mdscrub: residual html, control characters, headings, page markers

parity/tests/mdscrub.rs

@@ -0,0 +1,59 @@
+//! Cleaned markdown must match the Python byte for byte, except where the
+//! Rust is meant to differ — and there, the difference must be exactly the
+//! one that was argued for.
+
+fn case_text(case: &std::path::Path) -> String {
+    std::fs::read_to_string(case).expect("a readable case")
+}
+
+#[test]
+fn every_case_cleans_the_same_as_python() {
+    let cases = parity::cases("mdscrub");
+    assert!(!cases.is_empty(), "no cases found");
+
+    for case in cases {
+        let name = parity::case_name(&case);
+        if parity::DIVERGENT_MDSCRUB.contains(&name.as_str()) {
+            continue;
+        }
+        let ours = mdscrub::scrub(&case_text(&case));
+        let theirs = parity::read_golden_text(&format!("mdscrub/{name}.md"));
+        assert_eq!(ours, theirs, "{name} differs from the python");
+    }
+}
+
+#[test]
+fn the_documented_divergences_are_exactly_what_was_argued_for() {
+    for name in parity::DIVERGENT_MDSCRUB {
+        let case = parity::dir()
+            .join("cases/mdscrub")
+            .join(format!("{name}.md"));
+        let ours = mdscrub::scrub(&case_text(&case));
+        let theirs = parity::read_golden_text(&format!("mdscrub/{name}.md"));
+        assert_ne!(ours, theirs, "{name} no longer diverges — update KNOWN.md");
+        assert_eq!(
+            ours,
+            parity::read_golden_text(&format!("mdscrub/{name}.rust.md")),
+            "{name} diverges differently than recorded"
+        );
+    }
+}
+
+/// The one thing the divergence exists to prevent.
+#[test]
+fn a_line_break_tag_never_welds_two_words_together() {
+    let cleaned = mdscrub::scrub("the mill stood at the<br>northern end");
+    assert!(!cleaned.contains("thenorthern"), "{cleaned:?}");
+}
+
+/// Catches a golden file drifting away from a Python that has moved on.
+#[test]
+#[cfg(feature = "python")]
+fn the_golden_files_still_match_live_python() {
+    for case in parity::cases("mdscrub") {
+        let name = parity::case_name(&case);
+        let live = parity::run_oracle("mdscrub.py", &case_text(&case)).expect("the oracle runs");
+        let golden = parity::read_golden_text(&format!("mdscrub/{name}.md"));
+        assert_eq!(live, golden, "golden file for {name} is stale");
+    }
+}