unsigned
histhasher(char *str)
{
unsigned hashval = 0;
while (inblank(*str)) str++;
while (*str) {
if (inblank(*str)) {
do str++; while (inblank(*str));
if (*str)
hashval += (hashval << 5) + ' ';
}
else
hashval += (hashval << 5) + *(unsigned char *)str++;
}
return hashval;
}
static Cpattern
parse_pattern(char *name, char **sp, int *lp, char e, int *err)
{
Cpattern ret = NULL, r = NULL, n;
char *s = *sp;
convchar_t inchar;
int l = 0, inlen;
*err = 0;
MB_METACHARINIT();
while (*s && (e ? (*s != e) : !inblank(*s))) {
n = (Cpattern) hcalloc(sizeof(*n));
n->next = NULL;
if (*s == '[' || *s == '{') {
s = parse_class(n, s);
if (!*s) {
*err = 1;
zwarnnam(name, "unterminated character class");
return NULL;
}
s++;
} else if (*s == '?') {
n->tp = CPAT_ANY;
s++;
} else if (*s == '*' || *s == '(' || *s == ')' || *s == '=') {
*err = 1;
zwarnnam(name, "invalid pattern character `%c'", *s);
return NULL;
} else {
if (*s == '\\' && s[1])
s++;
inlen = MB_METACHARLENCONV(s, &inchar);
#ifdef MULTIBYTE_SUPPORT
if (inchar == WEOF)
inchar = (convchar_t)(*s == Meta ? s[1] ^ 32 : *s);
#endif
s += inlen;
n->tp = CPAT_CHAR;
n->u.chr = inchar;
}
if (ret)
r->next = n;
else
ret = n;
r = n;
l++;
}
*sp = (char *) s;
*lp = l;
return ret;
}
int
histstrcmp(const char *str1, const char *str2)
{
while (inblank(*str1)) str1++;
while (inblank(*str2)) str2++;
while (*str1 && *str2) {
if (inblank(*str1)) {
if (!inblank(*str2))
break;
do str1++; while (inblank(*str1));
do str2++; while (inblank(*str2));
}
else {
if (*str1 != *str2)
break;
str1++;
str2++;
}
}
return *str1 - *str2;
}
mod_export Cmatcher
parse_cmatcher(char *name, char *s)
{
Cmatcher ret = NULL, r = NULL, n;
Cpattern line, word, left, right;
int fl, fl2, ll, wl, lal, ral, err, both;
if (!*s)
return NULL;
while (*s) {
lal = ral = both = fl2 = 0;
left = right = NULL;
while (*s && inblank(*s)) s++;
if (!*s) break;
switch (*s) {
case 'b': fl2 = CMF_INTER;
case 'l': fl = CMF_LEFT; break;
case 'e': fl2 = CMF_INTER;
case 'r': fl = CMF_RIGHT; break;
case 'm': fl = 0; break;
case 'B': fl2 = CMF_INTER;
case 'L': fl = CMF_LEFT | CMF_LINE; break;
case 'E': fl2 = CMF_INTER;
case 'R': fl = CMF_RIGHT | CMF_LINE; break;
case 'M': fl = CMF_LINE; break;
default:
if (name)
zwarnnam(name, "unknown match specification character `%c'",
*s);
return pcm_err;
}
if (s[1] != ':') {
if (name)
zwarnnam(name, "missing `:'");
return pcm_err;
}
s += 2;
if (!*s) {
if (name)
zwarnnam(name, "missing patterns");
return pcm_err;
}
if ((fl & CMF_LEFT) && !fl2) {
left = parse_pattern(name, &s, &lal, '|', &err);
if (err)
return pcm_err;
if ((both = (*s && s[1] == '|')))
s++;
if (!*s || !*++s) {
if (name)
zwarnnam(name, "missing line pattern");
return pcm_err;
}
} else
left = NULL;
line = parse_pattern(name, &s, &ll,
(((fl & CMF_RIGHT) && !fl2) ? '|' : '='),
&err);
if (err)
return pcm_err;
if (both) {
right = line;
ral = ll;
line = NULL;
ll = 0;
}
if ((fl & CMF_RIGHT) && !fl2 && (!*s || !*++s)) {
if (name)
zwarnnam(name, "missing right anchor");
} else if (!(fl & CMF_RIGHT) || fl2) {
if (!*s) {
if (name)
zwarnnam(name, "missing word pattern");
return pcm_err;
}
s++;
}
if ((fl & CMF_RIGHT) && !fl2) {
if (*s == '|') {
left = line;
lal = ll;
line = NULL;
ll = 0;
s++;
}
right = parse_pattern(name, &s, &ral, '=', &err);
if (err)
return pcm_err;
if (!*s) {
if (name)
zwarnnam(name, "missing word pattern");
return pcm_err;
}
s++;
} else
right = NULL;
if (*s == '*') {
if (!(fl & (CMF_LEFT | CMF_RIGHT))) {
if (name)
zwarnnam(name, "need anchor for `*'");
return pcm_err;
}
word = NULL;
if (*++s == '*') {
s++;
wl = -2;
} else
wl = -1;
} else {
word = parse_pattern(name, &s, &wl, 0, &err);
if (!word && !line) {
if (name)
zwarnnam(name, "need non-empty word or line pattern");
return pcm_err;
}
}
if (err)
return pcm_err;
n = (Cmatcher) hcalloc(sizeof(*ret));
n->next = NULL;
n->flags = fl | fl2;
n->line = line;
n->llen = ll;
n->word = word;
n->wlen = wl;
n->left = left;
n->lalen = lal;
n->right = right;
n->ralen = ral;
if (ret)
r->next = n;
else
ret = n;
r = n;
}
return ret;
}
static enum lextok
gettokstr(int c, int sub)
{
int bct = 0, pct = 0, brct = 0, seen_brct = 0, fdpar = 0;
int intpos = 1, in_brace_param = 0;
int inquote, unmatched = 0;
enum lextok peek;
#ifdef DEBUG
int ocmdsp = cmdsp;
#endif
peek = STRING;
if (!sub) {
lexbuf.len = 0;
lexbuf.ptr = tokstr = (char *) hcalloc(lexbuf.siz = LEX_HEAP_SIZE);
}
for (;;) {
int act;
int e;
int inbl = inblank(c);
if (fdpar && !inbl && c != ')')
fdpar = 0;
if (inbl && !in_brace_param && !pct)
act = LX2_BREAK;
else {
act = lexact2[STOUC(c)];
c = lextok2[STOUC(c)];
}
switch (act) {
case LX2_BREAK:
if (!in_brace_param && !sub)
goto brk;
break;
case LX2_META:
c = hgetc();
#ifdef DEBUG
if (lexstop) {
fputs("BUG: input terminated by Meta\n", stderr);
fflush(stderr);
goto brk;
}
#endif
add(Meta);
break;
case LX2_OUTPAR:
if (fdpar) {
/* this is a single word `( )', treat as INOUTPAR */
add(c);
*lexbuf.ptr = '\0';
return INOUTPAR;
}
if ((sub || in_brace_param) && isset(SHGLOB))
break;
if (!in_brace_param && !pct--) {
if (sub) {
pct = 0;
break;
} else
goto brk;
}
c = Outpar;
break;
case LX2_BAR:
if (!pct && !in_brace_param) {
if (sub)
break;
else
goto brk;
}
if (unset(SHGLOB) || (!sub && !in_brace_param))
c = Bar;
break;
case LX2_STRING:
e = hgetc();
if (e == '[') {
cmdpush(CS_MATHSUBST);
add(String);
add(Inbrack);
c = dquote_parse(']', sub);
cmdpop();
if (c) {
peek = LEXERR;
goto brk;
}
c = Outbrack;
} else if (e == '(') {
add(String);
switch (cmd_or_math_sub()) {
case CMD_OR_MATH_CMD:
c = Outpar;
break;
case CMD_OR_MATH_MATH:
c = Outparmath;
break;
default:
peek = LEXERR;
goto brk;
}
} else {
if (e == '{') {
add(c);
c = Inbrace;
++bct;
cmdpush(CS_BRACEPAR);
if (!in_brace_param) {
if ((in_brace_param = bct))
seen_brct = 0;
}
} else {
hungetc(e);
lexstop = 0;
}
}
break;
case LX2_INBRACK:
if (!in_brace_param) {
brct++;
seen_brct = 1;
}
c = Inbrack;
break;
case LX2_OUTBRACK:
if (!in_brace_param)
brct--;
if (brct < 0)
brct = 0;
c = Outbrack;
break;
case LX2_INPAR:
if (isset(SHGLOB)) {
if (sub || in_brace_param)
break;
if (incasepat && !lexbuf.len)
return INPAR;
if (!isset(KSHGLOB) && lexbuf.len)
goto brk;
}
if (!in_brace_param) {
if (!sub) {
e = hgetc();
hungetc(e);
lexstop = 0;
/* For command words, parentheses are only
* special at the start. But now we're tokenising
* the remaining string. So I don't see what
* the old incmdpos test here is for.
* pws 1999/6/8
*
* Oh, no.
* func1( )
* is a valid function definition in [k]sh. The best
* thing we can do, without really nasty lookahead tricks,
* is break if we find a blank after a parenthesis. At
* least this can't happen inside braces or brackets. We
* only allow this with SHGLOB (set for both sh and ksh).
*
* Things like `print @( |foo)' should still
* work, because [k]sh don't allow multiple words
* in a function definition, so we only do this
* in command position.
* pws 1999/6/14
*/
if (e == ')' || (isset(SHGLOB) && inblank(e) && !bct &&
!brct && !intpos && incmdpos)) {
/*
* Either a () token, or a command word with
* something suspiciously like a ksh function
* definition.
* The current word isn't spellcheckable.
*/
nocorrect |= 2;
goto brk;
}
}
/*
* This also handles the [k]sh `foo( )' function definition.
* Maintain a variable fdpar, set as long as a single set of
* parentheses contains only space. Then if we get to the
* closing parenthesis and it is still set, we can assume we
* have a function definition. Only do this at the start of
* the word, since the (...) must be a separate token.
*/
if (!pct++ && isset(SHGLOB) && intpos && !bct && !brct)
fdpar = 1;
}
c = Inpar;
break;
case LX2_INBRACE:
if (isset(IGNOREBRACES) || sub)
c = '{';
else {
if (!lexbuf.len && incmdpos) {
add('{');
*lexbuf.ptr = '\0';
return STRING;
}
if (in_brace_param) {
cmdpush(CS_BRACE);
}
bct++;
}
break;
case LX2_OUTBRACE:
if ((isset(IGNOREBRACES) || sub) && !in_brace_param)
break;
if (!bct)
break;
if (in_brace_param) {
cmdpop();
}
if (bct-- == in_brace_param)
in_brace_param = 0;
c = Outbrace;
break;
case LX2_COMMA:
if (unset(IGNOREBRACES) && !sub && bct > in_brace_param)
c = Comma;
break;
case LX2_OUTANG:
if (in_brace_param || sub)
break;
e = hgetc();
if (e != '(') {
hungetc(e);
lexstop = 0;
goto brk;
}
add(OutangProc);
if (skipcomm()) {
peek = LEXERR;
goto brk;
}
c = Outpar;
break;
case LX2_INANG:
if (isset(SHGLOB) && sub)
break;
e = hgetc();
if (!(in_brace_param || sub) && e == '(') {
add(Inang);
if (skipcomm()) {
peek = LEXERR;
goto brk;
}
c = Outpar;
break;
}
hungetc(e);
if(isnumglob()) {
add(Inang);
while ((c = hgetc()) != '>')
add(c);
c = Outang;
break;
}
lexstop = 0;
if (in_brace_param || sub)
break;
goto brk;
case LX2_EQUALS:
if (!sub) {
if (intpos) {
e = hgetc();
if (e != '(') {
hungetc(e);
lexstop = 0;
c = Equals;
} else {
add(Equals);
if (skipcomm()) {
peek = LEXERR;
goto brk;
}
c = Outpar;
}
} else if (peek != ENVSTRING &&
(incmdpos || intypeset) && !bct && !brct) {
char *t = tokstr;
if (idigit(*t))
while (++t < lexbuf.ptr && idigit(*t));
else {
int sav = *lexbuf.ptr;
*lexbuf.ptr = '\0';
t = itype_end(t, IIDENT, 0);
if (t < lexbuf.ptr) {
skipparens(Inbrack, Outbrack, &t);
} else {
*lexbuf.ptr = sav;
}
}
if (*t == '+')
t++;
if (t == lexbuf.ptr) {
e = hgetc();
if (e == '(') {
*lexbuf.ptr = '\0';
return ENVARRAY;
}
hungetc(e);
lexstop = 0;
peek = ENVSTRING;
intpos = 2;
} else
c = Equals;
} else
c = Equals;
}
break;
case LX2_BKSLASH:
c = hgetc();
if (c == '\n') {
c = hgetc();
if (!lexstop)
continue;
} else {
add(Bnull);
if (c == STOUC(Meta)) {
c = hgetc();
#ifdef DEBUG
if (lexstop) {
fputs("BUG: input terminated by Meta\n", stderr);
fflush(stderr);
goto brk;
}
#endif
add(Meta);
}
}
if (lexstop)
goto brk;
break;
case LX2_QUOTE: {
int strquote = (lexbuf.len && lexbuf.ptr[-1] == String);
add(Snull);
cmdpush(CS_QUOTE);
for (;;) {
STOPHIST
while ((c = hgetc()) != '\'' && !lexstop) {
if (strquote && c == '\\') {
c = hgetc();
if (lexstop)
break;
/*
* Mostly we don't need to do anything special
* with escape backslashes or closing quotes
* inside $'...'; however in completion we
* need to be able to strip multiple backslashes
* neatly.
*/
if (c == '\\' || c == '\'')
add(Bnull);
else
add('\\');
} else if (!sub && isset(CSHJUNKIEQUOTES) && c == '\n') {
if (lexbuf.ptr[-1] == '\\')
lexbuf.ptr--, lexbuf.len--;
else
break;
}
add(c);
}
ALLOWHIST
if (c != '\'') {
unmatched = '\'';
peek = LEXERR;
cmdpop();
goto brk;
}
e = hgetc();
if (e != '\'' || unset(RCQUOTES) || strquote)
break;
add(c);
}
cmdpop();
hungetc(e);
lexstop = 0;
c = Snull;
break;
}
case LX2_DQUOTE:
add(Dnull);
cmdpush(CS_DQUOTE);
c = dquote_parse('"', sub);
cmdpop();
if (c) {
unmatched = '"';
peek = LEXERR;
goto brk;
}
c = Dnull;
break;
case LX2_BQUOTE:
add(Tick);
cmdpush(CS_BQUOTE);
SETPARBEGIN
inquote = 0;
while ((c = hgetc()) != '`' && !lexstop) {
if (c == '\\') {
c = hgetc();
if (c != '\n') {
add(c == '`' || c == '\\' || c == '$' ? Bnull : '\\');
add(c);
}
else if (!sub && isset(CSHJUNKIEQUOTES))
add(c);
} else {
if (!sub && isset(CSHJUNKIEQUOTES) && c == '\n') {
break;
}
add(c);
if (c == '\'') {
if ((inquote = !inquote))
STOPHIST
else
ALLOWHIST
}
}
}
if (inquote)
ALLOWHIST
cmdpop();
if (c != '`') {
unmatched = '`';
peek = LEXERR;
goto brk;
}
c = Tick;
SETPAREND
break;
case LX2_DASH:
/*
* - shouldn't be treated as a special character unless
* we're in a pattern. Howeve,simply counting "[" doesn't
* work as []a-z] is a valid expression and we don't know
* down here what this "[" is for as $foo[stuff] is valid
* in zsh. So just detect an opening [, which is enough
* to turn this into a pattern; the Dash will be harmlessly
* untokenised if not wanted.
*/
if (seen_brct)
c = Dash;
else
c = '-';
break;
case LX2_BANG:
/*
* Same logic as Dash, for ! to perform negation in range.
*/
if (seen_brct)
c = Bang;
else
c = '!';
}
add(c);
c = hgetc();
if (intpos)
intpos--;
if (lexstop)
break;
}
brk:
if (errflag) {
if (in_brace_param) {
while(bct-- >= in_brace_param)
cmdpop();
}
return LEXERR;
}
hungetc(c);
if (unmatched)
zerr("unmatched %c", unmatched);
if (in_brace_param) {
while(bct-- >= in_brace_param)
cmdpop();
zerr("closing brace expected");
} else if (unset(IGNOREBRACES) && !sub && lexbuf.len > 1 &&
peek == STRING && lexbuf.ptr[-1] == '}' &&
lexbuf.ptr[-2] != Bnull) {
/* hack to get {foo} command syntax work */
lexbuf.ptr--;
lexbuf.len--;
lexstop = 0;
hungetc('}');
}
*lexbuf.ptr = '\0';
DPUTS(cmdsp != ocmdsp, "BUG: gettok: cmdstack changed.");
return peek;
}
static int
skipcomm(void)
{
#ifdef ZSH_OLD_SKIPCOMM
int pct = 1, c, start = 1;
cmdpush(CS_CMDSUBST);
SETPARBEGIN
c = Inpar;
do {
int iswhite;
add(c);
c = hgetc();
if (itok(c) || lexstop)
break;
iswhite = inblank(c);
switch (c) {
case '(':
pct++;
break;
case ')':
pct--;
break;
case '\\':
add(c);
c = hgetc();
break;
case '\'': {
int strquote = lexbuf.ptr[-1] == '$';
add(c);
STOPHIST
while ((c = hgetc()) != '\'' && !lexstop) {
if (c == '\\' && strquote) {
add(c);
c = hgetc();
}
add(c);
}
ALLOWHIST
break;
}
case '\"':
add(c);
while ((c = hgetc()) != '\"' && !lexstop)
if (c == '\\') {
add(c);
add(hgetc());
} else
add(c);
break;
case '`':
add(c);
while ((c = hgetc()) != '`' && !lexstop)
if (c == '\\')
add(c), add(hgetc());
else
add(c);
break;
case '#':
if (start) {
add(c);
while ((c = hgetc()) != '\n' && !lexstop)
add(c);
iswhite = 1;
}
break;
}
start = iswhite;
}
while (pct);
if (!lexstop)
SETPAREND
cmdpop();
return lexstop;
#else
char *new_tokstr;
int new_lexstop, new_lex_add_raw;
int save_infor = infor;
struct lexbufstate new_lexbuf;
int noalias = noaliases;
noaliases = 1;
infor = 0;
cmdpush(CS_CMDSUBST);
SETPARBEGIN
add(Inpar);
new_lex_add_raw = lex_add_raw + 1;
if (!lex_add_raw) {
/*
* We'll combine the string so far with the input
* read in for the command substitution. To do this
* we'll just propagate the current tokstr etc. as the
* variables used for adding raw input, and
* ensure we swap those for the real tokstr etc. at the end.
*
* However, we need to save and restore the rest of the
* lexical and parse state as we're effectively parsing
* an internal string. Because we're still parsing it from
* the original input source (we have to --- we don't know
* when to stop inputting it otherwise and can't rely on
* the input being recoverable until we've read it) we need
* to keep the same history context.
*/
new_tokstr = tokstr;
new_lexbuf = lexbuf;
/*
* If we're expanding an alias at this point, we need the whole
* remaining text as part of the string for the command in
* parentheses, so don't backtrack. This is different from the
* usual case where the alias is fully within the command, where
* we want the unexpanded text so that it will be expanded
* again when the command in the parentheses is executed.
*
* I never wanted to be a software engineer, you know.
*/
if (inbufflags & INP_ALIAS)
inbufflags |= INP_RAW_KEEP;
zcontext_save_partial(ZCONTEXT_LEX|ZCONTEXT_PARSE);
hist_in_word(1);
} else {
/*
* Set up for nested command subsitution, however
* we don't actually need the string until we get
* back to the top level and recover the lot.
* The $() body just appears empty.
*
* We do need to propagate the raw variables which would
* otherwise by cleared, though.
*/
new_tokstr = tokstr_raw;
new_lexbuf = lexbuf_raw;
zcontext_save_partial(ZCONTEXT_LEX|ZCONTEXT_PARSE);
}
tokstr_raw = new_tokstr;
lexbuf_raw = new_lexbuf;
lex_add_raw = new_lex_add_raw;
/*
* Don't do any ZLE specials down here: they're only needed
* when we return the string from the recursive parse.
* (TBD: this probably means we should be initialising lexflags
* more consistently.)
*
* Note that in that case we're still using the ZLE line reading
* function at the history layer --- this is consistent with the
* intention of maintaining the history and input layers across
* the recursive parsing.
*/
lexflags &= ~LEXFLAGS_ZLE;
dbparens = 0; /* restored by zcontext_restore_partial() */
if (!parse_event(OUTPAR) || tok != OUTPAR)
lexstop = 1;
/* Outpar lexical token gets added in caller if present */
/*
* We're going to keep the full raw input string
* as the current token string after popping the stack.
*/
new_tokstr = tokstr_raw;
new_lexbuf = lexbuf_raw;
/*
* We're also going to propagate the lexical state:
* if we couldn't parse the command substitution we
* can't continue.
*/
new_lexstop = lexstop;
zcontext_restore_partial(ZCONTEXT_LEX|ZCONTEXT_PARSE);
if (lex_add_raw) {
/*
* Keep going, so retain the raw variables.
*/
tokstr_raw = new_tokstr;
lexbuf_raw = new_lexbuf;
} else {
if (!new_lexstop) {
/* Ignore the ')' added on input */
new_lexbuf.len--;
*--new_lexbuf.ptr = '\0';
}
/*
* Convince the rest of lex.c we were examining a string
* all along.
*/
tokstr = new_tokstr;
lexbuf = new_lexbuf;
lexstop = new_lexstop;
hist_in_word(0);
}
if (!lexstop)
SETPAREND
cmdpop();
infor = save_infor;
noaliases = noalias;
return lexstop;
#endif
}
static int
gettokstr(int c, int sub)
{
int bct = 0, pct = 0, brct = 0, fdpar = 0;
int intpos = 1, in_brace_param = 0;
int peek, inquote, unmatched = 0;
char endchar='"';
#ifdef DEBUG
int ocmdsp = cmdsp;
#endif
peek = STRING;
if (!sub) {
len = 0;
bptr = tokstr = (char *) hcalloc(bsiz = 32);
}
for (;;) {
int act;
int e;
int inbl = inblank(c);
if (fdpar && !inbl && c != ')')
fdpar = 0;
if (inbl && !in_brace_param && !pct)
act = LX2_BREAK;
else {
act = lexact2[STOUC(c)];
c = lextok2[STOUC(c)];
}
switch (act) {
case LX2_BREAK:
if (!in_brace_param && !sub)
goto brk;
break;
case LX2_META:
c = hgetc();
#ifdef DEBUG
if (lexstop) {
fputs("BUG: input terminated by Meta\n", stderr);
fflush(stderr);
goto brk;
}
#endif
add(Meta);
break;
case LX2_OUTPAR:
if (fdpar) {
/* this is a single word `( )', treat as INOUTPAR */
add(c);
*bptr = '\0';
return INOUTPAR;
}
if ((sub || in_brace_param) && isset(SHGLOB))
break;
if (!in_brace_param && !pct--) {
if (sub) {
pct = 0;
break;
} else
goto brk;
}
c = Outpar;
break;
case LX2_BAR:
if (!pct && !in_brace_param) {
if (sub)
break;
else
goto brk;
}
if (unset(SHGLOB) || (!sub && !in_brace_param))
c = Bar;
break;
case LX2_STRING:
e = hgetc();
if (e == '[') {
cmdpush(CS_MATHSUBST);
add(String);
add(Inbrack);
c = dquote_parse(']', sub);
cmdpop();
if (c) {
peek = LEXERR;
goto brk;
}
c = Outbrack;
} else if (e == '(') {
add(String);
c = cmd_or_math_sub();
if (c) {
peek = LEXERR;
goto brk;
}
c = Outpar;
} else {
if (e == '{') {
add(c);
c = Inbrace;
++bct;
cmdpush(CS_BRACEPAR);
if (!in_brace_param)
in_brace_param = bct;
} else {
hungetc(e);
lexstop = 0;
}
}
break;
case LX2_INBRACK:
if (!in_brace_param)
brct++;
c = Inbrack;
break;
case LX2_OUTBRACK:
if (!in_brace_param)
brct--;
if (brct < 0)
brct = 0;
c = Outbrack;
break;
case LX2_INPAR:
if (isset(SHGLOB)) {
if (sub || in_brace_param)
break;
if (incasepat && !len)
return INPAR;
}
if (!in_brace_param) {
if (!sub) {
e = hgetc();
hungetc(e);
lexstop = 0;
/* For command words, parentheses are only
* special at the start. But now we're tokenising
* the remaining string. So I don't see what
* the old incmdpos test here is for.
* pws 1999/6/8
*
* Oh, no.
* func1( )
* is a valid function definition in [k]sh. The best
* thing we can do, without really nasty lookahead tricks,
* is break if we find a blank after a parenthesis. At
* least this can't happen inside braces or brackets. We
* only allow this with SHGLOB (set for both sh and ksh).
*
* Things like `print @( |foo)' should still
* work, because [k]sh don't allow multiple words
* in a function definition, so we only do this
* in command position.
* pws 1999/6/14
*/
if (e == ')' || (isset(SHGLOB) && inblank(e) && !bct &&
!brct && !intpos && incmdpos))
goto brk;
}
/*
* This also handles the [k]sh `foo( )' function definition.
* Maintain a variable fdpar, set as long as a single set of
* parentheses contains only space. Then if we get to the
* closing parenthesis and it is still set, we can assume we
* have a function definition. Only do this at the start of
* the word, since the (...) must be a separate token.
*/
if (!pct++ && isset(SHGLOB) && intpos && !bct && !brct)
fdpar = 1;
}
c = Inpar;
break;
case LX2_INBRACE:
if (isset(IGNOREBRACES) || sub)
c = '{';
else {
if (!len && incmdpos) {
add('{');
*bptr = '\0';
return STRING;
}
if (in_brace_param) {
cmdpush(CS_BRACE);
}
bct++;
}
break;
case LX2_OUTBRACE:
if ((isset(IGNOREBRACES) || sub) && !in_brace_param)
break;
if (!bct)
break;
if (in_brace_param) {
cmdpop();
}
if (bct-- == in_brace_param)
in_brace_param = 0;
c = Outbrace;
break;
case LX2_COMMA:
if (unset(IGNOREBRACES) && !sub && bct > in_brace_param)
c = Comma;
break;
case LX2_OUTANG:
if (!intpos) {
if (in_brace_param || sub)
break;
else
goto brk;
}
e = hgetc();
if (e != '(') {
hungetc(e);
lexstop = 0;
goto brk;
}
add(Outang);
if (skipcomm()) {
peek = LEXERR;
goto brk;
}
c = Outpar;
break;
case LX2_INANG:
if (isset(SHGLOB) && sub)
break;
e = hgetc();
if(e == '(' && intpos) {
add(Inang);
if (skipcomm()) {
peek = LEXERR;
goto brk;
}
c = Outpar;
break;
}
hungetc(e);
if(isnumglob()) {
add(Inang);
while ((c = hgetc()) != '>')
add(c);
c = Outang;
break;
}
lexstop = 0;
if (in_brace_param || sub)
break;
goto brk;
case LX2_EQUALS:
if (intpos) {
e = hgetc();
if (e != '(') {
hungetc(e);
lexstop = 0;
c = Equals;
} else {
add(Equals);
if (skipcomm()) {
peek = LEXERR;
goto brk;
}
c = Outpar;
}
} else if (!sub && peek != ENVSTRING &&
incmdpos && !bct && !brct) {
char *t = tokstr;
if (idigit(*t))
while (++t < bptr && idigit(*t));
else {
while (iident(*t) && ++t < bptr);
if (t < bptr) {
*bptr = '\0';
skipparens(Inbrack, Outbrack, &t);
}
}
if (*t == '+')
t++;
if (t == bptr) {
e = hgetc();
if (e == '(' && incmdpos) {
*bptr = '\0';
return ENVARRAY;
}
hungetc(e);
lexstop = 0;
peek = ENVSTRING;
intpos = 2;
} else
c = Equals;
} else
c = Equals;
break;
#ifndef __SYMBIAN32__
case LX2_BKSLASH:
c = hgetc();
if (c == '\n') {
c = hgetc();
if (!lexstop)
continue;
} else
add(Bnull);
if (lexstop)
goto brk;
break;
#endif
case LX2_QUOTE: {
int strquote = (len && bptr[-1] == String);
add(Snull);
cmdpush(CS_QUOTE);
for (;;) {
STOPHIST
while ((c = hgetc()) != '\'' && !lexstop) {
if (strquote && c == '\\') {
add(c);
c = hgetc();
if (lexstop)
break;
} else if (!sub && isset(CSHJUNKIEQUOTES) && c == '\n') {
if (bptr[-1] == '\\')
bptr--, len--;
else
break;
}
add(c);
}
ALLOWHIST
if (c != '\'') {
unmatched = '\'';
peek = LEXERR;
cmdpop();
goto brk;
}
e = hgetc();
if (e != '\'' || unset(RCQUOTES) || strquote)
break;
add(c);
}
cmdpop();
hungetc(e);
lexstop = 0;
c = Snull;
break;
}
case LX2_DQUOTE:
add(Dnull);
cmdpush(CS_DQUOTE);
c = dquote_parse('"', sub);
cmdpop();
if (c) {
unmatched = '"';
peek = LEXERR;
goto brk;
}
c = Dnull;
break;
case LX2_BQUOTE:
add(Tick);
cmdpush(CS_BQUOTE);
SETPARBEGIN
inquote = 0;
while ((c = hgetc()) != '`' && !lexstop) {
if (c == '\\') {
c = hgetc();
if (c != '\n') {
add(c == '`' || c == '\\' || c == '$' ? Bnull : '\\');
add(c);
}
else if (!sub && isset(CSHJUNKIEQUOTES))
add(c);
} else {
if (!sub && isset(CSHJUNKIEQUOTES) && c == '\n') {
break;
}
add(c);
if (c == '\'') {
if ((inquote = !inquote))
STOPHIST
else
ALLOWHIST
}
}
}
if (inquote)
ALLOWHIST
cmdpop();
if (c != '`') {
unmatched = '`';
peek = LEXERR;
goto brk;
}
c = Tick;
SETPAREND
break;
}
#ifdef __SYMBIAN32__
if(c=='\\')
{
c = hgetc();
if (c != '\n') {
if (c == endchar)
add(Bnull);
else {
/* lexstop is implicitly handled here */
add('\\');
}
}
}
#endif
add(c);
c = hgetc();
if (intpos)
intpos--;
if (lexstop)
break;
}
brk:
hungetc(c);
if (unmatched)
zerr("unmatched %c", NULL, unmatched);
if (in_brace_param) {
while(bct-- >= in_brace_param)
cmdpop();
zerr("closing brace expected", NULL, 0);
} else if (unset(IGNOREBRACES) && !sub && len > 1 &&
peek == STRING && bptr[-1] == '}' && bptr[-2] != Bnull) {
/* hack to get {foo} command syntax work */
bptr--;
len--;
lexstop = 0;
hungetc('}');
}
*bptr = '\0';
DPUTS(cmdsp != ocmdsp, "BUG: gettok: cmdstack changed.");
return peek;
}
static int
skipcomm(void)
{
int pct = 1, c, start = 1;
cmdpush(CS_CMDSUBST);
SETPARBEGIN
c = Inpar;
do {
int iswhite;
add(c);
c = hgetc();
if (itok(c) || lexstop)
break;
iswhite = inblank(c);
switch (c) {
case '(':
pct++;
break;
case ')':
pct--;
break;
case '\\':
add(c);
c = hgetc();
break;
case '\'': {
int strquote = bptr[-1] == '$';
add(c);
STOPHIST
while ((c = hgetc()) != '\'' && !lexstop) {
if (c == '\\' && strquote) {
add(c);
c = hgetc();
}
add(c);
}
ALLOWHIST
break;
}
case '\"':
add(c);
while ((c = hgetc()) != '\"' && !lexstop)
if (c == '\\') {
add(c);
add(hgetc());
} else
add(c);
break;
case '`':
add(c);
while ((c = hgetc()) != '`' && !lexstop)
if (c == '\\')
add(c), add(hgetc());
else
add(c);
break;
case '#':
if (start) {
add(c);
while ((c = hgetc()) != '\n' && !lexstop)
add(c);
iswhite = 1;
}
break;
}
start = iswhite;
}
while (pct);
if (!lexstop)
SETPAREND
cmdpop();
return lexstop;
}
int
filesubstr(char **namptr, int assign)
{
#define isend(c) ( !(c) || (c)=='/' || (c)==Inpar || (assign && (c)==':') )
#define isend2(c) ( !(c) || (c)==Inpar || (assign && (c)==':') )
char *str = *namptr;
if (*str == Tilde && str[1] != '=' && str[1] != Equals) {
char *ptr;
int val;
val = zstrtol(str + 1, &ptr, 10);
if (isend(str[1])) { /* ~ */
*namptr = dyncat(home, str + 1);
return 1;
} else if (str[1] == '+' && isend(str[2])) { /* ~+ */
*namptr = dyncat(pwd, str + 2);
return 1;
} else if (str[1] == '-' && isend(str[2])) { /* ~- */
char *tmp;
*namptr = dyncat((tmp = oldpwd) ? tmp : pwd, str + 2);
return 1;
} else if (!inblank(str[1]) && isend(*ptr) &&
(!idigit(str[1]) || (ptr - str < 4))) {
char *ds;
if (val < 0)
val = -val;
ds = dstackent(str[1], val);
if (!ds)
return 0;
*namptr = dyncat(ds, ptr);
return 1;
} else if (iuser(str[1])) { /* ~foo */
char *ptr, *hom, save;
for (ptr = ++str; *ptr && iuser(*ptr); ptr++);
save = *ptr;
if (!isend(save))
return 0;
*ptr = 0;
if (!(hom = getnameddir(str))) {
if (isset(NOMATCH))
zerr("no such user or named directory: %s", str, 0);
*ptr = save;
return 0;
}
*ptr = save;
*namptr = dyncat(hom, ptr);
return 1;
}
} else if (*str == Equals && isset(EQUALS) && str[1]) { /* =foo */
char sav, *pp, *cnam;
for (pp = str + 1; !isend2(*pp); pp++);
sav = *pp;
*pp = 0;
if (!(cnam = findcmd(str + 1))) {
Alias a = (Alias) aliastab->getnode(aliastab, str + 1);
if (a)
cnam = ztrdup(a->text);
else {
if (isset(NOMATCH))
zerr("%s not found", str + 1, 0);
return 0;
}
}
*namptr = dupstring(cnam);
zsfree(cnam);
if (sav) {
*pp = sav;
*namptr = dyncat(*namptr, pp);
}
return 1;
}
return 0;
#undef isend
#undef isend2
}
