seriatim/internal/normalize/normalize.go

package normalize

import (
	"context"
	"encoding/json"
	"fmt"
	"os"
	"strings"

	"gitea.maximumdirect.net/eric/seriatim/internal/artifact"
	"gitea.maximumdirect.net/eric/seriatim/internal/buildinfo"
	"gitea.maximumdirect.net/eric/seriatim/internal/config"
	"gitea.maximumdirect.net/eric/seriatim/internal/report"
)

type normalizeAudit struct {
	Command                string   `json:"command"`
	InputFile              string   `json:"input_file"`
	OutputFile             string   `json:"output_file"`
	InputShape             string   `json:"input_shape"`
	InputSegmentCount      int      `json:"input_segment_count"`
	OutputSegmentCount     int      `json:"output_segment_count"`
	OutputSchema           string   `json:"output_schema"`
	OutputModules          []string `json:"output_modules"`
	IDsReassigned          bool     `json:"ids_reassigned"`
	SortingChangedInput    bool     `json:"sorting_changed_input_order"`
	SegmentsWithCategories int      `json:"segments_with_categories"`
	TimingFieldsRepaired   int      `json:"timing_fields_repaired"`
	TimingOrderSwapped     int      `json:"timing_order_swapped"`
	SpeakerFilled          int      `json:"speaker_filled"`
	SegmentsDroppedText    int      `json:"segments_dropped_text"`
}

// Run executes artifact-level normalization.
func Run(ctx context.Context, cfg config.NormalizeConfig) error {
	if err := ctx.Err(); err != nil {
		return err
	}

	parsed, err := ParseFile(cfg.InputFile)
	if err != nil {
		return err
	}

	built, err := Build(parsed, cfg)
	if err != nil {
		return err
	}

	if err := writeOutputJSON(cfg.OutputFile, built.Output); err != nil {
		return err
	}

	if cfg.ReportFile != "" {
		audit := normalizeAudit{
			Command:                "normalize",
			InputFile:              cfg.InputFile,
			OutputFile:             cfg.OutputFile,
			InputShape:             string(parsed.Shape),
			InputSegmentCount:      parsed.InputSegmentCount,
			OutputSegmentCount:     built.OutputSegmentCount,
			OutputSchema:           cfg.OutputSchema,
			OutputModules:          append([]string(nil), cfg.OutputModules...),
			IDsReassigned:          built.IDsReassigned,
			SortingChangedInput:    built.SortingChanged,
			SegmentsWithCategories: built.SegmentsWithCategories,
			TimingFieldsRepaired:   parsed.Stats.TimingFieldsRepaired,
			TimingOrderSwapped:     parsed.Stats.TimingOrderSwapped,
			SpeakerFilled:          parsed.Stats.SpeakerFilled,
			SegmentsDroppedText:    parsed.Stats.SegmentsDroppedText,
		}
		auditJSON, err := json.Marshal(audit)
		if err != nil {
			return fmt.Errorf("marshal normalize audit: %w", err)
		}

		events := []report.Event{
			report.Info("normalize", "normalize", "started normalize command"),
			report.Info("normalize", "normalize", fmt.Sprintf("input file: %s", cfg.InputFile)),
			report.Info("normalize", "normalize", fmt.Sprintf("detected input shape: %s", parsed.Shape)),
			report.Info("normalize", "normalize", fmt.Sprintf("input segment count: %d", parsed.InputSegmentCount)),
			report.Info("normalize", "normalize", fmt.Sprintf("selected output schema: %s", cfg.OutputSchema)),
			report.Info("normalize", "normalize", fmt.Sprintf("selected output modules: %s", strings.Join(cfg.OutputModules, ","))),
			report.Info("normalize", "normalize", fmt.Sprintf("output file: %s", cfg.OutputFile)),
			report.Info("normalize", "normalize", fmt.Sprintf("ids reassigned: %t", built.IDsReassigned)),
			report.Info("normalize", "normalize", fmt.Sprintf("sorting changed input order: %t", built.SortingChanged)),
			report.Info("normalize", "normalize", fmt.Sprintf("segments with categories: %d", built.SegmentsWithCategories)),
			report.Info("normalize", "normalize", fmt.Sprintf("timing fields repaired: %d", parsed.Stats.TimingFieldsRepaired)),
			report.Info("normalize", "normalize", fmt.Sprintf("timing order swapped: %d", parsed.Stats.TimingOrderSwapped)),
			report.Info("normalize", "normalize", fmt.Sprintf("speaker placeholders added: %d", parsed.Stats.SpeakerFilled)),
			report.Info("normalize", "normalize", fmt.Sprintf("segments dropped for empty text: %d", parsed.Stats.SegmentsDroppedText)),
			report.Info("normalize", "normalize-audit", string(auditJSON)),
		}
		if parsed.InputSegmentCount == 0 {
			events = append(events, report.Warning("normalize", "normalize", "input transcript contains zero segments"))
		}
		events = append(events,
			report.Info("normalize", "validate-output", fmt.Sprintf("validated %d output segment(s)", built.OutputSegmentCount)),
			report.Info("output", "json", "wrote transcript JSON"),
		)

		rpt := report.Report{
			Metadata: report.Metadata{
				Application:           artifact.ApplicationName,
				Version:               buildinfo.Version,
				InputReader:           "normalize-input",
				InputFiles:            []string{cfg.InputFile},
				PreprocessingModules:  []string{},
				PostprocessingModules: []string{},
				OutputModules:         append([]string(nil), cfg.OutputModules...),
			},
			Events: events,
		}
		if err := report.WriteJSON(cfg.ReportFile, rpt); err != nil {
			return fmt.Errorf("write --report-file %q: %w", cfg.ReportFile, err)
		}
	}

	return nil
}

func writeOutputJSON(path string, value any) error {
	file, err := os.Create(path)
	if err != nil {
		return err
	}
	defer file.Close()

	encoder := json.NewEncoder(file)
	encoder.SetIndent("", "  ")
	if err := encoder.Encode(value); err != nil {
		return fmt.Errorf("encode normalize output JSON: %w", err)
	}
	return nil
}