1 Commits

Author SHA1 Message Date
clawbot
eae6f6e9ac refactor: extract whitelist package from internal/imgcache
All checks were successful
check / check (push) Successful in 57s
Move 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.

Updated import in internal/imgcache/service.go to use the new package.
Tests moved and adapted to external test style (package whitelist_test).

Part of #39
2026-03-24 18:22:48 -07:00
20 changed files with 180 additions and 644 deletions

View File

@@ -9,7 +9,6 @@ import (
"log/slog"
"path/filepath"
"sort"
"strconv"
"strings"
"go.uber.org/fx"
@@ -22,10 +21,6 @@ import (
//go:embed schema/*.sql
var schemaFS embed.FS
// bootstrapVersion is the migration that creates the schema_migrations
// table itself. It is applied before the normal migration loop.
const bootstrapVersion = 0
// Params defines dependencies for Database.
type Params struct {
fx.In
@@ -43,40 +38,35 @@ type Database struct {
// ParseMigrationVersion extracts the numeric version prefix from a migration
// filename. Filenames must follow the pattern "<version>.sql" or
// "<version>_<description>.sql", where version is a zero-padded numeric
// string (e.g. "001", "002"). Returns the version as an integer and an
// error if the filename does not match the expected pattern.
func ParseMigrationVersion(filename string) (int, error) {
// string (e.g. "001", "002"). Returns the version string and an error if
// the filename does not match the expected pattern.
func ParseMigrationVersion(filename string) (string, error) {
name := strings.TrimSuffix(filename, filepath.Ext(filename))
if name == "" {
return 0, fmt.Errorf("invalid migration filename %q: empty name", filename)
return "", fmt.Errorf("invalid migration filename %q: empty name", filename)
}
// Split on underscore to separate version from description.
// If there's no underscore, the entire stem is the version.
versionStr := name
version := name
if idx := strings.IndexByte(name, '_'); idx >= 0 {
versionStr = name[:idx]
version = name[:idx]
}
if versionStr == "" {
return 0, fmt.Errorf("invalid migration filename %q: empty version prefix", filename)
if version == "" {
return "", fmt.Errorf("invalid migration filename %q: empty version prefix", filename)
}
// Validate the version is purely numeric.
for _, ch := range versionStr {
for _, ch := range version {
if ch < '0' || ch > '9' {
return 0, fmt.Errorf(
return "", fmt.Errorf(
"invalid migration filename %q: version %q contains non-numeric character %q",
filename, versionStr, string(ch),
filename, version, string(ch),
)
}
}
version, err := strconv.Atoi(versionStr)
if err != nil {
return 0, fmt.Errorf("invalid migration filename %q: %w", filename, err)
}
return version, nil
}
@@ -153,34 +143,17 @@ func collectMigrations() ([]string, error) {
return migrations, nil
}
// bootstrapMigrationsTable ensures the schema_migrations table exists
// by applying 000.sql if the table is missing.
func bootstrapMigrationsTable(ctx context.Context, db *sql.DB, log *slog.Logger) error {
var tableExists int
err := db.QueryRowContext(ctx,
"SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='schema_migrations'",
).Scan(&tableExists)
// ensureMigrationsTable creates the schema_migrations tracking table if
// it does not already exist.
func ensureMigrationsTable(ctx context.Context, db *sql.DB) error {
_, err := db.ExecContext(ctx, `
CREATE TABLE IF NOT EXISTS schema_migrations (
version TEXT PRIMARY KEY,
applied_at DATETIME DEFAULT CURRENT_TIMESTAMP
)
`)
if err != nil {
return fmt.Errorf("failed to check for migrations table: %w", err)
}
if tableExists > 0 {
return nil
}
content, err := schemaFS.ReadFile("schema/000.sql")
if err != nil {
return fmt.Errorf("failed to read bootstrap migration 000.sql: %w", err)
}
if log != nil {
log.Info("applying bootstrap migration", "version", bootstrapVersion)
}
_, err = db.ExecContext(ctx, string(content))
if err != nil {
return fmt.Errorf("failed to apply bootstrap migration: %w", err)
return fmt.Errorf("failed to create migrations table: %w", err)
}
return nil
@@ -191,7 +164,7 @@ func bootstrapMigrationsTable(ctx context.Context, db *sql.DB, log *slog.Logger)
// This is exported so tests can apply the real schema without the full fx
// lifecycle.
func ApplyMigrations(ctx context.Context, db *sql.DB, log *slog.Logger) error {
if err := bootstrapMigrationsTable(ctx, db, log); err != nil {
if err := ensureMigrationsTable(ctx, db); err != nil {
return err
}

View File

@@ -8,51 +8,37 @@ import (
_ "modernc.org/sqlite" // SQLite driver registration
)
// openTestDB returns a fresh in-memory SQLite database.
func openTestDB(t *testing.T) *sql.DB {
t.Helper()
db, err := sql.Open("sqlite", ":memory:")
if err != nil {
t.Fatalf("failed to open test db: %v", err)
}
t.Cleanup(func() { db.Close() })
return db
}
func TestParseMigrationVersion(t *testing.T) {
tests := []struct {
name string
filename string
want int
want string
wantErr bool
}{
{
name: "version only",
filename: "001.sql",
want: 1,
want: "001",
},
{
name: "version with description",
filename: "001_initial_schema.sql",
want: 1,
want: "001",
},
{
name: "multi-digit version",
filename: "042_add_indexes.sql",
want: 42,
want: "042",
},
{
name: "long version number",
filename: "00001_long_prefix.sql",
want: 1,
want: "00001",
},
{
name: "description with multiple underscores",
filename: "003_add_user_auth_tables.sql",
want: 3,
want: "003",
},
{
name: "empty filename",
@@ -81,7 +67,7 @@ func TestParseMigrationVersion(t *testing.T) {
got, err := ParseMigrationVersion(tt.filename)
if tt.wantErr {
if err == nil {
t.Errorf("ParseMigrationVersion(%q) expected error, got %d", tt.filename, got)
t.Errorf("ParseMigrationVersion(%q) expected error, got %q", tt.filename, got)
}
return
@@ -94,131 +80,76 @@ func TestParseMigrationVersion(t *testing.T) {
}
if got != tt.want {
t.Errorf("ParseMigrationVersion(%q) = %d, want %d", tt.filename, got, tt.want)
t.Errorf("ParseMigrationVersion(%q) = %q, want %q", tt.filename, got, tt.want)
}
})
}
}
func TestApplyMigrations_CreatesSchemaAndTables(t *testing.T) {
db := openTestDB(t)
ctx := context.Background()
func TestApplyMigrations(t *testing.T) {
db, err := sql.Open("sqlite", ":memory:")
if err != nil {
t.Fatalf("failed to open in-memory database: %v", err)
}
defer db.Close()
if err := ApplyMigrations(ctx, db, nil); err != nil {
// Apply migrations should succeed.
if err := ApplyMigrations(context.Background(), db, nil); err != nil {
t.Fatalf("ApplyMigrations failed: %v", err)
}
// The schema_migrations table must exist and contain at least
// version 0 (the bootstrap) and 1 (the initial schema).
rows, err := db.Query("SELECT version FROM schema_migrations ORDER BY version")
// Verify the schema_migrations table recorded the version.
var version string
err = db.QueryRowContext(context.Background(),
"SELECT version FROM schema_migrations LIMIT 1",
).Scan(&version)
if err != nil {
t.Fatalf("failed to query schema_migrations: %v", err)
}
defer rows.Close()
var versions []int
for rows.Next() {
var v int
if err := rows.Scan(&v); err != nil {
t.Fatalf("failed to scan version: %v", err)
if version != "001" {
t.Errorf("expected version %q, got %q", "001", version)
}
versions = append(versions, v)
}
// Verify a table from the migration exists (source_content).
var tableName string
if err := rows.Err(); err != nil {
t.Fatalf("row iteration error: %v", err)
}
if len(versions) < 2 {
t.Fatalf("expected at least 2 migrations recorded, got %d: %v", len(versions), versions)
}
if versions[0] != 0 {
t.Errorf("first recorded migration = %d, want %d", versions[0], 0)
}
if versions[1] != 1 {
t.Errorf("second recorded migration = %d, want %d", versions[1], 1)
}
// Verify that the application tables created by 001.sql exist.
for _, table := range []string{"source_content", "source_metadata", "output_content", "request_cache", "negative_cache", "cache_stats"} {
var count int
err := db.QueryRow(
"SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name=?",
table,
).Scan(&count)
err = db.QueryRowContext(context.Background(),
"SELECT name FROM sqlite_master WHERE type='table' AND name='source_content'",
).Scan(&tableName)
if err != nil {
t.Fatalf("failed to check for table %s: %v", table, err)
}
if count != 1 {
t.Errorf("table %s does not exist after migrations", table)
}
t.Fatalf("expected source_content table to exist: %v", err)
}
}
func TestApplyMigrations_Idempotent(t *testing.T) {
db := openTestDB(t)
ctx := context.Background()
func TestApplyMigrationsIdempotent(t *testing.T) {
db, err := sql.Open("sqlite", ":memory:")
if err != nil {
t.Fatalf("failed to open in-memory database: %v", err)
}
defer db.Close()
if err := ApplyMigrations(ctx, db, nil); err != nil {
// Apply twice should succeed (idempotent).
if err := ApplyMigrations(context.Background(), db, nil); err != nil {
t.Fatalf("first ApplyMigrations failed: %v", err)
}
// Running a second time must succeed without errors.
if err := ApplyMigrations(ctx, db, nil); err != nil {
if err := ApplyMigrations(context.Background(), db, nil); err != nil {
t.Fatalf("second ApplyMigrations failed: %v", err)
}
// Verify no duplicate rows in schema_migrations.
// Should still have exactly one migration recorded.
var count int
err := db.QueryRow("SELECT COUNT(*) FROM schema_migrations WHERE version = 0").Scan(&count)
err = db.QueryRowContext(context.Background(),
"SELECT COUNT(*) FROM schema_migrations",
).Scan(&count)
if err != nil {
t.Fatalf("failed to count version 0 rows: %v", err)
t.Fatalf("failed to count schema_migrations: %v", err)
}
if count != 1 {
t.Errorf("expected exactly 1 row for version 0, got %d", count)
}
}
func TestBootstrapMigrationsTable_FreshDatabase(t *testing.T) {
db := openTestDB(t)
ctx := context.Background()
if err := bootstrapMigrationsTable(ctx, db, nil); err != nil {
t.Fatalf("bootstrapMigrationsTable failed: %v", err)
}
// schema_migrations table must exist.
var tableCount int
err := db.QueryRow(
"SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='schema_migrations'",
).Scan(&tableCount)
if err != nil {
t.Fatalf("failed to check for table: %v", err)
}
if tableCount != 1 {
t.Fatalf("schema_migrations table not created")
}
// Version 0 must be recorded.
var recorded int
err = db.QueryRow(
"SELECT COUNT(*) FROM schema_migrations WHERE version = 0",
).Scan(&recorded)
if err != nil {
t.Fatalf("failed to check version: %v", err)
}
if recorded != 1 {
t.Errorf("expected version 0 to be recorded, got count %d", recorded)
t.Errorf("expected 1 migration record, got %d", count)
}
}

View File

@@ -1,9 +0,0 @@
-- Migration 000: Schema migrations tracking table
-- Applied as a bootstrap step before the normal migration loop.
CREATE TABLE IF NOT EXISTS schema_migrations (
version INTEGER PRIMARY KEY,
applied_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
INSERT OR IGNORE INTO schema_migrations (version) VALUES (0);

View File

@@ -13,7 +13,6 @@ 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"
@@ -73,7 +72,7 @@ func (s *Handlers) initImageService() error {
s.imgCache = cache
// Create the fetcher config
fetcherCfg := httpfetcher.DefaultConfig()
fetcherCfg := imgcache.DefaultFetcherConfig()
fetcherCfg.AllowHTTP = s.config.AllowHTTP
if s.config.UpstreamConnectionsPerHost > 0 {
fetcherCfg.MaxConnectionsPerHost = s.config.UpstreamConnectionsPerHost

View File

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

View File

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

View File

@@ -11,7 +11,6 @@ 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"
)
@@ -101,11 +100,11 @@ 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, httpfetcher.ErrSSRFBlocked):
case errors.Is(err, imgcache.ErrSSRFBlocked):
s.respondError(w, "forbidden", http.StatusForbidden)
case errors.Is(err, httpfetcher.ErrUpstreamError):
case errors.Is(err, imgcache.ErrUpstreamError):
s.respondError(w, "upstream error", http.StatusBadGateway)
case errors.Is(err, httpfetcher.ErrUpstreamTimeout):
case errors.Is(err, imgcache.ErrUpstreamTimeout):
s.respondError(w, "upstream timeout", http.StatusGatewayTimeout)
default:
s.log.Error("image request failed", "error", err)

View File

@@ -1,329 +0,0 @@
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

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

View File

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

View File

@@ -1,6 +1,4 @@
// Package httpfetcher fetches content from upstream HTTP origins with SSRF
// protection, per-host connection limits, and content-type validation.
package httpfetcher
package imgcache
import (
"context"
@@ -39,55 +37,25 @@ var (
ErrUpstreamTimeout = errors.New("upstream request timeout")
)
// 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.
// FetcherConfig holds configuration for the upstream fetcher.
type FetcherConfig 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 an allow list of MIME types to accept.
// AllowedContentTypes is a whitelist 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
}
// DefaultConfig returns a Config with sensible defaults.
func DefaultConfig() *Config {
return &Config{
// DefaultFetcherConfig returns sensible defaults.
func DefaultFetcherConfig() *FetcherConfig {
return &FetcherConfig{
Timeout: DefaultFetchTimeout,
MaxResponseSize: DefaultMaxResponseSize,
UserAgent: "pixa/1.0",
@@ -104,18 +72,18 @@ func DefaultConfig() *Config {
}
}
// HTTPFetcher implements Fetcher with SSRF protection and per-host connection limits.
// HTTPFetcher implements the Fetcher interface with SSRF protection.
type HTTPFetcher struct {
client *http.Client
config *Config
config *FetcherConfig
hostSems map[string]chan struct{} // per-host semaphores
hostSemMu sync.Mutex // protects hostSems map
}
// New creates a new HTTPFetcher with SSRF protection.
func New(config *Config) *HTTPFetcher {
// NewHTTPFetcher creates a new fetcher with SSRF protection.
func NewHTTPFetcher(config *FetcherConfig) *HTTPFetcher {
if config == nil {
config = DefaultConfig()
config = DefaultFetcherConfig()
}
// Create transport with SSRF-safe dialer
@@ -282,7 +250,7 @@ func (f *HTTPFetcher) Fetch(ctx context.Context, url string) (*FetchResult, erro
}, nil
}
// isAllowedContentType checks if the content type is in the allow list.
// isAllowedContentType checks if the content type is in the whitelist.
func (f *HTTPFetcher) isAllowedContentType(contentType string) bool {
// Extract the MIME type without parameters
mediaType := strings.TrimSpace(strings.Split(contentType, ";")[0])

View File

@@ -169,6 +169,36 @@ 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

@@ -1,6 +1,4 @@
// Package magic detects image formats from magic bytes and validates
// content against declared MIME types.
package magic
package imgcache
import (
"bytes"
@@ -29,20 +27,6 @@ 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
@@ -205,7 +189,7 @@ func PeekAndValidate(r io.Reader, declaredType string) (io.Reader, error) {
return io.MultiReader(bytes.NewReader(buf), r), nil
}
// MIMEToImageFormat converts a MIME type to an ImageFormat.
// MIMEToImageFormat converts a MIME type to our ImageFormat type.
func MIMEToImageFormat(mimeType string) (ImageFormat, bool) {
normalized := normalizeMIMEType(mimeType)
switch MIMEType(normalized) {
@@ -224,7 +208,7 @@ func MIMEToImageFormat(mimeType string) (ImageFormat, bool) {
}
}
// ImageFormatToMIME converts an ImageFormat to a MIME type string.
// ImageFormatToMIME converts our ImageFormat to a MIME type string.
func ImageFormatToMIME(format ImageFormat) string {
switch format {
case FormatJPEG:

View File

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

View File

@@ -1,4 +1,4 @@
package httpfetcher
package imgcache
import (
"context"
@@ -10,15 +10,15 @@ import (
"strings"
)
// MockFetcher implements Fetcher using an embedded filesystem.
// MockFetcher implements the Fetcher interface 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
}
// NewMock creates a new mock fetcher backed by the given filesystem.
func NewMock(fsys fs.FS) *MockFetcher {
// NewMockFetcher creates a new mock fetcher backed by the given filesystem.
func NewMockFetcher(fsys fs.FS) *MockFetcher {
return &MockFetcher{fs: fsys}
}

View File

@@ -11,19 +11,17 @@ 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"
"sneak.berlin/go/pixa/internal/whitelist"
)
// Service implements the ImageCache interface, orchestrating cache, fetcher, and processor.
type Service struct {
cache *Cache
fetcher httpfetcher.Fetcher
fetcher Fetcher
processor *imageprocessor.ImageProcessor
signer *Signer
allowlist *allowlist.HostAllowList
whitelist *whitelist.HostWhitelist
log *slog.Logger
allowHTTP bool
maxResponseSize int64
@@ -34,9 +32,9 @@ type ServiceConfig struct {
// Cache is the cache instance
Cache *Cache
// FetcherConfig configures the upstream fetcher (ignored if Fetcher is set)
FetcherConfig *httpfetcher.Config
FetcherConfig *FetcherConfig
// Fetcher is an optional custom fetcher (for testing)
Fetcher httpfetcher.Fetcher
Fetcher Fetcher
// SigningKey is the HMAC signing key (empty disables signing)
SigningKey string
// Whitelist is the list of hosts that don't require signatures
@@ -58,15 +56,15 @@ func NewService(cfg *ServiceConfig) (*Service, error) {
// Resolve fetcher config for defaults
fetcherCfg := cfg.FetcherConfig
if fetcherCfg == nil {
fetcherCfg = httpfetcher.DefaultConfig()
fetcherCfg = DefaultFetcherConfig()
}
// Use custom fetcher if provided, otherwise create HTTP fetcher
var fetcher httpfetcher.Fetcher
var fetcher Fetcher
if cfg.Fetcher != nil {
fetcher = cfg.Fetcher
} else {
fetcher = httpfetcher.New(fetcherCfg)
fetcher = NewHTTPFetcher(fetcherCfg)
}
signer := NewSigner(cfg.SigningKey)
@@ -88,7 +86,7 @@ func NewService(cfg *ServiceConfig) (*Service, error) {
fetcher: fetcher,
processor: imageprocessor.New(imageprocessor.Params{MaxInputBytes: maxResponseSize}),
signer: signer,
allowlist: allowlist.New(cfg.Whitelist),
whitelist: whitelist.NewHostWhitelist(cfg.Whitelist),
log: log,
allowHTTP: allowHTTP,
maxResponseSize: maxResponseSize,
@@ -114,7 +112,7 @@ func (s *Service) Get(ctx context.Context, req *ImageRequest) (*ImageResponse, e
"path", req.SourcePath,
)
return nil, fmt.Errorf("%w: %w", httpfetcher.ErrUpstreamError, ErrNegativeCached)
return nil, fmt.Errorf("%w: %w", ErrUpstreamError, ErrNegativeCached)
}
// Check variant cache first (disk only, no DB)
@@ -279,7 +277,7 @@ func (s *Service) fetchAndProcess(
)
// Validate magic bytes match content type
if err := magic.ValidateMagicBytes(sourceData, fetchResult.ContentType); err != nil {
if err := ValidateMagicBytes(sourceData, fetchResult.ContentType); err != nil {
return nil, fmt.Errorf("content validation failed: %w", err)
}
@@ -384,7 +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 allowed (no signature required)
// Check if host is whitelisted (no signature required)
sourceURL := req.SourceURL()
parsedURL, err := url.Parse(sourceURL)
@@ -392,11 +390,11 @@ func (s *Service) ValidateRequest(req *ImageRequest) error {
return fmt.Errorf("invalid source URL: %w", err)
}
if s.allowlist.IsAllowed(parsedURL) {
if s.whitelist.IsWhitelisted(parsedURL) {
return nil
}
// Signature required for non-allowed hosts
// Signature required for non-whitelisted hosts
return s.signer.Verify(req)
}
@@ -419,13 +417,13 @@ const (
// isNegativeCacheable returns true if the error should be cached.
func isNegativeCacheable(err error) bool {
return errors.Is(err, httpfetcher.ErrUpstreamError)
return errors.Is(err, 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, httpfetcher.ErrUpstreamError) {
if errors.Is(err, ErrUpstreamError) {
return httpStatusBadGateway
}

View File

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

View File

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

View File

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

View File

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