fixed batch mode error when one of the files fails FASTA test causing…

… other files in a pool not being analyzed.

ectyper/commandLineOptions.py

@@ -62,10 +62,9 @@ def checkdbversion():
     )
 
     parser.add_argument(
-        "-d",
-        "--maxdepth",
+        "--maxdirdepth",
         help="Maximum number of directories to descend when searching an input directory of files",
-        default=1e6, 
+        default=0, 
         type=int,   
         required=False
     )

ectyper/ectyper.py

@@ -121,7 +121,7 @@ def run_program():
     os.makedirs(temp_dir, exist_ok=True)
 
     LOG.info("Gathering genome files list ...")
-    input_files_list = genomeFunctions.get_files_as_list(args.input, args.maxdepth)
+    input_files_list = genomeFunctions.get_files_as_list(args.input, args.maxdirdepth)
     raw_genome_files = decompress_gunzip_files(input_files_list, temp_dir)
 
     LOG.info(f"Identifying genome file types on {len(raw_genome_files)} inputs ...")
@@ -157,7 +157,6 @@ def run_program():
             raw_files_dict['filesnotfound'],
             args)
 
-
 
     LOG.info("Standardizing the E.coli genome headers based on file names")
 

ectyper/genomeFunctions.py

@@ -47,7 +47,7 @@ def get_files_as_list(files_or_directories, max_depth_level):
             LOG.info(f"Directory level exceeded ({dir_level_current} > {max_depth_level}), skipping {file_or_directory} ...")
             continue
 
-        # if single directory is specified
+        # if directory is specified
         if os.path.isdir(file_or_directory):
             LOG.info(f"Gathering genomes from directory {file_or_directory} at level {dir_level_current} ...")
             # Create a list containing the file names

ectyper/predictionFunctions.py

@@ -868,7 +868,7 @@ def add_non_predicted(all_genomes_list, predictions_dict, other_dict, filesnotfo
     :param predictions_data_frame: the Dict containing the ectyper predictions
     :return: modified prediction file
     """
-
+    
     # genome names are given without the filename extension
     for g in all_genomes_list:
         gname = os.path.splitext(os.path.split(g)[1])[0]
@@ -887,7 +887,7 @@ def add_non_predicted(all_genomes_list, predictions_dict, other_dict, filesnotfo
             }
             else:
                 predictions_dict[gname] = {
-                    'error':  "No O and H antigen determinant E.coli genes were found. Try running with --verify parameter",
+                    'error':  f"No O and H antigen determinant E.coli genes were found in {gname}",
                     'species': ecoli_dict[gname]["species"]
                 }
 

ectyper/speciesIdentification.py

@@ -266,29 +266,29 @@ def verify_ecoli_and_inputs(fasta_fastq_files_dict, ofiles, filesnotfound, args)
     filesnotfound_dict = {}
 
     fasta_files = fasta_fastq_files_dict.keys()
+
     for fasta in fasta_files:
         sampleName = getSampleName(fasta)
         speciesname = "-"
 
-        if is_valid_fasta_file(fasta, sampleName) == False:
-            failverifyerrormessage = f"Sample {sampleName} FASTA file ({fasta}) is empty. This could happen when FASTA file generated from FASTQ input lacks raw reads mapping to O- and H- antigens database or input FASTA is empty/corrupted. Please check sequence input file of {sampleName}"
-            other_files_dict[sampleName] = {"species":speciesname,"filepath":fasta,"error":failverifyerrormessage}
-            return ecoli_files_dict, other_files_dict, filesnotfound_dict
-
         if sampleName in ecoli_files_dict or sampleName in other_files_dict:
             error_msg = "Duplicated parsed filenames found ('{}'). Offending file paths {}. Only unique file names are supported in batch mode".format(
                                 sampleName, [file for file in fasta_files if sampleName in file]
             )
             LOG.error(error_msg)
             raise ValueError(error_msg)
+
+        if is_valid_fasta_file(fasta, sampleName) == False:
+            failverifyerrormessage = f"Sample {sampleName} FASTA file ({fasta}) is invalid/empty. This could happen when FASTA file generated from FASTQ input lacks raw reads mapping to O- and H- antigens database or input FASTA is empty/corrupted. Please check sequence input file of {sampleName}"
+
 
         #do species always regardless of --verify param. Do prediction on fastq files if available for better accuracy
         if fasta_fastq_files_dict[fasta]:
             fastq_file = fasta_fastq_files_dict[fasta]
             speciesname = get_species(fastq_file, args, args.cores)
         else:
             speciesname = get_species(fasta, args, args.cores)
-
+        
         if args.verify:
             failverifyerrormessage = "Sample identified as " + speciesname + ": serotyping results are only available for E.coli samples." \
                                                                              "If sure that sample is E.coli run without --verify parameter."
@@ -311,5 +311,5 @@ def verify_ecoli_and_inputs(fasta_fastq_files_dict, ofiles, filesnotfound, args)
     for file in filesnotfound:
         sampleName = getSampleName(file)
         filesnotfound_dict[sampleName]={"error":"File {} not found!".format(file)}
-
+    
     return ecoli_files_dict, other_files_dict,filesnotfound_dict

ectyper/subprocess_util.py

@@ -37,7 +37,5 @@ def run_subprocess(cmd, input_data=None, un=False, ignorereturncode=False):
     else:
         LOG.error("Error in subprocess. The following command failed: {}".format(cmd))
         LOG.error("Subprocess failed with error: \"{}\"".format(comp_proc.stderr.decode("utf-8")))
-        #LOG.critical("ectyper has stopped")
         return comp_proc
-        #raise Exception(f"subprocess failure while running {cmd} command")