2 * Copyright (c) 1985 Sun Microsystems, Inc.
3 * Copyright (c) 1980, 1993
4 * The Regents of the University of California. All rights reserved.
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 * 3. All advertising materials mentioning features or use of this software
16 * must display the following acknowledgement:
17 * This product includes software developed by the University of
18 * California, Berkeley and its contributors.
19 * 4. Neither the name of the University nor the names of its contributors
20 * may be used to endorse or promote products derived from this software
21 * without specific prior written permission.
23 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
38 static char sccsid[] = "@(#)lexi.c 8.1 (Berkeley) 6/6/93";
41 #include <sys/cdefs.h>
42 __FBSDID("$FreeBSD$");
45 * Here we have the token scanner for indent. It scans off one token and puts
46 * it in the global variable "token". It returns a code, indicating the type
55 #include "indent_globs.h"
56 #include "indent_codes.h"
67 struct templ specials[1000] =
103 { /* this is used to facilitate the decision of
104 * what type (alphanumeric, operator) each
106 0, 0, 0, 0, 0, 0, 0, 0,
107 0, 0, 0, 0, 0, 0, 0, 0,
108 0, 0, 0, 0, 0, 0, 0, 0,
109 0, 0, 0, 0, 0, 0, 0, 0,
110 0, 3, 0, 0, 1, 3, 3, 0,
111 0, 0, 3, 3, 0, 3, 0, 3,
112 1, 1, 1, 1, 1, 1, 1, 1,
113 1, 1, 0, 0, 3, 3, 3, 3,
114 0, 1, 1, 1, 1, 1, 1, 1,
115 1, 1, 1, 1, 1, 1, 1, 1,
116 1, 1, 1, 1, 1, 1, 1, 1,
117 1, 1, 1, 0, 0, 0, 3, 1,
118 0, 1, 1, 1, 1, 1, 1, 1,
119 1, 1, 1, 1, 1, 1, 1, 1,
120 1, 1, 1, 1, 1, 1, 1, 1,
121 1, 1, 1, 0, 3, 0, 3, 0
127 int unary_delim; /* this is set to 1 if the current token
128 * forces a following operator to be unary */
129 static int last_code; /* the last token type returned */
130 static int l_struct; /* set to 1 if the last token was 'struct' */
131 int code; /* internal code to be returned */
132 char qchar; /* the delimiter character for a string */
134 e_token = s_token; /* point to start of place to save token */
136 ps.col_1 = ps.last_nl; /* tell world that this token started in
137 * column 1 iff the last thing scanned was nl */
140 while (*buf_ptr == ' ' || *buf_ptr == '\t') { /* get rid of blanks */
141 ps.col_1 = false; /* leading blanks imply token is not in column
143 if (++buf_ptr >= buf_end)
147 /* Scan an alphanumeric token */
148 if (chartype[(int)*buf_ptr] == alphanum || (buf_ptr[0] == '.' && isdigit(buf_ptr[1]))) {
150 * we have a character or number
152 const char *j; /* used for searching thru list of
157 if (isdigit(*buf_ptr) || (buf_ptr[0] == '.' && isdigit(buf_ptr[1]))) {
161 if (*buf_ptr == '0' &&
162 (buf_ptr[1] == 'x' || buf_ptr[1] == 'X')) {
163 *e_token++ = *buf_ptr++;
164 *e_token++ = *buf_ptr++;
165 while (isxdigit(*buf_ptr)) {
167 *e_token++ = *buf_ptr++;
172 if (*buf_ptr == '.') {
179 *e_token++ = *buf_ptr++;
180 if (!isdigit(*buf_ptr) && *buf_ptr != '.') {
181 if ((*buf_ptr != 'E' && *buf_ptr != 'e') || seenexp)
187 *e_token++ = *buf_ptr++;
188 if (*buf_ptr == '+' || *buf_ptr == '-')
189 *e_token++ = *buf_ptr++;
194 if (!(seensfx & 1) && (*buf_ptr == 'U' || *buf_ptr == 'u')) {
196 *e_token++ = *buf_ptr++;
200 if (!(seensfx & 2) && (strchr("fFlL", *buf_ptr) != NULL)) {
202 if (buf_ptr[1] == buf_ptr[0])
203 *e_token++ = *buf_ptr++;
204 *e_token++ = *buf_ptr++;
212 while (chartype[(int)*buf_ptr] == alphanum || *buf_ptr == BACKSLASH) {
213 /* fill_buffer() terminates buffer with newline */
214 if (*buf_ptr == BACKSLASH) {
215 if (*(buf_ptr + 1) == '\n') {
217 if (buf_ptr >= buf_end)
224 *e_token++ = *buf_ptr++;
225 if (buf_ptr >= buf_end)
229 while (*buf_ptr == ' ' || *buf_ptr == '\t') { /* get rid of blanks */
230 if (++buf_ptr >= buf_end)
233 ps.its_a_keyword = false;
234 ps.sizeof_keyword = false;
235 if (l_struct && !ps.p_l_follow) {
236 /* if last token was 'struct' and we're not
237 * in parentheses, then this token
238 * should be treated as a declaration */
244 ps.last_u_d = l_struct; /* Operator after identifier is binary
245 * unless last token was 'struct' */
247 last_code = ident; /* Remember that this is the code we will
251 const char *q = s_token;
252 size_t q_len = strlen(q);
253 /* Check if we have an "_t" in the end */
255 (strcmp(q + q_len - 2, "_t") == 0)) {
256 ps.its_a_keyword = true;
258 goto found_auto_typedef;
263 * This loop will check if the token is a keyword.
265 for (p = specials; (j = p->rwd) != NULL; p++) {
266 const char *q = s_token; /* point at scanned token */
267 if (*j++ != *q++ || *j++ != *q++)
268 continue; /* This test depends on the fact that
269 * identifiers are always at least 1 character
270 * long (ie. the first two bytes of the
271 * identifier are always meaningful) */
273 break; /* If its a one-character identifier */
276 goto found_keyword; /* I wish that C had a multi-level
279 if (p->rwd) { /* we have a keyword */
281 ps.its_a_keyword = true;
284 case 1: /* it is a switch */
286 case 2: /* a case or default */
289 case 3: /* a "struct" */
291 * Next time around, we will want to know that we have had a
297 case 4: /* one of the declaration keywords */
300 ps.cast_mask |= (1 << ps.p_l_follow) & ~ps.sizeof_mask;
301 break; /* inside parens: cast, param list or sizeof */
306 case 5: /* if, while, for */
309 case 6: /* do, else */
313 ps.sizeof_keyword = true;
314 default: /* all others are treated like any other
317 } /* end of switch */
318 } /* end of if (found_it) */
319 if (*buf_ptr == '(' && ps.tos <= 1 && ps.ind_level == 0) {
322 if (*tp++ == ')' && (*tp == ';' || *tp == ','))
324 strncpy(ps.procname, token, sizeof ps.procname - 1);
325 ps.in_parameter_declaration = 1;
330 * The following hack attempts to guess whether or not the current
331 * token is in fact a declaration keyword -- one that has been
334 if (((*buf_ptr == '*' && buf_ptr[1] != '=') || isalpha(*buf_ptr) || *buf_ptr == '_')
337 && (ps.last_token == rparen || ps.last_token == semicolon ||
338 ps.last_token == decl ||
339 ps.last_token == lbrace || ps.last_token == rbrace)) {
340 ps.its_a_keyword = true;
345 if (last_code == decl) /* if this is a declared variable, then
346 * following sign is unary */
347 ps.last_u_d = true; /* will make "int a -1" work */
349 return (ident); /* the ident is not in the list */
350 } /* end of procesing for alpanum character */
352 /* Scan a non-alphanumeric token */
354 *e_token++ = *buf_ptr; /* if it is only a one-character token, it is
357 if (++buf_ptr >= buf_end)
362 unary_delim = ps.last_u_d;
363 ps.last_nl = true; /* remember that we just had a newline */
364 code = (had_eof ? 0 : newline);
367 * if data has been exhausted, the newline is a dummy, and we should
368 * return code to stop
372 case '\'': /* start of quoted character */
373 case '"': /* start of string */
379 e_token = chfont(&bodyf, &stringf, e_token);
381 do { /* copy the string */
382 while (1) { /* move one character or [/<char>]<char> */
383 if (*buf_ptr == '\n') {
384 diag2(1, "Unterminated literal");
387 CHECK_SIZE_TOKEN; /* Only have to do this once in this loop,
388 * since CHECK_SIZE guarantees that there
389 * are at least 5 entries left */
390 *e_token = *buf_ptr++;
391 if (buf_ptr >= buf_end)
393 if (*e_token == BACKSLASH) { /* if escape, copy extra char */
394 if (*buf_ptr == '\n') /* check for escaped newline */
397 *++e_token = BACKSLASH;
398 if (*buf_ptr == BACKSLASH)
399 *++e_token = BACKSLASH;
401 *++e_token = *buf_ptr++;
402 ++e_token; /* we must increment this again because we
403 * copied two chars */
404 if (buf_ptr >= buf_end)
408 break; /* we copied one character */
409 } /* end of while (1) */
410 } while (*e_token++ != qchar);
412 e_token = chfont(&stringf, &bodyf, e_token - 1);
432 unary_delim = ps.last_u_d;
455 * if (ps.in_or_st) ps.block_init = 1;
457 /* ? code = ps.block_init ? lparen : lbrace; */
463 /* ? code = ps.block_init ? rparen : rbrace; */
467 case 014: /* a form feed */
468 unary_delim = ps.last_u_d;
469 ps.last_nl = true; /* remember this so we can set 'ps.col_1'
485 case '+': /* check for -, +, --, ++ */
486 code = (ps.last_u_d ? unary_op : binary_op);
489 if (*buf_ptr == token[0]) {
490 /* check for doubled character */
491 *e_token++ = *buf_ptr++;
492 /* buffer overflow will be checked at end of loop */
493 if (last_code == ident || last_code == rparen) {
494 code = (ps.last_u_d ? unary_op : postop);
495 /* check for following ++ or -- */
499 else if (*buf_ptr == '=')
500 /* check for operator += */
501 *e_token++ = *buf_ptr++;
502 else if (*buf_ptr == '>') {
503 /* check for operator -> */
504 *e_token++ = *buf_ptr++;
505 if (!pointer_as_binop) {
508 ps.want_blank = false;
511 break; /* buffer overflow will be checked at end of
518 if (chartype[*buf_ptr] == opchar) { /* we have two char assignment */
519 e_token[-1] = *buf_ptr++;
520 if ((e_token[-1] == '<' || e_token[-1] == '>') && e_token[-1] == *buf_ptr)
521 *e_token++ = *buf_ptr++;
522 *e_token++ = '='; /* Flip =+ to += */
526 if (*buf_ptr == '=') {/* == */
527 *e_token++ = '='; /* Flip =+ to += */
535 /* can drop thru!!! */
539 case '!': /* ops like <, <<, <=, !=, etc */
540 if (*buf_ptr == '>' || *buf_ptr == '<' || *buf_ptr == '=') {
541 *e_token++ = *buf_ptr;
542 if (++buf_ptr >= buf_end)
546 *e_token++ = *buf_ptr++;
547 code = (ps.last_u_d ? unary_op : binary_op);
552 if (token[0] == '/' && *buf_ptr == '*') {
553 /* it is start of comment */
556 if (++buf_ptr >= buf_end)
560 unary_delim = ps.last_u_d;
563 while (*(e_token - 1) == *buf_ptr || *buf_ptr == '=') {
565 * handle ||, &&, etc, and also things as in int *****i
567 *e_token++ = *buf_ptr;
568 if (++buf_ptr >= buf_end)
571 code = (ps.last_u_d ? unary_op : binary_op);
575 } /* end of switch */
576 if (code != newline) {
580 if (buf_ptr >= buf_end) /* check for input buffer empty */
582 ps.last_u_d = unary_delim;
583 *e_token = '\0'; /* null terminate the token */
588 * Add the given keyword to the keyword table, using val as the keyword type
591 addkey(char *key, int val)
593 struct templ *p = specials;
595 if (p->rwd[0] == key[0] && strcmp(p->rwd, key) == 0)
599 if (p >= specials + sizeof specials / sizeof specials[0])
600 return; /* For now, table overflows are silently