sow-tools/internal/assets/dupes.go

package assets

import (
	"flag"
	"fmt"
	"io"
	"os"
	"path/filepath"
	"sort"
	"strings"
)

// allFiles returns every regular file under root (recursive).
func allFiles(root string) ([]string, error) {
	var out []string
	err := filepath.WalkDir(root, func(p string, d os.DirEntry, err error) error {
		if err != nil {
			return err
		}
		if !d.IsDir() {
			out = append(out, p)
		}
		return nil
	})
	sort.Strings(out)
	return out, err
}

// runCheckDupes reports files whose lower-cased basename collides across the
// given dirs. Read-only. Exit exitFail if any collision is found.
func runCheckDupes(args []string, stdout, stderr io.Writer) int {
	fs := flag.NewFlagSet("check-dupes", flag.ContinueOnError)
	fs.SetOutput(stderr)
	if err := fs.Parse(args); err != nil {
		return exitUsage
	}
	dirs := fs.Args()
	if len(dirs) == 0 {
		fmt.Fprintln(stderr, "assets check-dupes: usage: check-dupes <dir>...")
		return exitUsage
	}

	first := map[string]string{}
	fail := false
	for _, dir := range dirs {
		if fi, err := os.Stat(dir); err != nil || !fi.IsDir() {
			fmt.Fprintf(stderr, "assets check-dupes: no such dir: %s\n", dir)
			return exitUsage
		}
		files, err := allFiles(dir)
		if err != nil {
			fmt.Fprintln(stderr, "assets check-dupes:", err)
			return exitTool
		}
		for _, f := range files {
			key := strings.ToLower(filepath.Base(f))
			if prev, ok := first[key]; ok {
				fmt.Fprintf(stderr, "runtime-name collision: %s collides with %s\n", f, prev)
				fail = true
			} else {
				first[key] = f
			}
		}
	}
	if fail {
		fmt.Fprintln(stderr, "check-dupes: found runtime-name collision(s)")
		return exitFail
	}
	fmt.Fprintln(stdout, "check-dupes: OK")
	return exitOK
}

// runCleanDupes deletes files from <clean> whose lower-cased basename collides
// with any file in <primary>. Mutates only <clean>. Refuses to run if the two
// trees overlap.
func runCleanDupes(args []string, stdout, stderr io.Writer) int {
	fs := flag.NewFlagSet("clean-dupes", flag.ContinueOnError)
	fs.SetOutput(stderr)
	dryRun := fs.Bool("dry-run", false, "report deletions without removing")
	if err := fs.Parse(args); err != nil {
		return exitUsage
	}
	pos := fs.Args()
	if len(pos) != 2 {
		fmt.Fprintln(stderr, "assets clean-dupes: usage: clean-dupes [--dry-run] <primary> <clean>")
		return exitUsage
	}
	primary, clean := pos[0], pos[1]
	for _, d := range []string{primary, clean} {
		if fi, err := os.Stat(d); err != nil || !fi.IsDir() {
			fmt.Fprintf(stderr, "assets clean-dupes: no such dir: %s\n", d)
			return exitUsage
		}
	}
	primaryReal, err1 := filepath.EvalSymlinks(primary)
	cleanReal, err2 := filepath.EvalSymlinks(clean)
	if err1 != nil || err2 != nil {
		fmt.Fprintln(stderr, "assets clean-dupes: cannot resolve dirs")
		return exitTool
	}
	if overlaps(primaryReal, cleanReal) {
		fmt.Fprintln(stderr, "assets clean-dupes: primary and clean dirs must not overlap")
		return exitUsage
	}

	primaryFiles, err := allFiles(primary)
	if err != nil {
		fmt.Fprintln(stderr, "assets clean-dupes:", err)
		return exitTool
	}
	names := map[string]bool{}
	for _, f := range primaryFiles {
		names[strings.ToLower(filepath.Base(f))] = true
	}

	cleanFiles, err := allFiles(clean)
	if err != nil {
		fmt.Fprintln(stderr, "assets clean-dupes:", err)
		return exitTool
	}
	removed := 0
	for _, f := range cleanFiles {
		if !names[strings.ToLower(filepath.Base(f))] {
			continue
		}
		if *dryRun {
			fmt.Fprintf(stderr, "would delete clean-tree collision: %s\n", f)
		} else {
			if err := os.Remove(f); err != nil {
				fmt.Fprintln(stderr, "assets clean-dupes:", err)
				return exitTool
			}
			fmt.Fprintf(stderr, "deleted clean-tree collision: %s\n", f)
		}
		removed++
	}
	verb := "removed"
	if *dryRun {
		verb = "would remove"
	}
	fmt.Fprintf(stdout, "clean-dupes: %s %d file(s)\n", verb, removed)
	return exitOK
}

// overlaps reports whether either directory contains the other (or they are
// equal), using cleaned absolute-ish paths with a trailing separator.
func overlaps(a, b string) bool {
	as := a + string(filepath.Separator)
	bs := b + string(filepath.Separator)
	return strings.HasPrefix(as, bs) || strings.HasPrefix(bs, as)
}