tracker
All repositories: gitoria
7.4 KB
// tests/realdata-026.mjs — tracker.worldapi.org#26, NOT the gate: on a COPY of live storage/ with the REAL TMDB (STATUS.md// "ticket #26"). For each person: their page (the fill adds the titles we don't have), then a filmography row of a title that// is still INCOMPLETE (one movie, one series — rows are tried until one shows the loading state) is clicked (client-side):// time until the page shows (skeleton), until it is complete (skeleton gone) and until the poster is loaded; /movies is asked// every 100 ms meanwhile (how long other requests wait); then a full reload of the same title (complete at once). Screenshots// (skeleton + complete) to $REAL_OUT. Env: REAL_PORT (8750), REAL_CHROME (8752-8753), REAL_OUT (/tmp/w059/real),// REAL_PEOPLE ('Slug-A:390,Slug-B:1280'; '' = none), REAL_TRIES (8 rows per kind at most), REAL_TITLES (see below).import { writeFileSync, mkdirSync } from 'node:fs';import { launchBrowser } from './cdp.mjs';process.env.HL_CHROME ||= '/opt/google/chrome/chrome';const BASE = `http://127.0.0.1:${process.env.REAL_PORT || 8750}`, OUT = process.env.REAL_OUT || '/tmp/w059/real';mkdirSync(OUT, { recursive: true });const [CH_FROM, CH_TO] = (process.env.REAL_CHROME || '8752-8753').split('-').map(Number);const TRIES = Number(process.env.REAL_TRIES || 8);const browser = await launchBrowser({ debugPortRange: [CH_FROM, CH_TO || CH_FROM] });const page = await browser.newPage();const ev = (e) => page.evaluate(e);const hydrated = () => page.waitFor('!!window.__hl && window.__hl.socket && window.__hl.socket.readyState === 1 && document.readyState === "complete"', { timeout: 30000, label: 'hydrated' });const imgsDone = () => page.waitFor(`Array.from(document.querySelectorAll('img')).filter(i => { const r = i.getBoundingClientRect(); return r.top < innerHeight && r.bottom > 0 }).every(i => i.complete)`, { timeout: 30000, label: 'imgs' }).catch(() => 'imgs timeout');const shot = async (n) => writeFileSync(`${OUT}/${n}.png`, Buffer.from((await page.send('Page.captureScreenshot', { format: 'png' })).data, 'base64'));const state = () => ev(`JSON.stringify({ h1: (document.querySelector('show-header h1') || {}).textContent || null, loading: !!document.querySelector('#showloading'),poster: !!document.querySelector('show-poster img'), posterLoaded: !!(document.querySelector('show-poster img') && document.querySelector('show-poster img').complete && document.querySelector('show-poster img').naturalWidth > 0),links: Array.from(document.querySelectorAll('show-links a.extlink')).map(a => a.textContent).join(','), genres: document.querySelectorAll('a.genre-pill').length,cast: document.querySelectorAll('a.artist-link').length, seasons: document.querySelectorAll('season-row').length, episodes: document.querySelectorAll('episode-row').length,summary: ((document.querySelector('show-summary') || {}).textContent || '').length, scrollW: document.documentElement.scrollWidth, marker: window.__w059 || null })`).then(JSON.parse);const out = [];const people = (process.env.REAL_PEOPLE ?? 'Patrick-Stewart:390,Maya-Rudolph:1280').split(',').filter(Boolean).map(c => c.split(':'));for (const [slug, width] of people) {const w = Number(width), mobile = w < 600;await page.send('Emulation.setDeviceMetricsOverride', { width: w, height: mobile ? 844 : 900, deviceScaleFactor: mobile ? 2 : 1, mobile });await page.goto(BASE + '/person/' + slug); await hydrated();await page.waitFor(`!document.querySelector('#personloading')`, { timeout: 120000, label: 'person filled' });const rows = JSON.parse(await ev(`JSON.stringify(Array.from(document.querySelectorAll('a.film-row')).map(a => [a.getAttribute('href'), a.querySelector('film-type').textContent, a.querySelector('film-title').textContent]))`));out.push(`${slug} (${w} px): ${rows.length} filmography rows`);for (const kind of ['Movie', 'Series']) {let tried = 0, done = false;for (const [href, type, title] of rows.filter(r => r[1] === kind)) {if (done || tried >= TRIES) break;tried++;await page.goto(BASE + '/person/' + slug); await hydrated();await ev(`window.__w059 = 'same'`);let polling = true; const lat = [];const poll = (async () => { while (polling) { const t = Date.now(); await fetch(BASE + '/movies'); lat.push(Date.now() - t); await new Promise(r => setTimeout(r, 100)); } })();const t0 = Date.now();await page.click(`a.film-row[href="${href}"]`);await page.waitFor(`location.pathname === ${JSON.stringify(href)} && !!document.querySelector('show-header h1')`, { timeout: 20000, label: 'title shown' });const shown = Date.now() - t0;const s0 = await state();if (!s0.loading) { polling = false; await poll; out.push(` ${kind} "${title}" ${href}: already complete (no loading) — next`); continue; }await shot(`${kind.toLowerCase()}-skeleton-${w}`);await page.waitFor(`!document.querySelector('#showloading')`, { timeout: 60000, label: 'complete' });const complete = Date.now() - t0;await page.waitFor(`!document.querySelector('show-poster img') || (document.querySelector('show-poster img').complete && document.querySelector('show-poster img').naturalWidth > 0)`, { timeout: 20000, label: 'poster' }).catch(() => {});const posterAt = Date.now() - t0;polling = false; await poll;await imgsDone();const s1 = await state();await shot(`${kind.toLowerCase()}-complete-${w}`);out.push(` ${kind} "${title}" ${href}: shown ${shown} ms (skeleton), complete ${complete} ms, poster ${posterAt} ms; before ${JSON.stringify(s0)}; after ${JSON.stringify(s1)}; /movies meanwhile n=${lat.length} max=${Math.max(...lat)} ms median=${lat.sort((a, b) => a - b)[lat.length >> 1]} ms`);const t2 = Date.now();await page.goto(BASE + href); await hydrated(); await imgsDone();const s2 = await state();out.push(` reload: full load ${Date.now() - t2} ms, loading=${s2.loading}, same parts=${s2.cast === s1.cast && s2.seasons === s1.seasons && s2.links === s1.links && s2.poster === s1.poster}`);await shot(`${kind.toLowerCase()}-reload-${w}`);done = true;}if (!done) out.push(` ${kind}: no incomplete title among ${tried} tried`);}}// REAL_TITLES='Slug-A,Slug-B': incomplete titles opened DIRECTLY (full load, 1280) — e.g. a talk show with thousands of episodesfor (const slug of (process.env.REAL_TITLES || '').split(',').filter(Boolean)) {await page.send('Emulation.setDeviceMetricsOverride', { width: 1280, height: 900, deviceScaleFactor: 1, mobile: false });let polling = true; const lat = [];const poll = (async () => { while (polling) { const t = Date.now(); await fetch(BASE + '/movies'); lat.push(Date.now() - t); await new Promise(r => setTimeout(r, 100)); } })();const t0 = Date.now();await page.goto(BASE + '/shows/' + slug); await hydrated();const s0 = await state();await page.waitFor(`!document.querySelector('#showloading')`, { timeout: 120000, label: 'complete' });const complete = Date.now() - t0;polling = false; await poll;await imgsDone();const s1 = await state();await shot(`direct-${slug}-1280`);out.push(`direct ${slug}: loading at first=${s0.loading}, complete ${complete} ms after the request; after ${JSON.stringify(s1)}; /movies meanwhile n=${lat.length} max=${Math.max(...lat)} ms median=${lat.sort((a, b) => a - b)[lat.length >> 1]} ms`);}console.log(out.join('\n'));console.log('problems', JSON.stringify(page.problems()));await browser.close();
Branches
- mainmain branch
Latest commits
- 94716fd2tracker mission 028 (code order) 2/5 util + topics: lib/util.hl holds envOr, storageDir, postersDir, profilesDir, newId, hexDigits, todayStr, dateOr, textOr, hasId, listOr, firstOf, sortDesc once (were copied into up to 5 files); tmdbsync.hl split into tmdb.hl (TMDB/TVmaze requests), sync.hl (one title's sync), sync-helpers.hl, backfill.hl; details.hl split into details.hl, credits.hl, credits-helpers.hl (isIncomplete to shows.hl); search-helpers.hl (words, query, ranking, slugs); collections.hl (the TMDB collection seed, out of franchises.hl); deltasync.hl renamed dailysync.hl; no behaviour change: gates 342/0, 32/0, 52/0, real-copy pages identicalmre
- 186079b0tracker mission 028 (code order) 1/5 move: every root .hl except project.hl into lib/ (styles.hl into components/), import paths only; gates 342/0, 32/0, 52/0; real-copy pages identicalmre
- 4f47f181tracker: report 027mre
- dc1d4be4tracker mission 027: Hybriel master 06617221 vendored (plugin allocator fixes 3a781359 + 413f60e4); real copy RSS through first-start jobs + 400 loads flat ~2.55 GB (190aa11d 2.3 -> 5.6 GB), page times <= 1.1x; gates 342/0, 32/0, 52/0mre
- 84e1b3e1tracker: reports 025 + 026mre
- dc40d859tracker#31 (mission 026): duplicate titles merged — the 68 type+tmdbId pairs held by 157 records were the old tracker's (all migrated); merge.hl repair job (own clock, before the TMDB jobs) keeps one keeper per title (follows/watches > old short id > oldest), moves follows, watches, seasons, cast, credits, timelines, tombstones the rest (mergedInto, never deleted), slugs + short ids 301 to the keeper; stray seasons merged into their listed twin (Reacher S3 watches) or linked when watched; search import re-checks before its put; deploy.sh waits up to 90 s for 200; real copy 68 -> 0 dup ids, az5b2 follows/watches equal; gates 342/0, 32/0, 52/0mre
- 2667da05tracker#30 (mission 025): /my/ pages from slim cached title cards, episode rows and watch sets (after the jobs /my/series 1.8 s -> 0.06 s, /my/unwatched 4.1 -> 0.18 s); timeline page shows its name once; franchise widget under the poster/title; movies with TV leftovers (First Contact) go through the details repair; tools/count-tmdb-ids.hl; gates 327/0, 52/0, 32/0mre
- 3909810dantcolony#40: mission references in README/STATUS/docs point to the moved missionsmre
- e63b1d28antcolony#40: history (LOG.md), worker briefs (missions/) and reports moved here from antcolony, numbered per project; old numbers in antcolony docs/mission-map.mdmre
- 1cda451dtracker: Hybriel master 190aa11d (#127 both shapes, GC correctness fc838894) — conductor adopts despite /my/series 2.4x after jobs (memory 8.0 → 1.7 GB boot); see reports/071mre
- c1fa2f2etracker (mission 071): Hybriel master 190aa11d measured on the real copy vs the live binary 8590df63 — NOT adopted (after the first-start jobs /my/series 2.4x slower, /series 1.6x, RSS swings 7.4-12.2 GB; fresh it is flat at 1.7-2.2 GB and /my/unwatched faster), vendor stays 8efba065, candidate kept in .scratch/w071/vendor-190aa11d; tests/kinds.mjs: collection seed off (its TMDB request broke check 1 in 1 of 4 runs); tests/realdata-071.sh + realdata-071-bench.mjs + tools/realdata-071-table.py; README + STATUS (numbers, how to repeat); gates 325/0, 32/0, 50/0mre
- 8081350atracker docs (mission 070): README (summary, Config HL_GC_BYTES — kept at Hybriel's default, the 256 MiB setting is taken out of docker-compose.yml again: the jobs grew to 12+ GB with it too, see STATUS), Test (three gates), Deploy (first start ~50 min: kinds then seed, restart once after collections done, memory numbers), Vendored Hybriel 8efba065 + #48 audit, Files; STATUS mission 070 entry (merges, migrated counts, lambda audit, gates, RSS old vs new, how to repeat, open points); docs/kinds.md + docs/franchises.md job order; tests/realdata-070-*.sh, tools/count-migrated.hl, tools/ref-params.py, tools/lambda-audit.pymre
- 1ad19c8ctracker: re-vendor Hybriel master 8efba065 (#126 GC by bytes, #48 lambda parameters copy) (mission 070): bin/hybriel sha256 50361e95…, plugins core crypto data fetch fs http http1 mpackdb proc smtp time web; lambda audit: 13 lambdas change a passed record/list (11 through a local alias), no caller relies on it — unchanged; 319 read-only lambda parameters get & (no copy per call: /my/schedule 2.35 → 0.46 s, /my/unwatched 13.7 → 5.7 s on the real copy); /my/unwatched one merge sort instead of n² inserts; docker-compose HL_GC_BYTES=268435456; deploy.sh runs kinds.mjs + franchises.mjs too (default ports 8700–8710); tests/realdata-070.mjs; gates browser 325/0, kinds 32/0, franchises 50/0mre
- 46b21389tracker (mission 070, conductor): the sync never destroys migrated data — the one-time summary step MOVES a copied summary to migratedSummary (marker summaries-moved.txt) instead of clearing it; a migrated record's first title/genres/homepage/tagline TMDB replaces → migratedTitle/migratedGenres/migratedHomepage/migratedTagline, a migrated season's/episode's title/summary → migratedTitle/migratedSummary (set once); tests/peek-shows.hl prints them; gate 325/0mre
- 749019b0Merge t19 (tracker#19 franchises + timelines) into main (mission 070): conflicts README/STATUS/show.hl/project.hl/browser.mjs/faketmdb.mjs, both sides kept; franchise/timeline pages get #20's typed heading (Franchise | …, Timeline | …), their title links via titlePath (/movies|/series|/shows); the collection seed waits for repair, kinds and credits too; franchises.mjs URLs + 2 new checks; gates browser 323/0, kinds 32/0, franchises 50/0mre
- daf49feaMerge t20 (tracker#20 typed headings + #21 series/shows split) into main (mission 070): conflicts README/STATUS/show.hl/project.hl/search.hl/components/search.hl/browser.mjs/faketmdb.mjs, both sides kept; clock order backfill → repair → kinds → credits; withDetailsFields stores tmdbType + kind; gates: browser.mjs URLs → /series|/movies, typed h1 selectors; kinds.mjs repair/credits off, fixture name = seed name; browser 323/0, kinds 32/0mre
- 20e09d89Merge t18 (tracker#18 delta sync) into main (mission 070): conflicts README/STATUS/show.hl/project.hl/browser.mjs, both sides kept; pageShowOf summary = summaryOfmre
- f83571c3tracker#18 (mission 067): daily sync by change lists — TMDB /tv|movie/changes (since the stored day, paged) + TVmaze /updates/shows → only our changed titles (followed: full step, unfollowed: light step — changed seasons, no TVmaze), full walk on first run / gap > 14 days / failed list; show record refreshed (title, tmdbSummary, tagline, status, genres …; renamed titles re-indexed); summary = the creator's own text (page: summary > tmdbSummary > tvmazeSummary), one-time clear of copied summaries (9,647 on the live copy); gate 261, tests/realdata-018*.mjs, README + STATUSmre
- 1ed5457etracker#20 + #21 (mission 068): typed headings "<Type> | <name>" in type colours; TV titles split into Series (/series) and Shows (/shows) by TMDB type + Reality/Talk/News genres — kind stored by sync/import/adult backfill + new kind backfill (resumes), /movies/<slug>, /shows/<slug> of a series/movie → 301, /my/series + /my/shows, home 5 tiles + 3 rows, search/filmography labels; gates kinds 32 + browser 266, tests/realdata-068.mjs, tools/count-kinds.hl, docs/kinds.md, README + STATUSmre
- f2b00674Merge t26 (tracker#26 + #28) into main (mission 062): short ids for every new person (castPersonId, guest route), guest stars stored on the title and created as people only when opened (/person/tmdb/<id>?show=<id> → 302), lean watch/follow clicks (showRow a small object, cast/crew from the slug, watches cached per user, face rows only after a season toggle); gate 311, tests/realdata-062.mjs, README + STATUSmre