github/overleaf
1
0
Fork 0
mirror of https://github.com/overleaf/overleaf.git synced 2025-04-20 19:16:00 +00:00
Code Issues Projects Releases Packages Wiki Activity

Merge pull request #23725 from overleaf/em-find-dangling-comments-archived-docs

Browse source 
Look at archived docs when looking for dangling comments

GitOrigin-RevId: fb04b9428ce83802b6e658153c5bbe70e983de65
This commit is contained in:
Eric Mc Sween 2025-02-20 08:16:06 -05:00 • committed by Copybot
parent 12abf74620
commit fb22d6f518
1 changed files with 26 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
services/web/scripts/find_dangling_comments.mjs
View file

@ -6,6 +6,8 @@ import {
ObjectId,
READ_PREFERENCE_SECONDARY,
} from '../app/src/infrastructure/mongodb.js'
import DocstoreManager from '../app/src/Features/Docstore/DocstoreManager.js'
import { NotFoundError } from '../app/src/Features/Errors/Errors.js'
const OPTS = parseArgs()
@ -47,7 +49,7 @@ async function main() {
)
projectsFound += 1
}
if (projectsProcessed % 100000 === 0) {
if (projectsProcessed % 10000 === 0) {
console.log(
`${projectsProcessed} projects processed - Last project: ${projectId}`
)
@ -60,7 +62,7 @@ async function* fetchThreadIdsByProject() {
const clauses = []
clauses.push({
deleted: { $ne: true },
'ranges.comments.0': { $exists: true },
$or: [{ 'ranges.comments.0': { $exists: true } }, { inS3: true }],
})
if (OPTS.minProjectId != null) {
clauses.push({ project_id: { $gte: new ObjectId(OPTS.minProjectId) } })
@ -72,7 +74,7 @@ async function* fetchThreadIdsByProject() {
{ $and: clauses },
{
sort: { project_id: 1 },
projection: { project_id: 1, 'ranges.comments': 1 },
projection: { project_id: 1, 'ranges.comments': 1, inS3: 1 },
readPreference: READ_PREFERENCE_SECONDARY,
}
)
@ -87,7 +89,27 @@ async function* fetchThreadIdsByProject() {
projectId = doc.project_id
for (const comment of doc.ranges.comments) {
let comments = []
if (doc.inS3) {
try {
const archivedDoc = await DocstoreManager.promises.getDoc(
projectId,
doc._id,
{ peek: true }
)
comments = archivedDoc.ranges?.comments ?? []
} catch (err) {
if (err instanceof NotFoundError) {
console.warn(`Doc ${doc._id} in project ${projectId} not found`)
} else {
throw err
}
}
} else {
comments = doc.ranges?.comments
}
for (const comment of comments) {
threadIds.add(comment.op.t.toString())
}
}