1402 lines
54 KiB
Plaintext
1402 lines
54 KiB
Plaintext
# This software is Copyright (c) 2012-2018 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 11) BMP version
|
|
#
|
|
# Number of candidates = 55,292 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
|
|
# 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).
|
|
[List.External:Repeats16]
|
|
int minlength, maxlength, maxc, length, c;
|
|
int charset[0x10000];
|
|
|
|
void init()
|
|
{
|
|
int i;
|
|
|
|
# Trigger UTF-32 handling in External mode
|
|
utf32 = 1;
|
|
|
|
if (req_minlen)
|
|
minlength = req_minlen;
|
|
else
|
|
minlength = 1;
|
|
|
|
if (req_maxlen)
|
|
maxlength = req_maxlen;
|
|
else
|
|
maxlength = cipher_limit;
|
|
|
|
/*
|
|
* This defines the character set. This is auto-generated from UnicodeData.txt
|
|
* and we skip control characters.
|
|
*/
|
|
i = 0;
|
|
// 0000..007F; Basic Latin
|
|
c = 0x20; // from SPACE
|
|
while (c <= 0x7e) // ..to TILDE
|
|
charset[i++] = c++;
|
|
// 0080..00FF; Latin-1 Supplement
|
|
c = 0xa0; // from NO-BREAK SPACE
|
|
while (c <= 0xff) // ..to LATIN SMALL LETTER Y WITH DIAERESIS
|
|
charset[i++] = c++;
|
|
// 0100..017F; Latin Extended-A
|
|
c = 0x100; // from LATIN CAPITAL LETTER A WITH MACRON
|
|
while (c <= 0x17f) // ..to LATIN SMALL LETTER LONG S
|
|
charset[i++] = c++;
|
|
// 0180..024F; Latin Extended-B
|
|
c = 0x180; // from LATIN SMALL LETTER B WITH STROKE
|
|
while (c <= 0x24f) // ..to LATIN SMALL LETTER Y WITH STROKE
|
|
charset[i++] = c++;
|
|
// 0250..02AF; IPA Extensions
|
|
c = 0x250; // from LATIN SMALL LETTER TURNED A
|
|
while (c <= 0x2af) // ..to LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
|
|
charset[i++] = c++;
|
|
// 02B0..02FF; Spacing Modifier Letters
|
|
c = 0x2b0; // from MODIFIER LETTER SMALL H
|
|
while (c <= 0x2ff) // ..to MODIFIER LETTER LOW LEFT ARROW
|
|
charset[i++] = c++;
|
|
// 0300..036F; Combining Diacritical Marks
|
|
c = 0x300; // from COMBINING GRAVE ACCENT
|
|
while (c <= 0x36f) // ..to COMBINING LATIN SMALL LETTER X
|
|
charset[i++] = c++;
|
|
// 0370..03FF; Greek and Coptic
|
|
c = 0x370; // from GREEK CAPITAL LETTER HETA
|
|
while (c <= 0x377) // ..to GREEK SMALL LETTER PAMPHYLIAN DIGAMMA
|
|
charset[i++] = c++;
|
|
c = 0x37a; // from GREEK YPOGEGRAMMENI
|
|
while (c <= 0x37f) // ..to GREEK CAPITAL LETTER YOT
|
|
charset[i++] = c++;
|
|
c = 0x384; // from GREEK TONOS
|
|
while (c <= 0x38a) // ..to GREEK CAPITAL LETTER IOTA WITH TONOS
|
|
charset[i++] = c++;
|
|
c = 0x38e; // from GREEK CAPITAL LETTER UPSILON WITH TONOS
|
|
while (c <= 0x3a1) // ..to GREEK CAPITAL LETTER RHO
|
|
charset[i++] = c++;
|
|
c = 0x3a3; // from GREEK CAPITAL LETTER SIGMA
|
|
while (c <= 0x3ff) // ..to GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL
|
|
charset[i++] = c++;
|
|
// 0400..04FF; Cyrillic
|
|
c = 0x400; // from CYRILLIC CAPITAL LETTER IE WITH GRAVE
|
|
while (c <= 0x4ff) // ..to CYRILLIC SMALL LETTER HA WITH STROKE
|
|
charset[i++] = c++;
|
|
// 0500..052F; Cyrillic Supplement
|
|
c = 0x500; // from CYRILLIC CAPITAL LETTER KOMI DE
|
|
while (c <= 0x52f) // ..to CYRILLIC SMALL LETTER EL WITH DESCENDER
|
|
charset[i++] = c++;
|
|
// 0530..058F; Armenian
|
|
c = 0x531; // from ARMENIAN CAPITAL LETTER AYB
|
|
while (c <= 0x556) // ..to ARMENIAN CAPITAL LETTER FEH
|
|
charset[i++] = c++;
|
|
c = 0x559; // from ARMENIAN MODIFIER LETTER LEFT HALF RING
|
|
while (c <= 0x58a) // ..to ARMENIAN HYPHEN
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x58d; // RIGHT-FACING ARMENIAN ETERNITY SIGN
|
|
charset[i++] = 0x58f; // ARMENIAN DRAM SIGN
|
|
// 0590..05FF; Hebrew
|
|
c = 0x591; // from HEBREW ACCENT ETNAHTA
|
|
while (c <= 0x5c7) // ..to HEBREW POINT QAMATS QATAN
|
|
charset[i++] = c++;
|
|
c = 0x5d0; // from HEBREW LETTER ALEF
|
|
while (c <= 0x5ea) // ..to HEBREW LETTER TAV
|
|
charset[i++] = c++;
|
|
c = 0x5ef; // from HEBREW YOD TRIANGLE
|
|
while (c <= 0x5f4) // ..to HEBREW PUNCTUATION GERSHAYIM
|
|
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
|
|
c = 0x700; // from SYRIAC END OF PARAGRAPH
|
|
while (c <= 0x70d) // ..to SYRIAC HARKLEAN ASTERISCUS
|
|
charset[i++] = c++;
|
|
c = 0x70f; // from SYRIAC ABBREVIATION MARK
|
|
while (c <= 0x74a) // ..to SYRIAC BARREKH
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x74d; // SYRIAC LETTER SOGDIAN ZHAIN
|
|
charset[i++] = 0x74f; // SYRIAC LETTER SOGDIAN FE
|
|
// 0750..077F; Arabic Supplement
|
|
c = 0x750; // from ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW
|
|
while (c <= 0x77f) // ..to ARABIC LETTER KAF WITH TWO DOTS ABOVE
|
|
charset[i++] = c++;
|
|
// 0780..07BF; Thaana
|
|
c = 0x780; // from THAANA LETTER HAA
|
|
while (c <= 0x7b1) // ..to THAANA LETTER NAA
|
|
charset[i++] = c++;
|
|
// 07C0..07FF; NKo
|
|
c = 0x7c0; // from NKO DIGIT ZERO
|
|
while (c <= 0x7fa) // ..to NKO LAJANYALAN
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x7fd; // NKO DANTAYALAN
|
|
charset[i++] = 0x7ff; // NKO TAMAN SIGN
|
|
// 0800..083F; Samaritan
|
|
c = 0x800; // from SAMARITAN LETTER ALAF
|
|
while (c <= 0x82d) // ..to SAMARITAN MARK NEQUDAA
|
|
charset[i++] = c++;
|
|
c = 0x830; // from SAMARITAN PUNCTUATION NEQUDAA
|
|
while (c <= 0x83e) // ..to SAMARITAN PUNCTUATION ANNAAU
|
|
charset[i++] = c++;
|
|
// 0840..085F; Mandaic
|
|
c = 0x840; // from MANDAIC LETTER HALQA
|
|
while (c <= 0x85b) // ..to MANDAIC GEMINATION MARK
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x85e; // MANDAIC PUNCTUATION
|
|
// 0860..086F; Syriac Supplement
|
|
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
|
|
charset[i++] = c++;
|
|
c = 0x8b6; // from ARABIC LETTER BEH WITH SMALL MEEM ABOVE
|
|
while (c <= 0x8bd) // ..to ARABIC LETTER AFRICAN NOON
|
|
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
|
|
c = 0x900; // from DEVANAGARI SIGN INVERTED CANDRABINDU
|
|
while (c <= 0x97f) // ..to DEVANAGARI LETTER BBA
|
|
charset[i++] = c++;
|
|
// 0980..09FF; Bengali
|
|
c = 0x980; // from BENGALI ANJI
|
|
while (c <= 0x983) // ..to BENGALI SIGN VISARGA
|
|
charset[i++] = c++;
|
|
c = 0x985; // from BENGALI LETTER A
|
|
while (c <= 0x98c) // ..to BENGALI LETTER VOCALIC L
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x98f; // BENGALI LETTER E
|
|
charset[i++] = 0x990; // BENGALI LETTER AI
|
|
c = 0x993; // from BENGALI LETTER O
|
|
while (c <= 0x9a8) // ..to BENGALI LETTER NA
|
|
charset[i++] = c++;
|
|
c = 0x9aa; // from BENGALI LETTER PA
|
|
while (c <= 0x9b0) // ..to BENGALI LETTER RA
|
|
charset[i++] = c++;
|
|
c = 0x9b6; // from BENGALI LETTER SHA
|
|
while (c <= 0x9b9) // ..to BENGALI LETTER HA
|
|
charset[i++] = c++;
|
|
c = 0x9bc; // from BENGALI SIGN NUKTA
|
|
while (c <= 0x9c4) // ..to BENGALI VOWEL SIGN VOCALIC RR
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x9c7; // BENGALI VOWEL SIGN E
|
|
charset[i++] = 0x9c8; // BENGALI VOWEL SIGN AI
|
|
c = 0x9cb; // from BENGALI VOWEL SIGN O
|
|
while (c <= 0x9ce) // ..to BENGALI LETTER KHANDA TA
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x9dc; // BENGALI LETTER RRA
|
|
charset[i++] = 0x9dd; // BENGALI LETTER RHA
|
|
c = 0x9df; // from BENGALI LETTER YYA
|
|
while (c <= 0x9e3) // ..to BENGALI VOWEL SIGN VOCALIC LL
|
|
charset[i++] = c++;
|
|
c = 0x9e6; // from BENGALI DIGIT ZERO
|
|
while (c <= 0x9fe) // ..to BENGALI SANDHI MARK
|
|
charset[i++] = c++;
|
|
// 0A00..0A7F; Gurmukhi
|
|
charset[i++] = 0xa01; // GURMUKHI SIGN ADAK BINDI
|
|
charset[i++] = 0xa03; // GURMUKHI SIGN VISARGA
|
|
c = 0xa05; // from GURMUKHI LETTER A
|
|
while (c <= 0xa0a) // ..to GURMUKHI LETTER UU
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xa0f; // GURMUKHI LETTER EE
|
|
charset[i++] = 0xa10; // GURMUKHI LETTER AI
|
|
c = 0xa13; // from GURMUKHI LETTER OO
|
|
while (c <= 0xa28) // ..to GURMUKHI LETTER NA
|
|
charset[i++] = c++;
|
|
c = 0xa2a; // from GURMUKHI LETTER PA
|
|
while (c <= 0xa30) // ..to GURMUKHI LETTER RA
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xa32; // GURMUKHI LETTER LA
|
|
charset[i++] = 0xa33; // GURMUKHI LETTER LLA
|
|
charset[i++] = 0xa35; // GURMUKHI LETTER VA
|
|
charset[i++] = 0xa36; // GURMUKHI LETTER SHA
|
|
charset[i++] = 0xa38; // GURMUKHI LETTER SA
|
|
charset[i++] = 0xa39; // GURMUKHI LETTER HA
|
|
c = 0xa3e; // from GURMUKHI VOWEL SIGN AA
|
|
while (c <= 0xa42) // ..to GURMUKHI VOWEL SIGN UU
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xa47; // GURMUKHI VOWEL SIGN EE
|
|
charset[i++] = 0xa48; // GURMUKHI VOWEL SIGN AI
|
|
charset[i++] = 0xa4b; // GURMUKHI VOWEL SIGN OO
|
|
charset[i++] = 0xa4d; // GURMUKHI SIGN VIRAMA
|
|
c = 0xa59; // from GURMUKHI LETTER KHHA
|
|
while (c <= 0xa5c) // ..to GURMUKHI LETTER RRA
|
|
charset[i++] = c++;
|
|
c = 0xa66; // from GURMUKHI DIGIT ZERO
|
|
while (c <= 0xa76) // ..to GURMUKHI ABBREVIATION SIGN
|
|
charset[i++] = c++;
|
|
// 0A80..0AFF; Gujarati
|
|
charset[i++] = 0xa81; // GUJARATI SIGN CANDRABINDU
|
|
charset[i++] = 0xa83; // GUJARATI SIGN VISARGA
|
|
c = 0xa85; // from GUJARATI LETTER A
|
|
while (c <= 0xa8d) // ..to GUJARATI VOWEL CANDRA E
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xa8f; // GUJARATI LETTER E
|
|
charset[i++] = 0xa91; // GUJARATI VOWEL CANDRA O
|
|
c = 0xa93; // from GUJARATI LETTER O
|
|
while (c <= 0xaa8) // ..to GUJARATI LETTER NA
|
|
charset[i++] = c++;
|
|
c = 0xaaa; // from GUJARATI LETTER PA
|
|
while (c <= 0xab0) // ..to GUJARATI LETTER RA
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xab2; // GUJARATI LETTER LA
|
|
charset[i++] = 0xab3; // GUJARATI LETTER LLA
|
|
c = 0xab5; // from GUJARATI LETTER VA
|
|
while (c <= 0xab9) // ..to GUJARATI LETTER HA
|
|
charset[i++] = c++;
|
|
c = 0xabc; // from GUJARATI SIGN NUKTA
|
|
while (c <= 0xac5) // ..to GUJARATI VOWEL SIGN CANDRA E
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xac7; // GUJARATI VOWEL SIGN E
|
|
charset[i++] = 0xac9; // GUJARATI VOWEL SIGN CANDRA O
|
|
charset[i++] = 0xacb; // GUJARATI VOWEL SIGN O
|
|
charset[i++] = 0xacd; // GUJARATI SIGN VIRAMA
|
|
c = 0xae0; // from GUJARATI LETTER VOCALIC RR
|
|
while (c <= 0xae3) // ..to GUJARATI VOWEL SIGN VOCALIC LL
|
|
charset[i++] = c++;
|
|
c = 0xae6; // from GUJARATI DIGIT ZERO
|
|
while (c <= 0xaf1) // ..to GUJARATI RUPEE SIGN
|
|
charset[i++] = c++;
|
|
c = 0xaf9; // from GUJARATI LETTER ZHA
|
|
while (c <= 0xaff) // ..to GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
|
|
charset[i++] = c++;
|
|
// 0B00..0B7F; Oriya
|
|
charset[i++] = 0xb01; // ORIYA SIGN CANDRABINDU
|
|
charset[i++] = 0xb03; // ORIYA SIGN VISARGA
|
|
c = 0xb05; // from ORIYA LETTER A
|
|
while (c <= 0xb0c) // ..to ORIYA LETTER VOCALIC L
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xb0f; // ORIYA LETTER E
|
|
charset[i++] = 0xb10; // ORIYA LETTER AI
|
|
c = 0xb13; // from ORIYA LETTER O
|
|
while (c <= 0xb28) // ..to ORIYA LETTER NA
|
|
charset[i++] = c++;
|
|
c = 0xb2a; // from ORIYA LETTER PA
|
|
while (c <= 0xb30) // ..to ORIYA LETTER RA
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xb32; // ORIYA LETTER LA
|
|
charset[i++] = 0xb33; // ORIYA LETTER LLA
|
|
c = 0xb35; // from ORIYA LETTER VA
|
|
while (c <= 0xb39) // ..to ORIYA LETTER HA
|
|
charset[i++] = c++;
|
|
c = 0xb3c; // from ORIYA SIGN NUKTA
|
|
while (c <= 0xb44) // ..to ORIYA VOWEL SIGN VOCALIC RR
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xb47; // ORIYA VOWEL SIGN E
|
|
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++] = 0xb57; // ORIYA AU LENGTH MARK
|
|
charset[i++] = 0xb5c; // ORIYA LETTER RRA
|
|
charset[i++] = 0xb5d; // ORIYA LETTER RHA
|
|
c = 0xb5f; // from ORIYA LETTER YYA
|
|
while (c <= 0xb63) // ..to ORIYA VOWEL SIGN VOCALIC LL
|
|
charset[i++] = c++;
|
|
c = 0xb66; // from ORIYA DIGIT ZERO
|
|
while (c <= 0xb77) // ..to ORIYA FRACTION THREE SIXTEENTHS
|
|
charset[i++] = c++;
|
|
// 0B80..0BFF; Tamil
|
|
charset[i++] = 0xb82; // TAMIL SIGN ANUSVARA
|
|
charset[i++] = 0xb83; // TAMIL SIGN VISARGA
|
|
c = 0xb85; // from TAMIL LETTER A
|
|
while (c <= 0xb8a) // ..to TAMIL LETTER UU
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xb8e; // TAMIL LETTER E
|
|
charset[i++] = 0xb90; // TAMIL LETTER AI
|
|
c = 0xb92; // from TAMIL LETTER O
|
|
while (c <= 0xb95) // ..to TAMIL LETTER KA
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xb99; // TAMIL LETTER NGA
|
|
charset[i++] = 0xb9a; // TAMIL LETTER CA
|
|
charset[i++] = 0xb9e; // TAMIL LETTER NYA
|
|
charset[i++] = 0xb9f; // TAMIL LETTER TTA
|
|
charset[i++] = 0xba3; // TAMIL LETTER NNA
|
|
charset[i++] = 0xba4; // TAMIL LETTER TA
|
|
charset[i++] = 0xba8; // TAMIL LETTER NA
|
|
charset[i++] = 0xbaa; // TAMIL LETTER PA
|
|
c = 0xbae; // from TAMIL LETTER MA
|
|
while (c <= 0xbb9) // ..to TAMIL LETTER HA
|
|
charset[i++] = c++;
|
|
c = 0xbbe; // from TAMIL VOWEL SIGN AA
|
|
while (c <= 0xbc2) // ..to TAMIL VOWEL SIGN UU
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xbc6; // TAMIL VOWEL SIGN E
|
|
charset[i++] = 0xbc8; // TAMIL VOWEL SIGN AI
|
|
c = 0xbca; // from TAMIL VOWEL SIGN O
|
|
while (c <= 0xbcd) // ..to TAMIL SIGN VIRAMA
|
|
charset[i++] = c++;
|
|
c = 0xbe6; // from TAMIL DIGIT ZERO
|
|
while (c <= 0xbfa) // ..to TAMIL NUMBER SIGN
|
|
charset[i++] = c++;
|
|
// 0C00..0C7F; Telugu
|
|
c = 0xc00; // from TELUGU SIGN COMBINING CANDRABINDU ABOVE
|
|
while (c <= 0xc0c) // ..to TELUGU LETTER VOCALIC L
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xc0e; // TELUGU LETTER E
|
|
charset[i++] = 0xc10; // TELUGU LETTER AI
|
|
c = 0xc12; // from TELUGU LETTER O
|
|
while (c <= 0xc28) // ..to TELUGU LETTER NA
|
|
charset[i++] = c++;
|
|
c = 0xc2a; // from TELUGU LETTER PA
|
|
while (c <= 0xc39) // ..to TELUGU LETTER HA
|
|
charset[i++] = c++;
|
|
c = 0xc3d; // from TELUGU SIGN AVAGRAHA
|
|
while (c <= 0xc44) // ..to TELUGU VOWEL SIGN VOCALIC RR
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xc46; // TELUGU VOWEL SIGN E
|
|
charset[i++] = 0xc48; // TELUGU VOWEL SIGN AI
|
|
c = 0xc4a; // from TELUGU VOWEL SIGN O
|
|
while (c <= 0xc4d) // ..to TELUGU SIGN VIRAMA
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xc55; // TELUGU LENGTH MARK
|
|
charset[i++] = 0xc56; // TELUGU AI LENGTH MARK
|
|
charset[i++] = 0xc58; // TELUGU LETTER TSA
|
|
charset[i++] = 0xc5a; // TELUGU LETTER RRRA
|
|
c = 0xc60; // from TELUGU LETTER VOCALIC RR
|
|
while (c <= 0xc63) // ..to TELUGU VOWEL SIGN VOCALIC LL
|
|
charset[i++] = c++;
|
|
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
|
|
while (c <= 0xc7f) // ..to TELUGU SIGN TUUMU
|
|
charset[i++] = c++;
|
|
// 0C80..0CFF; Kannada
|
|
c = 0xc80; // from KANNADA SIGN SPACING CANDRABINDU
|
|
while (c <= 0xc8c) // ..to KANNADA LETTER VOCALIC L
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xc8e; // KANNADA LETTER E
|
|
charset[i++] = 0xc90; // KANNADA LETTER AI
|
|
c = 0xc92; // from KANNADA LETTER O
|
|
while (c <= 0xca8) // ..to KANNADA LETTER NA
|
|
charset[i++] = c++;
|
|
c = 0xcaa; // from KANNADA LETTER PA
|
|
while (c <= 0xcb3) // ..to KANNADA LETTER LLA
|
|
charset[i++] = c++;
|
|
c = 0xcb5; // from KANNADA LETTER VA
|
|
while (c <= 0xcb9) // ..to KANNADA LETTER HA
|
|
charset[i++] = c++;
|
|
c = 0xcbc; // from KANNADA SIGN NUKTA
|
|
while (c <= 0xcc4) // ..to KANNADA VOWEL SIGN VOCALIC RR
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xcc6; // KANNADA VOWEL SIGN E
|
|
charset[i++] = 0xcc8; // KANNADA VOWEL SIGN AI
|
|
c = 0xcca; // from KANNADA VOWEL SIGN O
|
|
while (c <= 0xccd) // ..to KANNADA SIGN VIRAMA
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xcd5; // KANNADA LENGTH MARK
|
|
charset[i++] = 0xcd6; // KANNADA AI LENGTH MARK
|
|
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
|
|
// 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
|
|
charset[i++] = 0xd10; // MALAYALAM LETTER AI
|
|
c = 0xd12; // from MALAYALAM LETTER O
|
|
while (c <= 0xd44) // ..to MALAYALAM VOWEL SIGN VOCALIC RR
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xd46; // MALAYALAM VOWEL SIGN E
|
|
charset[i++] = 0xd48; // MALAYALAM VOWEL SIGN AI
|
|
c = 0xd4a; // from MALAYALAM VOWEL SIGN O
|
|
while (c <= 0xd4f) // ..to MALAYALAM SIGN PARA
|
|
charset[i++] = c++;
|
|
c = 0xd54; // from MALAYALAM LETTER CHILLU M
|
|
while (c <= 0xd63) // ..to MALAYALAM VOWEL SIGN VOCALIC LL
|
|
charset[i++] = c++;
|
|
c = 0xd66; // from MALAYALAM DIGIT ZERO
|
|
while (c <= 0xd7f) // ..to MALAYALAM LETTER CHILLU K
|
|
charset[i++] = c++;
|
|
// 0D80..0DFF; Sinhala
|
|
charset[i++] = 0xd82; // SINHALA SIGN ANUSVARAYA
|
|
charset[i++] = 0xd83; // SINHALA SIGN VISARGAYA
|
|
c = 0xd85; // from SINHALA LETTER AYANNA
|
|
while (c <= 0xd96) // ..to SINHALA LETTER AUYANNA
|
|
charset[i++] = c++;
|
|
c = 0xd9a; // from SINHALA LETTER ALPAPRAANA KAYANNA
|
|
while (c <= 0xdb1) // ..to SINHALA LETTER DANTAJA NAYANNA
|
|
charset[i++] = c++;
|
|
c = 0xdb3; // from SINHALA LETTER SANYAKA DAYANNA
|
|
while (c <= 0xdbb) // ..to SINHALA LETTER RAYANNA
|
|
charset[i++] = c++;
|
|
c = 0xdc0; // from SINHALA LETTER VAYANNA
|
|
while (c <= 0xdc6) // ..to SINHALA LETTER FAYANNA
|
|
charset[i++] = c++;
|
|
c = 0xdcf; // from SINHALA VOWEL SIGN AELA-PILLA
|
|
while (c <= 0xdd4) // ..to SINHALA VOWEL SIGN KETTI PAA-PILLA
|
|
charset[i++] = c++;
|
|
c = 0xdd8; // from SINHALA VOWEL SIGN GAETTA-PILLA
|
|
while (c <= 0xddf) // ..to SINHALA VOWEL SIGN GAYANUKITTA
|
|
charset[i++] = c++;
|
|
c = 0xde6; // from SINHALA LITH DIGIT ZERO
|
|
while (c <= 0xdef) // ..to SINHALA LITH DIGIT NINE
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xdf2; // SINHALA VOWEL SIGN DIGA GAETTA-PILLA
|
|
charset[i++] = 0xdf4; // SINHALA PUNCTUATION KUNDDALIYA
|
|
// 0E00..0E7F; Thai
|
|
c = 0xe01; // from THAI CHARACTER KO KAI
|
|
while (c <= 0xe3a) // ..to THAI CHARACTER PHINTHU
|
|
charset[i++] = c++;
|
|
c = 0xe3f; // from THAI CURRENCY SYMBOL BAHT
|
|
while (c <= 0xe5b) // ..to THAI CHARACTER KHOMUT
|
|
charset[i++] = c++;
|
|
// 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 = 0xec0; // from LAO VOWEL SIGN E
|
|
while (c <= 0xec4) // ..to LAO VOWEL SIGN AI
|
|
charset[i++] = c++;
|
|
c = 0xec8; // from LAO TONE MAI EK
|
|
while (c <= 0xecd) // ..to LAO NIGGAHITA
|
|
charset[i++] = c++;
|
|
c = 0xed0; // from LAO DIGIT ZERO
|
|
while (c <= 0xed9) // ..to LAO DIGIT NINE
|
|
charset[i++] = c++;
|
|
c = 0xedc; // from LAO HO NO
|
|
while (c <= 0xedf) // ..to LAO LETTER KHMU NYO
|
|
charset[i++] = c++;
|
|
// 0F00..0FFF; Tibetan
|
|
c = 0xf00; // from TIBETAN SYLLABLE OM
|
|
while (c <= 0xf47) // ..to TIBETAN LETTER JA
|
|
charset[i++] = c++;
|
|
c = 0xf49; // from TIBETAN LETTER NYA
|
|
while (c <= 0xf6c) // ..to TIBETAN LETTER RRA
|
|
charset[i++] = c++;
|
|
c = 0xf71; // from TIBETAN VOWEL SIGN AA
|
|
while (c <= 0xf97) // ..to TIBETAN SUBJOINED LETTER JA
|
|
charset[i++] = c++;
|
|
c = 0xf99; // from TIBETAN SUBJOINED LETTER NYA
|
|
while (c <= 0xfbc) // ..to TIBETAN SUBJOINED LETTER FIXED-FORM RA
|
|
charset[i++] = c++;
|
|
c = 0xfbe; // from TIBETAN KU RU KHA
|
|
while (c <= 0xfcc) // ..to TIBETAN SYMBOL NOR BU BZHI -KHYIL
|
|
charset[i++] = c++;
|
|
c = 0xfce; // from TIBETAN SIGN RDEL NAG RDEL DKAR
|
|
while (c <= 0xfda) // ..to TIBETAN MARK TRAILING MCHAN RTAGS
|
|
charset[i++] = c++;
|
|
// 1000..109F; Myanmar
|
|
c = 0x1000; // from MYANMAR LETTER KA
|
|
while (c <= 0x109f) // ..to MYANMAR SYMBOL SHAN EXCLAMATION
|
|
charset[i++] = c++;
|
|
// 10A0..10FF; Georgian
|
|
c = 0x10a0; // from GEORGIAN CAPITAL LETTER AN
|
|
while (c <= 0x10c5) // ..to GEORGIAN CAPITAL LETTER HOE
|
|
charset[i++] = c++;
|
|
c = 0x10d0; // from GEORGIAN LETTER AN
|
|
while (c <= 0x10ff) // ..to GEORGIAN LETTER LABIAL SIGN
|
|
charset[i++] = c++;
|
|
// 1100..11FF; Hangul Jamo
|
|
c = 0x1100; // from HANGUL CHOSEONG KIYEOK
|
|
while (c <= 0x11ff) // ..to HANGUL JONGSEONG SSANGNIEUN
|
|
charset[i++] = c++;
|
|
// 1200..137F; Ethiopic
|
|
c = 0x1200; // from ETHIOPIC SYLLABLE HA
|
|
while (c <= 0x1248) // ..to ETHIOPIC SYLLABLE QWA
|
|
charset[i++] = c++;
|
|
c = 0x124a; // from ETHIOPIC SYLLABLE QWI
|
|
while (c <= 0x124d) // ..to ETHIOPIC SYLLABLE QWE
|
|
charset[i++] = c++;
|
|
c = 0x1250; // from ETHIOPIC SYLLABLE QHA
|
|
while (c <= 0x1256) // ..to ETHIOPIC SYLLABLE QHO
|
|
charset[i++] = c++;
|
|
c = 0x125a; // from ETHIOPIC SYLLABLE QHWI
|
|
while (c <= 0x125d) // ..to ETHIOPIC SYLLABLE QHWE
|
|
charset[i++] = c++;
|
|
c = 0x1260; // from ETHIOPIC SYLLABLE BA
|
|
while (c <= 0x1288) // ..to ETHIOPIC SYLLABLE XWA
|
|
charset[i++] = c++;
|
|
c = 0x128a; // from ETHIOPIC SYLLABLE XWI
|
|
while (c <= 0x128d) // ..to ETHIOPIC SYLLABLE XWE
|
|
charset[i++] = c++;
|
|
c = 0x1290; // from ETHIOPIC SYLLABLE NA
|
|
while (c <= 0x12b0) // ..to ETHIOPIC SYLLABLE KWA
|
|
charset[i++] = c++;
|
|
c = 0x12b2; // from ETHIOPIC SYLLABLE KWI
|
|
while (c <= 0x12b5) // ..to ETHIOPIC SYLLABLE KWE
|
|
charset[i++] = c++;
|
|
c = 0x12b8; // from ETHIOPIC SYLLABLE KXA
|
|
while (c <= 0x12be) // ..to ETHIOPIC SYLLABLE KXO
|
|
charset[i++] = c++;
|
|
c = 0x12c2; // from ETHIOPIC SYLLABLE KXWI
|
|
while (c <= 0x12c5) // ..to ETHIOPIC SYLLABLE KXWE
|
|
charset[i++] = c++;
|
|
c = 0x12c8; // from ETHIOPIC SYLLABLE WA
|
|
while (c <= 0x12d6) // ..to ETHIOPIC SYLLABLE PHARYNGEAL O
|
|
charset[i++] = c++;
|
|
c = 0x12d8; // from ETHIOPIC SYLLABLE ZA
|
|
while (c <= 0x1310) // ..to ETHIOPIC SYLLABLE GWA
|
|
charset[i++] = c++;
|
|
c = 0x1312; // from ETHIOPIC SYLLABLE GWI
|
|
while (c <= 0x1315) // ..to ETHIOPIC SYLLABLE GWE
|
|
charset[i++] = c++;
|
|
c = 0x1318; // from ETHIOPIC SYLLABLE GGA
|
|
while (c <= 0x135a) // ..to ETHIOPIC SYLLABLE FYA
|
|
charset[i++] = c++;
|
|
c = 0x135d; // from ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK
|
|
while (c <= 0x137c) // ..to ETHIOPIC NUMBER TEN THOUSAND
|
|
charset[i++] = c++;
|
|
// 1380..139F; Ethiopic Supplement
|
|
c = 0x1380; // from ETHIOPIC SYLLABLE SEBATBEIT MWA
|
|
while (c <= 0x1399) // ..to ETHIOPIC TONAL MARK KURT
|
|
charset[i++] = c++;
|
|
// 13A0..13FF; Cherokee
|
|
c = 0x13a0; // from CHEROKEE LETTER A
|
|
while (c <= 0x13f5) // ..to CHEROKEE LETTER MV
|
|
charset[i++] = c++;
|
|
c = 0x13f8; // from CHEROKEE SMALL LETTER YE
|
|
while (c <= 0x13fd) // ..to CHEROKEE SMALL LETTER MV
|
|
charset[i++] = c++;
|
|
// 1400..167F; Unified Canadian Aboriginal Syllabics
|
|
c = 0x1400; // from CANADIAN SYLLABICS HYPHEN
|
|
while (c <= 0x167f) // ..to CANADIAN SYLLABICS BLACKFOOT W
|
|
charset[i++] = c++;
|
|
// 1680..169F; Ogham
|
|
c = 0x1680; // from OGHAM SPACE MARK
|
|
while (c <= 0x169c) // ..to OGHAM REVERSED FEATHER MARK
|
|
charset[i++] = c++;
|
|
// 16A0..16FF; Runic
|
|
c = 0x16a0; // from RUNIC LETTER FEHU FEOH FE F
|
|
while (c <= 0x16f8) // ..to RUNIC LETTER FRANKS CASKET AESC
|
|
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
|
|
charset[i++] = c++;
|
|
// 1720..173F; Hanunoo
|
|
c = 0x1720; // from HANUNOO LETTER A
|
|
while (c <= 0x1736) // ..to PHILIPPINE DOUBLE PUNCTUATION
|
|
charset[i++] = c++;
|
|
// 1740..175F; Buhid
|
|
c = 0x1740; // from BUHID LETTER A
|
|
while (c <= 0x1753) // ..to BUHID VOWEL SIGN U
|
|
charset[i++] = c++;
|
|
// 1760..177F; Tagbanwa
|
|
c = 0x1760; // from TAGBANWA LETTER A
|
|
while (c <= 0x176c) // ..to TAGBANWA LETTER YA
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x176e; // TAGBANWA LETTER LA
|
|
charset[i++] = 0x1770; // TAGBANWA LETTER SA
|
|
charset[i++] = 0x1772; // TAGBANWA VOWEL SIGN I
|
|
charset[i++] = 0x1773; // TAGBANWA VOWEL SIGN U
|
|
// 1780..17FF; Khmer
|
|
c = 0x1780; // from KHMER LETTER KA
|
|
while (c <= 0x17dd) // ..to KHMER SIGN ATTHACAN
|
|
charset[i++] = c++;
|
|
c = 0x17e0; // from KHMER DIGIT ZERO
|
|
while (c <= 0x17e9) // ..to KHMER DIGIT NINE
|
|
charset[i++] = c++;
|
|
c = 0x17f0; // from KHMER SYMBOL LEK ATTAK SON
|
|
while (c <= 0x17f9) // ..to KHMER SYMBOL LEK ATTAK PRAM-BUON
|
|
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
|
|
while (c <= 0x1878) // ..to MONGOLIAN LETTER CHA WITH TWO DOTS
|
|
charset[i++] = c++;
|
|
c = 0x1880; // from MONGOLIAN LETTER ALI GALI ANUSVARA ONE
|
|
while (c <= 0x18aa) // ..to MONGOLIAN LETTER MANCHU ALI GALI LHA
|
|
charset[i++] = c++;
|
|
// 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
|
|
c = 0x18b0; // from CANADIAN SYLLABICS OY
|
|
while (c <= 0x18f5) // ..to CANADIAN SYLLABICS CARRIER DENTAL S
|
|
charset[i++] = c++;
|
|
// 1900..194F; Limbu
|
|
c = 0x1900; // from LIMBU VOWEL-CARRIER LETTER
|
|
while (c <= 0x191e) // ..to LIMBU LETTER TRA
|
|
charset[i++] = c++;
|
|
c = 0x1920; // from LIMBU VOWEL SIGN A
|
|
while (c <= 0x192b) // ..to LIMBU SUBJOINED LETTER WA
|
|
charset[i++] = c++;
|
|
c = 0x1930; // from LIMBU SMALL LETTER KA
|
|
while (c <= 0x193b) // ..to LIMBU SIGN SA-I
|
|
charset[i++] = c++;
|
|
c = 0x1944; // from LIMBU EXCLAMATION MARK
|
|
while (c <= 0x194f) // ..to LIMBU DIGIT NINE
|
|
charset[i++] = c++;
|
|
// 1950..197F; Tai Le
|
|
c = 0x1950; // from TAI LE LETTER KA
|
|
while (c <= 0x196d) // ..to TAI LE LETTER AI
|
|
charset[i++] = c++;
|
|
c = 0x1970; // from TAI LE LETTER TONE-2
|
|
while (c <= 0x1974) // ..to TAI LE LETTER TONE-6
|
|
charset[i++] = c++;
|
|
// 1980..19DF; New Tai Lue
|
|
c = 0x1980; // from NEW TAI LUE LETTER HIGH QA
|
|
while (c <= 0x19ab) // ..to NEW TAI LUE LETTER LOW SUA
|
|
charset[i++] = c++;
|
|
c = 0x19b0; // from NEW TAI LUE VOWEL SIGN VOWEL SHORTENER
|
|
while (c <= 0x19c9) // ..to NEW TAI LUE TONE MARK-2
|
|
charset[i++] = c++;
|
|
c = 0x19d0; // from NEW TAI LUE DIGIT ZERO
|
|
while (c <= 0x19da) // ..to NEW TAI LUE THAM DIGIT ONE
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x19de; // NEW TAI LUE SIGN LAE
|
|
charset[i++] = 0x19df; // NEW TAI LUE SIGN LAEV
|
|
// 19E0..19FF; Khmer Symbols
|
|
c = 0x19e0; // from KHMER SYMBOL PATHAMASAT
|
|
while (c <= 0x19ff) // ..to KHMER SYMBOL DAP-PRAM ROC
|
|
charset[i++] = c++;
|
|
// 1A00..1A1F; Buginese
|
|
c = 0x1a00; // from BUGINESE LETTER KA
|
|
while (c <= 0x1a1b) // ..to BUGINESE VOWEL SIGN AE
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x1a1e; // BUGINESE PALLAWA
|
|
charset[i++] = 0x1a1f; // BUGINESE END OF SECTION
|
|
// 1A20..1AAF; Tai Tham
|
|
c = 0x1a20; // from TAI THAM LETTER HIGH KA
|
|
while (c <= 0x1a5e) // ..to TAI THAM CONSONANT SIGN SA
|
|
charset[i++] = c++;
|
|
c = 0x1a60; // from TAI THAM SIGN SAKOT
|
|
while (c <= 0x1a7c) // ..to TAI THAM SIGN KHUEN-LUE KARAN
|
|
charset[i++] = c++;
|
|
c = 0x1a7f; // from TAI THAM COMBINING CRYPTOGRAMMIC DOT
|
|
while (c <= 0x1a89) // ..to TAI THAM HORA DIGIT NINE
|
|
charset[i++] = c++;
|
|
c = 0x1a90; // from TAI THAM THAM DIGIT ZERO
|
|
while (c <= 0x1a99) // ..to TAI THAM THAM DIGIT NINE
|
|
charset[i++] = c++;
|
|
c = 0x1aa0; // from TAI THAM SIGN WIANG
|
|
while (c <= 0x1aad) // ..to TAI THAM SIGN CAANG
|
|
charset[i++] = c++;
|
|
// 1AB0..1AFF; Combining Diacritical Marks Extended
|
|
c = 0x1ab0; // from COMBINING DOUBLED CIRCUMFLEX ACCENT
|
|
while (c <= 0x1abe) // ..to COMBINING PARENTHESES OVERLAY
|
|
charset[i++] = c++;
|
|
// 1B00..1B7F; Balinese
|
|
c = 0x1b00; // from BALINESE SIGN ULU RICEM
|
|
while (c <= 0x1b4b) // ..to BALINESE LETTER ASYURA SASAK
|
|
charset[i++] = c++;
|
|
c = 0x1b50; // from BALINESE DIGIT ZERO
|
|
while (c <= 0x1b7c) // ..to BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING
|
|
charset[i++] = c++;
|
|
// 1B80..1BBF; Sundanese
|
|
c = 0x1b80; // from SUNDANESE SIGN PANYECEK
|
|
while (c <= 0x1bbf) // ..to SUNDANESE LETTER FINAL M
|
|
charset[i++] = c++;
|
|
// 1BC0..1BFF; Batak
|
|
c = 0x1bc0; // from BATAK LETTER A
|
|
while (c <= 0x1bf3) // ..to BATAK PANONGONAN
|
|
charset[i++] = c++;
|
|
c = 0x1bfc; // from BATAK SYMBOL BINDU NA METEK
|
|
while (c <= 0x1bff) // ..to BATAK SYMBOL BINDU PANGOLAT
|
|
charset[i++] = c++;
|
|
// 1C00..1C4F; Lepcha
|
|
c = 0x1c00; // from LEPCHA LETTER KA
|
|
while (c <= 0x1c37) // ..to LEPCHA SIGN NUKTA
|
|
charset[i++] = c++;
|
|
c = 0x1c3b; // from LEPCHA PUNCTUATION TA-ROL
|
|
while (c <= 0x1c49) // ..to LEPCHA DIGIT NINE
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x1c4d; // LEPCHA LETTER TTA
|
|
charset[i++] = 0x1c4f; // LEPCHA LETTER DDA
|
|
// 1C50..1C7F; Ol Chiki
|
|
c = 0x1c50; // from OL CHIKI DIGIT ZERO
|
|
while (c <= 0x1c7f) // ..to OL CHIKI PUNCTUATION DOUBLE MUCAAD
|
|
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
|
|
charset[i++] = c++;
|
|
// 1C90..1CBF; Georgian Extended
|
|
c = 0x1c90; // from GEORGIAN MTAVRULI CAPITAL LETTER AN
|
|
while (c <= 0x1cba) // ..to GEORGIAN MTAVRULI CAPITAL LETTER AIN
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x1cbd; // GEORGIAN MTAVRULI CAPITAL LETTER AEN
|
|
charset[i++] = 0x1cbf; // GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN
|
|
// 1CC0..1CCF; Sundanese Supplement
|
|
c = 0x1cc0; // from SUNDANESE PUNCTUATION BINDU SURYA
|
|
while (c <= 0x1cc7) // ..to SUNDANESE PUNCTUATION BINDU BA SATANGA
|
|
charset[i++] = c++;
|
|
// 1CD0..1CFF; Vedic Extensions
|
|
c = 0x1cd0; // from VEDIC TONE KARSHANA
|
|
while (c <= 0x1cf9) // ..to VEDIC TONE DOUBLE RING ABOVE
|
|
charset[i++] = c++;
|
|
// 1D00..1D7F; Phonetic Extensions
|
|
c = 0x1d00; // from LATIN LETTER SMALL CAPITAL A
|
|
while (c <= 0x1d7f) // ..to LATIN SMALL LETTER UPSILON WITH STROKE
|
|
charset[i++] = c++;
|
|
// 1D80..1DBF; Phonetic Extensions Supplement
|
|
c = 0x1d80; // from LATIN SMALL LETTER B WITH PALATAL HOOK
|
|
while (c <= 0x1dbf) // ..to MODIFIER LETTER SMALL THETA
|
|
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
|
|
c = 0x1e00; // from LATIN CAPITAL LETTER A WITH RING BELOW
|
|
while (c <= 0x1eff) // ..to LATIN SMALL LETTER Y WITH LOOP
|
|
charset[i++] = c++;
|
|
// 1F00..1FFF; Greek Extended
|
|
c = 0x1f00; // from GREEK SMALL LETTER ALPHA WITH PSILI
|
|
while (c <= 0x1f15) // ..to GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
|
|
charset[i++] = c++;
|
|
c = 0x1f18; // from GREEK CAPITAL LETTER EPSILON WITH PSILI
|
|
while (c <= 0x1f1d) // ..to GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
|
|
charset[i++] = c++;
|
|
c = 0x1f20; // from GREEK SMALL LETTER ETA WITH PSILI
|
|
while (c <= 0x1f45) // ..to GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA
|
|
charset[i++] = c++;
|
|
c = 0x1f48; // from GREEK CAPITAL LETTER OMICRON WITH PSILI
|
|
while (c <= 0x1f4d) // ..to GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA
|
|
charset[i++] = c++;
|
|
c = 0x1f50; // from GREEK SMALL LETTER UPSILON WITH PSILI
|
|
while (c <= 0x1f57) // ..to GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI
|
|
charset[i++] = c++;
|
|
c = 0x1f5f; // from GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI
|
|
while (c <= 0x1f7d) // ..to GREEK SMALL LETTER OMEGA WITH OXIA
|
|
charset[i++] = c++;
|
|
c = 0x1f80; // from GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
|
|
while (c <= 0x1fb4) // ..to GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
|
|
charset[i++] = c++;
|
|
c = 0x1fb6; // from GREEK SMALL LETTER ALPHA WITH PERISPOMENI
|
|
while (c <= 0x1fc4) // ..to GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
|
|
charset[i++] = c++;
|
|
c = 0x1fc6; // from GREEK SMALL LETTER ETA WITH PERISPOMENI
|
|
while (c <= 0x1fd3) // ..to GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
|
|
charset[i++] = c++;
|
|
c = 0x1fd6; // from GREEK SMALL LETTER IOTA WITH PERISPOMENI
|
|
while (c <= 0x1fdb) // ..to GREEK CAPITAL LETTER IOTA WITH OXIA
|
|
charset[i++] = c++;
|
|
c = 0x1fdd; // from GREEK DASIA AND VARIA
|
|
while (c <= 0x1fef) // ..to GREEK VARIA
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x1ff2; // GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
|
|
charset[i++] = 0x1ff4; // GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
|
|
c = 0x1ff6; // from GREEK SMALL LETTER OMEGA WITH PERISPOMENI
|
|
while (c <= 0x1ffe) // ..to GREEK DASIA
|
|
charset[i++] = c++;
|
|
// 2000..206F; General Punctuation
|
|
c = 0x2000; // from EN QUAD
|
|
while (c <= 0x2064) // ..to INVISIBLE PLUS
|
|
charset[i++] = c++;
|
|
c = 0x2066; // from LEFT-TO-RIGHT ISOLATE
|
|
while (c <= 0x206f) // ..to NOMINAL DIGIT SHAPES
|
|
charset[i++] = c++;
|
|
// 2070..209F; Superscripts and Subscripts
|
|
charset[i++] = 0x2070; // SUPERSCRIPT ZERO
|
|
charset[i++] = 0x2071; // SUPERSCRIPT LATIN SMALL LETTER I
|
|
c = 0x2074; // from SUPERSCRIPT FOUR
|
|
while (c <= 0x208e) // ..to SUBSCRIPT RIGHT PARENTHESIS
|
|
charset[i++] = c++;
|
|
c = 0x2090; // from LATIN SUBSCRIPT SMALL LETTER A
|
|
while (c <= 0x209c) // ..to LATIN SUBSCRIPT SMALL LETTER T
|
|
charset[i++] = c++;
|
|
// 20A0..20CF; Currency Symbols
|
|
c = 0x20a0; // from EURO-CURRENCY SIGN
|
|
while (c <= 0x20bf) // ..to BITCOIN SIGN
|
|
charset[i++] = c++;
|
|
// 20D0..20FF; Combining Diacritical Marks for Symbols
|
|
c = 0x20d0; // from COMBINING LEFT HARPOON ABOVE
|
|
while (c <= 0x20f0) // ..to COMBINING ASTERISK ABOVE
|
|
charset[i++] = c++;
|
|
// 2100..214F; Letterlike Symbols
|
|
c = 0x2100; // from ACCOUNT OF
|
|
while (c <= 0x214f) // ..to SYMBOL FOR SAMARITAN SOURCE
|
|
charset[i++] = c++;
|
|
// 2150..218F; Number Forms
|
|
c = 0x2150; // from VULGAR FRACTION ONE SEVENTH
|
|
while (c <= 0x218b) // ..to TURNED DIGIT THREE
|
|
charset[i++] = c++;
|
|
// 2190..21FF; Arrows
|
|
c = 0x2190; // from LEFTWARDS ARROW
|
|
while (c <= 0x21ff) // ..to LEFT RIGHT OPEN-HEADED ARROW
|
|
charset[i++] = c++;
|
|
// 2200..22FF; Mathematical Operators
|
|
c = 0x2200; // from FOR ALL
|
|
while (c <= 0x22ff) // ..to Z NOTATION BAG MEMBERSHIP
|
|
charset[i++] = c++;
|
|
// 2300..23FF; Miscellaneous Technical
|
|
c = 0x2300; // from DIAMETER SIGN
|
|
while (c <= 0x23ff) // ..to OBSERVER EYE SYMBOL
|
|
charset[i++] = c++;
|
|
// 2400..243F; Control Pictures
|
|
c = 0x2400; // from SYMBOL FOR NULL
|
|
while (c <= 0x2426) // ..to SYMBOL FOR SUBSTITUTE FORM TWO
|
|
charset[i++] = c++;
|
|
// 2440..245F; Optical Character Recognition
|
|
c = 0x2440; // from OCR HOOK
|
|
while (c <= 0x244a) // ..to OCR DOUBLE BACKSLASH
|
|
charset[i++] = c++;
|
|
// 2460..24FF; Enclosed Alphanumerics
|
|
c = 0x2460; // from CIRCLED DIGIT ONE
|
|
while (c <= 0x24ff) // ..to NEGATIVE CIRCLED DIGIT ZERO
|
|
charset[i++] = c++;
|
|
// 2500..257F; Box Drawing
|
|
c = 0x2500; // from BOX DRAWINGS LIGHT HORIZONTAL
|
|
while (c <= 0x257f) // ..to BOX DRAWINGS HEAVY UP AND LIGHT DOWN
|
|
charset[i++] = c++;
|
|
// 2580..259F; Block Elements
|
|
c = 0x2580; // from UPPER HALF BLOCK
|
|
while (c <= 0x259f) // ..to QUADRANT UPPER RIGHT AND LOWER LEFT AND LOWER RIGHT
|
|
charset[i++] = c++;
|
|
// 25A0..25FF; Geometric Shapes
|
|
c = 0x25a0; // from BLACK SQUARE
|
|
while (c <= 0x25ff) // ..to LOWER RIGHT TRIANGLE
|
|
charset[i++] = c++;
|
|
// 2600..26FF; Miscellaneous Symbols
|
|
c = 0x2600; // from BLACK SUN WITH RAYS
|
|
while (c <= 0x26ff) // ..to WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE
|
|
charset[i++] = c++;
|
|
// 2700..27BF; Dingbats
|
|
c = 0x2700; // from BLACK SAFETY SCISSORS
|
|
while (c <= 0x27bf) // ..to DOUBLE CURLY LOOP
|
|
charset[i++] = c++;
|
|
// 27C0..27EF; Miscellaneous Mathematical Symbols-A
|
|
c = 0x27c0; // from THREE DIMENSIONAL ANGLE
|
|
while (c <= 0x27ef) // ..to MATHEMATICAL RIGHT FLATTENED PARENTHESIS
|
|
charset[i++] = c++;
|
|
// 27F0..27FF; Supplemental Arrows-A
|
|
c = 0x27f0; // from UPWARDS QUADRUPLE ARROW
|
|
while (c <= 0x27ff) // ..to LONG RIGHTWARDS SQUIGGLE ARROW
|
|
charset[i++] = c++;
|
|
// 2800..28FF; Braille Patterns
|
|
c = 0x2800; // from BRAILLE PATTERN BLANK
|
|
while (c <= 0x28ff) // ..to BRAILLE PATTERN DOTS-12345678
|
|
charset[i++] = c++;
|
|
// 2900..297F; Supplemental Arrows-B
|
|
c = 0x2900; // from RIGHTWARDS TWO-HEADED ARROW WITH VERTICAL STROKE
|
|
while (c <= 0x297f) // ..to DOWN FISH TAIL
|
|
charset[i++] = c++;
|
|
// 2980..29FF; Miscellaneous Mathematical Symbols-B
|
|
c = 0x2980; // from TRIPLE VERTICAL BAR DELIMITER
|
|
while (c <= 0x29ff) // ..to MINY
|
|
charset[i++] = c++;
|
|
// 2A00..2AFF; Supplemental Mathematical Operators
|
|
c = 0x2a00; // from N-ARY CIRCLED DOT OPERATOR
|
|
while (c <= 0x2aff) // ..to N-ARY WHITE VERTICAL BAR
|
|
charset[i++] = c++;
|
|
// 2B00..2BFF; Miscellaneous Symbols and Arrows
|
|
c = 0x2b00; // from NORTH EAST WHITE ARROW
|
|
while (c <= 0x2b73) // ..to DOWNWARDS TRIANGLE-HEADED ARROW TO BAR
|
|
charset[i++] = c++;
|
|
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
|
|
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
|
|
charset[i++] = c++;
|
|
// 2C60..2C7F; Latin Extended-C
|
|
c = 0x2c60; // from LATIN CAPITAL LETTER L WITH DOUBLE BAR
|
|
while (c <= 0x2c7f) // ..to LATIN CAPITAL LETTER Z WITH SWASH TAIL
|
|
charset[i++] = c++;
|
|
// 2C80..2CFF; Coptic
|
|
c = 0x2c80; // from COPTIC CAPITAL LETTER ALFA
|
|
while (c <= 0x2cf3) // ..to COPTIC SMALL LETTER BOHAIRIC KHEI
|
|
charset[i++] = c++;
|
|
c = 0x2cf9; // from COPTIC OLD NUBIAN FULL STOP
|
|
while (c <= 0x2cff) // ..to COPTIC MORPHOLOGICAL DIVIDER
|
|
charset[i++] = c++;
|
|
// 2D00..2D2F; Georgian Supplement
|
|
c = 0x2d00; // from GEORGIAN SMALL LETTER AN
|
|
while (c <= 0x2d25) // ..to GEORGIAN SMALL LETTER HOE
|
|
charset[i++] = c++;
|
|
c = 0x2d27; // from GEORGIAN SMALL LETTER YN
|
|
while (c <= 0x2d2d) // ..to GEORGIAN SMALL LETTER AEN
|
|
charset[i++] = c++;
|
|
// 2D30..2D7F; Tifinagh
|
|
c = 0x2d30; // from TIFINAGH LETTER YA
|
|
while (c <= 0x2d67) // ..to TIFINAGH LETTER YO
|
|
charset[i++] = c++;
|
|
charset[i++] = 0x2d6f; // TIFINAGH MODIFIER LETTER LABIALIZATION MARK
|
|
charset[i++] = 0x2d70; // TIFINAGH SEPARATOR MARK
|
|
charset[i++] = 0x2d7f; // TIFINAGH CONSONANT JOINER
|
|
// 2D80..2DDF; Ethiopic Extended
|
|
c = 0x2d80; // from ETHIOPIC SYLLABLE LOA
|
|
while (c <= 0x2d96) // ..to ETHIOPIC SYLLABLE GGWE
|
|
charset[i++] = c++;
|
|
c = 0x2da0; // from ETHIOPIC SYLLABLE SSA
|
|
while (c <= 0x2da6) // ..to ETHIOPIC SYLLABLE SSO
|
|
charset[i++] = c++;
|
|
c = 0x2da8; // from ETHIOPIC SYLLABLE CCA
|
|
while (c <= 0x2dae) // ..to ETHIOPIC SYLLABLE CCO
|
|
charset[i++] = c++;
|
|
c = 0x2db0; // from ETHIOPIC SYLLABLE ZZA
|
|
while (c <= 0x2db6) // ..to ETHIOPIC SYLLABLE ZZO
|
|
charset[i++] = c++;
|
|
c = 0x2db8; // from ETHIOPIC SYLLABLE CCHA
|
|
while (c <= 0x2dbe) // ..to ETHIOPIC SYLLABLE CCHO
|
|
charset[i++] = c++;
|
|
c = 0x2dc0; // from ETHIOPIC SYLLABLE QYA
|
|
while (c <= 0x2dc6) // ..to ETHIOPIC SYLLABLE QYO
|
|
charset[i++] = c++;
|
|
c = 0x2dc8; // from ETHIOPIC SYLLABLE KYA
|
|
while (c <= 0x2dce) // ..to ETHIOPIC SYLLABLE KYO
|
|
charset[i++] = c++;
|
|
c = 0x2dd0; // from ETHIOPIC SYLLABLE XYA
|
|
while (c <= 0x2dd6) // ..to ETHIOPIC SYLLABLE XYO
|
|
charset[i++] = c++;
|
|
c = 0x2dd8; // from ETHIOPIC SYLLABLE GYA
|
|
while (c <= 0x2dde) // ..to ETHIOPIC SYLLABLE GYO
|
|
charset[i++] = c++;
|
|
// 2DE0..2DFF; Cyrillic Extended-A
|
|
c = 0x2de0; // from COMBINING CYRILLIC LETTER BE
|
|
while (c <= 0x2dff) // ..to COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
|
|
charset[i++] = c++;
|
|
// 2E00..2E7F; Supplemental Punctuation
|
|
c = 0x2e00; // from RIGHT ANGLE SUBSTITUTION MARKER
|
|
while (c <= 0x2e4e) // ..to PUNCTUS ELEVATUS MARK
|
|
charset[i++] = c++;
|
|
// 2E80..2EFF; CJK Radicals Supplement
|
|
c = 0x2e80; // from CJK RADICAL REPEAT
|
|
while (c <= 0x2e99) // ..to CJK RADICAL RAP
|
|
charset[i++] = c++;
|
|
c = 0x2e9b; // from CJK RADICAL CHOKE
|
|
while (c <= 0x2ef3) // ..to CJK RADICAL C-SIMPLIFIED TURTLE
|
|
charset[i++] = c++;
|
|
// 2F00..2FDF; Kangxi Radicals
|
|
c = 0x2f00; // from KANGXI RADICAL ONE
|
|
while (c <= 0x2fd5) // ..to KANGXI RADICAL FLUTE
|
|
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
|
|
charset[i++] = c++;
|
|
// 3000..303F; CJK Symbols and Punctuation
|
|
c = 0x3000; // from IDEOGRAPHIC SPACE
|
|
while (c <= 0x303f) // ..to IDEOGRAPHIC HALF FILL SPACE
|
|
charset[i++] = c++;
|
|
// 3040..309F; Hiragana
|
|
c = 0x3041; // from HIRAGANA LETTER SMALL A
|
|
while (c <= 0x3096) // ..to HIRAGANA LETTER SMALL KE
|
|
charset[i++] = c++;
|
|
c = 0x3099; // from COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK
|
|
while (c <= 0x309f) // ..to HIRAGANA DIGRAPH YORI
|
|
charset[i++] = c++;
|
|
// 30A0..30FF; Katakana
|
|
c = 0x30a0; // from KATAKANA-HIRAGANA DOUBLE HYPHEN
|
|
while (c <= 0x30ff) // ..to KATAKANA DIGRAPH KOTO
|
|
charset[i++] = c++;
|
|
// 3100..312F; Bopomofo
|
|
c = 0x3105; // from BOPOMOFO LETTER B
|
|
while (c <= 0x312f) // ..to BOPOMOFO LETTER NN
|
|
charset[i++] = c++;
|
|
// 3130..318F; Hangul Compatibility Jamo
|
|
c = 0x3131; // from HANGUL LETTER KIYEOK
|
|
while (c <= 0x318e) // ..to HANGUL LETTER ARAEAE
|
|
charset[i++] = c++;
|
|
// 3190..319F; Kanbun
|
|
c = 0x3190; // from IDEOGRAPHIC ANNOTATION LINKING MARK
|
|
while (c <= 0x319f) // ..to IDEOGRAPHIC ANNOTATION MAN MARK
|
|
charset[i++] = c++;
|
|
// 31A0..31BF; Bopomofo Extended
|
|
c = 0x31a0; // from BOPOMOFO LETTER BU
|
|
while (c <= 0x31ba) // ..to BOPOMOFO LETTER ZY
|
|
charset[i++] = c++;
|
|
// 31C0..31EF; CJK Strokes
|
|
c = 0x31c0; // from CJK STROKE T
|
|
while (c <= 0x31e3) // ..to CJK STROKE Q
|
|
charset[i++] = c++;
|
|
// 31F0..31FF; Katakana Phonetic Extensions
|
|
c = 0x31f0; // from KATAKANA LETTER SMALL KU
|
|
while (c <= 0x31ff) // ..to KATAKANA LETTER SMALL RO
|
|
charset[i++] = c++;
|
|
// 3200..32FF; Enclosed CJK Letters and Months
|
|
c = 0x3200; // from PARENTHESIZED HANGUL KIYEOK
|
|
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
|
|
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>
|
|
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>
|
|
charset[i++] = c++;
|
|
// A000..A48F; Yi Syllables
|
|
c = 0xa000; // from YI SYLLABLE IT
|
|
while (c <= 0xa48c) // ..to YI SYLLABLE YYR
|
|
charset[i++] = c++;
|
|
// A490..A4CF; Yi Radicals
|
|
c = 0xa490; // from YI RADICAL QOT
|
|
while (c <= 0xa4c6) // ..to YI RADICAL KE
|
|
charset[i++] = c++;
|
|
// A4D0..A4FF; Lisu
|
|
c = 0xa4d0; // from LISU LETTER BA
|
|
while (c <= 0xa4ff) // ..to LISU PUNCTUATION FULL STOP
|
|
charset[i++] = c++;
|
|
// A500..A63F; Vai
|
|
c = 0xa500; // from VAI SYLLABLE EE
|
|
while (c <= 0xa62b) // ..to VAI SYLLABLE NDOLE DO
|
|
charset[i++] = c++;
|
|
// A640..A69F; Cyrillic Extended-B
|
|
c = 0xa640; // from CYRILLIC CAPITAL LETTER ZEMLYA
|
|
while (c <= 0xa69f) // ..to COMBINING CYRILLIC LETTER IOTIFIED E
|
|
charset[i++] = c++;
|
|
// A6A0..A6FF; Bamum
|
|
c = 0xa6a0; // from BAMUM LETTER A
|
|
while (c <= 0xa6f7) // ..to BAMUM QUESTION MARK
|
|
charset[i++] = c++;
|
|
// A700..A71F; Modifier Tone Letters
|
|
c = 0xa700; // from MODIFIER LETTER CHINESE TONE YIN PING
|
|
while (c <= 0xa71f) // ..to MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
|
|
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
|
|
charset[i++] = c++;
|
|
c = 0xa7f7; // from LATIN EPIGRAPHIC LETTER SIDEWAYS I
|
|
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
|
|
charset[i++] = c++;
|
|
// A830..A83F; Common Indic Number Forms
|
|
c = 0xa830; // from NORTH INDIC FRACTION ONE QUARTER
|
|
while (c <= 0xa839) // ..to NORTH INDIC QUANTITY MARK
|
|
charset[i++] = c++;
|
|
// A840..A87F; Phags-pa
|
|
c = 0xa840; // from PHAGS-PA LETTER KA
|
|
while (c <= 0xa877) // ..to PHAGS-PA MARK DOUBLE SHAD
|
|
charset[i++] = c++;
|
|
// A880..A8DF; Saurashtra
|
|
c = 0xa880; // from SAURASHTRA SIGN ANUSVARA
|
|
while (c <= 0xa8c5) // ..to SAURASHTRA SIGN CANDRABINDU
|
|
charset[i++] = c++;
|
|
c = 0xa8ce; // from SAURASHTRA DANDA
|
|
while (c <= 0xa8d9) // ..to SAURASHTRA DIGIT NINE
|
|
charset[i++] = c++;
|
|
// A8E0..A8FF; Devanagari Extended
|
|
c = 0xa8e0; // from COMBINING DEVANAGARI DIGIT ZERO
|
|
while (c <= 0xa8ff) // ..to DEVANAGARI VOWEL SIGN AY
|
|
charset[i++] = c++;
|
|
// A900..A92F; Kayah Li
|
|
c = 0xa900; // from KAYAH LI DIGIT ZERO
|
|
while (c <= 0xa92f) // ..to KAYAH LI SIGN SHYA
|
|
charset[i++] = c++;
|
|
// A930..A95F; Rejang
|
|
c = 0xa930; // from REJANG LETTER KA
|
|
while (c <= 0xa953) // ..to REJANG VIRAMA
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xa95f; // REJANG SECTION MARK
|
|
// A960..A97F; Hangul Jamo Extended-A
|
|
c = 0xa960; // from HANGUL CHOSEONG TIKEUT-MIEUM
|
|
while (c <= 0xa97c) // ..to HANGUL CHOSEONG SSANGYEORINHIEUH
|
|
charset[i++] = c++;
|
|
// A980..A9DF; Javanese
|
|
c = 0xa980; // from JAVANESE SIGN PANYANGGA
|
|
while (c <= 0xa9cd) // ..to JAVANESE TURNED PADA PISELEH
|
|
charset[i++] = c++;
|
|
c = 0xa9cf; // from JAVANESE PANGRANGKEP
|
|
while (c <= 0xa9d9) // ..to JAVANESE DIGIT NINE
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xa9de; // JAVANESE PADA TIRTA TUMETES
|
|
charset[i++] = 0xa9df; // JAVANESE PADA ISEN-ISEN
|
|
// A9E0..A9FF; Myanmar Extended-B
|
|
c = 0xa9e0; // from MYANMAR LETTER SHAN GHA
|
|
while (c <= 0xa9fe) // ..to MYANMAR LETTER TAI LAING BHA
|
|
charset[i++] = c++;
|
|
// AA00..AA5F; Cham
|
|
c = 0xaa00; // from CHAM LETTER A
|
|
while (c <= 0xaa36) // ..to CHAM CONSONANT SIGN WA
|
|
charset[i++] = c++;
|
|
c = 0xaa40; // from CHAM LETTER FINAL K
|
|
while (c <= 0xaa4d) // ..to CHAM CONSONANT SIGN FINAL H
|
|
charset[i++] = c++;
|
|
c = 0xaa50; // from CHAM DIGIT ZERO
|
|
while (c <= 0xaa59) // ..to CHAM DIGIT NINE
|
|
charset[i++] = c++;
|
|
c = 0xaa5c; // from CHAM PUNCTUATION SPIRAL
|
|
while (c <= 0xaa5f) // ..to CHAM PUNCTUATION TRIPLE DANDA
|
|
charset[i++] = c++;
|
|
// AA60..AA7F; Myanmar Extended-A
|
|
c = 0xaa60; // from MYANMAR LETTER KHAMTI GA
|
|
while (c <= 0xaa7f) // ..to MYANMAR LETTER SHWE PALAUNG SHA
|
|
charset[i++] = c++;
|
|
// AA80..AADF; Tai Viet
|
|
c = 0xaa80; // from TAI VIET LETTER LOW KO
|
|
while (c <= 0xaac2) // ..to TAI VIET TONE MAI SONG
|
|
charset[i++] = c++;
|
|
c = 0xaadb; // from TAI VIET SYMBOL KON
|
|
while (c <= 0xaadf) // ..to TAI VIET SYMBOL KOI KOI
|
|
charset[i++] = c++;
|
|
// AAE0..AAFF; Meetei Mayek Extensions
|
|
c = 0xaae0; // from MEETEI MAYEK LETTER E
|
|
while (c <= 0xaaf6) // ..to MEETEI MAYEK VIRAMA
|
|
charset[i++] = c++;
|
|
// AB00..AB2F; Ethiopic Extended-A
|
|
c = 0xab01; // from ETHIOPIC SYLLABLE TTHU
|
|
while (c <= 0xab06) // ..to ETHIOPIC SYLLABLE TTHO
|
|
charset[i++] = c++;
|
|
c = 0xab09; // from ETHIOPIC SYLLABLE DDHU
|
|
while (c <= 0xab0e) // ..to ETHIOPIC SYLLABLE DDHO
|
|
charset[i++] = c++;
|
|
c = 0xab11; // from ETHIOPIC SYLLABLE DZU
|
|
while (c <= 0xab16) // ..to ETHIOPIC SYLLABLE DZO
|
|
charset[i++] = c++;
|
|
c = 0xab20; // from ETHIOPIC SYLLABLE CCHHA
|
|
while (c <= 0xab26) // ..to ETHIOPIC SYLLABLE CCHHO
|
|
charset[i++] = c++;
|
|
c = 0xab28; // from ETHIOPIC SYLLABLE BBA
|
|
while (c <= 0xab2e) // ..to ETHIOPIC SYLLABLE BBO
|
|
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
|
|
charset[i++] = c++;
|
|
// AB70..ABBF; Cherokee Supplement
|
|
c = 0xab70; // from CHEROKEE SMALL LETTER A
|
|
while (c <= 0xabbf) // ..to CHEROKEE SMALL LETTER YA
|
|
charset[i++] = c++;
|
|
// ABC0..ABFF; Meetei Mayek
|
|
c = 0xabc0; // from MEETEI MAYEK LETTER KOK
|
|
while (c <= 0xabed) // ..to MEETEI MAYEK APUN IYEK
|
|
charset[i++] = c++;
|
|
c = 0xabf0; // from MEETEI MAYEK DIGIT ZERO
|
|
while (c <= 0xabf9) // ..to MEETEI MAYEK DIGIT NINE
|
|
charset[i++] = c++;
|
|
// AC00..D7AF; Hangul Syllables
|
|
c = 0xac00; // from <Hangul Syllable, First>
|
|
while (c <= 0xd7a3) // ..to <Hangul Syllable, Last>
|
|
charset[i++] = c++;
|
|
// D7B0..D7FF; Hangul Jamo Extended-B
|
|
c = 0xd7b0; // from HANGUL JUNGSEONG O-YEO
|
|
while (c <= 0xd7c6) // ..to HANGUL JUNGSEONG ARAEA-E
|
|
charset[i++] = c++;
|
|
c = 0xd7cb; // from HANGUL JONGSEONG NIEUN-RIEUL
|
|
while (c <= 0xd7fb) // ..to HANGUL JONGSEONG PHIEUPH-THIEUTH
|
|
charset[i++] = c++;
|
|
// D800..DB7F; High Surrogates
|
|
// DB80..DBFF; High Private Use Surrogates
|
|
// DC00..DFFF; Low Surrogates
|
|
// E000..F8FF; Private Use Area
|
|
// F900..FAFF; CJK Compatibility Ideographs
|
|
c = 0xf900; // from CJK COMPATIBILITY IDEOGRAPH-F900
|
|
while (c <= 0xfa6d) // ..to CJK COMPATIBILITY IDEOGRAPH-FA6D
|
|
charset[i++] = c++;
|
|
c = 0xfa70; // from CJK COMPATIBILITY IDEOGRAPH-FA70
|
|
while (c <= 0xfad9) // ..to CJK COMPATIBILITY IDEOGRAPH-FAD9
|
|
charset[i++] = c++;
|
|
// FB00..FB4F; Alphabetic Presentation Forms
|
|
c = 0xfb00; // from LATIN SMALL LIGATURE FF
|
|
while (c <= 0xfb06) // ..to LATIN SMALL LIGATURE ST
|
|
charset[i++] = c++;
|
|
c = 0xfb13; // from ARMENIAN SMALL LIGATURE MEN NOW
|
|
while (c <= 0xfb17) // ..to ARMENIAN SMALL LIGATURE MEN XEH
|
|
charset[i++] = c++;
|
|
c = 0xfb1d; // from HEBREW LETTER YOD WITH HIRIQ
|
|
while (c <= 0xfb36) // ..to HEBREW LETTER ZAYIN WITH DAGESH
|
|
charset[i++] = c++;
|
|
c = 0xfb38; // from HEBREW LETTER TET WITH DAGESH
|
|
while (c <= 0xfb3c) // ..to HEBREW LETTER LAMED WITH DAGESH
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xfb40; // HEBREW LETTER NUN WITH DAGESH
|
|
charset[i++] = 0xfb41; // HEBREW LETTER SAMEKH WITH DAGESH
|
|
charset[i++] = 0xfb43; // HEBREW LETTER FINAL PE WITH DAGESH
|
|
charset[i++] = 0xfb44; // HEBREW LETTER PE WITH DAGESH
|
|
c = 0xfb46; // from HEBREW LETTER TSADI WITH DAGESH
|
|
while (c <= 0xfb4f) // ..to HEBREW LIGATURE ALEF LAMED
|
|
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
|
|
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
|
|
charset[i++] = c++;
|
|
// FE00..FE0F; Variation Selectors
|
|
c = 0xfe00; // from VARIATION SELECTOR-1
|
|
while (c <= 0xfe0f) // ..to VARIATION SELECTOR-16
|
|
charset[i++] = c++;
|
|
// FE10..FE1F; Vertical Forms
|
|
c = 0xfe10; // from PRESENTATION FORM FOR VERTICAL COMMA
|
|
while (c <= 0xfe19) // ..to PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
|
|
charset[i++] = c++;
|
|
// FE20..FE2F; Combining Half Marks
|
|
c = 0xfe20; // from COMBINING LIGATURE LEFT HALF
|
|
while (c <= 0xfe2f) // ..to COMBINING CYRILLIC TITLO RIGHT HALF
|
|
charset[i++] = c++;
|
|
// FE30..FE4F; CJK Compatibility Forms
|
|
c = 0xfe30; // from PRESENTATION FORM FOR VERTICAL TWO DOT LEADER
|
|
while (c <= 0xfe4f) // ..to WAVY LOW LINE
|
|
charset[i++] = c++;
|
|
// FE50..FE6F; Small Form Variants
|
|
charset[i++] = 0xfe50; // SMALL COMMA
|
|
charset[i++] = 0xfe52; // SMALL FULL STOP
|
|
c = 0xfe54; // from SMALL SEMICOLON
|
|
while (c <= 0xfe66) // ..to SMALL EQUALS SIGN
|
|
charset[i++] = c++;
|
|
c = 0xfe68; // from SMALL REVERSE SOLIDUS
|
|
while (c <= 0xfe6b) // ..to SMALL COMMERCIAL AT
|
|
charset[i++] = c++;
|
|
// FE70..FEFF; Arabic Presentation Forms-B
|
|
c = 0xfe70; // from ARABIC FATHATAN ISOLATED FORM
|
|
while (c <= 0xfe74) // ..to ARABIC KASRATAN ISOLATED FORM
|
|
charset[i++] = c++;
|
|
c = 0xfe76; // from ARABIC FATHA ISOLATED FORM
|
|
while (c <= 0xfefc) // ..to ARABIC LIGATURE LAM WITH ALEF FINAL FORM
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xfeff; // ZERO WIDTH NO-BREAK SPACE
|
|
// FF00..FFEF; Halfwidth and Fullwidth Forms
|
|
c = 0xff01; // from FULLWIDTH EXCLAMATION MARK
|
|
while (c <= 0xffbe) // ..to HALFWIDTH HANGUL LETTER HIEUH
|
|
charset[i++] = c++;
|
|
c = 0xffc2; // from HALFWIDTH HANGUL LETTER A
|
|
while (c <= 0xffc7) // ..to HALFWIDTH HANGUL LETTER E
|
|
charset[i++] = c++;
|
|
c = 0xffca; // from HALFWIDTH HANGUL LETTER YEO
|
|
while (c <= 0xffcf) // ..to HALFWIDTH HANGUL LETTER OE
|
|
charset[i++] = c++;
|
|
c = 0xffd2; // from HALFWIDTH HANGUL LETTER YO
|
|
while (c <= 0xffd7) // ..to HALFWIDTH HANGUL LETTER YU
|
|
charset[i++] = c++;
|
|
charset[i++] = 0xffda; // HALFWIDTH HANGUL LETTER EU
|
|
charset[i++] = 0xffdc; // HALFWIDTH HANGUL LETTER I
|
|
c = 0xffe0; // from FULLWIDTH CENT SIGN
|
|
while (c <= 0xffe6) // ..to FULLWIDTH WON SIGN
|
|
charset[i++] = c++;
|
|
c = 0xffe8; // from HALFWIDTH FORMS LIGHT VERTICAL
|
|
while (c <= 0xffee) // ..to HALFWIDTH WHITE CIRCLE
|
|
charset[i++] = c++;
|
|
// FFF0..FFFF; Specials
|
|
c = 0xfff9; // from INTERLINEAR ANNOTATION ANCHOR
|
|
while (c <= 0xfffd) // ..to REPLACEMENT CHARACTER
|
|
charset[i++] = c++;
|
|
|
|
/* Zero-terminate it, and cache the first character */
|
|
charset[maxc = i] = 0;
|
|
|
|
length = minlength; c = 0;
|
|
|
|
/* We must init word with dummy data, it doesn't get set until filter() */
|
|
word = 1;
|
|
}
|
|
|
|
void generate()
|
|
{
|
|
int i, cl, wl;
|
|
|
|
if (target_utf8) {
|
|
cl = 1;
|
|
if (charset[c] >= 0x80) {
|
|
cl++;
|
|
if (charset[c] >= 0x0800)
|
|
cl++;
|
|
wl = length * cl;
|
|
if (wl > cipher_limit) {
|
|
c = 0;
|
|
if (++length > maxlength) {
|
|
word = 0;
|
|
return;
|
|
}
|
|
cl = 1;
|
|
if (charset[0] >= 0x80) {
|
|
cl++;
|
|
if (charset[0] >= 0x0800)
|
|
cl++;
|
|
wl = length * cl;
|
|
if (wl > cipher_limit) {
|
|
word = 0;
|
|
return;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
i = 0;
|
|
while (i < length)
|
|
word[i++] = charset[c];
|
|
word[i] = 0;
|
|
|
|
if (++c < maxc)
|
|
return;
|
|
|
|
c = 0;
|
|
if (++length > maxlength)
|
|
length = 0; // Will NUL out the next "word" and thus terminate
|
|
|
|
return;
|
|
}
|
|
|
|
/* Reset length & c */
|
|
void restore()
|
|
{
|
|
length = 0;
|
|
|
|
while (word[length]) {
|
|
length++;
|
|
}
|
|
c = word[0];
|
|
}
|