qurator-spk/ocrd-galley
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd-galley.git synced 2025-10-31 19:24:12 +01:00
Code Issues Projects Releases Wiki Activity

🐛 ppn2ocr: Fix file:/ links to use file:///, and remove unavaiblable LOCAL file group

Browse source
This commit is contained in:
Gerber, Mike 2020-05-22 16:09:00 +02:00
parent 612d44b074
commit 8024064697
1 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ppn2ocr
View file

@ -18,9 +18,14 @@ oai_url="https://digital.staatsbibliothek-berlin.de/oai?verb=GetRecord&metadataP
echo "$oai_url"
curl "$oai_url" | xmlstarlet sel -t -c '//*[local-name()="mets"]' > mets.xml
# Fix 'file:/' URLs to 'file:///'
sed -i 's#file:/\([^/]\)#file:///\1#' mets.xml
# Patch mets.xml to use our NFS mount
sed -i 's#file:///goobi/tiff001/sbb/#file:///srv/digisam_images/sbb/#g' mets.xml
# Remove LOCAL file group as we do not have access to the files
ocrd workspace remove-group -rf --keep-files LOCAL
ocrd workspace validate mets.xml | grep -v "<notice>Won't download remote image"