qurator-spk/modstool
1
0
Fork 0
mirror of https://github.com/qurator-spk/modstool.git synced 2025-08-07 00:29:55 +02:00
Code Issues Releases Wiki Activity

🧹 MODS: Filter UUID

Browse source
This commit is contained in:
Gerber, Mike 2025-08-05 20:53:43 +02:00
parent c25de380b4
commit feb8d09126
1 changed files with 4 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/mods4pandas/mods4pandas.py
View file

@ -162,12 +162,16 @@ def mods_to_dict(mods, raise_errors=True):
.descend(raise_errors) .descend(raise_errors)
) )
elif tag == "{http://www.loc.gov/mods/v3}recordIdentifier": elif tag == "{http://www.loc.gov/mods/v3}recordIdentifier":
def no_uuid(record_identifier):
return record_identifier.attrib.get("type") != "uuid"
# By default we assume source="gbv-ppn" mods:recordIdentifiers (= PPNs), # By default we assume source="gbv-ppn" mods:recordIdentifiers (= PPNs),
# however, in mods:relatedItems, there may be source="dnb-ppns", # however, in mods:relatedItems, there may be source="dnb-ppns",
# which we need to distinguish by using a separate field name. # which we need to distinguish by using a separate field name.
try: try:
value["recordIdentifier"] = ( value["recordIdentifier"] = (
TagGroup(tag, group) TagGroup(tag, group)
.filter(no_uuid)
.is_singleton() .is_singleton()
.has_attributes({"source": "gbv-ppn"}) .has_attributes({"source": "gbv-ppn"})
.text() .text()