| commit | 2a6b47cb50eb9b62b050de2cddd03a9ac267e61f | |
| author | Tom Lane <tgl@sss.pgh.pa.us> | |
| Wed, 28 Feb 2024 21:05:17 +0000 (28 16:05 -0500) | ||
| committer | Tom Lane <tgl@sss.pgh.pa.us> | |
| Wed, 28 Feb 2024 21:05:28 +0000 (28 16:05 -0500) | ||
| tree | 1333375a44271b4ea324de3432eae93d98615e54 | treesnapshot (tar.gz zip) |
| parent | 363eb059966d0be0a41c206cee40dfd21eb73251 | commitdiff |
Improve plpgsql's error messages for incorrect %TYPE and %ROWTYPE.
If one of these constructs referenced a nonexistent object, we'd fall
through to feeding the whole construct to the core parser, which would
reject it with a "syntax error" message. That's pretty unhelpful and
misleading. There's no good reason for plpgsql_parse_wordtype and
friends not to throw a useful error for incorrect input, so make them
do that instead of returning NULL.
Discussion: https://postgr.es/m/1964516.1708977740@sss.pgh.pa.us
If one of these constructs referenced a nonexistent object, we'd fall
through to feeding the whole construct to the core parser, which would
reject it with a "syntax error" message. That's pretty unhelpful and
misleading. There's no good reason for plpgsql_parse_wordtype and
friends not to throw a useful error for incorrect input, so make them
do that instead of returning NULL.
Discussion: https://postgr.es/m/1964516.1708977740@sss.pgh.pa.us