Leave removed copies out of report and trees (closes #173) (#184)

internal/sfdupes/scan_test.go

@@ -1215,7 +1215,7 @@ func assertSmokeTreeGroups(t *testing.T, dir string, db *sql.DB) {
 
 	super, dirs := dbTree(t, db)
 
-	tg := collectTreeGroups(dirs, super, nil)
+	tg := collectTreeGroups(dirs, super, everyPathExists, nil)
 	if len(tg) != 1 {
 		t.Fatalf("len(tree groups) = %d, want 1", len(tg))
 	}
@@ -2307,23 +2307,86 @@ func TestPruneRoots(t *testing.T) {
 	}
 }
 
-func TestReportsNeverTouchFilesystem(t *testing.T) {
-	t.Parallel()
+// TestRunReportsLeaveOutRemovedCopies scans the smoke tree, then
+// removes copies the reports name. report leaves out each removed file,
+// and a group left with one path. trees checks only the root of each
+// duplicate tree: with a file under t2 removed it still names t2, and
+// with t2 removed it names nothing.
+func TestRunReportsLeaveOutRemovedCopies(t *testing.T) {
+	t.Setenv(databaseEnv, testDBPath(t))
 
 	dir := buildSmokeTree(t)
-	db := openTestDB(t)
+	p := func(name string) string { return filepath.Join(dir, name) }
 
-	syncTree(t, db, dir)
+	scanOK(t, dir)
 
-	// Remove the scanned tree entirely; the analysis must be
-	// unaffected because it reads the database alone.
-	err := os.RemoveAll(dir)
+	for _, name := range []string{"b/copy2.bin", "tiny2", "t2/sub/f2"} {
+		err := os.Remove(p(name))
+		if err != nil {
+			t.Fatal(err)
+		}
+	}
+
+	want := "first\tdupe\tsize\n" +
+		p("t1/f1") + "\t" + p("t2/f1") + "\t3000\n" +
+		p("t1/f1") + "\t" + p("t3/f1") + "\t3000\n" +
+		p("a/one.bin") + "\t" + p("b/copy.bin") + "\t2000\n" +
+		p("t1/sub/f2") + "\t" + p("t3/sub/f2renamed") + "\t100\n"
+	if got := runStdout(t, cmdReport); got != want {
+		t.Errorf("report stdout = %q, want %q", got, want)
+	}
+
+	// disk_size, the last column, depends on the filesystem.
+	header := "first\tdupe\tfiles\tsize\tdisk_size\n"
+
+	want = header + p("t1") + "\t" + p("t2") + "\t2\t3100\t"
+	if got := runStdout(t, cmdTrees); !strings.HasPrefix(got, want) ||
+		strings.Count(got, "\n") != 2 {
+		t.Errorf("trees stdout = %q, want one row starting %q", got, want)
+	}
+
+	err := os.RemoveAll(p("t2"))
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	assertSmokeDupeGroups(t, dir, db)
-	assertSmokeTreeGroups(t, dir, db)
+	if got := runStdout(t, cmdTrees); got != header {
+		t.Errorf("trees stdout after removing t2 = %q, want %q", got, header)
+	}
+}
+
+func TestPathExists(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	file := writeFile(t, dir, "file", nil)
+	locked := writeFile(t, dir, "locked/file", nil)
+
+	// Without search permission on its directory, a file cannot be
+	// looked at by anyone but root.
+	err := os.Chmod(filepath.Dir(locked), 0)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// Runs before t.TempDir's own cleanup, which must delete the files.
+	t.Cleanup(func() {
+		//nolint:gosec // removing the directory needs its search bit back
+		_ = os.Chmod(filepath.Dir(locked), 0o700)
+	})
+
+	cases := map[string]bool{
+		dir:                                 true,
+		file:                                true,
+		locked:                              true,
+		filepath.Join(dir, "gone"):          false,
+		filepath.Join(file, "under-a-file"): false,
+	}
+	for path, want := range cases {
+		if got := pathExists(path); got != want {
+			t.Errorf("pathExists(%q) = %v, want %v", path, got, want)
+		}
+	}
 }
 
 func TestUnderRoot(t *testing.T) {