mirror of
https://github.com/vitorpamplona/amethyst.git
synced 2026-10-05 19:28:25 +00:00
Claude
a7209a70b6
Reviewing what the tests actually reach turned up one live defect and a suite that mostly did not run. The defect is the comment bug again, in the elements whose content is text rather than markup. `<title>5 < 6, that's math</title>` is ordinary HTML: the `<` opened a phantom tag, the apostrophe opened a phantom attribute value, and every tag after it -- the whole og: block -- was swallowed. Same for `<textarea>`, and a `<meta>` written inside title text was parsed as a real one and won over the page's own. Title and textarea now skip to their end tag like script and style; the three tests for it fail without that change. The suite: MetaTagsParserTest lived in `androidDeviceTest`, so every attribute shape it covers -- unquoted values, single quotes, valueless attributes, duplicate-attribute rejection, `</head>` inside a value -- was unguarded in CI. Nothing in it is Android-specific, so it moves to commonTest. OpenGraphParser and HtmlCharsetParser had no tests at all. New coverage, all of it variants nothing exercised before: - end of scan: `</HEAD>`, `</head >`, `</head>` inside an attribute value, and a document with no `</head>` at all. - truncation: a body cut after a `/`, inside a quoted value, and right after a `<` -- the first is the crash the previous commit guarded and never pinned. - tag shapes: uppercase `<META>`, `<meta/>`, `/>` inside a quoted value, `<![CDATA[]]>`, and meta tags inside `<noscript>` (which must still be read). - attributes: a trailing valueless attribute, a value spanning lines, unknown attributes. - character references: query-string `&` left intact (og:image URLs are full of them), astral references (`😀`), unknown references left alone. - laziness: the sequence stops when the consumer does. - OpenGraphParser: property / name / itemprop sources, twitter and plain-name fallbacks, and that a field is taken in document order -- so a plain `<meta name="description">` above the og: one wins. That is why the brainstorm.world card shows the site description; pinned, not changed. - HtmlCharsetParser / HtmlParser: charset attribute, http-equiv content-type, the UTF-8 default, the 1 KB sniff window, and the response-charset > BOM > document-declaration precedence. 49 tests in the package, from 8 that ran. Co-Authored-By: Claude <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FumxeDJPEgPqX8mz3xkM6b