/* -*- Mode: C++; tab-width: 2; c-basic-offset: 2 -*- */
/*
PDFtk, the PDF Toolkit
Copyright (c) 2013 Steward and Lee, LLC
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see .
Visit: www.pdftk.com for pdftk information and articles
Permalink: http://www.pdflabs.com/tools/pdftk-the-pdf-toolkit/
Please email Sid Steward with questions or bug reports.
Include "pdftk" in the subject line to ensure successful delivery:
sid.steward at pdflabs dot com
*/
// Tell C++ compiler to use Java-style exceptions.
#pragma GCC java_exceptions
#include
#include "passwords.h"
/*
password character mapping by Acrobat (pre-1.7 PDF)
* characters in PDFDocEncoding use PDFDocEncoding
* some PDFDocEncoding characters are not accepted as input into Acrobat/Reader --
this is consistent with the next rule:
* unicode 0x200 and up: Acrobat/Reader prohibits input
* some chars below 0x200 are mapped to . (period)
* some chars below 0x200 are mapped to non-accented ASCII char
* many points are mapped to Windows CP-1250
These were tested on Windows 7 using Acrobat 7. From what I've read, Adobe's mapping
of characters that aren't in PDFDocEncoding is platform dependent. So this map should
only be used for mapping PDF passwords for decryption. When encrypting, it would be
best to enforce a limited set of characters for the purpose of platform independence.
*/
// unicode 0x100 - 0x1FF
static unsigned long unicode_latin_extended_windows_map[]=
{
// latin extended a
'A', //U+0100 Ā Latin Capital Letter A with macron
'a', //U+0101 ā Latin Small Letter A with macron
0xC3, //U+0102 Ă Latin Capital Letter A with breve
0xC4, //U+0103 ă Latin Small Letter A with breve
0xA5, //U+0104 Ą Latin Capital Letter A with ogonek
0xB9, //U+0105 ą Latin Small Letter A with ogonek
0xC6, //U+0106 Ć Latin Capital Letter C with acute
0xE6, //U+0107 ć Latin Small Letter C with acute
'.', //U+0108 Ĉ Latin Capital Letter C with circumflex
'.', //U+0109 ĉ Latin Small Letter C with circumflex
'.', //U+010A Ċ Latin Capital Letter C with dot above
'.', //U+010B ċ Latin Small Letter C with dot above
0xC8, //U+010C Č Latin Capital Letter C with caron
0xE8, //U+010D č Latin Small Letter C with caron
0xCF, //U+010E Ď Latin Capital Letter D with caron
0xEF, //U+010F ď Latin Small Letter D with caron
0xD0, //U+0110 Đ Latin Capital Letter D with stroke
0xF0, //U+0111 đ Latin Small Letter D with stroke
'E', //U+0112 Ē Latin Capital Letter E with macron
'e', //U+0113 ē Latin Small Letter E with macron
'.', //U+0114 Ĕ Latin Capital Letter E with breve
'.', //U+0115 ĕ Latin Small Letter E with breve
'E', //U+0116 Ė Latin Capital Letter E with dot above
'e', //U+0117 ė Latin Small Letter E with dot above
0xCA, //U+0118 Ę Latin Capital Letter E with ogonek
0xEA, //U+0119 ę Latin Small Letter E with ogonek
0xCC, //U+011A Ě Latin Capital Letter E with caron
0xEC, //U+011B ě Latin Small Letter E with caron
'.', //U+011C Ĝ Latin Capital Letter G with circumflex
'.', //U+011D ĝ Latin Small Letter G with circumflex
'G', //U+011E Ğ Latin Capital Letter G with breve
'g', //U+011F ğ Latin Small Letter G with breve
'.', //U+0120 Ġ Latin Capital Letter G with dot above
'.', //U+0121 ġ Latin Small Letter G with dot above
'G', //U+0122 Ģ Latin Capital Letter G with cedilla
'g', //U+0123 ģ Latin Small Letter G with cedilla
'.', //U+0124 Ĥ Latin Capital Letter H with circumflex
'.', //U+0125 ĥ Latin Small Letter H with circumflex
'.', //U+0126 Ħ Latin Capital Letter H with stroke
'.', //U+0127 ħ Latin Small Letter H with stroke
'.', //U+0128 Ĩ Latin Capital Letter I with tilde
'.', //U+0129 ĩ Latin Small Letter I with tilde
'I', //U+012A Ī Latin Capital Letter I with macron
'i', //U+012B ī Latin Small Letter I with macron
'.', //U+012C Ĭ Latin Capital Letter I with breve
'.', //U+012D ĭ Latin Small Letter I with breve
'I', //U+012E Į Latin Capital Letter I with ogonek
'i', //U+012F į Latin Small Letter I with ogonek
'I', //U+0130 İ Latin Capital Letter I with dot above
'i', //U+0131 ı Latin Small Letter dotless I
'.', //U+0132 IJ Latin Capital Ligature IJ
'.', //U+0133 ij Latin Small Ligature IJ
'.', //U+0134 Ĵ Latin Capital Letter J with circumflex
'.', //U+0135 ĵ Latin Small Letter J with circumflex
'K', //U+0136 Ķ Latin Capital Letter K with cedilla
'k', //U+0137 ķ Latin Small Letter K with cedilla
'.', //U+0138 ĸ Latin Small Letter Kra
0xC5, //U+0139 Ĺ Latin Capital Letter L with acute
0xE5, //U+013A ĺ Latin Small Letter L with acute
'L', //U+013B Ļ Latin Capital Letter L with cedilla
'l', //U+013C ļ Latin Small Letter L with cedilla
0xBC, //U+013D Ľ Latin Capital Letter L with caron
0xBE, //U+013E ľ Latin Small Letter L with caron
'.', //U+013F Ŀ Latin Capital Letter L with middle dot
'.', //U+0140 ŀ Latin Small Letter L with middle dot
0xA3, //U+0141 Ł Latin Capital Letter L with stroke
0xB3, //U+0142 ł Latin Small Letter L with stroke
0xD1, //U+0143 Ń Latin Capital Letter N with acute
0xF1, //U+0144 ń Latin Small Letter N with acute
'N', //U+0145 Ņ Latin Capital Letter N with cedilla
'n', //U+0146 ņ Latin Small Letter N with cedilla
0xD2, //U+0147 Ň Latin Capital Letter N with caron
0xF2, //U+0148 ň Latin Small Letter N with caron
'.', //U+0149 ʼn Latin Small Letter N preceded by apostrophe[1]
'.', //U+014A Ŋ Latin Capital Letter Eng
'.', //U+014B ŋ Latin Small Letter Eng
'O', //U+014C Ō Latin Capital Letter O with macron
'o', //U+014D ō Latin Small Letter O with macron
'.', //U+014E Ŏ Latin Capital Letter O with breve
'.', //U+014F ŏ Latin Small Letter O with breve
0xD5, //U+0150 Ő Latin Capital Letter O with double acute
0xF5, //U+0151 ő Latin Small Letter O with double acute
0226, //U+0152 ΠLatin Capital Ligature OE (mapped to PDFDocEncoding)
0234, //U+0153 œ Latin Small Ligature OE (mapped to PDFDocEncoding)
0xC0, //U+0154 Ŕ Latin Capital Letter R with acute
0xE0, //U+0155 ŕ Latin Small Letter R with acute
'R', //U+0156 Ŗ Latin Capital Letter R with cedilla
'r', //U+0157 ŗ Latin Small Letter R with cedilla
0xD8, //U+0158 Ř Latin Capital Letter R with caron
0xF8, //U+0159 ř Latin Small Letter R with caron
0x8C, //U+015A Ś Latin Capital Letter S with acute
0x9C, //U+015B ś Latin Small Letter S with acute
'.', //U+015C Ŝ Latin Capital Letter S with circumflex
'.', //U+015D ŝ Latin Small Letter S with circumflex
0xAA, //U+015E Ş Latin Capital Letter S with cedilla
0xBA, //U+015F ş Latin Small Letter S with cedilla
0x8A, //U+0160 Š Latin Capital Letter S with caron
0x9A, //U+0161 š Latin Small Letter S with caron
0xDE, //U+0162 Ţ Latin Capital Letter T with cedilla
0xFE, //U+0163 ţ Latin Small Letter T with cedilla
0x8D, //U+0164 Ť Latin Capital Letter T with caron
0x9D, //U+0165 ť Latin Small Letter T with caron
'T', //U+0166 Ŧ Latin Capital Letter T with stroke
't', //U+0167 ŧ Latin Small Letter T with stroke
'.', //U+0168 Ũ Latin Capital Letter U with tilde
'.', //U+0169 ũ Latin Small Letter U with tilde
'U', //U+016A Ū Latin Capital Letter U with macron
'u', //U+016B ū Latin Small Letter U with macron
'.', //U+016C Ŭ Latin Capital Letter U with breve
'.', //U+016D ŭ Latin Small Letter U with breve
0xD9, //U+016E Ů Latin Capital Letter U with ring above
0xF9, //U+016F ů Latin Small Letter U with ring above
0xDB, //U+0170 Ű Latin Capital Letter U with double acute
0xFB, //U+0171 ű Latin Small Letter U with double acute
'U', //U+0172 Ų Latin Capital Letter U with ogonek
'u', //U+0173 ų Latin Small Letter U with ogonek
'.', //U+0174 Ŵ Latin Capital Letter W with circumflex
'.', //U+0175 ŵ Latin Small Letter W with circumflex
'.', //U+0176 Ŷ Latin Capital Letter Y with circumflex
'.', //U+0177 ŷ Latin Small Letter Y with circumflex
0230, //U+0178 Ÿ Latin Capital Letter Y with diaeresis (mapped to PDFDocEncoding)
0x8F, //U+0179 Ź Latin Capital Letter Z with acute
0x9F, //U+017A ź Latin Small Letter Z with acute
0xAF, //U+017B Ż Latin Capital Letter Z with dot above
0xBF, //U+017C ż Latin Small Letter Z with dot above
0231, //U+017D Ž Latin Capital Letter Z with caron (mapped to PDFDocEncoding)
0236, //U+017E ž Latin Small Letter Z with caron (mapped to PDFDocEncoding)
'.', //U+017F ſ Latin Small Letter long S
// portion of latin extended b
'b', //U+0180 ƀ ƀ Latin Small Letter B with stroke
'.', //U+0181 Ɓ Ɓ Latin Capital Letter B with hook
'.', //U+0182 Ƃ Ƃ Latin Capital Letter B with top bar
'.', //U+0183 ƃ ƃ Latin Small Letter B with top bar
'.', //U+0184 Ƅ Ƅ Latin Capital Letter Tone Six
'.', //U+0185 ƅ ƅ Latin Small Letter Tone Six
'.', //U+0186 Ɔ Ɔ Latin Capital Letter Open O
'.', //U+0187 Ƈ Ƈ Latin Capital Letter C with hook
'.', //U+0188 ƈ ƈ Latin Small Letter C with hook
0xD0, //U+0189 Ɖ Ɖ Latin Capital Letter African D
'.', //U+018A Ɗ Ɗ Latin Capital Letter D with hook
'.', //U+018B Ƌ Ƌ Latin Capital Letter D with top bar
'.', //U+018C ƌ ƌ Latin Small Letter D with top bar
'.', //U+018D ƍ ƍ Latin Small Letter Turned Delta
'.', //U+018E Ǝ Ǝ Latin Capital Letter Reversed E
'.', //U+018F Ə Ə Latin Capital Letter Schwa
'.', //U+0190 Ɛ Ɛ Latin Capital Letter Open E
0x83, //U+0191 Ƒ Ƒ Latin Capital Letter F with hook (from win cp-1252)(maybe)
0x83, //U+0192 ƒ ƒ Latin Small Letter F with hook (from win cp-1252)(maybe)
'.', //U+0193 Ɠ Ɠ Latin Capital Letter G with hook
'.', //U+0194 Ɣ Ɣ Latin Capital Letter Gamma
'.', //U+0195 ƕ ƕ Latin Small Letter HV
'.', //U+0196 Ɩ Ɩ Latin Capital Letter Iota
'I', //U+0197 Ɨ Ɨ Latin Capital Letter I with stroke
'.', //U+0198 Ƙ Ƙ Latin Capital Letter K with hook
'.', //U+0199 ƙ ƙ Latin Small Letter K with hook
'l', //U+019A ƚ ƚ Latin Small Letter L with bar
'.', //U+019B ƛ ƛ Latin Small Letter Lambda with stroke
'.', //U+019C Ɯ Ɯ Latin Capital Letter Turned M
'.', //U+019D Ɲ Ɲ Latin Capital Letter N with left hook
'.', //U+019E ƞ ƞ Latin Small Letter N with long right leg
'O', //U+019F Ɵ Ɵ Latin Capital Letter O with middle tilde
'O', //U+01A0 Ơ Ơ Latin Capital Letter O with horn
'o', //U+01A1 ơ ơ Latin Small Letter O with horn
'.', //U+01A2 Ƣ Ƣ Latin Capital Letter OI (= Latin Capital Letter Gha)
'.', //U+01A3 ƣ ƣ Latin Small Letter OI (= Latin Small Letter Gha)
'.', //U+01A4 Ƥ Ƥ Latin Capital Letter P with hook
'.', //U+01A5 ƥ ƥ Latin Small Letter P with hook
'.', //U+01A6 Ʀ Ʀ Latin Letter YR
'.', //U+01A7 Ƨ Ƨ Latin Capital Letter Tone Two
'.', //U+01A8 ƨ ƨ Latin Small Letter Tone Two
'.', //U+01A9 Ʃ Ʃ Latin Capital Letter Esh
'.', //U+01AA ƪ ƪ Latin Letter Reversed Esh Loop
't', //U+01AB ƫ ƫ Latin Small Letter T with palatal hook
'.', //U+01AC Ƭ Ƭ Latin Capital Letter T with hook
'.', //U+01AD ƭ ƭ Latin Small Letter T with hook
'T', //U+01AE Ʈ Ʈ Latin Capital Letter T with retroflex hook
'U', //U+01AF Ư Ư Latin Capital Letter U with horn
'u', //U+01B0 ư ư Latin Small Letter U with horn
'.', //U+01B1 Ʊ Ʊ Latin Capital Letter Upsilon
'.', //U+01B2 Ʋ Ʋ Latin Capital Letter V with hook
'.', //U+01B3 Ƴ Ƴ Latin Capital Letter Y with hook
'.', //U+01B4 ƴ ƴ Latin Small Letter Y with hook
'.', //U+01B5 Ƶ Ƶ Latin Capital Letter Z with stroke
'.', //U+01B6 ƶ ƶ Latin Small Letter Z with stroke
'.', //U+01B7 Ʒ Ʒ Latin Capital Letter Ezh
'.', //U+01B8 Ƹ Ƹ Latin Capital Letter Ezh reversed
'.', //U+01B9 ƹ ƹ Latin Small Letter Ezh reversed
'.', //U+01BA ƺ ƺ Latin Small Letter Ezh with tail
'.', //U+01BB ƻ ƻ Latin Letter Two with stroke
'.', //U+01BC Ƽ Ƽ Latin Capital Letter Tone Five
'.', //U+01BD ƽ ƽ Latin Small Letter Tone Five
'.', //U+01BE ƾ ƾ Latin Letter Inverted Glottal Stop with stroke
'.', //U+01BF ƿ ƿ Latin Letter Wynn
'|', //U+01C0 ǀ ǀ Latin Letter Dental Click
// I couldn't figure this one out
'.', //U+01C1 ǁ ǁ Latin Letter Lateral Click
'.', //U+01C2 ǂ ǂ Latin Letter Alveolar Click
'!', //U+01C3 ǃ ǃ Latin Letter Retroflex Click
'.', //U+01C4 DŽ DŽ Latin Capital Letter DZ with caron
'.', //U+01C5 Dž Dž Latin Capital Letter D with Small Letter Z with caron
'.', //U+01C6 dž dž Latin Small Letter DZ with caron
'.', //U+01C7 LJ LJ Latin Capital Letter LJ
'.', //U+01C8 Lj Lj Latin Capital Letter L with Small Letter J
'.', //U+01C9 lj lj Latin Small Letter LJ
'.', //U+01CA NJ NJ Latin Capital Letter NJ
'.', //U+01CB Nj Nj Latin Capital Letter N with Small Letter J
'.', //U+01CC nj nj Latin Small Letter NJ
'.', //U+01CD Ǎ Ǎ Latin Capital Letter A with caron
'.', //U+01CE ǎ ǎ Latin Small Letter A with caron
'.', //U+01CF Ǐ Ǐ Latin Capital Letter I with caron
'.', //U+01D0 ǐ ǐ Latin Small Letter I with caron
'.', //U+01D1 Ǒ Ǒ Latin Capital Letter O with caron
'.', //U+01D2 ǒ ǒ Latin Small Letter O with caron
'.', //U+01D3 Ǔ Ǔ Latin Capital Letter U with caron
'.', //U+01D4 ǔ ǔ Latin Small Letter U with caron
'.', //U+01D5 Ǖ Ǖ Latin Capital Letter U with diaeresis and macron
'.', //U+01D6 ǖ ǖ Latin Small Letter U with diaeresis and macron
'.', //U+01D7 Ǘ Ǘ Latin Capital Letter U with diaeresis and acute
'.', //U+01D8 ǘ ǘ Latin Small Letter U with diaeresis and acute
'.', //U+01D9 Ǚ Ǚ Latin Capital Letter U with diaeresis and caron
'.', //U+01DA ǚ ǚ Latin Small Letter U with diaeresis and caron
'.', //U+01DB Ǜ Ǜ Latin Capital Letter U with diaeresis and grave
'.', //U+01DC ǜ ǜ Latin Small Letter U with diaeresis and grave
'.', //U+01DD ǝ ǝ Latin Small Letter Turned E
'A', //U+01DE Ǟ Ǟ Latin Capital Letter A with diaeresis and macron
'a', //U+01DF ǟ ǟ Latin Small Letter A with diaeresis and macron
'.', //U+01E0 Ǡ Ǡ Latin Capital Letter A with dot above and macron
'.', //U+01E1 ǡ ǡ Latin Small Letter A with dot above and macron
'.', //U+01E2 Ǣ Ǣ Latin Capital Letter Æ with macron
'.', //U+01E3 ǣ ǣ Latin Small Letter Æ with macron
'G', //U+01E4 Ǥ Ǥ Latin Capital Letter G with stroke
'g', //U+01E5 ǥ ǥ Latin Small Letter G with stroke
'.', //U+01E6 Ǧ Ǧ Latin Capital Letter G with caron
'.', //U+01E7 ǧ ǧ Latin Small Letter G with caron
'.', //U+01E8 Ǩ Ǩ Latin Capital Letter K with caron
'.', //U+01E9 ǩ ǩ Latin Small Letter K with caron
'.', //U+01EA Ǫ Ǫ Latin Capital Letter O with ogonek
'.', //U+01EB ǫ ǫ Latin Small Letter O with ogonek
'O', //U+01EC Ǭ Ǭ Latin Capital Letter O with ogonek and macron
'o', //U+01ED ǭ ǭ Latin Small Letter O with ogonek and macron
'.', //U+01EE Ǯ Ǯ Latin Capital Letter Ezh with caron
'.', //U+01EF ǯ ǯ Latin Small Letter Ezh with caron
'.', //U+01F0 ǰ ǰ Latin Small Letter J with caron
'.', //U+01F1 DZ DZ Latin Capital Letter DZ
'.', //U+01F2 Dz Dz Latin Capital Letter D with Small Letter Z
'.', //U+01F3 dz dz Latin Small Letter DZ
'.', //U+01F4 Ǵ Ǵ Latin Capital Letter G with acute
'.', //U+01F5 ǵ ǵ Latin Small Letter G with acute
'.', //U+01F6 Ƕ Ƕ Latin Capital Letter Hwair
'.', //U+01F7 Ƿ Ƿ Latin Capital Letter Wynn
'.', //U+01F8 Ǹ Ǹ Latin Capital Letter N with grave
'.', //U+01F9 ǹ ǹ Latin Small Letter N with grave
'.', //U+01FA Ǻ Ǻ Latin Capital Letter A with ring above and acute
'.', //U+01FB ǻ ǻ Latin Small Letter A with ring above and acute
'.', //U+01FC Ǽ Ǽ Latin Capital Letter Æ with acute
'.', //U+01FD ǽ ǽ Latin Small Letter Æ with acute
'.', //U+01FE Ǿ Ǿ Latin Capital Letter O with stroke and acute
'.' //U+01FF ǿ ǿ Latin Small Letter O with stroke and acute
};
/*
Older PDF security passwords use PDFDocEncoding, which is a modified iso-8859-1.
Newer PDF security (version 5) passwords use unicode.
This function is just for older PDF security passwords, since pdftk doesn't yet
handle version 5 security.
In practice, Acrobat/Reader accepts password characters outside of PDFDocEncoding.
Returns -1 if input ss uses invalid characters
otherwise returns the number of bytes copied to bb.
If bb is null, then returns the number of bytes needed to copy ss.
If we are encrypting, allow only the most conservative set of input characters
in order to maximize platform independence.
If we are decrypting, allow as many input characters as possible.
*/
int utf8_password_to_pdfdoc( jbyte* bb, const char* ss, int ss_size, bool encrypt_b ) {
int ret_val= 0;
for( int ii= 0; ii< ss_size && ss[ii] && ret_val!= -1; ) {
// decode UTF-8
unsigned long data= 0;
//
// our greatest valid point is 0x2122, so testing out to three bytes is enough
if( (ss[ii] & 0x80) == 0 )
{ // single byte
data= ss[ii];
ii++;
}
else if( (ss[ii] & 0xE0) == 0xC0 &&
ii+ 1< ss_size && (ss[ii+ 1] & 0xC0)== 0x80 )
{ // two-byte
data= (ss[ii] & 0x1f);
data= data<< 6;
data= data+ (ss[ii+ 1] & 0x3f);
ii+= 2;
}
else if( (ss[ii] & 0xF0) == 0xE0 &&
ii+ 1< ss_size && (ss[ii+ 1] & 0xC0)== 0x80 &&
ii+ 2< ss_size && (ss[ii+ 2] & 0xC0)== 0x80 )
{ // three-byte
data= (ss[ii] & 0x0f);
data= data<< 6;
data= data+ (ss[ii+ 1] & 0x3f);
data= data<< 6;
data= data+ (ss[ii+ 2] & 0x3f);
ii+= 3;
}
else { // something else: out of range
ret_val= -1;
break; // exit loop
}
if( 0x20<= data && data< 0x7f || 0xa0<= data && data<= 0xff ) {
// data point good
}
else { // convert some unicode points to PDFDocEncoding
switch( data ) {
case 0x0152: // OE ligature
data= 0226;
break;
case 0x0153: // oe ligature
data= 0234;
break;
case 0x0160: // Scaron
data= 0227;
break;
case 0x017E: // zcaron
data= 0236;
break;
case 0x0178: // Ydieresis
data= 0230;
break;
case 0x017D: // Zcaron
data= 0231;
break;
case 0x0192: // florin
data= 0206;
break;
case 0x0161: // scaron
data= 0235;
break;
default:
if( encrypt_b ) { // data point out of bounds
ret_val= -1;
break;
}
else {
// password is being used to decrypt, so test for more mappings to PDFDocEncoding;
if( 0x100<= data && data<= 0x1FF ) {
// use our latin extended windows map; these points are accepted by Acrobat/Reader
// but are mapped to single-byte alternatives in a platform-dependent way
data= unicode_latin_extended_windows_map[ data- 0x100 ];
}
else {
// in practice, Acorbat/Reader won't allow these characters to be input for V4 security and earlier;
switch( data ) {
case 0x20AC: // Euro
data= 0240;
break;
case 0x2022: // bullet
data= 0200;
break;
case 0x2020: // dagger
data= 0201;
break;
case 0x2021: // daggerdbl
data= 0202;
break;
case 0x2026: // ellipsis
data= 0203;
break;
case 0x02C6: // circumflex
data= 0032;
break;
case 0x2014 : // emdash
data= 0204;
break;
case 0x2013: // endash
data= 0205;
break;
case 0x2039: // guilsinglleft
data= 0210;
break;
case 0x203A: // guilsinglright
data= 0211;
break;
case 0x2030: // perthousand
data= 0213;
break;
case 0x201E: // quotedblbase
data= 0214;
break;
case 0x201C: // quotedblleft
data= 0215;
break;
case 0x201D: // quotedblright
data= 0216;
break;
case 0x2018: // quoteleft
data= 0217;
break;
case 0x2019: // quoteright
data= 0220;
break;
case 0x201A: // quotesinglebase
data= 0221;
break;
case 0x02DC: // tilde
data= 0037;
break;
case 0x2122: // trademark
data= 0222;
break;
default:
ret_val= -1; // data point is still out of bounds
break;
}
}
}
}
}
if( ret_val!= -1 ) {
if( bb )
bb[ ret_val ]= data;
++ret_val;
}
}
return ret_val;
}