Update app.py

app.py

@@ -2,45 +2,69 @@ import gradio as gr
 import pytesseract
 from pdf2image import convert_from_path
 from PIL import Image
+import os
 
-# لیست زبان‌هایی که می‌خوای همزمان پشتیبانی بشن
-# (حتماً باید پکیج زبان‌ها روی تسرکت نصب باشن)
-AUTO_LANGS = "eng+fas+ara+rus+spa+fra"
-
-def ocr_auto(input_file):
+# Function to perform OCR
+def ocr(input_file, lang='fas'):  # 'fas': Persian language (Farsi)
     extracted_text = ""
-
-    if isinstance(input_file, str) and input_file.endswith('.pdf'):
+    
+    # Check if the input file is a PDF or an image
+    if isinstance(input_file, str) and input_file.endswith('.pdf'):  # Check if the file is a PDF
+        # Convert PDF to images
         images = convert_from_path(input_file)
-        for page_number, image in enumerate(images, start=1):
-            text = pytesseract.image_to_string(image, lang=AUTO_LANGS)
-            extracted_text += f"\n--- Page {page_number} ---\n{text}"
-    elif isinstance(input_file, Image.Image):
-        extracted_text = pytesseract.image_to_string(input_file, lang=AUTO_LANGS)
+        
+        # Loop through each image and perform OCR
+        for page_number, image in enumerate(images):
+            text = pytesseract.image_to_string(image, lang=lang)
+            extracted_text += text
 
-    return extracted_text.strip()
+    elif isinstance(input_file, Image.Image):  # If the input is an image
+        text = pytesseract.image_to_string(input_file, lang=lang)
+        extracted_text = text
+
+    return extracted_text
 
 def gradio_interface():
+    # Define Gradio inputs and outputs
     input_type = gr.Radio(["PDF", "Image"], label="Choose Input Type", value="PDF")
-    file_input = gr.File(label="Upload PDF/Image", file_types=[".pdf", ".png", ".jpg", ".jpeg"])
+    file_input = gr.File(label="Upload PDF/Image")
+    language_input = gr.Dropdown(
+        label="Select OCR Language",
+        choices=[
+            ("English", "eng"),
+            ("Mandarin Chinese", "chi_sim"),
+            ("Hindi", "hin"),
+            ("Spanish", "spa"),
+            ("French", "fra"),
+            ("Standard Arabic", "ara"),
+            ("Bengali", "ben"),
+            ("Portuguese", "por"),
+            ("Russian", "rus"),
+            ("Urdu", "urd"),
+            ("Persian (Farsi)", "fas")
+        ],
+        value="fas"  # Default to Persian
+    )
     output_text = gr.Textbox(label="Extracted Text", interactive=False)
 
-    def process(input_type, file):
-        if not file:
-            return "⚠️ Please upload a file first."
+    # Function to process the inputs and return the outputs
+    def process(input_type, file, lang):
         if input_type == "PDF":
-            return ocr_auto(file.name)
+            extracted_text = ocr(file.name, lang)
         else:
             image = Image.open(file.name)
-            return ocr_auto(image)
+            extracted_text = ocr(image, lang)
+        return extracted_text
 
+    # Create and launch Gradio interface
     gr.Interface(
         fn=process,
-        inputs=[input_type, file_input],
+        inputs=[input_type, file_input, language_input],
         outputs=[output_text],
-        title="Auto OCR (PDF/Image)",
-        description="Upload a PDF or Image. OCR will automatically detect and extract text in multiple languages."
+        title="OCR (PDF/Image)",
+        description="Upload a PDF or Image, select the OCR language, and extract the text."
     ).launch()
 
-# Run
+
+# Call the function to create the interface
 gradio_interface()