diff options
Diffstat (limited to 'src/common-util/wiki-data.js')
| -rw-r--r-- | src/common-util/wiki-data.js | 98 |
1 files changed, 87 insertions, 11 deletions
diff --git a/src/common-util/wiki-data.js b/src/common-util/wiki-data.js index f97ecd63..546f1ad9 100644 --- a/src/common-util/wiki-data.js +++ b/src/common-util/wiki-data.js @@ -1,6 +1,6 @@ // Utility functions for interacting with wiki data. -import {accumulateSum, empty, unique} from './sugar.js'; +import {accumulateSum, chunkByConditions, empty, unique} from './sugar.js'; import {sortByDate} from './sort.js'; // This is a duplicate binding of filterMultipleArrays that's included purely @@ -57,10 +57,9 @@ export function getKebabCase(name) { // Specific data utilities -// Matches heading details from commentary data in roughly the formats: +// Matches heading details from commentary data in roughly the format: // -// <i>artistReference:</i> (annotation, date) -// <i>artistReference|artistDisplayText:</i> (annotation, date) +// <i>artistText:</i> (annotation, date) // // where capturing group "annotation" can be any text at all, except that the // last entry (past a comma or the only content within parentheses), if parsed @@ -83,8 +82,9 @@ export function getKebabCase(name) { // parentheses can be part of the actual annotation content. // // Capturing group "artistReference" is all the characters between <i> and </i> -// (apart from the pipe and "artistDisplayText" text, if present), and is either -// the name of an artist or an "artist:directory"-style reference. +// (apart from the pipe and the "artistText" group, if present), and is either +// the name of one or more artist or "artist:directory"-style references, +// joined by commas, if multiple. // // This regular expression *doesn't* match bodies, which will need to be parsed // out of the original string based on the indices matched using this. @@ -94,7 +94,7 @@ const dateRegex = groupName => String.raw`(?<${groupName}>[a-zA-Z]+ [0-9]{1,2}, [0-9]{4,4}|[0-9]{1,2} [^,]*[0-9]{4,4}|[0-9]{1,4}[-/][0-9]{1,4}[-/][0-9]{1,4})`; const commentaryRegexRaw = - String.raw`^<i>(?<artistReferences>.+?)(?:\|(?<artistDisplayText>.+))?:<\/i>(?: \((?<annotation>(?:.*?(?=,|\)[^)]*$))*?)(?:,? ?(?:(?<dateKind>sometime|throughout|around) )?${dateRegex('date')}(?: ?- ?${dateRegex('secondDate')})?(?: (?<accessKind>captured|accessed) ${dateRegex('accessDate')})?)?\))?`; + String.raw`^<i>(?<artistText>.+?):<\/i>(?: \((?<annotation>(?:.*?(?=,|\)[^)]*$))*?)(?:,? ?(?:(?<dateKind>sometime|throughout|around) )?${dateRegex('date')}(?: ?- ?${dateRegex('secondDate')})?(?: (?<accessKind>captured|accessed) ${dateRegex('accessDate')})?)?\))?`; export const commentaryRegexCaseInsensitive = new RegExp(commentaryRegexRaw, 'gmi'); export const commentaryRegexCaseSensitive = @@ -102,6 +102,36 @@ export const commentaryRegexCaseSensitive = export const commentaryRegexCaseSensitiveOneShot = new RegExp(commentaryRegexRaw); +// The #validators function isOldStyleLyrics() describes +// what this regular expression detects against. +export const multipleLyricsDetectionRegex = + /^<i>.*:<\/i>/m; + +export function matchContentEntries(sourceText) { + const matchEntries = []; + + let previousMatchEntry = null; + let previousEndIndex = null; + + for (const {0: matchText, index: startIndex, groups: matchEntry} + of sourceText.matchAll(commentaryRegexCaseSensitive)) { + if (previousMatchEntry) { + previousMatchEntry.body = sourceText.slice(previousEndIndex, startIndex); + } + + matchEntries.push(matchEntry); + + previousMatchEntry = matchEntry; + previousEndIndex = startIndex + matchText.length; + } + + if (previousMatchEntry) { + previousMatchEntry.body = sourceText.slice(previousEndIndex); + } + + return matchEntries; +} + export function filterAlbumsByCommentary(albums) { return albums .filter((album) => [album, ...album.tracks].some((x) => x.commentary)); @@ -167,10 +197,10 @@ export function getFlashLink(flash) { } export function getTotalDuration(tracks, { - originalReleasesOnly = false, + mainReleasesOnly = false, } = {}) { - if (originalReleasesOnly) { - tracks = tracks.filter(t => !t.originalReleaseTrack); + if (mainReleasesOnly) { + tracks = tracks.filter(t => !t.mainReleaseTrack); } return accumulateSum(tracks, track => track.duration); @@ -192,6 +222,25 @@ export function getArtistAvatar(artist, {to}) { return to('media.artistAvatar', artist.directory, artist.avatarFileExtension); } +// Used in multiple content functions for the artist info page, +// because shared logic is torture oooooooooooooooo. +export function chunkArtistTrackContributions(contributions) { + return ( + // First chunk by (contribution) date and album. + chunkByConditions(contributions, [ + ({date: date1}, {date: date2}) => + +date1 !== +date2, + ({thing: track1}, {thing: track2}) => + track1.album !== track2.album, + ]).map(contribs => + // Then, *within* the boundaries of the existing chunks, + // chunk contributions to the same thing together. + chunkByConditions(contribs, [ + ({thing: thing1}, {thing: thing2}) => + thing1 !== thing2, + ]))); +} + // Big-ass homepage row functions export function getNewAdditions(numAlbums, {albumData}) { @@ -342,7 +391,7 @@ export function filterItemsForCarousel(items) { return items .filter(item => item.hasCoverArt) - .filter(item => item.artTags.every(tag => !tag.isContentWarning)) + .filter(item => item.artTags.every(artTag => !artTag.isContentWarning)) .slice(0, maxCarouselLayoutItems + 1); } @@ -473,3 +522,30 @@ export function combineWikiDataArrays(arrays) { return combined; } } + +// Markdown stuff + +export function* matchMarkdownLinks(markdownSource, {marked}) { + const plausibleLinkRegexp = /\[.*?\)/g; + + let plausibleMatch = null; + while (plausibleMatch = plausibleLinkRegexp.exec(markdownSource)) { + // Pedantic rules use more particular parentheses detection in link + // destinations - they allow one level of balanced parentheses, and + // otherwise, parentheses must be escaped. This allows for entire links + // to be wrapped in parentheses, e.g below: + // + // This is so cool. ([You know??](https://example.com)) + // + const definiteMatch = + marked.Lexer.rules.inline.pedantic.link + .exec(markdownSource.slice(plausibleMatch.index)); + + if (definiteMatch) { + const [{length}, label, href] = definiteMatch; + const index = plausibleMatch.index + definiteMatch.index; + + yield {label, href, index, length}; + } + } +} |