diff options
Diffstat (limited to 'src/data/yaml.js')
| -rw-r--r-- | src/data/yaml.js | 275 |
1 files changed, 231 insertions, 44 deletions
diff --git a/src/data/yaml.js b/src/data/yaml.js index 07dbe882..abe3bde2 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, @@ -85,7 +87,7 @@ function makeProcessDocument(thingConstructor, { // ] // // ...means A can't coexist with B or C, B can't coexist with A or C, and - // C can't coexist iwth A, B, or D - but it's okay for D to coexist with + // C can't coexist with A, B, or D - but it's okay for D to coexist with // A or B. // invalidFieldCombinations = [], @@ -180,9 +182,22 @@ function makeProcessDocument(thingConstructor, { const fieldCombinationErrors = []; - for (const {message, fields} of invalidFieldCombinations) { + for (const {message, fields: fieldsSpec} of invalidFieldCombinations) { const fieldsPresent = - presentFields.filter(field => fields.includes(field)); + fieldsSpec.flatMap(fieldSpec => { + if (Array.isArray(fieldSpec)) { + const [field, match] = fieldSpec; + if (!presentFields.includes(field)) return []; + if (typeof match === 'function') { + return match(document[field]) ? [field] : []; + } else { + return document[field] === match ? [field] : []; + } + } + + const field = fieldSpec; + return presentFields.includes(field) ? [field] : []; + }); if (fieldsPresent.length >= 2) { const filteredDocument = @@ -192,7 +207,10 @@ function makeProcessDocument(thingConstructor, { {preserveOriginalOrder: true}); fieldCombinationErrors.push( - new FieldCombinationError(filteredDocument, message)); + new FieldCombinationError( + filteredDocument, + fieldsSpec, + message)); for (const field of Object.keys(filteredDocument)) { skippedFields.add(field); @@ -248,7 +266,9 @@ function makeProcessDocument(thingConstructor, { // This variable would like to certify itself as "not into capitalism". let propertyValue = - (fieldSpecs[field].transform + (documentValue === null + ? null + : fieldSpecs[field].transform ? fieldSpecs[field].transform(documentValue, transformUtilities) : documentValue); @@ -414,19 +434,36 @@ export class FieldCombinationAggregateError extends AggregateError { } export class FieldCombinationError extends Error { - constructor(fields, message) { - const fieldNames = Object.keys(fields); + constructor(filteredDocument, fieldsSpec, message) { + const fieldNames = Object.keys(filteredDocument); const fieldNamesText = fieldNames - .map(field => colors.red(field)) + .map(field => { + if (fieldsSpec.includes(field)) { + return colors.red(field); + } + + const match = + fieldsSpec + .find(fieldSpec => + Array.isArray(fieldSpec) && + fieldSpec[0] === field) + .at(1); + + if (typeof match === 'function') { + return colors.red(`${field}: ${filteredDocument[field]}`); + } else { + return colors.red(`${field}: ${match}`); + } + }) .join(', '); const mainMessage = `Don't combine ${fieldNamesText}`; const causeMessage = (typeof message === 'function' - ? message(fields) + ? message(filteredFields) : typeof message === 'string' ? message : null); @@ -438,7 +475,7 @@ export class FieldCombinationError extends Error { : null), }); - this.fields = fields; + this.fields = fieldNames; } } @@ -609,49 +646,39 @@ 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 +818,24 @@ 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 +853,135 @@ 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 = { @@ -849,6 +1011,12 @@ export const documentModes = { // array of processed documents (wiki objects). allInOne: Symbol('Document mode: allInOne'), + // allTogether: One or more documens, spread across any number of files. + // Expects files array (or function) and processDocument function. + // Calls save with an array of processed documents (wiki objects) - this is + // a flat array, *not* an array of the documents processed from *each* file. + allTogether: Symbol('Document mode: allTogether'), + // oneDocumentTotal: Just a single document, represented in one file. // Expects file string (or function) and processDocument function. Calls // save with the single processed wiki document (data object). @@ -895,7 +1063,7 @@ 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`); } @@ -959,6 +1127,7 @@ export async function getFilesFromDataStep(dataStep, {dataPath}) { } } + case documentModes.allTogether: case documentModes.headerAndEntries: case documentModes.onePerFile: { if (!dataStep.files) { @@ -1114,7 +1283,8 @@ export function processThingsFromDataStep(documents, dataStep) { const {documentMode} = dataStep; switch (documentMode) { - case documentModes.allInOne: { + case documentModes.allInOne: + case documentModes.allTogether: { const result = []; const aggregate = openAggregate({message: `Errors processing documents`}); @@ -1389,6 +1559,10 @@ export function saveThingsFromDataStep(thingLists, dataStep) { return dataStep.save(thing); } + case documentModes.allTogether: { + return dataStep.save(thingLists.flat()); + } + case documentModes.headerAndEntries: case documentModes.onePerFile: { return dataStep.save(thingLists); @@ -1495,6 +1669,10 @@ export function linkWikiDataArrays(wikiData, {bindFind, bindReverse}) { ['artworkData', ['artworkData']], + ['commentaryData', [/* find */]], + + ['creditingSourceData', [/* find */]], + ['flashData', [ 'wikiInfo', ]], @@ -1509,6 +1687,12 @@ export function linkWikiDataArrays(wikiData, {bindFind, bindReverse}) { ['homepageLayout.sections.rows', [/* find */]], + ['lyricsData', [/* find */]], + + ['referencingSourceData', [/* find */]], + + ['seriesData', [/* find */]], + ['trackData', [ 'artworkData', 'trackData', @@ -1777,14 +1961,16 @@ 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 +1981,12 @@ 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 +2012,7 @@ export function recombineDocumentsIntoYAMLSourceText(documents) { for (const document of documents) { if (sourceText) { - sourceText += divider + '\n'; + sourceText += divider; } sourceText += document.text; |