Conversation
-kwargs in interpolators RTK and BDM2 interpolators -CellDofsParents for broken spaces should construct correctly now -FEEvaluator uses dofgrid instead of xgrid now (last two should fix some issues with Hdiv-FE on subgrids)
- get_coeffs and get_basissubset depend on assembly grid (xgrid or dofgrid)
|
Is this ready for review? Please bump the version according to the changes. |
|
I am still trying to get the Stokes-Darcy problem running... so maybe some further bugfixes are needed. So should I add the version change to 1.0 directly to this PR? |
|
Yes, we make 1.0 now. And release it when it is ready |
- version bump to 1.0.0
|
my Stokes-Darcy problem in ExtendableFEM seems to run now with these bugfixes, somebody can review the changes and merge |
|
now also the ExtendableFEM tests should work |
pjaap
left a comment
pjaap
left a comment
There was a problem hiding this comment.
Looks basically good. One comment below.
If you are willing to polish: The commit messages are somewhat bad. I would reword them a bit and squash them into 4 commits. But this is up to you.
| over the entities AT of the grid. The result on every item is written into integral4items. | ||
| As usual, qpinfo allows to access information | ||
| at the current quadrature point. | ||
| The length of the result needs to be specified via resultdim. |
|
|
||
| over the entities AT of the grid. Here, qpinfo allows to access information | ||
| at the current quadrature point. | ||
| The length of the result needs to be specified via resultdim. |
There was a problem hiding this comment.
resultdim is a parameter in this function. Maybe it was a c&p error above?
There was a problem hiding this comment.
Yes, you guessed correctly :) I fixed it now.
3 participants
-kwargs in RTK and BDM2 interpolators
-regions in integrate methods are recognized + proper dosctrings
-TangentFlux operator for H1 functions
-CellDofsParents for broken spaces should construct correctly now
-FEEvaluator can use dofgrid (default) instead of xgrid now
-get_coefficients and get_basissubset now have an additional xgrid argument (they need to be available for xgrid or dofgrid depending on the assembly grid)
(last three should fix some issues with Hdiv-FE on subgrids, related to ExtendableFEM issue #43)