1 /* $NetBSD: tokenizer.c,v 1.28 2016/04/11 18:56:31 christos Exp $ */
4 * Copyright (c) 1992, 1993
5 * The Regents of the University of California. All rights reserved.
7 * This code is derived from software contributed to Berkeley by
8 * Christos Zoulas of Cornell University.
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions
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.
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
36 #if !defined(lint) && !defined(SCCSID)
38 static char sccsid
[] = "@(#)tokenizer.c 8.1 (Berkeley) 6/4/93";
40 __RCSID("$NetBSD: tokenizer.c,v 1.28 2016/04/11 18:56:31 christos Exp $");
42 #endif /* not lint && not SCCSID */
44 /* We build this file twice, once as NARROW, once as WIDE. */
46 * tokenize.c: Bourne shell like tokenizer
54 Q_none
, Q_single
, Q_double
, Q_one
, Q_doubleone
63 #define IFS STR("\t \n")
65 #define tok_malloc(a) malloc(a)
66 #define tok_free(a) free(a)
67 #define tok_realloc(a, b) realloc(a, b)
71 #define FUN(prefix, rest) prefix ## _ ## rest
72 #define TYPE(type) type
74 #define Strchr(s, c) strchr(s, c)
75 #define tok_strdup(s) strdup(s)
78 #define FUN(prefix, rest) prefix ## _w ## rest
79 #define TYPE(type) type ## W
81 #define Strchr(s, c) wcschr(s, c)
82 #define tok_strdup(s) wcsdup(s)
85 struct TYPE(tokenizer
) {
86 Char
*ifs
; /* In field separator */
87 size_t argc
, amax
; /* Current and maximum number of args */
88 Char
**argv
; /* Argument list */
89 Char
*wptr
, *wmax
; /* Space and limit on the word buffer */
90 Char
*wstart
; /* Beginning of next word */
91 Char
*wspace
; /* Space of word buffer */
92 quote_t quote
; /* Quoting state */
93 int flags
; /* flags; */
97 static void FUN(tok
,finish
)(TYPE(Tokenizer
) *);
100 /* FUN(tok,finish)():
101 * Finish a word in the tokenizer.
104 FUN(tok
,finish
)(TYPE(Tokenizer
) *tok
)
108 if ((tok
->flags
& TOK_KEEP
) || tok
->wptr
!= tok
->wstart
) {
109 tok
->argv
[tok
->argc
++] = tok
->wstart
;
110 tok
->argv
[tok
->argc
] = NULL
;
111 tok
->wstart
= ++tok
->wptr
;
113 tok
->flags
&= ~TOK_KEEP
;
118 * Initialize the tokenizer
121 FUN(tok
,init
)(const Char
*ifs
)
123 TYPE(Tokenizer
) *tok
= tok_malloc(sizeof(*tok
));
127 tok
->ifs
= tok_strdup(ifs
? ifs
: IFS
);
128 if (tok
->ifs
== NULL
) {
134 tok
->argv
= tok_malloc(sizeof(*tok
->argv
) * tok
->amax
);
135 if (tok
->argv
== NULL
) {
141 tok
->wspace
= tok_malloc(WINCR
* sizeof(*tok
->wspace
));
142 if (tok
->wspace
== NULL
) {
148 tok
->wmax
= tok
->wspace
+ WINCR
;
149 tok
->wstart
= tok
->wspace
;
150 tok
->wptr
= tok
->wspace
;
159 * Reset the tokenizer
162 FUN(tok
,reset
)(TYPE(Tokenizer
) *tok
)
166 tok
->wstart
= tok
->wspace
;
167 tok
->wptr
= tok
->wspace
;
177 FUN(tok
,end
)(TYPE(Tokenizer
) *tok
)
181 tok_free(tok
->wspace
);
189 * Bourne shell (sh(1)) like tokenizing
191 * tok current tokenizer state (setup with FUN(tok,init)())
196 * 2 Unmatched double quote
197 * 1 Unmatched single quote
199 * Modifies (if return value is 0):
200 * argc number of arguments
201 * argv argument array
202 * cursorc if !NULL, argv element containing cursor
203 * cursorv if !NULL, offset in argv[cursorc] of cursor
206 FUN(tok
,line
)(TYPE(Tokenizer
) *tok
, const TYPE(LineInfo
) *line
,
207 int *argc
, const Char
***argv
, int *cursorc
, int *cursoro
)
214 for (ptr
= line
->buffer
; ;ptr
++) {
215 if (ptr
>= line
->lastchar
)
217 if (ptr
== line
->cursor
) {
219 co
= (int)(tok
->wptr
- tok
->wstart
);
223 tok
->flags
|= TOK_KEEP
;
224 tok
->flags
&= ~TOK_EAT
;
225 switch (tok
->quote
) {
227 tok
->quote
= Q_single
; /* Enter single quote
231 case Q_single
: /* Exit single quote mode */
235 case Q_one
: /* Quote this ' */
240 case Q_double
: /* Stay in double quote mode */
244 case Q_doubleone
: /* Quote this ' */
245 tok
->quote
= Q_double
;
255 tok
->flags
&= ~TOK_EAT
;
256 tok
->flags
|= TOK_KEEP
;
257 switch (tok
->quote
) {
258 case Q_none
: /* Enter double quote mode */
259 tok
->quote
= Q_double
;
262 case Q_double
: /* Exit double quote mode */
266 case Q_one
: /* Quote this " */
271 case Q_single
: /* Stay in single quote mode */
275 case Q_doubleone
: /* Quote this " */
276 tok
->quote
= Q_double
;
286 tok
->flags
|= TOK_KEEP
;
287 tok
->flags
&= ~TOK_EAT
;
288 switch (tok
->quote
) {
289 case Q_none
: /* Quote next character */
293 case Q_double
: /* Quote next character */
294 tok
->quote
= Q_doubleone
;
297 case Q_one
: /* Quote this, restore state */
302 case Q_single
: /* Stay in single quote mode */
306 case Q_doubleone
: /* Quote this \ */
307 tok
->quote
= Q_double
;
317 tok
->flags
&= ~TOK_EAT
;
318 switch (tok
->quote
) {
324 *tok
->wptr
++ = *ptr
; /* Add the return */
327 case Q_doubleone
: /* Back to double, eat the '\n' */
328 tok
->flags
|= TOK_EAT
;
329 tok
->quote
= Q_double
;
332 case Q_one
: /* No quote, more eat the '\n' */
333 tok
->flags
|= TOK_EAT
;
343 switch (tok
->quote
) {
345 /* Finish word and return */
346 if (tok
->flags
& TOK_EAT
) {
347 tok
->flags
&= ~TOK_EAT
;
359 tok
->quote
= Q_double
;
374 tok
->flags
&= ~TOK_EAT
;
375 switch (tok
->quote
) {
377 if (Strchr(tok
->ifs
, *ptr
) != NULL
)
378 FUN(tok
,finish
)(tok
);
391 tok
->quote
= Q_double
;
407 if (tok
->wptr
>= tok
->wmax
- 4) {
408 size_t size
= (size_t)(tok
->wmax
- tok
->wspace
+ WINCR
);
409 Char
*s
= tok_realloc(tok
->wspace
,
414 if (s
!= tok
->wspace
) {
416 for (i
= 0; i
< tok
->argc
; i
++) {
418 (tok
->argv
[i
] - tok
->wspace
) + s
;
420 tok
->wptr
= (tok
->wptr
- tok
->wspace
) + s
;
421 tok
->wstart
= (tok
->wstart
- tok
->wspace
) + s
;
424 tok
->wmax
= s
+ size
;
426 if (tok
->argc
>= tok
->amax
- 4) {
429 p
= tok_realloc(tok
->argv
, tok
->amax
* sizeof(*p
));
438 if (cc
== -1 && co
== -1) {
440 co
= (int)(tok
->wptr
- tok
->wstart
);
446 FUN(tok
,finish
)(tok
);
447 *argv
= (const Char
**)tok
->argv
;
448 *argc
= (int)tok
->argc
;
453 * Simpler version of tok_line, taking a NUL terminated line
454 * and splitting into words, ignoring cursor state.
457 FUN(tok
,str
)(TYPE(Tokenizer
) *tok
, const Char
*line
, int *argc
,
462 memset(&li
, 0, sizeof(li
));
464 li
.cursor
= li
.lastchar
= Strchr(line
, '\0');
465 return FUN(tok
,line
)(tok
, &li
, argc
, argv
, NULL
, NULL
);