mirror/advplyr.audiobookshelf
1
0
Fork 0
mirror of https://github.com/advplyr/audiobookshelf.git synced 2025-07-09 17:04:58 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Change: scanner uses any .opf file, use description if plain text, use genres #141, Add: language book detail

Browse source
This commit is contained in:
advplyr 2021-11-09 17:54:28 -06:00
parent 3eb0dc9ac3
commit 7141f70aa5
6 changed files with 76 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

55
server/utils/parseOpfMetadata.js
View file

@ -20,20 +20,23 @@ function fetchCreator(creators, role) {
return creator ? creator.value : null
}
function fetchTagString(metadata, tag) {
if (!metadata[tag] || !metadata[tag].length) return null
var tag = metadata[tag][0]
if (typeof tag !== 'string') return null
return tag
}
function fetchDate(metadata) {
if (!metadata['dc:date']) return null
var dates = metadata['dc:date']
if (!dates.length || typeof dates[0] !== 'string') return null
var dateSplit = dates[0].split('-')
var date = fetchTagString(metadata, 'dc:date')
if (!date) return null
var dateSplit = date.split('-')
if (!dateSplit.length || dateSplit[0].length !== 4 || isNaN(dateSplit[0])) return null
return dateSplit[0]
}
function fetchPublisher(metadata) {
if (!metadata['dc:publisher']) return null
var publishers = metadata['dc:publisher']
if (!publishers.length || typeof publishers[0] !== 'string') return null
return publishers[0]
return fetchTagString(metadata, 'dc:publisher')
}
function fetchISBN(metadata) {
@ -44,22 +47,33 @@ function fetchISBN(metadata) {
}
function fetchTitle(metadata) {
if (!metadata['dc:title']) return null
var titles = metadata['dc:title']
if (!titles.length) return null
if (typeof titles[0] === 'string') {
return titles[0]
}
if (titles[0]['_']) {
return titles[0]['_']
}
return null
return fetchTagString(metadata, 'dc:title')
}
function fetchDescription(metadata) {
var description = fetchTagString(metadata, 'dc:description')
if (!description) return null
// check if description is HTML or plain text. only plain text allowed
// calibre stores < and > as &lt; and &gt;
description = description.replace(/&lt;/g, '<').replace(/&gt;/g, '>')
if (description.match(/<!DOCTYPE html>|<\/?\s*[a-z-][^>]*\s*>|(\&(?:[\w\d]+|#\d+|#x[a-f\d]+);)/)) return null
return description
}
function fetchGenres(metadata) {
if (!metadata['dc:subject'] || !metadata['dc:subject'].length) return []
return metadata['dc:subject'].map(g => typeof g === 'string' ? g : null).filter(g => !!g)
}
function fetchLanguage(metadata) {
return fetchTagString(metadata, 'dc:language')
}
module.exports.parseOpfMetadataXML = async (xml) => {
var json = await xmlToJSON(xml)
if (!json || !json.package || !json.package.metadata) return null
var metadata = json.package.metadata
if (Array.isArray(metadata)) {
if (!metadata.length) return null
metadata = metadata[0]
@ -72,7 +86,10 @@ module.exports.parseOpfMetadataXML = async (xml) => {
narrator: fetchCreator(creators, 'nrt'),
publishYear: fetchDate(metadata),
publisher: fetchPublisher(metadata),
isbn: fetchISBN(metadata)
isbn: fetchISBN(metadata),
description: fetchDescription(metadata),
genres: fetchGenres(metadata),
language: fetchLanguage(metadata)
}
return data
}