snakkimo-API/src/routes/feed.js

// GET /auth/feed?lang=sv&limit=20
// Returns hydrated pairs for the learning feed.
// Placeholders in sentences: {{label.w:wordId}} or {{label.o:objectId}}
// Pictures come from object_pairs → object_pictures → pictures.

const router = require('express').Router();
const jwt = require('jsonwebtoken');
const { query } = require('../db');

function requireJwt(req, res, next) {
  const header = req.headers['authorization'] || '';
  const token = header.startsWith('Bearer ') ? header.slice(7) : null;
  if (!token) return res.status(401).json({ error: 'Unauthorized' });
  try {
    req.user = jwt.verify(token, process.env.JWT_SECRET);
    next();
  } catch {
    return res.status(401).json({ error: 'Invalid or expired token' });
  }
}

// Parse {{label.w:uuid}} or {{label.o:uuid}} from a sentence string
function extractPlaceholders(text) {
  if (!text) return [];
  return [...text.matchAll(/\{\{([^.]+)\.(w|o):([0-9a-f-]{36})\}\}/g)]
    .map(m => ({ label: m[1], type: m[2] === 'w' ? 'word' : 'object', id: m[3] }));
}

// Collect unique IDs of a given type from multiple placeholder arrays
function collectIds(lists, filterType) {
  const ids = new Set();
  for (const list of lists) {
    for (const p of list) {
      if (!filterType || p.type === filterType) ids.add(p.id);
    }
  }
  return [...ids];
}

router.get('/', requireJwt, async (req, res, next) => {
  try {
    const lang  = ['de', 'en', 'sv'].includes(req.query.lang) ? req.query.lang : 'de';
    const limit = Math.min(parseInt(req.query.limit) || 20, 100);

    // 1. Random pairs — only fully ready content:
    //    pair published + linked question/statements published + a published picture exists.
    //    (Audio coverage is additionally enforced in Phase 2.)
    const pairsRes = await query(
      `SELECT p.id, p.answer_type, p.status, p.difficulty_level,
              p.question_id, p.positive_statement_id, p.negative_statement_id
         FROM pairs p
        WHERE p.status = 'published'
          AND (p.question_id IS NULL OR EXISTS (
                SELECT 1 FROM questions q WHERE q.id = p.question_id AND q.status = 'published'))
          AND (p.positive_statement_id IS NULL OR EXISTS (
                SELECT 1 FROM statements s WHERE s.id = p.positive_statement_id AND s.status = 'published'))
          AND (p.negative_statement_id IS NULL OR EXISTS (
                SELECT 1 FROM statements s WHERE s.id = p.negative_statement_id AND s.status = 'published'))
          AND EXISTS (
                SELECT 1 FROM object_pairs op
                  JOIN object_pictures pic ON pic.object_id = op.object_id
                  JOIN pictures pp ON pp.id = pic.picture_id
                 WHERE op.pair_id = p.id AND pp.status = 'published')
        ORDER BY random()
        LIMIT $1`,
      [limit]
    );
    if (!pairsRes.rows.length) return res.json([]);
    const pairs   = pairsRes.rows;
    const pairIds = pairs.map(p => p.id);

    // 2. Collect IDs
    const questionIds  = [...new Set(pairs.map(p => p.question_id).filter(Boolean))];
    const statementIds = [...new Set([
      ...pairs.map(p => p.positive_statement_id),
      ...pairs.map(p => p.negative_statement_id),
    ].filter(Boolean))];

    // 3. Fetch questions
    const questionsMap = {};
    if (questionIds.length) {
      const r = await query(
        `SELECT id, sentence_de, sentence_en, sentence_sv FROM questions WHERE id = ANY($1)`,
        [questionIds]
      );
      r.rows.forEach(q => { questionsMap[q.id] = q; });
    }

    // 4. Fetch statements
    const statementsMap = {};
    if (statementIds.length) {
      const r = await query(
        `SELECT id, positive_sentence_de, positive_sentence_en, positive_sentence_sv,
                negative_sentence_de, negative_sentence_en, negative_sentence_sv, answer
           FROM statements WHERE id = ANY($1)`,
        [statementIds]
      );
      r.rows.forEach(s => { statementsMap[s.id] = s; });
    }

    // 5. Parse all placeholders → find object IDs that need selections
    const allSentences = [
      ...Object.values(questionsMap).flatMap(q => [q.sentence_de, q.sentence_en, q.sentence_sv]),
      ...Object.values(statementsMap).flatMap(s => [
        s.positive_sentence_de, s.positive_sentence_en, s.positive_sentence_sv,
        s.negative_sentence_de, s.negative_sentence_en, s.negative_sentence_sv,
      ]),
    ];
    const allPlaceholderLists = allSentences.map(s => extractPlaceholders(s));
    const objectIds = collectIds(allPlaceholderLists, 'object');

    // 6. Fetch selections for object placeholders
    const selectionsMap = {}; // objectId → selections[]
    if (objectIds.length) {
      const r = await query(
        `SELECT id, selections FROM objects WHERE id = ANY($1)`,
        [objectIds]
      );
      r.rows.forEach(o => { selectionsMap[o.id] = o.selections || []; });
    }

    // Build global placeholder map: id → { type, selections? }
    // Labels are embedded in the sentence text — no lookup needed.
    const placeholderMap = {};
    for (const list of allPlaceholderLists) {
      for (const p of list) {
        if (!placeholderMap[p.id]) {
          placeholderMap[p.id] = p.type === 'object'
            ? { type: 'object', selections: selectionsMap[p.id] || [] }
            : { type: 'word' };
        }
      }
    }

    // 7. Fetch positive + negative words for PairWordCard answer options
    const statWordMap = {};
    if (statementIds.length) {
      const posRes = await query(
        `SELECT spw.statement_id, w.id, w.titel_de AS de, w.titel_en AS en, w.titel_sv AS sv
           FROM statement_positive_words spw
           JOIN words w ON w.id = spw.word_id
          WHERE spw.statement_id = ANY($1)`,
        [statementIds]
      );
      const negRes = await query(
        `SELECT snw.statement_id, w.id, w.titel_de AS de, w.titel_en AS en, w.titel_sv AS sv
           FROM statement_negative_words snw
           JOIN words w ON w.id = snw.word_id
          WHERE snw.statement_id = ANY($1)`,
        [statementIds]
      );
      statementIds.forEach(id => { statWordMap[id] = { positive: [], negative: [] }; });
      posRes.rows.forEach(r => { statWordMap[r.statement_id]?.positive.push({ id: r.id, de: r.de, en: r.en, sv: r.sv }); });
      negRes.rows.forEach(r => { statWordMap[r.statement_id]?.negative.push({ id: r.id, de: r.de, en: r.en, sv: r.sv }); });
    }

    // 7b. Fetch audios for the target language (question + statement sentences)
    //     keyed by `${source_table}|${source_id}|${source_field}`
    const audioMap = {};
    {
      const lookups = [];
      questionIds.forEach(id => lookups.push(['questions', id, 'sentence']));
      statementIds.forEach(id => {
        lookups.push(['statements', id, 'positive_sentence']);
        lookups.push(['statements', id, 'negative_sentence']);
      });
      if (lookups.length) {
        const ids = [...new Set(lookups.map(l => l[1]))];
        const r = await query(
          `SELECT source_table, source_id, source_field, audio_link, alignment
             FROM audios
            WHERE source_id = ANY($1) AND language = $2 AND status <> 'blocked'`,
          [ids, lang]
        );
        r.rows.forEach(a => {
          audioMap[`${a.source_table}|${a.source_id}|${a.source_field}`] =
            { url: a.audio_link, alignment: a.alignment };
        });
      }
    }
    const getAudio = (table, id, field) => audioMap[`${table}|${id}|${field}`] || null;

    // 8. Fetch pictures via object_pairs → object_pictures → pictures (one per pair)
    const pictureMap = {}; // pairId → { url, blurhash }
    if (pairIds.length) {
      const picRes = await query(
        `SELECT DISTINCT ON (op.pair_id)
                op.pair_id, p.picture_link AS url, p.blurhash
           FROM object_pairs op
           JOIN object_pictures pic ON pic.object_id = op.object_id
           JOIN pictures p ON p.id = pic.picture_id
          WHERE op.pair_id = ANY($1)
          ORDER BY op.pair_id, p.created_at`,
        [pairIds]
      );
      picRes.rows.forEach(r => { pictureMap[r.pair_id] = { url: r.url, blurhash: r.blurhash }; });
    }

    // 9. Build per-pair placeholder subset
    function getPairPlaceholders(p) {
      const sentences = [
        questionsMap[p.question_id]?.sentence_de,
        questionsMap[p.question_id]?.sentence_en,
        questionsMap[p.question_id]?.sentence_sv,
        statementsMap[p.positive_statement_id]?.positive_sentence_de,
        statementsMap[p.positive_statement_id]?.positive_sentence_en,
        statementsMap[p.positive_statement_id]?.positive_sentence_sv,
        statementsMap[p.negative_statement_id]?.negative_sentence_de,
        statementsMap[p.negative_statement_id]?.negative_sentence_en,
        statementsMap[p.negative_statement_id]?.negative_sentence_sv,
      ];
      const ids = new Set(sentences.flatMap(s => extractPlaceholders(s).map(ph => ph.id)));
      return Object.fromEntries([...ids].map(id => [id, placeholderMap[id] || null]));
    }

    function buildStatement(id) {
      if (!id || !statementsMap[id]) return null;
      const s = statementsMap[id];
      const posAudio = getAudio('statements', id, 'positive_sentence');
      const negAudio = getAudio('statements', id, 'negative_sentence');
      return {
        id,
        sentence_de:          s.positive_sentence_de,
        sentence_en:          s.positive_sentence_en,
        sentence_sv:          s.positive_sentence_sv,
        negative_sentence_de: s.negative_sentence_de,
        negative_sentence_en: s.negative_sentence_en,
        negative_sentence_sv: s.negative_sentence_sv,
        answer:         s.answer,
        positive_words: statWordMap[id]?.positive || [],
        negative_words: statWordMap[id]?.negative || [],
        audio_url:          posAudio?.url || null,
        audio_alignment:    posAudio?.alignment || null,
        negative_audio_url: negAudio?.url || null,
      };
    }

    function buildQuestion(id) {
      if (!id || !questionsMap[id]) return null;
      const q = questionsMap[id];
      const audio = getAudio('questions', id, 'sentence');
      return {
        id, sentence_de: q.sentence_de, sentence_en: q.sentence_en, sentence_sv: q.sentence_sv,
        audio_url: audio?.url || null, audio_alignment: audio?.alignment || null,
      };
    }

    // Audio-Gate: jeder nicht-leere Satz, der in der Zielsprache angezeigt wird,
    // muss ein Audio haben. Sonst fliegt das Pair aus dem Feed.
    function hasRequiredAudio(p) {
      const q = questionsMap[p.question_id];
      if (q && (q[`sentence_${lang}`] || '').trim() && !getAudio('questions', p.question_id, 'sentence'))
        return false;
      const ps = statementsMap[p.positive_statement_id];
      if (ps && (ps[`positive_sentence_${lang}`] || '').trim() && !getAudio('statements', p.positive_statement_id, 'positive_sentence'))
        return false;
      const ns = statementsMap[p.negative_statement_id];
      if (ns && (ns[`negative_sentence_${lang}`] || '').trim() && !getAudio('statements', p.negative_statement_id, 'negative_sentence'))
        return false;
      return true;
    }

    // 10. Assemble (only pairs whose displayed sentences all have audio)
    const result = pairs.filter(hasRequiredAudio).map(p => ({
      id:                  p.id,
      answer_type:         p.answer_type,
      status:              p.status,
      difficulty_level:    p.difficulty_level,
      lang,
      question:            buildQuestion(p.question_id),
      positive_statement:  buildStatement(p.positive_statement_id),
      negative_statement:  buildStatement(p.negative_statement_id),
      picture:             pictureMap[p.id] || null,
      placeholders:        getPairPlaceholders(p),
    }));

    res.json(result);
  } catch (err) { next(err); }
});

module.exports = { router, requireJwt };