Fix CairoMakie transforms

[ffreyer]

Description

Fixes #3545

Poly was using the scene transform_func rather than the plot transform_func, which can be different. For h/vspan that is the case, causing different results.

Type of change

• Bug fix (non-breaking change which fixes an issue)

Checklist

• Added an entry in NEWS.md (for new features and breaking changes)
• Added or changed relevant sections in the documentation
• Added unit tests for new algorithms, conversion methods, etc.
• Added reference image tests for new plotting functions, recipes, visual options, etc.

[MakieBot]

Compile Times benchmark

Note, that these numbers may fluctuate on the CI servers, so take them with a grain of salt. All benchmark results are based on the mean time and negative percent mean faster than the base branch. Note, that GLMakie + WGLMakie run on an emulated GPU, so the runtime benchmark is much slower. Results are from running:

using_time = @ctime using Backend
# Compile time
create_time = @ctime fig = scatter(1:4; color=1:4, colormap=:turbo, markersize=20, visible=true)
display_time = @ctime Makie.colorbuffer(display(fig))
# Runtime
create_time = @benchmark fig = scatter(1:4; color=1:4, colormap=:turbo, markersize=20, visible=true)
display_time = @benchmark Makie.colorbuffer(fig)

	using	create	display	create	display
GLMakie	3.58s (3.47, 3.72) 0.09+-	385.71ms (316.60, 427.14) 45.78+-	483.82ms (469.70, 507.97) 12.70+-	7.49ms (7.28, 7.76) 0.19+-	25.90ms (25.46, 26.26) 0.34+-
master	3.59s (3.50, 3.70) 0.09+-	418.58ms (395.81, 440.63) 14.99+-	498.06ms (470.90, 534.15) 20.83+-	7.56ms (7.26, 7.97) 0.25+-	25.93ms (25.44, 26.30) 0.33+-
evaluation	1.00x invariant, -0.01s (-0.11d, 0.84p, 0.09std)	1.09x noisy🤷‍♀️, -32.87ms (-0.96d, 0.11p, 30.39std)	1.03x invariant, -14.24ms (-0.83d, 0.15p, 16.76std)	1.01x invariant, -0.07ms (-0.31d, 0.57p, 0.22std)	1.00x invariant, -0.03ms (-0.10d, 0.86p, 0.34std)
CairoMakie	3.16s (3.07, 3.23) 0.06+-	335.83ms (313.83, 361.27) 15.85+-	149.55ms (138.16, 166.37) 9.82+-	7.42ms (7.21, 7.75) 0.18+-	606.99μs (601.30, 616.72) 5.75+-
master	3.14s (3.06, 3.26) 0.07+-	332.87ms (319.60, 356.90) 13.33+-	145.64ms (140.37, 155.82) 5.57+-	7.48ms (7.12, 7.94) 0.31+-	612.93μs (608.21, 621.30) 5.78+-
evaluation	0.99x invariant, 0.02s (0.37d, 0.51p, 0.07std)	0.99x invariant, 2.96ms (0.20d, 0.71p, 14.59std)	0.97x invariant, 3.92ms (0.49d, 0.38p, 7.69std)	1.01x invariant, -0.06ms (-0.23d, 0.68p, 0.24std)	1.01x invariant, -5.93μs (-1.03d, 0.08p, 5.77std)
WGLMakie	3.76s (3.74, 3.78) 0.02+-	323.75ms (319.80, 329.13) 3.16+-	8.95s (8.85, 9.14) 0.10+-	9.44ms (9.34, 9.58) 0.08+-	71.51ms (68.65, 77.37) 3.28+-
master	3.75s (3.73, 3.79) 0.03+-	322.54ms (317.55, 329.40) 3.74+-	8.96s (8.83, 9.16) 0.12+-	9.37ms (9.20, 9.59) 0.16+-	70.35ms (67.82, 82.06) 5.18+-
evaluation	1.00x invariant, 0.0s (0.17d, 0.76p, 0.02std)	1.00x invariant, 1.21ms (0.35d, 0.52p, 3.45std)	1.00x invariant, -0.01s (-0.10d, 0.85p, 0.11std)	0.99x invariant, 0.08ms (0.61d, 0.29p, 0.12std)	0.98x invariant, 1.16ms (0.27d, 0.63p, 4.23std)

[ffreyer]

Refimg sets Axis transform function to log10 and then plots with transformation = Transformation():

If the backend uses the scene transform function this should result in strong differences, e.g. for CairMakie master: