Linkification in IndexUnicodeProperties & ExtraProperty(Value)Aliases (#1263)

* IndexUnicodeProperties, ExtraPropertyAliases, ExtraPropertyValueAliases

* GenerateEnums

* format

* Two bugs, each of which would pin LinkEmail to 17.0

* Markus’s review

* Markus’s review

* Another ICU property trying to sneak into Link_* property derivations

* ! is exceptional for Link_Email

Author: eggrobin

unicodetools/src/main/java/org/unicode/props/UcdProperty.java

@@ -27,6 +27,7 @@
 import org.unicode.props.UcdPropertyValues.Joining_Group_Values;
 import org.unicode.props.UcdPropertyValues.Joining_Type_Values;
 import org.unicode.props.UcdPropertyValues.Line_Break_Values;
+import org.unicode.props.UcdPropertyValues.Link_Term_Values;
 import org.unicode.props.UcdPropertyValues.Math_Class_Ex_Values;
 import org.unicode.props.UcdPropertyValues.Math_Class_Values;
 import org.unicode.props.UcdPropertyValues.NFC_Quick_Check_Values;
@@ -98,6 +99,7 @@ public enum UcdProperty {
     Equivalent_Unified_Ideograph(PropertyType.String, DerivedPropertyStatus.Approved, "EqUIdeo"),
     FC_NFKC_Closure(PropertyType.String, DerivedPropertyStatus.Approved, "FC_NFKC"),
     Idn_Mapping(PropertyType.String, DerivedPropertyStatus.NonUCDNonProperty, "idnm"),
+    Link_Bracket(PropertyType.String, DerivedPropertyStatus.NonUCDProperty, "Link_Bracket"),
     Lowercase_Mapping(PropertyType.String, DerivedPropertyStatus.Approved, "lc"),
     NFKC_Casefold(PropertyType.String, DerivedPropertyStatus.Approved, "NFKC_CF"),
     NFKC_Simple_Casefold(PropertyType.String, DerivedPropertyStatus.Approved, "NFKC_SCF"),
@@ -761,6 +763,12 @@ public enum UcdProperty {
             Line_Break_Values.class,
             null,
             "lb"),
+    Link_Term(
+            PropertyType.Enumerated,
+            DerivedPropertyStatus.NonUCDProperty,
+            Link_Term_Values.class,
+            null,
+            "Link_Term"),
     Math_Class(
             PropertyType.Enumerated,
             DerivedPropertyStatus.NonUCDProperty,
@@ -921,6 +929,12 @@ public enum UcdProperty {
     ID_Start(PropertyType.Binary, DerivedPropertyStatus.Approved, Binary.class, null, "IDS"),
     Ideographic(PropertyType.Binary, DerivedPropertyStatus.Approved, Binary.class, null, "Ideo"),
     Join_Control(PropertyType.Binary, DerivedPropertyStatus.Approved, Binary.class, null, "Join_C"),
+    Link_Email(
+            PropertyType.Binary,
+            DerivedPropertyStatus.NonUCDProperty,
+            Binary.class,
+            null,
+            "Link_Email"),
     Logical_Order_Exception(
             PropertyType.Binary, DerivedPropertyStatus.Approved, Binary.class, null, "LOE"),
     Lowercase(PropertyType.Binary, DerivedPropertyStatus.Approved, Binary.class, null, "Lower"),

unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java

@@ -1890,6 +1890,39 @@ public static Line_Break_Values forName(String name) {
         }
     }
 
+    // Link_Bracket
+    public enum Link_Term_Values implements Named {
+        Include("Include"),
+        Hard("Hard"),
+        Soft("Soft"),
+        Close("Close"),
+        Open("Open");
+        private final PropertyNames<Link_Term_Values> names;
+
+        private Link_Term_Values(String shortName, String... otherNames) {
+            names =
+                    new PropertyNames<Link_Term_Values>(
+                            Link_Term_Values.class, this, shortName, otherNames);
+        }
+
+        @Override
+        public PropertyNames<Link_Term_Values> getNames() {
+            return names;
+        }
+
+        @Override
+        public String getShortName() {
+            return names.getShortName();
+        }
+
+        private static final NameMatcher<Link_Term_Values> NAME_MATCHER =
+                PropertyNames.getNameToEnums(Link_Term_Values.class);
+
+        public static Link_Term_Values forName(String name) {
+            return NAME_MATCHER.get(name);
+        }
+    }
+
     // Lowercase_Mapping
     public enum Math_Class_Values implements Named {
         None("None"),

unicodetools/src/main/resources/org/unicode/props/ExtraPropertyAliases.txt

@@ -9,6 +9,7 @@ REKS ; RGI_Emoji_Keycap_Sequence ; Emoji_Keycap_Sequence ; Emoji_Combining_Seque
 RETS ; RGI_Emoji_Tag_Sequence ; Emoji_Tag_Sequence ; NonUCDProperty
 REZS ; RGI_Emoji_Zwj_Sequence ; Emoji_Zwj_Sequence ; NonUCDProperty
 RGI_Emoji ; RGI_Emoji ; NonUCDProperty
+Link_Email ; Link_Email ; NonUCDProperty
 
 # ================================================
 # Enumerated Properties
@@ -38,6 +39,8 @@ Math_Class ; Math_Class ; NonUCDProperty
 # characters for which it historically lagged behind the value in MathClass.
 Math_Class_Ex ; Math_Class_Ex ; NonUCDNonProperty
 
+Link_Term  ; Link_Term  ; NonUCDProperty
+
 # ================================================
 # Numeric Properties
 # ================================================
@@ -87,6 +90,8 @@ kSEAL_MCJK ; kSEAL_MCJK ; Provisional
 
 Names_List_Cross_Ref ; Names_List_Cross_Ref ; UCDNonProperty
 
+Link_Bracket ; Link_Bracket ; NonUCDProperty
+
 # ================================================
 # Miscellaneous Properties
 # ================================================

unicodetools/src/main/resources/org/unicode/props/ExtraPropertyValueAliases.txt

@@ -89,6 +89,8 @@
 # @missing: 0000..10FFFF; kEH_NoMirror  ;  No
 # @missing: 0000..10FFFF; kEH_NoRotate  ;  No
 
+# @missing: 0000..10FFFF; Link_Email ; No
+
 # End of binary properties.
 
 # @missing: 0000..10FFFF; Canonical_Combining_Class; Not_Reordered
@@ -447,6 +449,12 @@ Math_Class_Ex ; U    ; Unary
 Math_Class_Ex ; V    ; Vary
 Math_Class_Ex ; X    ; Special
 
+Link_Term  ; Include ; Include
+Link_Term  ; Hard    ; Hard
+Link_Term  ; Soft    ; Soft
+Link_Term  ; Close   ; Close
+Link_Term  ; Open    ; Open
+
 # @missing: 0000..10FFFF; kVietnameseNumeric ; NaN
 # @missing: 0000..10FFFF; kZhuangNumeric ; NaN
 # @missing: 0000..10FFFF; kTayNumeric ; NaN

unicodetools/src/main/resources/org/unicode/props/IndexUnicodeProperties.txt

@@ -21,6 +21,7 @@ FileType ; UnicodeData ; HackField
 # Contains exactly one boolean property, with value "Yes"
 
 FileType ; CompositionExclusions ; List
+FileType ; linkification/*/LinkEmail ; List
 
 # PropertyValue File Type
 # The value is in field 2, except for binary properties, where the value is "Yes"
@@ -529,6 +530,10 @@ security/*/confusables ; Confusable_SA
 security/*/confusables ; Confusable_ML
 security/*/confusables ; Confusable_MA
 
+linkification/*/LinkBracket ; Link_Bracket
+linkification/*/LinkTerm    ; Link_Term
+linkification/*/LinkEmail   ; Link_Email
+
 # Unicode 13 moves the emoji-data.txt and emoji-variation-sequences.txt files
 # from the emoji folder to the ucd/emoji folder.
 # The line with the new location (i.e., the line without version number)

unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/179.txt

@@ -22,7 +22,8 @@ Propertywise [\x{2E60}   \N{WIGGLY EXCLAMATION MARK}
               \x{2E61}   \N{INVERTED WIGGLY EXCLAMATION MARK}]
 CorrespondTo [\x{0021} ! \N{EXCLAMATION MARK}]
     UpTo: East_Asian_Width (Neutral                  vs Narrow),
-          Block            (Supplemental_Punctuation vs Basic_Latin)
+          Block            (Supplemental_Punctuation vs Basic_Latin),
+          Link_Email       (No                       vs Yes)
 
 end Ignoring;