Commit Graph

27 Commits

Author SHA1 Message Date
Andrew Dunstan b1665bf01e Allow hyphens in ltree labels
Also increase the allowed length of labels to 1000 characters

Garen Torikian

Discussion: https://postgr.es/m/CAGXsc+-mNg9Gc0rp-ER0sv+zkZSZp2wE9-LX6XcoWSLVz22tZA@mail.gmail.com
2023-01-06 16:05:46 -05:00
Andrew Dunstan 7a05425d96 Convert contrib/ltree's input functions to report errors softly
Reviewed by Tom Lane and Amul Sul

Discussion: https://postgr.es/m/49e598c2-cfe8-0928-b6fb-d0cc51aab626@dunslane.net
2022-12-28 10:00:12 -05:00
Tom Lane 17ca067995 Clean up parsing of ltree and lquery some more.
Fix lquery parsing to handle repeated flag characters correctly,
and to enforce the max label length correctly in some cases where
it did not before, and to detect empty labels in some cases where
it did not before.

In a more cosmetic vein, use a switch rather than if-then chains to
handle the different states, and avoid unnecessary checks on charlen
when looking for ASCII characters, and factor out multiple copies of
the label length checking code.

Tom Lane and Dmitry Belyavsky

Discussion: https://postgr.es/m/CADqLbzLVkBuPX0812o+z=c3i6honszsZZ6VQOSKR3VPbB56P3w@mail.gmail.com
2020-04-01 19:44:17 -04:00
Tom Lane 70dc4c509b Fix lquery's NOT handling, and add ability to quantify non-'*' items.
The existing implementation of the ltree ~ lquery match operator is
sufficiently complex and undocumented that it's hard to tell exactly
what it does.  But one thing it clearly gets wrong is the combination
of NOT symbols (!) and '*' symbols.  A pattern such as '*.!foo.*'
should, by any ordinary understanding of regular expression behavior,
match any ltree that has at least one label that's not "foo".  As best
we can tell by experimentation, what it's actually matching is any
ltree in which *no* label is "foo".  That's surprising, and not at all
what the documentation says.

Now, that's arguably a useful behavior, so if we rewrite to fix the
bug we should provide some other way to get it.  To do so, add the
ability to attach lquery quantifiers to non-'*' items as well as '*'s.
Then the pattern '!foo{,}' expresses "any ltree in which no label is
foo".  For backwards compatibility, the default quantifier for non-'*'
items has to be "{1}", although the default for '*' items is '{,}'.
I wouldn't have done it like that in a green field, but it's not
totally horrible.

Armed with that, rewrite checkCond() from scratch.  Treating '*' and
non-'*' items alike makes it simpler, not more complicated, so that
the function actually gets a lot shorter than it was.

Filip Rembiałkowski, Tom Lane, Nikita Glukhov, per a very
ancient bug report from M. Palm

Discussion: https://postgr.es/m/CAP_rww=waX2Oo6q+MbMSiZ9ktdj6eaJj0cQzNu=Ry2cCDij5fw@mail.gmail.com
2020-03-31 11:14:42 -04:00
Tom Lane e07e2a40bd Improve error messages in ltree_in and lquery_in.
Ensure that the type name is mentioned in all cases (bare "syntax error"
isn't that helpful).  Avoid using the term "level", since that's not
used in the documentation.  Phrase error position reports as "at
character N" not "in position N"; the latter seems ambiguous, and it's
certainly not how we say it elsewhere.  For the same reason, make the
character position values be 1-based not 0-based.  Provide a position
in more cases.  (I continued to leave that out of messages complaining
about end-of-input, where it seemed pointless, as well as messages
complaining about overall input complexity, where fingering any one part
of the input would be arbitrary.)

Discussion: https://postgr.es/m/15582.1585529626@sss.pgh.pa.us
2020-03-31 11:14:42 -04:00
Alexander Korotkov 911e702077 Implement operator class parameters
PostgreSQL provides set of template index access methods, where opclasses have
much freedom in the semantics of indexing.  These index AMs are GiST, GIN,
SP-GiST and BRIN.  There opclasses define representation of keys, operations on
them and supported search strategies.  So, it's natural that opclasses may be
faced some tradeoffs, which require user-side decision.  This commit implements
opclass parameters allowing users to set some values, which tell opclass how to
index the particular dataset.

This commit doesn't introduce new storage in system catalog.  Instead it uses
pg_attribute.attoptions, which is used for table column storage options but
unused for index attributes.

In order to evade changing signature of each opclass support function, we
implement unified way to pass options to opclass support functions.  Options
are set to fn_expr as the constant bytea expression.  It's possible due to the
fact that opclass support functions are executed outside of expressions, so
fn_expr is unused for them.

This commit comes with some examples of opclass options usage.  We parametrize
signature length in GiST.  That applies to multiple opclasses: tsvector_ops,
gist__intbig_ops, gist_ltree_ops, gist__ltree_ops, gist_trgm_ops and
gist_hstore_ops.  Also we parametrize maximum number of integer ranges for
gist__int_ops.  However, the main future usage of this feature is expected
to be json, where users would be able to specify which way to index particular
json parts.

Catversion is bumped.

Discussion: https://postgr.es/m/d22c3a18-31c7-1879-fc11-4c1ce2f5e5af%40postgrespro.ru
Author: Nikita Glukhov, revised by me
Reviwed-by: Nikolay Shaplov, Robert Haas, Tom Lane, Tomas Vondra, Alvaro Herrera
2020-03-30 19:17:23 +03:00
Tom Lane 9950c8aadf Fix lquery's behavior for consecutive '*' items.
Something like "*{2}.*{3}" should presumably mean the same as
"*{5}", but it didn't.  Improve that.

Get rid of an undocumented and remarkably ugly (though not, as far as
I can tell, actually unsafe) static variable in favor of passing more
arguments to checkCond().

Reverse-engineer some commentary.  This function, like all of ltree,
is still far short of what I would consider the minimum acceptable
level of internal documentation, but at least now it has more than
zero comments.

Although this certainly seems like a bug fix, people might not
thank us for changing query behavior in stable branches, so
no back-patch.

Nikita Glukhov, with cosmetic improvements by me

Discussion: https://postgr.es/m/CAP_rww=waX2Oo6q+MbMSiZ9ktdj6eaJj0cQzNu=Ry2cCDij5fw@mail.gmail.com
2020-03-28 18:31:05 -04:00
Tom Lane 95f7ddfdad Protect against overflow of ltree.numlevel and lquery.numlevel.
These uint16 fields could be overflowed by excessively long input,
producing strange results.  Complain for invalid input.

Likewise check for out-of-range values of the repeat counts in lquery.
(We don't try too hard on that one, notably not bothering to detect
if atoi's result has overflowed.)

Also detect length overflow in ltree_concat.

In passing, be more consistent about whether "syntax error" messages
include the type name.  Also, clarify the documentation about what
the size limit is.

This has been broken for a long time, so back-patch to all supported
branches.

Nikita Glukhov, reviewed by Benjie Gillam and Tomas Vondra

Discussion: https://postgr.es/m/CAP_rww=waX2Oo6q+MbMSiZ9ktdj6eaJj0cQzNu=Ry2cCDij5fw@mail.gmail.com
2020-03-28 17:09:51 -04:00
Tom Lane 28a1ae5342 Fix crash in contrib/ltree's lca() function for empty input array.
lca_inner() wasn't prepared for the possibility of getting no inputs.
Fix that, and make some cosmetic improvements to the code while at it.

Also, I thought the documentation of this function as returning the
"longest common prefix" of the paths was entirely misleading; it really
returns a path one shorter than the longest common prefix, for the typical
definition of "prefix".  Don't use that term in the docs, and adjust the
examples to clarify what really happens.

This has been broken since its beginning, so back-patch to all supported
branches.

Per report from Hailong Li.  Thanks to Pierre Ducroquet for diagnosing
and for the initial patch, though I whacked it around some and added
test cases.

Discussion: https://postgr.es/m/5b0d8e4f-f2a3-1305-d612-e00e35a7be66@qunar.com
2018-07-13 18:45:30 -04:00
Heikki Linnakangas 181bdb90ba Fix typos in comments.
Backpatch to all supported versions, where applicable, to make backpatching
of future fixes go more smoothly.

Josh Soref

Discussion: https://www.postgresql.org/message-id/CACZqfqCf+5qRztLPgmmosr-B0Ye4srWzzw_mo4c_8_B_mtjmJQ@mail.gmail.com
2017-02-06 11:33:58 +02:00
Tom Lane ade49c605f Test all contrib-created operator classes with amvalidate.
I'd supposed that people would do this manually when creating new operator
classes, but the folly of that was exposed today.  The tests seem fast
enough that we can just apply them during the normal regression tests.

contrib/isn fails the checks for lack of complete sets of cross-type
operators.  That's a nice-to-have policy rather than a functional
requirement, so leave it as-is, but insert ORDER BY in the query to
ensure consistent cross-platform output.

Discussion: https://postgr.es/m/7076.1480446837@sss.pgh.pa.us
2016-11-29 15:05:22 -05:00
Tom Lane 629b3af27d Convert contrib modules to use the extension facility.
This isn't fully tested as yet, in particular I'm not sure that the
"foo--unpackaged--1.0.sql" scripts are OK.  But it's time to get some
buildfarm cycles on it.

sepgsql is not converted to an extension, mainly because it seems to
require a very nonstandard installation process.

Dimitri Fontaine and Tom Lane
2011-02-13 22:54:49 -05:00
Tom Lane 30e2c42e00 Fix a few contrib regression test scripts that hadn't gotten the word
about best practice for including the module creation scripts: to wit
that you should suppress NOTICE messages.  This avoids creating
regression failures by adding or removing comment lines in the module
scripts.
2007-11-13 06:29:04 +00:00
Bruce Momjian 0614c5e5fd Adjust expected file for new CVS version label. 2007-11-13 04:27:26 +00:00
Bruce Momjian 59d61409cd Move ltree parentsel() selectivity function into /contrib/ltree. 2006-04-26 22:33:36 +00:00
Tom Lane 3bd726333c Recent tightening of allowed array-literal syntax broke one test case
in contrib/ltree.  Fix.
2004-08-21 00:26:54 +00:00
Tom Lane 6ed071bca5 Update contrib regression tests for recent error message editing. 2003-08-01 02:38:09 +00:00
Tom Lane 8fd5b3ed67 Error message editing in contrib (mostly by Joe Conway --- thanks Joe!) 2003-07-24 17:52:50 +00:00
Teodor Sigaev 2c914937c1 Fix subpath and subltree. Allow to return '' value.
subpath(ltree,0,0) returns ''.
2003-07-18 13:27:43 +00:00
Tom Lane f85f43dfb5 Backend support for autocommit removed, per recent discussions. The
only remnant of this failed experiment is that the server will take
SET AUTOCOMMIT TO ON.  Still TODO: provide some client-side autocommit
logic in libpq.
2003-05-14 03:26:03 +00:00
Bruce Momjian baf6c8d21d Please, apply patch for contrib/ltree to current CVS and 7.3.2
CHANGES

Mar 28, 2003
    Added finctions index(ltree,ltree,offset), text2ltree(text),
                    ltree2text(text)

Teodor Sigaev
2003-03-31 20:53:45 +00:00
Bruce Momjian 71e1f531d3 Please apply patches for contrib/ltree.
ltree_73.patch.gz - for 7.3 :
        Fix ~ operation bug: eg '1.1.1' ~ '*.1'

ltree_74.patch.gz - for current CVS
    Fix ~ operation bug: eg '1.1.1' ~ '*.1'
    Add ? operation
    Optimize index storage

Last change needs drop/create all ltree indexes, so only for 7.4

Teodor Sigaev
2003-02-19 03:50:09 +00:00
Tom Lane 1e970dcee8 Ooops, forgot to fix contrib regression tests for WARNING/NOTICE change. 2002-11-01 22:46:04 +00:00
Bruce Momjian aa4c702eac Update /contrib for "autocommit TO 'on'".
Create objects in public schema.

Make spacing/capitalization consistent.

Remove transaction block use for object creation.

Remove unneeded function GRANTs.
2002-10-18 18:41:22 +00:00
Tom Lane ceb9e60e8e Update contrib regression tests for OPAQUE datatype changes. 2002-08-23 00:04:52 +00:00
Bruce Momjian 34f03b1630 Patch for current CVS. It add test of lca() to ltree test suite.
Teodor Sigaev
2002-08-06 05:35:29 +00:00
Bruce Momjian 1dedbf2da5 Add ltree data type to contrib, from Teodor Sigaev and Oleg Bartunov. 2002-07-30 16:40:34 +00:00