fix: Allow concurrent and large refgenie downloads

bio/refgenie/test/Snakefile

@@ -1,11 +1,25 @@
 rule obtain_asset:
     output:
         # the name refers to the refgenie seek key (see attributes on http://refgenomes.databio.org)
-        fai="refs/genome.fasta"
+        fai="refs/genome.fasta",
         # Multiple outputs/seek keys are possible here.
     params:
         genome="human_alu",
         asset="fasta",
-        tag="default"
+        tag="default",
+    log:
+        "logs/refgenie/obtain_large_asset.log",
+    wrapper:
+        "master/bio/refgenie"
+
+rule obtain_large_asset:
+    output:
+        star_index=directory("refs/star_index/hg38/star_index"),
+    params:
+        genome="hg38",
+        asset="star_index",
+        tag="default",
+    log:
+        "logs/refgenie/obtain_large_asset.log",
     wrapper:
         "master/bio/refgenie"

bio/refgenie/wrapper.py

@@ -5,17 +5,27 @@
 
 import os
 import refgenconf
+from refgenconf.exceptions import RefgenconfError
 
 genome = snakemake.params.genome
 asset = snakemake.params.asset
 tag = snakemake.params.tag
 
 conf_path = os.environ["REFGENIE"]
 
-rgc = refgenconf.RefGenConf(conf_path, writable=True)
-
+# BUG If there are multiple concurrent refgenie commands, this will fail due to
+# unable to acquire lock of the config file.
+try:
+    rgc = refgenconf.RefGenConf(conf_path, writable=True)
+except RefgenconfError:
+    # If read lock timeout, attempt to skip the read lock
+    rgc = refgenconf.RefGenConf(
+        conf_path, writable=True, skip_read_lock=True, genome_exact=False
+    )
 # pull asset if necessary
-gat, archive_data, server_url = rgc.pull(genome, asset, tag, force=False)
+gat, archive_data, server_url = rgc.pull(
+    genome, asset, tag, force=False, force_large=True
+)
 
 for seek_key, out in snakemake.output.items():
     path = rgc.seek(genome, asset, tag_name=tag, seek_key=seek_key, strict_exists=True)