1 Commits
Author SHA1 Message Date
clawbot c6470906d0 Name the database each command uses on stderr (closes #111)
check / check (push) Canceled after 0s
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.

Model: opus-5-5
2026-10-16 12:36:19 +00:00
4 changed files with 12 additions and 107 deletions
+3 -7
View File
@@ -279,13 +279,9 @@ All three subcommands operate on a single SQLite database file:
trees: database /srv/tmp/sfdupes/db.db (from SFDUPES_DATABASE)
```
The working directory put in front is the one `pwd -P` prints, with its
symlinks resolved. After a `cd` through a symlink to a directory, a path
starting `../` therefore names a file beside the directory the symlink leads
to, as it does for any other program. `scan` says `new database` when no
file is at that path as it starts. `report` and `trees` print the line
before they open the database, so the error for a missing database comes
after it.
`scan` says `new database` when no file is at that path as it starts.
`report` and `trees` print the line before they open the database, so the
error for a missing database comes after it.
- `scan` creates the database (and its parent directory) on first use. `report`
and `trees` require an existing database; a missing database file is a fatal
+4 -9
View File
@@ -93,9 +93,9 @@ var errScanRunning = errors.New("another scan is running")
// databasePath resolves the database location: SFDUPES_DATABASE when
// set and non-empty, the compiled-in default otherwise. It returns the
// path, with the working directory, its symlinks resolved, put in front
// of it when it is relative, and where the path came from, "default" or
// "from SFDUPES_DATABASE", for the line each subcommand prints first on
// path, with the working directory put in front of it when it is
// relative, and where the path came from, "default" or "from
// SFDUPES_DATABASE", for the line each subcommand prints first on
// stderr.
func databasePath() (string, string, error) {
path, source := defaultDatabasePath, "default"
@@ -107,12 +107,7 @@ func databasePath() (string, string, error) {
return path, source, nil
}
// The working directory as the kernel reports it, with no symlink
// in it. os.Getwd may return PWD instead, which can name it through
// a symlink; a ".." after that symlink then leads somewhere else
// once the path is cleaned, as scan cleans it to create the
// database's directory.
wd, err := unix.Getwd()
wd, err := os.Getwd()
if err != nil {
return "", "", fmt.Errorf("resolve database path %s: %w", path, err)
}
+3 -8
View File
@@ -44,14 +44,9 @@ func openTestDB(t *testing.T) *sql.DB {
func TestDatabasePath(t *testing.T) {
// README §Database: SFDUPES_DATABASE when set and non-empty, the
// default otherwise, with the working directory, its symlinks
// resolved, put in front of a relative path. Nothing is cleaned, so
// a ".." stays.
dir, err := filepath.EvalSymlinks(t.TempDir())
if err != nil {
t.Fatal(err)
}
// default otherwise, with the working directory put in front of a
// relative path. Nothing is cleaned, so a ".." stays.
dir := t.TempDir()
t.Chdir(dir)
fromEnv := "from " + databaseEnv
+2 -83
View File
@@ -359,14 +359,10 @@ func TestRunUsesDatabaseThroughSymlinkedDirectory(t *testing.T) {
// 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, err := filepath.EvalSymlinks(t.TempDir())
if err != nil {
t.Fatal(err)
}
dir := t.TempDir()
t.Chdir(dir)
err = os.MkdirAll(filepath.Join(dir, "real", "sub"), 0o750)
err := os.MkdirAll(filepath.Join(dir, "real", "sub"), 0o750)
if err != nil {
t.Fatal(err)
}
@@ -422,83 +418,6 @@ func TestRunUsesDatabaseThroughSymlinkedDirectory(t *testing.T) {
}
}
func TestRunScanFromSymlinkedWorkingDirectory(t *testing.T) {
// README §Database: a relative path gets the working directory, its
// symlinks resolved, put in front of it. With home/proj a symlink
// to data/proj, entered as the working directory through the
// symlink, ../new/db.sqlite names data/new/db.sqlite. scan must
// create that directory and file, and nothing beside home/proj.
dir, err := filepath.EvalSymlinks(t.TempDir())
if err != nil {
t.Fatal(err)
}
err = os.MkdirAll(filepath.Join(dir, "data", "proj"), 0o750)
if err != nil {
t.Fatal(err)
}
err = os.Mkdir(filepath.Join(dir, "home"), 0o750)
if err != nil {
t.Fatal(err)
}
err = os.Symlink(filepath.Join(dir, "data", "proj"),
filepath.Join(dir, "home", "proj"))
if err != nil {
t.Fatal(err)
}
// t.Chdir also sets PWD to the path through the symlink, as a
// shell does after cd.
t.Chdir(filepath.Join(dir, "home", "proj"))
t.Setenv(databaseEnv, "../new/db.sqlite")
want := "scan: new database " + dir + "/data/proj/../new/db.sqlite" +
" (from " + databaseEnv + ")\n"
if got := scanOK(t, t.TempDir()); !strings.HasPrefix(got, want) {
t.Errorf("scan stderr = %q, want it to start %q", got, want)
}
_, err = os.Stat(filepath.Join(dir, "data", "new", "db.sqlite"))
if err != nil {
t.Errorf("database the path names: %v", err)
}
_, err = os.Lstat(filepath.Join(dir, "home", "new"))
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("home/new: stat error %v, want it missing", err)
}
}
func TestRunEscapesDatabasePath(t *testing.T) {
// README §Database: each subcommand's first line escapes the
// database path like the paths in a report, so a tab, newline or
// backslash in it keeps the line one line.
dir := t.TempDir()
t.Setenv(databaseEnv, dir+"/a\tb\nc\\d.sqlite")
escaped := dir + `/a\tb\nc\\d.sqlite`
from := " (from " + databaseEnv + ")\n"
want := "scan: new database " + escaped + from
if got := scanOK(t, t.TempDir()); !strings.HasPrefix(got, want) {
t.Errorf("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 " + escaped + 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 TestRunNamesDefaultDatabase(t *testing.T) {
// README §Database: with SFDUPES_DATABASE empty, each subcommand's
// first line on stderr names the default database. A database may