Enhance binary file detection by integrating MIME type analysis, resolves #975

changelog.d/20240222_174417_abdul.muqadim_binary_file_detection_update.md

@@ -0,0 +1 @@
+- [Improvement] This is a non-breaking change. Enhanced is_binary_file function in env file for better binary file detection. (by @Abdul-Muqadim-Arbisoft)

tests/test_env.py

@@ -42,6 +42,15 @@ def test_files_are_rendered(self) -> None:
     def test_is_binary_file(self) -> None:
         self.assertTrue(env.is_binary_file("/home/somefile.ico"))
 
+    def test_is_binary_file_with_text_extension(self) -> None:
+        self.assertFalse(env.is_binary_file("/home/script.js"))
+
+    def test_is_binary_file_with_unrecognized_extension(self) -> None:
+        self.assertFalse(env.is_binary_file("/home/unknown.extension"))
+
+    def test_is_binary_file_without_extension(self) -> None:
+        self.assertFalse(env.is_binary_file("/home/file"))
+
     def test_find_os_path(self) -> None:
         environment = env.JinjaEnvironment()
         path = environment.find_os_path("local/docker-compose.yml")

tutor/env.py

@@ -6,6 +6,8 @@
 import typing as t
 from copy import deepcopy
 
+import mimetypes
+
 import jinja2
 import importlib_resources
 
@@ -26,6 +28,8 @@
     ".woff",
     ".woff2",
 ]
+TEXT_MIME_TYPES = ["application/xml", "application/json"]
+TEXT_FILE_EXTENSIONS = [".html", ".xml", ".json", ".css", ".js"]
 JinjaFilter = t.Callable[..., t.Any]
 
 
@@ -501,7 +505,29 @@ def read_core_template_file(*path: str) -> str:
 
 
 def is_binary_file(path: str) -> bool:
-    ext = os.path.splitext(path)[1]
+    """
+    Determines if the specified file is binary based on its MIME type or file extension.
+
+    This function first attempts to guess the MIME type of the file based on its path.
+    If the MIME type indicates that the file is not text and not a known text-based MIME type,
+    it is considered binary. If the MIME type cannot be determined or is not indicative
+    of a binary file, the function then checks the file's extension against a predefined
+    list of binary file extensions, as well as a list of known text file extensions.
+
+    Parameters:
+    - path (str): The path to the file whose type is to be determined.
+
+    Returns:
+    - bool: True if the file is determined to be binary, False otherwise.
+    """
+    mime_type, _ = mimetypes.guess_type(path)
+    if mime_type:
+        if mime_type.startswith("text/") or mime_type in TEXT_MIME_TYPES:
+            return False
+        return True
+    ext = os.path.splitext(path)[1].lower()
+    if ext in TEXT_FILE_EXTENSIONS:
+        return False
     return ext in BIN_FILE_EXTENSIONS