Fix: correct text/stream compression workaround (#14064)

src/paperless/middleware.py

@@ -1,8 +1,23 @@
+from compression_middleware.middleware import CompressionMiddleware
 from django.conf import settings
 
 from paperless import version
 
 
+class StreamAwareCompressionMiddleware(CompressionMiddleware):
+    """
+    Bypasses compression for server-sent streams (text/event-stream).
+
+    See https://github.com/friedelwolff/django-compression-middleware/pull/7
+    """
+
+    def process_response(self, request, response):
+        content_type = response.headers.get("Content-Type", "")
+        if content_type.startswith("text/event-stream"):
+            return response
+        return super().process_response(request, response)
+
+
 class ApiVersionMiddleware:
     def __init__(self, get_response):
         self.get_response = get_response

src/paperless/settings/__init__.py

@@ -10,7 +10,6 @@ from pathlib import Path
 from typing import Final
 from urllib.parse import urlparse
 
-from compression_middleware.middleware import CompressionMiddleware
 from django.core.exceptions import ImproperlyConfigured
 from django.utils.translation import gettext_lazy as _
 from dotenv import load_dotenv
@@ -201,22 +200,10 @@ MIDDLEWARE = [
     "allauth.account.middleware.AccountMiddleware",
 ]
 
-# Optional to enable compression
+# Optional to enable compression. The subclass leaves server-sent events
+# uncompressed; see paperless.middleware.StreamAwareCompressionMiddleware.
 if get_bool_from_env("PAPERLESS_ENABLE_COMPRESSION", "yes"):  # pragma: no cover
-    MIDDLEWARE.insert(0, "compression_middleware.middleware.CompressionMiddleware")
-
-# Workaround to not compress streaming responses (e.g. chat).
-# See https://github.com/friedelwolff/django-compression-middleware/pull/7
-original_process_response = CompressionMiddleware.process_response
-
-
-def patched_process_response(self, request, response):
-    if getattr(request, "compress_exempt", False):
-        return response
-    return original_process_response(self, request, response)
-
-
-CompressionMiddleware.process_response = patched_process_response
+    MIDDLEWARE.insert(0, "paperless.middleware.StreamAwareCompressionMiddleware")
 
 ROOT_URLCONF = "paperless.urls"
 

src/paperless/tests/test_compression_middleware.py

@@ -0,0 +1,54 @@
+from django.http import HttpResponse
+from django.http import StreamingHttpResponse
+from django.test import RequestFactory
+from django.test import TestCase
+
+from paperless.middleware import StreamAwareCompressionMiddleware
+
+
+class TestStreamAwareCompressionMiddleware(TestCase):
+    def setUp(self) -> None:
+        super().setUp()
+        self.factory = RequestFactory()
+        self.middleware = StreamAwareCompressionMiddleware(lambda request: None)
+
+    def _request(self):
+        return self.factory.get(
+            "/api/documents/chat/",
+            HTTP_ACCEPT_ENCODING="gzip, deflate, br, zstd",
+        )
+
+    def test_event_stream_is_not_compressed(self) -> None:
+        """
+        GIVEN:
+            - A server-sent event response produced chunk by chunk
+        WHEN:
+            - The compression middleware processes it
+        THEN:
+            - It is passed through unencoded, one wire chunk per source chunk
+        """
+        chunks = [f"token{i} ".encode() for i in range(40)]
+        response = StreamingHttpResponse(
+            iter(chunks),
+            content_type="text/event-stream",
+        )
+
+        response = self.middleware.process_response(self._request(), response)
+
+        assert not response.has_header("Content-Encoding")
+        assert list(response.streaming_content) == chunks
+
+    def test_regular_response_is_still_compressed(self) -> None:
+        """
+        GIVEN:
+            - An ordinary response large enough to be worth compressing
+        WHEN:
+            - The compression middleware processes it
+        THEN:
+            - It is compressed as before
+        """
+        response = HttpResponse(b"a" * 5000, content_type="application/json")
+
+        response = self.middleware.process_response(self._request(), response)
+
+        assert response.has_header("Content-Encoding")