package cli

import (
	"github.com/spf13/cobra"

	"gitea.maximumdirect.net/eric/seriatim/internal/builtin"
	"gitea.maximumdirect.net/eric/seriatim/internal/config"
	"gitea.maximumdirect.net/eric/seriatim/internal/pipeline"
)

func newMergeCommand() *cobra.Command {
	var opts config.MergeOptions

	cmd := &cobra.Command{
		Use:   "merge",
		Short: "Run the transcript merge pipeline",
		RunE: func(cmd *cobra.Command, args []string) error {
			cfg, err := config.NewMergeConfig(opts)
			if err != nil {
				return err
			}

			return pipeline.Run(cmd.Context(), cfg, builtin.NewRegistry())
		},
	}

	flags := cmd.Flags()
	flags.StringArrayVar(&opts.InputFiles, "input-file", nil, "input transcript file; may be repeated")
	flags.StringVar(&opts.OutputFile, "output-file", "", "output transcript JSON file")
	flags.StringVar(&opts.ReportFile, "report-file", "", "optional report JSON file")
	flags.StringVar(&opts.SpeakersFile, "speakers", "", "speaker map file")
	flags.StringVar(&opts.AutocorrectFile, "autocorrect", "", "autocorrect rules file")
	flags.StringVar(&opts.InputReader, "input-reader", config.DefaultInputReader, "input reader module")
	flags.StringVar(&opts.OutputModules, "output-modules", config.DefaultOutputModules, "comma-separated output modules")
	flags.StringVar(&opts.OutputSchema, "output-schema", config.DefaultOutputSchema, "output JSON schema: default, minimal, or seriatim")
	flags.StringVar(&opts.PreprocessingModules, "preprocessing-modules", config.DefaultPreprocessingModules, "comma-separated preprocessing modules")
	flags.StringVar(&opts.PostprocessingModules, "postprocessing-modules", config.DefaultPostprocessingModules, "comma-separated postprocessing modules")
	flags.StringVar(&opts.CoalesceGap, "coalesce-gap", config.DefaultCoalesceGapValue, "maximum same-speaker gap in seconds for coalesce")

	return cmd
}