qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-07 19:05:13 +02:00
Code Issues Releases Wiki Activity

Merge pull request #49 from kba/zip_input_files

Browse source 
ocrd cli: use core-provided zip_input_files method
This commit is contained in:
Mike Gerber 2020-11-19 18:54:21 +01:00 • committed by GitHub
commit 62670dd0c7
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

28
qurator/dinglehopper/ocrd_cli.py
View file

@ -34,7 +34,7 @@ class OcrdDinglehopperEvaluate(Processor):
textequiv_level = self.parameter["textequiv_level"] textequiv_level = self.parameter["textequiv_level"]
gt_grp, ocr_grp = self.input_file_grp.split(",") gt_grp, ocr_grp = self.input_file_grp.split(",")
input_file_tuples = self._zip_input_files([gt_grp, ocr_grp]) input_file_tuples = self.zip_input_files(on_error='abort')
for n, (gt_file, ocr_file) in enumerate(input_file_tuples): for n, (gt_file, ocr_file) in enumerate(input_file_tuples):
if not gt_file or not ocr_file: if not gt_file or not ocr_file:
# file/page was not found in this group # file/page was not found in this group
@ -77,31 +77,5 @@ class OcrdDinglehopperEvaluate(Processor):
# Clear cache between files # Clear cache between files
levenshtein_matrix_cache_clear() levenshtein_matrix_cache_clear()
def _zip_input_files(self, input_file_grps):
log = getLogger("processor.OcrdDinglehopperEvaluate")
input_file_tuples = list()
for page_id in (
[self.page_id] if self.page_id else self.workspace.mets.physical_pages
):
ifiles = list()
for input_file_grp in input_file_grps:
log.debug(
"Adding input file group %s to page %s", input_file_grp, page_id
)
files = self.workspace.mets.find_all_files(
pageId=page_id, fileGrp=input_file_grp
)
if not files:
log.error(
'Found no page "%s" in file group %s', page_id, input_file_grp
)
ifiles.append(None)
else:
ifiles.append(files[0])
if ifiles[0]:
input_file_tuples.append(tuple(ifiles))
return input_file_tuples
if __name__ == "__main__": if __name__ == "__main__":
ocrd_dinglehopper() ocrd_dinglehopper()