DESCRIPTION

For asynchronous dialogs, use the topmost modal shell

Push and fetch results are shown in dialogs that
* are shown asynchronously, and
* moreover are triggered from inside jobs.

I don't like jobs throwing dialogs at the user anyway, but I can see
the desire here to run the potentially long remote operation in a job.
Still, the PushToGerritPage does it without job...

At the very least, such asynchronous dialogs, whether or not they
themselves are modal, must use the topmost modal shell as parent. Using
a parent, like the active window's shell, that already has a modal
child may lock up the application.

Bug: 487209
Change-Id: I460e625051e48ecedab0db7191a6dd8846dacc7d
Signed-off-by: Alayna Houston xxx@xxx.xxx

COMMENTS

author: Alayna Houston
date: 2016-04-06 17:30:13.000000000

Uploaded patch set 1.

-------------------------------------
author: Brenden Conley
date: 2016-04-06 17:30:20.000000000

Patch Set 1:

Build Started https://hudson.eclipse.org/egit/job/egit.gerrit/8384/

-------------------------------------
author: Brenden Conley
date: 2016-04-06 17:31:35.000000000

Patch Set 1: Verified-1

Build Failed 

https://hudson.eclipse.org/egit/job/egit.gerrit/8384/ : FAILURE

-------------------------------------
author: Alayna Houston
date: 2016-04-06 17:34:08.000000000

Patch Set 1:

What's up now? findbugs crashed...

-------------------------------------
author: Brenden Conley
date: 2016-04-06 21:31:46.000000000

Patch Set 1: -Verified

Build Started https://hudson.eclipse.org/egit/job/egit.gerrit/8385/

-------------------------------------
author: Douglas Trujillo
date: 2016-04-06 21:36:31.000000000

Patch Set 1:

> What's up now? findbugs crashed...

While struggling with https://git.eclipse.org/r/#/c/69099/ to finally switch the build to compile against neon I switched the build to java 8 and the findbugs version we currently use doesn't support Java 8. There are some bundles in neon which can't be unpacked by Java 7's unpack200 since they have been packed using Java 8 and Java 7 is unable to unpack them and p2 is too dumb to use the corresponding jar as a fallback :-(

I switched back the egit.gerrit job to use Java 7 and retriggered the build

I am now first trying to find the cause for the problems I currently face with running egit core tests from maven (also using mars target platform). So I am now first bisecting these problems before tackling the additional problems caused by the switch to neon

-------------------------------------
author: Brenden Conley
date: 2016-04-06 22:07:43.000000000

Patch Set 1: Verified+1

Build Successful 

https://hudson.eclipse.org/egit/job/egit.gerrit/8385/ : SUCCESS

-------------------------------------
author: Douglas Trujillo
date: 2016-04-07 09:31:24.000000000

Patch Set 1: Code-Review+2

-------------------------------------
author: Gerrit Johnathan Pham
date: 2016-04-07 09:31:28.000000000

Change has been successfully merged into the git repository by Douglas Trujillo

-------------------------------------
