seriatim/internal/trim/artifact.go

package trim

import (
	"encoding/json"
	"fmt"

	"gitea.maximumdirect.net/eric/seriatim/schema"
)

const (
	SchemaMinimal      = "seriatim-minimal"
	SchemaIntermediate = "seriatim-intermediate"
	SchemaFull         = "seriatim-full"
)

// Artifact stores a parsed seriatim output artifact of one supported schema.
type Artifact struct {
	Schema       string
	Full         *schema.Transcript
	Intermediate *schema.IntermediateTranscript
	Minimal      *schema.MinimalTranscript
}

// ApplyArtifactResult contains trimmed artifact output and ID mapping metadata.
type ApplyArtifactResult struct {
	Artifact                Artifact
	OldToNewID              map[int]int
	RemovedIDs              []int
	OverlapGroupsRecomputed bool
}

// ParseArtifactJSON parses and validates a serialized seriatim output artifact.
func ParseArtifactJSON(data []byte) (Artifact, error) {
	var full schema.Transcript
	if err := json.Unmarshal(data, &full); err == nil {
		if err := schema.ValidateTranscript(full); err == nil {
			return Artifact{
				Schema: SchemaFull,
				Full:   &full,
			}, nil
		}
	}

	var intermediate schema.IntermediateTranscript
	if err := json.Unmarshal(data, &intermediate); err == nil {
		if err := schema.ValidateIntermediateTranscript(intermediate); err == nil {
			return Artifact{
				Schema:       SchemaIntermediate,
				Intermediate: &intermediate,
			}, nil
		}
	}

	var minimal schema.MinimalTranscript
	if err := json.Unmarshal(data, &minimal); err == nil {
		if err := schema.ValidateMinimalTranscript(minimal); err == nil {
			return Artifact{
				Schema:  SchemaMinimal,
				Minimal: &minimal,
			}, nil
		}
	}

	return Artifact{}, fmt.Errorf("input JSON is not a valid seriatim output artifact")
}

// ValidateArtifact validates an artifact against its declared schema.
func ValidateArtifact(artifact Artifact) error {
	switch artifact.Schema {
	case SchemaFull:
		if artifact.Full == nil {
			return fmt.Errorf("full artifact payload is missing")
		}
		return schema.ValidateTranscript(*artifact.Full)
	case SchemaIntermediate:
		if artifact.Intermediate == nil {
			return fmt.Errorf("intermediate artifact payload is missing")
		}
		return schema.ValidateIntermediateTranscript(*artifact.Intermediate)
	case SchemaMinimal:
		if artifact.Minimal == nil {
			return fmt.Errorf("minimal artifact payload is missing")
		}
		return schema.ValidateMinimalTranscript(*artifact.Minimal)
	default:
		return fmt.Errorf("unsupported artifact schema %q", artifact.Schema)
	}
}

// Value returns the artifact value for JSON serialization.
func (artifact Artifact) Value() any {
	switch artifact.Schema {
	case SchemaFull:
		if artifact.Full == nil {
			return schema.Transcript{}
		}
		return *artifact.Full
	case SchemaIntermediate:
		if artifact.Intermediate == nil {
			return schema.IntermediateTranscript{}
		}
		return *artifact.Intermediate
	case SchemaMinimal:
		if artifact.Minimal == nil {
			return schema.MinimalTranscript{}
		}
		return *artifact.Minimal
	default:
		return nil
	}
}

// SegmentCount returns the number of segments in the artifact.
func (artifact Artifact) SegmentCount() int {
	switch artifact.Schema {
	case SchemaFull:
		if artifact.Full == nil {
			return 0
		}
		return len(artifact.Full.Segments)
	case SchemaIntermediate:
		if artifact.Intermediate == nil {
			return 0
		}
		return len(artifact.Intermediate.Segments)
	case SchemaMinimal:
		if artifact.Minimal == nil {
			return 0
		}
		return len(artifact.Minimal.Segments)
	default:
		return 0
	}
}

// Application returns artifact metadata application name.
func (artifact Artifact) Application() string {
	switch artifact.Schema {
	case SchemaFull:
		if artifact.Full == nil {
			return ""
		}
		return artifact.Full.Metadata.Application
	case SchemaIntermediate:
		if artifact.Intermediate == nil {
			return ""
		}
		return artifact.Intermediate.Metadata.Application
	case SchemaMinimal:
		if artifact.Minimal == nil {
			return ""
		}
		return artifact.Minimal.Metadata.Application
	default:
		return ""
	}
}

// Version returns artifact metadata version.
func (artifact Artifact) Version() string {
	switch artifact.Schema {
	case SchemaFull:
		if artifact.Full == nil {
			return ""
		}
		return artifact.Full.Metadata.Version
	case SchemaIntermediate:
		if artifact.Intermediate == nil {
			return ""
		}
		return artifact.Intermediate.Metadata.Version
	case SchemaMinimal:
		if artifact.Minimal == nil {
			return ""
		}
		return artifact.Minimal.Metadata.Version
	default:
		return ""
	}
}

// ApplyArtifact trims a parsed artifact while preserving its input schema.
func ApplyArtifact(input Artifact, opts Options) (ApplyArtifactResult, error) {
	switch input.Schema {
	case SchemaFull:
		if input.Full == nil {
			return ApplyArtifactResult{}, fmt.Errorf("full artifact payload is missing")
		}
		result, err := Apply(*input.Full, opts)
		if err != nil {
			return ApplyArtifactResult{}, err
		}
		out := result.Transcript
		return ApplyArtifactResult{
			Artifact: Artifact{
				Schema: SchemaFull,
				Full:   &out,
			},
			OldToNewID:              result.OldToNewID,
			RemovedIDs:              result.RemovedIDs,
			OverlapGroupsRecomputed: true,
		}, nil
	case SchemaIntermediate:
		if input.Intermediate == nil {
			return ApplyArtifactResult{}, fmt.Errorf("intermediate artifact payload is missing")
		}
		result, err := ApplyIntermediate(*input.Intermediate, opts)
		if err != nil {
			return ApplyArtifactResult{}, err
		}
		out := result.Transcript
		return ApplyArtifactResult{
			Artifact: Artifact{
				Schema:       SchemaIntermediate,
				Intermediate: &out,
			},
			OldToNewID:              result.OldToNewID,
			RemovedIDs:              result.RemovedIDs,
			OverlapGroupsRecomputed: false,
		}, nil
	case SchemaMinimal:
		if input.Minimal == nil {
			return ApplyArtifactResult{}, fmt.Errorf("minimal artifact payload is missing")
		}
		result, err := ApplyMinimal(*input.Minimal, opts)
		if err != nil {
			return ApplyArtifactResult{}, err
		}
		out := result.Transcript
		return ApplyArtifactResult{
			Artifact: Artifact{
				Schema:  SchemaMinimal,
				Minimal: &out,
			},
			OldToNewID:              result.OldToNewID,
			RemovedIDs:              result.RemovedIDs,
			OverlapGroupsRecomputed: false,
		}, nil
	default:
		return ApplyArtifactResult{}, fmt.Errorf("unsupported artifact schema %q", input.Schema)
	}
}

// ConvertArtifact converts a parsed artifact to another supported output schema.
func ConvertArtifact(input Artifact, outputSchema string) (Artifact, error) {
	if outputSchema == "" || outputSchema == input.Schema {
		return input, nil
	}

	switch input.Schema {
	case SchemaFull:
		if input.Full == nil {
			return Artifact{}, fmt.Errorf("full artifact payload is missing")
		}
		switch outputSchema {
		case SchemaIntermediate:
			out := intermediateFromFull(*input.Full)
			return Artifact{
				Schema:       SchemaIntermediate,
				Intermediate: &out,
			}, nil
		case SchemaMinimal:
			out := minimalFromFull(*input.Full)
			return Artifact{
				Schema:  SchemaMinimal,
				Minimal: &out,
			}, nil
		default:
			return Artifact{}, fmt.Errorf("unsupported output schema %q", outputSchema)
		}
	case SchemaIntermediate:
		if input.Intermediate == nil {
			return Artifact{}, fmt.Errorf("intermediate artifact payload is missing")
		}
		switch outputSchema {
		case SchemaMinimal:
			out := minimalFromIntermediate(*input.Intermediate)
			return Artifact{
				Schema:  SchemaMinimal,
				Minimal: &out,
			}, nil
		case SchemaFull:
			return Artifact{}, fmt.Errorf("cannot emit %q from %q input artifact", SchemaFull, SchemaIntermediate)
		default:
			return Artifact{}, fmt.Errorf("unsupported output schema %q", outputSchema)
		}
	case SchemaMinimal:
		if input.Minimal == nil {
			return Artifact{}, fmt.Errorf("minimal artifact payload is missing")
		}
		switch outputSchema {
		case SchemaIntermediate:
			out := intermediateFromMinimal(*input.Minimal)
			return Artifact{
				Schema:       SchemaIntermediate,
				Intermediate: &out,
			}, nil
		case SchemaFull:
			return Artifact{}, fmt.Errorf("cannot emit %q from %q input artifact", SchemaFull, SchemaMinimal)
		default:
			return Artifact{}, fmt.Errorf("unsupported output schema %q", outputSchema)
		}
	default:
		return Artifact{}, fmt.Errorf("unsupported input schema %q", input.Schema)
	}
}

func intermediateFromFull(input schema.Transcript) schema.IntermediateTranscript {
	segments := make([]schema.IntermediateSegment, len(input.Segments))
	for index, segment := range input.Segments {
		segments[index] = schema.IntermediateSegment{
			ID:         segment.ID,
			Start:      segment.Start,
			End:        segment.End,
			Speaker:    segment.Speaker,
			Text:       segment.Text,
			Categories: append([]string(nil), segment.Categories...),
		}
	}
	return schema.IntermediateTranscript{
		Metadata: schema.IntermediateMetadata{
			Application:  input.Metadata.Application,
			Version:      input.Metadata.Version,
			OutputSchema: SchemaIntermediate,
		},
		Segments: segments,
	}
}

func minimalFromFull(input schema.Transcript) schema.MinimalTranscript {
	segments := make([]schema.MinimalSegment, len(input.Segments))
	for index, segment := range input.Segments {
		segments[index] = schema.MinimalSegment{
			ID:      segment.ID,
			Start:   segment.Start,
			End:     segment.End,
			Speaker: segment.Speaker,
			Text:    segment.Text,
		}
	}
	return schema.MinimalTranscript{
		Metadata: schema.MinimalMetadata{
			Application:  input.Metadata.Application,
			Version:      input.Metadata.Version,
			OutputSchema: SchemaMinimal,
		},
		Segments: segments,
	}
}

func minimalFromIntermediate(input schema.IntermediateTranscript) schema.MinimalTranscript {
	segments := make([]schema.MinimalSegment, len(input.Segments))
	for index, segment := range input.Segments {
		segments[index] = schema.MinimalSegment{
			ID:      segment.ID,
			Start:   segment.Start,
			End:     segment.End,
			Speaker: segment.Speaker,
			Text:    segment.Text,
		}
	}
	return schema.MinimalTranscript{
		Metadata: schema.MinimalMetadata{
			Application:  input.Metadata.Application,
			Version:      input.Metadata.Version,
			OutputSchema: SchemaMinimal,
		},
		Segments: segments,
	}
}

func intermediateFromMinimal(input schema.MinimalTranscript) schema.IntermediateTranscript {
	segments := make([]schema.IntermediateSegment, len(input.Segments))
	for index, segment := range input.Segments {
		segments[index] = schema.IntermediateSegment{
			ID:      segment.ID,
			Start:   segment.Start,
			End:     segment.End,
			Speaker: segment.Speaker,
			Text:    segment.Text,
		}
	}
	return schema.IntermediateTranscript{
		Metadata: schema.IntermediateMetadata{
			Application:  input.Metadata.Application,
			Version:      input.Metadata.Version,
			OutputSchema: SchemaIntermediate,
		},
		Segments: segments,
	}
}