Correct confusable pair for U+1D9F from U+1D4B to U+1D4C

roozbehp · roozbehp · commit 137b654f3214 · 2026-02-19T16:54:05.000-08:00
See unicode-org/properties#500 This needs a temporary patch to the code to skip the suppression of the new pair.
diff --git a/unicodetools/data/security/dev/confusables.txt b/unicodetools/data/security/dev/confusables.txt
@@ -1,5 +1,5 @@
 # confusables.txt
-# Date: 2026-02-06, 21:41:45 GMT
+# Date: 2026-02-20, 00:35:25 GMT
 # © 2026 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -2389,13 +2389,13 @@ A613 ;	0190 ;	MA	# ( ꘓ → Ɛ ) VAI SYMBOL FEENG → LATIN CAPITAL LETTER OPEN
 16F2D ;	0190 ;	MA	# ( 𖼭 → Ɛ ) MIAO LETTER NYHA → LATIN CAPITAL LETTER OPEN E	# 
 10401 ;	0190 ;	MA	# ( 𐐁 → Ɛ ) DESERET CAPITAL LETTER LONG E → LATIN CAPITAL LETTER OPEN E	# 
 
-1D9F ;	1D4B ;	MA	# ( ᶟ → ᵋ ) MODIFIER LETTER SMALL REVERSED OPEN E → MODIFIER LETTER SMALL OPEN E	# 
-
 1D08 ;	025C ;	MA	# ( ᴈ → ɜ ) LATIN SMALL LETTER TURNED OPEN E → LATIN SMALL LETTER REVERSED OPEN E	# 
 0437 ;	025C ;	MA	# ( з → ɜ ) CYRILLIC SMALL LETTER ZE → LATIN SMALL LETTER REVERSED OPEN E	# 
 
 0499 ;	025C 0326 ;	MA	# ( ҙ → ɜ̦ ) CYRILLIC SMALL LETTER ZE WITH DESCENDER → LATIN SMALL LETTER REVERSED OPEN E, COMBINING COMMA BELOW	# →з̡→
 
+1D9F ;	1D4C ;	MA	# ( ᶟ → ᵌ ) MODIFIER LETTER SMALL REVERSED OPEN E → MODIFIER LETTER SMALL TURNED OPEN E	# 
+
 10442 ;	025E ;	MA	# ( 𐑂 → ɞ ) DESERET SMALL LETTER VEE → LATIN SMALL LETTER CLOSED REVERSED OPEN E	# 
 
 A79D ;	029A ;	MA	# ( ꞝ → ʚ ) LATIN SMALL LETTER VOLAPUK OE → LATIN SMALL LETTER CLOSED OPEN E	# 
diff --git a/unicodetools/data/security/dev/confusablesSummary.txt b/unicodetools/data/security/dev/confusablesSummary.txt
@@ -1,5 +1,5 @@
 # confusablesSummary.txt
-# Date: 2026-02-06, 21:41:44 GMT
+# Date: 2026-02-20, 00:35:24 GMT
 # © 2026 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -12802,8 +12802,8 @@
 	(‎ ᴴ ‎)	1D34	 MODIFIER LETTER CAPITAL H
 ←	(‎ ᵸ ‎)	1D78	 MODIFIER LETTER CYRILLIC EN
 
-#	ᵋ	ᶟ
-	(‎ ᵋ ‎)	1D4B	 MODIFIER LETTER SMALL OPEN E
+#	ᵌ	ᶟ
+	(‎ ᵌ ‎)	1D4C	 MODIFIER LETTER SMALL TURNED OPEN E
 ←	(‎ ᶟ ‎)	1D9F	 MODIFIER LETTER SMALL REVERSED OPEN E
 
 #	ᵍ	ᶢ
diff --git a/unicodetools/data/security/dev/data/source/confusables-macFonts.txt b/unicodetools/data/security/dev/data/source/confusables-macFonts.txt
@@ -1204,8 +1204,6 @@
 
 1D34 ;	1D78	# ( ᴴ ~ ᵸ ) MODIFIER LETTER CAPITAL H ~ MODIFIER LETTER CYRILLIC EN
 
-1D4B ;	1D9F	# ( ᵋ ~ ᶟ ) MODIFIER LETTER SMALL OPEN E ~ MODIFIER LETTER SMALL REVERSED OPEN E
-
 1D4C ;	1D9F	# ( ᵌ ~ ᶟ ) MODIFIER LETTER SMALL TURNED OPEN E ~ MODIFIER LETTER SMALL REVERSED OPEN E
 
 1D4D ;	1DA2	# ( ᵍ ~ ᶢ ) MODIFIER LETTER SMALL G ~ MODIFIER LETTER SMALL SCRIPT G
diff --git a/unicodetools/data/security/dev/data/source/confusables-source.txt b/unicodetools/data/security/dev/data/source/confusables-source.txt
@@ -6151,3 +6151,6 @@ ABEC ; 002E
 1F675 ; 0026
 206A4 ; 3005
 27144 ; 8641
+
+# Correction (PAG ref #500)
+1D9F ; 1D4C
diff --git a/unicodetools/data/security/dev/data/source/formatted-macFonts.txt b/unicodetools/data/security/dev/data/source/formatted-macFonts.txt
@@ -1,6 +1,6 @@
 # formatted-macFonts.txt
-# Date: 2025-11-13, 04:42:21 GMT
-# © 2025 Unicode®, Inc.
+# Date: 2026-02-20, 00:35:23 GMT
+# © 2026 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
 #
@@ -883,7 +883,7 @@
 
 1D34 ;	1D78	# ( ᴴ ~ ᵸ ) MODIFIER LETTER CAPITAL H ~ MODIFIER LETTER CYRILLIC EN
 
-1D4B ;	1D9F	# ( ᵋ ~ ᶟ ) MODIFIER LETTER SMALL OPEN E ~ MODIFIER LETTER SMALL REVERSED OPEN E
+1D4C ;	1D9F	# ( ᵌ ~ ᶟ ) MODIFIER LETTER SMALL TURNED OPEN E ~ MODIFIER LETTER SMALL REVERSED OPEN E
 
 1D4D ;	1DA2	# ( ᵍ ~ ᶢ ) MODIFIER LETTER SMALL G ~ MODIFIER LETTER SMALL SCRIPT G
 
diff --git a/unicodetools/data/security/dev/data/source/formatted-source.txt b/unicodetools/data/security/dev/data/source/formatted-source.txt
@@ -1,5 +1,5 @@
 # formatted-source.txt
-# Date: 2026-02-06, 21:41:43 GMT
+# Date: 2026-02-20, 00:35:22 GMT
 # © 2026 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -4414,6 +4414,8 @@
 
 1D43 2044 209B ;	2101	#* ( ᵃ⁄ₛ ~ ℁ ) MODIFIER LETTER SMALL A, FRACTION SLASH, LATIN SUBSCRIPT SMALL LETTER S ~ ADDRESSED TO THE SUBJECT
 
+1D4C ;	1D9F	# ( ᵌ ~ ᶟ ) MODIFIER LETTER SMALL TURNED OPEN E ~ MODIFIER LETTER SMALL REVERSED OPEN E
+
 1D52 ;	2070	# ( ᵒ ~ ⁰ ) MODIFIER LETTER SMALL O ~ SUPERSCRIPT ZERO
 
 1D9C 2044 1D64 ;	2106	#* ( ᶜ⁄ᵤ ~ ℆ ) MODIFIER LETTER SMALL C, FRACTION SLASH, LATIN SUBSCRIPT SMALL LETTER U ~ CADA UNA
diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/GenerateConfusables.java b/unicodetools/src/main/java/org/unicode/text/UCD/GenerateConfusables.java
@@ -1384,7 +1384,15 @@ private void add2(String source, String target, String type, int count, String l
                                     + ";\t"
                                     + line);
                 }
-            } else if (suppress_NFKC && nfkdSource.equals(nfkdTarget)) {
+            } else if (suppress_NFKC
+                    && nfkdSource.equals(nfkdTarget)
+                    && !source.equals("\u1D4C")
+                    && !target.equals("\u1D4C")) {
+                // Skipping the suppression of U+1D4C temporarily so that we can
+                // add the confusable pair (U+1D9F, U+1D4C) that have the same
+                // compatibility decomposition, but not the same canonical decomposition.
+                // In the future, suppress_NFKC should be set to false and all
+                // resulting additions reviewed.
                 if (SHOW_SUPPRESS) {
                     System.out.println(
                             "*** Suppressing nfkc for:\t"
