github/overleaf
1
0
Fork 0
mirror of https://github.com/overleaf/overleaf.git synced 2024-12-26 08:31:22 +00:00
Code Issues Projects Releases Packages Wiki Activity

Merge pull request #236 from overleaf/jpa-skip-duplicate-writes

Browse source 
[ContentCacheManager] skip writing of duplicate streams
This commit is contained in:
Jakob Ackermann 2021-05-18 11:44:23 +02:00 committed by GitHub
commit 23dd93ae50
1 changed files with 7 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
services/clsi/app/js/ContentCacheManager.js
View file

@ -25,13 +25,20 @@ async function update(contentDir, filePath) {
const extractor = new PdfStreamsExtractor()
const ranges = []
const newRanges = []
const seenHashes = new Set()
for await (const chunk of stream) {
const pdfStreams = extractor.consume(chunk)
for (const pdfStream of pdfStreams) {
if (pdfStream.end - pdfStream.start < MIN_CHUNK_SIZE) continue
const hash = pdfStreamHash(pdfStream.buffers)
const range = { start: pdfStream.start, end: pdfStream.end, hash }
ranges.push(range)
// Optimization: Skip writing of duplicate streams.
if (seenHashes.has(hash)) continue
seenHashes.add(hash)
if (await writePdfStream(contentDir, hash, pdfStream.buffers)) {
newRanges.push(range)
}