On Thu, 05 Jan 2017 08:14:22 +0100, Takashi Sakamoto wrote: > > On Jan 5 2017 15:34, Takashi Iwai wrote: > > On Thu, 05 Jan 2017 01:41:31 +0100, > > Takashi Sakamoto wrote: > >> > >> This reverts commit 6b7e95d1336b9eb0d4c6db190ce756480496bd13. This commit > >> is based on a concern about value of the given parameter. It's expected > >> to be ORed value with some enumeration-constants, thus often it can not be > >> one of the enumeration-constants. I understood that this is out of > >> specification and causes implementation-dependent issues. > >> > >> In C language specification, enumerated type can be interpreted as an > >> integer type, in which all of enumeration-constants in corresponding > >> enumerator-list can be stored. Implementations can select one of char, > >> signed int and unsigned int as its type, and this selection is > >> implementation-dependent. > >> > >> In GCC, a signed integer is selected when at least one of > >> enumeration-constants has negative value, else an unsigned integer is > >> selected. This behaviour can be switched by -fshort-enums to short type. > >> Anyway, the type can be decided after scanning all of > >> enumeration-constants. > >> > >> Totally, there's no rules to constrain the value of enumerated type to > >> be one of enumeration-constants. In short, in enumerated type, decision > >> of actual type for the type is the most important and > >> enumeration-constants are just used for the decision, thus it's permitted > >> to have an integer value in a range of enumeration-constants. In our case, > >> actual type for the type is currently deterministic to be either char or > >> unsigned int. Under GCC, it's unsigned int. > > > > You sign-off is missing. > > Oops... > > Signed-off-by: Takashi Sakamoto <o-takashi@xxxxxxxxxxxxx> > > Should I re-post this with the sign-off? No, I applied with a manual adjustment now. Thanks. Takashi _______________________________________________ Alsa-devel mailing list Alsa-devel@xxxxxxxxxxxxxxxx http://mailman.alsa-project.org/mailman/listinfo/alsa-devel
