no warnings 'surrogate'; # surrogates can be inputs to this
use charnames ();
-our $VERSION = '0.58';
+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 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");
Some of the functions are called with a I<code point argument>, which is either
a decimal or a hexadecimal scalar designating a code point in the platform's
-native character set (extended to Unicode), or C<U+> followed by hexadecimals
+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.
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
+ '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
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>
=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
_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';
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>.)
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
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
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
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
=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 $value;
+ }
# The value name may be loosely or strictly matched; we don't know yet.
# But both types use lower-case.
sub prop_invlist ($;$) {
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;
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, $missing);
# If the overrides came from SPECIALS, the code point keys are
# packed UTF-8.
if ($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);
https://perl5.git.perl.org / perl5.git / blobdiff