Merged main

Author: jowilco

docs/pipeline.md

@@ -155,7 +155,7 @@ git checkout la-vache/main unicodetools/data/ucd/dev/extracted/*;
 git checkout la-vache/main unicodetools/data/ucd/dev/auxiliary/*;
 rm .\Generated\* -recurse -force;
 mvn compile exec:java '-Dexec.mainClass="org.unicode.text.UCD.Main"'  '-Dexec.args="build MakeUnicodeFiles"' -am -pl unicodetools  "-DCLDR_DIR=..\cldr\"  "-DUNICODETOOLS_GEN_DIR=Generated"  "-DUNICODETOOLS_REPO_DIR=.";
-cp .\Generated\UCD\17.0.0\* .\unicodetools\data\ucd\dev -recurse -force;
+cp .\Generated\UCD\18.0.0\* .\unicodetools\data\ucd\dev -recurse -force;
 rm unicodetools\data\ucd\dev\zzz-unchanged-*;
 rm unicodetools\data\ucd\dev\*\zzz-unchanged-*;
 rm .\unicodetools\data\ucd\dev\extra\*;
@@ -247,4 +247,4 @@ eggrobin (Windows, in-source).
 ```powershell
 mvn test -am -pl unicodetools "-DCLDR_DIR=$(gl|split-path -parent)\cldr\"  "-DUNICODETOOLS_GEN_DIR=$(gl|split-path -parent)\unicodetools\Generated\"  "-DUNICODETOOLS_REPO_DIR=$(gl|split-path -parent)\unicodetools\" "-DUVERSION=18.0.0" "-Dtest=TestTestUnicodeInvariants#testAdditionComparisons" -DfailIfNoTests=false -DtrimStackTrace=false
 ```
-Results are in Generated\UnicodeTestResults-addition-comparisons-[RMG issue number].html.
+Results are in Generated\UnicodeTestResults-addition-comparisons-[RMG issue number].html.

unicodetools/data/security/dev/confusables.txt

@@ -1,5 +1,5 @@
 # confusablesSummaryIdentifier.txt
-# Date: 2025-10-11, 02:30:37 GMT
+# Date: 2025-10-25, 07:52:31 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
@@ -459,9 +459,17 @@
 	(‎ φ ‎)	03C6	 GREEK SMALL LETTER PHI
 ←	(‎ ф ‎)	0444	 CYRILLIC SMALL LETTER EF	# →ɸ→
 
-#	́	َ
+#	́	َ	ަ
 	(‎ ́ ‎)	0301	 COMBINING ACUTE ACCENT
 ←	(‎ َ ‎)	064E	 ARABIC FATHA
+←	(‎ ަ ‎)	07A6	 THAANA ABAFILI
+
+#	́́	ަަ	̋	ً	ާ
+	(‎ ́́ ‎)	0301 0301	 COMBINING ACUTE ACCENT, COMBINING ACUTE ACCENT
+←	(‎ ަަ ‎)	07A6 07A6	 THAANA ABAFILI, THAANA ABAFILI
+←	(‎ ̋ ‎)	030B	 COMBINING DOUBLE ACUTE ACCENT
+←	(‎ ً ‎)	064B	 ARABIC FATHATAN	# →̋→
+←	(‎ ާ ‎)	07A7	 THAANA AABAAFILI	# →ަަ→
 
 #	̆	̌	ॅ
 	(‎ ̆ ‎)	0306	 COMBINING BREVE
@@ -481,29 +489,32 @@
 ←	(‎ ં ‎)	0A82	 GUJARATI SIGN ANUSVARA
 ←	(‎ ் ‎)	0BCD	 TAMIL SIGN VIRAMA
 
-#	̊	ْ	ํ	ໍ	ံ	ំ
+#	̊	ْ	ް	ํ	ໍ	ཾ	ံ	ំ
 	(‎ ̊ ‎)	030A	 COMBINING RING ABOVE
 ←	(‎ ْ ‎)	0652	 ARABIC SUKUN
+←	(‎ ް ‎)	07B0	 THAANA SUKUN
 ←	(‎ ํ ‎)	0E4D	 THAI CHARACTER NIKHAHIT
 ←	(‎ ໍ ‎)	0ECD	 LAO NIGGAHITA
+←	(‎ ཾ ‎)	0F7E	 TIBETAN SIGN RJES SU NGA RO
 ←	(‎ ံ ‎)	1036	 MYANMAR SIGN ANUSVARA
 ←	(‎ ំ ‎)	17C6	 KHMER SIGN NIKAHIT
 
-#	̋	ً
-	(‎ ̋ ‎)	030B	 COMBINING DOUBLE ACUTE ACCENT
-←	(‎ ً ‎)	064B	 ARABIC FATHATAN
+#	ِ	ި
+	(‎ ِ ‎)	0650	 ARABIC KASRA
+←	(‎ ި ‎)	07A8	 THAANA IBIFILI	# →̗→
 
 #	̦	̧
 	(‎ ̦ ‎)	0326	 COMBINING COMMA BELOW
 ←	(‎ ̧ ‎)	0327	 COMBINING CEDILLA	# →̡→
 
-#	̣	़	়	਼	઼	଼
+#	̣	़	়	਼	઼	଼	ฺ
 	(‎ ̣ ‎)	0323	 COMBINING DOT BELOW
 ←	(‎ ़ ‎)	093C	 DEVANAGARI SIGN NUKTA
 ←	(‎ ় ‎)	09BC	 BENGALI SIGN NUKTA
 ←	(‎ ਼ ‎)	0A3C	 GURMUKHI SIGN NUKTA
 ←	(‎ ઼ ‎)	0ABC	 GUJARATI SIGN NUKTA
 ←	(‎ ଼ ‎)	0B3C	 ORIYA SIGN NUKTA
+←	(‎ ฺ ‎)	0E3A	 THAI CHARACTER PHINTHU
 
 #	ॖ	ੁ
 	(‎ ॖ ‎)	0956	 DEVANAGARI VOWEL SIGN UE
@@ -513,6 +524,10 @@
 	(‎ ॗ ‎)	0957	 DEVANAGARI VOWEL SIGN UUE
 ←	(‎ ੂ ‎)	0A42	 GURMUKHI VOWEL SIGN UU
 
+#	ުު	ޫ
+	(‎ ުު ‎)	07AA 07AA	 THAANA UBUFILI, THAANA UBUFILI
+←	(‎ ޫ ‎)	07AB	 THAANA OOBOOFILI
+
 #	Γ	Г
 	(‎ Γ ‎)	0393	 GREEK CAPITAL LETTER GAMMA
 ←	(‎ Г ‎)	0413	 CYRILLIC CAPITAL LETTER GHE
@@ -684,6 +699,11 @@
 	(‎ پ̆ ‎)	067E 0306	 ARABIC LETTER PEH, COMBINING BREVE
 ←	(‎ ࢾ ‎)	08BE	 ARABIC LETTER PEH WITH SMALL V	# →‎پٚ‎→
 
+#	ِِ	ިި	ީ
+	(‎ ِِ ‎)	0650 0650	 ARABIC KASRA, ARABIC KASRA
+←	(‎ ިި ‎)	07A8 07A8	 THAANA IBIFILI, THAANA IBIFILI
+←	(‎ ީ ‎)	07A9	 THAANA EEBEEFILI	# →ިި→
+
 #	٢	۲
 	(‎ ٢ ‎)	0662	 ARABIC-INDIC DIGIT TWO
 ←	(‎ ۲ ‎)	06F2	 EXTENDED ARABIC-INDIC DIGIT TWO
@@ -725,6 +745,14 @@
 	(‎ ݧ ‎)	0767	 ARABIC LETTER NOON WITH TWO DOTS BELOW
 ←	(‎ ࢩ ‎)	08A9	 ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE	# →‎ݔ‎→
 
+#	ެު	ޮ
+	(‎ ެު ‎)	07AC 07AA	 THAANA EBEFILI, THAANA UBUFILI
+←	(‎ ޮ ‎)	07AE	 THAANA OBOFILI
+
+#	ެެ	ޭ
+	(‎ ެެ ‎)	07AC 07AC	 THAANA EBEFILI, THAANA EBEFILI
+←	(‎ ޭ ‎)	07AD	 THAANA EYBEYFILI
+
 #	अ̆	अॅ	ॲ
 	(‎ अ̆ ‎)	0905 0306	 DEVANAGARI LETTER A, COMBINING BREVE
 ←	(‎ अॅ ‎)	0905 0945	 DEVANAGARI LETTER A, DEVANAGARI VOWEL SIGN CANDRA E
@@ -888,13 +916,15 @@
 	(‎ ८ ‎)	096E	 DEVANAGARI DIGIT EIGHT
 ←	(‎ ૮ ‎)	0AEE	 GUJARATI DIGIT EIGHT
 
-#	ঃ	ః	ಃ	ഃ	ඃ	း
+#	ঃ	ః	ಃ	ഃ	ඃ	း	ះ	𑌃
 	(‎ ঃ ‎)	0983	 BENGALI SIGN VISARGA
 ←	(‎ ః ‎)	0C03	 TELUGU SIGN VISARGA	# →ਃ→
 ←	(‎ ಃ ‎)	0C83	 KANNADA SIGN VISARGA	# →ః→→ਃ→
 ←	(‎ ഃ ‎)	0D03	 MALAYALAM SIGN VISARGA	# →ಃ→→ః→→ਃ→
 ←	(‎ ඃ ‎)	0D83	 SINHALA SIGN VISARGAYA	# →ഃ→→ಃ→→ః→→ਃ→
 ←	(‎ း ‎)	1038	 MYANMAR SIGN VISARGA	# →ඃ→→ഃ→→ಃ→→ః→→ਃ→
+←	(‎ ះ ‎)	17C7	 KHMER SIGN REAHMUK
+←	(‎ 𑌃 ‎)	11303	 GRANTHA SIGN VISARGA
 
 #	অা	আ
 	(‎ অা ‎)	0985 09BE	 BENGALI LETTER A, BENGALI VOWEL SIGN AA
@@ -1255,6 +1285,14 @@
 	(‎ භ ‎)	0DB7	 SINHALA LETTER MAHAAPRAANA BAYANNA
 ←	(‎ හ ‎)	0DC4	 SINHALA LETTER HAYANNA
 
+#	ෘෘ	ෲ
+	(‎ ෘෘ ‎)	0DD8 0DD8	 SINHALA VOWEL SIGN GAETTA-PILLA, SINHALA VOWEL SIGN GAETTA-PILLA
+←	(‎ ෲ ‎)	0DF2	 SINHALA VOWEL SIGN DIGA GAETTA-PILLA
+
+#	ෙෙ	ෛ
+	(‎ ෙෙ ‎)	0DD9 0DD9	 SINHALA VOWEL SIGN KOMBUVA, SINHALA VOWEL SIGN KOMBUVA
+←	(‎ ෛ ‎)	0DDB	 SINHALA VOWEL SIGN KOMBU DEKA
+
 #	ข	ฃ
 	(‎ ข ‎)	0E02	 THAI CHARACTER KHO KHAI
 ←	(‎ ฃ ‎)	0E03	 THAI CHARACTER KHO KHUAT
@@ -1360,6 +1398,10 @@
 	(‎ ๋ ‎)	0E4B	 THAI CHARACTER MAI CHATTAWA
 ←	(‎ ໋ ‎)	0ECB	 LAO TONE MAI CATAWA
 
+#	ເເ	ແ
+	(‎ ເເ ‎)	0EC0 0EC0	 LAO VOWEL SIGN E, LAO VOWEL SIGN E
+←	(‎ ແ ‎)	0EC1	 LAO VOWEL SIGN EI
+
 #	ེེ	ཻ
 	(‎ ེེ ‎)	0F7A 0F7A	 TIBETAN VOWEL SIGN E, TIBETAN VOWEL SIGN E
 ←	(‎ ཻ ‎)	0F7B	 TIBETAN VOWEL SIGN EE
@@ -1386,6 +1428,10 @@
 ←	(‎ ဩော် ‎)	1029 1031 102C 103A	 MYANMAR LETTER O, MYANMAR VOWEL SIGN E, MYANMAR VOWEL SIGN AA, MYANMAR SIGN ASAT
 ←	(‎ ဪ ‎)	102A	 MYANMAR LETTER AU	# →ဩော်→
 
+#	ၵာ	ဢ
+	(‎ ဢ ‎)	1022	 MYANMAR LETTER SHAN A
+←	(‎ ၵာ ‎)	1075 102C	 MYANMAR LETTER SHAN KA, MYANMAR VOWEL SIGN AA
+
 #	ၽှ	ၾ
 	(‎ ၽှ ‎)	107D 103E	 MYANMAR LETTER SHAN PHA, MYANMAR CONSONANT SIGN MEDIAL HA
 ←	(‎ ၾ ‎)	107E	 MYANMAR LETTER SHAN FA
@@ -1394,9 +1440,26 @@
 	(‎ ដ ‎)	178A	 KHMER LETTER DA
 ←	(‎ ត ‎)	178F	 KHMER LETTER TA
 
+#	ទ្ប	ឡ
+	(‎ ទ្ប ‎)	1791 17D2 1794	 KHMER LETTER TO, KHMER SIGN COENG, KHMER LETTER BA
+←	(‎ ឡ ‎)	17A1	 KHMER LETTER LA
+
+#	ព្ធ	ឰ
+	(‎ ព្ធ ‎)	1796 17D2 1792	 KHMER LETTER PO, KHMER SIGN COENG, KHMER LETTER THO
+←	(‎ ឰ ‎)	17B0	 KHMER INDEPENDENT VOWEL QAI
+
+#	េี	េី	ើ
+	(‎ ើ ‎)	17BE	 KHMER VOWEL SIGN OE
+←	(‎ េี ‎)	17C1 0E35	 KHMER VOWEL SIGN E, THAI CHARACTER SARA II	# →េី→
+←	(‎ េី ‎)	17C1 17B8	 KHMER VOWEL SIGN E, KHMER VOWEL SIGN II
+
+#	េា	ោ
+	(‎ េា ‎)	17C1 17B6	 KHMER VOWEL SIGN E, KHMER VOWEL SIGN AA
+←	(‎ ោ ‎)	17C4	 KHMER VOWEL SIGN OO
+
 #	へ	ヘ
 	(‎ へ ‎)	3078	 HIRAGANA LETTER HE
 ←	(‎ ヘ ‎)	30D8	 KATAKANA LETTER HE
 
-# total : 500
+# total : 524
 

unicodetools/data/security/dev/confusablesSummary.txt

@@ -5759,3 +5759,55 @@ A7F1 ; 02E2  # ( ꟱ → ˢ ) MODIFIER LETTER CAPITAL S → MODIFIER LETTER SMAL
 
 # Confusables data for U+00A1 INVERTED EXCLAMATION MARK (PAG ref #453)
 00A1 ; 0069
+
+# Confusables data for dandas and double dandas (PAG ref #468)
+0964 ; 007C # DEVANAGARI DANDA
+104A ; 007C # MYANMAR SIGN LITTLE SECTION
+A8CE ; 007C # SAURASHTRA DANDA
+11047 ; 007C # BRAHMI DANDA
+110C0 ; 007C # KAITHI DANDA
+11141 ; 007C # CHAKMA DANDA
+111C5 ; 007C # SHARADA DANDA
+1144B ; 007C # NEWA DANDA
+11641 ; 007C # MODI DANDA
+11C41 ; 007C # BHAIKSUKI DANDA
+AA5D ; 007C # CHAM PUNCTUATION DANDA
+113D4 ; 007C # TULU-TIGALARI DANDA
+115C5 ; 007C # SIDDHAM SEPARATOR BAR
+16D63 ; 007C # KIRAT RAI VOWEL SIGN AA
+0965 ; 007C 007C # DEVANAGARI DOUBLE DANDA
+104B ; 007C 007C # MYANMAR SIGN SECTION
+A8CF ; 007C 007C # SAURASHTRA DOUBLE DANDA
+11048 ; 007C 007C # BRAHMI DOUBLE DANDA
+110C1 ; 007C 007C # KAITHI DOUBLE DANDA
+11142 ; 007C 007C # CHAKMA DOUBLE DANDA
+111C6 ; 007C 007C # SHARADA DOUBLE DANDA
+1144C ; 007C 007C # NEWA DOUBLE DANDA
+11642 ; 007C 007C # MODI DOUBLE DANDA
+11C42 ; 007C 007C # BHAIKSUKI DOUBLE DANDA
+113D5 ; 007C 007C # TULU-TIGALARI DOUBLE DANDA
+
+# High-priority confusables data (PAG ref #458)
+030B ; 0301 0301
+07A6 ; 0301
+07A7 ; 07A6 07A6
+07A8 ; 0317
+07A9 ; 07A8 07A8
+07AA ; 0350
+07AB ; 07AA 07AA
+07AC ; 1DFE
+07AD ; 07AC 07AC
+07AE ; 07AC 07AA
+07B0 ; 030A
+0DDB ; 0DD9 0DD9
+0DF2 ; 0DD8 0DD8
+0E3A ; 0323
+0EC1 ; 0EC0 0EC0
+0F7E ; 030A
+1022 ; 1075 102C
+17A1 ; 1791 17D2 1794
+17B0 ; 1796 17D2 1792
+17BE ; 17C1 17B8
+17C4 ; 17C1 17B6
+17C7 ; 0983
+11303 ; 0983