refactor!: introduce generic processors registry and remove normalize registry adapter

- add new `processors` package with canonical `Processor` interface
- add `processors.Registry` with Register/Build/BuildChain factory model
- switch `pipeline.Pipeline` to `[]processors.Processor`
- replace `normalize.Registry` + registry adapter with direct `normalize.Processor`
- remove `normalize/registry.go`
- update root docs to position normalize as one optional processing stage
- add tests for processors registry, normalize processor behavior, and pipeline flow

BREAKING CHANGE:
- `pipeline.Processor` removed; use `processors.Processor`
- `normalize.Registry` and old normalize processor adapter APIs removed
- downstream daemons must update processor wiring to new `processors.Registry`
  and `normalize.NewProcessor(...)`
This commit is contained in:
2026-03-16 13:14:24 -05:00
parent 6c5f95ad26
commit 96039f6530
12 changed files with 543 additions and 162 deletions

View File

@@ -1,4 +1,4 @@
// Package normalize provides an OPTIONAL normalization hook for feedkit pipelines.
// Package normalize provides a concrete normalization processor for feedkit pipelines.
//
// Motivation:
// Many daemons have sources that:
@@ -9,9 +9,9 @@
// encourages duplication (unit conversions, common mapping helpers, etc.).
//
// This package lets a source emit a "raw" event (e.g., Schema="raw.openweather.current.v1",
// Payload=json.RawMessage), and then a normalization processor can convert it into a
// Payload=json.RawMessage), and then a normalize.Processor can convert it into a
// normalized event (e.g., Schema="weather.observation.v1", Payload=WeatherObservation{}).
//
// Key property: normalization is optional.
// If no registered Normalizer matches an event, it passes through unchanged.
// If no Normalizer matches an event, Processor passes it through unchanged by default.
package normalize

57
normalize/processor.go Normal file
View File

@@ -0,0 +1,57 @@
package normalize
import (
"context"
"fmt"
"gitea.maximumdirect.net/ejr/feedkit/event"
)
// Processor applies ordered normalization rules to pipeline events.
//
// Selection rule:
// - iterate in Normalizers order
// - the first Normalizer whose Match returns true is applied
//
// If no normalizer matches, the default behavior is pass-through.
type Processor struct {
Normalizers []Normalizer
// If true, events that do not match any normalizer cause an error.
// Default is false (pass-through).
RequireMatch bool
}
// NewProcessor constructs a normalization processor from an ordered normalizer list.
func NewProcessor(normalizers []Normalizer, requireMatch bool) Processor {
return Processor{
Normalizers: append([]Normalizer(nil), normalizers...),
RequireMatch: requireMatch,
}
}
// Process implements processors.Processor.
func (p Processor) Process(ctx context.Context, in event.Event) (*event.Event, error) {
for _, n := range p.Normalizers {
if n == nil {
continue
}
if !n.Match(in) {
continue
}
out, err := n.Normalize(ctx, in)
if err != nil {
return nil, fmt.Errorf("normalize: normalizer failed: %w", err)
}
return out, nil
}
if p.RequireMatch {
return nil, fmt.Errorf("normalize: no normalizer matched event (id=%s kind=%s source=%s schema=%q)",
in.ID, in.Kind, in.Source, in.Schema)
}
out := in
return &out, nil
}

139
normalize/processor_test.go Normal file
View File

@@ -0,0 +1,139 @@
package normalize
import (
"context"
"errors"
"strings"
"testing"
"time"
"gitea.maximumdirect.net/ejr/feedkit/event"
)
func TestProcessorFirstMatchWins(t *testing.T) {
var firstCalls, secondCalls int
p := NewProcessor([]Normalizer{
Func{
MatchFn: func(event.Event) bool { return true },
NormalizeFn: func(_ context.Context, in event.Event) (*event.Event, error) {
firstCalls++
out := in
out.Schema = "normalized.first.v1"
return &out, nil
},
},
Func{
MatchFn: func(event.Event) bool { return true },
NormalizeFn: func(_ context.Context, in event.Event) (*event.Event, error) {
secondCalls++
out := in
out.Schema = "normalized.second.v1"
return &out, nil
},
},
}, false)
out, err := p.Process(context.Background(), testEvent())
if err != nil {
t.Fatalf("Process error: %v", err)
}
if out == nil {
t.Fatalf("expected output event, got nil")
}
if out.Schema != "normalized.first.v1" {
t.Fatalf("unexpected schema: %q", out.Schema)
}
if firstCalls != 1 {
t.Fatalf("expected first normalizer called once, got %d", firstCalls)
}
if secondCalls != 0 {
t.Fatalf("expected second normalizer skipped, got %d calls", secondCalls)
}
}
func TestProcessorNoMatchPassThroughAndRequireMatch(t *testing.T) {
in := testEvent()
in.Schema = "raw.schema.v1"
passThrough := NewProcessor([]Normalizer{
Func{
MatchFn: func(event.Event) bool { return false },
NormalizeFn: func(_ context.Context, in event.Event) (*event.Event, error) {
out := in
out.Schema = "should.not.run"
return &out, nil
},
},
}, false)
out, err := passThrough.Process(context.Background(), in)
if err != nil {
t.Fatalf("pass-through Process error: %v", err)
}
if out == nil {
t.Fatalf("expected pass-through output event, got nil")
}
if out.Schema != "raw.schema.v1" {
t.Fatalf("expected unchanged schema, got %q", out.Schema)
}
required := NewProcessor(nil, true)
_, err = required.Process(context.Background(), in)
if err == nil {
t.Fatalf("expected require-match error")
}
if !strings.Contains(err.Error(), "no normalizer matched") {
t.Fatalf("unexpected error: %v", err)
}
}
func TestProcessorDropAndErrorPropagation(t *testing.T) {
t.Run("drop", func(t *testing.T) {
p := NewProcessor([]Normalizer{
Func{
MatchFn: func(event.Event) bool { return true },
NormalizeFn: func(context.Context, event.Event) (*event.Event, error) {
return nil, nil
},
},
}, false)
out, err := p.Process(context.Background(), testEvent())
if err != nil {
t.Fatalf("Process error: %v", err)
}
if out != nil {
t.Fatalf("expected nil output for dropped event, got %#v", out)
}
})
t.Run("error", func(t *testing.T) {
p := NewProcessor([]Normalizer{
Func{
MatchFn: func(event.Event) bool { return true },
NormalizeFn: func(context.Context, event.Event) (*event.Event, error) {
return nil, errors.New("map failed")
},
},
}, false)
_, err := p.Process(context.Background(), testEvent())
if err == nil {
t.Fatalf("expected error")
}
if !strings.Contains(err.Error(), "normalizer failed") {
t.Fatalf("unexpected error: %v", err)
}
})
}
func testEvent() event.Event {
return event.Event{
ID: "evt-normalize-1",
Kind: event.Kind("observation"),
Source: "source-1",
EmittedAt: time.Now().UTC(),
Payload: map[string]any{"x": 1},
}
}

View File

@@ -1,140 +0,0 @@
package normalize
import (
"context"
"fmt"
"sync"
"gitea.maximumdirect.net/ejr/feedkit/event"
)
// Registry holds a set of Normalizers and selects one for a given event.
//
// Selection rule (simple + predictable):
// - iterate in registration order
// - the FIRST Normalizer whose Match(e) returns true is used
//
// If none match, the event passes through unchanged.
//
// Why "first match wins"?
// Normalization is usually a single mapping step from a raw schema/version into
// a normalized schema/version. If you want multiple transformation steps,
// model them as multiple pipeline processors (which feedkit already supports).
type Registry struct {
mu sync.RWMutex
ns []Normalizer
}
// Register adds a normalizer to the registry.
//
// Register panics if n is nil; this is a programmer error and should fail fast.
func (r *Registry) Register(n Normalizer) {
if n == nil {
panic("normalize.Registry.Register: normalizer cannot be nil")
}
r.mu.Lock()
defer r.mu.Unlock()
r.ns = append(r.ns, n)
}
// Normalize finds the first matching Normalizer and applies it.
//
// If no normalizer matches, it returns the input event unchanged.
//
// If a normalizer returns (nil, nil), the event is dropped.
func (r *Registry) Normalize(ctx context.Context, in event.Event) (*event.Event, error) {
if r == nil {
// Nil registry is a valid "feature off" state.
out := in
return &out, nil
}
r.mu.RLock()
ns := append([]Normalizer(nil), r.ns...) // copy for safe iteration outside lock
r.mu.RUnlock()
for _, n := range ns {
if n == nil {
// Shouldn't happen (Register panics), but guard anyway.
continue
}
if !n.Match(in) {
continue
}
out, err := n.Normalize(ctx, in)
if err != nil {
return nil, fmt.Errorf("normalize: normalizer failed: %w", err)
}
// out may be nil to signal "drop".
return out, nil
}
// No match: pass through unchanged.
out := in
return &out, nil
}
// Processor adapts a Registry into a pipeline Processor.
//
// It implements:
//
// Process(ctx context.Context, in event.Event) (*event.Event, error)
//
// which matches feedkit/pipeline.Processor.
//
// Optionality:
// - If Registry is nil, Processor becomes a no-op pass-through.
// - If Registry has no matching normalizer for an event, that event passes through unchanged.
type Processor struct {
Registry *Registry
// If true, events that do not match any normalizer cause an error.
// Default is false (pass-through), which is the behavior you asked for.
RequireMatch bool
}
// Process implements the pipeline.Processor interface.
func (p Processor) Process(ctx context.Context, in event.Event) (*event.Event, error) {
// "Feature off": no registry means no normalization.
if p.Registry == nil {
out := in
return &out, nil
}
out, err := p.Registry.Normalize(ctx, in)
if err != nil {
return nil, err
}
if out == nil {
// Dropped by normalization policy.
return nil, nil
}
if p.RequireMatch {
// Detect "no-op pass-through due to no match" by checking whether a match existed.
// We do this with a cheap second pass to avoid changing Normalize()'s signature.
// (This is rare to enable; correctness/clarity > micro-optimization.)
if !p.Registry.hasMatch(in) {
return nil, fmt.Errorf("normalize: no normalizer matched event (id=%s kind=%s source=%s schema=%q)",
in.ID, in.Kind, in.Source, in.Schema)
}
}
return out, nil
}
func (r *Registry) hasMatch(in event.Event) bool {
if r == nil {
return false
}
r.mu.RLock()
defer r.mu.RUnlock()
for _, n := range r.ns {
if n != nil && n.Match(in) {
return true
}
}
return false
}