Paul BakausandClaude Fable 5 7dcca2bb36 Count em-dash HTML entities in em-dash-overuse ...

The em-dash-overuse text analyzer ran stripHtmlToText over raw markup,
which drops tags but leaves character entities intact. A model that wrote
—, —, or — rendered a real em-dash the counter never
saw, so 12 entity-escaped dashes on a live page slipped through.

Decode the em-dash entities (named, zero-padded decimal, upper/lower hex)
to the literal glyph before counting. En-dash entities stay untouched: the
rule counts em-dashes, and the literal en-dash was never counted either.

The gap lived only in the regex / static-HTML path (detectText and
detect-html's runTextContentAnalyzers, both over raw HTML). The browser
adapter never ran this analyzer, so build:browser and build:extension
produce no diff.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-22 00:27:59 -07:00

..

bin

Add first-class Grok Build harness support

2026-07-21 18:02:58 -07:00

engine

Count em-dash HTML entities in em-dash-overuse

2026-07-22 00:27:59 -07:00

lib

Add first-class Grok Build harness support

2026-07-21 18:02:58 -07:00