Land rapid7#16054, updates to JTR compatibility with logging

data/jtr/dumb16.conf

@@ -1,17 +1,22 @@
-# This  software is Copyright (c) 2012-2018 magnum, and it is hereby
+# This  software is Copyright (c) 2012-2020 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 v11
-# (there's 55,292 of them). Even if a fast format can exhaust two characters
+# 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
 # in 15 minutes, three characters would take 1.5 years...
 #
 # Note that these modes will handle --max-len differently than normal: They
 # will consider number of characters as opposed to number of bytes. This
 # means you can naturally just use e.g. --max-len=3 for generating all
 # three-character candidates (which may be up to 9 bytes each).
+#
+# Note that the (newer) cracking mode --subsets=full-unicode is way faster than
+# this external mode, although not as easy to adapt to smaller portions of the
+# Unicode space.  See doc/SUBSETS
+
 [List.External:Dumb16]
 int maxlength;            // Maximum password length to try
 int last;                 // Last character position, zero-based
@@ -163,7 +168,7 @@ void init()
 	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 <= 0x8bd)	// ..to ARABIC LETTER AFRICAN NOON
+	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
@@ -300,7 +305,7 @@ void init()
 	charset[i++] = 0xb48;	// ORIYA VOWEL SIGN AI
 	charset[i++] = 0xb4b;	// ORIYA VOWEL SIGN O
 	charset[i++] = 0xb4d;	// ORIYA SIGN VIRAMA
-	charset[i++] = 0xb56;	// ORIYA AI LENGTH MARK
+	charset[i++] = 0xb55;	// ORIYA SIGN OVERLINE
 	charset[i++] = 0xb57;	// ORIYA AU LENGTH MARK
 	charset[i++] = 0xb5c;	// ORIYA LETTER RRA
 	charset[i++] = 0xb5d;	// ORIYA LETTER RHA
@@ -373,7 +378,7 @@ void init()
 	c = 0xc66;		// from TELUGU DIGIT ZERO
 	while (c <= 0xc6f)	// ..to TELUGU DIGIT NINE
 		charset[i++] = c++;
-	c = 0xc78;		// from TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR
+	c = 0xc77;		// from TELUGU SIGN SIDDHAM
 	while (c <= 0xc7f)	// ..to TELUGU SIGN TUUMU
 		charset[i++] = c++;
 // 0C80..0CFF; Kannada
@@ -411,9 +416,6 @@ void init()
 	charset[i++] = 0xcf2;	// KANNADA SIGN UPADHMANIYA
 // 0D00..0D7F; Malayalam
 	c = 0xd00;		// from MALAYALAM SIGN COMBINING ANUSVARA ABOVE
-	while (c <= 0xd03)	// ..to MALAYALAM SIGN VISARGA
-		charset[i++] = c++;
-	c = 0xd05;		// from MALAYALAM LETTER A
 	while (c <= 0xd0c)	// ..to MALAYALAM LETTER VOCALIC L
 		charset[i++] = c++;
 	charset[i++] = 0xd0e;	// MALAYALAM LETTER E
@@ -433,7 +435,7 @@ void init()
 	while (c <= 0xd7f)	// ..to MALAYALAM LETTER CHILLU K
 		charset[i++] = c++;
 // 0D80..0DFF; Sinhala
-	charset[i++] = 0xd82;	// SINHALA SIGN ANUSVARAYA
+	charset[i++] = 0xd81;	// SINHALA SIGN CANDRABINDU
 	charset[i++] = 0xd83;	// SINHALA SIGN VISARGAYA
 	c = 0xd85;		// from SINHALA LETTER AYANNA
 	while (c <= 0xd96)	// ..to SINHALA LETTER AUYANNA
@@ -468,23 +470,15 @@ void init()
 // 0E80..0EFF; Lao
 	charset[i++] = 0xe81;	// LAO LETTER KO
 	charset[i++] = 0xe82;	// LAO LETTER KHO SUNG
-	charset[i++] = 0xe87;	// LAO LETTER NGO
-	charset[i++] = 0xe88;	// LAO LETTER CO
-	c = 0xe94;		// from LAO LETTER DO
-	while (c <= 0xe97)	// ..to LAO LETTER THO TAM
-		charset[i++] = c++;
-	c = 0xe99;		// from LAO LETTER NO
-	while (c <= 0xe9f)	// ..to LAO LETTER FO SUNG
-		charset[i++] = c++;
-	charset[i++] = 0xea1;	// LAO LETTER MO
-	charset[i++] = 0xea3;	// LAO LETTER LO LING
-	charset[i++] = 0xeaa;	// LAO LETTER SO SUNG
-	charset[i++] = 0xeab;	// LAO LETTER HO SUNG
-	c = 0xead;		// from LAO LETTER O
-	while (c <= 0xeb9)	// ..to LAO VOWEL SIGN UU
-		charset[i++] = c++;
-	charset[i++] = 0xebb;	// LAO VOWEL SIGN MAI KON
-	charset[i++] = 0xebd;	// LAO SEMIVOWEL SIGN NYO
+	c = 0xe86;		// from LAO LETTER PALI GHA
+	while (c <= 0xe8a)	// ..to LAO LETTER SO TAM
+		charset[i++] = c++;
+	c = 0xe8c;		// from LAO LETTER PALI JHA
+	while (c <= 0xea3)	// ..to LAO LETTER LO LING
+		charset[i++] = c++;
+	c = 0xea7;		// from LAO LETTER WO
+	while (c <= 0xebd)	// ..to LAO SEMIVOWEL SIGN NYO
+		charset[i++] = c++;
 	c = 0xec0;		// from LAO VOWEL SIGN E
 	while (c <= 0xec4)	// ..to LAO VOWEL SIGN AI
 		charset[i++] = c++;
@@ -710,7 +704,7 @@ void init()
 		charset[i++] = c++;
 // 1AB0..1AFF; Combining Diacritical Marks Extended
 	c = 0x1ab0;		// from COMBINING DOUBLED CIRCUMFLEX ACCENT
-	while (c <= 0x1abe)	// ..to COMBINING PARENTHESES OVERLAY
+	while (c <= 0x1ac0)	// ..to COMBINING LATIN SMALL LETTER TURNED W BELOW
 		charset[i++] = c++;
 // 1B00..1B7F; Balinese
 	c = 0x1b00;		// from BALINESE SIGN ULU RICEM
@@ -759,7 +753,7 @@ void init()
 		charset[i++] = c++;
 // 1CD0..1CFF; Vedic Extensions
 	c = 0x1cd0;		// from VEDIC TONE KARSHANA
-	while (c <= 0x1cf9)	// ..to VEDIC TONE DOUBLE RING ABOVE
+	while (c <= 0x1cfa)	// ..to VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA
 		charset[i++] = c++;
 // 1D00..1D7F; Phonetic Extensions
 	c = 0x1d00;		// from LATIN LETTER SMALL CAPITAL A
@@ -926,11 +920,8 @@ void init()
 	c = 0x2b76;		// from NORTH WEST TRIANGLE-HEADED ARROW TO BAR
 	while (c <= 0x2b95)	// ..to RIGHTWARDS BLACK ARROW
 		charset[i++] = c++;
-	c = 0x2b98;		// from THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD
-	while (c <= 0x2bc8)	// ..to BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
-		charset[i++] = c++;
-	c = 0x2bca;		// from TOP HALF BLACK CIRCLE
-	while (c <= 0x2bfe)	// ..to REVERSED RIGHT ANGLE
+	c = 0x2b97;		// from SYMBOL FOR TYPE A ELECTRONICS
+	while (c <= 0x2bff)	// ..to HELLSCHREIBER PAUSE SYMBOL
 		charset[i++] = c++;
 // 2C00..2C5F; Glagolitic
 	c = 0x2c00;		// from GLAGOLITIC CAPITAL LETTER AZU
@@ -998,7 +989,7 @@ void init()
 		charset[i++] = c++;
 // 2E00..2E7F; Supplemental Punctuation
 	c = 0x2e00;		// from RIGHT ANGLE SUBSTITUTION MARKER
-	while (c <= 0x2e4e)	// ..to PUNCTUS ELEVATUS MARK
+	while (c <= 0x2e52)	// ..to TIRONIAN SIGN CAPITAL ET
 		charset[i++] = c++;
 // 2E80..2EFF; CJK Radicals Supplement
 	c = 0x2e80;		// from CJK RADICAL REPEAT
@@ -1044,7 +1035,7 @@ void init()
 		charset[i++] = c++;
 // 31A0..31BF; Bopomofo Extended
 	c = 0x31a0;		// from BOPOMOFO LETTER BU
-	while (c <= 0x31ba)	// ..to BOPOMOFO LETTER ZY
+	while (c <= 0x31bf)	// ..to BOPOMOFO LETTER AH
 		charset[i++] = c++;
 // 31C0..31EF; CJK Strokes
 	c = 0x31c0;		// from CJK STROKE T
@@ -1059,23 +1050,23 @@ void init()
 	while (c <= 0x321e)	// ..to PARENTHESIZED KOREAN CHARACTER O HU
 		charset[i++] = c++;
 	c = 0x3220;		// from PARENTHESIZED IDEOGRAPH ONE
-	while (c <= 0x32fe)	// ..to CIRCLED KATAKANA WO
+	while (c <= 0x32ff)	// ..to SQUARE ERA NAME REIWA
 		charset[i++] = c++;
 // 3300..33FF; CJK Compatibility
 	c = 0x3300;		// from SQUARE APAATO
 	while (c <= 0x33ff)	// ..to SQUARE GAL
 		charset[i++] = c++;
 // 3400..4DBF; CJK Unified Ideographs Extension A
 	c = 0x3400;		// from <CJK Ideograph Extension A, First>
-	while (c <= 0x4db5)	// ..to <CJK Ideograph Extension A, Last>
+	while (c <= 0x4dbf)	// ..to <CJK Ideograph Extension A, Last>
 		charset[i++] = c++;
 // 4DC0..4DFF; Yijing Hexagram Symbols
 	c = 0x4dc0;		// from HEXAGRAM FOR THE CREATIVE HEAVEN
 	while (c <= 0x4dff)	// ..to HEXAGRAM FOR BEFORE COMPLETION
 		charset[i++] = c++;
 // 4E00..9FFF; CJK Unified Ideographs
 	c = 0x4e00;		// from <CJK Ideograph, First>
-	while (c <= 0x9fef)	// ..to <CJK Ideograph, Last>
+	while (c <= 0x9ffc)	// ..to <CJK Ideograph, Last>
 		charset[i++] = c++;
 // A000..A48F; Yi Syllables
 	c = 0xa000;		// from YI SYLLABLE IT
@@ -1107,14 +1098,17 @@ void init()
 		charset[i++] = c++;
 // A720..A7FF; Latin Extended-D
 	c = 0xa720;		// from MODIFIER LETTER STRESS AND HIGH TONE
-	while (c <= 0xa7b9)	// ..to LATIN SMALL LETTER U WITH STROKE
+	while (c <= 0xa7bf)	// ..to LATIN SMALL LETTER GLOTTAL U
+		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++] = c++;
-	c = 0xa7f7;		// from LATIN EPIGRAPHIC LETTER SIDEWAYS I
+	c = 0xa7f5;		// from LATIN CAPITAL LETTER REVERSED HALF H
 	while (c <= 0xa7ff)	// ..to LATIN EPIGRAPHIC LETTER ARCHAIC M
 		charset[i++] = c++;
 // A800..A82F; Syloti Nagri
 	c = 0xa800;		// from SYLOTI NAGRI LETTER A
-	while (c <= 0xa82b)	// ..to SYLOTI NAGRI POETRY MARK-4
+	while (c <= 0xa82c)	// ..to SYLOTI NAGRI SIGN ALTERNATE HASANTA
 		charset[i++] = c++;
 // A830..A83F; Common Indic Number Forms
 	c = 0xa830;		// from NORTH INDIC FRACTION ONE QUARTER
@@ -1207,7 +1201,7 @@ void init()
 		charset[i++] = c++;
 // AB30..AB6F; Latin Extended-E
 	c = 0xab30;		// from LATIN SMALL LETTER BARRED ALPHA
-	while (c <= 0xab65)	// ..to GREEK LETTER SMALL CAPITAL OMEGA
+	while (c <= 0xab6b)	// ..to MODIFIER LETTER RIGHT TACK
 		charset[i++] = c++;
 // AB70..ABBF; Cherokee Supplement
 	c = 0xab70;		// from CHEROKEE SMALL LETTER A