optimization for subquery and function scan nodes: we can't just do it
unconditionally, we still have to check whether there is any need for
a whole-row Var.  I had been thinking that these node types couldn't
have any system columns, which is true, but that loop is also checking
for attno zero, ie, whole-row Var.  Fix comment to not be so misleading.
Per test case from Richard Huxton.

Per request from Marc.

replace use of predefined perl vars $a and $b with $x and $y - per Greg Sabino Mullane

possibility of a failure due to stack overflow when max_stack_depth is
not set properly for the platform.

fix problems with replacement-string backslashes that aren't followed by
one of the expected characters, avoid giving the impression that
replace_text_regexp() is meant to be called directly as a SQL function,
etc.

avoid leaking memory.  I would add a regression test for error handling
except it seems eval{} can't be used in unprivileged plperl :-(

if there isn't one already open. Upon dblink_close, only commit
the open transaction if it was started by dblink_open, and only
then when all cursors opened by dblink_open are closed. The transaction
accounting is done individually for all named connections, plus
the persistent unnamed connection.

when not using gcc (which has slightly nonstandard inclusion rules).

by a recent HP C compiler.  Mostly, get rid of useless local variables
that are assigned to but never used.

exported routines of ip.c, md5.c, and fe-auth.c to begin with 'pg_'.
Also get rid of the vestigial fe_setauthsvc/fe_getauthsvc routines
altogether.

of 4096.  Also add comment explaining why we don't suggest using
/etc/sysctl.conf to avoid needing to edit /etc/rc.

Euler Taveira de Oliveira

Fedora).  This was already done by somebody for the core flex files,
but these contrib files seem to have been missed.

or at any rate doesn't belong as a comment in a random SGML file.

rather than British. Patch from Michael Fuhr.

to determine whether fread() failed.

documentation. Mostly add some <xref>s, fix a few typos, and
document that zlib is required in the installation docs.

the facility has been set, the facility gets set to LOCAL0 and cannot
be changed later.  This seems reasonably plausible to happen, particularly
at higher debug log levels, though I am not certain it explains Han Holl's
recent report.  Easiest fix is to teach the code how to change the value
on-the-fly, which is nicer anyway.  I made the settings PGC_SIGHUP to
conform with log_destination.

of GUC memory doesn't cause us to start emitting a bogus ident string.
Per report from Han Holl.  Also some trivial code cleanup in write_syslog.

	regression=# select '23:59:59.9'::time(0);
	   time
	----------
	 24:00:00
	(1 row)

	This is bad because:

	regression=# select '24:00:00'::time(0);
	ERROR:  date/time field value out of range: "24:00:00"

The last example now works.

for the PL languages and for contrib.

etc. match the docs, which talk about "transaction identifier" not
"gid" or "global transaction identifier".

Steve Woodcock

'localhost'.

Improve kerberos error message.

affected types of objects.

direction of writing triggers in a procedural language, rather than C.
Per discussion.

of client_min_messages (fatal + panic) are valid and also fixes a slight
issue with how psql tried to display error messages that aren't sent to
the client.

We often tell people to ignore errors in response to requests for things
like "drop if exists", but there's no good way to completely hide this
without upping client_min_messages past ERROR.  When running a file like

SET client_min_messages TO 'FATAL';

DROP TABLE doesntexist;

with "psql -f filename" you get an error prefix of
"psql:/home/username/filename:3" even though there is no error message to
prefix because it isn't sent to the client.

Kris Jurka