From 67040a196f8777838e3eb9bbf4d88715d24a405d Mon Sep 17 00:00:00 2001
From: Ashvin <76151462+ashvinctrl@users.noreply.github.com>
Date: Sat, 27 Jun 2026 22:01:46 +0530
Subject: [PATCH] fix(docker): install python-magic and libmagic for upload
 MIME sniffing

Install libmagic1 and image-scoped python-magic in the Docker image so upload MIME detection can use content sniffing. Add regression coverage for the Dockerfile dependency pair and the libmagic-present sniffing path.
---
 Dockerfile                                   | 14 ++++++
 tests/test_upload_content_detection_magic.py | 46 ++++++++++++++++++++
 2 files changed, 60 insertions(+)
 create mode 100644 tests/test_upload_content_detection_magic.py

diff --git a/Dockerfile b/Dockerfile
index 221d462d1..9b305569c 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -32,6 +32,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libgl1 \
     libglib2.0-0t64 \
     libxcb1 \
+    libmagic1 \
     && rm -rf /var/lib/apt/lists/*
 
 # libgl1/libglib2.0-0t64/libxcb1 are runtime shared libs (libGL.so.1,
@@ -40,6 +41,14 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 # and dies with `libxcb.so.1: cannot open shared object file` despite a clean
 # pip install. Using full opencv-python (not -headless) because basicsr/gfpgan/
 # facexlib/realesrgan all depend on the `opencv-python` distribution by name.
+#
+# libmagic1 is the shared lib (libmagic.so.1) that python-magic dlopens for
+# content-based MIME sniffing in src/upload_handler.py. We install both here
+# (libmagic1 + the python-magic wrapper, below) rather than in requirements.txt
+# because python-magic resolves libmagic at import time: where the lib is
+# absent the import can block or raise, so keeping it image-only avoids
+# regressing pip/venv installs on hosts without libmagic. Debian always has the
+# lib here, so the import is instant and detection actually works.
 
 # Docker CLI (client only — daemon stays on the host via the
 # /var/run/docker.sock mount). The Debian `docker.io` package ships
@@ -67,6 +76,11 @@ COPY requirements.txt requirements-optional.txt ./
 RUN pip install --no-cache-dir -r requirements.txt \
     && if [ "$INSTALL_OPTIONAL" = "true" ]; then pip install --no-cache-dir -r requirements-optional.txt; fi
 
+# python-magic powers content-based MIME sniffing in src/upload_handler.py.
+# Image-only (not in requirements.txt) because it needs the libmagic1 system
+# lib installed above; see the apt note near the top of this stage.
+RUN pip install --no-cache-dir python-magic==0.4.27
+
 # Pre-install the patched basicsr/gfpgan/facexlib wheels built in the
 # realesrgan-wheels stage (--no-deps keeps the image lean — torch & friends are
 # pulled only when realesrgan is actually installed). With these dists already
diff --git a/tests/test_upload_content_detection_magic.py b/tests/test_upload_content_detection_magic.py
new file mode 100644
index 000000000..d5ae6a350
--- /dev/null
+++ b/tests/test_upload_content_detection_magic.py
@@ -0,0 +1,46 @@
+"""Regression for #4875: the official Docker image shipped without python-magic
+(and without the libmagic system lib), so content-based MIME detection in
+src/upload_handler.py was dead and uploads were typed by extension only.
+
+python-magic resolves libmagic at import time and can block/raise when the lib
+is absent, so it's installed in the Docker image (which always has libmagic1)
+rather than in the shared requirements.txt. These tests pin:
+  1. the Dockerfile installs both libmagic1 (apt) and python-magic (pip);
+  2. when libmagic is actually present, detect_content_type sniffs the MIME
+     from the bytes and overrides a misleading/missing extension.
+"""
+import io
+import os
+
+import pytest
+
+from src.upload_handler import UploadHandler
+
+# 1x1 PNG (header is enough for libmagic to report image/png).
+_PNG = (
+    b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01"
+    b"\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\nIDATx\x9cc\x00"
+    b"\x01\x00\x00\x05\x00\x01\r\n-\xb4\x00\x00\x00\x00IEND\xaeB`\x82"
+)
+
+_REPO_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+def test_dockerfile_installs_libmagic_and_python_magic():
+    with open(os.path.join(_REPO_ROOT, "Dockerfile"), encoding="utf-8") as f:
+        dockerfile = f.read()
+    # The C library python-magic dlopens, installed via apt...
+    assert "libmagic1" in dockerfile
+    # ...and the wrapper itself, installed via pip in the image.
+    assert "python-magic" in dockerfile
+
+
+def test_content_detection_overrides_misleading_extension(tmp_path):
+    handler = UploadHandler(base_dir=str(tmp_path), upload_dir=str(tmp_path))
+    if handler.file_detector is None:
+        pytest.skip("libmagic/python-magic not installed in this environment")
+
+    # PNG bytes behind a .bin name: extension sniffing can't help, so a correct
+    # image/png result proves content-based detection is doing the work.
+    detected = handler.detect_content_type(io.BytesIO(_PNG), "payload.bin")
+    assert detected == "image/png"