Add Node-side fixture runner — both sides now exercise the corpus

Mirrors `content.js` normalizeId() in a self-contained `fixtures/run-node.mjs`. Loads `query-extraction.json` and `shared-normalization.json` and asserts each case the same way the Python runner does. content.js can't be imported directly — it lives inside an injected IIFE in the extension — so the runner duplicates the regexes (ID_RE_DASHED, ID_RE_UNDASHED, BUILTIN_ID_NORMALIZERS). Inline comment + README update flag that they must be kept in sync. Why this matters: `shared-normalization.json` now actually catches cross-side drift. A case that passes one side but fails the other is the canary — without a Node runner, the contract was aspirational. Verified: $ node fixtures/run-node.mjs query-extraction.json -> normalizeId (10 cases): 10 passed shared-normalization.json -> normalizeId (5 cases): 5 passed OK: all 15 cases passed Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-23 11:18:52 +02:00
parent b9a24b3fb5
commit 8d6bdb81af
2 changed files with 117 additions and 7 deletions
@@ -0,0 +1,102 @@
+// Node-side fixture runner — mirrors content.js normalizeId() for
+// query-extraction.json + shared-normalization.json.
+//
+// IMPORTANT: this file *replicates* the regexes from content.js by hand.
+// content.js lives inside an injected IIFE in the extension, so a real
+// import isn't feasible without restructuring it. If you touch ID_RE_DASHED,
+// ID_RE_UNDASHED, or BUILTIN_ID_NORMALIZERS in content.js, update them
+// here too. fixtures/shared-normalization.json catches cross-side drift
+// because Python and this runner both exercise it.
+//
+// Usage:
+//   node fixtures/run-node.mjs
+//
+// Exits non-zero on any fixture case failure.
+
+import { readFileSync } from "node:fs";
+import { fileURLToPath } from "node:url";
+import { dirname, join } from "node:path";
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+
+// ---------- mirror of content.js ----------
+
+const ID_RE_DASHED = /\b([A-Za-z][A-Za-z0-9]{1,})-(\d{2,7})[a-zA-Z]?\b/;
+const ID_RE_UNDASHED = /\b([A-Za-z][A-Za-z0-9]{1,})(\d{3,5})[a-zA-Z]?\b/;
+
+const BUILTIN_ID_NORMALIZERS = [
+  // FC2-PPV in any dash configuration: FC2PPV12345, FC2-PPV12345, FC2-PPV-12345
+  { re: /\bFC2-?PPV-?(\d{4,})\b/i, fmt: "FC2-PPV-$1" },
+  // Some sites display FC2 IDs without the PPV segment: FC2-1841460.
+  { re: /\bFC2-(\d{4,})\b/i, fmt: "FC2-PPV-$1" },
+];
+
+function applyNormalizers(text, userList = []) {
+  const all = [...userList, ...BUILTIN_ID_NORMALIZERS];
+  for (const n of all) {
+    let re;
+    try { re = n.re instanceof RegExp ? n.re : new RegExp(n.re, "i"); } catch { continue; }
+    const m = text.match(re);
+    if (m) {
+      return n.fmt.replace(/\$(\d)/g, (_, i) => m[+i] || "");
+    }
+  }
+  return null;
+}
+
+function normalizeId(text) {
+  if (!text) return null;
+  const fromNormalizer = applyNormalizers(text);
+  if (fromNormalizer) return fromNormalizer.toUpperCase();
+  let m = text.match(ID_RE_DASHED);
+  if (!m) m = text.match(ID_RE_UNDASHED);
+  if (!m) return null;
+  return `${m[1].toUpperCase()}-${m[2]}`;
+}
+
+// ---------- harness ----------
+
+function load(name) {
+  return JSON.parse(readFileSync(join(__dirname, name), "utf8"));
+}
+
+function run(label, cases) {
+  let passed = 0;
+  let failed = 0;
+  for (const c of cases) {
+    const got = normalizeId(c.input);
+    if (got === c.expected) {
+      passed += 1;
+    } else {
+      failed += 1;
+      console.log(`  FAIL [${label}] ${JSON.stringify(c.name)}`);
+      console.log(`        input    = ${JSON.stringify(c.input)}`);
+      console.log(`        expected = ${JSON.stringify(c.expected)}`);
+      console.log(`        got      = ${JSON.stringify(got)}`);
+    }
+  }
+  return { passed, failed };
+}
+
+let totalPassed = 0;
+let totalFailed = 0;
+
+for (const [filename, fnLabel] of [
+  ["query-extraction.json", "normalizeId"],
+  ["shared-normalization.json", "normalizeId"],
+]) {
+  const doc = load(filename);
+  const cases = doc.cases || [];
+  console.log(`\n${filename}  ->  node.${fnLabel}  (${cases.length} cases)`);
+  const { passed, failed } = run(filename, cases);
+  totalPassed += passed;
+  totalFailed += failed;
+  console.log(`  ${passed} passed | ${failed} failed`);
+}
+
+console.log();
+if (totalFailed > 0) {
+  console.log(`FAILED: ${totalFailed} of ${totalPassed + totalFailed} cases`);
+  process.exit(1);
+}
+console.log(`OK: all ${totalPassed} cases passed`);