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 const char *q
= s_token
;
254 size_t q_len
= strlen(q
);
255 /* Check if we have an "_t" in the end */
257 (strcmp(q
+ q_len
- 2, "_t") == 0)) {
258 ps
.its_a_keyword
= true;
260 goto found_auto_typedef
;
265 * This loop will check if the token is a keyword.
267 for (p
= specials
; (j
= p
->rwd
) != 0; p
++) {
268 const char *q
= s_token
; /* point at scanned token */
269 if (*j
++ != *q
++ || *j
++ != *q
++)
270 continue; /* This test depends on the fact that
271 * identifiers are always at least 1 character
272 * long (ie. the first two bytes of the
273 * identifier are always meaningful) */
275 break; /* If its a one-character identifier */
278 goto found_keyword
; /* I wish that C had a multi-level
281 if (p
->rwd
) { /* we have a keyword */
283 ps
.its_a_keyword
= true;
286 case 1: /* it is a switch */
288 case 2: /* a case or default */
291 case 3: /* a "struct" */
293 * Next time around, we will want to know that we have had a
299 case 4: /* one of the declaration keywords */
302 ps
.cast_mask
|= (1 << ps
.p_l_follow
) & ~ps
.sizeof_mask
;
303 break; /* inside parens: cast, param list or sizeof */
308 case 5: /* if, while, for */
311 case 6: /* do, else */
315 ps
.sizeof_keyword
= true;
316 default: /* all others are treated like any other
319 } /* end of switch */
320 } /* end of if (found_it) */
321 if (*buf_ptr
== '(' && ps
.tos
<= 1 && ps
.ind_level
== 0) {
324 if (*tp
++ == ')' && (*tp
== ';' || *tp
== ','))
326 strncpy(ps
.procname
, token
, sizeof ps
.procname
- 1);
327 ps
.in_parameter_declaration
= 1;
332 * The following hack attempts to guess whether or not the current
333 * token is in fact a declaration keyword -- one that has been
336 if (((*buf_ptr
== '*' && buf_ptr
[1] != '=') || isalpha(*buf_ptr
) || *buf_ptr
== '_')
339 && (ps
.last_token
== rparen
|| ps
.last_token
== semicolon
||
340 ps
.last_token
== decl
||
341 ps
.last_token
== lbrace
|| ps
.last_token
== rbrace
)) {
342 ps
.its_a_keyword
= true;
347 if (last_code
== decl
) /* if this is a declared variable, then
348 * following sign is unary */
349 ps
.last_u_d
= true; /* will make "int a -1" work */
351 return (ident
); /* the ident is not in the list */
352 } /* end of procesing for alpanum character */
354 /* Scan a non-alphanumeric token */
356 *e_token
++ = *buf_ptr
; /* if it is only a one-character token, it is
359 if (++buf_ptr
>= buf_end
)
364 unary_delim
= ps
.last_u_d
;
365 ps
.last_nl
= true; /* remember that we just had a newline */
366 code
= (had_eof
? 0 : newline
);
369 * if data has been exhausted, the newline is a dummy, and we should
370 * return code to stop
374 case '\'': /* start of quoted character */
375 case '"': /* start of string */
381 e_token
= chfont(&bodyf
, &stringf
, e_token
);
383 do { /* copy the string */
384 while (1) { /* move one character or [/<char>]<char> */
385 if (*buf_ptr
== '\n') {
386 diag2(1, "Unterminated literal");
389 CHECK_SIZE_TOKEN
; /* Only have to do this once in this loop,
390 * since CHECK_SIZE guarantees that there
391 * are at least 5 entries left */
392 *e_token
= *buf_ptr
++;
393 if (buf_ptr
>= buf_end
)
395 if (*e_token
== BACKSLASH
) { /* if escape, copy extra char */
396 if (*buf_ptr
== '\n') /* check for escaped newline */
399 *++e_token
= BACKSLASH
;
400 if (*buf_ptr
== BACKSLASH
)
401 *++e_token
= BACKSLASH
;
403 *++e_token
= *buf_ptr
++;
404 ++e_token
; /* we must increment this again because we
405 * copied two chars */
406 if (buf_ptr
>= buf_end
)
410 break; /* we copied one character */
411 } /* end of while (1) */
412 } while (*e_token
++ != qchar
);
414 e_token
= chfont(&stringf
, &bodyf
, e_token
- 1);
434 unary_delim
= ps
.last_u_d
;
457 * if (ps.in_or_st) ps.block_init = 1;
459 /* ? code = ps.block_init ? lparen : lbrace; */
465 /* ? code = ps.block_init ? rparen : rbrace; */
469 case 014: /* a form feed */
470 unary_delim
= ps
.last_u_d
;
471 ps
.last_nl
= true; /* remember this so we can set 'ps.col_1'
487 case '+': /* check for -, +, --, ++ */
488 code
= (ps
.last_u_d
? unary_op
: binary_op
);
491 if (*buf_ptr
== token
[0]) {
492 /* check for doubled character */
493 *e_token
++ = *buf_ptr
++;
494 /* buffer overflow will be checked at end of loop */
495 if (last_code
== ident
|| last_code
== rparen
) {
496 code
= (ps
.last_u_d
? unary_op
: postop
);
497 /* check for following ++ or -- */
501 else if (*buf_ptr
== '=')
502 /* check for operator += */
503 *e_token
++ = *buf_ptr
++;
504 else if (*buf_ptr
== '>') {
505 /* check for operator -> */
506 *e_token
++ = *buf_ptr
++;
507 if (!pointer_as_binop
) {
510 ps
.want_blank
= false;
513 break; /* buffer overflow will be checked at end of
520 if (chartype
[*buf_ptr
] == opchar
) { /* we have two char assignment */
521 e_token
[-1] = *buf_ptr
++;
522 if ((e_token
[-1] == '<' || e_token
[-1] == '>') && e_token
[-1] == *buf_ptr
)
523 *e_token
++ = *buf_ptr
++;
524 *e_token
++ = '='; /* Flip =+ to += */
528 if (*buf_ptr
== '=') {/* == */
529 *e_token
++ = '='; /* Flip =+ to += */
537 /* can drop thru!!! */
541 case '!': /* ops like <, <<, <=, !=, etc */
542 if (*buf_ptr
== '>' || *buf_ptr
== '<' || *buf_ptr
== '=') {
543 *e_token
++ = *buf_ptr
;
544 if (++buf_ptr
>= buf_end
)
548 *e_token
++ = *buf_ptr
++;
549 code
= (ps
.last_u_d
? unary_op
: binary_op
);
554 if (token
[0] == '/' && *buf_ptr
== '*') {
555 /* it is start of comment */
558 if (++buf_ptr
>= buf_end
)
562 unary_delim
= ps
.last_u_d
;
565 while (*(e_token
- 1) == *buf_ptr
|| *buf_ptr
== '=') {
567 * handle ||, &&, etc, and also things as in int *****i
569 *e_token
++ = *buf_ptr
;
570 if (++buf_ptr
>= buf_end
)
573 code
= (ps
.last_u_d
? unary_op
: binary_op
);
577 } /* end of switch */
578 if (code
!= newline
) {
582 if (buf_ptr
>= buf_end
) /* check for input buffer empty */
584 ps
.last_u_d
= unary_delim
;
585 *e_token
= '\0'; /* null terminate the token */
590 * Add the given keyword to the keyword table, using val as the keyword type
593 addkey(char *key
, int val
)
595 struct templ
*p
= specials
;
597 if (p
->rwd
[0] == key
[0] && strcmp(p
->rwd
, key
) == 0)
601 if (p
>= specials
+ sizeof specials
/ sizeof specials
[0])
602 return; /* For now, table overflows are silently