Allow to_char() "D" format specifiers for interval/time.

It doesn't work, and I doubt it is useful enough to fix ("D" = day of
week).

< * Research storing disk pages with no alignment/padding
> * Consider ways of storing rows more compactly on disk
>
> 	o Store disk pages with no alignment/padding?
> 	o Reorder physical storage order to reduce padding?
> 	o Support a smaller header for short variable-length fields?
> 	o Reduce the row header size?

an earlier discussion.  Centralize assumptions about what libpq depends
on in one place in Makefile.global.  I am unconvinced that this list
is complete, but since ecpg seems to have gotten along with just these
entries, we'll try it this way and see what happens.

Per Chris Browne.

Per gripe from Jack Orenstein.

we probably should make them work reliably for all arrays.  Fix code
to handle NULLs and multidimensional arrays, move it into arrayfuncs.c.
GIN is still restricted to indexing arrays with no null elements, however.

agreed these symbols are less easily confused.  I made new pg_operator
entries (with new OIDs) for the old names, so as to provide backward
compatibility while making it pretty easy to remove the old names in
some future release cycle.  This commit only touches the core datatypes,
contrib will be fixed separately.

remove the old isbn_issn module which is about to be obsoleted by EAN13.
contrib/isn is by Germán Méndez Bravo.  Our thanks to Garrett A. Wollman
for having written the original isbn_issn module.

than before.  Albe Laurenz (but editorialized heavily by me, so if it
doesn't work it's my fault).

I had thought this code could be left alone, but I was wrong: as-is
it's failing to recognize when to use ALL for table privileges in 8.2.

to a relation on the nullable side of an outer join.  I had removed
this during the outer join planning rewrite a few months ago ... I think
I intended to put it somewhere else, but forgot ...

than being equivalent to setting log_min_duration_statement to zero, this
option now forces logging of all query durations, but doesn't force logging
of query text.  Also, add duration logging coverage for fastpath function
calls.

proposal.  Parameter logging works even for binary-format parameters, and
logging overhead is avoided when disabled.

log_statement = all output for the src/test/examples/testlibpq3.c example
now looks like

LOG:  statement: execute <unnamed>: SELECT * FROM test1 WHERE t = $1
DETAIL:  parameters: $1 = 'joe''s place'
LOG:  statement: execute <unnamed>: SELECT * FROM test1 WHERE i = $1::int4
DETAIL:  parameters: $1 = '2'

and log_min_duration_statement = 0 results in

LOG:  duration: 2.431 ms  parse <unnamed>: SELECT * FROM test1 WHERE t = $1
LOG:  duration: 2.335 ms  bind <unnamed> to <unnamed>: SELECT * FROM test1 WHERE t = $1
DETAIL:  parameters: $1 = 'joe''s place'
LOG:  duration: 0.394 ms  execute <unnamed>: SELECT * FROM test1 WHERE t = $1
DETAIL:  parameters: $1 = 'joe''s place'
LOG:  duration: 1.251 ms  parse <unnamed>: SELECT * FROM test1 WHERE i = $1::int4
LOG:  duration: 0.566 ms  bind <unnamed> to <unnamed>: SELECT * FROM test1 WHERE i = $1::int4
DETAIL:  parameters: $1 = '2'
LOG:  duration: 0.173 ms  execute <unnamed>: SELECT * FROM test1 WHERE i = $1::int4
DETAIL:  parameters: $1 = '2'

(This example demonstrates the folly of ignoring parse/bind steps for duration
logging purposes, BTW.)

Along the way, create a less ad-hoc mechanism for determining which commands
are logged by log_statement = mod and log_statement = ddl.  The former coding
was actually missing quite a few things that look like ddl to me, and it
did not handle EXECUTE or extended query protocol correctly at all.

This commit does not do anything about the question of whether log_duration
should be removed or made less redundant with log_min_duration_statement.

Float/Long aliasing doesn't work on all architecures.

Andrew Dunstan

that has parameters is always planned afresh for each Bind command,
treating the parameter values as constants in the planner.  This removes
the performance penalty formerly often paid for using out-of-line
parameters --- with this definition, the planner can do constant folding,
LIKE optimization, etc.  After a suggestion by Andrew@supernews.

Per buildfarm results.

pointers are int64, but warnings are emitted for position info in
error messages in parser, so, just cast it to int32

Michael Glaesemann

Marko Kreen