add comp back

generic_ner.py

@@ -297,29 +297,30 @@ def attach_comp_to_closest(entities):
         closest_entity = None
         min_distance = float("inf")
 
-        # Find the closest non-"comp.function" entity that is valid for attaching
+        # Find the closest non-"comp" entity that is valid for attaching
         for other_entity in other_entities:
-            distance = abs(
-                comp_entity["lOffset"] - other_entity["rOffset"]
-            )  # Calculate the distance
+            # Calculate distance between the comp entity and the other entity
+            if comp_entity["lOffset"] > other_entity["rOffset"]:
+                distance = comp_entity["lOffset"] - other_entity["rOffset"]
+            elif comp_entity["rOffset"] < other_entity["lOffset"]:
+                distance = other_entity["lOffset"] - comp_entity["rOffset"]
+            else:
+                distance = 0  # They overlap or touch
 
-            # Ensure that the other entity's type is valid for the attachment
+            # Ensure the entity type is valid and check for minimal distance
             if (
                 distance < min_distance
                 and other_entity["type"].split(".")[0] in valid_entity_types
             ):
-                # Additional context check: Ensure the comp_entity's text doesn't conflict with the target entity's text
-                if not conflicting_context(comp_entity, other_entity):
-                    min_distance = distance
-                    closest_entity = other_entity
+                min_distance = distance
+                closest_entity = other_entity
 
-        # Attach the "comp.function" entity using the suffix of 'entity' field if a valid entity is found
+        # Attach the "comp.function" or "comp.name" if a valid entity is found
         if closest_entity:
-            # Extract the suffix (e.g., "comp.title" becomes "title")
-            suffix = comp_entity["type"].split(".")[-1]
-            closest_entity[suffix] = comp_entity[
-                "surface"
-            ]  # Attach the text using the suffix as the key
+            suffix = comp_entity["type"].split(".")[
+                -1
+            ]  # Extract the suffix (e.g., 'name', 'function')
+            closest_entity[suffix] = comp_entity["surface"]  # Attach the text
 
     return other_entities
 
@@ -329,21 +330,12 @@ def conflicting_context(comp_entity, target_entity):
     Determines if there is a conflict between the comp_entity and the target entity.
     Prevents incorrect name and function attachments by using a rule-based approach.
     """
-    comp_text = comp_entity["surface"].lower()
-    target_text = target_entity["surface"].lower()
-
-    # Case 1: Check if the comp.name is already part of the entity's text.
-    # if "pers" in target_entity["type"] and comp_entity["type"].startswith("comp.name"):
-    #     # Avoid attaching a name if it's already part of the entity's surface text.
-    #     if comp_text in target_text:
-    #         return True  # Conflict: Name is already part of the target entity's text
-
-    # Case 2: Check for correct function attachment to person or organization entities
+    # Case 1: Check for correct function attachment to person or organization entities
     if comp_entity["type"].startswith("comp.function"):
         if not ("pers" in target_entity["type"] or "org" in target_entity["type"]):
             return True  # Conflict: Function should only attach to persons or organizations
 
-    # Case 3: Avoid attaching comp.* entities to non-person, non-organization types (like locations)
+    # Case 2: Avoid attaching comp.* entities to non-person, non-organization types (like locations)
     if "loc" in target_entity["type"]:
         return True  # Conflict: comp.* entities should not attach to locations or similar types