Refactoring/format

locidex/build.py

@@ -4,7 +4,7 @@
 import os, sys
 from argparse import (ArgumentParser, ArgumentDefaultsHelpFormatter, RawDescriptionHelpFormatter)
 from locidex.version import __version__
-from locidex.constants import FORMAT_RUN_DATA
+from locidex.constants import DBFiles
 from locidex.classes import run_command
 from locidex.constants import DBConfig
 
@@ -165,21 +165,10 @@ def run(cmd_args=None):
     input_file = cmd_args.input_file
     outdir = cmd_args.outdir
     force = cmd_args.force
-    run_data = FORMAT_RUN_DATA
+    run_data = dict()
     run_data['analysis_start_time'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
     run_data['parameters'] = vars(cmd_args)
 
-    #config = {}
-    #for f in DB_CONFIG_FIELDS:
-    #    config[f] = ''
-
-    #config["db_name"] = cmd_args.name
-    #config["db_version"] = cmd_args.db_ver
-    #config["db_desc"] = cmd_args.db_desc
-    #config["db_author"] = cmd_args.author
-    #if cmd_args.date == '':
-    #    config["db_date"] = datetime.now().strftime("%Y/%d/%m")
-
     config = DBConfig(
         db_name=cmd_args.name,
         db_version =cmd_args.db_ver,
@@ -199,14 +188,14 @@ def run(cmd_args=None):
         sys.exit()
 
     run_data['analysis_end_time'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-    with open(os.path.join(outdir,"config.json"),"w") as oh:
+    with open(os.path.join(outdir,DBFiles.config_file),"w") as oh:
         oh.write(json.dumps(obj.config.to_dict(),indent=4))
 
-    with open(os.path.join(outdir,"meta.json"),"w") as oh:
+    with open(os.path.join(outdir, DBFiles.meta_file),"w") as oh:
         oh.write(json.dumps(obj.meta,indent=4))
 
 
-    with open(os.path.join(outdir,"results.json"),"w") as oh:
+    with open(os.path.join(outdir, DBFiles.results_file),"w") as oh:
         oh.write(json.dumps(run_data,indent=4))
 
 

locidex/constants.py

@@ -1,7 +1,7 @@
 
 from dataclasses import dataclass, asdict, fields
 import pathlib
-from typing import Any, Union
+from typing import Any, Union, NamedTuple, Optional
 
 DNA_AMBIG_CHARS = ['b', 'd', 'e', 'f', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 'u', 'v', 'w', 'x',
                    'y', 'z', '-']
@@ -39,8 +39,8 @@
 
 
 FILE_TYPES = {
-    'genbank':["gbk","genbank","gbf","gbk.gz","genbank.gz","gbf.gz","gbff","gbff.gz"],
-    'fasta':["fasta","fas","fa","ffn","fna","fasta.gz","fas.gz","fa.gz","ffn.gz","fna.gz"],
+    'genbank': ["gbk","genbank","gbf","gbk.gz","genbank.gz","gbf.gz","gbff","gbff.gz"],
+    'fasta': ["fasta","fas","fa","ffn","fna","fasta.gz","fas.gz","fa.gz","ffn.gz","fna.gz"],
 }
 
 
@@ -121,9 +121,6 @@ class ManifestFields:
 
 }
 
-FORMAT_RUN_DATA = {
-
-}
 
 DB_EXPECTED_FILES = {
     'config':'config.json',
@@ -132,28 +129,53 @@ class ManifestFields:
     'protein':'protein.fasta',
 }
 
-LOCIDEX_DB_HEADER = [
-    'seq_id',
-    'locus_name',
-    'locus_name_alt',
-    'locus_product',
-    'locus_description',
-    'locus_uid',
-    'dna_seq',
-    'dna_seq_len',
-    'dna_seq_hash',
-    'aa_seq',
-    'aa_seq_len',
-    'aa_seq_hash',
-    'dna_min_len',
-    'dna_max_len',
-    'aa_min_len',
-    'aa_max_len',
-    'dna_min_ident',
-    'aa_min_ident',
-    'min_dna_match_cov',
-    'min_aa_match_cov',
-    'count_int_stops',
-    'dna_ambig_count'
 
-]
+class LocidexDBHeader(NamedTuple):
+    seq_id: str
+    locus_name: str
+    locus_name_alt: str 
+    locus_product: str
+    locus_description: str
+    locus_uid: str
+    dna_seq: str
+    dna_seq_len: int
+    dna_seq_hash: str
+    aa_seq: Optional[str]
+    aa_seq_len: Optional[int]
+    aa_seq_hash: Optional[str]
+    dna_min_len: int
+    dna_max_len: int
+    aa_min_len: Optional[int]
+    aa_max_len: Optional[int]
+    dna_min_ident: float
+    aa_min_ident: Optional[float]
+    min_dna_match_cov: int
+    min_aa_match_cov: Optional[int]
+    count_int_stops: int
+    dna_ambig_count: int
+
+
+#LOCIDEX_DB_HEADER = [
+#    'seq_id',
+#    'locus_name',
+#    'locus_name_alt',
+#    'locus_product',
+#    'locus_description',
+#    'locus_uid',
+#    'dna_seq',
+#    'dna_seq_len',
+#    'dna_seq_hash',
+#    'aa_seq',
+#    'aa_seq_len',
+#    'aa_seq_hash',
+#    'dna_min_len',
+#    'dna_max_len',
+#    'aa_min_len',
+#    'aa_max_len',
+#    'dna_min_ident',
+#    'aa_min_ident',
+#    'min_dna_match_cov',
+#    'min_aa_match_cov',
+#    'count_int_stops',
+#    'dna_ambig_count'
+#]

locidex/example/format_db_mlst_out/results.json

@@ -1,8 +1,8 @@
 {
-    "analysis_start_time": "2024-04-04 15:51:06",
+    "analysis_start_time": "2024-05-07 15:30:10",
     "parameters": {
-        "input": "locidex/example/format_db_mlst_in",
-        "outdir": "/tmp/pytest-of-mwells/pytest-115/build0",
+        "input": "./locidex/example/format_db_mlst_in/",
+        "outdir": "./locidex/example/format_db_mlst_out/",
         "min_len_frac": 0.7,
         "max_len_frac": 1.3,
         "min_ident": 80.0,
@@ -11,6 +11,6 @@
         "not_coding": false,
         "force": true
     },
-    "result_file": "/tmp/pytest-of-mwells/pytest-115/build0/locidex.txt",
-    "analysis_end_time": "2024-04-04 15:51:06"
+    "result_file": "./locidex/example/format_db_mlst_out/locidex.txt",
+    "analysis_end_time": "2024-05-07 15:30:10"
 }