1 /* $OpenBSD: db_lex.c,v 1.15 2020/10/15 03:14:00 deraadt Exp $ */
2 /* $NetBSD: db_lex.c,v 1.8 1996/02/05 01:57:05 christos Exp $ */
3
4 /*
5 * Mach Operating System
6 * Copyright (c) 1993,1992,1991,1990 Carnegie Mellon University
7 * All Rights Reserved.
8 *
9 * Permission to use, copy, modify and distribute this software and its
10 * documentation is hereby granted, provided that both the copyright
11 * notice and this permission notice appear in all copies of the
12 * software, derivative works or modified versions, and any portions
13 * thereof, and that both notices appear in supporting documentation.
14 *
15 * CARNEGIE MELLON ALLOWS FREE USE OF THIS SOFTWARE IN ITS "AS IS"
16 * CONDITION. CARNEGIE MELLON DISCLAIMS ANY LIABILITY OF ANY KIND FOR
17 * ANY DAMAGES WHATSOEVER RESULTING FROM THE USE OF THIS SOFTWARE.
18 *
19 * Carnegie Mellon requests users of this software to return to
20 *
21 * Software Distribution Coordinator or Software.Distribution@CS.CMU.EDU
22 * School of Computer Science
23 * Carnegie Mellon University
24 * Pittsburgh PA 15213-3890
25 *
26 * any improvements or extensions that they make and grant Carnegie Mellon
27 * the rights to redistribute these changes.
28 *
29 * Author: David B. Golub, Carnegie Mellon University
30 * Date: 7/90
31 */
32
33 /*
34 * Lexical analyzer.
35 */
36 #include <sys/param.h>
37 #include <sys/systm.h>
38
39 #include <machine/db_machdep.h>
40
41 #include <ddb/db_lex.h>
42 #include <ddb/db_output.h>
43 #include <ddb/db_command.h>
44 #include <ddb/db_extern.h>
45 #include <ddb/db_var.h>
46
47 char db_line[120];
48 char * db_lp, *db_endlp;
49
50 db_expr_t db_tok_number;
51 char db_tok_string[TOK_STRING_SIZE];
52
53 void db_flush_line(void);
54 int db_read_char(void);
55 void db_unread_char(int);
56
57 int
db_read_line(void)58 db_read_line(void)
59 {
60 int i;
61
62 i = db_readline(db_line, sizeof(db_line));
63 if (i == 0)
64 return (0); /* EOI */
65 db_lp = db_line;
66 db_endlp = db_lp + i;
67 return (i);
68 }
69
70 void
db_flush_line(void)71 db_flush_line(void)
72 {
73 db_lp = db_line;
74 db_endlp = db_line;
75 }
76
77 int db_look_char = 0;
78
79 int
db_read_char(void)80 db_read_char(void)
81 {
82 int c;
83
84 if (db_look_char != 0) {
85 c = db_look_char;
86 db_look_char = 0;
87 } else if (db_lp >= db_endlp)
88 c = -1;
89 else
90 c = *db_lp++;
91 return (c);
92 }
93
94 void
db_unread_char(int c)95 db_unread_char(int c)
96 {
97 db_look_char = c;
98 }
99
100 int db_look_token = 0;
101
102 void
db_unread_token(int t)103 db_unread_token(int t)
104 {
105 db_look_token = t;
106 }
107
108 int
db_read_token(void)109 db_read_token(void)
110 {
111 int t;
112
113 if (db_look_token) {
114 t = db_look_token;
115 db_look_token = 0;
116 } else
117 t = db_lex();
118 return (t);
119 }
120
121 void
db_flush_lex(void)122 db_flush_lex(void)
123 {
124 db_flush_line();
125 db_look_char = 0;
126 db_look_token = 0;
127 }
128
129 int
db_lex(void)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 } else
172 break;
173 db_tok_number = db_tok_number * r + digit;
174 c = db_read_char();
175 }
176 if ((c >= '0' && c <= '9') ||
177 (c >= 'A' && c <= 'Z') ||
178 (c >= 'a' && c <= 'z') ||
179 (c == '_')) {
180 db_error("Bad character in number\n");
181 /*NOTREACHED*/
182 }
183 db_unread_char(c);
184 return (tNUMBER);
185 }
186 if ((c >= 'A' && c <= 'Z') ||
187 (c >= 'a' && c <= 'z') ||
188 c == '_' || c == '\\') {
189 /* string */
190 char *cp;
191
192 cp = db_tok_string;
193 if (c == '\\') {
194 c = db_read_char();
195 if (c == '\n' || c == -1) {
196 db_error("Bad escape\n");
197 /*NOTREACHED*/
198 }
199 }
200 *cp++ = c;
201 while (1) {
202 c = db_read_char();
203 if ((c >= 'A' && c <= 'Z') ||
204 (c >= 'a' && c <= 'z') ||
205 (c >= '0' && c <= '9') ||
206 c == '_' || c == '\\' || c == ':') {
207 if (c == '\\') {
208 c = db_read_char();
209 if (c == '\n' || c == -1) {
210 db_error("Bad escape\n");
211 /*NOTREACHED*/
212 }
213 }
214 *cp++ = c;
215 if (cp == db_tok_string+sizeof(db_tok_string)) {
216 db_error("String too long\n");
217 /*NOTREACHED*/
218 }
219 continue;
220 } else {
221 *cp = '\0';
222 break;
223 }
224 }
225 db_unread_char(c);
226 return (tIDENT);
227 }
228
229 switch (c) {
230 case '+':
231 return (tPLUS);
232 case '-':
233 return (tMINUS);
234 case '.':
235 c = db_read_char();
236 if (c == '.')
237 return (tDOTDOT);
238 db_unread_char(c);
239 return (tDOT);
240 case '*':
241 return (tSTAR);
242 case '/':
243 return (tSLASH);
244 case '=':
245 return (tEQ);
246 case '%':
247 return (tPCT);
248 case '#':
249 return (tHASH);
250 case '(':
251 return (tLPAREN);
252 case ')':
253 return (tRPAREN);
254 case ',':
255 return (tCOMMA);
256 case '"':
257 return (tDITTO);
258 case '$':
259 return (tDOLLAR);
260 case '!':
261 return (tEXCL);
262 case '<':
263 c = db_read_char();
264 if (c == '<')
265 return (tSHIFT_L);
266 db_unread_char(c);
267 break;
268 case '>':
269 c = db_read_char();
270 if (c == '>')
271 return (tSHIFT_R);
272 db_unread_char(c);
273 break;
274 case -1:
275 return (tEOF);
276 }
277 db_printf("Bad character\n");
278 db_flush_lex();
279 return (tEOF);
280 }
281