OSDN Git Service
Tom Lane [Mon, 11 Sep 2006 15:14:46 +0000 (15:14 +0000)]
Rename the uninstall scripts for contrib/lo and contrib/tsearch2 to
match the convention that foo's uninstall script is uninstall_foo.sql.
Also, stop installing lo_test.sql, which really ought to be made into
a regression test anyway (though it's unclear how to avoid a dependency
on the current OID counter...)
Tom Lane [Mon, 11 Sep 2006 13:35:08 +0000 (13:35 +0000)]
Add LDAP_LIBS_FE to $(libpq) for static or AIX linking, per Albe Laurenz.
Tom Lane [Mon, 11 Sep 2006 02:50:07 +0000 (02:50 +0000)]
Ooops, forgot to update ecpg comparison files to match
source-code change.
Tom Lane [Mon, 11 Sep 2006 02:10:26 +0000 (02:10 +0000)]
Fix omissions in contrib uninstall scripts. Michael Fuhr
Tom Lane [Mon, 11 Sep 2006 01:41:35 +0000 (01:41 +0000)]
Fix unportable usage complained of by icc. Per buildfarm results.
Bruce Momjian [Sun, 10 Sep 2006 23:33:22 +0000 (23:33 +0000)]
Remove unnecessary brace pair.
Bruce Momjian [Sun, 10 Sep 2006 22:54:47 +0000 (22:54 +0000)]
Back out patch added during 8.2.X development:
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).
Bruce Momjian [Sun, 10 Sep 2006 22:20:01 +0000 (22:20 +0000)]
Add items:
< * 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?
Tom Lane [Sun, 10 Sep 2006 22:07:02 +0000 (22:07 +0000)]
Install a cleaner solution to the AIX libpq linking problem, as per
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.
Tom Lane [Sun, 10 Sep 2006 21:38:26 +0000 (21:38 +0000)]
Fix dblink build for --enable-nls or --enable-openssl on AIX.
Per Chris Browne.
Tom Lane [Sun, 10 Sep 2006 20:56:42 +0000 (20:56 +0000)]
Remove unhelpful/misleading advice about how to use SPI_saveplan().
Per gripe from Jack Orenstein.
Tom Lane [Sun, 10 Sep 2006 20:45:17 +0000 (20:45 +0000)]
contrib/isn updates from Jeremy Kronuz.
Tom Lane [Sun, 10 Sep 2006 20:14:20 +0000 (20:14 +0000)]
If we're going to advertise the array overlap/containment operators,
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.
Tom Lane [Sun, 10 Sep 2006 19:03:57 +0000 (19:03 +0000)]
Add missing documentation for new anyarray-overlap operator.
Tom Lane [Sun, 10 Sep 2006 17:36:52 +0000 (17:36 +0000)]
Rename contrib contains/contained-by operators to @> and <@, per discussion.
Tom Lane [Sun, 10 Sep 2006 00:29:35 +0000 (00:29 +0000)]
Rename contains/contained-by operators to @> and <@, per discussion that
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.
Tom Lane [Sat, 9 Sep 2006 18:45:37 +0000 (18:45 +0000)]
Remove reference to contrib/mac, which isn't there anymore.
Tom Lane [Sat, 9 Sep 2006 04:07:52 +0000 (04:07 +0000)]
Add contrib/isn module for ISBN/ISSN/EAN13/etc product numbers, and
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.
Tom Lane [Sat, 9 Sep 2006 03:15:40 +0000 (03:15 +0000)]
Revise OpenLDAP configuration and linking to work on more platforms
than before. Albe Laurenz (but editorialized heavily by me, so if it
doesn't work it's my fault).
Tom Lane [Fri, 8 Sep 2006 18:05:35 +0000 (18:05 +0000)]
Fix pg_dump for recent change removing separate RULE privilege.
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.
Tom Lane [Fri, 8 Sep 2006 17:49:13 +0000 (17:49 +0000)]
Put back plan-time check for trying to apply SELECT FOR UPDATE/SHARE
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 ...
Tom Lane [Fri, 8 Sep 2006 15:55:53 +0000 (15:55 +0000)]
Tweak the behavior of log_duration as proposed by Guillaume Smet: rather
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.
Michael Meskes [Fri, 8 Sep 2006 14:58:27 +0000 (14:58 +0000)]
Not all C compilers understand the "//" comment in this test case, so I removed it.
Michael Meskes [Fri, 8 Sep 2006 13:32:29 +0000 (13:32 +0000)]
Replaced complex tests with small ones.
Michael Meskes [Fri, 8 Sep 2006 09:03:40 +0000 (09:03 +0000)]
More logic from complex/test* moved to their own testcases.
Tom Lane [Thu, 7 Sep 2006 22:52:01 +0000 (22:52 +0000)]
Clean up logging for extended-query-protocol operations, as per my recent
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.
Bruce Momjian [Thu, 7 Sep 2006 18:13:56 +0000 (18:13 +0000)]
Update pgcvslog comments.
Bruce Momjian [Thu, 7 Sep 2006 15:37:25 +0000 (15:37 +0000)]
Specify lo_write() to take a _const_ buffer, to match documentation.
Michael Meskes [Thu, 7 Sep 2006 11:18:47 +0000 (11:18 +0000)]
Changing a test case also changes the output that is expected.
Float/Long aliasing doesn't work on all architecures.
Michael Meskes [Thu, 7 Sep 2006 08:15:58 +0000 (08:15 +0000)]
Removed one output because integer/double usage differ
Bruce Momjian [Thu, 7 Sep 2006 00:12:20 +0000 (00:12 +0000)]
HTLM cleanup.
Bruce Momjian [Thu, 7 Sep 2006 00:10:46 +0000 (00:10 +0000)]
Update Emacs/vim editor info.
Bruce Momjian [Thu, 7 Sep 2006 00:08:43 +0000 (00:08 +0000)]
Update emacs info for FAQ_DEV.
Andrew Dunstan
Bruce Momjian [Thu, 7 Sep 2006 00:04:48 +0000 (00:04 +0000)]
Add XML documentation.
Bruce Momjian [Wed, 6 Sep 2006 22:03:22 +0000 (22:03 +0000)]
Update tools directory name.
Tom Lane [Wed, 6 Sep 2006 20:40:48 +0000 (20:40 +0000)]
Change processing of extended-Query mode so that an unnamed statement
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.
Tom Lane [Wed, 6 Sep 2006 18:30:17 +0000 (18:30 +0000)]
Be more wary about which LIBS elements to pull into sslinfo link.
Per buildfarm results.
Teodor Sigaev [Wed, 6 Sep 2006 07:22:14 +0000 (07:22 +0000)]
Fix compiler warnings on 64-bit boxes: difference between
pointers are int64, but warnings are emitted for position info in
error messages in parser, so, just cast it to int32
Bruce Momjian [Wed, 6 Sep 2006 02:05:41 +0000 (02:05 +0000)]
Add interval division/multiplication regression tests.
Michael Glaesemann
Tom Lane [Tue, 5 Sep 2006 23:15:02 +0000 (23:15 +0000)]
Fix sslinfo so it builds on Darwin.
Tom Lane [Tue, 5 Sep 2006 23:07:16 +0000 (23:07 +0000)]
Silence compiler warning about signed vs unsigned chars.
Tom Lane [Tue, 5 Sep 2006 23:02:28 +0000 (23:02 +0000)]
Silence compiler warnings about incompatible function pointer types.
Tom Lane [Tue, 5 Sep 2006 21:26:48 +0000 (21:26 +0000)]
Remove pgcrypto functions that were deprecated and slated for removal.
Marko Kreen
Tom Lane [Tue, 5 Sep 2006 21:08:36 +0000 (21:08 +0000)]
Get rid of the separate RULE privilege for tables: now only a table's owner
can create or modify rules for the table. Do setRuleCheckAsUser() while
loading rules into the relcache, rather than when defining a rule. This
ensures that permission checks for tables referenced in a rule are done with
respect to the current owner of the rule's table, whereas formerly ALTER TABLE
OWNER would fail to update the permission checking for associated rules.
Removal of separate RULE privilege is needed to prevent various scenarios
in which a grantee of RULE privilege could effectively have any privilege
of the table owner. For backwards compatibility, GRANT/REVOKE RULE is still
accepted, but it doesn't do anything. Per discussion here:
http://archives.postgresql.org/pgsql-hackers/2006-04/msg01138.php
Tom Lane [Tue, 5 Sep 2006 19:18:13 +0000 (19:18 +0000)]
Make Gen_fmgrtab.sh locale-proof. Per report from Marko Kreen and
fix suggestion from Peter.
Teodor Sigaev [Tue, 5 Sep 2006 18:39:08 +0000 (18:39 +0000)]
Fix markup and license.
Teodor Sigaev [Tue, 5 Sep 2006 18:25:10 +0000 (18:25 +0000)]
Fix Intel compiler bug. Per discussion
'GIN FailedAssertions on Itanium2 with Intel compiler' in pgsql-hackers,
http://archives.postgresql.org/pgsql-hackers/2006-08/msg01914.php
Teodor Sigaev [Tue, 5 Sep 2006 18:00:58 +0000 (18:00 +0000)]
Add hstore contrib module.
Per discussion
http://archives.postgresql.org/pgsql-hackers/2006-08/msg01409.php
Tom Lane [Tue, 5 Sep 2006 17:20:29 +0000 (17:20 +0000)]
Remove contrib modules that have been migrated to pgfoundry: adddepend,
dbase, dbmirror, fulltextindex, mac, userlock; or abandoned: mSQL-interface,
tips.
Michael Meskes [Tue, 5 Sep 2006 12:17:09 +0000 (12:17 +0000)]
Lost some changes yet again
Michael Meskes [Tue, 5 Sep 2006 12:11:03 +0000 (12:11 +0000)]
Started to cleanup complex tests.
Added some interval checks to regression suite.
Michael Meskes [Tue, 5 Sep 2006 10:00:53 +0000 (10:00 +0000)]
Synced parser.
Fixed ecpglib trying to read one character after end-of-string.
Fixed port number setting in regression suite.
Bruce Momjian [Tue, 5 Sep 2006 03:09:56 +0000 (03:09 +0000)]
Remove GIN documentation
Christopher Kings-Lynne
Bruce Momjian [Tue, 5 Sep 2006 01:13:40 +0000 (01:13 +0000)]
Fix imprecision from interval rounding of multiplication/division.
Bruce, Michael Glaesemann
Bruce Momjian [Tue, 5 Sep 2006 00:13:41 +0000 (00:13 +0000)]
Update Japanese FAQ.
Jun Kuwamura
Tom Lane [Mon, 4 Sep 2006 23:13:01 +0000 (23:13 +0000)]
Fix information_schema.key_column_usage to show correct value of
position_in_unique_constraint (column newly added per SQL2003).
Greg Mullane
Tom Lane [Mon, 4 Sep 2006 22:22:36 +0000 (22:22 +0000)]
Bring sslinfo Makefile up to speed for VPATH and pgxs builds.
Bruce Momjian [Mon, 4 Sep 2006 21:47:25 +0000 (21:47 +0000)]
Update setseed() documentation.
Bruce Momjian [Mon, 4 Sep 2006 21:43:18 +0000 (21:43 +0000)]
Update LDAP installation wording.
Albe Laurenz
Bruce Momjian [Mon, 4 Sep 2006 21:40:23 +0000 (21:40 +0000)]
Trivial patch to double vacuum speed on tables with no indexes (prevent
second scan of table).
Gregory Stark
Bruce Momjian [Mon, 4 Sep 2006 21:30:40 +0000 (21:30 +0000)]
Add MSVC build tools.
Magnus Hagander
Tom Lane [Mon, 4 Sep 2006 21:15:56 +0000 (21:15 +0000)]
Disallow TRUNCATE when there are any pending after-trigger events for
the target relation(s). There might be some cases where we could discard
the pending event instead, but for the moment a conservative approach
seems sufficient. Per report from Markus Schiltknecht and subsequent
discussion.
Bruce Momjian [Mon, 4 Sep 2006 21:03:18 +0000 (21:03 +0000)]
Sequences were not being shown due to the use of lowercase 's' instead
of 'S', and the views were not checking for table visibility with
regards to temporary tables and sequences.
Greg Sabino Mullane
Bruce Momjian [Mon, 4 Sep 2006 20:10:53 +0000 (20:10 +0000)]
Add GIN documentation.
Christopher Kings-Lynne
Bruce Momjian [Mon, 4 Sep 2006 19:58:02 +0000 (19:58 +0000)]
Mention paremeterized queries do not work with partial indexes.
Simon Riggs
Bruce Momjian [Mon, 4 Sep 2006 19:36:21 +0000 (19:36 +0000)]
Remove trailing slash use in ecpg regression script; caused failures on
some platforms.
Tom Lane [Mon, 4 Sep 2006 18:32:55 +0000 (18:32 +0000)]
Change ILIKE to invoke lower() and then do plain LIKE comparison when
working in a multibyte encoding. This fixes the problems exhibited in
bug #1931 and other reports of ILIKE misbehavior in UTF8 encoding.
It's a pretty grotty solution though --- should rethink how to do it
after we install better locale support, someday.
Peter Eisentraut [Mon, 4 Sep 2006 15:07:46 +0000 (15:07 +0000)]
sslinfo contrib module - information about current SSL certificate
Author: Victor Wagner <vitus@cryptocom.ru>
Peter Eisentraut [Mon, 4 Sep 2006 14:57:27 +0000 (14:57 +0000)]
Add missing gettext calls for some SSL errors.
Bruce Momjian [Mon, 4 Sep 2006 03:49:05 +0000 (03:49 +0000)]
Update Japanese readme for pgstattuple.
Tom Lane [Mon, 4 Sep 2006 02:03:04 +0000 (02:03 +0000)]
Clean up some leftover problems in pgstattuple: remove unwanted and
unportable elog(NOTICE) report, fix install/uninstall sequence.
Itagaki Takahiro
Tom Lane [Mon, 4 Sep 2006 01:26:28 +0000 (01:26 +0000)]
Fix interval input parser so that fractional weeks and months are
cascaded first to days and only what is leftover into seconds. This
seems to satisfy the principle of least surprise given the general
conversion to three-part interval values --- it was an oversight that
these cases weren't dealt with in 8.1. Michael Glaesemann
Tom Lane [Sun, 3 Sep 2006 22:37:06 +0000 (22:37 +0000)]
Code review for UPDATE SET (columnlist) patch. Make it handle as much
of the syntax as this fundamentally dead-end approach can, in particular
combinations of single and multi column assignments. Improve rather
inadequate documentation and provide some regression tests.
Tom Lane [Sun, 3 Sep 2006 22:23:58 +0000 (22:23 +0000)]
Remove duplicated index entry.
Tom Lane [Sun, 3 Sep 2006 22:15:32 +0000 (22:15 +0000)]
Fix broken markup.
Tom Lane [Sun, 3 Sep 2006 19:30:43 +0000 (19:30 +0000)]
Suppress 'unused variable' warnings created by latest commit.
Tom Lane [Sun, 3 Sep 2006 19:06:15 +0000 (19:06 +0000)]
Fix non-improvement of description of archive_timeout. archive_command
is only invoked on completed WAL segments, period --- there's no 'by
default' about it.
Tom Lane [Sun, 3 Sep 2006 15:59:39 +0000 (15:59 +0000)]
Arrange for GetSnapshotData to copy live-subtransaction XIDs from the
PGPROC array into snapshots, and use this information to avoid visits
to pg_subtrans in HeapTupleSatisfiesSnapshot. This appears to solve
the pg_subtrans-related context swap storm problem that's been reported
by several people for 8.1. While at it, modify GetSnapshotData to not
take an exclusive lock on ProcArrayLock, as closer analysis shows that
shared lock is always sufficient.
Itagaki Takahiro and Tom Lane
Bruce Momjian [Sun, 3 Sep 2006 13:37:38 +0000 (13:37 +0000)]
Remove:
< * Change LIMIT/OFFSET and FETCH/MOVE to use int8
Michael Meskes [Sun, 3 Sep 2006 12:24:08 +0000 (12:24 +0000)]
Synced parser.
Added another regression test and fixed tcp test.
Bruce Momjian [Sun, 3 Sep 2006 03:34:04 +0000 (03:34 +0000)]
Properly round months into days and into seconds for interval
multiplication/division queries like select '41 mon 10:00:00'::interval
/ 10 as "pos".
Report from Michael Glaesemann
Bruce Momjian [Sun, 3 Sep 2006 03:26:42 +0000 (03:26 +0000)]
Reverted:
< * -Change LIMIT/OFFSET and FETCH/MOVE to use int8
> * Change LIMIT/OFFSET and FETCH/MOVE to use int8
Bruce Momjian [Sun, 3 Sep 2006 03:19:45 +0000 (03:19 +0000)]
Revert FETCH/MOVE int64 patch. Was using incorrect checks for
fetch/move in scan.l.
Bruce Momjian [Sun, 3 Sep 2006 01:59:09 +0000 (01:59 +0000)]
Update predicate locking text.
Bruce Momjian [Sun, 3 Sep 2006 01:22:56 +0000 (01:22 +0000)]
Fix case where "PM" to_timestamp() mask was eating too many characters.
Report from Josh Tolley.
Bruce Momjian [Sun, 3 Sep 2006 01:15:40 +0000 (01:15 +0000)]
Fix LLONG_MAX define used by new int64 FETCH/MOVE patch.
Bruce Momjian [Sun, 3 Sep 2006 00:46:41 +0000 (00:46 +0000)]
Remove unnecessary copyObject() call in update (values) code.
Bruce Momjian [Sat, 2 Sep 2006 23:47:39 +0000 (23:47 +0000)]
Add:
> * Simplify ability to create partitioned tables
>
> This would allow creation of partitioned tables without requiring
> creation of rules for INSERT/UPDATE/DELETE, and constraints for
> rapid partition selection. Options could include range and hash
> partition selection.
>
> * Allow auto-selection of partitioned tables for min/max() operations
Bruce Momjian [Sat, 2 Sep 2006 23:12:16 +0000 (23:12 +0000)]
Make autovacuum behavior more agressive, per discussion on hackers list
--- was part of autovacuum default 'on' patch that was reverted, but we
want this part.
Peter Eisentraut
Bruce Momjian [Sat, 2 Sep 2006 23:08:36 +0000 (23:08 +0000)]
Update postgresql.conf line for default superuser_reserved_connections.
Bruce Momjian [Sat, 2 Sep 2006 23:04:20 +0000 (23:04 +0000)]
Change "superuser_reserved_connections" default to 3, because of
possible autovacuum use.
Bruce Momjian [Sat, 2 Sep 2006 22:59:00 +0000 (22:59 +0000)]
Add URL for autovacuum default:
>
> http://archives.postgresql.org/pgsql-hackers/2006-08/msg01852.php
Bruce Momjian [Sat, 2 Sep 2006 22:03:30 +0000 (22:03 +0000)]
Use '' rather than \' for literal single quotes in strings in
/contrib/tsearch2.
Teodor Sigaev
Bruce Momjian [Sat, 2 Sep 2006 21:11:26 +0000 (21:11 +0000)]
Wording improvements for archive_timeout.
Joe Conway [Sat, 2 Sep 2006 21:11:15 +0000 (21:11 +0000)]
Added async query capability. Original patch by
Kai Londenberg, modified by Joe Conway
Bruce Momjian [Sat, 2 Sep 2006 20:52:01 +0000 (20:52 +0000)]
Small code cleanup for recent UPDATE SET (values) patch.
Bruce Momjian [Sat, 2 Sep 2006 20:34:47 +0000 (20:34 +0000)]
Add UPDATE tab SET ROW (col, ...) = (val, ...) for updating
multiple columns
Susanne Ebrecht
Bruce Momjian [Sat, 2 Sep 2006 20:31:50 +0000 (20:31 +0000)]
Update:
< Last updated: Sat Sep 2 08:31:04 EDT 2006
> Last updated: Sat Sep 2 16:31:46 EDT 2006
< o Allow UPDATE tab SET ROW (col, ...) = (...) for updating multiple
< columns
> o -Allow UPDATE tab SET ROW (col, ...) = (val, ...) for updating
> multiple columns
> o Allow UPDATE tab SET ROW (col, ...) = (SELECT...)
< A subselect can also be used as the value source.
Bruce Momjian [Sat, 2 Sep 2006 18:17:18 +0000 (18:17 +0000)]
Change FETCH/MOVE to use int8.
Dhanaraj M
Bruce Momjian [Sat, 2 Sep 2006 17:10:17 +0000 (17:10 +0000)]
Revert as not needed/inconsistent with SQL REINDEX:
Suppress some NOTICE messages from REINDEX command.
Euler Taveira de Oliveira