perluniprops: Clarify why certain properties are deprecated

[perl5.git] / lib / unicore / mktables

diff --git a/lib/unicore/mktables b/lib/unicore/mktables
index c468bac..181011b 100644 (file)
--- a/lib/unicore/mktables
+++ b/lib/unicore/mktables
@@ -843,6 +843,22 @@ if ($v_version ge v5.2.0) {
 my $EXTERNAL_MAP = 1;
 my $INTERNAL_MAP = 2;
 
+# To override computed values for writing the map tables for these properties.
+# The default for enum map tables is to write them out, so that the Unicode
+# .txt files can be removed, but all the data to compute any property value
+# for any code point is available in a more compact form.
+my %global_to_output_map = (
+    # Needed by UCD.pm, but don't want to publicize that it exists, so won't
+    # get stuck supporting it if things change.  Sinc it is a STRING property,
+    # it normally would be listed in the pod, but INTERNAL_MAP suppresses
+    # that.
+    Unicode_1_Name => $INTERNAL_MAP,
+
+    Present_In => 0,                # Suppress, as easily computed from Age
+    Canonical_Combining_Class => 0, # Duplicate of CombiningClass.pl
+    Block => 0,                     # Suppress, as Blocks.txt is retained.
+);
+
 # Properties that this program ignores.
 my @unimplemented_properties = (
 'Unicode_Radical_Stroke'    # Remove if changing to handle this one.
@@ -860,7 +876,7 @@ my %why_obsolete;    # Documentation only
 
     my $other_properties = 'other properties';
     my $contributory = "Used by Unicode internally for generating $other_properties and not intended to be used stand-alone";
-    my $why_no_expand  = "Deprecated by Unicode: less useful than UTF-specific calculations",
+    my $why_no_expand  = "Deprecated by Unicode.  These are characters that expand to more than one character in the specified normalization form, but whether they actually take up more bytes or not depends on the encoding being used.  For example, a UTF-8 encoded character may expand to a different number of bytes than a UTF-32 encoded character.";
 
     %why_deprecated = (
         'Grapheme_Link' => 'Deprecated by Unicode:  Duplicates ccc=vr (Canonical_Combining_Class=Virama)',
@@ -884,7 +900,6 @@ my %why_obsolete;    # Documentation only
         'Decomposition_Mapping' => 'Accessible via Unicode::Normalize',
 
         'ISO_Comment' => 'Apparently no demand for it, but can access it through Unicode::UCD::charinfo.  Obsoleted, and code points for it removed in Unicode 5.2',
-        'Unicode_1_Name' => "$simple, and no apparent demand for it, but can access it through Unicode::UCD::charinfo.  If there is no later name for a code point, then this one is used instead in charnames",
 
         'Simple_Case_Folding' => "$simple.  Can access this through Unicode::UCD::casefold",
         'Simple_Lowercase_Mapping' => "$simple.  Can access this through Unicode::UCD::charinfo",
@@ -5580,6 +5595,8 @@ sub trace { return main::trace(@_); }
         return $to_output_map{$addr} if defined $to_output_map{$addr};
 
         my $full_name = $self->full_name;
+        return $global_to_output_map{$full_name}
+                                if defined $global_to_output_map{$full_name};
 
         # If table says to output, do so; if says to suppress it, do so.
         return $EXTERNAL_MAP if grep { $_ eq $full_name } @output_mapped_properties;
@@ -10593,16 +10610,18 @@ sub filter_old_style_case_folding {
         }
 
         # C: complete, F: full, or I: dotted uppercase I -> dotless lowercase
-        # I are all full foldings
-        if ($type eq 'C' || $type eq 'F' || $type eq 'I') {
-            $_ = "$range; Case_Folding; $map";
+        # I are all full foldings; S is single-char.  For S, there is always
+        # an F entry, so we must allow multiple values for the same code
+        # point.  Fortunately this table doesn't need further manipulation
+        # which would preclude using multiple-values.  The S is now included
+        # so that _swash_inversion_hash() is able to construct closures
+        # without having to worry about F mappings.
+        if ($type eq 'C' || $type eq 'F' || $type eq 'I' || $type eq 'S') {
+            $_ = "$range; Case_Folding; $CMD_DELIM$REPLACE_CMD=$MULTIPLE$CMD_DELIM$map";
         }
         else {
             $_ = "";
-            if ($type ne 'S') {
-               $file->carp_bad_line('Expecting C F I S or T in second field');
-               return;
-            }
+            $file->carp_bad_line('Expecting C F I S or T in second field');
         }
 
         # C and S are simple foldings, but simple case folding is not needed
@@ -13233,10 +13252,11 @@ the properties are listed enclosed in (parentheses).
 
 =back
 
-An installation can choose to allow any of these to be matched by changing the
-controlling lists contained in the program
-C<\$Config{privlib}>/F<unicore/mktables> and then re-running F<mktables>.
-(C<\%Config> is available from the Config module).
+An installation can choose to allow any of these to be matched by downloading
+the Unicode database from L<http://www.unicode.org/Public/> to
+C<\$Config{privlib}>/F<unicore/>, changing the controlling lists contained in
+the program C<\$Config{privlib}>/F<unicore/mktables> and then re-running
+F<mktables>.  (C<\%Config> is available from the Config module).
 
 =head1 Files in the I<To> directory (for serious hackers only)
 
@@ -13266,7 +13286,9 @@ names in parentheses), and any flags or comments about them, are:
 
 An installation can choose to change which files are generated by changing the
 controlling lists contained in the program
-C<\$Config{privlib}>/F<unicore/mktables> and then re-running F<mktables>.
+C<\$Config{privlib}>/F<unicore/mktables> and then re-running F<mktables>
+(but the Unicode database must have been downloaded from
+L<http://www.unicode.org/Public/> to C<\$Config{privlib}>F</unicore/> first).
 
 Each of these files defines two hash entries to help reading programs decipher
 it.  One of them looks like this: