> * -Prevent to_char() on interval from returning meaningless values

Fix to_char(interval) to return large year/month/day/hour values that
are larger than possible timestamp values.
Prevent to_char(interval) format specifications that make no sense, like
Month.
Clean up formatting.c code to more logically handle return lengths.

AbortTransaction.  This can happen if a backend's InitPostgres transaction
fails (eg, because the given username is invalid).  Per Alvaro.

integer with flags.

max_fsm_relations.

Run autoconf/autoheader in case someone forgot in the past.

anyway, and in assert-enabled builds you are likely to get an assertion
failure.  Backpatch as far as 7.3; 7.2 seems not to have the problem.

and creation columns to behave for Unix or Win32.

caused PL languages and handlers to be dumped ALWAYS, even in the face
of contrary --schema or --table switches.  Adopt a slightly saner
definition.

by forcing search_path to be just pg_catalog.

their OID parameter.  It was possible to crash the backend with
select array_in('{123}',0,0); because that would bypass the needed step
of initializing the workspace.  These seem to be the only two places
with a problem, though (record_in and record_recv don't have the issue,
and the other array functions aren't depending on user-supplied input).
Back-patch as far as 7.4; 7.3 does not have the bug.

working state, not fcinfo->context.  Silly oversight on my part in last
go-round of fixes.

(the stats system has always collected this info, but the views were
filtering it out).  Modify autovacuum so that over-threshold activity
in a toast table can trigger a VACUUM of the parent table, even if the
parent didn't appear to need vacuuming itself.  Per discussion a month
or so back about "short, wide tables".

so that it will correctly dump owners of objects owned by non-login roles.

they don't miss owners that are NOLOGIN.

other stuff; change \du and \dg to be role-aware (Stefan Kaltenbrunner).
Also make tab completion fetch the list of GUC variables from pg_settings
instead of having a hard-wired copy of the list (Tom Lane).

SearchCatCacheList and ReleaseCatCacheList.  Previously, we incremented
and decremented the refcounts of list member tuples along with the list
itself, but that's unnecessary, and very expensive when the list is big.
It's cheaper to change only the list refcount.  When we are considering
deleting a cache entry, we have to check not only its own refcount but
its parent list's ... but it's easy to arrange the code so that this
check is not made in any commonly-used paths, so the cost is really nil.
The bigger gain though is to refrain from DLMoveToFront'ing each individual
member tuple each time the list is referenced.  To keep some semblance
of fair space management, lists are just marked as used or not since the
last cache cleanout search, and we do a MoveToFront pass only when about
to run a cleanout.  In combination, these changes reduce the costs of
SearchCatCacheList and ReleaseCatCacheList from about 4.5% of pgbench
runtime to under 1%, according to my gprof results.

remember the output parameter set for himself.  It's a bit of a kluge
but fixing array_in to work in bootstrap mode looks worse.
I removed the separate pg_file_length() function, as it no longer has any
real notational advantage --- you can write (pg_stat_file(...)).length.

Marko Kreen

Alvaro.

the pubkey functions a bit.  The actual RSA-specific code
there is tiny, most of the patch consists of reorg of the
pubkey code, as lots of it was written as elgamal-only.

---------------------------------------------------------------------------

The SHLIB section was copy-pasted from somewhere and contains
several unnecessary libs.  This cleans it up a bit.

 -lcrypt
   we don't use system crypt()

 -lssl, -lssleay32
   no SSL here

 -lz in win32 section
   already added on previous line

 -ldes
   The chance anybody has it is pretty low.
   And the chance pgcrypto works with it is even lower.

Also trim the win32 section.

---------------------------------------------------------------------------

It is already disabled in Makefile, remove code too.

---------------------------------------------------------------------------

I was bit hasty making the random exponent 'k' a prime.  Further researh
shows that Elgamal encryption has no specific needs in respect to k,
any random number is fine.

It is bit different for signing, there it needs to be 'relatively prime'
to p - 1,  that means GCD(k, p-1) == 1, which is also a lot lighter than
full primality.  As we don't do signing, this can be ignored.

This brings major speedup to Elgamal encryption.

---------------------------------------------------------------------------

o  pgp_mpi_free: Accept NULLs
o  pgp_mpi_cksum: result should be 16bit
o  Remove function name from error messages - to be similar to other
   SQL functions, and it does not match anyway the called function
o  remove couple junk lines

---------------------------------------------------------------------------

o  Support for RSA encryption
o  Big reorg to better separate generic and algorithm-specific code.
o  Regression tests for RSA.

---------------------------------------------------------------------------

o  Tom stuck a CVS id into file.  I doubt the usefulness of it,
   but if it needs to be in the file then rather at the end.
   Also tag it as comment for asciidoc.
o  Mention bytea vs. text difference
o  Couple clarifications

---------------------------------------------------------------------------

There is a choice whether to update it with pgp functions or
remove it.  I decided to remove it, updating is pointless.

I've tried to keep the core of pgcrypto relatively independent
from main PostgreSQL, to make it easy to use externally if needed,
and that is good.  Eg. that made development of PGP functions much
nicer.

But I have no plans to release it as generic library, so keeping such
doc
up-to-date is waste of time.  If anyone is interested in using it in
other products, he can probably bother to read the source too.

Commented source is another thing - I'll try to make another pass
over code to see if there is anything non-obvious that would need
more comments.

---------------------------------------------------------------------------

Marko Kreen

>>>I think a more accurate description would be "permissions not
>>>inherited by children," and that isn't necessarily a bug.
>>
>>I agree it may not be a bug - but it's more than the permissions not
>>being inherited: the parent is affected.
>
>
> Not really, once you understand what's happening.  Unless you use
> FROM ONLY, selecting from the parent selects from the parent *and*
> its children.  The parent itself isn't affected, as queries with
> FROM ONLY should demonstrate.  I understand what you're saying --
> that there's an apparent effect on the parent -- but there really
> isn't.

Sean Burlington

and it isn't really required.

only composite types as we did in 8.0.  Per discussion with Martijn
van Oosterhout.

David Fetter

stderr-in-service or output-from-syslogger-in-service code. Previously
everything was flagged as ERRORs there, which caused all instances to
log "LOG: logger shutting down" as error...

Please apply for 8.1. I'd also like it considered for 8.0 since logging
non-errors as errors can be cause for alarm amongst people who actually
look at their logs...

Magnus Hagander