Escape tab, newline, CR and backslash in report paths (closes #7)
check / check (push) Successful in 1m29s

A path holding a tab or newline split a row of the report or trees
output. The path columns of both now write a backslash, tab, newline
and carriage return as \\, \t, \n and \r; every other byte is written
unchanged. Grouping and sorting still use the stored path. Warnings
on stderr are escaped the same way in warnf, so each stays one line.

In trees, the root directory's node now has the path "/" instead of
an empty string, and its children's paths start with a single slash.

README states the rule under "Report output format".

Model: opus-5-5
This commit was merged in pull request #70.
This commit is contained in:
2026-10-03 15:30:37 +02:00
parent c9bf22d483
commit c887f80f57
7 changed files with 209 additions and 8 deletions
+118
View File
@@ -1,10 +1,128 @@
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()