Update read_photodocument.py

read_photodocument.py

@@ -19,6 +19,8 @@ from spellchecker import SpellChecker
 from tqdm.auto import tqdm
 import nltk 
 import contextlib
+import img2pdf
+from PIL import Image
 nltk.download("stopwords")  # TODO=find where this requirement originates from
 
 
@@ -28,6 +30,19 @@ def simple_rename(filepath, target_ext=".txt"):
     return f"OCR_{basename}_{target_ext}"
 
 
+def convert_image_to_pdf(image_path,model=None):
+    pdf_path = image_path.replace('.jpg','.pdf')
+    image = Image.open(image_path)
+    pdf_bytes = img2pdf.convert(image.filename)
+    file = open(pdf_path, "wb")
+    file.write(pdf_bytes)
+    image.close()
+    file.close()
+    return convert_PDF_to_Text(PDF_file=pdf_path,ocr_model=model)
+    
+    
+    
+
 def rm_local_text_files(name_contains="RESULT_"):
     """
     rm_local_text_files - remove local text files