From: Phil Pennock <zsh-workers+phil.pennock@spodhuis.org>
To: zsh-workers@zsh.org
Cc: Peter Stephenson <Peter.Stephenson@csr.com>
Subject: Re: UTF-8 and PCRE and metafy
Date: Fri, 21 Oct 2011 06:35:30 -0400 [thread overview]
Message-ID: <20111021103530.GA78708@redoubt.spodhuis.org> (raw)
In-Reply-To: <20111021095624.GA23272@redoubt.spodhuis.org>
[-- Attachment #1: Type: text/plain, Size: 308 bytes --]
On 2011-10-21 at 05:56 -0400, Phil Pennock wrote:
> Attached is what looks to me to be a correct patch. With bash_rematch
Oops, for the change around line 292, I switched to a new variable but
never called unmetafy().
One line added in the attached patch, which replaces the previous patch.
Sorry,
-Phil
[-- Attachment #2: pcre-utf8.patch --]
[-- Type: text/x-diff, Size: 5837 bytes --]
Index: Src/Modules/pcre.c
===================================================================
RCS file: /home/cvsroot/zsh/Src/Modules/pcre.c,v
retrieving revision 1.18
diff -a -u -p -r1.18 pcre.c
--- Src/Modules/pcre.c 20 Jan 2010 11:17:11 -0000 1.18
+++ Src/Modules/pcre.c 21 Oct 2011 10:29:14 -0000
@@ -77,6 +77,7 @@ bin_pcre_compile(char *nam, char **args,
{
int pcre_opts = 0, pcre_errptr;
const char *pcre_error;
+ char *target;
if(OPT_ISSET(ops,'a')) pcre_opts |= PCRE_ANCHORED;
if(OPT_ISSET(ops,'i')) pcre_opts |= PCRE_CASELESS;
@@ -92,8 +93,13 @@ bin_pcre_compile(char *nam, char **args,
if (pcre_pattern)
pcre_free(pcre_pattern);
- pcre_pattern = pcre_compile(*args, pcre_opts, &pcre_error, &pcre_errptr, NULL);
+ target = ztrdup(*args);
+ unmetafy(target, NULL);
+
+ pcre_pattern = pcre_compile(target, pcre_opts, &pcre_error, &pcre_errptr, NULL);
+ free(target);
+
if (pcre_pattern == NULL)
{
zwarnnam(nam, "error in regex: %s", pcre_error);
@@ -161,7 +167,7 @@ zpcre_get_substrings(char *arg, int *ove
sprintf(offset_all, "%d %d", ovec[0], ovec[1]);
setsparam("ZPCRE_OP", ztrdup(offset_all));
}
- match_all = ztrdup(captures[0]);
+ match_all = metafy(captures[0], -1, META_DUP);
setsparam(matchvar, match_all);
/*
* If we're setting match, mbegin, mend we only do
@@ -169,7 +175,15 @@ zpcre_get_substrings(char *arg, int *ove
* (c.f. regex.c).
*/
if (!want_begin_end || nelem) {
- matches = zarrdup(&captures[capture_start]);
+ char **x, **y;
+ y = &captures[capture_start];
+ matches = x = (char **) zalloc(sizeof(char *) * (arrlen(y) + 1));
+ do {
+ if (*y)
+ *x++ = metafy(*y, -1, META_DUP);
+ else
+ *x++ = NULL;
+ } while (*y++);
setaparam(substravar, matches);
}
@@ -255,6 +269,7 @@ bin_pcre_match(char *nam, char **args, O
{
int ret, capcount, *ovec, ovecsize, c;
char *matched_portion = NULL;
+ char *plaintext = NULL;
char *receptacle = NULL;
int return_value = 1;
/* The subject length and offset start are both int values in pcre_exec */
@@ -278,7 +293,7 @@ bin_pcre_match(char *nam, char **args, O
}
/* For the entire match, 'Return' the offset byte positions instead of the matched string */
if(OPT_ISSET(ops,'b')) want_offset_pair = 1;
-
+
if(!*args) {
zwarnnam(nam, "not enough arguments");
}
@@ -288,26 +303,28 @@ bin_pcre_match(char *nam, char **args, O
zwarnnam(nam, "error %d in fullinfo", ret);
return 1;
}
-
+
ovecsize = (capcount+1)*3;
ovec = zalloc(ovecsize*sizeof(int));
-
- subject_len = (int)strlen(*args);
+
+ plaintext = ztrdup(*args);
+ unmetafy(plaintext, NULL);
+ subject_len = (int)strlen(plaintext);
if (offset_start < 0 || offset_start >= subject_len)
ret = PCRE_ERROR_NOMATCH;
else
- ret = pcre_exec(pcre_pattern, pcre_hints, *args, subject_len, offset_start, 0, ovec, ovecsize);
+ ret = pcre_exec(pcre_pattern, pcre_hints, plaintext, subject_len, offset_start, 0, ovec, ovecsize);
if (ret==0) return_value = 0;
else if (ret==PCRE_ERROR_NOMATCH) /* no match */;
else if (ret>0) {
- zpcre_get_substrings(*args, ovec, ret, matched_portion, receptacle,
+ zpcre_get_substrings(plaintext, ovec, ret, matched_portion, receptacle,
want_offset_pair, 0, 0);
return_value = 0;
}
else {
- zwarnnam(nam, "error in pcre_exec");
+ zwarnnam(nam, "error in pcre_exec [%d]", ret);
}
if (ovec)
@@ -322,7 +339,8 @@ cond_pcre_match(char **a, int id)
{
pcre *pcre_pat;
const char *pcre_err;
- char *lhstr, *rhre, *avar=NULL;
+ char *lhstr, *rhre, *lhstr_plain, *rhre_plain, *avar=NULL;
+ char *p;
int r = 0, pcre_opts = 0, pcre_errptr, capcnt, *ov, ovsize;
int return_value = 0;
@@ -331,6 +349,10 @@ cond_pcre_match(char **a, int id)
lhstr = cond_str(a,0,0);
rhre = cond_str(a,1,0);
+ lhstr_plain = ztrdup(lhstr);
+ rhre_plain = ztrdup(rhre);
+ unmetafy(lhstr_plain, NULL);
+ unmetafy(rhre_plain, NULL);
pcre_pat = NULL;
ov = NULL;
@@ -339,7 +361,7 @@ cond_pcre_match(char **a, int id)
switch(id) {
case CPCRE_PLAIN:
- pcre_pat = pcre_compile(rhre, pcre_opts, &pcre_err, &pcre_errptr, NULL);
+ pcre_pat = pcre_compile(rhre_plain, pcre_opts, &pcre_err, &pcre_errptr, NULL);
if (pcre_pat == NULL) {
zwarn("failed to compile regexp /%s/: %s", rhre, pcre_err);
break;
@@ -347,7 +369,7 @@ cond_pcre_match(char **a, int id)
pcre_fullinfo(pcre_pat, NULL, PCRE_INFO_CAPTURECOUNT, &capcnt);
ovsize = (capcnt+1)*3;
ov = zalloc(ovsize*sizeof(int));
- r = pcre_exec(pcre_pat, NULL, lhstr, strlen(lhstr), 0, 0, ov, ovsize);
+ r = pcre_exec(pcre_pat, NULL, lhstr_plain, strlen(lhstr_plain), 0, 0, ov, ovsize);
/* r < 0 => error; r==0 match but not enough size in ov
* r > 0 => (r-1) substrings found; r==1 => no substrings
*/
@@ -356,13 +378,16 @@ cond_pcre_match(char **a, int id)
return_value = 1;
break;
}
- else if (r==PCRE_ERROR_NOMATCH) return 0; /* no match */
+ else if (r==PCRE_ERROR_NOMATCH) {
+ return_value = 0; /* no match */
+ break;
+ }
else if (r<0) {
- zwarn("pcre_exec() error: %d", r);
+ zwarn("pcre_exec() error [%d]", r);
break;
}
else if (r>0) {
- zpcre_get_substrings(lhstr, ov, r, NULL, avar, 0,
+ zpcre_get_substrings(lhstr_plain, ov, r, NULL, avar, 0,
isset(BASHREMATCH),
!isset(BASHREMATCH));
return_value = 1;
@@ -371,6 +396,10 @@ cond_pcre_match(char **a, int id)
break;
}
+ if (lhstr_plain)
+ free(lhstr_plain);
+ if(rhre_plain)
+ free(rhre_plain);
if (pcre_pat)
pcre_free(pcre_pat);
if (ov)
next prev parent reply other threads:[~2011-10-21 10:35 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-03-08 6:52 Phil Pennock
2011-03-08 8:19 ` Bart Schaefer
2011-03-08 9:58 ` Peter Stephenson
2011-10-21 9:56 ` [patch] " Phil Pennock
2011-10-21 10:35 ` Phil Pennock [this message]
2011-10-23 16:32 ` Peter Stephenson
2011-10-24 11:35 ` Phil Pennock
2011-10-24 11:43 ` Peter Stephenson
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=20111021103530.GA78708@redoubt.spodhuis.org \
--to=zsh-workers+phil.pennock@spodhuis.org \
--cc=Peter.Stephenson@csr.com \
--cc=zsh-workers@zsh.org \
/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).