add comp back

generic_ner.py

@@ -263,46 +263,30 @@ def conflicting_context(comp_entity, target_entity):
 def extract_name_from_text(text, partial_name):
     """
     Extracts the full name from the entity's text based on the partial name.
-    This function starts from the partial name, checks backward for the last capitalized word,
-    and includes all words from that point up to the partial name, including any lowercase words in between.
+    This function assumes that the full name starts with capitalized letters and goes backward
+    to include all capitalized words leading up to the partial name.
     """
+    # Split the text and partial name into words
+    words = text.split()
+    partial_words = partial_name.split()
 
-    print("text", text, "partial_name", partial_name)
+    # Find the position of the partial name in the word list
+    for i, word in enumerate(words):
+        if words[i:i + len(partial_words)] == partial_words:
+            # Initialize full name with the partial name
+            full_name = partial_words[:]
 
-    # Find the position of the partial name in the text
-    name_start_idx = text.find(partial_name)
+            # Check previous words and only add capitalized words (skip lowercase words)
+            j = i - 1
+            while j >= 0 and words[j][0].isupper():
+                full_name.insert(0, words[j])
+                j -= 1
 
-    print("textsss", text[:name_start_idx])
-
-    if name_start_idx != -1:
-        # Split the text into words
-        words = text.split()
-
-        # Find the position of the partial name in the word list
-        for i, word in enumerate(words):
-            if partial_name in word:
-                # Initialize full name with the partial name
-                full_name = [word]
-
-                # Check previous words to find the first capitalized word (include all in between)
-                j = i - 1
-                while j >= 0:
-                    # As soon as we find a capitalized word, stop going backward
-                    if words[j][0].isupper():
-                        full_name.insert(0, words[j])
-                    else:
-                        # Continue adding lowercase words like titles (e.g., 'chancelier')
-                        full_name.insert(0, words[j])
-                    j -= 1
-
-                return " ".join(
-                    full_name
-                ).strip()  # Join the words to form the full name
+            return ' '.join(full_name).strip()  # Join the words to form the full name
 
     # If not found, return the original text (as a fallback)
     return text.strip()
 
-
 def repair_names_in_entities(entities):
     """
     This function repairs the names in the entities by extracting the full name