no warnings 'surrogate'; # surrogates can be inputs to this
use charnames ();
-our $VERSION = '0.52';
+our $VERSION = '0.61';
require Exporter;
charblock charscript
charblocks charscripts
charinrange
+ charprop
general_categories bidi_types
compexcl
casefold all_casefolds casespec
num
prop_aliases
prop_value_aliases
+ prop_values
prop_invlist
prop_invmap
search_invlist
use Carp;
+sub IS_ASCII_PLATFORM { ord("A") == 65 }
+
=head1 NAME
Unicode::UCD - Unicode character database
use Unicode::UCD 'charinfo';
my $charinfo = charinfo($codepoint);
+ use Unicode::UCD 'charprop';
+ my $value = charprop($codepoint, $property);
+
use Unicode::UCD 'casefold';
- my $casefold = casefold(0xFB00);
+ my $casefold = casefold($codepoint);
use Unicode::UCD 'all_casefolds';
my $all_casefolds_ref = all_casefolds();
use Unicode::UCD 'casespec';
- my $casespec = casespec(0xFB00);
+ my $casespec = casespec($codepoint);
use Unicode::UCD 'charblock';
my $charblock = charblock($codepoint);
use Unicode::UCD 'prop_value_aliases';
my @gc_punct_names = prop_value_aliases("Gc", "Punct");
+ use Unicode::UCD 'prop_values';
+ my @all_EA_short_names = prop_values("East_Asian_Width");
+
use Unicode::UCD 'prop_invlist';
my @puncts = prop_invlist("gc=punctuation");
=head2 code point argument
Some of the functions are called with a I<code point argument>, which is either
-a decimal or a hexadecimal scalar designating a Unicode code point, or C<U+>
-followed by hexadecimals designating a Unicode code point. In other words, if
-you want a code point to be interpreted as a hexadecimal number, you must
-prefix it with either C<0x> or C<U+>, because a string like e.g. C<123> will be
-interpreted as a decimal code point.
+a decimal or a hexadecimal scalar designating a code point in the platform's
+native character set (extended to Unicode), or a string containing C<U+>
+followed by hexadecimals
+designating a Unicode code point. A leading 0 will force a hexadecimal
+interpretation, as will a hexadecimal digit that isn't a decimal digit.
Examples:
- 223 # Decimal 223
- 0223 # Hexadecimal 223 (= 547 decimal)
- 0xDF # Hexadecimal DF (= 223 decimal
- U+DF # Hexadecimal DF
+ 223 # Decimal 223 in native character set
+ 0223 # Hexadecimal 223, native (= 547 decimal)
+ 0xDF # Hexadecimal DF, native (= 223 decimal
+ 'U+DF' # Hexadecimal DF, in Unicode's character set
+ (= LATIN SMALL LETTER SHARP S)
Note that the largest code point in Unicode is U+10FFFF.
Fields that aren't applicable to the particular code point argument exist in the
returned hash, and are empty.
+For results that are less "raw" than this function returns, or to get the values for
+any property, not just the few covered by this function, use the
+L</charprop()> function.
+
The keys in the hash with the meanings of their values are:
=over
=item B<code>
-the input L</code point argument> expressed in hexadecimal, with leading zeros
+the input native L</code point argument> expressed in hexadecimal, with
+leading zeros
added if necessary to make it contain at least four hexdigits
=item B<name>
is empty if I<code> has no decomposition; or is one or more codes
(separated by spaces) that, taken in order, represent a decomposition for
I<code>. Each has at least four hexdigits.
-The codes may be preceded by a word enclosed in angle brackets then a space,
+The codes may be preceded by a word enclosed in angle brackets, then a space,
like C<E<lt>compatE<gt> >, giving the type of decomposition
This decomposition may be an intermediate one whose components are also
-decomposable. Use L<Unicode::Normalize> to get the final decomposition.
+decomposable. Use L<Unicode::Normalize> to get the final decomposition in one
+step.
=item B<decimal>
-if I<code> is a decimal digit this is its integer numeric value
+if I<code> represents a decimal digit this is its integer numeric value
=item B<digit>
=item B<upper>
-is empty if there is no single code point uppercase mapping for I<code>
-(its uppercase mapping is itself);
-otherwise it is that mapping expressed as at least four hexdigits.
-(L</casespec()> should be used in addition to B<charinfo()>
-for case mappings when the calling program can cope with multiple code point
-mappings.)
+is, if non-empty, the uppercase mapping for I<code> expressed as at least four
+hexdigits. This indicates that the full uppercase mapping is a single
+character, and is identical to the simple (single-character only) mapping.
+When this field is empty, it means that the simple uppercase mapping is
+I<code> itself; you'll need some other means, (like L</charprop()> or
+L</casespec()> to get the full mapping.
=item B<lower>
-is empty if there is no single code point lowercase mapping for I<code>
-(its lowercase mapping is itself);
-otherwise it is that mapping expressed as at least four hexdigits.
-(L</casespec()> should be used in addition to B<charinfo()>
-for case mappings when the calling program can cope with multiple code point
-mappings.)
+is, if non-empty, the lowercase mapping for I<code> expressed as at least four
+hexdigits. This indicates that the full lowercase mapping is a single
+character, and is identical to the simple (single-character only) mapping.
+When this field is empty, it means that the simple lowercase mapping is
+I<code> itself; you'll need some other means, (like L</charprop()> or
+L</casespec()> to get the full mapping.
=item B<title>
-is empty if there is no single code point titlecase mapping for I<code>
-(its titlecase mapping is itself);
-otherwise it is that mapping expressed as at least four hexdigits.
-(L</casespec()> should be used in addition to B<charinfo()>
-for case mappings when the calling program can cope with multiple code point
-mappings.)
+is, if non-empty, the titlecase mapping for I<code> expressed as at least four
+hexdigits. This indicates that the full titlecase mapping is a single
+character, and is identical to the simple (single-character only) mapping.
+When this field is empty, it means that the simple titlecase mapping is
+I<code> itself; you'll need some other means, (like L</charprop()> or
+L</casespec()> to get the full mapping.
=item B<block>
the block I<code> belongs to (used in C<\p{Blk=...}>).
-See L</Blocks versus Scripts>.
+The L</prop_value_aliases()> function can be used to get all the synonyms
+of the block name.
+See L</Blocks versus Scripts>.
=item B<script>
the script I<code> belongs to.
+The L</prop_value_aliases()> function can be used to get all the synonyms
+of the script name.
+
See L</Blocks versus Scripts>.
=back
Note that you cannot do (de)composition and casing based solely on the
-I<decomposition>, I<combining>, I<lower>, I<upper>, and I<title> fields;
-you will need also the L</compexcl()>, and L</casespec()> functions.
+I<decomposition>, I<combining>, I<lower>, I<upper>, and I<title> fields; you
+will need also the L</casespec()> function and the C<Composition_Exclusion>
+property. (Or you could just use the L<lc()|perlfunc/lc>,
+L<uc()|perlfunc/uc>, and L<ucfirst()|perlfunc/ucfirst> functions, and the
+L<Unicode::Normalize> module.)
=cut
if ($arg =~ /^[1-9]\d*$/) {
return $arg;
- } elsif ($arg =~ /^(?:[Uu]\+|0[xX])?([[:xdigit:]]+)$/) {
- return hex($1);
+ }
+ elsif ($arg =~ /^(?:0[xX])?([[:xdigit:]]+)$/) {
+ return CORE::hex($1);
+ }
+ elsif ($arg =~ /^[Uu]\+([[:xdigit:]]+)$/) { # Is of form U+0000, means
+ # wants the Unicode code
+ # point, not the native one
+ my $decimal = CORE::hex($1);
+ return $decimal if IS_ASCII_PLATFORM;
+ return utf8::unicode_to_native($decimal);
}
return;
@CATEGORIES =_read_table("To/Gc.pl") unless @CATEGORIES;
$prop{'category'} = _search(\@CATEGORIES, 0, $#CATEGORIES, $code)
// $utf8::SwashInfo{'ToGc'}{'missing'};
-
- return if $prop{'category'} eq 'Cn'; # Unassigned code points are undef
+ # Return undef if category value is 'Unassigned' or one of its synonyms
+ return if grep { lc $_ eq 'unassigned' }
+ prop_value_aliases('Gc', $prop{'category'});
$prop{'code'} = sprintf "%04X", $code;
$prop{'name'} = ($char =~ /\p{Cntrl}/) ? '<control>'
my $property = $table =~ s/\.pl//r;
$property = $utf8::file_to_swash_name{$property};
my $to_adjust = defined $property
- && $utf8::SwashInfo{$property}{'format'} eq 'a';
+ && $utf8::SwashInfo{$property}{'format'} =~ / ^ a /x;
for (split /^/m, $list) {
my ($start, $end, $value) = / ^ (.+?) \t (.*?) \t (.+?)
$ /x;
my $decimal_start = hex $start;
my $decimal_end = ($end eq "") ? $decimal_start : hex $end;
+ $value = hex $value if $to_adjust
+ && $utf8::SwashInfo{$property}{'format'} eq 'ax';
if ($return_hash) {
foreach my $i ($decimal_start .. $decimal_end) {
$return{$i} = ($to_adjust)
_search($range, 0, $#$range, $code);
}
+=head2 B<charprop()>
+
+ use Unicode::UCD 'charprop';
+
+ print charprop(0x41, "Gc"), "\n";
+ print charprop(0x61, "General_Category"), "\n";
+
+ prints
+ Lu
+ Ll
+
+This returns the value of the Unicode property given by the second parameter
+for the L</code point argument> given by the first.
+
+The passed-in property may be specified as any of the synonyms returned by
+L</prop_aliases()>.
+
+The return value is always a scalar, either a string or a number. For
+properties where there are synonyms for the values, the synonym returned by
+this function is the longest, most descriptive form, the one returned by
+L</prop_value_aliases()> when called in a scalar context. Of course, you can
+call L</prop_value_aliases()> on the result to get other synonyms.
+
+The return values are more "cooked" than the L</charinfo()> ones. For
+example, the C<"uc"> property value is the actual string containing the full
+uppercase mapping of the input code point. You have to go to extra trouble
+with C<charinfo> to get this value from its C<upper> hash element when the
+full mapping differs from the simple one.
+
+Special note should be made of the return values for a few properties:
+
+=over
+
+=item Block
+
+The value returned is the new-style (see L</Old-style versus new-style block
+names>).
+
+=item Decomposition_Mapping
+
+Like L</charinfo()>, the result may be an intermediate decomposition whose
+components are also decomposable. Use L<Unicode::Normalize> to get the final
+decomposition in one step.
+
+Unlike L</charinfo()>, this does not include the decomposition type. Use the
+C<Decomposition_Type> property to get that.
+
+=item Name_Alias
+
+If the input code point's name has more than one synonym, they are returned
+joined into a single comma-separated string.
+
+=item Numeric_Value
+
+If the result is a fraction, it is converted into a floating point number to
+the accuracy of your platform.
+
+=item Script_Extensions
+
+If the result is multiple script names, they are returned joined into a single
+comma-separated string.
+
+=back
+
+When called with a property that is a Perl extension that isn't expressible in
+a compound form, this function currently returns C<undef>, as the only two
+possible values are I<true> or I<false> (1 or 0 I suppose). This behavior may
+change in the future, so don't write code that relies on it. C<Present_In> is
+a Perl extension that is expressible in a bipartite or compound form (for
+example, C<\p{Present_In=4.0}>), so C<charprop> accepts it. But C<Any> is a
+Perl extension that isn't expressible that way, so C<charprop> returns
+C<undef> for it. Also C<charprop> returns C<undef> for all Perl extensions
+that are internal-only.
+
+=cut
+
+sub charprop ($$) {
+ my ($input_cp, $prop) = @_;
+
+ my $cp = _getcode($input_cp);
+ croak __PACKAGE__, "::charprop: unknown code point '$input_cp'" unless defined $cp;
+
+ my ($list_ref, $map_ref, $format, $default)
+ = prop_invmap($prop);
+ return undef unless defined $list_ref;
+
+ my $i = search_invlist($list_ref, $cp);
+ croak __PACKAGE__, "::charprop: prop_invmap return is invalid for charprop('$input_cp', '$prop)" unless defined $i;
+
+ # $i is the index into both the inversion list and map of $cp.
+ my $map = $map_ref->[$i];
+
+ # Convert enumeration values to their most complete form.
+ if (! ref $map) {
+ my $long_form = prop_value_aliases($prop, $map);
+ $map = $long_form if defined $long_form;
+ }
+
+ if ($format =~ / ^ s /x) { # Scalars
+ return join ",", @$map if ref $map; # Convert to scalar with comma
+ # separated array elements
+
+ # Resolve ambiguity as to whether an all digit value is a code point
+ # that should be converted to a character, or whether it is really
+ # just a number. To do this, look at the default. If it is a
+ # non-empty number, we can safely assume the result is also a number.
+ if ($map =~ / ^ \d+ $ /ax && $default !~ / ^ \d+ $ /ax) {
+ $map = chr $map;
+ }
+ elsif ($map =~ / ^ (?: Y | N ) $ /x) {
+
+ # prop_invmap() returns these values for properties that are Perl
+ # extensions. But this is misleading. For now, return undef for
+ # these, as currently documented.
+ undef $map unless
+ exists $Unicode::UCD::prop_aliases{utf8::_loose_name(lc $prop)};
+ }
+ return $map;
+ }
+ elsif ($format eq 'ar') { # numbers, including rationals
+ my $offset = $cp - $list_ref->[$i];
+ return $map if $map =~ /nan/i;
+ return $map + $offset if $offset != 0; # If needs adjustment
+ return eval $map; # Convert e.g., 1/2 to 0.5
+ }
+ elsif ($format =~ /^a/) { # Some entries need adjusting
+
+ # Linearize sequences into a string.
+ return join "", map { chr $_ } @$map if ref $map; # XXX && $format =~ /^ a [dl] /x;
+
+ return "" if $map eq "" && $format =~ /^a.*e/;
+
+ # These are all character mappings. Return the chr if no adjustment
+ # is needed
+ return chr $cp if $map eq "0";
+
+ # Convert special entry.
+ if ($map eq '<hangul syllable>' && $format eq 'ad') {
+ use Unicode::Normalize qw(NFD);
+ return NFD(chr $cp);
+ }
+
+ # The rest need adjustment from the first entry in the inversion list
+ # corresponding to this map.
+ my $offset = $cp - $list_ref->[$i];
+ return chr($map + $cp - $list_ref->[$i]);
+ }
+ elsif ($format eq 'n') { # The name property
+
+ # There are two special cases, handled here.
+ if ($map =~ / ( .+ ) <code\ point> $ /x) {
+ $map = sprintf("$1%04X", $cp);
+ }
+ elsif ($map eq '<hangul syllable>') {
+ $map = charnames::viacode($cp);
+ }
+ return $map;
+ }
+ else {
+ croak __PACKAGE__, "::charprop: Internal error: unknown format '$format'. Please perlbug this";
+ return undef;
+ }
+}
+
=head2 B<charblock()>
use Unicode::UCD 'charblock';
my $range = charblock('Armenian');
-With a L</code point argument> charblock() returns the I<block> the code point
+With a L</code point argument> C<charblock()> returns the I<block> the code point
belongs to, e.g. C<Basic Latin>. The old-style block name is returned (see
L</Old-style versus new-style block names>).
+The L</prop_value_aliases()> function can be used to get all the synonyms
+of the block name.
+
If the code point is unassigned, this returns the block it would belong to if
it were assigned. (If the Unicode version being used is so early as to not
have blocks, all code points are considered to be in C<No_Block>.)
See also L</Blocks versus Scripts>.
-If supplied with an argument that can't be a code point, charblock() tries to
-do the opposite and interpret the argument as an old-style block name. The
-return value
-is a I<range set> with one range: an anonymous list with a single element that
-consists of another anonymous list whose first element is the first code point
-in the block, and whose second (and final) element is the final code point in
-the block. (The extra list consisting of just one element is so that the same
-program logic can be used to handle both this return, and the return from
-L</charscript()> which can have multiple ranges.) You can test whether a code
-point is in a range using the L</charinrange()> function. If the argument is
-not a known block, C<undef> is returned.
+If supplied with an argument that can't be a code point, C<charblock()> tries to
+do the opposite and interpret the argument as an old-style block name. On an
+ASCII platform, the return value is a I<range set> with one range: an
+anonymous array with a single element that consists of another anonymous array
+whose first element is the first code point in the block, and whose second
+element is the final code point in the block. On an EBCDIC
+platform, the first two Unicode blocks are not contiguous. Their range sets
+are lists containing I<start-of-range>, I<end-of-range> code point pairs. You
+can test whether a code point is in a range set using the L</charinrange()>
+function. (To be precise, each I<range set> contains a third array element,
+after the range boundary ones: the old_style block name.)
+
+If the argument to C<charblock()> is not a known block, C<undef> is
+returned.
=cut
}
}
close($BLOCKSFH);
+ if (! IS_ASCII_PLATFORM) {
+ # The first two blocks, through 0xFF, are wrong on EBCDIC
+ # platforms.
+
+ my @new_blocks = _read_table("To/Blk.pl");
+
+ # Get rid of the first two ranges in the Unicode version, and
+ # replace them with the ones computed by mktables.
+ shift @BLOCKS;
+ shift @BLOCKS;
+ delete $BLOCKS{'Basic Latin'};
+ delete $BLOCKS{'Latin-1 Supplement'};
+
+ # But there are multiple entries in the computed versions, and
+ # we change their names to (which we know) to be the old-style
+ # ones.
+ for my $i (0.. @new_blocks - 1) {
+ if ($new_blocks[$i][2] =~ s/Basic_Latin/Basic Latin/
+ or $new_blocks[$i][2] =~
+ s/Latin_1_Supplement/Latin-1 Supplement/)
+ {
+ push @{$BLOCKS{$new_blocks[$i][2]}}, $new_blocks[$i];
+ }
+ else {
+ splice @new_blocks, $i;
+ last;
+ }
+ }
+ unshift @BLOCKS, @new_blocks;
+ }
}
}
}
my $range = charscript('Thai');
-With a L</code point argument> charscript() returns the I<script> the
-code point belongs to, e.g. C<Latin>, C<Greek>, C<Han>.
+With a L</code point argument>, C<charscript()> returns the I<script> the
+code point belongs to, e.g., C<Latin>, C<Greek>, C<Han>.
If the code point is unassigned or the Unicode version being used is so early
that it doesn't have scripts, this function returns C<"Unknown">.
+The L</prop_value_aliases()> function can be used to get all the synonyms
+of the script name.
If supplied with an argument that can't be a code point, charscript() tries
to do the opposite and interpret the argument as a script name. The
-return value is a I<range set>: an anonymous list of lists that contain
+return value is a I<range set>: an anonymous array of arrays that contain
I<start-of-range>, I<end-of-range> code point pairs. You can test whether a
-code point is in a range set using the L</charinrange()> function. If the
-argument is not a known script, C<undef> is returned.
+code point is in a range set using the L</charinrange()> function.
+(To be precise, each I<range set> contains a third array element,
+after the range boundary ones: the script name.)
+
+If the C<charscript()> argument is not a known script, C<undef> is returned.
See also L</Blocks versus Scripts>.
my $charblocks = charblocks();
-charblocks() returns a reference to a hash with the known block names
+C<charblocks()> returns a reference to a hash with the known block names
as the keys, and the code point ranges (see L</charblock()>) as the values.
The names are in the old-style (see L</Old-style versus new-style block
L<prop_invmap("block")|/prop_invmap()> can be used to get this same data in a
different type of data structure.
+L<prop_values("Block")|/prop_values()> can be used to get all
+the known new-style block names as a list, without the code point ranges.
+
See also L</Blocks versus Scripts>.
=cut
my $charscripts = charscripts();
-charscripts() returns a reference to a hash with the known script
+C<charscripts()> returns a reference to a hash with the known script
names as the keys, and the code point ranges (see L</charscript()>) as
the values.
L<prop_invmap("script")|/prop_invmap()> can be used to get this same data in a
different type of data structure.
+L<C<prop_values("Script")>|/prop_values()> can be used to get all
+the known script names as a list, without the code point ranges.
+
See also L</Blocks versus Scripts>.
=cut
In addition to using the C<\p{Blk=...}> and C<\P{Blk=...}> constructs, you
can also test whether a code point is in the I<range> as returned by
L</charblock()> and L</charscript()> or as the values of the hash returned
-by L</charblocks()> and L</charscripts()> by using charinrange():
+by L</charblocks()> and L</charscripts()> by using C<charinrange()>:
use Unicode::UCD qw(charscript charinrange);
one returned from
L</charinfo()> under the C<category> key.
-The L</prop_value_aliases()> function can be used to get all the synonyms of
-the category name.
+The L</prop_values()> and L</prop_value_aliases()> functions can be used as an
+alternative to this function; the first returning a simple list of the short
+category names; and the second gets all the synonyms of a given category name.
=cut
L<http://www.unicode.org/reports/tr9/>
(as of Unicode 5.0.0)
-The L</prop_value_aliases()> function can be used to get all the synonyms of
-the bidi type name.
+The L</prop_values()> and L</prop_value_aliases()> functions can be used as an
+alternative to this function; the first returning a simple list of the short
+bidi type names; and the second gets all the synonyms of a given bidi type
+name.
=cut
my $compexcl = compexcl(0x09dc);
This routine returns C<undef> if the Unicode version being used is so early
-that it doesn't have this property. It is included for backwards
+that it doesn't have this property.
+
+C<compexcl()> is included for backwards
compatibility, but as of Perl 5.12 and more modern Unicode versions, for
most purposes it is probably more convenient to use one of the following
instead:
=item B<code>
-the input L</code point argument> expressed in hexadecimal, with leading zeros
+the input native L</code point argument> expressed in hexadecimal, with
+leading zeros
added if necessary to make it contain at least four hexdigits
=item B<full>
=item B<code>
-the input L</code point argument> expressed in hexadecimal, with leading zeros
+the input native L</code point argument> expressed in hexadecimal, with
+leading zeros
added if necessary to make it contain at least four hexdigits
=item B<lower>
my ($hexcode, $lower, $title, $upper, $condition) =
($1, $2, $3, $4, $5);
+ if (! IS_ASCII_PLATFORM) { # Remap entry to native
+ foreach my $var_ref (\$hexcode,
+ \$lower,
+ \$title,
+ \$upper)
+ {
+ next unless defined $$var_ref;
+ $$var_ref = join " ",
+ map { sprintf("%04X",
+ utf8::unicode_to_native(hex $_)) }
+ split " ", $$var_ref;
+ }
+ }
+
my $code = hex($hexcode);
# In 2.1.8, there were duplicate entries; ignore all but
If used with a single argument in a scalar context, returns the string
consisting of the code points of the named sequence, or C<undef> if no
named sequence by that name exists. If used with a single argument in
-a list context, it returns the list of the ordinals of the code points. If used
-with no
-arguments in a list context, returns a hash with the names of the
-named sequences as the keys and the named sequences as strings as
+a list context, it returns the list of the ordinals of the code points.
+
+If used with no
+arguments in a list context, it returns a hash with the names of all the
+named sequences as the keys and their sequences as strings as
the values. Otherwise, it returns C<undef> or an empty list depending
on the context.
my $val = num("123");
my $one_quarter = num("\N{VULGAR FRACTION 1/4}");
-C<num> returns the numeric value of the input Unicode string; or C<undef> if it
+C<num()> returns the numeric value of the input Unicode string; or C<undef> if it
doesn't think the entire string has a completely valid, safe numeric value.
If the string is just one character in length, the Unicode numeric value
returned in the lists. C<prop_aliases('isL&')> and C<prop_aliases('isL_')>,
which are old synonyms for C<"Is_LC"> and should not be used in new code, are
examples of this. These both return C<(Is_LC, Cased_Letter)>. Thus this
-function allows you to take a discourarged form, and find its acceptable
+function allows you to take a discouraged form, and find its acceptable
alternatives. The same goes with single-form Block property equivalences.
Only the forms that begin with C<"In_"> are not discouraged; if you pass
C<prop_aliases> a discouraged form, you will get back the equivalent ones that
# there, the input is unknown.
return;
}
- else {
+ elsif ($loose =~ / [:=] /x) {
# Here we found the name but not its aliases, so it has to
- # exist. This means it must be one of the Perl single-form
- # extensions. First see if it is for a property-value
- # combination in one of the following properties.
+ # exist. Exclude property-value combinations. (This shows up
+ # for something like ccc=vr which matches loosely, but is a
+ # synonym for ccc=9 which matches only strictly.
+ return;
+ }
+ else {
+
+ # Here it has to exist, and isn't a property-value
+ # combination. This means it must be one of the Perl
+ # single-form extensions. First see if it is for a
+ # property-value combination in one of the following
+ # properties.
my @list;
foreach my $property ("gc", "script") {
@list = prop_value_aliases($property, $loose);
=pod
+=head2 B<prop_values()>
+
+ use Unicode::UCD 'prop_values';
+
+ print "AHex values are: ", join(", ", prop_values("AHex")),
+ "\n";
+ prints:
+ AHex values are: N, Y
+
+Some Unicode properties have a restricted set of legal values. For example,
+all binary properties are restricted to just C<true> or C<false>; and there
+are only a few dozen possible General Categories. Use C<prop_values>
+to find out if a given property is one such, and if so, to get a list of the
+values:
+
+ print join ", ", prop_values("NFC_Quick_Check");
+ prints:
+ M, N, Y
+
+If the property doesn't have such a restricted set, C<undef> is returned.
+
+There are usually several synonyms for each possible value. Use
+L</prop_value_aliases()> to access those.
+
+Case, white space, hyphens, and underscores are ignored in the input property
+name (except for the trailing underscore in the old-form grandfathered-in
+general category property value C<"L_">, which is better written as C<"LC">).
+
+If the property name is unknown, C<undef> is returned. Note that Perl typically
+recognizes property names in regular expressions with an optional C<"Is_>"
+(with or without the underscore) prefixed to them, such as C<\p{isgc=punct}>.
+This function does not recognize those in the property parameter, returning
+C<undef>.
+
+For the block property, new-style block names are returned (see
+L</Old-style versus new-style block names>).
+
+C<prop_values> does not know about any user-defined properties, and
+will return C<undef> if called with one of those.
+
+=cut
+
+# These are created by mktables for this module and stored in unicore/UCD.pl
+# where their structures are described.
+our %loose_to_standard_value;
+our %prop_value_aliases;
+
+sub prop_values ($) {
+ my $prop = shift;
+ return undef unless defined $prop;
+
+ require "unicore/UCD.pl";
+ require "utf8_heavy.pl";
+
+ # Find the property name synonym that's used as the key in other hashes,
+ # which is element 0 in the returned list.
+ ($prop) = prop_aliases($prop);
+ return undef if ! $prop;
+ $prop = utf8::_loose_name(lc $prop);
+
+ # Here is a legal property.
+ return undef unless exists $prop_value_aliases{$prop};
+ my @return;
+ foreach my $value_key (sort { lc $a cmp lc $b }
+ keys %{$prop_value_aliases{$prop}})
+ {
+ push @return, $prop_value_aliases{$prop}{$value_key}[0];
+ }
+ return @return;
+}
+
+=pod
+
=head2 B<prop_value_aliases()>
use Unicode::UCD 'prop_value_aliases';
print "The short name is $short_name\n";
print "The other aliases are: ", join(", ", @other_names), "\n";
- prints:
+ prints:
The full name is Punctuation
The short name is P
The other aliases are: Punct
all binary properties are restricted to just C<true> or C<false>; and there
are only a few dozen possible General Categories.
-For such properties, there are usually several synonyms for each possible
-value. For example, in binary properties, I<truth> can be represented by any of
-the strings "Y", "Yes", "T", or "True"; and the General Category
-"Punctuation" by that string, or "Punct", or simply "P".
+You can use L</prop_values()> to find out if a given property is one which has
+a restricted set of values, and if so, what those values are. But usually
+each value actually has several synonyms. For example, in Unicode binary
+properties, I<truth> can be represented by any of the strings "Y", "Yes", "T",
+or "True"; and the General Category "Punctuation" by that string, or "Punct",
+or simply "P".
Like property names, there is typically at least a short name for each such
-property-value, and a long name. If you know any name of the property-value,
-you can use C<prop_value_aliases>() to get the long name (when called in
-scalar context), or a list of all the names, with the short name in the 0th
-element, the long name in the next element, and any other synonyms in the
-remaining elements, in no particular order, except that any all-numeric
-synonyms will be last.
+property-value, and a long name. If you know any name of the property-value
+(which you can get by L</prop_values()>, you can use C<prop_value_aliases>()
+to get the long name (when called in scalar context), or a list of all the
+names, with the short name in the 0th element, the long name in the next
+element, and any other synonyms in the remaining elements, in no particular
+order, except that any all-numeric synonyms will be last.
The long name is returned in a form nicely capitalized, suitable for printing.
If called with a property that doesn't have synonyms for its values, it
returns the input value, possibly normalized with capitalization and
-underscores.
+underscores, but not necessarily checking that the input value is valid.
For the block property, new-style block names are returned (see
L</Old-style versus new-style block names>).
=cut
-# These are created by mktables for this routine and stored in unicore/UCD.pl
-# where their structures are described.
-our %loose_to_standard_value;
-our %prop_value_aliases;
-
sub prop_value_aliases ($$) {
my ($prop, $value) = @_;
return unless defined $prop && defined $value;
# anything, like most (if not all) string properties. These don't have
# synonyms anyway. Simply return the input. For example, there is no
# synonym for ('Uppercase_Mapping', A').
- return $value if ! exists $prop_value_aliases{$prop};
+ if (! exists $prop_value_aliases{$prop}) {
+
+ # Here, we have a legal property, but an unknown value. Since the
+ # property is legal, if it isn't in the prop_aliases hash, it must be
+ # a Perl-extension All perl extensions are binary, hence are
+ # enumerateds, which means that we know that the input unknown value
+ # is illegal.
+ return if ! exists $Unicode::UCD::prop_aliases{$prop};
+
+ # Otherwise, we assume it's valid, as documented.
+ return $value;
+ }
# The value name may be loosely or strictly matched; we don't know yet.
# But both types use lower-case.
your purposes.)
Note that the inversion lists returned by this function can possibly include
-non-Unicode code points, that is anything above 0x10FFFF. This is in
-contrast to Perl regular expression matches on those code points, in which a
-non-Unicode code point always fails to match. For example, both of these have
-the same result:
-
- chr(0x110000) =~ \p{ASCII_Hex_Digit=True} # Fails.
- chr(0x110000) =~ \p{ASCII_Hex_Digit=False} # Fails!
-
-And both raise a warning that a Unicode property is being used on a
-non-Unicode code point. It is arguable as to which is the correct thing to do
-here. This function has chosen the way opposite to the Perl regular
-expression behavior. This allows you to easily flip to to the Perl regular
-expression way (for you to go in the other direction would be far harder).
-Simply add 0x110000 at the end of the non-empty returned list if it isn't
-already that value; and pop that value if it is; like:
+non-Unicode code points, that is anything above 0x10FFFF. Unicode properties
+are not defined on such code points. You might wish to change the output to
+not include these. Simply add 0x110000 at the end of the non-empty returned
+list if it isn't already that value; and pop that value if it is; like:
my @list = prop_invlist("foo");
if (@list) {
sub prop_invlist ($;$) {
my $prop = $_[0];
- # Undocumented way to get at Perl internal properties
+ # Undocumented way to get at Perl internal properties; it may be changed
+ # or removed without notice at any time.
my $internal_ok = defined $_[1] && $_[1] eq '_perl_core_internal_ok';
return if ! defined $prop;
my @invlist;
- # The input lines look like:
- # 0041\t005A # [26]
- # 005F
+ if ($swash->{'LIST'} =~ /^V/) {
- # Split into lines, stripped of trailing comments
- foreach my $range (split "\n",
- $swash->{'LIST'} =~ s/ \s* (?: \# .* )? $ //xmgr)
- {
- # And find the beginning and end of the range on the line
- my ($hex_begin, $hex_end) = split "\t", $range;
- my $begin = hex $hex_begin;
-
- # If the new range merely extends the old, we remove the marker
- # created the last time through the loop for the old's end, which
- # causes the new one's end to be used instead.
- if (@invlist && $begin == $invlist[-1]) {
- pop @invlist;
- }
- else {
- # Add the beginning of the range
- push @invlist, $begin;
- }
+ # A 'V' as the first character marks the input as already an inversion
+ # list, in which case, all we need to do is put the remaining lines
+ # into our array.
+ @invlist = split "\n", $swash->{'LIST'} =~ s/ \s* (?: \# .* )? $ //xmgr;
+ shift @invlist;
+ }
+ else {
+ # The input lines look like:
+ # 0041\t005A # [26]
+ # 005F
- if (defined $hex_end) { # The next item starts with the code point 1
- # beyond the end of the range.
- push @invlist, hex($hex_end) + 1;
- }
- else { # No end of range, is a single code point.
- push @invlist, $begin + 1;
+ # Split into lines, stripped of trailing comments
+ foreach my $range (split "\n",
+ $swash->{'LIST'} =~ s/ \s* (?: \# .* )? $ //xmgr)
+ {
+ # And find the beginning and end of the range on the line
+ my ($hex_begin, $hex_end) = split "\t", $range;
+ my $begin = hex $hex_begin;
+
+ # If the new range merely extends the old, we remove the marker
+ # created the last time through the loop for the old's end, which
+ # causes the new one's end to be used instead.
+ if (@invlist && $begin == $invlist[-1]) {
+ pop @invlist;
+ }
+ else {
+ # Add the beginning of the range
+ push @invlist, $begin;
+ }
+
+ if (defined $hex_end) { # The next item starts with the code point 1
+ # beyond the end of the range.
+ no warnings 'portable';
+ my $end = hex $hex_end;
+ last if $end == $Unicode::UCD::MAX_CP;
+ push @invlist, $end + 1;
+ }
+ else { # No end of range, is a single code point.
+ push @invlist, $begin + 1;
+ }
}
}
- require "unicore/UCD.pl";
- my $FIRST_NON_UNICODE = $MAX_UNICODE_CODEPOINT + 1;
-
# Could need to be inverted: add or subtract a 0 at the beginning of the
- # list. And to keep it from matching non-Unicode, add or subtract the
- # first non-unicode code point.
+ # list.
if ($swash->{'INVERT_IT'}) {
if (@invlist && $invlist[0] == 0) {
shift @invlist;
else {
unshift @invlist, 0;
}
- if (@invlist && $invlist[-1] == $FIRST_NON_UNICODE) {
- pop @invlist;
- }
- else {
- push @invlist, $FIRST_NON_UNICODE;
- }
- }
-
- # Here, the list is set up to include only Unicode code points. But, if
- # the table is the default one for the property, it should contain all
- # non-Unicode code points. First calculate the loose name for the
- # property. This is done even for strict-name properties, as the data
- # structure that mktables generates for us is set up so that we don't have
- # to worry about that. The property-value needs to be split if compound,
- # as the loose rules need to be independently calculated on each part. We
- # know that it is syntactically valid, or SWASHNEW would have failed.
-
- $prop = lc $prop;
- my ($prop_only, $table) = split /\s*[:=]\s*/, $prop;
- if ($table) {
-
- # May have optional prefixed 'is'
- $prop = utf8::_loose_name($prop_only) =~ s/^is//r;
- $prop = $utf8::loose_property_name_of{$prop};
- $prop .= "=" . utf8::_loose_name($table);
- }
- else {
- $prop = utf8::_loose_name($prop);
- }
- if (exists $loose_defaults{$prop}) {
-
- # Here, is the default table. If a range ended with 10ffff, instead
- # continue that range to infinity, by popping the 110000; otherwise,
- # add the range from 11000 to infinity
- if (! @invlist || $invlist[-1] != $FIRST_NON_UNICODE) {
- push @invlist, $FIRST_NON_UNICODE;
- }
- else {
- pop @invlist;
- }
}
return @invlist;
Many Unicode properties have more than one name (or alias). C<prop_invmap>
understands all of these, including Perl extensions to them. Ambiguities are
resolved as described above for L</prop_aliases()>. The Perl internal
-property "Perl_Decimal_Digit, described below, is also accepted. C<undef> is
-returned if the property name is unknown.
+property "Perl_Decimal_Digit, described below, is also accepted. An empty
+list is returned if the property name is unknown.
See L<perluniprops/Properties accessible through Unicode::UCD> for the
properties acceptable as inputs to this function.
It is a fatal error to call this function except in list context.
-In addition to the t
he two arrays that form the inversion map, C<prop_invmap>
+In addition to the two arrays that form the inversion map, C<prop_invmap>
returns two other values; one is a scalar that gives some details as to the
format of the entries of the map array; the other is a default value, useful
in maps whose format name begins with the letter C<"a">, as described
This signifies that this entry should be replaced by the decompositions for
all the code points whose decomposition is algorithmically calculated. (All
-of them are currently in one range and no others outisde the range are likely
+of them are currently in one range and no others outside the range are likely
to ever be added to Unicode; the C<"n"> format
has this same entry.) These can be generated via the function
L<Unicode::Normalize::NFD()|Unicode::Normalize>.
C<prop_invmap> does not know about any user-defined properties, and will
return C<undef> if called with one of those.
+The returned values for the Perl extension properties, such as C<Any> and
+C<Greek> are somewhat misleading. The values are either C<"Y"> or C<"N>".
+All Unicode properties are bipartite, so you can actually use the C<"Y"> or
+C<"N>" in a Perl regular rexpression for these, like C<qr/\p{ID_Start=Y/}> or
+C<qr/\p{Upper=N/}>. But the Perl extensions aren't specified this way, only
+like C</qr/\p{Any}>, I<etc>. You can't actually use the C<"Y"> and C<"N>" in
+them.
+
=cut
# User-defined properties could be handled with some changes to utf8_heavy.pl;
our $HANGUL_BEGIN;
our $HANGUL_COUNT;
-sub prop_invmap ($) {
+sub prop_invmap ($;$) {
croak __PACKAGE__, "::prop_invmap: must be called in list context" unless wantarray;
my $prop = $_[0];
return unless defined $prop;
+ # Undocumented way to get at Perl internal properties; it may be changed
+ # or removed without notice at any time. It currently also changes the
+ # output to use the format specified in the file rather than the one we
+ # normally compute and return
+ my $internal_ok = defined $_[1] && $_[1] eq '_perl_core_internal_ok';
+
# Fail internal properties
- return if $prop =~ /^_/;
+ return if $prop =~ /^_/ && ! $internal_ok;
# The values returned by this function.
my (@invlist, @invmap, $format, $missing);
# The swash has two components we look at, the base list, and a hash,
# named 'SPECIALS', containing any additional members whose mappings don't
- # fit into the the base list scheme of things. These generally 'override'
+ # fit into the base list scheme of things. These generally 'override'
# any value in the base list for the same code point.
my $overrides;
my $code_point = hex $hex_code_point;
# The name of all controls is the default: the empty string.
- # The set of controls is immutable, so these hard-coded
- # constants work.
- next if $code_point <= 0x9F
- && ($code_point <= 0x1F || $code_point >= 0x7F);
+ # The set of controls is immutable
+ next if chr($code_point) =~ /[[:cntrl:]]/u;
# If this is a name_alias, it isn't a name
next if grep { $_ eq $name } @{$aliases{$code_point}};
$list .= "$hex_begin\t$hex_end\t$decimal_map\n";
} else {
- # Here, no combining done. Just appen the initial
+ # Here, no combining done. Just append the initial
# (and current) values.
$list .= "$hex_begin\t\t$decimal_map\n";
}
my $requires_adjustment = $format =~ /^a/;
- # The LIST input lines look like:
- # ...
- # 0374\t\tCommon
- # 0375\t0377\tGreek # [3]
- # 037A\t037D\tGreek # [4]
- # 037E\t\tCommon
- # 0384\t\tGreek
- # ...
- #
- # Convert them to like
- # 0374 => Common
- # 0375 => Greek
- # 0378 => $missing
- # 037A => Greek
- # 037E => Common
- # 037F => $missing
- # 0384 => Greek
- #
- # For binary properties, the final non-comment column is absent, and
- # assumed to be 'Y'.
-
- foreach my $range (split "\n", $swash->{'LIST'}) {
- $range =~ s/ \s* (?: \# .* )? $ //xg; # rmv trailing space, comments
-
- # Find the beginning and end of the range on the line
- my ($hex_begin, $hex_end, $map) = split "\t", $range;
- my $begin = hex $hex_begin;
- my $end = (defined $hex_end && $hex_end ne "")
- ? hex $hex_end
- : $begin;
-
- # Each time through the loop (after the first):
- # $invlist[-2] contains the beginning of the previous range processed
- # $invlist[-1] contains the end+1 of the previous range processed
- # $invmap[-2] contains the value of the previous range processed
- # $invmap[-1] contains the default value for missing ranges ($missing)
- #
- # Thus, things are set up for the typical case of a new non-adjacent
- # range of non-missings to be added. But, if the new range is
- # adjacent, it needs to replace the [-1] element; and if the new
- # range is a multiple value of the previous one, it needs to be added
- # to the [-2] map element.
-
- # The first time through, everything will be empty. If the property
- # doesn't have a range that begins at 0, add one that maps to $missing
- if (! @invlist) {
- if ($begin != 0) {
- push @invlist, 0;
- push @invmap, $missing;
- }
+ if ($swash->{'LIST'} =~ /^V/) {
+ @invlist = split "\n", $swash->{'LIST'} =~ s/ \s* (?: \# .* )? $ //xmgr;
+ shift @invlist;
+ foreach my $i (0 .. @invlist - 1) {
+ $invmap[$i] = ($i % 2 == 0) ? 'Y' : 'N'
}
- elsif (@invlist > 1 && $invlist[-2] == $begin) {
-
- # Here we handle the case where the input has multiple entries for
- # each code point. mktables should have made sure that each such
- # range contains only one code point. At this point, $invlist[-1]
- # is the $missing that was added at the end of the last loop
- # iteration, and [-2] is the last real input code point, and that
- # code point is the same as the one we are adding now, making the
- # new one a multiple entry. Add it to the existing entry, either
- # by pushing it to the existing list of multiple entries, or
- # converting the single current entry into a list with both on it.
- # This is all we need do for this iteration.
-
- if ($end != $begin) {
- croak __PACKAGE__, ":prop_invmap: Multiple maps per code point in '$prop' require single-element ranges: begin=$begin, end=$end, map=$map";
- }
- if (! ref $invmap[-2]) {
- $invmap[-2] = [ $invmap[-2], $map ];
- }
- else {
- push @{$invmap[-2]}, $map;
- }
- $has_multiples = 1;
- next;
+
+ # The map includes lines for all code points; add one for the range
+ # from 0 to the first Y.
+ if ($invlist[0] != 0) {
+ unshift @invlist, 0;
+ unshift @invmap, 'N';
}
- elsif ($invlist[-1] == $begin) {
-
- # If the input isn't in the most compact form, so that there are
- # two adjacent ranges that map to the same thing, they should be
- # combined (EXCEPT where the arrays require adjustments, in which
- # case everything is already set up correctly). This happens in
- # our constructed dt mapping, as Element [-2] is the map for the
- # latest range so far processed. Just set the beginning point of
- # the map to $missing (in invlist[-1]) to 1 beyond where this
- # range ends. For example, in
- # 12\t13\tXYZ
- # 14\t17\tXYZ
- # we have set it up so that it looks like
- # 12 => XYZ
- # 14 => $missing
+ }
+ else {
+ # The LIST input lines look like:
+ # ...
+ # 0374\t\tCommon
+ # 0375\t0377\tGreek # [3]
+ # 037A\t037D\tGreek # [4]
+ # 037E\t\tCommon
+ # 0384\t\tGreek
+ # ...
+ #
+ # Convert them to like
+ # 0374 => Common
+ # 0375 => Greek
+ # 0378 => $missing
+ # 037A => Greek
+ # 037E => Common
+ # 037F => $missing
+ # 0384 => Greek
+ #
+ # For binary properties, the final non-comment column is absent, and
+ # assumed to be 'Y'.
+
+ foreach my $range (split "\n", $swash->{'LIST'}) {
+ $range =~ s/ \s* (?: \# .* )? $ //xg; # rmv trailing space, comments
+
+ # Find the beginning and end of the range on the line
+ my ($hex_begin, $hex_end, $map) = split "\t", $range;
+ my $begin = hex $hex_begin;
+ no warnings 'portable';
+ my $end = (defined $hex_end && $hex_end ne "")
+ ? hex $hex_end
+ : $begin;
+
+ # Each time through the loop (after the first):
+ # $invlist[-2] contains the beginning of the previous range processed
+ # $invlist[-1] contains the end+1 of the previous range processed
+ # $invmap[-2] contains the value of the previous range processed
+ # $invmap[-1] contains the default value for missing ranges
+ # ($missing)
#
- # We now see that it should be
- # 12 => XYZ
- # 18 => $missing
- if (! $requires_adjustment && @invlist > 1 && ( (defined $map)
- ? $invmap[-2] eq $map
- : $invmap[-2] eq 'Y'))
- {
- $invlist[-1] = $end + 1;
+ # Thus, things are set up for the typical case of a new
+ # non-adjacent range of non-missings to be added. But, if the new
+ # range is adjacent, it needs to replace the [-1] element; and if
+ # the new range is a multiple value of the previous one, it needs
+ # to be added to the [-2] map element.
+
+ # The first time through, everything will be empty. If the
+ # property doesn't have a range that begins at 0, add one that
+ # maps to $missing
+ if (! @invlist) {
+ if ($begin != 0) {
+ push @invlist, 0;
+ push @invmap, $missing;
+ }
+ }
+ elsif (@invlist > 1 && $invlist[-2] == $begin) {
+
+ # Here we handle the case where the input has multiple entries
+ # for each code point. mktables should have made sure that
+ # each such range contains only one code point. At this
+ # point, $invlist[-1] is the $missing that was added at the
+ # end of the last loop iteration, and [-2] is the last real
+ # input code point, and that code point is the same as the one
+ # we are adding now, making the new one a multiple entry. Add
+ # it to the existing entry, either by pushing it to the
+ # existing list of multiple entries, or converting the single
+ # current entry into a list with both on it. This is all we
+ # need do for this iteration.
+
+ if ($end != $begin) {
+ croak __PACKAGE__, ":prop_invmap: Multiple maps per code point in '$prop' require single-element ranges: begin=$begin, end=$end, map=$map";
+ }
+ if (! ref $invmap[-2]) {
+ $invmap[-2] = [ $invmap[-2], $map ];
+ }
+ else {
+ push @{$invmap[-2]}, $map;
+ }
+ $has_multiples = 1;
next;
}
+ elsif ($invlist[-1] == $begin) {
+
+ # If the input isn't in the most compact form, so that there
+ # are two adjacent ranges that map to the same thing, they
+ # should be combined (EXCEPT where the arrays require
+ # adjustments, in which case everything is already set up
+ # correctly). This happens in our constructed dt mapping, as
+ # Element [-2] is the map for the latest range so far
+ # processed. Just set the beginning point of the map to
+ # $missing (in invlist[-1]) to 1 beyond where this range ends.
+ # For example, in
+ # 12\t13\tXYZ
+ # 14\t17\tXYZ
+ # we have set it up so that it looks like
+ # 12 => XYZ
+ # 14 => $missing
+ #
+ # We now see that it should be
+ # 12 => XYZ
+ # 18 => $missing
+ if (! $requires_adjustment && @invlist > 1 && ( (defined $map)
+ ? $invmap[-2] eq $map
+ : $invmap[-2] eq 'Y'))
+ {
+ $invlist[-1] = $end + 1;
+ next;
+ }
- # Here, the range started in the previous iteration that maps to
- # $missing starts at the same code point as this range. That
- # means there is no gap to fill that that range was intended for,
- # so we just pop it off the parallel arrays.
- pop @invlist;
- pop @invmap;
- }
-
- # Add the range beginning, and the range's map.
- push @invlist, $begin;
- if ($returned_prop eq 'ToDm') {
-
- # The decomposition maps are either a line like <hangul syllable>
- # which are to be taken as is; or a sequence of code points in hex
- # and separated by blanks. Convert them to decimal, and if there
- # is more than one, use an anonymous array as the map.
- if ($map =~ /^ < /x) {
- push @invmap, $map;
+ # Here, the range started in the previous iteration that maps
+ # to $missing starts at the same code point as this range.
+ # That means there is no gap to fill that that range was
+ # intended for, so we just pop it off the parallel arrays.
+ pop @invlist;
+ pop @invmap;
}
- else {
- my @map = split " ", $map;
- if (@map == 1) {
- push @invmap, $map[0];
+
+ # Add the range beginning, and the range's map.
+ push @invlist, $begin;
+ if ($returned_prop eq 'ToDm') {
+
+ # The decomposition maps are either a line like <hangul
+ # syllable> which are to be taken as is; or a sequence of code
+ # points in hex and separated by blanks. Convert them to
+ # decimal, and if there is more than one, use an anonymous
+ # array as the map.
+ if ($map =~ /^ < /x) {
+ push @invmap, $map;
}
else {
- push @invmap, \@map;
+ my @map = split " ", $map;
+ if (@map == 1) {
+ push @invmap, $map[0];
+ }
+ else {
+ push @invmap, \@map;
+ }
}
}
- }
- else {
+ else {
- # Otherwise, convert hex formatted list entries to decimal; add a
- # 'Y' map for the missing value in binary properties, or
- # otherwise, use the input map unchanged.
- $map = ($format eq 'x')
- ? hex $map
- : $format eq 'b'
- ? 'Y'
- : $map;
- push @invmap, $map;
- }
+ # Otherwise, convert hex formatted list entries to decimal;
+ # add a 'Y' map for the missing value in binary properties, or
+ # otherwise, use the input map unchanged.
+ $map = ($format eq 'x' || $format eq 'ax')
+ ? hex $map
+ : $format eq 'b'
+ ? 'Y'
+ : $map;
+ push @invmap, $map;
+ }
- # We just started a range. It ends with $end. The gap between it and
- # the next element in the list must be filled with a range that maps
- # to the default value. If there is no gap, the next iteration will
- # pop this, unless there is no next iteration, and we have filled all
- # of the Unicode code space, so check for that and skip.
- if ($end < $MAX_UNICODE_CODEPOINT) {
- push @invlist, $end + 1;
- push @invmap, $missing;
+ # We just started a range. It ends with $end. The gap between it
+ # and the next element in the list must be filled with a range
+ # that maps to the default value. If there is no gap, the next
+ # iteration will pop this, unless there is no next iteration, and
+ # we have filled all of the Unicode code space, so check for that
+ # and skip.
+ if ($end < $Unicode::UCD::MAX_CP) {
+ push @invlist, $end + 1;
+ push @invmap, $missing;
+ }
}
}
push @invmap, $missing;
}
- # And add in standard element that all non-Unicode code points map to:
- # $missing
- push @invlist, $MAX_UNICODE_CODEPOINT + 1;
- push @invmap, $missing;
+ # The final element is always for just the above-Unicode code points. If
+ # not already there, add it. It merely splits the current final range
+ # that extends to infinity into two elements, each with the same map.
+ # (This is to conform with the API that says the final element is for
+ # $MAX_UNICODE_CODEPOINT + 1 .. INFINITY.)
+ if ($invlist[-1] != $MAX_UNICODE_CODEPOINT + 1) {
+ push @invmap, $invmap[-1];
+ push @invlist, $MAX_UNICODE_CODEPOINT + 1;
+ }
# The second component of the map are those values that require
# non-standard specification, stored in SPECIALS. These override any
# If the overrides came from SPECIALS, the code point keys are
# packed UTF-8.
if ($overrides == $swash->{'SPECIALS'}) {
- $cp = unpack("C0U", $cp_maybe_utf8);
- @map = unpack "U0U*", $swash->{'SPECIALS'}{$cp_maybe_utf8};
+ $cp = $cp_maybe_utf8;
+ if (! utf8::decode($cp)) {
+ croak __PACKAGE__, "::prop_invmap: Malformed UTF-8: ",
+ map { sprintf("\\x{%02X}", unpack("C", $_)) }
+ split "", $cp;
+ }
+
+ $cp = unpack("W", $cp);
+ @map = unpack "W*", $swash->{'SPECIALS'}{$cp_maybe_utf8};
# The empty string will show up unpacked as an empty
# array.
=head2 B<Blocks versus Scripts>
The difference between a block and a script is that scripts are closer
-to the linguistic notion of a set of code points required to present
+to the linguistic notion of a set of code points required to represent
languages, while block is more of an artifact of the Unicode code point
numbering and separation into blocks of consecutive code points (so far the
size of a block is some multiple of 16, like 128 or 256).
C<Latin Extended-B>. On the other hand, the Latin script does not
contain all the characters of the C<Basic Latin> block (also known as
ASCII): it includes only the letters, and not, for example, the digits
-or the punctuation.
+nor the punctuation.
For blocks see L<http://www.unicode.org/Public/UNIDATA/Blocks.txt>
This newer style is consistent with the values of other Unicode properties.
To preserve backward compatibility, all the functions in Unicode::UCD that
-return block names (except one) return the old-style ones. That one function,
-L</prop_value_aliases()> can be used to convert from old-style to new-style:
+return block names (except as noted) return the old-style ones.
+L</prop_value_aliases()> returns the new-style and can be used to convert from
+old-style to new-style:
my $new_style = prop_values_aliases("block", $old_style);
Note that starting in Unicode 6.1, many of the block names have shorter
synonyms. These are always given in the new style.
-=head1 BUGS
-
-Does not yet support EBCDIC platforms.
-
=head1 AUTHOR
Jarkko Hietaniemi. Now maintained by perl5 porters.
https://perl5.git.perl.org / perl5.git / blobdiff