Update report

Author: github-actions[bot]

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++;
-// 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
+// 0870..089F; Arabic Extended-B
+	c = 0x870;		// from ARABIC LETTER ALEF WITH ATTACHED FATHA
+	while (c <= 0x88e)	// ..to ARABIC VERTICAL TAIL
 		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++] = 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++;
-	c = 0x8d3;		// from ARABIC SMALL LOW WAW
+// 08A0..08FF; Arabic Extended-A
+	c = 0x8a0;		// from ARABIC LETTER BEH WITH SMALL V BELOW
 	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
@@ -406,14 +406,16 @@ 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++;
 	c = 0xce6;		// from KANNADA DIGIT ZERO
 	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