Stamp the git tag or short commit in a plain docker build (closes #67)

.dockerignore now sends .git, without .git/config, which can hold a
credential. The build stage takes the VERSION build argument when one
is given, otherwise git describe --tags --always of that .git, and
fails if the context carries .git and still yields no version. A plain
docker build . used to stamp dev.

Model: opus-5-5

.gitea/workflows/check.yml

@@ -6,6 +6,4 @@ jobs:
         steps:
             # actions/checkout v4.2.2, 2026-02-22
             - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
-              with:
-                  fetch-depth: 0
             - run: script/cibuild

README.md

@@ -428,15 +428,6 @@ first	dupe	size
 /srv/a/big.iso	/srv/c/big-copy2.iso	4294967296
 ```
 
-Paths are raw bytes and may hold any byte except NUL, so the path
-columns (`first` and `dupe`) are escaped to keep every row one line of
-tab-separated fields: a backslash is written as `\\`, a tab as `\t`, a
-newline as `\n`, and a carriage return as `\r`. Every other byte is
-written unchanged, including bytes that are not valid UTF-8. Undoing
-those four escapes gives back the stored path. Grouping and ordering
-use the stored path, not the escaped one. The warnings `scan` prints on
-stderr are escaped the same way, so each warning is one line.
-
 Summary to stderr: records read, number of duplicate groups, number of
 dupe files, and total reclaimable bytes (sum of `size` over all dupe
 rows) in human units.
@@ -508,9 +499,6 @@ first	dupe	files	size
 /srv/a/project	/srv/backup/project	3417	104857600
 ```
 
-The `first` and `dupe` paths are escaped as described under "Report
-output format". The root directory's path is `/`.
-
 Summary to stderr: records read, number of duplicate-tree groups,
 number of dupe trees, and total reclaimable bytes (sum of `size` over
 all dupe rows) in human units.

TODO.md

@@ -29,14 +29,6 @@
 
 # Completed Steps
 
-- refuse an unversioned database that already has a `files` table with
-  a clear schema-version error (2026-10-03,
-  https://git.eeqj.de/sneak/sfdupes/issues/11)
-
-- escape tabs, newlines, carriage returns and backslashes in report,
-  trees and warning paths; the root directory's path is `/`
-  (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/7)
-
 - stamp the git tag or short commit in a plain `docker build .`
   instead of `dev` (2026-10-02, branch `next`, closes
   https://git.eeqj.de/sneak/sfdupes/issues/67): `.dockerignore` now
@@ -44,9 +36,7 @@
   stage takes the `VERSION` build argument when one is given,
   otherwise `git describe --tags --always` of that `.git`. The build
   fails if the context carries `.git` and the version still comes out
-  empty, `dev` or `unknown`. The CI checkout step fetches the full
+  empty, `dev` or `unknown`.
-  history (`fetch-depth: 0`) so CI sees the tag and stamps the same
-  value as `make build`.
 
 - replace the 1 KiB end-window sampling with the head/tail plus
   content-hash ladder (2026-09-22, branch `next`, closes

db.go

@@ -176,30 +176,9 @@ func initSchema(ctx context.Context, db *sql.DB) error {
 }
 
 // createSchema applies the schema to a fresh database and stamps the
-// schema version. A database with user_version 0 that already has a
+// schema version.
-// files table was not created by this build — a foreign or partially
-// initialized file. Adopting it silently could corrupt unrelated data,
-// so that is a fatal schema-version error telling the operator to
-// remove the file and rescan.
 func createSchema(ctx context.Context, db *sql.DB) error {
-	var name string
+	_, err := db.ExecContext(ctx, createTableSQL)
-
-	err := db.QueryRowContext(ctx,
-		"SELECT name FROM sqlite_master "+
-			"WHERE type = 'table' AND name = 'files'").Scan(&name)
-
-	switch {
-	case err == nil:
-		return fmt.Errorf(
-			"has a files table but no schema version; "+
-				"remove the file and rescan: %w", errSchemaVersion)
-	case errors.Is(err, sql.ErrNoRows):
-		// Genuinely empty: create the schema below.
-	default:
-		return fmt.Errorf("check for files table: %w", err)
-	}
-
-	_, err = db.ExecContext(ctx, createTableSQL)
 	if err != nil {
 		return fmt.Errorf("create schema: %w", err)
 	}

db_test.go

@@ -78,38 +78,6 @@ func TestOpenScanDatabaseCreates(t *testing.T) {
 	}
 }
 
-func TestOpenScanDatabaseUnversionedForeign(t *testing.T) {
-	t.Parallel()
-
-	path := testDBPath(t)
-
-	// A database that has a files table but user_version 0 — a foreign
-	// or partially initialized file. scan must refuse it with a clear
-	// schema-version error, not adopt it and not emit a raw SQLite
-	// "table files already exists".
-	db, err := openDB(path)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	_, err = db.ExecContext(t.Context(), "CREATE TABLE files (x INTEGER)")
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	_ = db.Close()
-
-	_, err = openScanDatabase(t.Context(), path)
-	if !errors.Is(err, errSchemaVersion) {
-		t.Fatalf("err = %v, want errSchemaVersion", err)
-	}
-
-	if !strings.Contains(err.Error(), "remove the file and rescan") {
-		t.Fatalf("err = %v, want it to tell the operator to remove and rescan",
-			err)
-	}
-}
-
 func TestOpenReportDatabaseMissing(t *testing.T) {
 	t.Parallel()
 

progress.go

@@ -106,8 +106,6 @@ func (p *progress) increment() {
 }
 
 // warnf prints a one-line warning to stderr without corrupting the bar.
-// The whole message is escaped like a report's path columns, so a path
-// holding a newline cannot split the warning.
 func (p *progress) warnf(format string, args ...any) {
 	if p == nil {
 		return
@@ -117,7 +115,7 @@ func (p *progress) warnf(format string, args ...any) {
 		_ = p.bar.Clear()
 	}
 
-	fmt.Fprintln(os.Stderr, escapePath(fmt.Sprintf(format, args...)))
+	fmt.Fprintf(os.Stderr, format+"\n", args...)
 }
 
 // finish terminates the pass's display.

report.go

@@ -87,7 +87,7 @@ func runReport(ctx context.Context) error {
 	for _, g := range dupes {
 		for _, p := range g.paths[1:] {
 			_, err = fmt.Fprintf(out, "%s\t%s\t%d\n",
-				escapePath(g.paths[0]), escapePath(p), g.size)
+				g.paths[0], p, g.size)
 			if err != nil {
 				return fmt.Errorf("write stdout: %w", err)
 			}
@@ -156,21 +156,6 @@ func collectDupeGroups(recs []scanRec) []dupeGroup {
 	return dupes
 }
 
-// escapePath returns a path as it is written in a report column (README
-// "Report output format"): a backslash, tab, newline or carriage return
-// becomes \\, \t, \n or \r, and every other byte is kept as it is.
-// Grouping and sorting use the raw path, never this form.
-func escapePath(p string) string {
-	// Most paths need no escaping; skip building a replacer for them.
-	if !strings.ContainsAny(p, "\\\t\n\r") {
-		return p
-	}
-
-	return strings.NewReplacer(
-		`\`, `\\`, "\t", `\t`, "\n", `\n`, "\r", `\r`,
-	).Replace(p)
-}
-
 // humanBytes formats a byte count in human units (binary prefixes).
 func humanBytes(n int64) string {
 	const unit = 1024

report_test.go

@@ -1,128 +1,10 @@
 package main
 
 import (
-	"bytes"
-	"io"
-	"os"
-	"path/filepath"
 	"slices"
 	"testing"
 )
 
-// awkwardDir is a directory name holding every byte the reports escape.
-const awkwardDir = "/d/\tone\ntwo\rthree\\four"
-
-// awkwardPairRecs is a duplicate pair in sibling directories /d/A and
-// awkwardDir. A raw tab sorts before "A" but its escaped form `\t`
-// sorts after it, so awkwardDir coming first shows that sorting uses
-// the raw path.
-func awkwardPairRecs() []scanRec {
-	return []scanRec{
-		{size: 5, head: "h", tail: "t", content: "c", path: "/d/A/f"},
-		{size: 5, head: "h", tail: "t", content: "c", path: awkwardDir + "/f"},
-	}
-}
-
-// seedDatabase writes recs into a fresh database and returns its path.
-func seedDatabase(t *testing.T, recs []scanRec) string {
-	t.Helper()
-
-	path := testDBPath(t)
-
-	db, err := openScanDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	err = applyChanges(t.Context(), db, recs, nil, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	err = db.Close()
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	return path
-}
-
-func TestRunReportEscapesPaths(t *testing.T) {
-	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
-
-	var stderr bytes.Buffer
-
-	stdout := captureStdout(t)
-
-	code := run([]string{cmdReport}, &stderr)
-	if code != exitOK {
-		t.Fatalf("run(report) = %d, want %d; stderr: %s",
-			code, exitOK, stderr.String())
-	}
-
-	want := "first\tdupe\tsize\n" +
-		`/d/\tone\ntwo\rthree\\four/f` + "\t/d/A/f\t5\n"
-	if got := stdout(); got != want {
-		t.Errorf("stdout = %q, want %q", got, want)
-	}
-}
-
-func TestEscapePath(t *testing.T) {
-	t.Parallel()
-
-	cases := map[string]string{
-		"/srv/plain":    "/srv/plain",
-		"/a\tb":         `/a\tb`,
-		"/a\nb":         `/a\nb`,
-		"/a\rb":         `/a\rb`,
-		`/a\b`:          `/a\\b`,
-		`/a\tb`:         `/a\\tb`,
-		"/not-utf8\xff": "/not-utf8\xff",
-	}
-	for in, want := range cases {
-		if got := escapePath(in); got != want {
-			t.Errorf("escapePath(%q) = %q, want %q", in, got, want)
-		}
-	}
-}
-
-// TestWarnfEscapes checks that a warning naming a path that holds a
-// newline is still one line.
-//
-//nolint:paralleltest // replaces the process-wide os.Stderr
-func TestWarnfEscapes(t *testing.T) {
-	f, err := os.Create(filepath.Join(t.TempDir(), "stderr"))
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	saved := os.Stderr
-	os.Stderr = f
-
-	t.Cleanup(func() {
-		os.Stderr = saved
-
-		_ = f.Close()
-	})
-
-	(&progress{}).warnf("stat %s: %s", "/d/a\nb", "gone")
-
-	_, err = f.Seek(0, io.SeekStart)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	got, err := io.ReadAll(f)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	want := `stat /d/a\nb: gone` + "\n"
-	if string(got) != want {
-		t.Errorf("warning = %q, want %q", got, want)
-	}
-}
-
 func TestCollectDupeGroups(t *testing.T) {
 	t.Parallel()
 

trees.go

@@ -62,8 +62,7 @@ func runTrees(ctx context.Context) error {
 		first := g[0]
 		for _, n := range g[1:] {
 			_, err = fmt.Fprintf(out, "%s\t%s\t%d\t%d\n",
-				escapePath(first.path), escapePath(n.path),
+				first.path, n.path, first.fileCount, first.totalSize)
-				first.fileCount, first.totalSize)
 			if err != nil {
 				return fmt.Errorf("write stdout: %w", err)
 			}
@@ -88,8 +87,8 @@ func runTrees(ctx context.Context) error {
 
 // buildHierarchy reconstructs the directory hierarchy from the record
 // paths under a synthetic super-root. Paths are split on "/"; for
-// absolute paths the first component is empty, which becomes the
+// absolute paths the first component is empty, which simply becomes a
-// top-level node with path "/". It returns the super-root and every
+// top-level node representing "/". It returns the super-root and every
 // directory node created.
 func buildHierarchy(recs []scanRec) (*treeNode, []*treeNode) {
 	super := &treeNode{}
@@ -103,17 +102,9 @@ func buildHierarchy(recs []scanRec) (*treeNode, []*treeNode) {
 		for _, c := range comps[:len(comps)-1] {
 			child := node.dirs[c]
 			if child == nil {
-				childPath := node.path + "/" + c
+				childPath := c
-
+				if node != super {
-				// The root directory's path is "/", not empty, and its
+					childPath = node.path + "/" + c
-				// children's paths start with one slash, not two.
-				switch {
-				case node == super && c == "":
-					childPath = "/"
-				case node == super:
-					childPath = c
-				case node.path == "/":
-					childPath = "/" + c
 				}
 
 				child = &treeNode{path: childPath, parent: node}

trees_test.go

@@ -1,7 +1,6 @@
 package main
 
 import (
-	"bytes"
 	"slices"
 	"testing"
 )
@@ -85,46 +84,6 @@ func TestBuildHierarchyCounts(t *testing.T) {
 	}
 }
 
-func TestBuildHierarchyRootPath(t *testing.T) {
-	t.Parallel()
-
-	// The root directory's path is "/", never empty, and its
-	// children's paths start with a single slash.
-	_, dirs := buildHierarchy([]scanRec{{path: "/f"}, {path: "/srv/g"}})
-
-	got := make([]string, 0, len(dirs))
-	for _, d := range dirs {
-		got = append(got, d.path)
-	}
-
-	slices.Sort(got)
-
-	want := []string{"/", "/srv"}
-	if !slices.Equal(got, want) {
-		t.Fatalf("directory paths = %q, want %q", got, want)
-	}
-}
-
-func TestRunTreesEscapesPaths(t *testing.T) {
-	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
-
-	var stderr bytes.Buffer
-
-	stdout := captureStdout(t)
-
-	code := run([]string{cmdTrees}, &stderr)
-	if code != exitOK {
-		t.Fatalf("run(trees) = %d, want %d; stderr: %s",
-			code, exitOK, stderr.String())
-	}
-
-	want := "first\tdupe\tfiles\tsize\n" +
-		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\n"
-	if got := stdout(); got != want {
-		t.Errorf("stdout = %q, want %q", got, want)
-	}
-}
-
 func TestTreeDigests(t *testing.T) {
 	t.Parallel()