add parser for names.dmp from NCBI taxonomy

backend/metagenedb/utils/parsers.py

@@ -48,3 +48,29 @@ def parse_ncbi_taxonomy_node(line):
     except Exception as e:
         _LOGGER.error(f"Could not parse: {line.rstrip()}. Are you sure it comes from nodes.dmp file?")
         raise(e)
+
+
+def parse_ncbi_taxonomy_name(line):
+    """
+    parse line from ncbi names.dmp file
+
+    From documentation:
+
+    Taxonomy names file (names.dmp):
+        tax_id                                  -- the id of node associated with this name
+        name_txt                                -- name itself
+        unique name                             -- the unique variant of this name if name not unique
+        name class                              -- (synonym, common name, ...)
+    """
+    elements = line.rstrip().split('|')
+    try:
+        parsed_line = {
+                "tax_id": elements[0].strip(),
+                "name_txt": elements[1].strip(),
+                "unique_name": elements[2].strip(),
+                "name_class": elements[3].strip(),
+            }
+        return parsed_line
+    except Exception as e:
+        _LOGGER.error(f"Could not parse: {line.rstrip()}. Are you sure it comes from nodes.dmp file?")
+        raise(e)

backend/metagenedb/utils/test_parsers.py

 from unittest import TestCase
 
-from metagenedb.utils.parsers import parse_ncbi_taxonomy_node
+from metagenedb.utils.parsers import parse_ncbi_taxonomy_node, parse_ncbi_taxonomy_name
 
 
 class TestNCBITaxonomyNodeParser(TestCase):
@@ -27,5 +27,24 @@ class TestNCBITaxonomyNodeParser(TestCase):
 
     def test_parse_wrong_line_format(self):
         node_line = "This is a wrong line format."
-        with self.assertRaises(Exception) as context:
-            test_dict = parse_ncbi_taxonomy_node(node_line)
+        with self.assertRaises(Exception) as context:  # noqa
+            parse_ncbi_taxonomy_node(node_line)
+
+
+class TestNCBITaxonomyNameParser(TestCase):
+
+    def test_parse_ncbi_taxonomy_name(self):
+        node_line = "2	|	Bacteria	|	Bacteria <prokaryotes>	|	scientific name	|\n"
+        expected_dict = {
+            "tax_id": "2",
+            "name_txt": "Bacteria",
+            "unique_name": "Bacteria <prokaryotes>",
+            "name_class": "scientific name",
+        }
+        test_dict = parse_ncbi_taxonomy_name(node_line)
+        self.assertDictEqual(test_dict, expected_dict)
+
+    def test_parse_wrong_line_format(self):
+        node_line = "This is a wrong line format."
+        with self.assertRaises(Exception) as context:  # noqa
+            parse_ncbi_taxonomy_name(node_line)