Update report

data/jtr/dumb16.conf

@@ -1,11 +1,11 @@
-# This  software is Copyright (c) 2012-2020 magnum, and it is hereby
+# This  software is Copyright (c) 2012-2024 magnum, and it is hereby
 # released to the general public under the following terms:
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted.
 #
 # Generic implementation of "dumb" exhaustive search of Unicode BMP.
-# Default is to try *all* allocated characters in the BMP of Unicode v13
-# (there's 55,387 of them). Even if a fast format can exhaust two characters
+# Default is to try *all* allocated characters in the BMP of Unicode v16
+# (there's 55,537 of them). Even if a fast format can exhaust two characters
 # in 15 minutes, three characters would take 1.5 years...
 #
 # Note that these modes will handle --max-len differently than normal: They
@@ -22,7 +22,7 @@ int maxlength;            // Maximum password length to try
 int last;                 // Last character position, zero-based
 int lastid;               // Character index in the last position
 int id[0x7f];             // Current character indices for other positions
-int charset[0x10000], c0; // Characters
+int charset[0xd900], c0;  // Characters
 
 void init()
 {
@@ -43,7 +43,7 @@ void init()
 
 /*
  * This defines the character set. This is auto-generated from UnicodeData.txt
- * and we skip control characters.
+ * of Unicode 16.0.0 and we skip control characters.
  */
 	i = 0;
 // 0000..007F; Basic Latin
@@ -119,9 +119,6 @@ void init()
 		charset[i++] = c++;
 // 0600..06FF; Arabic
 	c = 0x600;		// from ARABIC NUMBER SIGN
-	while (c <= 0x61c)	// ..to ARABIC LETTER MARK
-		charset[i++] = c++;
-	c = 0x61e;		// from ARABIC TRIPLE DOT PUNCTUATION MARK
 	while (c <= 0x6ff)	// ..to ARABIC LETTER HEH WITH INVERTED V
 		charset[i++] = c++;
 // 0700..074F; Syriac
@@ -163,14 +160,17 @@ void init()
 	c = 0x860;		// from SYRIAC LETTER MALAYALAM NGA
 	while (c <= 0x86a)	// ..to SYRIAC LETTER MALAYALAM SSA
 		charset[i++] = c++;
+// 0870..089F; Arabic Extended-B
+	c = 0x870;		// from ARABIC LETTER ALEF WITH ATTACHED FATHA
+	while (c <= 0x88e)	// ..to ARABIC VERTICAL TAIL
+		charset[i++] = c++;
+	charset[i++] = 0x890;	// ARABIC POUND MARK ABOVE
+	charset[i++] = 0x891;	// ARABIC PIASTRE MARK ABOVE
+	c = 0x897;		// from ARABIC PEPET
+	while (c <= 0x89f)	// ..to ARABIC HALF MADDA OVER MADDA
+		charset[i++] = c++;
 // 08A0..08FF; Arabic Extended-A
 	c = 0x8a0;		// from ARABIC LETTER BEH WITH SMALL V BELOW
-	while (c <= 0x8b4)	// ..to ARABIC LETTER KAF WITH DOT BELOW
-		charset[i++] = c++;
-	c = 0x8b6;		// from ARABIC LETTER BEH WITH SMALL MEEM ABOVE
-	while (c <= 0x8c7)	// ..to ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
-		charset[i++] = c++;
-	c = 0x8d3;		// from ARABIC SMALL LOW WAW
 	while (c <= 0x8ff)	// ..to ARABIC MARK SIDEWAYS NOON GHUNNA
 		charset[i++] = c++;
 // 0900..097F; Devanagari
@@ -360,7 +360,7 @@ void init()
 	c = 0xc2a;		// from TELUGU LETTER PA
 	while (c <= 0xc39)	// ..to TELUGU LETTER HA
 		charset[i++] = c++;
-	c = 0xc3d;		// from TELUGU SIGN AVAGRAHA
+	c = 0xc3c;		// from TELUGU SIGN NUKTA
 	while (c <= 0xc44)	// ..to TELUGU VOWEL SIGN VOCALIC RR
 		charset[i++] = c++;
 	charset[i++] = 0xc46;	// TELUGU VOWEL SIGN E
@@ -406,6 +406,8 @@ void init()
 		charset[i++] = c++;
 	charset[i++] = 0xcd5;	// KANNADA LENGTH MARK
 	charset[i++] = 0xcd6;	// KANNADA AI LENGTH MARK
+	charset[i++] = 0xcdd;	// KANNADA LETTER NAKAARA POLLU
+	charset[i++] = 0xcde;	// KANNADA LETTER FA
 	c = 0xce0;		// from KANNADA LETTER VOCALIC RR
 	while (c <= 0xce3)	// ..to KANNADA VOWEL SIGN VOCALIC LL
 		charset[i++] = c++;
@@ -413,7 +415,7 @@ void init()
 	while (c <= 0xcef)	// ..to KANNADA DIGIT NINE
 		charset[i++] = c++;
 	charset[i++] = 0xcf1;	// KANNADA SIGN JIHVAMULIYA
-	charset[i++] = 0xcf2;	// KANNADA SIGN UPADHMANIYA
+	charset[i++] = 0xcf3;	// KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 // 0D00..0D7F; Malayalam
 	c = 0xd00;		// from MALAYALAM SIGN COMBINING ANUSVARA ABOVE
 	while (c <= 0xd0c)	// ..to MALAYALAM LETTER VOCALIC L
@@ -483,7 +485,7 @@ void init()
 	while (c <= 0xec4)	// ..to LAO VOWEL SIGN AI
 		charset[i++] = c++;
 	c = 0xec8;		// from LAO TONE MAI EK
-	while (c <= 0xecd)	// ..to LAO NIGGAHITA
+	while (c <= 0xece)	// ..to LAO YAMAKKAN
 		charset[i++] = c++;
 	c = 0xed0;		// from LAO DIGIT ZERO
 	while (c <= 0xed9)	// ..to LAO DIGIT NINE
@@ -596,11 +598,9 @@ void init()
 		charset[i++] = c++;
 // 1700..171F; Tagalog
 	c = 0x1700;		// from TAGALOG LETTER A
-	while (c <= 0x170c)	// ..to TAGALOG LETTER YA
-		charset[i++] = c++;
-	c = 0x170e;		// from TAGALOG LETTER LA
-	while (c <= 0x1714)	// ..to TAGALOG SIGN VIRAMA
+	while (c <= 0x1715)	// ..to TAGALOG SIGN PAMUDPOD
 		charset[i++] = c++;
+	charset[i++] = 0x171f;	// TAGALOG LETTER ARCHAIC RA
 // 1720..173F; Hanunoo
 	c = 0x1720;		// from HANUNOO LETTER A
 	while (c <= 0x1736)	// ..to PHILIPPINE DOUBLE PUNCTUATION
@@ -629,9 +629,6 @@ void init()
 		charset[i++] = c++;
 // 1800..18AF; Mongolian
 	c = 0x1800;		// from MONGOLIAN BIRGA
-	while (c <= 0x180e)	// ..to MONGOLIAN VOWEL SEPARATOR
-		charset[i++] = c++;
-	c = 0x1810;		// from MONGOLIAN DIGIT ZERO
 	while (c <= 0x1819)	// ..to MONGOLIAN DIGIT NINE
 		charset[i++] = c++;
 	c = 0x1820;		// from MONGOLIAN LETTER A
@@ -704,14 +701,14 @@ void init()
 		charset[i++] = c++;
 // 1AB0..1AFF; Combining Diacritical Marks Extended
 	c = 0x1ab0;		// from COMBINING DOUBLED CIRCUMFLEX ACCENT
-	while (c <= 0x1ac0)	// ..to COMBINING LATIN SMALL LETTER TURNED W BELOW
+	while (c <= 0x1ace)	// ..to COMBINING LATIN SMALL LETTER INSULAR T
 		charset[i++] = c++;
 // 1B00..1B7F; Balinese
 	c = 0x1b00;		// from BALINESE SIGN ULU RICEM
-	while (c <= 0x1b4b)	// ..to BALINESE LETTER ASYURA SASAK
+	while (c <= 0x1b4c)	// ..to BALINESE LETTER ARCHAIC JNYA
 		charset[i++] = c++;
-	c = 0x1b50;		// from BALINESE DIGIT ZERO
-	while (c <= 0x1b7c)	// ..to BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING
+	c = 0x1b4e;		// from BALINESE INVERTED CARIK SIKI
+	while (c <= 0x1b7f)	// ..to BALINESE PANTI BAWAK
 		charset[i++] = c++;
 // 1B80..1BBF; Sundanese
 	c = 0x1b80;		// from SUNDANESE SIGN PANYECEK
@@ -739,7 +736,7 @@ void init()
 		charset[i++] = c++;
 // 1C80..1C8F; Cyrillic Extended-C
 	c = 0x1c80;		// from CYRILLIC SMALL LETTER ROUNDED VE
-	while (c <= 0x1c88)	// ..to CYRILLIC SMALL LETTER UNBLENDED UK
+	while (c <= 0x1c8a)	// ..to CYRILLIC SMALL LETTER TJE
 		charset[i++] = c++;
 // 1C90..1CBF; Georgian Extended
 	c = 0x1c90;		// from GEORGIAN MTAVRULI CAPITAL LETTER AN
@@ -765,9 +762,6 @@ void init()
 		charset[i++] = c++;
 // 1DC0..1DFF; Combining Diacritical Marks Supplement
 	c = 0x1dc0;		// from COMBINING DOTTED GRAVE ACCENT
-	while (c <= 0x1df9)	// ..to COMBINING WIDE INVERTED BRIDGE BELOW
-		charset[i++] = c++;
-	c = 0x1dfb;		// from COMBINING DELETION MARK
 	while (c <= 0x1dff)	// ..to COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
 		charset[i++] = c++;
 // 1E00..1EFF; Latin Extended Additional
@@ -831,7 +825,7 @@ void init()
 		charset[i++] = c++;
 // 20A0..20CF; Currency Symbols
 	c = 0x20a0;		// from EURO-CURRENCY SIGN
-	while (c <= 0x20bf)	// ..to BITCOIN SIGN
+	while (c <= 0x20c0)	// ..to SOM SIGN
 		charset[i++] = c++;
 // 20D0..20FF; Combining Diacritical Marks for Symbols
 	c = 0x20d0;		// from COMBINING LEFT HARPOON ABOVE
@@ -859,7 +853,7 @@ void init()
 		charset[i++] = c++;
 // 2400..243F; Control Pictures
 	c = 0x2400;		// from SYMBOL FOR NULL
-	while (c <= 0x2426)	// ..to SYMBOL FOR SUBSTITUTE FORM TWO
+	while (c <= 0x2429)	// ..to SYMBOL FOR DELETE MEDIUM SHADE FORM
 		charset[i++] = c++;
 // 2440..245F; Optical Character Recognition
 	c = 0x2440;		// from OCR HOOK
@@ -925,10 +919,7 @@ void init()
 		charset[i++] = c++;
 // 2C00..2C5F; Glagolitic
 	c = 0x2c00;		// from GLAGOLITIC CAPITAL LETTER AZU
-	while (c <= 0x2c2e)	// ..to GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
-		charset[i++] = c++;
-	c = 0x2c30;		// from GLAGOLITIC SMALL LETTER AZU
-	while (c <= 0x2c5e)	// ..to GLAGOLITIC SMALL LETTER LATINATE MYSLITE
+	while (c <= 0x2c5f)	// ..to GLAGOLITIC SMALL LETTER CAUDATE CHRIVI
 		charset[i++] = c++;
 // 2C60..2C7F; Latin Extended-C
 	c = 0x2c60;		// from LATIN CAPITAL LETTER L WITH DOUBLE BAR
@@ -989,7 +980,7 @@ void init()
 		charset[i++] = c++;
 // 2E00..2E7F; Supplemental Punctuation
 	c = 0x2e00;		// from RIGHT ANGLE SUBSTITUTION MARKER
-	while (c <= 0x2e52)	// ..to TIRONIAN SIGN CAPITAL ET
+	while (c <= 0x2e5d)	// ..to OBLIQUE HYPHEN
 		charset[i++] = c++;
 // 2E80..2EFF; CJK Radicals Supplement
 	c = 0x2e80;		// from CJK RADICAL REPEAT
@@ -1004,7 +995,7 @@ void init()
 		charset[i++] = c++;
 // 2FF0..2FFF; Ideographic Description Characters
 	c = 0x2ff0;		// from IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT
-	while (c <= 0x2ffb)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
+	while (c <= 0x2fff)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
 		charset[i++] = c++;
 // 3000..303F; CJK Symbols and Punctuation
 	c = 0x3000;		// from IDEOGRAPHIC SPACE
@@ -1039,8 +1030,9 @@ void init()
 		charset[i++] = c++;
 // 31C0..31EF; CJK Strokes
 	c = 0x31c0;		// from CJK STROKE T
-	while (c <= 0x31e3)	// ..to CJK STROKE Q
+	while (c <= 0x31e5)	// ..to CJK STROKE SZP
 		charset[i++] = c++;
+	charset[i++] = 0x31ef;	// IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
 // 31F0..31FF; Katakana Phonetic Extensions
 	c = 0x31f0;		// from KATAKANA LETTER SMALL KU
 	while (c <= 0x31ff)	// ..to KATAKANA LETTER SMALL RO
@@ -1066,7 +1058,7 @@ void init()
 		charset[i++] = c++;
 // 4E00..9FFF; CJK Unified Ideographs
 	c = 0x4e00;		// from <CJK Ideograph, First>
-	while (c <= 0x9ffc)	// ..to <CJK Ideograph, Last>
+	while (c <= 0x9fff)	// ..to <CJK Ideograph, Last>
 		charset[i++] = c++;
 // A000..A48F; Yi Syllables
 	c = 0xa000;		// from YI SYLLABLE IT
@@ -1098,12 +1090,14 @@ void init()
 		charset[i++] = c++;
 // A720..A7FF; Latin Extended-D
 	c = 0xa720;		// from MODIFIER LETTER STRESS AND HIGH TONE
-	while (c <= 0xa7bf)	// ..to LATIN SMALL LETTER GLOTTAL U
+	while (c <= 0xa7cd)	// ..to LATIN SMALL LETTER S WITH DIAGONAL STROKE
 		charset[i++] = c++;
-	c = 0xa7c2;		// from LATIN CAPITAL LETTER ANGLICANA W
-	while (c <= 0xa7ca)	// ..to LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
+	charset[i++] = 0xa7d0;	// LATIN CAPITAL LETTER CLOSED INSULAR G
+	charset[i++] = 0xa7d1;	// LATIN SMALL LETTER CLOSED INSULAR G
+	c = 0xa7d5;		// from LATIN SMALL LETTER DOUBLE WYNN
+	while (c <= 0xa7dc)	// ..to LATIN CAPITAL LETTER LAMBDA WITH STROKE
 		charset[i++] = c++;
-	c = 0xa7f5;		// from LATIN CAPITAL LETTER REVERSED HALF H
+	c = 0xa7f2;		// from MODIFIER LETTER CAPITAL C
 	while (c <= 0xa7ff)	// ..to LATIN EPIGRAPHIC LETTER ARCHAIC M
 		charset[i++] = c++;
 // A800..A82F; Syloti Nagri
@@ -1258,19 +1252,16 @@ void init()
 		charset[i++] = c++;
 // FB50..FDFF; Arabic Presentation Forms-A
 	c = 0xfb50;		// from ARABIC LETTER ALEF WASLA ISOLATED FORM
-	while (c <= 0xfbc1)	// ..to ARABIC SYMBOL SMALL TAH BELOW
+	while (c <= 0xfbc2)	// ..to ARABIC SYMBOL WASLA ABOVE
 		charset[i++] = c++;
 	c = 0xfbd3;		// from ARABIC LETTER NG ISOLATED FORM
-	while (c <= 0xfd3f)	// ..to ORNATE RIGHT PARENTHESIS
-		charset[i++] = c++;
-	c = 0xfd50;		// from ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM
 	while (c <= 0xfd8f)	// ..to ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
 		charset[i++] = c++;
 	c = 0xfd92;		// from ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM
 	while (c <= 0xfdc7)	// ..to ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
 		charset[i++] = c++;
 	c = 0xfdf0;		// from ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM
-	while (c <= 0xfdfd)	// ..to ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
+	while (c <= 0xfdff)	// ..to ARABIC LIGATURE AZZA WA JALL
 		charset[i++] = c++;
 // FE00..FE0F; Variation Selectors
 	c = 0xfe00;		// from VARIATION SELECTOR-1

data/jtr/dumb32.conf

@@ -1,11 +1,11 @@
-# This  software is Copyright (c) 2012-2020 magnum, and it is hereby
+# This  software is Copyright (c) 2012-2024 magnum, and it is hereby
 # released to the general public under the following terms:
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted.
 #
 # Generic implementation of "dumb" exhaustive search of FULL Unicode.
-# Default is to try *all* allocated characters in Unicode v13 (there's
-# 143,532 of them). Even if a fast format can exhaust two characters in one
+# Default is to try *all* allocated characters in Unicode v16 (there's
+# 154,663 of them). Even if a fast format can exhaust two characters in one
 # hour, three characters would take 12 years...
 #
 # Note that these modes will handle --max-len differently than normal: They
@@ -27,7 +27,7 @@ int maxlength;            // Maximum password length to try
 int last;                 // Last character position, zero-based
 int lastid;               // Character index in the last position
 int id[0x7f];             // Current character indices for other positions
-int charset[0x24000], c0; // Characters
+int charset[0x25c30], c0; // Characters
 
 void init()
 {
@@ -48,7 +48,7 @@ void init()
 
 /*
  * This defines the character set. This is auto-generated from UnicodeData.txt
- * and we skip control characters.
+ * of Unicode 16.0.0 and we skip control characters.
  */
 	i = 0;
 // 0000..007F; Basic Latin
@@ -124,9 +124,6 @@ void init()
 		charset[i++] = c++;
 // 0600..06FF; Arabic
 	c = 0x600;		// from ARABIC NUMBER SIGN
-	while (c <= 0x61c)	// ..to ARABIC LETTER MARK
-		charset[i++] = c++;
-	c = 0x61e;		// from ARABIC TRIPLE DOT PUNCTUATION MARK
 	while (c <= 0x6ff)	// ..to ARABIC LETTER HEH WITH INVERTED V
 		charset[i++] = c++;
 // 0700..074F; Syriac
@@ -168,14 +165,17 @@ void init()
 	c = 0x860;		// from SYRIAC LETTER MALAYALAM NGA
 	while (c <= 0x86a)	// ..to SYRIAC LETTER MALAYALAM SSA
 		charset[i++] = c++;
+// 0870..089F; Arabic Extended-B
+	c = 0x870;		// from ARABIC LETTER ALEF WITH ATTACHED FATHA
+	while (c <= 0x88e)	// ..to ARABIC VERTICAL TAIL
+		charset[i++] = c++;
+	charset[i++] = 0x890;	// ARABIC POUND MARK ABOVE
+	charset[i++] = 0x891;	// ARABIC PIASTRE MARK ABOVE
+	c = 0x897;		// from ARABIC PEPET
+	while (c <= 0x89f)	// ..to ARABIC HALF MADDA OVER MADDA
+		charset[i++] = c++;
 // 08A0..08FF; Arabic Extended-A
 	c = 0x8a0;		// from ARABIC LETTER BEH WITH SMALL V BELOW
-	while (c <= 0x8b4)	// ..to ARABIC LETTER KAF WITH DOT BELOW
-		charset[i++] = c++;
-	c = 0x8b6;		// from ARABIC LETTER BEH WITH SMALL MEEM ABOVE
-	while (c <= 0x8c7)	// ..to ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
-		charset[i++] = c++;
-	c = 0x8d3;		// from ARABIC SMALL LOW WAW
 	while (c <= 0x8ff)	// ..to ARABIC MARK SIDEWAYS NOON GHUNNA
 		charset[i++] = c++;
 // 0900..097F; Devanagari
@@ -365,7 +365,7 @@ void init()
 	c = 0xc2a;		// from TELUGU LETTER PA
 	while (c <= 0xc39)	// ..to TELUGU LETTER HA
 		charset[i++] = c++;
-	c = 0xc3d;		// from TELUGU SIGN AVAGRAHA
+	c = 0xc3c;		// from TELUGU SIGN NUKTA
 	while (c <= 0xc44)	// ..to TELUGU VOWEL SIGN VOCALIC RR
 		charset[i++] = c++;
 	charset[i++] = 0xc46;	// TELUGU VOWEL SIGN E
@@ -411,6 +411,8 @@ void init()
 		charset[i++] = c++;
 	charset[i++] = 0xcd5;	// KANNADA LENGTH MARK
 	charset[i++] = 0xcd6;	// KANNADA AI LENGTH MARK
+	charset[i++] = 0xcdd;	// KANNADA LETTER NAKAARA POLLU
+	charset[i++] = 0xcde;	// KANNADA LETTER FA
 	c = 0xce0;		// from KANNADA LETTER VOCALIC RR
 	while (c <= 0xce3)	// ..to KANNADA VOWEL SIGN VOCALIC LL
 		charset[i++] = c++;
@@ -418,7 +420,7 @@ void init()
 	while (c <= 0xcef)	// ..to KANNADA DIGIT NINE
 		charset[i++] = c++;
 	charset[i++] = 0xcf1;	// KANNADA SIGN JIHVAMULIYA
-	charset[i++] = 0xcf2;	// KANNADA SIGN UPADHMANIYA
+	charset[i++] = 0xcf3;	// KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 // 0D00..0D7F; Malayalam
 	c = 0xd00;		// from MALAYALAM SIGN COMBINING ANUSVARA ABOVE
 	while (c <= 0xd0c)	// ..to MALAYALAM LETTER VOCALIC L
@@ -488,7 +490,7 @@ void init()
 	while (c <= 0xec4)	// ..to LAO VOWEL SIGN AI
 		charset[i++] = c++;
 	c = 0xec8;		// from LAO TONE MAI EK
-	while (c <= 0xecd)	// ..to LAO NIGGAHITA
+	while (c <= 0xece)	// ..to LAO YAMAKKAN
 		charset[i++] = c++;
 	c = 0xed0;		// from LAO DIGIT ZERO
 	while (c <= 0xed9)	// ..to LAO DIGIT NINE
@@ -601,11 +603,9 @@ void init()
 		charset[i++] = c++;
 // 1700..171F; Tagalog
 	c = 0x1700;		// from TAGALOG LETTER A
-	while (c <= 0x170c)	// ..to TAGALOG LETTER YA
-		charset[i++] = c++;
-	c = 0x170e;		// from TAGALOG LETTER LA
-	while (c <= 0x1714)	// ..to TAGALOG SIGN VIRAMA
+	while (c <= 0x1715)	// ..to TAGALOG SIGN PAMUDPOD
 		charset[i++] = c++;
+	charset[i++] = 0x171f;	// TAGALOG LETTER ARCHAIC RA
 // 1720..173F; Hanunoo
 	c = 0x1720;		// from HANUNOO LETTER A
 	while (c <= 0x1736)	// ..to PHILIPPINE DOUBLE PUNCTUATION
@@ -634,9 +634,6 @@ void init()
 		charset[i++] = c++;
 // 1800..18AF; Mongolian
 	c = 0x1800;		// from MONGOLIAN BIRGA
-	while (c <= 0x180e)	// ..to MONGOLIAN VOWEL SEPARATOR
-		charset[i++] = c++;
-	c = 0x1810;		// from MONGOLIAN DIGIT ZERO
 	while (c <= 0x1819)	// ..to MONGOLIAN DIGIT NINE
 		charset[i++] = c++;
 	c = 0x1820;		// from MONGOLIAN LETTER A
@@ -709,14 +706,14 @@ void init()
 		charset[i++] = c++;
 // 1AB0..1AFF; Combining Diacritical Marks Extended
 	c = 0x1ab0;		// from COMBINING DOUBLED CIRCUMFLEX ACCENT
-	while (c <= 0x1ac0)	// ..to COMBINING LATIN SMALL LETTER TURNED W BELOW
+	while (c <= 0x1ace)	// ..to COMBINING LATIN SMALL LETTER INSULAR T
 		charset[i++] = c++;
 // 1B00..1B7F; Balinese
 	c = 0x1b00;		// from BALINESE SIGN ULU RICEM
-	while (c <= 0x1b4b)	// ..to BALINESE LETTER ASYURA SASAK
+	while (c <= 0x1b4c)	// ..to BALINESE LETTER ARCHAIC JNYA
 		charset[i++] = c++;
-	c = 0x1b50;		// from BALINESE DIGIT ZERO
-	while (c <= 0x1b7c)	// ..to BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING
+	c = 0x1b4e;		// from BALINESE INVERTED CARIK SIKI
+	while (c <= 0x1b7f)	// ..to BALINESE PANTI BAWAK
 		charset[i++] = c++;
 // 1B80..1BBF; Sundanese
 	c = 0x1b80;		// from SUNDANESE SIGN PANYECEK
@@ -744,7 +741,7 @@ void init()
 		charset[i++] = c++;
 // 1C80..1C8F; Cyrillic Extended-C
 	c = 0x1c80;		// from CYRILLIC SMALL LETTER ROUNDED VE
-	while (c <= 0x1c88)	// ..to CYRILLIC SMALL LETTER UNBLENDED UK
+	while (c <= 0x1c8a)	// ..to CYRILLIC SMALL LETTER TJE
 		charset[i++] = c++;
 // 1C90..1CBF; Georgian Extended
 	c = 0x1c90;		// from GEORGIAN MTAVRULI CAPITAL LETTER AN
@@ -770,9 +767,6 @@ void init()
 		charset[i++] = c++;
 // 1DC0..1DFF; Combining Diacritical Marks Supplement
 	c = 0x1dc0;		// from COMBINING DOTTED GRAVE ACCENT
-	while (c <= 0x1df9)	// ..to COMBINING WIDE INVERTED BRIDGE BELOW
-		charset[i++] = c++;
-	c = 0x1dfb;		// from COMBINING DELETION MARK
 	while (c <= 0x1dff)	// ..to COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
 		charset[i++] = c++;
 // 1E00..1EFF; Latin Extended Additional
@@ -836,7 +830,7 @@ void init()
 		charset[i++] = c++;
 // 20A0..20CF; Currency Symbols
 	c = 0x20a0;		// from EURO-CURRENCY SIGN
-	while (c <= 0x20bf)	// ..to BITCOIN SIGN
+	while (c <= 0x20c0)	// ..to SOM SIGN
 		charset[i++] = c++;
 // 20D0..20FF; Combining Diacritical Marks for Symbols
 	c = 0x20d0;		// from COMBINING LEFT HARPOON ABOVE
@@ -864,7 +858,7 @@ void init()
 		charset[i++] = c++;
 // 2400..243F; Control Pictures
 	c = 0x2400;		// from SYMBOL FOR NULL
-	while (c <= 0x2426)	// ..to SYMBOL FOR SUBSTITUTE FORM TWO
+	while (c <= 0x2429)	// ..to SYMBOL FOR DELETE MEDIUM SHADE FORM
 		charset[i++] = c++;
 // 2440..245F; Optical Character Recognition
 	c = 0x2440;		// from OCR HOOK
@@ -930,10 +924,7 @@ void init()
 		charset[i++] = c++;
 // 2C00..2C5F; Glagolitic
 	c = 0x2c00;		// from GLAGOLITIC CAPITAL LETTER AZU
-	while (c <= 0x2c2e)	// ..to GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
-		charset[i++] = c++;
-	c = 0x2c30;		// from GLAGOLITIC SMALL LETTER AZU
-	while (c <= 0x2c5e)	// ..to GLAGOLITIC SMALL LETTER LATINATE MYSLITE
+	while (c <= 0x2c5f)	// ..to GLAGOLITIC SMALL LETTER CAUDATE CHRIVI
 		charset[i++] = c++;
 // 2C60..2C7F; Latin Extended-C
 	c = 0x2c60;		// from LATIN CAPITAL LETTER L WITH DOUBLE BAR
@@ -994,7 +985,7 @@ void init()
 		charset[i++] = c++;
 // 2E00..2E7F; Supplemental Punctuation
 	c = 0x2e00;		// from RIGHT ANGLE SUBSTITUTION MARKER
-	while (c <= 0x2e52)	// ..to TIRONIAN SIGN CAPITAL ET
+	while (c <= 0x2e5d)	// ..to OBLIQUE HYPHEN
 		charset[i++] = c++;
 // 2E80..2EFF; CJK Radicals Supplement
 	c = 0x2e80;		// from CJK RADICAL REPEAT
@@ -1009,7 +1000,7 @@ void init()
 		charset[i++] = c++;
 // 2FF0..2FFF; Ideographic Description Characters
 	c = 0x2ff0;		// from IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT
-	while (c <= 0x2ffb)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
+	while (c <= 0x2fff)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
 		charset[i++] = c++;
 // 3000..303F; CJK Symbols and Punctuation
 	c = 0x3000;		// from IDEOGRAPHIC SPACE
@@ -1044,8 +1035,9 @@ void init()
 		charset[i++] = c++;
 // 31C0..31EF; CJK Strokes
 	c = 0x31c0;		// from CJK STROKE T
-	while (c <= 0x31e3)	// ..to CJK STROKE Q
+	while (c <= 0x31e5)	// ..to CJK STROKE SZP
 		charset[i++] = c++;
+	charset[i++] = 0x31ef;	// IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
 // 31F0..31FF; Katakana Phonetic Extensions
 	c = 0x31f0;		// from KATAKANA LETTER SMALL KU
 	while (c <= 0x31ff)	// ..to KATAKANA LETTER SMALL RO
@@ -1071,7 +1063,7 @@ void init()
 		charset[i++] = c++;
 // 4E00..9FFF; CJK Unified Ideographs
 	c = 0x4e00;		// from <CJK Ideograph, First>
-	while (c <= 0x9ffc)	// ..to <CJK Ideograph, Last>
+	while (c <= 0x9fff)	// ..to <CJK Ideograph, Last>
 		charset[i++] = c++;
 // A000..A48F; Yi Syllables
 	c = 0xa000;		// from YI SYLLABLE IT
@@ -1103,12 +1095,14 @@ void init()
 		charset[i++] = c++;
 // A720..A7FF; Latin Extended-D
 	c = 0xa720;		// from MODIFIER LETTER STRESS AND HIGH TONE
-	while (c <= 0xa7bf)	// ..to LATIN SMALL LETTER GLOTTAL U
+	while (c <= 0xa7cd)	// ..to LATIN SMALL LETTER S WITH DIAGONAL STROKE
 		charset[i++] = c++;
-	c = 0xa7c2;		// from LATIN CAPITAL LETTER ANGLICANA W
-	while (c <= 0xa7ca)	// ..to LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
+	charset[i++] = 0xa7d0;	// LATIN CAPITAL LETTER CLOSED INSULAR G
+	charset[i++] = 0xa7d1;	// LATIN SMALL LETTER CLOSED INSULAR G
+	c = 0xa7d5;		// from LATIN SMALL LETTER DOUBLE WYNN
+	while (c <= 0xa7dc)	// ..to LATIN CAPITAL LETTER LAMBDA WITH STROKE
 		charset[i++] = c++;
-	c = 0xa7f5;		// from LATIN CAPITAL LETTER REVERSED HALF H
+	c = 0xa7f2;		// from MODIFIER LETTER CAPITAL C
 	while (c <= 0xa7ff)	// ..to LATIN EPIGRAPHIC LETTER ARCHAIC M
 		charset[i++] = c++;
 // A800..A82F; Syloti Nagri
@@ -1263,19 +1257,16 @@ void init()
 		charset[i++] = c++;
 // FB50..FDFF; Arabic Presentation Forms-A
 	c = 0xfb50;		// from ARABIC LETTER ALEF WASLA ISOLATED FORM
-	while (c <= 0xfbc1)	// ..to ARABIC SYMBOL SMALL TAH BELOW
+	while (c <= 0xfbc2)	// ..to ARABIC SYMBOL WASLA ABOVE
 		charset[i++] = c++;
 	c = 0xfbd3;		// from ARABIC LETTER NG ISOLATED FORM
-	while (c <= 0xfd3f)	// ..to ORNATE RIGHT PARENTHESIS
-		charset[i++] = c++;
-	c = 0xfd50;		// from ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM
 	while (c <= 0xfd8f)	// ..to ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
 		charset[i++] = c++;
 	c = 0xfd92;		// from ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM
 	while (c <= 0xfdc7)	// ..to ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
 		charset[i++] = c++;
 	c = 0xfdf0;		// from ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM
-	while (c <= 0xfdfd)	// ..to ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
+	while (c <= 0xfdff)	// ..to ARABIC LIGATURE AZZA WA JALL
 		charset[i++] = c++;
 // FE00..FE0F; Variation Selectors
 	c = 0xfe00;		// from VARIATION SELECTOR-1
@@ -1448,6 +1439,33 @@ void init()
 	while (c <= 0x10563)	// ..to CAUCASIAN ALBANIAN LETTER KIW
 		charset[i++] = c++;
 	charset[i++] = 0x1056f;	// CAUCASIAN ALBANIAN CITATION MARK
+// 10570..105BF; Vithkuqi
+	c = 0x10570;		// from VITHKUQI CAPITAL LETTER A
+	while (c <= 0x1057a)	// ..to VITHKUQI CAPITAL LETTER GA
+		charset[i++] = c++;
+	c = 0x1057c;		// from VITHKUQI CAPITAL LETTER HA
+	while (c <= 0x1058a)	// ..to VITHKUQI CAPITAL LETTER RE
+		charset[i++] = c++;
+	c = 0x1058c;		// from VITHKUQI CAPITAL LETTER SE
+	while (c <= 0x10592)	// ..to VITHKUQI CAPITAL LETTER XE
+		charset[i++] = c++;
+	charset[i++] = 0x10594;	// VITHKUQI CAPITAL LETTER Y
+	charset[i++] = 0x10595;	// VITHKUQI CAPITAL LETTER ZE
+	c = 0x10597;		// from VITHKUQI SMALL LETTER A
+	while (c <= 0x105a1)	// ..to VITHKUQI SMALL LETTER GA
+		charset[i++] = c++;
+	c = 0x105a3;		// from VITHKUQI SMALL LETTER HA
+	while (c <= 0x105b1)	// ..to VITHKUQI SMALL LETTER RE
+		charset[i++] = c++;
+	c = 0x105b3;		// from VITHKUQI SMALL LETTER SE
+	while (c <= 0x105b9)	// ..to VITHKUQI SMALL LETTER XE
+		charset[i++] = c++;
+	charset[i++] = 0x105bb;	// VITHKUQI SMALL LETTER Y
+	charset[i++] = 0x105bc;	// VITHKUQI SMALL LETTER ZE
+// 105C0..105FF; Todhri
+	c = 0x105c0;		// from TODHRI LETTER A
+	while (c <= 0x105f3)	// ..to TODHRI LETTER OO
+		charset[i++] = c++;
 // 10600..1077F; Linear A
 	c = 0x10600;		// from LINEAR A SIGN AB001
 	while (c <= 0x10736)	// ..to LINEAR A SIGN A664
@@ -1458,6 +1476,16 @@ void init()
 	c = 0x10760;		// from LINEAR A SIGN A800
 	while (c <= 0x10767)	// ..to LINEAR A SIGN A807
 		charset[i++] = c++;
+// 10780..107BF; Latin Extended-F
+	c = 0x10780;		// from MODIFIER LETTER SMALL CAPITAL AA
+	while (c <= 0x10785)	// ..to MODIFIER LETTER SMALL B WITH HOOK
+		charset[i++] = c++;
+	c = 0x10787;		// from MODIFIER LETTER SMALL DZ DIGRAPH
+	while (c <= 0x107b0)	// ..to MODIFIER LETTER SMALL V WITH RIGHT HOOK
+		charset[i++] = c++;
+	c = 0x107b2;		// from MODIFIER LETTER SMALL CAPITAL Y
+	while (c <= 0x107ba)	// ..to MODIFIER LETTER SMALL S WITH CURL
+		charset[i++] = c++;
 // 10800..1083F; Cypriot Syllabary
 	c = 0x10800;		// from CYPRIOT SYLLABLE A
 	while (c <= 0x10805)	// ..to CYPRIOT SYLLABLE JA
@@ -1610,6 +1638,15 @@ void init()
 	c = 0x10d30;		// from HANIFI ROHINGYA DIGIT ZERO
 	while (c <= 0x10d39)	// ..to HANIFI ROHINGYA DIGIT NINE
 		charset[i++] = c++;
+// 10D40..10D8F; Garay
+	c = 0x10d40;		// from GARAY DIGIT ZERO
+	while (c <= 0x10d65)	// ..to GARAY CAPITAL LETTER OLD NA
+		charset[i++] = c++;
+	c = 0x10d69;		// from GARAY VOWEL SIGN E
+	while (c <= 0x10d85)	// ..to GARAY SMALL LETTER OLD NA
+		charset[i++] = c++;
+	charset[i++] = 0x10d8e;	// GARAY PLUS SIGN
+	charset[i++] = 0x10d8f;	// GARAY MINUS SIGN
 // 10E60..10E7F; Rumi Numeral Symbols
 	c = 0x10e60;		// from RUMI DIGIT ONE
 	while (c <= 0x10e7e)	// ..to RUMI FRACTION TWO THIRDS
@@ -1622,6 +1659,12 @@ void init()
 	charset[i++] = 0x10ead;	// YEZIDI HYPHENATION MARK
 	charset[i++] = 0x10eb0;	// YEZIDI LETTER LAM WITH DOT ABOVE
 	charset[i++] = 0x10eb1;	// YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
+// 10EC0..10EFF; Arabic Extended-C
+	charset[i++] = 0x10ec2;	// ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW
+	charset[i++] = 0x10ec4;	// ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW
+	c = 0x10efc;		// from ARABIC COMBINING ALEF OVERLAY
+	while (c <= 0x10eff)	// ..to ARABIC SMALL LOW WORD MADDA
+		charset[i++] = c++;
 // 10F00..10F2F; Old Sogdian
 	c = 0x10f00;		// from OLD SOGDIAN LETTER ALEPH
 	while (c <= 0x10f27)	// ..to OLD SOGDIAN LIGATURE AYIN-DALETH
@@ -1630,6 +1673,10 @@ void init()
 	c = 0x10f30;		// from SOGDIAN LETTER ALEPH
 	while (c <= 0x10f59)	// ..to SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
 		charset[i++] = c++;
+// 10F70..10FAF; Old Uyghur
+	c = 0x10f70;		// from OLD UYGHUR LETTER ALEPH
+	while (c <= 0x10f89)	// ..to OLD UYGHUR PUNCTUATION FOUR DOTS
+		charset[i++] = c++;
 // 10FB0..10FDF; Chorasmian
 	c = 0x10fb0;		// from CHORASMIAN LETTER ALEPH
 	while (c <= 0x10fcb)	// ..to CHORASMIAN NUMBER ONE HUNDRED
@@ -1643,12 +1690,12 @@ void init()
 	while (c <= 0x1104d)	// ..to BRAHMI PUNCTUATION LOTUS
 		charset[i++] = c++;
 	c = 0x11052;		// from BRAHMI NUMBER ONE
-	while (c <= 0x1106f)	// ..to BRAHMI DIGIT NINE
+	while (c <= 0x11075)	// ..to BRAHMI LETTER OLD TAMIL LLA
 		charset[i++] = c++;
 	charset[i++] = 0x1107f;	// BRAHMI NUMBER JOINER
 // 11080..110CF; Kaithi
 	c = 0x11080;		// from KAITHI SIGN CANDRABINDU
-	while (c <= 0x110c1)	// ..to KAITHI DOUBLE DANDA
+	while (c <= 0x110c2)	// ..to KAITHI VOWEL SIGN VOCALIC R
 		charset[i++] = c++;
 	charset[i++] = 0x110cd;	// KAITHI NUMBER SIGN ABOVE
 // 110D0..110FF; Sora Sompeng
@@ -1682,7 +1729,7 @@ void init()
 	while (c <= 0x11211)	// ..to KHOJKI LETTER JJA
 		charset[i++] = c++;
 	c = 0x11213;		// from KHOJKI LETTER NYA
-	while (c <= 0x1123e)	// ..to KHOJKI SIGN SUKUN
+	while (c <= 0x11241)	// ..to KHOJKI VOWEL SIGN VOCALIC R
 		charset[i++] = c++;
 // 11280..112AF; Multani
 	c = 0x11280;		// from MULTANI LETTER A
@@ -1740,6 +1787,26 @@ void init()
 	c = 0x11370;		// from COMBINING GRANTHA LETTER A
 	while (c <= 0x11374)	// ..to COMBINING GRANTHA LETTER PA
 		charset[i++] = c++;
+// 11380..113FF; Tulu-Tigalari
+	c = 0x11380;		// from TULU-TIGALARI LETTER A
+	while (c <= 0x11389)	// ..to TULU-TIGALARI LETTER VOCALIC LL
+		charset[i++] = c++;
+	c = 0x11390;		// from TULU-TIGALARI LETTER OO
+	while (c <= 0x113b5)	// ..to TULU-TIGALARI LETTER LLLA
+		charset[i++] = c++;
+	c = 0x113b7;		// from TULU-TIGALARI SIGN AVAGRAHA
+	while (c <= 0x113c0)	// ..to TULU-TIGALARI VOWEL SIGN VOCALIC LL
+		charset[i++] = c++;
+	c = 0x113c7;		// from TULU-TIGALARI VOWEL SIGN OO
+	while (c <= 0x113ca)	// ..to TULU-TIGALARI SIGN CANDRA ANUNASIKA
+		charset[i++] = c++;
+	c = 0x113cc;		// from TULU-TIGALARI SIGN ANUSVARA
+	while (c <= 0x113d5)	// ..to TULU-TIGALARI DOUBLE DANDA
+		charset[i++] = c++;
+	charset[i++] = 0x113d7;	// TULU-TIGALARI SIGN OM PUSHPIKA
+	charset[i++] = 0x113d8;	// TULU-TIGALARI SIGN SHRII PUSHPIKA
+	charset[i++] = 0x113e1;	// TULU-TIGALARI VEDIC TONE SVARITA
+	charset[i++] = 0x113e2;	// TULU-TIGALARI VEDIC TONE ANUDATTA
 // 11400..1147F; Newa
 	c = 0x11400;		// from NEWA LETTER A
 	while (c <= 0x1145b)	// ..to NEWA PLACEHOLDER MARK
@@ -1774,12 +1841,16 @@ void init()
 		charset[i++] = c++;
 // 11680..116CF; Takri
 	c = 0x11680;		// from TAKRI LETTER A
-	while (c <= 0x116b8)	// ..to TAKRI LETTER ARCHAIC KHA
+	while (c <= 0x116b9)	// ..to TAKRI ABBREVIATION SIGN
 		charset[i++] = c++;
 	c = 0x116c0;		// from TAKRI DIGIT ZERO
 	while (c <= 0x116c9)	// ..to TAKRI DIGIT NINE
 		charset[i++] = c++;
-// 11700..1173F; Ahom
+// 116D0..116FF; Myanmar Extended-C
+	c = 0x116d0;		// from MYANMAR PAO DIGIT ZERO
+	while (c <= 0x116e3)	// ..to MYANMAR EASTERN PWO KAREN DIGIT NINE
+		charset[i++] = c++;
+// 11700..1174F; Ahom
 	c = 0x11700;		// from AHOM LETTER KA
 	while (c <= 0x1171a)	// ..to AHOM LETTER ALTERNATE BA
 		charset[i++] = c++;
@@ -1787,7 +1858,7 @@ void init()
 	while (c <= 0x1172b)	// ..to AHOM SIGN KILLER
 		charset[i++] = c++;
 	c = 0x11730;		// from AHOM DIGIT ZERO
-	while (c <= 0x1173f)	// ..to AHOM SYMBOL VI
+	while (c <= 0x11746)	// ..to AHOM LETTER LLA
 		charset[i++] = c++;
 // 11800..1184F; Dogra
 	c = 0x11800;		// from DOGRA LETTER A
@@ -1836,10 +1907,25 @@ void init()
 	c = 0x11a50;		// from SOYOMBO LETTER A
 	while (c <= 0x11aa2)	// ..to SOYOMBO TERMINAL MARK-2
 		charset[i++] = c++;
+// 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
+	c = 0x11ab0;		// from CANADIAN SYLLABICS NATTILIK HI
+	while (c <= 0x11abf)	// ..to CANADIAN SYLLABICS SPA
+		charset[i++] = c++;
 // 11AC0..11AFF; Pau Cin Hau
 	c = 0x11ac0;		// from PAU CIN HAU LETTER PA
 	while (c <= 0x11af8)	// ..to PAU CIN HAU GLOTTAL STOP FINAL
 		charset[i++] = c++;
+// 11B00..11B5F; Devanagari Extended-A
+	c = 0x11b00;		// from DEVANAGARI HEAD MARK
+	while (c <= 0x11b09)	// ..to DEVANAGARI SIGN MINDU
+		charset[i++] = c++;
+// 11BC0..11BFF; Sunuwar
+	c = 0x11bc0;		// from SUNUWAR LETTER DEVI
+	while (c <= 0x11be1)	// ..to SUNUWAR SIGN PVO
+		charset[i++] = c++;
+	c = 0x11bf0;		// from SUNUWAR DIGIT ZERO
+	while (c <= 0x11bf9)	// ..to SUNUWAR DIGIT NINE
+		charset[i++] = c++;
 // 11C00..11C6F; Bhaiksuki
 	c = 0x11c00;		// from BHAIKSUKI LETTER A
 	while (c <= 0x11c08)	// ..to BHAIKSUKI LETTER VOCALIC L
@@ -1901,6 +1987,16 @@ void init()
 	c = 0x11ee0;		// from MAKASAR LETTER KA
 	while (c <= 0x11ef8)	// ..to MAKASAR END OF SECTION
 		charset[i++] = c++;
+// 11F00..11F5F; Kawi
+	c = 0x11f00;		// from KAWI SIGN CANDRABINDU
+	while (c <= 0x11f10)	// ..to KAWI LETTER O
+		charset[i++] = c++;
+	c = 0x11f12;		// from KAWI LETTER KA
+	while (c <= 0x11f3a)	// ..to KAWI VOWEL SIGN VOCALIC R
+		charset[i++] = c++;
+	c = 0x11f3e;		// from KAWI VOWEL SIGN E
+	while (c <= 0x11f5a)	// ..to KAWI SIGN NUKTA
+		charset[i++] = c++;
 // 11FB0..11FBF; Lisu Supplement
 	charset[i++] = 0x11fb0;	// LISU LETTER YHA
 // 11FC0..11FFF; Tamil Supplement
@@ -1923,18 +2019,30 @@ void init()
 	c = 0x12480;		// from CUNEIFORM SIGN AB TIMES NUN TENU
 	while (c <= 0x12543)	// ..to CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
 		charset[i++] = c++;
+// 12F90..12FFF; Cypro-Minoan
+	c = 0x12f90;		// from CYPRO-MINOAN SIGN CM001
+	while (c <= 0x12ff2)	// ..to CYPRO-MINOAN SIGN CM302
+		charset[i++] = c++;
 // 13000..1342F; Egyptian Hieroglyphs
 	c = 0x13000;		// from EGYPTIAN HIEROGLYPH A001
-	while (c <= 0x1342e)	// ..to EGYPTIAN HIEROGLYPH AA032
+	while (c <= 0x1342f)	// ..to EGYPTIAN HIEROGLYPH V011D
 		charset[i++] = c++;
-// 13430..1343F; Egyptian Hieroglyph Format Controls
+// 13430..1345F; Egyptian Hieroglyph Format Controls
 	c = 0x13430;		// from EGYPTIAN HIEROGLYPH VERTICAL JOINER
-	while (c <= 0x13438)	// ..to EGYPTIAN HIEROGLYPH END SEGMENT
+	while (c <= 0x13455)	// ..to EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
+		charset[i++] = c++;
+// 13460..143FF; Egyptian Hieroglyphs Extended-A
+	c = 0x13460;		// from EGYPTIAN HIEROGLYPH-13460
+	while (c <= 0x143fa)	// ..to EGYPTIAN HIEROGLYPH-143FA
 		charset[i++] = c++;
 // 14400..1467F; Anatolian Hieroglyphs
 	c = 0x14400;		// from ANATOLIAN HIEROGLYPH A001
 	while (c <= 0x14646)	// ..to ANATOLIAN HIEROGLYPH A530
 		charset[i++] = c++;
+// 16100..1613F; Gurung Khema
+	c = 0x16100;		// from GURUNG KHEMA LETTER A
+	while (c <= 0x16139)	// ..to GURUNG KHEMA DIGIT NINE
+		charset[i++] = c++;
 // 16800..16A3F; Bamum Supplement
 	c = 0x16800;		// from BAMUM LETTER PHASE-A NGKUE MFON
 	while (c <= 0x16a38)	// ..to BAMUM LETTER PHASE-F VUEQ
@@ -1948,6 +2056,13 @@ void init()
 		charset[i++] = c++;
 	charset[i++] = 0x16a6e;	// MRO DANDA
 	charset[i++] = 0x16a6f;	// MRO DOUBLE DANDA
+// 16A70..16ACF; Tangsa
+	c = 0x16a70;		// from TANGSA LETTER OZ
+	while (c <= 0x16abe)	// ..to TANGSA LETTER ZA
+		charset[i++] = c++;
+	c = 0x16ac0;		// from TANGSA DIGIT ZERO
+	while (c <= 0x16ac9)	// ..to TANGSA DIGIT NINE
+		charset[i++] = c++;
 // 16AD0..16AFF; Bassa Vah
 	c = 0x16ad0;		// from BASSA VAH LETTER ENNI
 	while (c <= 0x16aed)	// ..to BASSA VAH LETTER I
@@ -1971,6 +2086,10 @@ void init()
 	c = 0x16b7d;		// from PAHAWH HMONG CLAN SIGN TSHEEJ
 	while (c <= 0x16b8f)	// ..to PAHAWH HMONG CLAN SIGN VWJ
 		charset[i++] = c++;
+// 16D40..16D7F; Kirat Rai
+	c = 0x16d40;		// from KIRAT RAI SIGN ANUSVARA
+	while (c <= 0x16d79)	// ..to KIRAT RAI DIGIT NINE
+		charset[i++] = c++;
 // 16E40..16E9F; Medefaidrin
 	c = 0x16e40;		// from MEDEFAIDRIN CAPITAL LETTER M
 	while (c <= 0x16e9a)	// ..to MEDEFAIDRIN EXCLAMATION OH
@@ -2003,17 +2122,27 @@ void init()
 	c = 0x18b00;		// from KHITAN SMALL SCRIPT CHARACTER-18B00
 	while (c <= 0x18cd5)	// ..to KHITAN SMALL SCRIPT CHARACTER-18CD5
 		charset[i++] = c++;
-// 18D00..18D8F; Tangut Supplement
+	charset[i++] = 0x18cff;	// KHITAN SMALL SCRIPT CHARACTER-18CFF
+// 18D00..18D7F; Tangut Supplement
 	c = 0x18d00;		// from <Tangut Ideograph Supplement, First>
 	while (c <= 0x18d08)	// ..to <Tangut Ideograph Supplement, Last>
 		charset[i++] = c++;
+// 1AFF0..1AFFF; Kana Extended-B
+	c = 0x1aff0;		// from KATAKANA LETTER MINNAN TONE-2
+	while (c <= 0x1aff3)	// ..to KATAKANA LETTER MINNAN TONE-5
+		charset[i++] = c++;
+	c = 0x1aff5;		// from KATAKANA LETTER MINNAN TONE-7
+	while (c <= 0x1affb)	// ..to KATAKANA LETTER MINNAN NASALIZED TONE-5
+		charset[i++] = c++;
+	charset[i++] = 0x1affd;	// KATAKANA LETTER MINNAN NASALIZED TONE-7
+	charset[i++] = 0x1affe;	// KATAKANA LETTER MINNAN NASALIZED TONE-8
 // 1B000..1B0FF; Kana Supplement
 	c = 0x1b000;		// from KATAKANA LETTER ARCHAIC E
 	while (c <= 0x1b0ff)	// ..to HENTAIGANA LETTER RE-2
 		charset[i++] = c++;
 // 1B100..1B12F; Kana Extended-A
 	c = 0x1b100;		// from HENTAIGANA LETTER RE-3
-	while (c <= 0x1b11e)	// ..to HENTAIGANA LETTER N-MU-MO-2
+	while (c <= 0x1b122)	// ..to KATAKANA LETTER ARCHAIC WU
 		charset[i++] = c++;
 // 1B130..1B16F; Small Kana Extension
 	charset[i++] = 0x1b150;	// HIRAGANA LETTER SMALL WI
@@ -2045,6 +2174,23 @@ void init()
 	c = 0x1bca0;		// from SHORTHAND FORMAT LETTER OVERLAP
 	while (c <= 0x1bca3)	// ..to SHORTHAND FORMAT UP STEP
 		charset[i++] = c++;
+// 1CC00..1CEBF; Symbols for Legacy Computing Supplement
+	c = 0x1cc00;		// from UP-POINTING GO-KART
+	while (c <= 0x1ccf9)	// ..to OUTLINED DIGIT NINE
+		charset[i++] = c++;
+	c = 0x1cd00;		// from BLOCK OCTANT-3
+	while (c <= 0x1ceb3)	// ..to BLACK RIGHT TRIANGLE CARET
+		charset[i++] = c++;
+// 1CF00..1CFCF; Znamenny Musical Notation
+	c = 0x1cf00;		// from ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT
+	while (c <= 0x1cf2d)	// ..to ZNAMENNY COMBINING MARK KRYZH ON LEFT
+		charset[i++] = c++;
+	c = 0x1cf30;		// from ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO
+	while (c <= 0x1cf46)	// ..to ZNAMENNY PRIZNAK MODIFIER ROG
+		charset[i++] = c++;
+	c = 0x1cf50;		// from ZNAMENNY NEUME KRYUK
+	while (c <= 0x1cfc3)	// ..to ZNAMENNY NEUME PAUK
+		charset[i++] = c++;
 // 1D000..1D0FF; Byzantine Musical Symbols
 	c = 0x1d000;		// from BYZANTINE MUSICAL SYMBOL PSILI
 	while (c <= 0x1d0f5)	// ..to BYZANTINE MUSICAL SYMBOL GORGON NEO KATO
@@ -2054,12 +2200,16 @@ void init()
 	while (c <= 0x1d126)	// ..to MUSICAL SYMBOL DRUM CLEF-2
 		charset[i++] = c++;
 	c = 0x1d129;		// from MUSICAL SYMBOL MULTIPLE MEASURE REST
-	while (c <= 0x1d1e8)	// ..to MUSICAL SYMBOL KIEVAN FLAT SIGN
+	while (c <= 0x1d1ea)	// ..to MUSICAL SYMBOL KORON
 		charset[i++] = c++;
 // 1D200..1D24F; Ancient Greek Musical Notation
 	c = 0x1d200;		// from GREEK VOCAL NOTATION SYMBOL-1
 	while (c <= 0x1d245)	// ..to GREEK MUSICAL LEIMMA
 		charset[i++] = c++;
+// 1D2C0..1D2DF; Kaktovik Numerals
+	c = 0x1d2c0;		// from KAKTOVIK NUMERAL ZERO
+	while (c <= 0x1d2d3)	// ..to KAKTOVIK NUMERAL NINETEEN
+		charset[i++] = c++;
 // 1D2E0..1D2FF; Mayan Numerals
 	c = 0x1d2e0;		// from MAYAN NUMERAL ZERO
 	while (c <= 0x1d2f3)	// ..to MAYAN NUMERAL NINETEEN
@@ -2135,6 +2285,13 @@ void init()
 	c = 0x1daa1;		// from SIGNWRITING ROTATION MODIFIER-2
 	while (c <= 0x1daaf)	// ..to SIGNWRITING ROTATION MODIFIER-16
 		charset[i++] = c++;
+// 1DF00..1DFFF; Latin Extended-G
+	c = 0x1df00;		// from LATIN SMALL LETTER FENG DIGRAPH WITH TRILL
+	while (c <= 0x1df1e)	// ..to LATIN SMALL LETTER S WITH CURL
+		charset[i++] = c++;
+	c = 0x1df25;		// from LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK
+	while (c <= 0x1df2a)	// ..to LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
+		charset[i++] = c++;
 // 1E000..1E02F; Glagolitic Supplement
 	c = 0x1e000;		// from COMBINING GLAGOLITIC LETTER AZU
 	while (c <= 0x1e006)	// ..to COMBINING GLAGOLITIC LETTER ZHIVETE
@@ -2150,6 +2307,11 @@ void init()
 	c = 0x1e026;		// from COMBINING GLAGOLITIC LETTER YO
 	while (c <= 0x1e02a)	// ..to COMBINING GLAGOLITIC LETTER FITA
 		charset[i++] = c++;
+// 1E030..1E08F; Cyrillic Extended-D
+	c = 0x1e030;		// from MODIFIER LETTER CYRILLIC SMALL A
+	while (c <= 0x1e06d)	// ..to MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
+		charset[i++] = c++;
+	charset[i++] = 0x1e08f;	// COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 // 1E100..1E14F; Nyiakeng Puachue Hmong
 	c = 0x1e100;		// from NYIAKENG PUACHUE HMONG LETTER MA
 	while (c <= 0x1e12c)	// ..to NYIAKENG PUACHUE HMONG LETTER W
@@ -2162,11 +2324,36 @@ void init()
 		charset[i++] = c++;
 	charset[i++] = 0x1e14e;	// NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
 	charset[i++] = 0x1e14f;	// NYIAKENG PUACHUE HMONG CIRCLED CA
+// 1E290..1E2BF; Toto
+	c = 0x1e290;		// from TOTO LETTER PA
+	while (c <= 0x1e2ae)	// ..to TOTO SIGN RISING TONE
+		charset[i++] = c++;
 // 1E2C0..1E2FF; Wancho
 	c = 0x1e2c0;		// from WANCHO LETTER AA
 	while (c <= 0x1e2f9)	// ..to WANCHO DIGIT NINE
 		charset[i++] = c++;
 	charset[i++] = 0x1e2ff;	// WANCHO NGUN SIGN
+// 1E4D0..1E4FF; Nag Mundari
+	c = 0x1e4d0;		// from NAG MUNDARI LETTER O
+	while (c <= 0x1e4f9)	// ..to NAG MUNDARI DIGIT NINE
+		charset[i++] = c++;
+// 1E5D0..1E5FF; Ol Onal
+	c = 0x1e5d0;		// from OL ONAL LETTER O
+	while (c <= 0x1e5fa)	// ..to OL ONAL DIGIT NINE
+		charset[i++] = c++;
+	charset[i++] = 0x1e5ff;	// OL ONAL ABBREVIATION SIGN
+// 1E7E0..1E7FF; Ethiopic Extended-B
+	c = 0x1e7e0;		// from ETHIOPIC SYLLABLE HHYA
+	while (c <= 0x1e7e6)	// ..to ETHIOPIC SYLLABLE HHYO
+		charset[i++] = c++;
+	c = 0x1e7e8;		// from ETHIOPIC SYLLABLE GURAGE HHWA
+	while (c <= 0x1e7eb)	// ..to ETHIOPIC SYLLABLE HHWE
+		charset[i++] = c++;
+	charset[i++] = 0x1e7ed;	// ETHIOPIC SYLLABLE GURAGE MWI
+	charset[i++] = 0x1e7ee;	// ETHIOPIC SYLLABLE GURAGE MWEE
+	c = 0x1e7f0;		// from ETHIOPIC SYLLABLE GURAGE QWI
+	while (c <= 0x1e7fe)	// ..to ETHIOPIC SYLLABLE GURAGE PWEE
+		charset[i++] = c++;
 // 1E800..1E8DF; Mende Kikakui
 	c = 0x1e800;		// from MENDE KIKAKUI SYLLABLE M001 KI
 	while (c <= 0x1e8c4)	// ..to MENDE KIKAKUI SYLLABLE M060 NYON
@@ -2298,7 +2485,7 @@ void init()
 	c = 0x1f680;		// from ROCKET
 	while (c <= 0x1f6d7)	// ..to ELEVATOR
 		charset[i++] = c++;
-	c = 0x1f6e0;		// from HAMMER AND WRENCH
+	c = 0x1f6dc;		// from WIRELESS
 	while (c <= 0x1f6ec)	// ..to AIRPLANE ARRIVING
 		charset[i++] = c++;
 	c = 0x1f6f0;		// from SATELLITE
@@ -2306,15 +2493,19 @@ void init()
 		charset[i++] = c++;
 // 1F700..1F77F; Alchemical Symbols
 	c = 0x1f700;		// from ALCHEMICAL SYMBOL FOR QUINTESSENCE
-	while (c <= 0x1f773)	// ..to ALCHEMICAL SYMBOL FOR HALF OUNCE
+	while (c <= 0x1f776)	// ..to LUNAR ECLIPSE
+		charset[i++] = c++;
+	c = 0x1f77b;		// from HAUMEA
+	while (c <= 0x1f77f)	// ..to ORCUS
 		charset[i++] = c++;
 // 1F780..1F7FF; Geometric Shapes Extended
 	c = 0x1f780;		// from BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE
-	while (c <= 0x1f7d8)	// ..to NEGATIVE CIRCLED SQUARE
+	while (c <= 0x1f7d9)	// ..to NINE POINTED WHITE STAR
 		charset[i++] = c++;
 	c = 0x1f7e0;		// from LARGE ORANGE CIRCLE
 	while (c <= 0x1f7eb)	// ..to LARGE BROWN SQUARE
 		charset[i++] = c++;
+	charset[i++] = 0x1f7f0;	// HEAVY EQUALS SIGN
 // 1F800..1F8FF; Supplemental Arrows-C
 	c = 0x1f800;		// from LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD
 	while (c <= 0x1f80b)	// ..to DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
@@ -2331,16 +2522,13 @@ void init()
 	c = 0x1f890;		// from LEFTWARDS TRIANGLE ARROWHEAD
 	while (c <= 0x1f8ad)	// ..to WHITE ARROW SHAFT WIDTH TWO THIRDS
 		charset[i++] = c++;
-	charset[i++] = 0x1f8b0;	// ARROW POINTING UPWARDS THEN NORTH WEST
-	charset[i++] = 0x1f8b1;	// ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST
+	c = 0x1f8b0;		// from ARROW POINTING UPWARDS THEN NORTH WEST
+	while (c <= 0x1f8bb)	// ..to SOUTH WEST ARROW FROM BAR
+		charset[i++] = c++;
+	charset[i++] = 0x1f8c0;	// LEFTWARDS ARROW FROM DOWNWARDS ARROW
+	charset[i++] = 0x1f8c1;	// RIGHTWARDS ARROW FROM DOWNWARDS ARROW
 // 1F900..1F9FF; Supplemental Symbols and Pictographs
 	c = 0x1f900;		// from CIRCLED CROSS FORMEE WITH FOUR DOTS
-	while (c <= 0x1f978)	// ..to DISGUISED FACE
-		charset[i++] = c++;
-	c = 0x1f97a;		// from FACE WITH PLEADING EYES
-	while (c <= 0x1f9cb)	// ..to BUBBLE TEA
-		charset[i++] = c++;
-	c = 0x1f9cd;		// from STANDING PERSON
 	while (c <= 0x1f9ff)	// ..to NAZAR AMULET
 		charset[i++] = c++;
 // 1FA00..1FA6F; Chess Symbols
@@ -2352,41 +2540,37 @@ void init()
 		charset[i++] = c++;
 // 1FA70..1FAFF; Symbols and Pictographs Extended-A
 	c = 0x1fa70;		// from BALLET SHOES
-	while (c <= 0x1fa74)	// ..to THONG SANDAL
+	while (c <= 0x1fa7c)	// ..to CRUTCH
 		charset[i++] = c++;
-	charset[i++] = 0x1fa78;	// DROP OF BLOOD
-	charset[i++] = 0x1fa7a;	// STETHOSCOPE
 	c = 0x1fa80;		// from YO-YO
-	while (c <= 0x1fa86)	// ..to NESTING DOLLS
+	while (c <= 0x1fa89)	// ..to HARP
 		charset[i++] = c++;
-	c = 0x1fa90;		// from RINGED PLANET
-	while (c <= 0x1faa8)	// ..to ROCK
+	c = 0x1fa8f;		// from SHOVEL
+	while (c <= 0x1fac6)	// ..to FINGERPRINT
 		charset[i++] = c++;
-	c = 0x1fab0;		// from FLY
-	while (c <= 0x1fab6)	// ..to FEATHER
+	c = 0x1face;		// from MOOSE
+	while (c <= 0x1fadc)	// ..to ROOT VEGETABLE
 		charset[i++] = c++;
-	charset[i++] = 0x1fac0;	// ANATOMICAL HEART
-	charset[i++] = 0x1fac2;	// PEOPLE HUGGING
-	c = 0x1fad0;		// from BLUEBERRIES
-	while (c <= 0x1fad6)	// ..to TEAPOT
+	c = 0x1fadf;		// from SPLATTER
+	while (c <= 0x1fae9)	// ..to FACE WITH BAGS UNDER EYES
+		charset[i++] = c++;
+	c = 0x1faf0;		// from HAND WITH INDEX FINGER AND THUMB CROSSED
+	while (c <= 0x1faf8)	// ..to RIGHTWARDS PUSHING HAND
 		charset[i++] = c++;
 // 1FB00..1FBFF; Symbols for Legacy Computing
 	c = 0x1fb00;		// from BLOCK SEXTANT-1
 	while (c <= 0x1fb92)	// ..to UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
 		charset[i++] = c++;
 	c = 0x1fb94;		// from LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK
-	while (c <= 0x1fbca)	// ..to WHITE UP-POINTING CHEVRON
-		charset[i++] = c++;
-	c = 0x1fbf0;		// from SEGMENTED DIGIT ZERO
 	while (c <= 0x1fbf9)	// ..to SEGMENTED DIGIT NINE
 		charset[i++] = c++;
 // 20000..2A6DF; CJK Unified Ideographs Extension B
 	c = 0x20000;		// from <CJK Ideograph Extension B, First>
-	while (c <= 0x2a6dd)	// ..to <CJK Ideograph Extension B, Last>
+	while (c <= 0x2a6df)	// ..to <CJK Ideograph Extension B, Last>
 		charset[i++] = c++;
 // 2A700..2B73F; CJK Unified Ideographs Extension C
 	c = 0x2a700;		// from <CJK Ideograph Extension C, First>
-	while (c <= 0x2b734)	// ..to <CJK Ideograph Extension C, Last>
+	while (c <= 0x2b739)	// ..to <CJK Ideograph Extension C, Last>
 		charset[i++] = c++;
 // 2B740..2B81F; CJK Unified Ideographs Extension D
 	c = 0x2b740;		// from <CJK Ideograph Extension D, First>
@@ -2400,6 +2584,10 @@ void init()
 	c = 0x2ceb0;		// from <CJK Ideograph Extension F, First>
 	while (c <= 0x2ebe0)	// ..to <CJK Ideograph Extension F, Last>
 		charset[i++] = c++;
+// 2EBF0..2EE5F; CJK Unified Ideographs Extension I
+	c = 0x2ebf0;		// from <CJK Ideograph Extension I, First>
+	while (c <= 0x2ee5d)	// ..to <CJK Ideograph Extension I, Last>
+		charset[i++] = c++;
 // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
 	c = 0x2f800;		// from CJK COMPATIBILITY IDEOGRAPH-2F800
 	while (c <= 0x2fa1d)	// ..to CJK COMPATIBILITY IDEOGRAPH-2FA1D
@@ -2408,6 +2596,10 @@ void init()
 	c = 0x30000;		// from <CJK Ideograph Extension G, First>
 	while (c <= 0x3134a)	// ..to <CJK Ideograph Extension G, Last>
 		charset[i++] = c++;
+// 31350..323AF; CJK Unified Ideographs Extension H
+	c = 0x31350;		// from <CJK Ideograph Extension H, First>
+	while (c <= 0x323af)	// ..to <CJK Ideograph Extension H, Last>
+		charset[i++] = c++;
 // E0000..E007F; Tags
 	c = 0xe0020;		// from TAG SPACE
 	while (c <= 0xe007f)	// ..to CANCEL TAG

data/jtr/dynamic.conf

@@ -466,7 +466,7 @@ Test=$dynamic_1014$e463b65f14643afd970c7ea7e7efeb0f$1234567890123456789012345678
 ####################################################################
 # Dynamic type for md5(md5($p.$u).$s) for PostgreSQL 'pass the hash' weakness
 # See also dynamic_1034 for PostgreSQL MD5
-# http://www.openwall.com/lists/oss-security/2015/03/03/12
+# https://www.openwall.com/lists/oss-security/2015/03/03/12
 ####################################################################
 [List.Generic:dynamic_1015]
 Expression=md5(md5($p.$u).$s) (PostgreSQL 'pass the hash')

data/jtr/john.conf

@@ -1,6 +1,6 @@
 #
 # This file is part of John the Ripper password cracker,
-# Copyright (c) 1996-2006,2008-2013,2019 by Solar Designer
+# Copyright (c) 1996-2025 by Solar Designer and others
 #
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted.
@@ -11,8 +11,6 @@
 # license above, many source files in John the Ripper are under GPLv2.
 # For licensing terms for John the Ripper as a whole, see doc/LICENSE.
 #
-# ...with changes in the jumbo patch, by various authors
-#
 
 # The [Options] section is for general options only.
 # Note that MPI specific options have been moved
@@ -108,23 +106,35 @@ LogDateStderrFormat =
 # parsed as ESC for use in ANSI codes (like in the default)
 TerminalReset = ^[0m
 
+# If this is true, colorize some messages - such as test failures - if stdout
+# is a terminal.
+# The color codes can be redefined here if needed. The ^ character will be
+# parsed as ESC for use in ANSI escape sequences (like in the defaults here,
+# which define red for errors, green for notices and yellow for warnings).
+# Note that you don't strictly need to use ANSI sequences - other things are
+# fine too.
+# Set this to N or comment it out to disable all color stuff.
+UseColors = Y
+ColorError = ^[0;31m
+ColorNotice = ^[0;32m
+ColorWarning = ^[0;33m
+ColorEnd = ^[0m
+
 # This can be used to colorize (on screen) or otherwise emphasize (in log
-# files) output whenever a supposed administrator password gets cracked.
+# files or if stdout is not a terminal) output whenever a supposed
+# administrator password, or some other password, gets cracked.
+#
+# The colors used will be yellow for regular cracks and red for users that we
+# know or guess are admin users (including but not limited to uid 0 or 500,
+# or login 'root' or 'Administrator').
 #
 # Set this to N or comment it out to disable all "MarkAdmin" stuff.
 MarkAdminCracks = Y
+ColorAdmin = ^[0;31m
+ColorCrack = ^[0;33m
 
-# If MarkAdminCracks = Y above, the below will be used (if defined) for
-# terminal output. The default is to change color to red before the username
-# and reset to normal after it. Any "^" characters will be parsed as ESC for
-# use in ANSI codes (like in the defaults).
-# The "MarkOther" entries will make non-admin stuff brown.
-MarkAdminStart = ^[0;31m
-MarkAdminEnd = ^[0m
-MarkOtherStart = ^[0;33m
-MarkOtherEnd = ^[0m
-
-# If MarkAdminCracks = Y above, the below will be used (if defined) for logs.
+# If MarkAdminCracks = Y above, the below will be used (if defined) for logs
+# or otherwise where stdout is not a terminal.
 # This literal string will be printed after the " + Cracked: root" line.
 MarkAdminString = (ADMIN ACCOUNT)
 
@@ -173,7 +183,7 @@ SingleWordsPairMax = 6
 
 # Setting this to false stops Single mode from re-testing guessed plaintexts
 # with all other salts.  This is deprecated: Use command-line per-session
-# option --single-retest-guess=no instead.
+# option --no-single-retest-guess instead.
 SingleRetestGuessed = Y
 
 # Max recursion depth for SingleRetestGuessed, so we don't blow the stack
@@ -239,8 +249,22 @@ ShowRemainOnStatus = N
 # Write cracked passwords to the log file (default is just the user name)
 LogCrackedPasswords = N
 
+# Log per-rule statistics usable to generate re-ordered rule set with:
+#  cut -c14- john.log | grep '^Score ' | sort -rnk 2 | cut -d: -f2- | sed 's/\\/\\\\/g; s/\[/\\[/g; s/^-: //'
+# or for use on the slowest hashes:
+#  cut -c14- john.log | grep '^Score ' | sort -nk 4 | cut -d: -f2- | sed 's/\\/\\\\/g; s/\[/\\[/g; s/^-: //'
+# The "sed" invocation in these commands is to make the pre-processed rules
+# suitable for our rule preprocessor again.  It should be omitted for
+# re-ordering hashcat mode rule sets, because that mode disables the
+# preprocessor.  And yes, you cannot use these commands for re-ordering mixed
+# JtR native and hashcat mode rule sets, such as our Jumbo rule set, which
+# currently includes hashcat's best64.  That's not only because of the
+# preprocessor, but also because hashcat mode on/off would get misplaced.
+# Please note that enabling this option has some performance impact.
+PerRuleStats = N
+
 # Disable the dupe checking when loading hashes. For testing purposes only!
-# This is deprecated: Use per-session option --loader-dupecheck=no instead.
+# This is deprecated: Use per-session option --no-loader-dupe-check instead.
 NoLoaderDupeCheck = N
 
 # Default encoding for input files (ie. login/GECOS fields) and wordlists
@@ -350,6 +374,17 @@ AbortGraceTime = 30
 # This may produce some false positives if enabled, at least for SAP-B.
 SAPhalfHashes = N
 
+# Opportunistic duplicate candidate password suppressor for wordlist+rules
+[Options:Suppressor]
+# Memory allocation size in MiB per process, 0 to disable unless forced.
+# The default is 256 MiB, the maximum is just below 256 GiB (on 64-bit).
+Size = 256
+
+# Whether to lock the oldest half of entries as write-once (and only ever
+# update the other half).  Empirically, this often provides best results,
+# but it can also backfire.  The default is yes.
+LockHalf = Y
+
 [Options:CPUtune]
 # If preset is given, use it and skip autotune (NOTE: non-intel archs will
 # currently ignore this option and always autotune)
@@ -395,7 +430,22 @@ AbortTemperature = 95
 # interpret as intent to keep the GPU temperature around the limit.
 SleepOnTemperature = 1
 
+# Enable a workaround for busy-waits, introducing calls to usleep(3).  This
+# currently only applies to some formats on NVIDIA GPUs under Linux.
+AvoidBusyWait = Y
+
 [Options:OpenCL]
+# Mute buggy nvidia warnings about kernel overriding noinline
+# attribute. Even with this set, they will show at "debug verbosity"
+# as in --verbose:6.
+MuteBogusWarnings = Y
+
+# Add ptxas info (-cl-nv-verbose) to build options for nvidia
+NvidiaShowPtxas = Y
+
+# Show runtime build warnings regardless of verbosity.
+AlwaysShowBuildWarnings = N
+
 # Set default OpenCL device(s). Command line option will override this.
 # If not set, we will search for a GPU or fall-back to the most
 # powerful device.  Syntax is same as --device option.
@@ -722,7 +772,6 @@ DefaultCharset =
 -c /?d @?d >3 M [lc] Q Az"123" <+
 /?d @?d >2 al d
 -c /?d @?d >2 al M [lc] Q d
-(?a )?d /?d a0 'p Xpz0
 )?a (?d /?a a0 'p Xpz0
 
 # "Single crack" mode rules
@@ -730,11 +779,17 @@ DefaultCharset =
 # Simple rules come first...
 :
 -s x**
+<* $1
 -c (?a c Q
--c l Q
+(?a )?d /?d a0 'p Xpz0
+<* $[230754968]
+-c [lu] Q
 -s-c x** /?u l
-# These were not included in crackers I've seen, but are pretty efficient,
-# so I include them near the beginning
+Az"123" <+
+r c
+-c )?a r l
+<* $!
+<* p
 -<6 >6 '6
 -<7 >7 '7 l
 -<6 -c >6 '6 /?u l
@@ -746,12 +801,9 @@ DefaultCharset =
 # Weird order, eh? Can't do anything about it, the order is based on the
 # number of successful cracks...
 <* d
-r c
 -c <* (?a d c
 -<5 -c >5 '5 /?u l
--c u Q
--c )?a r l
--[:c] <* !?A \p1[lc] p
+-c <* [lc] Q p
 -c <* c Q d
 -<7 -c >7 '7 /?u
 -<4 >4 '4 l
@@ -779,51 +831,49 @@ r c
 # >4 x32 /?u l ... >9 x37 /?u l
 -c >[4-9] x3\p[2-7] /?u l
 # Now to the suffix stuff...
-<* l $[1-9!0a-rt-z"-/:-@\[-`{-~]
--c <* (?a c $[1-9!0a-rt-z"-/:-@\[-`{-~]
--[:c] <* !?A (?\p1[za] \p1[lc] $s M 'l p Q X0z0 'l $s
--[:c] <* /?A (?\p1[za] \p1[lc] $s
-<* l r $[1-9!]
--c <* /?a u $[1-9!]
--[:c] <- (?\p1[za] \p1[lc] Az"'s"
--[:c] <- (?\p1[za] \p1[lc] Az"!!"
--[:c] (?\p1[za] \p1[lc] $! <- Az"!!"
+-c <* [lc] Q $[1230754968!]
+-\r[:cc] <* \p1[:lc] \r\p1[:QQ] $[a-rt-z"-/:-@\[-`{-~]
+-[:c] <* (?\p1[za] \p1[lc] $s M 'l p Q X0z0 'l $s
+<* l r $[1230754968!]
+-c <* /?a u $[1230754968!]
+-\r[:cc] <- \p1[:lc] \r\p1[:QQ] Az"'s"
+-\r[:cc] <- \p1[:lc] \r\p1[:QQ] Az"!!"
+-\r[:cc] <- \p1[:lc] \r\p1[:QQ] $! <- Az"!!"
 # Removing vowels...
--[:c] /?v @?v >2 (?\p1[za] \p1[lc]
+-\r[:cc] /?v @?v >2 M \p1[:lc] \r\p1[:QQ]
 /?v @?v >2 <* d
 # crack -> cracked, crack -> cracking
-<* l [PI]
--c <* l [PI] (?a c
+-\r[:cc] <* \p1[:lc] \r\p1[:QQ] [PI]
 # mary -> marie
--[:c] <* (?\p1[za] \p1[lc] )y omi $e
+-\r[:cc] <* \p1[:lc] \r\p1[:QQ] )y omi $e
 # marie -> mary
--[:c] (?\p1[za] \p1[lc] )e \] <+ )i val1 oay
+-\r[:cc] <* \p1[:lc] \r\p1[:QQ] )e \] <+ )i val1 oay
 # The following are some 3l33t rules
--[:c] l /[aelos] s\0\p[4310$] (?\p1[za] \p1[:c]
--[:c] l /a /[elos] sa4 s\0\p[310$] (?\p1[za] \p1[:c]
--[:c] l /e /[los] se3 s\0\p[10$] (?\p1[za] \p1[:c]
--[:c] l /l /[os] sl1 s\0\p[0$] (?\p1[za] \p1[:c]
--[:c] l /o /s so0 ss$ (?\p1[za] \p1[:c]
--[:c] l /a /e /[los] sa4 se3 s\0\p[10$] (?\p1[za] \p1[:c]
--[:c] l /a /l /[os] sa4 sl1 s\0\p[0$] (?\p1[za] \p1[:c]
--[:c] l /a /o /s sa4 so0 ss$ (?\p1[za] \p1[:c]
--[:c] l /e /l /[os] se3 sl1 s\0\p[0$] (?\p1[za] \p1[:c]
--[:c] l /[el] /o /s s\0\p[31] so0 ss$ (?\p1[za] \p1[:c]
--[:c] l /a /e /l /[os] sa4 se3 sl1 s\0\p[0$] (?\p1[za] \p1[:c]
--[:c] l /a /[el] /o /s sa4 s\0\p[31] so0 ss$ (?\p1[za] \p1[:c]
--[:c] l /e /l /o /s se3 sl1 so0 ss$ (?\p1[za] \p1[:c]
--[:c] l /a /e /l /o /s sa4 se3 sl1 so0 ss$ (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /[aelos] s\0\p[4310$] (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /a /[elos] sa4 s\0\p[310$] (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /e /[los] se3 s\0\p[10$] (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /l /[os] sl1 s\0\p[0$] (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /o /s so0 ss$ (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /a /e /[los] sa4 se3 s\0\p[10$] (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /a /l /[os] sa4 sl1 s\0\p[0$] (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /a /o /s sa4 so0 ss$ (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /e /l /[os] se3 sl1 s\0\p[0$] (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /[el] /o /s s\0\p[31] so0 ss$ (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /a /e /l /[os] sa4 se3 sl1 s\0\p[0$] (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /a /[el] /o /s sa4 s\0\p[31] so0 ss$ (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /e /l /o /s se3 sl1 so0 ss$ (?\p1[za] \p1[:c]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] /a /e /l /o /s sa4 se3 sl1 so0 ss$ (?\p1[za] \p1[:c]
 # Now to the prefix stuff...
 l ^[1a-z2-90]
 -c l Q ^[A-Z]
 ^[A-Z]
 l ^["-/:-@\[-`{-~]
--[:c] <9 (?a \p1[lc] A0"[tT]he"
--[:c] <9 (?a \p1[lc] A0"[aA]my"
--[:c] <9 (?a \p1[lc] A0"[mdMD]r"
--[:c] <9 (?a \p1[lc] A0"[mdMD]r."
--[:c] <9 (?a \p1[lc] A0"__"
-<- !?A l p ^[240-9]
+-[:c] <9 (?\p1[za] \p1[lc] A0"[tT]he"
+-[:c] <9 (?\p1[za] \p1[lc] A0"[aA]my"
+-[:c] <9 (?\p1[za] \p1[lc] A0"[mdMD]r"
+-[:c] <9 (?\p1[za] \p1[lc] A0"[mdMD]r."
+-[:c] <9 (?\p1[za] \p1[lc] A0"__"
+<- l p ^[240-9]
 # Some word pair rules...
 # johnsmith -> JohnSmith, johnSmith
 -p-c (?a 2 (?a c 1 [cl]
@@ -841,8 +891,8 @@ l ^["-/:-@\[-`{-~]
 -p-[c:] 1 l 2 \p1[ur]
 -p-c 1 (?a c 2 [ur]
 # jsmith -> smithj, etc...
--[:c] (?a \p1[lc] [{}]
--[:c] (?a \p1[lc] [{}] \0
+-\r[:cc] \p1[:lc] \r\p1[:QQ] [{}]
+-\r[:cc] \p1[:lc] \r\p1[:QQ] [{}] \0
 # Toggle case...
 -c <+ )?u l Tm
 -c T0 Q M c Q l Q u Q C Q X0z0 'l
@@ -858,14 +908,11 @@ l ^["-/:-@\[-`{-~]
 =1?a \[ M c Q
 -c (?a >[1-9A-E] D\1 c
 # Inserting a dot...
--[:c] >3 (?a \p1[lc] i[12].
+-\r[:cc] >3 \p1[:lc] \r\p1[:QQ] i[12].
 # More suffix stuff...
-<- l Az"[190][0-9]"
--c <- (?a c Az"[190][0-9]"
-<- l Az"[782][0-9]"
--c <- (?a c Az"[782][0-9]"
-<* l $[A-Z]
--c <* (?a c $[A-Z]
+-\r[:cc] <- \p1[:lc] \r\p1[:QQ] Az"[190][0-9]"
+-\r[:cc] <- \p1[:lc] \r\p1[:QQ] Az"[782][0-9]"
+-\r[:cc] <* \p1[:lc] \r\p1[:QQ] $[A-Z]
 # cracking -> CRACKiNG
 -c u /I sIi
 # Crack96 -> cRACK96
@@ -880,33 +927,32 @@ l Q [RL]
 -c (?a c Q [RL]
 :[RL] \0 Q
 # Both prefixing and suffixing...
-<- l ^[1!@#$%^&*\-=_+.?|:'"] $\1
+<- l ^[10-9!@#$%^&*\-=_+.?|:'"] $\0
 <- l ^[({[<] $\p[)}\]>]
 # The rest of two-digit suffix stuff, less common numbers...
-<- l Az"[63-5][0-9]"
--c <- (?a c Az"[63-5][0-9]"
+-\r[:cc] <- \p1[:lc] \r\p1[:QQ] Az"[63-5][0-9]"
 # Some multi-digit numbers...
--[:c] (?a \p1[lc] Az"007" <+
--[:c] (?a \p1[lc] Az"123" <+
--[:c] (?a \p1[lc] Az"[0-9]\0\0" <+
--[:c] (?a \p1[lc] Az"1234" <+
--[:c] (?a \p1[lc] Az"[0-9]\0\0\0" <+
--[:c] (?a \p1[lc] Az"12345" <+
--[:c] (?a \p1[lc] Az"[0-9]\0\0\0\0" <+
--[:c] (?a \p1[lc] Az"123456" <+
--[:c] (?a \p1[lc] Az"[0-9]\0\0\0\0\0" <+
+-c [lc] Q Az"123" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"007" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"[0-9]\0\0" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"1234" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"[0-9]\0\0\0" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"12345" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"[0-9]\0\0\0\0" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"123456" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"[0-9]\0\0\0\0\0" <+
 # Some [birth] years...
-l Az"19[7-96-0]" <+ >-
-l Az"20[012]" <+ >-
-l Az"19[7-9][0-9]" <+
-l Az"20[012][0-9]" <+
-l Az"19[6-0][9-0]" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"19[7-96-0]" <+ >-
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"20[012]" <+ >-
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"19[7-9][0-9]" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"20[012][0-9]" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"19[6-0][9-0]" <+
 
 [List.Rules:Extra]
-# Insert/overstrike some characters...
-!?A >[1-6] l i\0[a-z]
-!?A l o0[a-z]
-!?A >[1-7] l o\0[a-z]
+# Overstrike/insert some characters...
+o0[a-z10-9A-Z] Q
+>[1-7] o\0[a-z10-9_@.\-#!] Q
+>[1-6] i\0[a-z10-9_@.\-# ]
 # Toggle case everywhere (up to length 8), assuming that certain case
 # combinations were already tried.
 -c T1 Q M T0 Q
@@ -917,13 +963,20 @@ l Az"19[6-0][9-0]" <+
 -c T6 Q M T[z0] T[z1] T[z2] T[z3] T[z4] T[z5] Q
 -c T7 Q M T[z0] T[z1] T[z2] T[z3] T[z4] T[z5] T[z6] Q
 # Very slow stuff...
-l Az"[1-90][0-9][0-9]" <+
--c (?a c Az"[1-90][0-9][0-9]" <+
+-\r[:cc] \p1[:lc] \r\p1[:QQ] Az"[1-90][0-9][0-9]" <+
 <[\-9] l A\p[z0]"[a-z][a-z]"
+<- l ^[A-Z] $\0
 <- l ^[a-z] $[a-z]
 
-# Wordlist mode rules
+.include <rules-by-score.conf>
+.include <rules-by-rate.conf>
+
+# New default wordlist mode rules
 [List.Rules:Wordlist]
+.include [List.Rules:Best-by-score]
+
+# Former default wordlist mode rules, now usable to enforce a policy
+[List.Rules:Policy]
 # Try words as they are
 :
 # Lowercase every pure alphanumeric word
@@ -1094,39 +1147,78 @@ s[ ][,&+*!'$/?:=#~] Q
 :
 ->F -<F >F 'F
 
-# Rules from Hash Runner 2014
+# Overstrike/insert rules originally from Hash Runner 2014
+
+# Overstrike any one character
 [List.Rules:o1]
-# o[0-9A-Z][ -~]
+# Trivial
+#o[0-9A-Z][ -~]
+# Optimized
 ->\r[1-9A-ZZ] >\p[0-9A-Z] o\0[ -~] Q
 
+# Overstrike any two characters
 [List.Rules:o2]
-# o[0-9A-E][ -~] Q M o[0-9A-E][ -~] Q
-->[1-9A-F] ->[1-9A-F] >\p1[0-9A-E] >\p2[0-9A-E] o\3[ -~] Q M o\4[ -~] Q
-
-[List.Rules:o3]
-# o[0-9][ -~] Q M o[0-9][ -~] Q M o[0-9][ -~] Q
-->[1-9A] ->[1-9A] ->[1-9A] >\p1[0-9] >\p2[0-9] >\p3[0-9] o\4[ -~] Q M o\5[ -~] Q M o\6[ -~] Q
+# Simple
+#o[0-9A-E][ -~] Q M o[0-9A-E][ -~] Q
+# Optimized, assumes we also run o1 separately if needed
+#->[1-9A-F] ->[2-9A-F] >\p1[0-9A-E] >\p2[1-9A-E] o\3[ -~] Q M o\4[ -~] Q
+# Optimized further, same assumption
+->[2-9A-F] >\p[1-9A-E] o0[ -~] Q M o\2[ -~] Q
+->[3-9A-F] >\p[2-9A-E] o1[ -~] Q M o\2[ -~] Q
+->[4-9A-F] >\p[3-9A-E] o2[ -~] Q M o\2[ -~] Q
+->[5-9A-F] >\p[4-9A-E] o3[ -~] Q M o\2[ -~] Q
+->[6-9A-F] >\p[5-9A-E] o4[ -~] Q M o\2[ -~] Q
+->[7-9A-F] >\p[6-9A-E] o5[ -~] Q M o\2[ -~] Q
+->[8-9A-F] >\p[7-9A-E] o6[ -~] Q M o\2[ -~] Q
+->[9A-F] >\p[8-9A-E] o7[ -~] Q M o\2[ -~] Q
+->[A-F] >\p[9A-E] o8[ -~] Q M o\2[ -~] Q
+->[B-F] >\p[A-E] o9[ -~] Q M o\2[ -~] Q
+->[C-F] >\p[B-E] oA[ -~] Q M o\2[ -~] Q
+->[D-F] >\p[C-E] oB[ -~] Q M o\2[ -~] Q
+->[E-F] >\p[D-E] oC[ -~] Q M o\2[ -~] Q
+->F >E oD[ -~] Q M oE[ -~] Q
 
+# Overstrike any one or two characters
 [List.Rules:o]
 .include [List.Rules:o1]
 .include [List.Rules:o2]
 
+# Insert any one character
 [List.Rules:i1]
-# i[0-9A-Z][ -~]
+# Trivial
+#i[0-9A-Z][ -~]
+# Optimized
 ->\r[2-9A-ZZZ] >\p1[0-9A-Z] i\0[ -~]
 
+# Insert any two characters
 [List.Rules:i2]
-# i[0-9A-E][ -~] i[0-9A-E][ -~]
-->[2-9A-G] ->[2-9A-G] >\p1[0-9A-E] >\p2[0-9A-E] i\3[ -~] i\4[ -~]
-
-[List.Rules:i3]
-# i[0-9][ -~] i[0-9][ -~] i[0-9][ -~]
-->[4-9A-D] ->[4-9A-D] ->[4-9A-D] >\p1[0-9] >\p2[0-9] >\p3[0-9] i\4[ -~] i\5[ -~] i\6[ -~]
+# Trivial
+#i[0-9A-E][ -~] i[0-9A-E][ -~]
+# Optimized
+#->[2-9A-G] ->[2-9A-G] i\p1[0-9A-E][ -~] >\3 >\p2[0-9A-E] i\p2[1-9A-F][ -~]
+# Optimized further
+->[2-9A-G] i0[ -~] >\p1[0-9A-E] i\p1[1-9A-F][ -~]
+->[3-9A-G] i1[ -~] >\p1[1-9A-E] i\p1[2-9A-F][ -~]
+->[4-9A-G] i2[ -~] >\p1[2-9A-E] i\p1[3-9A-F][ -~]
+->[5-9A-G] i3[ -~] >\p1[3-9A-E] i\p1[4-9A-F][ -~]
+->[6-9A-G] i4[ -~] >\p1[4-9A-E] i\p1[5-9A-F][ -~]
+->[7-9A-G] i5[ -~] >\p1[5-9A-E] i\p1[6-9A-F][ -~]
+->[8-9A-G] i6[ -~] >\p1[6-9A-E] i\p1[7-9A-F][ -~]
+->[9A-G] i7[ -~] >\p1[7-9A-E] i\p1[8-9A-F][ -~]
+->[A-G] i8[ -~] >\p1[8-9A-E] i\p1[9A-F][ -~]
+->[B-G] i9[ -~] >\p1[9A-E] i\p1[A-F][ -~]
+->[C-G] iA[ -~] >\p1[A-E] i\p1[B-F][ -~]
+->[D-G] iB[ -~] >\p1[B-E] i\p1[C-F][ -~]
+->[E-G] iC[ -~] >\p1[C-E] i\p1[D-F][ -~]
+->[F-G] iD[ -~] >\p1[D-E] i\p1[E-F][ -~]
+->G iE[ -~] >E iF[ -~]
 
+# Insert any one or two characters
 [List.Rules:i]
 .include [List.Rules:i1]
 .include [List.Rules:i2]
 
+# Overstrike or insert any one or two characters
 [List.Rules:oi]
 .include [List.Rules:o1]
 .include [List.Rules:i1]
@@ -1197,6 +1289,24 @@ a0 /?D l sa2 sb2 sc2 sd3 se3 sf3 sg4 sh4 si4 sj5 sk5 sl5 sm6 sn6 so6 sp7 sq7 sr7
 [List.Rules:passphrase-rule2]
 .include <rules/passphrase-rule2.rule>
 
+# These rules are an optimized (large) subset of the hashcat rules
+# https://notsosecure.com/one-rule-to-rule-them-all
+# https://github.com/NotSoSecure/password_cracking_rules
+[List.Rules:OneRuleToRuleThemAll]
+!! hashcat logic ON
+.include <rules/OneRuleToRuleThemAll.rule>
+!! hashcat logic OFF
+
+# These rules are an optimized version of OneRuleToRuleThemAll with removal of
+# rules that were effectively duplicate as well as some that were ineffective.
+# This cracks almost all of the same passwords in ~5% fewer rules.
+# https://in.security/2023/01/10/oneruletorulethemstill-new-and-improved/
+# https://github.com/stealthsploit/OneRuleToRuleThemStill
+[List.Rules:OneRuleToRuleThemStill]
+!! hashcat logic ON
+.include <rules/OneRuleToRuleThemStill.rule>
+!! hashcat logic OFF
+
 # Default Loopback mode rules.
 [List.Rules:Loopback]
 .include [List.Rules:ShiftToggle]
@@ -1219,8 +1329,7 @@ b1 ]
 # For Wordlist mode and very fast hashes
 [List.Rules:Jumbo]
 .include [List.Rules:Single-Extra]
-.include [List.Rules:Wordlist]
-.include [List.Rules:ShiftToggle]
+.include [List.Rules:Policy]
 .include [List.Rules:Multiword]
 .include [List.Rules:best64]
 .include [List.Rules:UnicodeSubstitution]
@@ -1233,9 +1342,12 @@ b1 ]
 # ridiculous quality and lack optimizations - you have been warned.
 [List.Rules:All]
 .include [List.Rules:Jumbo]
-.include [List.Rules:KoreLogic]
+.include [List.Rules:OneRuleToRuleThemStill]
 .include [List.Rules:T9]
 .include [List.Rules:hashcat]
+.include [List.Rules:ShiftToggle]
+.include [List.Rules:oi]
+.include [List.Rules:KoreLogic]
 
 # Incremental modes
 
@@ -1717,9 +1829,9 @@ void restore()
 
 /* Global variables: current length and word */
 /* make this 'long' enough for other externs that include this one */
-/* (up to 125 bytes long) */
+/* (up to 320 bytes long) */
 
-int length, current[126], max;
+int length, current[320], max;
 
 /* this new 'type' variable, is used to tell double what character set to
  * use. It can use the original (alpha).  If type is 0 (i.e. unset), then
@@ -1872,7 +1984,7 @@ void init()
 # sections which include this External_base section.
 # The generate() function will limit the maximum length of generated
 # candidates to either the format's limit (maximum password length)
-# or to the limit specified with --stdout=LENGTH (Default: 125),
+# or to the limit specified with --stdout=LENGTH (Default: 319),
 # thus avoiding duplicate candidates for formats with limited maximum
 # passwortd length.
 # The comparison of the current length and the limit is only done
@@ -1898,7 +2010,7 @@ void generate()
 	c = minc;
 
 	if (++length > maxlength)
-		c = 0; // Will NUL out the next "word" and thus terminate
+		length = 0; // Will NUL out the next "word" and thus terminate
 }
 
 # Try strings of repeated characters (range: space - 0xff).
@@ -1982,7 +2094,7 @@ void init()
 #
 # The generate() function will limit the maximum length of generated
 # candidates to either the format's limit (maximum password length)
-# or to the limit specified with --stdout=LENGTH (Default: 125),
+# or to the limit specified with --stdout=LENGTH (Default: 319),
 # thus avoiding duplicate candidates for formats with limited maximum
 # passwortd length.
 # The comparison of the current length and the limit is only done
@@ -2487,6 +2599,12 @@ void init()
 		}
 	}
 
+	// Must fit in id[] array
+	if (minlength > 15)
+		minlength = 15;
+	if (maxlength > 15)
+		maxlength = 15;
+
 	length = 0;
 	while (length < minlength)
 		id[length++] = 0;
@@ -3791,94 +3909,232 @@ void filter()
 	status = 1;			// Print the status line
 }
 
-#
-# Reference example hybrid-mode external. same as jtr-rule: $[0-9]$[0-9]
-# this format is to be used similar to a filter, in that it requires some
-# other word generator (markov, wordlist, etc).  However, this type external
-# will get new() called with each word, and then have next() called, until
-# the word[0]=0 is seen (meaning all candidates for the base word have been
-# generated.  Prior to new() or restore(), word[] is the 'base' word.
-# if the script is able to properly resume, then it should set the global
-# variable hybrid_total to the count of candidates that will be generated
-# for this word (in new() / restore(), then in the body of restore() there
-# is a global variable set 'hybrid_resume' that was the prior number of
-# canidates generated for this base-word.  Resume should start at the NEXT
-# If the script is not able to easily resume, then simply do NOT set the
-# global hybrid_total to anything either function.  JtR will 'still' resume
-# propery, but it will do so by calling new()/next()/next().../next() until
-# back to the proper resume location.
-#
-# script changed to append a _ character before the number, each time within
-# the next() function. Done this way to better validate that -restore within
-# jtr is working properly.
-#
-[List.External:Hybrid_example]
-/* static vars for the script */
-int cnt, length, total;
+# Several hybrid external modes follow.  These are to be used on top of another
+# cracking mode and they generate multiple candidate passwords from each "word"
+# output by the other mode.
+
+# Combine words coming from another cracking mode into pairs.  This gradually
+# memorizes up to the initial 1 MB worth of words and uses them to prefix and
+# suffix each current word.
+# Known limitations:
+# 1. --restore of interrupted session does not work right (no opportunity to
+# re-memorize the other mode's skipped words), so do not use it.
+# 2. The progress indicator and ETA are too optimistic (they assume linear
+# progress through the input stream, but complexity within 1 MB is quadratic).
+# Example usage: --wordlist --external=combinator --rules-stack=phrase
+[List.External:Combinator]
+int separator;
+int words[1000000], size;
+int base[160], base_size, base_length, swap, p, q;
 
 void init()
 {
-	/* in this simple example, we always generate 100 candidates per word */
-	total = 100;/* this is a VERY simple example */
+	separator = ' '; // Set to 0 for no separators
+
+	size = 1000000; // Must not exceed size of words array
+	base_size = 160; // Must not exceed size of base array, nor (319-1)/2+1
+
+	if (req_maxlen && base_size > req_maxlen + 1)
+		base_size = req_maxlen + 1;
+	q = 0;
 }
 
-/* new word */
 void new()
 {
-	/* get the word length) */
-	length = 0; while (word[length++]) ; --length;
+	swap = p = 0;
 
-	/*
-	 * If this was a more complex script, we would compute total candidates
-	 * at this location, if we can. If we can not compute total candidates
-	 * then it is likely we can not resume 'easily', so if that is the
-	 * case, we would simply set hybrid_total to -1, or do nothing, since
-	 * do_external_hybrid_crack() sets it to -1 before calling this function.
-	 */
-	 hybrid_total = total;
+/* Memorize this base word if it fits and is of right length */
+	base_length = -1;
+	while (q < size && (words[q++] = word[++base_length]))
+		continue;
+	if (q < size && base_length < base_size && base_length)
+		return;
 
-	/* Reset or counter for THIS word. */
-	cnt = 0;
-
-	/*
-	 * word will be too long to be used, or too short to be used. If so
-	 * then set hybrid_total to 0 and this entire word will be skipped.
-	 */
-	if (req_minlen > length - 2 || (req_maxlen && req_maxlen < length + 2))
-		hybrid_total = 0;
+/* Don't memorize this base word, but finish computing its length */
+	q -= base_length + 1;
+	if (word[base_length])
+		while (word[++base_length])
+			continue;
+	else if (!base_length)
+		base_length = base_size; // Skip empty words
 }
 
 void next()
 {
-	/* in this simple script, if cnt is 100, this word is DONE */
-	if (cnt == 100) {
-		word[0] = 0;
+	int i, j;
+
+	if (base_length >= base_size) {
+		word = 0;
 		return;
 	}
 
-	/* set word[] to the next candidate */
-	word[length++] = '_';
-	word[length  ] = '0' + cnt / 10;
-	word[length+1] = '0' + cnt % 10;
-	word[length+2] = 0;
-	++cnt;
+	if (swap) {
+/* Next memorized word first, separator and current base word next */
+		i = -1;
+		while (word[++i] = words[p++])
+			continue;
+		if (p >= q) {
+			word = 0;
+			return;
+		}
+		if (separator)
+			word[i++] = separator;
+		j = 0;
+		while (word[i++] = base[j++])
+			continue;
+		return;
+	}
+
+/* Current base word first, separator and next memorized word next */
+	i = base_length;
+	if (separator)
+		word[i++] = separator;
+	while (word[i++] = words[p++])
+		continue;
+	if (p >= q) {
+		p = 0;
+		swap++;
+		i = -1;
+		while (++i < base_length)
+			base[i] = word[i];
+		base[i] = 0;
+	}
 }
 
-/* Called when restoring an interrupted session */
-void restore()
+# Shuffle (try all permutations of) characters in each short input word
+[List.External:Shuffle]
+int max_length, ctz_bits, ctz_mask, ctz[0x80000]; // Max 0xa00000 for length 20
+int length, base[0x20], id[0x20], unseen[0x20], is_dup[0x100], c2mask[0x100];
+
+void init()
 {
-	int i;
+	max_length = 10; // ctz array size of 0x80000 is good up to length 16
 
-	length = 0; while (word[length++]) ; --length;
-
-	/* for this simple script, simply setting cnt resumes */
-	cnt = hybrid_resume + 1; if (cnt > 100) cnt=100;
+	/* Prepare a count trailing zero table */
+	int i, j, mask;
+	ctz_mask = (1 << (ctz_bits = max_length - 1)) - 1;
 	i = 0;
-	while (i++ < cnt) word[length++] = '_';
-	word[length] = 0;
+	while (i++ < ctz_bits) {
+		j = 0;
+		while (j <= ctz_mask)
+			j += 1 << (ctz[j] = i);
+	}
+	/* followed by its revisions for skipping some bits */
+	while ((i = j >> ctz_bits) < max_length) {
+		mask = j & ctz_mask;
+		while (i--)
+			mask &= mask - 1;
+		ctz[j++] = ctz[mask];
+	}
+}
 
-	/* tell john that we have properly 'resumed', by setting a 'proper' total */
-	hybrid_total = total;
+void new()
+{
+	int c, i;
+
+	length = i = -1;
+	while (c = word[++length]) {
+		if (length > max_length)
+			return;
+		c2mask[base[length] = c] = id[length] = 0;
+	}
+	while (c = word[++i]) {
+		is_dup[c] = c2mask[c];
+		c2mask[c] |= 1 << i;
+	}
+
+	unseen = 0;
+}
+
+void next()
+{
+	int prev_unseen, i, j;
+
+	if ((i = length - 1) < max_length)
+	while (i--) {
+		if (++id[i] >= length - i) {
+			id[i] = 0;
+			continue;
+		}
+
+		if (unseen)
+			prev_unseen = unseen[i];
+		else
+			unseen[i = 0] = prev_unseen = ctz_mask;
+		while (i < length) {
+			/* Skip id[i] previously unseen char indices */
+			/* Take that char and see if it's unique */
+			if (is_dup[word[i] = base[j = ctz[prev_unseen | (id[i] << ctz_bits)]]])
+				if (c2mask[word[i]] & prev_unseen & ((1 << j) - 1))
+					break; /* Dupe in wrong order */
+			unseen[++i] = prev_unseen &= ~(1 << j);
+		}
+
+		if (i >= length) /* Not a dupe */
+			return;
+
+		/* Next loop ++id[i] will skip the dupe char in i's position */
+		i++;
+	}
+
+	word = 0;
+}
+
+# Simplified or reference version of the above, same output much slower
+[List.External:Shuffle-simple]
+int max_length, length, base[320], id[320], jd[320];
+
+void init()
+{
+	max_length = 10; // Our usage of bitmasks is good up to length 32
+}
+
+void new()
+{
+	length = 0;
+	while (base[length] = word[length])
+		id[length++] = 0;
+}
+
+void next()
+{
+	int unseen, i, j, k;
+
+	if ((i = length) <= max_length)
+	while (i--) {
+		if (++id[i] >= length - i) {
+			id[i] = 0;
+			continue;
+		}
+
+		i = unseen = -1;
+		while (++i < length) {
+			/* Skip id[i] previously unseen char indices, count */
+			j = -1;
+			k = id[i];
+			while (k >= 0)
+				if (unseen & (1 << ++j))
+					k--;
+			/* Take that char */
+			word[k = i] = base[jd[i] = j];
+			/* Same chars must only appear in one order */
+			while (k--)
+				if (word[k] == word[i])
+					break;
+			if (k >= 0)
+				if (jd[k] >= j) /* Wrong order */
+					break;
+			unseen &= ~(1 << j);
+		}
+
+		if (i >= length) /* Not a dupe */
+			return;
+
+		/* Next loop ++id[i] will skip the dupe char in i's position */
+		i++;
+	}
+
+	word = 0;
 }
 
 # External hybrid 'leet code
@@ -3896,11 +4152,11 @@ void restore()
  *   t -> t7
  */
 
-int rotor[626]; /* max length input is 125 bytes [125*5+1]; */
-int rotors[125];
-int rotor_ptr[125];
-int rotor_idx[125];
-int rotor_cnt[125];
+int rotor[1596]; /* max length input is 319 bytes [319*5+1] */
+int rotors[319];
+int rotor_ptr[319];
+int rotor_idx[319];
+int rotor_cnt[319];
 int current_word_count;
 int max_mangle; /* controls how many bytes we run through our 'leet' code */
 int max_mangle_letters;
@@ -4011,11 +4267,11 @@ void next()
 # Shared base code for External hybrid CaSE and Wordcase mutation code
 [List.External_base:Case]
 
-int rotor[251]; /* max length input is 125 bytes [125*5+1]; */
-int rotors[125];
-int rotor_ptr[125];
-int rotor_idx[125];
-int rotor_cnt[125];
+int rotor[639]; /* max length input is 319 bytes [319*2+1] */
+int rotors[319];
+int rotor_ptr[319];
+int rotor_idx[319];
+int rotor_cnt[319];
 int current_word_count;
 int max_mangle; /* controls how many bytes we run through our 'leet' code */
 int original_word; /* if set to 1 then we start with original word. If 0, then start with first mangled word */

data/jtr/repeats16.conf

@@ -1,11 +1,11 @@
-# This software is Copyright (c) 2012-2020 magnum, and it is hereby
+# This software is Copyright (c) 2012-2024 magnum, and it is hereby
 # released to the general public under the following terms:
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted.
 #
-# Try strings of repeated characters, Unicode (version 13) BMP version
+# Try strings of repeated characters, Unicode (version 16) BMP version
 #
-# Number of candidates = 55,387 x max-length
+# Number of candidates = 55,537 x max-length
 #
 # Note that these modes will handle --max-len differently than normal: They
 # will consider number of characters as opposed to number of bytes. This
@@ -18,7 +18,7 @@
 
 [List.External:Repeats16]
 int minlength, maxlength, maxc, length, c;
-int charset[0x10000];
+int charset[0xd900];
 
 void init()
 {
@@ -39,7 +39,7 @@ void init()
 
 /*
  * This defines the character set. This is auto-generated from UnicodeData.txt
- * and we skip control characters.
+ * of Unicode 16.0.0 and we skip control characters.
  */
 	i = 0;
 // 0000..007F; Basic Latin
@@ -115,9 +115,6 @@ void init()
 		charset[i++] = c++;
 // 0600..06FF; Arabic
 	c = 0x600;		// from ARABIC NUMBER SIGN
-	while (c <= 0x61c)	// ..to ARABIC LETTER MARK
-		charset[i++] = c++;
-	c = 0x61e;		// from ARABIC TRIPLE DOT PUNCTUATION MARK
 	while (c <= 0x6ff)	// ..to ARABIC LETTER HEH WITH INVERTED V
 		charset[i++] = c++;
 // 0700..074F; Syriac
@@ -159,14 +156,17 @@ void init()
 	c = 0x860;		// from SYRIAC LETTER MALAYALAM NGA
 	while (c <= 0x86a)	// ..to SYRIAC LETTER MALAYALAM SSA
 		charset[i++] = c++;
+// 0870..089F; Arabic Extended-B
+	c = 0x870;		// from ARABIC LETTER ALEF WITH ATTACHED FATHA
+	while (c <= 0x88e)	// ..to ARABIC VERTICAL TAIL
+		charset[i++] = c++;
+	charset[i++] = 0x890;	// ARABIC POUND MARK ABOVE
+	charset[i++] = 0x891;	// ARABIC PIASTRE MARK ABOVE
+	c = 0x897;		// from ARABIC PEPET
+	while (c <= 0x89f)	// ..to ARABIC HALF MADDA OVER MADDA
+		charset[i++] = c++;
 // 08A0..08FF; Arabic Extended-A
 	c = 0x8a0;		// from ARABIC LETTER BEH WITH SMALL V BELOW
-	while (c <= 0x8b4)	// ..to ARABIC LETTER KAF WITH DOT BELOW
-		charset[i++] = c++;
-	c = 0x8b6;		// from ARABIC LETTER BEH WITH SMALL MEEM ABOVE
-	while (c <= 0x8c7)	// ..to ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
-		charset[i++] = c++;
-	c = 0x8d3;		// from ARABIC SMALL LOW WAW
 	while (c <= 0x8ff)	// ..to ARABIC MARK SIDEWAYS NOON GHUNNA
 		charset[i++] = c++;
 // 0900..097F; Devanagari
@@ -356,7 +356,7 @@ void init()
 	c = 0xc2a;		// from TELUGU LETTER PA
 	while (c <= 0xc39)	// ..to TELUGU LETTER HA
 		charset[i++] = c++;
-	c = 0xc3d;		// from TELUGU SIGN AVAGRAHA
+	c = 0xc3c;		// from TELUGU SIGN NUKTA
 	while (c <= 0xc44)	// ..to TELUGU VOWEL SIGN VOCALIC RR
 		charset[i++] = c++;
 	charset[i++] = 0xc46;	// TELUGU VOWEL SIGN E
@@ -402,6 +402,8 @@ void init()
 		charset[i++] = c++;
 	charset[i++] = 0xcd5;	// KANNADA LENGTH MARK
 	charset[i++] = 0xcd6;	// KANNADA AI LENGTH MARK
+	charset[i++] = 0xcdd;	// KANNADA LETTER NAKAARA POLLU
+	charset[i++] = 0xcde;	// KANNADA LETTER FA
 	c = 0xce0;		// from KANNADA LETTER VOCALIC RR
 	while (c <= 0xce3)	// ..to KANNADA VOWEL SIGN VOCALIC LL
 		charset[i++] = c++;
@@ -409,7 +411,7 @@ void init()
 	while (c <= 0xcef)	// ..to KANNADA DIGIT NINE
 		charset[i++] = c++;
 	charset[i++] = 0xcf1;	// KANNADA SIGN JIHVAMULIYA
-	charset[i++] = 0xcf2;	// KANNADA SIGN UPADHMANIYA
+	charset[i++] = 0xcf3;	// KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 // 0D00..0D7F; Malayalam
 	c = 0xd00;		// from MALAYALAM SIGN COMBINING ANUSVARA ABOVE
 	while (c <= 0xd0c)	// ..to MALAYALAM LETTER VOCALIC L
@@ -479,7 +481,7 @@ void init()
 	while (c <= 0xec4)	// ..to LAO VOWEL SIGN AI
 		charset[i++] = c++;
 	c = 0xec8;		// from LAO TONE MAI EK
-	while (c <= 0xecd)	// ..to LAO NIGGAHITA
+	while (c <= 0xece)	// ..to LAO YAMAKKAN
 		charset[i++] = c++;
 	c = 0xed0;		// from LAO DIGIT ZERO
 	while (c <= 0xed9)	// ..to LAO DIGIT NINE
@@ -592,11 +594,9 @@ void init()
 		charset[i++] = c++;
 // 1700..171F; Tagalog
 	c = 0x1700;		// from TAGALOG LETTER A
-	while (c <= 0x170c)	// ..to TAGALOG LETTER YA
-		charset[i++] = c++;
-	c = 0x170e;		// from TAGALOG LETTER LA
-	while (c <= 0x1714)	// ..to TAGALOG SIGN VIRAMA
+	while (c <= 0x1715)	// ..to TAGALOG SIGN PAMUDPOD
 		charset[i++] = c++;
+	charset[i++] = 0x171f;	// TAGALOG LETTER ARCHAIC RA
 // 1720..173F; Hanunoo
 	c = 0x1720;		// from HANUNOO LETTER A
 	while (c <= 0x1736)	// ..to PHILIPPINE DOUBLE PUNCTUATION
@@ -625,9 +625,6 @@ void init()
 		charset[i++] = c++;
 // 1800..18AF; Mongolian
 	c = 0x1800;		// from MONGOLIAN BIRGA
-	while (c <= 0x180e)	// ..to MONGOLIAN VOWEL SEPARATOR
-		charset[i++] = c++;
-	c = 0x1810;		// from MONGOLIAN DIGIT ZERO
 	while (c <= 0x1819)	// ..to MONGOLIAN DIGIT NINE
 		charset[i++] = c++;
 	c = 0x1820;		// from MONGOLIAN LETTER A
@@ -700,14 +697,14 @@ void init()
 		charset[i++] = c++;
 // 1AB0..1AFF; Combining Diacritical Marks Extended
 	c = 0x1ab0;		// from COMBINING DOUBLED CIRCUMFLEX ACCENT
-	while (c <= 0x1ac0)	// ..to COMBINING LATIN SMALL LETTER TURNED W BELOW
+	while (c <= 0x1ace)	// ..to COMBINING LATIN SMALL LETTER INSULAR T
 		charset[i++] = c++;
 // 1B00..1B7F; Balinese
 	c = 0x1b00;		// from BALINESE SIGN ULU RICEM
-	while (c <= 0x1b4b)	// ..to BALINESE LETTER ASYURA SASAK
+	while (c <= 0x1b4c)	// ..to BALINESE LETTER ARCHAIC JNYA
 		charset[i++] = c++;
-	c = 0x1b50;		// from BALINESE DIGIT ZERO
-	while (c <= 0x1b7c)	// ..to BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING
+	c = 0x1b4e;		// from BALINESE INVERTED CARIK SIKI
+	while (c <= 0x1b7f)	// ..to BALINESE PANTI BAWAK
 		charset[i++] = c++;
 // 1B80..1BBF; Sundanese
 	c = 0x1b80;		// from SUNDANESE SIGN PANYECEK
@@ -735,7 +732,7 @@ void init()
 		charset[i++] = c++;
 // 1C80..1C8F; Cyrillic Extended-C
 	c = 0x1c80;		// from CYRILLIC SMALL LETTER ROUNDED VE
-	while (c <= 0x1c88)	// ..to CYRILLIC SMALL LETTER UNBLENDED UK
+	while (c <= 0x1c8a)	// ..to CYRILLIC SMALL LETTER TJE
 		charset[i++] = c++;
 // 1C90..1CBF; Georgian Extended
 	c = 0x1c90;		// from GEORGIAN MTAVRULI CAPITAL LETTER AN
@@ -761,9 +758,6 @@ void init()
 		charset[i++] = c++;
 // 1DC0..1DFF; Combining Diacritical Marks Supplement
 	c = 0x1dc0;		// from COMBINING DOTTED GRAVE ACCENT
-	while (c <= 0x1df9)	// ..to COMBINING WIDE INVERTED BRIDGE BELOW
-		charset[i++] = c++;
-	c = 0x1dfb;		// from COMBINING DELETION MARK
 	while (c <= 0x1dff)	// ..to COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
 		charset[i++] = c++;
 // 1E00..1EFF; Latin Extended Additional
@@ -827,7 +821,7 @@ void init()
 		charset[i++] = c++;
 // 20A0..20CF; Currency Symbols
 	c = 0x20a0;		// from EURO-CURRENCY SIGN
-	while (c <= 0x20bf)	// ..to BITCOIN SIGN
+	while (c <= 0x20c0)	// ..to SOM SIGN
 		charset[i++] = c++;
 // 20D0..20FF; Combining Diacritical Marks for Symbols
 	c = 0x20d0;		// from COMBINING LEFT HARPOON ABOVE
@@ -855,7 +849,7 @@ void init()
 		charset[i++] = c++;
 // 2400..243F; Control Pictures
 	c = 0x2400;		// from SYMBOL FOR NULL
-	while (c <= 0x2426)	// ..to SYMBOL FOR SUBSTITUTE FORM TWO
+	while (c <= 0x2429)	// ..to SYMBOL FOR DELETE MEDIUM SHADE FORM
 		charset[i++] = c++;
 // 2440..245F; Optical Character Recognition
 	c = 0x2440;		// from OCR HOOK
@@ -921,10 +915,7 @@ void init()
 		charset[i++] = c++;
 // 2C00..2C5F; Glagolitic
 	c = 0x2c00;		// from GLAGOLITIC CAPITAL LETTER AZU
-	while (c <= 0x2c2e)	// ..to GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
-		charset[i++] = c++;
-	c = 0x2c30;		// from GLAGOLITIC SMALL LETTER AZU
-	while (c <= 0x2c5e)	// ..to GLAGOLITIC SMALL LETTER LATINATE MYSLITE
+	while (c <= 0x2c5f)	// ..to GLAGOLITIC SMALL LETTER CAUDATE CHRIVI
 		charset[i++] = c++;
 // 2C60..2C7F; Latin Extended-C
 	c = 0x2c60;		// from LATIN CAPITAL LETTER L WITH DOUBLE BAR
@@ -985,7 +976,7 @@ void init()
 		charset[i++] = c++;
 // 2E00..2E7F; Supplemental Punctuation
 	c = 0x2e00;		// from RIGHT ANGLE SUBSTITUTION MARKER
-	while (c <= 0x2e52)	// ..to TIRONIAN SIGN CAPITAL ET
+	while (c <= 0x2e5d)	// ..to OBLIQUE HYPHEN
 		charset[i++] = c++;
 // 2E80..2EFF; CJK Radicals Supplement
 	c = 0x2e80;		// from CJK RADICAL REPEAT
@@ -1000,7 +991,7 @@ void init()
 		charset[i++] = c++;
 // 2FF0..2FFF; Ideographic Description Characters
 	c = 0x2ff0;		// from IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT
-	while (c <= 0x2ffb)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
+	while (c <= 0x2fff)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
 		charset[i++] = c++;
 // 3000..303F; CJK Symbols and Punctuation
 	c = 0x3000;		// from IDEOGRAPHIC SPACE
@@ -1035,8 +1026,9 @@ void init()
 		charset[i++] = c++;
 // 31C0..31EF; CJK Strokes
 	c = 0x31c0;		// from CJK STROKE T
-	while (c <= 0x31e3)	// ..to CJK STROKE Q
+	while (c <= 0x31e5)	// ..to CJK STROKE SZP
 		charset[i++] = c++;
+	charset[i++] = 0x31ef;	// IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
 // 31F0..31FF; Katakana Phonetic Extensions
 	c = 0x31f0;		// from KATAKANA LETTER SMALL KU
 	while (c <= 0x31ff)	// ..to KATAKANA LETTER SMALL RO
@@ -1062,7 +1054,7 @@ void init()
 		charset[i++] = c++;
 // 4E00..9FFF; CJK Unified Ideographs
 	c = 0x4e00;		// from <CJK Ideograph, First>
-	while (c <= 0x9ffc)	// ..to <CJK Ideograph, Last>
+	while (c <= 0x9fff)	// ..to <CJK Ideograph, Last>
 		charset[i++] = c++;
 // A000..A48F; Yi Syllables
 	c = 0xa000;		// from YI SYLLABLE IT
@@ -1094,12 +1086,14 @@ void init()
 		charset[i++] = c++;
 // A720..A7FF; Latin Extended-D
 	c = 0xa720;		// from MODIFIER LETTER STRESS AND HIGH TONE
-	while (c <= 0xa7bf)	// ..to LATIN SMALL LETTER GLOTTAL U
+	while (c <= 0xa7cd)	// ..to LATIN SMALL LETTER S WITH DIAGONAL STROKE
 		charset[i++] = c++;
-	c = 0xa7c2;		// from LATIN CAPITAL LETTER ANGLICANA W
-	while (c <= 0xa7ca)	// ..to LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
+	charset[i++] = 0xa7d0;	// LATIN CAPITAL LETTER CLOSED INSULAR G
+	charset[i++] = 0xa7d1;	// LATIN SMALL LETTER CLOSED INSULAR G
+	c = 0xa7d5;		// from LATIN SMALL LETTER DOUBLE WYNN
+	while (c <= 0xa7dc)	// ..to LATIN CAPITAL LETTER LAMBDA WITH STROKE
 		charset[i++] = c++;
-	c = 0xa7f5;		// from LATIN CAPITAL LETTER REVERSED HALF H
+	c = 0xa7f2;		// from MODIFIER LETTER CAPITAL C
 	while (c <= 0xa7ff)	// ..to LATIN EPIGRAPHIC LETTER ARCHAIC M
 		charset[i++] = c++;
 // A800..A82F; Syloti Nagri
@@ -1254,19 +1248,16 @@ void init()
 		charset[i++] = c++;
 // FB50..FDFF; Arabic Presentation Forms-A
 	c = 0xfb50;		// from ARABIC LETTER ALEF WASLA ISOLATED FORM
-	while (c <= 0xfbc1)	// ..to ARABIC SYMBOL SMALL TAH BELOW
+	while (c <= 0xfbc2)	// ..to ARABIC SYMBOL WASLA ABOVE
 		charset[i++] = c++;
 	c = 0xfbd3;		// from ARABIC LETTER NG ISOLATED FORM
-	while (c <= 0xfd3f)	// ..to ORNATE RIGHT PARENTHESIS
-		charset[i++] = c++;
-	c = 0xfd50;		// from ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM
 	while (c <= 0xfd8f)	// ..to ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
 		charset[i++] = c++;
 	c = 0xfd92;		// from ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM
 	while (c <= 0xfdc7)	// ..to ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
 		charset[i++] = c++;
 	c = 0xfdf0;		// from ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM
-	while (c <= 0xfdfd)	// ..to ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
+	while (c <= 0xfdff)	// ..to ARABIC LIGATURE AZZA WA JALL
 		charset[i++] = c++;
 // FE00..FE0F; Variation Selectors
 	c = 0xfe00;		// from VARIATION SELECTOR-1

data/jtr/repeats32.conf

@@ -1,11 +1,11 @@
-# This software is Copyright (c) 2012-2020 magnum, and it is hereby
+# This software is Copyright (c) 2012-2024 magnum, and it is hereby
 # released to the general public under the following terms:
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted.
 #
-# Try strings of repeated characters, Full Unicode (version 13) version
+# Try strings of repeated characters, Full Unicode (version 16) version
 #
-# Number of candidates = 143,532 x length
+# Number of candidates = 154,663 x length
 #
 # Note that these modes will handle --max-len differently than normal: They
 # will consider number of characters as opposed to number of bytes. This
@@ -23,7 +23,7 @@
 
 [List.External:Repeats32]
 int minlength, maxlength, maxc, length, c;
-int charset[0x24000];
+int charset[0x25c30];
 
 void init()
 {
@@ -44,7 +44,7 @@ void init()
 
 /*
  * This defines the character set. This is auto-generated from UnicodeData.txt
- * and we skip control characters.
+ * of Unicode 16.0.0 and we skip control characters.
  */
 	i = 0;
 // 0000..007F; Basic Latin
@@ -120,9 +120,6 @@ void init()
 		charset[i++] = c++;
 // 0600..06FF; Arabic
 	c = 0x600;		// from ARABIC NUMBER SIGN
-	while (c <= 0x61c)	// ..to ARABIC LETTER MARK
-		charset[i++] = c++;
-	c = 0x61e;		// from ARABIC TRIPLE DOT PUNCTUATION MARK
 	while (c <= 0x6ff)	// ..to ARABIC LETTER HEH WITH INVERTED V
 		charset[i++] = c++;
 // 0700..074F; Syriac
@@ -164,14 +161,17 @@ void init()
 	c = 0x860;		// from SYRIAC LETTER MALAYALAM NGA
 	while (c <= 0x86a)	// ..to SYRIAC LETTER MALAYALAM SSA
 		charset[i++] = c++;
+// 0870..089F; Arabic Extended-B
+	c = 0x870;		// from ARABIC LETTER ALEF WITH ATTACHED FATHA
+	while (c <= 0x88e)	// ..to ARABIC VERTICAL TAIL
+		charset[i++] = c++;
+	charset[i++] = 0x890;	// ARABIC POUND MARK ABOVE
+	charset[i++] = 0x891;	// ARABIC PIASTRE MARK ABOVE
+	c = 0x897;		// from ARABIC PEPET
+	while (c <= 0x89f)	// ..to ARABIC HALF MADDA OVER MADDA
+		charset[i++] = c++;
 // 08A0..08FF; Arabic Extended-A
 	c = 0x8a0;		// from ARABIC LETTER BEH WITH SMALL V BELOW
-	while (c <= 0x8b4)	// ..to ARABIC LETTER KAF WITH DOT BELOW
-		charset[i++] = c++;
-	c = 0x8b6;		// from ARABIC LETTER BEH WITH SMALL MEEM ABOVE
-	while (c <= 0x8c7)	// ..to ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
-		charset[i++] = c++;
-	c = 0x8d3;		// from ARABIC SMALL LOW WAW
 	while (c <= 0x8ff)	// ..to ARABIC MARK SIDEWAYS NOON GHUNNA
 		charset[i++] = c++;
 // 0900..097F; Devanagari
@@ -361,7 +361,7 @@ void init()
 	c = 0xc2a;		// from TELUGU LETTER PA
 	while (c <= 0xc39)	// ..to TELUGU LETTER HA
 		charset[i++] = c++;
-	c = 0xc3d;		// from TELUGU SIGN AVAGRAHA
+	c = 0xc3c;		// from TELUGU SIGN NUKTA
 	while (c <= 0xc44)	// ..to TELUGU VOWEL SIGN VOCALIC RR
 		charset[i++] = c++;
 	charset[i++] = 0xc46;	// TELUGU VOWEL SIGN E
@@ -407,6 +407,8 @@ void init()
 		charset[i++] = c++;
 	charset[i++] = 0xcd5;	// KANNADA LENGTH MARK
 	charset[i++] = 0xcd6;	// KANNADA AI LENGTH MARK
+	charset[i++] = 0xcdd;	// KANNADA LETTER NAKAARA POLLU
+	charset[i++] = 0xcde;	// KANNADA LETTER FA
 	c = 0xce0;		// from KANNADA LETTER VOCALIC RR
 	while (c <= 0xce3)	// ..to KANNADA VOWEL SIGN VOCALIC LL
 		charset[i++] = c++;
@@ -414,7 +416,7 @@ void init()
 	while (c <= 0xcef)	// ..to KANNADA DIGIT NINE
 		charset[i++] = c++;
 	charset[i++] = 0xcf1;	// KANNADA SIGN JIHVAMULIYA
-	charset[i++] = 0xcf2;	// KANNADA SIGN UPADHMANIYA
+	charset[i++] = 0xcf3;	// KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 // 0D00..0D7F; Malayalam
 	c = 0xd00;		// from MALAYALAM SIGN COMBINING ANUSVARA ABOVE
 	while (c <= 0xd0c)	// ..to MALAYALAM LETTER VOCALIC L
@@ -484,7 +486,7 @@ void init()
 	while (c <= 0xec4)	// ..to LAO VOWEL SIGN AI
 		charset[i++] = c++;
 	c = 0xec8;		// from LAO TONE MAI EK
-	while (c <= 0xecd)	// ..to LAO NIGGAHITA
+	while (c <= 0xece)	// ..to LAO YAMAKKAN
 		charset[i++] = c++;
 	c = 0xed0;		// from LAO DIGIT ZERO
 	while (c <= 0xed9)	// ..to LAO DIGIT NINE
@@ -597,11 +599,9 @@ void init()
 		charset[i++] = c++;
 // 1700..171F; Tagalog
 	c = 0x1700;		// from TAGALOG LETTER A
-	while (c <= 0x170c)	// ..to TAGALOG LETTER YA
-		charset[i++] = c++;
-	c = 0x170e;		// from TAGALOG LETTER LA
-	while (c <= 0x1714)	// ..to TAGALOG SIGN VIRAMA
+	while (c <= 0x1715)	// ..to TAGALOG SIGN PAMUDPOD
 		charset[i++] = c++;
+	charset[i++] = 0x171f;	// TAGALOG LETTER ARCHAIC RA
 // 1720..173F; Hanunoo
 	c = 0x1720;		// from HANUNOO LETTER A
 	while (c <= 0x1736)	// ..to PHILIPPINE DOUBLE PUNCTUATION
@@ -630,9 +630,6 @@ void init()
 		charset[i++] = c++;
 // 1800..18AF; Mongolian
 	c = 0x1800;		// from MONGOLIAN BIRGA
-	while (c <= 0x180e)	// ..to MONGOLIAN VOWEL SEPARATOR
-		charset[i++] = c++;
-	c = 0x1810;		// from MONGOLIAN DIGIT ZERO
 	while (c <= 0x1819)	// ..to MONGOLIAN DIGIT NINE
 		charset[i++] = c++;
 	c = 0x1820;		// from MONGOLIAN LETTER A
@@ -705,14 +702,14 @@ void init()
 		charset[i++] = c++;
 // 1AB0..1AFF; Combining Diacritical Marks Extended
 	c = 0x1ab0;		// from COMBINING DOUBLED CIRCUMFLEX ACCENT
-	while (c <= 0x1ac0)	// ..to COMBINING LATIN SMALL LETTER TURNED W BELOW
+	while (c <= 0x1ace)	// ..to COMBINING LATIN SMALL LETTER INSULAR T
 		charset[i++] = c++;
 // 1B00..1B7F; Balinese
 	c = 0x1b00;		// from BALINESE SIGN ULU RICEM
-	while (c <= 0x1b4b)	// ..to BALINESE LETTER ASYURA SASAK
+	while (c <= 0x1b4c)	// ..to BALINESE LETTER ARCHAIC JNYA
 		charset[i++] = c++;
-	c = 0x1b50;		// from BALINESE DIGIT ZERO
-	while (c <= 0x1b7c)	// ..to BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING
+	c = 0x1b4e;		// from BALINESE INVERTED CARIK SIKI
+	while (c <= 0x1b7f)	// ..to BALINESE PANTI BAWAK
 		charset[i++] = c++;
 // 1B80..1BBF; Sundanese
 	c = 0x1b80;		// from SUNDANESE SIGN PANYECEK
@@ -740,7 +737,7 @@ void init()
 		charset[i++] = c++;
 // 1C80..1C8F; Cyrillic Extended-C
 	c = 0x1c80;		// from CYRILLIC SMALL LETTER ROUNDED VE
-	while (c <= 0x1c88)	// ..to CYRILLIC SMALL LETTER UNBLENDED UK
+	while (c <= 0x1c8a)	// ..to CYRILLIC SMALL LETTER TJE
 		charset[i++] = c++;
 // 1C90..1CBF; Georgian Extended
 	c = 0x1c90;		// from GEORGIAN MTAVRULI CAPITAL LETTER AN
@@ -766,9 +763,6 @@ void init()
 		charset[i++] = c++;
 // 1DC0..1DFF; Combining Diacritical Marks Supplement
 	c = 0x1dc0;		// from COMBINING DOTTED GRAVE ACCENT
-	while (c <= 0x1df9)	// ..to COMBINING WIDE INVERTED BRIDGE BELOW
-		charset[i++] = c++;
-	c = 0x1dfb;		// from COMBINING DELETION MARK
 	while (c <= 0x1dff)	// ..to COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
 		charset[i++] = c++;
 // 1E00..1EFF; Latin Extended Additional
@@ -832,7 +826,7 @@ void init()
 		charset[i++] = c++;
 // 20A0..20CF; Currency Symbols
 	c = 0x20a0;		// from EURO-CURRENCY SIGN
-	while (c <= 0x20bf)	// ..to BITCOIN SIGN
+	while (c <= 0x20c0)	// ..to SOM SIGN
 		charset[i++] = c++;
 // 20D0..20FF; Combining Diacritical Marks for Symbols
 	c = 0x20d0;		// from COMBINING LEFT HARPOON ABOVE
@@ -860,7 +854,7 @@ void init()
 		charset[i++] = c++;
 // 2400..243F; Control Pictures
 	c = 0x2400;		// from SYMBOL FOR NULL
-	while (c <= 0x2426)	// ..to SYMBOL FOR SUBSTITUTE FORM TWO
+	while (c <= 0x2429)	// ..to SYMBOL FOR DELETE MEDIUM SHADE FORM
 		charset[i++] = c++;
 // 2440..245F; Optical Character Recognition
 	c = 0x2440;		// from OCR HOOK
@@ -926,10 +920,7 @@ void init()
 		charset[i++] = c++;
 // 2C00..2C5F; Glagolitic
 	c = 0x2c00;		// from GLAGOLITIC CAPITAL LETTER AZU
-	while (c <= 0x2c2e)	// ..to GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
-		charset[i++] = c++;
-	c = 0x2c30;		// from GLAGOLITIC SMALL LETTER AZU
-	while (c <= 0x2c5e)	// ..to GLAGOLITIC SMALL LETTER LATINATE MYSLITE
+	while (c <= 0x2c5f)	// ..to GLAGOLITIC SMALL LETTER CAUDATE CHRIVI
 		charset[i++] = c++;
 // 2C60..2C7F; Latin Extended-C
 	c = 0x2c60;		// from LATIN CAPITAL LETTER L WITH DOUBLE BAR
@@ -990,7 +981,7 @@ void init()
 		charset[i++] = c++;
 // 2E00..2E7F; Supplemental Punctuation
 	c = 0x2e00;		// from RIGHT ANGLE SUBSTITUTION MARKER
-	while (c <= 0x2e52)	// ..to TIRONIAN SIGN CAPITAL ET
+	while (c <= 0x2e5d)	// ..to OBLIQUE HYPHEN
 		charset[i++] = c++;
 // 2E80..2EFF; CJK Radicals Supplement
 	c = 0x2e80;		// from CJK RADICAL REPEAT
@@ -1005,7 +996,7 @@ void init()
 		charset[i++] = c++;
 // 2FF0..2FFF; Ideographic Description Characters
 	c = 0x2ff0;		// from IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT
-	while (c <= 0x2ffb)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
+	while (c <= 0x2fff)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
 		charset[i++] = c++;
 // 3000..303F; CJK Symbols and Punctuation
 	c = 0x3000;		// from IDEOGRAPHIC SPACE
@@ -1040,8 +1031,9 @@ void init()
 		charset[i++] = c++;
 // 31C0..31EF; CJK Strokes
 	c = 0x31c0;		// from CJK STROKE T
-	while (c <= 0x31e3)	// ..to CJK STROKE Q
+	while (c <= 0x31e5)	// ..to CJK STROKE SZP
 		charset[i++] = c++;
+	charset[i++] = 0x31ef;	// IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
 // 31F0..31FF; Katakana Phonetic Extensions
 	c = 0x31f0;		// from KATAKANA LETTER SMALL KU
 	while (c <= 0x31ff)	// ..to KATAKANA LETTER SMALL RO
@@ -1067,7 +1059,7 @@ void init()
 		charset[i++] = c++;
 // 4E00..9FFF; CJK Unified Ideographs
 	c = 0x4e00;		// from <CJK Ideograph, First>
-	while (c <= 0x9ffc)	// ..to <CJK Ideograph, Last>
+	while (c <= 0x9fff)	// ..to <CJK Ideograph, Last>
 		charset[i++] = c++;
 // A000..A48F; Yi Syllables
 	c = 0xa000;		// from YI SYLLABLE IT
@@ -1099,12 +1091,14 @@ void init()
 		charset[i++] = c++;
 // A720..A7FF; Latin Extended-D
 	c = 0xa720;		// from MODIFIER LETTER STRESS AND HIGH TONE
-	while (c <= 0xa7bf)	// ..to LATIN SMALL LETTER GLOTTAL U
+	while (c <= 0xa7cd)	// ..to LATIN SMALL LETTER S WITH DIAGONAL STROKE
 		charset[i++] = c++;
-	c = 0xa7c2;		// from LATIN CAPITAL LETTER ANGLICANA W
-	while (c <= 0xa7ca)	// ..to LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
+	charset[i++] = 0xa7d0;	// LATIN CAPITAL LETTER CLOSED INSULAR G
+	charset[i++] = 0xa7d1;	// LATIN SMALL LETTER CLOSED INSULAR G
+	c = 0xa7d5;		// from LATIN SMALL LETTER DOUBLE WYNN
+	while (c <= 0xa7dc)	// ..to LATIN CAPITAL LETTER LAMBDA WITH STROKE
 		charset[i++] = c++;
-	c = 0xa7f5;		// from LATIN CAPITAL LETTER REVERSED HALF H
+	c = 0xa7f2;		// from MODIFIER LETTER CAPITAL C
 	while (c <= 0xa7ff)	// ..to LATIN EPIGRAPHIC LETTER ARCHAIC M
 		charset[i++] = c++;
 // A800..A82F; Syloti Nagri
@@ -1259,19 +1253,16 @@ void init()
 		charset[i++] = c++;
 // FB50..FDFF; Arabic Presentation Forms-A
 	c = 0xfb50;		// from ARABIC LETTER ALEF WASLA ISOLATED FORM
-	while (c <= 0xfbc1)	// ..to ARABIC SYMBOL SMALL TAH BELOW
+	while (c <= 0xfbc2)	// ..to ARABIC SYMBOL WASLA ABOVE
 		charset[i++] = c++;
 	c = 0xfbd3;		// from ARABIC LETTER NG ISOLATED FORM
-	while (c <= 0xfd3f)	// ..to ORNATE RIGHT PARENTHESIS
-		charset[i++] = c++;
-	c = 0xfd50;		// from ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM
 	while (c <= 0xfd8f)	// ..to ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
 		charset[i++] = c++;
 	c = 0xfd92;		// from ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM
 	while (c <= 0xfdc7)	// ..to ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
 		charset[i++] = c++;
 	c = 0xfdf0;		// from ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM
-	while (c <= 0xfdfd)	// ..to ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
+	while (c <= 0xfdff)	// ..to ARABIC LIGATURE AZZA WA JALL
 		charset[i++] = c++;
 // FE00..FE0F; Variation Selectors
 	c = 0xfe00;		// from VARIATION SELECTOR-1
@@ -1444,6 +1435,33 @@ void init()
 	while (c <= 0x10563)	// ..to CAUCASIAN ALBANIAN LETTER KIW
 		charset[i++] = c++;
 	charset[i++] = 0x1056f;	// CAUCASIAN ALBANIAN CITATION MARK
+// 10570..105BF; Vithkuqi
+	c = 0x10570;		// from VITHKUQI CAPITAL LETTER A
+	while (c <= 0x1057a)	// ..to VITHKUQI CAPITAL LETTER GA
+		charset[i++] = c++;
+	c = 0x1057c;		// from VITHKUQI CAPITAL LETTER HA
+	while (c <= 0x1058a)	// ..to VITHKUQI CAPITAL LETTER RE
+		charset[i++] = c++;
+	c = 0x1058c;		// from VITHKUQI CAPITAL LETTER SE
+	while (c <= 0x10592)	// ..to VITHKUQI CAPITAL LETTER XE
+		charset[i++] = c++;
+	charset[i++] = 0x10594;	// VITHKUQI CAPITAL LETTER Y
+	charset[i++] = 0x10595;	// VITHKUQI CAPITAL LETTER ZE
+	c = 0x10597;		// from VITHKUQI SMALL LETTER A
+	while (c <= 0x105a1)	// ..to VITHKUQI SMALL LETTER GA
+		charset[i++] = c++;
+	c = 0x105a3;		// from VITHKUQI SMALL LETTER HA
+	while (c <= 0x105b1)	// ..to VITHKUQI SMALL LETTER RE
+		charset[i++] = c++;
+	c = 0x105b3;		// from VITHKUQI SMALL LETTER SE
+	while (c <= 0x105b9)	// ..to VITHKUQI SMALL LETTER XE
+		charset[i++] = c++;
+	charset[i++] = 0x105bb;	// VITHKUQI SMALL LETTER Y
+	charset[i++] = 0x105bc;	// VITHKUQI SMALL LETTER ZE
+// 105C0..105FF; Todhri
+	c = 0x105c0;		// from TODHRI LETTER A
+	while (c <= 0x105f3)	// ..to TODHRI LETTER OO
+		charset[i++] = c++;
 // 10600..1077F; Linear A
 	c = 0x10600;		// from LINEAR A SIGN AB001
 	while (c <= 0x10736)	// ..to LINEAR A SIGN A664
@@ -1454,6 +1472,16 @@ void init()
 	c = 0x10760;		// from LINEAR A SIGN A800
 	while (c <= 0x10767)	// ..to LINEAR A SIGN A807
 		charset[i++] = c++;
+// 10780..107BF; Latin Extended-F
+	c = 0x10780;		// from MODIFIER LETTER SMALL CAPITAL AA
+	while (c <= 0x10785)	// ..to MODIFIER LETTER SMALL B WITH HOOK
+		charset[i++] = c++;
+	c = 0x10787;		// from MODIFIER LETTER SMALL DZ DIGRAPH
+	while (c <= 0x107b0)	// ..to MODIFIER LETTER SMALL V WITH RIGHT HOOK
+		charset[i++] = c++;
+	c = 0x107b2;		// from MODIFIER LETTER SMALL CAPITAL Y
+	while (c <= 0x107ba)	// ..to MODIFIER LETTER SMALL S WITH CURL
+		charset[i++] = c++;
 // 10800..1083F; Cypriot Syllabary
 	c = 0x10800;		// from CYPRIOT SYLLABLE A
 	while (c <= 0x10805)	// ..to CYPRIOT SYLLABLE JA
@@ -1606,6 +1634,15 @@ void init()
 	c = 0x10d30;		// from HANIFI ROHINGYA DIGIT ZERO
 	while (c <= 0x10d39)	// ..to HANIFI ROHINGYA DIGIT NINE
 		charset[i++] = c++;
+// 10D40..10D8F; Garay
+	c = 0x10d40;		// from GARAY DIGIT ZERO
+	while (c <= 0x10d65)	// ..to GARAY CAPITAL LETTER OLD NA
+		charset[i++] = c++;
+	c = 0x10d69;		// from GARAY VOWEL SIGN E
+	while (c <= 0x10d85)	// ..to GARAY SMALL LETTER OLD NA
+		charset[i++] = c++;
+	charset[i++] = 0x10d8e;	// GARAY PLUS SIGN
+	charset[i++] = 0x10d8f;	// GARAY MINUS SIGN
 // 10E60..10E7F; Rumi Numeral Symbols
 	c = 0x10e60;		// from RUMI DIGIT ONE
 	while (c <= 0x10e7e)	// ..to RUMI FRACTION TWO THIRDS
@@ -1618,6 +1655,12 @@ void init()
 	charset[i++] = 0x10ead;	// YEZIDI HYPHENATION MARK
 	charset[i++] = 0x10eb0;	// YEZIDI LETTER LAM WITH DOT ABOVE
 	charset[i++] = 0x10eb1;	// YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
+// 10EC0..10EFF; Arabic Extended-C
+	charset[i++] = 0x10ec2;	// ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW
+	charset[i++] = 0x10ec4;	// ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW
+	c = 0x10efc;		// from ARABIC COMBINING ALEF OVERLAY
+	while (c <= 0x10eff)	// ..to ARABIC SMALL LOW WORD MADDA
+		charset[i++] = c++;
 // 10F00..10F2F; Old Sogdian
 	c = 0x10f00;		// from OLD SOGDIAN LETTER ALEPH
 	while (c <= 0x10f27)	// ..to OLD SOGDIAN LIGATURE AYIN-DALETH
@@ -1626,6 +1669,10 @@ void init()
 	c = 0x10f30;		// from SOGDIAN LETTER ALEPH
 	while (c <= 0x10f59)	// ..to SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
 		charset[i++] = c++;
+// 10F70..10FAF; Old Uyghur
+	c = 0x10f70;		// from OLD UYGHUR LETTER ALEPH
+	while (c <= 0x10f89)	// ..to OLD UYGHUR PUNCTUATION FOUR DOTS
+		charset[i++] = c++;
 // 10FB0..10FDF; Chorasmian
 	c = 0x10fb0;		// from CHORASMIAN LETTER ALEPH
 	while (c <= 0x10fcb)	// ..to CHORASMIAN NUMBER ONE HUNDRED
@@ -1639,12 +1686,12 @@ void init()
 	while (c <= 0x1104d)	// ..to BRAHMI PUNCTUATION LOTUS
 		charset[i++] = c++;
 	c = 0x11052;		// from BRAHMI NUMBER ONE
-	while (c <= 0x1106f)	// ..to BRAHMI DIGIT NINE
+	while (c <= 0x11075)	// ..to BRAHMI LETTER OLD TAMIL LLA
 		charset[i++] = c++;
 	charset[i++] = 0x1107f;	// BRAHMI NUMBER JOINER
 // 11080..110CF; Kaithi
 	c = 0x11080;		// from KAITHI SIGN CANDRABINDU
-	while (c <= 0x110c1)	// ..to KAITHI DOUBLE DANDA
+	while (c <= 0x110c2)	// ..to KAITHI VOWEL SIGN VOCALIC R
 		charset[i++] = c++;
 	charset[i++] = 0x110cd;	// KAITHI NUMBER SIGN ABOVE
 // 110D0..110FF; Sora Sompeng
@@ -1678,7 +1725,7 @@ void init()
 	while (c <= 0x11211)	// ..to KHOJKI LETTER JJA
 		charset[i++] = c++;
 	c = 0x11213;		// from KHOJKI LETTER NYA
-	while (c <= 0x1123e)	// ..to KHOJKI SIGN SUKUN
+	while (c <= 0x11241)	// ..to KHOJKI VOWEL SIGN VOCALIC R
 		charset[i++] = c++;
 // 11280..112AF; Multani
 	c = 0x11280;		// from MULTANI LETTER A
@@ -1736,6 +1783,26 @@ void init()
 	c = 0x11370;		// from COMBINING GRANTHA LETTER A
 	while (c <= 0x11374)	// ..to COMBINING GRANTHA LETTER PA
 		charset[i++] = c++;
+// 11380..113FF; Tulu-Tigalari
+	c = 0x11380;		// from TULU-TIGALARI LETTER A
+	while (c <= 0x11389)	// ..to TULU-TIGALARI LETTER VOCALIC LL
+		charset[i++] = c++;
+	c = 0x11390;		// from TULU-TIGALARI LETTER OO
+	while (c <= 0x113b5)	// ..to TULU-TIGALARI LETTER LLLA
+		charset[i++] = c++;
+	c = 0x113b7;		// from TULU-TIGALARI SIGN AVAGRAHA
+	while (c <= 0x113c0)	// ..to TULU-TIGALARI VOWEL SIGN VOCALIC LL
+		charset[i++] = c++;
+	c = 0x113c7;		// from TULU-TIGALARI VOWEL SIGN OO
+	while (c <= 0x113ca)	// ..to TULU-TIGALARI SIGN CANDRA ANUNASIKA
+		charset[i++] = c++;
+	c = 0x113cc;		// from TULU-TIGALARI SIGN ANUSVARA
+	while (c <= 0x113d5)	// ..to TULU-TIGALARI DOUBLE DANDA
+		charset[i++] = c++;
+	charset[i++] = 0x113d7;	// TULU-TIGALARI SIGN OM PUSHPIKA
+	charset[i++] = 0x113d8;	// TULU-TIGALARI SIGN SHRII PUSHPIKA
+	charset[i++] = 0x113e1;	// TULU-TIGALARI VEDIC TONE SVARITA
+	charset[i++] = 0x113e2;	// TULU-TIGALARI VEDIC TONE ANUDATTA
 // 11400..1147F; Newa
 	c = 0x11400;		// from NEWA LETTER A
 	while (c <= 0x1145b)	// ..to NEWA PLACEHOLDER MARK
@@ -1770,12 +1837,16 @@ void init()
 		charset[i++] = c++;
 // 11680..116CF; Takri
 	c = 0x11680;		// from TAKRI LETTER A
-	while (c <= 0x116b8)	// ..to TAKRI LETTER ARCHAIC KHA
+	while (c <= 0x116b9)	// ..to TAKRI ABBREVIATION SIGN
 		charset[i++] = c++;
 	c = 0x116c0;		// from TAKRI DIGIT ZERO
 	while (c <= 0x116c9)	// ..to TAKRI DIGIT NINE
 		charset[i++] = c++;
-// 11700..1173F; Ahom
+// 116D0..116FF; Myanmar Extended-C
+	c = 0x116d0;		// from MYANMAR PAO DIGIT ZERO
+	while (c <= 0x116e3)	// ..to MYANMAR EASTERN PWO KAREN DIGIT NINE
+		charset[i++] = c++;
+// 11700..1174F; Ahom
 	c = 0x11700;		// from AHOM LETTER KA
 	while (c <= 0x1171a)	// ..to AHOM LETTER ALTERNATE BA
 		charset[i++] = c++;
@@ -1783,7 +1854,7 @@ void init()
 	while (c <= 0x1172b)	// ..to AHOM SIGN KILLER
 		charset[i++] = c++;
 	c = 0x11730;		// from AHOM DIGIT ZERO
-	while (c <= 0x1173f)	// ..to AHOM SYMBOL VI
+	while (c <= 0x11746)	// ..to AHOM LETTER LLA
 		charset[i++] = c++;
 // 11800..1184F; Dogra
 	c = 0x11800;		// from DOGRA LETTER A
@@ -1832,10 +1903,25 @@ void init()
 	c = 0x11a50;		// from SOYOMBO LETTER A
 	while (c <= 0x11aa2)	// ..to SOYOMBO TERMINAL MARK-2
 		charset[i++] = c++;
+// 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
+	c = 0x11ab0;		// from CANADIAN SYLLABICS NATTILIK HI
+	while (c <= 0x11abf)	// ..to CANADIAN SYLLABICS SPA
+		charset[i++] = c++;
 // 11AC0..11AFF; Pau Cin Hau
 	c = 0x11ac0;		// from PAU CIN HAU LETTER PA
 	while (c <= 0x11af8)	// ..to PAU CIN HAU GLOTTAL STOP FINAL
 		charset[i++] = c++;
+// 11B00..11B5F; Devanagari Extended-A
+	c = 0x11b00;		// from DEVANAGARI HEAD MARK
+	while (c <= 0x11b09)	// ..to DEVANAGARI SIGN MINDU
+		charset[i++] = c++;
+// 11BC0..11BFF; Sunuwar
+	c = 0x11bc0;		// from SUNUWAR LETTER DEVI
+	while (c <= 0x11be1)	// ..to SUNUWAR SIGN PVO
+		charset[i++] = c++;
+	c = 0x11bf0;		// from SUNUWAR DIGIT ZERO
+	while (c <= 0x11bf9)	// ..to SUNUWAR DIGIT NINE
+		charset[i++] = c++;
 // 11C00..11C6F; Bhaiksuki
 	c = 0x11c00;		// from BHAIKSUKI LETTER A
 	while (c <= 0x11c08)	// ..to BHAIKSUKI LETTER VOCALIC L
@@ -1897,6 +1983,16 @@ void init()
 	c = 0x11ee0;		// from MAKASAR LETTER KA
 	while (c <= 0x11ef8)	// ..to MAKASAR END OF SECTION
 		charset[i++] = c++;
+// 11F00..11F5F; Kawi
+	c = 0x11f00;		// from KAWI SIGN CANDRABINDU
+	while (c <= 0x11f10)	// ..to KAWI LETTER O
+		charset[i++] = c++;
+	c = 0x11f12;		// from KAWI LETTER KA
+	while (c <= 0x11f3a)	// ..to KAWI VOWEL SIGN VOCALIC R
+		charset[i++] = c++;
+	c = 0x11f3e;		// from KAWI VOWEL SIGN E
+	while (c <= 0x11f5a)	// ..to KAWI SIGN NUKTA
+		charset[i++] = c++;
 // 11FB0..11FBF; Lisu Supplement
 	charset[i++] = 0x11fb0;	// LISU LETTER YHA
 // 11FC0..11FFF; Tamil Supplement
@@ -1919,18 +2015,30 @@ void init()
 	c = 0x12480;		// from CUNEIFORM SIGN AB TIMES NUN TENU
 	while (c <= 0x12543)	// ..to CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
 		charset[i++] = c++;
+// 12F90..12FFF; Cypro-Minoan
+	c = 0x12f90;		// from CYPRO-MINOAN SIGN CM001
+	while (c <= 0x12ff2)	// ..to CYPRO-MINOAN SIGN CM302
+		charset[i++] = c++;
 // 13000..1342F; Egyptian Hieroglyphs
 	c = 0x13000;		// from EGYPTIAN HIEROGLYPH A001
-	while (c <= 0x1342e)	// ..to EGYPTIAN HIEROGLYPH AA032
+	while (c <= 0x1342f)	// ..to EGYPTIAN HIEROGLYPH V011D
 		charset[i++] = c++;
-// 13430..1343F; Egyptian Hieroglyph Format Controls
+// 13430..1345F; Egyptian Hieroglyph Format Controls
 	c = 0x13430;		// from EGYPTIAN HIEROGLYPH VERTICAL JOINER
-	while (c <= 0x13438)	// ..to EGYPTIAN HIEROGLYPH END SEGMENT
+	while (c <= 0x13455)	// ..to EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
+		charset[i++] = c++;
+// 13460..143FF; Egyptian Hieroglyphs Extended-A
+	c = 0x13460;		// from EGYPTIAN HIEROGLYPH-13460
+	while (c <= 0x143fa)	// ..to EGYPTIAN HIEROGLYPH-143FA
 		charset[i++] = c++;
 // 14400..1467F; Anatolian Hieroglyphs
 	c = 0x14400;		// from ANATOLIAN HIEROGLYPH A001
 	while (c <= 0x14646)	// ..to ANATOLIAN HIEROGLYPH A530
 		charset[i++] = c++;
+// 16100..1613F; Gurung Khema
+	c = 0x16100;		// from GURUNG KHEMA LETTER A
+	while (c <= 0x16139)	// ..to GURUNG KHEMA DIGIT NINE
+		charset[i++] = c++;
 // 16800..16A3F; Bamum Supplement
 	c = 0x16800;		// from BAMUM LETTER PHASE-A NGKUE MFON
 	while (c <= 0x16a38)	// ..to BAMUM LETTER PHASE-F VUEQ
@@ -1944,6 +2052,13 @@ void init()
 		charset[i++] = c++;
 	charset[i++] = 0x16a6e;	// MRO DANDA
 	charset[i++] = 0x16a6f;	// MRO DOUBLE DANDA
+// 16A70..16ACF; Tangsa
+	c = 0x16a70;		// from TANGSA LETTER OZ
+	while (c <= 0x16abe)	// ..to TANGSA LETTER ZA
+		charset[i++] = c++;
+	c = 0x16ac0;		// from TANGSA DIGIT ZERO
+	while (c <= 0x16ac9)	// ..to TANGSA DIGIT NINE
+		charset[i++] = c++;
 // 16AD0..16AFF; Bassa Vah
 	c = 0x16ad0;		// from BASSA VAH LETTER ENNI
 	while (c <= 0x16aed)	// ..to BASSA VAH LETTER I
@@ -1967,6 +2082,10 @@ void init()
 	c = 0x16b7d;		// from PAHAWH HMONG CLAN SIGN TSHEEJ
 	while (c <= 0x16b8f)	// ..to PAHAWH HMONG CLAN SIGN VWJ
 		charset[i++] = c++;
+// 16D40..16D7F; Kirat Rai
+	c = 0x16d40;		// from KIRAT RAI SIGN ANUSVARA
+	while (c <= 0x16d79)	// ..to KIRAT RAI DIGIT NINE
+		charset[i++] = c++;
 // 16E40..16E9F; Medefaidrin
 	c = 0x16e40;		// from MEDEFAIDRIN CAPITAL LETTER M
 	while (c <= 0x16e9a)	// ..to MEDEFAIDRIN EXCLAMATION OH
@@ -1999,17 +2118,27 @@ void init()
 	c = 0x18b00;		// from KHITAN SMALL SCRIPT CHARACTER-18B00
 	while (c <= 0x18cd5)	// ..to KHITAN SMALL SCRIPT CHARACTER-18CD5
 		charset[i++] = c++;
-// 18D00..18D8F; Tangut Supplement
+	charset[i++] = 0x18cff;	// KHITAN SMALL SCRIPT CHARACTER-18CFF
+// 18D00..18D7F; Tangut Supplement
 	c = 0x18d00;		// from <Tangut Ideograph Supplement, First>
 	while (c <= 0x18d08)	// ..to <Tangut Ideograph Supplement, Last>
 		charset[i++] = c++;
+// 1AFF0..1AFFF; Kana Extended-B
+	c = 0x1aff0;		// from KATAKANA LETTER MINNAN TONE-2
+	while (c <= 0x1aff3)	// ..to KATAKANA LETTER MINNAN TONE-5
+		charset[i++] = c++;
+	c = 0x1aff5;		// from KATAKANA LETTER MINNAN TONE-7
+	while (c <= 0x1affb)	// ..to KATAKANA LETTER MINNAN NASALIZED TONE-5
+		charset[i++] = c++;
+	charset[i++] = 0x1affd;	// KATAKANA LETTER MINNAN NASALIZED TONE-7
+	charset[i++] = 0x1affe;	// KATAKANA LETTER MINNAN NASALIZED TONE-8
 // 1B000..1B0FF; Kana Supplement
 	c = 0x1b000;		// from KATAKANA LETTER ARCHAIC E
 	while (c <= 0x1b0ff)	// ..to HENTAIGANA LETTER RE-2
 		charset[i++] = c++;
 // 1B100..1B12F; Kana Extended-A
 	c = 0x1b100;		// from HENTAIGANA LETTER RE-3
-	while (c <= 0x1b11e)	// ..to HENTAIGANA LETTER N-MU-MO-2
+	while (c <= 0x1b122)	// ..to KATAKANA LETTER ARCHAIC WU
 		charset[i++] = c++;
 // 1B130..1B16F; Small Kana Extension
 	charset[i++] = 0x1b150;	// HIRAGANA LETTER SMALL WI
@@ -2041,6 +2170,23 @@ void init()
 	c = 0x1bca0;		// from SHORTHAND FORMAT LETTER OVERLAP
 	while (c <= 0x1bca3)	// ..to SHORTHAND FORMAT UP STEP
 		charset[i++] = c++;
+// 1CC00..1CEBF; Symbols for Legacy Computing Supplement
+	c = 0x1cc00;		// from UP-POINTING GO-KART
+	while (c <= 0x1ccf9)	// ..to OUTLINED DIGIT NINE
+		charset[i++] = c++;
+	c = 0x1cd00;		// from BLOCK OCTANT-3
+	while (c <= 0x1ceb3)	// ..to BLACK RIGHT TRIANGLE CARET
+		charset[i++] = c++;
+// 1CF00..1CFCF; Znamenny Musical Notation
+	c = 0x1cf00;		// from ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT
+	while (c <= 0x1cf2d)	// ..to ZNAMENNY COMBINING MARK KRYZH ON LEFT
+		charset[i++] = c++;
+	c = 0x1cf30;		// from ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO
+	while (c <= 0x1cf46)	// ..to ZNAMENNY PRIZNAK MODIFIER ROG
+		charset[i++] = c++;
+	c = 0x1cf50;		// from ZNAMENNY NEUME KRYUK
+	while (c <= 0x1cfc3)	// ..to ZNAMENNY NEUME PAUK
+		charset[i++] = c++;
 // 1D000..1D0FF; Byzantine Musical Symbols
 	c = 0x1d000;		// from BYZANTINE MUSICAL SYMBOL PSILI
 	while (c <= 0x1d0f5)	// ..to BYZANTINE MUSICAL SYMBOL GORGON NEO KATO
@@ -2050,12 +2196,16 @@ void init()
 	while (c <= 0x1d126)	// ..to MUSICAL SYMBOL DRUM CLEF-2
 		charset[i++] = c++;
 	c = 0x1d129;		// from MUSICAL SYMBOL MULTIPLE MEASURE REST
-	while (c <= 0x1d1e8)	// ..to MUSICAL SYMBOL KIEVAN FLAT SIGN
+	while (c <= 0x1d1ea)	// ..to MUSICAL SYMBOL KORON
 		charset[i++] = c++;
 // 1D200..1D24F; Ancient Greek Musical Notation
 	c = 0x1d200;		// from GREEK VOCAL NOTATION SYMBOL-1
 	while (c <= 0x1d245)	// ..to GREEK MUSICAL LEIMMA
 		charset[i++] = c++;
+// 1D2C0..1D2DF; Kaktovik Numerals
+	c = 0x1d2c0;		// from KAKTOVIK NUMERAL ZERO
+	while (c <= 0x1d2d3)	// ..to KAKTOVIK NUMERAL NINETEEN
+		charset[i++] = c++;
 // 1D2E0..1D2FF; Mayan Numerals
 	c = 0x1d2e0;		// from MAYAN NUMERAL ZERO
 	while (c <= 0x1d2f3)	// ..to MAYAN NUMERAL NINETEEN
@@ -2131,6 +2281,13 @@ void init()
 	c = 0x1daa1;		// from SIGNWRITING ROTATION MODIFIER-2
 	while (c <= 0x1daaf)	// ..to SIGNWRITING ROTATION MODIFIER-16
 		charset[i++] = c++;
+// 1DF00..1DFFF; Latin Extended-G
+	c = 0x1df00;		// from LATIN SMALL LETTER FENG DIGRAPH WITH TRILL
+	while (c <= 0x1df1e)	// ..to LATIN SMALL LETTER S WITH CURL
+		charset[i++] = c++;
+	c = 0x1df25;		// from LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK
+	while (c <= 0x1df2a)	// ..to LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
+		charset[i++] = c++;
 // 1E000..1E02F; Glagolitic Supplement
 	c = 0x1e000;		// from COMBINING GLAGOLITIC LETTER AZU
 	while (c <= 0x1e006)	// ..to COMBINING GLAGOLITIC LETTER ZHIVETE
@@ -2146,6 +2303,11 @@ void init()
 	c = 0x1e026;		// from COMBINING GLAGOLITIC LETTER YO
 	while (c <= 0x1e02a)	// ..to COMBINING GLAGOLITIC LETTER FITA
 		charset[i++] = c++;
+// 1E030..1E08F; Cyrillic Extended-D
+	c = 0x1e030;		// from MODIFIER LETTER CYRILLIC SMALL A
+	while (c <= 0x1e06d)	// ..to MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
+		charset[i++] = c++;
+	charset[i++] = 0x1e08f;	// COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 // 1E100..1E14F; Nyiakeng Puachue Hmong
 	c = 0x1e100;		// from NYIAKENG PUACHUE HMONG LETTER MA
 	while (c <= 0x1e12c)	// ..to NYIAKENG PUACHUE HMONG LETTER W
@@ -2158,11 +2320,36 @@ void init()
 		charset[i++] = c++;
 	charset[i++] = 0x1e14e;	// NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
 	charset[i++] = 0x1e14f;	// NYIAKENG PUACHUE HMONG CIRCLED CA
+// 1E290..1E2BF; Toto
+	c = 0x1e290;		// from TOTO LETTER PA
+	while (c <= 0x1e2ae)	// ..to TOTO SIGN RISING TONE
+		charset[i++] = c++;
 // 1E2C0..1E2FF; Wancho
 	c = 0x1e2c0;		// from WANCHO LETTER AA
 	while (c <= 0x1e2f9)	// ..to WANCHO DIGIT NINE
 		charset[i++] = c++;
 	charset[i++] = 0x1e2ff;	// WANCHO NGUN SIGN
+// 1E4D0..1E4FF; Nag Mundari
+	c = 0x1e4d0;		// from NAG MUNDARI LETTER O
+	while (c <= 0x1e4f9)	// ..to NAG MUNDARI DIGIT NINE
+		charset[i++] = c++;
+// 1E5D0..1E5FF; Ol Onal
+	c = 0x1e5d0;		// from OL ONAL LETTER O
+	while (c <= 0x1e5fa)	// ..to OL ONAL DIGIT NINE
+		charset[i++] = c++;
+	charset[i++] = 0x1e5ff;	// OL ONAL ABBREVIATION SIGN
+// 1E7E0..1E7FF; Ethiopic Extended-B
+	c = 0x1e7e0;		// from ETHIOPIC SYLLABLE HHYA
+	while (c <= 0x1e7e6)	// ..to ETHIOPIC SYLLABLE HHYO
+		charset[i++] = c++;
+	c = 0x1e7e8;		// from ETHIOPIC SYLLABLE GURAGE HHWA
+	while (c <= 0x1e7eb)	// ..to ETHIOPIC SYLLABLE HHWE
+		charset[i++] = c++;
+	charset[i++] = 0x1e7ed;	// ETHIOPIC SYLLABLE GURAGE MWI
+	charset[i++] = 0x1e7ee;	// ETHIOPIC SYLLABLE GURAGE MWEE
+	c = 0x1e7f0;		// from ETHIOPIC SYLLABLE GURAGE QWI
+	while (c <= 0x1e7fe)	// ..to ETHIOPIC SYLLABLE GURAGE PWEE
+		charset[i++] = c++;
 // 1E800..1E8DF; Mende Kikakui
 	c = 0x1e800;		// from MENDE KIKAKUI SYLLABLE M001 KI
 	while (c <= 0x1e8c4)	// ..to MENDE KIKAKUI SYLLABLE M060 NYON
@@ -2294,7 +2481,7 @@ void init()
 	c = 0x1f680;		// from ROCKET
 	while (c <= 0x1f6d7)	// ..to ELEVATOR
 		charset[i++] = c++;
-	c = 0x1f6e0;		// from HAMMER AND WRENCH
+	c = 0x1f6dc;		// from WIRELESS
 	while (c <= 0x1f6ec)	// ..to AIRPLANE ARRIVING
 		charset[i++] = c++;
 	c = 0x1f6f0;		// from SATELLITE
@@ -2302,15 +2489,19 @@ void init()
 		charset[i++] = c++;
 // 1F700..1F77F; Alchemical Symbols
 	c = 0x1f700;		// from ALCHEMICAL SYMBOL FOR QUINTESSENCE
-	while (c <= 0x1f773)	// ..to ALCHEMICAL SYMBOL FOR HALF OUNCE
+	while (c <= 0x1f776)	// ..to LUNAR ECLIPSE
+		charset[i++] = c++;
+	c = 0x1f77b;		// from HAUMEA
+	while (c <= 0x1f77f)	// ..to ORCUS
 		charset[i++] = c++;
 // 1F780..1F7FF; Geometric Shapes Extended
 	c = 0x1f780;		// from BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE
-	while (c <= 0x1f7d8)	// ..to NEGATIVE CIRCLED SQUARE
+	while (c <= 0x1f7d9)	// ..to NINE POINTED WHITE STAR
 		charset[i++] = c++;
 	c = 0x1f7e0;		// from LARGE ORANGE CIRCLE
 	while (c <= 0x1f7eb)	// ..to LARGE BROWN SQUARE
 		charset[i++] = c++;
+	charset[i++] = 0x1f7f0;	// HEAVY EQUALS SIGN
 // 1F800..1F8FF; Supplemental Arrows-C
 	c = 0x1f800;		// from LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD
 	while (c <= 0x1f80b)	// ..to DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
@@ -2327,16 +2518,13 @@ void init()
 	c = 0x1f890;		// from LEFTWARDS TRIANGLE ARROWHEAD
 	while (c <= 0x1f8ad)	// ..to WHITE ARROW SHAFT WIDTH TWO THIRDS
 		charset[i++] = c++;
-	charset[i++] = 0x1f8b0;	// ARROW POINTING UPWARDS THEN NORTH WEST
-	charset[i++] = 0x1f8b1;	// ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST
+	c = 0x1f8b0;		// from ARROW POINTING UPWARDS THEN NORTH WEST
+	while (c <= 0x1f8bb)	// ..to SOUTH WEST ARROW FROM BAR
+		charset[i++] = c++;
+	charset[i++] = 0x1f8c0;	// LEFTWARDS ARROW FROM DOWNWARDS ARROW
+	charset[i++] = 0x1f8c1;	// RIGHTWARDS ARROW FROM DOWNWARDS ARROW
 // 1F900..1F9FF; Supplemental Symbols and Pictographs
 	c = 0x1f900;		// from CIRCLED CROSS FORMEE WITH FOUR DOTS
-	while (c <= 0x1f978)	// ..to DISGUISED FACE
-		charset[i++] = c++;
-	c = 0x1f97a;		// from FACE WITH PLEADING EYES
-	while (c <= 0x1f9cb)	// ..to BUBBLE TEA
-		charset[i++] = c++;
-	c = 0x1f9cd;		// from STANDING PERSON
 	while (c <= 0x1f9ff)	// ..to NAZAR AMULET
 		charset[i++] = c++;
 // 1FA00..1FA6F; Chess Symbols
@@ -2348,41 +2536,37 @@ void init()
 		charset[i++] = c++;
 // 1FA70..1FAFF; Symbols and Pictographs Extended-A
 	c = 0x1fa70;		// from BALLET SHOES
-	while (c <= 0x1fa74)	// ..to THONG SANDAL
+	while (c <= 0x1fa7c)	// ..to CRUTCH
 		charset[i++] = c++;
-	charset[i++] = 0x1fa78;	// DROP OF BLOOD
-	charset[i++] = 0x1fa7a;	// STETHOSCOPE
 	c = 0x1fa80;		// from YO-YO
-	while (c <= 0x1fa86)	// ..to NESTING DOLLS
+	while (c <= 0x1fa89)	// ..to HARP
 		charset[i++] = c++;
-	c = 0x1fa90;		// from RINGED PLANET
-	while (c <= 0x1faa8)	// ..to ROCK
+	c = 0x1fa8f;		// from SHOVEL
+	while (c <= 0x1fac6)	// ..to FINGERPRINT
 		charset[i++] = c++;
-	c = 0x1fab0;		// from FLY
-	while (c <= 0x1fab6)	// ..to FEATHER
+	c = 0x1face;		// from MOOSE
+	while (c <= 0x1fadc)	// ..to ROOT VEGETABLE
 		charset[i++] = c++;
-	charset[i++] = 0x1fac0;	// ANATOMICAL HEART
-	charset[i++] = 0x1fac2;	// PEOPLE HUGGING
-	c = 0x1fad0;		// from BLUEBERRIES
-	while (c <= 0x1fad6)	// ..to TEAPOT
+	c = 0x1fadf;		// from SPLATTER
+	while (c <= 0x1fae9)	// ..to FACE WITH BAGS UNDER EYES
+		charset[i++] = c++;
+	c = 0x1faf0;		// from HAND WITH INDEX FINGER AND THUMB CROSSED
+	while (c <= 0x1faf8)	// ..to RIGHTWARDS PUSHING HAND
 		charset[i++] = c++;
 // 1FB00..1FBFF; Symbols for Legacy Computing
 	c = 0x1fb00;		// from BLOCK SEXTANT-1
 	while (c <= 0x1fb92)	// ..to UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
 		charset[i++] = c++;
 	c = 0x1fb94;		// from LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK
-	while (c <= 0x1fbca)	// ..to WHITE UP-POINTING CHEVRON
-		charset[i++] = c++;
-	c = 0x1fbf0;		// from SEGMENTED DIGIT ZERO
 	while (c <= 0x1fbf9)	// ..to SEGMENTED DIGIT NINE
 		charset[i++] = c++;
 // 20000..2A6DF; CJK Unified Ideographs Extension B
 	c = 0x20000;		// from <CJK Ideograph Extension B, First>
-	while (c <= 0x2a6dd)	// ..to <CJK Ideograph Extension B, Last>
+	while (c <= 0x2a6df)	// ..to <CJK Ideograph Extension B, Last>
 		charset[i++] = c++;
 // 2A700..2B73F; CJK Unified Ideographs Extension C
 	c = 0x2a700;		// from <CJK Ideograph Extension C, First>
-	while (c <= 0x2b734)	// ..to <CJK Ideograph Extension C, Last>
+	while (c <= 0x2b739)	// ..to <CJK Ideograph Extension C, Last>
 		charset[i++] = c++;
 // 2B740..2B81F; CJK Unified Ideographs Extension D
 	c = 0x2b740;		// from <CJK Ideograph Extension D, First>
@@ -2396,6 +2580,10 @@ void init()
 	c = 0x2ceb0;		// from <CJK Ideograph Extension F, First>
 	while (c <= 0x2ebe0)	// ..to <CJK Ideograph Extension F, Last>
 		charset[i++] = c++;
+// 2EBF0..2EE5F; CJK Unified Ideographs Extension I
+	c = 0x2ebf0;		// from <CJK Ideograph Extension I, First>
+	while (c <= 0x2ee5d)	// ..to <CJK Ideograph Extension I, Last>
+		charset[i++] = c++;
 // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
 	c = 0x2f800;		// from CJK COMPATIBILITY IDEOGRAPH-2F800
 	while (c <= 0x2fa1d)	// ..to CJK COMPATIBILITY IDEOGRAPH-2FA1D
@@ -2404,6 +2592,10 @@ void init()
 	c = 0x30000;		// from <CJK Ideograph Extension G, First>
 	while (c <= 0x3134a)	// ..to <CJK Ideograph Extension G, Last>
 		charset[i++] = c++;
+// 31350..323AF; CJK Unified Ideographs Extension H
+	c = 0x31350;		// from <CJK Ideograph Extension H, First>
+	while (c <= 0x323af)	// ..to <CJK Ideograph Extension H, Last>
+		charset[i++] = c++;
 // E0000..E007F; Tags
 	c = 0xe0020;		// from TAG SPACE
 	while (c <= 0xe007f)	// ..to CANCEL TAG

data/wordlists/wp-exploitable-plugins.txt

@@ -10,7 +10,6 @@ bulletproof-security
 catch-themes-demo-import
 chopslider
 custom-registration-form-builder-with-submission-manager
-depicter
 download-manager
 drag-and-drop-multiple-file-upload-contact-form-7
 dukapress
@@ -30,6 +29,7 @@ learnpress
 loginizer
 masterstudy-lms-learning-management-system
 modern-events-calendar-lite
+modern-events-calendar-lite
 nextgen-gallery
 ninja-forms
 paid-memberships-pro
@@ -48,11 +48,7 @@ simple-file-list
 slideshow-gallery
 sp-client-document-manager
 subscribe-to-comments
-suretriggers
-tatsu
 ultimate-member
-user-registration
-user-registration-pro
 website-contact-form-with-file-upload
 woocommerce-abandoned-cart
 woocommerce-payments
@@ -60,17 +56,18 @@ wordpress-mobile-pack
 wordpress-popular-posts
 work-the-flow-file-upload
 wp-automatic
-wpdiscuz
 wp-easycart
 wp-fastest-cache
 wp-file-manager
 wp-gdpr-compliance
 wp-mobile-detector
 wp-mobile-edition
-wps-hide-login
-wpshop
+wp-symposium
 wp-symposium
 wp-time-capsule
-wptouch
 wp-ultimate-csv-importer
+wpdiscuz
+wps-hide-login
+wpshop
+wptouch
 wysija-newsletters

lib/rex/user_agent.rb

@@ -9,16 +9,16 @@ module Rex::UserAgent
   # Taken from https://www.whatismybrowser.com/guides/the-latest-user-agent/
   #
   COMMON_AGENTS = [
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36', # Chrome Windows
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36', # Chrome MacOS
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/147.0.0.0 Safari/537.36', # Chrome Windows
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/147.0.0.0 Safari/537.36', # Chrome MacOS
 
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36 Edg/131.0.2903.86', # Edge Windows
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/147.0.0.0 Safari/537.36 Edg/147.0.3912.98', # Edge Windows
 
-    'Mozilla/5.0 (iPad; CPU OS 17_7_2 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.4.1 Mobile/15E148 Safari/604.1', # Safari iPad
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 14_7_2) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.4.1 Safari/605.1.15', # Safari MacOS
+    'Mozilla/5.0 (iPad; CPU OS 18_7_8 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.0 Mobile/15E148 Safari/604.1', # Safari iPad
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 15_7_5) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.0 Safari/605.1.15', # Safari MacOS
 
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:133.0) Gecko/20100101 Firefox/133.0', # Firefox Windows
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 14.7; rv:133.0) Gecko/20100101 Firefox/133.0' # Firefox MacOS
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:150.0) Gecko/20100101 Firefox/150.0', # Firefox Windows
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 15.7; rv:150.0) Gecko/20100101 Firefox/150.0' # Firefox MacOS
   ]
 
   #