Update app.py

app.py

@@ -3,7 +3,12 @@ import whisper
 import os
 from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
 from docx import Document
-from fpdf import FPDF
+from reportlab.pdfgen import canvas
+from reportlab.pdfbase.ttfonts import TTFont
+from reportlab.pdfbase import pdfmetrics
+from reportlab.lib.pagesizes import A4
+import arabic_reshaper
+from bidi.algorithm import get_display
 from pptx import Presentation
 import subprocess
 import shlex
@@ -106,18 +111,53 @@ def reverse_text_for_rtl(text):
 
 # Helper function to write PDF documents
 def write_pdf(transcription, output_file, tokenizer=None, translation_model=None):
-    pdf = FPDF()
-    pdf.add_page()
-    font_path = "/home/user/app/B-NAZANIN.TTF"
-    pdf.add_font('B-NAZANIN', '', font_path, uni=True)
-    pdf.set_font('B-NAZANIN', size=12)
+    # Create PDF with A4 page size
+    c = canvas.Canvas(output_file, pagesize=A4)
+    
+    # Register the B-Nazanin font
+    font_path = "/usr/share/fonts/truetype/custom/B-NAZANIN.TTF"  # Update this path as needed
+    try:
+        pdfmetrics.registerFont(TTFont('B-Nazanin', font_path))
+    except Exception as e:
+        raise RuntimeError(f"Error registering font: {e}. Please ensure B-NAZANIN.TTF is available at {font_path}")
+    
+    # Set font and size
+    c.setFont('B-Nazanin', 12)
+    
+    # Initialize y position from top of page
+    y_position = A4[1] - 50  # Start 50 points from top
+    line_height = 20
+    
+    # Process each segment
     for i, segment in enumerate(transcription['segments']):
         text = segment['text']
+        
+        # Translate if translation model is provided
         if translation_model:
             text = translate_text(text, tokenizer, translation_model)
-        reversed_text = reverse_text_for_rtl(text)
-        pdf.multi_cell(0, 10, f"{i + 1}. {reversed_text.strip()}", align='L')
-    pdf.output(output_file)
+        
+        # Format the line with segment number
+        line = f"{i + 1}. {text.strip()}"
+        
+        # Reshape and reorder the text for correct RTL display
+        reshaped_text = arabic_reshaper.reshape(line)
+        bidi_text = get_display(reshaped_text)
+        
+        # Add new page if needed
+        if y_position < 50:  # Leave 50 points margin at bottom
+            c.showPage()
+            c.setFont('B-Nazanin', 12)
+            y_position = A4[1] - 50
+        
+        # Draw the text right-aligned
+        c.drawRightString(A4[0] - 50, y_position, bidi_text)  # 50 points margin from right
+        
+        # Update y position for next line
+        y_position -= line_height
+    
+    # Save the PDF
+    c.save()
+    return output_file
 
 # Helper function to write PowerPoint slides
 def write_ppt(transcription, output_file, tokenizer=None, translation_model=None):