OSDN Git Service

pg-rex/syncrep.git
18 years agoSmall cleanup.
Bruce Momjian [Thu, 25 Aug 2005 00:38:37 +0000 (00:38 +0000)]
Small cleanup.

18 years agoUpdate release checklist.
Bruce Momjian [Thu, 25 Aug 2005 00:30:10 +0000 (00:30 +0000)]
Update release checklist.

18 years agoAdd code to use Windows getaddrinfo and friends if they exist. This
Tom Lane [Wed, 24 Aug 2005 22:13:23 +0000 (22:13 +0000)]
Add code to use Windows getaddrinfo and friends if they exist.  This
has to be tested dynamically if we want to make portable executables.
Chuck McDevitt and Andrew Dunstan.

18 years agoPreliminary pass at release note editing.
Tom Lane [Wed, 24 Aug 2005 22:03:14 +0000 (22:03 +0000)]
Preliminary pass at release note editing.

18 years agofix up a few references to 8.1devel -> 8.1beta1
PostgreSQL Daemon [Wed, 24 Aug 2005 21:32:41 +0000 (21:32 +0000)]
fix up a few references to 8.1devel -> 8.1beta1

18 years agoRemove statement that to_char(interval) is deprecated; seems we are
Tom Lane [Wed, 24 Aug 2005 20:49:35 +0000 (20:49 +0000)]
Remove statement that to_char(interval) is deprecated; seems we are
going to keep it after all.

18 years agoRemove sentence:
Bruce Momjian [Wed, 24 Aug 2005 20:34:05 +0000 (20:34 +0000)]
Remove sentence:

<    Logically, a reload should set the same values as a
<           server restart.

18 years agoBack off allow_nonpic_in_shlib for FreeBSD builds: only set it on i386.
Tom Lane [Wed, 24 Aug 2005 20:20:38 +0000 (20:20 +0000)]
Back off allow_nonpic_in_shlib for FreeBSD builds: only set it on i386.
This might be overly conservative, but we know it does not work on amd64.
Per buildfarm results.

18 years agoUpdate:
Bruce Momjian [Wed, 24 Aug 2005 19:43:26 +0000 (19:43 +0000)]
Update:

<           Currently, if a variable is commented out, it keeps the
<           previous uncommented value until a server restarted.
>    Currently, if a variable is commented out, it keeps the
>    previous uncommented value until a server restarted.
>    Logically, a reload should set the same values as a
>           server restart.

18 years agoRun spellchecker over release notes.
Bruce Momjian [Wed, 24 Aug 2005 19:41:33 +0000 (19:41 +0000)]
Run spellchecker over release notes.

18 years agoMore beta1 cleanup.
Bruce Momjian [Wed, 24 Aug 2005 19:34:34 +0000 (19:34 +0000)]
More beta1 cleanup.

18 years agoFix SHOW and RESET grammar to accept custom variable names.
Tom Lane [Wed, 24 Aug 2005 19:34:12 +0000 (19:34 +0000)]
Fix SHOW and RESET grammar to accept custom variable names.

18 years agoSuggest markup items for the future.
Bruce Momjian [Wed, 24 Aug 2005 19:31:46 +0000 (19:31 +0000)]
Suggest markup items for the future.

18 years agoMake the plperl regression tests pass in 'use_strict' mode, by adding
Tom Lane [Wed, 24 Aug 2005 19:24:54 +0000 (19:24 +0000)]
Make the plperl regression tests pass in 'use_strict' mode, by adding
'my' where appropriate.  Michael Fuhr

18 years agoUpdate release notes for beta1.
Bruce Momjian [Wed, 24 Aug 2005 19:24:20 +0000 (19:24 +0000)]
Update release notes for beta1.

18 years agoMention BEGIN { strict->import(); } as a substitute for 'use strict'
Tom Lane [Wed, 24 Aug 2005 19:16:49 +0000 (19:16 +0000)]
Mention BEGIN { strict->import(); } as a substitute for 'use strict'
in plperl functions.

18 years agoGet rid of inappropriate use of croak(). Per report from Michael Fuhr.
Tom Lane [Wed, 24 Aug 2005 19:06:28 +0000 (19:06 +0000)]
Get rid of inappropriate use of croak().  Per report from Michael Fuhr.

18 years agoAdjust description of use_strict parameter. Some other minor editorial
Tom Lane [Wed, 24 Aug 2005 18:56:07 +0000 (18:56 +0000)]
Adjust description of use_strict parameter.  Some other minor editorial
cleanup.

18 years agoFix broken markup.
Tom Lane [Wed, 24 Aug 2005 18:26:36 +0000 (18:26 +0000)]
Fix broken markup.

18 years agoFix up plperl 'use_strict' so that it can be enabled or disabled on the
Tom Lane [Wed, 24 Aug 2005 18:16:58 +0000 (18:16 +0000)]
Fix up plperl 'use_strict' so that it can be enabled or disabled on the
fly.  Fix problem with incompletely duplicated setup code.  Andrew Dunstan,
from an idea of Michael Fuhr's.

18 years agoAdditem:
Bruce Momjian [Wed, 24 Aug 2005 17:56:20 +0000 (17:56 +0000)]
Additem:

> * Add sleep() function, remove from regress.c

18 years agoAdd small hack to support use of Unicode-based locales on WIN32. This
Tom Lane [Wed, 24 Aug 2005 17:50:00 +0000 (17:50 +0000)]
Add small hack to support use of Unicode-based locales on WIN32.  This
is not adequately tested yet, but let's get it into beta1 so it can be
tested.  Magnus Hagander and Tom Lane.

18 years agoFix ExecBRDeleteTriggers so that deletion is not suppressed when delete
Tom Lane [Wed, 24 Aug 2005 17:38:35 +0000 (17:38 +0000)]
Fix ExecBRDeleteTriggers so that deletion is not suppressed when delete
triggers exist but are all disabled.  Problem noted by Gavin Sherry in
original discussion of enable/disable trigger patch, but was never
addressed.

18 years agoAdd documentation for ALTER TABLE ENABLE/DISABLE TRIGGER.
Tom Lane [Wed, 24 Aug 2005 17:24:19 +0000 (17:24 +0000)]
Add documentation for ALTER TABLE ENABLE/DISABLE TRIGGER.

18 years agoAdd:
Bruce Momjian [Wed, 24 Aug 2005 16:49:39 +0000 (16:49 +0000)]
Add:

>  o Add sleep() to PL/PgSQL

18 years agoAdd to release notes.
Bruce Momjian [Wed, 24 Aug 2005 16:47:00 +0000 (16:47 +0000)]
Add to release notes.

18 years agoFix broken markup.
Tom Lane [Wed, 24 Aug 2005 15:35:01 +0000 (15:35 +0000)]
Fix broken markup.

18 years agoUpdate release notes.
Bruce Momjian [Wed, 24 Aug 2005 14:35:26 +0000 (14:35 +0000)]
Update release notes.

18 years agoFix typo.
Bruce Momjian [Wed, 24 Aug 2005 14:24:19 +0000 (14:24 +0000)]
Fix typo.

18 years agoMark "easy" items.
Bruce Momjian [Wed, 24 Aug 2005 14:05:37 +0000 (14:05 +0000)]
Mark "easy" items.

Jim C. Nasby

18 years agoUpdate:
Bruce Momjian [Wed, 24 Aug 2005 14:00:36 +0000 (14:00 +0000)]
Update:
<  o Do VACUUM FULL if table is nearly empty?
>  o Suggest VACUUM FULL if a table is nearly empty

18 years agoAdd explaination:
Bruce Momjian [Wed, 24 Aug 2005 13:57:27 +0000 (13:57 +0000)]
Add explaination:

>
>           Currently, if a variable is commented out, it keeps the
>           previous uncommented value until a server restarted.
>

18 years ago - Check for NULL before checking whether argument is an array.
Michael Meskes [Wed, 24 Aug 2005 10:34:19 +0000 (10:34 +0000)]
    - Check for NULL before checking whether argument is an array.
        - Remove stary character from string quoting.
        - Fixed check to report missing varchar pointer implementation.

18 years agoRemove periods on bullet items.
Bruce Momjian [Wed, 24 Aug 2005 03:47:11 +0000 (03:47 +0000)]
Remove periods on bullet items.

18 years agoMark item as complete, add another:
Bruce Momjian [Tue, 23 Aug 2005 23:51:18 +0000 (23:51 +0000)]
Mark item as complete, add another:

< * Allow triggers to be disabled [trigger]
> * -Allow triggers to be disabled [trigger]
> * Allow triggers to be disabled in only the current session.
<   Currently the only way to disable triggers is to modify the system
<   tables.
>   This is currently possible by starting a multi-statement transaction,
>   modifying the system tables, performing the desired SQL, restoring the
>   system tables, and committing the transaction.  ALTER TABLE ...
>   TRIGGER requires a table lock so it is not idea for this usage.

18 years agoRelease note cleanups.
Bruce Momjian [Tue, 23 Aug 2005 23:31:52 +0000 (23:31 +0000)]
Release note cleanups.

18 years agoAdd ALTER TABLE ENABLE/DISABLE TRIGGER commands. Change pg_dump to
Tom Lane [Tue, 23 Aug 2005 22:40:47 +0000 (22:40 +0000)]
Add ALTER TABLE ENABLE/DISABLE TRIGGER commands.  Change pg_dump to
use these instead of its previous hack of changing pg_class.reltriggers.
Documentation is lacking, will add that later.
Patch by Satoshi Nagayasu, review and some extra work by Tom Lane.

18 years agoUpdate pgcrypto items.
Bruce Momjian [Tue, 23 Aug 2005 21:25:56 +0000 (21:25 +0000)]
Update pgcrypto items.

18 years agoUpdate ALTER OWNER description.
Bruce Momjian [Tue, 23 Aug 2005 21:17:15 +0000 (21:17 +0000)]
Update ALTER OWNER description.

18 years agoAdd new file for win32 threading.
Bruce Momjian [Tue, 23 Aug 2005 21:11:22 +0000 (21:11 +0000)]
Add new file for win32 threading.

18 years agoThe attached patch updates the thread test program to run stand-alone on
Bruce Momjian [Tue, 23 Aug 2005 21:02:05 +0000 (21:02 +0000)]
The attached patch updates the thread test program to run stand-alone on
Windows. The test itself is bypassed in configure as discussed, and
libpq has been updated appropriately to allow it to build in thread-safe
mode.

Dave Page

18 years agoFix function name.
Bruce Momjian [Tue, 23 Aug 2005 20:51:27 +0000 (20:51 +0000)]
Fix function name.

18 years agoClean up some very old and crufty code for TID scan planning. Not much
Tom Lane [Tue, 23 Aug 2005 20:49:47 +0000 (20:49 +0000)]
Clean up some very old and crufty code for TID scan planning.  Not much
functional difference really, but make use of stuff added to the planner
since this code was touched last.

18 years agoBack out incorrect commit.
Bruce Momjian [Tue, 23 Aug 2005 20:48:47 +0000 (20:48 +0000)]
Back out incorrect commit.

18 years agoFix function name.
Bruce Momjian [Tue, 23 Aug 2005 20:45:11 +0000 (20:45 +0000)]
Fix function name.

18 years agoUpdate release notes.
Bruce Momjian [Tue, 23 Aug 2005 19:44:58 +0000 (19:44 +0000)]
Update release notes.

18 years agoMore release note updates.
Bruce Momjian [Tue, 23 Aug 2005 14:54:06 +0000 (14:54 +0000)]
More release note updates.

18 years agoFix broken lrand48() implementation, per Merlin Moncure.
Tom Lane [Tue, 23 Aug 2005 13:31:11 +0000 (13:31 +0000)]
Fix broken lrand48() implementation, per Merlin Moncure.

18 years agoRelease note updates.
Bruce Momjian [Tue, 23 Aug 2005 12:47:30 +0000 (12:47 +0000)]
Release note updates.

18 years agoRelease note updates.
Bruce Momjian [Tue, 23 Aug 2005 12:46:35 +0000 (12:46 +0000)]
Release note updates.

18 years agoAvoid bullets in subparagraphs.
Bruce Momjian [Tue, 23 Aug 2005 12:14:33 +0000 (12:14 +0000)]
Avoid bullets in subparagraphs.

18 years agoFix markup for para.
Bruce Momjian [Tue, 23 Aug 2005 11:59:09 +0000 (11:59 +0000)]
Fix markup for para.

18 years agoAdjust SGML so major feature items are all not in a single subparagraph.
Bruce Momjian [Tue, 23 Aug 2005 11:53:33 +0000 (11:53 +0000)]
Adjust SGML so major feature items are all not in a single subparagraph.

18 years agoUpdate release notes from community comments.
Bruce Momjian [Tue, 23 Aug 2005 11:32:33 +0000 (11:32 +0000)]
Update release notes from community comments.

18 years agoUpdate release notes for 8.1.
Bruce Momjian [Tue, 23 Aug 2005 02:57:07 +0000 (02:57 +0000)]
Update release notes for 8.1.

18 years agoFix wrong dependency on owner created by ALTER OPCLASS OWNER.
Tom Lane [Tue, 23 Aug 2005 01:41:30 +0000 (01:41 +0000)]
Fix wrong dependency on owner created by ALTER OPCLASS OWNER.
Per Alvaro.

18 years agoFix SGML sect1-3 alignment in the 8.0.X series.
Bruce Momjian [Tue, 23 Aug 2005 01:22:53 +0000 (01:22 +0000)]
Fix SGML sect1-3 alignment in the 8.0.X series.

18 years agoRewrite gather-write patch into something less obviously bolted on
Tom Lane [Mon, 22 Aug 2005 23:59:04 +0000 (23:59 +0000)]
Rewrite gather-write patch into something less obviously bolted on
after the fact.  Fix bug with incorrect test for whether we are at end
of logfile segment.  Arrange for writes triggered by XLogInsert's
is-cache-more-than-half-full test to synchronize with the cache boundaries,
so that in long transactions we tend to write alternating halves of the
cache rather than randomly chosen portions of it; this saves one more
write syscall per cache load.

18 years agoUpdate documentation that non-super users can now do ALTER OWNER.
Bruce Momjian [Mon, 22 Aug 2005 21:32:01 +0000 (21:32 +0000)]
Update documentation that non-super users can now do ALTER OWNER.

18 years agoBack out incorrect use of E'' escape addition.
Bruce Momjian [Mon, 22 Aug 2005 20:25:03 +0000 (20:25 +0000)]
Back  out incorrect use of E'' escape addition.

18 years agoCause ALTER INDEX OWNER to generate a warning and do nothing, rather than
Tom Lane [Mon, 22 Aug 2005 19:40:37 +0000 (19:40 +0000)]
Cause ALTER INDEX OWNER to generate a warning and do nothing, rather than
erroring out as it has done for the last couple weeks.  Document that this
form is now ignored because indexes can't usefully have different owners
from their parent tables.  Fix pg_dump to not generate ALTER OWNER commands
for indexes.

18 years agoFix unwanted denial of ALTER OWNER rights to superusers. There was some
Tom Lane [Mon, 22 Aug 2005 17:38:20 +0000 (17:38 +0000)]
Fix unwanted denial of ALTER OWNER rights to superusers.  There was some
discussion of getting around this by relaxing the checks made for regular
users, but I'm disinclined to toy with the security model right now,
so just special-case it for superusers where needed.

18 years agoenable_constraint_exclusion => constraint_exclusion
Bruce Momjian [Mon, 22 Aug 2005 17:35:03 +0000 (17:35 +0000)]
enable_constraint_exclusion => constraint_exclusion

Also improve wording.

18 years agoImprove xid wraparound message (the server isn't really shut down, just
Bruce Momjian [Mon, 22 Aug 2005 16:59:47 +0000 (16:59 +0000)]
Improve xid wraparound message (the server isn't really shut down, just
not accepting queries).

         errmsg("database is not accepting queries to avoid
 wraparound data loss in database \"%s\"",
         errhint("Stop the postmaster and use a standalone
 backend to VACUUM database \"%s\".",

18 years agoUse an initdb-time test to see if the local version of getaddrinfo()
Tom Lane [Mon, 22 Aug 2005 16:27:36 +0000 (16:27 +0000)]
Use an initdb-time test to see if the local version of getaddrinfo()
chokes on IPv6 addresses, and comment out the IPv6 entry in the default
pg_hba.conf if so.  Per Andrew Dunstan.

18 years agoFix some inconsistent choices of datatypes in xlog.c. Make buffer
Tom Lane [Mon, 22 Aug 2005 00:41:28 +0000 (00:41 +0000)]
Fix some inconsistent choices of datatypes in xlog.c.  Make buffer
indexes all be int, rather than variously int, uint16 and uint32;
add some casts where necessary to support large buffer arrays.

18 years agoMinor GUC cleanups: document krb_server_hostname and custom_variable_classes
Tom Lane [Sun, 21 Aug 2005 03:39:37 +0000 (03:39 +0000)]
Minor GUC cleanups: document krb_server_hostname and custom_variable_classes
in postgresql.conf.sample, mark custom_variable_classes as SIGHUP not
POSTMASTER to agree with the documentation (I can't see a reason it has
to be POSTMASTER so I think the docs are right).

18 years agoAdd:
Bruce Momjian [Sun, 21 Aug 2005 01:04:45 +0000 (01:04 +0000)]
Add:

> * Fix problems with wrong runtime encoding conversion for NLS message files

18 years agoSeems that the childXids list would be better based on Oid lists than
Tom Lane [Sat, 20 Aug 2005 23:45:08 +0000 (23:45 +0000)]
Seems that the childXids list would be better based on Oid lists than
integer lists.

18 years agoConvert the arithmetic for shared memory size calculation from 'int'
Tom Lane [Sat, 20 Aug 2005 23:26:37 +0000 (23:26 +0000)]
Convert the arithmetic for shared memory size calculation from 'int'
to 'Size' (that is, size_t), and install overflow detection checks in it.
This allows us to remove the former arbitrary restrictions on NBuffers
etc.  It won't make any difference in a 32-bit machine, but in a 64-bit
machine you could theoretically have terabytes of shared buffers.
(How efficiently we could manage 'em remains to be seen.)  Similarly,
num_temp_buffers, work_mem, and maintenance_work_mem can be set above
2Gb on a 64-bit machine.  Original patch from Koichi Suzuki, additional
work by moi.

18 years agoInvoke mksafefunc and mkunsafefunc with :: decoration. This seems a good
Tom Lane [Sat, 20 Aug 2005 19:19:21 +0000 (19:19 +0000)]
Invoke mksafefunc and mkunsafefunc with :: decoration.  This seems a good
idea on consistency grounds, whether or not it really fixes bug #1831.
Michael Fuhr

18 years agoMake GetMultiXactIdMembers() a public function.
Tatsuo Ishii [Sat, 20 Aug 2005 01:29:27 +0000 (01:29 +0000)]
Make GetMultiXactIdMembers() a public function.

18 years agoAdd BackendXidGetPid().
Tatsuo Ishii [Sat, 20 Aug 2005 01:26:36 +0000 (01:26 +0000)]
Add BackendXidGetPid().

18 years agoRepair problems with VACUUM destroying t_ctid chains too soon, and with
Tom Lane [Sat, 20 Aug 2005 00:40:32 +0000 (00:40 +0000)]
Repair problems with VACUUM destroying t_ctid chains too soon, and with
insufficient paranoia in code that follows t_ctid links.  (We must do both
because even with VACUUM doing it properly, the intermediate state with
a dangling t_ctid link is visible concurrently during lazy VACUUM, and
could be seen afterwards if either type of VACUUM crashes partway through.)
Also try to improve documentation about what's going on.  Patch is a bit
bulky because passing the XMAX information around required changing the
APIs of some low-level heapam.c routines, but it's not conceptually very
complicated.  Per trouble report from Teodor and subsequent analysis.
This needs to be back-patched, but I'll do that after 8.1 beta is out.

18 years agoFix LRU/ALL description mismatch for GUC parameter.
Bruce Momjian [Fri, 19 Aug 2005 18:58:18 +0000 (18:58 +0000)]
Fix LRU/ALL description mismatch for GUC parameter.

18 years agoConsistently align comments in postgresql.conf, move some slightly to
Bruce Momjian [Fri, 19 Aug 2005 01:55:18 +0000 (01:55 +0000)]
Consistently align comments in postgresql.conf, move some slightly to
the right to stand out.

18 years agoUpdate some obsolete comments --- code is using t_self now, not t_ctid.
Tom Lane [Thu, 18 Aug 2005 21:34:20 +0000 (21:34 +0000)]
Update some obsolete comments --- code is using t_self now, not t_ctid.

18 years agoFix up LIMIT/OFFSET planning so that we cope with non-constant LIMIT
Tom Lane [Thu, 18 Aug 2005 17:51:12 +0000 (17:51 +0000)]
Fix up LIMIT/OFFSET planning so that we cope with non-constant LIMIT
or OFFSET clauses by using estimate_expression_value().  The main advantage
of this is that if the expression is a Param and we have a value for the
Param, we'll use that value rather than defaulting.  Also, fix some
thinkos in the logic for combining LIMIT/OFFSET with an externally
supplied tuple fraction (this covers cases like EXISTS(...LIMIT...)).
And make sure the results of all this are shown by EXPLAIN.  Per a
gripe from Merlin Moncure.

18 years agoAdd:
Bruce Momjian [Thu, 18 Aug 2005 14:14:31 +0000 (14:14 +0000)]
Add:

>  o Remove unnecessary abstractions in pg_dump source code

18 years agoAdd hint for to_char(interval) invalid format specifications.
Bruce Momjian [Thu, 18 Aug 2005 13:43:08 +0000 (13:43 +0000)]
Add hint for to_char(interval) invalid format specifications.

18 years agoDone:
Bruce Momjian [Thu, 18 Aug 2005 04:42:41 +0000 (04:42 +0000)]
Done:

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

18 years agoFix to_char(interval) to return proper year and century values.
Bruce Momjian [Thu, 18 Aug 2005 04:37:08 +0000 (04:37 +0000)]
Fix to_char(interval) to return proper year and century 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.

18 years agoAvoid an Assert failure if OuterUserId hasn't been set yet during
Tom Lane [Wed, 17 Aug 2005 22:14:34 +0000 (22:14 +0000)]
Avoid an Assert failure if OuterUserId hasn't been set yet during
AbortTransaction.  This can happen if a backend's InitPostgres transaction
fails (eg, because the given username is invalid).  Per Alvaro.

18 years agoMore formatting.c cleanups.
Bruce Momjian [Wed, 17 Aug 2005 22:06:53 +0000 (22:06 +0000)]
More formatting.c cleanups.

18 years agoSmall cleanup.
Bruce Momjian [Wed, 17 Aug 2005 21:54:50 +0000 (21:54 +0000)]
Small cleanup.

18 years agoAdjust to_char/from_char code to use boolean "is_to_char" rather than
Bruce Momjian [Wed, 17 Aug 2005 21:47:55 +0000 (21:47 +0000)]
Adjust to_char/from_char code to use boolean "is_to_char" rather than
integer with flags.

18 years agoRemove unnecessary configure test for inet_ntop(), per Andrew Dunstan.
Tom Lane [Wed, 17 Aug 2005 20:20:10 +0000 (20:20 +0000)]
Remove unnecessary configure test for inet_ntop(), per Andrew Dunstan.

18 years agoFix declaration of dumpacl, per Alvaro.
Tom Lane [Wed, 17 Aug 2005 19:45:51 +0000 (19:45 +0000)]
Fix declaration of dumpacl, per Alvaro.

18 years agoFix FSM warning to mention increasing max_fsm_pages. Was incorrectly
Bruce Momjian [Wed, 17 Aug 2005 03:50:59 +0000 (03:50 +0000)]
Fix FSM warning to mention increasing max_fsm_pages.  Was incorrectly
max_fsm_relations.

18 years agoMinor cleanup.
Bruce Momjian [Wed, 17 Aug 2005 01:45:20 +0000 (01:45 +0000)]
Minor cleanup.

18 years agoUpdate comments.
Bruce Momjian [Tue, 16 Aug 2005 19:29:38 +0000 (19:29 +0000)]
Update comments.

18 years agoImprove comment.
Bruce Momjian [Tue, 16 Aug 2005 19:23:31 +0000 (19:23 +0000)]
Improve comment.

18 years agoUpdate pgcvslog comment on how to find branch start time.
Bruce Momjian [Tue, 16 Aug 2005 17:46:57 +0000 (17:46 +0000)]
Update pgcvslog comment on how to find branch start time.

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

18 years agoReject operator names >= NAMEDATALEN characters. These will not work
Tom Lane [Tue, 16 Aug 2005 00:48:12 +0000 (00:48 +0000)]
Reject operator names >= NAMEDATALEN characters.  These will not work
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.

18 years agoRename pg_stat_file columns to be more consistent. Split apart change
Bruce Momjian [Mon, 15 Aug 2005 23:00:14 +0000 (23:00 +0000)]
Rename pg_stat_file columns to be more consistent.  Split apart change
and creation columns to behave for Unix or Win32.

18 years agoClean up recent patch for PL handler functions in pg_catalog: the patch
Tom Lane [Mon, 15 Aug 2005 21:50:15 +0000 (21:50 +0000)]
Clean up recent patch for PL handler functions in pg_catalog: the patch
caused PL languages and handlers to be dumped ALWAYS, even in the face
of contrary --schema or --table switches.  Adopt a slightly saner
definition.

18 years agoMake createlang and droplang proof against weird search_path settings
Tom Lane [Mon, 15 Aug 2005 21:02:26 +0000 (21:02 +0000)]
Make createlang and droplang proof against weird search_path settings
by forcing search_path to be just pg_catalog.

18 years agoarray_in() and array_recv() need to be more paranoid about validating
Tom Lane [Mon, 15 Aug 2005 19:40:20 +0000 (19:40 +0000)]
array_in() and array_recv() need to be more paranoid about validating
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.

18 years agoint_array_enum function should be using fcinfo->flinfo->fn_extra for
Tom Lane [Mon, 15 Aug 2005 19:05:16 +0000 (19:05 +0000)]
int_array_enum function should be using fcinfo->flinfo->fn_extra for
working state, not fcinfo->context.  Silly oversight on my part in last
go-round of fixes.

18 years agoAllow the pgstat views to show toast tables as well as regular tables
Tom Lane [Mon, 15 Aug 2005 16:25:19 +0000 (16:25 +0000)]
Allow the pgstat views to show toast tables as well as regular tables
(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".