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

ReadingOrder may also contain UnorderedGroupIndexed

Browse source
This commit is contained in:
Konstantin Baierer 2021-05-18 17:34:08 +02:00
parent 1778b36a9a
commit 7fde00d911
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 = filter(lambda child: "index" in child.attrib.keys(), ro_children)
ro_children = sorted(ro_children, key=lambda child: int(child.attrib["index"])) 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) ro_children = list(group)
else: else:
raise NotImplementedError raise NotImplementedError
for ro_child in ro_children: 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( regions.extend(
extract_texts_from_reading_order_group( extract_texts_from_reading_order_group(
ro_child, tree, nsmap, textequiv_level ro_child, tree, nsmap, textequiv_level