custom named sequence of code points.
- old new
+Since the text to insert should be different
+in C<bytes> mode and out of it, the function should check the current
+state of C<bytes>-flag as in:
- HORIZONTAL TABULATION CHARACTER TABULATION
- VERTICAL TABULATION LINE TABULATION
- FILE SEPARATOR INFORMATION SEPARATOR FOUR
- GROUP SEPARATOR INFORMATION SEPARATOR THREE
- RECORD SEPARATOR INFORMATION SEPARATOR TWO
- UNIT SEPARATOR INFORMATION SEPARATOR ONE
- PARTIAL LINE DOWN PARTIAL LINE FORWARD
- PARTIAL LINE UP PARTIAL LINE BACKWARD
+ use bytes (); # for $bytes::hint_bits
+ sub translator {
+ if ($^H & $bytes::hint_bits) {
+ return bytes_translator(@_);
+ }
+ else {
+ return utf8_translator(@_);
+ }
+ }
-but the old names in addition to giving the character
-will also give a warning about being deprecated.
+See L</CUSTOM ALIASES> above for restrictions on I<CHARNAME>.
-=head1 ILLEGAL CHARACTERS
+Of course, C<vianame>, C<viacode>, and C<string_vianame> would need to be
+overridden as well.
-If you ask by name for a character that does not exist, a warning is
-given and the Unicode I<replacement character> "\x{FFFD}" is returned.
+=head1 BUGS
-If you ask by code for a character that does not exist, no warning is
-given and C<undef> is returned. (Though if you ask for a code point
-past U+10FFFF you do get a warning.)
+vianame() normally returns an ordinal code point, but when the input name is of
+the form C<U+...>, it returns a chr instead. In this case, if C<use bytes> is
+in effect and the character won't fit into a byte, it returns C<undef> and
+raises a warning.
-=head1 BUGS
+Names must be ASCII characters only, which means that you are out of luck if
+you want to create aliases in a language where some or all the characters of
+the desired aliases are non-ASCII.
-Since evaluation of the translation function happens in a middle of
-compilation (of a string literal), the translation function should not
-do any C<eval>s or C<require>s. This restriction should be lifted in
+Since evaluation of the translation function (see L</CUSTOM
+TRANSLATORS>) happens in the middle of compilation (of a string
+literal), the translation function should not do any C<eval>s or
+C<require>s. This restriction should be lifted (but is low priority) in
a future version of Perl.
=cut
+
+# ex: set ts=8 sts=2 sw=2 et: