zydronium/manage.get.gov
1
0
Fork 0
mirror of https://github.com/cisagov/manage.get.gov.git synced 2025-08-13 13:09:41 +02:00
Code Issues Projects Releases Packages Wiki Activity

Code comments + lint

Browse source
This commit is contained in:
zandercymatics 2025-01-09 12:24:03 -07:00
parent f170ab90ca
commit 028d033ff2
No known key found for this signature in database
GPG key ID: FF4636ABEC9682B7
1 changed files with 12 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

19
src/registrar/management/commands/patch_suborganizations.py
View file

@ -24,14 +24,14 @@ class Command(BaseCommand):
normalize_string("US Geological Survey"): {"keep": "U.S. Geological Survey"},
normalize_string("USDA/OC"): {"keep": "USDA, Office of Communications"},
normalize_string("GSA, IC, OGP WebPortfolio"): {"keep": "GSA, IC, OGP Web Portfolio"},
normalize_string("USDA/ARS/NAL"): {"keep": "USDA, ARS, NAL"}
# TODO - U.S Immigration and Customs Enforcement
normalize_string("USDA/ARS/NAL"): {"keep": "USDA, ARS, NAL"},
}
# First: Group all suborganization names by their "normalized" names (finding duplicates).
# Returns a dict that looks like this:
# {
# "amtrak": [<Suborganization: AMTRAK>, <Suborganization: aMtRaK>, <Suborganization: AMTRAK >],
# "usda/oc": [<Suborganization: USDA/OC>],
# ...etc
# }
#
@ -59,18 +59,19 @@ class Command(BaseCommand):
for normalized_name, duplicate_suborgs in name_groups.items():
# Delete data from our preset list
if normalized_name in extra_records_to_prune:
record = extra_records_to_prune.get(normalized_name)
# The 'keep' field expects a Suborganization but we just pass in a string, so this is just a workaround.
hardcoded_record_name = normalize_string(record.get("keep"))
name_group = name_groups.get(hardcoded_record_name, [])
# This assumes that there is only one item in the name_group array. Should be fine, given our data.
# This assumes that there is only one item in the name_group array (see usda/oc example). Should be fine, given our data.
hardcoded_record_name = extra_records_to_prune[normalized_name]["keep"]
name_group = name_groups.get(normalized_name(hardcoded_record_name), [])
keep = name_group[0] if name_group else None
records_to_prune[normalized_name] = {"keep": keep, "delete": duplicate_suborgs}
# Delete duplicates (extra spaces or casing differences)
elif len(duplicate_suborgs) > 1:
# Pick the best record (fewest spaces, most leading capitals)
best_record = max(duplicate_suborgs, key=lambda suborg: (-suborg.name.count(" "), count_capitals(suborg.name, leading_only=True)))
best_record = max(
duplicate_suborgs,
key=lambda suborg: (-suborg.name.count(" "), count_capitals(suborg.name, leading_only=True)),
)
records_to_prune[normalized_name] = {
"keep": best_record,
"delete": [s for s in duplicate_suborgs if s != best_record],
@ -95,7 +96,7 @@ class Command(BaseCommand):
preview_lines.append("")
preview = "\n".join(preview_lines)
# Fourth: Get user confirmation and execute deletions
# Fourth: Get user confirmation and delete
if TerminalHelper.prompt_for_execution(
system_exit_on_terminate=True,
prompt_message=preview,