Andreas/siyuan
1
0
Fork 0
mirror of https://github.com/siyuan-note/siyuan.git synced 2025-12-16 22:50:13 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

🎨 PDF files longer than 1024 pages are not included in asset file content searching https://github.com/siyuan-note/siyuan/issues/9053

Browse source
This commit is contained in:
Daniel 2023-08-27 11:09:19 +08:00
parent fd32668abc
commit b578506ea5
No known key found for this signature in database
GPG key ID: 86211BA83DF03017
1 changed files with 5 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

7
kernel/model/asset_content.go
View file

@ -748,7 +748,7 @@ func (parser *PdfAssetParser) getTextPageWorker(id int, instance pdfium.Pdfium,
// Parse will parse a PDF document using PDFium webassembly module using a worker pool
func (parser *PdfAssetParser) Parse(absPath string) (ret *AssetParseResult) {
st := time.Now()
now := time.Now()
if !strings.HasSuffix(strings.ToLower(absPath), ".pdf") {
return
}
@ -850,7 +850,10 @@ func (parser *PdfAssetParser) Parse(absPath string) (ret *AssetParseResult) {
}
}
close(results)
logging.LogInfof("convert [%s] PDF with %d pages using %d workers took %s.\n", tmp, pc.PageCount, cores, time.Since(st))
if 256 < pc.PageCount {
logging.LogInfof("convert [%s] PDF with [%d[ pages using [%d] workers took [%s]", absPath, pc.PageCount, cores, time.Since(now))
}
// loop through ordered PDF text pages and join content for asset parse DB result
content := ""