Merge pull request #56 from rki-mf1/fix/v.1

July Patch - Bug Fix

.version

@@ -1 +1 @@
-1.1.4
+1.1.5

lib/.version

@@ -1 +1 @@
-1.1.4
+1.1.5

lib/Lineages_UPDATER.py

@@ -82,6 +82,18 @@ def download_source(tmp_dir):
 
 def process_lineage(alias_key_path, lineages_path, output):
     print('Calculate all lineages')
+    # handle duplicate values
+    with open(alias_key_path) as f:
+		# load json objects to dictionaries
+        data_dict = json.load(f)
+
+    for k, v in data_dict.items():
+        if type(v) is list:
+            data_dict[k] = list(set(v))
+	# rewrite the json
+    with open(alias_key_path ,'w') as nf:
+        json.dump(data_dict, nf)
+
     aliasor = Aliasor(alias_key_path)
     df_lineages = pd.read_csv(lineages_path)
     lineages = df_lineages.lineage.unique()

lib/sonardb.py

@@ -1717,7 +1717,6 @@ def match(self,
 					profile_clause[-1] = "(" + " AND ".join(profile_clause[-1]) + ")"
 				else:
 					profile_clause[-1] = profile_clause[-1][0]
-
 			if len(profile_clause) > 1:
 				where_clause.append("(" + " OR ".join(profile_clause) + ")")
 			else:
@@ -2704,7 +2703,25 @@ def make_profile_explicit(self, profile):
 		for var in profile:
 			key = "dna" if self.isdnavar(var) else "aa"
 			extended_profile[key].extend([v for v in self.pinpoint_mutation(var, self.codedict[key]['code'])])
-		return extended_profile
+		return extended_profile 
+
+	def _fix_X_N_search(self, _profiles):
+		temp_include_profiles = []
+		for _list_var in _profiles:
+			for var in _list_var:
+				if (var[-1].lower() == 'x') and not self.isdnavar(var):
+					for v in self.pinpoint_mutation(var, self.codedict["aa"]['code']):
+						temp_include_profiles.append([v])
+
+				elif(var[-1].lower() == 'n') and self.isdnavar(var):
+					for v in self.pinpoint_mutation(var, self.codedict["dna"]['code']):
+						temp_include_profiles.append([v])
+
+		_profiles.extend(temp_include_profiles)
+		_profiles = [list(x) for x in set(tuple(x) for x in _profiles)]
+		#print("After update")
+		#print(_profiles)
+		return _profiles
 
 
 	def match(self,
@@ -2850,13 +2867,14 @@ def match(self,
 			sys.exit("input error: matching a given software version needs a software defined.")
 
 		# adding conditions of profiles to include to where clause
-		#print(include_profiles)
+		# print(include_profiles)
 		if include_profiles:
-			include_profiles = [ self.make_profile_explicit(x) for x in include_profiles ]
+			include_profiles = self._fix_X_N_search(include_profiles)
+			include_profiles = [ self.make_profile_explicit(x) for x in include_profiles ] # Fix here
 		# adding conditions of profiles to exclude to where clause
 		if exclude_profiles:
+			exclude_profiles = self._fix_X_N_search(exclude_profiles)
 			exclude_profiles = [ self.make_profile_explicit(x) for x in exclude_profiles ]
-		#print(include_profiles)
 		# adding accession, lineage, zips, and dates based conditions
 		include_acc = [x for x in accessions if not x.startswith("^")]
 		exclude_acc = [x[1:] for x in accessions if x.startswith("^")]
@@ -2967,6 +2985,8 @@ def match(self,
 
 
 				include_lin = _tmp_include_lin
+			#print(include_profiles)
+			#print(include_lin)
 
 			########################
 			rows = dbm.match(

sonar.py

@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 #author: Stephan Fuchs (Robert Koch Institute, MF1, fuchss@rki.de)
 
-VERSION = "1.1.4"
+VERSION = "1.1.5"
 import os
 from posixpath import split
 import sys
@@ -82,7 +82,7 @@ def parse_args():
 	parser_match_g2 = parser_match.add_mutually_exclusive_group()
 	parser_match_g2.add_argument('--only_frameshifts', help="show only genomes containing one or more frameshift mutations", action="store_true")
 	parser_match_g2.add_argument('--no_frameshifts', help="show only genomes containing no frameshift mutation", action="store_true")
-	parser_match_g2.add_argument('--tsv', help="use tsv instead of csv output", action="store_true")
+	parser_match.add_argument('--tsv', help="use tsv instead of csv output", action="store_true")
 	parser_match.add_argument('--debug', help="show database query for debugging", action="store_true")
 
 	#create the parser for the "restore" command