Add tracker mapping worker and initiator domain extraction

Poll-based worker that maps org-scoped tracker patterns to the
common knowledge base via pattern matching and domain-based
attribution. Populates initiator_domain on detected trackers
at report time. Resolves org-scoped vendors through the common
third party link.

Signed-off-by: Émile Ré <emile@getprobo.com>
Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
Émile Ré
2026-05-13 17:26:15 +04:00
committed by Émile Ré
parent f0483d5280
commit d6f268cb06
7 changed files with 498 additions and 15 deletions

View File

@@ -16,6 +16,7 @@ package coredata
import (
"context"
"errors"
"fmt"
"maps"
"time"
@@ -151,6 +152,33 @@ WHERE
return count, nil
}
func (dts *DetectedTrackers) LoadCommonThirdPartyIDByTrackerPatternID(
ctx context.Context,
conn pg.Querier,
trackerPatternID gid.GID,
) (*gid.GID, error) {
q := `
SELECT DISTINCT ctpd.common_third_party_id
FROM detected_trackers dt
JOIN common_third_party_domains ctpd ON ctpd.domain = dt.initiator_domain
WHERE dt.tracker_pattern_id = @tracker_pattern_id
AND dt.initiator_domain IS NOT NULL
LIMIT 1;
`
args := pgx.StrictNamedArgs{"tracker_pattern_id": trackerPatternID}
var commonThirdPartyID gid.GID
if err := conn.QueryRow(ctx, q, args).Scan(&commonThirdPartyID); err != nil {
if errors.Is(err, pgx.ErrNoRows) {
return nil, nil
}
return nil, fmt.Errorf("cannot load common third party ID by tracker pattern: %w", err)
}
return &commonThirdPartyID, nil
}
func (dts *DetectedTrackers) RelinkByTrackerPatternID(
ctx context.Context,
tx pg.Tx,