tracker
All repositories: gitoria
5.3 KB
// tools/sync-tmdb.hl — THE TMDB SYNC FROM THE COMMAND LINE (tracker.worldapi.org#9): the same per-show sync// the app runs every day (tmdbsync.hl), for every followed show, one after the other, waiting between shows// so TMDB's 40 requests / 10 s (and TVmaze's 20 / 10 s) are never exceeded. Idempotent: a second run adds nothing (prints 0 new).//// STOP THE APP FIRST (or run it on a COPY): hl:mpackdb does not coordinate two processes on one storage// directory (hybriel#21). The running app does this itself every day (project.hl `syncTick`) — this tool is// for tests, the real-data proof and a manual catch-up.//// set -a; . ./.env; set +a # TMDB_READ_TOKEN — never print it// TRACKER_STORAGE=/abs/path/storage/mpackdb ./bin/hybriel tools/sync-tmdb.hl [--limit N] [--delta [--since YYYY-MM-DD] [--plan]]//// Default: the FULL WALK (every followed show). --delta (tracker#18): what the app's daily run does — the change lists since// the last run (deltasync.hl; `--since` overrides the stored day), then only the changed titles of ours; stores the day at the// end like the app (not with --since or --limit). --plan: only the change lists and the queue they give, no title synced.//// Prints one line per show and the totals: shows, newSeasons, newEpisodes, updatedEpisodes, updatedSeasons,// posters, ids (external ids filled, tracker.worldapi.org#12), requests, tvmazeRequests, errors, seconds, and (#15) what// TVmaze added: tvmazeEpisodes, tvmazeSeasons, tvmazeFilled (episodes whose empty title/air date it filled), tvmazeSkipped// (shows TVmaze numbers differently, left alone).import { env, args, exit } from 'hl:proc'import { now, sleep, timestamp } from 'hl:time'import { syncEnabled, pauseMsAfter } from '../lib/tmdb.hl'import { syncShow, syncShowDelta, persistSync } from '../lib/sync.hl'import { emptyTotals, addTotals, totalsLine } from '../lib/sync-helpers.hl'import { allFollowedShowIds } from '../lib/follows.hl'import { applySynced, persistDetails } from '../lib/details.hl'import { planStart, planStep, planIds, planLine, markSynced, isFollowedInRun } from '../lib/dailysync.hl'storageDir = env('TRACKER_STORAGE')if (storageDir == null || !storageDir.startsWith('/')) { console.log('REFUSED: set TRACKER_STORAGE, absolute (app stopped, or a copy)') exit(2) }if (!syncEnabled) { console.log('REFUSED: TMDB_READ_TOKEN is not set') exit(2) }limit = -1delta = falseplanOnly = falsesince = nullargv = args()i = 0while (i < argv.length) {if (argv[i] == '--limit' && i + 1 < argv.length) { limit = toNumber(argv[i + 1]) }if (argv[i] == '--delta') { delta = true }if (argv[i] == '--plan') { planOnly = true }if (argv[i] == '--since' && i + 1 < argv.length) { since = argv[i + 1] }i = i + 1}started = now()totals = emptyTotals()today = timestamp(started).slice(0, 10)runMode = 'full'changeRequests = 0ids = []if (delta) {// --since: as if the last run had been on that day (the stored day stays as it is)let p = planStart(today, since)runMode = p.modeconsole.log('tmdb sync: ' + p.mode + ' (' + p.why + ')')if (p.mode == 'delta') {let t0 = now()let done = falsewhile (!done) {let ps = planStep()changeRequests = changeRequests + ps.requests + ps.tvmazeRequeststotals.requests = totals.requests + ps.requeststotals.tvmazeRequests = totals.tvmazeRequests + ps.tvmazeRequestsdone = ps.doneif (ps.failed != '') { runMode = 'full' }sleep(pauseMsAfter(ps) / 1000)}console.log('tmdb sync: ' + planLine() + ' in ' + ((now() - t0) / 1000) + ' s')ids = runMode == 'delta' ? planIds() : allFollowedShowIds()} else { ids = allFollowedShowIds() }} else { ids = allFollowedShowIds() }if (planOnly) {console.log('tmdb sync plan: ' + ids.length + ' titles: ' + ids.join(' '))exit(0)}console.log('tmdb sync: ' + ids.length + (runMode == 'delta' ? ' changed titles' : ' followed shows') + (limit >= 0 ? ', limit ' + limit : ''))for (id of ids) {if (limit < 0 || totals.shows < limit) {// tracker#18: in a delta run a title nobody follows gets the light step (changed seasons, no TVmaze — tmdbsync.hl syncShowDelta)let light = runMode == 'delta' && !isFollowedInRun(id)let r = light ? syncShowDelta(id) : syncShow(id)totals = addTotals(totals, r)// tracker#18 + #28: the record's own fields + the cast + crew from the same details answerlet c = r.details != null ? applySynced(id, r.details) : { renamed = false cast = 0 crew = 0 people = 0 error = '' }console.log(' ' + id + (light ? ' (light)' : '') + (c.renamed ? ' (renamed)' : '') + ': +' + r.newSeasons + ' seasons +' + r.newEpisodes + ' episodes ~' + r.updatedEpisodes + ' updated, poster ' + r.posters + ', ids +' + r.ids+ ', tvmaze +' + r.tvmazeEpisodes + ' episodes +' + r.tvmazeSeasons + ' seasons ~' + r.tvmazeFilled + ' filled' + (r.tvmazeSkipped > 0 ? ' SKIPPED (numbered differently)' : '') + ', cast ' + c.cast + ' crew ' + c.crew + ' +' + c.people + ' people' + (r.error != '' ? ' ERROR ' + r.error : '') + (c.error != '' ? ' ERROR ' + c.error : ''))if (totals.shows % 10 == 0) { persistDetails() }sleep(pauseMsAfter(r) / 1000)}}persistDetails()if (delta && since == null && limit < 0 && runMode == 'delta') { markSynced(today) }console.log('tmdb sync done: mode=' + runMode + ' changeRequests=' + changeRequests + ' ' + totalsLine(totals) + ' seconds=' + ((now() - started) / 1000))on Error(e) { console.log(' error absorbed: ' + e.message) }
Branches
- mainmain branch
Latest commits
- 54796ff2tracker mission 028 (code order) 4/5 thin faces + last copies: the show page's check/follow faces call lib/watches.hl toggleWatched / toggleSeasonWatched (seasonAllWatched moved there) and lib/follows.hl toggleFollowed; both logins (header selector face, /login/callback) share lib/users.hl userOfCode; todayStr/listOf copies in components and the export readers copied into tools/migrate.hl + tools/old-short-ids.hl now once (lib/util.hl, lib/export.hl); gates 342/0, 32/0, 52/0; old-short-ids output byte-identical, migrate output identicalmre
- 06b078e3tracker mission 028 (code order) 3/5 project.hl is the map: config, routes, wiring and a feature → file index (914 → 258 lines); the background jobs (daily sync run, backfills, details repair, credits job, merge, short ids, collection seed) moved unchanged into lib/jobs.hl (a class: their state is reassigned every step, a static cannot be; one instance made after the server), the login callback into lib/users.hl, poster/photo serving into lib/images.hl, the /shows/<slug> rule into lib/shows.hl showsMovedPath; route handlers are thin wrappers; gates 342/0, 32/0, 52/0, real-copy pages identicalmre
- 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