[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

W3C

– DRAFT –
ARIA WG

10 November 2022

Attendees

Present
Adam_Page, chlane, CurtBellew, daniel-montalvo, jcraig, MarkMcCarthy, scotto, spectranaut, StefanS
Regrets
-
Chair
-
Scribe
Adam_Page

Meeting minutes

New Issue Triage

jamesn: #1845

scotto: prevents possibility of img role="none" but with alt text from being exposed

jamesn: not exposed as a node in the tree at all?

scotto: from quick tests, yes, pruned from the tree. SR couldn’t get to alt text at all

jamesn: how to classify?

jcraig: would like interactive images to be _a thing_ in the future

jcraig: e.g., fully interactive SVG should be exposed as an image with content

jcraig: so want to make sure this proposal is compatible with that

jcraig: whatever the outcome is for this, it should not prevent a presentational image *with* exposeable content nodes

jamesn: need to clarify the “role="none" is equivalent to using `aria-hidden="true"`” language

scotto: this is triage

jamesn: we need clarification

jamesn: looking at 1.4 for this

scotto: I’ll take assignment and keep investigating

New PR Triage

Deep Dive planning

jamesn: deep dive on Dec 8

jamesn: do we want to plan any more?

jamesn: consensus: no

jamesn: can do more next year

holiday meetings

jamesn: we’ll meet next week unless people are out for Thanksgiving?

jamesn: we’ll keep on meeting up until Christmas

jamesn: will figure out which exact weeks we’ll take off

jamesn: if anyone has issues, let chairs know

ARIA F2F 2023

jamesn: set up survey for face-to-face

jamesn: have 8 responses so far, need more

jamesn: want to measure appetite, and rough idea for location

siri: lot of budget cuts

jamesn: will definitely have remote attendance options regardless

Other elements which may need special description computation conditions?

jamesn: scotto, this one’s from you?

scotto: this is related to work on accname and html-aam updating description table

scotto: in doing that, mentioned interesting callouts to Aaron

scotto: e.g., summary element has a weird use case where if it’s given an author accessible name, like aria-label, then subtree should be converted to description
… similar to button type with a value
… that value becomes a description
… kind of weird that we’re doing that
… other elements don’t have this behavior
… needs fixing
… either elements with special conditions should have those conditions removed
… or other elements should consistently get those same conditions

jamesn: or potentially we leave it how it is, and clarify the ones that have those conditions?

scotto: true, but some of these may actually fail Label in Name

jcraig: could add to characteristics table for those roles?

jcraig: would match current behavior now, and then we could modify table if needed

jcraig: would also confront us with the decision for any new roles that come in

jamesn: how would modifying this remediate the Label in Name issue?

scotto: you’re right, they would fail anyway

jamesn: sometimes the visible label contains extra content that gives a bad SR experience

jamesn: we could consider deprecating the weird behavior

jamesn: but people may be relying on it

jamesn: but I still grant that it’s difficult to justify; seems weird

jcraig: if we go with deprecation path, then we should definitely not update the characteristics table

jcraig: I support jamesn’s deprecation proposal

scotto: the only other elements that I investigated with potential could be hyperlinks, but now think that would be a bad idea based on this discussion

scotto: fieldset with legend is a squishy use case

scotto: option element with overwritten label text

scotto: this could expand into those cases

scotto: but if we do the deprecation path, it’s a signal that we’ll no longer do this

scotto: I just don’t get the use case for the elements where it’s been done

jamesn: although I proposed deprecation, I don’t know how we’d actually do that

scotto: need more people to weigh in

scotto: describe the 3 different options we’ve discussed and solicit feedback in the issue

jamesn: sounds similar to what James Teh has brought up

jamesn: this would be a description “guess” that the AT could choose how to expose

scotto: looping this back to triage, it’s a similar concept to img alt role="none"

scotto: maybe your point about having a new prop is the way to go

jamesn: `aria-shrug` ;-)

scotto: I actually like that one the most

scotto: could extend to other elements

<chlane> aria-any

<jamesn> aria-🤷‍♂️

scotto: becoming convinced that jcraig’s proposal is the way to go

jamesn: this issue does seem to be a repeating pattern

jamesn: we need to talk to AT makers and make sure they can work with it

jamesn: need to set up a discussion with Freedom Scientific, NVDA, etc.

<chlane> I like the additional property idea rather than making the concept of 'description' more complex for authors

jamesn: where is this on our priority list

scotto: to close this up, 2 paths forward

scotto: 1) potential deprecation

scotto: 2) potential new property to funnel this info into

scotto: need to see what appetite is

jamesn: and 3) do nothing, but explain why behavior is there for historical reason

scotto: I’ll write this up

scotto: I have enough context to shop this around

Support aria-description

scotto: needs reviews

jamesn: this is blocking other things in accname, so need to get this in

jamesn: this changes a lot; can’t merge in any other PRs

spectranaut: who needs to review?

jamesn: Bryan and Melanie

Bryan: I’ll review later today

scotto: you would never reference one’s self to get a description

jamesn: can add an editorial note to clarify

jcraig: is there any opinion on my editorial feedback?
… HTML caption is specifically referenced
… we should take that out IMO
… do others agree?
… line 239 in the source

scotto: can’t find in latest version of PR

jcraig: nevermind

scotto: maybe there’s a merge conflict?

jamesn: please move that one along

scotto: just need people to verify

jamesn: reviewers, please review

1.3 blocking issues agendabot]

jamesn: #1150 is on me
… #1159
… any updates?
… #1161
… depends on sarahhigley’s PR
… will look into that
… #1824
… what did we decide for this?

scotto: Wilco opened about aria-label and prohibited

jamesn: need an editorial note to confirm it’s global

jamesn: decided in last meeting, need to look at minutes

jamesn: let’s look at sarahhigley’s PR

<jamesn> https://github.com/w3c/aria/pull/1454

jamesn: pinged me for editorial review
… what else are we waiting for on this?

scotto: we should all take one more peek at it

jamesn: it’s not building successfully right now

jamesn: would like cyns, Aaron, and jcraig to give review

jamesn: need checkmarks of approval

scotto: I’ll do another quick review by EOD tomorrow

jamesn: this will unblock a lot of other stuff. Should be our next merge

jamesn: everyone, put this at the top of your list

Open PRs on ARIA

jamesn: let’s adjourn

jamesn: please fill out face-to-face survey, everyone

Minutes manually created (not a transcript), formatted by scribe.perl version 196 (Thu Oct 27 17:06:44 2022 UTC).

Diagnostics

Succeeded: s/aymore/any more/

Succeeded: s/thge/the

Succeeded: s/FS/Freedom Scientific/

Succeeded: s/shigley/sarahhigley/

No scribenick or scribe found. Guessed: Adam_Page

Maybe present: Bryan, jamesn, siri

All speakers: Bryan, jamesn, jcraig, scotto, siri, spectranaut

Active on IRC: Adam_Page, chlane, CurtBellew, daniel-montalvo, jamesn, jcraig, MarkMcCarthy, scotto, spectranaut, StefanS