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) &&
195 (*buf_ptr == 'U' || *buf_ptr == 'u')) {
197 *e_token++ = *buf_ptr++;
201 if (!(seensfx & 2) &&
202 (*buf_ptr == 'L' || *buf_ptr == 'l')) {
204 if (buf_ptr[1] == buf_ptr[0])
205 *e_token++ = *buf_ptr++;
206 *e_token++ = *buf_ptr++;
214 while (chartype[(int)*buf_ptr] == alphanum || *buf_ptr == BACKSLASH) {
215 /* fill_buffer() terminates buffer with newline */
216 if (*buf_ptr == BACKSLASH) {
217 if (*(buf_ptr + 1) == '\n') {
219 if (buf_ptr >= buf_end)
226 *e_token++ = *buf_ptr++;
227 if (buf_ptr >= buf_end)
231 while (*buf_ptr == ' ' || *buf_ptr == '\t') { /* get rid of blanks */
232 if (++buf_ptr >= buf_end)
235 ps.its_a_keyword = false;
236 ps.sizeof_keyword = false;
237 if (l_struct && !ps.p_l_follow) {
238 /* if last token was 'struct' and we're not
239 * in parentheses, then this token
240 * should be treated as a declaration */
246 ps.last_u_d = l_struct; /* Operator after identifier is binary
247 * unless last token was 'struct' */
249 last_code = ident; /* Remember that this is the code we will
253 * This loop will check if the token is a keyword.
255 for (p = specials; (j = p->rwd) != 0; p++) {
256 const char *q = s_token; /* point at scanned token */
257 if (*j++ != *q++ || *j++ != *q++)
258 continue; /* This test depends on the fact that
259 * identifiers are always at least 1 character
260 * long (ie. the first two bytes of the
261 * identifier are always meaningful) */
263 break; /* If its a one-character identifier */
266 goto found_keyword; /* I wish that C had a multi-level
269 if (p->rwd) { /* we have a keyword */
271 ps.its_a_keyword = true;
274 case 1: /* it is a switch */
276 case 2: /* a case or default */
279 case 3: /* a "struct" */
281 * Next time around, we will want to know that we have had a
287 case 4: /* one of the declaration keywords */
289 ps.cast_mask |= (1 << ps.p_l_follow) & ~ps.sizeof_mask;
290 break; /* inside parens: cast, param list or sizeof */
295 case 5: /* if, while, for */
298 case 6: /* do, else */
302 ps.sizeof_keyword = true;
303 default: /* all others are treated like any other
306 } /* end of switch */
307 } /* end of if (found_it) */
308 if (*buf_ptr == '(' && ps.tos <= 1 && ps.ind_level == 0) {
311 if (*tp++ == ')' && (*tp == ';' || *tp == ','))
313 strncpy(ps.procname, token, sizeof ps.procname - 1);
314 ps.in_parameter_declaration = 1;
319 * The following hack attempts to guess whether or not the current
320 * token is in fact a declaration keyword -- one that has been
323 if (((*buf_ptr == '*' && buf_ptr[1] != '=') || isalpha(*buf_ptr) || *buf_ptr == '_')
326 && (ps.last_token == rparen || ps.last_token == semicolon ||
327 ps.last_token == decl ||
328 ps.last_token == lbrace || ps.last_token == rbrace)) {
329 ps.its_a_keyword = true;
334 if (last_code == decl) /* if this is a declared variable, then
335 * following sign is unary */
336 ps.last_u_d = true; /* will make "int a -1" work */
338 return (ident); /* the ident is not in the list */
339 } /* end of procesing for alpanum character */
341 /* Scan a non-alphanumeric token */
343 *e_token++ = *buf_ptr; /* if it is only a one-character token, it is
346 if (++buf_ptr >= buf_end)
351 unary_delim = ps.last_u_d;
352 ps.last_nl = true; /* remember that we just had a newline */
353 code = (had_eof ? 0 : newline);
356 * if data has been exhausted, the newline is a dummy, and we should
357 * return code to stop
361 case '\'': /* start of quoted character */
362 case '"': /* start of string */
368 e_token = chfont(&bodyf, &stringf, e_token);
370 do { /* copy the string */
371 while (1) { /* move one character or [/<char>]<char> */
372 if (*buf_ptr == '\n') {
373 diag2(1, "Unterminated literal");
376 CHECK_SIZE_TOKEN; /* Only have to do this once in this loop,
377 * since CHECK_SIZE guarantees that there
378 * are at least 5 entries left */
379 *e_token = *buf_ptr++;
380 if (buf_ptr >= buf_end)
382 if (*e_token == BACKSLASH) { /* if escape, copy extra char */
383 if (*buf_ptr == '\n') /* check for escaped newline */
386 *++e_token = BACKSLASH;
387 if (*buf_ptr == BACKSLASH)
388 *++e_token = BACKSLASH;
390 *++e_token = *buf_ptr++;
391 ++e_token; /* we must increment this again because we
392 * copied two chars */
393 if (buf_ptr >= buf_end)
397 break; /* we copied one character */
398 } /* end of while (1) */
399 } while (*e_token++ != qchar);
401 e_token = chfont(&stringf, &bodyf, e_token - 1);
421 unary_delim = ps.last_u_d;
444 * if (ps.in_or_st) ps.block_init = 1;
446 /* ? code = ps.block_init ? lparen : lbrace; */
452 /* ? code = ps.block_init ? rparen : rbrace; */
456 case 014: /* a form feed */
457 unary_delim = ps.last_u_d;
458 ps.last_nl = true; /* remember this so we can set 'ps.col_1'
474 case '+': /* check for -, +, --, ++ */
475 code = (ps.last_u_d ? unary_op : binary_op);
478 if (*buf_ptr == token[0]) {
479 /* check for doubled character */
480 *e_token++ = *buf_ptr++;
481 /* buffer overflow will be checked at end of loop */
482 if (last_code == ident || last_code == rparen) {
483 code = (ps.last_u_d ? unary_op : postop);
484 /* check for following ++ or -- */
488 else if (*buf_ptr == '=')
489 /* check for operator += */
490 *e_token++ = *buf_ptr++;
491 else if (*buf_ptr == '>') {
492 /* check for operator -> */
493 *e_token++ = *buf_ptr++;
494 if (!pointer_as_binop) {
497 ps.want_blank = false;
500 break; /* buffer overflow will be checked at end of
507 if (chartype[*buf_ptr] == opchar) { /* we have two char assignment */
508 e_token[-1] = *buf_ptr++;
509 if ((e_token[-1] == '<' || e_token[-1] == '>') && e_token[-1] == *buf_ptr)
510 *e_token++ = *buf_ptr++;
511 *e_token++ = '='; /* Flip =+ to += */
515 if (*buf_ptr == '=') {/* == */
516 *e_token++ = '='; /* Flip =+ to += */
524 /* can drop thru!!! */
528 case '!': /* ops like <, <<, <=, !=, etc */
529 if (*buf_ptr == '>' || *buf_ptr == '<' || *buf_ptr == '=') {
530 *e_token++ = *buf_ptr;
531 if (++buf_ptr >= buf_end)
535 *e_token++ = *buf_ptr++;
536 code = (ps.last_u_d ? unary_op : binary_op);
541 if (token[0] == '/' && *buf_ptr == '*') {
542 /* it is start of comment */
545 if (++buf_ptr >= buf_end)
549 unary_delim = ps.last_u_d;
552 while (*(e_token - 1) == *buf_ptr || *buf_ptr == '=') {
554 * handle ||, &&, etc, and also things as in int *****i
556 *e_token++ = *buf_ptr;
557 if (++buf_ptr >= buf_end)
560 code = (ps.last_u_d ? unary_op : binary_op);
564 } /* end of switch */
565 if (code != newline) {
569 if (buf_ptr >= buf_end) /* check for input buffer empty */
571 ps.last_u_d = unary_delim;
572 *e_token = '\0'; /* null terminate the token */
577 * Add the given keyword to the keyword table, using val as the keyword type
580 addkey(char *key, int val)
582 struct templ *p = specials;
584 if (p->rwd[0] == key[0] && strcmp(p->rwd, key) == 0)
588 if (p >= specials + sizeof specials / sizeof specials[0])
589 return; /* For now, table overflows are silently