qurator-spk/ocrd-galley
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd-galley.git synced 2025-06-09 06:39:53 +02:00
Code Issues Projects Releases Wiki Activity

Add a PAGE validation step

Browse source
This commit is contained in:
Gerber, Mike 2019-06-19 14:55:50 +02:00
parent 10c4068a99
commit d98ce2d2d4
3 changed files with 4643 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
my_ocrd_workflow
View file

@ -54,10 +54,20 @@ do_ocr() {
#ocrd workspace validate mets.xml
}
page_validate_xml() {
filegrp=$1
local file
for file in `ocrd workspace find -G $filegrp`; do
xmllint --noout --schema `dirname $0`/xsd/pagecontent.2018-07-15.xsd $file
done
}
do_fontident
do_linesegmentation
do_ocr
page_validate_xml OCR-D-OCR-TESS # This also makes sure PAGE Viewer can open it
# XXX Multiple calls create multiple identical mets:agent elements