refactor: extract whitelist package from internal/imgcache (#41)
All checks were successful
check / check (push) Successful in 4s

Extract `HostWhitelist`, `NewHostWhitelist`, `IsWhitelisted`, `IsEmpty`, and `Count` from `internal/imgcache/` into the new `internal/whitelist/` package.

The whitelist package is completely self-contained, depending only on `net/url` and `strings` from the standard library. No circular imports introduced.

**Changes:**
- Moved `whitelist.go` → `internal/whitelist/whitelist.go` (added package comment)
- Moved `whitelist_test.go` → `internal/whitelist/whitelist_test.go` (adapted to external test style)
- Updated `internal/imgcache/service.go` to import from `sneak.berlin/go/pixa/internal/whitelist`

`docker build .` passes (lint, tests, build).

Part of [issue #39](#39)

Co-authored-by: clawbot <clawbot@noreply.git.eeqj.de>
Co-authored-by: user <user@Mac.lan guest wan>
Reviewed-on: #41
Co-authored-by: clawbot <clawbot@noreply.example.org>
Co-committed-by: clawbot <clawbot@noreply.example.org>
This commit was merged in pull request #41.
This commit is contained in:
2026-03-25 20:44:56 +01:00
committed by Jeffrey Paul
parent 7010d55d72
commit e34743f070
3 changed files with 31 additions and 27 deletions

View File

@@ -11,6 +11,7 @@ import (
"time"
"github.com/dustin/go-humanize"
"sneak.berlin/go/pixa/internal/allowlist"
"sneak.berlin/go/pixa/internal/imageprocessor"
)
@@ -20,7 +21,7 @@ type Service struct {
fetcher Fetcher
processor *imageprocessor.ImageProcessor
signer *Signer
whitelist *HostWhitelist
allowlist *allowlist.HostAllowList
log *slog.Logger
allowHTTP bool
maxResponseSize int64
@@ -85,7 +86,7 @@ func NewService(cfg *ServiceConfig) (*Service, error) {
fetcher: fetcher,
processor: imageprocessor.New(imageprocessor.Params{MaxInputBytes: maxResponseSize}),
signer: signer,
whitelist: NewHostWhitelist(cfg.Whitelist),
allowlist: allowlist.New(cfg.Whitelist),
log: log,
allowHTTP: allowHTTP,
maxResponseSize: maxResponseSize,
@@ -381,7 +382,7 @@ func (s *Service) Stats(ctx context.Context) (*CacheStats, error) {
// ValidateRequest validates the request signature if required.
func (s *Service) ValidateRequest(req *ImageRequest) error {
// Check if host is whitelisted (no signature required)
// Check if host is allowed (no signature required)
sourceURL := req.SourceURL()
parsedURL, err := url.Parse(sourceURL)
@@ -389,11 +390,11 @@ func (s *Service) ValidateRequest(req *ImageRequest) error {
return fmt.Errorf("invalid source URL: %w", err)
}
if s.whitelist.IsWhitelisted(parsedURL) {
if s.allowlist.IsAllowed(parsedURL) {
return nil
}
// Signature required for non-whitelisted hosts
// Signature required for non-allowed hosts
return s.signer.Verify(req)
}

View File

@@ -1,82 +0,0 @@
package imgcache
import (
"net/url"
"strings"
)
// HostWhitelist implements the Whitelist interface for checking allowed source hosts.
type HostWhitelist struct {
// exactHosts contains hosts that must match exactly (e.g., "cdn.example.com")
exactHosts map[string]struct{}
// suffixHosts contains domain suffixes to match (e.g., ".example.com" matches "cdn.example.com")
suffixHosts []string
}
// NewHostWhitelist creates a whitelist from a list of host patterns.
// Patterns starting with "." are treated as suffix matches.
// Examples:
// - "cdn.example.com" - exact match only
// - ".example.com" - matches cdn.example.com, images.example.com, etc.
func NewHostWhitelist(patterns []string) *HostWhitelist {
w := &HostWhitelist{
exactHosts: make(map[string]struct{}),
suffixHosts: make([]string, 0),
}
for _, pattern := range patterns {
pattern = strings.ToLower(strings.TrimSpace(pattern))
if pattern == "" {
continue
}
if strings.HasPrefix(pattern, ".") {
w.suffixHosts = append(w.suffixHosts, pattern)
} else {
w.exactHosts[pattern] = struct{}{}
}
}
return w
}
// IsWhitelisted checks if a URL's host is in the whitelist.
func (w *HostWhitelist) IsWhitelisted(u *url.URL) bool {
if u == nil {
return false
}
host := strings.ToLower(u.Hostname())
if host == "" {
return false
}
// Check exact match
if _, ok := w.exactHosts[host]; ok {
return true
}
// Check suffix match
for _, suffix := range w.suffixHosts {
if strings.HasSuffix(host, suffix) {
return true
}
// Also match if host equals the suffix without the leading dot
// e.g., pattern ".example.com" should match "example.com"
if host == strings.TrimPrefix(suffix, ".") {
return true
}
}
return false
}
// IsEmpty returns true if the whitelist has no entries.
func (w *HostWhitelist) IsEmpty() bool {
return len(w.exactHosts) == 0 && len(w.suffixHosts) == 0
}
// Count returns the total number of whitelist entries.
func (w *HostWhitelist) Count() int {
return len(w.exactHosts) + len(w.suffixHosts)
}

View File

@@ -1,190 +0,0 @@
package imgcache
import (
"net/url"
"testing"
)
func TestHostWhitelist_IsWhitelisted(t *testing.T) {
tests := []struct {
name string
patterns []string
testURL string
want bool
}{
{
name: "exact match",
patterns: []string{"cdn.example.com"},
testURL: "https://cdn.example.com/image.jpg",
want: true,
},
{
name: "exact match case insensitive",
patterns: []string{"CDN.Example.COM"},
testURL: "https://cdn.example.com/image.jpg",
want: true,
},
{
name: "exact match not found",
patterns: []string{"cdn.example.com"},
testURL: "https://other.example.com/image.jpg",
want: false,
},
{
name: "suffix match",
patterns: []string{".example.com"},
testURL: "https://cdn.example.com/image.jpg",
want: true,
},
{
name: "suffix match deep subdomain",
patterns: []string{".example.com"},
testURL: "https://cdn.images.example.com/image.jpg",
want: true,
},
{
name: "suffix match apex domain",
patterns: []string{".example.com"},
testURL: "https://example.com/image.jpg",
want: true,
},
{
name: "suffix match not found",
patterns: []string{".example.com"},
testURL: "https://notexample.com/image.jpg",
want: false,
},
{
name: "suffix match partial not allowed",
patterns: []string{".example.com"},
testURL: "https://fakeexample.com/image.jpg",
want: false,
},
{
name: "multiple patterns",
patterns: []string{"cdn.example.com", ".images.org", "static.test.net"},
testURL: "https://photos.images.org/image.jpg",
want: true,
},
{
name: "empty whitelist",
patterns: []string{},
testURL: "https://cdn.example.com/image.jpg",
want: false,
},
{
name: "nil url",
patterns: []string{"cdn.example.com"},
testURL: "",
want: false,
},
{
name: "url with port",
patterns: []string{"cdn.example.com"},
testURL: "https://cdn.example.com:443/image.jpg",
want: true,
},
{
name: "whitespace in patterns",
patterns: []string{" cdn.example.com ", " .other.com "},
testURL: "https://cdn.example.com/image.jpg",
want: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
w := NewHostWhitelist(tt.patterns)
var u *url.URL
if tt.testURL != "" {
var err error
u, err = url.Parse(tt.testURL)
if err != nil {
t.Fatalf("failed to parse test URL: %v", err)
}
}
got := w.IsWhitelisted(u)
if got != tt.want {
t.Errorf("IsWhitelisted() = %v, want %v", got, tt.want)
}
})
}
}
func TestHostWhitelist_IsEmpty(t *testing.T) {
tests := []struct {
name string
patterns []string
want bool
}{
{
name: "empty",
patterns: []string{},
want: true,
},
{
name: "nil",
patterns: nil,
want: true,
},
{
name: "whitespace only",
patterns: []string{" ", ""},
want: true,
},
{
name: "has entries",
patterns: []string{"example.com"},
want: false,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
w := NewHostWhitelist(tt.patterns)
if got := w.IsEmpty(); got != tt.want {
t.Errorf("IsEmpty() = %v, want %v", got, tt.want)
}
})
}
}
func TestHostWhitelist_Count(t *testing.T) {
tests := []struct {
name string
patterns []string
want int
}{
{
name: "empty",
patterns: []string{},
want: 0,
},
{
name: "exact hosts only",
patterns: []string{"a.com", "b.com", "c.com"},
want: 3,
},
{
name: "suffix hosts only",
patterns: []string{".a.com", ".b.com"},
want: 2,
},
{
name: "mixed",
patterns: []string{"exact.com", ".suffix.com"},
want: 2,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
w := NewHostWhitelist(tt.patterns)
if got := w.Count(); got != tt.want {
t.Errorf("Count() = %v, want %v", got, tt.want)
}
})
}
}