Add sfdupes implementation: scan, report, and trees subcommands

main.go

@@ -0,0 +1,81 @@
+// Command sfdupes quickly identifies candidate duplicate files across
+// very large filesystems without reading full file contents. Files are
+// considered duplicates when they have identical size, identical SHA-256
+// of their first 1024 bytes, and identical SHA-256 of their last 1024
+// bytes.
+//
+// Usage:
+//
+//	sfdupes scan [-root /srv] [-workers N] > files.dat
+//	sfdupes report [files.dat|-] > dupes.tsv
+//	sfdupes trees [files.dat|-] > dupetrees.tsv
+//
+// See README.md for the complete specification.
+package main
+
+import (
+	"fmt"
+	"os"
+
+	"github.com/spf13/cobra"
+)
+
+func main() {
+	root := &cobra.Command{
+		Use:   "sfdupes",
+		Short: "Find candidate duplicate files by size and head/tail SHA-256",
+		Args:  cobra.NoArgs,
+		Run: func(cmd *cobra.Command, args []string) {
+			// A missing subcommand prints usage and exits 2.
+			_ = cmd.Usage()
+			os.Exit(2)
+		},
+	}
+	// Everything on stdout is machine-readable data; all human-facing
+	// output (help, usage, errors) goes to stderr.
+	root.SetOut(os.Stderr)
+	root.SetErr(os.Stderr)
+	root.CompletionOptions.DisableDefaultCmd = true
+
+	scanCmd := &cobra.Command{
+		Use:   "scan [-root /srv] [-workers N]",
+		Short: "Walk a tree and emit one record per regular file on stdout",
+		// The README specifies single-dash flags (-root, -workers);
+		// parse them with the stdlib flag package inside runScan.
+		DisableFlagParsing: true,
+		Run: func(cmd *cobra.Command, args []string) {
+			runScan(args)
+		},
+	}
+
+	reportCmd := &cobra.Command{
+		Use:   "report [files.dat|-]",
+		Short: "Read a scan stream and print the file-level duplicates report",
+		Args:  cobra.MaximumNArgs(1),
+		Run: func(cmd *cobra.Command, args []string) {
+			runReport(args)
+		},
+	}
+
+	treesCmd := &cobra.Command{
+		Use:   "trees [files.dat|-]",
+		Short: "Read a scan stream and print the duplicate-tree report",
+		Args:  cobra.MaximumNArgs(1),
+		Run: func(cmd *cobra.Command, args []string) {
+			runTrees(args)
+		},
+	}
+
+	root.AddCommand(scanCmd, reportCmd, treesCmd)
+	if err := root.Execute(); err != nil {
+		// Cobra has already printed the error and usage to stderr;
+		// an invalid subcommand or bad arguments is a usage error.
+		os.Exit(2)
+	}
+}
+
+// fatalf reports a fatal error and exits 1.
+func fatalf(format string, args ...any) {
+	fmt.Fprintf(os.Stderr, "sfdupes: "+format+"\n", args...)
+	os.Exit(1)
+}