tts-voice-creator-clone-and.../static/js/magazine.js
mARTin-B78 5adba6b4c0
Some checks are pending
Test and SonarQube / quality (push) Waiting to run
feat: split-screen article review with numbered regions, per-page/whole-magazine "OCR again", and a real column-interleaving fix it found
Split-screen review: the rendered page (left) with a numbered box per
detected block, the extracted text (right) with matching numbers.
Clicking either side highlights the other. Checkboxes moved from a flat
list into this layout without changing their semantics (still gate
what gets narrated).

"OCR again": reocr_page() forces one page through the configured
vision engine again, replacing only that page's blocks -- deliberately
does NOT call build_articles(), so an already-approved article is not
silently re-grouped. A magazine-level option re-reads every page and
re-runs detection (with a confirmation, since that does reset article
status). extract_pages() gained force_vision_ocr to skip its quality
gate for this case.

Building the numbered-box review immediately did what it was built to
do -- surfaced a real bug on live production data (real magazine, real
scan, not a synthetic fixture): a photo caption at 49.9% of the page
width sat in the gutter between two genuinely separate columns and
merged them into one, so every block on the page came back column=0
and reading order fell back to pure top-to-bottom, interleaving the
two columns' sentences. Fixed two compounding causes: column boundary
detection now excludes blocks much wider than the page's median width,
and detect_columns' gutter threshold (3.5%) was itself narrower than
some real magazine gutters (~2.1% measured) -- lowered to 1.5%.

10 new/updated tests, including one built directly from the real
measured page-17 block coordinates that exposed the bug.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-07 14:00:34 +02:00

1218 lines
47 KiB
JavaScript
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.

// Magazine reader — contents tree, article review, dual reading views,
// sentence-highlighted playback and podcast mode.
//
// The canonical object is the ARTICLE, not the page (see
// architecture/magazine-ingestion.md). Nothing is narrated until a human has
// approved the detected boundaries, so the review screen is on the critical
// path rather than an optional extra.
//
// Two views stay linked: the reflowed article (comfortable reading, sentence
// highlighting) and the original PDF page (the visual source of truth). Every
// block carries page + bbox, so either view can jump to the other.
(function (root) {
'use strict';
const MAG = root.TTVC = root.TTVC || {};
const state = {
docs: [],
doc: null, // { id, title, issue, ingest, ... }
articles: [],
layout: null, // { page_count, pages[], blocks[] }
article: null, // the article being read or reviewed
sentences: [], // [{ text, blockId, page, bbox }]
images: [], // current article's figures, in reading order
view: 'library', // library | contents | review | read
pane: 'reflow', // reflow | pdf
playing: false,
cancel: false,
idx: 0, // current sentence
audio: null,
voices: [],
podcast: null,
queue: [], // article ids for "play all" (empty = not queued)
queueIndex: -1,
driving: false, // large-control, minimal-interaction view
karaoke: true, // word-level highlighting (approximate, see estimateWordTimings)
};
MAG.magazine = state;
const $ = (id) => document.getElementById(id);
const esc = (s) => String(s == null ? '' : s).replace(/[&<>"']/g,
(c) => ({ '&': '&amp;', '<': '&lt;', '>': '&gt;', '"': '&quot;', "'": '&#39;' }[c]));
function say(msg, kind) { if (typeof toast === 'function') toast(msg, kind || ''); }
async function api(path, opts) {
const r = await fetch(path, opts);
if (!r.ok) {
let detail = r.statusText;
try { detail = (await r.json()).detail || detail; } catch (_) {}
throw new Error(detail);
}
const type = r.headers.get('content-type') || '';
return type.includes('json') ? r.json() : r;
}
function fmtDuration(seconds) {
const s = Math.max(0, Math.round(seconds || 0));
if (s < 60) return s + ' sec';
const m = Math.round(s / 60);
return m < 60 ? m + ' min' : Math.floor(m / 60) + ' h ' + (m % 60) + ' min';
}
function fmtPages(pages) {
if (!pages || !pages.length) return '—';
if (pages.length === 1) return 'p. ' + pages[0];
// Non-contiguous page lists are the norm once a feature jumps, and showing
// "18–88" for pages [18, 88] would misdescribe it as a 70-page article.
const runs = [];
let start = pages[0], prev = pages[0];
for (let i = 1; i <= pages.length; i++) {
if (pages[i] === prev + 1) { prev = pages[i]; continue; }
runs.push(start === prev ? String(start) : start + '–' + prev);
start = prev = pages[i];
}
return 'pp. ' + runs.join(', ');
}
// ── Library ──────────────────────────────────────────────────────────────────
async function magLoadLibrary() {
const data = await api('/api/reader/docs');
state.docs = (data.docs || []).filter((d) => d.kind === 'magazine');
renderLibrary();
}
function renderLibrary() {
const host = $('mag-library-list');
if (!host) return;
if (!state.docs.length) {
host.innerHTML =
'<p class="muted" style="padding:18px 0">No magazines yet. Add one to get started — ' +
'upload a PDF and the articles are detected for you.</p>';
return;
}
host.innerHTML = state.docs.map((d) => {
const ing = d.ingest || {};
const badge = ing.status === 'done'
? '<span class="mag-pill ok">' + (ing.articles || 0) + ' articles</span>'
: ing.status === 'running' ? '<span class="mag-pill warn">ingesting…</span>'
: ing.status === 'failed' ? '<span class="mag-pill bad">failed</span>'
: '<span class="mag-pill">not ingested</span>';
return '<button type="button" class="mag-card" onclick="magOpen(\'' + d.id + '\')">' +
'<span class="mag-card-title">' + esc(d.title || 'Untitled') + '</span>' +
'<span class="mag-card-sub">' + esc(d.issue || '') + '</span>' +
badge + '</button>';
}).join('');
}
// ── Add-magazine dropzone (mirrors reader.js's setupReaderDropzone) ─────────
const MAG_DROPZONE_DEFAULT_NOTE = 'Scanned issues work too — pages without selectable text are read with OCR.';
function magShowDroppedFile(file) {
const noteEl = $('mag-dropzone-note');
if (noteEl) noteEl.textContent = file ? file.name : MAG_DROPZONE_DEFAULT_NOTE;
}
let _magDropGuardInstalled = false;
function setupMagDropzone() {
const zone = $('mag-dropzone');
const input = $('mag-new-file');
if (!zone || !input) return;
// A page-wide safety net: if a drop ever lands outside the zone (or the
// zone's own handler below fails to intercept it for any reason), the
// browser's native behaviour is to navigate to/open the dropped file --
// confirmed live as exactly what happened before this existed. Installed
// once regardless of which section is active, since a stray drop can land
// anywhere on the page.
if (!_magDropGuardInstalled) {
_magDropGuardInstalled = true;
window.addEventListener('dragover', (e) => { e.preventDefault(); });
window.addEventListener('drop', (e) => { e.preventDefault(); });
}
if (zone.dataset.magDropzoneWired) return;
zone.dataset.magDropzoneWired = '1';
// dragenter AND dragover both need preventDefault() -- some browsers only
// arm the element as a valid drop target once dragenter itself has been
// cancelled, not just the dragover events that follow it. Not gated on
// dataTransfer.types: during a real OS file drag, Chromium does not
// always populate that list synchronously on every one of these events,
// and gating on it here (confirmed live) silently skipped preventDefault
// often enough that neither the hover highlight nor the drop interception
// ever fired -- the browser fell through to opening the file itself.
const armDropTarget = (e) => { e.preventDefault(); zone.classList.add('dragover'); };
zone.addEventListener('dragenter', armDropTarget);
zone.addEventListener('dragover', armDropTarget);
zone.addEventListener('dragleave', () => zone.classList.remove('dragover'));
zone.addEventListener('drop', (e) => {
e.preventDefault();
zone.classList.remove('dragover');
const file = e.dataTransfer?.files?.[0];
if (!file) return;
if (file.type !== 'application/pdf' && !/\.pdf$/i.test(file.name)) {
return say('Only PDF files are supported', 'err');
}
// Route the dropped file through the same hidden <input> magCreate()
// already reads, so drag-and-drop and "Choose file" share one code path.
const dt = new DataTransfer();
dt.items.add(file);
input.files = dt.files;
magShowDroppedFile(file);
});
input.addEventListener('change', () => magShowDroppedFile(input.files?.[0]));
}
async function magCreate() {
const title = ($('mag-new-title')?.value || '').trim();
const issue = ($('mag-new-issue')?.value || '').trim();
const file = $('mag-new-file')?.files?.[0];
if (!title) return say('Give the magazine a title', 'err');
if (!file) return say('Choose or drop the PDF', 'err');
try {
const { id } = await api('/api/magazine/docs', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ title, issue }),
});
await api('/api/reader/docs/' + id + '/source?ext=pdf', { method: 'PUT', body: file });
say('Magazine added — starting ingestion', 'ok');
if ($('mag-new-title')) $('mag-new-title').value = '';
if ($('mag-new-issue')) $('mag-new-issue').value = '';
if ($('mag-new-file')) $('mag-new-file').value = '';
magShowDroppedFile(null);
await magOpen(id);
await magIngest();
} catch (e) {
say('Could not add magazine: ' + e.message, 'err');
}
}
// ── Ingestion ────────────────────────────────────────────────────────────────
// Remembers which magazine was open so a full page reload or the browser's
// own Back button (which, unlike in-app navigation, tears down all JS state)
// lands back on it instead of the empty library — confirmed live as the
// cause of a user re-uploading the same PDF, creating a duplicate under a
// completely different kind ("book", via Studio/Reader's own import) because
// the magazine they had been working on appeared to have vanished.
const MAG_LAST_DOC_KEY = 'ttsvc_mag_last_doc';
async function magOpen(docId) {
try {
state.doc = await api('/api/reader/docs/' + docId);
state.doc.id = docId;
await magRefreshArticles();
magShow('contents');
try { localStorage.setItem(MAG_LAST_DOC_KEY, docId); } catch (_) {}
if ((state.doc.ingest || {}).status === 'running') pollIngest();
} catch (e) {
say('Could not open magazine: ' + e.message, 'err');
try { localStorage.removeItem(MAG_LAST_DOC_KEY); } catch (_) {}
}
}
function magForgetLastDoc() {
try { localStorage.removeItem(MAG_LAST_DOC_KEY); } catch (_) {}
}
async function magIngest() {
if (!state.doc) return;
try {
await api('/api/magazine/' + state.doc.id + '/ingest', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({}),
});
pollIngest();
} catch (e) {
say('Ingestion could not start: ' + e.message, 'err');
}
}
// "OCR again" for the whole issue: forces every page through the vision
// engine regardless of its current quality, then re-detects articles --
// which is why this asks for confirmation. A single page's "OCR again" in
// review does not touch article grouping; re-reading the whole document
// does, since detection runs again over the freshly re-read text.
async function magReocrMagazine() {
if (!state.doc) return;
const hasReviewed = state.articles.some((a) => a.status !== 'detected');
if (hasReviewed && !confirm(
'Re-reading the whole magazine runs article detection again. ' +
'Any articles you already approved or rejected will need reviewing again. Continue?'
)) return;
try {
await api('/api/magazine/' + state.doc.id + '/ingest', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ force_vision_ocr: true }),
});
pollIngest();
} catch (e) {
say('Could not start OCR: ' + e.message, 'err');
}
}
// "Analysing page 28 of 204" -> a real percentage, not just spinner text.
function magParsePageProgress(detail) {
const m = /page (\d+) of (\d+)/i.exec(detail || '');
if (!m) return null;
const page = parseInt(m[1], 10), total = parseInt(m[2], 10);
if (!total) return null;
return { page, total, pct: Math.min(100, Math.round((page / total) * 100)) };
}
async function pollIngest() {
const bar = $('mag-ingest-status');
if (bar) { bar.hidden = false; bar.className = 'mag-status is-running'; }
for (;;) {
let data;
try {
data = await api('/api/magazine/' + state.doc.id + '/ingest/status');
} catch (_) { break; }
const ing = data.ingest || {};
const detail = (data.job || {}).detail || '';
if (bar) {
if (ing.status === 'running') {
bar.className = 'mag-status is-running';
const p = magParsePageProgress(detail);
bar.innerHTML =
'<div class="mag-ingest-row">' +
'<span class="mdi mdi-progress-clock mag-ingest-icon"></span>' +
'<div class="mag-ingest-text">' +
'<strong>' + esc(detail || 'Analysing…') + '</strong>' +
(p ? '<div class="mag-ingest-track"><div class="mag-ingest-fill" style="width:' + p.pct + '%"></div></div>' : '') +
'</div>' +
(p ? '<span class="mag-ingest-pct">' + p.pct + '%</span>' : '') +
'</div>';
} else if (ing.status === 'failed') {
bar.className = 'mag-status is-failed';
bar.innerHTML = '<div class="mag-ingest-row"><span class="mdi mdi-alert mag-ingest-icon"></span>' +
'<span>Ingestion failed: ' + esc(ing.error || '') + '</span></div>';
} else {
bar.className = 'mag-status is-done';
bar.innerHTML = '<div class="mag-ingest-row"><span class="mdi mdi-check-circle mag-ingest-icon"></span>' +
'<span>' + (ing.articles || 0) + ' article' + (ing.articles === 1 ? '' : 's') + ' detected</span></div>';
}
}
if (ing.status !== 'running') {
if (ing.status === 'done') await magRefreshArticles();
break;
}
await new Promise((r) => setTimeout(r, 2000));
}
}
async function magRefreshArticles() {
if (!state.doc) return;
try {
const data = await api('/api/magazine/' + state.doc.id + '/articles');
state.articles = data.articles || [];
state.doc.progress = data.progress || {};
state.doc.podcast = data.podcast || { hosts: [] };
state.doc.default_voice = data.default_voice || '';
} catch (_) {
state.articles = [];
}
renderContents();
}
// ── Contents tree ────────────────────────────────────────────────────────────
function confidenceLabel(c) {
if (c >= 0.85) return { cls: 'ok', text: Math.round(c * 100) + '% · listed in contents' };
if (c >= 0.5) return { cls: 'warn', text: Math.round(c * 100) + '% · from headline — check boundaries' };
return { cls: 'bad', text: Math.round(c * 100) + '% · little body copy — likely not an article' };
}
function renderContents() {
const host = $('mag-contents');
if (!host) return;
const title = $('mag-doc-title');
if (title && state.doc) {
title.textContent = (state.doc.title || 'Magazine') +
(state.doc.issue ? ' — ' + state.doc.issue : '');
}
if (!state.articles.length) {
host.innerHTML = '<p class="muted">No articles yet. Run ingestion to detect them.</p>';
return;
}
const bySection = new Map();
state.articles.forEach((a) => {
const key = a.section || 'Articles';
if (!bySection.has(key)) bySection.set(key, []);
bySection.get(key).push(a);
});
let html = '';
bySection.forEach((arts, section) => {
html += '<div class="mag-section"><h4>' + esc(section) + '</h4><ul class="mag-toc">';
arts.forEach((a) => {
const conf = confidenceLabel(a.confidence);
const done = a.status === 'approved';
const progress = (state.doc.progress || {})[a.id];
html += '<li class="mag-toc-row' + (done ? ' is-approved' : '') + '">' +
'<div class="mag-toc-main">' +
'<span class="mag-toc-title">' + esc(a.title || 'Untitled') + '</span>' +
(a.author ? '<span class="mag-toc-by">by ' + esc(a.author) + '</span>' : '') +
'</div>' +
'<div class="mag-toc-meta">' +
'<span>' + fmtPages(a.pages) + '</span>' +
'<span>' + fmtDuration(a.estimated_seconds) + '</span>' +
'<span class="mag-pill ' + conf.cls + '" title="' + esc(conf.text) + '">' +
Math.round(a.confidence * 100) + '%</span>' +
'<span class="mag-pill ' + (done ? 'ok' : '') + '">' +
(done ? 'approved' : a.status === 'rejected' ? 'rejected' : 'needs review') + '</span>' +
'</div>' +
'<div class="mag-toc-actions">' +
'<button type="button" class="btn-sm" onclick="magReview(\'' + a.id + '\')">Review</button>' +
(done
? '<button type="button" class="btn-sm primary" onclick="magRead(\'' + a.id + '\')">' +
(progress ? 'Continue' : 'Listen') + '</button>'
: '') +
'</div></li>';
});
html += '</ul></div>';
});
host.innerHTML = html;
}
// ── Review (Stage D) ─────────────────────────────────────────────────────────
async function magReview(articleId) {
const article = state.articles.find((a) => a.id === articleId);
if (!article) return;
state.article = article;
await ensureLayout();
// The whole review is one page at a time -- showing every page of a
// 10-page feature stacked at once was unreadable and made the boxes tiny.
state.reviewSpan = magReviewSpan(article);
state.reviewPage = state.reviewSpan[0] || null;
_magReviewChecked = null;
magShow('review');
renderReview();
}
async function ensureLayout() {
if (state.layout) return;
try {
state.layout = await api('/api/magazine/' + state.doc.id + '/layout');
} catch (e) {
say('Could not load layout: ' + e.message, 'err');
state.layout = { blocks: [], pages: [], page_count: 0 };
}
}
function blocksForPages(pages) {
const want = new Set(pages || []);
return (state.layout.blocks || [])
.filter((b) => want.has(b.page))
.sort((a, b) => a.page - b.page || a.reading_order - b.reading_order);
}
// Offer neighbouring pages too, so a boundary that started a page late (or a
// jump tail that should have been included) can be corrected without
// leaving the screen.
function magReviewSpan(article) {
if (!article.pages.length) return [];
return Array.from(new Set(article.pages.concat(
[article.pages[0] - 1, article.pages[article.pages.length - 1] + 1])))
.filter((p) => p >= 1 && p <= (state.layout.page_count || 0)).sort((x, y) => x - y);
}
function magReviewGoPage(page) {
if (!state.reviewSpan.includes(page)) return;
state.reviewPage = page;
renderReview();
}
function renderReview() {
const host = $('mag-review');
const a = state.article;
if (!host || !a) return;
const included = new Set(a.blocks || []);
const conf = confidenceLabel(a.confidence);
const page = state.reviewPage;
const pageMeta = (state.layout.pages || []).find((p) => p.page === page);
const pageBlocks = page == null ? [] : blocksForPages([page]);
const spanIdx = state.reviewSpan.indexOf(page);
const prevPage = spanIdx > 0 ? state.reviewSpan[spanIdx - 1] : null;
const nextPage = spanIdx >= 0 && spanIdx < state.reviewSpan.length - 1 ? state.reviewSpan[spanIdx + 1] : null;
let html =
'<div class="mag-review-head">' +
'<label>Title<input id="mag-rev-title" type="text" value="' + esc(a.title) + '"></label>' +
'<label>Author<input id="mag-rev-author" type="text" value="' + esc(a.author) + '"></label>' +
'<div class="mag-pill ' + conf.cls + '">' + esc(conf.text) + '</div>' +
'</div>' +
'<p class="muted">Untick anything that is not part of this article — a sidebar, an advert, ' +
'or a neighbouring piece. Only ticked text is read aloud. Click a numbered region on the page, ' +
'or its matching entry on the right, to line the two up.</p>';
html += '<div class="mag-review-pagenav">' +
'<button type="button" class="btn-sm" ' + (prevPage ? '' : 'disabled') +
' onclick="magReviewGoPage(' + prevPage + ')"><span class="mdi mdi-chevron-left"></span></button>' +
'<span>Page ' + (page ?? '—') + '</span>' +
'<button type="button" class="btn-sm" ' + (nextPage ? '' : 'disabled') +
' onclick="magReviewGoPage(' + nextPage + ')"><span class="mdi mdi-chevron-right"></span></button>' +
'<span class="mag-review-pagenav-spacer"></span>' +
'<button type="button" class="btn-sm" id="mag-reocr-btn" onclick="magReocrPage()">' +
'<span class="mdi mdi-text-recognition"></span> OCR again (this page)</button>' +
'<span id="mag-reocr-status" class="muted"></span>' +
'</div>';
html += '<div class="mag-review-split">';
// Left: the rendered page with a numbered box per block.
html += '<div class="mag-review-page">';
if (page != null) {
html += '<div class="mag-review-page-wrap">' +
'<img src="/api/magazine/' + state.doc.id + '/pages/' + page + '" alt="Page ' + page + '">';
pageBlocks.forEach((b, i) => {
if (!pageMeta) return;
const on = included.has(b.id);
const left = (b.bbox[0] / pageMeta.width * 100).toFixed(2);
const top = (b.bbox[1] / pageMeta.height * 100).toFixed(2);
const w = (b.bbox[2] / pageMeta.width * 100).toFixed(2);
const h = (b.bbox[3] / pageMeta.height * 100).toFixed(2);
html += '<div class="mag-review-box' + (on ? '' : ' is-excluded') + '" data-block="' + esc(b.id) +
'" style="left:' + left + '%;top:' + top + '%;width:' + w + '%;height:' + h + '%" ' +
'onclick="magReviewFocusBlock(\'' + esc(b.id) + '\')" title="' + esc(b.type) + '">' +
'<span class="mag-review-box-num">' + (i + 1) + '</span></div>';
});
html += '</div>';
} else {
html += '<p class="muted">No page to show.</p>';
}
html += '</div>';
// Right: the same blocks as text, numbered to match.
html += '<div class="mag-blocks">';
pageBlocks.forEach((b, i) => {
const narratable = ['title', 'deck', 'byline', 'body'].includes(b.type);
const on = included.has(b.id);
html += '<label class="mag-block' + (narratable ? '' : ' is-aux') + '" data-block-row="' + esc(b.id) + '" ' +
'onmouseenter="magReviewHighlightBox(\'' + esc(b.id) + '\')" onmouseleave="magReviewHighlightBox(null)">' +
'<span class="mag-block-num">' + (i + 1) + '</span>' +
'<input type="checkbox" ' + (on ? 'checked' : '') + ' data-block="' + esc(b.id) + '" onchange="magReviewToggleBox(this)">' +
'<span class="mag-block-type">' + esc(b.type) + '</span>' +
'<span class="mag-block-text">' + esc(b.text.slice(0, 220)) +
(b.text.length > 220 ? '…' : '') + '</span></label>';
});
if (!pageBlocks.length) html += '<p class="muted">Nothing detected on this page.</p>';
html += '</div>';
html += '</div>'; // /mag-review-split
html += '<div class="mag-review-foot">' +
'<button type="button" class="btn" onclick="magShow(\'contents\')">Back to contents</button>' +
'<button type="button" class="btn" onclick="magSetStatus(\'rejected\')">Not an article</button>' +
'<button type="button" class="btn primary" onclick="magApprove()">Approve</button>' +
'</div>';
host.innerHTML = html;
}
// Tracks every ticked block across ALL reviewed pages of this article, not
// just the one currently on screen -- switching pages must not forget a
// change made on a previous one.
let _magReviewChecked = null;
function magReviewToggleBox(input) {
if (!_magReviewChecked) _magReviewChecked = new Set(state.article.blocks || []);
if (input.checked) _magReviewChecked.add(input.dataset.block);
else _magReviewChecked.delete(input.dataset.block);
const box = document.querySelector('.mag-review-box[data-block="' + CSS.escape(input.dataset.block) + '"]');
if (box) box.classList.toggle('is-excluded', !input.checked);
}
function magReviewFocusBlock(blockId) {
const cb = document.querySelector('#mag-review input[data-block="' + CSS.escape(blockId) + '"]');
if (cb) { cb.checked = !cb.checked; magReviewToggleBox(cb); }
const row = document.querySelector('#mag-review [data-block-row="' + CSS.escape(blockId) + '"]');
if (row) row.scrollIntoView({ block: 'nearest', behavior: prefersReducedMotion() ? 'auto' : 'smooth' });
}
function magReviewHighlightBox(blockId) {
document.querySelectorAll('.mag-review-box.is-linked').forEach((el) => el.classList.remove('is-linked'));
if (!blockId) return;
const box = document.querySelector('.mag-review-box[data-block="' + CSS.escape(blockId) + '"]');
if (box) box.classList.add('is-linked');
}
function selectedBlockIds() {
if (_magReviewChecked) return Array.from(_magReviewChecked);
return Array.from(document.querySelectorAll('#mag-review input[data-block]:checked'))
.map((el) => el.dataset.block);
}
async function magReocrPage() {
const page = state.reviewPage;
if (page == null) return;
const btn = $('mag-reocr-btn');
const statusEl = $('mag-reocr-status');
if (btn) btn.disabled = true;
if (statusEl) statusEl.textContent = 'Reading page ' + page + '…';
let jobId;
try {
const r = await api('/api/magazine/' + state.doc.id + '/pages/' + page + '/reocr', {
method: 'POST', headers: { 'Content-Type': 'application/json' }, body: '{}',
});
jobId = r.job_id;
} catch (e) {
if (statusEl) statusEl.textContent = '';
if (btn) btn.disabled = false;
return say('Could not start OCR: ' + e.message, 'err');
}
for (;;) {
let job;
try { job = await api('/api/jobs/' + jobId); } catch (_) { break; }
if (job.done) {
if (job.error) say('OCR failed: ' + job.error, 'err');
else say('Page ' + page + ' re-read', 'ok');
break;
}
await new Promise((r) => setTimeout(r, 2000));
}
if (btn) btn.disabled = false;
if (statusEl) statusEl.textContent = '';
state.layout = null;
await ensureLayout();
renderReview();
}
async function magApprove() {
const a = state.article;
if (!a) return;
const blocks = selectedBlockIds();
if (!blocks.length) return say('Tick at least one block before approving', 'err');
try {
const updated = await api('/api/magazine/' + state.doc.id + '/articles/' + a.id, {
method: 'PATCH',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
blocks,
status: 'approved',
title: ($('mag-rev-title')?.value || a.title).trim(),
author: ($('mag-rev-author')?.value || a.author).trim(),
}),
});
Object.assign(a, updated);
say('Approved — ready to listen', 'ok');
await magRefreshArticles();
magShow('contents');
} catch (e) {
say('Could not approve: ' + e.message, 'err');
}
}
async function magSetStatus(status) {
const a = state.article;
if (!a) return;
try {
const updated = await api('/api/magazine/' + state.doc.id + '/articles/' + a.id, {
method: 'PATCH',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ status }),
});
Object.assign(a, updated);
await magRefreshArticles();
magShow('contents');
} catch (e) {
say('Could not update: ' + e.message, 'err');
}
}
// ── Reading: sentences, both views ───────────────────────────────────────────
// Sentence splitting keeps each piece tied to its source block, so highlighting
// in the reflowed view can drive the page shown in the PDF view.
function splitSentences(blocks) {
const out = [];
blocks.forEach((b) => {
const parts = String(b.text || '')
.split(/(?<=[.!?…])\s+(?=[A-ZÀ-Ü»„"'‘])/)
.map((s) => s.trim()).filter(Boolean);
(parts.length ? parts : [b.text]).forEach((text) => {
if (text && text.trim()) {
out.push({
text: text.trim(), blockId: b.id, page: b.page, bbox: b.bbox, type: b.type,
// Used to pick "the image reached so far" during playback (see
// currentImageIndex) -- the backend already computes this per
// block relative to the whole page, not just this article.
readingOrder: b.reading_order || 0,
words: text.trim().split(/\s+/).filter(Boolean),
});
}
});
});
return out;
}
// The current article's figures, in reading order, resolved from the full
// layout (fetched once) filtered to this article's own image ids. Kept
// separate from state.sentences because an image has no sentence of its
// own -- it is matched to "the most recent sentence at or before it".
function articleImages(article) {
const ids = new Set(article.images || []);
return (state.layout.images || [])
.filter((img) => ids.has(img.id))
.sort((a, b) => (a.reading_order || 0) - (b.reading_order || 0));
}
// The image to show once sentence `i` has been reached: the last image
// whose position in the page's reading order is at or before that
// sentence's own block. Falls back to the first image before any text has
// caught up to it, so a lead photo is not left blank at the very start.
function currentImageIndex(i) {
if (!state.images.length) return -1;
const order = (state.sentences[i] || {}).readingOrder || 0;
let found = -1;
for (let k = 0; k < state.images.length; k++) {
if ((state.images[k].reading_order || 0) <= order) found = k;
else break;
}
return found === -1 ? 0 : found;
}
function renderCurrentImage(i) {
const host = $('mag-read-image');
if (!host) return;
const idx = currentImageIndex(i);
if (idx < 0) { host.hidden = true; return; }
const img = state.images[idx];
if (state._shownImageId === img.id) { host.hidden = false; return; }
state._shownImageId = img.id;
host.hidden = false;
host.innerHTML = '<img src="/api/magazine/' + state.doc.id + '/images/' + encodeURIComponent(img.filename) +
'" alt="Figure from page ' + img.page + '" loading="lazy">';
}
async function magRead(articleId, opts) {
const a = state.articles.find((x) => x.id === articleId);
if (!a) return;
state.article = a;
await ensureLayout();
try {
const data = await api('/api/magazine/' + state.doc.id + '/articles/' + a.id + '/text?captions=' +
($('mag-read-captions')?.checked ? 1 : 0));
state.sentences = splitSentences(data.blocks || []);
} catch (e) {
return say('Could not load article text: ' + e.message, 'err');
}
state.images = articleImages(a);
state._shownImageId = null;
const forceStart = opts && opts.fromStart;
const saved = !forceStart && (state.doc.progress || {})[a.id];
state.idx = saved && saved.sentence < state.sentences.length ? saved.sentence : 0;
magShow('read');
renderArticle();
loadPodcastIfAny();
}
function renderArticle() {
const host = $('mag-article');
const a = state.article;
if (!host || !a) return;
$('mag-read-title').textContent = a.title || 'Untitled';
$('mag-read-by').textContent = a.author ? 'By ' + a.author : '';
$('mag-read-pages').textContent = fmtPages(a.pages);
host.innerHTML = state.sentences.map((s, i) => {
const tag = s.type === 'title' ? 'h2' : s.type === 'deck' ? 'p class="mag-deck"'
: s.type === 'byline' ? 'p class="mag-byline"' : s.type === 'caption'
? 'p class="mag-caption"' : 'span';
const open = tag.split(' ')[0];
// Each word gets its own span so playback can highlight it individually
// (see estimateWordTimings) -- sentence-level highlighting alone doesn't
// need this, but word-level does and this markup serves both.
const wordsHtml = s.words.map((w, j) =>
'<span class="mag-w" data-w="' + j + '">' + esc(w) + '</span>').join(' ');
return '<' + tag + ' class="mag-s' + (open === 'span' ? '' : '') + '" data-i="' + i + '" ' +
'onclick="magSeek(' + i + ')">' + wordsHtml + '</' + open + '> ';
}).join('');
highlight(state.idx);
}
function highlight(i) {
document.querySelectorAll('#mag-article [data-i]').forEach((el) => {
el.classList.toggle('is-current', Number(el.dataset.i) === i);
});
clearWordHighlight();
const el = document.querySelector('#mag-article [data-i="' + i + '"]');
if (el && !prefersReducedMotion()) el.scrollIntoView({ block: 'center', behavior: 'smooth' });
else if (el) el.scrollIntoView({ block: 'center' });
const s = state.sentences[i];
if (s && state.pane === 'pdf') showPage(s.page, s.bbox);
renderCurrentImage(i);
const counter = $('mag-read-progress');
if (counter) counter.textContent = (i + 1) + ' / ' + state.sentences.length;
const qText = state.queue.length ? 'Article ' + (state.queueIndex + 1) + ' / ' + state.queue.length : '';
['mag-queue-progress', 'mag-queue-progress-2'].forEach((id) => {
const el = $(id);
if (el) el.textContent = qText;
});
}
function clearWordHighlight() {
document.querySelectorAll('#mag-article .mag-w.is-current').forEach((el) => el.classList.remove('is-current'));
}
// ── Word-level highlighting (approximate) ────────────────────────────────
// No forced-alignment or TTS timestamp source exists in this pipeline, so
// per-word timing is ESTIMATED, not measured: each word's share of the
// sentence's real (measured) audio duration is proportional to its own
// character length, with a small fixed share added per word so short words
// are not given an unrealistically instant duration. This is a common
// karaoke approximation, not true alignment -- it can drift on sentences
// with heavy punctuation-driven pauses.
function estimateWordTimings(words, totalSeconds) {
if (!words.length || !totalSeconds) return [];
const FIXED = 0.6; // arbitrary units, shifts weight toward evening out short words
const weights = words.map((w) => Math.max(1, w.replace(/[.,!?;:"'()«»„"]/g, '').length) + FIXED);
const total = weights.reduce((a, b) => a + b, 0);
let t = 0;
return weights.map((w) => {
const dur = totalSeconds * (w / total);
const start = t;
t += dur;
return { start, end: t };
});
}
function highlightWord(sentenceIdx, wordIdx) {
const sentenceEl = document.querySelector('#mag-article [data-i="' + sentenceIdx + '"]');
if (!sentenceEl) return;
sentenceEl.querySelectorAll('.mag-w').forEach((el) => {
el.classList.toggle('is-current', Number(el.dataset.w) === wordIdx);
});
}
function prefersReducedMotion() {
try { return window.matchMedia('(prefers-reduced-motion: reduce)').matches; }
catch (_) { return false; }
}
function magSeek(i) {
state.idx = Math.max(0, Math.min(state.sentences.length - 1, i));
highlight(state.idx);
saveProgress();
}
function magSetPane(pane) {
state.pane = pane;
const reflow = $('mag-pane-reflow'), pdf = $('mag-pane-pdf');
if (reflow) reflow.hidden = pane !== 'reflow';
if (pdf) pdf.hidden = pane !== 'pdf';
document.querySelectorAll('[data-mag-pane]').forEach((b) => {
const on = b.dataset.magPane === pane;
b.classList.toggle('active', on);
b.setAttribute('aria-pressed', on ? 'true' : 'false');
});
if (pane === 'pdf') {
const s = state.sentences[state.idx];
if (s) showPage(s.page, s.bbox);
}
}
function showPage(page, bbox) {
const img = $('mag-page-img');
const box = $('mag-page-box');
if (!img) return;
const src = '/api/magazine/' + state.doc.id + '/pages/' + page;
if (img.getAttribute('src') !== src) img.setAttribute('src', src);
img.setAttribute('alt', 'Page ' + page + ' of ' + (state.doc.title || 'the magazine'));
const label = $('mag-page-label');
if (label) label.textContent = 'Page ' + page;
if (!box || !bbox) return;
// The layout stores PDF user-space units; the rendered PNG is a different
// size, so scale by the page dimensions rather than assuming they match.
const meta = (state.layout.pages || []).find((p) => p.page === page);
if (!meta) { box.hidden = true; return; }
box.hidden = false;
box.style.left = (bbox[0] / meta.width * 100) + '%';
box.style.top = (bbox[1] / meta.height * 100) + '%';
box.style.width = (bbox[2] / meta.width * 100) + '%';
box.style.height = (bbox[3] / meta.height * 100) + '%';
}
function magPeekPage(page) {
magShow('read');
magSetPane('pdf');
showPage(page, null);
}
// ── Playback ─────────────────────────────────────────────────────────────────
async function magPlay() {
if (state.playing) return magPause();
const voice = ($('mag-voice')?.value || state.doc.default_voice || '').trim();
if (!voice) return say('Pick a narrator voice first', 'err');
state.playing = true;
state.cancel = false;
syncPlayButton();
let finishedArticle = false;
try {
while (state.idx < state.sentences.length && !state.cancel) {
highlight(state.idx);
const sentence = state.sentences[state.idx];
let blob;
try {
blob = await fetchTtsPreviewBlob(voice, sentence.text, 'mp3');
} catch (e) {
say('Synthesis failed: ' + e.message, 'err');
break;
}
if (state.cancel) break;
await playBlob(blob, sentence);
if (state.cancel) break;
state.idx += 1;
saveProgress();
}
finishedArticle = state.idx >= state.sentences.length && !state.cancel;
} finally {
state.playing = false;
state.cancel = false;
syncPlayButton();
}
if (finishedArticle) {
state.idx = state.sentences.length - 1;
if (state.queue.length && state.queueIndex < state.queue.length - 1) {
// Play-all: move straight to the next approved article rather than
// stopping -- the whole point of a queue is not touching the screen
// between articles.
state.queueIndex += 1;
await magRead(state.queue[state.queueIndex], { fromStart: true });
magPlay();
} else {
state.queue = [];
state.queueIndex = -1;
say('Article finished', 'ok');
}
}
}
function playBlob(blob, sentence) {
return new Promise((resolve) => {
const url = URL.createObjectURL(blob);
const audio = new Audio(url);
state.audio = audio;
let timings = null;
const onTimeUpdate = () => {
if (!state.karaoke || !sentence || !sentence.words.length) return;
if (!timings) {
if (!audio.duration || !isFinite(audio.duration)) return;
timings = estimateWordTimings(sentence.words, audio.duration);
}
const t = audio.currentTime;
const wi = timings.findIndex((w) => t >= w.start && t < w.end);
if (wi !== -1) highlightWord(state.idx, wi);
};
if (state.karaoke) audio.addEventListener('timeupdate', onTimeUpdate);
const done = () => {
audio.removeEventListener('timeupdate', onTimeUpdate);
URL.revokeObjectURL(url);
state.audio = null;
resolve();
};
audio.onended = done;
audio.onerror = done;
audio.play().catch(done);
});
}
// ── Play all approved articles in sequence ──────────────────────────────
async function magPlayAll() {
const ids = state.articles.filter((a) => a.status === 'approved').map((a) => a.id);
if (!ids.length) return say('Approve at least one article first', 'err');
state.queue = ids;
state.queueIndex = 0;
await magRead(ids[0], { fromStart: true });
magPlay();
}
function magStopQueue() {
state.queue = [];
state.queueIndex = -1;
['mag-queue-progress', 'mag-queue-progress-2'].forEach((id) => {
const el = $(id);
if (el) el.textContent = '';
});
}
async function magQueueNext() {
if (!state.queue.length || state.queueIndex >= state.queue.length - 1) return;
const wasPlaying = state.playing;
if (wasPlaying) magPause();
state.queueIndex += 1;
await magRead(state.queue[state.queueIndex], { fromStart: true });
if (wasPlaying) magPlay();
}
function magPause() {
state.cancel = true;
if (state.audio) { try { state.audio.pause(); } catch (_) {} }
state.playing = false;
syncPlayButton();
}
function syncPlayButton() {
const btn = $('mag-play');
if (btn) {
btn.innerHTML = state.playing
? '<span class="mdi mdi-pause"></span> Pause'
: '<span class="mdi mdi-play"></span> Listen';
btn.setAttribute('aria-label', state.playing ? 'Pause narration' : 'Play narration');
}
if (state.driving) syncDrivingPlayButton();
}
let _saveTimer = null;
function saveProgress() {
if (!state.doc || !state.article) return;
clearTimeout(_saveTimer);
_saveTimer = setTimeout(() => {
fetch('/api/magazine/' + state.doc.id + '/progress', {
method: 'PATCH',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ article: state.article.id, sentence: state.idx }),
}).catch(() => {});
}, 800);
}
// ── Podcast mode ─────────────────────────────────────────────────────────────
async function magLoadVoices() {
try {
const data = await api('/api/voices');
state.voices = data.voices || data || [];
} catch (_) { state.voices = []; }
const options = '<option value="">— pick a voice —</option>' +
state.voices.map((v) => {
const id = v.id || v.name || v;
return '<option value="' + esc(id) + '">' + esc(v.name || id) + '</option>';
}).join('');
['mag-voice', 'mag-host-a', 'mag-host-b', 'mag-host-c'].forEach((id) => {
const el = $(id);
if (el) {
const keep = el.value;
el.innerHTML = options;
if (keep) el.value = keep;
}
});
const def = state.doc && state.doc.default_voice;
if (def && $('mag-voice') && !$('mag-voice').value) $('mag-voice').value = def;
}
async function loadPodcastIfAny() {
state.podcast = null;
renderPodcast();
// has_podcast comes from the articles listing so an article that never had
// a script generated skips the request entirely, rather than a 404 on
// every open.
if (!state.article || !state.article.has_podcast) return;
try {
state.podcast = await api('/api/magazine/' + state.doc.id + '/articles/' +
state.article.id + '/podcast');
} catch (_) { /* generated flag was stale — treat as none */ }
renderPodcast();
}
async function magGeneratePodcast() {
const a = state.article;
if (!a) return;
if (a.status !== 'approved') {
return say('Approve the article first — unreviewed boundaries may include an advert', 'err');
}
const hosts = ['mag-host-a', 'mag-host-b', 'mag-host-c']
.map((id) => ($(id)?.value || '').trim())
.filter(Boolean)
.map((voice, i) => ({ voice, name: ($('mag-host-name-' + 'abc'[i])?.value || '').trim() }));
if (hosts.length < 2) return say('Pick at least two host voices', 'err');
const btn = $('mag-podcast-gen');
if (btn) { btn.disabled = true; btn.textContent = 'Writing script…'; }
try {
state.podcast = await api('/api/magazine/' + state.doc.id + '/articles/' + a.id + '/podcast', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ hosts }),
});
a.has_podcast = true;
say('Podcast script ready', 'ok');
renderPodcast();
} catch (e) {
say('Could not generate: ' + e.message, 'err');
} finally {
if (btn) { btn.disabled = false; btn.textContent = 'Generate script'; }
}
}
function renderPodcast() {
const host = $('mag-podcast-script');
if (!host) return;
if (!state.podcast) {
host.innerHTML = '<p class="muted">No podcast script yet. Pick two or three voices and ' +
'generate one — the hosts discuss this article for someone who has not read it.</p>';
const play = $('mag-podcast-play');
if (play) play.hidden = true;
return;
}
const names = {};
(state.podcast.hosts || []).forEach((h) => { names[h.label] = h.name || ('Host ' + h.label); });
host.innerHTML = '<ol class="mag-turns">' + (state.podcast.turns || []).map((t, i) =>
'<li data-turn="' + i + '"><b>' + esc(names[t.host] || t.host) + '</b> ' +
esc(t.text) + '</li>').join('') + '</ol>';
const play = $('mag-podcast-play');
if (play) play.hidden = false;
}
async function magPlayPodcast() {
if (state.playing) return magPause();
if (!state.podcast) return;
const voiceOf = {};
(state.podcast.hosts || []).forEach((h) => { voiceOf[h.label] = h.voice; });
state.playing = true;
state.cancel = false;
const btn = $('mag-podcast-play');
if (btn) btn.textContent = 'Pause';
try {
const turns = state.podcast.turns || [];
for (let i = 0; i < turns.length && !state.cancel; i++) {
document.querySelectorAll('#mag-podcast-script [data-turn]').forEach((el) => {
el.classList.toggle('is-current', Number(el.dataset.turn) === i);
});
const voice = voiceOf[turns[i].host];
if (!voice) continue;
let blob;
try { blob = await fetchTtsPreviewBlob(voice, turns[i].text, 'mp3'); }
catch (e) { say('Synthesis failed: ' + e.message, 'err'); break; }
if (state.cancel) break;
await playBlob(blob);
}
} finally {
state.playing = false;
state.cancel = false;
if (btn) btn.textContent = 'Play podcast';
}
}
// ── View switching ───────────────────────────────────────────────────────────
function magShow(view) {
state.view = view;
['library', 'contents', 'review', 'read'].forEach((v) => {
const el = $('mag-view-' + v);
if (el) el.hidden = v !== view;
});
if (view !== 'read') magPause();
}
function magBackToContents() {
magPause();
magStopQueue();
state.driving = false;
magShow('contents');
magRefreshArticles();
}
// ── Driving mode ──────────────────────────────────────────────────────────
// Large, minimal-interaction controls for listening without looking at the
// screen (see Manual.md's planned driving-mode behaviour). Reuses whatever
// is already playing/queued rather than starting its own playback path --
// entering driving mode does not interrupt an article already in progress.
function magToggleDriving() {
state.driving = !state.driving;
const overlay = $('mag-driving');
if (overlay) overlay.hidden = !state.driving;
if (state.driving) renderDriving();
}
function renderDriving() {
const a = state.article;
if (!a) return;
const titleEl = $('mag-driving-title');
if (titleEl) titleEl.textContent = a.title || 'Untitled';
const byEl = $('mag-driving-by');
if (byEl) byEl.textContent = a.author ? 'By ' + a.author : '';
syncDrivingPlayButton();
const qEl = $('mag-driving-queue');
if (qEl) qEl.hidden = !state.queue.length;
}
function syncDrivingPlayButton() {
const btn = $('mag-driving-play');
if (!btn) return;
btn.innerHTML = state.playing
? '<span class="mdi mdi-pause"></span>'
: '<span class="mdi mdi-play"></span>';
btn.setAttribute('aria-label', state.playing ? 'Pause' : 'Play');
}
// ── Boot ─────────────────────────────────────────────────────────────────────
async function magInit() {
if (!$('mag-library-list')) return; // section not mounted
magLoadLibrary();
magLoadVoices();
setupMagDropzone();
let lastId = null;
try { lastId = localStorage.getItem(MAG_LAST_DOC_KEY); } catch (_) {}
if (lastId) {
// Confirmed live: without this, a full reload or the browser's own Back
// button (as opposed to in-app navigation) always dropped back to the
// empty library, making an in-progress magazine look like it had been
// lost. If it genuinely no longer exists (deleted elsewhere), fall back
// to the library rather than getting stuck on a permanent error toast.
try {
await api('/api/reader/docs/' + lastId);
await magOpen(lastId);
return;
} catch (_) {
magForgetLastDoc();
}
}
magShow('library');
}
root.magOpen = magOpen;
root.magCreate = magCreate;
root.magIngest = magIngest;
root.magReview = magReview;
root.magReviewGoPage = magReviewGoPage;
root.magReviewFocusBlock = magReviewFocusBlock;
root.magReviewHighlightBox = magReviewHighlightBox;
root.magReviewToggleBox = magReviewToggleBox;
root.magReocrPage = magReocrPage;
root.magReocrMagazine = magReocrMagazine;
root.magApprove = magApprove;
root.magSetStatus = magSetStatus;
root.magRead = magRead;
root.magSeek = magSeek;
root.magPlay = magPlay;
root.magPause = magPause;
root.magSetPane = magSetPane;
root.magPeekPage = magPeekPage;
root.magShow = magShow;
root.magBackToContents = magBackToContents;
root.magGeneratePodcast = magGeneratePodcast;
root.magPlayPodcast = magPlayPodcast;
root.magPlayAll = magPlayAll;
root.magQueueNext = magQueueNext;
root.magStopQueue = magStopQueue;
root.magToggleDriving = magToggleDriving;
root.magInit = magInit;
MAG.magazineApi = { load: magLoadLibrary, refresh: magRefreshArticles, splitSentences, fmtPages };
if (document.readyState === 'loading') {
document.addEventListener('DOMContentLoaded', magInit);
} else {
magInit();
}
})(window);