Hi Ping, On Jun 23 2014 or thereabouts, Ping Cheng wrote: > Hi Benjamin, > > On Mon, Jun 23, 2014 at 1:57 PM, Benjamin Tissoires > <benjamin.tissoi...@redhat.com> wrote: > > Currently, the pad events are sent through the stylus input device > > for the Intuos/Cintiqs, and through the touch input device for the > > Bamboos. > > > > To differentiate the buttons pressed on the pad from the ones pressed > > on the stylus, the Intuos/Cintiq uses MISC_SERIAL and ABS_MISC. This > > lead to a multiplexing of the events into one device, which are then > > splitted out in xf86-input-wacom. Bamboos are not using MISC events > > because the pad is attached to the touch interface, and only BTN_TOUCH > > is used for the finger (and DOUBLE_TAP, etc...). However, the user space > > driver still splits out the pad from the touch interface in the same > > way it does for the pro line devices. > > > > The other problem we can see with this fact is that some of the Intuos > > and Cintiq have a wheel, and the effective range of the reported values > > is [0..71]. Unfortunately, the airbrush stylus also sends wheel events > > (there is a small wheel on it), but in the range [0..1023]. From the user > > space point of view it is kind of difficult to understand that because > > the wheel on the pad are quite common, while the airbrush tool is not. > > > > A solution to fix all of these problems is to split out the pad device > > from the stylus/touch. This decision makes more sense because the pad is > > not linked to the absolute position of the finger or pen, and usually, the > > events from the pad are filtered out by the compositor, which then convert > > them into actions or keyboard shortcuts. > > This is a very good solution. I like it. > > > For backward compatibility with current xf86-input-wacom, the pad devices > > still present the ABS_X, ABS_Y and ABS_MISC events, but they can be > > completely ignored in the new implementation. > > I do not think we need to keep ABS_X and ABS_Y for pad. We've already > supported a tablet (Intuos pen small, a pen only tablet with buttons > reported on touch interface) that does not set ABS_X and ABS_Y for > pad.
Hmm, actually, when I tried removing X and Y, xf86-input-wacom complained that max_x and max_y where set to 0, and it thus rejected the device. Maybe there is a special quirk in the xorg driver for the device you mentioned? Anyway, it's not a big deal, and when both xorg and libinput will know how to handle properly the pad device nodes, we can remove this. > > Unless you plan to use other means to tell userland those events are > from PAD tool, ABS_MISC is necessary and is a reasonable way to group Well, given that the pad now has its own input node, ABS_MISC could be dropped. We just need to teach the users that whichever event comes from this input device is a PAD event. > PAD events. So, I do not think it is for backward compatibility. It is > there to stay. With that said, the whole patchset is > > > Signed-off-by: Benjamin Tissoires <benjamin.tissoi...@redhat.com> > > Reviewed-by: Ping Cheng <pi...@wacom.com> > Thanks, that is greatly appreciated! > Thank you, Benjamin, for your support. > > Ping > Cheers, Benjamin ------------------------------------------------------------------------------ Open source business process management suite built on Java and Eclipse Turn processes into business applications with Bonita BPM Community Edition Quickly connect people, data, and systems into organized workflows Winner of BOSSIE, CODIE, OW2 and Gartner awards http://p.sf.net/sfu/Bonitasoft _______________________________________________ Linuxwacom-devel mailing list Linuxwacom-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/linuxwacom-devel
