diff options
| -rw-r--r-- | lib/Unicode/UCD.pm | 52 | ||||
| -rw-r--r-- | lib/Unicode/UCD.t | 2 |
2 files changed, 26 insertions, 28 deletions
diff --git a/lib/Unicode/UCD.pm b/lib/Unicode/UCD.pm index eb4de2882d..522c540dd9 100644 --- a/lib/Unicode/UCD.pm +++ b/lib/Unicode/UCD.pm @@ -710,45 +710,43 @@ sub bidi_types { my $compexcl = compexcl(0x09dc); -This returns B<true> if the -L</code point argument> should not be produced by composition normalization, -B<AND> if that fact is not otherwise determinable from the Unicode data base. -It currently does not return B<true> if the code point has a decomposition +This routine is included for backwards compatibility, but as of Perl 5.12, for +most purposes it is probably more convenient to use one of the following +instead: + + my $compexcl = chr(0x09dc) =~ /\p{Comp_Ex}; + my $compexcl = chr(0x09dc) =~ /\p{Full_Composition_Exclusion}; + +or even + + my $compexcl = chr(0x09dc) =~ /\p{CE}; + my $compexcl = chr(0x09dc) =~ /\p{Composition_Exclusion}; + +The first two forms return B<true> if the L</code point argument> should not +be produced by composition normalization. The final two forms +additionally require that this fact not otherwise be determinable from +the Unicode data base for them to return B<true>. + +This routine behaves identically to the final two forms. That is, +it does not return B<true> if the code point has a decomposition consisting of another single code point, nor if its decomposition starts with a code point whose combining class is non-zero. Code points that meet either of these conditions should also not be produced by composition -normalization. +normalization, which is probably why you should use the +C<Full_Composition_Exclusion> property instead, as shown above. -It returns B<false> otherwise. +The routine returns B<false> otherwise. =cut -my %COMPEXCL; - -sub _compexcl { - unless (%COMPEXCL) { - if (openunicode(\$COMPEXCLFH, "CompositionExclusions.txt")) { - local $_; - while (<$COMPEXCLFH>) { - if (/^([0-9A-F]+)\s+\#\s+/) { - my $code = hex($1); - $COMPEXCL{$code} = undef; - } - } - close($COMPEXCLFH); - } - } -} - sub compexcl { my $arg = shift; my $code = _getcode($arg); croak __PACKAGE__, "::compexcl: unknown code '$arg'" unless defined $code; - _compexcl() unless %COMPEXCL; - - return exists $COMPEXCL{$code}; + no warnings "utf8"; # So works on surrogates and non-Unicode code points + return chr($code) =~ /\p{Composition_Exclusion}/; } =head2 B<casefold()> @@ -1233,8 +1231,6 @@ if you are wondering where one of your filehandles went, that's where. Does not yet support EBCDIC platforms. -L</compexcl()> should give a complete list of excluded code points. - =head1 AUTHOR Jarkko Hietaniemi diff --git a/lib/Unicode/UCD.t b/lib/Unicode/UCD.t index 795888aa2f..ae8432cfaf 100644 --- a/lib/Unicode/UCD.t +++ b/lib/Unicode/UCD.t @@ -301,6 +301,8 @@ is(Unicode::UCD::UnicodeVersion, '6.0.0', 'UnicodeVersion'); use Unicode::UCD qw(compexcl); ok(!compexcl(0x0100), 'compexcl'); +ok(!compexcl(0xD801), 'compexcl of surrogate'); +ok(!compexcl(0x110000), 'compexcl of non-Unicode code point'); ok( compexcl(0x0958)); use Unicode::UCD qw(casefold); |