mirror of
https://github.com/MadsLorentzen/ai-job-search.git
synced 2026-11-02 13:12:50 +00:00
fix(posting-guard): read style values like a browser and treat a collapsed, clipped box as hidden (#709)
* fix(posting-guard): read style values like a browser and treat a collapsed, clipped box as hidden The hidden-style regex ran on the raw attribute value, so "display:none" (entity-encoded colon) and "display:/**/none" (a CSS comment inside the declaration) both hid the content in a browser while the guard showed it under a clean verdict. A zero-height or zero-width box with overflow:hidden, the other common way to hide a block, was not a hidden style at all. Entity-decode and comment-strip the value before matching, and count a collapsed box as hidden only when both halves are present: overflow: hidden alone is on most cards and height:0 alone is a spacer. Three new Bypasses cases (seven subtests fail on master) plus a calibration case pinning that either half alone stays visible. * changelog: place the #709 entry under [Unreleased] Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Mads Lorentzen <madslorentzen_17@hotmail.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
3 files changed
+59
-3
No files matched your search
@@ -453,6 +453,28 @@ class Bypasses(GuardFixture):
|
||||
with self.subTest(style=style):
|
||||
self.assert_hidden(f"<p>Real.</p><span style='{style}'>SECRET</span>", "SECRET")
|
||||
|
||||
def test_entity_encoded_and_comment_broken_style_values_still_hide(self):
|
||||
# A browser decodes the attribute and ignores /**/ inside a declaration
|
||||
# before it parses the CSS; the regex saw neither and showed the text
|
||||
# under a clean verdict.
|
||||
for style in ("display:none", "display:/**/none", "visibility:/* */hidden", "opacity:/*x*/0"):
|
||||
with self.subTest(style=style):
|
||||
self.assert_hidden(f"<p>Real.</p><div style=\"{style}\">SECRET</div>", "SECRET")
|
||||
|
||||
def test_collapsed_box_with_clipped_overflow_hides(self):
|
||||
for style in ("height:0;overflow:hidden", "max-height: 0px; overflow: hidden", "width:0;overflow-x:hidden"):
|
||||
with self.subTest(style=style):
|
||||
self.assert_hidden(f"<p>Real.</p><div style='{style}'>SECRET</div>", "SECRET")
|
||||
|
||||
def test_either_half_of_a_collapsed_box_alone_is_layout_not_hiding(self):
|
||||
# overflow:hidden is on most cards and height:0 is a spacer; neither
|
||||
# alone hides text, and treating them as hidden would flag every page.
|
||||
for style in ("overflow:hidden", "height:0", "height:0.5em;overflow:hidden", "max-height:200px;overflow:hidden"):
|
||||
with self.subTest(style=style):
|
||||
code, out, err = self.run_main("--html", "--json", stdin_text=f"<p>Real.</p><div style='{style}'>Visible.</div>")
|
||||
self.assertIn("Visible.", self.text_of(out), style)
|
||||
self.assertEqual(self.findings_of(out)["hidden_blocks"], [], style)
|
||||
|
||||
def test_doctype_and_xml_prolog_are_not_text(self):
|
||||
code, out, err = self.run_main("--html", stdin_text="<!DOCTYPE html><?xml version='1.0'?><p>Real.</p>")
|
||||
text = self.text_of(out)
|
||||
|
||||
Reference in new issue
Block a user