Reduce assumptions about locale's behavior in new regex tests.

tglsfdc · tglsfdc · commit b66336c4e1af · 2021-08-17T13:00:36.000-04:00
I was overoptimistic to assume that UTF8-based locales would all consider U+1500 to be a member of the [[:alpha:]] char class. Tweak the test cases added by commit 78a843f to avoid that assumption. We might need to lobotomize them further, but this should be enough to fix the early buildfarm reports.
diff --git a/src/test/modules/test_regex/expected/test_regex_utf8.out b/src/test/modules/test_regex/expected/test_regex_utf8.out
@@ -107,18 +107,18 @@ select * from test_regex('[[:alnum:]]*[[:upper:]]*[\u1000-\u2000]*\u1237',
 (2 rows)
 
 -- systematically test char classes
-select * from test_regex('[[:alnum:]]+',  E'x\u1500\u1237', 'L');
+select * from test_regex('[[:alnum:]]+',  E'x*\u1500\u1237', 'L');
    test_regex    
 -----------------
  {0,REG_ULOCALE}
- {xᔀሷ}
+ {x}
 (2 rows)
 
-select * from test_regex('[[:alpha:]]+',  E'x\u1500\u1237', 'L');
+select * from test_regex('[[:alpha:]]+',  E'x*\u1500\u1237', 'L');
    test_regex    
 -----------------
  {0,REG_ULOCALE}
- {xᔀሷ}
+ {x}
 (2 rows)
 
 select * from test_regex('[[:ascii:]]+',  E'x\u1500\u1237', 'L');
@@ -197,10 +197,10 @@ select * from test_regex('[[:xdigit:]]+',  E'xa9\u1500\u1237', 'L');
  {a9}
 (2 rows)
 
-select * from test_regex('[[:word:]]+',  E'x_\u1500\u1237', 'L');
+select * from test_regex('[[:word:]]+',  E'x_*\u1500\u1237', 'L');
    test_regex    
 -----------------
  {0,REG_ULOCALE}
- {x_ᔀሷ}
+ {x_}
 (2 rows)
 
diff --git a/src/test/modules/test_regex/sql/test_regex_utf8.sql b/src/test/modules/test_regex/sql/test_regex_utf8.sql
@@ -62,8 +62,8 @@ select * from test_regex('[[:alnum:]]*[[:upper:]]*[\u1000-\u2000]*\u1237',
   E'\u1500\u1237', 'iELMP');
 
 -- systematically test char classes
-select * from test_regex('[[:alnum:]]+',  E'x\u1500\u1237', 'L');
-select * from test_regex('[[:alpha:]]+',  E'x\u1500\u1237', 'L');
+select * from test_regex('[[:alnum:]]+',  E'x*\u1500\u1237', 'L');
+select * from test_regex('[[:alpha:]]+',  E'x*\u1500\u1237', 'L');
 select * from test_regex('[[:ascii:]]+',  E'x\u1500\u1237', 'L');
 select * from test_regex('[[:blank:]]+',  E'x \t\u1500\u1237', 'L');
 select * from test_regex('[[:cntrl:]]+',  E'x\u1500\u1237', 'L');
@@ -75,4 +75,4 @@ select * from test_regex('[[:punct:]]+',  E'x.\u1500\u1237', 'L');
 select * from test_regex('[[:space:]]+',  E'x \t\u1500\u1237', 'L');
 select * from test_regex('[[:upper:]]+',  E'xX\u1500\u1237', 'L');
 select * from test_regex('[[:xdigit:]]+',  E'xa9\u1500\u1237', 'L');
-select * from test_regex('[[:word:]]+',  E'x_\u1500\u1237', 'L');
+select * from test_regex('[[:word:]]+',  E'x_*\u1500\u1237', 'L');
