Merge branch 'versions' into 'dev'

Get software versions directly

See merge request epi2melabs/workflow-containers/wf-artic!43

bin/report.py

@@ -2,24 +2,17 @@
 """Create report file."""
 
 import argparse
+import os
 
 from aplanat import annot, bars, hist, lines, report
 from aplanat.components import bcfstats, nextclade
 from aplanat.util import Colors
 from bokeh.layouts import gridplot, layout
 from bokeh.models import Panel, Range1d, Tabs
-import conda_versions
 import numpy as np
 import pandas as pd
 
 
-# software versions reported (from the environment where this script runs)
-# TODO: pass all these through using --versions
-software_versions = [
-    'np-artic', 'medaka', 'minimap2', 'bcftools', 'nextclade-cli',
-    'samtools', 'bcftools']
-
-
 def load_params(path):
     """Load the parameters csv into a dataframe."""
     params_cols = ['Name', 'Value']
@@ -112,7 +105,7 @@ def main():
         help="A csv containing the parameter key/values")
     parser.add_argument(
         "--versions",
-        help="CSV containing name,version for additional software versions.")
+        help="directory contained CSVs containing name,version.")
     args = parser.parse_args()
 
     report_doc = report.WFReport(
@@ -363,10 +356,20 @@ def main():
 
 The table below highlights versions of key software used within the analysis.
 ''')
-    versions = conda_versions.scrape_data(
-        as_dataframe=True, include=software_versions,
-        version_dir=args.versions)
-    section.table(versions[['Name', 'Version', 'Build']], index=False)
+    versions = list()
+    if args.versions is not None:
+        for fname in os.listdir(args.versions):
+            print("Reading versions from file:", fname)
+            try:
+                with open(os.path.join(args.versions, fname), 'r') as fh:
+                    for line in fh.readlines():
+                        name, version = line.strip().split(',')
+                        versions.append((name, version))
+            except Exception as e:
+                print(e)
+                pass
+    versions = pd.DataFrame(versions, columns=('Name', 'Version'))
+    section.table(versions, index=False)
 
     # Params reporting
     section = report_doc.add_section()

main.nf

@@ -149,6 +149,23 @@ process combineGenotypeSummaries {
 }
 
 
+process get_versions {
+    label "artic"
+    cpus 1
+    output:
+        path "versions.txt"
+    script:
+    """
+    medaka --version | sed 's/ /,/' >> versions.txt
+    minimap2 --version | sed 's/^/minimap2,/' >> versions.txt
+    bcftools --version | head -n 1 | sed 's/ /,/' >> versions.txt
+    samtools --version | head -n 1 | sed 's/ /,/' >> versions.txt
+    nextclade --version | sed 's/^/nextclade,/' >> versions.txt
+    artic --version | sed 's/ /,/' >> versions.txt
+    """
+}
+
+
 process report {
     label "artic"
     cpus 1
@@ -294,7 +311,7 @@ workflow pipeline {
         primers
         ref_variants
     main:
-        software_versions = Channel.empty()
+        software_versions = get_versions()
         combined_genotype_summary = null
         scheme_directory = copySchemeDir(scheme_directory)
         read_summaries = preArticQC(samples)