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

Add a PAGE fix XML step

Browse source
This commit is contained in:
Gerber, Mike 2019-06-19 15:03:16 +02:00
parent d98ce2d2d4
commit b6c490e18b
1 changed files with 11 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

11
my_ocrd_workflow
View file

@ -54,6 +54,16 @@ do_ocr() {
#ocrd workspace validate mets.xml #ocrd workspace validate mets.xml
} }
page_fix_xml() {
# XXX core does not produce valid XML https://github.com/OCR-D/core/issues/242
filegrp=$1
local file
for file in `ocrd workspace find -G $filegrp`; do
sed -i 's#pagecontent/2017-07-15#pagecontent/2018-07-15#g' $file
done
}
page_validate_xml() { page_validate_xml() {
filegrp=$1 filegrp=$1
@ -67,6 +77,7 @@ page_validate_xml() {
do_fontident do_fontident
do_linesegmentation do_linesegmentation
do_ocr do_ocr
page_fix_xml OCR-D-OCR-TESS
page_validate_xml OCR-D-OCR-TESS # This also makes sure PAGE Viewer can open it page_validate_xml OCR-D-OCR-TESS # This also makes sure PAGE Viewer can open it