qurator-spk/modstool
1
0
Fork 0
mirror of https://github.com/qurator-spk/modstool.git synced 2025-11-04 03:14:14 +01:00
Code Issues Releases Wiki Activity

✨ ALTO: Count alto:Tags

Browse source
This commit is contained in:
Gerber, Mike 2022-06-17 17:32:17 +02:00
parent de50f13043
commit a40716a320
2 changed files with 20 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
qurator/modstool/alto4pandas.py
View file

@ -86,7 +86,8 @@ def alto_to_dict(alto, raise_errors=True):
elif localname == 'Styles':
pass
elif localname == 'Tags':
pass
value[localname] = {}
value[localname].update(TagGroup(tag, group).subelement_counts())
else:
if raise_errors:
print(value)

18
qurator/modstool/tests/test_alto.py
View file

@ -37,3 +37,21 @@ def test_Page_counts():
assert d['Layout_Page_TextBlock-count'] == 1
assert d['Layout_Page_TextLine-count'] == 3
assert d['Layout_Page_String-count'] == 6
def test_Tags_counts():
d = dict_fromstring("""
<alto xmlns="http://www.loc.gov/standards/alto/ns-v2#">
<Tags>
<NamedEntityTag ID="PER0" LABEL="Pentlings"/>
<NamedEntityTag ID="LOC1" LABEL="Pentling"/>
<NamedEntityTag ID="LOC2" LABEL="Hamm"/>
<NamedEntityTag ID="PER4" LABEL="Hofes Pentling"/>
<NamedEntityTag ID="LOC5" LABEL="Hofs Pentling"/>
<NamedEntityTag ID="LOC7" LABEL="Hilbeck"/>
<NamedEntityTag ID="PER8" LABEL="Hoff"/>
<NamedEntityTag ID="PER9" LABEL="L i b e r"/>
<NamedEntityTag ID="PER10" LABEL="Jhesu Christi"/>
</Tags>
</alto>
""")
assert d['Tags_NamedEntityTag-count'] == 9