1 files changed, 24 insertions, 0 deletions
diff --git a/app/src/main/java/org/terst/feedreader/readability/ArticleLitter.kt b/app/src/main/java/org/terst/feedreader/readability/ArticleLitter.kt
new file mode 100644
index 0000000..decddc6
--- /dev/null
+++ b/app/src/main/java/org/terst/feedreader/readability/ArticleLitter.kt
@@ -0,0 +1,24 @@
+package org.terst.feedreader.readability
+
+/**
+ * Everything that gets cleaned out of an extracted article body, in one call.
+ *
+ * There are two places a body is cleaned -- a fresh extraction on its way out of [EvalDecision],
+ * and a cached one on its way back in through `loadCachedExtraction` -- and they must stay in
+ * step. A cached article is cleaned in place rather than discarded, so a cleaner wired into only
+ * the fresh path would leave every already-read article carrying litter that nothing would ever
+ * remove: the body is good, so it is never re-fetched.
+ *
+ * Hence one entry point rather than a list of calls repeated at both sites. Adding a cleaner here
+ * reaches both; adding one to a call site reaches one, and which one it misses would depend on
+ * which file was open at the time.
+ *
+ * None of these discard an article. They remove things from inside it, which is why they sit
+ * apart from [ConsentNotice] and [UnrenderedTex] -- those two decide a body is not worth keeping.
+ */
+object ArticleLitter {
+
+    /** [html] with the publisher's promo furniture removed. */
+    fun strip(html: String?): String? =
+        PreferredSourceBadge.strip(RecirculationWidgets.strip(html))
+}