qurator-spk/ocrd-galley
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd-galley.git synced 2025-10-30 18:54:14 +01:00
Code Issues Projects Releases Wiki Activity

🚧 Work around problems with ocrd-tesserocr producing TextEquiv/@conf

Browse source
This commit is contained in:
Gerber, Mike 2019-08-05 15:40:39 +02:00
parent 8b67866aac
commit 44772f1923
1 changed files with 15 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

17
my_ocrd_workflow
View file

@ -106,8 +106,21 @@ page_fix_image_references() {
done done
} }
page_workaround_remove_conf() {
# XXX Work around https://github.com/OCR-D/core/issues/269
do_fontident filegrp=$1
local file
for file in `ocrd workspace find -G $filegrp`; do
xmlstarlet ed --inplace \
-N 'page=http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15' \
-d '//page:TextEquiv/@conf' $file
done
}
# XXX do_fontident
do_binarization do_binarization
do_validate do_validate
@ -119,9 +132,9 @@ do_validate
do_ocr do_ocr
page_validate_xml OCR-D-OCR-TESS page_validate_xml OCR-D-OCR-TESS
page_workaround_remove_conf OCR-D-OCR-TESS
do_validate do_validate
page_fix_image_references OCR-D-OCR-TESS page_fix_image_references OCR-D-OCR-TESS
# vim:tw=120: # vim:tw=120: