Python files to add terms to both the concepts and relations.

This step is necessary so that data uploaded to Neo4j can be easily searched for.

config/config.ini

@@ -0,0 +1,4 @@
+[FileSection]
+descfile = snomed_files/sct2_Description_Snapshot-en-AU_AU1000168_20150531.txt
+conceptfile = snomed_files/sct2_Concept_Snapshot_AU1000168_20150531.txt
+relfile = snomed_files/sct2_Relationship_Snapshot_AU1000168_20150531.txt

config/read_config.py

@@ -0,0 +1,20 @@
+import configparser
+import os
+
+class SnomedConfig:
+    Config = configparser.ConfigParser()
+    Config.read(os.path.join(os.path.abspath(os.path.dirname(__file__)), 'config.ini'))
+
+    def ConfigSectionMap(self, section):
+        configMap = {}
+        options = self.Config.options(section)
+        for option in options:
+            try:
+                configMap[option] = self.Config.get(section, option)
+                if configMap[option] == -1:
+                    DebugPrint("skip: %s" % option)
+            except:
+                print("exception on %s!" % option)
+                configMap[option] = None
+        return configMap
+

import_Concepts_tsv.py

@@ -0,0 +1,38 @@
+from config.read_config import SnomedConfig
+import csv
+import os
+
+sc = SnomedConfig().ConfigSectionMap("FileSection")
+dir = os.path.dirname(__file__)
+descFile = os.path.join(dir, sc["descfile"])
+conceptFile = os.path.join(dir, sc["conceptfile"])
+
+with open(descFile, "rt", encoding='utf-8') as tsvin, open("new.csv", "wb") as tsvout:
+    dictReader = csv.DictReader(tsvin, delimiter="\t")
+    csv.writer(tsvout)
+
+    desc_result = dict(
+        (v['conceptId'], v['term']) for v in dictReader
+    )
+
+
+with open(conceptFile, 'rt', encoding='utf-8') as infile:
+    with open('conceptOutFile.csv', 'wt', encoding='utf-8') as outfile:
+        reader = csv.DictReader(infile, delimiter="\t")
+        print(reader.fieldnames)
+        # Use the same field names for the output file.
+        fieldnames = ['id', 'effectiveTime', 'active', 'moduleId', 'definitionStatusId', 'term']
+        writer = csv.DictWriter(outfile, fieldnames)
+        writer.writeheader()
+
+        # Iterate over the products in the input.
+
+        for concept in reader:
+            print(concept)
+            result = desc_result.get(concept['id'], " ")
+
+            # Update the product info.
+            concept['term'] = result
+
+            # Write it to the output file.
+            writer.writerow(concept)

import_Rel_tsv.py

@@ -0,0 +1,39 @@
+from config.read_config import SnomedConfig
+import csv
+import os
+
+sc = SnomedConfig().ConfigSectionMap("FileSection")
+dir = os.path.dirname(__file__)
+descFile = os.path.join(dir, sc["descfile"])
+conceptFile = os.path.join(dir, sc["conceptfile"])
+relFile = os.path.join(dir, sc["relfile"])
+
+with open(descFile, "rt", encoding='utf-8') as tsvin, open("new.csv", "wb") as tsvout:
+    dictReader = csv.DictReader(tsvin, delimiter="\t")
+    csv.writer(tsvout)
+
+    desc_result = dict(
+        (v['conceptId'], v['term']) for v in dictReader
+    )
+
+
+with open(relFile, 'rt', encoding='utf-8') as infile:
+    with open('relOutFile.csv', 'wt', encoding='utf-8') as outfile:
+        reader = csv.DictReader(infile, delimiter="\t")
+        print(reader.fieldnames)
+        # Use the same field names for the output file.
+        fieldnames = ['id', 'effectiveTime', 'active', 'moduleId', 'sourceId', 'destinationId', 'relationshipGroup', 'typeId', 'characteristicTypeId', 'modifierId', 'term']
+        writer = csv.DictWriter(outfile, fieldnames)
+        writer.writeheader()
+
+        # Iterate over the products in the input.
+
+        for rel in reader:
+            print(rel)
+            result = desc_result.get(rel['typeId'], " ")
+
+            # Update the product info.
+            rel['term'] = result
+
+            # Write it to the output file.
+            writer.writerow(rel)