renamed container sub_pg in preparation for other changes

README.md

 # ma_code
 
-Dieses Repo beinhaltet den Code und die Datasets zur Bachelorarbeit "Optimierung der Verwaltung von Graph-Daten in einem relationalen DBMS" von Julian Opitz
+Dieses Repo beinhaltet den Code zur Bachelorarbeit "Optimierung der Verwaltung von Graph-Daten in einem relationalen DBMS" von Julian Opitz
 
 ## setup
 
@@ -9,7 +9,7 @@ Folgende dateien herunterladen:
 [ta1-cadets-e3-official-1.json.tar.gz](https://drive.google.com/file/d/1EycO23tEvZVnN3VxOHZ7gdbSCwqEZTI1/view?usp=drive_link)
 [ta1-cadets-e3-official-2.json.tar.gz](https://drive.google.com/file/d/1AcWrYiBmgAqp7DizclKJYYJJBQbnDMfb/view?usp=drive_link)
 
-TODO datenformatierungsscript schreiben
+TODO datenformatierungsscript schreiben (entpacken, umbenennen, in zip komprimieren. alternativ endlich avro verwenden)
 
 postgres_pass und .pgpass müssen unter linux 0600 Berechtigung haben.
 

compose.yml

@@ -12,9 +12,9 @@ services:
       - data.zip
     depends_on: 
       - mosquitto
-      - sub_pg
+      - pg_inserter
 
-  sub_pg:
+  pg_inserter:
     build: streaming/sub/postgres
     environment:
       - MOS_HOST
@@ -49,7 +49,7 @@ services:
     secrets:
       - pgpass
     depends_on:
-      - sub_pg
+      - pg_inserter
 
   mosquitto:
     image: eclipse-mosquitto:latest

edge-id-no-index.yml

@@ -3,7 +3,7 @@ services:
     volumes:
       - ./postgres/initdb/02-initdb_edge_id_no_uuid_index.sql:/docker-entrypoint-initdb.d/02-initdb.sql:ro
 
-  sub_pg:
+  pg_inserter:
     environment:
       - EDGE_INSERTS=EDGE_INSERTS
       - UUID_EDGES=

edge-id-triggers.yml

@@ -4,7 +4,7 @@ services:
       - ./postgres/initdb/02-initdb_edge_id.sql:/docker-entrypoint-initdb.d/02-initdb.sql:ro
       - ./postgres/initdb/03-initdb_trigger_edge_id.sql:/docker-entrypoint-initdb.d/03-initdb.sql:ro
 
-  sub_pg:
+  pg_inserter:
     environment:
       - EDGE_INSERTS=
       - UUID_EDGES=

edge-id.yml

@@ -3,7 +3,7 @@ services:
     volumes:
       - ./postgres/initdb/02-initdb_edge_id.sql:/docker-entrypoint-initdb.d/02-initdb.sql:ro
 
-  sub_pg:
+  pg_inserter:
     environment:
       - EDGE_INSERTS=EDGE_INSERTS
       - UUID_EDGES=

edge-uuid.yml

@@ -3,7 +3,7 @@ services:
     volumes:
       - ./postgres/initdb/02-initdb_edge_uuid.sql:/docker-entrypoint-initdb.d/02-initdb.sql:ro
 
-  sub_pg:
+  pg_inserter:
     environment:
       - EDGE_INSERTS=EDGE_INSERTS
       - UUID_EDGES=UUID_EDGES

streaming/sub/postgres/sub_pg_cdm.py

@@ -11,7 +11,7 @@ import psycopg
 Parameter_Query: TypeAlias = Tuple[str, Iterable[Sequence[Any]]]
 HEADER_SCHEMA: Final[bytes] = b"com.bbn.tc.schema.avro.cdm18."
 NODE_TYPES: Final[dict] = {
-    # python trap: significant trailing commas
+    # Python trap: Tuple with exactly one item must have trailing comma. Can you spot all 3?
     "Event": (
         ("is_generated_by", ("subject", "UUID")),
         ("affects", ("predicateObject", "UUID")),
@@ -30,7 +30,6 @@ NODE_TYPES: Final[dict] = {
     "SrcSinkObject": (),
     "Principal": (),
     "Host": (),
-    # python trap: significant trailing commas
 }
 
 
@@ -71,6 +70,7 @@ def format_edge_uuid(nodes: Sequence[Tuple[str, str, dict]]) -> Parameter_Query:
     return ("INSERT INTO edge (source, destination, type) VALUES (%s, %s, %s)", edges)
 
 
+# currently produces malformed SQL when there are no edges
 def format_edge_id(nodes: Sequence[Tuple[str, str, dict]]) -> Tuple[str, Sequence[str]]:
     edges = [edge for node in nodes for edge in get_edges(*node)]
     query_str = (