BUGFIX: image processing only handles filenames with jpg

2023-09-21 14:42:47 +03:00
parent e96f23ddc8
commit 963d99404e
1 changed files with 5 additions and 1 deletions
@@ -44,7 +44,11 @@ def convert_image(image_path):

 def ocr_image(image_path):
    logging.info(f"OCR'ing {image_path}...")
-    text_filename = os.path.basename(image_path).replace(".jpg", ".txt")
+    
+    base_name = os.path.basename(image_path)
+    root_name, _ = os.path.splitext(base_name)
+    text_filename = f"{root_name}.txt"
+    
    text_path = os.path.join(CONVERTED_DIR, text_filename)
    cmd = ["tesseract", image_path, text_path.replace(".txt", "")]
    try: