/*-
* Copyright (c) 1992, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Christos Zoulas of Cornell University.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#define tok_malloc(a) malloc(a)
#define tok_free(a) free(a)
#define tok_realloc(a, b) realloc(a, b)
#ifdef NARROWCHAR
#define Char char
#define FUN(prefix, rest) prefix ## _ ## rest
#define TYPE(type) type
#define STR(x) x
#define Strchr(s, c) strchr(s, c)
#define tok_strdup(s) strdup(s)
#else
#define Char wchar_t
#define FUN(prefix, rest) prefix ## _w ## rest
#define TYPE(type) type ## W
#define STR(x) L ## x
#define Strchr(s, c) wcschr(s, c)
#define tok_strdup(s) wcsdup(s)
#endif
struct TYPE(tokenizer) {
Char *ifs; /* In field separator */
size_t argc, amax; /* Current and maximum number of args */
const Char **argv; /* Argument list */
Char *wptr, *wmax; /* Space and limit on the word buffer */
Char *wstart; /* Beginning of next word */
Char *wspace; /* Space of word buffer */
quote_t quote; /* Quoting state */
int flags; /* flags; */
};
static void FUN(tok,finish)(TYPE(Tokenizer) *);
/* FUN(tok,finish)():
* Finish a word in the tokenizer.
*/
static void
FUN(tok,finish)(TYPE(Tokenizer) *tok)
{
/* FUN(tok,line)():
* Bourne shell (sh(1)) like tokenizing
* Arguments:
* tok current tokenizer state (setup with FUN(tok,init)())
* line line to parse
* Returns:
* -1 Internal error
* 3 Quoted return
* 2 Unmatched double quote
* 1 Unmatched single quote
* 0 Ok
* Modifies (if return value is 0):
* argc number of arguments
* argv argument array
* cursorc if !NULL, argv element containing cursor
* cursorv if !NULL, offset in argv[cursorc] of cursor
*/
int
FUN(tok,line)(TYPE(Tokenizer) *tok, const TYPE(LineInfo) *line,
int *argc, const Char ***argv, int *cursorc, int *cursoro)
{
const Char *ptr;
int cc, co;
cc = co = -1;
ptr = line->buffer;
for (ptr = line->buffer; ;ptr++) {
if (ptr >= line->lastchar)
ptr = STR("");
if (ptr == line->cursor) {
cc = (int)tok->argc;
co = (int)(tok->wptr - tok->wstart);
}
switch (*ptr) {
case '\'':
tok->flags |= TOK_KEEP;
tok->flags &= ~TOK_EAT;
switch (tok->quote) {
case Q_none:
tok->quote = Q_single; /* Enter single quote
* mode */
break;
case Q_single: /* Exit single quote mode */
tok->quote = Q_none;
break;
case Q_one: /* Quote this ' */
tok->quote = Q_none;
*tok->wptr++ = *ptr;
break;
case Q_double: /* Stay in double quote mode */
*tok->wptr++ = *ptr;
break;
case Q_doubleone: /* Quote this ' */
tok->quote = Q_double;
*tok->wptr++ = *ptr;
break;
default:
return -1;
}
break;
case '"':
tok->flags &= ~TOK_EAT;
tok->flags |= TOK_KEEP;
switch (tok->quote) {
case Q_none: /* Enter double quote mode */
tok->quote = Q_double;
break;
case Q_one:
tok->quote = Q_none;
*tok->wptr++ = *ptr;
break;
default:
return -1;
}
break;
}
if (tok->wptr >= tok->wmax - 4) {
size_t size = (size_t)(tok->wmax - tok->wspace + WINCR);
Char *s = tok_realloc(tok->wspace,
size * sizeof(*s));
if (s == NULL)
return -1;
if (s != tok->wspace) {
size_t i;
for (i = 0; i < tok->argc; i++) {
tok->argv[i] =
(tok->argv[i] - tok->wspace) + s;
}
tok->wptr = (tok->wptr - tok->wspace) + s;
tok->wstart = (tok->wstart - tok->wspace) + s;
tok->wspace = s;
}
tok->wmax = s + size;
}
if (tok->argc >= tok->amax - 4) {
const Char **p;
tok->amax += AINCR;
p = tok_realloc(tok->argv, tok->amax * sizeof(*p));
if (p == NULL) {
tok->amax -= AINCR;
return -1;
}
tok->argv = p;
}
}
tok_line_outok:
if (cc == -1 && co == -1) {
cc = (int)tok->argc;
co = (int)(tok->wptr - tok->wstart);
}
if (cursorc != NULL)
*cursorc = cc;
if (cursoro != NULL)
*cursoro = co;
FUN(tok,finish)(tok);
*argv = tok->argv;
*argc = (int)tok->argc;
return 0;
}
/* FUN(tok,str)():
* Simpler version of tok_line, taking a NUL terminated line
* and splitting into words, ignoring cursor state.
*/
int
FUN(tok,str)(TYPE(Tokenizer) *tok, const Char *line, int *argc,
const Char ***argv)
{
TYPE(LineInfo) li;
