erlang · eksperimental · Sep 10, 2025
diff --git a/lib/stdlib/test/unicode_util_SUITE_data/GraphemeBreakTest.txt b/lib/stdlib/test/unicode_util_SUITE_data/GraphemeBreakTest.txt
diff --git a/lib/stdlib/test/unicode_util_SUITE_data/LineBreakTest.txt b/lib/stdlib/test/unicode_util_SUITE_data/LineBreakTest.txt
diff --git a/lib/stdlib/test/unicode_util_SUITE_data/NormalizationTest.txt b/lib/stdlib/test/unicode_util_SUITE_data/NormalizationTest.txt
diff --git a/lib/stdlib/test/unicode_util_SUITE_data/unicode_table.bin b/lib/stdlib/test/unicode_util_SUITE_data/unicode_table.bin
diff --git a/lib/stdlib/uc_spec/CaseFolding.txt b/lib/stdlib/uc_spec/CaseFolding.txt
@@ -1,6 +1,6 @@
-# CaseFolding-16.0.0.txt
-# Date: 2024-04-30, 21:48:11 GMT
-# © 2024 Unicode®, Inc.
+# CaseFolding-17.0.0.txt
+# Date: 2025-07-30, 23:54:36 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
 #
@@ -18,15 +18,15 @@
 # The data supports both implementations that require simple case foldings
 # (where string lengths don't change), and implementations that allow full case folding
 # (where string lengths may grow). Note that where they can be supported, the
-# full case foldings are superior: for example, they allow "MASSE" and "Maße" to match.
+# full case foldings are superior: for example, they allow "FUSS" and "Fuß" to match.
 #
 # All code points not listed in this file map to themselves.
 #
 # NOTE: case folding does not preserve normalization formats!
 #
 # For information on case folding, including how to have case folding
-# preserve normalization formats, see Section 3.13 Default Case Algorithms in
-# The Unicode Standard.
+# preserve normalization formats, see the
+# "Conformance" / "Default Case Algorithms" section of the core specification.
 #
 # ================================================================================
 # Format
@@ -1243,7 +1243,10 @@ A7C7; C; A7C8; # LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY
 A7C9; C; A7CA; # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY
 A7CB; C; 0264; # LATIN CAPITAL LETTER RAMS HORN
 A7CC; C; A7CD; # LATIN CAPITAL LETTER S WITH DIAGONAL STROKE
+A7CE; C; A7CF; # LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE
 A7D0; C; A7D1; # LATIN CAPITAL LETTER CLOSED INSULAR G
+A7D2; C; A7D3; # LATIN CAPITAL LETTER DOUBLE THORN
+A7D4; C; A7D5; # LATIN CAPITAL LETTER DOUBLE WYNN
 A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S
 A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S
 A7DA; C; A7DB; # LATIN CAPITAL LETTER LAMBDA
@@ -1616,6 +1619,31 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
 16E5D; C; 16E7D; # MEDEFAIDRIN CAPITAL LETTER O
 16E5E; C; 16E7E; # MEDEFAIDRIN CAPITAL LETTER AI
 16E5F; C; 16E7F; # MEDEFAIDRIN CAPITAL LETTER Y
+16EA0; C; 16EBB; # BERIA ERFE CAPITAL LETTER ARKAB
+16EA1; C; 16EBC; # BERIA ERFE CAPITAL LETTER BASIGNA
+16EA2; C; 16EBD; # BERIA ERFE CAPITAL LETTER DARBAI
+16EA3; C; 16EBE; # BERIA ERFE CAPITAL LETTER EH
+16EA4; C; 16EBF; # BERIA ERFE CAPITAL LETTER FITKO
+16EA5; C; 16EC0; # BERIA ERFE CAPITAL LETTER GOWAY
+16EA6; C; 16EC1; # BERIA ERFE CAPITAL LETTER HIRDEABO
+16EA7; C; 16EC2; # BERIA ERFE CAPITAL LETTER I
+16EA8; C; 16EC3; # BERIA ERFE CAPITAL LETTER DJAI
+16EA9; C; 16EC4; # BERIA ERFE CAPITAL LETTER KOBO
+16EAA; C; 16EC5; # BERIA ERFE CAPITAL LETTER LAKKO
+16EAB; C; 16EC6; # BERIA ERFE CAPITAL LETTER MERI
+16EAC; C; 16EC7; # BERIA ERFE CAPITAL LETTER NINI
+16EAD; C; 16EC8; # BERIA ERFE CAPITAL LETTER GNA
+16EAE; C; 16EC9; # BERIA ERFE CAPITAL LETTER NGAY
+16EAF; C; 16ECA; # BERIA ERFE CAPITAL LETTER OI
+16EB0; C; 16ECB; # BERIA ERFE CAPITAL LETTER PI
+16EB1; C; 16ECC; # BERIA ERFE CAPITAL LETTER ERIGO
+16EB2; C; 16ECD; # BERIA ERFE CAPITAL LETTER ERIGO TAMURA
+16EB3; C; 16ECE; # BERIA ERFE CAPITAL LETTER SERI
+16EB4; C; 16ECF; # BERIA ERFE CAPITAL LETTER SHEP
+16EB5; C; 16ED0; # BERIA ERFE CAPITAL LETTER TATASOUE
+16EB6; C; 16ED1; # BERIA ERFE CAPITAL LETTER UI
+16EB7; C; 16ED2; # BERIA ERFE CAPITAL LETTER WASSE
+16EB8; C; 16ED3; # BERIA ERFE CAPITAL LETTER AY
 1E900; C; 1E922; # ADLAM CAPITAL LETTER ALIF
 1E901; C; 1E923; # ADLAM CAPITAL LETTER DAALI
 1E902; C; 1E924; # ADLAM CAPITAL LETTER LAAM

diff --git a/lib/stdlib/uc_spec/CompositionExclusions.txt b/lib/stdlib/uc_spec/CompositionExclusions.txt
@@ -1,6 +1,6 @@
-# CompositionExclusions-16.0.0.txt
-# Date: 2024-02-02
-# © 2024 Unicode®, Inc.
+# CompositionExclusions-17.0.0.txt
+# Date: 2025-08-01
+# © 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
 #

diff --git a/lib/stdlib/uc_spec/EastAsianWidth.txt b/lib/stdlib/uc_spec/EastAsianWidth.txt
diff --git a/lib/stdlib/uc_spec/GraphemeBreakProperty.txt b/lib/stdlib/uc_spec/GraphemeBreakProperty.txt
@@ -1,6 +1,6 @@
-# GraphemeBreakProperty-16.0.0.txt
-# Date: 2024-05-31, 18:09:38 GMT
-# © 2024 Unicode®, Inc.
+# GraphemeBreakProperty-17.0.0.txt
+# Date: 2025-06-30, 06:20:23 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
 #
@@ -30,12 +30,11 @@
 113D1         ; Prepend # Lo       TULU-TIGALARI REPHA
 1193F         ; Prepend # Lo       DIVES AKURU PREFIXED NASAL SIGN
 11941         ; Prepend # Lo       DIVES AKURU INITIAL RA
-11A3A         ; Prepend # Lo       ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
 11A84..11A89  ; Prepend # Lo   [6] SOYOMBO SIGN JIHVAMULIYA..SOYOMBO CLUSTER-INITIAL LETTER SA
 11D46         ; Prepend # Lo       MASARAM GONDI REPHA
 11F02         ; Prepend # Lo       KAWI SIGN REPHA
 
-# Total code points: 28
+# Total code points: 27
 
 # ================================================
 
@@ -243,7 +242,8 @@ E01F0..E0FFF  ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
 1A7F          ; Extend # Mn       TAI THAM COMBINING CRYPTOGRAMMIC DOT
 1AB0..1ABD    ; Extend # Mn  [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW
 1ABE          ; Extend # Me       COMBINING PARENTHESES OVERLAY
-1ABF..1ACE    ; Extend # Mn  [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T
+1ABF..1ADD    ; Extend # Mn  [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW
+1AE0..1AEB    ; Extend # Mn  [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE
 1B00..1B03    ; Extend # Mn   [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG
 1B34          ; Extend # Mn       BALINESE SIGN REREKAN
 1B35          ; Extend # Mc       BALINESE VOWEL SIGN TEDUNG
@@ -339,7 +339,7 @@ FF9E..FF9F    ; Extend # Lm   [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
 10D24..10D27  ; Extend # Mn   [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
 10D69..10D6D  ; Extend # Mn   [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK
 10EAB..10EAC  ; Extend # Mn   [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
-10EFC..10EFF  ; Extend # Mn   [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA
+10EFA..10EFF  ; Extend # Mn   [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA
 10F46..10F50  ; Extend # Mn  [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
 10F82..10F85  ; Extend # Mn   [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
 11001         ; Extend # Mn       BRAHMI SIGN ANUSVARA
@@ -430,6 +430,9 @@ FF9E..FF9F    ; Extend # Lm   [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
 11A59..11A5B  ; Extend # Mn   [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
 11A8A..11A96  ; Extend # Mn  [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
 11A98..11A99  ; Extend # Mn   [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
+11B60         ; Extend # Mn       SHARADA VOWEL SIGN OE
+11B62..11B64  ; Extend # Mn   [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E
+11B66         ; Extend # Mn       SHARADA VOWEL SIGN CANDRA E
 11C30..11C36  ; Extend # Mn   [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
 11C38..11C3D  ; Extend # Mn   [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
 11C3F         ; Extend # Mn       BHAIKSUKI SIGN VIRAMA
@@ -489,13 +492,17 @@ FF9E..FF9F    ; Extend # Lm   [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
 1E2EC..1E2EF  ; Extend # Mn   [4] WANCHO TONE TUP..WANCHO TONE KOINI
 1E4EC..1E4EF  ; Extend # Mn   [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
 1E5EE..1E5EF  ; Extend # Mn   [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR
+1E6E3         ; Extend # Mn       TAI YO SIGN UE
+1E6E6         ; Extend # Mn       TAI YO SIGN AU
+1E6EE..1E6EF  ; Extend # Mn   [2] TAI YO SIGN AY..TAI YO SIGN ANG
+1E6F5         ; Extend # Mn       TAI YO SIGN OM
 1E8D0..1E8D6  ; Extend # Mn   [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
 1E944..1E94A  ; Extend # Mn   [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
 1F3FB..1F3FF  ; Extend # Sk   [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
 E0020..E007F  ; Extend # Cf  [96] TAG SPACE..CANCEL TAG
 E0100..E01EF  ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 2198
+# Total code points: 2237
 
 # ================================================
 
@@ -646,6 +653,9 @@ ABEC          ; SpacingMark # Mc       MEETEI MAYEK LUM IYEK
 11A39         ; SpacingMark # Mc       ZANABAZAR SQUARE SIGN VISARGA
 11A57..11A58  ; SpacingMark # Mc   [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
 11A97         ; SpacingMark # Mc       SOYOMBO SIGN VISARGA
+11B61         ; SpacingMark # Mc       SHARADA VOWEL SIGN OOE
+11B65         ; SpacingMark # Mc       SHARADA VOWEL SIGN SHORT O
+11B67         ; SpacingMark # Mc       SHARADA VOWEL SIGN CANDRA O
 11C2F         ; SpacingMark # Mc       BHAIKSUKI VOWEL SIGN AA
 11C3E         ; SpacingMark # Mc       BHAIKSUKI SIGN VISARGA
 11CA9         ; SpacingMark # Mc       MARCHEN SUBJOINED LETTER YA
@@ -661,7 +671,7 @@ ABEC          ; SpacingMark # Mc       MEETEI MAYEK LUM IYEK
 1612A..1612C  ; SpacingMark # Mc   [3] GURUNG KHEMA CONSONANT SIGN MEDIAL YA..GURUNG KHEMA CONSONANT SIGN MEDIAL HA
 16F51..16F87  ; SpacingMark # Mc  [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
 
-# Total code points: 378
+# Total code points: 381
 
 # ================================================
 

diff --git a/lib/stdlib/uc_spec/IndicSyllabicCategory.txt b/lib/stdlib/uc_spec/IndicSyllabicCategory.txt
@@ -1,6 +1,6 @@
-# IndicSyllabicCategory-16.0.0.txt
-# Date: 2024-04-30, 21:48:21 GMT
-# © 2024 Unicode®, Inc.
+# IndicSyllabicCategory-17.0.0.txt
+# Date: 2025-08-01, 04:02:23 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
 #
@@ -471,8 +471,6 @@ ABD1          ; Vowel_Independent # Lo       MEETEI MAYEK LETTER ATIYA
 11909         ; Vowel_Independent # Lo       DIVES AKURU LETTER O
 119A0..119A7  ; Vowel_Independent # Lo   [8] NANDINAGARI LETTER A..NANDINAGARI LETTER VOCALIC RR
 119AA..119AD  ; Vowel_Independent # Lo   [4] NANDINAGARI LETTER E..NANDINAGARI LETTER AU
-11A00         ; Vowel_Independent # Lo       ZANABAZAR SQUARE LETTER A
-11A50         ; Vowel_Independent # Lo       SOYOMBO LETTER A
 11C00..11C08  ; Vowel_Independent # Lo   [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
 11C0A..11C0D  ; Vowel_Independent # Lo   [4] BHAIKSUKI LETTER E..BHAIKSUKI LETTER AU
 11D00..11D06  ; Vowel_Independent # Lo   [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
@@ -729,6 +727,12 @@ ABE9..ABEA    ; Vowel_Dependent # Mc   [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEET
 11A51..11A56  ; Vowel_Dependent # Mn   [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
 11A57..11A58  ; Vowel_Dependent # Mc   [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
 11A59..11A5B  ; Vowel_Dependent # Mn   [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
+11B60         ; Vowel_Dependent # Mn       SHARADA VOWEL SIGN OE
+11B61         ; Vowel_Dependent # Mc       SHARADA VOWEL SIGN OOE
+11B62..11B64  ; Vowel_Dependent # Mn   [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E
+11B65         ; Vowel_Dependent # Mc       SHARADA VOWEL SIGN SHORT O
+11B66         ; Vowel_Dependent # Mn       SHARADA VOWEL SIGN CANDRA E
+11B67         ; Vowel_Dependent # Mc       SHARADA VOWEL SIGN CANDRA O
 11C2F         ; Vowel_Dependent # Mc       BHAIKSUKI VOWEL SIGN AA
 11C30..11C36  ; Vowel_Dependent # Mn   [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
 11C38..11C3B  ; Vowel_Dependent # Mn   [4] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI VOWEL SIGN AU
@@ -777,6 +781,8 @@ A926..A92A    ; Vowel # Mn   [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O
 # Indic script layout (NBSP and dotted circle), as well as a few script-
 # specific vowel-holder characters which are not technically
 # consonants, but serve instead as bases for placement of vowel marks.
+# Vowel carriers that are null consonants instead have the
+# Indic_Syllabic_Category Consonant.
 
 # [Not derivable]
 
@@ -787,7 +793,6 @@ A926..A92A    ; Vowel # Mn   [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O
 0A72..0A73    ; Consonant_Placeholder # Lo   [2] GURMUKHI IRI..GURMUKHI URA
 104B          ; Consonant_Placeholder # Po       MYANMAR SIGN SECTION
 104E          ; Consonant_Placeholder # Po       MYANMAR SYMBOL AFOREMENTIONED
-1900          ; Consonant_Placeholder # Lo       LIMBU VOWEL-CARRIER LETTER
 1CFA          ; Consonant_Placeholder # Lo       VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA
 2010..2014    ; Consonant_Placeholder # Pd   [5] HYPHEN..EM DASH
 25CC          ; Consonant_Placeholder # So       DOTTED CIRCLE
@@ -800,7 +805,14 @@ AA74..AA76    ; Consonant_Placeholder # Lo   [3] MYANMAR LOGOGRAM KHAMTI OAY..MY
 
 # Indic_Syllabic_Category=Consonant
 
-# Consonant (ordinary abugida consonants, with inherent vowels)
+# Consonant
+# This includes ordinary abugida consonants with inherent vowels.
+# In scripts that do not have distinct independent vowel characters, but instead
+# form independent vowels by adding dependent vowels to a vowel carrier which
+# otherwise represents the inherent vowel, that vowel carrier has the
+# Indic_Syllabic_Category Consonant, as a null consonant. Such vowel carriers
+# can often also be analyzed as glottal stops with inherent vowels.
+# An example is U+0F68 TIBETAN LETTER A.
 
 # [Not derivable]
 
@@ -878,7 +890,7 @@ AA74..AA76    ; Consonant_Placeholder # Lo   [3] MYANMAR LOGOGRAM KHAMTI OAY..MY
 1763..176C    ; Consonant # Lo  [10] TAGBANWA LETTER KA..TAGBANWA LETTER YA
 176E..1770    ; Consonant # Lo   [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA
 1780..17A2    ; Consonant # Lo  [35] KHMER LETTER KA..KHMER LETTER QA
-1901..191E    ; Consonant # Lo  [30] LIMBU LETTER KA..LIMBU LETTER TRA
+1900..191E    ; Consonant # Lo  [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA
 1950..1962    ; Consonant # Lo  [19] TAI LE LETTER KA..TAI LE LETTER NA
 1980..19AB    ; Consonant # Lo  [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
 1A00..1A16    ; Consonant # Lo  [23] BUGINESE LETTER KA..BUGINESE LETTER HA
@@ -955,7 +967,9 @@ ABD2..ABDA    ; Consonant # Lo   [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE
 11915..11916  ; Consonant # Lo   [2] DIVES AKURU LETTER NYA..DIVES AKURU LETTER TTA
 11918..1192F  ; Consonant # Lo  [24] DIVES AKURU LETTER DDA..DIVES AKURU LETTER ZA
 119AE..119D0  ; Consonant # Lo  [35] NANDINAGARI LETTER KA..NANDINAGARI LETTER RRA
+11A00         ; Consonant # Lo       ZANABAZAR SQUARE LETTER A
 11A0B..11A32  ; Consonant # Lo  [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
+11A50         ; Consonant # Lo       SOYOMBO LETTER A
 11A5C..11A83  ; Consonant # Lo  [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
 11C0E..11C2E  ; Consonant # Lo  [33] BHAIKSUKI LETTER KA..BHAIKSUKI LETTER HA
 11C72..11C8F  ; Consonant # Lo  [30] MARCHEN LETTER KA..MARCHEN LETTER A
@@ -985,50 +999,53 @@ ABD2..ABDA    ; Consonant # Lo   [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE
 
 # Indic_Syllabic_Category=Consonant_With_Stacker
 
-# Consonants that may make stacked ligatures with the next consonant
-# without the use of a virama
+# Consonants that may cause conjunct formation or consonant stacking with the
+# next consonant, without the use of a stacker
 
 # [Not derivable]
 
 0CF1..0CF2    ; Consonant_With_Stacker # Lo   [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
 1CF5..1CF6    ; Consonant_With_Stacker # Lo   [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
 11003..11004  ; Consonant_With_Stacker # Lo   [2] BRAHMI SIGN JIHVAMULIYA..BRAHMI SIGN UPADHMANIYA
 11460..11461  ; Consonant_With_Stacker # Lo   [2] NEWA SIGN JIHVAMULIYA..NEWA SIGN UPADHMANIYA
+11A3A         ; Consonant_With_Stacker # Lo       ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
 
 # ================================================
 
 # Indic_Syllabic_Category=Consonant_Prefixed
 
-# Cluster-initial consonants
+# Other consonants that behave like a Consonant_Preceding_Repha
 
 # [Not derivable]
 
 111C2..111C3  ; Consonant_Prefixed # Lo   [2] SHARADA SIGN JIHVAMULIYA..SHARADA SIGN UPADHMANIYA
 1193F         ; Consonant_Prefixed # Lo       DIVES AKURU PREFIXED NASAL SIGN
-11A3A         ; Consonant_Prefixed # Lo       ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
-11A84..11A89  ; Consonant_Prefixed # Lo   [6] SOYOMBO SIGN JIHVAMULIYA..SOYOMBO CLUSTER-INITIAL LETTER SA
+11A84..11A85  ; Consonant_Prefixed # Lo   [2] SOYOMBO SIGN JIHVAMULIYA..SOYOMBO SIGN UPADHMANIYA
+11A87..11A89  ; Consonant_Prefixed # Lo   [3] SOYOMBO CLUSTER-INITIAL LETTER LA..SOYOMBO CLUSTER-INITIAL LETTER SA
 
 # ================================================
 
 # Indic_Syllabic_Category=Consonant_Preceding_Repha
 
-# Repha Form of RA (reanalyzed in some scripts), when preceding the main
-# consonant.
+# Cluster-initial "r" consonants in the form of a dependent sign (also known as
+# "repha") that precede the base character in the encoding order, but are
+# reordered in text rendering to be somewhere after the base. Reanalyzed in
+# some orthographies to be a final consonant.
 
 # [Not derivable]
 
 0D4E          ; Consonant_Preceding_Repha # Lo       MALAYALAM LETTER DOT REPH
 113D1         ; Consonant_Preceding_Repha # Lo       TULU-TIGALARI REPHA
 11941         ; Consonant_Preceding_Repha # Lo       DIVES AKURU INITIAL RA
+11A86         ; Consonant_Preceding_Repha # Lo       SOYOMBO CLUSTER-INITIAL LETTER RA
 11D46         ; Consonant_Preceding_Repha # Lo       MASARAM GONDI REPHA
 11F02         ; Consonant_Preceding_Repha # Lo       KAWI SIGN REPHA
 
 # ================================================
 
 # Indic_Syllabic_Category=Consonant_Initial_Postfixed
 
-# Consonants that succeed the main consonant in character sequences, but are
-# pronounced before it.
+# Other consonants that behave like a Consonant_Succeeding_Repha
 
 # [Not derivable]
 
@@ -1038,7 +1055,9 @@ ABD2..ABDA    ; Consonant # Lo   [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE
 
 # Indic_Syllabic_Category=Consonant_Succeeding_Repha
 
-# Repha Form of RA (reanalyzed in some scripts), when succeeding the main
+# Cluster-initial "r" consonants that behave like a Consonant_Preceding_Repha
+# but succeed the base character in the encoding order, and are thus not
+# reordered in text rendering. Reanalyzed in some orthographies to be a final
 # consonant.
 
 # [Not derivable]