obsluga pdf

app.py

@@ -51,6 +51,8 @@ from functools import wraps
 from flask_talisman import Talisman
 from flask_session import Session
 from types import SimpleNamespace
+from pdf2image import convert_from_bytes
+
 
 # OCR
 import pytesseract
@@ -95,7 +97,7 @@ talisman = Talisman(
 
 register_heif_opener()  # pillow_heif dla HEIC
 SQLALCHEMY_ECHO = True
-ALLOWED_EXTENSIONS = {"png", "jpg", "jpeg", "gif", "webp", "heic"}
+ALLOWED_EXTENSIONS = {"png", "jpg", "jpeg", "gif", "webp", "heic", "pdf"}
 
 SYSTEM_PASSWORD = app.config.get("SYSTEM_PASSWORD")
 DEFAULT_ADMIN_USERNAME = app.config.get("DEFAULT_ADMIN_USERNAME")
@@ -161,6 +163,7 @@ class User(UserMixin, db.Model):
     password_hash = db.Column(db.String(512), nullable=False)
     is_admin = db.Column(db.Boolean, default=False)
 
+
 # Tabela pośrednia
 shopping_list_category = db.Table(
     "shopping_list_category",
@@ -285,7 +288,7 @@ def set_authorized_cookie(response):
         AUTHORIZED_COOKIE_VALUE,
         max_age=max_age,
         secure=secure_flag,
-        httponly=True
+        httponly=True,
     )
     return response
 
@@ -370,6 +373,7 @@ def serve_css_lib(filename):
     response.headers.pop("Content-Disposition", None)
     return response
 
+
 app.register_blueprint(static_bp)
 
 
@@ -864,7 +868,7 @@ def get_total_expenses_grouped_by_category(
         if str(category_id) == "none":
             if not l.categories:
                 data_map[key]["Bez kategorii"] += total_expense
-            continue 
+            continue
 
         if not l.categories:
             data_map[key]["Bez kategorii"] += total_expense
@@ -898,15 +902,36 @@ def get_total_expenses_grouped_by_category(
     return {"labels": labels, "datasets": datasets}
 
 
+def save_pdf_as_webp(file, path):
+    try:
+        images = convert_from_bytes(file.read(), dpi=300)
+        if not images:
+            raise ValueError("Nie udało się przekonwertować PDF na obraz.")
+
+        total_height = sum(img.height for img in images)
+        max_width = max(img.width for img in images)
+        combined = Image.new("RGB", (max_width, total_height), (255, 255, 255))
+
+        y_offset = 0
+        for img in images:
+            combined.paste(img, (0, y_offset))
+            y_offset += img.height
+
+        combined.thumbnail((2000, 20000))
+        new_path = path.rsplit(".", 1)[0] + ".webp"
+        combined.save(new_path, **WEBP_SAVE_PARAMS)
+
+    except Exception as e:
+        raise ValueError(f"Błąd podczas przetwarzania PDF: {e}")
+
+
 ############# OCR ###########################
 
 
 def preprocess_image_for_tesseract(image):
     image = ImageOps.autocontrast(image)
     image = image.point(lambda x: 0 if x < 150 else 255)
-    image = image.resize(
-        (image.width * 2, image.height * 2), Image.BICUBIC
-    )
+    image = image.resize((image.width * 2, image.height * 2), Image.BICUBIC)
     return image
 
 
@@ -1904,7 +1929,11 @@ def upload_receipt(list_id):
         file_path = os.path.join(app.config["UPLOAD_FOLDER"], webp_filename)
 
         try:
-            save_resized_image(file, file_path)
+            if file.filename.lower().endswith(".pdf"):
+                file.seek(0)
+                save_pdf_as_webp(file, file_path)
+            else:
+                save_resized_image(file, file_path)
         except ValueError as e:
             return receipt_error(str(e))
 
@@ -2815,7 +2844,11 @@ def healthcheck():
 
 @app.route("/robots.txt")
 def robots_txt():
-    content = "User-agent: *\nDisallow: /" if app.config.get("DISABLE_ROBOTS") else "User-agent: *\nAllow: /"
+    content = (
+        "User-agent: *\nDisallow: /"
+        if app.config.get("DISABLE_ROBOTS")
+        else "User-agent: *\nAllow: /"
+    )
     return content, 200, {"Content-Type": "text/plain"}