Name the database each command uses on stderr (closes #111)

scan, report and trees now print one line on stderr before anything else, naming the database and whether its path is the default or comes from SFDUPES_DATABASE; scan also says when the file is new. report and trees print it before opening the database, so a missing-database error follows it. A relative path gets the working directory put in front of it without cleaning: cleaning drops a ".." with the directory before it, which names another file when that directory is a symlink. README "Database" lists when scan writes each file. Unverified: the line on a terminal has no test of its own. Rule suppressed: TestDatabasePath carries nolint:paralleltest, as it changes the working directory. Model: opus-5-5
2026-10-16 12:34:49 +00:00
parent 198cefa152
commit df1d5cb8ff
9 changed files with 317 additions and 35 deletions
@@ -285,22 +285,29 @@ func assertFatalOutput(t *testing.T, stderr, stdout string) {

 func TestRunMissingDatabaseIsFatal(t *testing.T) {
 	// README §Database: report and trees need an existing database; a
-	// missing one exits 1 with a message telling the user to run scan.
+	// missing one exits 1 with a message telling the user to run scan,
+	// after the line naming the database.
 	for _, name := range []string{cmdReport, cmdTrees} {
 		t.Run(name, func(t *testing.T) {
 			path := testDBPath(t)
 			t.Setenv(databaseEnv, path)

-			var stdout, stderr bytes.Buffer
+			var stdout bytes.Buffer

-			code := run([]string{name}, &stdout, &stderr)
+			// run gets os.Stderr, where the subcommand prints its line,
+			// so the capture shows the two in the order printed.
+			stderr := captureStderr(t)
+
+			code := run([]string{name}, &stdout, os.Stderr)
 			if code != exitFatal {
 				t.Errorf("run(%s) = %d, want %d", name, code, exitFatal)
 			}

-			want := "sfdupes: " + path + ": no database (run \"sfdupes " +
+			want := name + ": database " + path + " (from " + databaseEnv +
+				")\n" +
+				"sfdupes: " + path + ": no database (run \"sfdupes " +
 				"scan\" first, or set " + databaseEnv + ")\n"
-			if got := stderr.String(); got != want {
+			if got := stderr(); got != want {
 				t.Errorf("stderr = %q, want %q", got, want)
 			}

@@ -311,6 +318,165 @@ func TestRunMissingDatabaseIsFatal(t *testing.T) {
 	}
 }

+func TestRunNamesRelativeDatabase(t *testing.T) {
+	// README §Database: each subcommand's first line on stderr names the
+	// database, a relative SFDUPES_DATABASE made absolute against the
+	// working directory. scan calls it new until a scan has created it.
+	path := testDBPath(t)
+	t.Chdir(filepath.Dir(path))
+	t.Setenv(databaseEnv, filepath.Base(path))
+
+	dir := t.TempDir()
+	from := " (from " + databaseEnv + ")\n"
+
+	want := "scan: new database " + path + from
+	if got := scanOK(t, dir); !strings.HasPrefix(got, want) {
+		t.Errorf("first scan stderr = %q, want it to start %q", got, want)
+	}
+
+	want = "scan: database " + path + from
+	if got := scanOK(t, dir); !strings.HasPrefix(got, want) {
+		t.Errorf("second scan stderr = %q, want it to start %q", got, want)
+	}
+
+	for _, name := range []string{cmdReport, cmdTrees} {
+		stderr := captureStderr(t)
+
+		code := run([]string{name}, io.Discard, os.Stderr)
+
+		want = name + ": database " + path + from
+		if got := stderr(); code != exitOK || !strings.HasPrefix(got, want) {
+			t.Errorf("run(%s) = %d with stderr %q, want %d and it to "+
+				"start %q", name, code, got, exitOK, want)
+		}
+	}
+}
+
+func TestRunUsesDatabaseThroughSymlinkedDirectory(t *testing.T) {
+	// README §Database: the path names the file exactly. With link a
+	// symlink to the directory real/sub, link/../db.sqlite names
+	// real/db.sqlite, not db.sqlite beside link. Every subcommand must
+	// use that file, relative or absolute, and its first line must name
+	// the path as set, with the working directory put in front of a
+	// relative one.
+	dir := t.TempDir()
+	t.Chdir(dir)
+
+	err := os.MkdirAll(filepath.Join(dir, "real", "sub"), 0o750)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	err = os.Symlink(filepath.Join(dir, "real", "sub"),
+		filepath.Join(dir, "link"))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	named := dir + "/link/../db.sqlite"
+	from := " (from " + databaseEnv + ")\n"
+	tree := t.TempDir()
+
+	t.Setenv(databaseEnv, "link/../db.sqlite")
+
+	want := "scan: new database " + named + from
+	if got := scanOK(t, tree); !strings.HasPrefix(got, want) {
+		t.Errorf("relative scan stderr = %q, want it to start %q", got, want)
+	}
+
+	// The absolute path names the database the relative one created.
+	t.Setenv(databaseEnv, named)
+
+	want = "scan: database " + named + from
+	if got := scanOK(t, tree); !strings.HasPrefix(got, want) {
+		t.Errorf("absolute scan stderr = %q, want it to start %q", got, want)
+	}
+
+	for _, name := range []string{cmdReport, cmdTrees} {
+		stderr := captureStderr(t)
+
+		code := run([]string{name}, io.Discard, os.Stderr)
+
+		want = name + ": database " + named + from
+		if got := stderr(); code != exitOK || !strings.HasPrefix(got, want) {
+			t.Errorf("run(%s) = %d with stderr %q, want %d and it to "+
+				"start %q", name, code, got, exitOK, want)
+		}
+	}
+
+	_, err = os.Stat(filepath.Join(dir, "real", "db.sqlite"))
+	if err != nil {
+		t.Errorf("database the path names: %v", err)
+	}
+
+	// With no file at the cleaned path, report and trees succeeded on
+	// the database in real.
+	_, err = os.Stat(filepath.Join(dir, "db.sqlite"))
+	if !errors.Is(err, fs.ErrNotExist) {
+		t.Errorf("database at the cleaned path: stat error %v, want it "+
+			"missing", err)
+	}
+}
+
+func TestRunNamesDefaultDatabase(t *testing.T) {
+	// README §Database: with SFDUPES_DATABASE empty, each subcommand's
+	// first line on stderr names the default database. A database may
+	// exist at the default path on the machine running the test, so
+	// nothing here may create or read one: scan gets an operand that
+	// does not exist, which stops it before it takes the lock, and
+	// report and trees a cancelled context, which stops them before
+	// they read anything.
+	t.Setenv(databaseEnv, "")
+
+	// Whether scan calls the database new depends on that machine too.
+	scanWant := "scan: database " + defaultDatabasePath + " (default)\n"
+
+	_, err := os.Stat(defaultDatabasePath)
+	if errors.Is(err, fs.ErrNotExist) {
+		scanWant = "scan: new database " + defaultDatabasePath +
+			" (default)\n"
+	}
+
+	missing := filepath.Join(t.TempDir(), "nope")
+
+	cases := map[string]struct {
+		run  func() error
+		want string
+	}{
+		cmdScan: {
+			run: func() error {
+				return runScan(t.Context(), []string{missing}, 1, false)
+			},
+			want: scanWant,
+		},
+		cmdReport: {
+			run: func() error {
+				return runReport(cancelledContext(t), io.Discard)
+			},
+			want: "report: database " + defaultDatabasePath + " (default)\n",
+		},
+		cmdTrees: {
+			run: func() error {
+				return runTrees(cancelledContext(t), io.Discard)
+			},
+			want: "trees: database " + defaultDatabasePath + " (default)\n",
+		},
+	}
+
+	for name, tc := range cases {
+		stderr := captureStderr(t)
+
+		err = tc.run()
+		if err == nil {
+			t.Errorf("%s: error = nil, want it stopped", name)
+		}
+
+		if got := stderr(); got != tc.want {
+			t.Errorf("%s stderr = %q, want %q", name, got, tc.want)
+		}
+	}
+}
+
 func TestRunUsageErrors(t *testing.T) {
 	// Usage errors keep exiting 2 with cobra's own report on stderr.
 	cases := map[string]struct {
@@ -661,7 +827,8 @@ func TestRunReportSucceeds(t *testing.T) {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}

-	want = "report: 2 records read, 1 duplicate groups, 1 dupe files, " +
+	want = "report: database " + path + " (from " + databaseEnv + ")\n" +
+		"report: 2 records read, 1 duplicate groups, 1 dupe files, " +
 		"300 B reclaimable\n"
 	if got := stderr(); got != want {
 		t.Errorf("stderr = %q, want %q", got, want)
@@ -694,7 +861,8 @@ func TestRunTreesSucceeds(t *testing.T) {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}

-	want = "trees: 2 records read, 1 duplicate tree groups, 1 dupe trees, " +
+	want = "trees: database " + path + " (from " + databaseEnv + ")\n" +
+		"trees: 2 records read, 1 duplicate tree groups, 1 dupe trees, " +
 		"300 B reclaimable\n"
 	if got := stderr(); got != want {
 		t.Errorf("stderr = %q, want %q", got, want)