feat: YAML content importer + phys/ct-2024 collection (proof)

content/phys/ct-2024.yaml — 15 questions from ЦЭ,ЦТ 2024 across 6 topics (kinem, mol, emf, electro, magnet, optics) as proof of format. backend/scripts/import-content.js — unified importer: - Validates schema (subject, year, options, exactly-1-correct) - Aliases (kinem, mol, ...) resolve to Russian topic names via get-or-create - Deduplicates by first 80 chars of text (matches legacy seed_*.js behavior) - Runs in a single transaction, idempotent re-runs On fresh DB: 13 added (2 dedup collisions — same 80-char prefix, expected). On prod DB: 0 added (all already exist from legacy seeds). Second run on either: 0 added (dedup works). Legacy seed_phys_ct2024.js kept as backup — see content/README.md for migration guide. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-06 17:42:07 +03:00
parent 977e46e75b
commit 25489a733a
5 changed files with 481 additions and 0 deletions
@@ -0,0 +1,169 @@
+#!/usr/bin/env node
+/**
+ * import-content.js — imports question collections from YAML manifests.
+ *
+ * Usage:
+ *   npm run import:content -- ../content/phys/ct-2024.yaml
+ *
+ * YAML format:  content/README.md
+ *
+ * Topic aliases (subject=phys):
+ *   kinem=29, dynam=30, cons=31, mol=32, thermo=33, electro=34,
+ *   dc=35, magnet=36, emf=37, optics=38, quantum=39, waves=40
+ *
+ * For subjects without predefined aliases, or for additional topics,
+ * add entries to SUBJECT_TOPIC_MAP below, or use full topic name strings
+ * as topic keys (they will be looked up / created automatically).
+ */
+'use strict';
+const fs   = require('fs');
+const path = require('path');
+const yaml = require('js-yaml');
+const db   = require('../src/db/db');
+
+/* ── Subject → topic alias → topic name (for get-or-create lookup) ────── */
+const SUBJECT_ID_MAP = { bio: 1, chem: 2, math: 3, phys: 4 };
+
+const SUBJECT_TOPIC_NAMES = {
+  phys: {
+    kinem:   'Кинематика',
+    dynam:   'Динамика',
+    cons:    'Законы сохранения',
+    mol:     'Молекулярная физика',
+    thermo:  'Термодинамика',
+    electro: 'Электростатика',
+    dc:      'Постоянный ток',
+    magnet:  'Магнетизм',
+    emf:     'Электромагнитная индукция',
+    optics:  'Оптика',
+    quantum: 'Квантовая и ядерная физика',
+    waves:   'Колебания и волны',
+  },
+  // Add math/bio/chem topic name maps here as collections are migrated
+};
+
+/* ── Look up or create topic by name (alias or full name) ─────────────── */
+function resolveTopicId(subjectId, key) {
+  const subjectSlug = Object.keys(SUBJECT_ID_MAP).find(s => SUBJECT_ID_MAP[s] === subjectId);
+  const aliasMap    = SUBJECT_TOPIC_NAMES[subjectSlug] || {};
+
+  // Resolve alias → full topic name (or use key as-is if it's already a name)
+  const topicName = aliasMap[key] || key;
+
+  const existing = db.prepare('SELECT id FROM topics WHERE subject_id=? AND LOWER(name)=LOWER(?)').get(subjectId, topicName);
+  if (existing) return existing.id;
+
+  const { lastInsertRowid } = db.prepare('INSERT INTO topics (subject_id, name) VALUES (?,?)').run(subjectId, topicName);
+  console.log(`[import] Created new topic: "${topicName}" (id=${lastInsertRowid})`);
+  return Number(lastInsertRowid);
+}
+
+/* ── Validation ──────────────────────────────────────────────────────── */
+function validate(doc, file) {
+  const errors = [];
+
+  if (!doc || typeof doc !== 'object')      { errors.push('document must be an object'); }
+  if (!doc?.meta?.subject)                  errors.push('meta.subject required');
+  if (!doc?.meta?.year)                     errors.push('meta.year required');
+  if (!SUBJECT_ID_MAP[doc?.meta?.subject])  errors.push(`unknown subject "${doc?.meta?.subject}" (valid: ${Object.keys(SUBJECT_ID_MAP).join(', ')})`);
+  if (!doc?.topics || typeof doc.topics !== 'object') errors.push('topics object required');
+
+  if (doc?.topics) {
+    for (const [topicKey, items] of Object.entries(doc.topics)) {
+      if (!Array.isArray(items)) { errors.push(`topics.${topicKey} must be array`); continue; }
+      items.forEach((q, i) => {
+        const loc = `topics.${topicKey}[${i}]`;
+        if (!q.text || typeof q.text !== 'string')  errors.push(`${loc}: text required (string)`);
+        if (!Array.isArray(q.options))               errors.push(`${loc}: options array required`);
+        else {
+          const correctCount = q.options.filter(o => o.correct).length;
+          if (correctCount !== 1) errors.push(`${loc}: exactly 1 correct option required (got ${correctCount})`);
+          q.options.forEach((o, oi) => {
+            if (!o.text) errors.push(`${loc}.options[${oi}]: text required`);
+          });
+        }
+        if (q.difficulty !== undefined && ![1, 2, 3].includes(Number(q.difficulty)))
+          errors.push(`${loc}: difficulty must be 1, 2, or 3`);
+      });
+    }
+  }
+
+  if (errors.length) {
+    console.error(`\n[import] FAIL: validation errors in ${path.basename(file)}:`);
+    errors.forEach(e => console.error(`  - ${e}`));
+    process.exit(2);
+  }
+}
+
+/* ── Import ──────────────────────────────────────────────────────────── */
+function importFile(file) {
+  const raw = fs.readFileSync(file, 'utf8');
+  const doc = yaml.load(raw);
+  validate(doc, file);
+
+  const subjectId = SUBJECT_ID_MAP[doc.meta.subject];
+  const year      = doc.meta.year;
+
+  // Dedup: skip questions whose first 80 chars already exist for this subject
+  const existingTexts = new Set(
+    db.prepare('SELECT text FROM questions WHERE subject_id=?').all(subjectId)
+      .map(q => q.text.slice(0, 80).trim())
+  );
+
+  const insertQ = db.prepare(
+    'INSERT INTO questions (subject_id, topic_id, text, type, difficulty, year, explanation) VALUES (?,?,?,?,?,?,?)'
+  );
+  const insertO = db.prepare(
+    'INSERT INTO options (question_id, text, is_correct, order_index) VALUES (?,?,?,?)'
+  );
+
+  let added = 0, skipped = 0;
+
+  db.transaction(() => {
+    for (const [topicKey, items] of Object.entries(doc.topics)) {
+      const topicId = resolveTopicId(subjectId, topicKey);
+
+      for (const q of items) {
+        const text = q.text.trim();
+        const key  = text.slice(0, 80).trim();
+
+        if (existingTexts.has(key)) { skipped++; continue; }
+        existingTexts.add(key);
+
+        const { lastInsertRowid } = insertQ.run(
+          subjectId,
+          topicId,
+          text,
+          q.type || 'single',
+          Number(q.difficulty) || 1,
+          year,
+          q.explanation || null
+        );
+
+        const qid = Number(lastInsertRowid);
+        q.options.forEach((o, i) => insertO.run(qid, o.text, o.correct ? 1 : 0, i));
+        added++;
+      }
+    }
+  })();
+
+  const source = doc.meta.source ? ` (${doc.meta.source})` : '';
+  console.log(`[import] ${path.basename(file)}${source} — added ${added}, skipped ${skipped} duplicates`);
+  return { added, skipped };
+}
+
+/* ── Entry point ─────────────────────────────────────────────────────── */
+const file = process.argv[2];
+if (!file) {
+  console.error('Usage: node import-content.js <path/to/collection.yaml>');
+  console.error('  npm run import:content -- ../content/phys/ct-2024.yaml');
+  process.exit(1);
+}
+
+const resolved = path.resolve(file);
+if (!fs.existsSync(resolved)) {
+  console.error(`[import] File not found: ${resolved}`);
+  process.exit(1);
+}
+
+importFile(resolved);