Uni 15: new block Arabic_Extended_C with default Bidi_Class=AL

markusicu · markusicu · commit 43652068cf34 · 2021-12-09T15:28:05.000-08:00
diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt
@@ -1,5 +1,5 @@
 # DerivedBidiClass-15.0.0.txt
-# Date: 2021-12-09, 17:39:32 GMT
+# Date: 2021-12-09, 22:21:24 GMT
 # © 2021 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
@@ -15,14 +15,14 @@
 #
 # The unassigned code points that default to AL are in the ranges:
 #     [\u0600-\u07BF \u0860-\u08FF \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF
-#      \U00010D00-\U00010D3F \U00010F30-\U00010F6F
+#      \U00010D00-\U00010D3F \U00010EC0-\U00010EFF \U00010F30-\U00010F6F
 #      \U0001EC70-\U0001ECBF \U0001ED00-\U0001ED4F \U0001EE00-\U0001EEFF]
 #
 #     This includes code points in the Arabic, Syriac, and Thaana blocks, among others.
 #
 # The unassigned code points that default to R are in the ranges:
 #     [\u0590-\u05FF \u07C0-\u085F \uFB1D-\uFB4F
-#      \U00010800-\U00010CFF \U00010D40-\U00010F2F \U00010F70-\U00010FFF
+#      \U00010800-\U00010CFF \U00010D40-\U00010EBF \U00010F00-\U00010F2F \U00010F70-\U00010FFF
 #      \U0001E800-\U0001EC6F \U0001ECC0-\U0001ECFF \U0001ED50-\U0001EDFF \U0001EF00-\U0001EFFF]
 #
 #     This includes code points in the Hebrew, NKo, and Phoenician blocks, among others.
@@ -1244,7 +1244,7 @@ FB46..FB4F    ; R # Lo  [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL
 10EAD         ; R # Pd       YEZIDI HYPHENATION MARK
 10EAE..10EAF  ; R # Cn   [2] <reserved-10EAE>..<reserved-10EAF>
 10EB0..10EB1  ; R # Lo   [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
-10EB2..10EFC  ; R # Cn  [75] <reserved-10EB2>..<reserved-10EFC>
+10EB2..10EBF  ; R # Cn  [14] <reserved-10EB2>..<reserved-10EBF>
 10F00..10F1C  ; R # Lo  [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL
 10F1D..10F26  ; R # No  [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF
 10F27         ; R # Lo       OLD SOGDIAN LIGATURE AYIN-DALETH
@@ -1272,7 +1272,7 @@ FB46..FB4F    ; R # Lo  [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL
 1ED50..1EDFF  ; R # Cn [176] <reserved-1ED50>..<reserved-1EDFF>
 1EF00..1EFFF  ; R # Cn [256] <reserved-1EF00>..<reserved-1EFFF>
 
-# Total code points: 3708
+# Total code points: 3647
 
 # ================================================
 
@@ -2388,6 +2388,7 @@ FEFD..FEFE    ; AL # Cn   [2] <reserved-FEFD>..<reserved-FEFE>
 10D00..10D23  ; AL # Lo  [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA
 10D28..10D2F  ; AL # Cn   [8] <reserved-10D28>..<reserved-10D2F>
 10D3A..10D3F  ; AL # Cn   [6] <reserved-10D3A>..<reserved-10D3F>
+10EC0..10EFC  ; AL # Cn  [61] <reserved-10EC0>..<reserved-10EFC>
 10F30..10F45  ; AL # Lo  [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN
 10F51..10F54  ; AL # No   [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED
 10F55..10F59  ; AL # Po   [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
@@ -2472,7 +2473,7 @@ FEFD..FEFE    ; AL # Cn   [2] <reserved-FEFD>..<reserved-FEFE>
 1EEBC..1EEEF  ; AL # Cn  [52] <reserved-1EEBC>..<reserved-1EEEF>
 1EEF2..1EEFF  ; AL # Cn  [14] <reserved-1EEF2>..<reserved-1EEFF>
 
-# Total code points: 1708
+# Total code points: 1769
 
 # ================================================
 
diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/UCD.java b/unicodetools/src/main/java/org/unicode/text/UCD/UCD.java
@@ -491,6 +491,11 @@ public byte getBidiClass(int codePoint) {
                 // New block 0870..089F "Arabic Extended-B" defaults to bc=AL.
                 blockData.keySet("Arabic_Extended_B", BIDI_AL_SET);
             }
+            if (versionInfo.getMajor() >= 15) {
+                // Unicode 15:
+                // New block 10EC0..10EFF "Arabic Extended-C" defaults to bc=AL.
+                blockData.keySet("Arabic_Extended_C", BIDI_AL_SET);
+            }
             BIDI_R_Delta.removeAll(BIDI_R_SET).removeAll(BIDI_AL_SET);
             if (SHOW_LOADING) {
                 System.out.println("R: Adding " + BIDI_R_Delta);
diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt
@@ -238,14 +238,14 @@ Property:	Bidi_Class
 #
 # The unassigned code points that default to AL are in the ranges:
 #     [\u0600-\u07BF \u0860-\u08FF \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF
-#      \U00010D00-\U00010D3F \U00010F30-\U00010F6F
+#      \U00010D00-\U00010D3F \U00010EC0-\U00010EFF \U00010F30-\U00010F6F
 #      \U0001EC70-\U0001ECBF \U0001ED00-\U0001ED4F \U0001EE00-\U0001EEFF]
 #
 #     This includes code points in the Arabic, Syriac, and Thaana blocks, among others.
 #
 # The unassigned code points that default to R are in the ranges:
 #     [\u0590-\u05FF \u07C0-\u085F \uFB1D-\uFB4F
-#      \U00010800-\U00010CFF \U00010D40-\U00010F2F \U00010F70-\U00010FFF
+#      \U00010800-\U00010CFF \U00010D40-\U00010EBF \U00010F00-\U00010F2F \U00010F70-\U00010FFF
 #      \U0001E800-\U0001EC6F \U0001ECC0-\U0001ECFF \U0001ED50-\U0001EDFF \U0001EF00-\U0001EFFF]
 #
 #     This includes code points in the Hebrew, NKo, and Phoenician blocks, among others.
diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt
@@ -205,8 +205,8 @@ Let $BMExclusions =[≠ ∤ ∦ ≢ \u2ADC]
 In [\p{dt=canonical}-$BMExclusions] Bidi_M * \P{bc=NSM} * dm = Bidi_M * \P{bc=NSM}
 
 # Additional BIDI invariant constants
-Let $AL_blocks = [\u0600-\u07BF \u0860-\u08FF \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF \U00010D00-\U00010D3F \U00010F30-\U00010F6F \U0001EC70-\U0001ECBF \U0001ED00-\U0001ED4F \U0001EE00-\U0001EEFF]
-Let $R_blocks = [\u0590-\u05FF \u07C0-\u085F \uFB1D-\uFB4F \U00010800-\U00010CFF \U00010D40-\U00010F2F \U00010F70-\U00010FFF \U0001E800-\U0001EC6F \U0001ECC0-\U0001ECFF \U0001ED50-\U0001EDFF \U0001EF00-\U0001EFFF]
+Let $AL_blocks = [\u0600-\u07BF \u0860-\u08FF \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF \U00010D00-\U00010D3F \U00010EC0-\U00010EFF \U00010F30-\U00010F6F \U0001EC70-\U0001ECBF \U0001ED00-\U0001ED4F \U0001EE00-\U0001EEFF]
+Let $R_blocks = [\u0590-\u05FF \u07C0-\u085F \uFB1D-\uFB4F \U00010800-\U00010CFF \U00010D40-\U00010EBF \U00010F00-\U00010F2F \U00010F70-\U00010FFF \U0001E800-\U0001EC6F \U0001ECC0-\U0001ECFF \U0001ED50-\U0001EDFF \U0001EF00-\U0001EFFF]
 # 6.1.0 updated blocks
 # 10.0 updated blocks (Syriac Supplement is bc=AL)
 # 11.0 updated blocks (Hanifi Rohingya, Sogdian, Indic Siyaq Numbers are bc=AL); Old Sogdian is bc=R

Original file line number	Diff line number	Diff line change
`@@ -238,14 +238,14 @@ Property: Bidi_Class`
`238`	`238`	`#`
`239`	`239`	`# The unassigned code points that default to AL are in the ranges:`
`240`	`240`	`# [\u0600-\u07BF \u0860-\u08FF \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF`
`241`		`-# \U00010D00-\U00010D3F \U00010F30-\U00010F6F`
	`241`	`+# \U00010D00-\U00010D3F \U00010EC0-\U00010EFF \U00010F30-\U00010F6F`
`242`	`242`	`# \U0001EC70-\U0001ECBF \U0001ED00-\U0001ED4F \U0001EE00-\U0001EEFF]`
`243`	`243`	`#`
`244`	`244`	`# This includes code points in the Arabic, Syriac, and Thaana blocks, among others.`
`245`	`245`	`#`
`246`	`246`	`# The unassigned code points that default to R are in the ranges:`
`247`	`247`	`# [\u0590-\u05FF \u07C0-\u085F \uFB1D-\uFB4F`
`248`		`-# \U00010800-\U00010CFF \U00010D40-\U00010F2F \U00010F70-\U00010FFF`
	`248`	`+# \U00010800-\U00010CFF \U00010D40-\U00010EBF \U00010F00-\U00010F2F \U00010F70-\U00010FFF`
`249`	`249`	`# \U0001E800-\U0001EC6F \U0001ECC0-\U0001ECFF \U0001ED50-\U0001EDFF \U0001EF00-\U0001EFFF]`
`250`	`250`	`#`
`251`	`251`	`# This includes code points in the Hebrew, NKo, and Phoenician blocks, among others.`