add hitcount to search index

.gitignore

@@ -7,6 +7,7 @@
 /postgres_data
 /instance
 /__pycache__
+/search.db
 /access_log.db
 /access_log.db.bak
 /folder_config.json

index_for_search.py

@@ -3,13 +3,20 @@ import json
 import sqlite3
 
 SEARCH_DB_NAME = 'search.db'
+ACCESS_LOG_DB_NAME = 'access_log.db'
 
+# Connect to the search database.
 search_db = sqlite3.connect(SEARCH_DB_NAME, check_same_thread=False)
 search_db.row_factory = sqlite3.Row
 
+# Open access_log.db in read-only mode.
+access_log_db = sqlite3.connect(f'file:{ACCESS_LOG_DB_NAME}?mode=ro', uri=True)
+access_log_db.row_factory = sqlite3.Row
+
 def init_db():
     """Initializes the database with the required schema."""
     cursor = search_db.cursor()
+    # Create table with the new 'hitcount' column.
     cursor.execute('''
         CREATE TABLE IF NOT EXISTS files (
             id INTEGER PRIMARY KEY AUTOINCREMENT,
@@ -17,10 +24,18 @@ def init_db():
             filename TEXT,
             filetype TEXT,
             transcript TEXT,
+            hitcount INTEGER DEFAULT 0,
             UNIQUE(relative_path, filename)
         )
     ''')
     search_db.commit()
+    # If the table already existed, try to add the 'hitcount' column.
+    try:
+        cursor.execute("ALTER TABLE files ADD COLUMN hitcount INTEGER DEFAULT 0")
+    except sqlite3.OperationalError:
+        # Likely the column already exists, so we ignore this error.
+        pass
+    search_db.commit()
 
 def scan_dir(directory):
     """Recursively scan directories using os.scandir for improved performance."""
@@ -37,6 +52,13 @@ def scan_dir(directory):
     except PermissionError:
         return
 
+def get_hit_count(relative_path):
+    """Returns the hit count for a given file from the access log database."""
+    cursor = access_log_db.cursor()
+    cursor.execute("SELECT COUNT(*) AS hit_count FROM file_access_log WHERE rel_path = ?", (relative_path,))
+    row = cursor.fetchone()
+    return row["hit_count"] if row else 0
+
 def updatefileindex():
     cursor = search_db.cursor()
 
@@ -54,7 +76,7 @@ def updatefileindex():
             base_len = len(norm_folderpath) + 1
 
             # Accumulate scanned file data and keys for this base folder.
-            scanned_files = []  # Each entry: (relative_path, filename, filetype, transcript)
+            scanned_files = []  # Each entry: (relative_path, filename, filetype, transcript, hitcount)
             current_keys = set()
 
             for entry in scan_dir(norm_folderpath):
@@ -66,7 +88,6 @@ def updatefileindex():
                     rel_part = os.path.relpath(entry_path, norm_folderpath)
                 # Prepend the foldername so it becomes part of the stored relative path.
                 relative_path = os.path.join(foldername, rel_part).replace(os.sep, '/')
-                print(relative_path)
                 filetype = os.path.splitext(entry.name)[1].lower()
                 transcript = None
 
@@ -82,7 +103,10 @@ def updatefileindex():
                     except Exception:
                         transcript = None
 
-                scanned_files.append((relative_path, entry.name, filetype, transcript))
+                # Retrieve the hit count for this file.
+                hit_count = get_hit_count(relative_path)
+
+                scanned_files.append((relative_path, entry.name, filetype, transcript, hit_count))
                 current_keys.add((relative_path, entry.name))
 
             # Remove database entries for files under this base folder that are no longer on disk.
@@ -96,7 +120,7 @@ def updatefileindex():
 
             # Bulk write the scanned files using INSERT OR REPLACE.
             cursor.executemany(
-                "INSERT OR REPLACE INTO files (relative_path, filename, filetype, transcript) VALUES (?, ?, ?, ?)",
+                "INSERT OR REPLACE INTO files (relative_path, filename, filetype, transcript, hitcount) VALUES (?, ?, ?, ?, ?)",
                 scanned_files
             )
 
@@ -105,9 +129,9 @@ def updatefileindex():
 
     return "File index updated successfully"
 
-
 if __name__ == "__main__":
     init_db()  # Initialize the database schema if it doesn't exist
     updatefileindex()  # Update the file index
-    search_db.close()  # Close the database connection
+    search_db.close()  # Close the search database connection
-    print("Database connection closed.")
+    access_log_db.close()  # Close the access log connection
+    print("Database connections closed.")