From: Peter Stephenson <pws@csr.com>
To: zsh-workers@sunsite.dk (Zsh hackers list)
Subject: Re: PATCH: bad patterns in ${var[(r)...]}
Date: Fri, 13 Apr 2007 12:49:19 +0100 [thread overview]
Message-ID: <20070413124919.84a17746.pws@csr.com> (raw)
In-Reply-To: <200704131121.l3DBLDAu010461@news01.csr.com>
Peter Stephenson <pws@csr.com> wrote:
> A reverse match of a parameter index with a bad pattern always retrieves
> the first element: see the test added to D04parameter.ztst. Presumably
> it should return the empty string as if the pattern didn't match.
Second attempt.
> Under these circumstances ${var[(I)...]} would return 0. You *could*
> argue that ${var[(r)...]} is just the value at the index given by
> ${var[(I)...]}, which, as 0 is mapped to 1, is what's happening at the
> moment.
However, that's inconsistent with the case where the pattern was OK
but matching failed, which is what I'm trying to make it like. So
I don't think that argument works at all.
> I think the patch below handles this without breaking anything else
> (certainly nothing that isn't obscure, since the parameter tests are
> fairly comprehensive).
The obscure case I broke was ${var[(I)...]} for a bad pattern, which
returned 1 instead of 0. I've augmented the test.
> It may not be the simplest change, however---it ought to be possible to
> treat the case exactly as a failed match instead of using a separate
> flag, but I didn't follow through all the logic for that.
I've done this the simple mechanical way of testing pprog before each
use of pattry(). That's not very efficient in this one special case, but I
don't think this is something that needs optimising. It's pretty much
guaranteed to work. Er... I think.
Index: Src/params.c
===================================================================
RCS file: /cvsroot/zsh/zsh/Src/params.c,v
retrieving revision 1.123
diff -u -r1.123 params.c
--- Src/params.c 8 Feb 2007 10:43:30 -0000 1.123
+++ Src/params.c 13 Apr 2007 11:43:53 -0000
@@ -954,7 +954,7 @@
int *prevcharlen, int *nextcharlen)
{
int hasbeg = 0, word = 0, rev = 0, ind = 0, down = 0, l, i, ishash;
- int keymatch = 0, needtok = 0, arglen;
+ int keymatch = 0, needtok = 0, arglen, len;
char *s = *str, *sep = NULL, *t, sav, *d, **ta, **p, *tt, c;
zlong num = 1, beg = 0, r = 0;
Patprog pprog = NULL;
@@ -1237,267 +1237,265 @@
if (!keymatch) {
tokenize(s);
remnulargs(s);
- }
-
- if (keymatch || (pprog = patcompile(s, 0, NULL))) {
- int len;
+ pprog = patcompile(s, 0, NULL);
+ } else
+ pprog = NULL;
- if (v->isarr) {
- if (ishash) {
- scanprog = pprog;
- scanstr = s;
- if (keymatch)
- v->isarr |= SCANPM_KEYMATCH;
- else if (ind)
- v->isarr |= SCANPM_MATCHKEY;
- else
- v->isarr |= SCANPM_MATCHVAL;
- if (down)
- v->isarr |= SCANPM_MATCHMANY;
- if ((ta = getvaluearr(v)) &&
- (*ta || ((v->isarr & SCANPM_MATCHMANY) &&
- (v->isarr & (SCANPM_MATCHKEY | SCANPM_MATCHVAL |
- SCANPM_KEYMATCH))))) {
- *inv = v->inv;
- *w = v->end;
- return 1;
+ if (v->isarr) {
+ if (ishash) {
+ scanprog = pprog;
+ scanstr = s;
+ if (keymatch)
+ v->isarr |= SCANPM_KEYMATCH;
+ else if (ind)
+ v->isarr |= SCANPM_MATCHKEY;
+ else
+ v->isarr |= SCANPM_MATCHVAL;
+ if (down)
+ v->isarr |= SCANPM_MATCHMANY;
+ if ((ta = getvaluearr(v)) &&
+ (*ta || ((v->isarr & SCANPM_MATCHMANY) &&
+ (v->isarr & (SCANPM_MATCHKEY | SCANPM_MATCHVAL |
+ SCANPM_KEYMATCH))))) {
+ *inv = v->inv;
+ *w = v->end;
+ return 1;
+ }
+ } else
+ ta = getarrvalue(v);
+ if (!ta || !*ta)
+ return 0;
+ len = arrlen(ta);
+ if (beg < 0)
+ beg += len;
+ if (beg >= 0 && beg < len) {
+ if (down) {
+ if (!hasbeg)
+ beg = len - 1;
+ for (r = 1 + beg, p = ta + beg; p >= ta; r--, p--) {
+ if (pprog && pattry(pprog, *p) && !--num)
+ return r;
}
} else
- ta = getarrvalue(v);
- if (!ta || !*ta)
- return 0;
- len = arrlen(ta);
- if (beg < 0)
- beg += len;
- if (beg >= 0 && beg < len) {
- if (down) {
- if (!hasbeg)
- beg = len - 1;
- for (r = 1 + beg, p = ta + beg; p >= ta; r--, p--) {
- if (pattry(pprog, *p) && !--num)
- return r;
- }
- } else
- for (r = 1 + beg, p = ta + beg; *p; r++, p++)
- if (pattry(pprog, *p) && !--num)
- return r;
+ for (r = 1 + beg, p = ta + beg; *p; r++, p++)
+ if (pprog && pattry(pprog, *p) && !--num)
+ return r;
+ }
+ } else if (word) {
+ ta = sepsplit(d = s = getstrvalue(v), sep, 1, 1);
+ len = arrlen(ta);
+ if (beg < 0)
+ beg += len;
+ if (beg >= 0 && beg < len) {
+ if (down) {
+ if (!hasbeg)
+ beg = len - 1;
+ for (r = 1 + beg, p = ta + beg; p >= ta; p--, r--)
+ if (pprog && pattry(pprog, *p) && !--num)
+ break;
+ if (p < ta)
+ return 0;
+ } else {
+ for (r = 1 + beg, p = ta + beg; *p; r++, p++)
+ if (pprog && pattry(pprog, *p) && !--num)
+ break;
+ if (!*p)
+ return 0;
}
- } else if (word) {
- ta = sepsplit(d = s = getstrvalue(v), sep, 1, 1);
- len = arrlen(ta);
- if (beg < 0)
- beg += len;
- if (beg >= 0 && beg < len) {
+ }
+ if (a2)
+ r++;
+ for (i = 0; (t = findword(&d, sep)) && *t; i++)
+ if (!--r) {
+ r = (zlong)(t - s + (a2 ? -1 : 1));
+ if (!a2 && *tt != ',')
+ *w = r + strlen(ta[i]) - 1;
+ return r;
+ }
+ return a2 ? -1 : 0;
+ } else {
+ /* Searching characters */
+ int slen;
+ d = getstrvalue(v);
+ if (!d || !*d)
+ return 0;
+ /*
+ * beg and len are character counts, not raw offsets.
+ * Remember we need to return a raw offset.
+ */
+ len = MB_METASTRLEN(d);
+ slen = strlen(d);
+ if (beg < 0)
+ beg += len;
+ MB_METACHARINIT();
+ if (beg >= 0 && beg < len) {
+ char *de = d + slen;
+
+ if (a2) {
+ /*
+ * Second argument: we don't need to
+ * handle prevcharlen or nextcharlen, but
+ * we do need to handle characters appropriately.
+ */
if (down) {
+ int nmatches = 0;
+ char *lastpos = NULL;
+
if (!hasbeg)
- beg = len - 1;
- for (r = 1 + beg, p = ta + beg; p >= ta; p--, r--)
- if (pattry(pprog, *p) && !--num)
- break;
- if (p < ta)
- return 0;
- } else {
- for (r = 1 + beg, p = ta + beg; *p; r++, p++)
- if (pattry(pprog, *p) && !--num)
- break;
- if (!*p)
- return 0;
- }
- }
- if (a2)
- r++;
- for (i = 0; (t = findword(&d, sep)) && *t; i++)
- if (!--r) {
- r = (zlong)(t - s + (a2 ? -1 : 1));
- if (!a2 && *tt != ',')
- *w = r + strlen(ta[i]) - 1;
- return r;
- }
- return a2 ? -1 : 0;
- } else {
- /* Searching characters */
- int slen;
- d = getstrvalue(v);
- if (!d || !*d)
- return 0;
- /*
- * beg and len are character counts, not raw offsets.
- * Remember we need to return a raw offset.
- */
- len = MB_METASTRLEN(d);
- slen = strlen(d);
- if (beg < 0)
- beg += len;
- MB_METACHARINIT();
- if (beg >= 0 && beg < len) {
- char *de = d + slen;
+ beg = len;
- if (a2) {
/*
- * Second argument: we don't need to
- * handle prevcharlen or nextcharlen, but
- * we do need to handle characters appropriately.
+ * See below: we have to move forward,
+ * but need to count from the end.
*/
- if (down) {
- int nmatches = 0;
- char *lastpos = NULL;
-
- if (!hasbeg)
- beg = len;
-
- /*
- * See below: we have to move forward,
- * but need to count from the end.
- */
- for (t = d, r = 0; r <= beg; r++) {
- sav = *t;
- *t = '\0';
- if (pattry(pprog, d)) {
- nmatches++;
- lastpos = t;
- }
- *t = sav;
- if (t == de)
- break;
- t += MB_METACHARLEN(t);
+ for (t = d, r = 0; r <= beg; r++) {
+ sav = *t;
+ *t = '\0';
+ if (pprog && pattry(pprog, d)) {
+ nmatches++;
+ lastpos = t;
}
+ *t = sav;
+ if (t == de)
+ break;
+ t += MB_METACHARLEN(t);
+ }
- if (nmatches >= num) {
- if (num > 1) {
- nmatches -= num;
- MB_METACHARINIT();
- for (t = d, r = 0; ; r++) {
- sav = *t;
- *t = '\0';
- if (pattry(pprog, d) &&
- nmatches-- == 0) {
- lastpos = t;
- *t = sav;
- break;
- }
+ if (nmatches >= num) {
+ if (num > 1) {
+ nmatches -= num;
+ MB_METACHARINIT();
+ for (t = d, r = 0; ; r++) {
+ sav = *t;
+ *t = '\0';
+ if (pprog && pattry(pprog, d) &&
+ nmatches-- == 0) {
+ lastpos = t;
*t = sav;
- t += MB_METACHARLEN(t);
+ break;
}
- }
- /* else lastpos is already OK */
-
- return lastpos - d;
- }
- } else {
- /*
- * This handling of the b flag
- * gives odd results, but this is the
- * way it's always worked.
- */
- for (t = d; beg && t <= de; beg--)
- t += MB_METACHARLEN(t);
- for (;;) {
- sav = *t;
- *t = '\0';
- if (pattry(pprog, d) && !--num) {
*t = sav;
- /*
- * This time, don't increment
- * pointer, since it's already
- * after everything we matched.
- */
- return t - d;
+ t += MB_METACHARLEN(t);
}
- *t = sav;
- if (t == de)
- break;
- t += MB_METACHARLEN(t);
}
+ /* else lastpos is already OK */
+
+ return lastpos - d;
}
} else {
/*
- * First argument: this is the only case
- * where we need prevcharlen and nextcharlen.
+ * This handling of the b flag
+ * gives odd results, but this is the
+ * way it's always worked.
*/
- int lastcharlen;
+ for (t = d; beg && t <= de; beg--)
+ t += MB_METACHARLEN(t);
+ for (;;) {
+ sav = *t;
+ *t = '\0';
+ if (pprog && pattry(pprog, d) && !--num) {
+ *t = sav;
+ /*
+ * This time, don't increment
+ * pointer, since it's already
+ * after everything we matched.
+ */
+ return t - d;
+ }
+ *t = sav;
+ if (t == de)
+ break;
+ t += MB_METACHARLEN(t);
+ }
+ }
+ } else {
+ /*
+ * First argument: this is the only case
+ * where we need prevcharlen and nextcharlen.
+ */
+ int lastcharlen;
- if (down) {
- int nmatches = 0;
- char *lastpos = NULL;
-
- if (!hasbeg)
- beg = len;
-
- /*
- * We can only move forward through
- * multibyte strings, so record the
- * matches.
- * Unfortunately the count num works
- * from the end, so it's easy to get the
- * last one but we need to repeat if
- * we want another one.
- */
- for (t = d, r = 0; r <= beg; r++) {
- if (pattry(pprog, t)) {
- nmatches++;
- lastpos = t;
- }
- if (t == de)
- break;
- t += MB_METACHARLEN(t);
+ if (down) {
+ int nmatches = 0;
+ char *lastpos = NULL;
+
+ if (!hasbeg)
+ beg = len;
+
+ /*
+ * We can only move forward through
+ * multibyte strings, so record the
+ * matches.
+ * Unfortunately the count num works
+ * from the end, so it's easy to get the
+ * last one but we need to repeat if
+ * we want another one.
+ */
+ for (t = d, r = 0; r <= beg; r++) {
+ if (pprog && pattry(pprog, t)) {
+ nmatches++;
+ lastpos = t;
}
+ if (t == de)
+ break;
+ t += MB_METACHARLEN(t);
+ }
- if (nmatches >= num) {
- if (num > 1) {
- /*
- * Need to start again and repeat
- * to get the right match.
- */
- nmatches -= num;
- MB_METACHARINIT();
- for (t = d, r = 0; ; r++) {
- if (pattry(pprog, t) &&
- nmatches-- == 0) {
- lastpos = t;
- break;
- }
- t += MB_METACHARLEN(t);
+ if (nmatches >= num) {
+ if (num > 1) {
+ /*
+ * Need to start again and repeat
+ * to get the right match.
+ */
+ nmatches -= num;
+ MB_METACHARINIT();
+ for (t = d, r = 0; ; r++) {
+ if (pprog && pattry(pprog, t) &&
+ nmatches-- == 0) {
+ lastpos = t;
+ break;
}
+ t += MB_METACHARLEN(t);
}
- /* else lastpos is already OK */
+ }
+ /* else lastpos is already OK */
+
+ /* return pointer after matched char */
+ lastpos +=
+ (lastcharlen = MB_METACHARLEN(lastpos));
+ if (prevcharlen)
+ *prevcharlen = lastcharlen;
+ if (nextcharlen)
+ *nextcharlen = MB_METACHARLEN(lastpos);
+ return lastpos - d;
+ }
+ for (r = beg + 1, t = d + beg; t >= d; r--, t--) {
+ if (pprog && pattry(pprog, t) &&
+ !--num)
+ return r;
+ }
+ } else {
+ for (t = d; beg && t <= de; beg--)
+ t += MB_METACHARLEN(t);
+ for (;;) {
+ if (pprog && pattry(pprog, t) && !--num) {
/* return pointer after matched char */
- lastpos +=
- (lastcharlen = MB_METACHARLEN(lastpos));
+ t += (lastcharlen = MB_METACHARLEN(t));
if (prevcharlen)
*prevcharlen = lastcharlen;
if (nextcharlen)
- *nextcharlen = MB_METACHARLEN(lastpos);
- return lastpos - d;
- }
-
- for (r = beg + 1, t = d + beg; t >= d; r--, t--) {
- if (pattry(pprog, t) &&
- !--num)
- return r;
- }
- } else {
- for (t = d; beg && t <= de; beg--)
- t += MB_METACHARLEN(t);
- for (;;) {
- if (pattry(pprog, t) && !--num) {
- /* return pointer after matched char */
- t += (lastcharlen = MB_METACHARLEN(t));
- if (prevcharlen)
- *prevcharlen = lastcharlen;
- if (nextcharlen)
- *nextcharlen = MB_METACHARLEN(t);
- return t - d;
- }
- if (t == de)
- break;
- t += MB_METACHARLEN(t);
+ *nextcharlen = MB_METACHARLEN(t);
+ return t - d;
}
+ if (t == de)
+ break;
+ t += MB_METACHARLEN(t);
}
}
}
- return down ? 0 : slen + 1;
}
+ return down ? 0 : slen + 1;
}
}
return r;
Index: Test/D04parameter.ztst
===================================================================
RCS file: /cvsroot/zsh/zsh/Test/D04parameter.ztst,v
retrieving revision 1.24
diff -u -r1.24 D04parameter.ztst
--- Test/D04parameter.ztst 21 Jan 2007 22:47:42 -0000 1.24
+++ Test/D04parameter.ztst 13 Apr 2007 11:43:53 -0000
@@ -903,3 +903,13 @@
>6100620061
>6100620062
>610063
+
+ array=(X)
+ patterns=("*X*" "spong" "a[b")
+ for pat in $patterns; do
+ print A${array[(r)$pat]}B C${array[(I)$pat]}D
+ done
+0:Bad patterns should never match array elements
+>AXB C1D
+>AB C0D
+>AB C0D
--
Peter Stephenson <pws@csr.com> Software Engineer
CSR PLC, Churchill House, Cambridge Business Park, Cowley Road
Cambridge, CB4 0WZ, UK Tel: +44 (0)1223 692070
To access the latest news from CSR copy this link into a web browser: http://www.csr.com/email_sig.php
To get further information regarding CSR, please visit our Investor Relations page at http://ir.csr.com/csr/about/overview
prev parent reply other threads:[~2007-04-13 11:50 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-13 11:21 Peter Stephenson
2007-04-13 11:49 ` Peter Stephenson [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20070413124919.84a17746.pws@csr.com \
--to=pws@csr.com \
--cc=zsh-workers@sunsite.dk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://git.vuxu.org/mirror/zsh/
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).