UI and backend for basic OCR functionality

backend/generate_tests.py

@@ -0,0 +1,20 @@
+from reportlab.pdfgen import canvas
+from PIL import Image, ImageDraw
+
+def create_pdf(filename, text):
+    c = canvas.Canvas(filename)
+    c.drawString(100, 750, text)
+    c.save()
+    print(f"Created {filename}")
+
+def create_image(filename, text):
+    img = Image.new('RGB', (400, 100), color = (255, 255, 255))
+    d = ImageDraw.Draw(img)
+    # Default font is usually tiny, but readable by tesseract
+    d.text((10,10), text, fill=(0,0,0))
+    img.save(filename)
+    print(f"Created {filename}")
+
+if __name__ == "__main__":
+    create_pdf("test_ocr.pdf", "Hello World PDF OCR")
+    create_image("test_ocr.png", "Hello World Image OCR")