phase 5

backend/app/images/zip_handler.py

@@ -0,0 +1,73 @@
+"""ZIP file extraction handler for batch image uploads."""
+
+import io
+import zipfile
+from collections.abc import AsyncIterator
+
+from fastapi import HTTPException, UploadFile, status
+
+
+async def extract_images_from_zip(zip_file: UploadFile) -> AsyncIterator[tuple[str, bytes]]:
+    """
+    Extract image files from ZIP archive.
+
+    Args:
+        zip_file: Uploaded ZIP file
+
+    Yields:
+        Tuples of (filename, contents) for each image file
+
+    Raises:
+        HTTPException: If ZIP is invalid or too large
+    """
+    # Read ZIP contents
+    zip_contents = await zip_file.read()
+
+    # Check ZIP size (max 200MB for ZIP)
+    max_zip_size = 200 * 1024 * 1024  # 200MB
+    if len(zip_contents) > max_zip_size:
+        raise HTTPException(
+            status_code=status.HTTP_413_REQUEST_ENTITY_TOO_LARGE,
+            detail=f"ZIP file too large. Maximum size is {max_zip_size / 1_048_576:.1f}MB",
+        )
+
+    try:
+        # Open ZIP file
+        with zipfile.ZipFile(io.BytesIO(zip_contents)) as zip_ref:
+            # Get list of image files (filter by extension)
+            image_extensions = {".jpg", ".jpeg", ".png", ".gif", ".webp", ".svg"}
+            image_files = [
+                name
+                for name in zip_ref.namelist()
+                if not name.startswith("__MACOSX/")  # Skip macOS metadata
+                and not name.startswith(".")  # Skip hidden files
+                and any(name.lower().endswith(ext) for ext in image_extensions)
+            ]
+
+            if not image_files:
+                raise HTTPException(
+                    status_code=status.HTTP_400_BAD_REQUEST,
+                    detail="No valid image files found in ZIP archive",
+                )
+
+            # Extract each image
+            for filename in image_files:
+                # Skip directories
+                if filename.endswith("/"):
+                    continue
+
+                # Get just the filename without path
+                base_filename = filename.split("/")[-1]
+
+                # Read file contents
+                file_contents = zip_ref.read(filename)
+
+                yield base_filename, file_contents
+
+    except zipfile.BadZipFile as e:
+        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid ZIP file") from e
+    except Exception as e:
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=f"Error processing ZIP file: {str(e)}",
+        ) from e