-
Notifications
You must be signed in to change notification settings - Fork 6
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #1651 from dchiller/i1644-clean-frag-and-dact-ids
Add command to standardize formatting of DACT IDs and Fragmentarium IDs
- Loading branch information
Showing
2 changed files
with
105 additions
and
0 deletions.
There are no files selected for viewing
49 changes: 49 additions & 0 deletions
49
django/cantusdb_project/main_app/management/commands/reformat_source_ids.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,49 @@ | ||
""" | ||
A command designed to do a one-time reformatting of DACT IDs and Fragment | ||
IDs in the database. | ||
Fragment IDs should be of the form "F-XXXX" where XXXX is some alphanumeric. | ||
Fragment IDs are currently assumed to be in the form "F-XXXX" or "XXXX". | ||
DACT IDs should be of the form "D:0XXXX" where XXXX is the Fragment ID alphanumeric. | ||
DACT IDs are currently assumed to be in the form "0XXXX" or "D-0XXXX". | ||
This command simply adds the prefix "F-" to all Fragment IDs and "D:" to all | ||
DACT IDs where they are missing. | ||
""" | ||
|
||
from django.core.management.base import BaseCommand | ||
|
||
from main_app.models import Source | ||
|
||
|
||
class Command(BaseCommand): | ||
help = "Reformat DACT IDs and Fragment IDs in the database." | ||
|
||
def handle(self, *args, **options): | ||
sources = Source.objects.all() | ||
for source in sources: | ||
if source.dact_id: | ||
if len(source.dact_id) == 5 and source.dact_id.startswith("0"): | ||
source.dact_id = f"D:{source.dact_id}" | ||
elif len(source.dact_id) == 7 and source.dact_id.startswith("D-0"): | ||
source.dact_id = f"D:{source.dact_id[2:]}" | ||
else: | ||
self.stdout.write( | ||
self.style.WARNING( | ||
f"{source.id} | DACT ID {source.dact_id} is not in the correct format." | ||
) | ||
) | ||
if source.fragmentarium_id: | ||
if len(source.fragmentarium_id) == 4: | ||
source.fragmentarium_id = f"F-{source.fragmentarium_id}" | ||
elif len( | ||
source.fragmentarium_id | ||
) == 6 and source.fragmentarium_id.startswith("F-"): | ||
pass | ||
else: | ||
self.stdout.write( | ||
self.style.WARNING( | ||
f"{source.id} | Fragment ID {source.fragmentarium_id} is not in the correct format." | ||
) | ||
) | ||
source.save() |
56 changes: 56 additions & 0 deletions
56
django/cantusdb_project/main_app/tests/test_reformat_source_ids.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,56 @@ | ||
from django.test import TestCase | ||
from django.core.management import call_command | ||
|
||
from main_app.models import Source | ||
from main_app.tests.make_fakes import make_fake_institution, make_fake_segment | ||
|
||
|
||
class TestReformatSourceIDs(TestCase): | ||
def test_command(self): | ||
segment = make_fake_segment() | ||
fake_inst = make_fake_institution() | ||
correct_source_1 = Source.objects.create( | ||
segment=segment, | ||
shelfmark="Correct Source 1", | ||
holding_institution=fake_inst, | ||
dact_id="0a1b3", | ||
fragmentarium_id="a1b3", | ||
) | ||
correct_source_2 = Source.objects.create( | ||
segment=segment, | ||
shelfmark="Correct Source 2", | ||
holding_institution=fake_inst, | ||
dact_id="D-0a1b3", | ||
fragmentarium_id="F-a1b3", | ||
) | ||
source_with_no_ids = Source.objects.create( | ||
segment=segment, | ||
shelfmark="Source with no IDs", | ||
holding_institution=fake_inst, | ||
) | ||
source_with_incorrect_ids = Source.objects.create( | ||
segment=segment, | ||
shelfmark="Source with incorrect IDs", | ||
holding_institution=fake_inst, | ||
dact_id="a1b3", | ||
fragmentarium_id="F-1b3", | ||
) | ||
|
||
call_command("reformat_source_ids") | ||
self.assertEqual(Source.objects.get(pk=correct_source_1.pk).dact_id, "D:0a1b3") | ||
self.assertEqual( | ||
Source.objects.get(pk=correct_source_1.pk).fragmentarium_id, "F-a1b3" | ||
) | ||
self.assertEqual(Source.objects.get(pk=correct_source_2.pk).dact_id, "D:0a1b3") | ||
self.assertEqual( | ||
Source.objects.get(pk=correct_source_2.pk).fragmentarium_id, "F-a1b3" | ||
) | ||
self.assertIsNone(Source.objects.get(pk=source_with_no_ids.pk).dact_id) | ||
self.assertIsNone(Source.objects.get(pk=source_with_no_ids.pk).fragmentarium_id) | ||
self.assertEqual( | ||
Source.objects.get(pk=source_with_incorrect_ids.pk).dact_id, "a1b3" | ||
) | ||
self.assertEqual( | ||
Source.objects.get(pk=source_with_incorrect_ids.pk).fragmentarium_id, | ||
"F-1b3", | ||
) |