100 batch failing cause of tx pool i think

yield each
2024-04-12 18:06:14 +10:00 · 2024-04-12 17:24:39 +10:00
47 changed files with 5192 additions and 22378 deletions
@@ -1,6 +0,0 @@
 data/
 node_modules/
 .env
 vision-credentials.json
@@ -1,7 +1,8 @@
 .env
 .venv/
-vision-credentials.json
+gimmeme-d052de2b9472.json
 gimmeme-db7225b3cf31.json
 __pycache__/
 node_modules
@@ -1,21 +0,0 @@
 FROM node:20 as builder
 WORKDIR /app
 COPY . ./
 RUN npm i
 RUN npm run build
 # execution
 FROM node:20
 WORKDIR /app
 COPY --from=builder /app/build /app
 # packages are not bundled in the build because sharp uses native modules
 COPY package.json /app/package.json
 RUN npm i --include prod
 # prisma setup
 COPY ./prisma /app/prisma
 RUN npx prisma generate
 CMD node index.js
@@ -1,336 +0,0 @@
 // index.ts
 import "dotenv/config";
 import pino from "pino";
 import * as Minio from "minio";
 import Vision from "@google-cloud/vision";
 import { PrismaClient } from "@prisma/client";
 import { MeiliSearch } from "meilisearch";
 // src/scraper.ts
 import { setTimeout } from "timers/promises";
 import axios2 from "axios";
 import _2 from "lodash";
 // src/attachments.ts
 import sharp from "sharp";
 import axios from "axios";
 import mime from "mime-types";
 import _ from "lodash";
 var STORAGE_BUCKET = process.env.STORAGE_BUCKET;
 var IMAGE_TYPES = [
  "image/png",
  "image/jpeg",
  "image/webp",
  "image/gif"
 ];
 function isImage(a) {
  return IMAGE_TYPES.includes(a.contentType);
 }
 function objectName(a) {
  if (isImage(a))
    return `${a.memeId}.webp`;
  return `${a.memeId}.${mime.extension(a.contentType)}`;
 }
 async function attachmentService(log, minio, prisma, memes) {
  async function ensureStorageBucketExists() {
    const exists = await minio.bucketExists(STORAGE_BUCKET);
    if (exists)
      return true;
    await minio.makeBucket(STORAGE_BUCKET);
  }
  async function storeAttachment(a) {
    const download = await axios.get(a.url, { responseType: "stream" });
    const stream = () => {
      if (isImage(a)) {
        const converter = sharp().webp();
        download.data.pipe(converter);
        return converter;
      }
      return download.data;
    };
    return minio.putObject(
      STORAGE_BUCKET,
      objectName(a),
      stream(),
      null,
      // hardcode this for now, we upload everything as webp
      { "Content-Type": "image/webp" }
    );
  }
  async function deleteAttachment(a) {
    return minio.removeObject(STORAGE_BUCKET, objectName(a));
  }
  async function process2(a, history) {
    try {
      const results = await prisma.$transaction(async (prisma2) => {
        const meme = memes.fromAttachment(a);
        const dbMeme = await prisma2.meme.upsert({ create: meme, update: meme, where: { id: meme.id } });
        const dbA = await prisma2.attachment.upsert({ create: a, update: a, where: { id: a.id } });
        log.debug({ msg: "pending addition to db", dbMeme });
        const upload = await storeAttachment(a);
        log.debug({ msg: "successfully uploaded", upload });
        await memes.persist(dbMeme);
        log.info(dbMeme, "new meme");
        return { meme: dbMeme, upload, attachment: dbA };
      }, { timeout: 6e4 });
    } catch (e) {
      if (e.meta?.modelName !== "Meme" || e.meta?.target?.[0] !== "attachmentId") {
        log.error(e, "failed to process attachment");
        log.error(_.omit(a, ["vision"]), "failed to process attachment");
      }
      await deleteAttachment(a);
    }
    const newHistory = await prisma.channelHistory.update({ data: history, where: { id: history.id } });
    log.debug({ newHistory }, "updated channel history");
    return true;
  }
  await ensureStorageBucketExists();
  return {
    process: process2
  };
 }
 // src/scraper.ts
 function convertSnowflakeToDate(snowflake) {
  const DISCORD_EPOCH = 14200704e5;
  const milliseconds = global.BigInt(snowflake) >> 22n;
  return new Date(Number(milliseconds) + DISCORD_EPOCH);
 }
 async function scraper(discordAuth, vision, minio, prisma, baseLog, attachments) {
  const headers = {
    "Authorization": discordAuth
  };
  async function fetchChannelMessages(channelId) {
    const url = `https://discord.com/api/v9/channels/${channelId}/messages&limit=100`;
    const res = await axios2.get(url, { headers });
    return res.data;
  }
  async function fetchChannelMessagesAfter(channelId, lastMessageId) {
    const url = `https://discord.com/api/v9/channels/${channelId}/messages?after=${lastMessageId}&limit=100`;
    const res = await axios2.get(url, { headers });
    return res.data;
  }
  async function fetchChannelMessagesBefore(channelId, earliestMessageId) {
    const url = `https://discord.com/api/v9/channels/${channelId}/messages?before=${earliestMessageId}&limit=100`;
    const res = await axios2.get(url, { headers });
    return res.data;
  }
  async function fetchGuildDetails(guildId) {
    const url = `https://discord.com/api/v9/guilds/${guildId}`;
    const res = await axios2.get(url, { headers });
    return _2.omit(res.data, ["emojis", "stickers", "roles", "features"]);
  }
  async function fetchChannel(channelId) {
    const url = `https://discord.com/api/v9/channels/${channelId}`;
    const res = await axios2.get(url, { headers });
    return res.data;
  }
  async function detectText(attachment) {
    if (!IMAGE_TYPES.includes(attachment.contentType))
      return {};
    const annotateRequest = {
      image: {
        source: {
          imageUri: attachment.url
        }
      },
      features: [{ type: "TEXT_DETECTION" }]
    };
    const res = await vision.annotateImage(annotateRequest);
    return res[0] || {};
  }
  async function fetchMissingVision() {
    const attachments2 = await prisma.attachment.findMany({ where: { vision: {}, contentType: { in: IMAGE_TYPES } } });
    baseLog.info({ attachments: attachments2.length }, "missing vision attachments");
  }
  async function processChannel(channelId) {
    const channel = await fetchChannel(channelId);
    const guild = await fetchGuildDetails(channel.guild_id);
    const log = baseLog.child({ guild: guild.name, channel: channel.name, channelId });
    async function filterAttachments(messages) {
      const acceptedContentTypes = [
        ...IMAGE_TYPES
        // ...VIDEO_TYPES,
      ];
      const validAttachments = messages.filter((m) => m.attachments).flatMap((m) => m.attachments.map((a) => [a, m])).filter(([a, m]) => acceptedContentTypes.includes(a.content_type));
      log.debug({ validAttachments: validAttachments.length }, "attachments found in messages");
      return Promise.all(validAttachments.map(async ([a, m]) => {
        const attachment = {
          id: BigInt(a.id),
          msgId: BigInt(m.id),
          channelId: BigInt(m.channel_id),
          url: a.url,
          contentType: a.content_type,
          // create this ahead of time to associate with our copy of the media
          memeId: crypto.randomUUID(),
          vision: {},
          // quick hack so that detectText can receive a full attachment
          guild,
          channel,
          message: m,
          postedAt: convertSnowflakeToDate(a.id),
          // ts asks for these to be included but they don't need to be set
          createdAt: void 0,
          updatedAt: void 0
        };
        return { ...attachment, vision: await detectText(attachment) };
      }));
    }
    async function* fetchNew(channelId2, log2, latestMessageId) {
      const messages = (await fetchChannelMessagesAfter(channelId2, latestMessageId)).reverse();
      if (messages.length === 0) {
        log2.info("reached latest message");
      }
      log2.debug({ messages: messages.length, latestMessageId }, "fetched new messages");
      yield* await filterAttachments(messages);
    }
    async function* fetchOld(channelId2, log2, earliestMessageId) {
      const messages = await fetchChannelMessagesBefore(channelId2, earliestMessageId);
      if (messages.length === 0) {
        log2.info("reached beginning of history");
      }
      log2.debug({ messages: messages.length, earliestMessageId }, "fetched older messages");
      yield* await filterAttachments(messages);
    }
    const ensureHistory = async () => {
      const stored = await prisma.channelHistory.findFirst({ where: { id: channelId } });
      if (stored)
        return stored;
      const lastMessageId = channel.last_message_id;
      return await prisma.channelHistory.create({
        data: { latestMessageId: lastMessageId, earliestMessageId: lastMessageId, id: channelId }
      });
    };
    const history = await ensureHistory();
    async function processLoop() {
      const history2 = await ensureHistory();
      const newAttachments = fetchNew(channelId, log, history2.latestMessageId);
      const oldAttachments = fetchOld(channelId, log, history2.earliestMessageId);
      let oldCount = 0;
      let newCount = 0;
      for await (const attachment of newAttachments) {
        log.debug({ msg: "scraped new attachment", attachment: _2.omit(attachment, ["guild", "message", "channel", "vision"]) });
        const newHistory = { id: history2.id, latestMessageId: attachment.msgId };
        await attachments.process(attachment, newHistory);
        oldCount++;
      }
      for await (const attachment of oldAttachments) {
        log.debug({ msg: "scraped old attachment", attachment: _2.omit(attachment, ["guild", "message", "channel", "vision"]) });
        const newHistory = { id: history2.id, earliestMessageId: attachment.msgId };
        await attachments.process(attachment, newHistory);
        newCount++;
      }
      log.info({ oldCount, newCount }, "processed attachments");
      const shouldWait = newCount === 0 && oldCount === 0;
      const PROCESS_DELAY_MS = 1e3 * 60;
      if (shouldWait) {
        log.info({ PROCESS_DELAY_MS }, "waiting for new messages");
        await setTimeout(PROCESS_DELAY_MS);
      }
      return processLoop();
    }
    await processLoop();
  }
  return {
    processChannel
  };
 }
 // src/memes.ts
 import _3 from "lodash";
 var STORAGE_BUCKET2 = process.env.STORAGE_BUCKET;
 function memeUrl(a) {
  const STORAGE_URL = process.env.STORAGE_URL;
  const u = new URL(`${STORAGE_BUCKET2}/${objectName(a)}`, `https://${STORAGE_URL}`);
  return u.href;
 }
 async function memeService(baseLog, prisma, meili) {
  const log = baseLog.child({ service: "meme" });
  function fromAttachment(a) {
    const text = a.vision.fullTextAnnotation?.text || "";
    const tags = [
      a.guild.name,
      a.channel.name,
      a.message.author.username
    ];
    const m = {
      id: a.memeId,
      url: memeUrl(a),
      text,
      tags,
      attachmentId: a.id,
      postedAt: a.postedAt,
      createdAt: void 0,
      updatedAt: void 0
    };
    return m;
  }
  async function ensureMeiliIndex() {
    const task = await meili.createIndex("memes", { primaryKey: "id" });
    const result = await meili.waitForTask(task.taskUid);
    log.debug(result);
    const index = await meili.index("memes");
    await index.updateSortableAttributes(["postedAt"]);
    return index;
  }
  async function resetMeili() {
    const delTask = await meili.deleteIndex("memes");
    const delResult = await meili.waitForTask(delTask.taskUid);
    const index = await ensureMeiliIndex();
    const memes = (await prisma.meme.findMany()).map((m) => ({ ...m, postedAt: m.postedAt.valueOf() }));
    for await (const batch of _3.chunk(memes, 1e3)) {
      const task = await index.updateDocuments(batch);
      const res = await meili.waitForTask(task.taskUid);
      log.info({ res }, "added meme batch");
    }
  }
  async function persist(m) {
    const index = meili.index("memes");
    const doc = { ...m, postedAt: m.postedAt.valueOf() };
    return index.updateDocuments([doc]);
  }
  await ensureMeiliIndex();
  return {
    ensureMeiliIndex,
    resetMeili,
    fromAttachment,
    persist
  };
 }
 // index.ts
 BigInt.prototype.toJSON = function bigIntStringify() {
  return this.toString();
 };
 async function main() {
  const VISION_CREDENTIALS = (await import(process.env.GOOGLE_APPLICATION_CREDENTIALS, { with: { type: "json" } })).default;
  const log = pino({ base: {} });
  const vision = new Vision.ImageAnnotatorClient({ credentials: VISION_CREDENTIALS });
  const prisma = new PrismaClient();
  const minio = new Minio.Client({
    endPoint: process.env.STORAGE_URL,
    accessKey: process.env.STORAGE_ACCESS_KEY,
    secretKey: process.env.STORAGE_SECRET_KEY
  });
  const meili = new MeiliSearch({
    host: process.env.MEILI_URL,
    apiKey: process.env.MEILI_MASTER_KEY
  });
  const memes = await memeService(log, prisma, meili);
  const attachments = await attachmentService(log, minio, prisma, memes);
  const scraper2 = await scraper(process.env.DISCORD_AUTH, vision, minio, prisma, log, attachments);
  const CHANNEL_IDS = [
    367936426962190336n,
    // TPM shitposts
    367936467592413194n,
    // tpm screenshots
    1028511952277864501n,
    // tpm sludge
    725835129326665768n,
    // machinegirl memes
    1095060717117374687n
    // aella memes
  ];
  await Promise.all(CHANNEL_IDS.map((id) => scraper2.processChannel(id)));
 }
 main().then(() => true).catch((e) => console.error(e));
@@ -1,68 +0,0 @@
 import "dotenv/config"
 import fs from 'fs/promises'
 import { exec as execCb } from 'child_process'
 import { promisify } from 'util'
 import pino from 'pino'
 import * as Minio from 'minio'
 import Vision from '@google-cloud/vision'
 import { PrismaClient } from '@prisma/client'
 import { MeiliSearch } from 'meilisearch'
 import discordScraper from './src/scraper'
 import attachmentService from "./src/attachments"
 import memeService from "./src/memes"
 // @ts-ignore - ts don't know wtf it talking about
 BigInt.prototype.toJSON = function bigIntStringify() {
    return this.toString();
 };
 const exec = promisify(execCb)
 async function main() {
    const VISION_CREDENTIALS = (await import(process.env.GOOGLE_APPLICATION_CREDENTIALS, { with: { type: "json" } })).default
    const log = pino({ base: {} });
    const vision = new Vision.ImageAnnotatorClient({ credentials: VISION_CREDENTIALS })
    const prisma = new PrismaClient()
    const minio = new Minio.Client({
        endPoint: process.env.STORAGE_URL,
        accessKey: process.env.STORAGE_ACCESS_KEY,
        secretKey: process.env.STORAGE_SECRET_KEY,
    })
    const meili = new MeiliSearch({
      host: process.env.MEILI_URL,
      apiKey: process.env.MEILI_MASTER_KEY,
    })
    const memes = await memeService(log, prisma, meili)
    const attachments = await attachmentService(log, minio, prisma, memes)
    const scraper = await discordScraper(process.env.DISCORD_AUTH, vision, minio, prisma, log, attachments)
    const CHANNEL_IDS = [
        367936426962190336n,  // TPM shitposts
        367936467592413194n,  // tpm screenshots
        1028511952277864501n,  // tpm sludge
        725835129326665768n, // machinegirl memes
        1095060717117374687n, // aella memes
    ]
    async function migrateDb() {
        const output = await exec('prisma migrate deploy')
        log.info(output)
    }
    await migrateDb()
    await Promise.all(CHANNEL_IDS.map(id => scraper.processChannel(id)))
 }
 main()
    .then(() => true)
    .catch(e => console.error(e))
@@ -1,25 +0,0 @@
 /*
  Warnings:
  - Added the required column `postedAt` to the `attachments` table without a default value. This is not possible if the table is not empty.
  - Added the required column `timestamp` to the `memes` table without a default value. This is not possible if the table is not empty.
 */
 -- AlterTable
 ALTER TABLE "attachments"
  ADD COLUMN     "postedAt"
  TIMESTAMP(3);
 UPDATE "attachments"
  set "postedAt" = TIMESTAMP 'epoch' + ((id >> 22) + 1420070400000) * INTERVAL '1 millisecond';
 -- AlterTable
 ALTER TABLE "memes"
  ADD COLUMN     "postedAt"
  TIMESTAMP(3);
 UPDATE "memes"
  set "postedAt" = TIMESTAMP 'epoch' + (("attachmentId" >> 22) + 1420070400000) * INTERVAL '1 millisecond';
 ALTER TABLE "attachments" ALTER COLUMN "postedAt" SET NOT NULL;
 ALTER TABLE "memes" ALTER COLUMN "postedAt" SET NOT NULL;
@@ -1,25 +0,0 @@
 # See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
 # dependencies
 /node_modules
 /.pnp
 .pnp.js
 # testing
 /coverage
 # production
 /build
 # misc
 .DS_Store
 .env.local
 .env.development.local
 .env.test.local
 .env.production.local
 npm-debug.log*
 yarn-debug.log*
 yarn-error.log*
 .env
@@ -1,13 +0,0 @@
 # build step
 FROM node:20 AS build-env
 WORKDIR /app
 COPY . ./
 RUN npm i
 RUN npm run build
 # static server
 FROM nginx
 WORKDIR /srv/app
 COPY --from=build-env /app/build /srv/app
 COPY ./nginx.conf /etc/nginx/nginx.conf
@@ -1,70 +0,0 @@
 # Getting Started with Create React App
 This project was bootstrapped with [Create React App](https://github.com/facebook/create-react-app).
 ## Available Scripts
 In the project directory, you can run:
 ### `npm start`
 Runs the app in the development mode.\
 Open [http://localhost:3000](http://localhost:3000) to view it in your browser.
 The page will reload when you make changes.\
 You may also see any lint errors in the console.
 ### `npm test`
 Launches the test runner in the interactive watch mode.\
 See the section about [running tests](https://facebook.github.io/create-react-app/docs/running-tests) for more information.
 ### `npm run build`
 Builds the app for production to the `build` folder.\
 It correctly bundles React in production mode and optimizes the build for the best performance.
 The build is minified and the filenames include the hashes.\
 Your app is ready to be deployed!
 See the section about [deployment](https://facebook.github.io/create-react-app/docs/deployment) for more information.
 ### `npm run eject`
 **Note: this is a one-way operation. Once you `eject`, you can't go back!**
 If you aren't satisfied with the build tool and configuration choices, you can `eject` at any time. This command will remove the single build dependency from your project.
 Instead, it will copy all the configuration files and the transitive dependencies (webpack, Babel, ESLint, etc) right into your project so you have full control over them. All of the commands except `eject` will still work, but they will point to the copied scripts so you can tweak them. At this point you're on your own.
 You don't have to ever use `eject`. The curated feature set is suitable for small and middle deployments, and you shouldn't feel obligated to use this feature. However we understand that this tool wouldn't be useful if you couldn't customize it when you are ready for it.
 ## Learn More
 You can learn more in the [Create React App documentation](https://facebook.github.io/create-react-app/docs/getting-started).
 To learn React, check out the [React documentation](https://reactjs.org/).
 ### Code Splitting
 This section has moved here: [https://facebook.github.io/create-react-app/docs/code-splitting](https://facebook.github.io/create-react-app/docs/code-splitting)
 ### Analyzing the Bundle Size
 This section has moved here: [https://facebook.github.io/create-react-app/docs/analyzing-the-bundle-size](https://facebook.github.io/create-react-app/docs/analyzing-the-bundle-size)
 ### Making a Progressive Web App
 This section has moved here: [https://facebook.github.io/create-react-app/docs/making-a-progressive-web-app](https://facebook.github.io/create-react-app/docs/making-a-progressive-web-app)
 ### Advanced Configuration
 This section has moved here: [https://facebook.github.io/create-react-app/docs/advanced-configuration](https://facebook.github.io/create-react-app/docs/advanced-configuration)
 ### Deployment
 This section has moved here: [https://facebook.github.io/create-react-app/docs/deployment](https://facebook.github.io/create-react-app/docs/deployment)
 ### `npm run build` fails to minify
 This section has moved here: [https://facebook.github.io/create-react-app/docs/troubleshooting#npm-run-build-fails-to-minify](https://facebook.github.io/create-react-app/docs/troubleshooting#npm-run-build-fails-to-minify)
@@ -1,49 +0,0 @@
 events {
    worker_connections 1024;
 }
 http {
    include mime.types;
    sendfile on;
    server {
        listen 8080;
        listen [::]:8080;
        autoindex off;
        root /srv/app;
        gzip on;
        gzip_disable "msie6";
        gzip_vary on;
        gzip_proxied any;
        gzip_comp_level 6;
        gzip_buffers 16 8k;
        gzip_http_version 1.1;
        gzip_min_length 256;
        gzip_types
            application/atom+xml
            application/geo+json
            application/javascript
            application/x-javascript
            application/json
            application/ld+json
            application/manifest+json
            application/rdf+xml
            application/rss+xml
            application/xhtml+xml
            application/xml
            font/eot
            font/otf
            font/ttf
            image/svg+xml
            text/css
            text/javascript
            text/plain
            text/xml;
        error_page 404 /;
    }
 }
@@ -1,42 +0,0 @@
 {
  "name": "memestream-client",
  "version": "0.1.0",
  "private": true,
  "dependencies": {
    "@meilisearch/instant-meilisearch": "^0.17.0",
    "@testing-library/jest-dom": "^5.17.0",
    "@testing-library/react": "^13.4.0",
    "@testing-library/user-event": "^13.5.0",
    "instantsearch.css": "^8.1.0",
    "react": "^18.2.0",
    "react-dom": "^18.2.0",
    "react-instantsearch": "^7.7.1",
    "react-scripts": "5.0.1",
    "web-vitals": "^2.1.4"
  },
  "scripts": {
    "start": "react-scripts start",
    "build": "react-scripts build",
    "test": "react-scripts test",
    "eject": "react-scripts eject",
    "deploy": "docker build . -t registry.strix.systems/memestream-client && docker push registry.strix.systems/memestream-client && kubectl rollout restart deployment memestream-client"
  },
  "eslintConfig": {
    "extends": [
      "react-app",
      "react-app/jest"
    ]
  },
  "browserslist": {
    "production": [
      ">0.2%",
      "not dead",
      "not op_mini all"
    ],
    "development": [
      "last 1 chrome version",
      "last 1 firefox version",
      "last 1 safari version"
    ]
  }
 }
@@ -1,43 +0,0 @@
 <!DOCTYPE html>
 <html lang="en">
  <head>
    <meta charset="utf-8" />
    <link rel="icon" href="%PUBLIC_URL%/favicon.ico" />
    <meta name="viewport" content="width=device-width, initial-scale=1" />
    <meta name="theme-color" content="#000000" />
    <meta
      name="description"
      content="Search memes by text"
    />
    <link rel="apple-touch-icon" href="%PUBLIC_URL%/logo192.png" />
    <!--
      manifest.json provides metadata used when your web app is installed on a
      user's mobile device or desktop. See https://developers.google.com/web/fundamentals/web-app-manifest/
    -->
    <link rel="manifest" href="%PUBLIC_URL%/manifest.json" />
    <!--
      Notice the use of %PUBLIC_URL% in the tags above.
      It will be replaced with the URL of the `public` folder during the build.
      Only files inside the `public` folder can be referenced from the HTML.
      Unlike "/favicon.ico" or "favicon.ico", "%PUBLIC_URL%/favicon.ico" will
      work correctly both with client-side routing and a non-root public URL.
      Learn how to configure a non-root public URL by running `npm run build`.
    -->
    <title>MemeStream</title>
  </head>
  <body>
    <noscript>You need to enable JavaScript to run this app.</noscript>
    <div id="root"></div>
    <!--
      This HTML file is a template.
      If you open it directly in the browser, you will see an empty page.
      You can add webfonts, meta tags, or analytics to this file.
      The build step will place the bundled scripts into the <body> tag.
      To begin the development, run `npm start` or `yarn start`.
      To create a production bundle, use `npm run build` or `yarn build`.
    -->
  </body>
 </html>
@@ -1,25 +0,0 @@
 {
  "short_name": "React App",
  "name": "Create React App Sample",
  "icons": [
    {
      "src": "favicon.ico",
      "sizes": "64x64 32x32 24x24 16x16",
      "type": "image/x-icon"
    },
    {
      "src": "logo192.png",
      "type": "image/png",
      "sizes": "192x192"
    },
    {
      "src": "logo512.png",
      "type": "image/png",
      "sizes": "512x512"
    }
  ],
  "start_url": ".",
  "display": "standalone",
  "theme_color": "#000000",
  "background_color": "#ffffff"
 }
@@ -1,3 +0,0 @@
 # https://www.robotstxt.org/robotstxt.html
 User-agent: *
 Disallow:
@@ -1,172 +0,0 @@
 :root {
  --colour-fg:    rgb(158, 149, 137);
  --colour-bg:    #1a1c1d;
  --colour-bg-dark: #131516;
  --colour-gray:  rgb(60, 65, 68);
  --colour-pink:  rgb(238, 48, 112);
  --colour-pink:  rgb(238, 48, 112);
 }
 html {
  font-family: sans-serif;
  padding: 1em;
  font-size: 16px;
  color: var(--colour-fg);
  background-color: var(--colour-bg);
 }
 h1 {
  color: var(--colour-pink);
  font-size: 3rem;
 }
 /* reset the fonts on all this shit*/
 [class^="ais-"] {
  font-size: unset;
 }
 .ais-ClearRefinements {
  margin: 1em 0;
 }
 .ais-SearchBox {
  margin: 1rem 0;
  font-size: 2rem;
 }
 .ais-Pagination {
  margin-top: 1em;
 }
 .ais-InstantSearch {
  padding: 0 3rem;
  overflow: hidden;
  margin: 0 auto;
 }
 .ais-Hits-list, .ais-InfiniteHits-list {
  display: grid;
  grid-template-columns: repeat(2, 1fr);
  grid-gap: 0.5rem;
 }
 .ais-InfiniteHits-item, .ais-InfiniteResults-item, .ais-Hits-item, .ais-Results-item {
  flex: 1;
  background-color: var(--colour-bg-dark);
  border-radius: 0.5rem;
  border: 1px solid var(--colour-gray);
  width: unset;
  box-shadow: none;
  padding: 1rem;
 }
 .ais-Hits-item img, .ais-InfiniteHits-item img {
  margin-right: 1em;
  margin-bottom: 0.5em;
  max-height: 40rem;
  max-width: 100%;
 }
 .hit {
  font-size: 1.25rem;
  display: grid;
  grid-template-areas:
    "img"
    "info"
    "text";
  align-content: flex-start;
  align-items: flex-start;
  justify-content: flex-start;
  height: 100%;
 }
 .hit .img {
  grid-area: img;
  display: grid;
  justify-content: center;
 }
 .hit .info {
  font-weight: bold;
  grid-area: info;
  margin: 2rem 0;
 }
 .hit .text {
 }
 .ais-SearchBox-input {
  height: 4rem;
  width: 100%;
  padding-left: 3rem;
  padding-right: 0.5rem;
  background-position: left 1rem top 50%;
  background-color: #131516;
  border-color: var(--colour-gray);
  border-width: 1px;
  border-style: solid;
  border-radius: 0.5rem;
  outline: none;
  outline-color: currentcolor;
  color: var(--colour-fg);
  font-weight: 500;
  line-height: 22px;
 }
 .ais-SearchBox-input:hover {
  border-color: var(--colour-pink);
 }
 .ais-Highlight-highlighted, .ais-Snippet-highlighted {
  background-color: var(--colour-pink);
 }
 .ais-Breadcrumb, .ais-ClearRefinements, .ais-CurrentRefinements, .ais-GeoSearch, .ais-HierarchicalMenu, .ais-Hits, .ais-Results, .ais-HitsPerPage, .ais-ResultsPerPage, .ais-InfiniteHits, .ais-InfiniteResults, .ais-Menu, .ais-MenuSelect, .ais-NumericMenu, .ais-NumericSelector, .ais-Pagination, .ais-Panel, .ais-PoweredBy, .ais-RangeInput, .ais-RangeSlider, .ais-RatingMenu, .ais-RefinementList, .ais-SearchBox, .ais-RelevantSort, .ais-SortBy, .ais-Stats, .ais-ToggleRefinement {
  color: rgb(158, 149, 137)
 }
 .ais-SearchBox-submit{
  left: 1rem;
 }
 .ais-SearchBox-reset {
  right: 1rem;
 }
 .ais-SearchBox-submitIcon path, .ais-SearchBox-resetIcon path {
  fill: var(--colour-fg);
  color: var(--colour-fg);
 }
 .ais-Breadcrumb-link, .ais-HierarchicalMenu-link, .ais-Menu-link, .ais-Pagination-link, .ais-RatingMenu-link
 .ais-Breadcrumb-link:hover, .ais-HierarchicalMenu-link:hover, .ais-Menu-link:hover, .ais-Pagination-link:hover, .ais-RatingMenu-link:hover {
  color: var(--colour-pink);
 }
 .ais-Pagination-item--selected .ais-Pagination-link, .ais-InfiniteHits-loadMore {
  background-color: var(--colour-pink);
  border-color: var(--colour-pink);
  color: white;
 /*  color: var(--colour-fg);*/
 }
 .ais-ClearRefinements-button:hover, .ais-ClearRefinements-button:focus, .ais-CurrentRefinements-reset:hover, .ais-CurrentRefinements-reset:focus, .ais-GeoSearch-redo:hover, .ais-GeoSearch-redo:focus, .ais-GeoSearch-reset:hover, .ais-GeoSearch-reset:focus, .ais-HierarchicalMenu-showMore:hover, .ais-HierarchicalMenu-showMore:focus, .ais-InfiniteHits-loadPrevious:hover, .ais-InfiniteHits-loadPrevious:focus, .ais-InfiniteHits-loadMore:hover, .ais-InfiniteHits-loadMore:focus, .ais-InfiniteResults-loadMore:hover, .ais-InfiniteResults-loadMore:focus, .ais-Menu-showMore:hover, .ais-Menu-showMore:focus, .ais-RefinementList-showMore:hover, .ais-RefinementList-showMore:focus, .ais-RelevantSort-button:hover, .ais-RelevantSort-button:focus {
  background-color: var(--colour-pink);
  border-color: white;
 }
 .ais-SortBy {
  display: none;
 }
@media (max-width:900px)  {
  .ais-InstantSearch {
    padding: 0;
  }
  .ais-Hits-list {
    grid-template-columns: 1fr;
  }
 }
@@ -1,76 +0,0 @@
 import "instantsearch.css/themes/algolia-min.css";
 import React from "react";
 import {
  InstantSearch,
  SearchBox,
  Highlight,
  SortBy,
  InfiniteHits,
 } from "react-instantsearch";
 import "./App.css";
 import { instantMeiliSearch } from "@meilisearch/instant-meilisearch";
 import { convertSnowflakeToDate } from "./util";
 const { searchClient } = instantMeiliSearch(
  "https://search.memestream.strix.systems",
  "ef006ab414a12b49eb797e0637219d5d6bcf3c84b8195c9fac49f2629713705a",
  {
    finitePagination: false,
    placeholderSearch: true,
  }
 );
 const placeholders = [
  "we're so back",
  "it's so over",
  'freud',
  'hegel',
  'satire',
  'literally me',
  'rake',
  'we are not the same',
  'anarchy',
  'goblin',
  'wise'
 ]
 // <SortBy items={[
 //   { label: 'Latest', value: 'memes:attachmentId:desc'}
 // ]} />
 const placeholder = placeholders[Math.floor(Math.random() * placeholders.length)]
 const initialUiState= {
  memes: {
    query: '',
    sortBy: 'memes:postedAt:desc',
 }
 }
 const App = () => (
  <div className="ais-InstantSearch">
    <h1>MemeStream</h1>
    <InstantSearch indexName="memes" searchClient={searchClient} initialUiState={initialUiState} >
      <SearchBox autoFocus placeholder={placeholder}/>
      <InfiniteHits hitComponent={Hit} />
      <SortBy items={[{ label: 'Latest', value: 'memes:attachmentId:desc'}]} />
    </InstantSearch>
  </div>
 );
 const Hit = ({ hit }) => (
  <div class="hit" key={hit.id}>
    <a href={hit.url} class="img" target="_blank" rel="noreferrer">
      <img src={hit.url} alt={hit.text} />
    </a>
    <div className="info">
      <div>{hit.tags[0]} #{hit.tags[1]} @{hit.tags[2]}</div>
      <div>{convertSnowflakeToDate(hit.attachmentId).toLocaleString()}</div>
    </div>
    <Highlight className="text" attribute="text" hit={hit} />
  </div>
 );
 export default App;
@@ -1,8 +0,0 @@
 import { render, screen } from '@testing-library/react';
 import App from './App';
 test('renders learn react link', () => {
  render(<App />);
  const linkElement = screen.getByText(/learn react/i);
  expect(linkElement).toBeInTheDocument();
 });
@@ -1,13 +0,0 @@
 body {
  margin: 0;
  font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', 'Roboto', 'Oxygen',
    'Ubuntu', 'Cantarell', 'Fira Sans', 'Droid Sans', 'Helvetica Neue',
    sans-serif;
  -webkit-font-smoothing: antialiased;
  -moz-osx-font-smoothing: grayscale;
 }
 code {
  font-family: source-code-pro, Menlo, Monaco, Consolas, 'Courier New',
    monospace;
 }
@@ -1,17 +0,0 @@
 import React from 'react';
 import ReactDOM from 'react-dom/client';
 import './index.css';
 import App from './App';
 import reportWebVitals from './reportWebVitals';
 const root = ReactDOM.createRoot(document.getElementById('root'));
 root.render(
  <React.StrictMode>
    <App />
  </React.StrictMode>
 );
 // If you want to start measuring performance in your app, pass a function
 // to log results (for example: reportWebVitals(console.log))
 // or send to an analytics endpoint. Learn more: https://bit.ly/CRA-vitals
 reportWebVitals();
@@ -1 +0,0 @@
 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 841.9 595.3"><g fill="#61DAFB"><path d="M666.3 296.5c0-32.5-40.7-63.3-103.1-82.4 14.4-63.6 8-114.2-20.2-130.4-6.5-3.8-14.1-5.6-22.4-5.6v22.3c4.6 0 8.3.9 11.4 2.6 13.6 7.8 19.5 37.5 14.9 75.7-1.1 9.4-2.9 19.3-5.1 29.4-19.6-4.8-41-8.5-63.5-10.9-13.5-18.5-27.5-35.3-41.6-50 32.6-30.3 63.2-46.9 84-46.9V78c-27.5 0-63.5 19.6-99.9 53.6-36.4-33.8-72.4-53.2-99.9-53.2v22.3c20.7 0 51.4 16.5 84 46.6-14 14.7-28 31.4-41.3 49.9-22.6 2.4-44 6.1-63.6 11-2.3-10-4-19.7-5.2-29-4.7-38.2 1.1-67.9 14.6-75.8 3-1.8 6.9-2.6 11.5-2.6V78.5c-8.4 0-16 1.8-22.6 5.6-28.1 16.2-34.4 66.7-19.9 130.1-62.2 19.2-102.7 49.9-102.7 82.3 0 32.5 40.7 63.3 103.1 82.4-14.4 63.6-8 114.2 20.2 130.4 6.5 3.8 14.1 5.6 22.5 5.6 27.5 0 63.5-19.6 99.9-53.6 36.4 33.8 72.4 53.2 99.9 53.2 8.4 0 16-1.8 22.6-5.6 28.1-16.2 34.4-66.7 19.9-130.1 62-19.1 102.5-49.9 102.5-82.3zm-130.2-66.7c-3.7 12.9-8.3 26.2-13.5 39.5-4.1-8-8.4-16-13.1-24-4.6-8-9.5-15.8-14.4-23.4 14.2 2.1 27.9 4.7 41 7.9zm-45.8 106.5c-7.8 13.5-15.8 26.3-24.1 38.2-14.9 1.3-30 2-45.2 2-15.1 0-30.2-.7-45-1.9-8.3-11.9-16.4-24.6-24.2-38-7.6-13.1-14.5-26.4-20.8-39.8 6.2-13.4 13.2-26.8 20.7-39.9 7.8-13.5 15.8-26.3 24.1-38.2 14.9-1.3 30-2 45.2-2 15.1 0 30.2.7 45 1.9 8.3 11.9 16.4 24.6 24.2 38 7.6 13.1 14.5 26.4 20.8 39.8-6.3 13.4-13.2 26.8-20.7 39.9zm32.3-13c5.4 13.4 10 26.8 13.8 39.8-13.1 3.2-26.9 5.9-41.2 8 4.9-7.7 9.8-15.6 14.4-23.7 4.6-8 8.9-16.1 13-24.1zM421.2 430c-9.3-9.6-18.6-20.3-27.8-32 9 .4 18.2.7 27.5.7 9.4 0 18.7-.2 27.8-.7-9 11.7-18.3 22.4-27.5 32zm-74.4-58.9c-14.2-2.1-27.9-4.7-41-7.9 3.7-12.9 8.3-26.2 13.5-39.5 4.1 8 8.4 16 13.1 24 4.7 8 9.5 15.8 14.4 23.4zM420.7 163c9.3 9.6 18.6 20.3 27.8 32-9-.4-18.2-.7-27.5-.7-9.4 0-18.7.2-27.8.7 9-11.7 18.3-22.4 27.5-32zm-74 58.9c-4.9 7.7-9.8 15.6-14.4 23.7-4.6 8-8.9 16-13 24-5.4-13.4-10-26.8-13.8-39.8 13.1-3.1 26.9-5.8 41.2-7.9zm-90.5 125.2c-35.4-15.1-58.3-34.9-58.3-50.6 0-15.7 22.9-35.6 58.3-50.6 8.6-3.7 18-7 27.7-10.1 5.7 19.6 13.2 40 22.5 60.9-9.2 20.8-16.6 41.1-22.2 60.6-9.9-3.1-19.3-6.5-28-10.2zM310 490c-13.6-7.8-19.5-37.5-14.9-75.7 1.1-9.4 2.9-19.3 5.1-29.4 19.6 4.8 41 8.5 63.5 10.9 13.5 18.5 27.5 35.3 41.6 50-32.6 30.3-63.2 46.9-84 46.9-4.5-.1-8.3-1-11.3-2.7zm237.2-76.2c4.7 38.2-1.1 67.9-14.6 75.8-3 1.8-6.9 2.6-11.5 2.6-20.7 0-51.4-16.5-84-46.6 14-14.7 28-31.4 41.3-49.9 22.6-2.4 44-6.1 63.6-11 2.3 10.1 4.1 19.8 5.2 29.1zm38.5-66.7c-8.6 3.7-18 7-27.7 10.1-5.7-19.6-13.2-40-22.5-60.9 9.2-20.8 16.6-41.1 22.2-60.6 9.9 3.1 19.3 6.5 28.1 10.2 35.4 15.1 58.3 34.9 58.3 50.6-.1 15.7-23 35.6-58.4 50.6zM320.8 78.4z"/><circle cx="420.9" cy="296.5" r="45.7"/><path d="M520.5 78.1z"/></g></svg>
@@ -1,13 +0,0 @@
 const reportWebVitals = onPerfEntry => {
  if (onPerfEntry && onPerfEntry instanceof Function) {
    import('web-vitals').then(({ getCLS, getFID, getFCP, getLCP, getTTFB }) => {
      getCLS(onPerfEntry);
      getFID(onPerfEntry);
      getFCP(onPerfEntry);
      getLCP(onPerfEntry);
      getTTFB(onPerfEntry);
    });
  }
 };
 export default reportWebVitals;
@@ -1,5 +0,0 @@
 // jest-dom adds custom jest matchers for asserting on DOM nodes.
 // allows you to do things like:
 // expect(element).toHaveTextContent(/react/i)
 // learn more: https://github.com/testing-library/jest-dom
 import '@testing-library/jest-dom';
@@ -1,9 +0,0 @@
 export const DISCORD_EPOCH = 1420070400000
 // Converts a snowflake ID string into a JS Date object using the provided epoch (in ms), or Discord's epoch if not provided
 export function convertSnowflakeToDate(snowflake, epoch = DISCORD_EPOCH) {
    // Convert snowflake to BigInt to extract timestamp bits
    // https://discord.com/developers/docs/reference#snowflakes
    const milliseconds = global.BigInt(snowflake) >> 22n
    return new Date(Number(milliseconds) + epoch)
 }
@@ -12,6 +12,15 @@ services:
    volumes:
      - "./data/pg:/var/lib/postgresql/data"
  redis:
    image: redis:latest
    ports:
      - '6379:6379'
    command: ['redis-server', '/usr/local/etc/redis/redis.conf']
    volumes:
      - "./data/redis:/data"
      - "./redis.conf:/usr/local/etc/redis/redis.conf"
  meili:
    image: getmeili/meilisearch:v1.7
    ports:
@@ -33,13 +42,17 @@ services:
      MINIO_ROOT_USER: '${MINIO_ROOT_USER}'
      MINIO_ROOT_PASSWORD: '${MINIO_ROOT_PASSWORD}'
-  archiver:
+  # meilisync:
-    build: ./archiver
+  #   platform: linux/x86_64
-    volumes:
+  #   image: long2ice/meilisync
-      - './.env:/app/.env'
+  #   volumes:
-      - './archiver/vision-credentials.json:/app/vision-credentials.json'
+  #     - ./config.yml:/meilisync/config.yml
-  client:
+  # nginx:
-    build: ./client
+  #   image: nginx:latest
-    ports:
+  #   depends_on:
-      - 8080:8080
+  #     - 'api'
  #   volumes:
  #     - './nginx/localhost.nginx.conf:/etc/nginx/conf.d/default.conf'
  #   ports:
  #     - '80:80'
@@ -0,0 +1,54 @@
 import "dotenv/config"
 import fs from 'fs/promises'
 import pino from 'pino'
 import * as Minio from 'minio'
 import Vision from '@google-cloud/vision'
 import { PrismaClient } from '@prisma/client'
 import { MeiliSearch } from 'meilisearch'
 import discordScraper from './src/scraper'
 import testAttachment from "./src/test.attachment"
 import attachmentService from "./src/attachments"
 import memeService from "./src/memes"
 // @ts-ignore - ts don't know wtf it talking about
 BigInt.prototype.toJSON = function bigIntStringify() {
    return this.toString();
 };
 const VISION_CREDENTIALS = (await import(process.env.GOOGLE_APPLICATION_CREDENTIALS, { assert: { type: "json" } })).default
 const log = pino({ base: {} });
 const vision = new Vision.ImageAnnotatorClient({ credentials: VISION_CREDENTIALS })
 const prisma = new PrismaClient()
 const minio = new Minio.Client({
    endPoint: process.env.STORAGE_URL,
    accessKey: process.env.STORAGE_ACCESS_KEY,
    secretKey: process.env.STORAGE_SECRET_KEY,
 })
 const meili = new MeiliSearch({
  host: process.env.MEILI_URL,
  apiKey: process.env.MEILI_MASTER_KEY,
 })
 const memes = await memeService(log, prisma, meili)
 const attachments = await attachmentService(log, minio, prisma, memes)
 const scraper = discordScraper(process.env.DISCORD_AUTH, vision, minio, prisma, log, attachments, memes)
 const CHANNEL_IDS = [
    367936426962190336n,  // TPM shitposts
    1095060717117374687n, // aella memes
 ]
 async function main() {
    await Promise.all(CHANNEL_IDS.map(id => scraper.processChannel(id)))
    await memes.updateMeili();
 }
 await main()
@@ -6,9 +6,7 @@
  "type": "module",
  "scripts": {
    "start": "esrun index.ts | pino-pretty",
    "start:bundle": "node index.js",
    "dev": "esrun --watch index.ts | pino-pretty",
    "build": "esbuild index.ts --bundle --format=esm --outdir=build --platform=node --target=node22.1 --packages=external",
    "migrate:make": "prisma migrate dev --name",
    "test": "esrun src/scraper.test.ts | pino-pretty"
  },
@@ -17,6 +15,7 @@
  "dependencies": {
    "@google-cloud/vision": "^4.2.0",
    "@prisma/client": "^5.12.1",
    "@theinternetfolks/snowflake": "^1.3.0",
    "axios": "^1.6.8",
    "dotenv": "^16.4.1",
    "lodash": "^4.17.21",
@@ -25,12 +24,11 @@
    "minio": "^7.1.3",
    "pino": "^8.20.0",
    "pino-pretty": "^11.0.0",
-    "sharp": "^0.33.3"
+    "sharp": "^0.33.3",
    "typescript": "^5.3.3"
  },
  "devDependencies": {
    "@types/lodash": "^4.17.0",
    "typescript": "^5.3.3",
    "esbuild": "^0.20.2",
    "esrun": "^3.2.26",
    "prisma": "^5.12.1"
  }
@@ -1,7 +1,7 @@
 generator client {
    provider = "prisma-client-js"
    // include for node docker image
-    binaryTargets = ["native", "debian-openssl-1.1.x", "debian-openssl-3.0.x"]
+    binaryTargets = ["native", "debian-openssl-1.1.x"]
 }
 datasource db {
@@ -27,7 +27,6 @@ model Attachment {
    createdAt  DateTime @default(now())
    updatedAt  DateTime @default(now())
    postedAt   DateTime
    @@index([channelId])
    @@map("attachments")
@@ -39,12 +38,6 @@ model Meme {
    text       String
    tags       Json
    // need an timestamp for giving to meili to sort by
    // i think a usize would actually work but can't
    // convince the meili-js lib to serialize it properly to json
    // this one actually has to be .valueOf()'d before we send it
    // cause js numbers are bigger than postgres int4
    postedAt   DateTime
    createdAt  DateTime @default(now())
    updatedAt  DateTime @default(now())
@@ -0,0 +1 @@
 appendfsync everysec
@@ -0,0 +1,40 @@
 <!DOCTYPE html>
 <html lang="en">
  <head>
    <meta charset="utf-8" />
    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@meilisearch/instant-meilisearch/templates/basic_search.css" />
  </head>
  <body>
      <div id="app" class="wrapper"></div>
  </body>
  <script src="https://unpkg.com/react@18/umd/react.development.js" crossorigin></script>
  <script src="https://unpkg.com/react-dom@18/umd/react-dom.development.js" crossorigin></script>
  <script src="https://cdn.jsdelivr.net/npm/react-instantsearch-dom@6.7.0/dist/umd/ReactInstantSearchDOM.js"></script>
  <script src="https://cdn.jsdelivr.net/npm/@meilisearch/instant-meilisearch/dist/instant-meilisearch.umd.min.js"></script>
  <script>
    const { InstantSearch, SearchBox, Hits, Highlight, Configure } = ReactInstantSearchDOM;
    const searchClient = instantMeiliSearch(
      "http://localhost:7700",
      '33e714590199031d076954182c55a47b09ae7546e3dbf6f35862eb99cc950e1e'
    );
    const App = () => (
      React.createElement(InstantSearch, {
        indexName: "memes",
        searchClient: searchClient
      }, [
        React.createElement(SearchBox, { key: 1 }),
        React.createElement(Hits, { hitComponent: Hit, key: 2 }),
        React.createElement(Configure, { hitsPerPage: 10 })]
      )
    );
    const Hit = (props) => (
      React.createElement(Highlight, {
        attribute: "id",
        hit: props.hit
      })
    );
    ReactDOM.createRoot(document.querySelector('#app')).render(App());
    console.log(searchClient)
  </script>
 </html>
@@ -2,8 +2,6 @@ import sharp from 'sharp'
 import axios from 'axios'
 import mime from 'mime-types'
 import _ from 'lodash';
 import type { Logger } from 'pino'
 import type Minio from 'minio'
@@ -55,21 +53,16 @@ export default async function attachmentService(log: Logger, minio: Minio.Client
            return download.data
        }
-        return minio.putObject(STORAGE_BUCKET,
+        return minio.putObject(STORAGE_BUCKET, objectName(a), stream())
            objectName(a),
            stream(),
            null,
            // hardcode this for now, we upload everything as webp
            { 'Content-Type': 'image/webp' })
    }
    async function deleteAttachment(a: Attachment) {
        return minio.removeObject(STORAGE_BUCKET, objectName(a))
    }
-    async function process(a: Attachment, history: Partial<ChannelHistory>) {
+    async function process(a: Attachment) {
        try {
-            const results = await prisma.$transaction(async prisma => {
+            return prisma.$transaction(async prisma => {
                const meme = memes.fromAttachment(a)
                const dbMeme = await prisma.meme.upsert({ create: meme, update: meme, where: { id: meme.id } })
                const dbA = await prisma.attachment.upsert({ create: a, update: a, where: { id: a.id } })
@@ -78,30 +71,24 @@ export default async function attachmentService(log: Logger, minio: Minio.Client
                const upload = await storeAttachment(a)
                log.debug({ msg: 'successfully uploaded', upload })
                await memes.persist(dbMeme)
                log.info(dbMeme, 'new meme')
                return { meme: dbMeme, upload, attachment: dbA }
            }, { timeout: 60000 })
        } catch (e) {
            // this happens pretty regularly it seems
            // when ppl reply to an attachment it is included in their message
-            if (e.meta?.modelName !== 'Meme' || e.meta?.target?.[0] !== 'attachmentId') {
+            if (e.meta.modelName !== 'Meme' && e.meta.target[0] !== 'attachmentId') {
                log.error(e, 'failed to process attachment')
-                log.error(_.omit(a, ['vision']), 'failed to process attachment')
+                log.error(a, 'failed to process attachment')
            }
            // deletes the upload if we got that far
            // (probably not)
            await deleteAttachment(a)
        }
-        // we assume here that a failure in processing was caused by a duplicate
+            // throw again cause we gather with allSettled
-        // so we update pg to say we've processed it
+            throw e
-        const newHistory = await prisma.channelHistory.update({ data: history, where: { id: history.id }})
+        }
        log.debug({ newHistory }, 'updated channel history')
        return true
    }
    await ensureStorageBucketExists()
@@ -2,8 +2,6 @@ import type { PrismaClient, Attachment, Meme } from '@prisma/client';
 import type { Meilisearch } from 'meilisearch';
 import type { Logger } from 'pino';
 import _ from 'lodash'
 import * as attachments from './attachments'
 const STORAGE_BUCKET = process.env.STORAGE_BUCKET
@@ -31,7 +29,6 @@ export default async function memeService(baseLog: Logger, prisma: PrismaClient,
            text,
            tags: tags,
            attachmentId: a.id,
            postedAt: a.postedAt,
            createdAt: undefined,
            updatedAt: undefined
        }
@@ -40,45 +37,36 @@ export default async function memeService(baseLog: Logger, prisma: PrismaClient,
    }
    async function ensureMeiliIndex() {
        const delTask = await meili.deleteIndex('memes')
        const delResult = await meili.waitForTask(delTask.taskUid)
        const task = await meili.createIndex('memes', { primaryKey: 'id' })
        const result = await meili.waitForTask(task.taskUid)
        log.debug(result);
-        const index = await meili.index('memes')
+        return meili.index('memes')
        await index.updateSortableAttributes(['postedAt'])
        return index;
    }
-    // BLOWS IT UP
+    async function updateMeili() {
-    async function resetMeili() {
+        await ensureMeiliIndex();
        const delTask = await meili.deleteIndex('memes')
        const delResult = await meili.waitForTask(delTask.taskUid)
        const index = await ensureMeiliIndex()
        const memes = (await prisma.meme.findMany())
            .map(m => ({ ...m, postedAt: m.postedAt.valueOf() }));
        for await (const batch of _.chunk(memes, 1000)) {
            const task = await index.updateDocuments(batch)
            const res = await meili.waitForTask(task.taskUid)
            log.info({ res }, 'added meme batch')
        }
    }
    async function persist(m: Meme) {
        const index = meili.index('memes')
-        const doc = ({ ...m, postedAt: m.postedAt.valueOf() })
+        const memes = await prisma.meme.findMany();
-        return index.updateDocuments([doc])
+        const task = await index.updateDocuments(memes)
        const res = await meili.waitForTask(task.taskUid)
        log.debug(res)
    }
    async function addToIndex(memes: Meme[]) {
        const index = meili.index('memes')
        return index.updateDocuments(memes)
    }
    await ensureMeiliIndex();
-
+    await updateMeili();
    // BAM
    // await resetMeili();
    return {
        ensureMeiliIndex,
-        resetMeili,
+        updateMeili,
        fromAttachment,
-        persist,
+        addToIndex,
    }
 }
@@ -0,0 +1,44 @@
 import "dotenv/config"
 import fs from 'fs/promises'
 import pino from 'pino'
 import * as Minio from 'minio'
 import Vision from '@google-cloud/vision'
 import { PrismaClient } from '@prisma/client'
 import { MeiliSearch } from 'meilisearch'
 import discordScraper from './scraper'
 import attachmentService from "./attachments"
 // @ts-ignore - ts don't know wtf it talking about
 BigInt.prototype.toJSON = function bigIntStringify() {
    return this.toString();
 };
 const VISION_CREDENTIALS = (await import(process.env.GOOGLE_APPLICATION_CREDENTIALS, { assert: { type: "json" } })).default
 const STORAGE_BUCKET = process.env.STORAGE_BUCKET
 const log = pino({ base: {} });
 const vision = new Vision.ImageAnnotatorClient({ credentials: VISION_CREDENTIALS })
 const prisma = new PrismaClient()
 const minio = new Minio.Client({
    endPoint: process.env.STORAGE_URL,
    accessKey: process.env.STORAGE_ACCESS_KEY,
    secretKey: process.env.STORAGE_SECRET_KEY,
 })
 const meili = new MeiliSearch({
  host: process.env.MEILI_URL,
  apiKey: process.env.MEILI_MASTER_KEY,
 })
 const attachments = attachmentService(log, minio, prisma)
 const scraper = discordScraper(process.env.DISCORD_AUTH, vision, minio, prisma, log)
 const CHANNEL_IDS = [
    367936426962190336n,  // TPM shitposts
    1095060717117374687n, // aella memes
 ]
 await Promise.all(CHANNEL_IDS.map(id => scraper.processChannel(id)))
@@ -1,4 +1,3 @@
 import { setTimeout } from 'timers/promises'
 import axios from 'axios'
 import _ from 'lodash';
@@ -12,23 +11,19 @@ import sharp from 'sharp';
 import type { AttachmentService } from './attachments'
 import { IMAGE_TYPES, VIDEO_TYPES } from './attachments'
 import { MemeService } from './memes';
 // TODO
 // also fetch embeds and their descriptions
-function convertSnowflakeToDate(snowflake) {
+export default function scraper(
    const DISCORD_EPOCH = 1420070400000
    const milliseconds = global.BigInt(snowflake) >> 22n
    return new Date(Number(milliseconds) + DISCORD_EPOCH)
 }
 export default async function scraper(
    discordAuth,
    vision: ImageAnnotatorClient,
    minio: Minio.Client,
    prisma: PrismaClient,
    baseLog: Logger,
-    attachments: AttachmentService
+    attachments: AttachmentService,
    memes: MemeService,
 ) {
    const headers = {
        'Authorization': discordAuth,
@@ -56,7 +51,9 @@ export default async function scraper(
    async function fetchGuildDetails(guildId) {
        const url = `https://discord.com/api/v9/guilds/${guildId}`
        const res = await axios.get(url, { headers })
-        return _.omit(res.data, ['emojis', 'stickers', 'roles', 'features'])
+        const keys_to_remove = ['emojis', 'stickers', 'roles', 'features']
        keys_to_remove.forEach(k => delete res.data[k])
        return res.data
    }
    async function fetchChannel(channelId) {
@@ -82,12 +79,6 @@ export default async function scraper(
        return res[0] || {}
    }
    async function fetchMissingVision() {
        const attachments = await prisma.attachment
            .findMany({ where: { vision: {}, contentType: { in: IMAGE_TYPES } }})
        baseLog.info({attachments: attachments.length }, 'missing vision attachments')
    }
    async function processChannel(channelId) {
        const channel = await fetchChannel(channelId)
        const guild = await fetchGuildDetails(channel.guild_id)
@@ -96,18 +87,19 @@ export default async function scraper(
        async function filterAttachments(messages): Promise<Attachment[]> {
            const acceptedContentTypes = [
                ...IMAGE_TYPES,
-                // ...VIDEO_TYPES,
+                ...VIDEO_TYPES,
            ]
            const validAttachments = messages
                .filter(m => m.attachments)
                // bundle message and attachment together
                .flatMap(m => m.attachments.map(a => [a, m]))
-                .filter(([a, m]) => acceptedContentTypes.includes(a.content_type));
+                .filter(([a, m]) => acceptedContentTypes.includes(a.content_type))
-            log.debug({ validAttachments: validAttachments.length }, 'attachments found in messages')
+            const newAttachments = validAttachments.filter(([a, m]) => ![].includes(a.id))
            log.info({ newAttachments: newAttachments.length, validAttachments: validAttachments.length })
-            return Promise.all(validAttachments
+            return Promise.all(newAttachments
                .map(async ([a, m]) => {
                    const attachment: Attachment = {
                        id: BigInt(a.id),
@@ -119,41 +111,47 @@ export default async function scraper(
                        // create this ahead of time to associate with our copy of the media
                        memeId: crypto.randomUUID(),
-                        vision: {}, // quick hack so that detectText can receive a full attachment
+                        // @ts-ignore it's fine
                        vision: {},
                        guild,
                        channel,
                        message: m,
-                        postedAt: convertSnowflakeToDate(a.id),
+
                        // ts asks for these to be included but they don't need to be set
                        createdAt: undefined,
                        updatedAt: undefined
                    }
-                    // actually assign vision here
+                    const visionData = await detectText(attachment)
-                    return { ...attachment, vision: await detectText(attachment) }
+                    return { ...attachment, vision: visionData }
                }))
        }
-        async function* fetchNew(channelId, log, latestMessageId): AsyncIterable<Attachment> {
+        async function* fetchNew(channelId, log, latestMessageId) {
            // reverse the messages because we want to yield them in chronological order
            // the api call returns them most recent first
            const messages = (await fetchChannelMessagesAfter(channelId, latestMessageId)).reverse()
            if (messages.length === 0) {
-                log.info('reached latest message')
+                log.info('no new messages')
                return
            }
-            log.debug({ messages: messages.length, latestMessageId }, 'fetched new messages')
+            log.info({ messages: messages.length, latestMessageId }, 'fetched new messages')
-            yield* await filterAttachments(messages)
+            const cursor = _.last(messages).id
            yield [await filterAttachments(messages), cursor]
            yield* fetchNew(channelId, log, cursor)
        }
-        async function* fetchOld(channelId, log, earliestMessageId): AsyncIterable<Attachment> {
+        async function* fetchOld(channelId, log, earliestMessageId) {
            const messages = await fetchChannelMessagesBefore(channelId, earliestMessageId)
            if (messages.length === 0) {
-                log.info('reached beginning of history')
+                log.info('no new messages')
                return
            }
-            log.debug({ messages: messages.length, earliestMessageId }, 'fetched older messages')
+            log.info({ messages: messages.length, earliestMessageId }, 'fetched old messages')
-            yield* await filterAttachments(messages)
+            const cursor = _.last(messages).id
            yield [await filterAttachments(messages), cursor]
            yield* fetchOld(channelId, log, cursor)
        }
        const ensureHistory = async () => {
@@ -166,45 +164,43 @@ export default async function scraper(
            })
        }
-        const history = await ensureHistory()
+        const startingHistory = await ensureHistory()
-        async function processLoop() {
+        const updateHistory = async update => prisma.channelHistory
-            const history = await ensureHistory()
+            .update({ data: update, where: { id: startingHistory.id } })
            const newAttachments = fetchNew(channelId, log, history.latestMessageId)
            const oldAttachments = fetchOld(channelId, log, history.earliestMessageId)
-            let oldCount = 0;
+        async function processBatch([batch, cursor], genHistory) {
-            let newCount = 0;
+            log.debug({ msg: 'scraped new attachments', attachments: batch.length })
            const results = await Promise.allSettled(batch.map(async a => attachments.process(a)))
            const inserts = results
                .filter(r => r.value)
                .map(r => r.value)
-            for await (const attachment of newAttachments) {
+            const failures = results
-                log.debug({ msg: 'scraped new attachment', attachment: _.omit(attachment, ['guild', 'message', 'channel', 'vision']) })
+                .filter(r => r.reason)
-                const newHistory = { id: history.id, latestMessageId: attachment.msgId }
+                .map(r => r.reason)
-                await attachments.process(attachment, newHistory)
+
-                // pretty oldschool, the async iterable from the fetch fn does not have a count
+            if (failures.length) log.error({ failures }, 'batch failures')
-                // so we just use a plain old count to see if we should wait
+            log.info({ inserts: inserts.length }, 'batch success')
-                oldCount++
+
            await memes.addToIndex(inserts.map(i => i.meme))
            // yeah cool whatever we processed the whole lot... sure
            const newHistory = await updateHistory(genHistory())
            log.debug({ newHistory }, 'updated channel history')
            return inserts
        }
-            for await (const attachment of oldAttachments) {
+        for await (const batch of fetchNew(channelId, log, startingHistory.latestMessageId)) {
-                log.debug({ msg: 'scraped old attachment', attachment: _.omit(attachment, ['guild', 'message', 'channel', 'vision']) })
+            const genHistory = cursor => ({ latestMessageId: cursor })
-                const newHistory = { id: history.id, earliestMessageId: attachment.msgId }
+            await processBatch(batch, genHistory)
                await attachments.process(attachment, newHistory)
                newCount++
        }
-            log.info({ oldCount, newCount }, 'processed attachments')
+        for await (const batch of fetchOld(channelId, log, startingHistory.latestMessageId)) {
-
+            const genHistory = cursor => ({ earliestMessageId: cursor })
-            const shouldWait = newCount === 0 && oldCount === 0
+            await processBatch(batch, genHistory)
            const PROCESS_DELAY_MS = 1000 * 60 // 1 minute
            if (shouldWait) {
                log.info({ PROCESS_DELAY_MS }, 'waiting for new messages')
                await setTimeout(PROCESS_DELAY_MS)
        }
            return processLoop()
        }
        await processLoop();
    }
    return {
Author	SHA1	Message	Date
Nathan Rashleigh	ad4b6e1f70	100 batch failing cause of tx pool i think	2024-04-12 18:06:14 +10:00
Nathan Rashleigh	8212f9bbf3	yield each	2024-04-12 17:24:39 +10:00
		`@@ -1 +0,0 @@`
			<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 841.9 595.3"><g fill="#61DAFB"><path d="M666.3 296.5c0-32.5-40.7-63.3-103.1-82.4 14.4-63.6 8-114.2-20.2-130.4-6.5-3.8-14.1-5.6-22.4-5.6v22.3c4.6 0 8.3.9 11.4 2.6 13.6 7.8 19.5 37.5 14.9 75.7-1.1 9.4-2.9 19.3-5.1 29.4-19.6-4.8-41-8.5-63.5-10.9-13.5-18.5-27.5-35.3-41.6-50 32.6-30.3 63.2-46.9 84-46.9V78c-27.5 0-63.5 19.6-99.9 53.6-36.4-33.8-72.4-53.2-99.9-53.2v22.3c20.7 0 51.4 16.5 84 46.6-14 14.7-28 31.4-41.3 49.9-22.6 2.4-44 6.1-63.6 11-2.3-10-4-19.7-5.2-29-4.7-38.2 1.1-67.9 14.6-75.8 3-1.8 6.9-2.6 11.5-2.6V78.5c-8.4 0-16 1.8-22.6 5.6-28.1 16.2-34.4 66.7-19.9 130.1-62.2 19.2-102.7 49.9-102.7 82.3 0 32.5 40.7 63.3 103.1 82.4-14.4 63.6-8 114.2 20.2 130.4 6.5 3.8 14.1 5.6 22.5 5.6 27.5 0 63.5-19.6 99.9-53.6 36.4 33.8 72.4 53.2 99.9 53.2 8.4 0 16-1.8 22.6-5.6 28.1-16.2 34.4-66.7 19.9-130.1 62-19.1 102.5-49.9 102.5-82.3zm-130.2-66.7c-3.7 12.9-8.3 26.2-13.5 39.5-4.1-8-8.4-16-13.1-24-4.6-8-9.5-15.8-14.4-23.4 14.2 2.1 27.9 4.7 41 7.9zm-45.8 106.5c-7.8 13.5-15.8 26.3-24.1 38.2-14.9 1.3-30 2-45.2 2-15.1 0-30.2-.7-45-1.9-8.3-11.9-16.4-24.6-24.2-38-7.6-13.1-14.5-26.4-20.8-39.8 6.2-13.4 13.2-26.8 20.7-39.9 7.8-13.5 15.8-26.3 24.1-38.2 14.9-1.3 30-2 45.2-2 15.1 0 30.2.7 45 1.9 8.3 11.9 16.4 24.6 24.2 38 7.6 13.1 14.5 26.4 20.8 39.8-6.3 13.4-13.2 26.8-20.7 39.9zm32.3-13c5.4 13.4 10 26.8 13.8 39.8-13.1 3.2-26.9 5.9-41.2 8 4.9-7.7 9.8-15.6 14.4-23.7 4.6-8 8.9-16.1 13-24.1zM421.2 430c-9.3-9.6-18.6-20.3-27.8-32 9 .4 18.2.7 27.5.7 9.4 0 18.7-.2 27.8-.7-9 11.7-18.3 22.4-27.5 32zm-74.4-58.9c-14.2-2.1-27.9-4.7-41-7.9 3.7-12.9 8.3-26.2 13.5-39.5 4.1 8 8.4 16 13.1 24 4.7 8 9.5 15.8 14.4 23.4zM420.7 163c9.3 9.6 18.6 20.3 27.8 32-9-.4-18.2-.7-27.5-.7-9.4 0-18.7.2-27.8.7 9-11.7 18.3-22.4 27.5-32zm-74 58.9c-4.9 7.7-9.8 15.6-14.4 23.7-4.6 8-8.9 16-13 24-5.4-13.4-10-26.8-13.8-39.8 13.1-3.1 26.9-5.8 41.2-7.9zm-90.5 125.2c-35.4-15.1-58.3-34.9-58.3-50.6 0-15.7 22.9-35.6 58.3-50.6 8.6-3.7 18-7 27.7-10.1 5.7 19.6 13.2 40 22.5 60.9-9.2 20.8-16.6 41.1-22.2 60.6-9.9-3.1-19.3-6.5-28-10.2zM310 490c-13.6-7.8-19.5-37.5-14.9-75.7 1.1-9.4 2.9-19.3 5.1-29.4 19.6 4.8 41 8.5 63.5 10.9 13.5 18.5 27.5 35.3 41.6 50-32.6 30.3-63.2 46.9-84 46.9-4.5-.1-8.3-1-11.3-2.7zm237.2-76.2c4.7 38.2-1.1 67.9-14.6 75.8-3 1.8-6.9 2.6-11.5 2.6-20.7 0-51.4-16.5-84-46.6 14-14.7 28-31.4 41.3-49.9 22.6-2.4 44-6.1 63.6-11 2.3 10.1 4.1 19.8 5.2 29.1zm38.5-66.7c-8.6 3.7-18 7-27.7 10.1-5.7-19.6-13.2-40-22.5-60.9 9.2-20.8 16.6-41.1 22.2-60.6 9.9 3.1 19.3 6.5 28.1 10.2 35.4 15.1 58.3 34.9 58.3 50.6-.1 15.7-23 35.6-58.4 50.6zM320.8 78.4z"/><circle cx="420.9" cy="296.5" r="45.7"/><path d="M520.5 78.1z"/></g></svg>