mirror of
https://github.com/advplyr/audiobookshelf.git
synced 2025-12-23 04:09:38 +00:00
Clean and parse author name from directory, sort by author last name, scan for covers
This commit is contained in:
Mark Cooper
parent
9300a0bfb6
commit
e230cb47e8
28 changed files with 783 additions and 59 deletions
|
|
@ -62,6 +62,10 @@ class Audiobook {
|
|||
return this.book ? this.book.author : 'Unknown'
|
||||
}
|
||||
|
||||
get authorLF() {
|
||||
return this.book ? this.book.authorLF : null
|
||||
}
|
||||
|
||||
get genres() {
|
||||
return this.book ? this.book.genres || [] : []
|
||||
}
|
||||
|
|
@ -136,9 +140,9 @@ class Audiobook {
|
|||
toJSONExpanded() {
|
||||
return {
|
||||
id: this.id,
|
||||
title: this.title,
|
||||
author: this.author,
|
||||
cover: this.cover,
|
||||
// title: this.title,
|
||||
// author: this.author,
|
||||
// cover: this.cover,
|
||||
path: this.path,
|
||||
fullPath: this.fullPath,
|
||||
addedAt: this.addedAt,
|
||||
|
|
@ -306,6 +310,10 @@ class Audiobook {
|
|||
return hasUpdates
|
||||
}
|
||||
|
||||
syncAuthorNames(audiobookData) {
|
||||
return this.book.syncAuthorNames(audiobookData.authorFL, audiobookData.authorLF)
|
||||
}
|
||||
|
||||
isSearchMatch(search) {
|
||||
return this.book.isSearchMatch(search.toLowerCase().trim())
|
||||
}
|
||||
|
|
|
|||
|
|
@ -4,7 +4,10 @@ class Book {
|
|||
this.olid = null
|
||||
this.title = null
|
||||
this.author = null
|
||||
this.authorFL = null
|
||||
this.authorLF = null
|
||||
this.series = null
|
||||
this.volumeNumber = null
|
||||
this.publishYear = null
|
||||
this.publisher = null
|
||||
this.description = null
|
||||
|
|
@ -24,7 +27,10 @@ class Book {
|
|||
this.olid = book.olid
|
||||
this.title = book.title
|
||||
this.author = book.author
|
||||
this.authorFL = book.authorFL || null
|
||||
this.authorLF = book.authorLF || null
|
||||
this.series = book.series
|
||||
this.volumeNumber = book.volumeNumber || null
|
||||
this.publishYear = book.publishYear
|
||||
this.publisher = book.publisher
|
||||
this.description = book.description
|
||||
|
|
@ -37,7 +43,10 @@ class Book {
|
|||
olid: this.olid,
|
||||
title: this.title,
|
||||
author: this.author,
|
||||
authorFL: this.authorFL,
|
||||
authorLF: this.authorLF,
|
||||
series: this.series,
|
||||
volumeNumber: this.volumeNumber,
|
||||
publishYear: this.publishYear,
|
||||
publisher: this.publisher,
|
||||
description: this.description,
|
||||
|
|
@ -50,7 +59,10 @@ class Book {
|
|||
this.olid = data.olid || null
|
||||
this.title = data.title || null
|
||||
this.author = data.author || null
|
||||
this.authorLF = data.authorLF || null
|
||||
this.authorFL = data.authorFL || null
|
||||
this.series = data.series || null
|
||||
this.volumeNumber = data.volumeNumber || null
|
||||
this.publishYear = data.publishYear || null
|
||||
this.description = data.description || null
|
||||
this.cover = data.cover || null
|
||||
|
|
@ -83,7 +95,20 @@ class Book {
|
|||
hasUpdates = true
|
||||
}
|
||||
}
|
||||
return true
|
||||
return hasUpdates
|
||||
}
|
||||
|
||||
syncAuthorNames(authorFL, authorLF) {
|
||||
var hasUpdates = false
|
||||
if (authorFL !== this.authorFL) {
|
||||
this.authorFL = authorFL
|
||||
hasUpdates = true
|
||||
}
|
||||
if (authorLF !== this.authorLF) {
|
||||
this.authorLF = authorLF
|
||||
hasUpdates = true
|
||||
}
|
||||
return hasUpdates
|
||||
}
|
||||
|
||||
isSearchMatch(search) {
|
||||
|
|
|
|||
|
|
@ -26,7 +26,17 @@ class BookFinder {
|
|||
return title
|
||||
}
|
||||
|
||||
replaceAccentedChars(str) {
|
||||
try {
|
||||
return str.normalize('NFD').replace(/[\u0300-\u036f]/g, "")
|
||||
} catch (error) {
|
||||
Logger.error('[BookFinder] str normalize error', error)
|
||||
return str
|
||||
}
|
||||
}
|
||||
|
||||
cleanTitleForCompares(title) {
|
||||
if (!title) return ''
|
||||
// Remove subtitle if there (i.e. "Cool Book: Coolest Ever" becomes "Cool Book")
|
||||
var stripped = this.stripSubtitle(title)
|
||||
|
||||
|
|
@ -35,16 +45,34 @@ class BookFinder {
|
|||
|
||||
// Remove single quotes (i.e. "Ender's Game" becomes "Enders Game")
|
||||
cleaned = cleaned.replace(/'/g, '')
|
||||
cleaned = this.replaceAccentedChars(cleaned)
|
||||
return cleaned.toLowerCase()
|
||||
}
|
||||
|
||||
cleanAuthorForCompares(author) {
|
||||
if (!author) return ''
|
||||
var cleaned = this.replaceAccentedChars(author)
|
||||
return cleaned.toLowerCase()
|
||||
}
|
||||
|
||||
filterSearchResults(books, title, author, maxTitleDistance, maxAuthorDistance) {
|
||||
var searchTitle = this.cleanTitleForCompares(title)
|
||||
var searchAuthor = this.cleanAuthorForCompares(author)
|
||||
return books.map(b => {
|
||||
b.cleanedTitle = this.cleanTitleForCompares(b.title)
|
||||
b.titleDistance = levenshteinDistance(b.cleanedTitle, title)
|
||||
if (author) {
|
||||
b.authorDistance = levenshteinDistance(b.author || '', author)
|
||||
if (!b.author) {
|
||||
b.authorDistance = author.length
|
||||
} else {
|
||||
b.cleanedAuthor = this.cleanAuthorForCompares(b.author)
|
||||
|
||||
var cleanedAuthorDistance = levenshteinDistance(b.cleanedAuthor, searchAuthor)
|
||||
var authorDistance = levenshteinDistance(b.author || '', author)
|
||||
// Use best distance
|
||||
if (cleanedAuthorDistance > authorDistance) b.authorDistance = authorDistance
|
||||
else b.authorDistance = cleanedAuthorDistance
|
||||
}
|
||||
}
|
||||
b.totalDistance = b.titleDistance + (b.authorDistance || 0)
|
||||
b.totalPossibleDistance = b.title.length
|
||||
|
|
@ -142,7 +170,8 @@ class BookFinder {
|
|||
|
||||
async findCovers(provider, title, author, options = {}) {
|
||||
var searchResults = await this.search(provider, title, author, options)
|
||||
console.log('Find Covers search results', searchResults)
|
||||
Logger.info(`[BookFinder] FindCovers search results: ${searchResults.length}`)
|
||||
|
||||
var covers = []
|
||||
searchResults.forEach((result) => {
|
||||
if (result.covers && result.covers.length) {
|
||||
|
|
|
|||
|
|
@ -13,6 +13,8 @@ class Scanner {
|
|||
this.db = db
|
||||
this.emitter = emitter
|
||||
|
||||
this.cancelScan = false
|
||||
|
||||
this.bookFinder = new BookFinder()
|
||||
}
|
||||
|
||||
|
|
@ -34,6 +36,11 @@ class Scanner {
|
|||
const scanStart = Date.now()
|
||||
var audiobookDataFound = await getAllAudiobookFiles(this.AudiobookPath)
|
||||
|
||||
if (this.cancelScan) {
|
||||
this.cancelScan = false
|
||||
return null
|
||||
}
|
||||
|
||||
var scanResults = {
|
||||
removed: 0,
|
||||
updated: 0,
|
||||
|
|
@ -54,6 +61,10 @@ class Scanner {
|
|||
scanResults.removed++
|
||||
this.emitter('audiobook_removed', this.audiobooks[i].toJSONMinified())
|
||||
}
|
||||
if (this.cancelScan) {
|
||||
this.cancelScan = false
|
||||
return null
|
||||
}
|
||||
}
|
||||
|
||||
for (let i = 0; i < audiobookDataFound.length; i++) {
|
||||
|
|
@ -109,6 +120,11 @@ class Scanner {
|
|||
hasUpdates = true
|
||||
}
|
||||
|
||||
if (audiobookData.author && existingAudiobook.syncAuthorNames(audiobookData)) {
|
||||
Logger.info(`[Scanner] "${existingAudiobook.title}" author names updated, "${existingAudiobook.authorLF}"`)
|
||||
hasUpdates = true
|
||||
}
|
||||
|
||||
if (hasUpdates) {
|
||||
Logger.info(`[Scanner] "${existingAudiobook.title}" was updated - saving`)
|
||||
existingAudiobook.lastUpdate = Date.now()
|
||||
|
|
@ -138,10 +154,17 @@ class Scanner {
|
|||
}
|
||||
var progress = Math.round(100 * (i + 1) / audiobookDataFound.length)
|
||||
this.emitter('scan_progress', {
|
||||
total: audiobookDataFound.length,
|
||||
done: i + 1,
|
||||
progress
|
||||
scanType: 'files',
|
||||
progress: {
|
||||
total: audiobookDataFound.length,
|
||||
done: i + 1,
|
||||
progress
|
||||
}
|
||||
})
|
||||
if (this.cancelScan) {
|
||||
this.cancelScan = false
|
||||
break
|
||||
}
|
||||
}
|
||||
const scanElapsed = Math.floor((Date.now() - scanStart) / 1000)
|
||||
Logger.info(`[Scanned] Finished | ${scanResults.added} added | ${scanResults.updated} updated | ${scanResults.removed} removed | elapsed: ${secondsToTimestamp(scanElapsed)}`)
|
||||
|
|
@ -161,6 +184,47 @@ class Scanner {
|
|||
return scanResult
|
||||
}
|
||||
|
||||
async scanCovers() {
|
||||
var audiobooksNeedingCover = this.audiobooks.filter(ab => !ab.cover && ab.author)
|
||||
var found = 0
|
||||
var notFound = 0
|
||||
for (let i = 0; i < audiobooksNeedingCover.length; i++) {
|
||||
var audiobook = audiobooksNeedingCover[i]
|
||||
var options = {
|
||||
titleDistance: 2,
|
||||
authorDistance: 2
|
||||
}
|
||||
var results = await this.bookFinder.findCovers('openlibrary', audiobook.title, audiobook.author, options)
|
||||
if (results.length) {
|
||||
Logger.info(`[Scanner] Found best cover for "${audiobook.title}"`)
|
||||
audiobook.book.cover = results[0]
|
||||
await this.db.updateAudiobook(audiobook)
|
||||
found++
|
||||
} else {
|
||||
notFound++
|
||||
}
|
||||
|
||||
var progress = Math.round(100 * (i + 1) / audiobooksNeedingCover.length)
|
||||
this.emitter('scan_progress', {
|
||||
scanType: 'covers',
|
||||
progress: {
|
||||
total: audiobooksNeedingCover.length,
|
||||
done: i + 1,
|
||||
progress
|
||||
}
|
||||
})
|
||||
|
||||
if (this.cancelScan) {
|
||||
this.cancelScan = false
|
||||
break
|
||||
}
|
||||
}
|
||||
return {
|
||||
found,
|
||||
notFound
|
||||
}
|
||||
}
|
||||
|
||||
async find(req, res) {
|
||||
var method = req.params.method
|
||||
var query = req.query
|
||||
|
|
|
|||
|
|
@ -42,6 +42,7 @@ class Server {
|
|||
this.clients = {}
|
||||
|
||||
this.isScanning = false
|
||||
this.isScanningCovers = false
|
||||
this.isInitialized = false
|
||||
}
|
||||
|
||||
|
|
@ -64,13 +65,28 @@ class Server {
|
|||
Logger.info('[Server] Starting Scan')
|
||||
this.isScanning = true
|
||||
this.isInitialized = true
|
||||
this.emitter('scan_start')
|
||||
this.emitter('scan_start', 'files')
|
||||
var results = await this.scanner.scan()
|
||||
this.isScanning = false
|
||||
this.emitter('scan_complete', results)
|
||||
this.emitter('scan_complete', { scanType: 'files', results })
|
||||
Logger.info('[Server] Scan complete')
|
||||
}
|
||||
|
||||
async scanCovers() {
|
||||
Logger.info('[Server] Start cover scan')
|
||||
this.isScanningCovers = true
|
||||
this.emitter('scan_start', 'covers')
|
||||
var results = await this.scanner.scanCovers()
|
||||
this.isScanningCovers = false
|
||||
this.emitter('scan_complete', { scanType: 'covers', results })
|
||||
Logger.info('[Server] Cover scan complete')
|
||||
}
|
||||
|
||||
cancelScan() {
|
||||
if (!this.isScanningCovers && !this.isScanning) return
|
||||
this.scanner.cancelScan = true
|
||||
}
|
||||
|
||||
async init() {
|
||||
Logger.info('[Server] Init')
|
||||
await this.streamManager.removeOrphanStreams()
|
||||
|
|
@ -149,6 +165,8 @@ class Server {
|
|||
|
||||
socket.on('auth', (token) => this.authenticateSocket(socket, token))
|
||||
socket.on('scan', this.scan.bind(this))
|
||||
socket.on('scan_covers', this.scanCovers.bind(this))
|
||||
socket.on('cancel_scan', this.cancelScan.bind(this))
|
||||
socket.on('open_stream', (audiobookId) => this.streamManager.openStreamSocketRequest(socket, audiobookId))
|
||||
socket.on('close_stream', () => this.streamManager.closeStreamRequest(socket))
|
||||
socket.on('stream_update', (payload) => this.streamManager.streamUpdate(socket, payload))
|
||||
|
|
|
|||
67
server/utils/parseAuthors.js
Normal file
67
server/utils/parseAuthors.js
Normal file
|
|
@ -0,0 +1,67 @@
|
|||
const parseFullName = require('./parseFullName')
|
||||
|
||||
function parseName(name) {
|
||||
var parts = parseFullName(name)
|
||||
var firstName = parts.first
|
||||
if (firstName && parts.middle) firstName += ' ' + parts.middle
|
||||
|
||||
return {
|
||||
first_name: firstName,
|
||||
last_name: parts.last
|
||||
}
|
||||
}
|
||||
|
||||
// Check if this name segment is of the format "Last, First" or "First Last"
|
||||
// return true is "Last, First"
|
||||
function checkIsALastName(name) {
|
||||
if (!name.includes(' ')) return true // No spaces must be a Last name
|
||||
|
||||
var parsed = parseFullName(name)
|
||||
if (!parsed.first) return true // had spaces but not a first name i.e. "von Mises", must be last name only
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
module.exports = (author) => {
|
||||
if (!author) return null
|
||||
var splitByComma = author.split(', ')
|
||||
|
||||
var authors = []
|
||||
|
||||
// 1 author FIRST LAST
|
||||
if (splitByComma.length === 1) {
|
||||
authors.push(parseName(author))
|
||||
} else {
|
||||
var firstChunkIsALastName = checkIsALastName(splitByComma[0])
|
||||
var isEvenNum = splitByComma.length % 2 === 0
|
||||
|
||||
if (!isEvenNum && firstChunkIsALastName) {
|
||||
// console.error('Multi-author LAST,FIRST entry has a straggler (could be roman numerals or a suffix), ignore it', splitByComma[splitByComma.length - 1])
|
||||
splitByComma = splitByComma.slice(0, splitByComma.length - 1)
|
||||
}
|
||||
|
||||
if (firstChunkIsALastName) {
|
||||
var numAuthors = splitByComma.length / 2
|
||||
for (let i = 0; i < numAuthors; i++) {
|
||||
var last = splitByComma.shift()
|
||||
var first = splitByComma.shift()
|
||||
authors.push({
|
||||
first_name: first,
|
||||
last_name: last
|
||||
})
|
||||
}
|
||||
} else {
|
||||
splitByComma.forEach((segment) => {
|
||||
authors.push(parseName(segment))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
var firstLast = authors.length ? authors.map(a => a.first_name ? `${a.first_name} ${a.last_name}` : a.last_name).join(', ') : ''
|
||||
var lastFirst = authors.length ? authors.map(a => a.first_name ? `${a.last_name}, ${a.first_name}` : a.last_name).join(', ') : ''
|
||||
return {
|
||||
authorFL: firstLast,
|
||||
authorLF: lastFirst,
|
||||
authorsParsed: authors
|
||||
}
|
||||
}
|
||||
346
server/utils/parseFullName.js
Normal file
346
server/utils/parseFullName.js
Normal file
|
|
@ -0,0 +1,346 @@
|
|||
|
||||
|
||||
// https://github.com/RateGravity/parse-full-name/blob/master/index.js
|
||||
module.exports = (nameToParse, partToReturn, fixCase, stopOnError, useLongLists) => {
|
||||
|
||||
var i, j, k, l, m, n, part, comma, titleList, suffixList, prefixList, regex,
|
||||
partToCheck, partFound, partsFoundCount, firstComma, remainingCommas,
|
||||
nameParts = [], nameCommas = [null], partsFound = [],
|
||||
conjunctionList = ['&', 'and', 'et', 'e', 'of', 'the', 'und', 'y'],
|
||||
parsedName = {
|
||||
title: '', first: '', middle: '', last: '', nick: '', suffix: '', error: []
|
||||
};
|
||||
|
||||
// Validate inputs, or set to defaults
|
||||
partToReturn = partToReturn && ['title', 'first', 'middle', 'last', 'nick',
|
||||
'suffix', 'error'].indexOf(partToReturn.toLowerCase()) > -1 ?
|
||||
partToReturn.toLowerCase() : 'all';
|
||||
// 'all' = return object with all parts, others return single part
|
||||
if (fixCase === false) fixCase = 0;
|
||||
if (fixCase === true) fixCase = 1;
|
||||
fixCase = fixCase !== 'undefined' && (fixCase === 0 || fixCase === 1) ?
|
||||
fixCase : -1; // -1 = fix case only if input is all upper or lowercase
|
||||
if (stopOnError === true) stopOnError = 1;
|
||||
stopOnError = stopOnError && stopOnError === 1 ? 1 : 0;
|
||||
// false = output warnings on parse error, but don't stop
|
||||
if (useLongLists === true) useLongLists = 1;
|
||||
useLongLists = useLongLists && useLongLists === 1 ? 1 : 0; // 0 = short lists
|
||||
|
||||
// If stopOnError = 1, throw error, otherwise return error messages in array
|
||||
function handleError(errorMessage) {
|
||||
if (stopOnError) {
|
||||
throw 'Error: ' + errorMessage;
|
||||
} else {
|
||||
parsedName.error.push('Error: ' + errorMessage);
|
||||
}
|
||||
}
|
||||
|
||||
// If fixCase = 1, fix case of parsedName parts before returning
|
||||
function fixParsedNameCase(fixedCaseName, fixCaseNow) {
|
||||
var forceCaseList = ['e', 'y', 'av', 'af', 'da', 'dal', 'de', 'del', 'der', 'di',
|
||||
'la', 'le', 'van', 'der', 'den', 'vel', 'von', 'II', 'III', 'IV', 'J.D.', 'LL.M.',
|
||||
'M.D.', 'D.O.', 'D.C.', 'Ph.D.'];
|
||||
var forceCaseListIndex;
|
||||
var namePartLabels = [];
|
||||
var namePartWords;
|
||||
if (fixCaseNow) {
|
||||
namePartLabels = Object.keys(parsedName)
|
||||
.filter(function (v) { return v !== 'error'; });
|
||||
for (i = 0, l = namePartLabels.length; i < l; i++) {
|
||||
if (fixedCaseName[namePartLabels[i]]) {
|
||||
namePartWords = (fixedCaseName[namePartLabels[i]] + '').split(' ');
|
||||
for (j = 0, m = namePartWords.length; j < m; j++) {
|
||||
forceCaseListIndex = forceCaseList
|
||||
.map(function (v) { return v.toLowerCase(); })
|
||||
.indexOf(namePartWords[j].toLowerCase());
|
||||
if (forceCaseListIndex > -1) { // Set case of words in forceCaseList
|
||||
namePartWords[j] = forceCaseList[forceCaseListIndex];
|
||||
} else if (namePartWords[j].length === 1) { // Uppercase initials
|
||||
namePartWords[j] = namePartWords[j].toUpperCase();
|
||||
} else if (
|
||||
namePartWords[j].length > 2 &&
|
||||
namePartWords[j].slice(0, 1) ===
|
||||
namePartWords[j].slice(0, 1).toUpperCase() &&
|
||||
namePartWords[j].slice(1, 2) ===
|
||||
namePartWords[j].slice(1, 2).toLowerCase() &&
|
||||
namePartWords[j].slice(2) ===
|
||||
namePartWords[j].slice(2).toUpperCase()
|
||||
) { // Detect McCASE and convert to McCase
|
||||
namePartWords[j] = namePartWords[j].slice(0, 3) +
|
||||
namePartWords[j].slice(3).toLowerCase();
|
||||
} else if (
|
||||
namePartLabels[j] === 'suffix' &&
|
||||
nameParts[j].slice(-1) !== '.' &&
|
||||
!suffixList.indexOf(nameParts[j].toLowerCase())
|
||||
) { // Convert suffix abbreviations to UPPER CASE
|
||||
if (namePartWords[j] === namePartWords[j].toLowerCase()) {
|
||||
namePartWords[j] = namePartWords[j].toUpperCase();
|
||||
}
|
||||
} else { // Convert to Title Case
|
||||
namePartWords[j] = namePartWords[j].slice(0, 1).toUpperCase() +
|
||||
namePartWords[j].slice(1).toLowerCase();
|
||||
}
|
||||
}
|
||||
fixedCaseName[namePartLabels[i]] = namePartWords.join(' ');
|
||||
}
|
||||
}
|
||||
}
|
||||
return fixedCaseName;
|
||||
}
|
||||
|
||||
// If no input name, or input name is not a string, abort
|
||||
if (!nameToParse || typeof nameToParse !== 'string') {
|
||||
handleError('No input');
|
||||
parsedName = fixParsedNameCase(parsedName, fixCase);
|
||||
return partToReturn === 'all' ? parsedName : parsedName[partToReturn];
|
||||
} else {
|
||||
nameToParse = nameToParse.trim();
|
||||
}
|
||||
|
||||
// Auto-detect fixCase: fix if nameToParse is all upper or all lowercase
|
||||
if (fixCase === -1) {
|
||||
fixCase = (
|
||||
nameToParse === nameToParse.toUpperCase() ||
|
||||
nameToParse === nameToParse.toLowerCase() ? 1 : 0
|
||||
);
|
||||
}
|
||||
|
||||
// Initilize lists of prefixs, suffixs, and titles to detect
|
||||
// Note: These list entries must be all lowercase
|
||||
if (useLongLists) {
|
||||
suffixList = ['esq', 'esquire', 'jr', 'jnr', 'sr', 'snr', '2', 'ii', 'iii', 'iv',
|
||||
'v', 'clu', 'chfc', 'cfp', 'md', 'phd', 'j.d.', 'll.m.', 'm.d.', 'd.o.', 'd.c.',
|
||||
'p.c.', 'ph.d.'];
|
||||
prefixList = ['a', 'ab', 'antune', 'ap', 'abu', 'al', 'alm', 'alt', 'bab', 'bäck',
|
||||
'bar', 'bath', 'bat', 'beau', 'beck', 'ben', 'berg', 'bet', 'bin', 'bint', 'birch',
|
||||
'björk', 'björn', 'bjur', 'da', 'dahl', 'dal', 'de', 'degli', 'dele', 'del',
|
||||
'della', 'der', 'di', 'dos', 'du', 'e', 'ek', 'el', 'escob', 'esch', 'fleisch',
|
||||
'fitz', 'fors', 'gott', 'griff', 'haj', 'haug', 'holm', 'ibn', 'kauf', 'kil',
|
||||
'koop', 'kvarn', 'la', 'le', 'lind', 'lönn', 'lund', 'mac', 'mhic', 'mic', 'mir',
|
||||
'na', 'naka', 'neder', 'nic', 'ni', 'nin', 'nord', 'norr', 'ny', 'o', 'ua', 'ui\'',
|
||||
'öfver', 'ost', 'över', 'öz', 'papa', 'pour', 'quarn', 'skog', 'skoog', 'sten',
|
||||
'stor', 'ström', 'söder', 'ter', 'ter', 'tre', 'türk', 'van', 'väst', 'väster',
|
||||
'vest', 'von'];
|
||||
titleList = ['mr', 'mrs', 'ms', 'miss', 'dr', 'herr', 'monsieur', 'hr', 'frau',
|
||||
'a v m', 'admiraal', 'admiral', 'air cdre', 'air commodore', 'air marshal',
|
||||
'air vice marshal', 'alderman', 'alhaji', 'ambassador', 'baron', 'barones',
|
||||
'brig', 'brig gen', 'brig general', 'brigadier', 'brigadier general',
|
||||
'brother', 'canon', 'capt', 'captain', 'cardinal', 'cdr', 'chief', 'cik', 'cmdr',
|
||||
'coach', 'col', 'col dr', 'colonel', 'commandant', 'commander', 'commissioner',
|
||||
'commodore', 'comte', 'comtessa', 'congressman', 'conseiller', 'consul',
|
||||
'conte', 'contessa', 'corporal', 'councillor', 'count', 'countess',
|
||||
'crown prince', 'crown princess', 'dame', 'datin', 'dato', 'datuk',
|
||||
'datuk seri', 'deacon', 'deaconess', 'dean', 'dhr', 'dipl ing', 'doctor',
|
||||
'dott', 'dott sa', 'dr', 'dr ing', 'dra', 'drs', 'embajador', 'embajadora', 'en',
|
||||
'encik', 'eng', 'eur ing', 'exma sra', 'exmo sr', 'f o', 'father',
|
||||
'first lieutient', 'first officer', 'flt lieut', 'flying officer', 'fr',
|
||||
'frau', 'fraulein', 'fru', 'gen', 'generaal', 'general', 'governor', 'graaf',
|
||||
'gravin', 'group captain', 'grp capt', 'h e dr', 'h h', 'h m', 'h r h', 'hajah',
|
||||
'haji', 'hajim', 'her highness', 'her majesty', 'herr', 'high chief',
|
||||
'his highness', 'his holiness', 'his majesty', 'hon', 'hr', 'hra', 'ing', 'ir',
|
||||
'jonkheer', 'judge', 'justice', 'khun ying', 'kolonel', 'lady', 'lcda', 'lic',
|
||||
'lieut', 'lieut cdr', 'lieut col', 'lieut gen', 'lord', 'm', 'm l', 'm r',
|
||||
'madame', 'mademoiselle', 'maj gen', 'major', 'master', 'mevrouw', 'miss',
|
||||
'mlle', 'mme', 'monsieur', 'monsignor', 'mr', 'mrs', 'ms', 'mstr', 'nti', 'pastor',
|
||||
'president', 'prince', 'princess', 'princesse', 'prinses', 'prof', 'prof dr',
|
||||
'prof sir', 'professor', 'puan', 'puan sri', 'rabbi', 'rear admiral', 'rev',
|
||||
'rev canon', 'rev dr', 'rev mother', 'reverend', 'rva', 'senator', 'sergeant',
|
||||
'sheikh', 'sheikha', 'sig', 'sig na', 'sig ra', 'sir', 'sister', 'sqn ldr', 'sr',
|
||||
'sr d', 'sra', 'srta', 'sultan', 'tan sri', 'tan sri dato', 'tengku', 'teuku',
|
||||
'than puying', 'the hon dr', 'the hon justice', 'the hon miss', 'the hon mr',
|
||||
'the hon mrs', 'the hon ms', 'the hon sir', 'the very rev', 'toh puan', 'tun',
|
||||
'vice admiral', 'viscount', 'viscountess', 'wg cdr', 'ind', 'misc', 'mx'];
|
||||
} else {
|
||||
suffixList = ['esq', 'esquire', 'jr', 'jnr', 'sr', 'snr', '2', 'ii', 'iii', 'iv',
|
||||
'md', 'phd', 'j.d.', 'll.m.', 'm.d.', 'd.o.', 'd.c.', 'p.c.', 'ph.d.'];
|
||||
prefixList = ['ab', 'bar', 'bin', 'da', 'dal', 'de', 'de la', 'del', 'della', 'der',
|
||||
'di', 'du', 'ibn', 'l\'', 'la', 'le', 'san', 'st', 'st.', 'ste', 'ter', 'van',
|
||||
'van de', 'van der', 'van den', 'vel', 'ver', 'vere', 'von'];
|
||||
titleList = ['dr', 'miss', 'mr', 'mrs', 'ms', 'prof', 'sir', 'frau', 'herr', 'hr',
|
||||
'monsieur', 'captain', 'doctor', 'judge', 'officer', 'professor', 'ind', 'misc',
|
||||
'mx'];
|
||||
}
|
||||
|
||||
// Nickname: remove and store parts with surrounding punctuation as nicknames
|
||||
regex = /\s(?:[‘’']([^‘’']+)[‘’']|[“”"]([^“”"]+)[“”"]|\[([^\]]+)\]|\(([^\)]+)\)),?\s/g;
|
||||
partFound = (' ' + nameToParse + ' ').match(regex);
|
||||
if (partFound) partsFound = partsFound.concat(partFound);
|
||||
partsFoundCount = partsFound.length;
|
||||
if (partsFoundCount === 1) {
|
||||
parsedName.nick = partsFound[0].slice(2).slice(0, -2);
|
||||
if (parsedName.nick.slice(-1) === ',') {
|
||||
parsedName.nick = parsedName.nick.slice(0, -1);
|
||||
}
|
||||
nameToParse = (' ' + nameToParse + ' ').replace(partsFound[0], ' ').trim();
|
||||
partsFound = [];
|
||||
} else if (partsFoundCount > 1) {
|
||||
handleError(partsFoundCount + ' nicknames found');
|
||||
for (i = 0; i < partsFoundCount; i++) {
|
||||
nameToParse = (' ' + nameToParse + ' ')
|
||||
.replace(partsFound[i], ' ').trim();
|
||||
partsFound[i] = partsFound[i].slice(2).slice(0, -2);
|
||||
if (partsFound[i].slice(-1) === ',') {
|
||||
partsFound[i] = partsFound[i].slice(0, -1);
|
||||
}
|
||||
}
|
||||
parsedName.nick = partsFound.join(', ');
|
||||
partsFound = [];
|
||||
}
|
||||
if (!nameToParse.trim().length) {
|
||||
parsedName = fixParsedNameCase(parsedName, fixCase);
|
||||
return partToReturn === 'all' ? parsedName : parsedName[partToReturn];
|
||||
}
|
||||
|
||||
// Split remaining nameToParse into parts, remove and store preceding commas
|
||||
for (i = 0, n = nameToParse.split(' '), l = n.length; i < l; i++) {
|
||||
part = n[i];
|
||||
comma = null;
|
||||
if (part.slice(-1) === ',') {
|
||||
comma = ',';
|
||||
part = part.slice(0, -1);
|
||||
}
|
||||
nameParts.push(part);
|
||||
nameCommas.push(comma);
|
||||
}
|
||||
|
||||
// Suffix: remove and store matching parts as suffixes
|
||||
for (l = nameParts.length, i = l - 1; i > 0; i--) {
|
||||
partToCheck = (nameParts[i].slice(-1) === '.' ?
|
||||
nameParts[i].slice(0, -1).toLowerCase() : nameParts[i].toLowerCase());
|
||||
if (
|
||||
suffixList.indexOf(partToCheck) > -1 ||
|
||||
suffixList.indexOf(partToCheck + '.') > -1
|
||||
) {
|
||||
partsFound = nameParts.splice(i, 1).concat(partsFound);
|
||||
if (nameCommas[i] === ',') { // Keep comma, either before or after
|
||||
nameCommas.splice(i + 1, 1);
|
||||
} else {
|
||||
nameCommas.splice(i, 1);
|
||||
}
|
||||
}
|
||||
}
|
||||
partsFoundCount = partsFound.length;
|
||||
if (partsFoundCount === 1) {
|
||||
parsedName.suffix = partsFound[0];
|
||||
partsFound = [];
|
||||
} else if (partsFoundCount > 1) {
|
||||
handleError(partsFoundCount + ' suffixes found');
|
||||
parsedName.suffix = partsFound.join(', ');
|
||||
partsFound = [];
|
||||
}
|
||||
if (!nameParts.length) {
|
||||
parsedName = fixParsedNameCase(parsedName, fixCase);
|
||||
return partToReturn === 'all' ? parsedName : parsedName[partToReturn];
|
||||
}
|
||||
|
||||
// Title: remove and store matching parts as titles
|
||||
for (l = nameParts.length, i = l - 1; i >= 0; i--) {
|
||||
partToCheck = (nameParts[i].slice(-1) === '.' ?
|
||||
nameParts[i].slice(0, -1).toLowerCase() : nameParts[i].toLowerCase());
|
||||
if (
|
||||
titleList.indexOf(partToCheck) > -1 ||
|
||||
titleList.indexOf(partToCheck + '.') > -1
|
||||
) {
|
||||
partsFound = nameParts.splice(i, 1).concat(partsFound);
|
||||
if (nameCommas[i] === ',') { // Keep comma, either before or after
|
||||
nameCommas.splice(i + 1, 1);
|
||||
} else {
|
||||
nameCommas.splice(i, 1);
|
||||
}
|
||||
}
|
||||
}
|
||||
partsFoundCount = partsFound.length;
|
||||
if (partsFoundCount === 1) {
|
||||
parsedName.title = partsFound[0];
|
||||
partsFound = [];
|
||||
} else if (partsFoundCount > 1) {
|
||||
handleError(partsFoundCount + ' titles found');
|
||||
parsedName.title = partsFound.join(', ');
|
||||
partsFound = [];
|
||||
}
|
||||
if (!nameParts.length) {
|
||||
parsedName = fixParsedNameCase(parsedName, fixCase);
|
||||
return partToReturn === 'all' ? parsedName : parsedName[partToReturn];
|
||||
}
|
||||
|
||||
// Join name prefixes to following names
|
||||
if (nameParts.length > 1) {
|
||||
for (i = nameParts.length - 2; i >= 0; i--) {
|
||||
if (prefixList.indexOf(nameParts[i].toLowerCase()) > -1) {
|
||||
nameParts[i] = nameParts[i] + ' ' + nameParts[i + 1];
|
||||
nameParts.splice(i + 1, 1);
|
||||
nameCommas.splice(i + 1, 1);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Join conjunctions to surrounding names
|
||||
if (nameParts.length > 2) {
|
||||
for (i = nameParts.length - 3; i >= 0; i--) {
|
||||
if (conjunctionList.indexOf(nameParts[i + 1].toLowerCase()) > -1) {
|
||||
nameParts[i] = nameParts[i] + ' ' + nameParts[i + 1] + ' ' + nameParts[i + 2];
|
||||
nameParts.splice(i + 1, 2);
|
||||
nameCommas.splice(i + 1, 2);
|
||||
i--;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Suffix: remove and store items after extra commas as suffixes
|
||||
nameCommas.pop();
|
||||
firstComma = nameCommas.indexOf(',');
|
||||
remainingCommas = nameCommas.filter(function (v) { return v !== null; }).length;
|
||||
if (firstComma > 1 || remainingCommas > 1) {
|
||||
for (i = nameParts.length - 1; i >= 2; i--) {
|
||||
if (nameCommas[i] === ',') {
|
||||
partsFound = nameParts.splice(i, 1).concat(partsFound);
|
||||
nameCommas.splice(i, 1);
|
||||
remainingCommas--;
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (partsFound.length) {
|
||||
if (parsedName.suffix) {
|
||||
partsFound = [parsedName.suffix].concat(partsFound);
|
||||
}
|
||||
parsedName.suffix = partsFound.join(', ');
|
||||
partsFound = [];
|
||||
}
|
||||
|
||||
// Last name: remove and store last name
|
||||
if (remainingCommas > 0) {
|
||||
if (remainingCommas > 1) {
|
||||
handleError((remainingCommas - 1) + ' extra commas found');
|
||||
}
|
||||
// Remove and store all parts before first comma as last name
|
||||
if (nameCommas.indexOf(',')) {
|
||||
parsedName.last = nameParts.splice(0, nameCommas.indexOf(',')).join(' ');
|
||||
nameCommas.splice(0, nameCommas.indexOf(','));
|
||||
}
|
||||
} else {
|
||||
// Remove and store last part as last name
|
||||
parsedName.last = nameParts.pop();
|
||||
}
|
||||
if (!nameParts.length) {
|
||||
parsedName = fixParsedNameCase(parsedName, fixCase);
|
||||
return partToReturn === 'all' ? parsedName : parsedName[partToReturn];
|
||||
}
|
||||
|
||||
// First name: remove and store first part as first name
|
||||
parsedName.first = nameParts.shift();
|
||||
if (!nameParts.length) {
|
||||
parsedName = fixParsedNameCase(parsedName, fixCase);
|
||||
return partToReturn === 'all' ? parsedName : parsedName[partToReturn];
|
||||
}
|
||||
|
||||
// Middle name: store all remaining parts as middle name
|
||||
if (nameParts.length > 2) {
|
||||
handleError(nameParts.length + ' middle names');
|
||||
}
|
||||
parsedName.middle = nameParts.join(' ');
|
||||
|
||||
parsedName = fixParsedNameCase(parsedName, fixCase);
|
||||
return partToReturn === 'all' ? parsedName : parsedName[partToReturn];
|
||||
};
|
||||
|
|
@ -1,6 +1,7 @@
|
|||
const Path = require('path')
|
||||
const dir = require('node-dir')
|
||||
const Logger = require('../Logger')
|
||||
const parseAuthors = require('./parseAuthors')
|
||||
const { cleanString } = require('./index')
|
||||
|
||||
const AUDIOBOOK_PARTS_FORMATS = ['m4b', 'mp3']
|
||||
|
|
@ -74,6 +75,14 @@ async function getAllAudiobookFiles(abRootPath) {
|
|||
parts: [],
|
||||
otherFiles: []
|
||||
}
|
||||
if (author) {
|
||||
var parsedAuthors = parseAuthors(author)
|
||||
if (parsedAuthors) {
|
||||
var { authorLF, authorFL } = parsedAuthors
|
||||
audiobooks[path].authorLF = authorLF || null
|
||||
audiobooks[path].authorFL = authorFL || null
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
var filetype = getFileType(pathformat.ext)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue