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

internal/sfdupes/report_test.go

@@ -72,15 +72,37 @@ type dupeGroup struct {
 	paths []string
 }
 
+// everyPathExists stands in for pathExists where a test's records name
+// made-up paths that are not on disk.
+func everyPathExists(string) bool { return true }
+
+// recsOnDisk returns a new directory and recs with each path moved
+// under it, after creating an empty file at each moved path: report and
+// trees then find every path still on disk.
+func recsOnDisk(t *testing.T, recs []scanRec) (string, []scanRec) {
+	t.Helper()
+
+	dir := realTempDir(t)
+	moved := make([]scanRec, len(recs))
+
+	for i, r := range recs {
+		r.path = writeFile(t, dir, r.path, nil)
+		moved[i] = r
+	}
+
+	return dir, moved
+}
+
 // dupeGroups returns the duplicate groups report reads from db, in
 // report order, from the rows it writes: a group's rows come together,
-// each naming the group's first path.
+// each naming the group's first path. Every path counts as still on
+// disk.
 func dupeGroups(t *testing.T, db *sql.DB) []dupeGroup {
 	t.Helper()
 
 	var out bytes.Buffer
 
-	_, err := readReport(t.Context(), db, "", &out, nil)
+	_, err := readReport(t.Context(), db, "", &out, everyPathExists, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -127,7 +149,8 @@ func dupeGroupsOf(t *testing.T, recs []scanRec) []dupeGroup {
 }
 
 func TestRunReportEscapesPaths(t *testing.T) {
-	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
+	dir, recs := recsOnDisk(t, awkwardPairRecs())
+	t.Setenv(databaseEnv, seedDatabase(t, recs))
 
 	var stdout, stderr bytes.Buffer
 
@@ -138,7 +161,7 @@ func TestRunReportEscapesPaths(t *testing.T) {
 	}
 
 	want := "first\tdupe\tsize\n" +
-		`/d/\tone\ntwo\rthree\\four/f` + "\t/d/A/f\t5\n"
+		dir + `/d/\tone\ntwo\rthree\\four/f` + "\t" + dir + "/d/A/f\t5\n"
 	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
@@ -172,7 +195,8 @@ func TestReportStdoutFailsWhileReading(t *testing.T) {
 	// Counts the records read, and draws nothing.
 	prog := &progress{now: time.Now}
 
-	_, err = readReport(t.Context(), db, "", failingWriter{}, prog)
+	_, err = readReport(t.Context(), db, "", failingWriter{},
+		everyPathExists, prog)
 	if !errors.Is(err, errWriteFailed) ||
 		!strings.HasPrefix(err.Error(), "write stdout: ") {
 		t.Errorf("error = %v, want write stdout: %v", err, errWriteFailed)
@@ -203,7 +227,8 @@ const smokeReport = "first\tdupe\tsize\n" +
 // it ends; read counts the 6 records before it reads them. The summary
 // comes last, and stdout holds the report alone.
 func TestRunReportProgressNamesEachPhase(t *testing.T) {
-	path := seedDatabase(t, smokeTreeRecs())
+	dir, recs := recsOnDisk(t, smokeTreeRecs())
+	path := seedDatabase(t, recs)
 	t.Setenv(databaseEnv, path)
 
 	stderr := captureStderr(t)
@@ -216,8 +241,9 @@ func TestRunReportProgressNamesEachPhase(t *testing.T) {
 			code, exitOK, stderr())
 	}
 
-	if got := stdout.String(); got != smokeReport {
-		t.Errorf("stdout = %q, want %q", got, smokeReport)
+	report := strings.ReplaceAll(smokeReport, "/d/", dir+"/d/")
+	if got := stdout.String(); got != report {
+		t.Errorf("stdout = %q, want %q", got, report)
 	}
 
 	// How each line starts; the rate at the end of a phase varies.
@@ -266,7 +292,7 @@ func TestReadReportOnTerminal(t *testing.T) {
 		waitingFor: countingRecords,
 	}, terminalWidth, time.Hour, time.Now)
 
-	_, err = readReport(t.Context(), db, "", os.Stderr, p)
+	_, err = readReport(t.Context(), db, "", os.Stderr, everyPathExists, p)
 
 	p.finish()
 
@@ -301,6 +327,8 @@ func TestRunReportsIgnoreInsertionOrder(t *testing.T) {
 		scanRec{size: 50, head: a, tail: a, content: a, path: "/x/1"},
 	)
 
+	_, recs = recsOnDisk(t, recs)
+
 	reversed := slices.Clone(recs)
 	slices.Reverse(reversed)
 
@@ -455,6 +483,119 @@ func TestDupeGroupsLeavesOutEmptyFiles(t *testing.T) {
 	}
 }
 
+// TestReadReportChecksOnlyPossibleDuplicates checks that report asks
+// whether a path is on disk only when its signature has two or more
+// records, and never for an empty file.
+func TestReadReportChecksOnlyPossibleDuplicates(t *testing.T) {
+	t.Parallel()
+
+	a, u, e := testHash("a"), testHash("u"), sha256.Sum256(nil)
+	recs := []scanRec{
+		{size: 9, head: a, tail: a, content: a, path: "/copy/1"},
+		{size: 9, head: a, tail: a, content: a, path: "/copy/2"},
+		{size: 9, head: a, tail: a, content: a, path: "/copy/3"},
+		{size: 9, head: u, tail: u, content: u, path: "/lonely"},
+		{size: 0, head: e, tail: e, content: e, path: "/empty1"},
+		{size: 0, head: e, tail: e, content: e, path: "/empty2"},
+	}
+
+	db := openTestDB(t)
+
+	err := applyChanges(t.Context(), db, recs, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	var checked []string
+
+	exists := func(path string) bool {
+		checked = append(checked, path)
+
+		return true
+	}
+
+	_, err = readReport(t.Context(), db, "", io.Discard, exists, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	slices.Sort(checked)
+
+	want := []string{"/copy/1", "/copy/2", "/copy/3"}
+	if !slices.Equal(checked, want) {
+		t.Errorf("paths checked on disk = %q, want %q", checked, want)
+	}
+}
+
+// TestReadReportDropsGroupLeftWithOnePath checks that a group of two
+// paths, one of them gone, is no duplicate group. If kept, it would
+// write no row, but the summary line would count it.
+func TestReadReportDropsGroupLeftWithOnePath(t *testing.T) {
+	t.Parallel()
+
+	a := testHash("a")
+	recs := []scanRec{
+		{size: 9, head: a, tail: a, content: a, path: "/a/kept"},
+		{size: 9, head: a, tail: a, content: a, path: "/a/gone"},
+	}
+
+	db := openTestDB(t)
+
+	err := applyChanges(t.Context(), db, recs, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	exists := func(path string) bool { return path != "/a/gone" }
+
+	report, err := readReport(t.Context(), db, "", io.Discard, exists, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if report.dupeGroups != 0 {
+		t.Errorf("duplicate groups = %d, want 0", report.dupeGroups)
+	}
+}
+
+// TestReadReportKeepsGroupLeftWithTwoPaths checks that a group of three
+// paths, one of them gone, is a duplicate group of the other two.
+func TestReadReportKeepsGroupLeftWithTwoPaths(t *testing.T) {
+	t.Parallel()
+
+	a := testHash("a")
+	recs := []scanRec{
+		{size: 9, head: a, tail: a, content: a, path: "/b/kept1"},
+		{size: 9, head: a, tail: a, content: a, path: "/b/gone"},
+		{size: 9, head: a, tail: a, content: a, path: "/b/kept2"},
+	}
+
+	db := openTestDB(t)
+
+	err := applyChanges(t.Context(), db, recs, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	exists := func(path string) bool { return path != "/b/gone" }
+
+	var out bytes.Buffer
+
+	report, err := readReport(t.Context(), db, "", &out, exists, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if report.dupeGroups != 1 {
+		t.Errorf("duplicate groups = %d, want 1", report.dupeGroups)
+	}
+
+	want := "first\tdupe\tsize\n/b/kept1\t/b/kept2\t9\n"
+	if got := out.String(); got != want {
+		t.Errorf("stdout = %q, want %q", got, want)
+	}
+}
+
 func TestDupeGroupsContentSeparates(t *testing.T) {
 	t.Parallel()