fix average calculation

app.py

@@ -216,6 +216,8 @@ def gematria_search_interface(phrases: str, max_words: int, show_translation: bo
     results = []
     all_results = []  # Store results for each phrase
     middle_words_results = []  # Store middle word results for all books
+    all_names_average_position = 0  # Initialize variable for average position across all names and books
+    total_name_count = 0  # Initialize counter for the total number of names processed
 
     phrases = phrases.strip().splitlines()
     if not phrases:
@@ -265,13 +267,25 @@ def gematria_search_interface(phrases: str, max_words: int, show_translation: bo
                   <a href='{link}' target='_blank' class='bible-link'>[See on Bible Gateway]</a>
                 </div>
                 """)
-        results.append("</div>")
 
+        # Calculate average position for the current name across all books
+        name_average_position = calculate_average_position_for_name(results_by_book)
+        if name_average_position is not None:
+            results.append(f"<p><b>Average Word Position for '{phrase}' across all books:</b> {name_average_position:.2f}</p>")
+            all_names_average_position += name_average_position
+            total_name_count += 1
+
+        results.append("</div>")
         all_results.append(results_by_book)  # Store results by book without the phrase
 
-    # Calculate middle words for all input lines
+    # Calculate the average word position across all names and all their books
+    if total_name_count > 0:
+        all_names_average_position /= total_name_count
+        results.append(f"<h2>Average Word Position Across All Names and Books: {all_names_average_position:.2f}</h2>")
+
+    # Calculate middle words for all input lines (common books)
     if len(all_results) >= 2:
-        results.append("<h2>Middle Words:</h2>")
+        results.append("<h2>Middle Words (Common Books):</h2>")
         results.append("<div class='results-container'>")
 
         common_books = set.intersection(*[set(results.keys()) for results in all_results])
@@ -356,27 +370,30 @@ def gematria_search_interface(phrases: str, max_words: int, show_translation: bo
         """
     return style + "\n".join(results)
 
+def calculate_average_position_for_name(results_by_book: Dict[str, List[Tuple]]) -> float:
+    """Calculates the average word position for a single name across all books."""
+    positions = []
+    for book, phrases in results_by_book.items():
+        for _, _, _, _, word_position in phrases:
+            start, end = map(int, word_position.split('-'))
+            positions.append((start + end) / 2)
+    return sum(positions) / len(positions) if positions else None
+
 def find_nearest_positions(results_lists: List[List]) -> List[int]:
     """Finds the nearest word positions among multiple lists of results."""
     nearest_positions = []
     for i in range(len(results_lists)):
-        positions_i = [(int(pos.split('-')[0]), int(pos.split('-')[1])) for _, _, _, _, pos in results_lists[i]]  # Get start and end positions
-        min_distance = float('inf')
-        nearest_pos_start = None
-        nearest_pos_end = None
-        for j in range(len(results_lists)):
-            if i == j:
-                continue
-            positions_j = [(int(pos.split('-')[0]), int(pos.split('-')[1])) for _, _, _, _, pos in results_lists[j]]  # Get start and end positions
-            for pos_i_start, pos_i_end in positions_i:
-                for pos_j_start, pos_j_end in positions_j:
-                    distance = abs((pos_i_start + pos_i_end) // 2 - (pos_j_start + pos_j_end) // 2)
-                    if distance < min_distance:
-                        min_distance = distance
-                        nearest_pos_start = pos_i_start  # Take the start position from the first list
-                        nearest_pos_end = pos_i_end  # Take the end position from the first list
-        if nearest_pos_start is not None and nearest_pos_end is not None:
-            nearest_positions.extend([nearest_pos_start, nearest_pos_end])
+        positions_i = [(int(pos.split('-')[0]) + int(pos.split('-')[1])) / 2
+                       for _, _, _, _, pos in results_lists[i]]  # Get average of start and end positions
+        logging.debug(f"Positions for phrase {i+1}: {positions_i}")
+
+        # Calculate the average position for the current phrase
+        average_position = sum(positions_i) / len(positions_i) if positions_i else None
+        logging.debug(f"Average position for phrase {i+1}: {average_position}")
+
+        if average_position is not None:
+            nearest_positions.append(average_position)
+
     return nearest_positions