Updated this to the latest version of develop, got rid of most of the duplication, might be missing some packages in toml, needs testing

app/helpers/file.py

@@ -0,0 +1,95 @@
+import datetime
+from pathlib import Path
+import base64
+import io
+import os
+import shutil
+import subprocess
+from typing import Optional
+
+import numpy as np
+import pypandoc
+from PIL import Image
+
+import aiofiles
+
+
+class FileHelper:
+
+    @staticmethod
+    def delete_files_older_than_one_day(directory: str):
+        current_time = datetime.datetime.now()
+
+        for entry in os.scandir(directory):
+            if entry.is_file():
+                file_path = Path(entry)
+                file_name = file_path.name
+                file_modified_time = datetime.datetime.fromtimestamp(file_path.stat().st_mtime)
+                time_difference = current_time - file_modified_time
+                if time_difference.days > 1 and "placeholder" not in file_name:
+                    file_path.unlink()
+                    print(f"Deleted file: {file_path}")
+
+    # Supposedly pandoc covers a wide range of file extensions only tested with docx
+    @staticmethod
+    def convert_file_to_pdf(input_path: str, output_path: str):
+        pypandoc.convert_file(input_path, 'pdf', outputfile=output_path, extra_args=[
+            '-V', 'geometry:paperwidth=5.5in',
+            '-V', 'geometry:paperheight=8.5in',
+            '-V', 'geometry:margin=0.5in',
+            '-V', 'pagestyle=empty'
+        ])
+
+    @staticmethod
+    def convert_file_to_html(input_path: str, output_path: str):
+        pypandoc.convert_file(input_path, 'html', outputfile=output_path)
+
+    @staticmethod
+    def pdf_to_png(path_id: str):
+        to_png = f"pdftoppm -png exercises.pdf page"
+        result = subprocess.run(to_png, shell=True, cwd=f'./tmp/{path_id}', capture_output=True, text=True)
+        if result.returncode != 0:
+            raise Exception(
+                f"Couldn't convert pdf to png. Failed to run command '{to_png}' -> ```cmd {result.stderr}```")
+
+    @staticmethod
+    def is_page_blank(image_bytes: bytes, image_threshold=10) -> bool:
+        with Image.open(io.BytesIO(image_bytes)) as img:
+            img_gray = img.convert('L')
+            img_array = np.array(img_gray)
+            non_white_pixels = np.sum(img_array < 255)
+
+        return non_white_pixels <= image_threshold
+
+    @classmethod
+    async def _encode_image(cls, image_path: str, image_threshold=10) -> Optional[str]:
+        async with aiofiles.open(image_path, "rb") as image_file:
+            image_bytes = await image_file.read()
+
+        if cls.is_page_blank(image_bytes, image_threshold):
+            return None
+
+        return base64.b64encode(image_bytes).decode('utf-8')
+
+    @classmethod
+    def b64_pngs(cls, path_id: str, files: list[str]):
+        png_messages = []
+        for filename in files:
+            b64_string = cls._encode_image(os.path.join(f'./tmp/{path_id}', filename))
+            if b64_string:
+                png_messages.append({
+                    "type": "image_url",
+                    "image_url": {
+                        "url": f"data:image/png;base64,{b64_string}"
+                    }
+                })
+        return png_messages
+
+    @staticmethod
+    def remove_directory(path):
+        try:
+            if os.path.exists(path):
+                if os.path.isdir(path):
+                    shutil.rmtree(path)
+        except Exception as e:
+            print(f"An error occurred while trying to remove {path}: {str(e)}")