mod_export int
parse_subst_string(char *s)
{
int c, l = strlen(s), err, olen, lexstop_ret;
if (!*s || !strcmp(s, nulstring))
return 0;
lexsave();
untokenize(s);
inpush(dupstring(s), 0, NULL);
strinbeg(0);
len = 0;
bptr = tokstr = s;
bsiz = l + 1;
c = hgetc();
lexstop_ret = lexstop;
c = gettokstr(c, 1);
err = errflag;
strinend();
inpop();
DPUTS(cmdsp, "BUG: parse_subst_string: cmdstack not empty.");
olen = len;
lexrestore();
errflag = err;
if (c == LEXERR) {
untokenize(s);
return 1;
}
#ifdef DEBUG
if (c != STRING || olen != l || errflag) {
fprintf(stderr, "Oops. Bug in parse_subst_string: %s\n",
olen < l ? "len < l" : errflag ? "errflag" : "c != STRING");
fflush(stderr);
untokenize(s);
return 1;
}
#endif
return 0;
}
static enum lextok
gettok(void)
{
int c, d;
int peekfd = -1;
enum lextok peek;
beginning:
tokstr = NULL;
while (iblank(c = hgetc()) && !lexstop);
toklineno = lineno;
if (lexstop)
return (errflag) ? LEXERR : ENDINPUT;
isfirstln = 0;
if ((lexflags & LEXFLAGS_ZLE))
wordbeg = inbufct - (qbang && c == bangchar);
hwbegin(-1-(qbang && c == bangchar));
/* word includes the last character read and possibly \ before ! */
if (dbparens) {
lexbuf.len = 0;
lexbuf.ptr = tokstr = (char *) hcalloc(lexbuf.siz = LEX_HEAP_SIZE);
hungetc(c);
cmdpush(CS_MATH);
c = dquote_parse(infor ? ';' : ')', 0);
cmdpop();
*lexbuf.ptr = '\0';
if (!c && infor) {
infor--;
return DINPAR;
}
if (c || (c = hgetc()) != ')') {
hungetc(c);
return LEXERR;
}
dbparens = 0;
return DOUTPAR;
} else if (idigit(c)) { /* handle 1< foo */
d = hgetc();
if(d == '&') {
d = hgetc();
if(d == '>') {
peekfd = c - '0';
hungetc('>');
c = '&';
} else {
hungetc(d);
lexstop = 0;
hungetc('&');
}
} else if (d == '>' || d == '<') {
peekfd = c - '0';
c = d;
} else {
hungetc(d);
lexstop = 0;
}
}
/* chars in initial position in word */
/*
* Handle comments. There are some special cases when this
* is not normal command input: lexflags implies we are examining
* a line lexically without it being used for normal command input.
*/
if (c == hashchar && !nocomments &&
(isset(INTERACTIVECOMMENTS) ||
((!lexflags || (lexflags & LEXFLAGS_COMMENTS)) && !expanding &&
(!interact || unset(SHINSTDIN) || strin)))) {
/* History is handled here to prevent extra *
* newlines being inserted into the history. */
if (lexflags & LEXFLAGS_COMMENTS_KEEP) {
lexbuf.len = 0;
lexbuf.ptr = tokstr =
(char *)hcalloc(lexbuf.siz = LEX_HEAP_SIZE);
add(c);
}
hwend();
while ((c = ingetc()) != '\n' && !lexstop) {
hwaddc(c);
addtoline(c);
if (lexflags & LEXFLAGS_COMMENTS_KEEP)
add(c);
}
if (errflag)
peek = LEXERR;
else {
if (lexflags & LEXFLAGS_COMMENTS_KEEP) {
*lexbuf.ptr = '\0';
if (!lexstop)
hungetc(c);
peek = STRING;
} else {
hwend();
hwbegin(0);
hwaddc('\n');
addtoline('\n');
/*
* If splitting a line and removing comments,
* we don't want a newline token since it's
* treated specially.
*/
if ((lexflags & LEXFLAGS_COMMENTS_STRIP) && lexstop)
peek = ENDINPUT;
else
peek = NEWLIN;
}
}
return peek;
}
switch (lexact1[STOUC(c)]) {
case LX1_BKSLASH:
d = hgetc();
if (d == '\n')
goto beginning;
hungetc(d);
lexstop = 0;
break;
case LX1_NEWLIN:
return NEWLIN;
case LX1_SEMI:
d = hgetc();
if(d == ';')
return DSEMI;
else if(d == '&')
return SEMIAMP;
else if (d == '|')
return SEMIBAR;
hungetc(d);
lexstop = 0;
return SEMI;
case LX1_AMPER:
d = hgetc();
if (d == '&')
return DAMPER;
else if (d == '!' || d == '|')
return AMPERBANG;
else if (d == '>') {
tokfd = peekfd;
d = hgetc();
if (d == '!' || d == '|')
return OUTANGAMPBANG;
else if (d == '>') {
d = hgetc();
if (d == '!' || d == '|')
return DOUTANGAMPBANG;
hungetc(d);
lexstop = 0;
return DOUTANGAMP;
}
hungetc(d);
lexstop = 0;
return AMPOUTANG;
}
hungetc(d);
lexstop = 0;
return AMPER;
case LX1_BAR:
d = hgetc();
if (d == '|')
return DBAR;
else if (d == '&')
return BARAMP;
hungetc(d);
lexstop = 0;
return BAR;
case LX1_INPAR:
d = hgetc();
if (d == '(') {
if (infor) {
dbparens = 1;
return DINPAR;
}
if (incmdpos || (isset(SHGLOB) && !isset(KSHGLOB))) {
lexbuf.len = 0;
lexbuf.ptr = tokstr = (char *)
hcalloc(lexbuf.siz = LEX_HEAP_SIZE);
switch (cmd_or_math(CS_MATH)) {
case CMD_OR_MATH_MATH:
return DINPAR;
case CMD_OR_MATH_CMD:
/*
* Not math, so we don't return the contents
* as a string in this case.
*/
tokstr = NULL;
return INPAR;
case CMD_OR_MATH_ERR:
/*
* LEXFLAGS_ACTIVE means we came from bufferwords(),
* so we treat as an incomplete math expression
*/
if (lexflags & LEXFLAGS_ACTIVE)
tokstr = dyncat("((", tokstr ? tokstr : "");
/* fall through */
default:
return LEXERR;
}
}
} else if (d == ')')
return INOUTPAR;
hungetc(d);
lexstop = 0;
if (!(isset(SHGLOB) || incond == 1 || incmdpos))
break;
return INPAR;
case LX1_OUTPAR:
return OUTPAR;
case LX1_INANG:
d = hgetc();
if (d == '(') {
hungetc(d);
lexstop = 0;
unpeekfd:
if(peekfd != -1) {
hungetc(c);
c = '0' + peekfd;
}
break;
}
if (d == '>') {
peek = INOUTANG;
} else if (d == '<') {
int e = hgetc();
if (e == '(') {
hungetc(e);
hungetc(d);
peek = INANG;
} else if (e == '<')
peek = TRINANG;
else if (e == '-')
peek = DINANGDASH;
else {
hungetc(e);
lexstop = 0;
peek = DINANG;
}
} else if (d == '&') {
peek = INANGAMP;
} else {
hungetc(d);
if(isnumglob())
goto unpeekfd;
peek = INANG;
}
tokfd = peekfd;
return peek;
case LX1_OUTANG:
d = hgetc();
if (d == '(') {
hungetc(d);
goto unpeekfd;
} else if (d == '&') {
d = hgetc();
if (d == '!' || d == '|')
peek = OUTANGAMPBANG;
else {
hungetc(d);
lexstop = 0;
peek = OUTANGAMP;
}
} else if (d == '!' || d == '|')
peek = OUTANGBANG;
else if (d == '>') {
d = hgetc();
if (d == '&') {
d = hgetc();
if (d == '!' || d == '|')
peek = DOUTANGAMPBANG;
else {
hungetc(d);
lexstop = 0;
peek = DOUTANGAMP;
}
} else if (d == '!' || d == '|')
peek = DOUTANGBANG;
else if (d == '(') {
hungetc(d);
hungetc('>');
peek = OUTANG;
} else {
hungetc(d);
lexstop = 0;
peek = DOUTANG;
if (isset(HISTALLOWCLOBBER))
hwaddc('|');
}
} else {
hungetc(d);
lexstop = 0;
peek = OUTANG;
if (!incond && isset(HISTALLOWCLOBBER))
hwaddc('|');
}
tokfd = peekfd;
return peek;
}
/* we've started a string, now get the *
* rest of it, performing tokenization */
return gettokstr(c, 0);
}
mod_export int
parse_subst_string(char *s)
{
int c, l = strlen(s), err;
char *ptr;
enum lextok ctok;
if (!*s || !strcmp(s, nulstring))
return 0;
zcontext_save();
untokenize(s);
inpush(dupstring(s), 0, NULL);
strinbeg(0);
lexbuf.len = 0;
lexbuf.ptr = tokstr = s;
lexbuf.siz = l + 1;
c = hgetc();
ctok = gettokstr(c, 1);
err = errflag;
strinend();
inpop();
DPUTS(cmdsp, "BUG: parse_subst_string: cmdstack not empty.");
zcontext_restore();
/* Keep any interrupt error status */
errflag = err | (errflag & ERRFLAG_INT);
if (ctok == LEXERR) {
untokenize(s);
return 1;
}
#ifdef DEBUG
/*
* Historical note: we used to check here for olen (the value of lexbuf.len
* before zcontext_restore()) == l, but that's not necessarily the case if
* we stripped an RCQUOTE.
*/
if (ctok != STRING || (errflag && !noerrs)) {
fprintf(stderr, "Oops. Bug in parse_subst_string: %s\n",
errflag ? "errflag" : "ctok != STRING");
fflush(stderr);
untokenize(s);
return 1;
}
#endif
/* Check for $'...' quoting. This needs special handling. */
for (ptr = s; *ptr; )
{
if (*ptr == String && ptr[1] == Snull)
{
char *t;
int len, tlen, diff;
t = getkeystring(ptr + 2, &len, GETKEYS_DOLLARS_QUOTE, NULL);
len += 2;
tlen = strlen(t);
diff = len - tlen;
/*
* Yuk.
* parse_subst_string() currently handles strings in-place.
* That's not so easy to fix without knowing whether
* additional memory should come off the heap or
* otherwise. So we cheat by copying the unquoted string
* into place, unless it's too long. That's not the
* normal case, but I'm worried there are pathological
* cases with converting metafied multibyte strings.
* If someone can prove there aren't I will be very happy.
*/
if (diff < 0) {
DPUTS(1, "$'...' subst too long: fix get_parse_string()");
return 1;
}
memcpy(ptr, t, tlen);
ptr += tlen;
if (diff > 0) {
char *dptr = ptr;
char *sptr = ptr + diff;
while ((*dptr++ = *sptr++))
;
}
} else
ptr++;
}
return 0;
}
int
gettok(void)
{
int c, d;
int peekfd = -1, peek;
beginning:
tokstr = NULL;
while (iblank(c = hgetc()) && !lexstop);
if (lexstop)
return (errflag) ? LEXERR : ENDINPUT;
isfirstln = 0;
wordbeg = inbufct - (qbang && c == bangchar);
hwbegin(-1-(qbang && c == bangchar));
/* word includes the last character read and possibly \ before ! */
if (dbparens) {
len = 0;
bptr = tokstr = (char *) hcalloc(bsiz = 32);
hungetc(c);
cmdpush(CS_MATH);
c = dquote_parse(infor ? ';' : ')', 0);
cmdpop();
*bptr = '\0';
if (!c && infor) {
infor--;
return DINPAR;
}
if (c || (c = hgetc()) != ')') {
hungetc(c);
return LEXERR;
}
dbparens = 0;
return DOUTPAR;
} else if (idigit(c)) { /* handle 1< foo */
d = hgetc();
if(d == '&') {
d = hgetc();
if(d == '>') {
peekfd = c - '0';
hungetc('>');
c = '&';
} else {
hungetc(d);
lexstop = 0;
hungetc('&');
}
} else if (d == '>' || d == '<') {
peekfd = c - '0';
c = d;
} else {
hungetc(d);
lexstop = 0;
}
}
/* chars in initial position in word */
if (c == hashchar && !nocomments &&
(isset(INTERACTIVECOMMENTS) ||
(!zleparse && !expanding &&
(!interact || unset(SHINSTDIN) || strin)))) {
/* History is handled here to prevent extra *
* newlines being inserted into the history. */
while ((c = ingetc()) != '\n' && !lexstop) {
hwaddc(c);
addtoline(c);
}
if (errflag)
peek = LEXERR;
else {
hwend();
hwbegin(0);
hwaddc('\n');
addtoline('\n');
peek = NEWLIN;
}
return peek;
}
switch (lexact1[STOUC(c)]) {
case LX1_BKSLASH:
d = hgetc();
if (d == '\n')
goto beginning;
hungetc(d);
lexstop = 0;
break;
case LX1_NEWLIN:
return NEWLIN;
case LX1_SEMI:
d = hgetc();
if(d == ';')
return DSEMI;
else if(d == '&')
return SEMIAMP;
hungetc(d);
lexstop = 0;
return SEMI;
case LX1_AMPER:
d = hgetc();
if (d == '&')
return DAMPER;
else if (d == '!' || d == '|')
return AMPERBANG;
else if (d == '>') {
tokfd = peekfd;
d = hgetc();
if (d == '!' || d == '|')
return OUTANGAMPBANG;
else if (d == '>') {
d = hgetc();
if (d == '!' || d == '|')
return DOUTANGAMPBANG;
hungetc(d);
lexstop = 0;
return DOUTANGAMP;
}
hungetc(d);
lexstop = 0;
return AMPOUTANG;
}
hungetc(d);
lexstop = 0;
return AMPER;
case LX1_BAR:
d = hgetc();
if (d == '|')
return DBAR;
else if (d == '&')
return BARAMP;
hungetc(d);
lexstop = 0;
return BAR;
case LX1_INPAR:
d = hgetc();
if (d == '(') {
if (infor) {
dbparens = 1;
return DINPAR;
}
if (incmdpos) {
len = 0;
bptr = tokstr = (char *) hcalloc(bsiz = 32);
return cmd_or_math(CS_MATH) ? DINPAR : INPAR;
}
} else if (d == ')')
return INOUTPAR;
hungetc(d);
lexstop = 0;
if (!(incond == 1 || incmdpos))
break;
return INPAR;
case LX1_OUTPAR:
return OUTPAR;
case LX1_INANG:
d = hgetc();
if (!incmdpos && d == '(') {
hungetc(d);
lexstop = 0;
unpeekfd:
if(peekfd != -1) {
hungetc(c);
c = '0' + peekfd;
}
break;
}
if (d == '>') {
peek = INOUTANG;
} else if (d == '<') {
int e = hgetc();
if (e == '(') {
hungetc(e);
hungetc(d);
peek = INANG;
} else if (e == '<')
peek = TRINANG;
else if (e == '-')
peek = DINANGDASH;
else {
hungetc(e);
lexstop = 0;
peek = DINANG;
}
} else if (d == '&') {
peek = INANGAMP;
} else {
hungetc(d);
if(isnumglob())
goto unpeekfd;
peek = INANG;
}
tokfd = peekfd;
return peek;
case LX1_OUTANG:
d = hgetc();
if (d == '(') {
hungetc(d);
goto unpeekfd;
} else if (d == '&') {
d = hgetc();
if (d == '!' || d == '|')
peek = OUTANGAMPBANG;
else {
hungetc(d);
lexstop = 0;
peek = OUTANGAMP;
}
} else if (d == '!' || d == '|')
peek = OUTANGBANG;
else if (d == '>') {
d = hgetc();
if (d == '&') {
d = hgetc();
if (d == '!' || d == '|')
peek = DOUTANGAMPBANG;
else {
hungetc(d);
lexstop = 0;
peek = DOUTANGAMP;
}
} else if (d == '!' || d == '|')
peek = DOUTANGBANG;
else if (d == '(') {
hungetc(d);
hungetc('>');
peek = OUTANG;
} else {
hungetc(d);
lexstop = 0;
peek = DOUTANG;
if (isset(HISTALLOWCLOBBER))
hwaddc('|');
}
} else {
hungetc(d);
lexstop = 0;
peek = OUTANG;
if (!incond && isset(HISTALLOWCLOBBER))
hwaddc('|');
}
tokfd = peekfd;
return peek;
}
/* we've started a string, now get the *
* rest of it, performing tokenization */
return gettokstr(c, 0);
}