Write gen DIR's manifest to DIR/index.mf (closes #178) #180

Merged
clawbot merged 1 commits from issue-178-gen-output into next 2026-10-08 03:08:41 +02:00
6 changed files with 299 additions and 32 deletions
+9
View File
@@ -269,6 +269,15 @@ are now tracked only in the [issues](https://git.eeqj.de/sneak/mfer/issues).
- recurses under current directory and writes out an `index.mf`
- records every file's mode as `0000` unless given `--include-permissions`,
which records each file's permission bits (`0777` at most)
- `mfer gen /media/drive`
- writes `/media/drive/index.mf`, listing each file by its path under
`/media/drive`, so `mfer check /media/drive` verifies it. Given a file,
gen writes `index.mf` beside it and lists the file by its name; given
several paths, it writes `index.mf` in the current directory
- `--output` names another file to write instead. What gen lists depends
only on the paths it is given and the files under them, so with the same
`--seed` and an unchanged tree it writes the same bytes wherever the
manifest goes. The file it writes to is never listed
- `mfer check` / `mfer check .`
- verifies checksums of all files in manifest, displaying error and exiting
nonzero if any files are missing or corrupted, or have permission bits
+174
View File
@@ -1289,6 +1289,180 @@ func TestGenerateLeavesLeftoverTempFileOutOfListing(t *testing.T) {
assert.Equal(t, []string{testFileTxt}, manifestPaths(t, fs, output))
}
// writeTestTree writes file.txt and sub/nested.txt under dir.
func writeTestTree(t *testing.T, fs afero.Fs, dir string) {
t.Helper()
require.NoError(t, fs.MkdirAll(filepath.Join(dir, testSubdir), 0o750))
writeTestFile(t, fs, filepath.Join(dir, testFileTxt), "hello")
writeTestFile(t, fs, filepath.Join(dir, testSubdir, "nested.txt"), "in sub")
}
// TestGenerateDefaultOutput runs gen without --output on one directory or
// one file: it writes index.mf in that directory, or beside that file,
// listing each file by its path under the directory index.mf is in, and
// check given that directory passes.
func TestGenerateDefaultOutput(t *testing.T) {
t.Parallel()
// Paths are relative to a temp dir holding file.txt and sub/nested.txt.
for name, tc := range map[string]struct {
input, output string
listed []string
}{
"directory": {
".", defaultManifestName, []string{testFileTxt, "sub/nested.txt"},
},
"subdirectory": {testSubdir, testSubdirManifest, []string{"nested.txt"}},
"file": {testFileTxt, defaultManifestName, []string{testFileTxt}},
} {
t.Run(name, func(t *testing.T) {
t.Parallel()
root := t.TempDir()
fs := afero.NewOsFs()
writeTestTree(t, fs, root)
opts := testOpts([]string{
testApp, cmdGenerate, "-q", filepath.Join(root, tc.input),
}, fs)
require.Equal(t, 0, runCLI(opts), "stderr: %s", testStderr(t, opts))
output := filepath.Join(root, tc.output)
assert.ElementsMatch(t, tc.listed, manifestPaths(t, fs, output))
opts = testOpts([]string{
testApp, cmdCheck, "-q", filepath.Dir(output),
}, fs)
assert.Equal(t, 0, runCLI(opts), "stderr: %s", testStderr(t, opts))
})
}
}
// TestGenerateSeveralPathsDefaultOutput runs gen without --output on two
// directories: it writes index.mf in the current directory, listing both
// directories' files, and writes no index.mf in either directory.
//
//nolint:paralleltest // changes the process-global working directory
func TestGenerateSeveralPathsDefaultOutput(t *testing.T) {
root := t.TempDir()
fs := afero.NewOsFs()
dirs := []string{"first", "second"}
for _, dir := range dirs {
require.NoError(t, fs.MkdirAll(filepath.Join(root, dir), 0o750))
writeTestFile(t, fs, filepath.Join(root, dir, dir+".txt"), dir)
}
t.Chdir(root)
opts := testOpts(append([]string{testApp, cmdGenerate, "-q"}, dirs...), fs)
require.Equal(t, 0, runCLI(opts), "stderr: %s", testStderr(t, opts))
assert.ElementsMatch(t, []string{"first.txt", "second.txt"},
manifestPaths(t, fs, filepath.Join(root, defaultManifestName)))
for _, dir := range dirs {
exists, err := afero.Exists(fs, filepath.Join(root, dir, defaultManifestName))
require.NoError(t, err)
assert.False(t, exists, "index.mf written in %s", dir)
}
}
// TestGenerateBytesDoNotDependOnOutput runs gen --seed on one tree, each
// time writing to another file, over a file already there and beside an
// earlier run's temp file: neither is listed, and what is listed depends
// only on the tree, so every manifest has the same bytes.
func TestGenerateBytesDoNotDependOnOutput(t *testing.T) {
t.Parallel()
root := t.TempDir()
tree := filepath.Join(root, "tree")
defaultOutput := filepath.Join(tree, defaultManifestName)
fs := afero.NewOsFs()
writeTestTree(t, fs, tree)
var first []byte
for _, output := range []string{
defaultOutput,
filepath.Join(tree, "listing.mf"),
filepath.Join(tree, testSubdir, "listing.mf"),
filepath.Join(root, "outside.mf"),
} {
writeTestFile(t, fs, output, "previous manifest")
writeTestFile(t, fs, manifestTempPath(output), "part of a manifest")
args := []string{testApp, cmdGenerate, "-q", "-f", "--seed", "mfer"}
if output != defaultOutput {
args = append(args, "-o", output)
}
args = append(args, tree)
opts := testOpts(args, fs)
require.Equal(t, 0, runCLI(opts),
"output %s, stderr: %s", output, testStderr(t, opts))
got, err := afero.ReadFile(fs, output)
require.NoError(t, err)
require.NoError(t, fs.Remove(output))
if first == nil {
first = got
}
assert.Equal(t, first, got, "output %s", output)
}
}
// TestGenerateRefusesExistingDefaultOutput runs gen without --output or
// --force on a directory already holding index.mf: gen fails, naming that
// file, and leaves it as it was.
func TestGenerateRefusesExistingDefaultOutput(t *testing.T) {
t.Parallel()
output := filepath.Join(testDir, defaultManifestName)
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll(testDir, 0o755))
writeTestFile(t, fs, testFile1, "hello")
writeTestFile(t, fs, output, "previous manifest")
opts := testOpts([]string{testApp, cmdGenerate, "-q", testDir}, fs)
assert.Equal(t, 1, runCLI(opts))
assert.Contains(t, testStderr(t, opts),
"output file "+output+" already exists (use --force to overwrite)")
content, err := afero.ReadFile(fs, output)
require.NoError(t, err)
assert.Equal(t, "previous manifest", string(content))
}
// TestGenerateRefusesEmptyOutput runs gen with --force and an --output
// given an empty value, as an unset shell variable gives it, on a
// directory already holding index.mf: gen fails and leaves that file as it
// was.
func TestGenerateRefusesEmptyOutput(t *testing.T) {
t.Parallel()
output := filepath.Join(testDir, defaultManifestName)
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll(testDir, 0o755))
writeTestFile(t, fs, testFile1, "hello")
writeTestFile(t, fs, output, "previous manifest")
opts := testOpts([]string{testApp, cmdGenerate, "-q", "-f", "-o", "", testDir}, fs)
assert.Equal(t, 1, runCLI(opts))
assert.Contains(t, testStderr(t, opts), errEmptyOutput.Error())
content, err := afero.ReadFile(fs, output)
require.NoError(t, err)
assert.Equal(t, "previous manifest", string(content))
}
func TestGenerateAtomicWriteUsesTemp(t *testing.T) {
t.Parallel()
+76 -27
View File
@@ -4,6 +4,7 @@ import (
"context"
"errors"
"fmt"
"io"
"os"
"os/signal"
"path/filepath"
@@ -26,6 +27,8 @@ var (
// rendered message stays exactly as mfer has always printed it.
errOutputExists = errors.New(
"already exists (use --force to overwrite)")
// errEmptyOutput indicates --output given with an empty value.
errEmptyOutput = errors.New("--output must not be empty")
)
// reportEnumProgress renders enumeration progress until the channel
@@ -88,9 +91,40 @@ func (mfa *CLIApp) collectInputPaths(args cli.Args) ([]string, error) {
return paths, nil
}
// buildScannerOptions constructs scanner options from the CLI flags.
func (mfa *CLIApp) buildScannerOptions(cmd *cli.Command) *mfer.ScannerOptions {
output := cmd.String("output")
// outputPath returns the file gen writes the manifest to: the one --output
// names, or else index.mf in the directory the only argument names, or
// beside the file it names, or else in the current directory. An --output
// given with an empty value is refused.
func (mfa *CLIApp) outputPath(cmd *cli.Command) (string, error) {
if cmd.IsSet("output") {
output := cmd.String("output")
if output == "" {
return "", errEmptyOutput
}
return output, nil
}
if cmd.Args().Len() != 1 {
return defaultManifestName, nil
}
arg := cmd.Args().First()
// A path that does not exist is refused when it is enumerated.
info, err := mfa.Fs.Stat(arg)
if err == nil && !info.IsDir() {
return filepath.Join(filepath.Dir(arg), defaultManifestName), nil
}
return filepath.Join(arg, defaultManifestName), nil
}
// buildScannerOptions constructs scanner options from the CLI flags and
// the path the manifest is written to.
func (mfa *CLIApp) buildScannerOptions(
cmd *cli.Command, output string,
) *mfer.ScannerOptions {
opts := &mfer.ScannerOptions{
IncludeDotfiles: cmd.Bool("include-dotfiles"),
FollowSymLinks: cmd.Bool("follow-symlinks"),
@@ -202,23 +236,54 @@ func (mfa *CLIApp) runEnumeratePhase(cmd *cli.Command, s *mfer.Scanner) error {
return nil
}
// runScanPhase reads the enumerated files and writes the manifest to out,
// with optional progress reporting.
func (mfa *CLIApp) runScanPhase(
ctx context.Context, cmd *cli.Command, s *mfer.Scanner, out io.Writer,
) error {
var (
scanProgress chan mfer.ScanStatus
scanWg sync.WaitGroup
)
if cmd.Bool("progress") {
scanProgress = make(chan mfer.ScanStatus, 1)
scanWg.Add(1)
go reportScanProgress(scanProgress, &scanWg)
}
err := s.ToManifest(ctx, out, scanProgress)
scanWg.Wait()
if err != nil {
return fmt.Errorf("generate manifest: %w", err)
}
return nil
}
func (mfa *CLIApp) generateManifestOperation(
ctx context.Context, cmd *cli.Command,
) error {
log.Debug("generateManifestOperation()")
s := mfer.NewScannerWithOptions(mfa.buildScannerOptions(cmd))
// Phase 1: Enumeration - collect paths and stat files
err := mfa.runEnumeratePhase(cmd, s)
outputPath, err := mfa.outputPath(cmd)
if err != nil {
return err
}
showProgress := cmd.Bool("progress")
s := mfer.NewScannerWithOptions(mfa.buildScannerOptions(cmd, outputPath))
// Phase 1: Enumeration - collect paths and stat files
err = mfa.runEnumeratePhase(cmd, s)
if err != nil {
return err
}
// Check if output file exists
outputPath := cmd.String("output")
if exists, _ := afero.Exists(mfa.Fs, outputPath); exists && !cmd.Bool("force") {
return fmt.Errorf("output file %s %w", outputPath, errOutputExists)
}
@@ -249,25 +314,9 @@ func (mfa *CLIApp) generateManifestOperation(
}()
// Phase 2: Scan - read file contents and generate manifest
var (
scanProgress chan mfer.ScanStatus
scanWg sync.WaitGroup
)
if showProgress {
scanProgress = make(chan mfer.ScanStatus, 1)
scanWg.Add(1)
go reportScanProgress(scanProgress, &scanWg)
}
err = s.ToManifest(ctx, outFile, scanProgress)
scanWg.Wait()
err = mfa.runScanPhase(ctx, cmd, s, outFile)
if err != nil {
return fmt.Errorf("generate manifest: %w", err)
return err
}
// Close file before rename to ensure all data is flushed
+3 -2
View File
@@ -211,9 +211,10 @@ func (mfa *CLIApp) generateCommand() *cli.Command {
},
&cli.StringFlag{
Name: "output",
Value: defaultManifestName,
Aliases: []string{"o"},
Usage: "Specify output filename",
Usage: "File to write the manifest to (default: index.mf in " +
"the directory given, or beside the file given; with no " +
"path or several, index.mf in the current directory)",
},
&cli.BoolFlag{
Name: "force",
+15 -3
View File
@@ -160,7 +160,9 @@ func (s *Scanner) EnumeratePath(
return s.enumerateFS(afs, abs, progress)
}
// EnumeratePaths walks multiple directory paths and adds all files to the scanner.
// EnumeratePaths adds to the scanner the files under each directory path,
// listed by their paths under it, and each file path, listed by its name
// as EnumerateFile lists it.
// If progress is non-nil, status updates are sent as files are discovered.
// The progress channel is closed when the method returns.
func (s *Scanner) EnumeratePaths(
@@ -177,9 +179,19 @@ func (s *Scanner) EnumeratePaths(
return err
}
afs := afero.NewReadOnlyFs(afero.NewBasePathFs(s.fs, abs))
info, err := s.fs.Stat(abs)
if err != nil {
return err
}
if info.IsDir() {
afs := afero.NewReadOnlyFs(afero.NewBasePathFs(s.fs, abs))
err = s.enumerateFS(afs, abs, progress)
} else {
err = s.enumerateFileWithInfo(
filepath.Base(abs), filepath.Dir(abs), info, progress)
}
err = s.enumerateFS(afs, abs, progress)
if err != nil {
return err
}
+22
View File
@@ -134,6 +134,28 @@ func TestScannerEnumeratePaths(t *testing.T) {
assert.Equal(t, FileCount(2), s.FileCount())
}
// TestScannerEnumeratePathsFile gives EnumeratePaths a directory and a
// file: the file is listed by its name, as EnumerateFile lists it.
func TestScannerEnumeratePathsFile(t *testing.T) {
t.Parallel()
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/dir/sub", 0o755))
require.NoError(t, fs.MkdirAll("/other", 0o755))
require.NoError(t, afero.WriteFile(fs, "/dir/sub/one.txt", []byte("1"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/other/two.txt", []byte("2"), 0o644))
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})
require.NoError(t, s.EnumeratePaths(nil, "/dir", "/other/two.txt"))
paths := make([]RelFilePath, 0, s.FileCount())
for _, f := range s.Files() {
paths = append(paths, f.Path)
}
assert.Equal(t, []RelFilePath{"sub/one.txt", "two.txt"}, paths)
}
func TestScannerExcludeDotfiles(t *testing.T) {
t.Parallel()