Handle binary/octet-stream content type

docs/source/release-history.rst

@@ -5,7 +5,7 @@ Release History
 In Development
 --------------
 
-n/a
+- Treat the `binary/octet-stream` as a generic media type, just like `application/octet-stream`, when trying to determine if content is not HTML. Even though `binary/octet-stream` is not a registered IANA media type it turns out some AWS SDKs use it when uploading files to S3, so it’s somewhat common.
 
 
 Version 0.1.4 (2024-01-01)

web_monitoring_diff/content_type.py

@@ -38,6 +38,7 @@
 # Matches Content Types that *could* be acceptable for diffing as HTML
 UNKNOWN_CONTENT_TYPE_PATTERN = re.compile(r'^(%s)$' % '|'.join((
     r'application/octet-stream',
+    r'binary/octet-stream',
     r'application/x-download',
     r'text/.+'
 )))
@@ -70,6 +71,7 @@ def is_not_html(text, headers=None, check_options='normal'):
         - `nosniff` uses the `Content-Type` header but does not sniff.
         - `ignore` doesn’t do any checking at all.
     """
+    print(f'#is_not_html: check_options="{check_options}", headers={headers}, text={text[:500]}')
     if headers and (check_options == 'normal' or check_options == 'nosniff'):
         content_type = headers.get('Content-Type', '').split(';', 1)[0].strip()
         if content_type and VALID_CONTENT_TYPE_PATTERN.match(content_type):

web_monitoring_diff/tests/test_html_diff_validity.py

@@ -198,6 +198,14 @@ def test_html_diff_render_should_not_check_content_type_header_if_header_is_malf
         b_headers={'Content-Type': 'text/html'})
 
 
+def test_html_diff_render_should_not_check_content_type_header_if_header_is_generic():
+    html_diff_render(
+        '<p>Just a little HTML</p>',
+        '<p>Just some HTML</p>',
+        a_headers={'Content-Type': 'binary/octet-stream'},
+        b_headers={'Content-Type': 'application/x-download'})
+
+
 def test_html_diff_render_should_not_check_content_type_header_if_content_type_options_is_nocheck():
     html_diff_render(
         '<p>Just a little HTML</p>',