[UTC-184-A72] Change the Identifier_Type of 3 characters (#1174)

josh-hadley · web-flow · commit 212ce9a37570 · 2025-07-29T14:25:50.000-07:00
* [UTC-184-A72] Change Identifier_Types of 3 characters - removals.txt * [UTC-184-A72] Change Identifier_Types of 3 characters - generated * Address test failure
diff --git a/unicodetools/data/security/dev/IdentifierStatus.txt b/unicodetools/data/security/dev/IdentifierStatus.txt
@@ -1,5 +1,5 @@
 # IdentifierStatus.txt
-# Date: 2025-05-07, 21:39:39 GMT
+# Date: 2025-07-29, 02:36:52 GMT
 # © 2025 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
@@ -149,7 +149,6 @@
 08BB..08BD    ; Allowed    # 9.0    [3] ARABIC LETTER AFRICAN FEH..ARABIC LETTER AFRICAN NOON
 08BE..08C2    ; Allowed    # 13.0   [5] ARABIC LETTER PEH WITH SMALL V..ARABIC LETTER KEHEH WITH SMALL V
 08C7          ; Allowed    # 13.0       ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
-08C9          ; Allowed    # 14.0       ARABIC SMALL FARSI YEH
 0901..0903    ; Allowed    # 1.1    [3] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN VISARGA
 0905..090B    ; Allowed    # 1.1    [7] DEVANAGARI LETTER A..DEVANAGARI LETTER VOCALIC R
 090D..0928    ; Allowed    # 1.1   [28] DEVANAGARI LETTER CANDRA E..DEVANAGARI LETTER NA
@@ -1617,7 +1616,6 @@ AC00..D7A3    ; Allowed    # 2.0 [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH
 11301         ; Allowed    # 7.0        GRANTHA SIGN CANDRABINDU
 11303         ; Allowed    # 7.0        GRANTHA SIGN VISARGA
 1133C         ; Allowed    # 7.0        GRANTHA SIGN NUKTA
-16FF0..16FF1  ; Allowed    # 13.0   [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
 1E7E0..1E7E6  ; Allowed    # 14.0   [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; Allowed    # 14.0   [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; Allowed    # 14.0   [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@@ -1681,4 +1679,4 @@ AC00..D7A3    ; Allowed    # 2.0 [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH
 28CD2         ; Allowed    # 3.1        CJK UNIFIED IDEOGRAPH-28CD2
 29D98         ; Allowed    # 3.1        CJK UNIFIED IDEOGRAPH-29D98
 
-# Total code points: 33794
+# Total code points: 33791
diff --git a/unicodetools/data/security/dev/IdentifierType.txt b/unicodetools/data/security/dev/IdentifierType.txt
@@ -1,5 +1,5 @@
 # IdentifierType.txt
-# Date: 2025-07-25, 18:31:31 GMT
+# Date: 2025-07-29, 02:36:51 GMT
 # © 2025 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
@@ -145,7 +145,6 @@
 08BB..08BD    ; Recommended                    # 9.0    [3] ARABIC LETTER AFRICAN FEH..ARABIC LETTER AFRICAN NOON
 08BE..08C2    ; Recommended                    # 13.0   [5] ARABIC LETTER PEH WITH SMALL V..ARABIC LETTER KEHEH WITH SMALL V
 08C7          ; Recommended                    # 13.0       ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
-08C9          ; Recommended                    # 14.0       ARABIC SMALL FARSI YEH
 0901..0903    ; Recommended                    # 1.1    [3] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN VISARGA
 0905..090B    ; Recommended                    # 1.1    [7] DEVANAGARI LETTER A..DEVANAGARI LETTER VOCALIC R
 090D..0928    ; Recommended                    # 1.1   [28] DEVANAGARI LETTER CANDRA E..DEVANAGARI LETTER NA
@@ -1609,7 +1608,6 @@ AC00..D7A3    ; Recommended                    # 2.0 [11172] HANGUL SYLLABLE GA.
 11301         ; Recommended                    # 7.0        GRANTHA SIGN CANDRABINDU
 11303         ; Recommended                    # 7.0        GRANTHA SIGN VISARGA
 1133C         ; Recommended                    # 7.0        GRANTHA SIGN NUKTA
-16FF0..16FF1  ; Recommended                    # 13.0   [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
 1E7E0..1E7E6  ; Recommended                    # 14.0   [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; Recommended                    # 14.0   [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; Recommended                    # 14.0   [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@@ -1673,7 +1671,7 @@ AC00..D7A3    ; Recommended                    # 2.0 [11172] HANGUL SYLLABLE GA.
 28CD2         ; Recommended                    # 3.1        CJK UNIFIED IDEOGRAPH-28CD2
 29D98         ; Recommended                    # 3.1        CJK UNIFIED IDEOGRAPH-29D98
 
-# Total code points: 33776
+# Total code points: 33773
 
 #	Identifier_Type:	Inclusion
 
@@ -3550,6 +3548,7 @@ A8FC          ; Uncommon_Use Obsolete Not_XID  # 8.0        DEVANAGARI SIGN SIDD
 0671          ; Technical                      # 1.1        ARABIC LETTER ALEF WASLA
 06E5..06E6    ; Technical                      # 1.1    [2] ARABIC SMALL WAW..ARABIC SMALL YEH
 0870..0887    ; Technical                      # 14.0  [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT
+08C9          ; Technical                      # 14.0       ARABIC SMALL FARSI YEH
 0950          ; Technical                      # 1.1        DEVANAGARI OM
 0953..0954    ; Technical                      # 1.1    [2] DEVANAGARI GRAVE ACCENT..DEVANAGARI ACUTE ACCENT
 097D          ; Technical                      # 4.1        DEVANAGARI LETTER GLOTTAL STOP
@@ -3635,7 +3634,7 @@ FE73          ; Technical                      # 3.2        ARABIC TAIL FRAGMENT
 1DF00..1DF1E  ; Technical                      # 14.0  [31] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER S WITH CURL
 1DF25..1DF2A  ; Technical                      # 15.0   [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
 
-# Total code points: 681
+# Total code points: 682
 
 #	Identifier_Type:	Technical Exclusion
 
@@ -4316,6 +4315,7 @@ D7CB..D7FB    ; Obsolete                       # 5.2   [49] HANGUL JONGSEONG NIE
 101FD         ; Obsolete                       # 5.1        PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
 102E0         ; Obsolete                       # 7.0        COPTIC EPACT THOUSANDS MARK
 16FE3         ; Obsolete                       # 12.0       OLD CHINESE ITERATION MARK
+16FF0..16FF1  ; Obsolete                       # 13.0   [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
 1B000..1B001  ; Obsolete                       # 6.0    [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
 1B002..1B11E  ; Obsolete                       # 10.0 [285] HENTAIGANA LETTER A-1..HENTAIGANA LETTER N-MU-MO-2
 1B11F..1B122  ; Obsolete                       # 14.0   [4] HIRAGANA LETTER ARCHAIC WU..KATAKANA LETTER ARCHAIC WU
@@ -4325,7 +4325,7 @@ D7CB..D7FB    ; Obsolete                       # 5.2   [49] HANGUL JONGSEONG NIE
 1B164..1B167  ; Obsolete                       # 12.0   [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
 1E08F         ; Obsolete                       # 15.0       COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 
-# Total code points: 1637
+# Total code points: 1639
 
 #	Identifier_Type:	Obsolete Not_XID
 
diff --git a/unicodetools/data/security/dev/data/draft-restrictions.txt b/unicodetools/data/security/dev/data/draft-restrictions.txt
@@ -23663,6 +23663,8 @@ D7FB          ;  ; Obsolete #      (ퟻ)  HANGUL JONGSEONG PHIEUPH-THIEUTH
 10400..10425  ;  ; Obsolete # [38] (𐐀..𐐥)  DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER ENG
 10428..1044D  ;  ; Obsolete # [38] (𐐨..𐑍)  DESERET SMALL LETTER LONG I..DESERET SMALL LETTER ENG
 16FE3         ;  ; Obsolete #      (𖿣)  OLD CHINESE ITERATION MARK
+16FF0         ;  ; Obsolete #      (𖿰)  VIETNAMESE ALTERNATE READING MARK CA
+16FF1         ;  ; Obsolete #      (𖿱)  VIETNAMESE ALTERNATE READING MARK NHAY
 1B000         ;  ; Obsolete #      (𛀀)  KATAKANA LETTER ARCHAIC E
 1B001         ;  ; Obsolete #      (𛀁)  HIRAGANA LETTER ARCHAIC YE
 1B002         ;  ; Obsolete #      (𛀂)  HENTAIGANA LETTER A-1
@@ -23968,7 +23970,7 @@ D7FB          ;  ; Obsolete #      (ퟻ)  HANGUL JONGSEONG PHIEUPH-THIEUTH
 1D244         ;  ; Obsolete #      (𝉄)  COMBINING GREEK MUSICAL PENTASEME
 1E08F         ;  ; Obsolete #      (𞂏)  COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 
-# Total code points: 2023
+# Total code points: 2025
 
 0180          ;  ; Technical #      (ƀ)  LATIN SMALL LETTER B WITH STROKE
 01C0          ;  ; Technical #      (ǀ)  LATIN LETTER DENTAL CLICK
@@ -24216,6 +24218,7 @@ D7FB          ;  ; Obsolete #      (ퟻ)  HANGUL JONGSEONG PHIEUPH-THIEUTH
 0885          ;  ; Technical #      (ࢅ)  ARABIC TATWEEL WITH TWO DOTS BELOW
 0886          ;  ; Technical #      (ࢆ)  ARABIC LETTER THIN YEH
 0887          ;  ; Technical #      (ࢇ)  ARABIC BASELINE ROUND DOT
+08C9          ;  ; Technical #      (ࣉ)  ARABIC SMALL FARSI YEH
 0950          ;  ; Technical #      (ॐ)  DEVANAGARI OM
 0953          ;  ; Technical #      (॓)  DEVANAGARI GRAVE ACCENT
 0954          ;  ; Technical #      (॔)  DEVANAGARI ACUTE ACCENT
@@ -24650,7 +24653,7 @@ FE73          ;  ; Technical #      (ﹳ)  ARABIC TAIL FRAGMENT
 1DF29         ;  ; Technical #      (𝼩)  LATIN SMALL LETTER S WITH MID-HEIGHT LEFT HOOK
 1DF2A         ;  ; Technical #      (𝼪)  LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
 
-# Total code points: 747
+# Total code points: 748
 
 0114          ;  ; Uncommon_Use #      (Ĕ)  LATIN CAPITAL LETTER E WITH BREVE
 0115          ;  ; Uncommon_Use #      (ĕ)  LATIN SMALL LETTER E WITH BREVE
@@ -58020,7 +58023,6 @@ FA29          ;  ; Uncommon_Use #      (﨩)  CJK COMPATIBILITY IDEOGRAPH-FA29
 08C1          ; Allowed ; Recommended #      (ࣁ)  ARABIC LETTER TCHEH WITH SMALL V
 08C2          ; Allowed ; Recommended #      (ࣂ)  ARABIC LETTER KEHEH WITH SMALL V
 08C7          ; Allowed ; Recommended #      (ࣇ)  ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
-08C9          ; Allowed ; Recommended #      (ࣉ)  ARABIC SMALL FARSI YEH
 0901          ; Allowed ; Recommended #      (ँ)  DEVANAGARI SIGN CANDRABINDU
 0902          ; Allowed ; Recommended #      (ं)  DEVANAGARI SIGN ANUSVARA
 0903          ; Allowed ; Recommended #      (ः)  DEVANAGARI SIGN VISARGA
@@ -59507,15 +59509,13 @@ AC00..D7A3    ; Allowed ; Recommended # [11172] (가..힣)  HANGUL SYLLABLE GA..
 11301         ; Allowed ; Recommended #      (𑌁)  GRANTHA SIGN CANDRABINDU
 11303         ; Allowed ; Recommended #      (𑌃)  GRANTHA SIGN VISARGA
 1133C         ; Allowed ; Recommended #      (𑌼)  GRANTHA SIGN NUKTA
-16FF0         ; Allowed ; Recommended #      (𖿰)  VIETNAMESE ALTERNATE READING MARK CA
-16FF1         ; Allowed ; Recommended #      (𖿱)  VIETNAMESE ALTERNATE READING MARK NHAY
 1E7E0..1E7E6  ; Allowed ; Recommended #  [7] (𞟠..𞟦)  ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; Allowed ; Recommended #  [4] (𞟨..𞟫)  ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; Allowed ; Recommended #  [2] (𞟭..𞟮)  ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
 1E7F0..1E7FE  ; Allowed ; Recommended # [15] (𞟰..𞟾)  ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE
 E0100..E01EF  ; Allowed ; Recommended # [240] (U+E0100..U+E01EF)  VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 14139
+# Total code points: 14136
 
 0000..002F    ; ~Unicode Identifier # [48] (U+0000../)  <control-0000>..SOLIDUS
 003A..0040    ; ~Unicode Identifier #  [7] (:..@)  COLON..COMMERCIAL AT
diff --git a/unicodetools/data/security/dev/data/idnchars.txt b/unicodetools/data/security/dev/data/idnchars.txt
@@ -1,5 +1,5 @@
 # idnchars.txt
-# Date: 2025-05-07, 21:39:41 GMT
+# Date: 2025-07-29, 02:36:52 GMT
 # © 2025 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
@@ -178,7 +178,6 @@
 08A2..08A9    ; output #  [8] (ࢢ..ࢩ)  ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE
 08BB..08C2    ; output #  [8] (ࢻ..ࣂ)  ARABIC LETTER AFRICAN FEH..ARABIC LETTER KEHEH WITH SMALL V
 08C7          ; output #      (ࣇ)  ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
-08C9          ; output #      (ࣉ)  ARABIC SMALL FARSI YEH
 0901..0903    ; output #  [3] (ँ..ः)  DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN VISARGA
 0905..090B    ; output #  [7] (अ..ऋ)  DEVANAGARI LETTER A..DEVANAGARI LETTER VOCALIC R
 090D..0928    ; output # [28] (ऍ..न)  DEVANAGARI LETTER CANDRA E..DEVANAGARI LETTER NA
@@ -459,13 +458,12 @@ AC00..D7A3    ; output # [11172] (가..힣)  HANGUL SYLLABLE GA..HANGUL SYLLABLE
 11301         ; output #      (𑌁)  GRANTHA SIGN CANDRABINDU
 11303         ; output #      (𑌃)  GRANTHA SIGN VISARGA
 1133C         ; output #      (𑌼)  GRANTHA SIGN NUKTA
-16FF0..16FF1  ; output #  [2] (𖿰..𖿱)  VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
 1E7E0..1E7E6  ; output #  [7] (𞟠..𞟦)  ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; output #  [4] (𞟨..𞟫)  ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; output #  [2] (𞟭..𞟮)  ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
 1E7F0..1E7FE  ; output # [15] (𞟰..𞟾)  ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE
 
-# Total code points: 13498
+# Total code points: 13495
 
 # Not allowed at start of identifier
 
@@ -557,6 +555,5 @@ AA7B          ; nonstarting #      (ꩻ)  MYANMAR SIGN PAO KAREN TONE
 11301         ; nonstarting #      (𑌁)  GRANTHA SIGN CANDRABINDU
 11303         ; nonstarting #      (𑌃)  GRANTHA SIGN VISARGA
 1133C         ; nonstarting #      (𑌼)  GRANTHA SIGN NUKTA
-16FF0..16FF1  ; nonstarting #  [2] (𖿰..𖿱)  VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
 
-# Total code points: 351
+# Total code points: 349
diff --git a/unicodetools/data/security/dev/data/review.txt b/unicodetools/data/security/dev/data/review.txt
@@ -1,5 +1,5 @@
 # review.txt
-# Date: 2025-07-25, 18:31:36 GMT
+# Date: 2025-07-29, 02:36:52 GMT
 # © 2025 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
@@ -2050,7 +2050,7 @@
 08C6          ; Restricted ; Uncommon_Use      #      (ࣆ)  ARABIC LETTER JEEM WITH THREE DOTS BELOW
 08C7          ; output                         #      (ࣇ)  ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
 08C8          ; Restricted ; Uncommon_Use      #      (ࣈ)  ARABIC LETTER GRAF
-08C9          ; output                         #      (ࣉ)  ARABIC SMALL FARSI YEH
+08C9          ; Restricted ; Technical         #      (ࣉ)  ARABIC SMALL FARSI YEH
 08CA          ; Restricted ; Uncommon_Use      #      (࣊)  ARABIC SMALL HIGH FARSI YEH
 08CB          ; Restricted ; Uncommon_Use      #      (࣋)  ARABIC SMALL HIGH YEH BARREE WITH TWO DOTS BELOW
 08CC          ; Restricted ; Uncommon_Use      #      (࣌)  ARABIC SMALL HIGH WORD SAH
@@ -25091,8 +25091,8 @@ FFEE          ; Restricted ; Not_XID           #      (￮)  HALFWIDTH WHITE CIR
 16FE2         ; Restricted ; Not_XID           #      (𖿢)  OLD CHINESE HOOK MARK
 16FE3         ; Restricted ; Obsolete          #      (𖿣)  OLD CHINESE ITERATION MARK
 16FE4         ; Restricted ; Exclusion         #      (𖿤)  KHITAN SMALL SCRIPT FILLER
-16FF0         ; output-nonstarting             #      (𖿰)  VIETNAMESE ALTERNATE READING MARK CA
-16FF1         ; output-nonstarting             #      (𖿱)  VIETNAMESE ALTERNATE READING MARK NHAY
+16FF0         ; Restricted ; Obsolete          #      (𖿰)  VIETNAMESE ALTERNATE READING MARK CA
+16FF1         ; Restricted ; Obsolete          #      (𖿱)  VIETNAMESE ALTERNATE READING MARK NHAY
 16FF2         ; Restricted ; Technical         #      (𖿲)  CHINESE SMALL SIMPLIFIED ER
 16FF3         ; Restricted ; Technical         #      (𖿳)  CHINESE SMALL TRADITIONAL ER
 16FF4         ; Restricted ; Technical         #      (𖿴)  YANGQIN SIGN SLOW ONE BEAT
diff --git a/unicodetools/data/security/dev/data/source/removals.txt b/unicodetools/data/security/dev/data/source/removals.txt
@@ -1210,3 +1210,8 @@ AB66..AB67; Uncommon_Use
 [麭-麰麲-黫黭-黰黲-鼂鼄-鼐鼒鼓鼕-鼥鼧-齄齆-齒齔-齬齮-龠龢龤龥𠜎𠜱𠝹𠱓𠱸𠲖𠳏𠳕𠴕𠵼𠵿𠸎𠸏𠹷𠺝𠺢𠻗𠻹𠻺𠼭𠼮𠽌𠾴𠾼𠿪]; Recommended
 [𡁜𡁯𡁵𡁶𡁻𡃁𡃉𡇙𢃇𢞵𢫕𢭃𢯊𢱑𢱕𢳂𢴈𢵌𢵧𢺳𣲷𤓓𤶸𤷪𥄫𦉘𦟌𦧲𦧺𧨾𨅝𨈇𨋢𨳊𨳍𨳒𩶘]; Recommended
 
+# Unicode 17.0
+# UTC-184-A72 ... Change the Identifier_Type of U+08C9 ARABIC SMALL FARSI YEH from Recommended to Technical, and of 
+# U+16FF0 and U+16FF1 VIETNAMESE ALTERNATE READING MARK CA and NHAY from Recommended to Obsolete.
+08C9; Technical
+16FF0..16FF1; Obsolete
diff --git a/unicodetools/src/test/java/org/unicode/propstest/TestInvariants.java b/unicodetools/src/test/java/org/unicode/propstest/TestInvariants.java
