spider/internal/pipeline/phase.go

package pipeline

import (
	"context"
	"spider/internal/model"
)

// Settings is a minimal interface satisfied by *service.SettingsService.
// Using an interface here avoids an import cycle (service → worker → pipeline → service).
type Settings interface {
	GetInt(ctx context.Context, key string, defaultVal int) int
	GetFloat(ctx context.Context, key string, defaultVal float64) float64
	GetBool(ctx context.Context, key string, defaultVal bool) bool
}

// Phase 每个采集阶段的接口
type Phase interface {
	Name() string
	Run(ctx context.Context, task *model.Task, opts *Options) error
}

// Options Pipeline 执行选项（来自任务参数）
type Options struct {
	Target     string
	SkipPhases []string
	TestRun    *TestRun
}

type TestRun struct {
	ItemLimit    int
	MessageLimit int
}

// ProgressReporter 进度上报函数类型
// 由 pipeline.Runner 提供，各 phase 调用
type ProgressReporter func(phase string, current, total int, message string)

// ShouldSkip 检查某阶段是否被跳过
func ShouldSkip(phaseName string, skipPhases []string) bool {
	for _, s := range skipPhases {
		if s == phaseName {
			return true
		}
	}
	return false
}