Merge pull request #21748 from overleaf/jpa-publish-mongo-utils

[copybara] publish mongo-utils library

GitOrigin-RevId: 0ef269f186ed645f7bcb9d948a4d1e591c687b31

libraries/mongo-utils/.dockerignore

@@ -0,0 +1 @@
+node_modules/

libraries/mongo-utils/.gitignore

@@ -0,0 +1,3 @@
+
+# managed by monorepo$ bin/update_build_scripts
+.npmrc

libraries/mongo-utils/.nvmrc

@@ -0,0 +1 @@
+18.20.4

libraries/mongo-utils/batchedUpdate.js

@@ -0,0 +1,282 @@
+// @ts-check
+/* eslint-disable no-console */
+const { ObjectId, ReadPreference } = require('mongodb')
+
+const READ_PREFERENCE_SECONDARY =
+  process.env.MONGO_HAS_SECONDARIES === 'true'
+    ? ReadPreference.secondary.mode
+    : ReadPreference.secondaryPreferred.mode
+
+const ONE_MONTH_IN_MS = 1000 * 60 * 60 * 24 * 31
+let ID_EDGE_PAST
+const ID_EDGE_FUTURE = objectIdFromMs(Date.now() + 1000)
+let BATCH_DESCENDING
+let BATCH_SIZE
+let VERBOSE_LOGGING
+let BATCH_RANGE_START
+let BATCH_RANGE_END
+let BATCH_MAX_TIME_SPAN_IN_MS
+
+/**
+ * @typedef {import("mongodb").Collection} Collection
+ * @typedef {import("mongodb-legacy").Collection} LegacyCollection
+ * @typedef {import("mongodb").Document} Document
+ * @typedef {import("mongodb").FindOptions} FindOptions
+ * @typedef {import("mongodb").UpdateFilter<Document>} UpdateDocument
+ */
+
+/**
+ * @typedef {Object} BatchedUpdateOptions
+ * @property {string} [BATCH_DESCENDING]
+ * @property {string} [BATCH_LAST_ID]
+ * @property {string} [BATCH_MAX_TIME_SPAN_IN_MS]
+ * @property {string} [BATCH_RANGE_END]
+ * @property {string} [BATCH_RANGE_START]
+ * @property {string} [BATCH_SIZE]
+ * @property {string} [VERBOSE_LOGGING]
+ */
+
+/**
+ * @param {BatchedUpdateOptions} options
+ */
+function refreshGlobalOptionsForBatchedUpdate(options = {}) {
+  options = Object.assign({}, options, process.env)
+
+  BATCH_DESCENDING = options.BATCH_DESCENDING === 'true'
+  BATCH_SIZE = parseInt(options.BATCH_SIZE || '1000', 10) || 1000
+  VERBOSE_LOGGING = options.VERBOSE_LOGGING === 'true'
+  if (options.BATCH_LAST_ID) {
+    BATCH_RANGE_START = new ObjectId(options.BATCH_LAST_ID)
+  } else if (options.BATCH_RANGE_START) {
+    BATCH_RANGE_START = new ObjectId(options.BATCH_RANGE_START)
+  } else {
+    if (BATCH_DESCENDING) {
+      BATCH_RANGE_START = ID_EDGE_FUTURE
+    } else {
+      BATCH_RANGE_START = ID_EDGE_PAST
+    }
+  }
+  BATCH_MAX_TIME_SPAN_IN_MS = parseInt(
+    options.BATCH_MAX_TIME_SPAN_IN_MS || ONE_MONTH_IN_MS.toString(),
+    10
+  )
+  if (options.BATCH_RANGE_END) {
+    BATCH_RANGE_END = new ObjectId(options.BATCH_RANGE_END)
+  } else {
+    if (BATCH_DESCENDING) {
+      BATCH_RANGE_END = ID_EDGE_PAST
+    } else {
+      BATCH_RANGE_END = ID_EDGE_FUTURE
+    }
+  }
+}
+
+/**
+ * @param {Collection | LegacyCollection} collection
+ * @param {Document} query
+ * @param {ObjectId} start
+ * @param {ObjectId} end
+ * @param {Document} projection
+ * @param {FindOptions} findOptions
+ * @return {Promise<Array<Document>>}
+ */
+async function getNextBatch(
+  collection,
+  query,
+  start,
+  end,
+  projection,
+  findOptions
+) {
+  if (BATCH_DESCENDING) {
+    query._id = {
+      $gt: end,
+      $lte: start,
+    }
+  } else {
+    query._id = {
+      $gt: start,
+      $lte: end,
+    }
+  }
+  return await collection
+    .find(query, findOptions)
+    .project(projection)
+    .sort({ _id: BATCH_DESCENDING ? -1 : 1 })
+    .limit(BATCH_SIZE)
+    .toArray()
+}
+
+/**
+ * @param {Collection | LegacyCollection} collection
+ * @param {Array<Document>} nextBatch
+ * @param {UpdateDocument} update
+ * @return {Promise<void>}
+ */
+async function performUpdate(collection, nextBatch, update) {
+  await collection.updateMany(
+    { _id: { $in: nextBatch.map(entry => entry._id) } },
+    update
+  )
+}
+
+/**
+ * @param {number} ms
+ * @return {ObjectId}
+ */
+function objectIdFromMs(ms) {
+  return ObjectId.createFromTime(ms / 1000)
+}
+
+/**
+ * @param {ObjectId} id
+ * @return {number}
+ */
+function getMsFromObjectId(id) {
+  return id.getTimestamp().getTime()
+}
+
+/**
+ * @param {ObjectId} start
+ * @return {ObjectId}
+ */
+function getNextEnd(start) {
+  let end
+  if (BATCH_DESCENDING) {
+    end = objectIdFromMs(getMsFromObjectId(start) - BATCH_MAX_TIME_SPAN_IN_MS)
+    if (getMsFromObjectId(end) <= getMsFromObjectId(BATCH_RANGE_END)) {
+      end = BATCH_RANGE_END
+    }
+  } else {
+    end = objectIdFromMs(getMsFromObjectId(start) + BATCH_MAX_TIME_SPAN_IN_MS)
+    if (getMsFromObjectId(end) >= getMsFromObjectId(BATCH_RANGE_END)) {
+      end = BATCH_RANGE_END
+    }
+  }
+  return end
+}
+
+/**
+ * @param {Collection | LegacyCollection} collection
+ * @return {Promise<ObjectId|null>}
+ */
+async function getIdEdgePast(collection) {
+  const [first] = await collection
+    .find({})
+    .project({ _id: 1 })
+    .sort({ _id: 1 })
+    .limit(1)
+    .toArray()
+  if (!first) return null
+  // Go one second further into the past in order to include the first entry via
+  // first._id > ID_EDGE_PAST
+  return objectIdFromMs(Math.max(0, getMsFromObjectId(first._id) - 1000))
+}
+
+/**
+ * @param {Collection | LegacyCollection} collection
+ * @param {Document} query
+ * @param {UpdateDocument | ((batch: Array<Document>) => Promise<void>)} update
+ * @param {Document} [projection]
+ * @param {FindOptions} [findOptions]
+ * @param {BatchedUpdateOptions} [batchedUpdateOptions]
+ */
+async function batchedUpdate(
+  collection,
+  query,
+  update,
+  projection,
+  findOptions,
+  batchedUpdateOptions
+) {
+  ID_EDGE_PAST = await getIdEdgePast(collection)
+  if (!ID_EDGE_PAST) {
+    console.warn(
+      `The collection ${collection.collectionName} appears to be empty.`
+    )
+    return 0
+  }
+  refreshGlobalOptionsForBatchedUpdate(batchedUpdateOptions)
+
+  findOptions = findOptions || {}
+  findOptions.readPreference = READ_PREFERENCE_SECONDARY
+
+  projection = projection || { _id: 1 }
+  let nextBatch
+  let updated = 0
+  let start = BATCH_RANGE_START
+
+  while (start !== BATCH_RANGE_END) {
+    let end = getNextEnd(start)
+    nextBatch = await getNextBatch(
+      collection,
+      query,
+      start,
+      end,
+      projection,
+      findOptions
+    )
+    if (nextBatch.length > 0) {
+      end = nextBatch[nextBatch.length - 1]._id
+      updated += nextBatch.length
+
+      if (VERBOSE_LOGGING) {
+        console.log(
+          `Running update on batch with ids ${JSON.stringify(
+            nextBatch.map(entry => entry._id)
+          )}`
+        )
+      } else {
+        console.error(`Running update on batch ending ${end}`)
+      }
+
+      if (typeof update === 'function') {
+        await update(nextBatch)
+      } else {
+        await performUpdate(collection, nextBatch, update)
+      }
+    }
+    console.error(`Completed batch ending ${end}`)
+    start = end
+  }
+  return updated
+}
+
+/**
+ * @param {Collection | LegacyCollection} collection
+ * @param {Document} query
+ * @param {UpdateDocument | ((batch: Array<Object>) => Promise<void>)} update
+ * @param {Document} [projection]
+ * @param {FindOptions} [findOptions]
+ * @param {BatchedUpdateOptions} [batchedUpdateOptions]
+ */
+function batchedUpdateWithResultHandling(
+  collection,
+  query,
+  update,
+  projection,
+  findOptions,
+  batchedUpdateOptions
+) {
+  batchedUpdate(
+    collection,
+    query,
+    update,
+    projection,
+    findOptions,
+    batchedUpdateOptions
+  )
+    .then(processed => {
+      console.error({ processed })
+      process.exit(0)
+    })
+    .catch(error => {
+      console.error({ error })
+      process.exit(1)
+    })
+}
+
+module.exports = {
+  batchedUpdate,
+  batchedUpdateWithResultHandling,
+}

libraries/mongo-utils/buildscript.txt

@@ -0,0 +1,10 @@
+mongo-utils
+--dependencies=None
+--docker-repos=gcr.io/overleaf-ops
+--env-add=
+--env-pass-through=
+--esmock-loader=False
+--is-library=True
+--node-version=18.20.4
+--public-repo=False
+--script-version=4.5.0

libraries/mongo-utils/package.json

@@ -0,0 +1,30 @@
+{
+  "name": "@overleaf/mongo-utils",
+  "version": "0.0.1",
+  "description": "utilities to help working with mongo",
+  "main": "index.js",
+  "scripts": {
+    "test": "npm run lint && npm run format && npm run types:check && npm run test:unit",
+    "test:unit": "mocha --exit test/**/*.{js,cjs}",
+    "lint": "eslint --ext .js --ext .cjs --ext .ts --max-warnings 0 --format unix .",
+    "lint:fix": "eslint --fix --ext .js --ext .cjs --ext .ts .",
+    "format": "prettier --list-different $PWD/'**/*.{js,cjs,ts}'",
+    "format:fix": "prettier --write $PWD/'**/*.{js,cjs,ts}'",
+    "test:ci": "npm run test:unit",
+    "types:check": "tsc --noEmit"
+  },
+  "author": "Overleaf (https://www.overleaf.com)",
+  "license": "AGPL-3.0-only",
+  "dependencies": {
+    "mongodb": "6.7.0",
+    "mongodb-legacy": "6.1.0"
+  },
+  "devDependencies": {
+    "chai": "^4.3.6",
+    "mocha": "^10.2.0",
+    "sandboxed-module": "^2.0.4",
+    "sinon": "^9.2.4",
+    "sinon-chai": "^3.7.0",
+    "typescript": "^5.0.4"
+  }
+}

libraries/mongo-utils/test/setup.js

@@ -0,0 +1,11 @@
+const chai = require('chai')
+const sinonChai = require('sinon-chai')
+const SandboxedModule = require('sandboxed-module')
+
+// Chai configuration
+chai.should()
+chai.use(sinonChai)
+
+SandboxedModule.configure({
+  globals: { Buffer, JSON, console, process },
+})

libraries/mongo-utils/tsconfig.json

@@ -0,0 +1,7 @@
+{
+  "extends": "../../tsconfig.backend.json",
+  "include": [
+    "**/*.js",
+    "**/*.cjs"
+  ]
+}