mirror of
https://git.postgresql.org/git/postgresql.git
synced 2024-07-28 09:25:32 +02:00
70dc4c509b
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
|
||
|---|---|---|
| .. | ||
| data | ||
| expected | ||
| sql | ||
| _ltree_gist.c | ||
| _ltree_op.c | ||
| .gitignore | ||
| crc32.c | ||
| crc32.h | ||
| lquery_op.c | ||
| ltree_gist.c | ||
| ltree_io.c | ||
| ltree_op.c | ||
| ltree--1.0--1.1.sql | ||
| ltree--1.1--1.2.sql | ||
| ltree--1.1.sql | ||
| ltree.control | ||
| ltree.h | ||
| ltreetest.sql | ||
| ltxtquery_io.c | ||
| ltxtquery_op.c | ||
| Makefile | ||