Files
tapir/scripts/spike-media/build_page.py
T
mathiasandClaude Opus 5 489b4bb2a1
CI / Lint / Test / Vet (push) Successful in 37s
CI / Build & Import (push) Failing after 5s
CI / Deploy via GitOps (push) Skipped
chore(spike): recover the /bygge toolchain from tmpfs (#28)
analyze_srt.py, build_page.py and transcode.yaml produced the /bygge
prototype. They were sitting in a session scratchpad on tmpfs, one reboot
from gone, while spike issues #29-#31 were written as if they had to be
built from scratch.

Committed as found, defects documented rather than fixed: max_tokens=6000
truncates anything past ~6 minutes of audio, the page title is hardcoded,
and the schema still carries fields no consumer renders.

The four-check validator is the part worth keeping — the coverage-gap and
Swedish-number-grounding checks catch errors that timestamp and citation
checks structurally cannot.

Real transcripts and analyses stay out: this repo is public and the
recordings are a named person discussing a client's project. Only the
synthetic fixture is committed, which exercises all four checks with no
model call.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
2026-08-13 11:37:03 +02:00

358 lines
14 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
"""Bygg en fristaende HTML-sida: video + SRT + tidssynkad analys.
Sidan ar sjalvbarande sa nar som pa videofilen - transkription och analys
bakas in i HTML:en. Det gor att den fungerar aven over file:// (fetch mot
en lokal JSON blockeras av CORS).
python3 build_page.py payload.json IMG_1233.web.mp4 > index.html
"""
from __future__ import annotations
import html
import json
import sys
TEMPLATE = """<!doctype html>
<html lang="sv">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>__TITLE__</title>
<style>
:root {
--bg:#f6f7f9; --panel:#fff; --ink:#16181d; --muted:#6b7280; --line:#e3e6ea;
--accent:#2563eb; --accent-soft:#eff4ff;
--beslut:#0f9d58; --alt:#d97706; --oppen:#dc2626; --matt:#7c3aed;
}
@media (prefers-color-scheme: dark) {
:root {
--bg:#0e1116; --panel:#161a21; --ink:#e6e9ef; --muted:#9aa3b2; --line:#262c36;
--accent:#60a5fa; --accent-soft:#17233b;
--beslut:#34d399; --alt:#fbbf24; --oppen:#f87171; --matt:#a78bfa;
}
}
:root[data-theme="dark"] {
--bg:#0e1116; --panel:#161a21; --ink:#e6e9ef; --muted:#9aa3b2; --line:#262c36;
--accent:#60a5fa; --accent-soft:#17233b;
--beslut:#34d399; --alt:#fbbf24; --oppen:#f87171; --matt:#a78bfa;
}
:root[data-theme="light"] {
--bg:#f6f7f9; --panel:#fff; --ink:#16181d; --muted:#6b7280; --line:#e3e6ea;
--accent:#2563eb; --accent-soft:#eff4ff;
--beslut:#0f9d58; --alt:#d97706; --oppen:#dc2626; --matt:#7c3aed;
}
* { box-sizing:border-box; }
body {
margin:0; background:var(--bg); color:var(--ink);
font:15px/1.55 -apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,sans-serif;
}
header {
padding:14px 20px; border-bottom:1px solid var(--line); background:var(--panel);
display:flex; align-items:baseline; gap:14px; flex-wrap:wrap;
}
header h1 { margin:0; font-size:17px; font-weight:650; }
header .sub { color:var(--muted); font-size:13px; }
.wrap {
display:grid; grid-template-columns: minmax(0,1.35fr) minmax(320px,1fr);
gap:20px; padding:20px; align-items:start; max-width:1600px; margin:0 auto;
}
@media (max-width: 950px) { .wrap { grid-template-columns:1fr; } }
/* Videon star stilla; analysen ror sig bredvid. */
.videocol { position:sticky; top:20px; }
video { width:100%; border-radius:10px; background:#000; display:block; }
.nowbar {
margin-top:10px; padding:12px 14px; background:var(--panel);
border:1px solid var(--line); border-radius:10px; min-height:64px;
}
.nowbar .label { font-size:11px; text-transform:uppercase; letter-spacing:.07em; color:var(--muted); }
.nowbar .text { margin-top:4px; font-size:16px; }
.tabs { display:flex; gap:6px; margin-bottom:12px; flex-wrap:wrap; }
.tab {
padding:6px 12px; border:1px solid var(--line); background:var(--panel);
border-radius:999px; cursor:pointer; font-size:13px; color:var(--ink);
}
.tab[aria-selected="true"] { background:var(--accent); border-color:var(--accent); color:#fff; }
.pane { display:none; }
.pane.active { display:block; }
.scroller {
max-height: calc(100vh - 190px); overflow-y:auto; padding-right:6px;
scroll-behavior:smooth;
}
.card {
background:var(--panel); border:1px solid var(--line); border-left:3px solid var(--line);
border-radius:8px; padding:11px 13px; margin-bottom:9px; cursor:pointer;
transition:border-color .15s, background .15s;
}
.card:hover { border-color:var(--accent); }
.card.on { background:var(--accent-soft); border-left-color:var(--accent); }
.card .k {
font-size:10px; text-transform:uppercase; letter-spacing:.07em;
font-weight:700; margin-bottom:5px;
}
.card .t { font-size:11px; color:var(--muted); font-variant-numeric:tabular-nums; }
.card .cit { display:block; margin-top:6px; color:var(--muted); font-size:13px; font-style:italic; }
.k.beslut{color:var(--beslut)} .k.alt{color:var(--alt)}
.k.oppen{color:var(--oppen)} .k.matt{color:var(--matt)}
.card.beslut{border-left-color:var(--beslut)} .card.alt{border-left-color:var(--alt)}
.card.oppen{border-left-color:var(--oppen)} .card.matt{border-left-color:var(--matt)}
.opts { margin:6px 0 0; padding-left:18px; font-size:13px; }
.lutar { font-size:12px; color:var(--muted); margin-top:5px; }
.cue {
padding:5px 9px; border-radius:6px; cursor:pointer; display:flex; gap:10px;
font-size:14px; border-left:2px solid transparent;
}
.cue:hover { background:var(--accent-soft); }
.cue.on { background:var(--accent-soft); border-left-color:var(--accent); font-weight:600; }
.cue .ts {
color:var(--muted); font-variant-numeric:tabular-nums; font-size:12px;
flex:0 0 46px; padding-top:2px;
}
.sec-head {
margin:16px 0 7px; font-size:12px; font-weight:700; text-transform:uppercase;
letter-spacing:.06em; color:var(--muted); border-bottom:1px solid var(--line);
padding-bottom:5px;
}
.sec-head:first-child { margin-top:0; }
.warn {
background:var(--panel); border:1px solid var(--line); border-left:3px solid var(--alt);
border-radius:8px; padding:11px 13px; font-size:13px; color:var(--muted);
}
.warn b { color:var(--ink); }
.warn ul { margin:6px 0 0; padding-left:18px; }
</style>
</head>
<body>
<header>
<h1>__TITLE__</h1>
<span class="sub">__SUB__</span>
</header>
<div class="wrap">
<div class="videocol">
<video id="v" controls preload="metadata" src="__VIDEO__"></video>
<div class="nowbar">
<div class="label">Sägs nu</div>
<div class="text" id="now">—</div>
</div>
</div>
<div>
<div class="tabs" role="tablist">
<button class="tab" role="tab" aria-selected="true" data-pane="analys">Analys</button>
<button class="tab" role="tab" aria-selected="false" data-pane="text">Transkription</button>
<button class="tab" role="tab" aria-selected="false" data-pane="kvalitet">Kvalitet</button>
</div>
<div class="pane active" id="pane-analys"><div class="scroller" id="analys"></div></div>
<div class="pane" id="pane-text"><div class="scroller" id="text"></div></div>
<div class="pane" id="pane-kvalitet"><div class="scroller" id="kvalitet"></div></div>
</div>
</div>
<script>
const DATA = __DATA__;
const v = document.getElementById('v');
const hms = s => {
s = Math.max(0, Math.floor(s));
return String(Math.floor(s/60)).padStart(2,'0') + ':' + String(s%60).padStart(2,'0');
};
const toSec = t => {
if (t == null) return null;
const p = String(t).trim().split(':').map(Number);
if (p.some(isNaN)) return null;
return p.length === 3 ? p[0]*3600+p[1]*60+p[2] : p.length === 2 ? p[0]*60+p[1] : p[0];
};
const esc = s => { const d = document.createElement('div'); d.textContent = s ?? ''; return d.innerHTML; };
/* Varje kort bar sin tid; ett klick soker dit. Analysen ar tidsforankrad
hela vagen ned, sa synkningen ar bara en sortering pa den tiden. */
const items = [];
const A = DATA.analys;
(A.avsnitt || []).forEach((s, i) => {
const t = toSec(s.start) ?? 0;
items.push({t, end: toSec(s.slut) ?? 1e9, kind:'avsnitt', html:
`<div class="k">Avsnitt ${i+1} · ${esc(s.start)}${esc(s.slut)}</div>
<div style="font-weight:650;font-size:15px">${esc(s.rubrik)}</div>
<div style="margin-top:5px">${esc(s.sammanfattning)}</div>`});
(s.nyckelpunkter || []).forEach(k => {
const kt = toSec(k.tid); if (kt == null) return;
items.push({t:kt, end:kt+6, kind:'punkt', citat:k.citat, html:
`<div class="t">${esc(k.tid)}</div><div>${esc(k.pastaende)}</div>
<div class="cit">”${esc(k.citat)}”</div>`});
});
});
(A.beslut || []).forEach(b => {
const t = toSec(b.tid); if (t == null) return;
items.push({t, end:t+8, kind:'beslut', citat:b.citat, html:
`<div class="k beslut">Beslut</div><div class="t">${esc(b.tid)}</div>
<div style="font-weight:600">${esc(b.vad)}</div>
${b.skal ? `<div class="lutar">Skäl: ${esc(b.skal)}</div>` : ''}
<div class="cit">”${esc(b.citat)}”</div>`});
});
(A.alternativ || []).forEach(a => {
const t = toSec(a.tid); if (t == null) return;
items.push({t, end:t+8, kind:'alt', citat:a.citat, html:
`<div class="k alt">Alternativ</div><div class="t">${esc(a.tid)}</div>
<div style="font-weight:600">${esc(a.fraga)}</div>
<ul class="opts">${(a.optioner||[]).map(o=>`<li>${esc(o)}</li>`).join('')}</ul>
<div class="lutar">${a.lutar_at ? 'Lutar åt: <b>'+esc(a.lutar_at)+'</b>' : 'Oavgjort'}</div>
<div class="cit">”${esc(a.citat)}”</div>`});
});
(A.oppna_fragor || []).forEach(o => {
const t = toSec(o.tid); if (t == null) return;
items.push({t, end:t+8, kind:'oppen', citat:o.citat, html:
`<div class="k oppen">Öppen fråga</div><div class="t">${esc(o.tid)}</div>
<div style="font-weight:600">${esc(o.fraga)}</div>
${o.beror_pa ? `<div class="lutar">Beror på: ${esc(o.beror_pa)}</div>` : ''}
<div class="cit">”${esc(o.citat)}”</div>`});
});
(A.matt || []).forEach(m => {
const t = toSec(m.tid); if (t == null) return;
items.push({t, end:t+6, kind:'matt', citat:m.citat, html:
`<div class="k matt">Mått</div><div class="t">${esc(m.tid)}</div>
<div>${esc(m.vad)}</div><div class="cit">”${esc(m.citat)}”</div>`});
});
const RANK = {avsnitt:0, beslut:1, oppen:2, alt:3, matt:4, punkt:5};
/* Samma replik klassas ofta bade som nyckelpunkt och som matt/beslut.
Visa den mest specifika varianten en gang i stallet for tva nastan
identiska kort - annars later flodet som ett eko. */
const bestByQuote = new Map();
items.forEach(it => {
const key = (it.citat||'').trim().toLowerCase() + '@' + it.t;
if (!it.citat) return;
const prev = bestByQuote.get(key);
if (prev === undefined || RANK[it.kind] < RANK[prev.kind]) bestByQuote.set(key, it);
});
const kept = items.filter(it => {
if (!it.citat) return true;
const key = (it.citat||'').trim().toLowerCase() + '@' + it.t;
return bestByQuote.get(key) === it;
});
items.length = 0; items.push(...kept);
items.sort((a,b) => a.t - b.t || RANK[a.kind] - RANK[b.kind]);
const analysEl = document.getElementById('analys');
analysEl.innerHTML = items.map((it,i) =>
`<div class="card ${it.kind}" data-i="${i}" data-t="${it.t}">${it.html}</div>`).join('');
const textEl = document.getElementById('text');
textEl.innerHTML = DATA.cues.map((c,i) =>
`<div class="cue" data-ci="${i}" data-t="${c.t}">
<span class="ts">${hms(c.t)}</span><span>${esc(c.text)}</span></div>`).join('');
const warns = (A._meta && A._meta.varningar) || [];
document.getElementById('kvalitet').innerHTML = `
<div class="warn">
<b>Automatisk källkontroll</b><br>
Modell: ${esc((A._meta&&A._meta.modell)||'')} · ${DATA.cues.length} repliker · längd ${esc((A._meta&&A._meta.langd)||'')}<br><br>
Varje påstående kontrolleras mot sitt eget citat: citatet måste återfinnas
ordagrant i transkriptionen, tiden måste ligga inom klippet, och varje tal i
påståendet måste styrkas av citatet.
${warns.length
? `<br><br><b>${warns.length} varningar:</b><ul>${warns.map(w=>`<li>${esc(w)}</li>`).join('')}</ul>`
: '<br><br>Inga avvikelser.'}
</div>`;
/* Klick söker i videon - åt båda håll: kort och replik. */
document.addEventListener('click', e => {
const el = e.target.closest('.card, .cue');
if (!el) return;
v.currentTime = parseFloat(el.dataset.t) + 0.05;
v.play().catch(()=>{});
});
document.querySelectorAll('.tab').forEach(tab => {
tab.addEventListener('click', () => {
document.querySelectorAll('.tab').forEach(t => t.setAttribute('aria-selected','false'));
tab.setAttribute('aria-selected','true');
document.querySelectorAll('.pane').forEach(p => p.classList.remove('active'));
document.getElementById('pane-' + tab.dataset.pane).classList.add('active');
});
});
/* Auto-scroll bara nar anvandaren inte sjalv scrollar - annars slits vyn
ur handerna pa den som lasar. */
let userScrolled = 0;
document.querySelectorAll('.scroller').forEach(s =>
s.addEventListener('wheel', () => { userScrolled = Date.now(); }, {passive:true}));
let lastCard = -1, lastCue = -1;
function sync() {
const t = v.currentTime;
let ci = -1;
for (let i = 0; i < DATA.cues.length; i++) {
if (t >= DATA.cues[i].t - 0.15) ci = i; else break;
}
if (ci !== lastCue) {
document.querySelectorAll('.cue.on').forEach(e => e.classList.remove('on'));
if (ci >= 0) {
const el = textEl.querySelector(`[data-ci="${ci}"]`);
if (el) {
el.classList.add('on');
if (Date.now() - userScrolled > 3000) el.scrollIntoView({block:'center'});
}
document.getElementById('now').textContent = DATA.cues[ci].text;
}
lastCue = ci;
}
let ai = -1;
for (let i = 0; i < items.length; i++) {
if (t >= items[i].t - 0.15) ai = i; else break;
}
if (ai !== lastCard) {
document.querySelectorAll('.card.on').forEach(e => e.classList.remove('on'));
if (ai >= 0) {
const el = analysEl.querySelector(`[data-i="${ai}"]`);
if (el) {
el.classList.add('on');
if (Date.now() - userScrolled > 3000 &&
document.getElementById('pane-analys').classList.contains('active')) {
el.scrollIntoView({block:'center'});
}
}
}
lastCard = ai;
}
requestAnimationFrame(sync);
}
requestAnimationFrame(sync);
</script>
</body>
</html>
"""
def main() -> None:
payload_path, video = sys.argv[1], sys.argv[2]
payload = json.load(open(payload_path, encoding="utf-8"))
a = payload["analys"]
proj = a.get("projekt") or {}
sub = " · ".join(
x for x in [proj.get("typ"), (a.get("_meta") or {}).get("langd"), video] if x
)
out = (
TEMPLATE.replace("__TITLE__", html.escape("Jonas genomgång av tillbyggnad"))
.replace("__SUB__", html.escape(sub))
.replace("__VIDEO__", html.escape(video))
.replace("__DATA__", json.dumps(payload, ensure_ascii=False))
)
sys.stdout.write(out)
if __name__ == "__main__":
main()