jcoffey-dev
cd8aa290ca
Extends the agent, ingest, storage, api, and web with Windows Event Log/ETW sourcing and Tantivy-backed free-text search, per the approved Phase 1 plan. - CLAUDE.md: materialized on disk (never existed as a file before) with a new Phase 1 "done looks like" section. - agent: Windows Event Log (EvtSubscribe) and ETW sources, Windows service wrapper (install/uninstall/run-service), both feature- and target_os-gated so Linux builds/tests/clippy stay unaffected. Also fixed two pre-existing Phase 0 clippy gaps (dead-code on default-features-only builds, a type-inference edge case) found while testing every feature combination properly for the first time. UNVERIFIED on real Windows -- no Windows toolchain existed anywhere in the build environment; flagged prominently in three places. - proto/ingest: new record_id field, assigned once server-side in ingest's gRPC front end so ClickHouse and Tantivy agree on the same ID for the same record. - storage: record_id column + bloom filter index, verified against a live ClickHouse. - search: new service, Tantivy index, rskafka consumer as an independent second consumer group on the same Redpanda topic ingest already reads. - api/web: new /search endpoint and page, sharing the query page's result-table shape and component. - hack/windows-fixture: sends realistic Windows-shaped data straight to ingest, so the pipeline's handling of it is verifiable without a Windows host. Verified end-to-end on the live docker-compose stack: the same record_id comes back from both /query and /search for the same log line, including for windows-fixture's synthetic Windows Event Log data. Real bugs found and fixed along the way: api/Dockerfile missing proto/ in its build context, search's logs being completely silent (RUST_LOG gap), and search/target/ missing from .gitignore/.dockerignore.
69 lines
2.0 KiB
Go
69 lines
2.0 KiB
Go
// Package normalize maps the wire-format LogRecord (as agents send it)
|
|
// into the ClickHouse row shape defined in /storage. This is the "OTel-log-
|
|
// like schema" normalization step called for in the ingest design — Phase
|
|
// 0 keeps it to the minimal column set; full OTel field mapping (separate
|
|
// SeverityNumber/SeverityText, resource attributes, etc.) is deferred, see
|
|
// the open questions in /docs/architecture.md.
|
|
package normalize
|
|
|
|
import (
|
|
"time"
|
|
|
|
"github.com/google/uuid"
|
|
|
|
logsv1 "github.com/sentry/sentry/proto/sentry/logs/v1"
|
|
)
|
|
|
|
type Row struct {
|
|
Timestamp time.Time
|
|
Host string
|
|
Service string
|
|
Severity string
|
|
Message string
|
|
Attributes map[string]string
|
|
RecordID uuid.UUID
|
|
}
|
|
|
|
func ToRow(rec *logsv1.LogRecord) Row {
|
|
attrs := rec.GetAttributes()
|
|
if attrs == nil {
|
|
attrs = map[string]string{}
|
|
}
|
|
// grpcserver's PushBatch handler always assigns a valid UUID before a
|
|
// record reaches this point (see its doc comment for why), so a parse
|
|
// failure here would mean something upstream is bypassing that —
|
|
// fall back to the nil UUID rather than failing the whole row, same
|
|
// "never silently drop a record" spirit as the rest of this pipeline.
|
|
recordID, _ := uuid.Parse(rec.GetRecordId())
|
|
return Row{
|
|
Timestamp: time.Unix(0, rec.GetTimestampUnixNano()).UTC(),
|
|
Host: rec.GetHost(),
|
|
Service: rec.GetService(),
|
|
Severity: severityText(rec.GetSeverity()),
|
|
Message: rec.GetMessage(),
|
|
Attributes: attrs,
|
|
RecordID: recordID,
|
|
}
|
|
}
|
|
|
|
// severityText maps the proto Severity enum to short OTel-style severity
|
|
// names, stored as the `severity` column's value.
|
|
func severityText(sev logsv1.Severity) string {
|
|
switch sev {
|
|
case logsv1.Severity_SEVERITY_TRACE:
|
|
return "TRACE"
|
|
case logsv1.Severity_SEVERITY_DEBUG:
|
|
return "DEBUG"
|
|
case logsv1.Severity_SEVERITY_INFO:
|
|
return "INFO"
|
|
case logsv1.Severity_SEVERITY_WARN:
|
|
return "WARN"
|
|
case logsv1.Severity_SEVERITY_ERROR:
|
|
return "ERROR"
|
|
case logsv1.Severity_SEVERITY_FATAL:
|
|
return "FATAL"
|
|
default:
|
|
return "UNSPECIFIED"
|
|
}
|
|
}
|