3 Commits

Author SHA1 Message Date
clawbot
a853fe7ee7 refactor: extract httpfetcher package from imgcache
All checks were successful
check / check (push) Successful in 57s
Move HTTPFetcher, Config (was FetcherConfig), SSRF-safe dialer, rate
limiting, content-type validation, and related error vars from
internal/imgcache/fetcher.go into new internal/httpfetcher/ package.

The Fetcher interface and FetchResult type also move to httpfetcher
to avoid circular imports (imgcache imports httpfetcher, not the other
way around).

Renames to avoid stuttering:
  NewHTTPFetcher -> httpfetcher.New
  FetcherConfig  -> httpfetcher.Config
  NewMockFetcher -> httpfetcher.NewMock

The ServiceConfig.FetcherConfig field is retained (it describes what
kind of config it holds, not a stutter).

Pure refactor - no behavior changes. Unit tests for the httpfetcher
package are included.

refs #39
2026-04-17 06:47:05 +00:00
6b4a1d7607 refactor: extract magic byte detection into internal/magic package (#42)
All checks were successful
check / check (push) Successful in 1m39s
## Summary

Extract magic byte detection and MIME type handling from `internal/imgcache/` into a new focused `internal/magic/` package.

Part of [issue #39](#39)

## Changes

### New package: `internal/magic/`

Moved the following from `internal/imgcache/magic.go`:
- `MIMEType` type and constants (`MIMETypeJPEG`, `MIMETypePNG`, etc.)
- `DetectFormat()` — detects image format from magic bytes
- `ValidateMagicBytes()` — validates content matches declared MIME type
- `PeekAndValidate()` — reads minimum bytes, validates, returns combined reader
- `IsSupportedMIMEType()` — checks if a MIME type is supported
- `MIMEToImageFormat()` — converts MIME type to ImageFormat
- `ImageFormatToMIME()` — converts ImageFormat to MIME string
- All error sentinels (`ErrUnknownFormat`, `ErrMagicByteMismatch`, `ErrNotEnoughData`)
- All helper functions (`detectSVG`, `skipBOM`, `normalizeMIMEType`)

The magic package defines its own `ImageFormat` type and constants to avoid circular imports (`imgcache` → `magic` for validation; `magic` cannot import `imgcache`).

### Updated imports
- `internal/imgcache/service.go`: uses `magic.ValidateMagicBytes()`
- `internal/imgcache/service_test.go`: uses `magic.DetectFormat()` and `magic.MIMEToImageFormat()`

### Naming
- Clean package-qualified names: `magic.DetectFormat()`, `magic.ValidateMagicBytes()`, etc.
- No stuttering names

### Tests
- Full test suite moved to `internal/magic/magic_test.go` (all 15 test functions preserved)
- All existing tests pass unchanged
- `docker build .` passes (includes `make check`: fmt, lint, tests)

Co-authored-by: user <user@Mac.lan guest wan>
Reviewed-on: #42
Co-authored-by: clawbot <clawbot@noreply.example.org>
Co-committed-by: clawbot <clawbot@noreply.example.org>
2026-04-07 00:41:48 +02:00
e34743f070 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>
2026-03-25 20:44:56 +01:00
17 changed files with 472 additions and 109 deletions

View File

@@ -1,25 +1,26 @@
package imgcache
// Package allowlist provides host-based URL allow-listing for the image proxy.
package allowlist
import (
"net/url"
"strings"
)
// HostWhitelist implements the Whitelist interface for checking allowed source hosts.
type HostWhitelist struct {
// HostAllowList checks whether source hosts are permitted.
type HostAllowList 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.
// New creates a HostAllowList 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{
func New(patterns []string) *HostAllowList {
w := &HostAllowList{
exactHosts: make(map[string]struct{}),
suffixHosts: make([]string, 0),
}
@@ -40,8 +41,8 @@ func NewHostWhitelist(patterns []string) *HostWhitelist {
return w
}
// IsWhitelisted checks if a URL's host is in the whitelist.
func (w *HostWhitelist) IsWhitelisted(u *url.URL) bool {
// IsAllowed checks if a URL's host is in the allow list.
func (w *HostAllowList) IsAllowed(u *url.URL) bool {
if u == nil {
return false
}
@@ -71,12 +72,12 @@ func (w *HostWhitelist) IsWhitelisted(u *url.URL) bool {
return false
}
// IsEmpty returns true if the whitelist has no entries.
func (w *HostWhitelist) IsEmpty() bool {
// IsEmpty returns true if the allow list has no entries.
func (w *HostAllowList) IsEmpty() bool {
return len(w.exactHosts) == 0 && len(w.suffixHosts) == 0
}
// Count returns the total number of whitelist entries.
func (w *HostWhitelist) Count() int {
// Count returns the total number of allow list entries.
func (w *HostAllowList) Count() int {
return len(w.exactHosts) + len(w.suffixHosts)
}

View File

@@ -1,11 +1,13 @@
package imgcache
package allowlist_test
import (
"net/url"
"testing"
"sneak.berlin/go/pixa/internal/allowlist"
)
func TestHostWhitelist_IsWhitelisted(t *testing.T) {
func TestHostAllowList_IsAllowed(t *testing.T) {
tests := []struct {
name string
patterns []string
@@ -67,7 +69,7 @@ func TestHostWhitelist_IsWhitelisted(t *testing.T) {
want: true,
},
{
name: "empty whitelist",
name: "empty allow list",
patterns: []string{},
testURL: "https://cdn.example.com/image.jpg",
want: false,
@@ -94,7 +96,7 @@ func TestHostWhitelist_IsWhitelisted(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
w := NewHostWhitelist(tt.patterns)
w := allowlist.New(tt.patterns)
var u *url.URL
if tt.testURL != "" {
@@ -105,15 +107,15 @@ func TestHostWhitelist_IsWhitelisted(t *testing.T) {
}
}
got := w.IsWhitelisted(u)
got := w.IsAllowed(u)
if got != tt.want {
t.Errorf("IsWhitelisted() = %v, want %v", got, tt.want)
t.Errorf("IsAllowed() = %v, want %v", got, tt.want)
}
})
}
}
func TestHostWhitelist_IsEmpty(t *testing.T) {
func TestHostAllowList_IsEmpty(t *testing.T) {
tests := []struct {
name string
patterns []string
@@ -143,7 +145,7 @@ func TestHostWhitelist_IsEmpty(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
w := NewHostWhitelist(tt.patterns)
w := allowlist.New(tt.patterns)
if got := w.IsEmpty(); got != tt.want {
t.Errorf("IsEmpty() = %v, want %v", got, tt.want)
}
@@ -151,7 +153,7 @@ func TestHostWhitelist_IsEmpty(t *testing.T) {
}
}
func TestHostWhitelist_Count(t *testing.T) {
func TestHostAllowList_Count(t *testing.T) {
tests := []struct {
name string
patterns []string
@@ -181,7 +183,7 @@ func TestHostWhitelist_Count(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
w := NewHostWhitelist(tt.patterns)
w := allowlist.New(tt.patterns)
if got := w.Count(); got != tt.want {
t.Errorf("Count() = %v, want %v", got, tt.want)
}

View File

@@ -13,6 +13,7 @@ import (
"sneak.berlin/go/pixa/internal/database"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/healthcheck"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imgcache"
"sneak.berlin/go/pixa/internal/logger"
"sneak.berlin/go/pixa/internal/session"
@@ -72,7 +73,7 @@ func (s *Handlers) initImageService() error {
s.imgCache = cache
// Create the fetcher config
fetcherCfg := imgcache.DefaultFetcherConfig()
fetcherCfg := httpfetcher.DefaultConfig()
fetcherCfg.AllowHTTP = s.config.AllowHTTP
if s.config.UpstreamConnectionsPerHost > 0 {
fetcherCfg.MaxConnectionsPerHost = s.config.UpstreamConnectionsPerHost

View File

@@ -18,6 +18,7 @@ import (
"github.com/go-chi/chi/v5"
"sneak.berlin/go/pixa/internal/database"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imgcache"
)
@@ -116,16 +117,16 @@ func newMockFetcher(fs fs.FS) *mockFetcher {
return &mockFetcher{fs: fs}
}
func (f *mockFetcher) Fetch(ctx context.Context, url string) (*imgcache.FetchResult, error) {
func (f *mockFetcher) Fetch(ctx context.Context, url string) (*httpfetcher.FetchResult, error) {
// Remove https:// prefix
path := url[8:] // Remove "https://"
data, err := fs.ReadFile(f.fs, path)
if err != nil {
return nil, imgcache.ErrUpstreamError
return nil, httpfetcher.ErrUpstreamError
}
return &imgcache.FetchResult{
return &httpfetcher.FetchResult{
Content: io.NopCloser(bytes.NewReader(data)),
ContentLength: int64(len(data)),
ContentType: "image/jpeg",

View File

@@ -8,6 +8,7 @@ import (
"time"
"github.com/go-chi/chi/v5"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imgcache"
)
@@ -97,13 +98,13 @@ func (s *Handlers) HandleImage() http.HandlerFunc {
)
// Check for specific error types
if errors.Is(err, imgcache.ErrSSRFBlocked) {
if errors.Is(err, httpfetcher.ErrSSRFBlocked) {
s.respondError(w, "forbidden", http.StatusForbidden)
return
}
if errors.Is(err, imgcache.ErrUpstreamError) {
if errors.Is(err, httpfetcher.ErrUpstreamError) {
s.respondError(w, "upstream error", http.StatusBadGateway)
return

View File

@@ -11,6 +11,7 @@ import (
"github.com/go-chi/chi/v5"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imgcache"
)
@@ -100,11 +101,11 @@ func (s *Handlers) HandleImageEnc() http.HandlerFunc {
// handleImageError converts image service errors to HTTP responses.
func (s *Handlers) handleImageError(w http.ResponseWriter, err error) {
switch {
case errors.Is(err, imgcache.ErrSSRFBlocked):
case errors.Is(err, httpfetcher.ErrSSRFBlocked):
s.respondError(w, "forbidden", http.StatusForbidden)
case errors.Is(err, imgcache.ErrUpstreamError):
case errors.Is(err, httpfetcher.ErrUpstreamError):
s.respondError(w, "upstream error", http.StatusBadGateway)
case errors.Is(err, imgcache.ErrUpstreamTimeout):
case errors.Is(err, httpfetcher.ErrUpstreamTimeout):
s.respondError(w, "upstream timeout", http.StatusGatewayTimeout)
default:
s.log.Error("image request failed", "error", err)

View File

@@ -1,4 +1,6 @@
package imgcache
// Package httpfetcher fetches content from upstream HTTP origins with SSRF
// protection, per-host connection limits, and content-type validation.
package httpfetcher
import (
"context"
@@ -37,25 +39,55 @@ var (
ErrUpstreamTimeout = errors.New("upstream request timeout")
)
// FetcherConfig holds configuration for the upstream fetcher.
type FetcherConfig struct {
// Timeout for upstream requests
// Fetcher retrieves content from upstream origins.
type Fetcher interface {
// Fetch retrieves content from the given URL.
Fetch(ctx context.Context, url string) (*FetchResult, error)
}
// FetchResult contains the result of fetching from upstream.
type FetchResult struct {
// Content is the raw image data.
Content io.ReadCloser
// ContentLength is the size in bytes (-1 if unknown).
ContentLength int64
// ContentType is the MIME type from upstream.
ContentType string
// Headers contains all response headers from upstream.
Headers map[string][]string
// StatusCode is the HTTP status code from upstream.
StatusCode int
// FetchDurationMs is how long the fetch took in milliseconds.
FetchDurationMs int64
// RemoteAddr is the IP:port of the upstream server.
RemoteAddr string
// HTTPVersion is the protocol version (e.g., "1.1", "2.0").
HTTPVersion string
// TLSVersion is the TLS protocol version (e.g., "TLS 1.3").
TLSVersion string
// TLSCipherSuite is the negotiated cipher suite name.
TLSCipherSuite string
}
// Config holds configuration for the upstream fetcher.
type Config struct {
// Timeout for upstream requests.
Timeout time.Duration
// MaxResponseSize is the maximum allowed response body size
// MaxResponseSize is the maximum allowed response body size.
MaxResponseSize int64
// UserAgent to send to upstream servers
// UserAgent to send to upstream servers.
UserAgent string
// AllowedContentTypes is a whitelist of MIME types to accept
// AllowedContentTypes is an allow list of MIME types to accept.
AllowedContentTypes []string
// AllowHTTP allows non-TLS connections (for testing only)
// AllowHTTP allows non-TLS connections (for testing only).
AllowHTTP bool
// MaxConnectionsPerHost limits concurrent connections to each upstream host
// MaxConnectionsPerHost limits concurrent connections to each upstream host.
MaxConnectionsPerHost int
}
// DefaultFetcherConfig returns sensible defaults.
func DefaultFetcherConfig() *FetcherConfig {
return &FetcherConfig{
// DefaultConfig returns a Config with sensible defaults.
func DefaultConfig() *Config {
return &Config{
Timeout: DefaultFetchTimeout,
MaxResponseSize: DefaultMaxResponseSize,
UserAgent: "pixa/1.0",
@@ -72,18 +104,18 @@ func DefaultFetcherConfig() *FetcherConfig {
}
}
// HTTPFetcher implements the Fetcher interface with SSRF protection.
// HTTPFetcher implements Fetcher with SSRF protection and per-host connection limits.
type HTTPFetcher struct {
client *http.Client
config *FetcherConfig
config *Config
hostSems map[string]chan struct{} // per-host semaphores
hostSemMu sync.Mutex // protects hostSems map
}
// NewHTTPFetcher creates a new fetcher with SSRF protection.
func NewHTTPFetcher(config *FetcherConfig) *HTTPFetcher {
// New creates a new HTTPFetcher with SSRF protection.
func New(config *Config) *HTTPFetcher {
if config == nil {
config = DefaultFetcherConfig()
config = DefaultConfig()
}
// Create transport with SSRF-safe dialer
@@ -250,7 +282,7 @@ func (f *HTTPFetcher) Fetch(ctx context.Context, url string) (*FetchResult, erro
}, nil
}
// isAllowedContentType checks if the content type is in the whitelist.
// isAllowedContentType checks if the content type is in the allow list.
func (f *HTTPFetcher) isAllowedContentType(contentType string) bool {
// Extract the MIME type without parameters
mediaType := strings.TrimSpace(strings.Split(contentType, ";")[0])

View File

@@ -0,0 +1,329 @@
package httpfetcher
import (
"context"
"errors"
"io"
"net"
"testing"
"testing/fstest"
)
func TestDefaultConfig(t *testing.T) {
cfg := DefaultConfig()
if cfg.Timeout != DefaultFetchTimeout {
t.Errorf("Timeout = %v, want %v", cfg.Timeout, DefaultFetchTimeout)
}
if cfg.MaxResponseSize != DefaultMaxResponseSize {
t.Errorf("MaxResponseSize = %d, want %d", cfg.MaxResponseSize, DefaultMaxResponseSize)
}
if cfg.MaxConnectionsPerHost != DefaultMaxConnectionsPerHost {
t.Errorf("MaxConnectionsPerHost = %d, want %d",
cfg.MaxConnectionsPerHost, DefaultMaxConnectionsPerHost)
}
if cfg.AllowHTTP {
t.Error("AllowHTTP should default to false")
}
if len(cfg.AllowedContentTypes) == 0 {
t.Error("AllowedContentTypes should not be empty")
}
}
func TestNewWithNilConfigUsesDefaults(t *testing.T) {
f := New(nil)
if f == nil {
t.Fatal("New(nil) returned nil")
}
if f.config == nil {
t.Fatal("config should be populated from DefaultConfig")
}
if f.config.Timeout != DefaultFetchTimeout {
t.Errorf("Timeout = %v, want %v", f.config.Timeout, DefaultFetchTimeout)
}
}
func TestIsAllowedContentType(t *testing.T) {
f := New(DefaultConfig())
tests := []struct {
contentType string
want bool
}{
{"image/jpeg", true},
{"image/png", true},
{"image/webp", true},
{"image/jpeg; charset=utf-8", true},
{"IMAGE/JPEG", true},
{"text/html", false},
{"application/octet-stream", false},
{"", false},
}
for _, tc := range tests {
t.Run(tc.contentType, func(t *testing.T) {
got := f.isAllowedContentType(tc.contentType)
if got != tc.want {
t.Errorf("isAllowedContentType(%q) = %v, want %v", tc.contentType, got, tc.want)
}
})
}
}
func TestExtractHost(t *testing.T) {
tests := []struct {
url string
want string
}{
{"https://example.com/path", "example.com"},
{"http://example.com:8080/path", "example.com:8080"},
{"https://example.com", "example.com"},
{"https://example.com?q=1", "example.com"},
{"example.com/path", "example.com"},
{"", ""},
}
for _, tc := range tests {
t.Run(tc.url, func(t *testing.T) {
got := extractHost(tc.url)
if got != tc.want {
t.Errorf("extractHost(%q) = %q, want %q", tc.url, got, tc.want)
}
})
}
}
func TestIsLocalhost(t *testing.T) {
tests := []struct {
host string
want bool
}{
{"localhost", true},
{"LOCALHOST", true},
{"127.0.0.1", true},
{"::1", true},
{"[::1]", true},
{"foo.localhost", true},
{"foo.local", true},
{"example.com", false},
{"127.0.0.2", false}, // Handled by isPrivateIP, not isLocalhost string match
}
for _, tc := range tests {
t.Run(tc.host, func(t *testing.T) {
got := isLocalhost(tc.host)
if got != tc.want {
t.Errorf("isLocalhost(%q) = %v, want %v", tc.host, got, tc.want)
}
})
}
}
func TestIsPrivateIP(t *testing.T) {
tests := []struct {
ip string
want bool
}{
{"127.0.0.1", true}, // loopback
{"10.0.0.1", true}, // private
{"192.168.1.1", true}, // private
{"172.16.0.1", true}, // private
{"169.254.1.1", true}, // link-local
{"0.0.0.0", true}, // unspecified
{"224.0.0.1", true}, // multicast
{"::1", true}, // IPv6 loopback
{"fe80::1", true}, // IPv6 link-local
{"8.8.8.8", false}, // public
{"2001:4860:4860::8888", false}, // public IPv6
}
for _, tc := range tests {
t.Run(tc.ip, func(t *testing.T) {
ip := net.ParseIP(tc.ip)
if ip == nil {
t.Fatalf("failed to parse IP %q", tc.ip)
}
got := isPrivateIP(ip)
if got != tc.want {
t.Errorf("isPrivateIP(%q) = %v, want %v", tc.ip, got, tc.want)
}
})
}
if !isPrivateIP(nil) {
t.Error("isPrivateIP(nil) should return true")
}
}
func TestValidateURL_RejectsNonHTTPS(t *testing.T) {
err := validateURL("http://example.com/path", false)
if !errors.Is(err, ErrUnsupportedScheme) {
t.Errorf("validateURL http = %v, want ErrUnsupportedScheme", err)
}
}
func TestValidateURL_AllowsHTTPWhenConfigured(t *testing.T) {
// Use a host that won't resolve (explicit .invalid TLD) so we don't hit DNS.
err := validateURL("http://nonexistent.invalid/path", true)
// We expect a host resolution error, not ErrUnsupportedScheme.
if errors.Is(err, ErrUnsupportedScheme) {
t.Error("validateURL with AllowHTTP should not return ErrUnsupportedScheme")
}
}
func TestValidateURL_RejectsLocalhost(t *testing.T) {
err := validateURL("https://localhost/path", false)
if !errors.Is(err, ErrSSRFBlocked) {
t.Errorf("validateURL localhost = %v, want ErrSSRFBlocked", err)
}
}
func TestValidateURL_EmptyHost(t *testing.T) {
err := validateURL("https:///path", false)
if !errors.Is(err, ErrInvalidHost) {
t.Errorf("validateURL empty host = %v, want ErrInvalidHost", err)
}
}
func TestMockFetcher_FetchesFile(t *testing.T) {
mockFS := fstest.MapFS{
"example.com/images/photo.jpg": &fstest.MapFile{Data: []byte("fake-jpeg-data")},
}
m := NewMock(mockFS)
result, err := m.Fetch(context.Background(), "https://example.com/images/photo.jpg")
if err != nil {
t.Fatalf("Fetch() error = %v", err)
}
defer func() { _ = result.Content.Close() }()
if result.ContentType != "image/jpeg" {
t.Errorf("ContentType = %q, want image/jpeg", result.ContentType)
}
data, err := io.ReadAll(result.Content)
if err != nil {
t.Fatalf("read content: %v", err)
}
if string(data) != "fake-jpeg-data" {
t.Errorf("Content = %q, want %q", string(data), "fake-jpeg-data")
}
if result.ContentLength != int64(len("fake-jpeg-data")) {
t.Errorf("ContentLength = %d, want %d", result.ContentLength, len("fake-jpeg-data"))
}
}
func TestMockFetcher_MissingFileReturnsUpstreamError(t *testing.T) {
mockFS := fstest.MapFS{}
m := NewMock(mockFS)
_, err := m.Fetch(context.Background(), "https://example.com/missing.jpg")
if !errors.Is(err, ErrUpstreamError) {
t.Errorf("Fetch() error = %v, want ErrUpstreamError", err)
}
}
func TestMockFetcher_RespectsContextCancellation(t *testing.T) {
mockFS := fstest.MapFS{
"example.com/photo.jpg": &fstest.MapFile{Data: []byte("data")},
}
m := NewMock(mockFS)
ctx, cancel := context.WithCancel(context.Background())
cancel()
_, err := m.Fetch(ctx, "https://example.com/photo.jpg")
if !errors.Is(err, context.Canceled) {
t.Errorf("Fetch() error = %v, want context.Canceled", err)
}
}
func TestDetectContentTypeFromPath(t *testing.T) {
tests := []struct {
path string
want string
}{
{"foo/bar.jpg", "image/jpeg"},
{"foo/bar.JPG", "image/jpeg"},
{"foo/bar.jpeg", "image/jpeg"},
{"foo/bar.png", "image/png"},
{"foo/bar.gif", "image/gif"},
{"foo/bar.webp", "image/webp"},
{"foo/bar.avif", "image/avif"},
{"foo/bar.svg", "image/svg+xml"},
{"foo/bar.bin", "application/octet-stream"},
{"foo/bar", "application/octet-stream"},
}
for _, tc := range tests {
t.Run(tc.path, func(t *testing.T) {
got := detectContentTypeFromPath(tc.path)
if got != tc.want {
t.Errorf("detectContentTypeFromPath(%q) = %q, want %q", tc.path, got, tc.want)
}
})
}
}
func TestLimitedReader_EnforcesLimit(t *testing.T) {
src := make([]byte, 100)
r := &limitedReader{
reader: &byteReader{data: src},
remaining: 50,
}
buf := make([]byte, 100)
n, err := r.Read(buf)
if err != nil {
t.Fatalf("first Read error = %v", err)
}
if n > 50 {
t.Errorf("read %d bytes, should be capped at 50", n)
}
// Drain until limit is exhausted.
total := n
for total < 50 {
nn, err := r.Read(buf)
total += nn
if err != nil {
t.Fatalf("during drain: %v", err)
}
}
// Now the limit is exhausted — next read should error.
_, err = r.Read(buf)
if !errors.Is(err, ErrResponseTooLarge) {
t.Errorf("exhausted Read error = %v, want ErrResponseTooLarge", err)
}
}
// byteReader is a minimal io.Reader over a byte slice for testing.
type byteReader struct {
data []byte
pos int
}
func (r *byteReader) Read(p []byte) (int, error) {
if r.pos >= len(r.data) {
return 0, io.EOF
}
n := copy(p, r.data[r.pos:])
r.pos += n
return n, nil
}

View File

@@ -1,4 +1,4 @@
package imgcache
package httpfetcher
import (
"context"
@@ -10,15 +10,15 @@ import (
"strings"
)
// MockFetcher implements the Fetcher interface using an embedded filesystem.
// MockFetcher implements Fetcher using an embedded filesystem.
// Files are organized as: hostname/path/to/file.ext
// URLs like https://example.com/images/photo.jpg map to example.com/images/photo.jpg
// URLs like https://example.com/images/photo.jpg map to example.com/images/photo.jpg.
type MockFetcher struct {
fs fs.FS
}
// NewMockFetcher creates a new mock fetcher backed by the given filesystem.
func NewMockFetcher(fsys fs.FS) *MockFetcher {
// NewMock creates a new mock fetcher backed by the given filesystem.
func NewMock(fsys fs.FS) *MockFetcher {
return &MockFetcher{fs: fsys}
}

View File

@@ -9,6 +9,8 @@ import (
"io"
"path/filepath"
"time"
"sneak.berlin/go/pixa/internal/httpfetcher"
)
// Cache errors.
@@ -111,7 +113,7 @@ func (c *Cache) StoreSource(
ctx context.Context,
req *ImageRequest,
content io.Reader,
result *FetchResult,
result *httpfetcher.FetchResult,
) (ContentHash, error) {
// Store content
contentHash, size, err := c.srcContent.Store(content)

View File

@@ -9,6 +9,7 @@ import (
"time"
_ "modernc.org/sqlite"
"sneak.berlin/go/pixa/internal/httpfetcher"
)
func setupTestDB(t *testing.T) *sql.DB {
@@ -152,7 +153,7 @@ func TestCache_StoreAndLookup(t *testing.T) {
// Store source content
sourceContent := []byte("fake jpeg data")
fetchResult := &FetchResult{
fetchResult := &httpfetcher.FetchResult{
ContentType: "image/jpeg",
Headers: map[string][]string{"Content-Type": {"image/jpeg"}},
}

View File

@@ -169,36 +169,6 @@ type Whitelist interface {
IsWhitelisted(u *url.URL) bool
}
// Fetcher fetches images from upstream origins
type Fetcher interface {
// Fetch retrieves an image from the origin
Fetch(ctx context.Context, url string) (*FetchResult, error)
}
// FetchResult contains the result of fetching from upstream
type FetchResult struct {
// Content is the raw image data
Content io.ReadCloser
// ContentLength is the size in bytes (-1 if unknown)
ContentLength int64
// ContentType is the MIME type from upstream
ContentType string
// Headers contains all response headers from upstream
Headers map[string][]string
// StatusCode is the HTTP status code from upstream
StatusCode int
// FetchDurationMs is how long the fetch took in milliseconds
FetchDurationMs int64
// RemoteAddr is the IP:port of the upstream server
RemoteAddr string
// HTTPVersion is the protocol version (e.g., "1.1", "2.0")
HTTPVersion string
// TLSVersion is the TLS protocol version (e.g., "TLS 1.3")
TLSVersion string
// TLSCipherSuite is the negotiated cipher suite name
TLSCipherSuite string
}
// Storage handles persistent storage of cached content
type Storage interface {
// Store saves content and returns its hash

View File

@@ -11,16 +11,19 @@ import (
"time"
"github.com/dustin/go-humanize"
"sneak.berlin/go/pixa/internal/allowlist"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imageprocessor"
"sneak.berlin/go/pixa/internal/magic"
)
// Service implements the ImageCache interface, orchestrating cache, fetcher, and processor.
type Service struct {
cache *Cache
fetcher Fetcher
fetcher httpfetcher.Fetcher
processor *imageprocessor.ImageProcessor
signer *Signer
whitelist *HostWhitelist
allowlist *allowlist.HostAllowList
log *slog.Logger
allowHTTP bool
maxResponseSize int64
@@ -31,9 +34,9 @@ type ServiceConfig struct {
// Cache is the cache instance
Cache *Cache
// FetcherConfig configures the upstream fetcher (ignored if Fetcher is set)
FetcherConfig *FetcherConfig
FetcherConfig *httpfetcher.Config
// Fetcher is an optional custom fetcher (for testing)
Fetcher Fetcher
Fetcher httpfetcher.Fetcher
// SigningKey is the HMAC signing key (empty disables signing)
SigningKey string
// Whitelist is the list of hosts that don't require signatures
@@ -55,15 +58,15 @@ func NewService(cfg *ServiceConfig) (*Service, error) {
// Resolve fetcher config for defaults
fetcherCfg := cfg.FetcherConfig
if fetcherCfg == nil {
fetcherCfg = DefaultFetcherConfig()
fetcherCfg = httpfetcher.DefaultConfig()
}
// Use custom fetcher if provided, otherwise create HTTP fetcher
var fetcher Fetcher
var fetcher httpfetcher.Fetcher
if cfg.Fetcher != nil {
fetcher = cfg.Fetcher
} else {
fetcher = NewHTTPFetcher(fetcherCfg)
fetcher = httpfetcher.New(fetcherCfg)
}
signer := NewSigner(cfg.SigningKey)
@@ -85,7 +88,7 @@ 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,
@@ -111,7 +114,7 @@ func (s *Service) Get(ctx context.Context, req *ImageRequest) (*ImageResponse, e
"path", req.SourcePath,
)
return nil, fmt.Errorf("%w: %w", ErrUpstreamError, ErrNegativeCached)
return nil, fmt.Errorf("%w: %w", httpfetcher.ErrUpstreamError, ErrNegativeCached)
}
// Check variant cache first (disk only, no DB)
@@ -276,7 +279,7 @@ func (s *Service) fetchAndProcess(
)
// Validate magic bytes match content type
if err := ValidateMagicBytes(sourceData, fetchResult.ContentType); err != nil {
if err := magic.ValidateMagicBytes(sourceData, fetchResult.ContentType); err != nil {
return nil, fmt.Errorf("content validation failed: %w", err)
}
@@ -381,7 +384,7 @@ 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 +392,11 @@ 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)
}
@@ -416,13 +419,13 @@ const (
// isNegativeCacheable returns true if the error should be cached.
func isNegativeCacheable(err error) bool {
return errors.Is(err, ErrUpstreamError)
return errors.Is(err, httpfetcher.ErrUpstreamError)
}
// extractStatusCode extracts HTTP status code from error message.
func extractStatusCode(err error) int {
// Default to 502 Bad Gateway for upstream errors
if errors.Is(err, ErrUpstreamError) {
if errors.Is(err, httpfetcher.ErrUpstreamError) {
return httpStatusBadGateway
}

View File

@@ -5,6 +5,8 @@ import (
"io"
"testing"
"time"
"sneak.berlin/go/pixa/internal/magic"
)
func TestService_Get_WhitelistedHost(t *testing.T) {
@@ -315,17 +317,17 @@ func TestService_Get_FormatConversion(t *testing.T) {
t.Fatalf("failed to read response: %v", err)
}
detectedMIME, err := DetectFormat(data)
detectedMIME, err := magic.DetectFormat(data)
if err != nil {
t.Fatalf("failed to detect format: %v", err)
}
expectedFormat, ok := MIMEToImageFormat(tt.wantMIME)
expectedFormat, ok := magic.MIMEToImageFormat(tt.wantMIME)
if !ok {
t.Fatalf("unknown format for MIME type: %s", tt.wantMIME)
}
detectedFormat, ok := MIMEToImageFormat(string(detectedMIME))
detectedFormat, ok := magic.MIMEToImageFormat(string(detectedMIME))
if !ok {
t.Fatalf("unknown format for detected MIME type: %s", detectedMIME)
}

View File

@@ -15,6 +15,7 @@ import (
"time"
"sneak.berlin/go/pixa/internal/database"
"sneak.berlin/go/pixa/internal/httpfetcher"
)
// TestFixtures contains paths to test files in the mock filesystem.
@@ -172,7 +173,7 @@ func SetupTestService(t *testing.T, opts ...TestServiceOption) (*Service, *TestF
svc, err := NewService(&ServiceConfig{
Cache: cache,
Fetcher: NewMockFetcher(mockFS),
Fetcher: httpfetcher.NewMock(mockFS),
SigningKey: cfg.signingKey,
Whitelist: cfg.whitelist,
})

View File

@@ -1,4 +1,6 @@
package imgcache
// Package magic detects image formats from magic bytes and validates
// content against declared MIME types.
package magic
import (
"bytes"
@@ -27,6 +29,20 @@ const (
MIMETypeSVG = MIMEType("image/svg+xml")
)
// ImageFormat represents supported output image formats.
// This mirrors the type in imgcache to avoid circular imports.
type ImageFormat string
// Supported image output formats.
const (
FormatOriginal ImageFormat = "orig"
FormatJPEG ImageFormat = "jpeg"
FormatPNG ImageFormat = "png"
FormatWebP ImageFormat = "webp"
FormatAVIF ImageFormat = "avif"
FormatGIF ImageFormat = "gif"
)
// MinMagicBytes is the minimum number of bytes needed to detect format.
const MinMagicBytes = 12
@@ -189,7 +205,7 @@ func PeekAndValidate(r io.Reader, declaredType string) (io.Reader, error) {
return io.MultiReader(bytes.NewReader(buf), r), nil
}
// MIMEToImageFormat converts a MIME type to our ImageFormat type.
// MIMEToImageFormat converts a MIME type to an ImageFormat.
func MIMEToImageFormat(mimeType string) (ImageFormat, bool) {
normalized := normalizeMIMEType(mimeType)
switch MIMEType(normalized) {
@@ -208,7 +224,7 @@ func MIMEToImageFormat(mimeType string) (ImageFormat, bool) {
}
}
// ImageFormatToMIME converts our ImageFormat to a MIME type string.
// ImageFormatToMIME converts an ImageFormat to a MIME type string.
func ImageFormatToMIME(format ImageFormat) string {
switch format {
case FormatJPEG:

View File

@@ -1,4 +1,4 @@
package imgcache
package magic
import (
"bytes"