Files
silo-server/web/vendor/foliate-js/opds.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

401 lines
16 KiB
JavaScript

const NS = {
ATOM: 'http://www.w3.org/2005/Atom',
OPDS: 'http://opds-spec.org/2010/catalog',
THR: 'http://purl.org/syndication/thread/1.0',
DC: 'http://purl.org/dc/elements/1.1/',
DCTERMS: 'http://purl.org/dc/terms/',
FH: 'http://purl.org/syndication/history/1.0',
PSE: 'http://vaemendis.net/opds-pse/ns',
OS: 'http://a9.com/-/spec/opensearch/1.1/',
}
const MIME = {
ATOM: 'application/atom+xml',
OPDS2: 'application/opds+json',
}
export const REL = {
ACQ: 'http://opds-spec.org/acquisition',
FACET: 'http://opds-spec.org/facet',
GROUP: 'http://opds-spec.org/group',
COVER: [
'http://opds-spec.org/image',
'http://opds-spec.org/cover', // ManyBooks legacy, not in spec
'x-stanza-cover-image', // Lexcycle Stanza legacy
],
THUMBNAIL: [
'http://opds-spec.org/image/thumbnail',
'http://opds-spec.org/thumbnail', // ManyBooks legacy, not in spec
'x-stanza-cover-image-thumbnail', // Lexcycle Stanza legacy
],
STREAM: 'http://vaemendis.net/opds-pse/stream',
}
export const SYMBOL = {
SUMMARY: Symbol('summary'),
CONTENT: Symbol('content'),
}
const FACET_GROUP = Symbol('facetGroup')
const groupByArray = (arr, f) => {
const map = new Map()
if (arr) {
for (const el of arr) {
const keys = f(el)
const keyArray = keys == null ? [] : (Array.isArray(keys) ? keys : [keys])
for (const key of keyArray) {
const group = map.get(key)
if (group) group.push(el)
else map.set(key, [el])
}
}
}
return map
}
// https://www.rfc-editor.org/rfc/rfc7231#section-3.1.1
const parseMediaType = str => {
if (!str) return
const [mediaType, ...ps] = str.split(/ *; */)
if (!mediaType) return
return {
mediaType: mediaType.toLowerCase(),
parameters: ps.reduce((acc, p) => {
const [name, val] = p.split('=')
if (name) {
acc[name.toLowerCase()] = val?.replace(/(^"|"$)/g, '')
}
return acc
}, {}),
}
}
export const isOPDSCatalog = str => {
const parsed = parseMediaType(str)
if (!parsed) return false
const { mediaType, parameters } = parsed
if (mediaType === MIME.OPDS2) return true
return mediaType === MIME.ATOM && parameters.profile?.toLowerCase() === 'opds-catalog'
}
// ignore the namespace if it doesn't appear in document at all
const useNS = (doc, ns) =>
doc.lookupNamespaceURI(null) === ns || doc.lookupPrefix(ns) ? ns : undefined
const filterNS = ns => ns
? name => el => el.namespaceURI === ns && el.localName === name
: name => el => el.localName === name
const getContent = el => {
if (!el) return
const type = el.getAttribute('type') ?? 'text'
const value = type === 'xhtml' ? el.innerHTML
: type === 'html' ? el.textContent
.replaceAll('&lt;', '<')
.replaceAll('&gt;', '>')
.replaceAll('&amp;', '&')
: el.textContent
return { value, type }
}
const getTextContent = el => {
const content = getContent(el)
if (content?.type === 'text') return content.value
}
const getSummary = (a, b) => getTextContent(a) ?? getTextContent(b)
// Fetch only direct children to avoid polluting with nested deep indirect acquisitions
const getDirectChildren = (el, ns, localName, tagName) => {
return Array.from(el.childNodes).filter(node =>
node.nodeType === 1 &&
(
(node.namespaceURI === ns && node.localName === localName) ||
(node.tagName === tagName)
)
)
}
const getPrice = link => {
const prices = getDirectChildren(link, NS.OPDS, 'price', 'opds:price')
if (!prices.length) return
const parsed = prices.reduce((acc, price) => {
const value = parseFloat(price.textContent)
if (!Number.isNaN(value)) {
acc.push({
currency: price.getAttribute('currencycode') ?? undefined,
value,
})
}
return acc
}, [])
if (!parsed.length) return
// OPDS 1.x allows multiple prices, OPDS 2.0 schema defines price as a single object
return parsed.length === 1 ? parsed[0] : parsed
}
const getIndirectAcquisition = el => {
const ias = getDirectChildren(el, NS.OPDS, 'indirectAcquisition', 'opds:indirectAcquisition')
if (!ias.length) return []
return ias.reduce((acc, ia) => {
const type = ia.getAttribute('type')
if (type) {
acc.push({
type,
child: getIndirectAcquisition(ia),
})
}
return acc
}, [])
}
const getLink = link => {
const relAttr = link.getAttribute('rel')
const rel = relAttr ? relAttr.split(/ +/) : undefined
const isAcquisition = rel?.some(r => r.startsWith(REL.ACQ) || r === 'preview')
const isStream = rel?.includes(REL.STREAM)
// Map OPDS 1.x active facets to OPDS 2.0 "self" link
const activeFacet = link.getAttributeNS(NS.OPDS, 'activeFacet') || link.getAttribute('opds:activeFacet')
const mappedRel = activeFacet === 'true' ? [rel ?? []].flat().concat('self') : rel
// Maps OPDS 1.x thr:count seamlessly to OPDS 2.0 properties.numberOfItems
const thrCount = link.getAttributeNS(NS.THR, 'count') || link.getAttribute('thr:count')
// Support for systems that incorrectly use standard `count` for facet hints
const fallbackCount = link.getAttribute('count')
// --- OPDS-PSE Extensions ---
const pseCount = link.getAttributeNS(NS.PSE, 'count') || link.getAttribute('pse:count')
const pseLastRead = link.getAttributeNS(NS.PSE, 'lastRead') || link.getAttribute('pse:lastRead')
const pseLastReadDate = link.getAttributeNS(NS.PSE, 'lastReadDate') || link.getAttribute('pse:lastReadDate')
return {
rel: mappedRel,
href: link.getAttribute('href') ?? undefined,
type: link.getAttribute('type') ?? undefined,
title: link.getAttribute('title') ?? undefined,
// --- Facet Grouping ---
[FACET_GROUP]: (link.getAttributeNS(NS.OPDS, 'facetGroup') || link.getAttribute('opds:facetGroup')) ?? undefined,
properties: {
price: (isAcquisition || isStream) ? getPrice(link) : undefined,
indirectAcquisition: (isAcquisition || isStream) ? getIndirectAcquisition(link) : undefined,
// --- Pagination / Facet Counters ---
numberOfItems: thrCount != null ? Number(thrCount) : (!isStream && fallbackCount != null) ? Number(fallbackCount) : undefined,
'pse:count': isStream && (pseCount ?? fallbackCount) != null ? Number(pseCount ?? fallbackCount) : undefined,
'pse:lastRead': isStream && pseLastRead != null ? Number(pseLastRead) : undefined,
'pse:lastReadDate': isStream ? pseLastReadDate ?? undefined : undefined,
},
}
}
const getPerson = person => {
const NS = person.namespaceURI
const uri = person.getElementsByTagNameNS(NS, 'uri')[0]?.textContent
return {
name: person.getElementsByTagNameNS(NS, 'name')[0]?.textContent ?? undefined,
links: uri ? [{ href: uri }] : [],
}
}
export const getPublication = entry => {
const filter = filterNS(useNS(entry.ownerDocument, NS.ATOM))
const children = Array.from(entry.children)
const filterDCEL = filterNS(NS.DC)
const filterDCTERMS = filterNS(NS.DCTERMS)
const filterDC = x => y => filterDCEL(x)(y) || filterDCTERMS(x)(y)
const links = children.filter(filter('link')).map(getLink)
const linksByRel = groupByArray(links, link => link.rel)
return {
metadata: {
id: children.find(filter('id'))?.textContent ?? undefined,
updated: children.find(filter('updated'))?.textContent ?? undefined,
title: children.find(filter('title'))?.textContent ?? undefined,
author: children.filter(filter('author')).map(getPerson),
contributor: children.filter(filter('contributor')).map(getPerson),
publisher: children.find(filterDC('publisher'))?.textContent ?? undefined,
published: (children.find(filter('published'))
?? children.find(filterDCTERMS('issued'))
?? children.find(filterDC('date')))?.textContent ?? undefined,
language: children.find(filterDC('language'))?.textContent ?? undefined,
identifier: children.find(filterDC('identifier'))?.textContent ?? undefined,
subject: children.filter(filter('category')).map(category => ({
name: category.getAttribute('label') ?? undefined,
code: category.getAttribute('term') ?? undefined,
scheme: category.getAttribute('scheme') ?? undefined,
})),
rights: children.find(filter('rights'))?.textContent ?? undefined,
[SYMBOL.CONTENT]: getContent(children.find(filter('content')) ?? children.find(filter('summary'))) ?? undefined,
},
links,
images: REL.COVER.concat(REL.THUMBNAIL)
.map(R => linksByRel.get(R)?.[0]).filter(Boolean),
}
}
export const getFeed = doc => {
const ns = useNS(doc, NS.ATOM)
const filter = filterNS(ns)
const children = Array.from(doc.documentElement.children)
const entries = children.filter(filter('entry'))
const links = children.filter(filter('link')).map(getLink)
const linksByRel = groupByArray(links, link => link.rel)
const filterFH = filterNS(NS.FH)
const filterOS = filterNS(NS.OS)
const groupedItems = new Map([[undefined, []]])
const groupLinkMap = new Map()
for (const entry of entries) {
const children = Array.from(entry.children)
const links = children.filter(filter('link')).map(getLink)
const linksByRel = groupByArray(links, link => link.rel)
const isPub = Array.from(linksByRel.keys())
.some(rel => rel?.startsWith(REL.ACQ) || rel === 'preview' || rel === REL.STREAM)
const groupLinks = linksByRel.get(REL.GROUP) ?? linksByRel.get('collection')
const groupLink = groupLinks?.length
? groupLinks.find(link => groupedItems.has(link.href)) ?? groupLinks[0] : undefined
if (groupLink?.href && !groupLinkMap.has(groupLink.href)) {
groupLinkMap.set(groupLink.href, groupLink)
}
const item = isPub
? getPublication(entry)
: Object.assign(links.find(link => isOPDSCatalog(link.type)) ?? links[0] ?? {}, {
title: children.find(filter('title'))?.textContent ?? undefined,
[SYMBOL.SUMMARY]: getSummary(children.find(filter('summary')),
children.find(filter('content'))) ?? undefined,
})
// Flag the item with its resolved OPDS 2.0 type
item.__type = isPub ? 'publication' : 'navigation'
const arr = groupedItems.get(groupLink?.href)
if (arr) arr.push(item)
else groupedItems.set(groupLink.href, [item])
}
const [items, ...groups] = Array.from(groupedItems, ([key, groupItems]) => {
// Separate publications and navigation items within the group
const publications = []
const navigation = []
for (const item of groupItems) {
if (item.__type === 'publication') {
delete item.__type
publications.push(item)
} else {
delete item.__type
navigation.push(item)
}
}
const groupContent = {}
if (publications.length) groupContent.publications = publications
if (navigation.length) groupContent.navigation = navigation
if (key === undefined) return groupContent
const link = groupLinkMap.get(key)
return {
metadata: {
title: link?.title,
numberOfItems: link?.properties?.numberOfItems,
},
links: [{ rel: 'self', href: link?.href, type: link?.type }],
...groupContent,
}
})
// --- OPDS 2.0 Pagination (derived from OpenSearch / RFC 5005) ---
const totalResults = children.find(filterOS('totalResults'))?.textContent
const itemsPerPage = children.find(filterOS('itemsPerPage'))?.textContent
const startIndex = children.find(filterOS('startIndex'))?.textContent
let currentPage
if (startIndex != null && itemsPerPage != null) {
const start = Number(startIndex)
const items = Number(itemsPerPage)
// Resolves typical 1-based offset to a page number
currentPage = Math.floor((start > 0 ? start - 1 : 0) / items) + 1
}
return {
metadata: {
id: children.find(filter('id'))?.textContent ?? undefined,
updated: children.find(filter('updated'))?.textContent ?? undefined,
title: children.find(filter('title'))?.textContent ?? undefined,
subtitle: children.find(filter('subtitle'))?.textContent ?? undefined,
numberOfItems: totalResults != null ? Number(totalResults) : undefined,
itemsPerPage: itemsPerPage != null ? Number(itemsPerPage) : undefined,
currentPage,
},
links,
isComplete: !!children.find(filterFH('complete')) || undefined,
isArchive: !!children.find(filterFH('archive')) || undefined,
...items, // contains top-level 'publications' and/or 'navigation' arrays
groups: groups.length ? groups : undefined,
facets: Array.from(
groupByArray(linksByRel.get(REL.FACET) ?? [], link => link[FACET_GROUP]),
([facet, links]) => ({ metadata: { title: facet ?? undefined }, links })
),
}
}
export const getSearch = async link => {
const { replace, getVariables } = await import('./uri-template.js')
const href = link.href || ''
return {
metadata: {
title: link.title ?? undefined,
},
search: map => replace(href, map.get(undefined)),
params: Array.from(getVariables(href), name => ({ name })),
}
}
export const getOpenSearch = doc => {
const defaultNS = doc.documentElement.namespaceURI
const filter = filterNS(defaultNS)
const children = Array.from(doc.documentElement.children)
const $$urls = children.filter(filter('Url'))
const $url = $$urls.find(url => isOPDSCatalog(url.getAttribute('type'))) ?? $$urls[0]
if (!$url) throw new Error('document must contain at least one Url element')
const regex = /{(?:([^}]+?):)?(.+?)(\?)?}/g
const defaultMap = new Map([
['count', '100'],
['startIndex', $url.getAttribute('indexOffset') ?? '0'],
['startPage', $url.getAttribute('pageOffset') ?? '0'],
['language', '*'],
['inputEncoding', 'UTF-8'],
['outputEncoding', 'UTF-8'],
])
const template = $url.getAttribute('template') || ''
return {
metadata: {
title: (children.find(filter('LongName')) ?? children.find(filter('ShortName')))?.textContent ?? undefined,
description: children.find(filter('Description'))?.textContent ?? undefined,
},
search: map => template.replace(regex, (_, prefix, param) => {
const namespace = prefix ? $url.lookupNamespaceURI(prefix) : undefined
const ns = namespace === defaultNS ? undefined : namespace
const val = map.get(ns)?.get(param)
return encodeURIComponent(val ?? (!ns ? defaultMap.get(param) ?? '' : ''))
}),
params: Array.from(template.matchAll(regex), ([, prefix, param, optional]) => {
const namespace = prefix ? $url.lookupNamespaceURI(prefix) : undefined
const ns = namespace === defaultNS ? undefined : namespace
return {
ns,
name: param, // (.+?) ensures `param` is non-empty
required: !optional,
value: ns && ns !== defaultNS ? undefined : defaultMap.get(param) ?? undefined,
}
}),
}
}