translation cache for cli version

cli_clock.py

@@ -7,6 +7,7 @@ import pytz
 from deep_translator import GoogleTranslator
 from deep_translator.exceptions import NotValidLength, RequestError
 from utils import process_json_files, flatten_text_with_line_breaks, build_word_index
+import sqlite3 # Import sqlite3 for database handling
 
 # Set up logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
@@ -15,77 +16,101 @@ logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(
 TANACH_DATA = process_json_files(1, 39)
 WORD_INDEX = build_word_index(TANACH_DATA)
 
-# --- Translation Cache ---
-translation_cache = {}
-
-def translate_chapter(hebrew_chapter):
-    """Translates a Hebrew chapter to English, caching the result."""
-    if hebrew_chapter in translation_cache:
-        return translation_cache[hebrew_chapter]
-
-    try:
-        translator = GoogleTranslator(source='iw', target='en')
-        max_length = 2000  # Slightly below the limit to be safe
-        translated_text = ""
-
-        # Split the chapter into chunks smaller than the max length
-        chunks = [hebrew_chapter[i:i + max_length] for i in range(0, len(hebrew_chapter), max_length)]
-
-        for chunk in chunks:
-            translated_text += translator.translate(chunk)
-
-        translation_cache[hebrew_chapter] = translated_text.split('\n') # Store as list of lines
-        return translation_cache[hebrew_chapter]
-
-    except RequestError as e:
-        logging.warning(f"Translation failed: Request Error - {e}")
-        return ["Translation unavailable: Request Error"]
+# --- Database Setup ---
+conn = sqlite3.connect('translation_cache.db') # Create or connect to database
+cursor = conn.cursor()
+cursor.execute('''
+  CREATE TABLE IF NOT EXISTS translations (
+      book_id INTEGER,
+      chapter_id INTEGER,
+      english_text TEXT,
+      PRIMARY KEY (book_id, chapter_id)
+  )
+''')
+conn.commit()
+
+def translate_chapter(hebrew_chapter, book_id, chapter_id):
+  """Translates a Hebrew chapter to English, caching the result in the database."""
+
+  # Check if translation exists in the database
+  cursor.execute(
+      "SELECT english_text FROM translations WHERE book_id=? AND chapter_id=?",
+      (book_id, chapter_id)
+  )
+  result = cursor.fetchone()
+
+  if result:
+    return result[0].split('\n') # Retrieve from database and split into lines
+
+  try:
+    translator = GoogleTranslator(source='iw', target='en')
+    max_length = 2000 # Slightly below the limit to be safe
+    translated_text = ""
+
+    # Split the chapter into chunks smaller than the max length
+    chunks = [hebrew_chapter[i:i + max_length] for i in range(0, len(hebrew_chapter), max_length)]
+
+    for chunk in chunks:
+      translated_text += translator.translate(chunk)
+
+    # Store the translation in the database
+    cursor.execute(
+      "INSERT INTO translations (book_id, chapter_id, english_text) VALUES (?, ?, ?)",
+      (book_id, chapter_id, translated_text)
+    )
+    conn.commit()
+
+    return translated_text.split('\n') # Return as list of lines
+
+  except RequestError as e:
+    logging.warning(f"Translation failed: Request Error - {e}")
+    return ["Translation unavailable: Request Error"]
 
 def display_current_verse():
-    """Displays the verse corresponding to the current time."""
-    while True:
-        now = datetime.datetime.now()
-        current_time_str = now.strftime("%H:%M:%S")
-
-        word_data, _ = get_current_word_data(current_time_str)
-        if word_data is None:
-            logging.error("Word data not found for current time.")
-            time.sleep(1)
-            continue
-
-        book_id = word_data["book_id"]
-        chapter_id = word_data["chapter_id"]
-        verse_id = word_data["verse_id"]
-
-        hebrew_chapter = flatten_text_with_line_breaks(TANACH_DATA[book_id]["text"][chapter_id])
-        english_chapter = translate_chapter('\n'.join(hebrew_chapter))
-
-        print("\033c", end="")  # Clear the terminal
-        print(f"Time: {current_time_str}")
-        print(f"{TANACH_DATA[book_id]['title']}, Chapter {chapter_id + 1}, Verse {verse_id}")
-        print("-" * 30)
-        print(hebrew_chapter[verse_id - 1])
-        print(english_chapter[verse_id - 1]) # Display corresponding English line
-        print("-" * 30)
-        time.sleep(1)
+  """Displays the verse corresponding to the current time."""
+  while True:
+    now = datetime.datetime.now()
+    current_time_str = now.strftime("%H:%M:%S")
+
+    word_data, _ = get_current_word_data(current_time_str)
+    if word_data is None:
+      logging.error("Word data not found for current time.")
+      time.sleep(1)
+      continue
+
+    book_id = word_data["book_id"]
+    chapter_id = word_data["chapter_id"]
+    verse_id = word_data["verse_id"]
+
+    hebrew_chapter = flatten_text_with_line_breaks(TANACH_DATA[book_id]["text"][chapter_id])
+    english_chapter = translate_chapter('\n'.join(hebrew_chapter), book_id, chapter_id)
+
+    print("\033c", end="") # Clear the terminal
+    print(f"Time: {current_time_str}")
+    print(f"{TANACH_DATA[book_id]['title']}, Chapter {chapter_id + 1}, Verse {verse_id}")
+    print("-" * 30)
+    print(hebrew_chapter[verse_id - 1])
+    print(english_chapter[verse_id - 1]) # Display corresponding English line
+    print("-" * 30)
+    time.sleep(1)
 
 # --- Utility Functions --- (Same as before)
 
 def get_current_word_data(client_time_str):
-    """Gets data about the current word based on the client's time."""
-    try:
-        client_time = datetime.datetime.strptime(client_time_str, "%H:%M:%S")
-        total_seconds = int(client_time.strftime("%H")) * 3600 + \
-                        int(client_time.strftime("%M")) * 60 + \
-                        int(client_time.strftime("%S"))
+  """Gets data about the current word based on the client's time."""
+  try:
+    client_time = datetime.datetime.strptime(client_time_str, "%H:%M:%S")
+    total_seconds = int(client_time.strftime("%H")) * 3600 + \
+            int(client_time.strftime("%M")) * 60 + \
+            int(client_time.strftime("%S"))
 
-        # Find the closest key in WORD_INDEX
-        word_position = min(WORD_INDEX.keys(), key=lambda k: abs(k - total_seconds))
+    # Find the closest key in WORD_INDEX
+    word_position = min(WORD_INDEX.keys(), key=lambda k: abs(k - total_seconds))
 
-        return WORD_INDEX[word_position], word_position
-    except Exception as e:
-        logging.error(f"Error processing client time: {e}")
-        return None, None
+    return WORD_INDEX[word_position], word_position
+  except Exception as e:
+    logging.error(f"Error processing client time: {e}")
+    return None, None
 
 if __name__ == "__main__":
-    display_current_verse()
+  display_current_verse()