notarius/internal/modules/input/seriatim/model.go

package seriatim

import (
	"bytes"
	"encoding/json"
	"fmt"
	"io"
)

type transcript struct {
	Metadata map[string]any `json:"metadata"`
	Segments []segment      `json:"segments"`
}

type segment struct {
	ID      string      `json:"id"`
	Start   json.Number `json:"start"`
	End     json.Number `json:"end"`
	Speaker string      `json:"speaker"`
	Text    string      `json:"text"`
}

func decodeTranscript(raw []byte) (transcript, error) {
	var fields map[string]json.RawMessage
	if err := decodeJSON(raw, &fields); err != nil {
		return transcript{}, err
	}
	if fields == nil {
		return transcript{}, fmt.Errorf("top-level value must be an object")
	}

	metadataRaw, ok := fields["metadata"]
	if !ok {
		return transcript{}, fmt.Errorf("metadata is required")
	}
	var metadata map[string]any
	if err := decodeJSON(metadataRaw, &metadata); err != nil {
		return transcript{}, fmt.Errorf("metadata must be an object: %w", err)
	}
	if metadata == nil {
		return transcript{}, fmt.Errorf("metadata must be an object")
	}

	segmentsRaw, ok := fields["segments"]
	if !ok {
		return transcript{}, fmt.Errorf("segments are required")
	}
	var segments []segment
	if err := decodeJSON(segmentsRaw, &segments); err != nil {
		return transcript{}, fmt.Errorf("segments must be an array: %w", err)
	}
	if segments == nil {
		return transcript{}, fmt.Errorf("segments must be an array")
	}

	return transcript{
		Metadata: metadata,
		Segments: segments,
	}, nil
}

func decodeJSON(raw []byte, out any) error {
	decoder := json.NewDecoder(bytes.NewReader(raw))
	decoder.UseNumber()
	if err := decoder.Decode(out); err != nil {
		return err
	}
	if err := decoder.Decode(&struct{}{}); err != io.EOF {
		if err == nil {
			return fmt.Errorf("unexpected trailing JSON value")
		}
		return err
	}
	return nil
}