1 files changed, 32 insertions, 0 deletions
diff --git a/app/src/test/java/org/terst/feedreader/data/CachedExtractionTest.kt b/app/src/test/java/org/terst/feedreader/data/CachedExtractionTest.kt
index 72dc73f..fc9c32e 100644
--- a/app/src/test/java/org/terst/feedreader/data/CachedExtractionTest.kt
+++ b/app/src/test/java/org/terst/feedreader/data/CachedExtractionTest.kt
@@ -33,6 +33,7 @@ class CachedExtractionTest {
         val result = loadCachedExtraction(content) { cleared = true }
         assertEquals(content, result.content)
         assertFalse(result.discardedConsentNotice)
+        assertFalse(result.discarded)
         assertFalse("a good cache must not be cleared", cleared)
     }
 
@@ -54,6 +55,37 @@ class CachedExtractionTest {
         assertFalse(cleared)
     }
 
+    // Same shape of problem as the consent notice, different cause: this content was
+    // extracted before extraction knew how to render maths, so it holds the raw TeX source
+    // Substack ships. A fixed extractor never gets a look at it -- the cached copy is
+    // returned first and the article is never re-extracted.
+    @Test
+    fun `a cached extraction holding raw tex source is discarded and deleted`() = runTest {
+        var cleared = false
+        val rawTex = "<div id=\"readability-page-1\"><p>Imagine the following sentence:</p>" +
+            "<div data-component-name=\"Latex\"><p><span>" +
+            "\\(p = \\text{\u201Cif }p\\text{ is true, then pigs can fly\u201D}\\)</span></p></div>" +
+            "<p>" + "Considered as a whole, the statement cannot be true. ".repeat(20) + "</p></div>"
+        val result = loadCachedExtraction(rawTex) { cleared = true }
+        assertNull("raw TeX source must not be shown as the article", result.content)
+        assertTrue(result.discardedUnrenderedTex)
+        assertTrue("the stale row must be cleared so a re-extract can replace it", cleared)
+        assertTrue("the caller must be told to extract again", result.discarded)
+    }
+
+    @Test
+    fun `an extraction with rendered maths is kept`() = runTest {
+        var cleared = false
+        val withMathMl = "<p>A slice of the set looks like this:</p>" +
+            "<math xmlns=\"http://www.w3.org/1998/Math/MathML\" display=\"block\"><semantics>" +
+            "<mrow><mi>p</mi><mo>=</mo></mrow></semantics></math>" +
+            "<p>" + "The rest of the article continues from there. ".repeat(20) + "</p>"
+        val result = loadCachedExtraction(withMathMl) { cleared = true }
+        assertEquals(withMathMl, result.content)
+        assertFalse(result.discardedUnrenderedTex)
+        assertFalse("a good cache must not be cleared", cleared)
+    }
+
     // A blank value is as good as nothing cached -- it is not a consent notice, so
     // reporting it as a discarded one would make the caller re-extract on a false
     // premise.