Files
seriatim/internal/builtin/postprocess.go

195 lines
5.7 KiB
Go

package builtin
import (
"context"
"fmt"
"gitea.maximumdirect.net/eric/seriatim/internal/artifact"
"gitea.maximumdirect.net/eric/seriatim/internal/autocorrect"
"gitea.maximumdirect.net/eric/seriatim/internal/backchannel"
"gitea.maximumdirect.net/eric/seriatim/internal/coalesce"
"gitea.maximumdirect.net/eric/seriatim/internal/config"
"gitea.maximumdirect.net/eric/seriatim/internal/filler"
"gitea.maximumdirect.net/eric/seriatim/internal/model"
"gitea.maximumdirect.net/eric/seriatim/internal/overlap"
"gitea.maximumdirect.net/eric/seriatim/internal/report"
"gitea.maximumdirect.net/eric/seriatim/schema"
)
type assignIDs struct{}
func (assignIDs) Name() string {
return "assign-ids"
}
func (assignIDs) Process(ctx context.Context, in model.MergedTranscript, cfg config.Config) (model.MergedTranscript, []report.Event, error) {
if err := ctx.Err(); err != nil {
return model.MergedTranscript{}, nil, err
}
for index := range in.Segments {
in.Segments[index].ID = index + 1
}
return in, []report.Event{
report.Info("postprocessing", "assign-ids", "assigned final segment IDs"),
}, nil
}
type validateOutput struct{}
func (validateOutput) Name() string {
return "validate-output"
}
func (validateOutput) Process(ctx context.Context, in model.MergedTranscript, cfg config.Config) (model.MergedTranscript, []report.Event, error) {
if err := ctx.Err(); err != nil {
return model.MergedTranscript{}, nil, err
}
transcript := artifact.FromMerged(cfg, in)
if err := schema.ValidateTranscript(transcript); err != nil {
return model.MergedTranscript{}, nil, fmt.Errorf("validate-output: %w", err)
}
return in, []report.Event{
report.Info("postprocessing", "validate-output", fmt.Sprintf("validated %d output segment(s)", len(in.Segments))),
}, nil
}
type detectOverlaps struct{}
func (detectOverlaps) Name() string {
return "detect-overlaps"
}
func (detectOverlaps) Process(ctx context.Context, in model.MergedTranscript, cfg config.Config) (model.MergedTranscript, []report.Event, error) {
if err := ctx.Err(); err != nil {
return model.MergedTranscript{}, nil, err
}
in = overlap.Detect(in)
return in, []report.Event{
report.Info("postprocessing", "detect-overlaps", fmt.Sprintf("detected %d overlap group(s)", len(in.OverlapGroups))),
}, nil
}
type resolveOverlaps struct{}
func (resolveOverlaps) Name() string {
return "resolve-overlaps"
}
func (resolveOverlaps) Process(ctx context.Context, in model.MergedTranscript, cfg config.Config) (model.MergedTranscript, []report.Event, error) {
if err := ctx.Err(); err != nil {
return model.MergedTranscript{}, nil, err
}
resolved, summary, err := overlap.Resolve(in, cfg.OverlapWordRunGap, cfg.WordRunReorderWindow)
if err != nil {
return model.MergedTranscript{}, nil, err
}
return resolved, []report.Event{
report.Info(
"postprocessing",
"resolve-overlaps",
fmt.Sprintf(
"processed %d overlap group(s); changed %d; removed %d original segment(s); created %d replacement segment(s)",
summary.GroupsProcessed,
summary.GroupsChanged,
summary.OriginalsRemoved,
summary.ReplacementsCreated,
),
),
}, nil
}
type backchannelPostprocessor struct{}
func (backchannelPostprocessor) Name() string {
return "backchannel"
}
func (backchannelPostprocessor) Process(ctx context.Context, in model.MergedTranscript, cfg config.Config) (model.MergedTranscript, []report.Event, error) {
if err := ctx.Err(); err != nil {
return model.MergedTranscript{}, nil, err
}
out, tagged := backchannel.Apply(in)
return out, []report.Event{
report.Info("postprocessing", "backchannel", fmt.Sprintf("tagged %d backchannel segment(s)", tagged)),
}, nil
}
type fillerPostprocessor struct{}
func (fillerPostprocessor) Name() string {
return "filler"
}
func (fillerPostprocessor) Process(ctx context.Context, in model.MergedTranscript, cfg config.Config) (model.MergedTranscript, []report.Event, error) {
if err := ctx.Err(); err != nil {
return model.MergedTranscript{}, nil, err
}
out, tagged := filler.Apply(in)
return out, []report.Event{
report.Info("postprocessing", "filler", fmt.Sprintf("tagged %d filler segment(s)", tagged)),
}, nil
}
type coalescePostprocessor struct{}
func (coalescePostprocessor) Name() string {
return "coalesce"
}
func (coalescePostprocessor) Process(ctx context.Context, in model.MergedTranscript, cfg config.Config) (model.MergedTranscript, []report.Event, error) {
if err := ctx.Err(); err != nil {
return model.MergedTranscript{}, nil, err
}
out, summary := coalesce.Apply(in, cfg.CoalesceGap)
return out, []report.Event{
report.Info(
"postprocessing",
"coalesce",
fmt.Sprintf("merged %d original segment(s) into %d coalesced segment(s)", summary.OriginalSegmentsMerged, summary.CoalescedSegments),
),
}, nil
}
type autocorrectPostprocessor struct{}
func (autocorrectPostprocessor) Name() string {
return "autocorrect"
}
func (autocorrectPostprocessor) Process(ctx context.Context, in model.MergedTranscript, cfg config.Config) (model.MergedTranscript, []report.Event, error) {
if err := ctx.Err(); err != nil {
return model.MergedTranscript{}, nil, err
}
if cfg.AutocorrectFile == "" {
return in, []report.Event{
report.Info("postprocessing", "autocorrect", "skipped autocorrect because no autocorrect file was supplied"),
}, nil
}
rules, err := autocorrect.Load(cfg.AutocorrectFile)
if err != nil {
return model.MergedTranscript{}, nil, err
}
replacements := 0
for index := range in.Segments {
var count int
in.Segments[index].Text, count = rules.Apply(in.Segments[index].Text)
replacements += count
}
return in, []report.Event{
report.Info("postprocessing", "autocorrect", fmt.Sprintf("applied %d autocorrect replacement(s)", replacements)),
}, nil
}