diff options
Diffstat (limited to 'src/data/yaml.js')
| -rw-r--r-- | src/data/yaml.js | 206 |
1 files changed, 173 insertions, 33 deletions
diff --git a/src/data/yaml.js b/src/data/yaml.js index 07dbe882..9a0295b8 100644 --- a/src/data/yaml.js +++ b/src/data/yaml.js @@ -8,9 +8,11 @@ import {inspect as nodeInspect} from 'node:util'; import yaml from 'js-yaml'; import {colors, ENABLE_COLOR, logInfo, logWarn} from '#cli'; +import {parseContentNodes, splitContentNodesAround} from '#replacer'; import {sortByName} from '#sort'; import Thing from '#thing'; import thingConstructors from '#things'; +import {matchContentEntries, multipleLyricsDetectionRegex} from '#wiki-data'; import { aggregateThrows, @@ -609,49 +611,39 @@ export function parseContributors(entries) { }); } -export function parseAdditionalFiles(entries) { +export function parseAdditionalFiles(entries, {subdoc, AdditionalFile}) { return parseArrayEntries(entries, item => { if (typeof item !== 'object') return item; - return { - title: item['Title'], - description: item['Description'] ?? null, - files: item['Files'], - }; + return subdoc(AdditionalFile, item, {bindInto: 'thing'}); }); } -export function parseAdditionalNames(entries) { +export function parseAdditionalNames(entries, {subdoc, AdditionalName}) { return parseArrayEntries(entries, item => { - if (typeof item === 'object' && typeof item['Name'] === 'string') - return { - name: item['Name'], - annotation: item['Annotation'] ?? null, - }; + if (typeof item === 'object') { + return subdoc(AdditionalName, item, {bindInto: 'thing'}); + } if (typeof item !== 'string') return item; const match = item.match(extractAccentRegex); if (!match) return item; - return { - name: match.groups.main, - annotation: match.groups.accent ?? null, + const document = { + ['Name']: match.groups.main, + ['Annotation']: match.groups.accent ?? null, }; + + return subdoc(AdditionalName, document, {bindInto: 'thing'}); }); } -export function parseSerieses(entries) { +export function parseSerieses(entries, {subdoc, Series}) { return parseArrayEntries(entries, item => { if (typeof item !== 'object') return item; - return { - name: item['Name'], - description: item['Description'] ?? null, - albums: item['Albums'] ?? null, - - showAlbumArtists: item['Show Album Artists'] ?? null, - }; + return subdoc(Series, item, {bindInto: 'group'}); }); } @@ -791,18 +783,24 @@ export function parseAnnotatedReferences(entries, { export function parseArtwork({ single = false, - dimensionsFromThingProperty, - fileExtensionFromThingProperty, - dateFromThingProperty, - artistContribsFromThingProperty, - artistContribsArtistProperty, + thingProperty = null, + dimensionsFromThingProperty = null, + fileExtensionFromThingProperty = null, + dateFromThingProperty = null, + artistContribsFromThingProperty = null, + artistContribsArtistProperty = null, + artTagsFromThingProperty = null, + referencedArtworksFromThingProperty = null, }) { const provide = { + thingProperty, dimensionsFromThingProperty, fileExtensionFromThingProperty, dateFromThingProperty, artistContribsFromThingProperty, artistContribsArtistProperty, + artTagsFromThingProperty, + referencedArtworksFromThingProperty, }; const parseSingleEntry = (entry, {subdoc, Artwork}) => @@ -820,6 +818,135 @@ export function parseArtwork({ return transform; } +export function parseContentEntriesFromSourceText(thingClass, sourceText, {subdoc}) { + function map(matchEntry) { + let artistText = null, artistReferences = null; + + const artistTextNodes = + Array.from( + splitContentNodesAround( + parseContentNodes(matchEntry.artistText), + /\|/g)); + + const separatorIndices = + artistTextNodes + .filter(node => node.type === 'separator') + .map(node => artistTextNodes.indexOf(node)); + + if (empty(separatorIndices)) { + if (artistTextNodes.length === 1 && artistTextNodes[0].type === 'text') { + artistReferences = matchEntry.artistText; + } else { + artistText = matchEntry.artistText; + } + } else { + const firstSeparatorIndex = + separatorIndices.at(0); + + const secondSeparatorIndex = + separatorIndices.at(1) ?? + artistTextNodes.length; + + artistReferences = + matchEntry.artistText.slice( + artistTextNodes.at(0).i, + artistTextNodes.at(firstSeparatorIndex - 1).iEnd); + + artistText = + matchEntry.artistText.slice( + artistTextNodes.at(firstSeparatorIndex).iEnd, + artistTextNodes.at(secondSeparatorIndex - 1).iEnd); + } + + if (artistReferences) { + artistReferences = + artistReferences + .split(',') + .map(ref => ref.trim()); + } + + return { + 'Artists': + artistReferences, + + 'Artist Text': + artistText, + + 'Annotation': + matchEntry.annotation, + + 'Date': + matchEntry.date, + + 'Second Date': + matchEntry.secondDate, + + 'Date Kind': + matchEntry.dateKind, + + 'Access Date': + matchEntry.accessDate, + + 'Access Kind': + matchEntry.accessKind, + + 'Body': + matchEntry.body, + }; + } + + const documents = + matchContentEntries(sourceText) + .map(matchEntry => + withEntries( + map(matchEntry), + entries => entries + .filter(([key, value]) => + value !== undefined && + value !== null))); + + const subdocs = + documents.map(document => + subdoc(thingClass, document, {bindInto: 'thing'})); + + return subdocs; +} + +export function parseContentEntries(thingClass, value, {subdoc}) { + if (typeof value === 'string') { + return parseContentEntriesFromSourceText(thingClass, value, {subdoc}); + } else if (Array.isArray(value)) { + return value.map(doc => subdoc(thingClass, doc, {bindInto: 'thing'})); + } else { + return value; + } +} + +export function parseCommentary(value, {subdoc, CommentaryEntry}) { + return parseContentEntries(CommentaryEntry, value, {subdoc}); +} + +export function parseCreditingSources(value, {subdoc, CreditingSourcesEntry}) { + return parseContentEntries(CreditingSourcesEntry, value, {subdoc}); +} + +export function parseReferencingSources(value, {subdoc, ReferencingSourcesEntry}) { + return parseContentEntries(ReferencingSourcesEntry, value, {subdoc}); +} + +export function parseLyrics(value, {subdoc, LyricsEntry}) { + if ( + typeof value === 'string' && + !multipleLyricsDetectionRegex.test(value) + ) { + const document = {'Body': value}; + + return [subdoc(LyricsEntry, document, {bindInto: 'thing'})]; + } + + return parseContentEntries(LyricsEntry, value, {subdoc}); +} + // documentModes: Symbols indicating sets of behavior for loading and processing // data files. export const documentModes = { @@ -895,7 +1022,7 @@ export const documentModes = { export function getAllDataSteps() { try { thingConstructors; - } catch (error) { + } catch { throw new Error(`Thing constructors aren't ready yet, can't get all data steps`); } @@ -1495,6 +1622,10 @@ export function linkWikiDataArrays(wikiData, {bindFind, bindReverse}) { ['artworkData', ['artworkData']], + ['commentaryData', [/* find */]], + + ['creditingSourceData', [/* find */]], + ['flashData', [ 'wikiInfo', ]], @@ -1509,6 +1640,12 @@ export function linkWikiDataArrays(wikiData, {bindFind, bindReverse}) { ['homepageLayout.sections.rows', [/* find */]], + ['lyricsData', [/* find */]], + + ['referencingSourceData', [/* find */]], + + ['seriesData', [/* find */]], + ['trackData', [ 'artworkData', 'trackData', @@ -1777,14 +1914,16 @@ export function flattenThingLayoutToDocumentOrder(layout) { } export function* splitDocumentsInYAMLSourceText(sourceText) { - const dividerRegex = /^-{3,}\n?/gm; + // Not multiline! + const dividerRegex = /(?:\r\n|\n|^)-{3,}(?:\r\n|\n|$)/g; + let previousDivider = ''; while (true) { const {lastIndex} = dividerRegex; const match = dividerRegex.exec(sourceText); if (match) { - const nextDivider = match[0].trim(); + const nextDivider = match[0]; yield { previousDivider, @@ -1795,11 +1934,12 @@ export function* splitDocumentsInYAMLSourceText(sourceText) { previousDivider = nextDivider; } else { const nextDivider = ''; + const lineBreak = previousDivider.match(/\r?\n/)?.[0] ?? ''; yield { previousDivider, nextDivider, - text: sourceText.slice(lastIndex).replace(/(?<!\n)$/, '\n'), + text: sourceText.slice(lastIndex).replace(/(?<!\n)$/, lineBreak), }; return; @@ -1825,7 +1965,7 @@ export function recombineDocumentsIntoYAMLSourceText(documents) { for (const document of documents) { if (sourceText) { - sourceText += divider + '\n'; + sourceText += divider; } sourceText += document.text; |