Fastq now runs through fastq2fasta pipeline

then gets added to pangenome analysis.

2 files changed, 15 insertions, 5 deletions

diff --git a/bh20sequploader/main.py b/bh20sequploader/main.py
index 8b8fefe..56cbe22 100644
--- a/bh20sequploader/main.py
+++ b/bh20sequploader/main.py
@@ -20,12 +20,18 @@ def main():
 
     api = arvados.api(host=ARVADOS_API_HOST, token=ARVADOS_API_TOKEN, insecure=True)
 
-    qc_metadata(args.metadata.name)
+    if not qc_metadata(args.metadata.name):
+        print("Failed metadata qc")
+        exit(1)
 
     col = arvados.collection.Collection(api_client=api)
 
-    print("Reading FASTA")
-    with col.open("sequence.fasta", "w") as f:
+    if args.sequence.name.endswith("fasta") or args.sequence.name.endswith("fa"):
+        target = "sequence.fasta"
+    elif args.sequence.name.endswith("fastq") or args.sequence.name.endswith("fq"):
+        target = "reads.fastq"
+
+    with col.open(target, "w") as f:
         r = args.sequence.read(65536)
         print(r[0:20])
         while r:
@@ -52,5 +58,7 @@ def main():
                  (properties['upload_user'], properties['upload_ip']),
                  properties=properties, ensure_unique_name=True)
 
+    print("Done")
+
 if __name__ == "__main__":
     main()
diff --git a/bh20sequploader/qc_metadata.py b/bh20sequploader/qc_metadata.py
index 78b31b2..ebe4dfc 100644
--- a/bh20sequploader/qc_metadata.py
+++ b/bh20sequploader/qc_metadata.py
@@ -1,6 +1,7 @@
 import schema_salad.schema
 import logging
 import pkg_resources
+import logging
 
 def qc_metadata(metadatafile):
     schema_resource = pkg_resources.resource_stream(__name__, "bh20seq-schema.yml")
@@ -17,5 +18,6 @@ def qc_metadata(metadatafile):
     try:
         doc, metadata = schema_salad.schema.load_and_validate(document_loader, avsc_names, metadatafile, True)
         return True
-    except:
-        return False
+    except Exception as e:
+        logging.warn(e)
+    return False