1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-09 20:00:01 +02:00

🧹 dinglehopper: Do not hardcode joiner to \n

This commit is contained in:
Gerber, Mike 2020-10-20 18:43:56 +02:00
parent 3848412349
commit 75733039b8

View file

@ -187,6 +187,9 @@ class ExtractedText:
children_for_localname = { children_for_localname = {
'TextRegion': 'TextLine' 'TextRegion': 'TextLine'
} }
joiner_for_textequiv_level = {
'line': '\n'
}
segment_id = text_segment.attrib['id'] segment_id = text_segment.attrib['id']
localname = ET.QName(text_segment).localname localname = ET.QName(text_segment).localname
@ -209,7 +212,7 @@ class ExtractedText:
sub_segment, nsmap, sub_segment, nsmap,
textequiv_level=sub_textequiv_level) textequiv_level=sub_textequiv_level)
) )
joiner = '\n' # XXX joiner = joiner_for_textequiv_level[sub_textequiv_level]
return cls(segment_id, segments, joiner, None) return cls(segment_id, segments, joiner, None)