vocabmerge: a subject scheme, supplied rather than compiled in

parity/tests/subjects.rs

@@ -0,0 +1,123 @@
+//! Every judgement a subject scheme makes must match the Python exactly.
+//!
+//! A scheme decides what a shelf can be browsed by. A heading mapped onto the
+//! wrong subject files a book where nobody will look for it, and a fiction
+//! genre left on a biography puts a life of somebody in among the novels.
+
+use bibclean::scheme::Scheme;
+use serde_json::Value;
+
+fn records(text: &str) -> Vec<Value> {
+    text.lines()
+        .filter(|line| !line.trim().is_empty())
+        .map(|line| serde_json::from_str(line).expect("valid JSON"))
+        .collect()
+}
+
+fn cases() -> Vec<Value> {
+    let text = std::fs::read_to_string(parity::dir().join("cases/subjects/cases.ndjson"))
+        .expect("a readable case file");
+    records(&text)
+}
+
+fn strings(value: &Value) -> Vec<String> {
+    value
+        .as_array()
+        .expect("an array")
+        .iter()
+        .map(|item| item.as_str().expect("a string").to_string())
+        .collect()
+}
+
+#[test]
+fn every_judgement_matches_python() {
+    let golden = records(&parity::read_golden_text("subjects/cases.ndjson"));
+    let cases = cases();
+    assert_eq!(cases.len(), golden.len(), "case count moved — regenerate");
+
+    let mut wrong: Vec<String> = Vec::new();
+    for (case, theirs) in cases.iter().zip(&golden) {
+        let name = case["name"].as_str().expect("a name");
+        let kind = case["kind"].as_str().expect("a kind");
+        assert_eq!(theirs["name"].as_str(), Some(name), "cases out of order");
+
+        // The scheme travels with the case, because a scheme is exactly the
+        // thing that is not compiled in.
+        let scheme: Scheme =
+            serde_json::from_value(case["scheme"].clone()).expect("a readable scheme");
+        let title = case["title"].as_str();
+
+        let mut note = |field: &str, ours: String, theirs: &Value| {
+            wrong.push(format!("{name}.{field}: python {theirs}, rust {ours}"));
+        };
+
+        match kind {
+            "canonical" => {
+                let ours = scheme.canonical(case["tag"].as_str().expect("a tag"));
+                if ours != theirs["subject"].as_str() {
+                    note("subject", format!("{ours:?}"), &theirs["subject"]);
+                }
+            }
+            "parents" => {
+                let ours = scheme.with_parents(&strings(&case["subjects"]));
+                if ours != strings(&theirs["subjects"]) {
+                    note("subjects", format!("{ours:?}"), &theirs["subjects"]);
+                }
+            }
+            "fiction" => {
+                let ours = scheme.without_impossible_fiction(&strings(&case["subjects"]), title);
+                if ours != strings(&theirs["subjects"]) {
+                    note("subjects", format!("{ours:?}"), &theirs["subjects"]);
+                }
+            }
+            "compose" => {
+                let ours = scheme.compose(&strings(&case["subjects"]), title);
+                if ours != strings(&theirs["subjects"]) {
+                    note("subjects", format!("{ours:?}"), &theirs["subjects"]);
+                }
+            }
+            "needs" => {
+                let ours = scheme.needs_subject(&strings(&case["existing"]));
+                if Some(ours) != theirs["needs"].as_bool() {
+                    note("needs", ours.to_string(), &theirs["needs"]);
+                }
+            }
+            other => panic!("nothing answers a {other} case"),
+        }
+    }
+
+    assert!(
+        wrong.is_empty(),
+        "{} judgements differ:\n{}",
+        wrong.len(),
+        wrong
+            .iter()
+            .take(20)
+            .map(|line| line.chars().take(200).collect::<String>())
+            .collect::<Vec<_>>()
+            .join("\n")
+    );
+}
+
+/// Every question has to be asked, or the file proves less than it looks like
+/// it does.
+#[test]
+fn every_kind_of_case_is_present() {
+    let cases = cases();
+    for kind in ["canonical", "parents", "fiction", "compose", "needs"] {
+        assert!(
+            cases.iter().any(|case| case["kind"] == kind),
+            "no {kind} case"
+        );
+    }
+}
+
+/// Catches a golden file drifting away from a Python that has moved on.
+#[test]
+#[cfg(feature = "python")]
+fn the_golden_file_still_matches_live_python() {
+    let cases = std::fs::read_to_string(parity::dir().join("cases/subjects/cases.ndjson"))
+        .expect("a readable case file");
+    let live = parity::run_oracle("subjects.py", &cases).expect("the oracle runs");
+    assert_eq!(live, parity::read_golden_text("subjects/cases.ndjson"));
+}