Skip to content

Commit c3d67fe

Browse files
zubeydecivelekkpsherva
authored andcommitted
fix(dumper) use the dump creation date
1 parent ca6f8ae commit c3d67fe

8 files changed

Lines changed: 34 additions & 1 deletion

File tree

cds_migrator_kit/transform/dumper.py

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -42,7 +42,10 @@ def first_created(self):
4242
"""Get first record creation date."""
4343
# modification datetime of first revision is the creation date of the whole record
4444
# this assumption is based on the hstRECORD dump from invenio-migrator module
45-
return self.data["record"][0]["modification_datetime"]
45+
# for older records first revision is not the creation of record
46+
# so we added creation_date field to dump and it's getting it from bibrec
47+
# https://github.com/inveniosoftware/invenio-migrator/blob/master/invenio_migrator/legacy/records.py#L216
48+
return self.data["creation_date"]
4649

4750
def prepare_revisions(self):
4851
"""Prepare revisions."""

tests/cds-rdm/data/bulletin_issue/dumps/test_records.json

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,7 @@
33
"files": [],
44
"collections": null,
55
"recid": 2234683,
6+
"creation_date": "2020-05-01 00:00:00",
67
"record": [
78
{
89
"marcxml": "<record>\n <controlfield tag=\"001\">2234683</controlfield>\n <controlfield tag=\"005\">20220323170811.0</controlfield>\n <datafield tag=\"690\" ind1=\"C\" ind2=\" \">\n <subfield code=\"a\">CERN Bulletin Printable Version</subfield>\n </datafield>\n <datafield tag=\"773\" ind1=\" \" ind2=\" \">\n <subfield code=\"y\">2020</subfield>\n </datafield>\n <datafield tag=\"787\" ind1=\" \" ind2=\" \">\n <subfield code=\"w\">1713049</subfield>\n <subfield code=\"i\">issue</subfield>\n </datafield>\n <datafield tag=\"980\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">Bulletin</subfield>\n </datafield>\n <datafield tag=\"980\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">BULLETINEVENTS</subfield>\n </datafield>\n <datafield tag=\"925\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">5-</subfield>\n </datafield>\n <datafield tag=\"260\" ind1=\" \" ind2=\" \">\n <subfield code=\"c\">2020</subfield>\n </datafield>\n <datafield tag=\"245\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">CERN Bulletin Issue No. 56</subfield>\n </datafield>\n <datafield tag=\"246\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">5-6/2020</subfield>\n </datafield>\n <datafield tag=\"916\" ind1=\" \" ind2=\" \">\n <subfield code=\"z\">5-6</subfield>\n </datafield>\n <datafield tag=\"925\" ind1=\" \" ind2=\" \">\n <subfield code=\"b\">-6</subfield>\n </datafield>\n</record>",

tests/cds-rdm/data/hr/dumps/test_records.json

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,7 @@
33
"files": [],
44
"collections": null,
55
"recid": 2647384,
6+
"creation_date": "2018-11-16 14:14:00",
67
"record": [
78
{
89
"marcxml": "<record>\n <controlfield tag=\"001\">2647384</controlfield>\n <controlfield tag=\"005\">20210427161418.0</controlfield>\n <datafield tag=\"037\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">CERN-STAFF-RULES-ED01</subfield>\n </datafield>\n <datafield tag=\"041\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">eng</subfield>\n </datafield>\n<datafield tag=\"041\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">fr</subfield>\n </datafield>\n <datafield tag=\"246\" ind1=\" \" ind2=\"1\">\n <subfield code=\"a\">Mobilit\u00e9 interne</subfield>\n </datafield>\n <datafield tag=\"260\" ind1=\" \" ind2=\" \">\n <subfield code=\"c\">2021</subfield>\n </datafield>\n <datafield tag=\"269\" ind1=\" \" ind2=\" \">\n <subfield code=\"b\">CERN</subfield>\n <subfield code=\"a\">Geneva</subfield>\n <subfield code=\"c\">01 May 2021</subfield>\n </datafield>\n <datafield tag=\"591\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">CERN Internal</subfield>\n </datafield>\n <datafield tag=\"270\" ind1=\" \" ind2=\" \">\n <subfield code=\"m\">admin@inveniosoftware.org</subfield>\n </datafield>\n <datafield tag=\"690\" ind1=\"C\" ind2=\" \">\n <subfield code=\"a\">Administrative Circular</subfield>\n </datafield>\n <datafield tag=\"710\" ind1=\" \" ind2=\" \">\n <subfield code=\"5\">HR</subfield>\n <subfield code=\"b\">DI</subfield>\n </datafield>\n <datafield tag=\"773\" ind1=\" \" ind2=\" \">\n <subfield code=\"t\">HR-DHO</subfield>\n </datafield>\n <datafield tag=\"925\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">2021-05-01</subfield>\n <subfield code=\"b\">2222-12-31</subfield>\n </datafield>\n <datafield tag=\"980\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">STAFFRULES</subfield>\n </datafield>\n </record>",
@@ -45,6 +46,7 @@
4546
],
4647
"collections": null,
4748
"recid": 2364643,
49+
"creation_date": "2018-11-16 14:14:00",
4850
"record": [
4951
{
5052
"marcxml": "<record>\n <controlfield tag=\"001\">2364643</controlfield>\n <controlfield tag=\"005\">20210427161418.0</controlfield>\n <datafield tag=\"245\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">Another document</subfield>\n </datafield>\n <datafield tag=\"260\" ind1=\" \" ind2=\" \">\n <subfield code=\"c\">2021</subfield>\n </datafield>\n <datafield tag=\"269\" ind1=\" \" ind2=\" \">\n <subfield code=\"b\">CERN</subfield>\n <subfield code=\"a\">Geneva</subfield>\n <subfield code=\"c\">01 May 2021</subfield>\n </datafield>\n <datafield tag=\"591\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">PUBLIC</subfield>\n </datafield>\n <datafield tag=\"270\" ind1=\" \" ind2=\" \">\n <subfield code=\"m\">admin@inveniosoftware.org</subfield>\n </datafield>\n <datafield tag=\"690\" ind1=\"C\" ind2=\" \">\n <subfield code=\"a\">Administrative Circular</subfield>\n </datafield>\n <datafield tag=\"710\" ind1=\" \" ind2=\" \">\n <subfield code=\"5\">HR</subfield>\n <subfield code=\"b\">DI</subfield>\n </datafield>\n <datafield tag=\"773\" ind1=\" \" ind2=\" \">\n <subfield code=\"t\">HR-DHO</subfield>\n </datafield>\n <datafield tag=\"925\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">2025-12-09</subfield>\n <subfield code=\"b\">9999-12-31</subfield>\n </datafield>\n <datafield tag=\"980\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">ADMINCIRCULAR</subfield>\n </datafield>\n </record>",

tests/cds-rdm/data/hr_restricted/dumps/test_records.json

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -33,6 +33,7 @@
3333
],
3434
"collections": null,
3535
"recid": 555555,
36+
"creation_date": "2019-05-06 04:03:12",
3637
"record": [
3738
{
3839
"marcxml": "<record>\n <controlfield tag=\"001\">555555</controlfield>\n <controlfield tag=\"005\">20210427161418.0</controlfield>\n <datafield tag=\"245\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">Another document</subfield>\n </datafield>\n <datafield tag=\"260\" ind1=\" \" ind2=\" \">\n <subfield code=\"c\">2021</subfield>\n </datafield>\n <datafield tag=\"269\" ind1=\" \" ind2=\" \">\n <subfield code=\"b\">CERN</subfield>\n <subfield code=\"a\">Geneva</subfield>\n <subfield code=\"c\">01 May 2021</subfield>\n </datafield>\n <datafield tag=\"591\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">PUBLIC</subfield>\n </datafield>\n <datafield tag=\"270\" ind1=\" \" ind2=\" \">\n <subfield code=\"m\">admin@inveniosoftware.org</subfield>\n </datafield>\n <datafield tag=\"690\" ind1=\"C\" ind2=\" \">\n <subfield code=\"a\">Administrative Circular</subfield>\n </datafield>\n <datafield tag=\"710\" ind1=\" \" ind2=\" \">\n <subfield code=\"5\">HR</subfield>\n <subfield code=\"b\">DI</subfield>\n </datafield>\n <datafield tag=\"773\" ind1=\" \" ind2=\" \">\n <subfield code=\"t\">HR-DHO</subfield>\n </datafield>\n <datafield tag=\"925\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">2025-12-09</subfield>\n <subfield code=\"b\">9999-12-31</subfield>\n </datafield>\n <datafield tag=\"980\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">ADMINCIRCULAR</subfield>\n </datafield>\n </record>",
@@ -75,6 +76,7 @@
7576
],
7677
"collections": null,
7778
"recid": 23646466,
79+
"creation_date": "2013-09-06 09:31:03",
7880
"record": [
7981
{
8082
"marcxml": "<record>\n <controlfield tag=\"001\">23646466</controlfield>\n <controlfield tag=\"005\">20210427161418.0</controlfield>\n <datafield tag=\"245\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">Another document</subfield>\n </datafield>\n <datafield tag=\"260\" ind1=\" \" ind2=\" \">\n <subfield code=\"c\">2021</subfield>\n </datafield>\n <datafield tag=\"269\" ind1=\" \" ind2=\" \">\n <subfield code=\"b\">CERN</subfield>\n <subfield code=\"a\">Geneva</subfield>\n <subfield code=\"c\">01 May 2021</subfield>\n </datafield>\n <datafield tag=\"591\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">PUBLIC</subfield>\n </datafield>\n <datafield tag=\"270\" ind1=\" \" ind2=\" \">\n <subfield code=\"m\">admin@inveniosoftware.org</subfield>\n </datafield>\n <datafield tag=\"690\" ind1=\"C\" ind2=\" \">\n <subfield code=\"a\">Administrative Circular</subfield>\n </datafield>\n <datafield tag=\"710\" ind1=\" \" ind2=\" \">\n <subfield code=\"5\">HR</subfield>\n <subfield code=\"b\">DI</subfield>\n </datafield>\n <datafield tag=\"773\" ind1=\" \" ind2=\" \">\n <subfield code=\"t\">HR-DHO</subfield>\n </datafield>\n <datafield tag=\"925\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">2025-12-09</subfield>\n <subfield code=\"b\">9999-12-31</subfield>\n </datafield>\n <datafield tag=\"980\" ind1=\" \" ind2=\" \">\n <subfield code=\"a\">ADMINCIRCULAR</subfield>\n </datafield>\n </record>",

0 commit comments

Comments
 (0)