From 3b2fd00960ff8ea6004101893284dbbd4b7940cd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?G=C3=B6k=C3=A7en=20Eraslan?= <gokcen.eraslan@gmail.com>
Date: Mon, 10 Oct 2022 14:49:28 -0700
Subject: [PATCH] Handle scalar datasets too (#2344)

* Handle scalar datasets too

After @ivirshup's pytables PR (#2064) we started having issues with loading h5 files with scalar datasets, such as those created by CellBender (https://github.com/broadinstitute/CellBender/issues/128). It is currently not an issue for the 10X h5 files for now since they don't have any scalars, however it'd be good to just handle scalars as well as arrays 1- to fix the cellbender file loading problem 2- to fix potential problems we might end up having if 10X h5 format includes scalar datasets.

* Add a scalar to the multiple_genomes.h5 test file

* Fixes #2203
---
 scanpy/readwrite.py                           |   2 +-
 .../_data/10x_data/1.2.0/multiple_genomes.h5  | Bin 52082 -> 54138 bytes
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/scanpy/readwrite.py b/scanpy/readwrite.py
index 5ff556ddc5..742595987e 100644
--- a/scanpy/readwrite.py
+++ b/scanpy/readwrite.py
@@ -253,7 +253,7 @@ def _read_legacy_10x_h5(filename, *, genome=None, start=None):
 def _collect_datasets(dsets: dict, group: h5py.Group):
     for k, v in group.items():
         if isinstance(v, h5py.Dataset):
-            dsets[k] = v[:]
+            dsets[k] = v[()]
         else:
             _collect_datasets(dsets, v)
 
diff --git a/scanpy/tests/_data/10x_data/1.2.0/multiple_genomes.h5 b/scanpy/tests/_data/10x_data/1.2.0/multiple_genomes.h5
index 3d04d4e909c5ac4570351a5eb0d9767bc60ccddd..c1834ed0bdde874bd4f8fa0336f9d573f90169dd 100644
GIT binary patch
delta 182
zcmew~jrrFy<_Q{1RhKtvEze?1*nBA~l!=jJvPSMlt^fuIC^|iHquk^P+#Hh?^At8`
z=0#Xa7AGg>Bo@V|B$gx=r<O1<FhZ3EOx)-`Il)b0v*ij)Whq7mHi!&VnvsD6td5ak
wa`$9)c_t>XI0u6SSd^Ku=rY6@h^om8%SG5PSJ)&oFihAS$lJ=!!34Dh0L+ai<p2Nx

delta 55
zcmV-70LcIPrUUYp1CS^Ja?7zQr)rbH2MDv-YEA+H2a_mm@sp4X2$M-}Ad`R$Dzj^D
NRymSJc(XaEIU|iZ79Rir