pixa/internal/handlers/handlers.go

// Package handlers provides HTTP request handlers.
package handlers

import (
	"context"
	"encoding/json"
	"errors"
	"log/slog"
	"net/http"
	"time"

	"github.com/prometheus/client_golang/prometheus"
	"go.uber.org/fx"
	"sneak.berlin/go/pixa/internal/allowlist"
	"sneak.berlin/go/pixa/internal/config"
	"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"
)

// Params defines dependencies for Handlers.
type Params struct {
	fx.In

	Logger      *logger.Logger
	Healthcheck *healthcheck.Healthcheck
	Database    *database.Database
	Config      *config.Config

	// MetricsRegistry is the registry the image cache registers its
	// counters on. pixad provides Prometheus' default registry, the one
	// /metrics serves.
	MetricsRegistry prometheus.Registerer

	// Fetcher, when provided, fetches upstream images in place of the
	// fetcher the handlers build from the config. Only tests provide one;
	// pixad does not.
	Fetcher httpfetcher.Fetcher `optional:"true"`
}

// Handlers provides HTTP request handlers.
type Handlers struct {
	log         *slog.Logger
	hc          *healthcheck.Healthcheck
	db          *database.Database
	config      *config.Config
	fetcher     httpfetcher.Fetcher
	imgSvc      *imgcache.Service
	imgCache    *imgcache.Cache
	sessMgr     *session.Manager
	encGen      *encurl.Generator
	csrfProtect func(http.Handler) http.Handler

	// refererBlocklist matches the hosts of referer_blocklist; its IsAllowed
	// reports whether a URL's host is on that list.
	refererBlocklist *allowlist.HostAllowList

	// metricsRegistry is the registry the image cache registers its
	// counters on.
	metricsRegistry prometheus.Registerer
}

// New creates a new Handlers instance.
func New(lc fx.Lifecycle, params Params) (*Handlers, error) {
	csrfProtect, err := newCSRFProtect(params.Config.SigningKey, params.Config.Debug)
	if err != nil {
		return nil, err
	}

	s := &Handlers{
		log:              params.Logger.Get(),
		hc:               params.Healthcheck,
		db:               params.Database,
		config:           params.Config,
		fetcher:          params.Fetcher,
		csrfProtect:      csrfProtect,
		refererBlocklist: allowlist.New(params.Config.RefererBlocklist),
		metricsRegistry:  params.MetricsRegistry,
	}

	lc.Append(fx.Hook{
		//nolint:contextcheck // the cache's goroutines outlive OnStart; OnStop stops them
		OnStart: func(_ context.Context) error {
			return s.initImageService()
		},
		// The pending access times are written here, before the database's
		// stop hook closes it.
		OnStop: func(ctx context.Context) error {
			if s.imgCache == nil {
				return nil
			}

			return errors.Join(
				s.imgCache.StopEviction(ctx),
				s.imgCache.StopPendingAccessTimeWrites(ctx),
			)
		},
	})

	return s, nil
}

// WaitForProcessing waits until no image is being processed, or until ctx
// ends, and returns how many images were still being processed then.
func (s *Handlers) WaitForProcessing(ctx context.Context) int {
	return s.imgSvc.WaitForProcessing(ctx)
}

// newCacheConfig builds the image cache's configuration from cfg.
// cache_max_bytes: 0 disables the disk cache entirely; any other value
// is the eviction limit in bytes; when it is omitted, the cache works
// out the default limit itself.
func newCacheConfig(cfg *config.Config, log *slog.Logger) imgcache.CacheConfig {
	return imgcache.CacheConfig{
		StateDir:           cfg.StateDir,
		NegativeTTL:        imgcache.DefaultNegativeTTL,
		MaxBytes:           cfg.CacheMaxBytes,
		UseDefaultMaxBytes: !cfg.CacheMaxBytesExplicit,
		DisableDiskCache:   cfg.CacheMaxBytesExplicit && cfg.CacheMaxBytes == 0,
		Logger:             log,
	}
}

// initImageService initializes the image cache and service.
func (s *Handlers) initImageService() error {
	cache, err := imgcache.NewCache(
		s.db.DB(), newCacheConfig(s.config, s.log), s.metricsRegistry)
	if err != nil {
		return err
	}

	s.imgCache = cache

	// Background eviction: startup reconciliation, then periodic and
	// write-pressure passes, and the removal of expired negative cache
	// rows, which is all it does when the disk cache is disabled.
	cache.StartEviction(imgcache.DefaultEvictionInterval)

	// Writes the access times that requests hand over, so that no request
	// waits for the database to record them
	cache.StartPendingAccessTimeWrites()

	// Create the fetcher config
	fetcherCfg := httpfetcher.DefaultConfig()
	fetcherCfg.AllowHTTP = s.config.AllowHTTP
	fetcherCfg.Timeout = s.config.UpstreamFetchTimeout
	fetcherCfg.MaxResponseSize = s.config.UpstreamMaxResponseSize

	if s.config.UpstreamConnectionsPerHost > 0 {
		fetcherCfg.MaxConnectionsPerHost = s.config.UpstreamConnectionsPerHost
	}

	fetcherCfg.MaxConnections = s.config.UpstreamConnections
	fetcherCfg.BlockedNetworks = s.config.BlockedNetworks

	// Create the service. With no fetcher provided, it builds its own from
	// fetcherCfg.
	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
		Cache:                   cache,
		FetcherConfig:           fetcherCfg,
		Fetcher:                 s.fetcher,
		SigningKey:              s.config.SigningKey,
		Allowlist:               s.config.AllowlistHosts,
		MaxConcurrentProcessing: s.config.MaxConcurrentProcessing,
		Logger:                  s.log,
	})
	if err != nil {
		return err
	}

	s.imgSvc = svc
	s.log.Info("image service initialized")

	// Initialize session manager (signing key is validated at config load
	// time). Session cookies are always Secure/HttpOnly/SameSite=Strict.
	// The random value that each logout replaces is saved in the database,
	// so it outlasts a restart.
	sessMgr, err := session.NewManagerWithDatabase(
		context.Background(), s.config.SigningKey, s.db.DB())
	if err != nil {
		return err
	}

	s.sessMgr = sessMgr

	// Initialize encrypted URL generator
	encGen, err := encurl.NewGenerator(s.config.SigningKey)
	if err != nil {
		return err
	}

	s.encGen = encGen

	s.log.Info("session manager and URL generator initialized")

	return nil
}

func (s *Handlers) respondJSON(w http.ResponseWriter, data any, status int) {
	w.Header().Set("Content-Type", "application/json")
	w.WriteHeader(status)

	if data != nil {
		err := json.NewEncoder(w).Encode(data)
		if err != nil {
			s.log.Error("json encode error", "error", err)
		}
	}
}

func (s *Handlers) respondError(w http.ResponseWriter, message string, status int) {
	s.respondJSON(w, map[string]any{
		"error":     message,
		"status":    status,
		"timestamp": time.Now().UTC().Format(time.RFC3339),
	}, status)
}