Add trim report output

internal/cli/trim.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"os"
+	"sort"
 
 	"github.com/spf13/cobra"
 
@@ -12,6 +13,29 @@ import (
 	triminternal "gitea.maximumdirect.net/eric/seriatim/internal/trim"
 )
 
+type trimAuditReport struct {
+	Operation               string          `json:"operation"`
+	InputFile               string          `json:"input_file"`
+	OutputFile              string          `json:"output_file"`
+	InputSchema             string          `json:"input_schema"`
+	OutputSchema            string          `json:"output_schema"`
+	Mode                    string          `json:"mode"`
+	Selector                string          `json:"selector"`
+	SelectedIDs             []int           `json:"selected_ids"`
+	AllowEmpty              bool            `json:"allow_empty"`
+	InputSegmentCount       int             `json:"input_segment_count"`
+	RetainedSegmentCount    int             `json:"retained_segment_count"`
+	RemovedSegmentCount     int             `json:"removed_segment_count"`
+	RemovedInputIDs         []int           `json:"removed_input_ids"`
+	OldToNewIDMapping       []trimIDMapping `json:"old_to_new_id_mapping"`
+	OverlapGroupsRecomputed bool            `json:"overlap_groups_recomputed"`
+}
+
+type trimIDMapping struct {
+	OldID int `json:"old_id"`
+	NewID int `json:"new_id"`
+}
+
 func newTrimCommand() *cobra.Command {
 	var opts config.TrimOptions
 
@@ -43,6 +67,8 @@ func newTrimCommand() *cobra.Command {
 			if err != nil {
 				return fmt.Errorf("--input-file %q: %w", cfg.InputFile, err)
 			}
+			inputSegmentCount := artifact.SegmentCount()
+			inputSchema := artifact.Schema
 
 			mode := triminternal.ModeKeep
 			if cfg.Mode == "remove" {
@@ -77,6 +103,28 @@ func newTrimCommand() *cobra.Command {
 			}
 
 			if cfg.ReportFile != "" {
+				audit := trimAuditReport{
+					Operation:               "trim",
+					InputFile:               cfg.InputFile,
+					OutputFile:              cfg.OutputFile,
+					InputSchema:             inputSchema,
+					OutputSchema:            outputArtifact.Schema,
+					Mode:                    cfg.Mode,
+					Selector:                cfg.Selector,
+					SelectedIDs:             selector.IDs(),
+					AllowEmpty:              cfg.AllowEmpty,
+					InputSegmentCount:       inputSegmentCount,
+					RetainedSegmentCount:    len(trimmed.OldToNewID),
+					RemovedSegmentCount:     len(trimmed.RemovedIDs),
+					RemovedInputIDs:         append([]int(nil), trimmed.RemovedIDs...),
+					OldToNewIDMapping:       orderedIDMapping(trimmed.OldToNewID),
+					OverlapGroupsRecomputed: trimmed.OverlapGroupsRecomputed,
+				}
+				auditJSON, err := json.Marshal(audit)
+				if err != nil {
+					return fmt.Errorf("marshal trim audit report: %w", err)
+				}
+
 				rpt := report.Report{
 					Metadata: report.Metadata{
 						Application:   outputArtifact.Application(),
@@ -86,7 +134,8 @@ func newTrimCommand() *cobra.Command {
 						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", "trim", fmt.Sprintf("trimmed %d input segment(s) into %d output segment(s) with mode=%s", inputSegmentCount, outputArtifact.SegmentCount(), cfg.Mode)),
+						report.Info("trim", "trim-audit", string(auditJSON)),
 						report.Info("trim", "validate-output", fmt.Sprintf("validated %d output segment(s)", outputArtifact.SegmentCount())),
 						report.Info("output", "json", "wrote transcript JSON"),
 					},
@@ -123,3 +172,20 @@ func writeOutputJSON(path string, value any) error {
 	enc.SetIndent("", "  ")
 	return enc.Encode(value)
 }
+
+func orderedIDMapping(mapping map[int]int) []trimIDMapping {
+	keys := make([]int, 0, len(mapping))
+	for oldID := range mapping {
+		keys = append(keys, oldID)
+	}
+	sort.Ints(keys)
+
+	pairs := make([]trimIDMapping, 0, len(keys))
+	for _, oldID := range keys {
+		pairs = append(pairs, trimIDMapping{
+			OldID: oldID,
+			NewID: mapping[oldID],
+		})
+	}
+	return pairs
+}