Re: <n> == <n->?

[Zefram <zefram@xxxxxxxx>]

[Johan Sundstr_m] wrote:
>When upgrading from zsh 3.1.6 to 3.1.6-dev-17 (as found in the Mandrake
>zsh-3.1.6dev17-1mdk rpm), I was sad to notice that the glob behaviour of
>the pattern <number> had changed to something identical to what I had
>earlier (and still can) specified as <number->, that is, an open range of
>numbers, from number onwards.

Hmm.

I thought we'd decided, quite some time ago, that the numeric glob syntax
was going to require a "-", to minimise ambiguity with redirection.
This is, in fact, what zshexpn(1) shows.  However, that was when the
<> operator was being introduced, so perhaps that change was limited
to making "<>" be always a redirection rather than a glob operator,
requiring "<->" for globbing.

<fx: checks>

Actually, lex.c is more lenient than that.  Anything matching
/\<[-0-9]+\>/ is initially lexed as a string rather than as operators.
However, gettokstr() has some nasties here.  Although the above grammar
applies at the beginning of a word, gettokstr() makes no such check
in the middle of a word.  As far as it's concerned, anything matching
/\<[-0-9]/ is the start of a glob operator, and it'll keep adding to
the string (past whitespace and so on) until it finds the closing ">".
Try typing "echo a<1" (and compare against "echo <1").

To complete the set, tokenize() insists on /\<[0-9]*-[0-9]*\>/.  So it
looks like it's *intended* that the "-" be required, but the lexer just
isn't actually enforcing it.  The code that actually causes "<n>" to
be treated like "<n->" is in pattern.c: it sees that it has a starting
number but no ending number, and just doesn't distinguish the two cases.

>                         <n> isn't useless, if (s)he who changed its 
>behaviour thought so, since it matches all the number n with any amount of
>leading zeroes, a feature I have daily use for, when rummaging through
>huge log directories, for instance.

"0#n" will do that (# = zero or more of the previous character).

OK.  This patch (already in the repository) fixes the grammar
disagreements, making all the relevant places check for the
/\<[0-9]*-[0-9]*\>/ syntax.  "<n>" is consequently removed; you'll have
to use "0#n" or "<n-n>".  No doc change, since this is changing things
to match the documented behaviour.

On the way, I fixed the rather nasty bug that if a word started with
a digit followed by a numeric glob, the initial digit got swallowed.
(The digit was provisionally treated as a file descriptor number and
never got restored.)

Incidentally, Adam, in /home/groups/zsh/zsh, you've managed to set all
*regular* files to be sgid, rather than all directories.  Can we have
from Adam and Peter please a "chgrp -R zsh /home/groups/zsh; chmod -R
g+w,g-s /home/groups/zsh; chmod g+s /home/groups/zsh/**/*(/)".

-zefram

Index: ChangeLog
===================================================================
RCS file: /cvsroot/zsh/zsh/ChangeLog,v
retrieving revision 1.3
diff -c -r1.3 ChangeLog
*** ChangeLog	2000/04/02 17:37:34	1.3
--- ChangeLog	2000/04/04 01:11:25
***************
*** 1,3 ****
--- 1,9 ----
+ 2000-04-04  Andrew Main  <zefram@xxxxxxx>
+ 
+ 	* 10444: Src/lex.c, Src/pattern.c: Insist on proper syntax
+ 	for numeric globbing (with the "-").  Also fix the bug whereby
+ 	"echo 1<2-3>" would lose the "1".
+ 
  2000-04-02  Peter Stephenson  <pws@xxxxxxxxxxxxxxxxxxxxxxxx>
  
  	* pws: Config/version.mk: 3.1.6-dev-21.
Index: Src/lex.c
===================================================================
RCS file: /cvsroot/zsh/zsh/Src/lex.c,v
retrieving revision 1.1.1.19
diff -c -r1.1.1.19 lex.c
*** Src/lex.c	2000/03/13 09:44:19	1.1.1.19
--- Src/lex.c	2000/04/04 01:11:29
***************
*** 569,575 ****
--- 569,612 ----
      return skipcomm();
  }
  
+ /* Check whether we're looking at valid numeric globbing syntax      *
+  * (/\<[0-9]*-[0-9]*\>/).  Call pointing just after the opening "<". *
+  * Leaves the input in the same place, returning 0 or 1.             */
+ 
  /**/
+ static int
+ isnumglob(void)
+ {
+     int c, ec = '-', ret = 0;
+     int tbs = 256, n = 0;
+     char *tbuf = (char *)zalloc(tbs);
+ 
+     while(1) {
+ 	c = hgetc();
+ 	if(lexstop) {
+ 	    lexstop = 0;
+ 	    break;
+ 	}
+ 	tbuf[n++] = c;
+ 	if(!idigit(c)) {
+ 	    if(c != ec)
+ 		break;
+ 	    if(ec == '>') {
+ 		ret = 1;
+ 		break;
+ 	    }
+ 	    ec = '>';
+ 	}
+ 	if(n == tbs)
+ 	    tbuf = (char *)realloc(tbuf, tbs *= 2);
+     }
+     while(n--)
+ 	hungetc(tbuf[n]);
+     zfree(tbuf, tbs);
+     return ret;
+ }
+ 
+ /**/
  int
  gettok(void)
  {
***************
*** 719,759 ****
  	if (!incmdpos && d == '(') {
  	    hungetc(d);
  	    lexstop = 0;
  	    break;
  	}
! 	if (d == '>')
  	    peek = INOUTANG;
- 	else if (idigit(d) || d == '-') {
- 	    int tbs = 256, n = 0, nc;
- 	    char *tbuf, *tbp, *ntb;
- 
- 	    tbuf = tbp = (char *)zalloc(tbs);
- 	    hungetc(d);
- 
- 	    while ((nc = hgetc()) && !lexstop) {
- 		if (!idigit(nc) && nc != '-')
- 		    break;
- 		*tbp++ = (char)nc;
- 		if (++n == tbs) {
- 		    ntb = (char *)realloc(tbuf, tbs *= 2);
- 		    tbp += ntb - tbuf;
- 		    tbuf = ntb;
- 		}
- 	    }
- 	    if (nc == '>' && !lexstop) {
- 		hungetc(nc);
- 		while (n--)
- 		    hungetc(*--tbp);
- 		zfree(tbuf, tbs);
- 		break;
- 	    }
- 	    if (nc && !lexstop)
- 		hungetc(nc);
- 	    lexstop = 0;
- 	    while (n--)
- 		hungetc(*--tbp);
- 	    zfree(tbuf, tbs);
- 	    peek = INANG;
  	} else if (d == '<') {
  	    int e = hgetc();
  
--- 756,770 ----
  	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();
  
***************
*** 770,781 ****
  		lexstop = 0;
  		peek = DINANG;
  	    }
! 	} else if (d == '&')
  	    peek = INANGAMP;
! 	else {
! 	    peek = INANG;
  	    hungetc(d);
! 	    lexstop = 0;
  	}
  	tokfd = peekfd;
  	return peek;
--- 781,793 ----
  		lexstop = 0;
  		peek = DINANG;
  	    }
! 	} else if (d == '&') {
  	    peek = INANGAMP;
! 	} else {
  	    hungetc(d);
! 	    if(isnumglob())
! 		goto unpeekfd;
! 	    peek = INANG;
  	}
  	tokfd = peekfd;
  	return peek;
***************
*** 783,789 ****
  	d = hgetc();
  	if (d == '(') {
  	    hungetc(d);
! 	    break;
  	} else if (d == '&') {
  	    d = hgetc();
  	    if (d == '!' || d == '|')
--- 795,801 ----
  	d = hgetc();
  	if (d == '(') {
  	    hungetc(d);
! 	    goto unpeekfd;
  	} else if (d == '&') {
  	    d = hgetc();
  	    if (d == '!' || d == '|')
***************
*** 1056,1084 ****
  	    if (isset(SHGLOB) && sub)
  		break;
  	    e = hgetc();
! 	    if (!(idigit(e) || e == '-' || (e == '(' && intpos))) {
! 		hungetc(e);
! 		lexstop = 0;
! 		if (in_brace_param || sub)
! 		    break;
! 		goto brk;
! 	    }
! 	    c = Inang;
! 	    if (e == '(') {
! 		add(c);
  		if (skipcomm()) {
  		    peek = LEXERR;
  		    goto brk;
  		}
  		c = Outpar;
! 	    } else {
! 		add(c);
! 		c = e;
! 		while (c != '>' && !lexstop)
! 		    add(c), c = hgetc();
  		c = Outang;
  	    }
! 	    break;
  	case LX2_EQUALS:
  	    if (intpos) {
  		e = hgetc();
--- 1068,1094 ----
  	    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();
Index: Src/pattern.c
===================================================================
RCS file: /cvsroot/zsh/zsh/Src/pattern.c,v
retrieving revision 1.2
diff -c -r1.2 pattern.c
*** Src/pattern.c	2000/04/01 20:49:48	1.2
--- Src/pattern.c	2000/04/04 01:11:37
***************
*** 989,1002 ****
  		patparse = nptr;
  		len |= 1;
  	    }
! 	    if (*patparse == '-') {
! 		patparse++;
! 		if (idigit(*patparse)) {
! 		    to = (zrange_t) zstrtol((char *)patparse,
! 					      (char **)&nptr, 10);
! 		    patparse = nptr;
! 		    len |= 2;
! 		}
  	    }
  	    if (*patparse != Outang)
  		return 0;
--- 989,1001 ----
  		patparse = nptr;
  		len |= 1;
  	    }
! 	    DPUTS(*patparse != '-', "BUG: - missing from numeric glob");
! 	    patparse++;
! 	    if (idigit(*patparse)) {
! 		to = (zrange_t) zstrtol((char *)patparse,
! 					  (char **)&nptr, 10);
! 		patparse = nptr;
! 		len |= 2;
  	    }
  	    if (*patparse != Outang)
  		return 0;
END