fixed formatting with ruff

gaftools/cli/order_gfa.py

@@ -9,7 +9,7 @@
 import os
 import logging
 import time
-from collections import namedtuple, defaultdict
+from collections import defaultdict
 from gaftools.gfa import GFA
 
 logger = logging.getLogger(__name__)
@@ -49,8 +49,7 @@ def run_order_gfa(
     chromosome_order=None,
     with_sequence=False,
 ):
-
-    if not chromosome_order is None:
+    if chromosome_order is not None:
         chromosome_order = chromosome_order.split(sep=",")
 
     if not os.path.isdir(outdir):
@@ -67,7 +66,6 @@ def run_order_gfa(
             logging.error(f"were not able to create directory {outdir}, OSError")
             sys.exit()
 
-
     logger.info(f"Reading {gfa_filename}")
     if with_sequence:
         graph = GFA(gfa_filename, low_memory=False)
@@ -114,8 +112,8 @@ def run_order_gfa(
         # Initialize files
         # f_gfa = open(outdir+'/'+gfa_filename.split("/")[-1][:-4]+'-'+chromosome+'.gfa', 'w')
 
-        scaffold_nodes, inside_nodes, node_order, bo, bubble_count = (
-            decompose_and_order(graph, component_nodes, chromosome, bo)
+        scaffold_nodes, inside_nodes, node_order, bo, bubble_count = decompose_and_order(
+            graph, component_nodes, chromosome, bo
         )
 
         # skip a chromosome if something went wrong
@@ -130,12 +128,7 @@ def run_order_gfa(
             )
             out_files.append(f_gfa)
             f_colors = open(
-                outdir
-                + os.sep
-                + gfa_filename.split(os.sep)[-1][:-4]
-                + "-"
-                + chromosome
-                + ".csv",
+                outdir + os.sep + gfa_filename.split(os.sep)[-1][:-4] + "-" + chromosome + ".csv",
                 "w",
             )
             f_colors.write("Name,Color,SN,SO,BO,NO\n")
@@ -163,9 +156,7 @@ def run_order_gfa(
                 else:
                     so_tag = "NA"
                 f_colors.write(
-                    "{},{},{},{},{},{}\n".format(
-                        node_name, color, sn_tag, so_tag, bo_tag, no_tag
-                    )
+                    "{},{},{},{},{},{}\n".format(node_name, color, sn_tag, so_tag, bo_tag, no_tag)
                 )
 
             graph.write_gfa(
@@ -180,11 +171,7 @@ def run_order_gfa(
         else:
             logger.warning(f"Chromosome {chromosome} was skipped")
     final_gfa = (
-        outdir
-        + os.sep
-        + gfa_filename.split(os.sep)[-1].split(".")[0]
-        + "-complete"
-        + ".gfa"
+        outdir + os.sep + gfa_filename.split(os.sep)[-1].split(".")[0] + "-complete" + ".gfa"
     )
     with open(final_gfa, "w") as outfile:
         # outputting all the S lines first
@@ -251,12 +238,8 @@ def decompose_and_order(graph, component, component_name, bo_start=0):
     logger.info(f"  Scaffold graph: {len(scaffold_graph)} nodes")
 
     # Find start/end points of the line by looking for nodes with degree 1
-    degree_one = [
-        x.id for x in scaffold_graph.nodes.values() if len(x.neighbors()) == 1
-    ]
-    degree_two = [
-        x.id for x in scaffold_graph.nodes.values() if len(x.neighbors()) == 2
-    ]
+    degree_one = [x.id for x in scaffold_graph.nodes.values() if len(x.neighbors()) == 1]
+    degree_two = [x.id for x in scaffold_graph.nodes.values() if len(x.neighbors()) == 2]
 
     try:
         assert len(degree_one) == 2
@@ -314,7 +297,7 @@ def count_sn(graph, comp):
     """
     counts = defaultdict(int)
     for n in comp:
-        if not "SN" in graph[n].tags:
+        if "SN" not in graph[n].tags:
             continue
         counts[graph[n].tags["SN"][1]] += 1
     return counts

gaftools/cli/realign.py

@@ -12,7 +12,7 @@
 from gaftools.timer import StageTimer
 from gaftools.gaf import GAF
 from gaftools.gfa import GFA
-from pywfa.align import WavefrontAligner, cigartuples_to_str
+from pywfa.align import WavefrontAligner
 
 
 logger = logging.getLogger(__name__)
@@ -23,6 +23,7 @@ class PriorityAlignment:
     """
     Simple data class to store the sequences and their priorities so the GAF output matches the GAf input
     """
+
     priority: int
     seq: str
     field(compare=False)
@@ -76,9 +77,7 @@ def run_realign(gaf, graph, fasta, output=None, cores=1):
         output = open(output, "w")
 
     if cores > mp.cpu_count():
-        logger.warning(
-            "Number of cores requested is greater than the total number of CPU cores."
-        )
+        logger.warning("Number of cores requested is greater than the total number of CPU cores.")
         cores = min(mp.cpu_count() - 1, cores)
 
     # realign_gaf(gaf, graph, fasta, output, ext, cores)
@@ -214,9 +213,7 @@ def realign_gaf(gaf, graph, fasta, output, cores=1):
                                 "One of the processes had a none-zero exit code. One reason could be that one of the processes consumed too much memory and was killed"
                             )
                             sys.exit(1)
-                if (
-                    out_string_obj is None
-                ):  # sentinel counter to count finished processes
+                if out_string_obj is None:  # sentinel counter to count finished processes
                     n_sentinels += 1
                 else:  # priority queue to keep the output order same as input order
                     p_queue.put(out_string_obj)

tests/test_run_realign.py

@@ -2,53 +2,52 @@
 Tests for 'gaftools realign'
 """
 
-
 from gaftools.gaf import GAF
 from gaftools.cli.realign import run_realign
 
 
 def test_order_gfa(tmp_path):
-    #gaftools realign alignments.gaf smallgraph.gfa reads.fa
-    input_gaf = 'tests/data/alignments-graphaligner.gaf'
-    output_gaf = str(tmp_path) + '/output.gaf'
+    # gaftools realign alignments.gaf smallgraph.gfa reads.fa
+    input_gaf = "tests/data/alignments-graphaligner.gaf"
+    output_gaf = str(tmp_path) + "/output.gaf"
     run_realign(
-        gaf  = input_gaf,
-        graph = 'tests/data/smallgraph.gfa',
-        fasta = 'tests/data/reads.fa',
-        output = output_gaf,
-        cores=1
+        gaf=input_gaf,
+        graph="tests/data/smallgraph.gfa",
+        fasta="tests/data/reads.fa",
+        output=output_gaf,
+        cores=1,
     )
 
     gaf = GAF(output_gaf)
     gaf_lines = list(gaf.read_file())
     assert len(gaf_lines) == 2
 
-    assert gaf_lines[0].query_name == 'read_s8_s9'
+    assert gaf_lines[0].query_name == "read_s8_s9"
     assert gaf_lines[0].query_length == 398
     assert gaf_lines[0].query_start == 0
     assert gaf_lines[0].query_end == 398
-    assert gaf_lines[0].strand == '+'
-    assert gaf_lines[0].path == '>s8>s9'
+    assert gaf_lines[0].strand == "+"
+    assert gaf_lines[0].path == ">s8>s9"
     assert gaf_lines[0].path_length == 10109
     assert gaf_lines[0].path_start == 6166
     assert gaf_lines[0].path_end == 6564
     assert gaf_lines[0].residue_matches == 398
     assert gaf_lines[0].alignment_block_length == 398
     assert gaf_lines[0].mapping_quality == 60
-    assert gaf_lines[0].cigar == '398='
-    #assert gaf_lines[0].is_primary
+    assert gaf_lines[0].cigar == "398="
+    # assert gaf_lines[0].is_primary
 
-    assert gaf_lines[1].query_name == 'read_s8_s9_deletion15'
+    assert gaf_lines[1].query_name == "read_s8_s9_deletion15"
     assert gaf_lines[1].query_length == 383
     assert gaf_lines[1].query_start == 0
     assert gaf_lines[1].query_end == 383
-    assert gaf_lines[1].strand == '+'
-    assert gaf_lines[1].path == '>s8>s9'
+    assert gaf_lines[1].strand == "+"
+    assert gaf_lines[1].path == ">s8>s9"
     assert gaf_lines[1].path_length == 10109
     assert gaf_lines[1].path_start == 6166
     assert gaf_lines[1].path_end == 6564
     assert gaf_lines[1].residue_matches == 383
     assert gaf_lines[1].alignment_block_length == 398
     assert gaf_lines[1].mapping_quality == 60
-    assert gaf_lines[1].cigar == '189=15D194='
-    #assert gaf_lines[1].is_primary
+    assert gaf_lines[1].cigar == "189=15D194="
+    # assert gaf_lines[1].is_primary