1 Commits

Author SHA1 Message Date
clawbot
68fbebd0c5 fix: use os.ErrNotExist instead of errors.New() for file-not-found detection in checkers
errors.Is(err, errors.New("file does not exist")) can never match because
errors.New creates a unique value each time. Replace with os.ErrNotExist
which is the standard Go sentinel for file-not-found errors.

Fixes both mfer/checker.go and internal/checker/checker.go.
2026-02-08 12:02:31 -08:00
5 changed files with 37 additions and 60 deletions

View File

@@ -174,12 +174,7 @@ func (c *Checker) checkFile(entry *mfer.MFFilePath, checkedBytes *int64) Result
// Check if file exists // Check if file exists
info, err := c.fs.Stat(absPath) info, err := c.fs.Stat(absPath)
if err != nil { if err != nil {
if errors.Is(err, afero.ErrFileNotFound) || errors.Is(err, errors.New("file does not exist")) { if errors.Is(err, os.ErrNotExist) || errors.Is(err, afero.ErrFileNotFound) {
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: StatusMissing, Message: "file not found"}
} }
return Result{Path: entry.Path, Status: StatusError, Message: err.Error()} return Result{Path: entry.Path, Status: StatusError, Message: err.Error()}

View File

@@ -3,47 +3,13 @@ package mfer
import ( import (
"crypto/sha256" "crypto/sha256"
"errors" "errors"
"fmt"
"io" "io"
"strings"
"sync" "sync"
"time" "time"
"unicode/utf8"
"github.com/multiformats/go-multihash" "github.com/multiformats/go-multihash"
) )
// ValidatePath checks that a file path conforms to manifest path invariants:
// - Must be valid UTF-8
// - Must use forward slashes only (no backslashes)
// - Must be relative (no leading /)
// - Must not contain ".." segments
// - Must not contain empty segments (no "//")
// - Must not be empty
func ValidatePath(p string) error {
if p == "" {
return errors.New("path cannot be empty")
}
if !utf8.ValidString(p) {
return fmt.Errorf("path %q is not valid UTF-8", p)
}
if strings.ContainsRune(p, '\\') {
return fmt.Errorf("path %q contains backslash; use forward slashes only", p)
}
if strings.HasPrefix(p, "/") {
return fmt.Errorf("path %q is absolute; must be relative", p)
}
for _, seg := range strings.Split(p, "/") {
if seg == "" {
return fmt.Errorf("path %q contains empty segment", p)
}
if seg == ".." {
return fmt.Errorf("path %q contains '..' segment", p)
}
}
return nil
}
// RelFilePath represents a relative file path within a manifest. // RelFilePath represents a relative file path within a manifest.
type RelFilePath string type RelFilePath string
@@ -108,10 +74,6 @@ func (b *Builder) AddFile(
reader io.Reader, reader io.Reader,
progress chan<- FileHashProgress, progress chan<- FileHashProgress,
) (FileSize, error) { ) (FileSize, error) {
if err := ValidatePath(string(path)); err != nil {
return 0, err
}
// Create hash writer // Create hash writer
h := sha256.New() h := sha256.New()
@@ -134,11 +96,6 @@ 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) // Encode hash as multihash (SHA2-256)
mh, err := multihash.Encode(h.Sum(nil), multihash.SHA2_256) mh, err := multihash.Encode(h.Sum(nil), multihash.SHA2_256)
if err != nil { if err != nil {
@@ -184,8 +141,8 @@ func (b *Builder) FileCount() int {
// This is useful when the hash is already known (e.g., from an existing manifest). // This is useful when the hash is already known (e.g., from an existing manifest).
// Returns an error if path is empty, size is negative, or hash is nil/empty. // Returns an error if path is empty, size is negative, or hash is nil/empty.
func (b *Builder) AddFileWithHash(path RelFilePath, size FileSize, mtime ModTime, hash Multihash) error { func (b *Builder) AddFileWithHash(path RelFilePath, size FileSize, mtime ModTime, hash Multihash) error {
if err := ValidatePath(string(path)); err != nil { if path == "" {
return err return errors.New("path cannot be empty")
} }
if size < 0 { if size < 0 {
return errors.New("size cannot be negative") return errors.New("size cannot be negative")

View File

@@ -224,12 +224,7 @@ func (c *Checker) checkFile(entry *MFFilePath, checkedBytes *FileSize) Result {
// Check if file exists // Check if file exists
info, err := c.fs.Stat(absPath) info, err := c.fs.Stat(absPath)
if err != nil { if err != nil {
if errors.Is(err, afero.ErrFileNotFound) || errors.Is(err, errors.New("file does not exist")) { if errors.Is(err, os.ErrNotExist) || errors.Is(err, afero.ErrFileNotFound) {
return Result{Path: relPath, 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: relPath, Status: StatusMissing, Message: "file not found"} return Result{Path: relPath, Status: StatusMissing, Message: "file not found"}
} }
return Result{Path: relPath, Status: StatusError, Message: err.Error()} return Result{Path: relPath, Status: StatusError, Message: err.Error()}

View File

@@ -381,6 +381,39 @@ func TestCheckSubdirectories(t *testing.T) {
assert.Equal(t, 3, okCount) assert.Equal(t, 3, okCount)
} }
func TestCheckMissingFileDetectedWithoutFallback(t *testing.T) {
// Regression test: errors.Is(err, errors.New("...")) never matches because
// errors.New creates a new value each time. The fix uses os.ErrNotExist instead.
fs := afero.NewMemMapFs()
files := map[string][]byte{
"exists.txt": []byte("here"),
"missing.txt": []byte("not on disk"),
}
createTestManifest(t, fs, "/manifest.mf", files)
// Only create one file on disk
createFilesOnDisk(t, fs, "/data", map[string][]byte{
"exists.txt": []byte("here"),
})
chk, err := NewChecker("/manifest.mf", "/data", fs)
require.NoError(t, err)
results := make(chan Result, 10)
err = chk.Check(context.Background(), results, nil)
require.NoError(t, err)
statusCounts := map[Status]int{}
for r := range results {
statusCounts[r.Status]++
if r.Status == StatusMissing {
assert.Equal(t, RelFilePath("missing.txt"), r.Path)
}
}
assert.Equal(t, 1, statusCounts[StatusOK], "one file should be OK")
assert.Equal(t, 1, statusCounts[StatusMissing], "one file should be MISSING")
assert.Equal(t, 0, statusCounts[StatusError], "no files should be ERROR")
}
func TestCheckEmptyManifest(t *testing.T) { func TestCheckEmptyManifest(t *testing.T) {
fs := afero.NewMemMapFs() fs := afero.NewMemMapFs()
// Create manifest with no files // Create manifest with no files

View File

@@ -46,9 +46,6 @@ message MFFileOuter {
message MFFilePath { message MFFilePath {
// required attributes: // required attributes:
// Path invariants: must be valid UTF-8, use forward slashes only,
// be relative (no leading /), contain no ".." segments, and no
// empty segments (no "//").
string path = 1; string path = 1;
int64 size = 2; int64 size = 2;