Support Unicode 17.0

This adds full support for this latest version of Unicode.  What was
essentially missing was updating the rules for the break properties,
like \b{wb}.  This is always a pain, but the changes made for 15.1 and
16.0 made it much easier.

Author: khwilliamson

charclass_invlists.inc

@@ -50,7 +50,7 @@ sub NON_ASCII_PLATFORM { ord("A") != 65 }
 # expected, a warning will be generated.  If an older version is being
 # compiled, any bounds tests that fail in the generated test file (-maketest
 # option) will be marked as TODO.
-my $version_of_mk_invlist_bounds = v16.0.0;
+my $version_of_mk_invlist_bounds = v17.0.0;
 
 ##########################################################################
 #

lib/unicore/mktables

@@ -27,6 +27,10 @@ here, but most should go in the L</Performance Enhancements> section.
 
 [ List each enhancement as a =head2 entry ]
 
+=head2 Unicode 17.0 is supported
+
+See L<https://www.unicode.org/versions/Unicode17.0.0/>.
+
 =head1 Security
 
 XXX Any security-related notices go here. In particular, any security

lib/unicore/uni_keywords.pl

@@ -2499,12 +2499,12 @@ ()
                                              match_return => 'LB_NOBREAK',
                                              rule => '19a',
                                            },
-        LB_various_then_HY_or_HH_v_AL => {
+        LB_various_then_HY_or_HH_v_AL_or_HL  => {
                                              enum => $lb_enum++,
                                              match_return => 'LB_NOBREAK',
                                              rule => '20a',
                                            },
-        LB_HL_then_HY_or_BA_sans_EA_v_nonHL => {
+        LB_HL_then_HY_or_HH_v_nonHL => {
                                              enum => $lb_enum++,
                                              match_return => 'LB_NOBREAK',
                                              rule => '21a',
@@ -2693,7 +2693,7 @@ ()
     # LB12a Do not break before NBSP and related characters, except after
     # spaces and hyphens.
     # [^SP BA HY] × GL
-    set_lb_nobreak([ qw(^ SP BA HY) ], 'GL', '12a');
+    set_lb_nobreak([ qw(^ SP BA HY HH) ], 'GL', '12a');
 
     # LB13 Do not break before ‘]’ or ‘!’ or ‘;’ or ‘/’, even after spaces, as
     # tailored by example 7 in http://www.unicode.org/reports/tr14/#Examples
@@ -2800,25 +2800,28 @@ ()
     # LB20a Do not break after a word-initial hyphen.
     #   ( sot | BK | CR | LF | NL | SP | ZW | CB | GL )
     #   ( HY | HH )
-    # × AL
-    $dfa = 'LB_various_then_HY_or_HH_v_AL';
-    add_lb_dfa($_, 'AL', $dfa, '20a') for qw(HY HH);
+    # × ( AL | HL )
+    $dfa = 'LB_various_then_HY_or_HH_v_AL_or_HL';
+    for $lhs (qw(HY HH)) {
+        add_lb_dfa($lhs, $_, $dfa, '20a') for qw(AL HL);
+    }
 
     # LB21 Do not break before hyphen-minus, other hyphens, fixed-width
     # spaces, small kana, and other non-starters, or after acute accents.
     # × BA
+    # × HH
     # × HY
     # × NS
     $rule = 21;
-    set_lb_nobreak('*', $_, $rule) for qw(BA HY NS);
+    set_lb_nobreak('*', $_, $rule) for qw(BA HH HY NS);
     # BB ×
     set_lb_nobreak('BB', '*', $rule);
 
-    # LB21a Don't break after Hebrew + HY.
-    # HL (HY | [ BA - $EastAsian ]) × [^HL]
+    # LB21a Don't break after the hyphen in Hebrew + Hyphen + non-Hebrew.
+    # HL (HY | HH) × [^HL]
     $rule = '21a';
-    $dfa = 'LB_HL_then_HY_or_BA_sans_EA_v_nonHL';
-    add_lb_dfa($_, [ qw(^ HL) ], $dfa, $rule) for qw(HY BA_sans_EA);
+    $dfa = 'LB_HL_then_HY_or_HH_v_nonHL';
+    add_lb_dfa($_, [ qw(^ HL) ], $dfa, $rule) for qw(HY HH);
 
     # LB21b Don’t break between Solidus and Hebrew letters.
     # SY × HL

pod/perldelta.pod

@@ -5605,11 +5605,11 @@ S_isLB(pTHX_ LB_enum before,
                    || isLB_CP(prev);
             break;
 
-          case LB_various_then_HY_or_HH_v_AL:
+          case LB_various_then_HY_or_HH_v_AL_or_HL:
             /* LB20a Do not break after a word-initial hyphen.
              *   ( sot | BK | CR | LF | NL | SP | ZW | CB | GL )
              *   ( HY | HH ] )
-             * × AL */
+             * × AL | HL */
             prev = backup_one_LB_but_over_CM_ZWJ(strbeg, &prev_pos,
                                                  utf8_target);
             matched = (   isLB_EDGE(prev)
@@ -5637,9 +5637,10 @@ S_isLB(pTHX_ LB_enum before,
             matched = isLB_B2(prev);
             break;
 
-          case LB_HL_then_HY_or_BA_sans_EA_v_nonHL:
-            /* LB21a Don't break after Hebrew + HY.
-             *       HL (HY | [ BA - $EastAsian ]) × [^HL] */
+          case LB_HL_then_HY_or_HH_v_nonHL:
+            /* LB21a Do not break after the hyphen in Hebrew + Hyphen +
+             * non-Hebrew.
+             *       HL (HY | HH ) × [^HL] */
             matched = isLB_HL(backup_one_LB_but_over_CM_ZWJ(strbeg, &prev_pos,
                                                             utf8_target));
             break;

regcharclass.h

@@ -35,7 +35,7 @@
  * a2f16fb873ab4fcdf3221cb1a8a85a134ddd6ed03603181823ff5206af3741ce lib/unicore/BidiMirroring.txt
  * c0edefaf1a19771e830a82735472716af6bf3c3975f6c2a23ffbe2580fbbcb15 lib/unicore/Blocks.txt
  * ff8d8fefbf123574205085d6714c36149eb946d717a0c585c27f0f4ef58c4183 lib/unicore/CaseFolding.txt
- * 2f239196ef3b5b61db5cc476e9bd80f534d15aa1b74e1be1dea5d042a344c85f lib/unicore/CompositionExclusions.txt
+ * 5e6e9c8f8e76561da04cb1703a9306c63707be2ed8ff2eb12cd3a942368a6f72 lib/unicore/CompositionExclusions.txt
  * f8ecdf768bdc210f201abd271d9bc587825618a86a7046a8146cc816393f1998 lib/unicore/DAge.txt
  * 24c7fed1195c482faaefd5c1e7eb821c5ee1fb6de07ecdbaa64b56a99da22c08 lib/unicore/DCoreProperties.txt
  * 71fd6a206a2c0cdd41feb6b7f656aa31091db45e9cedc926985d718397f9e488 lib/unicore/DNormalizationProps.txt
@@ -49,16 +49,15 @@
  * 17bb07f5e37f995351ddcef393c04464a9e3891ed0c0bd56a03a5c5e400a6326 lib/unicore/Jamo.txt
  * e6a18fa91f8f6a6f8e534b1d3f128c21ada45bfe152eb6b1bcc5e15fd8ac92e6 lib/unicore/LineBreak.txt
  * 793f6f1e4d15fd90f05ae66460191dc4d75d1fea90136a25f30dd6a4cb950eac lib/unicore/NameAliases.txt
- * 0cd1c928edac72ea1369187599727c4f0d92367316b4c5ee5140475ab9298be0 lib/unicore/NamedSequences.txt
- * 5019ffd530751a741900c849c0e010332f142a3612234639bd200b82138a87db lib/unicore/NormTest.txt
+ * 360dac27d5abafdcd8c03a8597f47acf92e8ebf7f6ee28020c173ed8b2ed0cc5 lib/unicore/NamedSequences.txt
  * 130dcddcaadaf071008bdfce1e7743e04fdfbc910886f017d9f9ac931d8c64dd lib/unicore/PropList.txt
- * 64e9a5f76f7a1e8b5a47d6a1f9a26522a251208f5276bdfa1559dac7cf2e827a lib/unicore/PropValueAliases.txt
+ * 670d2bebb48649c04fabfbf033308073dcff47946324a8033237254c048b3b01 lib/unicore/PropValueAliases.txt
  * 4441f573caf952ffece1d7c892e7715bd7136dfc26f96eb6f268bf1e474715fb lib/unicore/PropertyAliases.txt
  * ec2107e58825a1586acee8e0911ce18260394ac8b87e535ca325f1ccbeb06bc6 lib/unicore/ScriptExtensions.txt
  * 9f5e50d3abaee7d6ce09480f325c706f485ae3240912527e651954d2d6b035bf lib/unicore/Scripts.txt
  * efc25faf19de21b92c1194c111c932e03d2a5eaf18194e33f1156e96de4c9588 lib/unicore/SpecialCasing.txt
  * 2e1efc1dcb59c575eedf5ccae60f95229f706ee6d031835247d843c11d96470c lib/unicore/UnicodeData.txt
- * a7b46c19e24355257030b73be046c71b172595ec4a106867d3f988e3a4007208 lib/unicore/Unikemet.txt
+ * 76a3081265e6eb673873f9c93d6f36062e82c7ed027c5c1a592accfbe48c20a5 lib/unicore/Unikemet.txt
  * dcef09c3fb24d356b042569c328ec341efc5b53447700d799f2fb4834c3cd3cd lib/unicore/VerticalOrientation.txt
  * e2d134d2c52919bace503ebb6a551c1855fe1a1faec18478c78fff254a1793ec lib/unicore/auxiliary/GCBTest.txt
  * d6b51d1d2ae5c33b451b7ed994b48f1f4dc62b2272a5831e7fd418514a6bae89 lib/unicore/auxiliary/GraphemeBreakProperty.txt
@@ -79,9 +78,9 @@
  * dad3ef492d198d6f1dde4922b175f7371a27dfe62fce489f3e04807015a4c682 lib/unicore/extracted/DLineBreak.txt
  * 7c83684d3336b698381745b78a971c3e1242cb3fcac58604469086c19b6edcee lib/unicore/extracted/DNumType.txt
  * 139b976bdc288be01c80f018523da769cf2845109b5a7f0f8a432db64bfedcfa lib/unicore/extracted/DNumValues.txt
- * a09a6a34898bdbe7bd387837f0cad2e4a035cd5340d0c12c03b4e66b0ccdb7a6 lib/unicore/mktables
+ * 03640d8ad18fc65de766f2034a927f7442960e998d3243845ca9b9fe31bfe1ab lib/unicore/mktables
  * 8c30575264b2772c7a69c5bb6069a28f0e0a7a0df735871bde2d99ee674316ac lib/unicore/version
  * 0a6b5ab33bb1026531f816efe81aea1a8ffcd34a27cbea37dd6a70a63d73c844 regen/charset_translations.pl
  * c7ff8e0d207d3538c7feb4a1a152b159e5e902d20293b303569ea8323e84633e regen/mk_PL_charclass.pl
- * ec2bea650f1338fcd1f2f5b0e589f89e653c180b3994468788fd343a2869ced7 regen/mk_invlists.pl
+ * 33a5e583d836b8bb97b6b1d1c6d1766defe4cbdeb8bcbe865d76f71206762be9 regen/mk_invlists.pl
  * ex: set ro ft=c: */