sys/ddb/db_lex.c

   1 /*
   2  * Mach Operating System
   3  * Copyright (c) 1991,1990 Carnegie Mellon University
   4  * All Rights Reserved.
   5  *
   6  * Permission to use, copy, modify and distribute this software and its
   7  * documentation is hereby granted, provided that both the copyright
   8  * notice and this permission notice appear in all copies of the
   9  * software, derivative works or modified versions, and any portions
  10  * thereof, and that both notices appear in supporting documentation.
  11  *
  12  * CARNEGIE MELLON ALLOWS FREE USE OF THIS SOFTWARE IN ITS
  13  * CONDITION.  CARNEGIE MELLON DISCLAIMS ANY LIABILITY OF ANY KIND FOR
  14  * ANY DAMAGES WHATSOEVER RESULTING FROM THE USE OF THIS SOFTWARE.
  15  *
  16  * Carnegie Mellon requests users of this software to return to
  17  *
  18  *  Software Distribution Coordinator  or  Software.Distribution@CS.CMU.EDU
  19  *  School of Computer Science
  20  *  Carnegie Mellon University
  21  *  Pittsburgh PA 15213-3890
  22  *
  23  * any improvements or extensions that they make and grant Carnegie the
  24  * rights to redistribute these changes.
  25  *
  26  * $FreeBSD: src/sys/ddb/db_lex.c,v 1.18 1999/08/28 00:41:08 peter Exp $
  27  * $DragonFly: src/sys/ddb/db_lex.c,v 1.5 2005/12/23 21:35:44 swildner Exp $
  28  */
  29
  30 /*
  31  *      Author: David B. Golub, Carnegie Mellon University
  32  *      Date:   7/90
  33  */
  34 /*
  35  * Lexical analyzer.
  36  */
  37 #include <sys/param.h>
  38
  39 #include <ddb/ddb.h>
  40 #include <ddb/db_lex.h>
  41
  42 static char     db_line[120];
  43 static char *   db_lp, *db_endlp;
  44
  45 static int      db_lex (void);
  46 static void     db_flush_line (void);
  47 static int      db_read_char (void);
  48 static void     db_unread_char (int);
  49
  50 int
  51 db_read_line(void)
  52 {
  53         int     i;
  54
  55         i = db_readline(db_line, sizeof(db_line));
  56         if (i == 0)
  57             return (0); /* EOI */
  58         db_lp = db_line;
  59         db_endlp = db_lp + i;
  60         return (i);
  61 }
  62
  63 static void
  64 db_flush_line(void)
  65 {
  66         db_lp = db_line;
  67         db_endlp = db_line;
  68 }
  69
  70 static int      db_look_char = 0;
  71
  72 static int
  73 db_read_char(void)
  74 {
  75         int     c;
  76
  77         if (db_look_char != 0) {
  78             c = db_look_char;
  79             db_look_char = 0;
  80         }
  81         else if (db_lp >= db_endlp)
  82             c = -1;
  83         else
  84             c = *db_lp++;
  85         return (c);
  86 }
  87
  88 static void
  89 db_unread_char(int c)
  90 {
  91         db_look_char = c;
  92 }
  93
  94 static int      db_look_token = 0;
  95
  96 void
  97 db_unread_token(int t)
  98 {
  99         db_look_token = t;
 100 }
 101
 102 int
 103 db_read_token(void)
 104 {
 105         int     t;
 106
 107         if (db_look_token) {
 108             t = db_look_token;
 109             db_look_token = 0;
 110         }
 111         else
 112             t = db_lex();
 113         return (t);
 114 }
 115
 116 db_expr_t       db_tok_number;
 117 char    db_tok_string[TOK_STRING_SIZE];
 118
 119 db_expr_t       db_radix = 16;
 120
 121 void
 122 db_flush_lex(void)
 123 {
 124         db_flush_line();
 125         db_look_char = 0;
 126         db_look_token = 0;
 127 }
 128
 129 static int
 130 db_lex(void)
 131 {
 132         int     c;
 133
 134         c = db_read_char();
 135         while (c <= ' ' || c > '~') {
 136             if (c == '\n' || c == -1)
 137                 return (tEOL);
 138             c = db_read_char();
 139         }
 140
 141         if (c >= '0' && c <= '9') {
 142             /* number */
 143             int r, digit = 0;
 144
 145             if (c > '0')
 146                 r = db_radix;
 147             else {
 148                 c = db_read_char();
 149                 if (c == 'O' || c == 'o')
 150                     r = 8;
 151                 else if (c == 'T' || c == 't')
 152                     r = 10;
 153                 else if (c == 'X' || c == 'x')
 154                     r = 16;
 155                 else {
 156                     r = db_radix;
 157                     db_unread_char(c);
 158                 }
 159                 c = db_read_char();
 160             }
 161             db_tok_number = 0;
 162             for (;;) {
 163                 if (c >= '0' && c <= ((r == 8) ? '7' : '9'))
 164                     digit = c - '0';
 165                 else if (r == 16 && ((c >= 'A' && c <= 'F') ||
 166                                      (c >= 'a' && c <= 'f'))) {
 167                     if (c >= 'a')
 168                         digit = c - 'a' + 10;
 169                     else if (c >= 'A')
 170                         digit = c - 'A' + 10;
 171                 }
 172                 else
 173                     break;
 174                 db_tok_number = db_tok_number * r + digit;
 175                 c = db_read_char();
 176             }
 177             if ((c >= '0' && c <= '9') ||
 178                 (c >= 'A' && c <= 'Z') ||
 179                 (c >= 'a' && c <= 'z') ||
 180                 (c == '_'))
 181             {
 182                 db_error("Bad character in number\n");
 183                 db_flush_lex();
 184                 return (tEOF);
 185             }
 186             db_unread_char(c);
 187             return (tNUMBER);
 188         }
 189         if ((c >= 'A' && c <= 'Z') ||
 190             (c >= 'a' && c <= 'z') ||
 191             c == '_' || c == '\\')
 192         {
 193             /* string */
 194             char *cp;
 195
 196             cp = db_tok_string;
 197             if (c == '\\') {
 198                 c = db_read_char();
 199                 if (c == '\n' || c == -1)
 200                     db_error("Bad escape\n");
 201             }
 202             *cp++ = c;
 203             while (1) {
 204                 c = db_read_char();
 205                 if ((c >= 'A' && c <= 'Z') ||
 206                     (c >= 'a' && c <= 'z') ||
 207                     (c >= '0' && c <= '9') ||
 208                     c == '_' || c == '\\' || c == ':')
 209                 {
 210                     if (c == '\\') {
 211                         c = db_read_char();
 212                         if (c == '\n' || c == -1)
 213                             db_error("Bad escape\n");
 214                     }
 215                     *cp++ = c;
 216                     if (cp == db_tok_string+sizeof(db_tok_string)) {
 217                         db_error("String too long\n");
 218                         db_flush_lex();
 219                         return (tEOF);
 220                     }
 221                     continue;
 222                 }
 223                 else {
 224                     *cp = '\0';
 225                     break;
 226                 }
 227             }
 228             db_unread_char(c);
 229             return (tIDENT);
 230         }
 231
 232         switch (c) {
 233             case '+':
 234                 return (tPLUS);
 235             case '-':
 236                 return (tMINUS);
 237             case '.':
 238                 c = db_read_char();
 239                 if (c == '.')
 240                     return (tDOTDOT);
 241                 db_unread_char(c);
 242                 return (tDOT);
 243             case '*':
 244                 return (tSTAR);
 245             case '/':
 246                 return (tSLASH);
 247             case '=':
 248                 return (tEQ);
 249             case '%':
 250                 return (tPCT);
 251             case '#':
 252                 return (tHASH);
 253             case '(':
 254                 return (tLPAREN);
 255             case ')':
 256                 return (tRPAREN);
 257             case ',':
 258                 return (tCOMMA);
 259             case '"':
 260                 return (tDITTO);
 261             case '$':
 262                 return (tDOLLAR);
 263             case '!':
 264                 return (tEXCL);
 265             case '<':
 266                 c = db_read_char();
 267                 if (c == '<')
 268                     return (tSHIFT_L);
 269                 db_unread_char(c);
 270                 break;
 271             case '>':
 272                 c = db_read_char();
 273                 if (c == '>')
 274                     return (tSHIFT_R);
 275                 db_unread_char(c);
 276                 break;
 277             case -1:
 278                 return (tEOF);
 279         }
 280         db_printf("Bad character\n");
 281         db_flush_lex();
 282         return (tEOF);
 283 }