Feature: document metadata (#123)

* Rework metadata structure in processing messages to be a subgraph
* Add subgraph creation for tg-load-pdf and tg-load-text based on command-line passing of doc attributes
* Document metadata is added to knowledge graph with subjectOf linkage to extracted entities

trustgraph-base/trustgraph/knowledge/identifier.py

@@ -0,0 +1,23 @@
+
+import uuid
+import hashlib
+
+def hash(data):
+
+    if isinstance(data, str):
+        data = data.encode("utf-8")
+
+    # Create a SHA256 hash from the data
+    id = hashlib.sha256(data).hexdigest()
+
+    # Convert into a UUID, 64-byte hash becomes 32-byte UUID
+    id = str(uuid.UUID(id[::2]))
+
+    return id
+
+def to_uri(pref, id):
+    return f"https://trustgraph.ai/{pref}/{id}"
+
+PREF_PUBEV = "pubev"
+PREF_ORG = "org"
+PREF_DOC = "doc"