12 Commits

Author SHA1 Message Date
clawbot
6646e02821 Fix AddFile to verify actual bytes read matches declared size
Return an error if totalRead != size after reading the file,
preventing silent data corruption from truncated or oversized reads.

Closes #25
2026-02-08 16:10:54 -08:00
4b80c0067b docs: replace TODO.md with design questions and implementation plan 2026-02-08 18:40:31 +01:00
5ab092098b progress 2026-02-08 09:25:58 -08:00
4a2060087d Add GPG signature verification on manifest load
- Implement gpgVerify function that creates a temporary keyring to verify
  detached signatures against embedded public keys
- Signature verification happens during deserialization after hash
  validation but before decompression
- Extract signatureString() as a method on manifest for generating the
  canonical signature string (MAGIC-UUID-MULTIHASH)
- Add --require-signature flag to check command to mandate signature from
  a specific GPG key ID
- Expose IsSigned() and Signer() methods on Checker for signature status
2025-12-18 05:56:16 -08:00
213364bab5 Add UUID to manifest and verify integrity before decompression
- Add UUID field to both inner and outer manifest messages
- Generate random v4 UUID when creating manifest
- Hash compressed data (not uncompressed) for integrity check
- Verify hash before decompression to prevent malicious payloads
- Validate UUIDs are proper format and match between inner/outer
- Sign string format: MAGIC-UUID-MULTIHASH
2025-12-18 02:20:51 -08:00
778999a285 Add GPG signing support for manifest generation
- Add --sign-key flag and MFER_SIGN_KEY env var to gen and freshen commands
- Sign inner message multihash with GPG detached signature
- Include signer fingerprint and public key in outer wrapper
- Add comprehensive tests with temporary GPG keyring
- Increase test timeout to 10s for GPG key generation
2025-12-18 02:12:54 -08:00
308c583d57 Remove codebase structure section from README
godoc provides this documentation automatically
2025-12-18 01:38:13 -08:00
019fe41c3d Update .gitignore for new bin/ build directory 2025-12-18 01:30:50 -08:00
fc0b38ea19 Add TODO.md with codebase audit findings
Document issues found during code audit including:
- Critical: broken error comparison, unchecked hash writes, URL path traversal
- Important: goroutine leak, timestamp precision, missing context cancellation
- Code quality: duplicate functions, inefficient calculations, missing validation
2025-12-18 01:30:01 -08:00
61c17ca585 Normalize markdown formatting in documentation
- Use consistent dash-style bullet points
- Remove trailing whitespace
- Add missing blank lines between sections
- Add trailing newline to README.md
2025-12-18 01:29:56 -08:00
dae6c64e24 Change build output path from mfer.cmd to bin/mfer
Use conventional bin/ directory for build output instead of
placing executable in project root.
2025-12-18 01:29:47 -08:00
a5b0343b28 Use Go 1.13+ octal literal syntax throughout codebase
Update file permission literals from legacy octal format (0755, 0644)
to explicit Go 1.13+ format (0o755, 0o644) for improved readability.
2025-12-18 01:29:40 -08:00
28 changed files with 1776 additions and 353 deletions

2
.gitignore vendored
View File

@@ -1,4 +1,4 @@
/mfer.cmd
/bin/
/tmp
*.tmp
*.dockerimage

View File

@@ -1,20 +1,20 @@
# Important Rules
* when fixing a bug, write a failing test FIRST. only after the test fails, write
- when fixing a bug, write a failing test FIRST. only after the test fails, write
the code to fix the bug. then ensure the test passes. leave the test in
place and commit it with the bugfix. don't run shell commands to test
bugfixes or reproduce bugs. write tests!
* never, ever mention claude or anthropic in commit messages. do not use attribution
- never, ever mention claude or anthropic in commit messages. do not use attribution
* after each change, run "make fmt".
- after each change, run "make fmt".
* after each change, run "make test" and ensure all tests pass.
- after each change, run "make test" and ensure all tests pass.
* after each change, run "make lint" and ensure no linting errors. fix any
- after each change, run "make lint" and ensure no linting errors. fix any
you find, one by one.
* after each change, commit the files you've changed. push after
- after each change, commit the files you've changed. push after
committing.
* NEVER use `git add -A`. always add only individual files that you've changed.
- NEVER use `git add -A`. always add only individual files that you've changed.

View File

@@ -17,14 +17,14 @@ GOFLAGS := -ldflags "$(GOLDFLAGS)"
default: fmt test
run: ./mfer.cmd
run: ./bin/mfer
./$<
./$< gen
ci: test
test: $(SOURCEFILES) mfer/mf.pb.go
go test -v --timeout 3s ./...
go test -v --timeout 10s ./...
$(PROTOC_GEN_GO):
test -e $(PROTOC_GEN_GO) || go install -v google.golang.org/protobuf/cmd/protoc-gen-go@v1.28.1
@@ -38,12 +38,12 @@ devprereqs:
mfer/mf.pb.go: mfer/mf.proto
cd mfer && go generate .
mfer.cmd: $(SOURCEFILES) mfer/mf.pb.go
bin/mfer: $(SOURCEFILES) mfer/mf.pb.go
protoc --version
cd cmd/mfer && go build -tags urfave_cli_no_docs -o ../../mfer.cmd $(GOFLAGS) .
cd cmd/mfer && go build -tags urfave_cli_no_docs -o ../../bin/mfer $(GOFLAGS) .
clean:
rm -rfv mfer/*.pb.go mfer.cmd cmd/mfer/mfer *.dockerimage
rm -rfv mfer/*.pb.go bin/mfer cmd/mfer/mfer *.dockerimage
fmt: mfer/mf.pb.go
gofumpt -l -w mfer internal cmd

191
README.md
View File

@@ -52,188 +52,6 @@ Reading file contents and computing cryptographic hashes for manifest generation
- **NO_COLOR:** Respect the `NO_COLOR` environment variable for disabling colored output.
- **Options pattern:** Use `NewWithOptions(opts *Options)` constructor pattern for configurable types.
# Codebase Structure
## cmd/mfer/
### main.go
- **Variables**
- `Appname string` - Application name
- `Version string` - Version string (set at build time)
- `Gitrev string` - Git revision (set at build time)
## internal/cli/
### entry.go
- **Variables**
- `NO_COLOR bool` - Disables color output when NO_COLOR env var is set
- **Functions**
- `Run(Appname, Version, Gitrev string) int` - Main entry point for the CLI
### mfer.go
- **Types**
- `CLIApp struct` - Main CLI application container
- **Methods**
- `(*CLIApp) VersionString() string` - Returns formatted version string
## internal/log/
### log.go
- **Functions**
- `Init()` - Initializes the logger
- `Info(arg string)` - Logs at info level
- `Infof(format string, args ...interface{})` - Logs at info level with formatting
- `Debug(arg string)` - Logs at debug level with caller info
- `Debugf(format string, args ...interface{})` - Logs at debug level with formatting and caller info
- `Dump(args ...interface{})` - Logs spew dump at debug level
- `Progressf(format string, args ...interface{})` - Prints progress message (overwrites current line)
- `ProgressDone()` - Completes progress line with newline
- `EnableDebugLogging()` - Sets log level to debug
- `SetLevel(arg log.Level)` - Sets log level
- `SetLevelFromVerbosity(l int)` - Sets log level from verbosity count
- `GetLevel() log.Level` - Returns current log level
- `GetLogger() *log.Logger` - Returns underlying logger
- `WithError(e error) *log.Entry` - Returns log entry with error attached
- `DisableStyling()` - Disables colors and styling (for NO_COLOR)
## internal/scanner/
### scanner.go
- **Types**
- `Options struct` - Options for scanner behavior
- `IncludeDotfiles bool` - Include dot (hidden) files (excluded by default)
- `FollowSymLinks bool`
- `EnumerateStatus struct` - Progress information for enumeration phase
- `FilesFound int64`
- `BytesFound int64`
- `ScanStatus struct` - Progress information for scan phase
- `TotalFiles int64`
- `ScannedFiles int64`
- `TotalBytes int64`
- `ScannedBytes int64`
- `BytesPerSec float64`
- `ETA time.Duration`
- `FileEntry struct` - Represents an enumerated file
- `Path string` - Relative path (used in manifest)
- `AbsPath string` - Absolute path (used for reading file content)
- `Size int64`
- `Mtime time.Time`
- `Ctime time.Time`
- `Scanner struct` - Accumulates files and generates manifests
- **Functions**
- `New() *Scanner` - Creates a new Scanner with default options
- `NewWithOptions(opts *Options) *Scanner` - Creates a new Scanner with given options
- **Methods (Enumeration Phase)**
- `(*Scanner) EnumerateFile(path string) error` - Enumerates a single file, calling stat() for metadata
- `(*Scanner) EnumeratePath(inputPath string, progress chan<- EnumerateStatus) error` - Walks a directory and enumerates all files
- `(*Scanner) EnumeratePaths(progress chan<- EnumerateStatus, inputPaths ...string) error` - Walks multiple directories
- `(*Scanner) EnumerateFS(afs afero.Fs, basePath string, progress chan<- EnumerateStatus) error` - Walks an afero filesystem
- **Methods (Accessors)**
- `(*Scanner) Files() []*FileEntry` - Returns copy of all enumerated files
- `(*Scanner) FileCount() int64` - Returns number of files
- `(*Scanner) TotalBytes() int64` - Returns total size of all files
- **Methods (Scan Phase)**
- `(*Scanner) ToManifest(ctx context.Context, w io.Writer, progress chan<- ScanStatus) error` - Reads file contents, computes hashes, generates manifest
## internal/checker/
### checker.go
- **Types**
- `Result struct` - Outcome of checking a single file
- `Path string` - File path from manifest
- `Status Status` - Verification status
- `Message string` - Error or status message
- `Status int` - Verification status enumeration
- `StatusOK` - File matches manifest
- `StatusMissing` - File not found
- `StatusSizeMismatch` - File size differs from manifest
- `StatusHashMismatch` - File hash differs from manifest
- `StatusError` - Error occurred during verification
- `CheckStatus struct` - Progress information for check operation
- `TotalFiles int64`
- `CheckedFiles int64`
- `TotalBytes int64`
- `CheckedBytes int64`
- `BytesPerSec float64`
- `ETA time.Duration`
- `Failures int64`
- `Checker struct` - Verifies files against a manifest
- **Functions**
- `NewChecker(manifestPath string, basePath string) (*Checker, error)` - Creates a new Checker for the given manifest and base path
- **Methods**
- `(s Status) String() string` - Returns string representation of status
- `(*Checker) FileCount() int64` - Returns number of files in the manifest
- `(*Checker) TotalBytes() int64` - Returns total size of all files in manifest
- `(*Checker) Check(ctx context.Context, results chan<- Result, progress chan<- CheckStatus) error` - Verifies all files against the manifest
## mfer/
### manifest.go
- **Types**
- `manifest struct` - Internal representation of a manifest file
- **Methods**
- `(*manifest) Files() []*MFFilePath` - Returns all file entries from a loaded manifest
### builder.go
- **Types**
- `FileHashProgress struct` - Progress info during file hashing (BytesRead int64)
- `Builder struct` - Constructs manifests by adding files one at a time
- **Functions**
- `NewBuilder() *Builder` - Creates a new Builder
- **Methods**
- `(*Builder) AddFile(path string, size int64, mtime time.Time, reader io.Reader, progress chan<- FileHashProgress) (int64, error)` - Reads file, computes hash, adds to manifest
- `(*Builder) AddFileWithHash(path string, size int64, mtime time.Time, hash []byte)` - Adds file with pre-computed hash
- `(*Builder) FileCount() int` - Returns number of files added
- `(*Builder) Build(w io.Writer) error` - Finalizes and writes manifest
### serialize.go
- **Constants**
- `MAGIC string` - Magic bytes prefix for manifest files ("ZNAVSRFG")
### deserialize.go
- **Functions**
- `NewManifestFromReader(input io.Reader) (*manifest, error)` - Reads and parses manifest from io.Reader
- `NewManifestFromFile(fs afero.Fs, path string) (*manifest, error)` - Reads and parses manifest from file path
### mf.pb.go (generated from mf.proto)
- **Enum Types**
- `MFFileOuter_Version` - Outer file format version
- `MFFileOuter_VERSION_NONE`
- `MFFileOuter_VERSION_ONE`
- `MFFileOuter_CompressionType` - Compression type for inner message
- `MFFileOuter_COMPRESSION_NONE`
- `MFFileOuter_COMPRESSION_ZSTD`
- `MFFile_Version` - Inner file format version
- `MFFile_VERSION_NONE`
- `MFFile_VERSION_ONE`
- **Message Types**
- `Timestamp struct` - Timestamp with seconds and nanoseconds
- `GetSeconds() int64`
- `GetNanos() int32`
- `MFFileOuter struct` - Outer wrapper containing compressed/signed inner message
- `GetVersion() MFFileOuter_Version`
- `GetCompressionType() MFFileOuter_CompressionType`
- `GetSize() int64`
- `GetSha256() []byte`
- `GetInnerMessage() []byte`
- `GetSignature() []byte`
- `GetSigner() []byte`
- `GetSigningPubKey() []byte`
- `MFFilePath struct` - Individual file entry in manifest
- `GetPath() string`
- `GetSize() int64`
- `GetHashes() []*MFFileChecksum`
- `GetMimeType() string`
- `GetMtime() *Timestamp`
- `GetCtime() *Timestamp`
- `GetAtime() *Timestamp`
- `MFFileChecksum struct` - File checksum using multihash
- `GetMultiHash() []byte`
- `MFFile struct` - Inner manifest containing file list
- `GetVersion() MFFile_Version`
- `GetFiles() []*MFFilePath`
- `GetCreatedAt() *Timestamp`
# Build Status
[![Build Status](https://drone.datavi.be/api/badges/sneak/mfer/status.svg)](https://drone.datavi.be/sneak/mfer)
@@ -253,7 +71,6 @@ requests](https://git.eeqj.de/sneak/mfer/pulls) and pass CI to be merged.
Any changes submitted to this project must also be
[WTFPL-licensed](https://wtfpl.net) to be considered.
# Problem Statement
Given a plain URL, there is no standard way to safely and programmatically
@@ -424,13 +241,13 @@ desired username for an account on this Gitea instance.
## Links
* Repo: [https://git.eeqj.de/sneak/mfer](https://git.eeqj.de/sneak/mfer)
* Issues: [https://git.eeqj.de/sneak/mfer/issues](https://git.eeqj.de/sneak/mfer/issues)
- Repo: [https://git.eeqj.de/sneak/mfer](https://git.eeqj.de/sneak/mfer)
- Issues: [https://git.eeqj.de/sneak/mfer/issues](https://git.eeqj.de/sneak/mfer/issues)
# Authors
* [@sneak &lt;sneak@sneak.berlin&gt;](mailto:sneak@sneak.berlin)
- [@sneak &lt;sneak@sneak.berlin&gt;](mailto:sneak@sneak.berlin)
# License
* [WTFPL](https://wtfpl.net)
- [WTFPL](https://wtfpl.net)

122
TODO.md Normal file
View File

@@ -0,0 +1,122 @@
# TODO: mfer 1.0
## Design Questions
*sneak: please answer inline below each question. These are preserved for posterity.*
### Format Design
**1. Should `MFFileChecksum` be simplified?**
Currently it's a separate message wrapping a single `bytes multiHash` field. Since multihash already self-describes the algorithm, `repeated bytes hashes` directly on `MFFilePath` would be simpler and reduce per-file protobuf overhead. Is the extra message layer intentional (e.g. planning to add per-hash metadata like `verified_at`)?
> *answer:*
**2. Should file permissions/mode be stored?**
The format stores mtime/ctime but not Unix file permissions. For archival use (ExFAT, filesystem-independent checksums) this may not matter, but for software distribution or filesystem restoration it's a gap. Should we reserve a field now (e.g. `optional uint32 mode = 305`) even if we don't populate it yet?
> *answer:*
**3. Should `atime` be removed from the schema?**
Access time is volatile, non-deterministic, and often disabled (`noatime`). Including it means two manifests of the same directory at different times will differ, which conflicts with the determinism goal. Remove it, or document it as "never set by default"?
> *answer:*
**4. What are the path normalization rules?**
The proto has `string path` with no specification about: always forward-slash? Must be relative? No `..` components allowed? UTF-8 NFC vs NFD normalization (macOS vs Linux)? Max path length? This is a security issue (path traversal) and a cross-platform compatibility issue. What rules should the spec mandate?
> *answer:*
**5. Should we add a version byte after the magic?**
Currently `ZNAVSRFG` is followed immediately by protobuf. Adding a version byte (`ZNAVSRFG\x01`) would allow future framing changes without requiring protobuf parsing to detect the version. `MFFileOuter.Version` serves this purpose but requires successful deserialization to read. Worth the extra byte?
> *answer:*
**6. Should we add a length-prefix after the magic?**
Protobuf is not self-delimiting. If we ever want to concatenate manifests or append data after the protobuf, the current framing is insufficient. Add a varint or fixed-width length-prefix?
> *answer:*
### Signature Design
**7. What does the outer SHA-256 hash cover — compressed or uncompressed data?**
The review notes it currently hashes compressed data (good for verifying before decompression), but this should be explicitly documented. Which is the intended behavior?
> *answer:*
**8. Should `signatureString()` sign raw bytes instead of a hex-encoded string?**
Currently the canonical string is `MAGIC-UUID-MULTIHASH` with hex encoding, which adds a transformation layer. Signing the raw `sha256` bytes (or compressed `innerMessage` directly) would be simpler. Keep the string format or switch to raw bytes?
> *answer:*
**9. Should we support detached signature files (`.mf.sig`)?**
Embedded signatures are better for single-file distribution. Detached `.mf.sig` files follow the familiar `SHASUMS`/`SHASUMS.asc` pattern and are simpler for HTTP serving. Support both modes?
> *answer:*
**10. GPG vs pure-Go crypto for signatures?**
Shelling out to `gpg` is fragile (may not be installed, version-dependent output). `github.com/ProtonMail/go-crypto` provides pure-Go OpenPGP, or we could go Ed25519/signify (simpler, no key management). Which direction?
> *answer:*
### Implementation Design
**11. Should manifests be deterministic by default?**
This means: sort file entries by path, omit `createdAt` timestamp (or make it opt-in), no `atime`. Should determinism be the default, with a `--include-timestamps` flag to opt in?
> *answer:*
**12. Should we consolidate or keep both scanner/checker implementations?**
There are two parallel implementations: `mfer/scanner.go` + `mfer/checker.go` (typed with `FileSize`, `RelFilePath`) and `internal/scanner/` + `internal/checker/` (raw `int64`, `string`). The `mfer/` versions are superior. Delete the `internal/` versions?
> *answer:*
**13. Should the `manifest` type be exported?**
Currently unexported with exported constructors (`New`, `NewFromPaths`, etc.). Consumers can't declare `var m *mfer.manifest`. Export the type, or define an interface?
> *answer:*
**14. What should the Go module path be for 1.0?**
Currently mixed between `sneak.berlin/go/mfer` and `git.eeqj.de/sneak/mfer`. Which is canonical?
> *answer:*
---
## Implementation Plan
### Phase 1: Foundation (format correctness)
- [ ] Delete `internal/scanner/` and `internal/checker/` — consolidate on `mfer/` package versions; update CLI code
- [ ] Add deterministic file ordering — sort entries by path (lexicographic, byte-order) in `Builder.Build()`; add test asserting byte-identical output from two runs
- [ ] Add decompression size limit — `io.LimitReader` in `deserializeInner()` with `m.pbOuter.Size` as bound
- [ ] Fix `errors.Is` dead code in checker — replace with `os.IsNotExist(err)` or `errors.Is(err, fs.ErrNotExist)`
- [ ] Fix `AddFile` to verify size — check `totalRead == size` after reading, return error on mismatch
- [ ] Specify path invariants — add proto comments (UTF-8, forward-slash, relative, no `..`, no leading `/`); validate in `Builder.AddFile` and `Builder.AddFileWithHash`
### Phase 2: CLI polish
- [ ] Fix flag naming — all CLI flags use kebab-case as primary (`--include-dotfiles`, `--follow-symlinks`)
- [ ] Fix URL construction in fetch — use `BaseURL.JoinPath()` or `url.JoinPath()` instead of string concatenation
- [ ] Add progress rate-limiting to Checker — throttle to once per second, matching Scanner
- [ ] Add `--deterministic` flag (or make it default) — omit `createdAt`, sort files
### Phase 3: Robustness
- [ ] Replace GPG subprocess with pure-Go crypto — `github.com/ProtonMail/go-crypto` or Ed25519/signify
- [ ] Add timeout to any remaining subprocess calls
- [ ] Add fuzzing tests for `NewManifestFromReader`
- [ ] Add retry logic to fetch — exponential backoff for transient HTTP errors
### Phase 4: Format finalization
- [ ] Remove or deprecate `atime` from proto (pending design question answer)
- [ ] Reserve `optional uint32 mode = 305` in `MFFilePath` for future file permissions
- [ ] Add version byte after magic — `ZNAVSRFG\x01` for format version 1
- [ ] Write format specification document — separate from README: magic, outer structure, compression, inner structure, path invariants, signature scheme, canonical serialization
### Phase 5: Release prep
- [ ] Finalize Go module path
- [ ] Audit all error messages for consistency and helpfulness
- [ ] Add `--version` output matching SemVer
- [ ] Tag v1.0.0

1
go.mod
View File

@@ -6,6 +6,7 @@ require (
github.com/apex/log v1.9.0
github.com/davecgh/go-spew v1.1.1
github.com/dustin/go-humanize v1.0.1
github.com/google/uuid v1.1.2
github.com/klauspost/compress v1.18.2
github.com/multiformats/go-multihash v0.2.3
github.com/pterm/pterm v0.12.35

1
go.sum
View File

@@ -135,6 +135,7 @@ github.com/google/pprof v0.0.0-20201203190320-1bf35d6f28c2/go.mod h1:kpwsk12EmLe
github.com/google/pprof v0.0.0-20201218002935-b9804c9f04c2/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
github.com/google/uuid v1.1.1/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/google/uuid v1.1.2 h1:EVhdT+1Kseyi1/pUmXKaFxYsDNy9RQYkMWRH68J/W7Y=
github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/googleapis/gax-go/v2 v2.0.4/go.mod h1:0Wqv26UfaUD9n4G6kQubkQ+KchISgw+vpHVxEJEs9eg=
github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5mhpdKc/us6bOk=

281
internal/checker/checker.go Normal file
View File

@@ -0,0 +1,281 @@
package checker
import (
"bytes"
"context"
"crypto/sha256"
"errors"
"io"
"os"
"path/filepath"
"github.com/multiformats/go-multihash"
"github.com/spf13/afero"
"sneak.berlin/go/mfer/mfer"
)
// Result represents the outcome of checking a single file.
type Result struct {
Path string // Relative path from manifest
Status Status // Verification result status
Message string // Human-readable description of the result
}
// Status represents the verification status of a file.
type Status int
const (
StatusOK Status = iota // File matches manifest (size and hash verified)
StatusMissing // File not found on disk
StatusSizeMismatch // File size differs from manifest
StatusHashMismatch // File hash differs from manifest
StatusExtra // File exists on disk but not in manifest
StatusError // Error occurred during verification
)
func (s Status) String() string {
switch s {
case StatusOK:
return "OK"
case StatusMissing:
return "MISSING"
case StatusSizeMismatch:
return "SIZE_MISMATCH"
case StatusHashMismatch:
return "HASH_MISMATCH"
case StatusExtra:
return "EXTRA"
case StatusError:
return "ERROR"
default:
return "UNKNOWN"
}
}
// CheckStatus contains progress information for the check operation.
type CheckStatus struct {
TotalFiles int64 // Total number of files in manifest
CheckedFiles int64 // Number of files checked so far
TotalBytes int64 // Total bytes to verify (sum of all file sizes)
CheckedBytes int64 // Bytes verified so far
BytesPerSec float64 // Current throughput rate
Failures int64 // Number of verification failures encountered
}
// Checker verifies files against a manifest.
type Checker struct {
basePath string
files []*mfer.MFFilePath
fs afero.Fs
// manifestPaths is a set of paths in the manifest for quick lookup
manifestPaths map[string]struct{}
}
// NewChecker creates a new Checker for the given manifest, base path, and filesystem.
// The basePath is the directory relative to which manifest paths are resolved.
// If fs is nil, the real filesystem (OsFs) is used.
func NewChecker(manifestPath string, basePath string, fs afero.Fs) (*Checker, error) {
if fs == nil {
fs = afero.NewOsFs()
}
m, err := mfer.NewManifestFromFile(fs, manifestPath)
if err != nil {
return nil, err
}
abs, err := filepath.Abs(basePath)
if err != nil {
return nil, err
}
files := m.Files()
manifestPaths := make(map[string]struct{}, len(files))
for _, f := range files {
manifestPaths[f.Path] = struct{}{}
}
return &Checker{
basePath: abs,
files: files,
fs: fs,
manifestPaths: manifestPaths,
}, nil
}
// FileCount returns the number of files in the manifest.
func (c *Checker) FileCount() int64 {
return int64(len(c.files))
}
// TotalBytes returns the total size of all files in the manifest.
func (c *Checker) TotalBytes() int64 {
var total int64
for _, f := range c.files {
total += f.Size
}
return total
}
// Check verifies all files against the manifest.
// Results are sent to the results channel as files are checked.
// Progress updates are sent to the progress channel approximately once per second.
// Both channels are closed when the method returns.
func (c *Checker) Check(ctx context.Context, results chan<- Result, progress chan<- CheckStatus) error {
if results != nil {
defer close(results)
}
if progress != nil {
defer close(progress)
}
totalFiles := int64(len(c.files))
totalBytes := c.TotalBytes()
var checkedFiles int64
var checkedBytes int64
var failures int64
for _, entry := range c.files {
select {
case <-ctx.Done():
return ctx.Err()
default:
}
result := c.checkFile(entry, &checkedBytes)
if result.Status != StatusOK {
failures++
}
checkedFiles++
if results != nil {
results <- result
}
// Send progress (simplified - every file for now)
if progress != nil {
sendCheckStatus(progress, CheckStatus{
TotalFiles: totalFiles,
CheckedFiles: checkedFiles,
TotalBytes: totalBytes,
CheckedBytes: checkedBytes,
Failures: failures,
})
}
}
return nil
}
func (c *Checker) checkFile(entry *mfer.MFFilePath, checkedBytes *int64) Result {
absPath := filepath.Join(c.basePath, entry.Path)
// Check if file exists
info, err := c.fs.Stat(absPath)
if err != nil {
if errors.Is(err, afero.ErrFileNotFound) || errors.Is(err, errors.New("file does not exist")) {
return Result{Path: entry.Path, Status: StatusMissing, Message: "file not found"}
}
// Check for "file does not exist" style errors
exists, _ := afero.Exists(c.fs, absPath)
if !exists {
return Result{Path: entry.Path, Status: StatusMissing, Message: "file not found"}
}
return Result{Path: entry.Path, Status: StatusError, Message: err.Error()}
}
// Check size
if info.Size() != entry.Size {
*checkedBytes += info.Size()
return Result{
Path: entry.Path,
Status: StatusSizeMismatch,
Message: "size mismatch",
}
}
// Open and hash file
f, err := c.fs.Open(absPath)
if err != nil {
return Result{Path: entry.Path, Status: StatusError, Message: err.Error()}
}
defer f.Close()
h := sha256.New()
n, err := io.Copy(h, f)
if err != nil {
return Result{Path: entry.Path, Status: StatusError, Message: err.Error()}
}
*checkedBytes += n
// Encode as multihash and compare
computed, err := multihash.Encode(h.Sum(nil), multihash.SHA2_256)
if err != nil {
return Result{Path: entry.Path, Status: StatusError, Message: err.Error()}
}
// Check against all hashes in manifest (at least one must match)
for _, hash := range entry.Hashes {
if bytes.Equal(computed, hash.MultiHash) {
return Result{Path: entry.Path, Status: StatusOK}
}
}
return Result{Path: entry.Path, Status: StatusHashMismatch, Message: "hash mismatch"}
}
// FindExtraFiles walks the filesystem and reports files not in the manifest.
// Results are sent to the results channel. The channel is closed when done.
func (c *Checker) FindExtraFiles(ctx context.Context, results chan<- Result) error {
if results != nil {
defer close(results)
}
return afero.Walk(c.fs, c.basePath, func(path string, info os.FileInfo, err error) error {
if err != nil {
return err
}
select {
case <-ctx.Done():
return ctx.Err()
default:
}
// Skip directories
if info.IsDir() {
return nil
}
// Get relative path
relPath, err := filepath.Rel(c.basePath, path)
if err != nil {
return err
}
// Check if path is in manifest
if _, exists := c.manifestPaths[relPath]; !exists {
if results != nil {
results <- Result{
Path: relPath,
Status: StatusExtra,
Message: "not in manifest",
}
}
}
return nil
})
}
// sendCheckStatus sends a status update without blocking.
func sendCheckStatus(ch chan<- CheckStatus, status CheckStatus) {
if ch == nil {
return
}
select {
case ch <- status:
default:
}
}

View File

@@ -1,8 +1,10 @@
package cli
import (
"encoding/hex"
"fmt"
"path/filepath"
"strings"
"time"
"github.com/dustin/go-humanize"
@@ -68,6 +70,35 @@ func (mfa *CLIApp) checkManifestOperation(ctx *cli.Context) error {
return fmt.Errorf("failed to load manifest: %w", err)
}
// Check signature requirement
requiredSigner := ctx.String("require-signature")
if requiredSigner != "" {
// Validate fingerprint format: must be exactly 40 hex characters
if len(requiredSigner) != 40 {
return fmt.Errorf("invalid fingerprint: must be exactly 40 hex characters, got %d", len(requiredSigner))
}
if _, err := hex.DecodeString(requiredSigner); err != nil {
return fmt.Errorf("invalid fingerprint: must be valid hex: %w", err)
}
if !chk.IsSigned() {
return fmt.Errorf("manifest is not signed, but signature from %s is required", requiredSigner)
}
// Extract fingerprint from the embedded public key (not from the signer field)
// This validates the key is importable and gets its actual fingerprint
embeddedFP, err := chk.ExtractEmbeddedSigningKeyFP()
if err != nil {
return fmt.Errorf("failed to extract fingerprint from embedded signing key: %w", err)
}
// Compare fingerprints - must be exact match (case-insensitive)
if !strings.EqualFold(embeddedFP, requiredSigner) {
return fmt.Errorf("embedded signing key fingerprint %s does not match required %s", embeddedFP, requiredSigner)
}
log.Infof("manifest signature verified (signer: %s)", embeddedFP)
}
log.Infof("manifest contains %d files, %s", chk.FileCount(), humanize.IBytes(uint64(chk.TotalBytes())))
// Set up results channel

View File

@@ -65,9 +65,9 @@ func TestGenerateCommand(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test files in memory filesystem
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello world"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("test content"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello world"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("test content"), 0o644))
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/testdir/test.mf", "/testdir"}, fs)
@@ -85,9 +85,9 @@ func TestGenerateAndCheckCommand(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test files with subdirectory
require.NoError(t, fs.MkdirAll("/testdir/subdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello world"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/subdir/file2.txt", []byte("test content"), 0644))
require.NoError(t, fs.MkdirAll("/testdir/subdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello world"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/subdir/file2.txt", []byte("test content"), 0o644))
// Generate manifest
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/testdir/test.mf", "/testdir"}, fs)
@@ -104,8 +104,8 @@ func TestCheckCommandWithMissingFile(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test file
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello world"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello world"), 0o644))
// Generate manifest
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/testdir/test.mf", "/testdir"}, fs)
@@ -125,8 +125,8 @@ func TestCheckCommandWithCorruptedFile(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test file
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello world"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello world"), 0o644))
// Generate manifest
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/testdir/test.mf", "/testdir"}, fs)
@@ -134,7 +134,7 @@ func TestCheckCommandWithCorruptedFile(t *testing.T) {
require.Equal(t, 0, exitCode, "generate failed: %s", opts.Stderr.(*bytes.Buffer).String())
// Corrupt the file (change content but keep same size)
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("HELLO WORLD"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("HELLO WORLD"), 0o644))
// Check manifest - should fail with hash mismatch
opts = testOpts([]string{"mfer", "check", "-q", "--base", "/testdir", "/testdir/test.mf"}, fs)
@@ -146,8 +146,8 @@ func TestCheckCommandWithSizeMismatch(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test file
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello world"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello world"), 0o644))
// Generate manifest
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/testdir/test.mf", "/testdir"}, fs)
@@ -155,7 +155,7 @@ func TestCheckCommandWithSizeMismatch(t *testing.T) {
require.Equal(t, 0, exitCode, "generate failed: %s", opts.Stderr.(*bytes.Buffer).String())
// Change file size
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("different size content here"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("different size content here"), 0o644))
// Check manifest - should fail with size mismatch
opts = testOpts([]string{"mfer", "check", "-q", "--base", "/testdir", "/testdir/test.mf"}, fs)
@@ -167,8 +167,8 @@ func TestBannerOutput(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test file
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
// Run without -q to see banner
opts := testOpts([]string{"mfer", "generate", "-o", "/testdir/test.mf", "/testdir"}, fs)
@@ -193,9 +193,9 @@ func TestGenerateExcludesDotfilesByDefault(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test files including dotfiles
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/.hidden", []byte("secret"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/.hidden", []byte("secret"), 0o644))
// Generate manifest without --include-dotfiles (default excludes dotfiles)
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/testdir/test.mf", "/testdir"}, fs)
@@ -217,9 +217,9 @@ func TestGenerateWithIncludeDotfiles(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test files including dotfiles
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/.hidden", []byte("secret"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/.hidden", []byte("secret"), 0o644))
// Generate manifest with --include-dotfiles
opts := testOpts([]string{"mfer", "generate", "-q", "--include-dotfiles", "-o", "/testdir/test.mf", "/testdir"}, fs)
@@ -236,10 +236,10 @@ func TestMultipleInputPaths(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test files in multiple directories
require.NoError(t, fs.MkdirAll("/dir1", 0755))
require.NoError(t, fs.MkdirAll("/dir2", 0755))
require.NoError(t, afero.WriteFile(fs, "/dir1/file1.txt", []byte("content1"), 0644))
require.NoError(t, afero.WriteFile(fs, "/dir2/file2.txt", []byte("content2"), 0644))
require.NoError(t, fs.MkdirAll("/dir1", 0o755))
require.NoError(t, fs.MkdirAll("/dir2", 0o755))
require.NoError(t, afero.WriteFile(fs, "/dir1/file1.txt", []byte("content1"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/dir2/file2.txt", []byte("content2"), 0o644))
// Generate manifest from multiple paths
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/output.mf", "/dir1", "/dir2"}, fs)
@@ -254,9 +254,9 @@ func TestNoExtraFilesPass(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test files
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("world"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("world"), 0o644))
// Generate manifest
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/manifest.mf", "/testdir"}, fs)
@@ -273,8 +273,8 @@ func TestNoExtraFilesFail(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test files
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
// Generate manifest
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/manifest.mf", "/testdir"}, fs)
@@ -282,7 +282,7 @@ func TestNoExtraFilesFail(t *testing.T) {
require.Equal(t, 0, exitCode)
// Add an extra file after manifest generation
require.NoError(t, afero.WriteFile(fs, "/testdir/extra.txt", []byte("extra"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/extra.txt", []byte("extra"), 0o644))
// Check with --no-extra-files (should fail - extra file exists)
opts = testOpts([]string{"mfer", "check", "-q", "--no-extra-files", "--base", "/testdir", "/manifest.mf"}, fs)
@@ -294,9 +294,9 @@ func TestNoExtraFilesWithSubdirectory(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test files with subdirectory
require.NoError(t, fs.MkdirAll("/testdir/subdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/subdir/file2.txt", []byte("world"), 0644))
require.NoError(t, fs.MkdirAll("/testdir/subdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/subdir/file2.txt", []byte("world"), 0o644))
// Generate manifest
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/manifest.mf", "/testdir"}, fs)
@@ -304,7 +304,7 @@ func TestNoExtraFilesWithSubdirectory(t *testing.T) {
require.Equal(t, 0, exitCode)
// Add extra file in subdirectory
require.NoError(t, afero.WriteFile(fs, "/testdir/subdir/extra.txt", []byte("extra"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/subdir/extra.txt", []byte("extra"), 0o644))
// Check with --no-extra-files (should fail)
opts = testOpts([]string{"mfer", "check", "-q", "--no-extra-files", "--base", "/testdir", "/manifest.mf"}, fs)
@@ -316,8 +316,8 @@ func TestCheckWithoutNoExtraFilesIgnoresExtra(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test file
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
// Generate manifest
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/manifest.mf", "/testdir"}, fs)
@@ -325,7 +325,7 @@ func TestCheckWithoutNoExtraFilesIgnoresExtra(t *testing.T) {
require.Equal(t, 0, exitCode)
// Add extra file
require.NoError(t, afero.WriteFile(fs, "/testdir/extra.txt", []byte("extra"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/extra.txt", []byte("extra"), 0o644))
// Check WITHOUT --no-extra-files (should pass - extra files ignored)
opts = testOpts([]string{"mfer", "check", "-q", "--base", "/testdir", "/manifest.mf"}, fs)
@@ -337,8 +337,8 @@ func TestGenerateAtomicWriteNoTempFileOnSuccess(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test file
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
// Generate manifest
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/output.mf", "/testdir"}, fs)
@@ -360,11 +360,11 @@ func TestGenerateAtomicWriteOverwriteWithForce(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test file
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
// Create existing manifest with different content
require.NoError(t, afero.WriteFile(fs, "/output.mf", []byte("old content"), 0644))
require.NoError(t, afero.WriteFile(fs, "/output.mf", []byte("old content"), 0o644))
// Generate manifest with --force
opts := testOpts([]string{"mfer", "generate", "-q", "-f", "-o", "/output.mf", "/testdir"}, fs)
@@ -386,11 +386,11 @@ func TestGenerateFailsWithoutForceWhenOutputExists(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test file
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
// Create existing manifest
require.NoError(t, afero.WriteFile(fs, "/output.mf", []byte("existing"), 0644))
require.NoError(t, afero.WriteFile(fs, "/output.mf", []byte("existing"), 0o644))
// Generate manifest WITHOUT --force (should fail)
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/output.mf", "/testdir"}, fs)
@@ -411,8 +411,8 @@ func TestGenerateAtomicWriteUsesTemp(t *testing.T) {
fs := afero.NewMemMapFs()
// Create test file
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("hello"), 0o644))
// Generate manifest
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/output.mf", "/testdir"}, fs)
@@ -464,8 +464,8 @@ func TestGenerateAtomicWriteCleansUpOnError(t *testing.T) {
baseFs := afero.NewMemMapFs()
// Create test files - need enough content to trigger the write failure
require.NoError(t, baseFs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(baseFs, "/testdir/file1.txt", []byte("hello world this is a test file"), 0644))
require.NoError(t, baseFs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(baseFs, "/testdir/file1.txt", []byte("hello world this is a test file"), 0o644))
// Wrap with failing writer that fails after writing some bytes
fs := &failingWriterFs{Fs: baseFs, failAfter: 10}
@@ -489,8 +489,8 @@ func TestGenerateValidatesInputPaths(t *testing.T) {
fs := afero.NewMemMapFs()
// Create one valid directory
require.NoError(t, fs.MkdirAll("/validdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/validdir/file.txt", []byte("content"), 0644))
require.NoError(t, fs.MkdirAll("/validdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/validdir/file.txt", []byte("content"), 0o644))
t.Run("nonexistent path fails fast", func(t *testing.T) {
opts := testOpts([]string{"mfer", "generate", "-q", "-o", "/output.mf", "/nonexistent"}, fs)
@@ -527,7 +527,7 @@ func TestCheckDetectsManifestCorruption(t *testing.T) {
// Create many small files with random names to generate a ~1MB manifest
// Each manifest entry is roughly 50-60 bytes, so we need ~20000 files
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
numFiles := 20000
for i := 0; i < numFiles; i++ {
@@ -536,7 +536,7 @@ func TestCheckDetectsManifestCorruption(t *testing.T) {
// Small random content
content := make([]byte, 16+rng.Intn(48))
rng.Read(content)
require.NoError(t, afero.WriteFile(fs, filename, content, 0644))
require.NoError(t, afero.WriteFile(fs, filename, content, 0o644))
}
// Generate manifest outside of testdir
@@ -551,7 +551,7 @@ func TestCheckDetectsManifestCorruption(t *testing.T) {
t.Logf("manifest size: %d bytes (%d files)", len(validManifest), numFiles)
// First corruption: truncate the manifest
require.NoError(t, afero.WriteFile(fs, "/manifest.mf", validManifest[:len(validManifest)/2], 0644))
require.NoError(t, afero.WriteFile(fs, "/manifest.mf", validManifest[:len(validManifest)/2], 0o644))
// Check should fail with truncated manifest
opts = testOpts([]string{"mfer", "check", "-q", "--base", "/testdir", "/manifest.mf"}, fs)
@@ -559,7 +559,7 @@ func TestCheckDetectsManifestCorruption(t *testing.T) {
assert.Equal(t, 1, exitCode, "check should fail with truncated manifest")
// Verify check passes with valid manifest
require.NoError(t, afero.WriteFile(fs, "/manifest.mf", validManifest, 0644))
require.NoError(t, afero.WriteFile(fs, "/manifest.mf", validManifest, 0o644))
opts = testOpts([]string{"mfer", "check", "-q", "--base", "/testdir", "/manifest.mf"}, fs)
exitCode = RunWithOptions(opts)
require.Equal(t, 0, exitCode, "check should pass with valid manifest")
@@ -579,7 +579,7 @@ func TestCheckDetectsManifestCorruption(t *testing.T) {
}
corrupted[offset] = newByte
require.NoError(t, afero.WriteFile(fs, "/manifest.mf", corrupted, 0644))
require.NoError(t, afero.WriteFile(fs, "/manifest.mf", corrupted, 0o644))
// Check should fail with corrupted manifest
opts = testOpts([]string{"mfer", "check", "-q", "--base", "/testdir", "/manifest.mf"}, fs)
@@ -588,6 +588,6 @@ func TestCheckDetectsManifestCorruption(t *testing.T) {
i, offset, originalByte, newByte)
// Restore valid manifest for next iteration
require.NoError(t, afero.WriteFile(fs, "/manifest.mf", validManifest, 0644))
require.NoError(t, afero.WriteFile(fs, "/manifest.mf", validManifest, 0o644))
}
}

View File

@@ -257,7 +257,7 @@ func downloadFile(fileURL, localPath string, entry *mfer.MFFilePath, progress ch
// Create parent directories if needed
dir := filepath.Dir(localPath)
if dir != "" && dir != "." {
if err := os.MkdirAll(dir, 0755); err != nil {
if err := os.MkdirAll(dir, 0o755); err != nil {
return err
}
}

View File

@@ -13,7 +13,6 @@ import (
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/mfer/internal/scanner"
"sneak.berlin/go/mfer/mfer"
)
@@ -107,15 +106,15 @@ func TestFetchFromHTTP(t *testing.T) {
for path, content := range testFiles {
fullPath := "/" + path // MemMapFs needs absolute paths
dir := filepath.Dir(fullPath)
require.NoError(t, sourceFs.MkdirAll(dir, 0755))
require.NoError(t, afero.WriteFile(sourceFs, fullPath, content, 0644))
require.NoError(t, sourceFs.MkdirAll(dir, 0o755))
require.NoError(t, afero.WriteFile(sourceFs, fullPath, content, 0o644))
}
// Generate manifest using scanner
opts := &scanner.Options{
opts := &mfer.ScannerOptions{
Fs: sourceFs,
}
s := scanner.NewWithOptions(opts)
s := mfer.NewScannerWithOptions(opts)
require.NoError(t, s.EnumerateFS(sourceFs, "/", nil))
var manifestBuf bytes.Buffer
@@ -197,11 +196,11 @@ func TestFetchHashMismatch(t *testing.T) {
// Create source filesystem with a test file
sourceFs := afero.NewMemMapFs()
originalContent := []byte("Original content")
require.NoError(t, afero.WriteFile(sourceFs, "/file.txt", originalContent, 0644))
require.NoError(t, afero.WriteFile(sourceFs, "/file.txt", originalContent, 0o644))
// Generate manifest
opts := &scanner.Options{Fs: sourceFs}
s := scanner.NewWithOptions(opts)
opts := &mfer.ScannerOptions{Fs: sourceFs}
s := mfer.NewScannerWithOptions(opts)
require.NoError(t, s.EnumerateFS(sourceFs, "/", nil))
var manifestBuf bytes.Buffer
@@ -249,11 +248,11 @@ func TestFetchSizeMismatch(t *testing.T) {
// Create source filesystem with a test file
sourceFs := afero.NewMemMapFs()
originalContent := []byte("Original content with specific size")
require.NoError(t, afero.WriteFile(sourceFs, "/file.txt", originalContent, 0644))
require.NoError(t, afero.WriteFile(sourceFs, "/file.txt", originalContent, 0o644))
// Generate manifest
opts := &scanner.Options{Fs: sourceFs}
s := scanner.NewWithOptions(opts)
opts := &mfer.ScannerOptions{Fs: sourceFs}
s := mfer.NewScannerWithOptions(opts)
require.NoError(t, s.EnumerateFS(sourceFs, "/", nil))
var manifestBuf bytes.Buffer
@@ -298,11 +297,11 @@ func TestFetchProgress(t *testing.T) {
sourceFs := afero.NewMemMapFs()
// Create content large enough to trigger multiple progress updates
content := bytes.Repeat([]byte("x"), 100*1024) // 100KB
require.NoError(t, afero.WriteFile(sourceFs, "/large.txt", content, 0644))
require.NoError(t, afero.WriteFile(sourceFs, "/large.txt", content, 0o644))
// Generate manifest
opts := &scanner.Options{Fs: sourceFs}
s := scanner.NewWithOptions(opts)
opts := &mfer.ScannerOptions{Fs: sourceFs}
s := mfer.NewScannerWithOptions(opts)
require.NoError(t, s.EnumerateFS(sourceFs, "/", nil))
var manifestBuf bytes.Buffer

View File

@@ -227,6 +227,14 @@ func (mfa *CLIApp) freshenManifestOperation(ctx *cli.Context) error {
builder := mfer.NewBuilder()
// Set up signing options if sign-key is provided
if signKey := ctx.String("sign-key"); signKey != "" {
builder.SetSigningOptions(&mfer.SigningOptions{
KeyID: mfer.GPGKeyID(signKey),
})
log.Infof("signing manifest with GPG key: %s", signKey)
}
for _, e := range entries {
select {
case <-ctx.Done():

View File

@@ -8,7 +8,6 @@ import (
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/mfer/internal/scanner"
"sneak.berlin/go/mfer/mfer"
)
@@ -16,20 +15,20 @@ func TestFreshenUnchanged(t *testing.T) {
// Create filesystem with test files
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("content1"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("content2"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("content1"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("content2"), 0o644))
// Generate initial manifest
opts := &scanner.Options{Fs: fs}
s := scanner.NewWithOptions(opts)
opts := &mfer.ScannerOptions{Fs: fs}
s := mfer.NewScannerWithOptions(opts)
require.NoError(t, s.EnumeratePath("/testdir", nil))
var manifestBuf bytes.Buffer
require.NoError(t, s.ToManifest(context.Background(), &manifestBuf, nil))
// Write manifest to filesystem
require.NoError(t, afero.WriteFile(fs, "/testdir/.index.mf", manifestBuf.Bytes(), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/.index.mf", manifestBuf.Bytes(), 0o644))
// Parse manifest to verify
manifest, err := mfer.NewManifestFromFile(fs, "/testdir/.index.mf")
@@ -41,20 +40,20 @@ func TestFreshenWithChanges(t *testing.T) {
// Create filesystem with test files
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("content1"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("content2"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("content1"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("content2"), 0o644))
// Generate initial manifest
opts := &scanner.Options{Fs: fs}
s := scanner.NewWithOptions(opts)
opts := &mfer.ScannerOptions{Fs: fs}
s := mfer.NewScannerWithOptions(opts)
require.NoError(t, s.EnumeratePath("/testdir", nil))
var manifestBuf bytes.Buffer
require.NoError(t, s.ToManifest(context.Background(), &manifestBuf, nil))
// Write manifest to filesystem
require.NoError(t, afero.WriteFile(fs, "/testdir/.index.mf", manifestBuf.Bytes(), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/.index.mf", manifestBuf.Bytes(), 0o644))
// Verify initial manifest has 2 files
manifest, err := mfer.NewManifestFromFile(fs, "/testdir/.index.mf")
@@ -62,10 +61,10 @@ func TestFreshenWithChanges(t *testing.T) {
assert.Len(t, manifest.Files(), 2)
// Add a new file
require.NoError(t, afero.WriteFile(fs, "/testdir/file3.txt", []byte("content3"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file3.txt", []byte("content3"), 0o644))
// Modify file2 (change content and size)
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("modified content2"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("modified content2"), 0o644))
// Remove file1
require.NoError(t, fs.Remove("/testdir/file1.txt"))

View File

@@ -25,6 +25,14 @@ func (mfa *CLIApp) generateManifestOperation(ctx *cli.Context) error {
Fs: mfa.Fs,
}
// Set up signing options if sign-key is provided
if signKey := ctx.String("sign-key"); signKey != "" {
opts.SigningOptions = &mfer.SigningOptions{
KeyID: mfer.GPGKeyID(signKey),
}
log.Infof("signing manifest with GPG key: %s", signKey)
}
s := mfer.NewScannerWithOptions(opts)
// Phase 1: Enumeration - collect paths and stat files

View File

@@ -148,6 +148,12 @@ func (mfa *CLIApp) run(args []string) {
Aliases: []string{"P"},
Usage: "Show progress during enumeration and scanning",
},
&cli.StringFlag{
Name: "sign-key",
Aliases: []string{"s"},
Usage: "GPG key ID to sign the manifest with",
EnvVars: []string{"MFER_SIGN_KEY"},
},
),
},
{
@@ -175,6 +181,12 @@ func (mfa *CLIApp) run(args []string) {
Name: "no-extra-files",
Usage: "Fail if files exist in base directory that are not in manifest",
},
&cli.StringFlag{
Name: "require-signature",
Aliases: []string{"S"},
Usage: "Require manifest to be signed by the specified GPG key ID",
EnvVars: []string{"MFER_REQUIRE_SIGNATURE"},
},
),
},
{
@@ -208,6 +220,12 @@ func (mfa *CLIApp) run(args []string) {
Aliases: []string{"P"},
Usage: "Show progress during scanning and hashing",
},
&cli.StringFlag{
Name: "sign-key",
Aliases: []string{"s"},
Usage: "GPG key ID to sign the manifest with",
EnvVars: []string{"MFER_SIGN_KEY"},
},
),
},
{

373
internal/scanner/scanner.go Normal file
View File

@@ -0,0 +1,373 @@
package scanner
import (
"context"
"io"
"io/fs"
"path"
"path/filepath"
"strings"
"sync"
"time"
"github.com/spf13/afero"
"sneak.berlin/go/mfer/mfer"
)
// Phase 1: Enumeration
// ---------------------
// Walking directories and calling stat() on files to collect metadata.
// Builds the list of files to be scanned. Relatively fast (metadata only).
// EnumerateStatus contains progress information for the enumeration phase.
type EnumerateStatus struct {
FilesFound int64 // Number of files discovered so far
BytesFound int64 // Total size of discovered files (from stat)
}
// Phase 2: Scan (ToManifest)
// --------------------------
// Reading file contents and computing hashes for manifest generation.
// This is the expensive phase that reads all file data.
// ScanStatus contains progress information for the scan phase.
type ScanStatus struct {
TotalFiles int64 // Total number of files to scan
ScannedFiles int64 // Number of files scanned so far
TotalBytes int64 // Total bytes to read (sum of all file sizes)
ScannedBytes int64 // Bytes read so far
BytesPerSec float64 // Current throughput rate
}
// Options configures scanner behavior.
type Options struct {
IgnoreDotfiles bool // Skip files and directories starting with a dot
FollowSymLinks bool // Resolve symlinks instead of skipping them
Fs afero.Fs // Filesystem to use, defaults to OsFs if nil
}
// FileEntry represents a file that has been enumerated.
type FileEntry struct {
Path string // Relative path (used in manifest)
AbsPath string // Absolute path (used for reading file content)
Size int64 // File size in bytes
Mtime time.Time // Last modification time
Ctime time.Time // Creation time (platform-dependent)
}
// Scanner accumulates files and generates manifests from them.
type Scanner struct {
mu sync.RWMutex
files []*FileEntry
options *Options
fs afero.Fs
}
// New creates a new Scanner with default options.
func New() *Scanner {
return NewWithOptions(nil)
}
// NewWithOptions creates a new Scanner with the given options.
func NewWithOptions(opts *Options) *Scanner {
if opts == nil {
opts = &Options{}
}
fs := opts.Fs
if fs == nil {
fs = afero.NewOsFs()
}
return &Scanner{
files: make([]*FileEntry, 0),
options: opts,
fs: fs,
}
}
// EnumerateFile adds a single file to the scanner, calling stat() to get metadata.
func (s *Scanner) EnumerateFile(filePath string) error {
abs, err := filepath.Abs(filePath)
if err != nil {
return err
}
info, err := s.fs.Stat(abs)
if err != nil {
return err
}
// For single files, use the filename as the relative path
basePath := filepath.Dir(abs)
return s.enumerateFileWithInfo(filepath.Base(abs), basePath, info, nil)
}
// EnumeratePath walks a directory path and adds all files to the scanner.
// 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) EnumeratePath(inputPath string, progress chan<- EnumerateStatus) error {
if progress != nil {
defer close(progress)
}
abs, err := filepath.Abs(inputPath)
if err != nil {
return err
}
afs := afero.NewReadOnlyFs(afero.NewBasePathFs(s.fs, abs))
return s.enumerateFS(afs, abs, progress)
}
// EnumeratePaths walks multiple directory paths and adds all files to the scanner.
// 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(progress chan<- EnumerateStatus, inputPaths ...string) error {
if progress != nil {
defer close(progress)
}
for _, p := range inputPaths {
abs, err := filepath.Abs(p)
if err != nil {
return err
}
afs := afero.NewReadOnlyFs(afero.NewBasePathFs(s.fs, abs))
if err := s.enumerateFS(afs, abs, progress); err != nil {
return err
}
}
return nil
}
// EnumerateFS walks an afero filesystem and adds all files to the scanner.
// If progress is non-nil, status updates are sent as files are discovered.
// The progress channel is closed when the method returns.
// basePath is used to compute absolute paths for file reading.
func (s *Scanner) EnumerateFS(afs afero.Fs, basePath string, progress chan<- EnumerateStatus) error {
if progress != nil {
defer close(progress)
}
return s.enumerateFS(afs, basePath, progress)
}
// enumerateFS is the internal implementation that doesn't close the progress channel.
func (s *Scanner) enumerateFS(afs afero.Fs, basePath string, progress chan<- EnumerateStatus) error {
return afero.Walk(afs, "/", func(p string, info fs.FileInfo, err error) error {
if err != nil {
return err
}
if s.options.IgnoreDotfiles && pathIsHidden(p) {
if info.IsDir() {
return filepath.SkipDir
}
return nil
}
return s.enumerateFileWithInfo(p, basePath, info, progress)
})
}
// enumerateFileWithInfo adds a file with pre-existing fs.FileInfo.
func (s *Scanner) enumerateFileWithInfo(filePath string, basePath string, info fs.FileInfo, progress chan<- EnumerateStatus) error {
if info.IsDir() {
// Manifests contain only files, directories are implied
return nil
}
// Clean the path - remove leading slash if present
cleanPath := filePath
if len(cleanPath) > 0 && cleanPath[0] == '/' {
cleanPath = cleanPath[1:]
}
// Compute absolute path for file reading
absPath := filepath.Join(basePath, cleanPath)
entry := &FileEntry{
Path: cleanPath,
AbsPath: absPath,
Size: info.Size(),
Mtime: info.ModTime(),
// Note: Ctime not available from fs.FileInfo on all platforms
// Will need platform-specific code to extract it
}
s.mu.Lock()
s.files = append(s.files, entry)
filesFound := int64(len(s.files))
var bytesFound int64
for _, f := range s.files {
bytesFound += f.Size
}
s.mu.Unlock()
sendEnumerateStatus(progress, EnumerateStatus{
FilesFound: filesFound,
BytesFound: bytesFound,
})
return nil
}
// Files returns a copy of all files added to the scanner.
func (s *Scanner) Files() []*FileEntry {
s.mu.RLock()
defer s.mu.RUnlock()
out := make([]*FileEntry, len(s.files))
copy(out, s.files)
return out
}
// FileCount returns the number of files in the scanner.
func (s *Scanner) FileCount() int64 {
s.mu.RLock()
defer s.mu.RUnlock()
return int64(len(s.files))
}
// TotalBytes returns the total size of all files in the scanner.
func (s *Scanner) TotalBytes() int64 {
s.mu.RLock()
defer s.mu.RUnlock()
var total int64
for _, f := range s.files {
total += f.Size
}
return total
}
// ToManifest reads all file contents, computes hashes, and generates a manifest.
// If progress is non-nil, status updates are sent approximately once per second.
// The progress channel is closed when the method returns.
// The manifest is written to the provided io.Writer.
func (s *Scanner) ToManifest(ctx context.Context, w io.Writer, progress chan<- ScanStatus) error {
if progress != nil {
defer close(progress)
}
s.mu.RLock()
files := make([]*FileEntry, len(s.files))
copy(files, s.files)
totalFiles := int64(len(files))
var totalBytes int64
for _, f := range files {
totalBytes += f.Size
}
s.mu.RUnlock()
builder := mfer.NewBuilder()
var scannedFiles int64
var scannedBytes int64
lastProgressTime := time.Now()
startTime := time.Now()
for _, entry := range files {
// Check for cancellation
select {
case <-ctx.Done():
return ctx.Err()
default:
}
// Open file
f, err := s.fs.Open(entry.AbsPath)
if err != nil {
return err
}
// Add to manifest with progress callback
bytesRead, err := builder.AddFile(
entry.Path,
entry.Size,
entry.Mtime,
f,
func(fileBytes int64) {
// Send progress at most once per second
now := time.Now()
if progress != nil && now.Sub(lastProgressTime) >= time.Second {
elapsed := now.Sub(startTime).Seconds()
currentBytes := scannedBytes + fileBytes
var rate float64
if elapsed > 0 {
rate = float64(currentBytes) / elapsed
}
sendScanStatus(progress, ScanStatus{
TotalFiles: totalFiles,
ScannedFiles: scannedFiles,
TotalBytes: totalBytes,
ScannedBytes: currentBytes,
BytesPerSec: rate,
})
lastProgressTime = now
}
},
)
f.Close()
if err != nil {
return err
}
scannedFiles++
scannedBytes += bytesRead
}
// Send final progress
if progress != nil {
elapsed := time.Since(startTime).Seconds()
var rate float64
if elapsed > 0 {
rate = float64(scannedBytes) / elapsed
}
sendScanStatus(progress, ScanStatus{
TotalFiles: totalFiles,
ScannedFiles: scannedFiles,
TotalBytes: totalBytes,
ScannedBytes: scannedBytes,
BytesPerSec: rate,
})
}
// Build and write manifest
return builder.Build(w)
}
// pathIsHidden returns true if the path or any of its parent directories
// start with a dot (hidden files/directories).
func pathIsHidden(p string) bool {
tp := path.Clean(p)
if strings.HasPrefix(tp, ".") {
return true
}
for {
d, f := path.Split(tp)
if strings.HasPrefix(f, ".") {
return true
}
if d == "" {
return false
}
tp = d[0 : len(d)-1] // trim trailing slash from dir
}
}
// sendEnumerateStatus sends a status update without blocking.
// If the channel is full, the update is dropped.
func sendEnumerateStatus(ch chan<- EnumerateStatus, status EnumerateStatus) {
if ch == nil {
return
}
select {
case ch <- status:
default:
// Channel full, drop this update
}
}
// sendScanStatus sends a status update without blocking.
// If the channel is full, the update is dropped.
func sendScanStatus(ch chan<- ScanStatus, status ScanStatus) {
if ch == nil {
return
}
select {
case ch <- status:
default:
// Channel full, drop this update
}
}

View File

@@ -3,6 +3,7 @@ package mfer
import (
"crypto/sha256"
"errors"
"fmt"
"io"
"sync"
"time"
@@ -53,6 +54,7 @@ type Builder struct {
mu sync.Mutex
files []*MFFilePath
createdAt time.Time
signingOptions *SigningOptions
}
// NewBuilder creates a new Builder.
@@ -95,6 +97,11 @@ func (b *Builder) AddFile(
}
}
// Verify actual bytes read matches declared size
if totalRead != size {
return totalRead, fmt.Errorf("size mismatch for %q: declared %d bytes but read %d bytes", path, size, totalRead)
}
// Encode hash as multihash (SHA2-256)
mh, err := multihash.Encode(h.Sum(nil), multihash.SHA2_256)
if err != nil {
@@ -165,6 +172,14 @@ func (b *Builder) AddFileWithHash(path RelFilePath, size FileSize, mtime ModTime
return nil
}
// SetSigningOptions sets the GPG signing options for the manifest.
// If opts is non-nil, the manifest will be signed when Build() is called.
func (b *Builder) SetSigningOptions(opts *SigningOptions) {
b.mu.Lock()
defer b.mu.Unlock()
b.signingOptions = opts
}
// Build finalizes the manifest and writes it to the writer.
func (b *Builder) Build(w io.Writer) error {
b.mu.Lock()
@@ -180,6 +195,7 @@ func (b *Builder) Build(w io.Writer) error {
// Create a temporary manifest to use existing serialization
m := &manifest{
pbInner: inner,
signingOptions: b.signingOptions,
}
// Generate outer wrapper

View File

@@ -70,6 +70,10 @@ type Checker struct {
fs afero.Fs
// manifestPaths is a set of paths in the manifest for quick lookup
manifestPaths map[RelFilePath]struct{}
// signature info from the manifest
signature []byte
signer []byte
signingPubKey []byte
}
// NewChecker creates a new Checker for the given manifest, base path, and filesystem.
@@ -101,6 +105,9 @@ func NewChecker(manifestPath string, basePath string, fs afero.Fs) (*Checker, er
files: files,
fs: fs,
manifestPaths: manifestPaths,
signature: m.pbOuter.Signature,
signer: m.pbOuter.Signer,
signingPubKey: m.pbOuter.SigningPubKey,
}, nil
}
@@ -118,6 +125,31 @@ func (c *Checker) TotalBytes() FileSize {
return total
}
// IsSigned returns true if the manifest has a signature.
func (c *Checker) IsSigned() bool {
return len(c.signature) > 0
}
// Signer returns the signer fingerprint if the manifest is signed, nil otherwise.
func (c *Checker) Signer() []byte {
return c.signer
}
// SigningPubKey returns the signing public key if the manifest is signed, nil otherwise.
func (c *Checker) SigningPubKey() []byte {
return c.signingPubKey
}
// ExtractEmbeddedSigningKeyFP imports the manifest's embedded public key into a
// temporary keyring and extracts its fingerprint. This validates the key and
// returns its actual fingerprint from the key material itself.
func (c *Checker) ExtractEmbeddedSigningKeyFP() (string, error) {
if len(c.signingPubKey) == 0 {
return "", errors.New("manifest has no signing public key")
}
return gpgExtractPubKeyFingerprint(c.signingPubKey)
}
// Check verifies all files against the manifest.
// Results are sent to the results channel as files are checked.
// Progress updates are sent to the progress channel approximately once per second.

View File

@@ -2,9 +2,12 @@ package mfer
import (
"bytes"
"crypto/sha256"
"errors"
"fmt"
"io"
"github.com/google/uuid"
"github.com/klauspost/compress/zstd"
"github.com/spf13/afero"
"google.golang.org/protobuf/proto"
@@ -12,6 +15,19 @@ import (
"sneak.berlin/go/mfer/internal/log"
)
// validateUUID checks that the byte slice is a valid UUID (16 bytes, parseable).
func validateUUID(data []byte) error {
if len(data) != 16 {
return errors.New("invalid UUID length")
}
// Try to parse as UUID to validate format
_, err := uuid.FromBytes(data)
if err != nil {
return errors.New("invalid UUID format")
}
return nil
}
func (m *manifest) deserializeInner() error {
if m.pbOuter.Version != MFFileOuter_VERSION_ONE {
return errors.New("unknown version")
@@ -20,6 +36,38 @@ func (m *manifest) deserializeInner() error {
return errors.New("unknown compression type")
}
// Validate outer UUID before any decompression
if err := validateUUID(m.pbOuter.Uuid); err != nil {
return errors.New("outer UUID invalid: " + err.Error())
}
// Verify hash of compressed data before decompression
h := sha256.New()
if _, err := h.Write(m.pbOuter.InnerMessage); err != nil {
return err
}
sha256Hash := h.Sum(nil)
if !bytes.Equal(sha256Hash, m.pbOuter.Sha256) {
return errors.New("compressed data hash mismatch")
}
// Verify signature if present
if len(m.pbOuter.Signature) > 0 {
if len(m.pbOuter.SigningPubKey) == 0 {
return errors.New("signature present but no public key")
}
sigString, err := m.signatureString()
if err != nil {
return fmt.Errorf("failed to generate signature string for verification: %w", err)
}
if err := gpgVerify([]byte(sigString), m.pbOuter.Signature, m.pbOuter.SigningPubKey); err != nil {
return fmt.Errorf("signature verification failed: %w", err)
}
log.Infof("signature verified successfully")
}
bb := bytes.NewBuffer(m.pbOuter.InnerMessage)
zr, err := zstd.NewReader(bb)
@@ -45,6 +93,16 @@ func (m *manifest) deserializeInner() error {
return err
}
// Validate inner UUID
if err := validateUUID(m.pbInner.Uuid); err != nil {
return errors.New("inner UUID invalid: " + err.Error())
}
// Verify UUIDs match
if !bytes.Equal(m.pbOuter.Uuid, m.pbInner.Uuid) {
return errors.New("outer and inner UUID mismatch")
}
log.Infof("loaded manifest with %d files", len(m.pbInner.Files))
return nil
}

212
mfer/gpg.go Normal file
View File

@@ -0,0 +1,212 @@
package mfer
import (
"bytes"
"fmt"
"os"
"os/exec"
"path/filepath"
"strings"
)
// GPGKeyID represents a GPG key identifier (fingerprint or key ID).
type GPGKeyID string
// SigningOptions contains options for GPG signing.
type SigningOptions struct {
KeyID GPGKeyID
}
// gpgSign creates a detached signature of the data using the specified key.
// Returns the armored detached signature.
func gpgSign(data []byte, keyID GPGKeyID) ([]byte, error) {
cmd := exec.Command("gpg",
"--detach-sign",
"--armor",
"--local-user", string(keyID),
)
cmd.Stdin = bytes.NewReader(data)
var stdout, stderr bytes.Buffer
cmd.Stdout = &stdout
cmd.Stderr = &stderr
if err := cmd.Run(); err != nil {
return nil, fmt.Errorf("gpg sign failed: %w: %s", err, stderr.String())
}
return stdout.Bytes(), nil
}
// gpgExportPublicKey exports the public key for the specified key ID.
// Returns the armored public key.
func gpgExportPublicKey(keyID GPGKeyID) ([]byte, error) {
cmd := exec.Command("gpg",
"--export",
"--armor",
string(keyID),
)
var stdout, stderr bytes.Buffer
cmd.Stdout = &stdout
cmd.Stderr = &stderr
if err := cmd.Run(); err != nil {
return nil, fmt.Errorf("gpg export failed: %w: %s", err, stderr.String())
}
if stdout.Len() == 0 {
return nil, fmt.Errorf("gpg key not found: %s", keyID)
}
return stdout.Bytes(), nil
}
// gpgGetKeyFingerprint gets the full fingerprint for a key ID.
func gpgGetKeyFingerprint(keyID GPGKeyID) ([]byte, error) {
cmd := exec.Command("gpg",
"--with-colons",
"--fingerprint",
string(keyID),
)
var stdout, stderr bytes.Buffer
cmd.Stdout = &stdout
cmd.Stderr = &stderr
if err := cmd.Run(); err != nil {
return nil, fmt.Errorf("gpg fingerprint lookup failed: %w: %s", err, stderr.String())
}
// Parse the colon-delimited output to find the fingerprint
lines := strings.Split(stdout.String(), "\n")
for _, line := range lines {
fields := strings.Split(line, ":")
if len(fields) >= 10 && fields[0] == "fpr" {
return []byte(fields[9]), nil
}
}
return nil, fmt.Errorf("fingerprint not found for key: %s", keyID)
}
// gpgExtractPubKeyFingerprint imports a public key into a temporary keyring
// and extracts its fingerprint. This verifies the key is valid and returns
// the actual fingerprint from the key material.
func gpgExtractPubKeyFingerprint(pubKey []byte) (string, error) {
// Create temporary directory for GPG operations
tmpDir, err := os.MkdirTemp("", "mfer-gpg-fingerprint-*")
if err != nil {
return "", fmt.Errorf("failed to create temp dir: %w", err)
}
defer os.RemoveAll(tmpDir)
// Set restrictive permissions
if err := os.Chmod(tmpDir, 0o700); err != nil {
return "", fmt.Errorf("failed to set temp dir permissions: %w", err)
}
// Write public key to temp file
pubKeyFile := filepath.Join(tmpDir, "pubkey.asc")
if err := os.WriteFile(pubKeyFile, pubKey, 0o600); err != nil {
return "", fmt.Errorf("failed to write public key: %w", err)
}
// Import the public key into the temporary keyring
importCmd := exec.Command("gpg",
"--homedir", tmpDir,
"--import",
pubKeyFile,
)
var importStderr bytes.Buffer
importCmd.Stderr = &importStderr
if err := importCmd.Run(); err != nil {
return "", fmt.Errorf("failed to import public key: %w: %s", err, importStderr.String())
}
// List keys to get fingerprint
listCmd := exec.Command("gpg",
"--homedir", tmpDir,
"--with-colons",
"--fingerprint",
)
var listStdout, listStderr bytes.Buffer
listCmd.Stdout = &listStdout
listCmd.Stderr = &listStderr
if err := listCmd.Run(); err != nil {
return "", fmt.Errorf("failed to list keys: %w: %s", err, listStderr.String())
}
// Parse the colon-delimited output to find the fingerprint
lines := strings.Split(listStdout.String(), "\n")
for _, line := range lines {
fields := strings.Split(line, ":")
if len(fields) >= 10 && fields[0] == "fpr" {
return fields[9], nil
}
}
return "", fmt.Errorf("fingerprint not found in imported key")
}
// gpgVerify verifies a detached signature against data using the provided public key.
// It creates a temporary keyring to import the public key for verification.
func gpgVerify(data, signature, pubKey []byte) error {
// Create temporary directory for GPG operations
tmpDir, err := os.MkdirTemp("", "mfer-gpg-verify-*")
if err != nil {
return fmt.Errorf("failed to create temp dir: %w", err)
}
defer os.RemoveAll(tmpDir)
// Set restrictive permissions
if err := os.Chmod(tmpDir, 0o700); err != nil {
return fmt.Errorf("failed to set temp dir permissions: %w", err)
}
// Write public key to temp file
pubKeyFile := filepath.Join(tmpDir, "pubkey.asc")
if err := os.WriteFile(pubKeyFile, pubKey, 0o600); err != nil {
return fmt.Errorf("failed to write public key: %w", err)
}
// Write signature to temp file
sigFile := filepath.Join(tmpDir, "signature.asc")
if err := os.WriteFile(sigFile, signature, 0o600); err != nil {
return fmt.Errorf("failed to write signature: %w", err)
}
// Write data to temp file
dataFile := filepath.Join(tmpDir, "data")
if err := os.WriteFile(dataFile, data, 0o600); err != nil {
return fmt.Errorf("failed to write data: %w", err)
}
// Import the public key into the temporary keyring
importCmd := exec.Command("gpg",
"--homedir", tmpDir,
"--import",
pubKeyFile,
)
var importStderr bytes.Buffer
importCmd.Stderr = &importStderr
if err := importCmd.Run(); err != nil {
return fmt.Errorf("failed to import public key: %w: %s", err, importStderr.String())
}
// Verify the signature
verifyCmd := exec.Command("gpg",
"--homedir", tmpDir,
"--verify",
sigFile,
dataFile,
)
var verifyStderr bytes.Buffer
verifyCmd.Stderr = &verifyStderr
if err := verifyCmd.Run(); err != nil {
return fmt.Errorf("signature verification failed: %w: %s", err, verifyStderr.String())
}
return nil
}

347
mfer/gpg_test.go Normal file
View File

@@ -0,0 +1,347 @@
package mfer
import (
"bytes"
"context"
"os"
"os/exec"
"path/filepath"
"strings"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// testGPGEnv sets up a temporary GPG home directory with a test key.
// Returns the key ID and a cleanup function.
func testGPGEnv(t *testing.T) (GPGKeyID, func()) {
t.Helper()
// Check if gpg is installed
if _, err := exec.LookPath("gpg"); err != nil {
t.Skip("gpg not installed, skipping signing test")
return "", func() {}
}
// Create temporary GPG home directory
gpgHome, err := os.MkdirTemp("", "mfer-gpg-test-*")
require.NoError(t, err)
// Set restrictive permissions on GPG home
require.NoError(t, os.Chmod(gpgHome, 0o700))
// Save original GNUPGHOME and set new one
origGPGHome := os.Getenv("GNUPGHOME")
os.Setenv("GNUPGHOME", gpgHome)
cleanup := func() {
if origGPGHome == "" {
os.Unsetenv("GNUPGHOME")
} else {
os.Setenv("GNUPGHOME", origGPGHome)
}
os.RemoveAll(gpgHome)
}
// Generate a test key with no passphrase
keyParams := `%no-protection
Key-Type: RSA
Key-Length: 2048
Name-Real: MFER Test Key
Name-Email: test@mfer.test
Expire-Date: 0
%commit
`
paramsFile := filepath.Join(gpgHome, "key-params")
require.NoError(t, os.WriteFile(paramsFile, []byte(keyParams), 0o600))
cmd := exec.Command("gpg", "--batch", "--gen-key", paramsFile)
cmd.Env = append(os.Environ(), "GNUPGHOME="+gpgHome)
output, err := cmd.CombinedOutput()
if err != nil {
cleanup()
t.Skipf("failed to generate test GPG key: %v: %s", err, output)
return "", func() {}
}
// Get the key fingerprint
cmd = exec.Command("gpg", "--list-keys", "--with-colons", "test@mfer.test")
cmd.Env = append(os.Environ(), "GNUPGHOME="+gpgHome)
output, err = cmd.Output()
if err != nil {
cleanup()
t.Fatalf("failed to list test key: %v", err)
}
// Parse fingerprint from output
var keyID string
for _, line := range strings.Split(string(output), "\n") {
fields := strings.Split(line, ":")
if len(fields) >= 10 && fields[0] == "fpr" {
keyID = fields[9]
break
}
}
if keyID == "" {
cleanup()
t.Fatal("failed to find test key fingerprint")
}
return GPGKeyID(keyID), cleanup
}
func TestGPGSign(t *testing.T) {
keyID, cleanup := testGPGEnv(t)
defer cleanup()
data := []byte("test data to sign")
sig, err := gpgSign(data, keyID)
require.NoError(t, err)
assert.NotEmpty(t, sig)
assert.Contains(t, string(sig), "-----BEGIN PGP SIGNATURE-----")
assert.Contains(t, string(sig), "-----END PGP SIGNATURE-----")
}
func TestGPGExportPublicKey(t *testing.T) {
keyID, cleanup := testGPGEnv(t)
defer cleanup()
pubKey, err := gpgExportPublicKey(keyID)
require.NoError(t, err)
assert.NotEmpty(t, pubKey)
assert.Contains(t, string(pubKey), "-----BEGIN PGP PUBLIC KEY BLOCK-----")
assert.Contains(t, string(pubKey), "-----END PGP PUBLIC KEY BLOCK-----")
}
func TestGPGGetKeyFingerprint(t *testing.T) {
keyID, cleanup := testGPGEnv(t)
defer cleanup()
fingerprint, err := gpgGetKeyFingerprint(keyID)
require.NoError(t, err)
assert.NotEmpty(t, fingerprint)
// The fingerprint should be 40 hex chars
assert.Len(t, fingerprint, 40, "fingerprint should be 40 hex chars")
}
func TestGPGSignInvalidKey(t *testing.T) {
// Set up test environment (we need GNUPGHOME set)
_, cleanup := testGPGEnv(t)
defer cleanup()
data := []byte("test data")
_, err := gpgSign(data, GPGKeyID("NONEXISTENT_KEY_ID_12345"))
assert.Error(t, err)
}
func TestBuilderWithSigning(t *testing.T) {
keyID, cleanup := testGPGEnv(t)
defer cleanup()
// Create a builder with signing options
b := NewBuilder()
b.SetSigningOptions(&SigningOptions{
KeyID: keyID,
})
// Add a test file
content := []byte("test file content")
reader := bytes.NewReader(content)
_, err := b.AddFile("test.txt", FileSize(len(content)), ModTime{}, reader, nil)
require.NoError(t, err)
// Build the manifest
var buf bytes.Buffer
err = b.Build(&buf)
require.NoError(t, err)
// Parse the manifest and verify signature fields are populated
manifest, err := NewManifestFromReader(&buf)
require.NoError(t, err)
require.NotNil(t, manifest.pbOuter)
assert.NotEmpty(t, manifest.pbOuter.Signature, "signature should be populated")
assert.NotEmpty(t, manifest.pbOuter.Signer, "signer should be populated")
assert.NotEmpty(t, manifest.pbOuter.SigningPubKey, "signing public key should be populated")
// Verify signature is a valid PGP signature
assert.Contains(t, string(manifest.pbOuter.Signature), "-----BEGIN PGP SIGNATURE-----")
// Verify public key is a valid PGP public key block
assert.Contains(t, string(manifest.pbOuter.SigningPubKey), "-----BEGIN PGP PUBLIC KEY BLOCK-----")
}
func TestScannerWithSigning(t *testing.T) {
keyID, cleanup := testGPGEnv(t)
defer cleanup()
// Create in-memory filesystem with test files
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("content1"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("content2"), 0o644))
// Create scanner with signing options
opts := &ScannerOptions{
Fs: fs,
SigningOptions: &SigningOptions{
KeyID: keyID,
},
}
s := NewScannerWithOptions(opts)
// Enumerate files
require.NoError(t, s.EnumeratePath("/testdir", nil))
assert.Equal(t, FileCount(2), s.FileCount())
// Generate signed manifest
var buf bytes.Buffer
require.NoError(t, s.ToManifest(context.Background(), &buf, nil))
// Parse and verify
manifest, err := NewManifestFromReader(&buf)
require.NoError(t, err)
assert.NotEmpty(t, manifest.pbOuter.Signature)
assert.NotEmpty(t, manifest.pbOuter.Signer)
assert.NotEmpty(t, manifest.pbOuter.SigningPubKey)
}
func TestGPGVerify(t *testing.T) {
keyID, cleanup := testGPGEnv(t)
defer cleanup()
data := []byte("test data to sign and verify")
sig, err := gpgSign(data, keyID)
require.NoError(t, err)
pubKey, err := gpgExportPublicKey(keyID)
require.NoError(t, err)
// Verify the signature
err = gpgVerify(data, sig, pubKey)
require.NoError(t, err)
}
func TestGPGVerifyInvalidSignature(t *testing.T) {
keyID, cleanup := testGPGEnv(t)
defer cleanup()
data := []byte("test data to sign")
sig, err := gpgSign(data, keyID)
require.NoError(t, err)
pubKey, err := gpgExportPublicKey(keyID)
require.NoError(t, err)
// Try to verify with different data - should fail
wrongData := []byte("different data")
err = gpgVerify(wrongData, sig, pubKey)
assert.Error(t, err)
}
func TestGPGVerifyBadPublicKey(t *testing.T) {
keyID, cleanup := testGPGEnv(t)
defer cleanup()
data := []byte("test data")
sig, err := gpgSign(data, keyID)
require.NoError(t, err)
// Try to verify with invalid public key - should fail
badPubKey := []byte("not a valid public key")
err = gpgVerify(data, sig, badPubKey)
assert.Error(t, err)
}
func TestManifestSignatureVerification(t *testing.T) {
keyID, cleanup := testGPGEnv(t)
defer cleanup()
// Create a builder with signing options
b := NewBuilder()
b.SetSigningOptions(&SigningOptions{
KeyID: keyID,
})
// Add a test file
content := []byte("test file content for verification")
reader := bytes.NewReader(content)
_, err := b.AddFile("test.txt", FileSize(len(content)), ModTime{}, reader, nil)
require.NoError(t, err)
// Build the manifest
var buf bytes.Buffer
err = b.Build(&buf)
require.NoError(t, err)
// Parse the manifest - signature should be verified during load
manifest, err := NewManifestFromReader(&buf)
require.NoError(t, err)
require.NotNil(t, manifest)
// Signature should be present and valid
assert.NotEmpty(t, manifest.pbOuter.Signature)
}
func TestManifestTamperedSignatureFails(t *testing.T) {
keyID, cleanup := testGPGEnv(t)
defer cleanup()
// Create a signed manifest
b := NewBuilder()
b.SetSigningOptions(&SigningOptions{
KeyID: keyID,
})
content := []byte("test file content")
reader := bytes.NewReader(content)
_, err := b.AddFile("test.txt", FileSize(len(content)), ModTime{}, reader, nil)
require.NoError(t, err)
var buf bytes.Buffer
err = b.Build(&buf)
require.NoError(t, err)
// Tamper with the signature by replacing some bytes
data := buf.Bytes()
// Find and modify a byte in the signature portion
for i := range data {
if i > 100 && data[i] == 'A' {
data[i] = 'B'
break
}
}
// Try to load the tampered manifest - should fail
_, err = NewManifestFromReader(bytes.NewReader(data))
assert.Error(t, err)
}
func TestBuilderWithoutSigning(t *testing.T) {
// Create a builder without signing options
b := NewBuilder()
// Add a test file
content := []byte("test file content")
reader := bytes.NewReader(content)
_, err := b.AddFile("test.txt", FileSize(len(content)), ModTime{}, reader, nil)
require.NoError(t, err)
// Build the manifest
var buf bytes.Buffer
err = b.Build(&buf)
require.NoError(t, err)
// Parse the manifest and verify signature fields are empty
manifest, err := NewManifestFromReader(&buf)
require.NoError(t, err)
require.NotNil(t, manifest.pbOuter)
assert.Empty(t, manifest.pbOuter.Signature, "signature should be empty when not signing")
assert.Empty(t, manifest.pbOuter.Signer, "signer should be empty when not signing")
assert.Empty(t, manifest.pbOuter.SigningPubKey, "signing public key should be empty when not signing")
}

View File

@@ -2,7 +2,11 @@ package mfer
import (
"bytes"
"encoding/hex"
"errors"
"fmt"
"github.com/multiformats/go-multihash"
)
// manifest holds the internal representation of a manifest file.
@@ -12,6 +16,7 @@ type manifest struct {
pbInner *MFFile
pbOuter *MFFileOuter
output *bytes.Buffer
signingOptions *SigningOptions
}
func (m *manifest) String() string {
@@ -29,3 +34,26 @@ func (m *manifest) Files() []*MFFilePath {
}
return m.pbInner.Files
}
// signatureString generates the canonical string used for signing/verification.
// Format: MAGIC-UUID-MULTIHASH where UUID and multihash are hex-encoded.
// Requires pbOuter to be set with Uuid and Sha256 fields.
func (m *manifest) signatureString() (string, error) {
if m.pbOuter == nil {
return "", errors.New("pbOuter not set")
}
if len(m.pbOuter.Uuid) == 0 {
return "", errors.New("UUID not set")
}
if len(m.pbOuter.Sha256) == 0 {
return "", errors.New("SHA256 hash not set")
}
mh, err := multihash.Encode(m.pbOuter.Sha256, multihash.SHA2_256)
if err != nil {
return "", fmt.Errorf("failed to encode multihash: %w", err)
}
uuidStr := hex.EncodeToString(m.pbOuter.Uuid)
mhStr := hex.EncodeToString(mh)
return fmt.Sprintf("%s-%s-%s", MAGIC, uuidStr, mhStr), nil
}

View File

@@ -220,6 +220,8 @@ type MFFileOuter struct {
// and not for cryptographic integrity.
Size int64 `protobuf:"varint,103,opt,name=size,proto3" json:"size,omitempty"`
Sha256 []byte `protobuf:"bytes,104,opt,name=sha256,proto3" json:"sha256,omitempty"`
// uuid must match the uuid in the inner message
Uuid []byte `protobuf:"bytes,105,opt,name=uuid,proto3" json:"uuid,omitempty"`
InnerMessage []byte `protobuf:"bytes,199,opt,name=innerMessage,proto3" json:"innerMessage,omitempty"`
// detached signature, ascii or binary
Signature []byte `protobuf:"bytes,201,opt,name=signature,proto3,oneof" json:"signature,omitempty"`
@@ -289,6 +291,13 @@ func (x *MFFileOuter) GetSha256() []byte {
return nil
}
func (x *MFFileOuter) GetUuid() []byte {
if x != nil {
return x.Uuid
}
return nil
}
func (x *MFFileOuter) GetInnerMessage() []byte {
if x != nil {
return x.InnerMessage
@@ -463,6 +472,9 @@ type MFFile struct {
Version MFFile_Version `protobuf:"varint,100,opt,name=version,proto3,enum=MFFile_Version" json:"version,omitempty"`
// required manifest attributes:
Files []*MFFilePath `protobuf:"bytes,101,rep,name=files,proto3" json:"files,omitempty"`
// uuid is a random v4 UUID generated when creating the manifest
// used as part of the signature to prevent replay attacks
Uuid []byte `protobuf:"bytes,102,opt,name=uuid,proto3" json:"uuid,omitempty"`
// optional manifest attributes 2xx:
CreatedAt *Timestamp `protobuf:"bytes,201,opt,name=createdAt,proto3,oneof" json:"createdAt,omitempty"`
unknownFields protoimpl.UnknownFields
@@ -513,6 +525,13 @@ func (x *MFFile) GetFiles() []*MFFilePath {
return nil
}
func (x *MFFile) GetUuid() []byte {
if x != nil {
return x.Uuid
}
return nil
}
func (x *MFFile) GetCreatedAt() *Timestamp {
if x != nil {
return x.CreatedAt
@@ -527,12 +546,13 @@ const file_mf_proto_rawDesc = "" +
"\bmf.proto\";\n" +
"\tTimestamp\x12\x18\n" +
"\aseconds\x18\x01 \x01(\x03R\aseconds\x12\x14\n" +
"\x05nanos\x18\x02 \x01(\x05R\x05nanos\"\xdc\x03\n" +
"\x05nanos\x18\x02 \x01(\x05R\x05nanos\"\xf0\x03\n" +
"\vMFFileOuter\x12.\n" +
"\aversion\x18e \x01(\x0e2\x14.MFFileOuter.VersionR\aversion\x12F\n" +
"\x0fcompressionType\x18f \x01(\x0e2\x1c.MFFileOuter.CompressionTypeR\x0fcompressionType\x12\x12\n" +
"\x04size\x18g \x01(\x03R\x04size\x12\x16\n" +
"\x06sha256\x18h \x01(\fR\x06sha256\x12#\n" +
"\x06sha256\x18h \x01(\fR\x06sha256\x12\x12\n" +
"\x04uuid\x18i \x01(\fR\x04uuid\x12#\n" +
"\finnerMessage\x18\xc7\x01 \x01(\fR\finnerMessage\x12\"\n" +
"\tsignature\x18\xc9\x01 \x01(\fH\x00R\tsignature\x88\x01\x01\x12\x1c\n" +
"\x06signer\x18\xca\x01 \x01(\fH\x01R\x06signer\x88\x01\x01\x12*\n" +
@@ -564,10 +584,11 @@ const file_mf_proto_rawDesc = "" +
"\x06_ctimeB\b\n" +
"\x06_atime\".\n" +
"\x0eMFFileChecksum\x12\x1c\n" +
"\tmultiHash\x18\x01 \x01(\fR\tmultiHash\"\xc2\x01\n" +
"\tmultiHash\x18\x01 \x01(\fR\tmultiHash\"\xd6\x01\n" +
"\x06MFFile\x12)\n" +
"\aversion\x18d \x01(\x0e2\x0f.MFFile.VersionR\aversion\x12!\n" +
"\x05files\x18e \x03(\v2\v.MFFilePathR\x05files\x12.\n" +
"\x05files\x18e \x03(\v2\v.MFFilePathR\x05files\x12\x12\n" +
"\x04uuid\x18f \x01(\fR\x04uuid\x12.\n" +
"\tcreatedAt\x18\xc9\x01 \x01(\v2\n" +
".TimestampH\x00R\tcreatedAt\x88\x01\x01\",\n" +
"\aVersion\x12\x10\n" +

View File

@@ -28,6 +28,9 @@ message MFFileOuter {
int64 size = 103;
bytes sha256 = 104;
// uuid must match the uuid in the inner message
bytes uuid = 105;
bytes innerMessage = 199;
// 2xx for optional manifest root attributes
// think we might use gosignify instead of gpg:
@@ -72,6 +75,10 @@ message MFFile {
// required manifest attributes:
repeated MFFilePath files = 101;
// uuid is a random v4 UUID generated when creating the manifest
// used as part of the signature to prevent replay attacks
bytes uuid = 102;
// optional manifest attributes 2xx:
optional Timestamp createdAt = 201;
}

View File

@@ -46,6 +46,7 @@ type ScannerOptions struct {
IncludeDotfiles bool // Include files and directories starting with a dot (default: exclude)
FollowSymLinks bool // Resolve symlinks instead of skipping them
Fs afero.Fs // Filesystem to use, defaults to OsFs if nil
SigningOptions *SigningOptions // GPG signing options (nil = no signing)
}
// FileEntry represents a file that has been enumerated.
@@ -272,6 +273,9 @@ func (s *Scanner) ToManifest(ctx context.Context, w io.Writer, progress chan<- S
s.mu.RUnlock()
builder := NewBuilder()
if s.options.SigningOptions != nil {
builder.SetSigningOptions(s.options.SigningOptions)
}
var scannedFiles FileCount
var scannedBytes FileSize

View File

@@ -38,7 +38,7 @@ func TestNewScannerWithOptions(t *testing.T) {
func TestScannerEnumerateFile(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, afero.WriteFile(fs, "/test.txt", []byte("hello world"), 0644))
require.NoError(t, afero.WriteFile(fs, "/test.txt", []byte("hello world"), 0o644))
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})
err := s.EnumerateFile("/test.txt")
@@ -62,10 +62,10 @@ func TestScannerEnumerateFileMissing(t *testing.T) {
func TestScannerEnumeratePath(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir/subdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("one"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("two"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/subdir/file3.txt", []byte("three"), 0644))
require.NoError(t, fs.MkdirAll("/testdir/subdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("one"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("two"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/subdir/file3.txt", []byte("three"), 0o644))
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})
err := s.EnumeratePath("/testdir", nil)
@@ -77,9 +77,9 @@ func TestScannerEnumeratePath(t *testing.T) {
func TestScannerEnumeratePathWithProgress(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("one"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("two"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("one"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("two"), 0o644))
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})
progress := make(chan EnumerateStatus, 10)
@@ -101,10 +101,10 @@ func TestScannerEnumeratePathWithProgress(t *testing.T) {
func TestScannerEnumeratePaths(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/dir1", 0755))
require.NoError(t, fs.MkdirAll("/dir2", 0755))
require.NoError(t, afero.WriteFile(fs, "/dir1/a.txt", []byte("aaa"), 0644))
require.NoError(t, afero.WriteFile(fs, "/dir2/b.txt", []byte("bbb"), 0644))
require.NoError(t, fs.MkdirAll("/dir1", 0o755))
require.NoError(t, fs.MkdirAll("/dir2", 0o755))
require.NoError(t, afero.WriteFile(fs, "/dir1/a.txt", []byte("aaa"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/dir2/b.txt", []byte("bbb"), 0o644))
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})
err := s.EnumeratePaths(nil, "/dir1", "/dir2")
@@ -115,10 +115,10 @@ func TestScannerEnumeratePaths(t *testing.T) {
func TestScannerExcludeDotfiles(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir/.hidden", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/visible.txt", []byte("visible"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/.hidden.txt", []byte("hidden"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/.hidden/inside.txt", []byte("inside"), 0644))
require.NoError(t, fs.MkdirAll("/testdir/.hidden", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/visible.txt", []byte("visible"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/.hidden.txt", []byte("hidden"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/.hidden/inside.txt", []byte("inside"), 0o644))
t.Run("exclude by default", func(t *testing.T) {
s := NewScannerWithOptions(&ScannerOptions{Fs: fs, IncludeDotfiles: false})
@@ -141,9 +141,9 @@ func TestScannerExcludeDotfiles(t *testing.T) {
func TestScannerToManifest(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("content one"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("content two"), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file1.txt", []byte("content one"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/file2.txt", []byte("content two"), 0o644))
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})
err := s.EnumeratePath("/testdir", nil)
@@ -160,8 +160,8 @@ func TestScannerToManifest(t *testing.T) {
func TestScannerToManifestWithProgress(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file.txt", bytes.Repeat([]byte("x"), 1000), 0644))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file.txt", bytes.Repeat([]byte("x"), 1000), 0o644))
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})
err := s.EnumeratePath("/testdir", nil)
@@ -189,11 +189,11 @@ func TestScannerToManifestWithProgress(t *testing.T) {
func TestScannerToManifestContextCancellation(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
// Create many files to ensure we have time to cancel
for i := 0; i < 100; i++ {
name := string(rune('a'+i%26)) + string(rune('0'+i/26)) + ".txt"
require.NoError(t, afero.WriteFile(fs, "/testdir/"+name, bytes.Repeat([]byte("x"), 100), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/"+name, bytes.Repeat([]byte("x"), 100), 0o644))
}
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})
@@ -223,7 +223,7 @@ func TestScannerToManifestEmptyScanner(t *testing.T) {
func TestScannerFilesCopiesSlice(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, afero.WriteFile(fs, "/test.txt", []byte("hello"), 0644))
require.NoError(t, afero.WriteFile(fs, "/test.txt", []byte("hello"), 0o644))
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})
require.NoError(t, s.EnumerateFile("/test.txt"))
@@ -237,9 +237,9 @@ func TestScannerFilesCopiesSlice(t *testing.T) {
func TestScannerEnumerateFS(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir/sub", 0755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file.txt", []byte("hello"), 0644))
require.NoError(t, afero.WriteFile(fs, "/testdir/sub/nested.txt", []byte("world"), 0644))
require.NoError(t, fs.MkdirAll("/testdir/sub", 0o755))
require.NoError(t, afero.WriteFile(fs, "/testdir/file.txt", []byte("hello"), 0o644))
require.NoError(t, afero.WriteFile(fs, "/testdir/sub/nested.txt", []byte("world"), 0o644))
// Create a basepath filesystem
baseFs := afero.NewBasePathFs(fs, "/testdir")
@@ -297,7 +297,7 @@ func TestSendStatusNilChannel(t *testing.T) {
func TestScannerFileEntryFields(t *testing.T) {
fs := afero.NewMemMapFs()
now := time.Now().Truncate(time.Second)
require.NoError(t, afero.WriteFile(fs, "/test.txt", []byte("content"), 0644))
require.NoError(t, afero.WriteFile(fs, "/test.txt", []byte("content"), 0o644))
require.NoError(t, fs.Chtimes("/test.txt", now, now))
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})
@@ -316,12 +316,12 @@ func TestScannerFileEntryFields(t *testing.T) {
func TestScannerLargeFileEnumeration(t *testing.T) {
fs := afero.NewMemMapFs()
require.NoError(t, fs.MkdirAll("/testdir", 0755))
require.NoError(t, fs.MkdirAll("/testdir", 0o755))
// Create 100 files
for i := 0; i < 100; i++ {
name := "/testdir/" + string(rune('a'+i%26)) + string(rune('0'+i/26%10)) + ".txt"
require.NoError(t, afero.WriteFile(fs, name, []byte("data"), 0644))
require.NoError(t, afero.WriteFile(fs, name, []byte("data"), 0o644))
}
s := NewScannerWithOptions(&ScannerOptions{Fs: fs})

View File

@@ -4,8 +4,10 @@ import (
"bytes"
"crypto/sha256"
"errors"
"fmt"
"time"
"github.com/google/uuid"
"github.com/klauspost/compress/zstd"
"google.golang.org/protobuf/proto"
)
@@ -47,14 +49,17 @@ func (m *manifest) generateOuter() error {
if m.pbInner == nil {
return errors.New("internal error")
}
// Generate UUID and set on inner message
manifestUUID := uuid.New()
m.pbInner.Uuid = manifestUUID[:]
innerData, err := proto.MarshalOptions{Deterministic: true}.Marshal(m.pbInner)
if err != nil {
return err
}
h := sha256.New()
h.Write(innerData)
// Compress the inner data
idc := new(bytes.Buffer)
zw, err := zstd.NewWriter(idc, zstd.WithEncoderLevel(zstd.SpeedBestCompression))
if err != nil {
@@ -64,16 +69,51 @@ func (m *manifest) generateOuter() error {
if err != nil {
return err
}
_ = zw.Close()
o := &MFFileOuter{
InnerMessage: idc.Bytes(),
compressedData := idc.Bytes()
// Hash the compressed data for integrity verification before decompression
h := sha256.New()
if _, err := h.Write(compressedData); err != nil {
return err
}
sha256Hash := h.Sum(nil)
m.pbOuter = &MFFileOuter{
InnerMessage: compressedData,
Size: int64(len(innerData)),
Sha256: h.Sum(nil),
Sha256: sha256Hash,
Uuid: manifestUUID[:],
Version: MFFileOuter_VERSION_ONE,
CompressionType: MFFileOuter_COMPRESSION_ZSTD,
}
m.pbOuter = o
// Sign the manifest if signing options are provided
if m.signingOptions != nil && m.signingOptions.KeyID != "" {
sigString, err := m.signatureString()
if err != nil {
return fmt.Errorf("failed to generate signature string: %w", err)
}
sig, err := gpgSign([]byte(sigString), m.signingOptions.KeyID)
if err != nil {
return fmt.Errorf("failed to sign manifest: %w", err)
}
m.pbOuter.Signature = sig
fingerprint, err := gpgGetKeyFingerprint(m.signingOptions.KeyID)
if err != nil {
return fmt.Errorf("failed to get key fingerprint: %w", err)
}
m.pbOuter.Signer = fingerprint
pubKey, err := gpgExportPublicKey(m.signingOptions.KeyID)
if err != nil {
return fmt.Errorf("failed to export public key: %w", err)
}
m.pbOuter.SigningPubKey = pubKey
}
return nil
}