Auto-update: Sun Nov 3 12:08:45 PST 2024

aax2mp3

@@ -5,6 +5,10 @@ import subprocess
 import glob
 import os
 import multiprocessing
+import re
+import nltk
+from nltk.corpus import words
+from nltk.corpus import wordnet
 
 # Different ways to get CPU count
 logical_cores = os.cpu_count()  # All cores including hyperthreading
@@ -24,6 +28,59 @@ def convert_file(aax_file):
     print(f"Converting {aax_file} to {mp3_file}")
     subprocess.run(['ffmpeg', '-activation_bytes', os.getenv('AUDIBLE_ACTIVATION_BYTES'),
                    '-i', aax_file, mp3_file], check=True)
+    return mp3_file
+
+def rename_file(mp3_file):
+    print(f"\n{'='*50}")
+    print(f"Original: {mp3_file}")
+    base, ext = os.path.splitext(mp3_file)
+    new_base = rename_base(base)
+    new_name = new_base + ext
+    print(f"New name: {new_name}")
+
+    if new_name != mp3_file:
+        try:
+            os.rename(mp3_file, new_name)
+            print(f"Renamed: {mp3_file} -> {new_name}")
+        except OSError as e:
+            print(f"Error renaming {mp3_file}: {e}")
+
+def rename_base(base):
+    words = re.split('(?<!^)(?=[A-Z])', base)
+    processed = [process_word(word) for word in words]
+    return ' '.join(''.join(processed).split())
+
+def process_word(word):
+    if word.lower() in always_valid:
+        return word
+
+    if word.lower() in word_set:
+        return word
+
+    for common in common_words:
+        if word.lower().endswith(common):
+            remainder = word[:-len(common)]
+            common_case = word[-len(common):]
+            return process_word(remainder) + ' ' + common_case
+
+    match = re.search(r'([a-zA-Z]+)(\d+)$', word)
+    if match:
+        text, num = match.groups()
+        if text.lower() in word_set:
+            return text + ' ' + num
+
+    return word
+
+word_set = set(word.lower() for word in words.words())
+common_words = ['and', 'in', 'the', 'of', 'to', 'at', 'by', 'for', 'with', 'from']
+always_valid = {'the', 'a', 'an', 'and', 'or', 'but', 'nor', 'for', 'yet', 'so'}
+try:
+    word_list = words.words()
+    nltk.download('wordnet')
+except LookupError:
+    nltk.download('words')
+    nltk.download('wordnet')
+    word_list = words.words()
 
 aax_files = glob.glob('*.aax')
 if not aax_files:
@@ -34,5 +91,8 @@ print(f"Found {len(aax_files)} files to convert")
 print(f"Will convert {max_workers} files simultaneously")
 
 with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
-    list(executor.map(convert_file, aax_files))
+    mp3_files = list(executor.map(convert_file, aax_files))
+
+for mp3_file in mp3_files:
+    rename_file(mp3_file)