feedkit/config/config.go

package config

import (
	"fmt"
	"strconv"
	"strings"
	"time"

	"gopkg.in/yaml.v3"
)

// Config is the top-level YAML configuration used by feedkit-style daemons.
//
// IMPORTANT: This package is intentionally domain-agnostic.
//   - We validate *shape* and internal consistency (required fields, uniqueness, etc.).
//   - We do NOT enforce domain rules (e.g., "observation|forecast|alert").
//     Domain modules (weatherfeeder/newsfeeder/...) can add their own validation layer.
type Config struct {
	Sources []SourceConfig `yaml:"sources"`
	Sinks   []SinkConfig   `yaml:"sinks"`
	Routes  []RouteConfig  `yaml:"routes"`
}

// SourceMode selects how a source receives upstream input.
//
// Empty mode means "auto": feedkit infers mode from the registered driver type.
type SourceMode string

const (
	SourceModeAuto   SourceMode = ""
	SourceModePoll   SourceMode = "poll"
	SourceModeStream SourceMode = "stream"
)

// Normalize lowercases and trims the mode.
func (m SourceMode) Normalize() SourceMode {
	switch strings.ToLower(strings.TrimSpace(string(m))) {
	case "":
		return SourceModeAuto
	case string(SourceModePoll):
		return SourceModePoll
	case string(SourceModeStream):
		return SourceModeStream
	default:
		return SourceMode(strings.ToLower(strings.TrimSpace(string(m))))
	}
}

// SourceConfig describes one input source.
//
// This is intentionally generic:
//   - driver-specific knobs belong in Params.
//   - mode controls polling vs streaming behavior.
//   - expected emitted kinds are optional and domain-defined.
type SourceConfig struct {
	Name   string `yaml:"name"`
	Driver string `yaml:"driver"` // e.g. "openmeteo_observation", "rss_feed", etc.

	// Mode is optional:
	//   - "poll": Every must be set (>0)
	//   - "stream": Every must be omitted/zero
	//   - empty: infer from driver registration type (poll vs stream)
	Mode SourceMode `yaml:"mode"`

	// Every is the poll cadence for poll-mode sources ("15m", "1m", etc.).
	Every Duration `yaml:"every"`

	// Kinds is optional and domain-defined.
	// If set, it describes the expected emitted event kinds for this source.
	Kinds []string `yaml:"kinds"`

	// Kind is the legacy singular form. Prefer "kinds".
	// If both kind and kinds are set, validation fails.
	Kind string `yaml:"kind"`

	// Params are driver-specific settings (URL, headers, station IDs, API keys, etc.).
	// The driver implementation is responsible for reading/validating these.
	Params map[string]any `yaml:"params"`
}

// ExpectedKinds returns normalized expected kinds from config.
// "kinds" takes precedence; "kind" is used as a legacy fallback.
func (cfg SourceConfig) ExpectedKinds() []string {
	if len(cfg.Kinds) > 0 {
		out := make([]string, 0, len(cfg.Kinds))
		for _, k := range cfg.Kinds {
			k = strings.TrimSpace(k)
			if k == "" {
				continue
			}
			out = append(out, k)
		}
		return out
	}
	if k := strings.TrimSpace(cfg.Kind); k != "" {
		return []string{k}
	}
	return nil
}

// SinkConfig describes one output sink adapter.
type SinkConfig struct {
	Name   string         `yaml:"name"`
	Driver string         `yaml:"driver"` // "stdout", "file", "postgres", "rabbitmq", ...
	Params map[string]any `yaml:"params"` // sink-specific settings
}

// RouteConfig describes a routing rule: which sink receives which kinds.
type RouteConfig struct {
	Sink string `yaml:"sink"` // sink name

	// Kinds is domain-defined. feedkit only enforces that each entry is non-empty.
	//
	// If Kinds is omitted or empty, the route matches ALL kinds.
	// This is useful when you want explicit per-sink routing rules even when a
	// particular sink should receive everything.
	Kinds []string `yaml:"kinds"`
}

// Duration is a YAML-friendly duration wrapper.
//
// Supported YAML formats:
//
//	every: 15m      # string duration (recommended)
//	every: 30s
//	every: 1h
//
// Also supported for convenience (interpreted as minutes):
//
//	every: 15       # integer minutes
//	every: "15"     # string minutes
type Duration struct {
	time.Duration
}

func (d *Duration) UnmarshalYAML(value *yaml.Node) error {
	// We expect a scalar (string or int).
	if value.Kind != yaml.ScalarNode {
		return fmt.Errorf("duration must be a scalar (e.g. 15m), got %v", value.Kind)
	}

	// Case 1: YAML integer -> interpret as minutes.
	if value.Tag == "!!int" {
		n, err := strconv.Atoi(value.Value)
		if err != nil {
			return fmt.Errorf("invalid integer duration %q: %w", value.Value, err)
		}
		if n <= 0 {
			return fmt.Errorf("duration must be > 0, got %d", n)
		}
		d.Duration = time.Duration(n) * time.Minute
		return nil
	}

	// Case 2: YAML string.
	if value.Tag == "!!str" {
		s := strings.TrimSpace(value.Value)
		if s == "" {
			return fmt.Errorf("duration cannot be empty")
		}

		// If it’s all digits, interpret as minutes (e.g. "15").
		if isAllDigits(s) {
			n, err := strconv.Atoi(s)
			if err != nil {
				return fmt.Errorf("invalid numeric duration %q: %w", s, err)
			}
			if n <= 0 {
				return fmt.Errorf("duration must be > 0, got %d", n)
			}
			d.Duration = time.Duration(n) * time.Minute
			return nil
		}

		// Otherwise parse as Go duration string (15m, 30s, 1h, etc.).
		parsed, err := time.ParseDuration(s)
		if err != nil {
			return fmt.Errorf("invalid duration %q (expected e.g. 15m, 30s, 1h): %w", s, err)
		}
		if parsed <= 0 {
			return fmt.Errorf("duration must be > 0, got %s", parsed)
		}
		d.Duration = parsed
		return nil
	}

	// Anything else: reject.
	return fmt.Errorf("duration must be a string like 15m or an integer minutes, got tag %s", value.Tag)
}