1/*-
2 * SPDX-License-Identifier: BSD-3-Clause
3 *
4 * Copyright (c) 1991, 1993
5 *	The Regents of the University of California.  All rights reserved.
6 *
7 * This code is derived from software contributed to Berkeley by
8 * Kenneth Almquist.
9 *
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions
12 * are met:
13 * 1. Redistributions of source code must retain the above copyright
14 *    notice, this list of conditions and the following disclaimer.
15 * 2. Redistributions in binary form must reproduce the above copyright
16 *    notice, this list of conditions and the following disclaimer in the
17 *    documentation and/or other materials provided with the distribution.
18 * 3. Neither the name of the University nor the names of its contributors
19 *    may be used to endorse or promote products derived from this software
20 *    without specific prior written permission.
21 *
22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
25 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
32 * SUCH DAMAGE.
33 */
34
35/*
36 * This program creates syntax.h and syntax.c.
37 */
38
39#include <stdio.h>
40#include <stdlib.h>
41#include <string.h>
42#include "parser.h"
43
44
45struct synclass {
46	const char *name;
47	const char *comment;
48};
49
50/* Syntax classes */
51static const struct synclass synclass[] = {
52	{ "CWORD",	"character is nothing special" },
53	{ "CNL",	"newline character" },
54	{ "CQNL",	"newline character in quotes" },
55	{ "CBACK",	"a backslash character" },
56	{ "CSBACK",	"a backslash character in single quotes" },
57	{ "CSQUOTE",	"single quote" },
58	{ "CDQUOTE",	"double quote" },
59	{ "CENDQUOTE",	"a terminating quote" },
60	{ "CBQUOTE",	"backwards single quote" },
61	{ "CVAR",	"a dollar sign" },
62	{ "CENDVAR",	"a '}' character" },
63	{ "CLP",	"a left paren in arithmetic" },
64	{ "CRP",	"a right paren in arithmetic" },
65	{ "CEOF",	"end of file" },
66	{ "CCTL",	"like CWORD, except it must be escaped" },
67	{ "CSPCL",	"these terminate a word" },
68	{ "CIGN",       "character should be ignored" },
69	{ NULL,		NULL }
70};
71
72
73/*
74 * Syntax classes for is_ functions.  Warning:  if you add new classes
75 * you may have to change the definition of the is_in_name macro.
76 */
77static const struct synclass is_entry[] = {
78	{ "ISDIGIT",	"a digit" },
79	{ "ISUPPER",	"an upper case letter" },
80	{ "ISLOWER",	"a lower case letter" },
81	{ "ISUNDER",	"an underscore" },
82	{ "ISSPECL",	"the name of a special parameter" },
83	{ NULL, 	NULL }
84};
85
86static const char writer[] = "\
87/*\n\
88 * This file was generated by the mksyntax program.\n\
89 */\n\
90\n";
91
92
93static FILE *cfile;
94static FILE *hfile;
95
96static void add_default(void);
97static void finish(void);
98static void init(const char *);
99static void add(const char *, const char *);
100static void output_type_macros(void);
101
102int
103main(int argc __unused, char **argv __unused)
104{
105	int i;
106	char buf[80];
107	int pos;
108
109	/* Create output files */
110	if ((cfile = fopen("syntax.c", "w")) == NULL) {
111		perror("syntax.c");
112		exit(2);
113	}
114	if ((hfile = fopen("syntax.h", "w")) == NULL) {
115		perror("syntax.h");
116		exit(2);
117	}
118	fputs(writer, hfile);
119	fputs(writer, cfile);
120
121	fputs("#include <sys/cdefs.h>\n", hfile);
122	fputs("#include <limits.h>\n\n", hfile);
123
124	/* Generate the #define statements in the header file */
125	fputs("/* Syntax classes */\n", hfile);
126	for (i = 0 ; synclass[i].name ; i++) {
127		sprintf(buf, "#define %s %d", synclass[i].name, i);
128		fputs(buf, hfile);
129		for (pos = strlen(buf) ; pos < 32 ; pos = (pos + 8) & ~07)
130			putc('\t', hfile);
131		fprintf(hfile, "/* %s */\n", synclass[i].comment);
132	}
133	putc('\n', hfile);
134	fputs("/* Syntax classes for is_ functions */\n", hfile);
135	for (i = 0 ; is_entry[i].name ; i++) {
136		sprintf(buf, "#define %s %#o", is_entry[i].name, 1 << i);
137		fputs(buf, hfile);
138		for (pos = strlen(buf) ; pos < 32 ; pos = (pos + 8) & ~07)
139			putc('\t', hfile);
140		fprintf(hfile, "/* %s */\n", is_entry[i].comment);
141	}
142	putc('\n', hfile);
143	fputs("#define SYNBASE (1 - CHAR_MIN)\n", hfile);
144	fputs("#define PEOF -SYNBASE\n\n", hfile);
145	putc('\n', hfile);
146	fputs("#define BASESYNTAX (basesyntax + SYNBASE)\n", hfile);
147	fputs("#define DQSYNTAX (dqsyntax + SYNBASE)\n", hfile);
148	fputs("#define SQSYNTAX (sqsyntax + SYNBASE)\n", hfile);
149	fputs("#define ARISYNTAX (arisyntax + SYNBASE)\n", hfile);
150	putc('\n', hfile);
151	output_type_macros();		/* is_digit, etc. */
152	putc('\n', hfile);
153
154	/* Generate the syntax tables. */
155	fputs("#include \"parser.h\"\n", cfile);
156	fputs("#include \"shell.h\"\n", cfile);
157	fputs("#include \"syntax.h\"\n\n", cfile);
158
159	fputs("/* syntax table used when not in quotes */\n", cfile);
160	init("basesyntax");
161	add_default();
162	add("\n", "CNL");
163	add("\\", "CBACK");
164	add("'", "CSQUOTE");
165	add("\"", "CDQUOTE");
166	add("`", "CBQUOTE");
167	add("$", "CVAR");
168	add("}", "CENDVAR");
169	add("<>();&| \t", "CSPCL");
170	finish();
171
172	fputs("\n/* syntax table used when in double quotes */\n", cfile);
173	init("dqsyntax");
174	add_default();
175	add("\n", "CQNL");
176	add("\\", "CBACK");
177	add("\"", "CENDQUOTE");
178	add("`", "CBQUOTE");
179	add("$", "CVAR");
180	add("}", "CENDVAR");
181	/* ':/' for tilde expansion, '-^]' for [a\-x] pattern ranges */
182	add("!*?[]=~:/-^", "CCTL");
183	finish();
184
185	fputs("\n/* syntax table used when in single quotes */\n", cfile);
186	init("sqsyntax");
187	add_default();
188	add("\n", "CQNL");
189	add("\\", "CSBACK");
190	add("'", "CENDQUOTE");
191	/* ':/' for tilde expansion, '-^]' for [a\-x] pattern ranges */
192	add("!*?[]=~:/-^", "CCTL");
193	finish();
194
195	fputs("\n/* syntax table used when in arithmetic */\n", cfile);
196	init("arisyntax");
197	add_default();
198	add("\n", "CQNL");
199	add("\\", "CBACK");
200	add("`", "CBQUOTE");
201	add("\"", "CIGN");
202	add("$", "CVAR");
203	add("}", "CENDVAR");
204	add("(", "CLP");
205	add(")", "CRP");
206	finish();
207
208	fputs("\n/* character classification table */\n", cfile);
209	init("is_type");
210	add("0123456789", "ISDIGIT");
211	add("abcdefghijklmnopqrstuvwxyz", "ISLOWER");
212	add("ABCDEFGHIJKLMNOPQRSTUVWXYZ", "ISUPPER");
213	add("_", "ISUNDER");
214	add("#?$!-*@", "ISSPECL");
215	finish();
216
217	exit(0);
218}
219
220
221/*
222 * Output the header and declaration of a syntax table.
223 */
224
225static void
226init(const char *name)
227{
228	fprintf(hfile, "extern const char %s[];\n", name);
229	fprintf(cfile, "const char %s[SYNBASE + CHAR_MAX + 1] = {\n", name);
230}
231
232
233static void
234add_one(const char *key, const char *type)
235{
236	fprintf(cfile, "\t[SYNBASE + %s] = %s,\n", key, type);
237}
238
239
240/*
241 * Add default values to the syntax table.
242 */
243
244static void
245add_default(void)
246{
247	add_one("PEOF",                "CEOF");
248	add_one("CTLESC",              "CCTL");
249	add_one("CTLVAR",              "CCTL");
250	add_one("CTLENDVAR",           "CCTL");
251	add_one("CTLBACKQ",            "CCTL");
252	add_one("CTLBACKQ + CTLQUOTE", "CCTL");
253	add_one("CTLARI",              "CCTL");
254	add_one("CTLENDARI",           "CCTL");
255	add_one("CTLQUOTEMARK",        "CCTL");
256	add_one("CTLQUOTEEND",         "CCTL");
257}
258
259
260/*
261 * Output the footer of a syntax table.
262 */
263
264static void
265finish(void)
266{
267	fputs("};\n", cfile);
268}
269
270
271/*
272 * Add entries to the syntax table.
273 */
274
275static void
276add(const char *p, const char *type)
277{
278	for (; *p; ++p) {
279		char c = *p;
280		switch (c) {
281		case '\t': c = 't';  break;
282		case '\n': c = 'n';  break;
283		case '\'': c = '\''; break;
284		case '\\': c = '\\'; break;
285
286		default:
287			fprintf(cfile, "\t[SYNBASE + '%c'] = %s,\n", c, type);
288			continue;
289		}
290		fprintf(cfile, "\t[SYNBASE + '\\%c'] = %s,\n", c, type);
291	}
292}
293
294
295/*
296 * Output character classification macros (e.g. is_digit).  If digits are
297 * contiguous, we can test for them quickly.
298 */
299
300static const char *macro[] = {
301	"#define is_digit(c)\t((unsigned int)((c) - '0') <= 9)",
302	"#define is_eof(c)\t((c) == PEOF)",
303	"#define is_alpha(c)\t((is_type+SYNBASE)[(int)c] & (ISUPPER|ISLOWER))",
304	"#define is_name(c)\t((is_type+SYNBASE)[(int)c] & (ISUPPER|ISLOWER|ISUNDER))",
305	"#define is_in_name(c)\t((is_type+SYNBASE)[(int)c] & (ISUPPER|ISLOWER|ISUNDER|ISDIGIT))",
306	"#define is_special(c)\t((is_type+SYNBASE)[(int)c] & (ISSPECL|ISDIGIT))",
307	"#define digit_val(c)\t((c) - '0')",
308	NULL
309};
310
311static void
312output_type_macros(void)
313{
314	const char **pp;
315
316	for (pp = macro ; *pp ; pp++)
317		fprintf(hfile, "%s\n", *pp);
318}
319