qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-07-01 06:29:59 +02:00
Code Issues Releases Wiki Activity

Merge pull request #58 from kba/unorderedgroupindexed
All checks were successful
continuous-integration/drone/push Build is passing
Details

Browse source 
ReadingOrder may also contain UnorderedGroupIndexed
This commit is contained in:
Mike Gerber 2021-05-18 18:32:32 +02:00 • committed by GitHub
commit 0b9af3a21e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
qurator/dinglehopper/ocr_files.py
View file

@ -97,14 +97,14 @@ def extract_texts_from_reading_order_group(group, tree, nsmap, textequiv_level):
ro_children = filter(lambda child: "index" in child.attrib.keys(), ro_children)
ro_children = sorted(ro_children, key=lambda child: int(child.attrib["index"]))
elif ET.QName(group.tag).localname == "UnorderedGroup":
elif ET.QName(group.tag).localname in ["UnorderedGroup","UnorderedGroupIndexed"]:
ro_children = list(group)
else:
raise NotImplementedError
for ro_child in ro_children:
if ET.QName(ro_child.tag).localname in ["OrderedGroup", "OrderedGroupIndexed", "UnorderedGroup"]:
if ET.QName(ro_child.tag).localname in ["OrderedGroup", "OrderedGroupIndexed", "UnorderedGroup", "UnorderedGroupIndexed"]:
regions.extend(
extract_texts_from_reading_order_group(
ro_child, tree, nsmap, textequiv_level