chore: updates to satisfy ruff and sprocket lint

.github/workflows/sprocket-test.yaml

@@ -38,4 +38,4 @@ jobs:
       env: 
         RUNNER: ${{ matrix.runner }}
       run: |
-        sprocket dev test --filter-tag reference --filter-tag slow --filter-tag high_mem ${{ matrix.file }}
+        sprocket dev test --exclude-tag reference --exclude-tag slow --exclude-tag high_mem ${{ matrix.file }}

data_structures/flag_filter.wdl

@@ -83,6 +83,8 @@ task validate_string_is_12bit_int {
     }
 
     command <<<
+        set -euo pipefail
+
         if [[ "~{number}" =~ ^[1-9][0-9]*$ ]]; then
             # number is in decimal
             if [ "~{number}" -lt 4096 ]; then

data_structures/read_group.wdl

@@ -127,6 +127,8 @@ task get_read_groups {
     Int disk_size_gb = ceil(bam_size) + 10 + modify_disk_size_gb
 
     command <<<
+        set -euo pipefail
+
         python3 /scripts/data_structures/get_read_groups.py \
             "~{bam}" \
             read_groups.json
@@ -181,6 +183,8 @@ task validate_read_group {
     ]
 
     command <<<
+        set -euo pipefail
+
         exit_code=0
         if ~{restrictive}; then
             if [[ "~{read_group.ID}" =~ ~{restrictive_pattern} ]]
@@ -396,6 +400,8 @@ task inner_read_group_to_string {
         else " "
 
     command <<<
+        set -euo pipefail
+
         if ~{format_as_sam_record}; then
             echo -n "@RG~{delimiter}" > out.txt
         fi

scripts/data_structures/get_read_groups.py

@@ -1,19 +1,19 @@
-import pysam
 import json
 
+import pysam
+
 
 def main(bam_path, outfile_path):
     sam = pysam.AlignmentFile(bam_path, "rb")
 
-    out_file = open(outfile_path, "w")
-    header = sam.header.to_dict()["RG"]
-    modified_header = []
-    for read_group in sorted(header, key=lambda d: d["ID"]):
-        modified_header.append(
-            {k: v.upper() if k == "PL" else v for k, v in read_group.items()}
-        )
-    json.dump(modified_header, out_file)
-    out_file.close()
+    with open(outfile_path, "w") as out_file:
+        header = sam.header.to_dict()["RG"]
+        modified_header = []
+        for read_group in sorted(header, key=lambda d: d["ID"]):
+            modified_header.append(
+                {k: v.upper() if k == "PL" else v for k, v in read_group.items()}
+            )
+        json.dump(modified_header, out_file)
 
 
 if __name__ == "__main__":

scripts/htseq/calc_tpm.py

@@ -1,35 +1,32 @@
 def main(counts_name_path, feature_lengths_path, outfile_path, has_header):
-    counts_file = open(counts_name_path, "r")
-    counts = {}
-    if has_header:
-        counts_file.readline()
-    for line in counts_file:
-        gene, count = line.split("\t")
-        if gene[0:2] == "__":
-            break
-        counts[gene.strip()] = int(count.strip())
-    counts_file.close()
+    with open(counts_name_path, "r") as counts_file:
+        counts = {}
+        if has_header:
+            counts_file.readline()
+        for line in counts_file:
+            gene, count = line.split("\t")
+            if gene[0:2] == "__":
+                break
+            counts[gene.strip()] = int(count.strip())
 
-    lengths_file = open(feature_lengths_path, "r")
-    rpks = {}  # Reads Per Kilobase
-    tot_rpk = 0
-    lengths_file.readline()  # discard header
-    for line in lengths_file:
-        gene, length = line.split("\t")
-        rpk = counts[gene.strip()] / int(length.strip()) * 1000
-        tot_rpk += rpk
-        rpks[gene.strip()] = rpk
-    lengths_file.close()
+    with open(feature_lengths_path, "r") as lengths_file:
+        rpks = {}  # Reads Per Kilobase
+        tot_rpk = 0
+        lengths_file.readline()  # discard header
+        for line in lengths_file:
+            gene, length = line.split("\t")
+            rpk = counts[gene.strip()] / int(length.strip()) * 1000
+            tot_rpk += rpk
+            rpks[gene.strip()] = rpk
 
     scaling_factor = tot_rpk / 1000000
 
     sample_name = ".".join(outfile_path.split(".")[:-2])  # assumed to end in `.TPM.txt`
-    outfile = open(outfile_path, "w")
-    print(f"feature\t{sample_name}", file=outfile)
-    for gene, rpk in sorted(rpks.items()):
-        tpm = rpk / scaling_factor
-        print(f"{gene}\t{tpm:.3f}", file=outfile)
-    outfile.close()
+    with open(outfile_path, "w") as outfile:
+        print(f"feature\t{sample_name}", file=outfile)
+        for gene, rpk in sorted(rpks.items()):
+            tpm = rpk / scaling_factor
+            print(f"{gene}\t{tpm:.3f}", file=outfile)
 
 
 if __name__ == "__main__":

scripts/methylation/combine.py

@@ -1,4 +1,5 @@
 import argparse
+
 import pandas as pd
 
 

scripts/methylation/filter.py

@@ -1,7 +1,8 @@
+import argparse
 import csv
-import pandas as pd
+
 import numpy as np
-import argparse
+import pandas as pd
 
 
 def get_args():

scripts/methylation/generate_umap.py

@@ -1,6 +1,7 @@
+import argparse
+
 import pandas as pd
 import umap
-import argparse
 
 
 def get_args():

scripts/methylation/plot_umap.py

@@ -1,7 +1,8 @@
-import pandas as pd
-import matplotlib.pyplot as plt
 import argparse
 
+import matplotlib.pyplot as plt
+import pandas as pd
+
 
 def get_args():
     parser = argparse.ArgumentParser(description="Plot UMAP coordinates.")

scripts/util/calc_feature_lengths.py

@@ -1,14 +1,15 @@
+from collections import defaultdict
+
 import gtfparse
 import numpy as np
-from collections import defaultdict
 
 
 def main(gtf_path, outfile_path, id_attr):
     gtf = gtfparse.read_gtf(gtf_path)
 
     only_exons = gtf[gtf["feature"] == "exon"]
-    exon_starts = defaultdict(lambda: [])
-    exon_ends = defaultdict(lambda: [])
+    exon_starts = defaultdict(list)
+    exon_ends = defaultdict(list)
     gene_start_offset = {}
     gene_end_offset = {}
     gene_exon_intersection = {}
@@ -43,16 +44,14 @@ def main(gtf_path, outfile_path, id_attr):
                 - gene_start_offset[feature_id]
             ] = True
 
-    outfile = open(outfile_path, "w")
-    print("feature\tlength", file=outfile)
-    for gene, exonic_intersection in sorted(gene_exon_intersection.items()):
-        # np.count_nonzero() is faster than sum
-        # np.count_nonzero() evaluates the "truthfulness" of
-        # of all elements (by calling their '.__bool__()' method)
-        length = np.count_nonzero(exonic_intersection)
-        print(f"{gene}\t{length}", file=outfile)
-
-    outfile.close()
+    with open(outfile_path, "w") as outfile:
+        print("feature\tlength", file=outfile)
+        for gene, exonic_intersection in sorted(gene_exon_intersection.items()):
+            # np.count_nonzero() is faster than sum
+            # np.count_nonzero() evaluates the "truthfulness" of
+            # of all elements (by calling their '.__bool__()' method)
+            length = np.count_nonzero(exonic_intersection)
+            print(f"{gene}\t{length}", file=outfile)
 
 
 if __name__ == "__main__":