The tests used string concatenation to test statistics on expressions,
but that made the tests locale-dependent, e.g. because the ordering of
'11' and '1X' depends on the collation. This affected both the estimated
and actual row couts, breaking some of the tests.

Fixed by replacing the string concatenation with upper() function call,
so that the text values contain only digits.

Discussion: https://postgr.es/m/b650920b-2767-fbc3-c87a-cb8b5d693cbf%40enterprisedb.com