/* $Id: ckmxla.c,v 1.6 91/12/15 23:18:06 rick Exp $ * $Source: /uw/mackermit/RCS/ckmxla.c,v $ *------------------------------------------------------------------ * $Log: ckmxla.c,v $ * Revision 1.6 91/12/15 23:18:06 rick * ut9 * * Revision 1.5 91/10/22 11:56:16 rick * Fixup includes. * * Revision 1.4 91/10/21 21:43:58 fdc * Make sure all sources lines are < 80. * Update with a year's worth of changes from Unix version, * but use only three character sets. Fix the tables, functions, * and tables of functions. And the comments. Etc etc. * * Revision 1.3 91/10/03 12:43:03 rick * UT(5) * *------------------------------------------------------------------ * $Endlog$ */ char *xlav = "Macintosh Character Set Translation 5A(011), 25 Dec 91"; /* C K M X L A */ /* C-Kermit tables and functions supporting character set translation. */ /* Macintosh-only version */ /* Author: Frank da Cruz (fdc@columbia.edu, FDCCU@CUVMA.BITNET), Columbia University Center for Computing Activities. Copyright (C) 1985, 1992, Trustees of Columbia University in the City of New York. Permission is granted to any individual or institution to use this software as long as it is not sold for profit. This copyright notice must be retained. This software may not be included in commercial products without written permission of Columbia University. */ #include "ckcdeb.h" /* Includes... */ #include "ckcker.h" #include "ckucmd.h" /* Needed for struct keytab */ #include "ckmdef.h" #include "ckmptp.h" /* ckm* Prototypes */ #include "ckcxla.h" #include "ckmxla.h" #ifndef NULL #define NULL 0 #endif /* Character set translation data and functions */ extern int zincnt; extern char *zinptr; extern int zoutcnt; extern char *zoutptr; int tslevel = TS_L0; /* Transfer syntax level (0,1,2) */ int tcharset = TC_TRANSP; /* Transfer syntax character set */ int fcharset = FC_APPQD; /* Local file character set */ int tcsr = FC_USASCII; /* Remote terminal character set */ int tcsl = FC_APPQD; /* Local terminal character set */ int language = L_USASCII; /* Language */ /* This list is indexed by the transfer character set number. */ struct csinfo tcsinfo[] = { /* Transfer character-set info */ /* Name size code designator alphabet keyword */ "TRANSPARENT", 256,TC_TRANSP, "", AL_UNK, "transparent", /* 0 */ "ASCII", 128,TC_USASCII,"", AL_ROMAN,"ascii", /* 1 */ "LATIN1, ISO 8859-1",256,TC_1LATIN, "I6/100",AL_ROMAN,"latin1-iso", /* 2 */ }; int ntcsets = (sizeof(tcsinfo) / sizeof(struct csinfo)); struct keytab tcstab[] = { /* Keyword table for */ "ascii", TC_USASCII, 0, /* SET TRANSFER CHARACTER-SET */ "latin1-iso", TC_1LATIN, 0, "transparent", TC_TRANSP, 0 }; int ntcs = (sizeof(tcstab) / sizeof(struct keytab)); /* Grrr... Had to back off on moving this to ckmxla.h because that file */ /* is included by more than one module, so link complains about multiple */ /* definitions of _fcsinfo, _fcstab, etc. */ /* File character set information structure, indexed by character set code, */ /* as defined in ckmxla.h. This table must be in order of file character */ /* set number! */ struct csinfo fcsinfo[] = { /* File character set information... */ /* Descriptive Name Size Designator */ "US ASCII", 128, FC_USASCII, NULL, AL_ROMAN, "ascii", "ISO 8859-1 Latin-1", 256, FC_1LATIN, NULL, AL_ROMAN,"latin1-iso", "Macintosh Latin", 256, FC_APPQD, NULL, AL_ROMAN,"macintosh-latin" }; /* Local file character sets */ struct keytab fcstab[] = { /* Keyword table for 'set file character-set' */ /* Keyword Value Flags */ "apple-quickdraw", FC_APPQD, CM_INV, /* Macintosh Quickraw */ "ascii", FC_USASCII, 0, /* ASCII */ "latin1-iso", FC_1LATIN, 0, /* ISO Latin Alphabet 1 */ "macintosh-latin", FC_APPQD, 0, /* "Extended Mac Latin */ }; int nfilc = (sizeof(fcstab) / sizeof(struct keytab)); /* size of this table */ /* Languages: This table allows C-Kermit to have a SET LANGUAGE command to apply special language-specific rules when translating from a character set that contains national characters into plain ASCII, like German umlaut-a becomes ae. Originally, I thought it would be a good idea to let SET LANGUAGE also select an appropriate FILE CHARACTER-SET and TRANSFER CHARACTER-SET automatically, and these are included in the langinfo structure. Later I realized that this was a bad idea. Users are confused by unexpected side effects. If this functionality is desired, it's better to define a macro to do it. */ struct langinfo langs[] = { /* Language code File Charset Xfer Charset Name */ L_USASCII, FC_USASCII, TC_USASCII, "ASCII (American English)", L_DANISH, FC_APPQD, TC_1LATIN, "Danish", L_DUTCH, FC_APPQD, TC_1LATIN, "Dutch", L_FINNISH, FC_APPQD, TC_1LATIN, "Finnish", L_FRENCH, FC_APPQD, TC_1LATIN, "French", L_GERMAN, FC_APPQD, TC_1LATIN, "German", L_HUNGARIAN, FC_APPQD, TC_1LATIN, "Hungarian", L_ICELANDIC, FC_APPQD, TC_1LATIN, "Icelandic", L_ITALIAN, FC_APPQD, TC_1LATIN, "Italian", L_NORWEGIAN, FC_APPQD, TC_1LATIN, "Norwegian", L_PORTUGUESE, FC_APPQD, TC_1LATIN, "Portuguese", L_SPANISH, FC_APPQD, TC_1LATIN, "Spanish", L_SWEDISH, FC_APPQD, TC_1LATIN, "Swedish", L_SWISS, FC_APPQD, TC_1LATIN, "Swiss" }; int nlangs = (sizeof(langs) / sizeof(struct langinfo)); /* Keyword table for the SET LANGUAGE command. Only a few of these (German, Scandinavian, etc) actually do anything. The language is used to invoke special translation rules when converting from an 8-bit character set to ASCII; for example, German u-diaeresis becomes "ue", Dutch y-diaeresis becomes "ij". Languages without associated rules are invisible (CM_INV). */ struct keytab lngtab[] = { "ascii", L_USASCII, CM_INV, "danish", L_DANISH, 0, "dutch", L_DUTCH, 0, "english", L_USASCII, CM_INV, "finnish", L_FINNISH, 0, "french", L_FRENCH, 0, "german", L_GERMAN, 0, #ifdef HEBREW "hebrew", L_HEBREW, CM_INV, #endif /* HEBREW */ "hungarian", L_HUNGARIAN, CM_INV, "icelandic", L_ICELANDIC, 0, "italian", L_ITALIAN, CM_INV, #ifdef KANJI "japanese", L_JAPANESE, CM_INV, #endif /* KANJI */ "norwegian", L_NORWEGIAN, 0, "none", L_USASCII, 0, "portuguese", L_PORTUGUESE, CM_INV, #ifdef CYRILLIC "russian", L_RUSSIAN, 0, #endif /* CYRILLIC */ "spanish", L_SPANISH, CM_INV, "swedish", L_SWEDISH, 0 #ifdef CYRILLIC , "ukrainian", L_RUSSIAN, 0 #endif /* CYRILLIC */ }; int nlng = (sizeof(lngtab) / sizeof(struct keytab)); /* how many languages */ /* Translation tables ... */ /* Note, many more can and should be added, space permitting! Presently we have only ASCII and Latin-1 as transfer character sets and ASCII, Latin-1, and the Adobe-extended-Macintosh set as file character sets. For each pair of (file,transfer) character sets, we need two translation functions, one for sending, one for receiving. It is recommended that functions and tables for all computers be included in this file, perhaps within #ifdef's, so that corrections need be made only in one place. */ /* Here is the first table, fully annotated... */ CHAR yl1as[] = { /* ISO 8859-1 Latin Alphabet 1 to US ASCII */ /* Source character Description => Translation */ /* Dec row/col Set */ 0, /* 000 00/00 C0 NUL Ctrl-@ => (self) */ 1, /* 001 00/01 C0 SOH Ctrl-A => (self) */ 2, /* 002 00/02 C0 STX Ctrl-B => (self) */ 3, /* 003 00/03 C0 ETX Ctrl-C => (self) */ 4, /* 004 00/04 C0 EOT Ctrl-D => (self) */ 5, /* 005 00/05 C0 ENQ Ctrl-E => (self) */ 6, /* 006 00/06 C0 ACK Ctrl-F => (self) */ 7, /* 007 00/07 C0 BEL Ctrl-G => (self) */ 8, /* 008 00/08 C0 BS Ctrl-H => (self) */ 9, /* 009 00/09 C0 HT Ctrl-I => (self) */ 10, /* 010 00/10 C0 LF Ctrl-J => (self) */ 11, /* 011 00/11 C0 VT Ctrl-K => (self) */ 12, /* 012 00/12 C0 FF Ctrl-L => (self) */ 13, /* 013 00/13 C0 CR Ctrl-M => (self) */ 14, /* 014 00/14 C0 SO Ctrl-N => (self) */ 15, /* 015 00/15 C0 SI Ctrl-O => (self) */ 16, /* 016 01/00 C0 DLE Ctrl-P => (self) */ 17, /* 017 01/01 C0 DC1 Ctrl-Q => (self) */ 18, /* 018 01/02 C0 DC2 Ctrl-R => (self) */ 19, /* 019 01/03 C0 DC3 Ctrl-S => (self) */ 20, /* 020 01/04 C0 DC4 Ctrl-T => (self) */ 21, /* 021 01/05 C0 NAK Ctrl-U => (self) */ 22, /* 022 01/06 C0 SYN Ctrl-V => (self) */ 23, /* 023 01/07 C0 ETB Ctrl-W => (self) */ 24, /* 024 01/08 C0 CAN Ctrl-X => (self) */ 25, /* 025 01/09 C0 EM Ctrl-Y => (self) */ 26, /* 026 01/10 C0 SUB Ctrl-Z => (self) */ 27, /* 027 01/11 C0 ESC Ctrl-[ => (self) */ 28, /* 028 01/12 C0 FS Ctrl-\ => (self) */ 29, /* 029 01/13 C0 GS Ctrl-] => (self) */ 30, /* 030 01/14 C0 RS Ctrl-^ => (self) */ 31, /* 031 01/15 C0 US Ctrl-_ => (self) */ 32, /* 032 02/00 SP Space => (self) */ 33, /* 033 02/01 G0 ! Exclamation mark => (self) */ 34, /* 034 02/02 G0 " Doublequote => (self) */ 35, /* 035 02/03 G0 # Number sign => (self) */ 36, /* 036 02/04 G0 $ Dollar sign => (self) */ 37, /* 037 02/05 G0 % Percent sign => (self) */ 38, /* 038 02/06 G0 & Ampersand => (self) */ 39, /* 039 02/07 G0 ' Apostrophe => (self) */ 40, /* 040 02/08 G0 ( Left parenthesis => (self) */ 41, /* 041 02/09 G0 ) Right parenthesis => (self) */ 42, /* 042 02/10 G0 * Asterisk => (self) */ 43, /* 043 02/11 G0 + Plus sign => (self) */ 44, /* 044 02/12 G0 , Comma => (self) */ 45, /* 045 02/13 G0 - Hyphen, minus sign => (self) */ 46, /* 046 02/14 G0 . Period, full stop => (self) */ 47, /* 047 02/15 G0 / Slash, solidus => (self) */ 48, /* 048 03/00 G0 0 Digit 0 => (self) */ 49, /* 049 03/01 G0 1 Digit 1 => (self) */ 50, /* 050 03/02 G0 2 Digit 2 => (self) */ 51, /* 051 03/03 G0 3 Digit 3 => (self) */ 52, /* 052 03/04 G0 4 Digit 4 => (self) */ 53, /* 053 03/05 G0 5 Digit 5 => (self) */ 54, /* 054 03/06 G0 6 Digit 6 => (self) */ 55, /* 055 03/07 G0 7 Digit 7 => (self) */ 56, /* 056 03/08 G0 8 Digit 8 => (self) */ 57, /* 057 03/09 G0 9 Digit 9 => (self) */ 58, /* 058 03/10 G0 : Colon => (self) */ 59, /* 059 03/11 G0 ; Semicolon => (self) */ 60, /* 060 03/12 G0 < Less-than sign => (self) */ 61, /* 061 03/13 G0 = Equals sign => (self) */ 62, /* 062 03/14 G0 > Greater-than sign => (self) */ 63, /* 063 03/15 G0 ? Question mark => (self) */ 64, /* 064 04/00 G0 @ Commercial at sign => (self) */ 65, /* 065 04/01 G0 A Letter A => (self) */ 66, /* 066 04/02 G0 B Letter B => (self) */ 67, /* 067 04/03 G0 C Letter C => (self) */ 68, /* 068 04/04 G0 D Letter D => (self) */ 69, /* 069 04/05 G0 E Letter E => (self) */ 70, /* 070 04/06 G0 F Letter F => (self) */ 71, /* 071 04/07 G0 G Letter G => (self) */ 72, /* 072 04/08 G0 H Letter H => (self) */ 73, /* 073 04/09 G0 I Letter I => (self) */ 74, /* 074 04/10 G0 J Letter J => (self) */ 75, /* 075 04/11 G0 K Letter K => (self) */ 76, /* 076 04/12 G0 L Letter L => (self) */ 77, /* 077 04/13 G0 M Letter M => (self) */ 78, /* 078 04/14 G0 N Letter N => (self) */ 79, /* 079 04/15 G0 O Letter O => (self) */ 80, /* 080 05/00 G0 P Letter P => (self) */ 81, /* 081 05/01 G0 Q Letter Q => (self) */ 82, /* 082 05/02 G0 R Letter R => (self) */ 83, /* 083 05/03 G0 S Letter S => (self) */ 84, /* 084 05/04 G0 T Letter T => (self) */ 85, /* 085 05/05 G0 U Letter U => (self) */ 86, /* 086 05/06 G0 V Letter V => (self) */ 87, /* 087 05/07 G0 W Letter W => (self) */ 88, /* 088 05/08 G0 X Letter X => (self) */ 89, /* 089 05/09 G0 Y Letter Y => (self) */ 90, /* 090 05/10 G0 Z Letter Z => (self) */ 91, /* 091 05/11 G0 [ Left square bracket => (self) */ 92, /* 092 05/12 G0 \ Reverse slash => (self) */ 93, /* 093 05/13 G0 ] Right square bracket => (self) */ 94, /* 094 05/14 G0 ^ Circumflex accent => (self) */ 95, /* 095 05/15 G0 _ Underline, low line => (self) */ 96, /* 096 06/00 G0 ` Grave accent => (self) */ 97, /* 097 06/01 G0 a Letter a => (self) */ 98, /* 098 06/02 G0 b Letter b => (self) */ 99, /* 099 06/03 G0 c Letter c => (self) */ 100, /* 100 06/04 G0 d Letter d => (self) */ 101, /* 101 06/05 G0 e Letter e => (self) */ 102, /* 102 06/06 G0 f Letter f => (self) */ 103, /* 103 06/07 G0 g Letter g => (self) */ 104, /* 104 06/08 G0 h Letter h => (self) */ 105, /* 105 06/09 G0 i Letter i => (self) */ 106, /* 106 06/10 G0 j Letter j => (self) */ 107, /* 107 06/11 G0 k Letter k => (self) */ 108, /* 108 06/12 G0 l Letter l => (self) */ 109, /* 109 06/13 G0 m Letter m => (self) */ 110, /* 110 06/14 G0 n Letter n => (self) */ 111, /* 111 06/15 G0 o Letter o => (self) */ 112, /* 112 07/00 G0 p Letter p => (self) */ 113, /* 113 07/01 G0 q Letter q => (self) */ 114, /* 114 07/02 G0 r Letter r => (self) */ 115, /* 115 07/03 G0 s Letter s => (self) */ 116, /* 116 07/04 G0 t Letter t => (self) */ 117, /* 117 07/05 G0 u Letter u => (self) */ 118, /* 118 07/06 G0 v Letter v => (self) */ 119, /* 119 07/07 G0 w Letter w => (self) */ 120, /* 120 07/08 G0 x Letter x => (self) */ 121, /* 121 07/09 G0 y Letter y => (self) */ 122, /* 122 07/10 G0 z Letter z => (self) */ 123, /* 123 07/11 G0 { Left curly bracket => (self) */ 124, /* 124 07/12 G0 | Vertical bar => (self) */ 125, /* 125 07/13 G0 } Right curly bracket => (self) */ 126, /* 126 07/14 G0 ~ Tilde => (self) */ 127, /* 127 07/15 DEL Delete, Rubout => (self) */ UNK, /* 128 08/00 C1 => UNK */ UNK, /* 129 08/01 C1 => UNK */ UNK, /* 130 08/02 C1 => UNK */ UNK, /* 131 08/03 C1 => UNK */ UNK, /* 132 08/04 C1 IND => UNK */ UNK, /* 133 08/05 C1 NEL => UNK */ UNK, /* 134 08/06 C1 SSA => UNK */ UNK, /* 135 08/07 C1 ESA => UNK */ UNK, /* 136 08/08 C1 HTS => UNK */ UNK, /* 137 08/09 C1 => UNK */ UNK, /* 138 08/10 C1 => UNK */ UNK, /* 139 08/11 C1 => UNK */ UNK, /* 140 08/12 C1 => UNK */ UNK, /* 141 08/13 C1 RI => UNK */ UNK, /* 142 08/14 C1 SS2 => UNK */ UNK, /* 143 08/15 C1 SS3 => UNK */ UNK, /* 144 09/00 C1 DCS => UNK */ UNK, /* 145 09/01 C1 => UNK */ UNK, /* 146 09/02 C1 => UNK */ UNK, /* 147 09/03 C1 STS => UNK */ UNK, /* 148 09/04 C1 => UNK */ UNK, /* 149 09/05 C1 => UNK */ UNK, /* 150 09/06 C1 SPA => UNK */ UNK, /* 151 09/07 C1 EPA => UNK */ UNK, /* 152 09/08 C1 => UNK */ UNK, /* 153 09/09 C1 => UNK */ UNK, /* 154 09/10 C1 => UNK */ UNK, /* 155 09/11 C1 CSI => UNK */ UNK, /* 156 09/12 C1 ST => UNK */ UNK, /* 157 09/13 C1 OSC => UNK */ UNK, /* 158 09/14 C1 PM => UNK */ UNK, /* 159 09/15 C1 APC => UNK */ 32, /* 160 10/00 G1 No-break space => SP */ 33, /* 161 10/01 G1 Inverted exclamation => ! */ 99, /* 162 10/02 G1 Cent sign => c */ 35, /* 163 10/03 G1 Pound sign => # */ 36, /* 164 10/04 G1 Currency sign => $ */ 89, /* 165 10/05 G1 Yen sign => Y */ 124, /* 166 10/06 G1 Broken bar => | */ 80, /* 167 10/07 G1 Paragraph sign => P */ 34, /* 168 10/08 G1 Diaeresis => " */ 67, /* 169 10/09 G1 Copyright sign => C */ 97, /* 170 10/10 G1 Feminine ordinal => a */ 34, /* 171 10/11 G1 Left angle quotation => " */ 126, /* 172 10/12 G1 Not sign => ~ */ 45, /* 173 10/13 G1 Soft hyphen => - */ 82, /* 174 10/14 G1 Registered trade mark => R */ 95, /* 175 10/15 G1 Macron => _ */ 111, /* 176 11/00 G1 Degree sign, ring above => o */ UNK, /* 177 11/01 G1 Plus-minus sign => UNK */ 50, /* 178 11/02 G1 Superscript two => 2 */ 51, /* 179 11/03 G1 Superscript three => 3 */ 39, /* 180 11/04 G1 Acute accent => ' */ 117, /* 181 11/05 G1 Micro sign => u */ 45, /* 182 11/06 G1 Pilcrow sign => - */ 45, /* 183 11/07 G1 Middle dot => - */ 44, /* 184 11/08 G1 Cedilla => , */ 49, /* 185 11/09 G1 Superscript one => 1 */ 111, /* 186 11/10 G1 Masculine ordinal => o */ 34, /* 187 11/11 G1 Right angle quotation => " */ UNK, /* 188 11/12 G1 One quarter => UNK */ UNK, /* 189 11/13 G1 One half => UNK */ UNK, /* 190 11/14 G1 Three quarters => UNK */ 63, /* 191 11/15 G1 Inverted question mark => ? */ 65, /* 192 12/00 G1 A grave => A */ 65, /* 193 12/01 G1 A acute => A */ 65, /* 194 12/02 G1 A circumflex => A */ 65, /* 195 12/03 G1 A tilde => A */ 65, /* 196 12/04 G1 A diaeresis => A */ 65, /* 197 12/05 G1 A ring above => A */ 65, /* 198 12/06 G1 A with E => A */ 67, /* 199 12/07 G1 C Cedilla => C */ 69, /* 200 12/08 G1 E grave => E */ 69, /* 201 12/09 G1 E acute => E */ 69, /* 202 12/10 G1 E circumflex => E */ 69, /* 203 12/11 G1 E diaeresis => E */ 73, /* 204 12/12 G1 I grave => I */ 73, /* 205 12/13 G1 I acute => I */ 73, /* 206 12/14 G1 I circumflex => I */ 73, /* 207 12/15 G1 I diaeresis => I */ 68, /* 208 13/00 G1 Icelandic Eth => D */ 78, /* 209 13/01 G1 N tilde => N */ 79, /* 210 13/02 G1 O grave => O */ 79, /* 211 13/03 G1 O acute => O */ 79, /* 212 13/04 G1 O circumflex => O */ 79, /* 213 13/05 G1 O tilde => O */ 79, /* 214 13/06 G1 O diaeresis => O */ 120, /* 215 13/07 G1 Multiplication sign => x */ 79, /* 216 13/08 G1 O oblique stroke => O */ 85, /* 217 13/09 G1 U grave => U */ 85, /* 218 13/10 G1 U acute => U */ 85, /* 219 13/11 G1 U circumflex => U */ 85, /* 220 13/12 G1 U diaeresis => U */ 89, /* 221 13/13 G1 Y acute => Y */ 84, /* 222 13/14 G1 Icelandic Thorn => T */ 115, /* 223 13/15 G1 German sharp s => s */ 97, /* 224 14/00 G1 a grave => a */ 97, /* 225 14/01 G1 a acute => a */ 97, /* 226 14/02 G1 a circumflex => a */ 97, /* 227 14/03 G1 a tilde => a */ 97, /* 228 14/04 G1 a diaeresis => a */ 97, /* 229 14/05 G1 a ring above => a */ 97, /* 230 14/06 G1 a with e => a */ 99, /* 231 14/07 G1 c cedilla => c */ 101, /* 232 14/08 G1 e grave => e */ 101, /* 233 14/09 G1 e acute => e */ 101, /* 234 14/10 G1 e circumflex => e */ 101, /* 235 14/11 G1 e diaeresis => e */ 105, /* 236 14/12 G1 i grave => i */ 105, /* 237 14/13 G1 i acute => i */ 105, /* 238 14/14 G1 i circumflex => i */ 105, /* 239 14/15 G1 i diaeresis => i */ 100, /* 240 15/00 G1 Icelandic eth => d */ 110, /* 241 15/01 G1 n tilde => n */ 111, /* 242 15/02 G1 o grave => o */ 111, /* 243 15/03 G1 o acute => o */ 111, /* 244 15/04 G1 o circumflex => o */ 111, /* 245 15/05 G1 o tilde => o */ 111, /* 246 15/06 G1 o diaeresis => o */ 47, /* 247 15/07 G1 Division sign => / */ 111, /* 248 15/08 G1 o oblique stroke => o */ 117, /* 249 15/09 G1 u grave => u */ 117, /* 250 15/10 G1 u acute => u */ 117, /* 251 15/11 G1 u circumflex => u */ 117, /* 252 15/12 G1 u diaeresis => u */ 121, /* 253 15/13 G1 y acute => y */ 116, /* 254 15/14 G1 Icelandic thorn => t */ 121 /* 255 15/15 G1 y diaeresis => y */ } ; /* Translation tables for ISO Latin Alphabet 1 to local file character sets */ CHAR yl1aq[] = { /* Latin-1 to Extended Mac Latin (based on Apple QuickDraw) */ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 182, 183, 184, 185, 189, 196, 197, 198, 206, 207, 210, 211, 217, 218, 195, 212, 209, 215, 213, 226, 227, 228, 240, 245, 246, 247, 249, 250, 251, 253, 254, 255, 202, 193, 162, 163, 219, 180, 201, 164, 172, 169, 187, 199, 194, 208, 168, 248, 161, 177, 170, 173, 171, 181, 166, 225, 252, 176, 188, 200, 178, 179, 186, 192, 203, 231, 229, 204, 128, 129, 174, 130, 233, 131, 230, 232, 237, 234, 235, 236, 220, 132, 241, 238, 239, 205, 133, 165, 175, 244, 242, 243, 134, 160, 222, 167, 136, 135, 137, 139, 138, 140, 190, 141, 143, 142, 144, 145, 147, 146, 148, 149, 221, 150, 152, 151, 153, 155, 154, 214, 191, 157, 156, 158, 159, 224, 223, 216 }; /* Local file character sets to ISO Latin Alphabet 1 */ #ifdef COMMENT CHAR yasl1[] = { /* ASCII to Latin-1 */ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127 }; #endif /* COMMENT */ CHAR yaql1[] = { /* Extended Mac Latin (based on Apple Quickdraw) to Latin-1 */ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 196, 197, 199, 201, 209, 214, 220, 225, 224, 226, 228, 227, 229, 231, 233, 232, 234, 235, 237, 236, 238, 239, 241, 243, 242, 244, 246, 245, 250, 249, 251, 252, 221, 176, 162, 163, 167, 215, 182, 223, 174, 169, 178, 180, 168, 179, 198, 216, 185, 177, 188, 189, 165, 181, 128, 129, 130, 131, 190, 170, 186, 132, 230, 248, 191, 161, 172, 142, 133, 134, 135, 171, 187, 166, 160, 192, 195, 213, 136, 137, 173, 144, 138, 139, 143, 146, 247, 145, 255, 140, 141, 164, 208, 240, 222, 254, 253, 183, 147, 148, 149, 194, 202, 193, 203, 200, 205, 206, 207, 204, 211, 212, 150, 210, 218, 219, 217, 151, 152, 153, 175, 154, 155, 156, 184, 157, 158, 159 }; /* Translation functions ... */ #ifdef COMMENT /* Not needed... */ CHAR /* The identity translation function */ ident(c) CHAR c; { return(c); } #endif /* COMMENT */ /* Latin-1 to US ASCII... */ CHAR #ifdef CK_ANSIC xl1as(CHAR c) #else xl1as(c) CHAR c; #endif /* CK_ANSIC */ { /* xl1as */ switch(langs[language].id) { case L_DUTCH: if (c == 255) { /* Dutch umlaut-y */ zmstuff('j'); /* becomes ij */ return('i'); } else return(yl1as[c]); /* all others by the book */ case L_GERMAN: switch (c) { /* German, special rules. */ case 196: /* umlaut-A -> Ae */ zmstuff('e'); return('A'); case 214: /* umlaut-O -> Oe */ zmstuff('e'); return('O'); case 220: /* umlaut-U -> Ue */ zmstuff('e'); return('U'); case 228: /* umlaut-a -> ae */ zmstuff('e'); return('a'); case 246: /* umlaut-o -> oe */ zmstuff('e'); return('o'); case 252: /* umlaut-u -> ue */ zmstuff('e'); return('u'); case 223: /* ess-zet -> ss */ zmstuff('s'); return('s'); default: return(yl1as[c]); /* all others by the book */ } case L_DANISH: case L_FINNISH: case L_NORWEGIAN: case L_SWEDISH: switch (c) { /* Scandanavian languages. */ case 196: /* umlaut-A -> Ae */ case 198: /* AE ligature also -> Ae */ zmstuff('e'); return('A'); case 214: /* umlaut-O -> Oe */ case 216: /* O-slash -> Oe */ zmstuff('e'); return('O'); case 220: /* umlaut-U -> Ue */ /* return('Y'); replaced by "Ue" by popular demand. */ /* Y for Umlaut-U is only used in German names. */ zmstuff('e'); return('U'); case 228: /* umlaut-a -> ae */ case 230: /* ditto for ae ligature */ zmstuff('e'); return('a'); case 246: /* umlaut-o -> oe */ case 248: /* o-slash -> oe */ zmstuff('e'); return('o'); case 252: /* umlaut-u -> ue */ /* return('y'); replaced by "ue" by popular demand. */ zmstuff('e'); return('u'); case 197: /* A-ring -> Aa */ zmstuff('a'); return('A'); case 229: /* a-ring -> aa */ zmstuff('a'); return('a'); default: return(yl1as[c]); /* All others by the book */ } case L_ICELANDIC: /* Icelandic. */ switch (c) { case 198: /* uppercase AE -> AE */ zmstuff('e'); return('A'); case 208: /* uppercase Eth -> D */ return('D'); case 222: /* uppercase Thorn -> Th */ zmstuff('h'); return('T'); case 230: /* lowercase ae -> ae */ zmstuff('e'); return('a'); case 240: /* lowercase Eth -> d */ return('d'); case 254: /* lowercase Thorn -> th */ zmstuff('h'); return('t'); default: return(yl1as[c]); /* All others by the book */ } default: return(yl1as[c]); /* None of the above, by the table. */ } } /* Translation functions for receiving files and translating them into ASCII */ CHAR zl1as(CHAR c) { switch(langs[language].id) { case L_DUTCH: if (c == 255) { /* Dutch umlaut-y */ zdstuff('j'); /* becomes ij */ return('i'); } else return(yl1as[c]); /* all others by the book */ case L_GERMAN: switch (c) { /* German, special rules. */ case 196: /* umlaut-A -> Ae */ zdstuff('e'); return('A'); case 214: /* umlaut-O -> Oe */ zdstuff('e'); return('O'); case 220: /* umlaut-U -> Ue */ zdstuff('e'); return('U'); case 228: /* umlaut-a -> ae */ zdstuff('e'); return('a'); case 246: /* umlaut-o -> oe */ zdstuff('e'); return('o'); case 252: /* umlaut-u -> ue */ zdstuff('e'); return('u'); case 223: /* ess-zet -> ss */ zdstuff('s'); return('s'); default: return(yl1as[c]); /* all others by the book */ } case L_DANISH: case L_FINNISH: case L_NORWEGIAN: case L_SWEDISH: switch (c) { /* Scandanavian languages. */ case 196: /* umlaut-A -> Ae */ zdstuff('e'); return('A'); case 214: /* umlaut-O -> Oe */ case 216: /* O-slash -> Oe */ zdstuff('e'); return('O'); case 220: /* umlaut-U -> Y */ /* return('Y'); */ zdstuff('e'); return('U'); case 228: /* umlaut-a -> ae */ zdstuff('e'); return('a'); case 246: /* umlaut-o -> oe */ case 248: /* o-slash -> oe */ zdstuff('e'); return('o'); case 252: /* umlaut-u -> y */ /* return('y'); */ zdstuff('e'); return('u'); case 197: /* A-ring -> Aa */ zdstuff('a'); return('A'); case 229: /* a-ring -> aa */ zdstuff('a'); return('a'); default: return(yl1as[c]); /* All others by the book */ } default: return(yl1as[c]); /* Not German, by the table. */ } } /* Apple Mac to ASCII */ CHAR #ifdef CK_ANSIC xaqas(CHAR c) #else xaqas(c) CHAR c; #endif /* CK_ANSIC */ { /* xaqas */ c = yaql1[c]; /* Translate to Latin-1 */ return(xl1as(c)); /* then to ASCII. */ } CHAR #ifdef CK_ANSIC xl1aq(CHAR c) #else xl1aq(c) CHAR c; #endif /* CK_ANSIC */ { /* xl1aq */ /* Latin-1 to Apple Macintosh Character Set */ return(yl1aq[c]); } /* Apple Macintosh Character Set to Latin-1 */ CHAR #ifdef CK_ANSIC xaql1(CHAR c) #else xaql1(c) CHAR c; #endif /* CK_ANSIC */ { /* xaql1 */ return(yaql1[c]); } /* Table of translation functions for receiving files. Array of pointers to functions for translating from the transfer syntax to the local file character set. The first index is the transfer syntax character set number, the second index is the file character set number. */ #ifdef CK_ANSIC CHAR (*xlr[MAXTCSETS+1][MAXFCSETS+1])(CHAR) = #else CHAR (*xlr[MAXTCSETS+1][MAXFCSETS+1])() = #endif /* CK_ANSIC */ { NULL, /* 0,0 transparent to us ascii */ NULL, /* 0,1 transparent to latin-1 */ NULL, /* 0,2 transparent to Apple Quickdraw */ NULL, /* 1,0 ascii to us ascii */ NULL, /* 1,2 ascii to latin-1 */ NULL, /* 1,3 ascii to Apple Quickdraw */ zl1as, /* 2,0 latin-1 to us ascii */ NULL, /* 2,1 latin-1 to latin-1 */ xl1aq /* 2,2 latin-1 to Apple Quickdraw */ }; /* Translation functions for sending files. Array of pointers to functions for translating from the local file character set to the transfer syntax character set. Indexed in the same way as the xlr array above. */ #ifdef CK_ANSIC CHAR (*xls[MAXTCSETS+1][MAXFCSETS+1])(CHAR) = #else CHAR (*xls[MAXTCSETS+1][MAXFCSETS+1])() = #endif /* CK_ANSIC */ { NULL, /* 0,0 us ascii to transparent */ NULL, /* 0,1 latin-1 to transparent */ NULL, /* 0,2 Apple Quickdraw to transparent */ NULL, /* 1,0 ascii to ascii */ xl1as, /* 1,2 latin-1 to ascii */ xaqas, /* 1,3 Apple Quickdraw to ascii */ NULL, /* 2,0 ascii to latin-1 */ NULL, /* 2,1 latin-1 to latin-1 */ xaql1 /* 2,2 Apple Quickdraw to latin-1 */ };