qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-09 11:50:00 +02:00
Code Issues Releases Wiki Activity

🐛 Fix OCR-D CLI for newest OCR-D

Browse source 
Now that find_files() is a generator, we can't use [0] to get the file.
This commit is contained in:
Gerber, Mike 2020-10-16 14:58:17 +02:00
parent 5ed184c8c4
commit f2367ac0c3
2 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
qurator/dinglehopper/ocrd_cli.py
View file

@ -34,8 +34,8 @@ class OcrdDinglehopperEvaluate(Processor):
metrics = self.parameter['metrics'] metrics = self.parameter['metrics']
gt_grp, ocr_grp = self.input_file_grp.split(',') gt_grp, ocr_grp = self.input_file_grp.split(',')
for n, page_id in enumerate(self.workspace.mets.physical_pages): for n, page_id in enumerate(self.workspace.mets.physical_pages):
gt_file = self.workspace.mets.find_files(fileGrp=gt_grp, pageId=page_id)[0] gt_file = next(self.workspace.mets.find_files(fileGrp=gt_grp, pageId=page_id))
ocr_file = self.workspace.mets.find_files(fileGrp=ocr_grp, pageId=page_id)[0] ocr_file = next(self.workspace.mets.find_files(fileGrp=ocr_grp, pageId=page_id))
gt_file = self.workspace.download_file(gt_file) gt_file = self.workspace.download_file(gt_file)
ocr_file = self.workspace.download_file(ocr_file) ocr_file = self.workspace.download_file(ocr_file)
log.info("INPUT FILES %i / %s↔ %s", n, gt_file, ocr_file) log.info("INPUT FILES %i / %s↔ %s", n, gt_file, ocr_file)

4
requirements.txt
View file

@ -5,7 +5,7 @@ uniseg
numpy numpy
colorama colorama
MarkupSafe MarkupSafe
ocrd >= 2.13.1 ocrd >= 2.18.0
attrs attrs
multimethod == 1.3 # latest version to officially support Python 3.5 multimethod == 1.3 # latest version to officially support Python 3.5
tqdm tqdm