mirror of
https://github.com/postgres/postgres.git
synced 2025-05-31 00:01:57 -04:00
Skip citext_utf8 test on Windows.
Back-patch of commit cff4e5a3 to 15 and 16, per request from Oleg Tselebrovskiy. Original commit message: On other Windows build farm animals it is already skipped because they don't use UTF-8 encoding. On "hamerkop", UTF-8 is used, and then the test fails. It is not clear to me (a non-Windows person looking only at buildfarm evidence) whether Windows is less sophisticated than other OSes and doesn't know how to downcase Turkish İ with the standard Unicode database, or if it is more sophisticated than other systems and uses locale-specific behavior like ICU does. Whichever the reason, the result is the same: we need to skip the test on Windows, just as we already do for ICU, at least until a Windows-savvy developer comes up with a better idea. The technique for detecting the OS is borrowed from collate.windows.win1252.sql. This was anticipated by commit c2e8bd27, but the problem only surfaced when Windows build farm animals started using Meson. Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us> Discussion: https://postgr.es/m/CA%2BhUKGJ1LeC3aE2qQYTK95rFVON3ZVoTQpTKJqxkHdtEyawH4A%40mail.gmail.com
This commit is contained in:
parent
0540b5fd43
commit
91f498fdec
@ -6,8 +6,11 @@
|
||||
* Turkish dotted I is not correct for many ICU locales. citext always
|
||||
* uses the default collation, so it's not easy to restrict the test
|
||||
* to the "tr-TR-x-icu" collation where it will succeed.
|
||||
*
|
||||
* Also disable for Windows. It fails similarly, at least in some locales.
|
||||
*/
|
||||
SELECT getdatabaseencoding() <> 'UTF8' OR
|
||||
version() ~ '(Visual C\+\+|mingw32|windows)' OR
|
||||
(SELECT (datlocprovider = 'c' AND datctype = 'C') OR datlocprovider = 'i'
|
||||
FROM pg_database
|
||||
WHERE datname=current_database())
|
||||
|
@ -6,8 +6,11 @@
|
||||
* Turkish dotted I is not correct for many ICU locales. citext always
|
||||
* uses the default collation, so it's not easy to restrict the test
|
||||
* to the "tr-TR-x-icu" collation where it will succeed.
|
||||
*
|
||||
* Also disable for Windows. It fails similarly, at least in some locales.
|
||||
*/
|
||||
SELECT getdatabaseencoding() <> 'UTF8' OR
|
||||
version() ~ '(Visual C\+\+|mingw32|windows)' OR
|
||||
(SELECT (datlocprovider = 'c' AND datctype = 'C') OR datlocprovider = 'i'
|
||||
FROM pg_database
|
||||
WHERE datname=current_database())
|
||||
|
@ -6,9 +6,12 @@
|
||||
* Turkish dotted I is not correct for many ICU locales. citext always
|
||||
* uses the default collation, so it's not easy to restrict the test
|
||||
* to the "tr-TR-x-icu" collation where it will succeed.
|
||||
*
|
||||
* Also disable for Windows. It fails similarly, at least in some locales.
|
||||
*/
|
||||
|
||||
SELECT getdatabaseencoding() <> 'UTF8' OR
|
||||
version() ~ '(Visual C\+\+|mingw32|windows)' OR
|
||||
(SELECT (datlocprovider = 'c' AND datctype = 'C') OR datlocprovider = 'i'
|
||||
FROM pg_database
|
||||
WHERE datname=current_database())
|
||||
|
Loading…
x
Reference in New Issue
Block a user