Move common third-party resolver to thirdparty pkg

resolveOrCreateCommonThirdParty lived as a package-level helper in the
tracker mapping worker, but the common pattern enrichment worker now
reuses it. Homing shared catalog logic in a mapping-named file made the
enrichment worker quietly depend on the mapping worker's file, and it is
not a mapping concern.

Move it to pkg/thirdparty as exported ResolveOrCreateCommonThirdParty,
decoupled from cookiebanner's TrackerMappingAgentResult (it now takes a
name and category) to avoid an import cycle. It stays a transaction-
scoped free function so both workers compose it into their own tx for
atomicity rather than receiving a service that owns its own connection.

Relocate the catalog dedup DB test alongside it.

Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
Émile Ré
2026-05-29 19:35:17 +02:00
parent 9b03d199da
commit 8d5571cf91
5 changed files with 357 additions and 258 deletions

View File

@@ -27,7 +27,6 @@ import (
"go.probo.inc/probo/pkg/coredata"
"go.probo.inc/probo/pkg/gid"
"go.probo.inc/probo/pkg/llm"
"go.probo.inc/probo/pkg/slug"
"go.probo.inc/probo/pkg/thirdparty"
"go.probo.inc/probo/pkg/uri"
)
@@ -661,10 +660,12 @@ func (h *trackerMappingHandler) persistAgentIdentification(
tp coredata.TrackerPattern,
ident agentIdentification,
) (*catalogMatch, error) {
commonThirdPartyID, err := h.resolveOrCreateCommonThirdParty(
commonThirdPartyID, err := thirdparty.ResolveOrCreateCommonThirdParty(
ctx,
tx,
ident.result,
h.logger,
ident.result.ThirdPartyName,
ident.result.Category,
ident.domains,
)
if err != nil {
@@ -702,67 +703,6 @@ func (h *trackerMappingHandler) persistAgentIdentification(
}, nil
}
func (h *trackerMappingHandler) resolveOrCreateCommonThirdParty(
ctx context.Context,
tx pg.Tx,
identification TrackerMappingAgentResult,
domains []string,
) (*gid.GID, error) {
var party coredata.CommonThirdParty
if err := party.LoadByName(ctx, tx, identification.ThirdPartyName); err == nil {
return &party.ID, nil
}
partySlug := slug.Make(identification.ThirdPartyName)
if partySlug == "" {
return nil, nil
}
if err := party.LoadBySlug(ctx, tx, partySlug); err == nil {
return &party.ID, nil
}
category := identification.Category
now := time.Now()
party = coredata.CommonThirdParty{
ID: gid.New(gid.NilTenant, coredata.CommonThirdPartyEntityType),
Name: identification.ThirdPartyName,
Slug: partySlug,
Category: category,
Certifications: []string{},
CreatedAt: now,
UpdatedAt: now,
}
if err := party.Insert(ctx, tx); err != nil {
return nil, fmt.Errorf("cannot create common third party: %w", err)
}
for _, domain := range domains {
domainRecord := coredata.CommonThirdPartyDomain{
ID: gid.New(gid.NilTenant, coredata.CommonThirdPartyDomainEntityType),
CommonThirdPartyID: party.ID,
Domain: domain,
CreatedAt: now,
UpdatedAt: now,
}
if _, err := domainRecord.Upsert(ctx, tx); err != nil {
return nil, fmt.Errorf("cannot create common third party domain: %w", err)
}
}
h.logger.InfoCtx(
ctx,
"created common third party from agent identification",
log.String("name", identification.ThirdPartyName),
log.String("category", category.String()),
)
return &party.ID, nil
}
// matchBySiblingOrigin finds other tracker patterns on the same banner
// that share initiator domains with the current pattern. Sharing an
// origin across multiple detected patterns is a strong indicator of the