Thread: Re: pgsql: Fix overread in JSON parsing errors for incomplete byte sequence

On 2024-May-09, Michael Paquier wrote:

> Fix overread in JSON parsing errors for incomplete byte sequences

I'm getting this error in the new test:

t/002_inline.pl ........................ 1/? 
#   Failed test 'incomplete UTF-8 sequence, chunk size 3: correct error output'
#   at t/002_inline.pl line 134.
#                   'Escape sequence "\�1+2" is invalid.'
#     doesn't match '(?^:(Token|Escape sequence) ""?\\\x{F5}" is invalid)'
# Looks like you failed 1 test of 850.

Not sure what's going on here, or why it fails for me while the
buildfarm is all happy.

-- 
Álvaro Herrera         PostgreSQL Developer  —  https://www.EnterpriseDB.com/
"Every machine is a smoke machine if you operate it wrong enough."
https://twitter.com/libseybieda/status/1541673325781196801

On 2024-May-10, Alvaro Herrera wrote:

> Not sure what's going on here, or why it fails for me while the
> buildfarm is all happy.

Ah, I ran 'git clean -dfx' and now it works correctly.  I must have had
an incomplete rebuild.

-- 
Álvaro Herrera         PostgreSQL Developer  —  https://www.EnterpriseDB.com/
"World domination is proceeding according to plan"        (Andrew Morton)

On Fri, May 10, 2024 at 02:23:09PM +0200, Alvaro Herrera wrote:
> Ah, I ran 'git clean -dfx' and now it works correctly.  I must have had
> an incomplete rebuild.

I am going to assume that this is an incorrect build.  It seems to me
that src/common/ was compiled with a past version not sufficient to
make the new test pass as more bytes got pushed to the error output as
the pre-855517307db8 code could point to some random junk.
--
Michael

On 10.05.24 14:23, Alvaro Herrera wrote:
> On 2024-May-10, Alvaro Herrera wrote:
> 
>> Not sure what's going on here, or why it fails for me while the
>> buildfarm is all happy.
> 
> Ah, I ran 'git clean -dfx' and now it works correctly.  I must have had
> an incomplete rebuild.

I saw the same thing.  The problem is that there is incomplete 
dependency information in the makefiles (not meson) between src/common/ 
and what is using it.  So whenever anything changes in src/common/, you 
pretty much have to do a forced rebuild of everything.

On Tue, May 14, 2024 at 10:39:36AM +0200, Peter Eisentraut wrote:
> I saw the same thing.  The problem is that there is incomplete dependency
> information in the makefiles (not meson) between src/common/ and what is
> using it.  So whenever anything changes in src/common/, you pretty much have
> to do a forced rebuild of everything.

Is that a recent regression?  I have some blurry memories from
working on these areas that changing src/common/ reflected on the
compiled pieces effectively at some point.
--
Michael

On 15.05.24 02:00, Michael Paquier wrote:
> On Tue, May 14, 2024 at 10:39:36AM +0200, Peter Eisentraut wrote:
>> I saw the same thing.  The problem is that there is incomplete dependency
>> information in the makefiles (not meson) between src/common/ and what is
>> using it.  So whenever anything changes in src/common/, you pretty much have
>> to do a forced rebuild of everything.
> 
> Is that a recent regression?  I have some blurry memories from
> working on these areas that changing src/common/ reflected on the
> compiled pieces effectively at some point.

One instance of this problem that I can reproduce at least back to PG12 is

1. touch src/common/exec.c
2. make -C src/bin/pg_dump

This will rebuild libpgcommon, but it will not relink pg_dump.

On Tue, May 14, 2024 at 11:15 PM Peter Eisentraut <peter@eisentraut.org> wrote:
>
> On 15.05.24 02:00, Michael Paquier wrote:
> > Is that a recent regression?  I have some blurry memories from
> > working on these areas that changing src/common/ reflected on the
> > compiled pieces effectively at some point.
>
> One instance of this problem that I can reproduce at least back to PG12 is
>
> 1. touch src/common/exec.c
> 2. make -C src/bin/pg_dump
>
> This will rebuild libpgcommon, but it will not relink pg_dump.

I remember src/common/unicode changes having similar trouble, as well [1].

--Jacob

[1] https://www.postgresql.org/message-id/CAFBsxsGZTwzDnTs=TVM38CCTPP3Y0D3=h+UiWt8M83D5THHf9A@mail.gmail.com