[clsi] initial version of /convert/pdf-to-jpeg (#33752)

* [monorepo] consolidate clsi-lb host/ip env-vars

Target env-var is CLSI_LB_HOST. Keep CLSI_LB_IP populated for a week.

* [clsi] initial version of /convert/pdf-to-jpeg

* [rails] use fake-secrets in CI and Codespaces

* [rails] adapt tests for using clsi to convert PDFs to image

* [rails] add rake task for comparing clsi conversion with transloadit

* [clsi] double check that output.jpg is a regular file

Co-authored-by: Brian Gough <brian.gough@overleaf.com>

* [clsi] fix composing basename

* [monorepo] fix clsi-lb host env-var post merge

* [monorepo] sort dev-environment.env hosts

* [rails] use local pdf file rather than downloading it again

Download from the old renderer code path still. It's dead code.

* [terraform] clsi: enable pdf to jpg conversion

---------

Co-authored-by: Brian Gough <brian.gough@overleaf.com>
GitOrigin-RevId: 5ecaa8559d299486340bb3961f06b29f7c4dfcca

services/clsi/app/js/ConversionController.js

@@ -14,6 +14,7 @@ import RequestParser from './RequestParser.js'
 import { pipeline } from 'node:stream/promises'
 import Settings from '@overleaf/settings'
 import Path from 'node:path'
+import { z } from '@overleaf/validation-tools'
 
 const CONVERSION_CONFIGS = {
   docx: { extension: 'docx' },
@@ -77,6 +78,51 @@ async function convertDocumentToLaTeX(req, res) {
   }
 }
 
+const PDFToJPEGQuerySchema = z.object({
+  mode: z.enum(['preview', 'thumbnail']),
+})
+
+async function convertPDFToJPEG(req, res) {
+  const { path } = req.file
+  if (!Settings.enablePdfConversions) {
+    await fs.unlink(path).catch(() => {})
+    return res.sendStatus(404)
+  }
+  const parsed = PDFToJPEGQuerySchema.safeParse(req.query)
+  if (!parsed.success) {
+    await fs.unlink(path).catch(() => {})
+    return res.sendStatus(400)
+  }
+  const { mode } = parsed.data
+  logger.debug({ path, mode }, 'received pdf for conversion to jpeg')
+  const conversionId = crypto.randomUUID()
+  let jpegPath
+  try {
+    jpegPath = await ConversionManager.promises.convertPDFToJPEGWithLock(
+      conversionId,
+      path,
+      mode
+    )
+  } finally {
+    await fs.unlink(path).catch(() => {})
+  }
+
+  try {
+    const jpegStat = await fs.stat(jpegPath)
+
+    res.setHeader('Content-Length', jpegStat.size)
+    res.attachment('output.jpg')
+    res.setHeader('X-Content-Type-Options', 'nosniff')
+
+    const readStream = fsSync.createReadStream(jpegPath)
+    await pipeline(readStream, res)
+  } finally {
+    await fs
+      .rm(Path.dirname(jpegPath), { recursive: true, force: true })
+      .catch(() => {})
+  }
+}
+
 async function convertProjectToDocument(req, res) {
   if (!Settings.enablePandocConversions) {
     return res.sendStatus(404)
@@ -207,4 +253,5 @@ async function convertProjectToDocument(req, res) {
 export default {
   convertDocumentToLaTeX: expressify(convertDocumentToLaTeX),
   convertProjectToDocument: expressify(convertProjectToDocument),
+  convertPDFToJPEG: expressify(convertPDFToJPEG),
 }