qurator-spk/ocrd_repair_inconsistencies
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd_repair_inconsistencies.git synced 2025-10-31 08:54:13 +01:00
Code Issues Releases Wiki Activity

Merge pull request #10 from kba/file-ids-and-such

Browse source 
use make_file_id and assert_file_grp_cardinality
This commit is contained in:
Mike Gerber 2020-08-12 11:51:47 +02:00 • committed by GitHub
commit 8182063a4f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

11
ocrd_repair_inconsistencies/ocrd_repair_inconsistencies.py
View file

@ -11,7 +11,9 @@ from ocrd_models.ocrd_page import (
to_xml to_xml
) )
from ocrd_utils import ( from ocrd_utils import (
getLogger, concat_padded, assert_file_grp_cardinality,
getLogger,
make_file_id,
polygon_from_points, polygon_from_points,
MIMETYPE_PAGE MIMETYPE_PAGE
) )
@ -30,6 +32,9 @@ class RepairInconsistencies(Processor):
super(RepairInconsistencies, self).__init__(*args, **kwargs) super(RepairInconsistencies, self).__init__(*args, **kwargs)
def process(self): def process(self):
assert_file_grp_cardinality(self.input_file_grp, 1)
assert_file_grp_cardinality(self.output_file_grp, 1)
for (n, input_file) in enumerate(self.input_files): for (n, input_file) in enumerate(self.input_files):
page_id = input_file.pageId or input_file.ID page_id = input_file.pageId or input_file.ID
LOG.info("INPUT FILE %i / %s", n, page_id) LOG.info("INPUT FILE %i / %s", n, page_id)
@ -101,9 +106,7 @@ class RepairInconsistencies(Processor):
_fix_segment(word, page_id, reverse=(readingDirection == 'right-to-left')) _fix_segment(word, page_id, reverse=(readingDirection == 'right-to-left'))
file_id = input_file.ID.replace(self.input_file_grp, self.output_file_grp) file_id = make_file_id(input_file, self.output_file_grp)
if file_id == input_file.ID:
file_id = concat_padded(self.output_file_grp, n)
self.workspace.add_file( self.workspace.add_file(
ID=file_id, ID=file_id,
file_grp=self.output_file_grp, file_grp=self.output_file_grp,