zydronium/manage.get.gov
1
0
Fork 0
mirror of https://github.com/cisagov/manage.get.gov.git synced 2025-08-27 19:43:43 +02:00
Code Issues Projects Releases Packages Wiki Activity

Fix linter C901 error

Browse source
This commit is contained in:
zandercymatics 2025-01-10 10:46:58 -07:00
parent 104b1f8848
commit 0ddb3a2ca7
No known key found for this signature in database
GPG key ID: FF4636ABEC9682B7
1 changed files with 56 additions and 51 deletions
Download patch file Download diff file Expand all files Collapse all files

107
src/registrar/management/commands/patch_suborganizations.py
View file

@ -27,57 +27,10 @@ class Command(BaseCommand):
normalize_string("USDA/ARS/NAL"): {"replace_with": "USDA, ARS, NAL"}, normalize_string("USDA/ARS/NAL"): {"replace_with": "USDA, ARS, NAL"},
} }
# First: Group all suborganization names by their "normalized" names (finding duplicates). # Second: loop through every Suborganization and return a dict of what to keep, and what to delete
# Returns a dict that looks like this: # for each duplicate or "incorrect" record. We do this by pruning records with extra spaces or bad caps
# { # Note that "extra_records_to_prune" is just a manual mapping.
# "amtrak": [<Suborganization: AMTRAK>, <Suborganization: aMtRaK>, <Suborganization: AMTRAK >], records_to_prune = self.get_records_to_prune(extra_records_to_prune)
# "usda/oc": [<Suborganization: USDA/OC>],
# ...etc
# }
#
name_groups = {}
for suborg in Suborganization.objects.all():
normalized_name = normalize_string(suborg.name)
if normalized_name not in name_groups:
name_groups[normalized_name] = []
name_groups[normalized_name].append(suborg)
# Second: find the record we should keep, and the records we should delete
# Returns a dict that looks like this:
# {
# "amtrak": {
# "keep": <Suborganization: AMTRAK>
# "delete": [<Suborganization: aMtRaK>, <Suborganization: AMTRAK >]
# },
# "usda/oc": {
# "keep": <Suborganization: USDA, Office of Communications>,
# "delete": [<Suborganization: USDA/OC>]
# },
# ...etc
# }
records_to_prune = {}
for normalized_name, duplicate_suborgs in name_groups.items():
# Delete data from our preset list
if normalized_name in extra_records_to_prune:
# The 'keep' field expects a Suborganization but we just pass in a string, so this is just a workaround.
# This assumes that there is only one item in the name_group array (see usda/oc example).
# But this should be fine, given our data.
hardcoded_record_name = extra_records_to_prune[normalized_name]["replace_with"]
name_group = name_groups.get(normalize_string(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)),
)
records_to_prune[normalized_name] = {
"keep": best_record,
"delete": [s for s in duplicate_suborgs if s != best_record],
}
if len(records_to_prune) == 0: if len(records_to_prune) == 0:
TerminalHelper.colorful_logger(logger.error, TerminalColors.FAIL, "No suborganizations to delete.") TerminalHelper.colorful_logger(logger.error, TerminalColors.FAIL, "No suborganizations to delete.")
return return
@ -126,3 +79,55 @@ class Command(BaseCommand):
TerminalHelper.colorful_logger( TerminalHelper.colorful_logger(
logger.error, TerminalColors.FAIL, f"Failed to delete suborganizations: {str(e)}" logger.error, TerminalColors.FAIL, f"Failed to delete suborganizations: {str(e)}"
) )
def get_records_to_prune(self, extra_records_to_prune):
"""Maps all suborgs into a dictionary with a record to keep, and an array of records to delete."""
# 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
# }
#
name_groups = {}
for suborg in Suborganization.objects.all():
normalized_name = normalize_string(suborg.name)
name_groups.setdefault(normalized_name, []).append(suborg)
# Second: find the record we should keep, and the records we should delete
# Returns a dict that looks like this:
# {
# "amtrak": {
# "keep": <Suborganization: AMTRAK>
# "delete": [<Suborganization: aMtRaK>, <Suborganization: AMTRAK >]
# },
# "usda/oc": {
# "keep": <Suborganization: USDA, Office of Communications>,
# "delete": [<Suborganization: USDA/OC>]
# },
# ...etc
# }
records_to_prune = {}
for normalized_name, duplicate_suborgs in name_groups.items():
# Delete data from our preset list
if normalized_name in extra_records_to_prune:
# The 'keep' field expects a Suborganization but we just pass in a string, so this is just a workaround.
# This assumes that there is only one item in the name_group array (see usda/oc example).
# But this should be fine, given our data.
hardcoded_record_name = extra_records_to_prune[normalized_name]["replace_with"]
name_group = name_groups.get(normalize_string(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)),
)
records_to_prune[normalized_name] = {
"keep": best_record,
"delete": [s for s in duplicate_suborgs if s != best_record],
}
return records_to_prune