Add trim CLI command

This commit is contained in:
2026-05-08 14:53:59 +00:00
parent 1c0e4438ae
commit ac3dcf2557
7 changed files with 996 additions and 1 deletions

125
internal/cli/trim.go Normal file
View File

@@ -0,0 +1,125 @@
package cli
import (
"encoding/json"
"fmt"
"os"
"github.com/spf13/cobra"
"gitea.maximumdirect.net/eric/seriatim/internal/config"
"gitea.maximumdirect.net/eric/seriatim/internal/report"
triminternal "gitea.maximumdirect.net/eric/seriatim/internal/trim"
)
func newTrimCommand() *cobra.Command {
var opts config.TrimOptions
cmd := &cobra.Command{
Use: "trim",
Short: "Trim an existing seriatim transcript artifact by segment ID",
RunE: func(cmd *cobra.Command, args []string) error {
trimOpts := opts
if !cmd.Flags().Changed("output-schema") {
trimOpts.OutputSchema = ""
}
cfg, err := config.NewTrimConfig(trimOpts)
if err != nil {
return err
}
selector, err := triminternal.ParseSelector(cfg.Selector)
if err != nil {
return fmt.Errorf("invalid selector %q: %w", cfg.Selector, err)
}
data, err := os.ReadFile(cfg.InputFile)
if err != nil {
return fmt.Errorf("read --input-file %q: %w", cfg.InputFile, err)
}
artifact, err := triminternal.ParseArtifactJSON(data)
if err != nil {
return fmt.Errorf("--input-file %q: %w", cfg.InputFile, err)
}
mode := triminternal.ModeKeep
if cfg.Mode == "remove" {
mode = triminternal.ModeRemove
}
trimmed, err := triminternal.ApplyArtifact(artifact, triminternal.Options{
Mode: mode,
Selector: selector,
AllowEmpty: cfg.AllowEmpty,
})
if err != nil {
return err
}
outputSchema := artifact.Schema
if cfg.OutputSchema != "" {
outputSchema = cfg.OutputSchema
}
outputArtifact, err := triminternal.ConvertArtifact(trimmed.Artifact, outputSchema)
if err != nil {
return err
}
if err := triminternal.ValidateArtifact(outputArtifact); err != nil {
return fmt.Errorf("validate trimmed output: %w", err)
}
if err := writeOutputJSON(cfg.OutputFile, outputArtifact.Value()); err != nil {
return err
}
if cfg.ReportFile != "" {
rpt := report.Report{
Metadata: report.Metadata{
Application: outputArtifact.Application(),
Version: outputArtifact.Version(),
InputReader: "trim-artifact",
InputFiles: []string{cfg.InputFile},
OutputModules: []string{"json"},
},
Events: []report.Event{
report.Info("trim", "trim", fmt.Sprintf("mode=%s retained %d segment(s), removed %d segment(s)", cfg.Mode, len(trimmed.OldToNewID), len(trimmed.RemovedIDs))),
report.Info("trim", "validate-output", fmt.Sprintf("validated %d output segment(s)", outputArtifact.SegmentCount())),
report.Info("output", "json", "wrote transcript JSON"),
},
}
if err := report.WriteJSON(cfg.ReportFile, rpt); err != nil {
return err
}
}
return nil
},
}
flags := cmd.Flags()
flags.StringVar(&opts.InputFile, "input-file", "", "input seriatim transcript artifact JSON file")
flags.StringVar(&opts.OutputFile, "output-file", "", "output transcript JSON file")
flags.StringVar(&opts.ReportFile, "report-file", "", "optional report JSON file")
flags.StringVar(&opts.Keep, "keep", "", "segment ID selector to keep (for example: 1-10,15)")
flags.StringVar(&opts.Remove, "remove", "", "segment ID selector to remove (for example: 1-10,15)")
flags.StringVar(&opts.OutputSchema, "output-schema", "", "optional output JSON schema override: seriatim-minimal, seriatim-intermediate, or seriatim-full")
flags.BoolVar(&opts.AllowEmpty, "allow-empty", false, "allow trimming to an empty transcript")
return cmd
}
func writeOutputJSON(path string, value any) error {
file, err := os.Create(path)
if err != nil {
return err
}
defer file.Close()
enc := json.NewEncoder(file)
enc.SetIndent("", " ")
return enc.Encode(value)
}