2b:null 2c:["$","title",null,{"children":"Mastodon Archive Tool | Andi | Observable"}] 31:T6a2,html`${stats ? '

Statistics:

' : ''} ${stats ? '

Top Ten Likes sent:

' : ''} ${ stats ? table(stats.likesByUser.slice(0, 10).map(([username, urls]) => ({username, urls})), { sortable: true, paged: 10, columns: { username: { title: 'Username', }, urls: { title: 'Likes', formatter: (item) => { return `

${item.length} likes

${item.map((object) => `${object}`).join('
')}

`; }, } } }) : `` }

${stats ? '

Top 10 most boosted users:

' : ''} ${stats ? table(stats.mostBoosted.slice(0, 10).map(([username, statuses]) => ({username, statuses})), { sortable: true, paged: 10, columns: { username: { title: 'Username', }, statuses: { title: 'Boosts', formatter: (item) => { return `

${item.length} boosts

${item.map(({object}) => `${object.id || object}`).join('
')}

`; }, } } }) : `` }

${stats ? '

Top 10 most mentioned users:

' : ''} ${ stats ? table(stats.mostMentioned.slice(1, 11).map(([username, mentions]) => ({username, mentions})), { sortable: true, paged: 10, columns: { username: { title: 'Username', }, mentions: { title: 'Mentions', formatter: (item) => { return `

${item.length} mentions

${item.map(({object}) => `${object.id || object}`).join('
')}

`; }, } } }) : `` } `32:T74e,stats = { if (!archive || !archive.likes) return; const { outbox, likes } = archive; // The following will only match Masto likes. @TODO make work with Pleroma. const userPattern = /https?:\/\/([^/]+)\/users\/([^/]+)/; const likesByUser = [...likes.orderedItems.filter(i => i).reduce((a, c) => { const result = userPattern.exec(c); if (!result) { console.warn(`Couldn't parse for most likes:`, c); return a; } const [ domain, user ] = result.slice(1); const username = `${user}@${domain}`; return a.set(username, [...(a.get(username) || []), c]); }, new Map()).entries()].sort(([, v1], [, v2]) => v2.length - v1.length); const mostBoosted = [...outbox.orderedItems.filter(({type}) => type === "Announce") .reduce((a, c) => { const { object } = c; const id = object.id || object; const result = userPattern.exec(id); if (!result) { console.warn(`Couldn't parse for most boosted:`, c); return a; } const [ domain, user ] = result.slice(1); const username = `${user}@${domain}`; return a.set(username, [...(a.get(username) || []), c]); }, new Map()).entries()].sort(([, v1], [, v2]) => v2.length - v1.length); const mostMentioned = [...outbox.orderedItems .reduce((a, c) => { const { cc } = c; for (const item of cc) { const result = userPattern.exec(item); if (!result) { console.warn(`Couldn't parse for most mentioned:`, c); return a; } const [ domain, user ] = result.slice(1); const username = `${user}@${domain}`; return a.set(username, [...(a.get(username) || []), c]); } return a; }, new Map()).entries()].sort(([, v1], [, v2]) => v2.length - v1.length); return { likesByUser, mostBoosted, mostMentioned, }; }33:T53e,archive = { try { if (archiveFile.length > 1) { // Multiple files uploaded return await archiveFile.reduce(async (ac, cur) => { const [label] = cur.name.split("."); return { ...(await ac), [label]: await cur.json() }; }, Promise.resolve({})); } else { // Single file uploaded const [tarFile] = archiveFile; if (tarFile._.type === "application/json") { // JSON file return { outbox: await tarFile.json() }; } else { // tar.gz file const file = await tarFile.arrayBuffer(); const { buffer } = pako.ungzip(file); console.log(buffer); const archive = await tar(buffer); console.log(archive); return ["outbox", "likes"].reduce((ac, cur) => { const outbox = archive.find((d) => d.name === `${cur}.json`); if (!outbox) return ac; const dv = new DataView(outbox.buffer); const decoder = new TextDecoder("utf-8"); const data = decoder.decode(dv); return { ...ac, [cur]: JSON.parse(data) }; }, {}); } } } catch (e) { console.error(e); throw new Error(`Error parsing archive file! Please send the following stack trace to the @andi@nuklear.family! ----ERROR---- ${e} ${navigator.userAgent} ----/ERROR---- `); } }34:[] 2f:{"id":"a027b32e579c0a7d","slug":"mastodon-archive-tool","title":"Mastodon Archive Tool","thumbnail":"41d22b67c8a9d6fa4b84a0c7c366a9e4ccda719a1ad680683058e339d067d147","access_level":"public","create_time":"$D2018-12-18T17:46:54.634Z","update_time":"$D2024-03-08T18:54:54.932Z","view_time":null,"first_public_time":"$D2018-12-18T18:34:10.456Z","fork":false,"stars":5,"starred":false,"owner":{"type":"team","id":"d415b54b94322f53","login":"nuklearfiziks","name":"Andi","avatar_url":"https://avatars-next.observableusercontent.com/e9f23a21ec8ffbb11cc96e2be11a2d708c7fc98b5f5b86653dc2c9194fd8b4f2","tier":"starter_2024"},"version":445,"publish_version":null,"role":null,"authored":false,"authors":[{"type":"individual","id":"180d402767078a29","login":"nuklearfiziks","name":"Andi","avatar_url":"https://avatars-next.observableusercontent.com/e9f23a21ec8ffbb11cc96e2be11a2d708c7fc98b5f5b86653dc2c9194fd8b4f2","tier":null}],"members":[{"type":"individual","id":"180d402767078a29","login":"nuklearfiziks","name":"Andi","avatar_url":"https://avatars-next.observableusercontent.com/e9f23a21ec8ffbb11cc96e2be11a2d708c7fc98b5f5b86653dc2c9194fd8b4f2","tier":null,"role":"editor"}],"comments":[],"custom_thumbnail":false,"trashed":false,"subscribed":null,"forks":7,"collection":{"id":"316b7d43e1449daa","slug":"mastodon-tools","title":"Mastodon Tools","owner":{"id":"d415b54b94322f53","login":"nuklearfiziks","name":"Andi"}},"type":"notebook","body":{"title":"Mastodon Archive Tool","cells":[{"id":0,"value":"md`# Mastodon Archive Tool\nSelect your Mastodon archive using the button below to be able to easily search through it! ✨\n\n_Please note, ObservableHQ doesn't actually upload any data when you choose a file below; it all remains in your browser!_\n\n## To get your Mastodon archive:\n\n1. Go to *Preferences* ➡ *Data export* ➡ *Request your archive*\n2. Download your archive\n3. Choose the entire .tar.gz file below\n\n### Having issues?\n\nI've had issues reported for larger archives (>4gb). If this is the case and you're getting the red error text, one option is to extract your archive and _only_ upload the *outbox.json* and *likes.json* files (hold ctrl/cmd when selecting files in the dialogue).\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":2,"value":"viewof archiveFile = Inputs.file({label: \"Archive file\", accept: \".json,.tar,.gz\", required: true, multiple: true})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":18,"value":"{console.log(archive)\n if (!archive)\n return html`

Please use the button above to upload your archive.tar.gz file

`;\n\n if (!archive.outbox) return html`

No outbox detected, something's not right... :(

`\n \n const { outbox } = archive;\n // Populate index\n outbox.orderedItems\n .filter((d) => d.type === \"Create\")\n .forEach(({ object }) => {\n object.content = striptags(object.content);\n index.addDoc(object);\n });\n\n return html`Toots loaded: ${outbox.totalItems}`;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":34,"value":"viewof query = html`${archiveFile ? `` : ''}`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":194,"value":"query && results.length ? html`

Results for \"${query}\": ${results.length}

` : html``","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":62,"value":"{\n if (query && results.length) return formatTable(results) \n else if (!query && (Object.values(index.documentStore.docs).length > 0)) \n return formatTable(Object.values(index.documentStore.docs).sort((a, b) => new Date(b.published) - new Date(a.published)));\n else if (query && results.length === 0) return html`

No results for \"${query}\"

` \n\n return html``;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":434,"value":"formatTable = (results) => table(results.map(({published, id, summary, content, tag}) => \n ({published, id, summary, content: {content, tag}})), {\n sortable: true,\n paged: 25,\n columns: {\n published: {\n title: 'Published date',\n formatter: d => format(new Date(d))\n },\n id: {\n title: 'Link',\n formatter: id => `${id.substr(id.lastIndexOf('/') + 1)}`\n },\n summary: {\n title: 'CW',\n formatter: summary => summary ? decodeHtml(summary) : ''\n },\n content: {\n formatter: ({content: d, tag}) => {\n const emoji = tag.filter(e => e.type === \"Emoji\");\n if (emoji.length) {\n emoji.forEach(e => {\n d = d.replace(new RegExp(e.name, 'g'), ` $\"${e.name}$ `);\n });\n }\n \n return d;\n },\n }\n }\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":276,"value":"$31","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":151,"value":"html`

Changelog

2022-11-18: Added ability to select JSON files; fixed JSON file import.
2022-11-17: Switching to Observable's new file input system, changing versioning to be based off of edit date instead of arbitrary semver. Trying to fix issues with archive >2gb
v7: Fixes fatal bug. Thanks Alex and Eject!!!
v6: Firefox fix. Thanks Eject!! 💚
v5: Stats now work for both Masto archive formats 🤬
v4: Added basic stats 📈
v3: Added custom emoji support 💚💚💚
v2: Now you can just select the entire tar.gz file, your browser will ungzip/untar it for you. 🤓
v1: Inital release.

\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":189,"value":"styles = html`\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":211,"value":"$32","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":66,"value":"decodeHtml = function (html) {\n const txt = DOM.element(\"textarea\");\n txt.innerHTML = html;\n return txt.value;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":3,"value":"$33","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":40,"value":"results = [...(index.search(query))].map(({ref}) => index.documentStore.getDoc(ref));","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":4,"value":"index = elasticlunr(function(){\n this.addField('content');\n this.addField('inReplyTo');\n this.addField('sensitive');\n this.addField('summary');\n this.setRef('url');\n});","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":5,"value":"striptags = require(\"striptags\");","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":6,"value":"elasticlunr = require(\"elasticlunr\");","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":79,"value":"tar = require('js-untar');","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":96,"value":"pako = import(\"https://esm.sh/pako-es\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":181,"value":"timeFormat = require(\"d3-time-format\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":185,"value":"format = timeFormat.timeFormat(\"%c\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":169,"value":"import {table} from \"@tmcw/tables@513\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"}],"files":"$W34","stdlib":"1","titling":"auto"}} 30:"$2f:body"