mirror of
https://github.com/qurator-spk/ocrd-galley.git
synced 2025-06-08 22:29:56 +02:00
Add a PAGE validation step
This commit is contained in:
parent
10c4068a99
commit
d98ce2d2d4
3 changed files with 4643 additions and 0 deletions
|
@ -54,10 +54,20 @@ do_ocr() {
|
||||||
#ocrd workspace validate mets.xml
|
#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_fontident
|
||||||
do_linesegmentation
|
do_linesegmentation
|
||||||
do_ocr
|
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
|
# XXX Multiple calls create multiple identical mets:agent elements
|
||||||
|
|
2137
xsd/pagecontent.2017-07-15.xsd
Normal file
2137
xsd/pagecontent.2017-07-15.xsd
Normal file
File diff suppressed because it is too large
Load diff
2496
xsd/pagecontent.2018-07-15.xsd
Normal file
2496
xsd/pagecontent.2018-07-15.xsd
Normal file
File diff suppressed because it is too large
Load diff
Loading…
Add table
Add a link
Reference in a new issue