1 files changed, 116 insertions, 0 deletions
diff --git a/app/src/test/java/org/terst/feedreader/readability/UnrenderedTexTest.kt b/app/src/test/java/org/terst/feedreader/readability/UnrenderedTexTest.kt
new file mode 100644
index 0000000..016b148
--- /dev/null
+++ b/app/src/test/java/org/terst/feedreader/readability/UnrenderedTexTest.kt
@@ -0,0 +1,116 @@
+package org.terst.feedreader.readability
+
+import org.junit.Assert.assertFalse
+import org.junit.Assert.assertTrue
+import org.junit.Test
+
+/**
+ * Recognising a cached extraction that still holds raw TeX source.
+ *
+ * Substack ships maths as TeX source text in the page (`\(p = \text{...}\)` inside a
+ * `latex-rendered` wrapper) and renders it client-side with its own script, which never
+ * runs in this app. Extraction now converts that source to MathML before Readability sees
+ * it -- but an article extracted BEFORE that existed has the raw source sitting in
+ * `articles.extractedContent`, and every subsequent open reads it straight back out. The
+ * reported article came with "extractedContent cached: true", so this is the half a fixed
+ * extractor cannot reach.
+ *
+ * Over-detecting is the real risk: a false positive makes the article re-extract on every
+ * single open, since re-extracting cannot change a verdict the content itself causes. So
+ * the bar is a complete delimiter pair around something that actually looks like TeX, and
+ * never anything already carrying rendered MathML.
+ */
+class UnrenderedTexTest {
+
+    // "$$" cannot be written inline in a Kotlin string followed by a letter -- that parses
+    // as a template expression.
+    private val dollars = "$" + "$"
+
+    @Test
+    fun `substack's inline-delimited tex source is recognised`() {
+        assertTrue(
+            UnrenderedTex.looksLikeUnrenderedTex(
+                "<div data-component-name=\"Latex\"><p><span>" +
+                    "\\(p = \\text{“if }p\\text{ is true, then pigs can fly”}\\)</span></p></div>"
+            )
+        )
+    }
+
+    @Test
+    fun `bracket-delimited display tex source is recognised`() {
+        assertTrue(UnrenderedTex.looksLikeUnrenderedTex("<p>\\[\\begin{align} a &= b \\end{align}\\]</p>"))
+    }
+
+    @Test
+    fun `double-dollar display tex source is recognised`() {
+        assertTrue(UnrenderedTex.looksLikeUnrenderedTex("<p>" + dollars + "x_{1} + y^{2}" + dollars + "</p>"))
+    }
+
+    @Test
+    fun `content already carrying rendered mathml is left alone`() {
+        assertFalse(
+            UnrenderedTex.looksLikeUnrenderedTex(
+                "<p><math xmlns=\"http://www.w3.org/1998/Math/MathML\"><mi>p</mi></math></p>"
+            )
+        )
+    }
+
+    // An expression KaTeX could not render stays in the output as source. If the presence of
+    // any source at all convicted the whole article, that article would re-extract on every
+    // open, for ever, and never come out any different. Rendered maths anywhere in the
+    // content is proof the extraction already had its go at it.
+    @Test
+    fun `a leftover unrenderable expression alongside rendered mathml does not convict`() {
+        assertFalse(
+            UnrenderedTex.looksLikeUnrenderedTex(
+                "<p><math><mi>a</mi></math></p><p>\\(\\thisIsNotRealTex{}\\)</p>"
+            )
+        )
+    }
+
+    @Test
+    fun `ordinary prose is not tex`() {
+        assertFalse(
+            UnrenderedTex.looksLikeUnrenderedTex(
+                "<p>The repair bill came to $$ in the end; the second quote was $$ as well, and (as it " +
+                    "turned out) the warranty had lapsed anyway.</p>"
+            )
+        )
+    }
+
+    // The inner span between two stray delimiters is HTML, not one expression -- markup
+    // brings its own underscores and braces along (ids, filenames, inline styles), so a tag
+    // anywhere inside is on its own enough to say these two delimiters are unrelated.
+    @Test
+    fun `delimiters spanning real markup are not one expression`() {
+        assertFalse(
+            UnrenderedTex.looksLikeUnrenderedTex(
+                "<p>It cost $$ for the <a href=\"https://ex.com/part_no_4.html\">part</a>, " +
+                    "and $$ again for the labour.</p>"
+            )
+        )
+    }
+
+    @Test
+    fun `an unclosed delimiter is not tex`() {
+        assertFalse(UnrenderedTex.looksLikeUnrenderedTex("<p>Then he wrote \\(x, trailed off, and left.</p>"))
+    }
+
+    // Extraction deliberately skips <pre>/<code> when rendering maths -- an article ABOUT
+    // TeX quotes the source on purpose. Convicting on that would re-extract it on every
+    // open and still, correctly, change nothing.
+    @Test
+    fun `tex quoted inside a code block is not a stale extraction`() {
+        assertFalse(
+            UnrenderedTex.looksLikeUnrenderedTex(
+                "<p>Write it like this:</p><pre><code>\\(x^{2} + y^{2}\\)</code></pre>"
+            )
+        )
+    }
+
+    @Test
+    fun `nothing cached is not tex`() {
+        assertFalse(UnrenderedTex.looksLikeUnrenderedTex(null))
+        assertFalse(UnrenderedTex.looksLikeUnrenderedTex("   "))
+    }
+}