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

22
processors/doc.go Normal file
View File

@@ -0,0 +1,22 @@
// Package processors defines feedkit's generic processor abstraction and registry.
//
// Processors are optional pipeline stages that can transform, drop, or reject
// events before dispatch to sinks.
//
// Registry provides name-based construction so daemons can assemble processor
// chains without embedding switch statements in wiring code.
//
// Example:
//
// reg := processors.NewRegistry()
// reg.Register("normalize", func() (processors.Processor, error) {
// return normalize.NewProcessor(myNormalizers, false), nil
// })
//
// chain, err := reg.BuildChain([]string{"normalize"})
// if err != nil {
// // handle wiring error
// }
//
// p := &pipeline.Pipeline{Processors: chain}
package processors

15
processors/processor.go Normal file
View File

@@ -0,0 +1,15 @@
package processors
import (
"context"
"gitea.maximumdirect.net/ejr/feedkit/event"
)
// Processor can mutate/drop events (dedupe, rate-limit, normalization tweaks).
type Processor interface {
Process(ctx context.Context, in event.Event) (out *event.Event, err error)
}
// Factory constructs a configured Processor instance.
type Factory func() (Processor, error)

71
processors/registry.go Normal file
View File

@@ -0,0 +1,71 @@
package processors
import (
"fmt"
"strings"
)
type Registry struct {
byDriver map[string]Factory
}
func NewRegistry() *Registry {
return &Registry{byDriver: map[string]Factory{}}
}
// Register associates a processor driver name with a factory.
//
// Register panics for empty driver names, nil factories, and duplicates.
func (r *Registry) Register(driver string, f Factory) {
if r == nil {
panic("processors.Registry.Register: registry cannot be nil")
}
driver = strings.TrimSpace(driver)
if driver == "" {
panic("processors.Registry.Register: driver cannot be empty")
}
if f == nil {
panic(fmt.Sprintf("processors.Registry.Register: factory cannot be nil (driver=%q)", driver))
}
if r.byDriver == nil {
r.byDriver = map[string]Factory{}
}
if _, exists := r.byDriver[driver]; exists {
panic(fmt.Sprintf("processors.Registry.Register: driver %q already registered", driver))
}
r.byDriver[driver] = f
}
// Build constructs a Processor by driver name.
func (r *Registry) Build(driver string) (Processor, error) {
if r == nil {
return nil, fmt.Errorf("processors registry is nil")
}
driver = strings.TrimSpace(driver)
f, ok := r.byDriver[driver]
if !ok {
return nil, fmt.Errorf("unknown processor driver: %q", driver)
}
p, err := f()
if err != nil {
return nil, fmt.Errorf("build processor %q: %w", driver, err)
}
if p == nil {
return nil, fmt.Errorf("build processor %q: factory returned nil processor", driver)
}
return p, nil
}
// BuildChain constructs an ordered processor chain from a driver list.
func (r *Registry) BuildChain(drivers []string) ([]Processor, error) {
out := make([]Processor, 0, len(drivers))
for i, driver := range drivers {
p, err := r.Build(driver)
if err != nil {
return nil, fmt.Errorf("build processor chain[%d] (%q): %w", i, strings.TrimSpace(driver), err)
}
out = append(out, p)
}
return out, nil
}

100
processors/registry_test.go Normal file
View File

@@ -0,0 +1,100 @@
package processors
import (
"context"
"errors"
"strings"
"testing"
"gitea.maximumdirect.net/ejr/feedkit/event"
)
type testProcessor struct {
name string
}
func (p testProcessor) Process(context.Context, event.Event) (*event.Event, error) {
return nil, nil
}
func TestRegistryRegisterValidation(t *testing.T) {
t.Run("empty driver panics", func(t *testing.T) {
r := NewRegistry()
assertPanics(t, func() {
r.Register(" ", func() (Processor, error) { return testProcessor{name: "x"}, nil })
})
})
t.Run("nil factory panics", func(t *testing.T) {
r := NewRegistry()
assertPanics(t, func() {
r.Register("normalize", nil)
})
})
t.Run("duplicate driver panics", func(t *testing.T) {
r := NewRegistry()
r.Register("normalize", func() (Processor, error) { return testProcessor{name: "a"}, nil })
assertPanics(t, func() {
r.Register("normalize", func() (Processor, error) { return testProcessor{name: "b"}, nil })
})
})
}
func TestRegistryBuildUnknownDriver(t *testing.T) {
r := NewRegistry()
_, err := r.Build("does_not_exist")
if err == nil {
t.Fatalf("expected error for unknown driver")
}
if !strings.Contains(err.Error(), "unknown processor driver") {
t.Fatalf("unexpected error: %v", err)
}
}
func TestRegistryBuildChainPreservesOrder(t *testing.T) {
r := NewRegistry()
r.Register("first", func() (Processor, error) { return testProcessor{name: "first"}, nil })
r.Register("second", func() (Processor, error) { return testProcessor{name: "second"}, nil })
chain, err := r.BuildChain([]string{"first", "second"})
if err != nil {
t.Fatalf("BuildChain error: %v", err)
}
if len(chain) != 2 {
t.Fatalf("expected 2 processors, got %d", len(chain))
}
p0, ok := chain[0].(testProcessor)
if !ok || p0.name != "first" {
t.Fatalf("unexpected chain[0]: %#v", chain[0])
}
p1, ok := chain[1].(testProcessor)
if !ok || p1.name != "second" {
t.Fatalf("unexpected chain[1]: %#v", chain[1])
}
}
func TestRegistryBuildChainIndexedFailure(t *testing.T) {
r := NewRegistry()
r.Register("ok", func() (Processor, error) { return testProcessor{name: "ok"}, nil })
r.Register("broken", func() (Processor, error) { return nil, errors.New("boom") })
_, err := r.BuildChain([]string{"ok", "broken"})
if err == nil {
t.Fatalf("expected error")
}
if !strings.Contains(err.Error(), "chain[1]") {
t.Fatalf("expected indexed error, got: %v", err)
}
}
func assertPanics(t *testing.T, fn func()) {
t.Helper()
defer func() {
if recover() == nil {
t.Fatalf("expected panic")
}
}()
fn()
}