Files
silo-server/web/vendor/foliate-js/tts.js
8b70357703 feat(ebooks): first-class ebook libraries, scanner, and reader (#124)
* docs: define ebook architecture matching audiobooks

* docs: plan ebook audiobook-parity implementation

* feat: add ebook scanner parser foundation

* fix: harden ebook scanner foundation

* fix: handle ebook isbn labels

* fix: guard ebook subtree scans

* feat: scan ebook libraries in core

* fix: preserve ebook scan people credits

* fix: refresh ebook scan metadata safely

* feat: persist ebook series membership

* test: cover ebook series persistence decisions

* fix: address ebook scanner PR review

* docs: clarify ebook foundation PR scope

* feat: add ebook metadata enricher

* fix: harden ebook poster cache

* feat: wire ebook metadata sync task

* feat: expose ebook library metadata setup

* feat: add ebook catalog scope support

* feat: add ebook detail view

* feat: label ebook file versions by format

* feat: use file-size copy for downloads

* feat: use file language in download dialog

* test: cover ebook detail authors and downloads

* fix: drop narrator credits from ebook scanner merges

* fix: align ebook collection filters with book media

* fix: drop asin provider ids from ebook enrichment

* fix: force ebook people refresh for stale narrators

* chore: omit ebook planning docs from branch

* feat: add ebook detail related content

* feat: add ebook reader file entrypoint

* feat: render ebooks with foliate reader

* feat: persist ebook reader progress

* feat: add ebook reader controls

* feat: extract ebook pdf metadata

* feat: favor scanner isbn during ebook enrichment

* feat: extract fbz ebook metadata

* feat: count cbz ebook pages

* feat: show ebook file page counts

* feat: show ebook download summaries

* feat: switch ebook reader files

* feat: prefer epub for ebook read action

* feat: surface ebook reader progress

* feat: sync ebook reader progress cache

* feat: hide ebook read action for unsupported files

* feat: filter ebook reader file selector

* fix: serve fbz ebook archives with reader mime type

* fix: detect fbz ebooks from compound filename

* fix: authorize fbz ebooks from compound filename

* fix: scope ebook catalog facets

* fix: reject narrator queries for ebooks

* fix: build ebook recommendation text from authors

* fix: include ebooks in embedding eligibility

* fix: include ebooks in recommendation media mix

* fix: include ebooks in recently added recommendations

* feat: include ebook progress in recommendation signals

* feat: include ebooks in continue watching sections

* feat: include ebooks in catalog progress metrics

* fix: read ebook isbn from epub metadata

* fix: filter ebook asin provider aliases

* fix: fall back from unsupported ebook reader files

* fix: sort ebook catalogs by reader progress

* fix: filter ebook catalogs by reader progress

* fix: include ebooks in last watched catalog filters

* feat: reflect ebook reader progress in item user state

* feat: share ebook progress state across item surfaces

* feat: report ebook scan progress

* fix: include ebook activity in recommendations

* fix: expose ebook reader progress on item detail

* fix: support ebook subtree scans

* fix: honor profile header for ebook item progress

* fix: add ebook library default sections

* fix: route ebook continue cards to reader

* fix: hide watched toggle for ebooks

* fix: route ebook watch tonight cards to reader

* fix: route ebook hero actions to reader

* fix: detect archive ebook reader formats by filename

* feat: cache embedded ebook covers during scan

* fix: encode ebook hero reader links

* fix: persist non-epub ebook reader progress

* fix: scope narrator catalog badges to audiobooks

* fix: merge ebook reader progress during item repair

* fix: label ebook progress filters as read

* fix: show ebook related rails as book covers

* fix: remove txt ebook reader support

* fix: reject txt ebook reader files

* fix: label ebook advanced filters as read

* fix: label ebook personalized sorts as read

* fix: remove plain text reader loader path

* test: cover ebook unread catalog rules

* fix: preserve ebook reader library context

* fix: link ebook genres with library scope

* fix: encode related rail item links

* fix: encode catalog card item links

* fix: encode hero and continue item links

* fix: encode watch tonight item links

* fix: encode recommendation and search item links

* test: cover ebook scan format set

* fix: label ebook search results clearly

* fix: make global search prompt media neutral

* fix: encode catalog read API ids

* fix: encode item API ids

* fix: include ebook reader vendor in docker build

* fix: make ebook reader build clean

* fix: clean ebook embedded descriptions

* docs: plan ebook reader shell parity

* feat: add ebook reader shell controls

* fix: widen ebook scrolled reader flow

* fix: remove scrolled reader content width cap

* docs: plan ebook reader full parity

* feat: persist ebook reader config

* feat: add ebook annotations and bookmarks

* feat: add ebook reader tools and aids

* feat: add ebook advanced reader settings

* fix: keep ebook reader panel in viewport

* fix: use foliate sizing units for ebook scroll flow

* fix: keep ebook settings controls readable

* fix: simplify ebook reader settings controls

* feat(ebooks): extract local covers during scan (#98)

* feat(ebooks): extract local covers during scan

* fix(ebooks): read nullable poster paths during cover scan

* fix(catalog): coalesce nullable media artwork fields

* fix(ebooks): group sibling formats by book identity

* fix(ebooks): tolerate legacy ebook metadata encodings

* fix(ebooks): decode PDF hex metadata strings

* fix(ebooks): harden local cover extraction and format grouping

Address review findings on the local cover scan:

- Restrict generic sidecar covers (cover.jpg, folder.png, ...) to
  single-book directories, always accept images named after the book
  file, and apply exactly one cover per reconcile with sidecar taking
  precedence over the embedded cover.
- Replace the read-then-write poster update with an atomic conditional
  UPDATE (ItemRepository.SetLocalPoster) so provider/admin artwork is
  never clobbered by concurrent writers, and refresh locally owned
  posters when the extracted cover bytes change (thumbhash compare).
- Preserve UTF-8 PDF Info strings (including a UTF-8 BOM) instead of
  forcing everything through Windows-1252; the cp1252 fallback now only
  applies to non-UTF-8 bytes.
- Select EPUB covers by manifest media-type with properties="cover-image"
  outranking the EPUB2 meta name="cover" id, so XHTML cover pages no
  longer shadow the real image.
- Order CBZ pages naturally (2.jpg before 10.jpg, ch2/ before ch10/)
  when picking the cover page, via a single O(n) min-scan.
- Bump the ebook content group key scheme to version 2 and reprocess
  rows written under older versions so pre-existing libraries gain
  sibling-format grouping instead of accumulating duplicates.
- Group different formats only (a same-format sibling with colliding
  sparse metadata stays a separate item) and stop a joining sibling's
  embedded metadata from overwriting a provider-matched item.
- Decode any IANA-labelled OPF/FB2 XML charset (windows-1251, koi8-r,
  shift_jis, ...) via x/net/html/charset, and wire the charset reader
  into FB2 parsing which previously had none.
- Strip the full .fb2.zip double extension from filename-derived titles
  and group keys.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: rxwatcher <rxwatcher@users.noreply.github.com>
Co-authored-by: Quick <31828688+Quick104@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

* feat(ebooks): add reader profiles and ruler (#99)

* feat(ebooks): extract local covers during scan

* fix(ebooks): read nullable poster paths during cover scan

* fix(catalog): coalesce nullable media artwork fields

* fix(ebooks): group sibling formats by book identity

* fix(ebooks): tolerate legacy ebook metadata encodings

* fix(ebooks): decode PDF hex metadata strings

* feat(ebooks): add reader profiles and ruler

* fix(ebooks): address reader ruler and profile review findings

- skip renderer setStyles/render when computed styles and attributes are
  unchanged, so ruler position updates no longer re-style the book view
- drag the ruler via a local draft that commits on release, with the
  surface rect cached at pointer-down
- migrate font values persisted before the generic stacks (Inter,
  Georgia, Merriweather, legacy serif) so the font select never renders
  blank, with a Custom fallback option for unknown values
- make the ruler band click-through and move dragging to a dedicated
  keyboard-accessible slider handle so links and text selection keep
  working under the band
- share font stacks between options and profiles via READER_FONT_STACKS
- surface the active reading profile, move presets to the top of the
  settings panel, and drop the redundant profile button aria-labels

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ebooks): resolve prefer-const lint error in readest document lib

`pnpm run lint` failed on the branch because `direction` is never
reassigned in getDirection; split the destructure so only the
reassigned `writingMode` stays mutable.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: rxwatcher <rxwatcher@users.noreply.github.com>
Co-authored-by: Quick <31828688+Quick104@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

* Merge branch 'main' into work/ebooks-reader-base

Brings the ebook integration branch up to date with main (audiobook
library redesign, continue-watching rework and card affordances,
quic-go bump, jellycompat fixes). Conflict resolutions favor main's
generalized mechanisms and register ebooks with them:

- media scope validation goes through IsValidMediaScope (now including
  "ebook" alongside main's "video" group scope), in Go and in the web
  filter/search types
- continue-watching uses main's typed rails; reading-type sections pull
  resume points from ebook_reader_progress and the ebook library default
  section is wired to ContinueTypeConfig(ContinueTypeReading)
- item_repo keeps main's derived select-list machinery (itemColumnExpr)
  and both poster accessors (GetPoster/SetLocalPoster for ebook covers,
  GetPosterPath for audiobook covers)
- web cards/hero/watch-tonight adopt main's buildMediaPlayHref helpers,
  which now route ebooks to /reader/ebook and encode content ids;
  ebook affordances (BookOpen icon, Read verb, percent-read subtitle)
  carry over onto main's reworked components
- LibraryForm ebook support ported into main's refactored
  useLibraryForm/libraryTypes modules

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(docker): copy foliate-js vendor into Dockerfile.dev frontend stage

foliate-js is a file:vendor/foliate-js dependency, so pnpm install needs
the vendor directory before the lockfile install layer. The production
Dockerfile already copies it; the dev image was missed, breaking
make dev-deploy with ENOENT on /app/web/vendor/foliate-js.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(ebooks): render Continue Reading sections as upright poster cards

All-ebook continue sections previously fell through to the horizontal
16:9 wide card; include ebooks in the poster-variant check so book
covers render in their natural 2:3 framing.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ui): stop related-rail highlight ring clipping on detail pages

Move the current-item ring onto the cover artwork with a themed
ring-offset color (matching the sidebar profile highlight) and give
the scroll container top headroom so the ring is not cut off by
overflow-x-auto. Applies to both ebook and audiobook detail rails.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(scanner): harden ebook scanning against data loss and bad metadata

- Reconcile missing ebook files like video/audio, with real per-root walk
  failure tracking (failed/unmounted roots are excluded from deletion),
  symlinked-root support via the shared logical walker, and the empty-root
  cleanup allowance before any destructive reconciliation.
- Create ebook items as 'pending' so enrichment can promote them to
  'matched' (backfill migration included), and protect matched items from
  re-scan clobbering: title/year skipped, people/series fill-empty only.
- PDF metadata: scan head + tail windows (non-linearized PDFs keep the Info
  dict at the end), require proper key delimiters, head values win.
- Cap plain .fb2 reads like .fbz entries; drop .md as an ebook format.
- gofmt internal/scanner/audiobook.go (pre-existing drift).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ebooks): make enrichment failures non-terminal with dedicated backoff state

- Provider errors now record a failure (capped retries) instead of stamping
  last_refreshed, which permanently excluded items after transient outages.
- Unconfigured metadata chains and the scan-window membership race skip the
  item without stamping or burning a retry.
- Failure tracking moves to a new ebook_enrichment_state table, decoupling
  it from media_items.refresh_failures (shared with metadata refresh debt).
- Preserve non-author people credits when persisting enrichment results.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(catalog): gate ebook progress on hidden history and centralize threshold

- Apply user_history_hidden_items gating (video semantics) to the ebook
  watched/in-progress filters, progress sort plan, and Continue Reading.
- Continue Reading pages past dismissed items via the shared collector and
  dedupes items across pages (also fixes the video path's latent exposure).
- Centralize the 0.9 finished threshold as models.EbookFinishedProgressThreshold
  with a single SQL-interpolated mirror in catalog.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(recommendations): correct watcher counting and wire ebook taste signals

- itemWatchersQuery dedupes to distinct (watcher, item) rows so one
  binge-watcher can no longer satisfy minWatchers; the eligibility floor
  now counts distinct accounts rather than profiles.
- Hidden-history gating on GetEbookReaderProgressForUser (signal reader).
- Ebook reading produces canonical implicit taste signals (weighted like
  the equivalent movie progress ratio); ebooks join taste-seed candidates.
- Stale GetRecentlyAddedItems doc comment corrected.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(api): harden ebook reader endpoints and serve a Content-Security-Policy

- Serve a CSP on all SPA HTML responses: blob/srcdoc book iframes inherit
  it, so script-src 'self' 'wasm-unsafe-eval' blocks script execution from
  malicious book content (sandbox alone is defeated by the WebKit
  allow-scripts requirement). Threat model documented on the constant.
- X-Content-Type-Options: nosniff on frontend, jellycompat, and ebook file
  responses; MIME resolution can no longer fall through to octet-stream
  for an admitted ebook file.
- Annotation PATCH: presence-aware field semantics (absent keeps, present
  sets/clears), invariant re-validation on the merged row, and an atomic
  SELECT ... FOR UPDATE read-merge-write.
- Request size caps (413) on progress/config/annotation writes;
  Content-Disposition via mime.FormatMediaType; hidden-history gating in
  the shared ebook progress lister; FK-cascade indexes for reader tables.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(api): native read-state endpoints for ebooks

- POST/DELETE /watched/{id} accepts ebook content IDs: mark read upserts
  progress 1.0 preserving the reader's file/location (or picks the
  preferred reader file for never-opened books); mark unread mirrors video
  unwatch semantics and deletes the progress row.
- /history/remove accepts ebooks: hides via user_history_hidden_items
  without touching the reading position (hidden != unread; next reading
  activity resurfaces the book, mirroring video re-watch).
- Access-filter checks match the video branch; shared logic lives in
  ebook_read_state.go. Sort metrics/user-state thresholds use the shared
  constant; profile-header fallback deduplicated.

Clients: response is {type: "ebook", affected_count: 1, played: bool};
the existing watched SSE event fires.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(web): harden the ebook reader UI

- Open-flow race: cancellation checked after every await with full stale-run
  teardown (no wrong-file progress saves, no leaked views/blob URLs);
  book.destroy() on cleanup.
- Progress: monotonic stale-response guard; visibilitychange flush uses the
  refresh-capable client, pagehide uses keepalive; per-book cross-format
  progress documented as deliberate.
- Settings: side effects out of the setState updater; local edits no longer
  clobbered by late server config; pending saves flushed on unmount/pagehide.
- TTS: generation token so Stop actually stops (Chromium/Firefox synthetic
  events); Media Session uninstalled on unmount.
- External book links: http(s) only, opened with noopener,noreferrer.
- apiBlob 512 MiB guard with a user-facing error; fraction bookmarks
  navigable; search-result key collisions fixed; dead e-ink code removed;
  getLibrarySortRelevanceScope deduplicated; md format dropped.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(web): mark read/unread affordances for ebooks

- Item detail gets a Mark Read/Unread button; card menus drop the ebook
  gate and share type-aware labels/toasts (also dedupes audiobook wording).
- Watched-state invalidation includes the reader progress query key so the
  Continue button and percent refresh after toggling.
- Continue Reading dismiss copy for ebooks; dismissal path now URL-encodes
  item IDs (ebook content IDs can contain reserved characters).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: record the PR #124 review and hardening pass

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: rxwatcher <rxwatcher@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-06-10 08:18:35 -04:00

451 lines
16 KiB
JavaScript

const NS = {
XML: 'http://www.w3.org/XML/1998/namespace',
SSML: 'http://www.w3.org/2001/10/synthesis',
}
const blockTags = new Set([
'article', 'aside', 'audio', 'blockquote', 'caption',
'details', 'dialog', 'div', 'dl', 'dt', 'dd',
'figure', 'footer', 'form', 'figcaption',
'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'header', 'hgroup', 'hr', 'li',
'main', 'math', 'nav', 'ol', 'p', 'pre', 'section', 'tr',
])
const getLang = el => {
const x = el.lang || el?.getAttributeNS?.(NS.XML, 'lang')
return x ? x : el.parentElement ? getLang(el.parentElement) : null
}
const getAlphabet = el => {
const x = el?.getAttributeNS?.(NS.XML, 'lang')
return x ? x : el.parentElement ? getAlphabet(el.parentElement) : null
}
const getSegmenter = (lang, granularity = 'word') => {
const segmenter = new Intl.Segmenter(lang || undefined, { granularity })
const granularityIsWord = granularity === 'word'
return function* (strs, makeRange) {
const str = strs.join('').replace(/\r\n/g, ' ').replace(/\r/g, ' ').replace(/\n/g, ' ')
let name = 0
let strIndex = -1
let sum = 0
const rawSegments = Array.from(segmenter.segment(str))
const mergedSegments = []
for (let i = 0, j = 0; i < rawSegments.length; i++) {
const current = rawSegments[i]
const segment = ' ' + current.segment
const endsWithAbbr = /\s([A-Z]{1,2}[a-z]{0,5}|[a-z]{1,3})\.\s*$/.test(segment)
if (!endsWithAbbr || i >= (rawSegments.length-1)) {
const mergedSegment = {
index: rawSegments[j].index,
segment: '',
isWordLike: (i == j) ? current.isWordLike : true,
}
while (j <= i) {
mergedSegment.segment += rawSegments[j++].segment
}
mergedSegments.push(mergedSegment)
}
}
for (const { index, segment, isWordLike } of mergedSegments) {
if (granularityIsWord && !isWordLike) continue
while (sum <= index) sum += strs[++strIndex].length
const startIndex = strIndex
const startOffset = index - (sum - strs[strIndex].length)
const end = index + segment.length - 1
if (end < str.length) while (sum <= end) sum += strs[++strIndex].length
const endIndex = strIndex
const endOffset = end - (sum - strs[strIndex].length) + 1
yield [(name++).toString(),
makeRange(startIndex, startOffset, endIndex, endOffset)]
}
}
}
const fragmentToSSML = (fragment, nodeFilter, inherited) => {
const ssml = document.implementation.createDocument(NS.SSML, 'speak')
const { lang } = inherited
if (lang) ssml.documentElement.setAttributeNS(NS.XML, 'lang', lang)
const convert = (node, parent, inheritedAlphabet) => {
if (!node) return
if (node.nodeType === 3) return ssml.createTextNode(node.textContent)
if (node.nodeType === 4) return ssml.createCDATASection(node.textContent)
if (node.nodeType !== 1 && node.nodeType !== 11) return
if (nodeFilter && nodeFilter(node) === NodeFilter.FILTER_REJECT) return
let el
const nodeName = node.nodeName.toLowerCase()
if (nodeName === 'foliate-mark') {
el = ssml.createElementNS(NS.SSML, 'mark')
el.setAttribute('name', node.dataset.name)
}
else if (nodeName === 'br')
el = ssml.createElementNS(NS.SSML, 'break')
else if (nodeName === 'em' || nodeName === 'strong')
el = ssml.createElementNS(NS.SSML, 'emphasis')
const lang = node.lang || node.getAttributeNS?.(NS.XML, 'lang')
if (lang) {
if (!el) el = ssml.createElementNS(NS.SSML, 'lang')
el.setAttributeNS(NS.XML, 'lang', lang)
}
const alphabet = node.getAttributeNS?.(NS.SSML, 'alphabet') || inheritedAlphabet
if (!el) {
const ph = node.getAttributeNS?.(NS.SSML, 'ph')
if (ph) {
el = ssml.createElementNS(NS.SSML, 'phoneme')
if (alphabet) el.setAttribute('alphabet', alphabet)
el.setAttribute('ph', ph)
}
}
if (!el) el = parent
let child = node.firstChild
while (child) {
const childEl = convert(child, el, alphabet)
if (childEl && el !== childEl) el.append(childEl)
child = child.nextSibling
}
return el
}
convert(fragment, ssml.documentElement, inherited.alphabet)
return ssml
}
const getFragmentWithMarks = (range, textWalker, nodeFilter, granularity) => {
const lang = getLang(range.commonAncestorContainer)
const alphabet = getAlphabet(range.commonAncestorContainer)
const segmenter = getSegmenter(lang, granularity)
const fragment = range.cloneContents()
// we need ranges on both the original document (for highlighting)
// and the document fragment (for inserting marks)
// so unfortunately need to do it twice, as you can't copy the ranges
const entries = [...textWalker(range, segmenter, nodeFilter)]
const fragmentEntries = [...textWalker(fragment, segmenter, nodeFilter)]
for (const [name, range] of fragmentEntries) {
const mark = document.createElement('foliate-mark')
mark.dataset.name = name
range.insertNode(mark)
}
const ssml = fragmentToSSML(fragment, nodeFilter, { lang, alphabet })
return { entries, ssml }
}
const rangeIsEmpty = range => !range.toString().trim()
// For PDF text layers, split content into sentence-level blocks so TTS
// reads one sentence at a time instead of the whole page in one block.
// Text nodes are split at sentence boundaries so that every block range
// aligns with node edges — this prevents the text walker from including
// text outside the sentence in word marks.
function* getPDFSentenceBlocks(doc, textLayer) {
const collectNodes = () => {
const w = doc.createTreeWalker(textLayer, NodeFilter.SHOW_TEXT)
const res = []
for (let n = w.nextNode(); n; n = w.nextNode()) res.push(n)
return res
}
let nodes = collectNodes()
if (!nodes.length) return
const fullText = nodes.map(n => n.nodeValue).join('')
if (!fullText.trim()) return
// Find sentence boundary positions
const lang = getLang(textLayer) || undefined
const segmenter = new Intl.Segmenter(lang, { granularity: 'sentence' })
const boundaries = new Set()
for (const { index } of segmenter.segment(fullText))
if (index > 0) boundaries.add(index)
// Split text nodes at sentence boundaries so ranges align with node edges.
// Process in reverse order to preserve earlier character positions.
let cum = 0
const nodeStarts = nodes.map(n => { const s = cum; cum += n.nodeValue.length; return s })
for (const pos of [...boundaries].sort((a, b) => b - a)) {
for (let i = 0; i < nodes.length; i++) {
const start = nodeStarts[i]
const end = start + nodes[i].nodeValue.length
if (pos > start && pos < end) {
nodes[i].splitText(pos - start)
break
}
}
}
// Re-collect nodes after splits and group into sentence blocks
nodes = collectNodes()
cum = 0
let groupStart = 0
let blockCount = 0
for (let i = 0; i < nodes.length; i++) {
cum += nodes[i].nodeValue.length
const isEnd = i === nodes.length - 1 || boundaries.has(cum)
if (isEnd) {
const range = doc.createRange()
range.setStart(nodes[groupStart], 0)
range.setEnd(nodes[i], nodes[i].nodeValue.length)
if (!rangeIsEmpty(range)) {
blockCount++
yield range
}
groupStart = i + 1
}
}
}
function* getBlocks(doc) {
const root = doc.body
?? doc.querySelector('body')
?? doc.documentElement
// For PDF text layers, yield sentence-level blocks
const textLayer = root.querySelector?.('.textLayer')
if (textLayer) {
yield* getPDFSentenceBlocks(doc, textLayer)
return
}
let last
const walker = doc.createTreeWalker(root, NodeFilter.SHOW_ELEMENT)
for (let node = walker.nextNode(); node; node = walker.nextNode()) {
const name = node.tagName.toLowerCase()
if (blockTags.has(name)) {
if (last) {
last.setEndBefore(node)
if (!rangeIsEmpty(last)) yield last
}
last = doc.createRange()
last.setStart(node, 0)
}
}
if (!last) {
last = doc.createRange()
last.setStart(root.firstChild ?? root, 0)
}
last.setEndAfter(root.lastChild ?? root)
if (!rangeIsEmpty(last)) yield last
}
class ListIterator {
#arr = []
#iter
#index = -1
#f
constructor(iter, f = x => x) {
this.#iter = iter
this.#f = f
}
current() {
if (this.#arr[this.#index]) return this.#f(this.#arr[this.#index])
}
first() {
const newIndex = 0
if (this.#arr[newIndex]) {
this.#index = newIndex
return this.#f(this.#arr[newIndex])
}
}
prev() {
const newIndex = this.#index - 1
if (this.#arr[newIndex]) {
this.#index = newIndex
return this.#f(this.#arr[newIndex])
}
}
next() {
const newIndex = this.#index + 1
if (this.#arr[newIndex]) {
this.#index = newIndex
return this.#f(this.#arr[newIndex])
}
while (true) {
const { done, value } = this.#iter.next()
if (done) break
this.#arr.push(value)
if (this.#arr[newIndex]) {
this.#index = newIndex
return this.#f(this.#arr[newIndex])
}
}
}
find(f) {
const index = this.#arr.findIndex(x => f(x))
if (index > -1) {
this.#index = index
return this.#f(this.#arr[index])
}
while (true) {
const { done, value } = this.#iter.next()
if (done) break
this.#arr.push(value)
if (f(value)) {
this.#index = this.#arr.length - 1
return this.#f(value)
}
}
}
}
export class TTS {
#list
#ranges
#lastMark
#serializer = new XMLSerializer()
constructor(doc, textWalker, nodeFilter, highlight, granularity) {
this.doc = doc
this.highlight = highlight
this.#list = new ListIterator(getBlocks(doc), range => {
const { entries, ssml } = getFragmentWithMarks(range, textWalker, nodeFilter, granularity)
this.#ranges = new Map(entries)
return [ssml, range]
})
}
#getMarkElement(doc, mark) {
if (!mark) return null
return doc.querySelector(`mark[name="${CSS.escape(mark)}"`)
}
#speak(doc, getNode) {
if (!doc) return
if (!getNode) return this.#serializer.serializeToString(doc)
const ssml = document.implementation.createDocument(NS.SSML, 'speak')
ssml.documentElement.replaceWith(ssml.importNode(doc.documentElement, true))
let node = getNode(ssml)?.previousSibling
while (node) {
const next = node.previousSibling ?? node.parentNode?.previousSibling
node.parentNode.removeChild(node)
node = next
}
const ssmlStr = this.#serializer.serializeToString(ssml)
return ssmlStr
}
start() {
this.#lastMark = null
const [doc] = this.#list.first() ?? []
if (!doc) return this.next()
return this.#speak(doc, ssml => this.#getMarkElement(ssml, this.#lastMark))
}
resume() {
const [doc] = this.#list.current() ?? []
if (!doc) return this.next()
return this.#speak(doc, ssml => this.#getMarkElement(ssml, this.#lastMark))
}
prev(paused) {
this.#lastMark = null
const [doc, range] = this.#list.prev() ?? []
if (paused && range) this.highlight(range.cloneRange())
return this.#speak(doc)
}
next(paused) {
this.#lastMark = null
const [doc, range] = this.#list.next() ?? []
if (paused && range) this.highlight(range.cloneRange())
return this.#speak(doc)
}
prevMark(paused) {
const marks = Array.from(this.#ranges.keys())
if (marks.length === 0) return
const currentIndex = this.#lastMark ? marks.indexOf(this.#lastMark) : -1
if (currentIndex > 0) {
const prevMarkName = marks[currentIndex - 1]
const range = this.#ranges.get(prevMarkName)
if (range) {
this.#lastMark = prevMarkName
if (paused) this.highlight(range.cloneRange())
const [doc] = this.#list.current() ?? []
return this.#speak(doc, ssml => this.#getMarkElement(ssml, prevMarkName))
}
} else {
const [doc, range] = this.#list.prev() ?? []
if (doc && range) {
const prevMarks = Array.from(this.#ranges.keys())
if (prevMarks.length > 0) {
const lastMarkName = prevMarks[prevMarks.length - 1]
const lastMarkRange = this.#ranges.get(lastMarkName)
if (lastMarkRange) {
this.#lastMark = lastMarkName
if (paused) this.highlight(lastMarkRange.cloneRange())
return this.#speak(doc, ssml => this.#getMarkElement(ssml, lastMarkName))
}
} else {
this.#lastMark = null
if (paused) this.highlight(range.cloneRange())
return this.#speak(doc)
}
}
}
}
nextMark(paused) {
const marks = Array.from(this.#ranges.keys())
if (marks.length === 0) return
const currentIndex = this.#lastMark ? marks.indexOf(this.#lastMark) : -1
if (currentIndex >= 0 && currentIndex < marks.length - 1) {
const nextMarkName = marks[currentIndex + 1]
const range = this.#ranges.get(nextMarkName)
if (range) {
this.#lastMark = nextMarkName
if (paused) this.highlight(range.cloneRange())
const [doc] = this.#list.current() ?? []
return this.#speak(doc, ssml => this.#getMarkElement(ssml, nextMarkName))
}
} else {
const [doc, range] = this.#list.next() ?? []
if (doc && range) {
const nextMarks = Array.from(this.#ranges.keys())
if (nextMarks.length > 0) {
const firstMarkName = nextMarks[0]
const firstMarkRange = this.#ranges.get(firstMarkName)
if (firstMarkRange) {
this.#lastMark = firstMarkName
if (paused) this.highlight(firstMarkRange.cloneRange())
return this.#speak(doc, ssml => this.#getMarkElement(ssml, firstMarkName))
}
} else {
this.#lastMark = null
if (paused) this.highlight(range.cloneRange())
return this.#speak(doc)
}
}
}
}
from(range) {
this.#lastMark = null
const [doc] = this.#list.find(range_ =>
range.compareBoundaryPoints(Range.END_TO_START, range_) <= 0)
let mark
for (const [name, range_] of this.#ranges.entries())
if (range.compareBoundaryPoints(Range.START_TO_START, range_) <= 0) {
mark = name
break
}
return this.#speak(doc, ssml => this.#getMarkElement(ssml, mark))
}
getLastRange() {
if (this.#lastMark) {
const range = this.#ranges.get(this.#lastMark)
if (range) return range.cloneRange()
}
}
setMark(mark) {
const range = this.#ranges.get(mark)
if (range) {
this.#lastMark = mark
this.highlight(range.cloneRange())
return range
}
}
}