StasonJatham
e8f7d6bfdf
Single stateless Go process that consumes CT logs via embedded (patched) CertSpotter internals, classifies cloud/database/storage DNS identifiers in-process with a zero-allocation classifier, enriches via round-robin DNS resolvers with CNAME following, and batch-writes useful findings to PostgreSQL. - third_party/certspotter: 2-hunk IdentifierSink patch, no stdout/JSON/files - internal/classify: AWS/Azure/GCP/Firebase/Cloudflare R2/DigitalOcean/Supabase/OCI - internal/dns: sharded bounded TTL cache, multi-resolver load balancing + failover - internal/pipeline: bounded queues, dedup, direct-priority load shedding - internal/store: pgx batch writer, Postgres CT checkpoints (no cert contents) - internal/probe: optional non-destructive reachability checks (off by default) - Docker: distroless non-root, read-only rootfs, no app volume, resource limits - tests enforce 0 allocs/op on the classifier and sink hot path
114 lines
3.6 KiB
Go
114 lines
3.6 KiB
Go
package classify
|
|
|
|
import "tea.karlcom.de/karl/bucketeer/internal/model"
|
|
|
|
func azure(service model.Service, resource, region string) model.Match {
|
|
return model.Match{
|
|
Provider: model.ProviderAzure,
|
|
Service: service,
|
|
ResourceSpecific: true,
|
|
Region: region,
|
|
Resource: resource,
|
|
}
|
|
}
|
|
|
|
// classifyAzureCore handles *.blob|dfs|file|queue|table|web.core.windows.net.
|
|
func classifyAzureCore(s *scanner) (model.Match, bool) {
|
|
n := s.n
|
|
if n < 5 || s.label(n-1) != "net" || s.label(n-2) != "windows" || s.label(n-3) != "core" {
|
|
return model.Match{}, false
|
|
}
|
|
svc := s.label(n - 4)
|
|
resource := s.label(0)
|
|
if resource == "" {
|
|
return model.Match{}, false
|
|
}
|
|
switch svc {
|
|
case "blob", "dfs":
|
|
return azure(model.ServiceBlobStorage, resource, ""), true
|
|
case "file":
|
|
return azure(model.ServiceFileStorage, resource, ""), true
|
|
case "queue":
|
|
return azure(model.ServiceQueue, resource, ""), true
|
|
case "table":
|
|
return azure(model.ServiceTableStorage, resource, ""), true
|
|
case "web":
|
|
return azure(model.ServiceWebApp, resource, ""), true
|
|
}
|
|
return model.Match{}, false
|
|
}
|
|
|
|
// classifyAzureDatabase handles <server>.database.windows.net.
|
|
func classifyAzureDatabase(s *scanner) (model.Match, bool) {
|
|
n := s.n
|
|
if n < 4 || s.label(n-1) != "net" || s.label(n-2) != "windows" || s.label(n-3) != "database" {
|
|
return model.Match{}, false
|
|
}
|
|
return azure(model.ServiceDatabase, s.label(0), ""), true
|
|
}
|
|
|
|
// classifyAzureFlexibleServer handles <server>.{postgres,mysql}.database.azure.com.
|
|
func classifyAzureFlexibleServer(s *scanner) (model.Match, bool) {
|
|
n := s.n
|
|
if n < 5 || s.label(n-1) != "com" || s.label(n-2) != "azure" || s.label(n-3) != "database" {
|
|
return model.Match{}, false
|
|
}
|
|
switch s.label(n - 4) {
|
|
case "postgres":
|
|
return azure(model.ServicePostgres, s.label(0), ""), true
|
|
case "mysql":
|
|
return azure(model.ServiceMySQL, s.label(0), ""), true
|
|
}
|
|
return model.Match{}, false
|
|
}
|
|
|
|
// classifyAzureDocuments handles <account>.documents.azure.com (Cosmos DB).
|
|
func classifyAzureDocuments(s *scanner) (model.Match, bool) {
|
|
n := s.n
|
|
if n < 4 || s.label(n-1) != "com" || s.label(n-2) != "azure" || s.label(n-3) != "documents" {
|
|
return model.Match{}, false
|
|
}
|
|
return azure(model.ServiceCosmosDB, s.label(0), ""), true
|
|
}
|
|
|
|
// classifyAzureCosmos handles <account>.{mongo,cassandra,gremlin}.cosmos.azure.com.
|
|
func classifyAzureCosmos(s *scanner) (model.Match, bool) {
|
|
n := s.n
|
|
if n < 5 || s.label(n-1) != "com" || s.label(n-2) != "azure" || s.label(n-3) != "cosmos" {
|
|
return model.Match{}, false
|
|
}
|
|
switch s.label(n - 4) {
|
|
case "mongo", "cassandra", "gremlin":
|
|
return azure(model.ServiceCosmosDB, s.label(0), ""), true
|
|
}
|
|
return model.Match{}, false
|
|
}
|
|
|
|
// classifyAzureRedis handles <name>.redis.cache.windows.net.
|
|
func classifyAzureRedis(s *scanner) (model.Match, bool) {
|
|
n := s.n
|
|
if n < 5 || s.label(n-1) != "net" || s.label(n-2) != "windows" ||
|
|
s.label(n-3) != "cache" || s.label(n-4) != "redis" {
|
|
return model.Match{}, false
|
|
}
|
|
return azure(model.ServiceRedis, s.label(0), ""), true
|
|
}
|
|
|
|
// classifyAzureManagedRedis handles <name>.redis.azure.net.
|
|
func classifyAzureManagedRedis(s *scanner) (model.Match, bool) {
|
|
n := s.n
|
|
if n < 4 || s.label(n-1) != "net" || s.label(n-2) != "azure" || s.label(n-3) != "redis" {
|
|
return model.Match{}, false
|
|
}
|
|
return azure(model.ServiceRedis, s.label(0), ""), true
|
|
}
|
|
|
|
// classifyAzureSearch handles <service>.search.windows.net.
|
|
func classifyAzureSearch(s *scanner) (model.Match, bool) {
|
|
n := s.n
|
|
if n < 4 || s.label(n-1) != "net" || s.label(n-2) != "windows" || s.label(n-3) != "search" {
|
|
return model.Match{}, false
|
|
}
|
|
return azure(model.ServiceSearch, s.label(0), ""), true
|
|
}
|