From ab392e2ab983a4c87e241b457c98244251b2206a Mon Sep 17 00:00:00 2001
From: Peter Stone <thepeterstone@gmail.com>
Date: Thu, 23 Jul 2026 22:32:14 +0000
Subject: Strip <header> chrome before Readability parses; show full article
 title in reader content

- Confirmed live (Ars Technica): a section-kicker badge, the dek/subhead, and
  an orphaned duplicate hero-image caption were all leaking into extracted
  content because they live in a <header> Readability doesn't exclude by tag,
  only deprioritizes in scoring. Strip <header> from the DOM ourselves before
  handing off to Readability -- a pre-processing decision on our side, not a
  change to Readability's own algorithm, per instruction not to touch it.
- Render the article's full title as a heading at the top of the reader
  content itself (wrapReaderHtml), not just the top bar, which truncates to
  one line. This also replaces whatever heading Readability happened to keep
  in-body, now that <header> (and any <h1> inside it) is stripped pre-parse.
- Bump extraction timeout 15s -> 25s: confirmed live, several heavy
  real-world pages were timing out before onPageFinished ever fired, well
  short of a real parsing failure.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EZ7ikw2ukGJFTHE3bJS7zL
---
 .../main/java/org/terst/feedreader/ui/ReaderWebView.kt  | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

(limited to 'app/src/main/java/org/terst/feedreader/ui/ReaderWebView.kt')

diff --git a/app/src/main/java/org/terst/feedreader/ui/ReaderWebView.kt b/app/src/main/java/org/terst/feedreader/ui/ReaderWebView.kt
index 503f71e..f95dfed 100644
--- a/app/src/main/java/org/terst/feedreader/ui/ReaderWebView.kt
+++ b/app/src/main/java/org/terst/feedreader/ui/ReaderWebView.kt
@@ -28,14 +28,27 @@ fun newReaderWebView(context: Context, onOpenLink: (String) -> Unit): WebView =
         }
     }
 
+private fun escapeHtml(text: String): String = text
+    .replace("&", "&amp;")
+    .replace("<", "&lt;")
+    .replace(">", "&gt;")
+    .replace("\"", "&quot;")
+    .replace("'", "&#39;")
+
 // Hardcoded dark palette, not @media (prefers-color-scheme) -- the app itself always
 // forces dark colorScheme() regardless of system setting (see MainActivity), so reader
 // content should match rather than following a system light/dark the app itself ignores.
-fun wrapReaderHtml(bodyContent: String): String = """
+//
+// title is rendered here, as a real heading at the top of the content, rather than relying
+// on whatever heading Readability happened to keep in bodyContent (increasingly nothing --
+// see ReaderExtractor's <header> stripping) or on the top app bar's title, which truncates
+// to one line and was the only place a long title showed up before this.
+fun wrapReaderHtml(bodyContent: String, title: String? = null): String = """
     <html><head><meta name="viewport" content="width=device-width, initial-scale=1">
     <style>
     body { font-family: sans-serif; font-size: 18px; line-height: 1.5; padding: 16px;
            background-color: #121212; color: #e1e1e1; }
+    h1.article-title { font-size: 1.5em; line-height: 1.3; margin: 0 0 0.6em 0; }
     a { color: #8ab4f8; }
     img { max-width: 100%; height: auto; }
     svg { max-width: 100%; }
@@ -49,5 +62,5 @@ fun wrapReaderHtml(bodyContent: String): String = """
        those alone -- just cap the ones that would otherwise size themselves. */
     svg:not([width]):not([height]) { max-width: 32px; max-height: 32px; }
     </style></head>
-    <body>$bodyContent</body></html>
+    <body>${if (!title.isNullOrBlank()) "<h1 class=\"article-title\">${escapeHtml(title)}</h1>" else ""}$bodyContent</body></html>
 """.trimIndent()
-- 
cgit v1.2.3