/* * This file is part of Commodore 64 emulator * and Program Development System. * * Copyright (C) 1993-1995,1996, Jouko Valta * * 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, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * * This program converts your SEQ files as well as expands tokenized * C64/128 BASIC programs into 7-bit ASCII text. Unprintable characters * can be shown as hexadecimal codes in parenthesis, via `-c' option. * It is also possible to convert programs from ascii listings into * tokenized basic v2.0, v3.5, v4.0, v7.0 or simon's basic programs. This * program also replaces certain control code names with the actual codes. * * A list of Toolkit Basic (published by Compute! Books) token codes * would be greatly appreciated. (-: * * Runs on UNIX or Atari ST. * * In shell: * tr '\015A-Za-z\301-\332\\\|\[\{\]\}' '\012a-zA-ZA-Z\|\\\{\[\}\]' * or * tr '\015A-Za-z\\\|\[\{\]\}' '\012a-zA-Z\|\\\{\[\}\]' * * Written by * Jouko Valta * * With additional changes by * Ettore Perazzoli * Spiro Trikaliotis * * Support for Final Cartridge III extensions to c64 2.0 basic * Matti 'ccr' Hämäläinen * * Support for many of the other extensions by * Marco van den Heuvel * * Modified for use with ct-BASIC (derived from EhBASIC by Lee Davidson) by * C. Meyer, , 20.05.2009 * runs on Win32 */ /* #define DEBUG */ #include #include #include #include //#include "types.h" #define PETCATVERSION 2.17 #define PETCATLEVEL 1 /* Limits */ #define NUM_COMM 116 /* common for all versions 2.0 ... 10.0 */ #define MAX_COMM 0xFE /* common for all versions */ #define KW_NONE 0xFE /* flag unused token */ #define CLARIF_LP '#' /* control code left delimiter */ #define CLARIF_RP '#' /* control code right delimiter */ #define CLARIF_LP_ST "#" /* control code left delimiter, "string version" */ #define CLARIF_RP_ST "#" /* control code right delimiter, "string version" */ /* ------------------------------------------------------------------------- */ /* * Printer's control code symbols */ /* all numeric codes */ /* 0x00 - 0x1f */ static const char *ctrl1[] = { "", "", "", "", "", "WHT", "", "", "DISH", "ENSH", "\N", "", "\F", "\N", "SWLC", "", "", "DOWN", "RVON", "HOME", "DEL", "", "", "", "", "", "", "ESC", "RED", "RGHT", "GRN", "BLU" }; /* 0x80 - 0x9f */ static const char *ctrl2[] = { "", "ORNG", "", "", "", "F1", "F3", "F5", "F7", "F2", "F4", "F6", "F8", "SRET", "SWUC", "", "BLK", "UP", "RVOF", "CLR", "INST", "BRN", "LRED", "GRY1", "GRY2", "LGRN", "LBLU", "GRY3", "PUR", "LEFT", "YEL", "CYN" }; #define NUM_VERSIONS 1 /* * Two BASIC tokens which need some special care */ #define TOKEN_REM (0x99 - 0x80) #define TOKEN_DATA (0x83 - 0x80) /* * EhBasic Keywords Functions with (): SGN() INT() ABS() USR() FRE() POS() SQR() RND() LOG() EXP() COS() SIN() TAN() ATN() PEEK() DEEK() SADD() LEN() STR$() VAL() ASC() UCASE$() LCASE$() CHR$() HEX$() BIN$() BITTST() MAX() MIN() VARPTR() LEFT$() RIGHT$() MID$() */ const char *keyword[] = { /* EhBASIC Keywords */ "END", "FOR", "NEXT", "DATA", "INPUT", "DIM", "READ", "LET", "DEC", "GOTO", "RUN", "IF", "RESTORE", "GOSUB", "COLOR", "CURSOR", "LABCMD", "LABCLR", "LABINP", "LABOUT", "LABREQ", "LABBUS", "MACRO", "RENUMBER", "RETURN", "REM", "PLOT", "ON", "BANK", "INC", "WAIT", "LOAD", "SAVE", "DIR", "DEF", "POKE", "DOKE", "CALL", "DO", "LOOP", "PRINT", "FRAME", "LIST", "CLEAR", "NEW", "WIDTH", "GET", "SWAP", "BITSET", "BITCLR", "TAB(", "TO", "FN", "SPC(", "THEN", "NOT", "STEP", "UNTIL", "WHILE", "OFF", "+", "-", "*", "/", "^", "AND", "EOR", "OR", ">>", "<<", ">", "=", "<", "SGN(", "INT(", "ABS(", "USR(", "FRE(", "POS(", "SQR(", "RND(", "LOG(", "EXP(", "COS(", "SIN(", "TAN(", "ATN(", "PEEK(", "DEEK(", "SADD(", "LEN(", "STR$(", "VAL(", "ASC(", "UCASE$(", "LCASE$(", "CHR$(", "HEX$(", "BIN$(", "BITTST(", "MAX(", "MIN(", "PI", "TWOPI", "VARPTR(", "LEFT$(", "RIGHT$(", "MID$(", "POSITION", "GRID", "SIZE", "MOVE", "PIXEL", "LINE", "RECT", "FILL" }; /* ------------------------------------------------------------------------- */ static int parse_version(char *str); static void list_keywords(int max); static void pet_2_asc (int ctrls); static void _p_toascii(int c, int ctrls); static int p_expand(int version, int addr, int ctrls); static void p_tokenize(int version, unsigned int addr, int ctrls); static unsigned char sstrcmp(unsigned char *line, const char **wordlist, int token, int maxitems); /* ------------------------------------------------------------------------- */ static FILE *source, *dest; static int kwlen; /* ------------------------------------------------------------------------- */ int main(int argc, char **argv) { char *progname, *outfilename = NULL; int c = 0; long offset = 0; int wr_mode = 0; /* best defaults */ int load_addr = 0, ctrls= -1, hdr = -1, show_words = 0; int fil = 0, outf = 0, overwrt = 0, textmode = 0; int flg = 0; /* files on stdin */ /* Parse arguments */ progname = argv[0]; while (--argc && ((*++argv)[0] == '-')) { if (!strcmp(argv[0], "--")) { --argc; ++argv; break; } if (!strcmp(argv[0], "-l")) { /* load address */ if (argc > 1 && sscanf(argv[1], "%x", &load_addr) == 1) { --argc; ++argv; continue; } /* Fall to error */ } if (!strcmp(argv[0], "-c")) { ctrls = 1; continue; } else { if (!strcmp(argv[0], "-nc")) { ctrls = 0; continue; } } if (!strcmp(argv[0], "-k")) { show_words = 1; continue; } if (!strcmp(argv[0], "-h")) { hdr = 1; continue; } else if (!strcmp(argv[0], "-nh")) { hdr = 0; continue; } else if (!strcmp(argv[0], "-f")) { /* force overwrite */ ++overwrt; continue; } else if (!strcmp(argv[0], "-o")) { if (argc > 1) { outfilename = argv[1]; ++outf; --argc; ++argv; continue; } fprintf (stderr, "\nOutput filename missing\n"); /* Fall to error */ } /* reading offset */ if (!strcmp(argv[0], "-skip") || !strcmp(argv[0], "-offset")) { if (argc > 1 && sscanf(argv[1], "%lx", &offset) == 1) { --argc; ++argv; continue; } /* Fall to error */ } else if (!strcmp(argv[0], "-text")) { /* force text mode */ ++textmode; continue; } else if (!strcmp(argv[0], "-help") || !strncmp(argv[0], "-v", 2)) { /* version ID */ fprintf(stdout, "\n\t%s V%4.2f PL %d -- EhBASIC list/crunch utility.\n\tPart of ct-BASIC\n", progname, (float)PETCATVERSION, PETCATLEVEL ); /* Fall to error for Usage */ } fprintf(stdout, "\nUsage: %7s [-c | -nc] [-h | -nh] [-text | - | -w]" "\n\t\t[-skip ] [-l ] [--] [file list]\n\t\t[-k]\n", progname); fprintf(stdout, "\n" " -help\tOutput this help screen here\n" " -v\t\tSame as above\n" " -c\t\tcontrols (interpret also control codes) \n" " -nc\t\tno controls (suppress control codes in printout)\n" " \t\t\n" " -h\t\twrite header \n" " -nh\t\tno header \n" " -skip \tSkip bytes in the beginning of input file. Ignored on P00.\n" " -text\tForce text mode\n" " -k\t\tlist all keywords for EhBASIC\n" " -l\t\tSpecify load address for program (in hex, no loading chars!).\n" " -o\tSpecify the output file name\n" " -f\t\tForce overwritten the output file\n" " \t\tThe default depends on the BASIC version.\n"); fprintf(stdout, "\tUsage examples:\n" "\tehbc -o outputfile.txt -- inputfile.bas\n" "\t\tConvert inputfile.bas to a text file in outputfile.txt\n" "\tehbc -o outputfile.bas -- inputfile.txt\n" "\t\tConvert inputfile.txt to a BAS file in outputfile.bas\n"); exit(1); } /* * Check parameters */ if (argc) fil++; if (hdr==-1) hdr = outf ? 0 : 1; if (show_words) { list_keywords(NUM_COMM); return (0); } if (ctrls < 0) ctrls = (textmode ? 0 : 1); /*default ON for prgs, OFF for text */ if (!load_addr) { load_addr = 0x0800; } if (wr_mode) { fprintf (stderr, "\nLoad address %04x\n", load_addr); if ((load_addr & 255) != 0) { fprintf (stderr, "I'm afraid I cannot accept that.\n"); exit(1); } fprintf(stderr, "Control code set: %s\n\n", (ctrls ? "enabled" : "disabled")); } /* * Loop all files */ do { int plen = 0; flg = 0; /* stdin loop flag */ if ((source = fopen(argv[0], "rb")) == NULL) { fprintf(stderr, "\n%s: Can't open file %s\n", progname, argv[0]); exit(1); } if (!outf) dest = stdout; else { /*if (extension && *extension == '.') { sprintf(outfilename, "%s%s", argv[0], extension); }*/ if ((dest = fopen(outfilename, "wb")) == NULL) { fprintf(stderr, "\n%s: Can't open output file %s\n", progname, outfilename); exit(1); } } if (wr_mode) { p_tokenize(0, load_addr, ctrls); } else { if (hdr) fprintf(dest, "\n\n%s", (fil ? argv[0] : ""),"\n"); /* * Use TEXT mode if the offset doesn't equal BASIC load addresses * and the first bytes to be read do not contain load address. * Explicitly selected textmode overrules these conditions. */ if (textmode || ((offset & 255) !=1 && ((c = getc(source)) != EOF && ungetc(c, source) != EOF && c && c != 1)) ) { pet_2_asc(ctrls); } else { /* get load address */ getc(source); load_addr =0x800; if (hdr) fprintf(dest, "==%04x==\n", load_addr,"\n"); if (p_expand(0, load_addr, ctrls)) { fprintf(dest, "\n*** Machine language part skipped. ***\n"); } else /* End of BASIC on stdin. Is there more ? */ if (!fil && (c = getc(source)) != EOF && ungetc(c, source) != EOF && c) { ++flg; ++hdr; } } if (hdr) fputc('\n', dest); } if (fil) fclose(source); if (outf) fclose(dest); } while (flg || (fil && --argc && ++argv)); /* next file */ return(0); } /* ------------------------------------------------------------------------- */ static void list_keywords(int max) { int n,m; printf("\nAvailable EhBASIC tokens\n\n"); for (n = 0; n < max/4; n++) { for (m = 0; m < 4; m++) { printf("%3d %s \t", n*4+m, keyword[n*4+m] /*, n | 0x80*/); } printf("\n"); } printf("\n\n"); } /* ------------------------------------------------------------------------- */ /* * Conversion Routines */ static void pet_2_asc(int ctrls) { int c; while ((c = getc(source)) != EOF) { _p_toascii(c, ctrls); /* convert character */ } /* line */ } static void _p_toascii(int c, int ctrls) { switch (c) { case 0x00: /* 00 for SEQ */ case 0x0a: case 0x0d: fputc ('\n', dest); break; default: if (isprint(c)) fputc(c, dest); else if (ctrls) { fprintf(dest, CLARIF_LP_ST "$%02x" CLARIF_RP_ST, c & 0xff); } /* ctrls */ } /* switch */ } /* * This routine starts from the beginning of Basic, and not from the * load address included on program files. That way it can list from * RAM dump. */ static int p_expand(int version, int addr, int ctrls) { static char line[4]; unsigned int c; int quote, spnum, directory = 0; int sysflg = 0; /* * It seems to be common mistake not to terminate BASIC properly * before the machine language part, so we don't check for the * low byte of line link here. * Line link and line number are read separately to leave possible * next file on stdin intact. */ while ((fread(line, 1, 2, source) == 2) && (/*line[0] ||*/ line[1]) && fread(line + 2, 1, 2, source) == 2) { quote = 0; fprintf(dest, " %4d ", (spnum = (line[2] & 0xff) + ((line[3] & 0xff) << 8)) ); if (directory) { if (spnum >= 100) spnum = 0; else if (spnum >= 10) spnum = 1; else spnum = 2; } /* prevent list protection from terminating listing */ while ((c = getc(source)) != EOF && !c); if (c == 0x12 && !line[2] && !line[3]) { /* 00 00 12 22 */ directory++; } do { if (c == 0x22) quote ^= c; /* basic 2.0, 7.0 & 10.0 and extensions */ if (!quote && c > 0x7f) { if (c <= MAX_COMM) { fprintf(dest, "%s", keyword[c & 0x7f]); if (c == 0x9E) { ++sysflg; } continue; } fprintf(dest, "%s", keyword[c & 0x7f]); } /* quote */ if (directory && spnum && c == 0x20) { spnum--; /* eat spaces to adjust directory lines */ continue; } _p_toascii((int)c, ctrls); /* convert character */ } while ((c = getc(source)) != EOF && c); fprintf(dest, "\n"); } /* line */ #ifdef DEBUG printf("\n c %02x EOF %d *line %d sysflg %d\n", c, feof(source), *line, sysflg); #endif return (!feof(source) && (*line | line[1]) && sysflg); } /* 03/09/2006 gpz: - changed to output tokenized line into a second buffer instead of putting the tokens back in the input buffer. i wonder how this ever worked, control codes with a reasonable high repeatcount made previous versions of petcat segfault (or with luck, output trash) - added error message when there is an unknown controlcode inside braces */ static void p_tokenize(int version, unsigned int addr, int ctrls) { static char line[256]; static char tokenizedline[256]; unsigned char *p1, *p2, quote, c; unsigned char rem_data_mode, rem_data_endchar = '\0'; int len = 0, match; unsigned int linum = 10; fprintf(dest, "%c%c", (addr & 255), ((addr >> 8) & 255)); /* Copies from p2 to p1 */ while((p2 = (unsigned char *)fgets(line, 255, source)) != NULL) { memset(tokenizedline, 0, 256); p1 = (unsigned char *)tokenizedline; #ifndef GEMDOS if (sscanf(line, "%d%n", &linum, &len) == 1) p2 += len; #else if (sscanf(line, "%d", &linum) == 1) while (isspace(*p2) || isdigit(*p2)) p2++; #endif #ifdef DEBUG fprintf(stderr,"line: %d\n",linum); #endif quote = 0; rem_data_mode = 0; while (isspace(*p2)) p2++; while (*p2) { if (*p2 == 0x22) { quote ^= *p2; } if (*p2 == 0x0a || *p2 == 0x0d) break; match = 0; if (quote) { /* * control code evaluation * only strings that appear inside quotes are * interpreted -- they should not be used elsewhere */ if (ctrls && (*p2 == CLARIF_LP)) { unsigned char *p; p = p2; #ifdef DEBUG fprintf(stderr,"controlcode start: %c\n", *p2); #endif /* repetition count */ len = 1; #ifndef GEMDOS if (sscanf((char *)++p, "%d%n", &len, &kwlen) == 1) { p += kwlen; #else if (sscanf(++p, "%d", &len) == 1) { while (isspace(*p) || isdigit(*p)) p++; #endif #ifdef DEBUG fprintf(stderr,"controlcode repeat count: len:%d kwlen:%d\n", len,kwlen); #endif if (*p == ' ') ++p; } } #ifdef DEBUG /* fprintf(stderr,"controlcode end\n"); */ #endif } else if (rem_data_mode) { /* if we have already encountered a REM or a DATA, simply copy the char */ /* DO NOTHING! As we do not set "match", the if (!match) will be true, * and this part will copy the char over to the new buffer */ } else if (isalpha(*p2) || strchr("+-*/^>=<", *p2)) { /* Common Keywords * Note: ~ (pi) is tested later */ if (!match) { int max; max = NUM_COMM; if ((c = sstrcmp(p2, keyword, 0, max)) != KW_NONE) { if (c != 0x4e) { /* Skip prefix */ *p1++ = c | 0x80; p2 += kwlen; match++; /* Check if the keyword is a REM or a DATA */ switch (c) { case TOKEN_DATA: rem_data_mode = 1; rem_data_endchar = ':'; break; case TOKEN_REM: rem_data_mode = 1; rem_data_endchar = '\0'; break; } } } } } /* !quote */ if (!match) { if ((*p2 >= 0x5b) && (*p2 <= 0x7e)) *p1++ = *p2 ^ 0x20; else if ((*p2 >= 'A') && (*p2 <= 'Z')) *p1++ = *p2 | 0x80; else *p1++ = *p2; /* check if the REM/DATA mode has to be stopped: */ if (*p2 == rem_data_endchar) rem_data_mode = 0; ++p2; } /* match */ } /* while */ #ifdef DEBUG fprintf(stderr,"output line start: %s\n", line); /* fprintf(stderr,"output line petscii: %s\n", tokenizedline); */ #endif *p1 = 0; if ((len = strlen(tokenizedline) ) > 0) { addr += len + 5; fprintf(dest, "%c%c%c%c%s%c", addr & 255, (addr>>8) & 255, linum & 255, (linum>>8) & 255, tokenizedline, '\0'); linum += 2; /* auto line numbering by default */ } #ifdef DEBUG fprintf(stderr,"output line end\n"); #endif } /* while */ fprintf(dest, "%c%c", 0, 0); /* program end marker */ } static unsigned char sstrcmp(unsigned char *line, const char **wordlist, int token, int maxitems) { int j; const char *p, *q; kwlen = 1; /* search for keyword */ for (; token < maxitems; token++) { for (p = wordlist[token], q = (char *)line, j = 0; *p && *q && *p == *q; p++, q++, j++); /*fprintf (stderr, "compare %s %s - %d %d\n", wordlist[token], line, j, kwlen);*/ /* found an exact or abbreviated keyword */ if (j && (!*p || (*p && (*p ^ *q) == 0x20 && j++)) ) { kwlen = j; /*fprintf (stderr, "found %s %2x\n", wordlist[token], token);*/ return token; } } /* for */ return (KW_NONE); }