Structure data mvp (#452)

* Structured data tech spec

* Architecture principles

* New schemas

* Updated schemas and specs

* Object extractor

* Add .coveragerc

* New tests

* Cassandra object storage

* Trying to object extraction working, issues exist

trustgraph-base/trustgraph/messaging/translators/__init__.py

@@ -1,5 +1,5 @@
 from .base import Translator, MessageTranslator
-from .primitives import ValueTranslator, TripleTranslator, SubgraphTranslator
+from .primitives import ValueTranslator, TripleTranslator, SubgraphTranslator, RowSchemaTranslator, FieldTranslator, row_schema_translator, field_translator
 from .metadata import DocumentMetadataTranslator, ProcessingMetadataTranslator
 from .agent import AgentRequestTranslator, AgentResponseTranslator
 from .embeddings import EmbeddingsRequestTranslator, EmbeddingsResponseTranslator

trustgraph-base/trustgraph/messaging/translators/primitives.py

@@ -1,5 +1,5 @@
 from typing import Dict, Any, List
-from ...schema import Value, Triple
+from ...schema import Value, Triple, RowSchema, Field
 from .base import Translator
 
 
@@ -44,4 +44,97 @@ class SubgraphTranslator(Translator):
         return [self.triple_translator.to_pulsar(t) for t in data]
     
     def from_pulsar(self, obj: List[Triple]) -> List[Dict[str, Any]]:
-        return [self.triple_translator.from_pulsar(t) for t in obj]
+        return [self.triple_translator.from_pulsar(t) for t in obj]
+
+
+class RowSchemaTranslator(Translator):
+    """Translator for RowSchema objects"""
+    
+    def to_pulsar(self, data: Dict[str, Any]) -> RowSchema:
+        """Convert dict to RowSchema Pulsar object"""
+        fields = []
+        for field_data in data.get("fields", []):
+            field = Field(
+                name=field_data.get("name", ""),
+                type=field_data.get("type", "string"),
+                size=field_data.get("size", 0),
+                primary=field_data.get("primary", False),
+                description=field_data.get("description", ""),
+                required=field_data.get("required", False),
+                indexed=field_data.get("indexed", False),
+                enum_values=field_data.get("enum_values", [])
+            )
+            fields.append(field)
+        
+        return RowSchema(
+            name=data.get("name", ""),
+            description=data.get("description", ""),
+            fields=fields
+        )
+    
+    def from_pulsar(self, obj: RowSchema) -> Dict[str, Any]:
+        """Convert RowSchema Pulsar object to JSON-serializable dictionary"""
+        result = {
+            "name": obj.name,
+            "description": obj.description,
+            "fields": []
+        }
+        
+        for field in obj.fields:
+            field_dict = {
+                "name": field.name,
+                "type": field.type,
+                "size": field.size,
+                "primary": field.primary,
+                "description": field.description,
+                "required": field.required,
+                "indexed": field.indexed
+            }
+            
+            # Handle enum_values array
+            if field.enum_values:
+                field_dict["enum_values"] = list(field.enum_values)
+            
+            result["fields"].append(field_dict)
+        
+        return result
+
+
+class FieldTranslator(Translator):
+    """Translator for Field objects"""
+    
+    def to_pulsar(self, data: Dict[str, Any]) -> Field:
+        """Convert dict to Field Pulsar object"""
+        return Field(
+            name=data.get("name", ""),
+            type=data.get("type", "string"),
+            size=data.get("size", 0),
+            primary=data.get("primary", False),
+            description=data.get("description", ""),
+            required=data.get("required", False),
+            indexed=data.get("indexed", False),
+            enum_values=data.get("enum_values", [])
+        )
+    
+    def from_pulsar(self, obj: Field) -> Dict[str, Any]:
+        """Convert Field Pulsar object to JSON-serializable dictionary"""
+        result = {
+            "name": obj.name,
+            "type": obj.type,
+            "size": obj.size,
+            "primary": obj.primary,
+            "description": obj.description,
+            "required": obj.required,
+            "indexed": obj.indexed
+        }
+        
+        # Handle enum_values array
+        if obj.enum_values:
+            result["enum_values"] = list(obj.enum_values)
+        
+        return result
+
+
+# Create singleton instances for easy access
+row_schema_translator = RowSchemaTranslator()
+field_translator = FieldTranslator()