Add NFKC_SCF (#423)

.project

@@ -16,12 +16,12 @@
 	</natures>
 	<filteredResources>
 		<filter>
-			<id>1625608051965</id>
+			<id>1683027586342</id>
 			<name></name>
 			<type>30</type>
 			<matcher>
 				<id>org.eclipse.core.resources.regexFilterMatcher</id>
-				<arguments>node_modules|.git|__CREATED_BY_JAVA_LANGUAGE_SERVER__</arguments>
+				<arguments>node_modules|\.git|__CREATED_BY_JAVA_LANGUAGE_SERVER__</arguments>
 			</matcher>
 		</filter>
 	</filteredResources>

unicodetools/.project

@@ -35,12 +35,12 @@
 	</natures>
 	<filteredResources>
 		<filter>
-			<id>1625517710081</id>
+			<id>1683027586324</id>
 			<name></name>
 			<type>30</type>
 			<matcher>
 				<id>org.eclipse.core.resources.regexFilterMatcher</id>
-				<arguments>node_modules|.git|__CREATED_BY_JAVA_LANGUAGE_SERVER__</arguments>
+				<arguments>node_modules|\.git|__CREATED_BY_JAVA_LANGUAGE_SERVER__</arguments>
 			</matcher>
 		</filter>
 	</filteredResources>

unicodetools/data/ucd/dev/PropertyAliases.txt

@@ -1,5 +1,5 @@
 # PropertyAliases-15.1.0.txt
-# Date: 2023-01-31, 22:27:07 GMT
+# Date: 2023-03-23, 00:36:58 GMT
 # © 2023 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use, see https://www.unicode.org/terms_of_use.html
@@ -73,6 +73,7 @@ EqUIdeo                  ; Equivalent_Unified_Ideograph
 FC_NFKC                  ; FC_NFKC_Closure
 lc                       ; Lowercase_Mapping
 NFKC_CF                  ; NFKC_Casefold
+NFKC_SCF                 ; NFKC_Simple_Casefold
 scf                      ; Simple_Case_Folding         ; sfc
 slc                      ; Simple_Lowercase_Mapping
 stc                      ; Simple_Titlecase_Mapping
@@ -210,6 +211,6 @@ XO_NFKC                  ; Expands_On_NFKC
 XO_NFKD                  ; Expands_On_NFKD
 
 # ================================================
-# Total:    132
+# Total:    133
 
 # EOF

unicodetools/data/ucd/dev/PropertyValueAliases.txt

@@ -1,5 +1,5 @@
 # PropertyValueAliases-15.1.0.txt
-# Date: 2023-04-26
+# Date: 2023-05-02, 10:31:42 GMT
 # © 2023 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use, see https://www.unicode.org/terms_of_use.html
@@ -1173,6 +1173,9 @@ NFKC_QC; M                            ; Maybe
 NFKC_QC; N                            ; No
 NFKC_QC; Y                            ; Yes
 
+# NFKC_Simple_Casefold (NFKC_SCF)
+
+
 # NFKD_Quick_Check (NFKD_QC)
 
 NFKD_QC; N                            ; No

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

@@ -228,7 +228,10 @@ public void put(
             String value,
             Merge<String> merger,
             boolean hackHangul) {
-        if (value != null && value.isEmpty() && property != UcdProperty.NFKC_Casefold) {
+        if (value != null
+                && value.isEmpty()
+                && property != UcdProperty.NFKC_Casefold
+                && property != UcdProperty.NFKC_Simple_Casefold) {
             value = null;
         }
         value = normalizeAndVerify(value);
@@ -679,7 +682,9 @@ private static void parsePropertyValueFile(
                                 : line.getParts()[2];
                 // The value should not be an empty string.
                 // Exception: NFKC_Casefold does remove some characters by mapping them to nothing.
-                assert !value.isEmpty() || propInfo.property == UcdProperty.NFKC_Casefold;
+                assert !value.isEmpty()
+                        || propInfo.property == UcdProperty.NFKC_Casefold
+                        || propInfo.property == UcdProperty.NFKC_Simple_Casefold;
                 if (propInfo.property == UcdProperty.kMandarin) {
                     if (indexUnicodeProperties.oldVersion) {
                         value =
@@ -695,6 +700,7 @@ private static void parsePropertyValueFile(
                     String defaultValue = null;
                     switch (propInfo.property) {
                         case NFKC_Casefold:
+                        case NFKC_Simple_Casefold:
                             defaultValue = "<code point>";
                             break;
                         default:

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

@@ -60,6 +60,7 @@ public enum UcdProperty {
     Idn_Mapping(PropertyType.String, "idnm"),
     Lowercase_Mapping(PropertyType.String, "lc"),
     NFKC_Casefold(PropertyType.String, "NFKC_CF"),
+    NFKC_Simple_Casefold(PropertyType.String, "NFKC_SCF"),
     Simple_Case_Folding(PropertyType.String, "scf", "sfc"),
     Simple_Lowercase_Mapping(PropertyType.String, "slc"),
     Simple_Titlecase_Mapping(PropertyType.String, "stc"),

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

@@ -1599,6 +1599,7 @@ public static NFKC_Quick_Check_Values forName(String name) {
         }
     }
 
+    // NFKC_Simple_Casefold
     public enum NFKD_Quick_Check_Values implements Named {
         No("N"),
         Yes("Y");

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

@@ -316,7 +316,11 @@ public final String getFirstNameAlias() {
 
     public final String getFirstValueAlias(String value) {
         if (valueToFirstValueAlias == null) _getFirstValueAliasCache();
-        return valueToFirstValueAlias.get(value).toString();
+        String result = valueToFirstValueAlias.get(value);
+        if (result == null) {
+            throw new IllegalArgumentException(value + " is not a value alias for " + name);
+        }
+        return result;
     }
 
     private void _getFirstValueAliasCache() {

unicodetools/src/main/java/org/unicode/text/UCD/GenerateCaseFolding.java

@@ -93,8 +93,8 @@ public static void makeCaseFold(boolean normalized) throws java.io.IOException {
         for (int ch = 0; ch <= 0x10FFFF; ++ch) {
             Utility.dot(ch);
 
-            var normativeSCF = new StringBuffer();
-            var normativeCF = new StringBuffer();
+            var normativeSCF = new StringBuilder();
+            var normativeCF = new StringBuilder();
 
             try {
                 if (!charsUsed.get(ch)) {
@@ -185,8 +185,8 @@ static void drawLine(
             int ch,
             String type,
             String result,
-            StringBuffer normativeSCF,
-            StringBuffer normativeCF) {
+            StringBuilder normativeSCF,
+            StringBuilder normativeCF) {
         String comment = "";
         if (COMMENT_DIFFS) {
             final String lower = Default.ucd().getCase(UTF16.valueOf(ch), FULL, LOWER);

unicodetools/src/main/java/org/unicode/text/UCD/MakeUnicodeFiles.java

@@ -120,10 +120,11 @@ public static class PrintStyle {
             boolean sortNumeric = false;
 
             String parse(String options) {
-                options = options.replace('\t', ' ');
-                final String[] pieces = Utility.split(options, ' ');
-                for (int i = 1; i < pieces.length; ++i) {
-                    final String piece = pieces[i];
+                Matcher matcher = Pattern.compile("([^\" \t]|\"[^\"]*\")+").matcher(options);
+                matcher.find();
+                String firstPiece = matcher.group();
+                while (matcher.find()) {
+                    final String piece = matcher.group();
                     // binary
                     if (piece.equals("noLabel")) {
                         noLabel = true;
@@ -165,10 +166,10 @@ String parse(String options) {
                         skipUnassigned = afterEquals(piece);
                     } else if (piece.length() != 0) {
                         throw new IllegalArgumentException(
-                                "Illegal PrintStyle Parameter: " + piece + " in " + pieces[0]);
+                                "Illegal PrintStyle Parameter: " + piece + " in " + firstPiece);
                     }
                 }
-                return pieces[0];
+                return firstPiece;
             }
 
             private boolean afterEqualsBoolean(String piece) {
@@ -253,8 +254,26 @@ Map<String, String> getValue2CommentsMap(String property) {
             return propertyToValueToComments.get(property);
         }
 
+        // Returns strings without U+0022 QUOTATION MARK (") unchanged.
+        // Strings that contain " must be enclosed in them, and are returned unquoted, with "" as
+        // the escape sequence, thus:
+        //   meow       ↦ meow
+        //   "meow"     ↦ meow
+        //   """meow""" ↦ "meow"
+        static String unquote(String source) {
+            String contents = source;
+            if (source.charAt(0) == '"' && source.charAt(source.length() - 1) == '"') {
+                contents = source.substring(1, source.length() - 1);
+            }
+            if (contents.matches("(?<!\")(\"\")*\"(?!\")")) {
+                throw new IllegalArgumentException(
+                        "Syntax error: improper quotation marks in " + source);
+            }
+            return contents.replace("\"\"", "\"");
+        }
+
         static String afterEquals(String source) {
-            return source.substring(source.indexOf('=') + 1);
+            return unquote(source.substring(source.indexOf('=') + 1));
         }
 
         static String afterWhitespace(String source) {
@@ -994,6 +1013,7 @@ public static void generateValueAliasFile(String filename) throws IOException {
             if (propName.equals("Bidi_Mirroring_Glyph")
                     || propName.equals("Equivalent_Unified_Ideograph")
                     || propName.equals("NFKC_Casefold")
+                    || propName.equals("NFKC_Simple_Casefold")
                     || propName.equals("Script_Extensions")) {
                 // Action item [172-A71]: Don't print @missing lines
                 // for properties whose specific data files already contain such lines.
@@ -1156,7 +1176,7 @@ public static void generatePropertyFile(String filename) throws IOException {
                 if (v == null) {
                     v = ps.skipUnassigned;
                 }
-                if (!v.equals("<codepoint>")) {
+                if (!v.equals("<code point>")) {
                     final String v2 = prop.getFirstValueAlias(v);
                     if (UnicodeProperty.compareNames(v, v2) != 0) {
                         v = v + " (" + v2 + ")";