Refacto load all functions

Unbounded LoadAll* loaders materialised an entire result set in one
query with no ceiling. A table that is small in development can grow
without bound in production, so these loaders were a latent memory
and query-time hazard.

Remove the LoadAll* methods from pkg/coredata and walk the cursor-
paginated LoadBy* siblings instead through a shared page.LoadAll
helper. The helper advances a MaxCursorSize forward cursor until the
result set is exhausted and concatenates the pages. It caps a single
call at MaxLoadAllPages (20) batches of 500 rows and errors past that
rather than materialising an unbounded set, so a runaway caller fails
loudly instead of exhausting memory.

Callers that genuinely need every row now express that explicitly,
and the coredata load-naming rule and docs are updated to discourage
new unbounded loaders.

Signed-off-by: Sacha Al Himdani <sacha@probo.com>
This commit is contained in:
Sacha Al Himdani
2026-06-09 19:33:36 +02:00
committed by Sacha Al Himdani
parent 853f2404a6
commit 9ab8ea2085
46 changed files with 1218 additions and 1674 deletions

View File

@@ -776,76 +776,6 @@ WHERE
return count, nil
}
func (v *ThirdParties) LoadAllByOrganizationID(
ctx context.Context,
conn pg.Querier,
scope Scoper,
organizationID gid.GID,
filter *ThirdPartyFilter,
) error {
q := `
SELECT
id,
organization_id,
parent_third_party_id,
common_third_party_id,
name,
description,
category,
headquarter_address,
legal_name,
website_url,
privacy_policy_url,
service_level_agreement_url,
data_processing_agreement_url,
business_associate_agreement_url,
subprocessors_list_url,
certifications,
countries,
business_owner_profile_id,
security_owner_profile_id,
status_page_url,
terms_of_service_url,
security_page_url,
trust_page_url,
show_on_trust_center,
level,
vetting_status,
vetting_website_url,
vetting_procedure,
vetting_processing_started_at,
vetting_error_message,
created_at,
updated_at
FROM
third_parties
WHERE
%s
AND organization_id = @organization_id
AND %s
ORDER BY name ASC
`
q = fmt.Sprintf(q, scope.SQLFragment(), filter.SQLFragment())
args := pgx.StrictNamedArgs{"organization_id": organizationID}
maps.Copy(args, scope.SQLArguments())
maps.Copy(args, filter.SQLArguments())
rows, err := conn.Query(ctx, q, args)
if err != nil {
return fmt.Errorf("cannot query thirdParties: %w", err)
}
thirdParties, err := pgx.CollectRows(rows, pgx.RowToAddrOfStructByName[ThirdParty])
if err != nil {
return fmt.Errorf("cannot collect thirdParties: %w", err)
}
*v = thirdParties
return nil
}
func (v *ThirdParties) LoadByOrganizationID(
ctx context.Context,
conn pg.Querier,
@@ -1230,113 +1160,6 @@ WHERE %s
return count, nil
}
func (vs *ThirdParties) LoadAllByDatumID(
ctx context.Context,
conn pg.Querier,
scope Scoper,
datumID gid.GID,
) error {
q := `
WITH vend AS (
SELECT
v.id,
v.tenant_id,
v.organization_id,
v.parent_third_party_id,
v.common_third_party_id,
v.name,
v.description,
v.category,
v.headquarter_address,
v.legal_name,
v.website_url,
v.privacy_policy_url,
v.service_level_agreement_url,
v.data_processing_agreement_url,
v.business_associate_agreement_url,
v.subprocessors_list_url,
v.certifications,
v.countries,
v.business_owner_profile_id,
v.security_owner_profile_id,
v.status_page_url,
v.terms_of_service_url,
v.security_page_url,
v.trust_page_url,
v.show_on_trust_center,
v.level,
v.vetting_status,
v.vetting_website_url,
v.vetting_procedure,
v.vetting_processing_started_at,
v.vetting_error_message,
v.created_at,
v.updated_at
FROM
third_parties v
INNER JOIN
data_third_parties dv ON v.id = dv.third_party_id
WHERE
dv.datum_id = @datum_id
)
SELECT
id,
organization_id,
parent_third_party_id,
common_third_party_id,
name,
description,
category,
headquarter_address,
legal_name,
website_url,
privacy_policy_url,
service_level_agreement_url,
data_processing_agreement_url,
business_associate_agreement_url,
subprocessors_list_url,
certifications,
countries,
business_owner_profile_id,
security_owner_profile_id,
status_page_url,
terms_of_service_url,
security_page_url,
trust_page_url,
show_on_trust_center,
level,
vetting_status,
vetting_website_url,
vetting_procedure,
vetting_processing_started_at,
vetting_error_message,
created_at,
updated_at
FROM
vend
WHERE %s
ORDER BY name ASC
`
q = fmt.Sprintf(q, scope.SQLFragment())
args := pgx.StrictNamedArgs{"datum_id": datumID}
maps.Copy(args, scope.SQLArguments())
rows, err := conn.Query(ctx, q, args)
if err != nil {
return fmt.Errorf("cannot query thirdParties: %w", err)
}
thirdParties, err := pgx.CollectRows(rows, pgx.RowToAddrOfStructByName[ThirdParty])
if err != nil {
return fmt.Errorf("cannot collect thirdParties: %w", err)
}
*vs = thirdParties
return nil
}
func (vs *ThirdParties) LoadByDatumID(
ctx context.Context,
conn pg.Querier,
@@ -1624,113 +1447,6 @@ ORDER BY
return thirdPartyMap, nil
}
func (vs *ThirdParties) LoadAllByAssetID(
ctx context.Context,
conn pg.Querier,
scope Scoper,
assetID gid.GID,
) error {
q := `
WITH vend AS (
SELECT
v.id,
v.tenant_id,
v.organization_id,
v.parent_third_party_id,
v.common_third_party_id,
v.name,
v.description,
v.category,
v.headquarter_address,
v.legal_name,
v.website_url,
v.privacy_policy_url,
v.service_level_agreement_url,
v.data_processing_agreement_url,
v.business_associate_agreement_url,
v.subprocessors_list_url,
v.certifications,
v.countries,
v.business_owner_profile_id,
v.security_owner_profile_id,
v.status_page_url,
v.terms_of_service_url,
v.security_page_url,
v.trust_page_url,
v.show_on_trust_center,
v.level,
v.vetting_status,
v.vetting_website_url,
v.vetting_procedure,
v.vetting_processing_started_at,
v.vetting_error_message,
v.created_at,
v.updated_at
FROM
third_parties v
INNER JOIN
asset_third_parties av ON v.id = av.third_party_id
WHERE
av.asset_id = @asset_id
)
SELECT
id,
organization_id,
parent_third_party_id,
common_third_party_id,
name,
description,
category,
headquarter_address,
legal_name,
website_url,
privacy_policy_url,
service_level_agreement_url,
data_processing_agreement_url,
business_associate_agreement_url,
subprocessors_list_url,
certifications,
countries,
business_owner_profile_id,
security_owner_profile_id,
status_page_url,
terms_of_service_url,
security_page_url,
trust_page_url,
show_on_trust_center,
level,
vetting_status,
vetting_website_url,
vetting_procedure,
vetting_processing_started_at,
vetting_error_message,
created_at,
updated_at
FROM
vend
WHERE %s
ORDER BY name ASC
`
q = fmt.Sprintf(q, scope.SQLFragment())
args := pgx.StrictNamedArgs{"asset_id": assetID}
maps.Copy(args, scope.SQLArguments())
rows, err := conn.Query(ctx, q, args)
if err != nil {
return fmt.Errorf("cannot query thirdParties: %w", err)
}
thirdParties, err := pgx.CollectRows(rows, pgx.RowToAddrOfStructByName[ThirdParty])
if err != nil {
return fmt.Errorf("cannot collect thirdParties: %w", err)
}
*vs = thirdParties
return nil
}
func (v *ThirdParty) LoadByOrganizationIDAndCommonThirdPartyID(
ctx context.Context,
conn pg.Querier,