You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
ocrd-galley/my_ocrd_workflow

29 lines
1.1 KiB
Plaintext

5 years ago
#!/bin/bash
set -e # Abort on error
set -x
remove_filegrp() {
filegrp_use=$1
mets=$2
xmlstarlet ed --inplace \
-N mets=http://www.loc.gov/METS/ \
-d "//mets:fileGrp[@USE='$filegrp_use']" $mets
}
remove_filegrp OCR-D-FONTIDENT mets.xml
ocrd-typegroups-classifier -l DEBUG -m mets.xml -I OCR-D-IMG -O OCR-D-FONTIDENT -p <(echo '{"network": "/home/mike/devel/OCR-D/monorepo/ocrd_typegroups_classifier/ocrd_typegroups_classifier/models/classifier.tgc", "stride":143}')
# XXX does DEFAULT have any meaning? /buerger_gedichte_1778.ocrd does not have
# any DEFAULT, yet -I DEFAULT seems to work for ocrd-typegroups-classifier
#ocrd workspace validate mets.xml
# XXX <error>Unspecified USE category 'FONTIDENT' in fileGrp 'OCR-D-FONTIDENT'</error>
# XXX <error>File 'OCR-D-FONTIDENT_OCR-D-IMG_0002' does not manifest any physical page.</error>
# XXX <notice>Won't download remote image <OCR-D-IMG/OCR-D-IMG_0002></notice>
remove_filegrp OCR-D-SEG-LINE mets.xml
ocrd-tesserocr-segment-line -l DEBUG -m mets.xml -I OCR-D-IMG -O OCR-D-SEG-LINE
#ocrd workspace validate mets.xml