mirror of
https://github.com/qurator-spk/ocrd-galley.git
synced 2025-06-09 06:39:53 +02:00
Add a PAGE fix XML step
This commit is contained in:
parent
d98ce2d2d4
commit
b6c490e18b
1 changed files with 11 additions and 0 deletions
|
@ -54,6 +54,16 @@ do_ocr() {
|
|||
#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() {
|
||||
filegrp=$1
|
||||
|
||||
|
@ -67,6 +77,7 @@ page_validate_xml() {
|
|||
do_fontident
|
||||
do_linesegmentation
|
||||
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
|
||||
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue