sfdupes/info_test.go

package main

import (
	"fmt"
	"os"
	"path/filepath"
	"strings"
	"testing"
	"time"
)

// infoOpenLine is the plain line of info's open phase when it opens the
// database at once; it prints it as the phase starts and as it ends.
const infoOpenLine = "[1/2] open: opening the database, elapsed 0s, " +
	"eta unknown"

// infoCountLine is the plain line of info's count phase when the count
// takes under a second; it prints it as the phase starts and as it
// ends.
const infoCountLine = "[2/2] count: counting the records, elapsed 0s, " +
	"eta unknown"

// infoRecs are four records: a duplicate pair with every hash, a file
// of 20 MiB with head and tail hashes but no content hash yet, and a
// file never hashed.
func infoRecs() []scanRec {
	return []scanRec{
		{size: 5, head: "h", tail: "t", content: "c", path: "/d/a"},
		{size: 5, head: "h", tail: "t", content: "c", path: "/d/b"},
		{size: 20 << 20, head: "bh", tail: "bt", path: "/d/big"},
		{size: 7, path: "/d/unique"},
	}
}

// TestRunInfo runs info on an empty and on a filled database, with
// stdout and stderr the same file that is not a terminal, and checks
// everything written there: the line naming the database, each phase's
// line as it starts and as it ends, and then the details, each on a
// line of its own. No -wal file is beside a database scan has closed.
func TestRunInfo(t *testing.T) {
	cases := map[string]struct {
		recs []scanRec
		want string // the details after the database file's time
	}{
		"empty": {
			want: "schema version\t1\n" +
				"records\t0\n" +
				"records with head and tail hashes\t0\n" +
				"records with content hash\t0\n" +
				"size of recorded files\t0 (0 B)\n",
		},
		"filled": {
			recs: infoRecs(),
			want: "schema version\t1\n" +
				"records\t4\n" +
				"records with head and tail hashes\t3\n" +
				"records with content hash\t2\n" +
				"size of recorded files\t20971537 (20.0 MiB)\n",
		},
	}

	for name, tc := range cases {
		t.Run(name, func(t *testing.T) {
			path := seedDatabase(t, tc.recs)
			t.Setenv(databaseEnv, path)

			file, err := os.Stat(path)
			if err != nil {
				t.Fatal(err)
			}

			stderr := captureStderr(t)

			code := run([]string{cmdInfo}, os.Stderr, os.Stderr)
			if code != exitOK {
				t.Fatalf("run(info) = %d, want %d; stderr: %s",
					code, exitOK, stderr())
			}

			named := path + " (from " + databaseEnv + ")\n"
			want := "info: database " + named +
				infoOpenLine + "\n" + infoOpenLine + "\n" +
				infoCountLine + "\n" + infoCountLine + "\n" +
				"database\t" + named +
				fmt.Sprintf("database file size\t%d (%s)\n",
					file.Size(), humanBytes(file.Size())) +
				"modified\t" + file.ModTime().UTC().Format(time.RFC3339) +
				"\n" + tc.want

			if got := stderr(); got != want {
				t.Errorf("stdout and stderr = %q, want %q", got, want)
			}
		})
	}
}

// TestRunInfoDuringScan runs info while a scan holds the lock and has
// the database open in WAL mode, with records committed to the -wal
// file only. info must count those records and show the -wal file's
// size, also when the database path is a symlink: SQLite keeps the
// -wal file beside the symlink's target.
func TestRunInfoDuringScan(t *testing.T) {
	path := testDBPath(t)
	link := filepath.Join(t.TempDir(), "link.sqlite")

	err := os.Symlink(path, link)
	if err != nil {
		t.Fatal(err)
	}

	db, err := openScanDatabase(t.Context(), path)
	if err != nil {
		t.Fatal(err)
	}

	t.Cleanup(func() { _ = db.Close() })

	err = applyChanges(t.Context(), db, infoRecs(), nil, nil)
	if err != nil {
		t.Fatal(err)
	}

	holdScanLock(t, path)

	wal, err := os.Stat(path + "-wal")
	if err != nil {
		t.Fatal(err)
	}

	for _, named := range []string{path, link} {
		t.Run(filepath.Base(named), func(t *testing.T) {
			t.Setenv(databaseEnv, named)

			stdout := runStdout(t, cmdInfo)

			for _, want := range []string{
				"database\t" + named + " (from " + databaseEnv + ")\n",
				fmt.Sprintf("\n-wal file size\t%d (%s)\n",
					wal.Size(), humanBytes(wal.Size())),
				"\nrecords\t4\n",
			} {
				if !strings.Contains(stdout, want) {
					t.Errorf("stdout = %q, want it to hold %q", stdout, want)
				}
			}
		})
	}
}

func TestRunInfoNeedsOnlyReadAccess(t *testing.T) {
	// README "`info` mode": like report, info needs only read access to
	// the database file and none to its directory.
	path := testDBPath(t)
	t.Setenv(databaseEnv, path)

	scanFixture(t)
	makeReadOnly(t, path)

	stdout := runStdout(t, cmdInfo)

	if want := "\nrecords\t2\n"; !strings.Contains(stdout, want) {
		t.Errorf("stdout = %q, want it to hold %q", stdout, want)
	}

	if strings.Contains(stdout, "-wal") {
		t.Errorf("stdout = %q, want no -wal file between scans", stdout)
	}
}