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"
70 * This table has to be sorted alphabetically, because it'll be used in binary
71 * search. For the same reason, string must be the first thing in struct templ.
73 struct templ specials[] =
109 const char **typenames;
111 int typename_top = -1;
114 { /* this is used to facilitate the decision of
115 * what type (alphanumeric, operator) each
117 0, 0, 0, 0, 0, 0, 0, 0,
118 0, 0, 0, 0, 0, 0, 0, 0,
119 0, 0, 0, 0, 0, 0, 0, 0,
120 0, 0, 0, 0, 0, 0, 0, 0,
121 0, 3, 0, 0, 1, 3, 3, 0,
122 0, 0, 3, 3, 0, 3, 0, 3,
123 1, 1, 1, 1, 1, 1, 1, 1,
124 1, 1, 0, 0, 3, 3, 3, 3,
125 0, 1, 1, 1, 1, 1, 1, 1,
126 1, 1, 1, 1, 1, 1, 1, 1,
127 1, 1, 1, 1, 1, 1, 1, 1,
128 1, 1, 1, 0, 0, 0, 3, 1,
129 0, 1, 1, 1, 1, 1, 1, 1,
130 1, 1, 1, 1, 1, 1, 1, 1,
131 1, 1, 1, 1, 1, 1, 1, 1,
132 1, 1, 1, 0, 3, 0, 3, 0
136 strcmp_type(const void *e1, const void *e2)
138 return (strcmp(e1, *(const char * const *)e2));
144 int unary_delim; /* this is set to 1 if the current token
145 * forces a following operator to be unary */
146 static int last_code; /* the last token type returned */
147 static int l_struct; /* set to 1 if the last token was 'struct' */
148 int code; /* internal code to be returned */
149 char qchar; /* the delimiter character for a string */
151 e_token = s_token; /* point to start of place to save token */
153 ps.col_1 = ps.last_nl; /* tell world that this token started in
154 * column 1 iff the last thing scanned was nl */
157 while (*buf_ptr == ' ' || *buf_ptr == '\t') { /* get rid of blanks */
158 ps.col_1 = false; /* leading blanks imply token is not in column
160 if (++buf_ptr >= buf_end)
164 /* Scan an alphanumeric token */
165 if (chartype[(int)*buf_ptr] == alphanum || (buf_ptr[0] == '.' && isdigit(buf_ptr[1]))) {
167 * we have a character or number
171 if (isdigit(*buf_ptr) || (buf_ptr[0] == '.' && isdigit(buf_ptr[1]))) {
173 BASE_2, BASE_8, BASE_10, BASE_16
178 enum base in_base = BASE_10;
180 if (*buf_ptr == '0') {
181 if (buf_ptr[1] == 'b' || buf_ptr[1] == 'B')
183 else if (buf_ptr[1] == 'x' || buf_ptr[1] == 'X')
185 else if (isdigit(buf_ptr[1]))
190 *e_token++ = *buf_ptr++;
191 *e_token++ = *buf_ptr++;
192 while (*buf_ptr == '0' || *buf_ptr == '1') {
194 *e_token++ = *buf_ptr++;
198 *e_token++ = *buf_ptr++;
199 while (*buf_ptr >= '0' && *buf_ptr <= '8') {
201 *e_token++ = *buf_ptr++;
205 *e_token++ = *buf_ptr++;
206 *e_token++ = *buf_ptr++;
207 while (isxdigit(*buf_ptr)) {
209 *e_token++ = *buf_ptr++;
214 if (*buf_ptr == '.') {
221 *e_token++ = *buf_ptr++;
222 if (!isdigit(*buf_ptr) && *buf_ptr != '.') {
223 if ((*buf_ptr != 'E' && *buf_ptr != 'e') || seenexp)
229 *e_token++ = *buf_ptr++;
230 if (*buf_ptr == '+' || *buf_ptr == '-')
231 *e_token++ = *buf_ptr++;
238 if (!(seensfx & 1) && (*buf_ptr == 'U' || *buf_ptr == 'u')) {
240 *e_token++ = *buf_ptr++;
244 if (!(seensfx & 2) && (strchr("fFlL", *buf_ptr) != NULL)) {
246 if (buf_ptr[1] == buf_ptr[0])
247 *e_token++ = *buf_ptr++;
248 *e_token++ = *buf_ptr++;
256 while (chartype[(int)*buf_ptr] == alphanum || *buf_ptr == BACKSLASH) {
257 /* fill_buffer() terminates buffer with newline */
258 if (*buf_ptr == BACKSLASH) {
259 if (*(buf_ptr + 1) == '\n') {
261 if (buf_ptr >= buf_end)
268 *e_token++ = *buf_ptr++;
269 if (buf_ptr >= buf_end)
274 if (s_token[0] == 'L' && s_token[1] == '\0' &&
275 (*buf_ptr == '"' || *buf_ptr == '\''))
278 while (*buf_ptr == ' ' || *buf_ptr == '\t') { /* get rid of blanks */
279 if (++buf_ptr >= buf_end)
283 if (l_struct && !ps.p_l_follow) {
284 /* if last token was 'struct' and we're not
285 * in parentheses, then this token
286 * should be treated as a declaration */
292 ps.last_u_d = l_struct; /* Operator after identifier is binary
293 * unless last token was 'struct' */
295 last_code = ident; /* Remember that this is the code we will
300 sizeof(specials) / sizeof(specials[0]),
303 if (p == NULL) { /* not a special keyword... */
306 /* ... so maybe a type_t or a typedef */
307 if ((auto_typedefs && ((u = strrchr(s_token, '_')) != NULL) &&
308 strcmp(u, "_t") == 0) || (typename_top >= 0 &&
309 bsearch(s_token, typenames, typename_top + 1,
310 sizeof(typenames[0]), strcmp_type))) {
311 ps.keyword = 4; /* a type name */
315 } else { /* we have a keyword */
316 ps.keyword = p->rwcode;
319 case 7: /* it is a switch */
321 case 8: /* a case or default */
324 case 3: /* a "struct" */
326 * Next time around, we will want to know that we have had a
332 case 4: /* one of the declaration keywords */
335 /* inside parens: cast, param list, offsetof or sizeof */
336 ps.cast_mask |= (1 << ps.p_l_follow) & ~ps.not_cast_mask;
342 case 5: /* if, while, for */
345 case 6: /* do, else */
348 case 10: /* storage class specifier */
351 default: /* all others are treated like any other
354 } /* end of switch */
355 } /* end of if (found_it) */
356 if (*buf_ptr == '(' && ps.tos <= 1 && ps.ind_level == 0) {
359 if (*tp++ == ')' && (*tp == ';' || *tp == ','))
361 strncpy(ps.procname, token, sizeof ps.procname - 1);
363 ps.in_parameter_declaration = 1;
368 * The following hack attempts to guess whether or not the current
369 * token is in fact a declaration keyword -- one that has been
372 if (((*buf_ptr == '*' && buf_ptr[1] != '=') || isalpha(*buf_ptr) || *buf_ptr == '_')
375 && (ps.last_token == rparen || ps.last_token == semicolon ||
376 ps.last_token == decl ||
377 ps.last_token == lbrace || ps.last_token == rbrace)) {
378 ps.keyword = 4; /* a type name */
383 if (last_code == decl) /* if this is a declared variable, then
384 * following sign is unary */
385 ps.last_u_d = true; /* will make "int a -1" work */
387 return (ident); /* the ident is not in the list */
388 } /* end of procesing for alpanum character */
390 /* Scan a non-alphanumeric token */
392 *e_token++ = *buf_ptr; /* if it is only a one-character token, it is
395 if (++buf_ptr >= buf_end)
400 unary_delim = ps.last_u_d;
401 ps.last_nl = true; /* remember that we just had a newline */
402 code = (had_eof ? 0 : newline);
405 * if data has been exhausted, the newline is a dummy, and we should
406 * return code to stop
410 case '\'': /* start of quoted character */
411 case '"': /* start of string */
417 e_token = chfont(&bodyf, &stringf, e_token);
419 do { /* copy the string */
420 while (1) { /* move one character or [/<char>]<char> */
421 if (*buf_ptr == '\n') {
422 diag2(1, "Unterminated literal");
425 CHECK_SIZE_TOKEN; /* Only have to do this once in this loop,
426 * since CHECK_SIZE guarantees that there
427 * are at least 5 entries left */
428 *e_token = *buf_ptr++;
429 if (buf_ptr >= buf_end)
431 if (*e_token == BACKSLASH) { /* if escape, copy extra char */
432 if (*buf_ptr == '\n') /* check for escaped newline */
435 *++e_token = BACKSLASH;
436 if (*buf_ptr == BACKSLASH)
437 *++e_token = BACKSLASH;
439 *++e_token = *buf_ptr++;
440 ++e_token; /* we must increment this again because we
441 * copied two chars */
442 if (buf_ptr >= buf_end)
446 break; /* we copied one character */
447 } /* end of while (1) */
448 } while (*e_token++ != qchar);
450 e_token = chfont(&stringf, &bodyf, e_token - 1);
470 unary_delim = ps.last_u_d;
493 * if (ps.in_or_st) ps.block_init = 1;
495 /* ? code = ps.block_init ? lparen : lbrace; */
501 /* ? code = ps.block_init ? rparen : rbrace; */
505 case 014: /* a form feed */
506 unary_delim = ps.last_u_d;
507 ps.last_nl = true; /* remember this so we can set 'ps.col_1'
523 case '+': /* check for -, +, --, ++ */
524 code = (ps.last_u_d ? unary_op : binary_op);
527 if (*buf_ptr == token[0]) {
528 /* check for doubled character */
529 *e_token++ = *buf_ptr++;
530 /* buffer overflow will be checked at end of loop */
531 if (last_code == ident || last_code == rparen) {
532 code = (ps.last_u_d ? unary_op : postop);
533 /* check for following ++ or -- */
537 else if (*buf_ptr == '=')
538 /* check for operator += */
539 *e_token++ = *buf_ptr++;
540 else if (*buf_ptr == '>') {
541 /* check for operator -> */
542 *e_token++ = *buf_ptr++;
543 if (!pointer_as_binop) {
546 ps.want_blank = false;
549 break; /* buffer overflow will be checked at end of
556 if (chartype[*buf_ptr] == opchar) { /* we have two char assignment */
557 e_token[-1] = *buf_ptr++;
558 if ((e_token[-1] == '<' || e_token[-1] == '>') && e_token[-1] == *buf_ptr)
559 *e_token++ = *buf_ptr++;
560 *e_token++ = '='; /* Flip =+ to += */
564 if (*buf_ptr == '=') {/* == */
565 *e_token++ = '='; /* Flip =+ to += */
573 /* can drop thru!!! */
577 case '!': /* ops like <, <<, <=, !=, etc */
578 if (*buf_ptr == '>' || *buf_ptr == '<' || *buf_ptr == '=') {
579 *e_token++ = *buf_ptr;
580 if (++buf_ptr >= buf_end)
584 *e_token++ = *buf_ptr++;
585 code = (ps.last_u_d ? unary_op : binary_op);
590 if (token[0] == '/' && *buf_ptr == '*') {
591 /* it is start of comment */
594 if (++buf_ptr >= buf_end)
598 unary_delim = ps.last_u_d;
601 while (*(e_token - 1) == *buf_ptr || *buf_ptr == '=') {
603 * handle ||, &&, etc, and also things as in int *****i
605 *e_token++ = *buf_ptr;
606 if (++buf_ptr >= buf_end)
609 code = (ps.last_u_d ? unary_op : binary_op);
613 } /* end of switch */
614 if (code != newline) {
618 if (buf_ptr >= buf_end) /* check for input buffer empty */
620 ps.last_u_d = unary_delim;
621 *e_token = '\0'; /* null terminate the token */
626 alloc_typenames(void)
629 typenames = (const char **)malloc(sizeof(typenames[0]) *
630 (typename_count = 16));
631 if (typenames == NULL)
636 add_typename(const char *key)
641 if (typename_top + 1 >= typename_count) {
642 typenames = realloc((void *)typenames,
643 sizeof(typenames[0]) * (typename_count *= 2));
644 if (typenames == NULL)
647 if (typename_top == -1)
648 typenames[++typename_top] = copy = strdup(key);
649 else if ((comparison = strcmp(key, typenames[typename_top])) >= 0) {
650 /* take advantage of sorted input */
651 if (comparison == 0) /* remove duplicates */
653 typenames[++typename_top] = copy = strdup(key);
658 for (p = 0; (comparison = strcmp(key, typenames[p])) > 0; p++)
659 /* find place for the new key */;
660 if (comparison == 0) /* remove duplicates */
662 memmove(&typenames[p + 1], &typenames[p],
663 sizeof(typenames[0]) * (++typename_top - p));
664 typenames[p] = copy = strdup(key);